#include <linux/page_owner.h>
#include <linux/jump_label.h>
#include <linux/migrate.h>
+#include <linux/stackdepot.h>
+#include <linux/seq_file.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 int order;
+ gfp_t gfp_mask;
+ int last_migrate_reason;
+ depot_stack_handle_t handle;
+};
+
static bool page_owner_disabled = true;
DEFINE_STATIC_KEY_FALSE(page_owner_inited);
+static depot_stack_handle_t dummy_handle;
+static depot_stack_handle_t failure_handle;
+
static void init_early_allocated_pages(void);
static int early_page_owner_param(char *buf)
return true;
}
+static noinline void register_dummy_stack(void)
+{
+ unsigned long entries[4];
+ struct stack_trace dummy;
+
+ dummy.nr_entries = 0;
+ dummy.max_entries = ARRAY_SIZE(entries);
+ dummy.entries = &entries[0];
+ dummy.skip = 0;
+
+ save_stack_trace(&dummy);
+ dummy_handle = depot_save_stack(&dummy, GFP_KERNEL);
+}
+
+static noinline void register_failure_stack(void)
+{
+ unsigned long entries[4];
+ struct stack_trace failure;
+
+ failure.nr_entries = 0;
+ failure.max_entries = ARRAY_SIZE(entries);
+ failure.entries = &entries[0];
+ failure.skip = 0;
+
+ save_stack_trace(&failure);
+ failure_handle = depot_save_stack(&failure, GFP_KERNEL);
+}
+
static void init_page_owner(void)
{
if (page_owner_disabled)
return;
+ register_dummy_stack();
+ register_failure_stack();
static_branch_enable(&page_owner_inited);
init_early_allocated_pages();
}
struct page_ext_operations page_owner_ops = {
+ .size = sizeof(struct page_owner),
.need = need_page_owner,
.init = init_page_owner,
};
+static inline struct page_owner *get_page_owner(struct page_ext *page_ext)
+{
+ return (void *)page_ext + page_owner_ops.offset;
+}
+
void __reset_page_owner(struct page *page, unsigned int order)
{
int i;
}
}
-void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask)
+static inline bool check_recursive_alloc(struct stack_trace *trace,
+ unsigned long ip)
{
- struct page_ext *page_ext = lookup_page_ext(page);
+ int i, count;
+
+ if (!trace->nr_entries)
+ return false;
+ for (i = 0, count = 0; i < trace->nr_entries; i++) {
+ if (trace->entries[i] == ip && ++count == 2)
+ return true;
+ }
+
+ return false;
+}
+
+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,
- .max_entries = ARRAY_SIZE(page_ext->trace_entries),
- .entries = &page_ext->trace_entries[0],
- .skip = 3,
+ .entries = entries,
+ .max_entries = PAGE_OWNER_STACK_DEPTH,
+ .skip = 0
};
+ 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;
+}
+
+noinline void __set_page_owner(struct page *page, unsigned int order,
+ gfp_t gfp_mask)
+{
+ struct page_ext *page_ext = lookup_page_ext(page);
+ struct page_owner *page_owner;
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;
+ page_owner = get_page_owner(page_ext);
+ page_owner->handle = save_stack(gfp_mask);
+ page_owner->order = order;
+ page_owner->gfp_mask = gfp_mask;
+ page_owner->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);
+ struct page_owner *page_owner;
+
if (unlikely(!page_ext))
return;
- page_ext->last_migrate_reason = reason;
+ page_owner = get_page_owner(page_ext);
+ page_owner->last_migrate_reason = reason;
}
-gfp_t __get_page_owner_gfp(struct page *page)
+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))
- /*
- * The caller just returns 0 if no valid gfp
- * So return 0 here too.
- */
- return 0;
+ return;
- return page_ext->gfp_mask;
+ page_owner = get_page_owner(page_ext);
+ page_owner->order = 0;
+ for (i = 1; i < (1 << order); i++)
+ __copy_page_owner(page, page + i);
}
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;
+ struct page_owner *old_page_owner, *new_page_owner;
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];
+ old_page_owner = get_page_owner(old_ext);
+ new_page_owner = get_page_owner(new_ext);
+ new_page_owner->order = old_page_owner->order;
+ new_page_owner->gfp_mask = old_page_owner->gfp_mask;
+ new_page_owner->last_migrate_reason =
+ old_page_owner->last_migrate_reason;
+ new_page_owner->handle = old_page_owner->handle;
/*
* We don't clear the bit on the oldpage as it's going to be freed
__set_bit(PAGE_EXT_OWNER, &new_ext->flags);
}
+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_ext *page_ext)
+ 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 = page_ext->nr_entries,
- .entries = &page_ext->trace_entries[0],
+ .nr_entries = 0,
+ .entries = entries,
+ .max_entries = PAGE_OWNER_STACK_DEPTH,
+ .skip = 0
};
kbuf = kmalloc(count, GFP_KERNEL);
ret = snprintf(kbuf, count,
"Page allocated via order %u, mask %#x(%pGg)\n",
- page_ext->order, page_ext->gfp_mask,
- &page_ext->gfp_mask);
+ 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_ext->gfp_mask);
+ 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,
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_ext->last_migrate_reason != -1) {
+ 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_ext->last_migrate_reason]);
+ migrate_reason_names[page_owner->last_migrate_reason]);
if (ret >= count)
goto err;
}
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 = page_ext->nr_entries,
- .entries = &page_ext->trace_entries[0],
+ .nr_entries = 0,
+ .entries = entries,
+ .max_entries = PAGE_OWNER_STACK_DEPTH,
+ .skip = 0
};
+ depot_stack_handle_t handle;
gfp_t gfp_mask;
int mt;
pr_alert("There is not page extension available.\n");
return;
}
- gfp_mask = page_ext->gfp_mask;
+
+ 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)) {
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_ext->order, migratetype_names[mt], gfp_mask, &gfp_mask);
+ page_owner->order, migratetype_names[mt], gfp_mask, &gfp_mask);
print_stack_trace(&trace, 0);
- if (page_ext->last_migrate_reason != -1)
+ if (page_owner->last_migrate_reason != -1)
pr_alert("page has been migrated, last migrate reason: %s\n",
- migrate_reason_names[page_ext->last_migrate_reason]);
+ migrate_reason_names[page_owner->last_migrate_reason]);
}
static ssize_t
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;
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_ext);
+ return print_page_owner(buf, count, pfn, page,
+ page_owner, handle);
}
return 0;