Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Pengfei Li <lpf.vector@gmail.com>
To:     akpm@linux-foundation.org, willy@infradead.org
Cc:     urezki@gmail.com, rpenyaev@suse.de, peterz@infradead.org,
        guro@fb.com, rick.p.edgecombe@intel.com, rppt@linux.ibm.com,
        aryabinin@virtuozzo.com, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
Subject: [PATCH v6 1/2] mm/vmalloc: do not keep unpurged areas in the busy tree
Date:   Tue, 16 Jul 2019 23:26:55 +0800
Message-Id: <20190716152656.12255-2-lpf.vector@gmail.com>
In-Reply-To: <20190716152656.12255-1-lpf.vector@gmail.com>
References: <20190716152656.12255-1-lpf.vector@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: "Uladzislau Rezki (Sony)" <urezki@gmail.com>

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.

Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
---
 mm/vmalloc.c | 52 ++++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 44 insertions(+), 8 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 4fa8d84599b0..71d8040a8a0b 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);
@@ -1276,7 +1275,14 @@ 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)
@@ -1318,6 +1324,10 @@ 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);
 
@@ -2137,14 +2147,13 @@ 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);
@@ -2152,6 +2161,8 @@ struct vm_struct *remove_vm_area(const void *addr)
 
 		return vm;
 	}
+
+	spin_unlock(&vmap_area_lock);
 	return NULL;
 }
 
@@ -3431,6 +3442,22 @@ 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;
@@ -3443,10 +3470,9 @@ 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;
 	}
@@ -3482,6 +3508,16 @@ 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;
 }
 
-- 
2.21.0