From 9654e1d8beb445030f30cf2f325eb832792a8ddd Mon Sep 17 00:00:00 2001
From: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Date: Mon, 23 Sep 2019 15:36:36 -0700
Subject: [PATCH] mm/vmalloc: do not keep unpurged areas in the busy tree

References: bnc#1155780 (VM/FS functional and performance backports)
Patch-mainline: v5.4-rc1
Git-commit: dd3b8353bae79395b12a178de057b183ff0122eb

The busy tree can be quite big, even though the area is freed or unmapped
it still stays there until "purge" logic removes it.

1) Optimize and reduce the size of "busy" tree by removing a node from
   it right away as soon as user triggers free paths.  It is possible to
   do so, because the allocation is done using another augmented tree.

The vmalloc test driver shows the difference, for example the
"fix_size_alloc_test" is ~11% better comparing with default configuration:

sudo ./test_vmalloc.sh performance

<default>
Summary: fix_size_alloc_test loops: 1000000 avg: 993985 usec
Summary: full_fit_alloc_test loops: 1000000 avg: 973554 usec
Summary: long_busy_list_alloc_test loops: 1000000 avg: 12617652 usec
<default>

<this patch>
Summary: fix_size_alloc_test loops: 1000000 avg: 882263 usec
Summary: full_fit_alloc_test loops: 1000000 avg: 973407 usec
Summary: long_busy_list_alloc_test loops: 1000000 avg: 12593929 usec
<this patch>

2) Since the busy tree now contains allocated areas only and does not
   interfere with lazily free nodes, introduce the new function
   show_purge_info() that dumps "unpurged" areas that is propagated
   through "/proc/vmallocinfo".

3) Eliminate VM_LAZY_FREE flag.

Link: http://lkml.kernel.org/r/20190716152656.12255-2-lpf.vector@gmail.com
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Pengfei Li <lpf.vector@gmail.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Uladzislau Rezki <urezki@gmail.com>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/vmalloc.c | 52 ++++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 44 insertions(+), 8 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index c40a554bfb2f..5dd0ba94d8e2 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -329,7 +329,6 @@ EXPORT_SYMBOL(vmalloc_to_pfn);
 #define DEBUG_AUGMENT_PROPAGATE_CHECK 0
 #define DEBUG_AUGMENT_LOWEST_MATCH_CHECK 0
 
-#define VM_LAZY_FREE	0x02
 #define VM_VM_AREA	0x04
 
 static DEFINE_SPINLOCK(vmap_area_lock);
@@ -1298,7 +1297,14 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
 	llist_for_each_entry_safe(va, n_va, valist, purge_list) {
 		unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT;
 
-		__free_vmap_area(va);
+		/*
+		 * Finally insert or merge lazily-freed area. It is
+		 * detached and there is no need to "unlink" it from
+		 * anything.
+		 */
+		merge_or_add_vmap_area(va,
+			&free_vmap_area_root, &free_vmap_area_list);
+
 		atomic_long_sub(nr, &vmap_lazy_nr);
 
 		if (atomic_long_read(&vmap_lazy_nr) < resched_threshold)
@@ -1340,6 +1346,10 @@ static void free_vmap_area_noflush(struct vmap_area *va)
 {
 	unsigned long nr_lazy;
 
+	spin_lock(&vmap_area_lock);
+	unlink_va(va, &vmap_area_root);
+	spin_unlock(&vmap_area_lock);
+
 	nr_lazy = atomic_long_add_return((va->va_end - va->va_start) >>
 				PAGE_SHIFT, &vmap_lazy_nr);
 
@@ -2159,14 +2169,13 @@ struct vm_struct *remove_vm_area(const void *addr)
 
 	might_sleep();
 
-	va = find_vmap_area((unsigned long)addr);
+	spin_lock(&vmap_area_lock);
+	va = __find_vmap_area((unsigned long)addr);
 	if (va && va->flags & VM_VM_AREA) {
 		struct vm_struct *vm = va->vm;
 
-		spin_lock(&vmap_area_lock);
 		va->vm = NULL;
 		va->flags &= ~VM_VM_AREA;
-		va->flags |= VM_LAZY_FREE;
 		spin_unlock(&vmap_area_lock);
 
 		kasan_free_shadow(vm);
@@ -2174,6 +2183,8 @@ struct vm_struct *remove_vm_area(const void *addr)
 
 		return vm;
 	}
+
+	spin_unlock(&vmap_area_lock);
 	return NULL;
 }
 
@@ -3466,6 +3477,22 @@ static void show_numa_info(struct seq_file *m, struct vm_struct *v)
 	}
 }
 
+static void show_purge_info(struct seq_file *m)
+{
+	struct llist_node *head;
+	struct vmap_area *va;
+
+	head = READ_ONCE(vmap_purge_list.first);
+	if (head == NULL)
+		return;
+
+	llist_for_each_entry(va, head, purge_list) {
+		seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n",
+			(void *)va->va_start, (void *)va->va_end,
+			va->va_end - va->va_start);
+	}
+}
+
 static int s_show(struct seq_file *m, void *p)
 {
 	struct vmap_area *va;
@@ -3478,10 +3505,9 @@ static int s_show(struct seq_file *m, void *p)
 	 * behalf of vmap area is being tear down or vm_map_ram allocation.
 	 */
 	if (!(va->flags & VM_VM_AREA)) {
-		seq_printf(m, "0x%pK-0x%pK %7ld %s\n",
+		seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n",
 			(void *)va->va_start, (void *)va->va_end,
-			va->va_end - va->va_start,
-			va->flags & VM_LAZY_FREE ? "unpurged vm_area" : "vm_map_ram");
+			va->va_end - va->va_start);
 
 		return 0;
 	}
@@ -3520,6 +3546,16 @@ static int s_show(struct seq_file *m, void *p)
 
 	show_numa_info(m, v);
 	seq_putc(m, '\n');
+
+	/*
+	 * As a final step, dump "unpurged" areas. Note,
+	 * that entire "/proc/vmallocinfo" output will not
+	 * be address sorted, because the purge list is not
+	 * sorted.
+	 */
+	if (list_is_last(&va->list, &vmap_area_list))
+		show_purge_info(m);
+
 	return 0;
 }