__test_page_isolated_in_pageblock(struct zone *zone, unsigned long pfn,
unsigned long end_pfn, bool skip_hwpoisoned_pages)
#endif
{
struct page *page;
while (pfn < end_pfn) {
if (!pfn_valid_within(pfn)) {
pfn++;
continue;
}
page = pfn_to_page(pfn);
#if defined(CONFIG_CMA) && defined(CONFIG_MTK_SVP) // SVP 07
if (page_zone(page) != zone)
break;
#endif
if (PageBuddy(page)) {
/*
* If race between isolatation and allocation happens,
* some free pages could be in MIGRATE_MOVABLE list
* although pageblock's migratation type of the page
* is MIGRATE_ISOLATE. Catch it and move the page into
* MIGRATE_ISOLATE list.
*/
if (get_freepage_migratetype(page) != MIGRATE_ISOLATE) {
struct page *end_page;
end_page = page + (1 << page_order(page)) - 1;
move_freepages(page_zone(page), page, end_page,
MIGRATE_ISOLATE);
}
pfn += 1 << page_order(page);
}
else if (page_count(page) == 0 &&
get_freepage_migratetype(page) == MIGRATE_ISOLATE)
pfn += 1;
else if (skip_hwpoisoned_pages && PageHWPoison(page)) {
/*
* The HWPoisoned page may be not in buddy
* system, and page_count() is not 0.
*/
pfn++;
continue;
}
else
break;
}
if (pfn < end_pfn)
return 0;
return 1;
}
/*
* Test all pages in the range is free(means isolated) or not.
* all pages in [start_pfn...end_pfn) must be in the same zone.
* zone->lock must be held before call this.
*
* Returns 1 if all pages in the range are isolated.
*/
static int
__test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn)
{
struct page *page;
while (pfn < end_pfn) {
if (!pfn_valid_within(pfn)) {
pfn++;
continue;
}
page = pfn_to_page(pfn);
if (PageBuddy(page))
pfn += 1 << page_order(page);
else if (page_count(page) == 0 &&
page_private(page) == MIGRATE_ISOLATE) {
pfn += 1;
printk(KERN_INFO "%s:%d ", __func__, __LINE__);
dump_page(page);
} else {
printk(KERN_INFO "%s:%d ", __func__, __LINE__);
dump_page(page);
break;
}
}
if (pfn < end_pfn)
return 0;
return 1;
}
/*
* Test all pages in the range is free(means isolated) or not.
* all pages in [start_pfn...end_pfn) must be in the same zone.
* zone->lock must be held before call this.
*
* Returns the last tested pfn.
*/
static unsigned long
__test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn,
bool skip_hwpoisoned_pages)
{
struct page *page;
while (pfn < end_pfn) {
if (!pfn_valid_within(pfn)) {
pfn++;
continue;
}
page = pfn_to_page(pfn);
if (PageBuddy(page))
/*
* If the page is on a free list, it has to be on
* the correct MIGRATE_ISOLATE freelist. There is no
* simple way to verify that as VM_BUG_ON(), though.
*/
pfn += 1 << page_order(page);
else if (skip_hwpoisoned_pages && PageHWPoison(page))
/* A HWPoisoned page cannot be also PageBuddy */
pfn++;
else
break;
}
return pfn;
}
static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
{
struct page *page;
struct page_ext *page_ext;
unsigned long pfn = zone->zone_start_pfn, block_end_pfn;
unsigned long end_pfn = pfn + zone->spanned_pages;
unsigned long count = 0;
/* 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; ) {
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);
page = pfn_to_page(pfn);
for (; pfn < block_end_pfn; pfn++) {
if (!pfn_valid_within(pfn))
continue;
page = pfn_to_page(pfn);
/*
* We are safe to check buddy flag and order, because
* this is init stage and only single thread runs.
*/
if (PageBuddy(page)) {
pfn += (1UL << page_order(page)) - 1;
continue;
}
if (PageReserved(page))
continue;
page_ext = lookup_page_ext(page);
/* Maybe overraping zone */
if (test_bit(PAGE_EXT_OWNER, &page_ext->flags))
continue;
/* Found early allocated page */
set_page_owner(page, 0, 0);
count++;
}
}
pr_info("Node %d, zone %8s: page owner found early allocated %lu pages\n",
pgdat->node_id, zone->name, count);
}
struct page *
perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff)
{
if (pgoff > (1UL << page_order(rb)))
return NULL;
return vmalloc_to_page((void *)rb->user_page + pgoff * PAGE_SIZE);
}
void unset_migratetype_isolate(struct page *page, unsigned migratetype)
{
struct zone *zone;
unsigned long flags, nr_pages;
struct page *isolated_page = NULL;
unsigned int order;
unsigned long page_idx, buddy_idx;
struct page *buddy;
zone = page_zone(page);
spin_lock_irqsave(&zone->lock, flags);
if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
goto out;
/*
* Because freepage with more than pageblock_order on isolated
* pageblock is restricted to merge due to freepage counting problem,
* it is possible that there is free buddy page.
* move_freepages_block() doesn't care of merge so we need other
* approach in order to merge them. Isolation and free will make
* these pages to be merged.
*/
if (PageBuddy(page)) {
order = page_order(page);
if (order >= pageblock_order) {
page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1);
buddy_idx = __find_buddy_index(page_idx, order);
buddy = page + (buddy_idx - page_idx);
if (!is_migrate_isolate_page(buddy)) {
__isolate_free_page(page, order);
set_page_refcounted(page);
isolated_page = page;
}
}
}
/*
* If we isolate freepage with more than pageblock_order, there
* should be no freepage in the range, so we could avoid costly
* pageblock scanning for freepage moving.
*/
if (!isolated_page) {
nr_pages = move_freepages_block(zone, page, migratetype);
#if !defined(CONFIG_CMA) || !defined(CONFIG_MTK_SVP) // SVP 16
__mod_zone_freepage_state(zone, nr_pages, migratetype);
#else
__mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages);
#endif
}
set_pageblock_migratetype(page, migratetype);
zone->nr_isolate_pageblock--;
out:
spin_unlock_irqrestore(&zone->lock, flags);
if (isolated_page)
__free_pages(isolated_page, order);
}
static inline bool page_is_buddy(struct page *page, int order)
{
if ((page_order(page) == order) &&
(page_count(page) == 0) &&
(!page_reserved(page)))
return true;
return false;
}
static void unset_migratetype_isolate(struct page *page, unsigned migratetype)
{
struct zone *zone;
unsigned long flags, nr_pages;
bool isolated_page = false;
unsigned int order;
unsigned long pfn, buddy_pfn;
struct page *buddy;
zone = page_zone(page);
spin_lock_irqsave(&zone->lock, flags);
if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
goto out;
/*
* Because freepage with more than pageblock_order on isolated
* pageblock is restricted to merge due to freepage counting problem,
* it is possible that there is free buddy page.
* move_freepages_block() doesn't care of merge so we need other
* approach in order to merge them. Isolation and free will make
* these pages to be merged.
*/
if (PageBuddy(page)) {
order = page_order(page);
if (order >= pageblock_order) {
pfn = page_to_pfn(page);
buddy_pfn = __find_buddy_pfn(pfn, order);
buddy = page + (buddy_pfn - pfn);
if (pfn_valid_within(buddy_pfn) &&
!is_migrate_isolate_page(buddy)) {
__isolate_free_page(page, order);
isolated_page = true;
}
}
}
/*
* If we isolate freepage with more than pageblock_order, there
* should be no freepage in the range, so we could avoid costly
* pageblock scanning for freepage moving.
*/
if (!isolated_page) {
nr_pages = move_freepages_block(zone, page, migratetype);
__mod_zone_freepage_state(zone, nr_pages, migratetype);
}
set_pageblock_migratetype(page, migratetype);
zone->nr_isolate_pageblock--;
out:
spin_unlock_irqrestore(&zone->lock, flags);
if (isolated_page) {
post_alloc_hook(page, order, __GFP_MOVABLE);
__free_pages(page, order);
}
}
//---------------------------------------------------------------------------
IMPLEMENTATION[!ppc32]:
PUBLIC
Address
Pdir::virt_to_phys(Address virt) const
{
Virt_addr va(virt);
auto i = walk(va);
if (!i.is_valid())
return Invalid_address;
return i.page_addr() | cxx::get_lsb(virt, i.page_order());
}
/*
* Test all pages in the range is free(means isolated) or not.
* all pages in [start_pfn...end_pfn) must be in the same zone.
* zone->lock must be held before call this.
*
* Returns 1 if all pages in the range are isolated.
*/
static int
__test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn)
{
struct page *page;
while (pfn < end_pfn) {
if (!pfn_valid_within(pfn)) {
pfn++;
continue;
}
page = pfn_to_page(pfn);
if (PageBuddy(page)) {
/*
* If race between isolatation and allocation happens,
* some free pages could be in MIGRATE_MOVABLE list
* although pageblock's migratation type of the page
* is MIGRATE_ISOLATE. Catch it and move the page into
* MIGRATE_ISOLATE list.
*/
if (get_freepage_migratetype(page) != MIGRATE_ISOLATE) {
struct page *end_page;
end_page = page + (1 << page_order(page)) - 1;
move_freepages(page_zone(page), page, end_page,
MIGRATE_ISOLATE);
}
pfn += 1 << page_order(page);
}
else if (page_count(page) == 0 &&
get_freepage_migratetype(page) == MIGRATE_ISOLATE)
pfn += 1;
else
break;
}
if (pfn < end_pfn)
return 0;
return 1;
}
static void rb_free_work(struct work_struct *work)
{
struct ring_buffer *rb;
void *base;
int i, nr;
rb = container_of(work, struct ring_buffer, work);
nr = 1 << page_order(rb);
base = rb->user_page;
for (i = 0; i < nr + 1; i++)
perf_mmap_unmark_page(base + (i * PAGE_SIZE));
vfree(base);
kfree(rb);
}
PUBLIC
bool
Vm_vmx_ept::v_lookup(Mem_space::Vaddr virt, Mem_space::Phys_addr *phys,
Mem_space::Page_order *order, Mem_space::Attr *page_attribs)
{
auto i = _ept->walk(virt);
if (order) *order = Mem_space::Page_order(i.page_order());
if (!i.is_valid())
return false;
// FIXME: we may get a problem on 32 bit systems and using more than 4G ram
if (phys) *phys = Mem_space::Phys_addr(i.page_addr());
if (page_attribs) *page_attribs = i.attribs();
return true;
}
//---------------------------------------------------------------------------
IMPLEMENTATION[ppc32]:
PUBLIC
Address
Pdir::virt_to_phys(Address virt) const
{
auto i = walk(Virt_addr(virt));
//if (!i.is_valid())
return Invalid_address;
#ifdef FIX_THIS
Address phys;
Pte_htab::pte_lookup(i.e, &phys);
return phys | (virt & ~(~0UL << i.page_order()));
#endif
}
//---------------------------------------------------------------------------
IMPLEMENTATION [arm]:
#include "mem_unit.h"
#include "kmem_space.h"
#include "paging.h"
#include <cassert>
IMPLEMENT inline
Mword Kmem::is_kmem_page_fault(Mword pfa, Mword)
{
return in_kernel(pfa);
}
IMPLEMENT inline
Mword Kmem::is_io_bitmap_page_fault(Mword)
{
return 0;
}
PUBLIC static
Address
Kmem::mmio_remap(Address phys)
{
static Address ndev = 0;
Address v = phys_to_pmem(phys);
if (v != ~0UL)
return v;
Address dm = Mem_layout::Registers_map_start + ndev;
assert(dm < Mem_layout::Registers_map_end);
ndev += Config::SUPERPAGE_SIZE;
auto m = Kmem_space::kdir()->walk(Virt_addr(dm), Pte_ptr::Super_level);
assert (!m.is_valid());
assert (m.page_order() == Config::SUPERPAGE_SHIFT);
Address phys_page = cxx::mask_lsb(phys, Config::SUPERPAGE_SHIFT);
m.create_page(Phys_mem_addr(phys_page), Page::Attr(Page::Rights::RWX(), Page::Type::Uncached(),
Page::Kern::Global()));
m.write_back_if(true, Mem_unit::Asid_kernel);
add_pmem(phys_page, dm, Config::SUPERPAGE_SIZE);
return phys_to_pmem(phys);
}
/*
* page_alloc.c
*/
bool
is_free_buddy_page(struct page *page) {
struct zone *zone = page_zone(page);
unsigned long pfn = page_to_pfn(page);
unsigned long flags;
int order;
spin_lock_irqsave(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++) {
struct page *page_head = page - (pfn & ((1 << order) - 1));
if (PageBuddy(page_head) && page_order(page_head) >= order)
break;
}
spin_unlock_irqrestore(&zone->lock, flags);
return order < MAX_ORDER;
}
/*
* Test all pages in the range is free(means isolated) or not.
* all pages in [start_pfn...end_pfn) must be in the same zone.
* zone->lock must be held before call this.
*
* Returns 0 if all pages in the range is isolated.
*/
static int
__test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn)
{
struct page *page;
while (pfn < end_pfn) {
if (!pfn_valid_within(pfn)) {
pfn++;
continue;
}
page = pfn_to_page(pfn);
if (PageBuddy(page))
pfn += 1 << page_order(page);
else if (page_count(page) == 0 &&
page_private(page) == MIGRATE_ISOLATE)
pfn += 1;
else
break;
}
if (pfn < end_pfn)
return 0;
return 1;
}
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 = zone->zone_start_pfn, block_end_pfn;
unsigned long end_pfn = pfn + zone->spanned_pages;
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; ) {
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);
page = pfn_to_page(pfn);
pageblock_mt = get_pageblock_migratetype(page);
for (; pfn < block_end_pfn; pfn++) {
if (!pfn_valid_within(pfn))
continue;
page = pfn_to_page(pfn);
if (page_zone(page) != zone)
continue;
if (PageBuddy(page)) {
pfn += (1UL << page_order(page)) - 1;
continue;
}
if (PageReserved(page))
continue;
page_ext = lookup_page_ext(page);
if (unlikely(!page_ext))
continue;
if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
continue;
page_owner = get_page_owner(page_ext);
page_mt = gfpflags_to_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;
break;
}
pfn += (1UL << page_owner->order) - 1;
}
}
/* 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');
}
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)
{
struct page *page;
struct page_ext *page_ext;
unsigned long pfn = zone->zone_start_pfn, block_end_pfn;
unsigned long end_pfn = pfn + zone->spanned_pages;
unsigned long count = 0;
/* 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; ) {
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);
page = pfn_to_page(pfn);
for (; pfn < block_end_pfn; pfn++) {
if (!pfn_valid_within(pfn))
continue;
page = pfn_to_page(pfn);
if (page_zone(page) != zone)
continue;
/*
* We are safe to check buddy flag and order, because
* this is init stage and only single thread runs.
*/
if (PageBuddy(page)) {
pfn += (1UL << page_order(page)) - 1;
continue;
}
if (PageReserved(page))
continue;
page_ext = lookup_page_ext(page);
if (unlikely(!page_ext))
continue;
/* Maybe overraping zone */
if (test_bit(PAGE_EXT_OWNER, &page_ext->flags))
continue;
/* Found early allocated page */
set_page_owner(page, 0, 0);
count++;
}
}
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;
unsigned long flags;
for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
if (!populated_zone(zone))
continue;
spin_lock_irqsave(&zone->lock, flags);
init_pages_in_zone(pgdat, zone);
spin_unlock_irqrestore(&zone->lock, flags);
}
}
static void init_early_allocated_pages(void)
{
pg_data_t *pgdat;
drain_all_pages(NULL);
for_each_online_pgdat(pgdat)
init_zones_in_node(pgdat);
}
int perf_output_begin(struct perf_output_handle *handle,
struct perf_event *event, unsigned int size)
{
struct ring_buffer *rb;
unsigned long tail, offset, head;
int have_lost;
struct perf_sample_data sample_data;
struct {
struct perf_event_header header;
u64 id;
u64 lost;
} lost_event;
rcu_read_lock();
/*
* For inherited events we send all the output towards the parent.
*/
if (event->parent)
event = event->parent;
rb = rcu_dereference(event->rb);
if (!rb)
goto out;
handle->rb = rb;
handle->event = event;
if (!rb->nr_pages)
goto out;
have_lost = local_read(&rb->lost);
if (have_lost) {
lost_event.header.size = sizeof(lost_event);
perf_event_header__init_id(&lost_event.header, &sample_data,
event);
size += lost_event.header.size;
}
perf_output_get_handle(handle);
do {
/*
* Userspace could choose to issue a mb() before updating the
* tail pointer. So that all reads will be completed before the
* write is issued.
*/
tail = ACCESS_ONCE(rb->user_page->data_tail);
smp_rmb();
offset = head = local_read(&rb->head);
head += size;
if (unlikely(!perf_output_space(rb, tail, offset, head)))
goto fail;
} while (local_cmpxchg(&rb->head, offset, head) != offset);
if (head - local_read(&rb->wakeup) > rb->watermark)
local_add(rb->watermark, &rb->wakeup);
handle->page = offset >> (PAGE_SHIFT + page_order(rb));
handle->page &= rb->nr_pages - 1;
handle->size = offset & ((PAGE_SIZE << page_order(rb)) - 1);
handle->addr = rb->data_pages[handle->page];
handle->addr += handle->size;
handle->size = (PAGE_SIZE << page_order(rb)) - handle->size;
if (have_lost) {
lost_event.header.type = PERF_RECORD_LOST;
lost_event.header.misc = 0;
lost_event.id = event->id;
lost_event.lost = local_xchg(&rb->lost, 0);
perf_output_put(handle, lost_event);
perf_event__output_id_sample(event, handle, &sample_data);
}
return 0;
fail:
local_inc(&rb->lost);
perf_output_put_handle(handle);
out:
rcu_read_unlock();
return -ENOSPC;
}
void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask)
{
struct page_ext *page_ext = lookup_page_ext(page);
struct stack_trace trace = {
.nr_entries = 0,
.max_entries = ARRAY_SIZE(page_ext->trace_entries),
.entries = &page_ext->trace_entries[0],
.skip = 3,
};
if (unlikely(!page_ext))
return;
save_stack_trace(&trace);
page_ext->order = order;
page_ext->gfp_mask = gfp_mask;
page_ext->nr_entries = trace.nr_entries;
page_ext->last_migrate_reason = -1;
__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
}
void __set_page_owner_migrate_reason(struct page *page, int reason)
{
struct page_ext *page_ext = lookup_page_ext(page);
if (unlikely(!page_ext))
return;
page_ext->last_migrate_reason = reason;
}
gfp_t __get_page_owner_gfp(struct page *page)
{
struct page_ext *page_ext = lookup_page_ext(page);
if (unlikely(!page_ext))
/*
* The caller just returns 0 if no valid gfp
* So return 0 here too.
*/
return 0;
return page_ext->gfp_mask;
}
void __copy_page_owner(struct page *oldpage, struct page *newpage)
{
struct page_ext *old_ext = lookup_page_ext(oldpage);
struct page_ext *new_ext = lookup_page_ext(newpage);
int i;
if (unlikely(!old_ext || !new_ext))
return;
new_ext->order = old_ext->order;
new_ext->gfp_mask = old_ext->gfp_mask;
new_ext->nr_entries = old_ext->nr_entries;
for (i = 0; i < ARRAY_SIZE(new_ext->trace_entries); i++)
new_ext->trace_entries[i] = old_ext->trace_entries[i];
/*
* We don't clear the bit on the oldpage as it's going to be freed
* after migration. Until then, the info can be useful in case of
* a bug, and the overal stats will be off a bit only temporarily.
* Also, migrate_misplaced_transhuge_page() can still fail the
* migration and then we want the oldpage to retain the info. But
* in that case we also don't need to explicitly clear the info from
* the new page, which will be freed.
*/
__set_bit(PAGE_EXT_OWNER, &new_ext->flags);
}
static ssize_t
print_page_owner(char __user *buf, size_t count, unsigned long pfn,
struct page *page, struct page_ext *page_ext)
{
int ret;
int pageblock_mt, page_mt;
char *kbuf;
struct stack_trace trace = {
.nr_entries = page_ext->nr_entries,
.entries = &page_ext->trace_entries[0],
};
kbuf = kmalloc(count, GFP_KERNEL);
if (!kbuf)
return -ENOMEM;
ret = snprintf(kbuf, count,
"Page allocated via order %u, mask %#x(%pGg)\n",
page_ext->order, page_ext->gfp_mask,
&page_ext->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_ext->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;
ret += snprint_stack_trace(kbuf + ret, count - ret, &trace, 0);
if (ret >= count)
goto err;
if (page_ext->last_migrate_reason != -1) {
ret += snprintf(kbuf + ret, count - ret,
"Page has been migrated, last migrate reason: %s\n",
migrate_reason_names[page_ext->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 stack_trace trace = {
.nr_entries = page_ext->nr_entries,
.entries = &page_ext->trace_entries[0],
};
gfp_t gfp_mask = page_ext->gfp_mask;
int mt = gfpflags_to_migratetype(gfp_mask);
if (unlikely(!page_ext)) {
pr_alert("There is not page extension available.\n");
return;
}
if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) {
pr_alert("page_owner info is not active (free page?)\n");
return;
}
pr_alert("page allocated via order %u, migratetype %s, gfp_mask %#x(%pGg)\n",
page_ext->order, migratetype_names[mt], gfp_mask, &gfp_mask);
print_stack_trace(&trace, 0);
if (page_ext->last_migrate_reason != -1)
pr_alert("page has been migrated, last migrate reason: %s\n",
migrate_reason_names[page_ext->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;
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;
/* 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_ext);
}
return 0;
}
static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
{
struct page *page;
struct page_ext *page_ext;
unsigned long pfn = zone->zone_start_pfn, block_end_pfn;
unsigned long end_pfn = pfn + zone->spanned_pages;
unsigned long count = 0;
/* 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; ) {
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);
page = pfn_to_page(pfn);
for (; pfn < block_end_pfn; pfn++) {
if (!pfn_valid_within(pfn))
continue;
page = pfn_to_page(pfn);
if (page_zone(page) != zone)
continue;
/*
* We are safe to check buddy flag and order, because
* this is init stage and only single thread runs.
*/
if (PageBuddy(page)) {
pfn += (1UL << page_order(page)) - 1;
continue;
}
if (PageReserved(page))
continue;
page_ext = lookup_page_ext(page);
if (unlikely(!page_ext))
continue;
/* Maybe overraping zone */
if (test_bit(PAGE_EXT_OWNER, &page_ext->flags))
continue;
/* Found early allocated page */
set_page_owner(page, 0, 0);
count++;
}
}
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;
unsigned long flags;
for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
if (!populated_zone(zone))
continue;
spin_lock_irqsave(&zone->lock, flags);
init_pages_in_zone(pgdat, zone);
spin_unlock_irqrestore(&zone->lock, flags);
}
}
static void init_early_allocated_pages(void)
{
pg_data_t *pgdat;
drain_all_pages(NULL);
for_each_online_pgdat(pgdat)
init_zones_in_node(pgdat);
}
