mm/rmap.c: don't reuse anon_vma if we just want a copy

PATCH Superseded Wei Yang 1 participant 3 messages Oct 11, 2019

Subsystems (2)

Memory management MM rmap

lore

Share & tools

lore

Wei Yang

author

2019-10-11 03:00 UTC #0 lore raw

PATCH v3 1/2 mm/rmap.c: don't reuse anon_vma if we just want a copy

Before commit 7a3ef208e662 ("mm: prevent endless growth of anon_vma hierarchy"), anon_vma_clone() doesn't change dst->anon_vma. While after this commit, anon_vma_clone() will try to reuse an exist one on forking.

But this commit go a little bit further for the case not forking. anon_vma_clone() is called from __vma_split(), __split_vma(), copy_vma() and anon_vma_fork(). For the first three places, the purpose here is get a copy of src and we don't expect to touch dst->anon_vma even it is NULL. While after that commit, it is possible to reuse an anon_vma when dst->anon_vma is NULL. This is not we intend to have.

This patch stop reuse anon_vma for non-fork cases.

Fix commit 7a3ef208e662 ("mm: prevent endless growth of anon_vma hierarchy")

Signed-off-by Wei Yang <[email protected]>

---
v3:
* use dst->anon_vma and src->anon_vma to get reuse state pointed by Konstantin Khlebnikov

---
 mm/rmap.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

mm/rmap.c +9 -3

index d9a23bb773bf..fc0aba7fb9b9 100644
@@ -250,7 +250,13 @@ static inline void unlock_anon_vma_root(struct anon_vma *root)
  * Attach the anon_vmas from src to dst.
  * Returns 0 on success, -ENOMEM on failure.
  *
- * If dst->anon_vma is NULL this function tries to find and reuse existing
+ * anon_vma_clone() is called by __vma_split(), __split_vma(), copy_vma() and
+ * anon_vma_fork(). The first three want an exact copy of src, while the last
+ * one, anon_vma_fork(), may try to reuse an existing anon_vma to prevent
+ * endless growth of anon_vma. Since dst->anon_vma is set to NULL before call,
+ * we can identify this case by (reuse = !dst->anon_vma && src->anon_vma).
+ *
+ * If reuse is true, this function tries to find and reuse existing
  * anon_vma which has no vmas and only one child anon_vma. This prevents
  * degradation of anon_vma hierarchy to endless linear chain in case of
  * constantly forking task. On the other hand, an anon_vma with more than one

@@ -262,6 +268,7 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
 {
 	struct anon_vma_chain *avc, *pavc;
 	struct anon_vma *root = NULL;
+	bool reuse = !dst->anon_vma && src->anon_vma;
 
 	list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) {
 		struct anon_vma *anon_vma;

@@ -286,8 +293,7 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
 		 * will always reuse it. Root anon_vma is never reused:
 		 * it has self-parent reference and at least one child.
 		 */
-		if (!dst->anon_vma && anon_vma != src->anon_vma &&
-				anon_vma->degree < 2)
+		if (reuse && anon_vma != src->anon_vma && anon_vma->degree < 2)
 			dst->anon_vma = anon_vma;
 	}
 	if (dst->anon_vma)

Signature · 1 line

2.17.1

Wei Yang

author

2019-10-11 02:59 UTC #1 lore raw

PATCH v3 2/2 mm/rmap.c: reuse mergeable anon_vma as parent when fork

In function __anon_vma_prepare(), we will try to find anon_vma if it is possible to reuse it. While on fork, the logic is different.

Since commit 5beb49305251 ("mm: change anon_vma linking to fix multi-process server scalability issue"), function anon_vma_clone() tries to allocate new anon_vma for child process. But the logic here will allocate a new anon_vma for each vma, even in parent this vma is mergeable and share the same anon_vma with its sibling. This may do better for scalability issue, while it is not necessary to do so especially after interval tree is used.

Commit 7a3ef208e662 ("mm: prevent endless growth of anon_vma hierarchy") tries to reuse some anon_vma by counting child anon_vma and attached vmas. While for those mergeable anon_vmas, we can just reuse it and not necessary to go through the logic.

After this change, kernel build test reduces 20% anon_vma allocation.

Do the same kernel build test, it shows run time in sys reduced 11.5%.

Origin:

real    2m50.467s
user    17m52.002s
sys     1m51.953s

real    2m48.662s
user    17m55.464s
sys     1m50.553s

real    2m51.143s
user    17m59.687s
sys     1m53.600s

Patched:

real 2m40.080s
user 17m4.644s
sys 1m39.321s

real 2m39.967s
user 17m2.445s
sys 1m38.850s

real 2m40.581s
user 17m1.975s
sys 1m39.065s

Signed-off-by Wei Yang <[email protected]>

---
 mm/rmap.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

mm/rmap.c +12 -0

index fc0aba7fb9b9..0dd5f8b04a48 100644
@@ -269,6 +269,18 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
 	struct anon_vma_chain *avc, *pavc;
 	struct anon_vma *root = NULL;
 	bool reuse = !dst->anon_vma && src->anon_vma;
+	struct vm_area_struct *prev = dst->vm_prev, *pprev = src->vm_prev;
+
+	/*
+	 * If parent share anon_vma with its vm_prev, keep this sharing in in
+	 * child.
+	 *
+	 * 1. Parent has vm_prev, which implies we have vm_prev.
+	 * 2. Parent and its vm_prev have the same anon_vma.
+	 */
+	if (reuse && pprev && pprev->anon_vma == src->anon_vma)
+		dst->anon_vma = prev->anon_vma;
+
 
 	list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) {
 		struct anon_vma *anon_vma;

Signature · 1 line

2.17.1

Wei Yang

author

2019-10-11 05:21 UTC #2 lore raw

In reply to Wei Yang

Quoted 54 lines · Wei Yang

Before commit 7a3ef208e662 ("mm: prevent endless growth of anon_vma hierarchy"), anon_vma_clone() doesn't change dst->anon_vma. While after this commit, anon_vma_clone() will try to reuse an exist one on forking.
But this commit go a little bit further for the case not forking. anon_vma_clone() is called from __vma_split(), __split_vma(), copy_vma() and anon_vma_fork(). For the first three places, the purpose here is get a copy of src and we don't expect to touch dst->anon_vma even it is NULL. While after that commit, it is possible to reuse an anon_vma when dst->anon_vma is NULL. This is not we intend to have.
This patch stop reuse anon_vma for non-fork cases.
Fix commit 7a3ef208e662 ("mm: prevent endless growth of anon_vma hierarchy")
Signed-off-by Wei Yang <[email protected]>
---
v3:
* use dst->anon_vma and src->anon_vma to get reuse state pointed by Konstantin Khlebnikov
---
mm/rmap.c | 12 +++++++++---
1 file changed, 9 insertions(+), 3 deletions(-)
mm/rmap.c +8 -1
index d9a23bb773bf..fc0aba7fb9b9 100644
@@ -250,7 +250,13 @@ static inline void unlock_anon_vma_root(struct anon_vma *root)
 * Attach the anon_vmas from src to dst.
 * Returns 0 on success, -ENOMEM on failure.
 *
- * If dst->anon_vma is NULL this function tries to find and reuse existing
+ * anon_vma_clone() is called by __vma_split(), __split_vma(), copy_vma() and
+ * anon_vma_fork(). The first three want an exact copy of src, while the last
+ * one, anon_vma_fork(), may try to reuse an existing anon_vma to prevent
+ * endless growth of anon_vma. Since dst->anon_vma is set to NULL before call,
+ * we can identify this case by (reuse = !dst->anon_vma && src->anon_vma).
+ *
+ * If reuse is true, this function tries to find and reuse existing
 * anon_vma which has no vmas and only one child anon_vma. This prevents
 * degradation of anon_vma hierarchy to endless linear chain in case of
 * constantly forking task. On the other hand, an anon_vma with more than one
@@ -262,6 +268,7 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
 {
 	struct anon_vma_chain *avc, *pavc;
 	struct anon_vma *root = NULL;
+	bool reuse = !dst->anon_vma && src->anon_vma;
 
 	list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) {
 		struct anon_vma *anon_vma;

mm/rmap.c int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) · line 297

Quoted 7 lines

mm/rmap.c +1 -2

@@ -286,8 +293,7 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
 		 * will always reuse it. Root anon_vma is never reused:
 		 * it has self-parent reference and at least one child.
 		 */
-		if (!dst->anon_vma && anon_vma != src->anon_vma &&
-				anon_vma->degree < 2)
+		if (reuse && anon_vma != src->anon_vma && anon_vma->degree < 2)
 			dst->anon_vma = anon_vma;

What a shame.

dst->anon_vma would be changed in the loop, so we only need to assign it when dst->anon_vma == NULL.

Quoted 4 lines

mm/rmap.c +0 -0
 	}
 	if (dst->anon_vma)
Signature · 1 line
2.17.1

Signature · 2 lines

Wei Yang
Help you, Help me