All of lore.kernel.org
 help / color / mirror / Atom feed
From: Daniel Axtens <dja@axtens.net>
To: kasan-dev@googlegroups.com, linux-mm@kvack.org, x86@kernel.org,
	aryabinin@virtuozzo.com, glider@google.com, luto@kernel.org,
	linux-kernel@vger.kernel.org, mark.rutland@arm.com,
	dvyukov@google.com, christophe.leroy@c-s.fr,
	akpm@linux-foundation.org, urezki@gmail.com
Cc: cai@lca.pw, linuxppc-dev@lists.ozlabs.org, gor@linux.ibm.com,
	Daniel Axtens <dja@axtens.net>
Subject: [PATCH] update to "kasan: support backing vmalloc space with real shadow memory"
Date: Wed, 20 Nov 2019 16:27:19 +1100	[thread overview]
Message-ID: <20191120052719.7201-1-dja@axtens.net> (raw)
In-Reply-To: <20191031093909.9228-2-dja@axtens.net>

Hi Andrew,

This is a quick fixup to patch 1 of the "kasan: support backing
vmalloc space with real shadow memory" series, v11, which you pulled
in to your mmotm tree.

There are 2 changes:

 - A fixup to the per-cpu allocator path to avoid allocating memory
   under a spinlock, thanks Qian Cai.

 - Insert flush_cache_vmap() between mapping shadow and poisoning
   it. This is a no-op on x86 and arm64, but on powerpc it does a
   ptesync instruction which prevents occasional page faults.

Here are updated benchmark figures for the commit message:

Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that:

 - Turning on KASAN, inline instrumentation, without vmalloc, introuduces
   a 5.7x-6.4x slowdown in vmalloc operations.

 - Turning this on introduces the following slowdowns over KASAN:
     * ~1.82x slower single-threaded (test_vmalloc.sh performance)
     * ~2.11x slower when both cpus are performing operations
       simultaneously (test_vmalloc.sh sequential_test_order=1)

This is unfortunate, but given that this is a debug feature only, not
the end of the world.

The full results are:

Performance

                              No KASAN      KASAN original x baseline  KASAN vmalloc x baseline    x KASAN

fix_size_alloc_test             662004            11404956      17.23       19144610      28.92       1.68
full_fit_alloc_test             710950            12029752      16.92       13184651      18.55       1.10
long_busy_list_alloc_test      9431875            43990172       4.66       82970178       8.80       1.89
random_size_alloc_test         5033626            23061762       4.58       47158834       9.37       2.04
fix_align_alloc_test           1252514            15276910      12.20       31266116      24.96       2.05
random_size_align_alloc_te     1648501            14578321       8.84       25560052      15.51       1.75
align_shift_alloc_test             147                 830       5.65           5692      38.72       6.86
pcpu_alloc_test                  80732              125520       1.55         140864       1.74       1.12
Total Cycles              119240774314        763211341128       6.40  1390338696894      11.66       1.82

Sequential, 2 cpus

                              No KASAN      KASAN original x baseline  KASAN vmalloc x baseline    x KASAN

fix_size_alloc_test            1423150            14276550      10.03       27733022      19.49       1.94
full_fit_alloc_test            1754219            14722640       8.39       15030786       8.57       1.02
long_busy_list_alloc_test     11451858            52154973       4.55      107016027       9.34       2.05
random_size_alloc_test         5989020            26735276       4.46       68885923      11.50       2.58
fix_align_alloc_test           2050976            20166900       9.83       50491675      24.62       2.50
random_size_align_alloc_te     2858229            17971700       6.29       38730225      13.55       2.16
align_shift_alloc_test             405                6428      15.87          26253      64.82       4.08
pcpu_alloc_test                 127183              151464       1.19         216263       1.70       1.43
Total Cycles               54181269392        308723699764       5.70   650772566394      12.01       2.11
fix_size_alloc_test            1420404            14289308      10.06       27790035      19.56       1.94
full_fit_alloc_test            1736145            14806234       8.53       15274301       8.80       1.03
long_busy_list_alloc_test     11404638            52270785       4.58      107550254       9.43       2.06
random_size_alloc_test         6017006            26650625       4.43       68696127      11.42       2.58
fix_align_alloc_test           2045504            20280985       9.91       50414862      24.65       2.49
random_size_align_alloc_te     2845338            17931018       6.30       38510276      13.53       2.15
align_shift_alloc_test             472                3760       7.97           9656      20.46       2.57
pcpu_alloc_test                 118643              132732       1.12         146504       1.23       1.10
Total Cycles               54040011688        309102805492       5.72   651325675652      12.05       2.11

Cc: Qian Cai <cai@lca.pw>
Signed-off-by: Daniel Axtens <dja@axtens.net>
---
 mm/kasan/common.c | 2 ++
 mm/vmalloc.c      | 5 ++++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 6e7bc5d3fa83..df3371d5c572 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -794,6 +794,8 @@ int kasan_populate_vmalloc(unsigned long requested_size, struct vm_struct *area)
 	if (ret)
 		return ret;
 
+	flush_cache_vmap(shadow_start, shadow_end);
+
 	kasan_unpoison_shadow(area->addr, requested_size);
 
 	area->flags |= VM_KASAN;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index a4b950a02d0b..bf030516258c 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -3417,11 +3417,14 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
 
 		setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC,
 				 pcpu_get_vm_areas);
+	}
+	spin_unlock(&vmap_area_lock);
 
+	/* populate the shadow space outside of the lock */
+	for (area = 0; area < nr_vms; area++) {
 		/* assume success here */
 		kasan_populate_vmalloc(sizes[area], vms[area]);
 	}
-	spin_unlock(&vmap_area_lock);
 
 	kfree(vas);
 	return vms;
-- 
2.20.1


WARNING: multiple messages have this Message-ID (diff)
From: Daniel Axtens <dja@axtens.net>
To: kasan-dev@googlegroups.com, linux-mm@kvack.org, x86@kernel.org,
	aryabinin@virtuozzo.com, glider@google.com, luto@kernel.org,
	linux-kernel@vger.kernel.org, mark.rutland@arm.com,
	dvyukov@google.com, christophe.leroy@c-s.fr,
	akpm@linux-foundation.org, urezki@gmail.com
Cc: linuxppc-dev@lists.ozlabs.org, gor@linux.ibm.com, cai@lca.pw,
	Daniel Axtens <dja@axtens.net>
Subject: [PATCH] update to "kasan: support backing vmalloc space with real shadow memory"
Date: Wed, 20 Nov 2019 16:27:19 +1100	[thread overview]
Message-ID: <20191120052719.7201-1-dja@axtens.net> (raw)
In-Reply-To: <20191031093909.9228-2-dja@axtens.net>

Hi Andrew,

This is a quick fixup to patch 1 of the "kasan: support backing
vmalloc space with real shadow memory" series, v11, which you pulled
in to your mmotm tree.

There are 2 changes:

 - A fixup to the per-cpu allocator path to avoid allocating memory
   under a spinlock, thanks Qian Cai.

 - Insert flush_cache_vmap() between mapping shadow and poisoning
   it. This is a no-op on x86 and arm64, but on powerpc it does a
   ptesync instruction which prevents occasional page faults.

Here are updated benchmark figures for the commit message:

Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that:

 - Turning on KASAN, inline instrumentation, without vmalloc, introuduces
   a 5.7x-6.4x slowdown in vmalloc operations.

 - Turning this on introduces the following slowdowns over KASAN:
     * ~1.82x slower single-threaded (test_vmalloc.sh performance)
     * ~2.11x slower when both cpus are performing operations
       simultaneously (test_vmalloc.sh sequential_test_order=1)

This is unfortunate, but given that this is a debug feature only, not
the end of the world.

The full results are:

Performance

                              No KASAN      KASAN original x baseline  KASAN vmalloc x baseline    x KASAN

fix_size_alloc_test             662004            11404956      17.23       19144610      28.92       1.68
full_fit_alloc_test             710950            12029752      16.92       13184651      18.55       1.10
long_busy_list_alloc_test      9431875            43990172       4.66       82970178       8.80       1.89
random_size_alloc_test         5033626            23061762       4.58       47158834       9.37       2.04
fix_align_alloc_test           1252514            15276910      12.20       31266116      24.96       2.05
random_size_align_alloc_te     1648501            14578321       8.84       25560052      15.51       1.75
align_shift_alloc_test             147                 830       5.65           5692      38.72       6.86
pcpu_alloc_test                  80732              125520       1.55         140864       1.74       1.12
Total Cycles              119240774314        763211341128       6.40  1390338696894      11.66       1.82

Sequential, 2 cpus

                              No KASAN      KASAN original x baseline  KASAN vmalloc x baseline    x KASAN

fix_size_alloc_test            1423150            14276550      10.03       27733022      19.49       1.94
full_fit_alloc_test            1754219            14722640       8.39       15030786       8.57       1.02
long_busy_list_alloc_test     11451858            52154973       4.55      107016027       9.34       2.05
random_size_alloc_test         5989020            26735276       4.46       68885923      11.50       2.58
fix_align_alloc_test           2050976            20166900       9.83       50491675      24.62       2.50
random_size_align_alloc_te     2858229            17971700       6.29       38730225      13.55       2.16
align_shift_alloc_test             405                6428      15.87          26253      64.82       4.08
pcpu_alloc_test                 127183              151464       1.19         216263       1.70       1.43
Total Cycles               54181269392        308723699764       5.70   650772566394      12.01       2.11
fix_size_alloc_test            1420404            14289308      10.06       27790035      19.56       1.94
full_fit_alloc_test            1736145            14806234       8.53       15274301       8.80       1.03
long_busy_list_alloc_test     11404638            52270785       4.58      107550254       9.43       2.06
random_size_alloc_test         6017006            26650625       4.43       68696127      11.42       2.58
fix_align_alloc_test           2045504            20280985       9.91       50414862      24.65       2.49
random_size_align_alloc_te     2845338            17931018       6.30       38510276      13.53       2.15
align_shift_alloc_test             472                3760       7.97           9656      20.46       2.57
pcpu_alloc_test                 118643              132732       1.12         146504       1.23       1.10
Total Cycles               54040011688        309102805492       5.72   651325675652      12.05       2.11

Cc: Qian Cai <cai@lca.pw>
Signed-off-by: Daniel Axtens <dja@axtens.net>
---
 mm/kasan/common.c | 2 ++
 mm/vmalloc.c      | 5 ++++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 6e7bc5d3fa83..df3371d5c572 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -794,6 +794,8 @@ int kasan_populate_vmalloc(unsigned long requested_size, struct vm_struct *area)
 	if (ret)
 		return ret;
 
+	flush_cache_vmap(shadow_start, shadow_end);
+
 	kasan_unpoison_shadow(area->addr, requested_size);
 
 	area->flags |= VM_KASAN;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index a4b950a02d0b..bf030516258c 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -3417,11 +3417,14 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
 
 		setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC,
 				 pcpu_get_vm_areas);
+	}
+	spin_unlock(&vmap_area_lock);
 
+	/* populate the shadow space outside of the lock */
+	for (area = 0; area < nr_vms; area++) {
 		/* assume success here */
 		kasan_populate_vmalloc(sizes[area], vms[area]);
 	}
-	spin_unlock(&vmap_area_lock);
 
 	kfree(vas);
 	return vms;
-- 
2.20.1



  parent reply	other threads:[~2019-11-20  5:39 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-31  9:39 [PATCH v11 0/4] kasan: support backing vmalloc space with real shadow memory Daniel Axtens
2019-10-31  9:39 ` [PATCH v11 1/4] " Daniel Axtens
2019-11-15 16:36   ` Qian Cai
2019-11-18  3:29     ` Daniel Axtens
2019-11-19  9:54       ` Andrey Ryabinin
2019-11-29 10:43         ` Dmitry Vyukov
2019-11-29 10:43           ` Dmitry Vyukov
2019-11-29 10:58           ` Dmitry Vyukov
2019-11-29 10:58             ` Dmitry Vyukov
2019-11-29 11:02             ` Dmitry Vyukov
2019-11-29 11:02               ` Dmitry Vyukov
2019-11-29 11:38               ` Andrey Ryabinin
2019-11-29 11:38                 ` Andrey Ryabinin
2019-11-29 11:47                 ` Dmitry Vyukov
2019-11-29 11:47                   ` Dmitry Vyukov
2019-11-29 11:53                   ` Andrey Ryabinin
2019-11-29 11:53                     ` Andrey Ryabinin
2019-11-29 12:29                     ` Daniel Axtens
2019-11-29 12:29                       ` Daniel Axtens
2019-11-29 12:45                       ` Dmitry Vyukov
2019-11-29 12:45                         ` Dmitry Vyukov
2019-11-29 15:13                         ` Dmitry Vyukov
2019-11-29 15:13                           ` Dmitry Vyukov
2019-11-29 15:15                       ` XFS check crash (WAS Re: [PATCH v11 1/4] kasan: support backing vmalloc space with real shadow memory) Qian Cai
2019-11-29 15:15                         ` Qian Cai
2019-11-29 15:50                         ` Daniel Axtens
2019-11-29 15:50                           ` Daniel Axtens
2019-11-29 12:09             ` [PATCH v11 1/4] kasan: support backing vmalloc space with real shadow memory Daniel Axtens
2019-11-29 12:09               ` Daniel Axtens
2019-11-29 12:15               ` Dmitry Vyukov
2019-11-29 12:15                 ` Dmitry Vyukov
2019-11-20  5:27   ` Daniel Axtens [this message]
2019-11-20  5:27     ` [PATCH] update to "kasan: support backing vmalloc space with real shadow memory" Daniel Axtens
2019-10-31  9:39 ` [PATCH v11 2/4] kasan: add test for vmalloc Daniel Axtens
2019-10-31  9:39 ` [PATCH v11 3/4] fork: support VMAP_STACK with KASAN_VMALLOC Daniel Axtens
2019-10-31  9:39 ` [PATCH v11 4/4] x86/kasan: support KASAN_VMALLOC Daniel Axtens
2019-11-08 22:36 ` [PATCH v11 0/4] kasan: support backing vmalloc space with real shadow memory Andrey Ryabinin
2019-11-08 22:36   ` Andrey Ryabinin
2019-12-02  8:07 ` Christophe Leroy

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=20191120052719.7201-1-dja@axtens.net \
    --to=dja@axtens.net \
    --cc=akpm@linux-foundation.org \
    --cc=aryabinin@virtuozzo.com \
    --cc=cai@lca.pw \
    --cc=christophe.leroy@c-s.fr \
    --cc=dvyukov@google.com \
    --cc=glider@google.com \
    --cc=gor@linux.ibm.com \
    --cc=kasan-dev@googlegroups.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=luto@kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=urezki@gmail.com \
    --cc=x86@kernel.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.