From 9e60109f125013b6c571f399a15a8b0fe1ffa4e6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 22 Mar 2011 16:32:46 -0700 Subject: mm: rename drop_anon_vma() to put_anon_vma() The normal code pattern used in the kernel is: get/put. Signed-off-by: Peter Zijlstra Reviewed-by: KAMEZAWA Hiroyuki Acked-by: Hugh Dickins Reviewed-by: Rik van Riel Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/rmap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm/rmap.c') diff --git a/mm/rmap.c b/mm/rmap.c index 941bf82e8961..ad416afb2061 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -278,7 +278,7 @@ static void anon_vma_unlink(struct anon_vma_chain *anon_vma_chain) if (empty) { /* We no longer need the root anon_vma */ if (anon_vma->root != anon_vma) - drop_anon_vma(anon_vma->root); + put_anon_vma(anon_vma->root); anon_vma_free(anon_vma); } } @@ -1493,7 +1493,7 @@ int try_to_munlock(struct page *page) * we know we are the last user, nobody else can get a reference and we * can do the freeing without the lock. */ -void drop_anon_vma(struct anon_vma *anon_vma) +void put_anon_vma(struct anon_vma *anon_vma) { BUG_ON(atomic_read(&anon_vma->external_refcount) <= 0); if (atomic_dec_and_lock(&anon_vma->external_refcount, &anon_vma->root->lock)) { -- cgit From 83813267c699ab11cc65a6d9d0f42db42f0862b3 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 22 Mar 2011 16:32:48 -0700 Subject: mm: move anon_vma ref out from under CONFIG_foo We need the anon_vma refcount unconditionally to simplify the anon_vma lifetime rules. Signed-off-by: Peter Zijlstra Acked-by: Mel Gorman Reviewed-by: KAMEZAWA Hiroyuki Acked-by: Hugh Dickins Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/rmap.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'mm/rmap.c') diff --git a/mm/rmap.c b/mm/rmap.c index ad416afb2061..873cd9ef912c 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -272,7 +272,7 @@ static void anon_vma_unlink(struct anon_vma_chain *anon_vma_chain) 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) && !anonvma_external_refcount(anon_vma); + empty = list_empty(&anon_vma->head) && !atomic_read(&anon_vma->refcount); anon_vma_unlock(anon_vma); if (empty) { @@ -303,7 +303,7 @@ static void anon_vma_ctor(void *data) struct anon_vma *anon_vma = data; spin_lock_init(&anon_vma->lock); - anonvma_external_refcount_init(anon_vma); + atomic_set(&anon_vma->refcount, 0); INIT_LIST_HEAD(&anon_vma->head); } @@ -1486,7 +1486,6 @@ int try_to_munlock(struct page *page) return try_to_unmap_file(page, TTU_MUNLOCK); } -#if defined(CONFIG_KSM) || defined(CONFIG_MIGRATION) /* * Drop an anon_vma refcount, freeing the anon_vma and anon_vma->root * if necessary. Be careful to do all the tests under the lock. Once @@ -1495,8 +1494,8 @@ int try_to_munlock(struct page *page) */ void put_anon_vma(struct anon_vma *anon_vma) { - BUG_ON(atomic_read(&anon_vma->external_refcount) <= 0); - if (atomic_dec_and_lock(&anon_vma->external_refcount, &anon_vma->root->lock)) { + BUG_ON(atomic_read(&anon_vma->refcount) <= 0); + if (atomic_dec_and_lock(&anon_vma->refcount, &anon_vma->root->lock)) { struct anon_vma *root = anon_vma->root; int empty = list_empty(&anon_vma->head); int last_root_user = 0; @@ -1507,8 +1506,8 @@ void put_anon_vma(struct anon_vma *anon_vma) * the refcount on the root and check if we need to free it. */ if (empty && anon_vma != root) { - BUG_ON(atomic_read(&root->external_refcount) <= 0); - last_root_user = atomic_dec_and_test(&root->external_refcount); + BUG_ON(atomic_read(&root->refcount) <= 0); + last_root_user = atomic_dec_and_test(&root->refcount); root_empty = list_empty(&root->head); } anon_vma_unlock(anon_vma); @@ -1520,7 +1519,6 @@ void put_anon_vma(struct anon_vma *anon_vma) } } } -#endif #ifdef CONFIG_MIGRATION /* -- cgit From 01d8b20dec5f4019283e244aba50ba86fe6ead6e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 22 Mar 2011 16:32:49 -0700 Subject: mm: simplify anon_vma refcounts 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. Signed-off-by: Peter Zijlstra Reviewed-by: KAMEZAWA Hiroyuki Acked-by: Hugh Dickins Acked-by: Mel Gorman Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/rmap.c | 76 +++++++++++++++++++++++---------------------------------------- 1 file changed, 28 insertions(+), 48 deletions(-) (limited to 'mm/rmap.c') diff --git a/mm/rmap.c b/mm/rmap.c index 873cd9ef912c..4a8e99a0fb97 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -67,11 +67,24 @@ static struct kmem_cache *anon_vma_chain_cachep; 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->refcount, 1); + /* + * Initialise the anon_vma root to point to itself. If called + * from fork, the root will be reset to the parents anon_vma. + */ + anon_vma->root = anon_vma; + } + + return anon_vma; } -void anon_vma_free(struct anon_vma *anon_vma) +static inline void anon_vma_free(struct anon_vma *anon_vma) { + VM_BUG_ON(atomic_read(&anon_vma->refcount)); kmem_cache_free(anon_vma_cachep, anon_vma); } @@ -133,11 +146,6 @@ int anon_vma_prepare(struct vm_area_struct *vma) if (unlikely(!anon_vma)) goto out_enomem_free_avc; allocated = anon_vma; - /* - * This VMA had no anon_vma yet. This anon_vma is - * the root of any anon_vma tree that might form. - */ - anon_vma->root = anon_vma; } anon_vma_lock(anon_vma); @@ -156,7 +164,7 @@ int anon_vma_prepare(struct vm_area_struct *vma) anon_vma_unlock(anon_vma); if (unlikely(allocated)) - anon_vma_free(allocated); + put_anon_vma(allocated); if (unlikely(avc)) anon_vma_chain_free(avc); } @@ -241,9 +249,9 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) */ anon_vma->root = pvma->anon_vma->root; /* - * With KSM refcounts, an anon_vma can stay around longer than the - * process it belongs to. The root anon_vma needs to be pinned - * until this anon_vma is freed, because the lock lives in the root. + * With refcounts, an anon_vma can stay around longer than the + * process it belongs to. The root anon_vma needs to be pinned until + * this anon_vma is freed, because the lock lives in the root. */ get_anon_vma(anon_vma->root); /* Mark this anon_vma as the one where our new (COWed) pages go. */ @@ -253,7 +261,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) return 0; out_error_free_anon_vma: - anon_vma_free(anon_vma); + put_anon_vma(anon_vma); out_error: unlink_anon_vmas(vma); return -ENOMEM; @@ -272,15 +280,11 @@ static void anon_vma_unlink(struct anon_vma_chain *anon_vma_chain) 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->refcount); + empty = list_empty(&anon_vma->head); anon_vma_unlock(anon_vma); - if (empty) { - /* We no longer need the root anon_vma */ - if (anon_vma->root != anon_vma) - put_anon_vma(anon_vma->root); - anon_vma_free(anon_vma); - } + if (empty) + put_anon_vma(anon_vma); } void unlink_anon_vmas(struct vm_area_struct *vma) @@ -1486,38 +1490,14 @@ int try_to_munlock(struct page *page) return try_to_unmap_file(page, TTU_MUNLOCK); } -/* - * Drop an anon_vma refcount, freeing the anon_vma and anon_vma->root - * if necessary. Be careful to do all the tests under the lock. Once - * we know we are the last user, nobody else can get a reference and we - * can do the freeing without the lock. - */ -void put_anon_vma(struct anon_vma *anon_vma) +void __put_anon_vma(struct anon_vma *anon_vma) { - BUG_ON(atomic_read(&anon_vma->refcount) <= 0); - if (atomic_dec_and_lock(&anon_vma->refcount, &anon_vma->root->lock)) { - struct anon_vma *root = anon_vma->root; - int empty = list_empty(&anon_vma->head); - int last_root_user = 0; - int root_empty = 0; + struct anon_vma *root = anon_vma->root; - /* - * The refcount on a non-root anon_vma got dropped. Drop - * the refcount on the root and check if we need to free it. - */ - if (empty && anon_vma != root) { - BUG_ON(atomic_read(&root->refcount) <= 0); - last_root_user = atomic_dec_and_test(&root->refcount); - root_empty = list_empty(&root->head); - } - anon_vma_unlock(anon_vma); + if (root != anon_vma && atomic_dec_and_test(&root->refcount)) + anon_vma_free(root); - if (empty) { - anon_vma_free(anon_vma); - if (root_empty && last_root_user) - anon_vma_free(root); - } - } + anon_vma_free(anon_vma); } #ifdef CONFIG_MIGRATION -- cgit From 250df6ed274d767da844a5d9f05720b804240197 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 22 Mar 2011 22:23:36 +1100 Subject: fs: protect inode->i_state with inode->i_lock Protect inode state transitions and validity checks with the inode->i_lock. This enables us to make inode state transitions independently of the inode_lock and is the first step to peeling away the inode_lock from the code. This requires that __iget() is done atomically with i_state checks during list traversals so that we don't race with another thread marking the inode I_FREEING between the state check and grabbing the reference. Also remove the unlock_new_inode() memory barrier optimisation required to avoid taking the inode_lock when clearing I_NEW. Simplify the code by simply taking the inode->i_lock around the state change and wakeup. Because the wakeup is no longer tricky, remove the wake_up_inode() function and open code the wakeup where necessary. Signed-off-by: Dave Chinner Signed-off-by: Al Viro --- mm/rmap.c | 1 + 1 file changed, 1 insertion(+) (limited to 'mm/rmap.c') diff --git a/mm/rmap.c b/mm/rmap.c index 4a8e99a0fb97..7dada0456448 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -32,6 +32,7 @@ * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in __set_page_dirty_buffers) * inode_lock (in set_page_dirty's __mark_inode_dirty) + * inode->i_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) * mapping->tree_lock (widely used, in set_page_dirty, * in arch-dependent flush_dcache_mmap_lock, -- cgit From a66979abad090b2765a6c6790c9fdeab996833f2 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 22 Mar 2011 22:23:41 +1100 Subject: fs: move i_wb_list out from under inode_lock Protect the inode writeback list with a new global lock inode_wb_list_lock and use it to protect the list manipulations and traversals. This lock replaces the inode_lock as the inodes on the list can be validity checked while holding the inode->i_lock and hence the inode_lock is no longer needed to protect the list. Signed-off-by: Dave Chinner Signed-off-by: Al Viro --- mm/rmap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm/rmap.c') diff --git a/mm/rmap.c b/mm/rmap.c index 7dada0456448..8da044a1db0f 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -31,12 +31,12 @@ * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in __set_page_dirty_buffers) - * inode_lock (in set_page_dirty's __mark_inode_dirty) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) + * inode_wb_list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) * mapping->tree_lock (widely used, in set_page_dirty, * in arch-dependent flush_dcache_mmap_lock, - * within inode_lock in __sync_single_inode) + * within inode_wb_list_lock in __sync_single_inode) * * (code doesn't rely on that order so it could be switched around) * ->tasklist_lock -- cgit