Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - a few misc bits

 - ocfs2

 - most(?) of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (125 commits)
  thp: fix comments of __pmd_trans_huge_lock()
  cgroup: remove unnecessary 0 check from css_from_id()
  cgroup: fix idr leak for the first cgroup root
  mm: memcontrol: fix documentation for compound parameter
  mm: memcontrol: remove BUG_ON in uncharge_list
  mm: fix build warnings in <linux/compaction.h>
  mm, thp: convert from optimistic swapin collapsing to conservative
  mm, thp: fix comment inconsistency for swapin readahead functions
  thp: update Documentation/{vm/transhuge,filesystems/proc}.txt
  shmem: split huge pages beyond i_size under memory pressure
  thp: introduce CONFIG_TRANSPARENT_HUGE_PAGECACHE
  khugepaged: add support of collapse for tmpfs/shmem pages
  shmem: make shmem_inode_info::lock irq-safe
  khugepaged: move up_read(mmap_sem) out of khugepaged_alloc_page()
  thp: extract khugepaged from mm/huge_memory.c
  shmem, thp: respect MADV_{NO,}HUGEPAGE for file mappings
  shmem: add huge pages support
  shmem: get_unmapped_area align huge page
  shmem: prepare huge= mount option and sysfs knob
  mm, rmap: account shmem thp pages
  ...

1 files changed, 131 insertions, 26 deletions

diff --git a/mm/page_owner.c b/mm/page_owner.c
index fedeba88c9cb..ec6dc1886f71 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -7,11 +7,22 @@
 #include <linux/page_owner.h>
 #include <linux/jump_label.h>
 #include <linux/migrate.h>
+#include <linux/stackdepot.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)
+
 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)
@@ -34,11 +45,41 @@ static bool need_page_owner(void)
 	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();
 }
@@ -61,25 +102,66 @@ void __reset_page_owner(struct page *page, unsigned int order)
 	}
 }
 
-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);
 
 	if (unlikely(!page_ext))
 		return;
 
-	save_stack_trace(&trace);
-
+	page_ext->handle = save_stack(gfp_mask);
 	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);
@@ -94,34 +176,31 @@ void __set_page_owner_migrate_reason(struct page *page, int reason)
 	page_ext->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);
+
 	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_ext->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;
 
 	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];
+	new_ext->last_migrate_reason = old_ext->last_migrate_reason;
+	new_ext->handle = old_ext->handle;
 
 	/*
 	 * We don't clear the bit on the oldpage as it's going to be freed
@@ -137,14 +216,18 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage)
 
 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_ext *page_ext,
+		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);
@@ -173,6 +256,7 @@ print_page_owner(char __user *buf, size_t count, unsigned long 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;
@@ -203,10 +287,14 @@ err:
 void __dump_page_owner(struct page *page)
 {
 	struct page_ext *page_ext = lookup_page_ext(page);
+	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;
 
@@ -222,6 +310,13 @@ void __dump_page_owner(struct page *page)
 		return;
 	}
 
+	handle = READ_ONCE(page_ext->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);
 	print_stack_trace(&trace, 0);
@@ -237,6 +332,7 @@ 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;
+	depot_stack_handle_t handle;
 
 	if (!static_branch_unlikely(&page_owner_inited))
 		return -EINVAL;
@@ -285,10 +381,19 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 		if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
 			continue;
 
+		/*
+		 * Access to page_ext->handle isn't synchronous so we should
+		 * be careful to access it.
+		 */
+		handle = READ_ONCE(page_ext->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_ext, handle);
 	}
 
 	return 0;