lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Fri,  1 Oct 2021 13:56:57 -0700
From:   Suren Baghdasaryan <surenb@...gle.com>
To:     akpm@...ux-foundation.org
Cc:     ccross@...gle.com, sumit.semwal@...aro.org, mhocko@...e.com,
        dave.hansen@...el.com, keescook@...omium.org, willy@...radead.org,
        kirill.shutemov@...ux.intel.com, vbabka@...e.cz,
        hannes@...xchg.org, corbet@....net, viro@...iv.linux.org.uk,
        rdunlap@...radead.org, kaleshsingh@...gle.com, peterx@...hat.com,
        rppt@...nel.org, peterz@...radead.org, catalin.marinas@....com,
        vincenzo.frascino@....com, chinwen.chang@...iatek.com,
        axelrasmussen@...gle.com, aarcange@...hat.com, jannh@...gle.com,
        apopple@...dia.com, jhubbard@...dia.com, yuzhao@...gle.com,
        will@...nel.org, fenghua.yu@...el.com, thunder.leizhen@...wei.com,
        hughd@...gle.com, feng.tang@...el.com, jgg@...pe.ca, guro@...com,
        tglx@...utronix.de, krisman@...labora.com, chris.hyser@...cle.com,
        pcc@...gle.com, ebiederm@...ssion.com, axboe@...nel.dk,
        legion@...nel.org, eb@...ix.com, gorcunov@...il.com, pavel@....cz,
        songmuchun@...edance.com, viresh.kumar@...aro.org,
        thomascedeno@...gle.com, sashal@...nel.org, cxfcosmos@...il.com,
        linux@...musvillemoes.dk, linux-kernel@...r.kernel.org,
        linux-fsdevel@...r.kernel.org, linux-doc@...r.kernel.org,
        linux-mm@...ck.org, kernel-team@...roid.com, surenb@...gle.com
Subject: [PATCH v10 3/3] mm: add anonymous vma name refcounting

While forking a process with high number (64K) of named anonymous vmas the
overhead caused by strdup() is noticeable. Experiments with ARM64 Android
device show up to 40% performance regression when forking a process with
64k unpopulated anonymous vmas using the max name lengths vs the same
process with the same number of anonymous vmas having no name.
Introduce anon_vma_name refcounted structure to avoid the overhead of
copying vma names during fork() and when splitting named anonymous vmas.
When a vma is duplicated, instead of copying the name we increment the
refcount of this structure. Multiple vmas can point to the same
anon_vma_name as long as they increment the refcount. The name member of
anon_vma_name structure is assigned at structure allocation time and is
never changed. If vma name changes then the refcount of the original
structure is dropped, a new anon_vma_name structure is allocated
to hold the new name and the vma pointer is updated to point to the new
structure.
With this approach the fork() performance regressions is reduced 3-4x
times and with usecases using more reasonable number of VMAs (a few
thousand) the regressions is not measurable.

Signed-off-by: Suren Baghdasaryan <surenb@...gle.com>
Reviewed-by: Kees Cook <keescook@...omium.org>
---
previous version at:
https://lore.kernel.org/linux-mm/20210902231813.3597709-3-surenb@google.com/

changes in v10
- Changed anon_vma_name_alloc() to use struct_size() and avoid strcpy(),
per Kees Cook

 include/linux/mm_types.h |  9 ++++++++-
 mm/madvise.c             | 42 ++++++++++++++++++++++++++++++++++------
 2 files changed, 44 insertions(+), 7 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index f1896c9b2da9..30c571b4f8d3 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -5,6 +5,7 @@
 #include <linux/mm_types_task.h>
 
 #include <linux/auxvec.h>
+#include <linux/kref.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/rbtree.h>
@@ -310,6 +311,12 @@ struct vm_userfaultfd_ctx {
 struct vm_userfaultfd_ctx {};
 #endif /* CONFIG_USERFAULTFD */
 
+struct anon_vma_name {
+	struct kref kref;
+	/* The name needs to be at the end because it is dynamically sized. */
+	char name[];
+};
+
 /*
  * This struct describes a virtual memory area. There is one of these
  * per VM-area/task. A VM area is any part of the process virtual memory
@@ -361,7 +368,7 @@ struct vm_area_struct {
 			unsigned long rb_subtree_last;
 		} shared;
 		/* Serialized by mmap_sem. */
-		char *anon_name;
+		struct anon_vma_name *anon_name;
 	};
 
 	/*
diff --git a/mm/madvise.c b/mm/madvise.c
index 69729930dde1..2f1ec13faaaa 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -63,6 +63,29 @@ static int madvise_need_mmap_write(int behavior)
 	}
 }
 
+static struct anon_vma_name *anon_vma_name_alloc(const char *name)
+{
+	struct anon_vma_name *anon_name;
+	size_t count;
+
+	/* Add 1 for NUL terminator at the end of the anon_name->name */
+	count = strlen(name) + 1;
+	anon_name = kmalloc(struct_size(anon_name, name, count), GFP_KERNEL);
+	if (anon_name) {
+		kref_init(&anon_name->kref);
+		memcpy(anon_name->name, name, count);
+	}
+
+	return anon_name;
+}
+
+static void vma_anon_name_free(struct kref *kref)
+{
+	struct anon_vma_name *anon_name =
+			container_of(kref, struct anon_vma_name, kref);
+	kfree(anon_name);
+}
+
 static inline bool has_vma_anon_name(struct vm_area_struct *vma)
 {
 	return !vma->vm_file && vma->anon_name;
@@ -75,7 +98,7 @@ const char *vma_anon_name(struct vm_area_struct *vma)
 
 	mmap_assert_locked(vma->vm_mm);
 
-	return vma->anon_name;
+	return vma->anon_name->name;
 }
 
 void dup_vma_anon_name(struct vm_area_struct *orig_vma,
@@ -84,34 +107,41 @@ void dup_vma_anon_name(struct vm_area_struct *orig_vma,
 	if (!has_vma_anon_name(orig_vma))
 		return;
 
-	new_vma->anon_name = kstrdup(orig_vma->anon_name, GFP_KERNEL);
+	kref_get(&orig_vma->anon_name->kref);
+	new_vma->anon_name = orig_vma->anon_name;
 }
 
 void free_vma_anon_name(struct vm_area_struct *vma)
 {
+	struct anon_vma_name *anon_name;
+
 	if (!has_vma_anon_name(vma))
 		return;
 
-	kfree(vma->anon_name);
+	anon_name = vma->anon_name;
 	vma->anon_name = NULL;
+	kref_put(&anon_name->kref, vma_anon_name_free);
 }
 
 /* mmap_lock should be write-locked */
 static int replace_vma_anon_name(struct vm_area_struct *vma, const char *name)
 {
+	const char *anon_name;
+
 	if (!name) {
 		free_vma_anon_name(vma);
 		return 0;
 	}
 
-	if (vma->anon_name) {
+	anon_name = vma_anon_name(vma);
+	if (anon_name) {
 		/* Same name, nothing to do here */
-		if (!strcmp(name, vma->anon_name))
+		if (!strcmp(name, anon_name))
 			return 0;
 
 		free_vma_anon_name(vma);
 	}
-	vma->anon_name = kstrdup(name, GFP_KERNEL);
+	vma->anon_name = anon_vma_name_alloc(name);
 	if (!vma->anon_name)
 		return -ENOMEM;
 
-- 
2.33.0.800.g4c38ced690-goog

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ