linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Suren Baghdasaryan <surenb@google.com>
To: akpm@linux-foundation.org
Cc: ccross@google.com, sumit.semwal@linaro.org, mhocko@suse.com,
	dave.hansen@intel.com, keescook@chromium.org,
	willy@infradead.org, kirill.shutemov@linux.intel.com,
	vbabka@suse.cz, hannes@cmpxchg.org, corbet@lwn.net,
	viro@zeniv.linux.org.uk, rdunlap@infradead.org,
	kaleshsingh@google.com, peterx@redhat.com, rppt@kernel.org,
	peterz@infradead.org, catalin.marinas@arm.com,
	vincenzo.frascino@arm.com, chinwen.chang@mediatek.com,
	axelrasmussen@google.com, aarcange@redhat.com, jannh@google.com,
	apopple@nvidia.com, jhubbard@nvidia.com, yuzhao@google.com,
	will@kernel.org, fenghua.yu@intel.com,
	thunder.leizhen@huawei.com, hughd@google.com,
	feng.tang@intel.com, jgg@ziepe.ca, guro@fb.com,
	tglx@linutronix.de, krisman@collabora.com,
	chris.hyser@oracle.com, pcc@google.com, ebiederm@xmission.com,
	axboe@kernel.dk, legion@kernel.org, eb@emlix.com,
	gorcunov@gmail.com, pavel@ucw.cz, songmuchun@bytedance.com,
	viresh.kumar@linaro.org, thomascedeno@google.com,
	sashal@kernel.org, cxfcosmos@gmail.com, linux@rasmusvillemoes.dk,
	linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-doc@vger.kernel.org, linux-mm@kvack.org,
	kernel-team@android.com, surenb@google.com
Subject: [PATCH v11 3/3] mm: add anonymous vma name refcounting
Date: Tue, 19 Oct 2021 14:55:11 -0700	[thread overview]
Message-ID: <20211019215511.3771969-3-surenb@google.com> (raw)
In-Reply-To: <20211019215511.3771969-1-surenb@google.com>

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@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
---
previous version at:
https://lore.kernel.org/all/20211001205657.815551-3-surenb@google.com/

 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 3ad85843e924..89cd74c891fa 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 948fad92ba1b..a4e21bc56cab 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -64,6 +64,29 @@ static int madvise_need_mmap_write(int behavior)
 }
 
 #ifdef CONFIG_ANON_VMA_NAME
+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;
@@ -76,7 +99,7 @@ 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,
@@ -85,34 +108,41 @@ 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;
 
-- 
2.33.0.1079.g6e70778dc9-goog


      parent reply	other threads:[~2021-10-19 21:55 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-10-19 21:55 [PATCH v11 1/3] mm: rearrange madvise code to allow for reuse Suren Baghdasaryan
2021-10-19 21:55 ` [PATCH v11 2/3] mm: add a field to store names for private anonymous memory Suren Baghdasaryan
2021-10-19 21:58   ` Suren Baghdasaryan
2021-11-16  5:19     ` Andrew Morton
2021-11-16  6:10       ` Suren Baghdasaryan
2021-10-27 18:35   ` Alexey Alexandrov
2021-10-27 20:01     ` Suren Baghdasaryan
2021-10-28 22:08       ` Suren Baghdasaryan
2021-11-15 18:59         ` Suren Baghdasaryan
2021-11-16  9:51           ` Michal Hocko
2021-11-16 16:29             ` Suren Baghdasaryan
2021-10-19 21:55 ` Suren Baghdasaryan [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20211019215511.3771969-3-surenb@google.com \
    --to=surenb@google.com \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=apopple@nvidia.com \
    --cc=axboe@kernel.dk \
    --cc=axelrasmussen@google.com \
    --cc=catalin.marinas@arm.com \
    --cc=ccross@google.com \
    --cc=chinwen.chang@mediatek.com \
    --cc=chris.hyser@oracle.com \
    --cc=corbet@lwn.net \
    --cc=cxfcosmos@gmail.com \
    --cc=dave.hansen@intel.com \
    --cc=eb@emlix.com \
    --cc=ebiederm@xmission.com \
    --cc=feng.tang@intel.com \
    --cc=fenghua.yu@intel.com \
    --cc=gorcunov@gmail.com \
    --cc=guro@fb.com \
    --cc=hannes@cmpxchg.org \
    --cc=hughd@google.com \
    --cc=jannh@google.com \
    --cc=jgg@ziepe.ca \
    --cc=jhubbard@nvidia.com \
    --cc=kaleshsingh@google.com \
    --cc=keescook@chromium.org \
    --cc=kernel-team@android.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=krisman@collabora.com \
    --cc=legion@kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux@rasmusvillemoes.dk \
    --cc=mhocko@suse.com \
    --cc=pavel@ucw.cz \
    --cc=pcc@google.com \
    --cc=peterx@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rdunlap@infradead.org \
    --cc=rppt@kernel.org \
    --cc=sashal@kernel.org \
    --cc=songmuchun@bytedance.com \
    --cc=sumit.semwal@linaro.org \
    --cc=tglx@linutronix.de \
    --cc=thomascedeno@google.com \
    --cc=thunder.leizhen@huawei.com \
    --cc=vbabka@suse.cz \
    --cc=vincenzo.frascino@arm.com \
    --cc=viresh.kumar@linaro.org \
    --cc=viro@zeniv.linux.org.uk \
    --cc=will@kernel.org \
    --cc=willy@infradead.org \
    --cc=yuzhao@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).