mm/vmalloc: keep a separate lazy-free list

When mixing lots of vmallocs and set_memory_*() (which calls
vm_unmap_aliases()) I encountered situations where the performance
degraded severely due to the walking of the entire vmap_area list each
invocation.

One simple improvement is to add the lazily freed vmap_area to a
separate lockless free list, such that we then avoid having to walk the
full list on each purge.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Roman Pen <r.peniaev@gmail.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Roman Pen <r.peniaev@gmail.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Toshi Kani <toshi.kani@hp.com>
Cc: Shawn Lin <shawn.lin@rock-chips.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index d1f1d33..957adb7 100644 (file)
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -4,6 +4,7 @@
 #include <linux/spinlock.h>
 #include <linux/init.h>
 #include <linux/list.h>
+#include <linux/llist.h>
 #include <asm/page.h>          /* pgprot_t */
 #include <linux/rbtree.h>
 
@@ -44,7 +45,7 @@ struct vmap_area {
        unsigned long flags;
        struct rb_node rb_node;         /* address sorted rbtree */
        struct list_head list;          /* address sorted list */
-       struct list_head purge_list;    /* "lazy purge" list */
+       struct llist_node purge_list;    /* "lazy purge" list */
        struct vm_struct *vm;
        struct rcu_head rcu_head;
 };

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index ae7d20b..6e32918 100644 (file)
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -274,13 +274,12 @@ EXPORT_SYMBOL(vmalloc_to_pfn);
 
 /*** Global kva allocator ***/
 
-#define VM_LAZY_FREE   0x01
-#define VM_LAZY_FREEING        0x02
 #define VM_VM_AREA     0x04
 
 static DEFINE_SPINLOCK(vmap_area_lock);
 /* Export for kexec only */
 LIST_HEAD(vmap_area_list);
+static LLIST_HEAD(vmap_purge_list);
 static struct rb_root vmap_area_root = RB_ROOT;
 
 /* The vmap cache globals are protected by vmap_area_lock */
@@ -601,7 +600,7 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end,
                                        int sync, int force_flush)
 {
        static DEFINE_SPINLOCK(purge_lock);
-       LIST_HEAD(valist);
+       struct llist_node *valist;
        struct vmap_area *va;
        struct vmap_area *n_va;
        int nr = 0;
@@ -620,20 +619,14 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end,
        if (sync)
                purge_fragmented_blocks_allcpus();
 
-       rcu_read_lock();
-       list_for_each_entry_rcu(va, &vmap_area_list, list) {
-               if (va->flags & VM_LAZY_FREE) {
-                       if (va->va_start < *start)
-                               *start = va->va_start;
-                       if (va->va_end > *end)
-                               *end = va->va_end;
-                       nr += (va->va_end - va->va_start) >> PAGE_SHIFT;
-                       list_add_tail(&va->purge_list, &valist);
-                       va->flags |= VM_LAZY_FREEING;
-                       va->flags &= ~VM_LAZY_FREE;
-               }
+       valist = llist_del_all(&vmap_purge_list);
+       llist_for_each_entry(va, valist, purge_list) {
+               if (va->va_start < *start)
+                       *start = va->va_start;
+               if (va->va_end > *end)
+                       *end = va->va_end;
+               nr += (va->va_end - va->va_start) >> PAGE_SHIFT;
        }
-       rcu_read_unlock();
 
        if (nr)
                atomic_sub(nr, &vmap_lazy_nr);
@@ -643,7 +636,7 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end,
 
        if (nr) {
                spin_lock(&vmap_area_lock);
-               list_for_each_entry_safe(va, n_va, &valist, purge_list)
+               llist_for_each_entry_safe(va, n_va, valist, purge_list)
                        __free_vmap_area(va);
                spin_unlock(&vmap_area_lock);
        }
@@ -678,9 +671,15 @@ static void purge_vmap_area_lazy(void)
  */
 static void free_vmap_area_noflush(struct vmap_area *va)
 {
-       va->flags |= VM_LAZY_FREE;
-       atomic_add((va->va_end - va->va_start) >> PAGE_SHIFT, &vmap_lazy_nr);
-       if (unlikely(atomic_read(&vmap_lazy_nr) > lazy_max_pages()))
+       int nr_lazy;
+
+       nr_lazy = atomic_add_return((va->va_end - va->va_start) >> PAGE_SHIFT,
+                                   &vmap_lazy_nr);
+
+       /* After this point, we may free va at any time */
+       llist_add(&va->purge_list, &vmap_purge_list);
+
+       if (unlikely(nr_lazy > lazy_max_pages()))
                try_purge_vmap_area_lazy();
 }