This patch changes the anon_vma refcount to be 0 when the object is free. It does this by adding 1 ref to being in use in the anon_vma structure (iow. the anon_vma->head list is not empty). This allows a simpler release scheme without having to check both the refcount and the list as well as avoids taking a ref for each entry on the list. We then use this new refcount in the migration code to avoid a long RCU read side section and convert page_lock_anon_vma() over to use refcounts. This later is done for each of convertion of anon_vma from spinlock to mutex. Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx> --- include/linux/rmap.h | 7 +++++++ mm/ksm.c | 9 +-------- mm/migrate.c | 17 ++++++----------- mm/rmap.c | 45 ++++++++++++++++++++++++++++++--------------- 4 files changed, 44 insertions(+), 34 deletions(-) Index: linux-2.6/include/linux/rmap.h =================================================================== --- linux-2.6.orig/include/linux/rmap.h +++ linux-2.6/include/linux/rmap.h @@ -100,6 +100,13 @@ static inline void anon_vma_merge(struct unlink_anon_vmas(next); } +struct anon_vma *anon_vma_get(struct page *page); +static inline void anon_vma_put(struct anon_vma *anon_vma) +{ + if (atomic_dec_and_test(&anon_vma->ref)) + anon_vma_free(anon_vma); +} + /* * rmap interfaces called when adding or removing pte of page */ Index: linux-2.6/mm/ksm.c =================================================================== --- linux-2.6.orig/mm/ksm.c +++ linux-2.6/mm/ksm.c @@ -323,14 +323,7 @@ static void hold_anon_vma(struct rmap_it static void drop_anon_vma(struct rmap_item *rmap_item) { - struct anon_vma *anon_vma = rmap_item->anon_vma; - - if (atomic_dec_and_lock(&anon_vma->ref, &anon_vma->lock)) { - int empty = list_empty(&anon_vma->head); - spin_unlock(&anon_vma->lock); - if (empty) - anon_vma_free(anon_vma); - } + anon_vma_put(rmap_item->anon_vma); } /* Index: linux-2.6/mm/migrate.c =================================================================== --- linux-2.6.orig/mm/migrate.c +++ linux-2.6/mm/migrate.c @@ -545,7 +545,7 @@ static int unmap_and_move(new_page_t get int rc = 0; int *result = NULL; struct page *newpage = get_new_page(page, private, &result); - int rcu_locked = 0; + struct anon_vma *anon_vma = NULL; int charge = 0; struct mem_cgroup *mem = NULL; @@ -601,10 +601,8 @@ static int unmap_and_move(new_page_t get * File Caches may use write_page() or lock_page() in migration, then, * just care Anon page here. */ - if (PageAnon(page)) { - rcu_read_lock(); - rcu_locked = 1; - } + if (PageAnon(page)) + anon_vma = anon_vma_get(page); /* * Corner case handling: @@ -622,10 +620,7 @@ static int unmap_and_move(new_page_t get if (!PageAnon(page) && page_has_private(page)) { /* * Go direct to try_to_free_buffers() here because - * a) that's what try_to_release_page() would do anyway - * b) we may be under rcu_read_lock() here, so we can't - * use GFP_KERNEL which is what try_to_release_page() - * needs to be effective. + * that's what try_to_release_page() would do anyway */ try_to_free_buffers(page); goto rcu_unlock; @@ -643,8 +638,8 @@ skip_unmap: if (rc) remove_migration_ptes(page, page); rcu_unlock: - if (rcu_locked) - rcu_read_unlock(); + if (anon_vma) + anon_vma_put(anon_vma); uncharge: if (!charge) mem_cgroup_end_migration(mem, page, newpage); Index: linux-2.6/mm/rmap.c =================================================================== --- linux-2.6.orig/mm/rmap.c +++ linux-2.6/mm/rmap.c @@ -66,11 +66,18 @@ static struct kmem_cache *anon_vma_chain static inline struct anon_vma *anon_vma_alloc(void) { - return kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); + struct anon_vma *anon_vma; + + anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); + if (anon_vma) + atomic_set(&anon_vma->ref, 1); + + return anon_vma; } void anon_vma_free(struct anon_vma *anon_vma) { + VM_BUG_ON(atomic_read(&anon_vma->ref)); kmem_cache_free(anon_vma_cachep, anon_vma); } @@ -149,7 +156,7 @@ int anon_vma_prepare(struct vm_area_stru spin_unlock(&anon_vma->lock); if (unlikely(allocated)) { - anon_vma_free(allocated); + anon_vma_put(allocated); anon_vma_chain_free(avc); } } @@ -230,7 +237,7 @@ int anon_vma_fork(struct vm_area_struct return 0; out_error_free_anon_vma: - anon_vma_free(anon_vma); + anon_vma_put(anon_vma); out_error: unlink_anon_vmas(vma); return -ENOMEM; @@ -247,13 +254,11 @@ static void anon_vma_unlink(struct anon_ spin_lock(&anon_vma->lock); list_del(&anon_vma_chain->same_anon_vma); - - /* We must garbage collect the anon_vma if it's empty */ - empty = list_empty(&anon_vma->head) && !atomic_read(&anon_vma->ref); + empty = list_empty(&anon_vma->head); spin_unlock(&anon_vma->lock); if (empty) - anon_vma_free(anon_vma); + anon_vma_put(anon_vma); } void unlink_anon_vmas(struct vm_area_struct *vma) @@ -286,11 +291,11 @@ void __init anon_vma_init(void) /* * Getting a lock on a stable anon_vma from a page off the LRU is - * tricky: page_lock_anon_vma rely on RCU to guard against the races. + * tricky: page_lock_anon_vma relies on RCU to guard against the races. */ -struct anon_vma *page_lock_anon_vma(struct page *page) +struct anon_vma *anon_vma_get(struct page *page) { - struct anon_vma *anon_vma; + struct anon_vma *anon_vma = NULL; unsigned long anon_mapping; rcu_read_lock(); @@ -302,23 +307,33 @@ again: goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); - spin_lock(&anon_vma->lock); + if (!atomic_inc_not_zero(&anon_vma->ref)) + anon_vma = NULL; if (page_rmapping(page) != anon_vma) { - spin_unlock(&anon_vma->lock); + anon_vma_put(anon_vma); goto again; } - return anon_vma; out: rcu_read_unlock(); - return NULL; + return anon_vma; +} + +struct anon_vma *page_lock_anon_vma(struct page *page) +{ + struct anon_vma *anon_vma = anon_vma_get(page); + + if (anon_vma) + spin_lock(&anon_vma->lock); + + return anon_vma; } void page_unlock_anon_vma(struct anon_vma *anon_vma) { spin_unlock(&anon_vma->lock); - rcu_read_unlock(); + anon_vma_put(anon_vma); } /* -- To unsubscribe from this list: send the line "unsubscribe linux-arch" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html