From: Konstantin Khlebnikov <koct9i@gmail.com>
Subject: mm: prevent endless growth of anon_vma hierarchy
Patch-mainline: 3.19-rc4
References: bnc#904242
Git-commit: 7a3ef208e662f4b63d43a23f61a64a129c525bbc

Constantly forking task causes unlimited grow of anon_vma chain.
Each next child allocate new level of anon_vmas and links vmas to all
previous levels because it inherits pages from them. None of anon_vmas
cannot be freed because there might be pages which points to them.

This patch adds heuristic which decides to reuse existing anon_vma instead
of forking new one. It counts vmas and direct descendants for each anon_vma.
Anon_vma with degree lower than two will be reused at next fork.
As a result each anon_vma has either alive vma or at least two descendants,
endless chains are no longer possible and count of anon_vmas is no more than
two times more than count of vmas.

Signed-off-by: Konstantin Khlebnikov <koct9i@gmail.com>
Link: http://lkml.kernel.org/r/20120816024610.GA5350@evergreen.ssec.wisc.edu
Acked-by: Michal Hocko <mhocko@suse.cz>

---
 include/linux/rmap.h |   16 ++++++++++++++++
 mm/rmap.c            |   29 ++++++++++++++++++++++++++++-
 2 files changed, 44 insertions(+), 1 deletion(-)

--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -45,6 +45,22 @@ struct anon_vma {
 	 * mm_take_all_locks() (mm_all_locks_mutex).
 	 */
 	struct list_head head;	/* Chain of private "related" vmas */
+
+	/*
+	 * Count of child anon_vmas and VMAs which points to this anon_vma.
+	 *
+	 * This counter is used for making decision about reusing old anon_vma
+	 * instead of forking new one. It allows to detect anon_vmas which have
+	 * just one direct descendant and no vmas. Reusing such anon_vma not
+	 * leads to significant preformance regression but prevents degradation
+	 * of anon_vma hierarchy to endless linear chain.
+	 *
+	 * Root anon_vma is never reused because it is its own parent and it has
+	 * at leat one vma or child, thus at fork it's degree is at least 2.
+	 */
+	unsigned degree;
+
+	struct anon_vma *parent;	/* Parent of this anon_vma */
 };
 
 /*
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -73,6 +73,8 @@ static inline struct anon_vma *anon_vma_
 	anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
 	if (anon_vma) {
 		atomic_set(&anon_vma->refcount, 1);
+		anon_vma->degree = 1;	/* Reference for first vma */
+		anon_vma->parent = anon_vma;
 		/*
 		 * Initialise the anon_vma root to point to itself. If called
 		 * from fork, the root will be reset to the parents anon_vma.
@@ -181,6 +183,7 @@ int anon_vma_prepare(struct vm_area_stru
 			avc->vma = vma;
 			list_add(&avc->same_vma, &vma->anon_vma_chain);
 			list_add_tail(&avc->same_anon_vma, &anon_vma->head);
+			anon_vma->degree++;
 			allocated = NULL;
 			avc = NULL;
 		}
@@ -264,7 +267,17 @@ int anon_vma_clone(struct vm_area_struct
 		anon_vma = pavc->anon_vma;
 		root = lock_anon_vma_root(root, anon_vma);
 		anon_vma_chain_link(dst, avc, anon_vma);
+
+		/*
+		 * Reuse existing anon_vma if its degree lower than two,
+		 * that means it has no vma and just one anon_vma child.
+		 */
+		if (!dst->anon_vma && anon_vma != src->anon_vma &&
+				anon_vma->degree < 2)
+			dst->anon_vma = anon_vma;
 	}
+	if (dst->anon_vma)
+		dst->anon_vma->degree++;
 	unlock_anon_vma_root(root);
 	return 0;
 
@@ -287,6 +300,9 @@ int anon_vma_fork(struct vm_area_struct
 	if (!pvma->anon_vma)
 		return 0;
 
+	/* Drop inherited anon_vma, we'll reuse old one or allocate new. */
+	vma->anon_vma = NULL;
+
 	/*
 	 * First, attach the new VMA to the parent VMA's anon_vmas,
 	 * so rmap can find non-COWed pages in child processes.
@@ -294,6 +310,10 @@ int anon_vma_fork(struct vm_area_struct
 	if (anon_vma_clone(vma, pvma))
 		return -ENOMEM;
 
+	/* An old anon_vma has been reused. */
+	if (vma->anon_vma)
+		return 0;
+
 	/* Then add our own anon_vma. */
 	anon_vma = anon_vma_alloc();
 	if (!anon_vma)
@@ -307,6 +327,7 @@ int anon_vma_fork(struct vm_area_struct
 	 * lock any of the anon_vmas in this anon_vma tree.
 	 */
 	anon_vma->root = pvma->anon_vma->root;
+	anon_vma->parent = pvma->anon_vma;
 	/*
 	 * With refcounts, an anon_vma can stay around longer than the
 	 * process it belongs to. The root anon_vma needs to be pinned until
@@ -317,6 +338,7 @@ int anon_vma_fork(struct vm_area_struct
 	vma->anon_vma = anon_vma;
 	anon_vma_lock(anon_vma);
 	anon_vma_chain_link(vma, avc, anon_vma);
+	anon_vma->parent->degree++;
 	anon_vma_unlock(anon_vma);
 
 	return 0;
@@ -347,12 +369,16 @@ void unlink_anon_vmas(struct vm_area_str
 		 * Leave empty anon_vmas on the list - we'll need
 		 * to free them outside the lock.
 		 */
-		if (list_empty(&anon_vma->head))
+		if (list_empty(&anon_vma->head)) {
+			anon_vma->parent->degree--;
 			continue;
+		}
 
 		list_del(&avc->same_vma);
 		anon_vma_chain_free(avc);
 	}
+	if (vma->anon_vma)
+		vma->anon_vma->degree--;
 	unlock_anon_vma_root(root);
 
 	/*
@@ -363,6 +389,7 @@ void unlink_anon_vmas(struct vm_area_str
 	list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
 		struct anon_vma *anon_vma = avc->anon_vma;
 
+		BUG_ON(anon_vma->degree);
 		put_anon_vma(anon_vma);
 
 		list_del(&avc->same_vma);
