mm: support __GFP_REPEAT in kvmalloc_node
diff mbox

Message ID 20170104181229.GB10183@dhcp22.suse.cz
State New
Headers show

Commit Message

Michal Hocko Jan. 4, 2017, 6:12 p.m. UTC
While checking opencoded users I've encountered that vhost code would
really like to use kvmalloc with __GFP_REPEAT [1] so the following patch
adds support for __GFP_REPEAT and converts both vhost users.

So currently I am sitting on 3 patches. I will wait for more feedback -
especially about potential split ups or cleanups few more days and then
repost the whole series.

[1] http://lkml.kernel.org/r/20170104150800.GO25453@dhcp22.suse.cz
---
From 0b92e4d2e040524b878d4e7b9ee88fbad5284b33 Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Wed, 4 Jan 2017 18:01:39 +0100
Subject: [PATCH] mm: support __GFP_REPEAT in kvmalloc_node

vhost code uses __GFP_REPEAT when allocating vhost_virtqueue resp.
vhost_vsock because it would really like to prefer kmalloc to the
vmalloc fallback - see 23cc5a991c7a ("vhost-net: extend device
allocation to vmalloc") for more context. Michael Tsirkin has also
noted:
"
__GFP_REPEAT overhead is during allocation time.  Using vmalloc means all
accesses are slowed down.  Allocation is not on data path, accesses are.
"

Let's teach kvmalloc_node to handle __GFP_REPEAT properly. There are two
things to be careful about. First we should prevent from the OOM killer
and so have to involve __GFP_NORETRY by default and secondly override
__GFP_REPEAT for !costly order requests as the __GFP_REPEAT is ignored
for !costly orders.

This patch shouldn't introduce any functional change.

Cc: "Michael S. Tsirkin" <mst@redhat.com>
Signed-off-by: Michal Hocko <mhocko@suse.com>
---
 drivers/vhost/net.c   | 9 +++------
 drivers/vhost/vsock.c | 9 +++------
 mm/util.c             | 9 +++++++--
 3 files changed, 13 insertions(+), 14 deletions(-)

Comments

Vlastimil Babka Jan. 6, 2017, 12:09 p.m. UTC | #1
On 01/04/2017 07:12 PM, Michal Hocko wrote:
> While checking opencoded users I've encountered that vhost code would
> really like to use kvmalloc with __GFP_REPEAT [1] so the following patch
> adds support for __GFP_REPEAT and converts both vhost users.
> 
> So currently I am sitting on 3 patches. I will wait for more feedback -
> especially about potential split ups or cleanups few more days and then
> repost the whole series.
> 
> [1] http://lkml.kernel.org/r/20170104150800.GO25453@dhcp22.suse.cz
> ---
> From 0b92e4d2e040524b878d4e7b9ee88fbad5284b33 Mon Sep 17 00:00:00 2001
> From: Michal Hocko <mhocko@suse.com>
> Date: Wed, 4 Jan 2017 18:01:39 +0100
> Subject: [PATCH] mm: support __GFP_REPEAT in kvmalloc_node
> 
> vhost code uses __GFP_REPEAT when allocating vhost_virtqueue resp.
> vhost_vsock because it would really like to prefer kmalloc to the
> vmalloc fallback - see 23cc5a991c7a ("vhost-net: extend device
> allocation to vmalloc") for more context. Michael Tsirkin has also
> noted:
> "
> __GFP_REPEAT overhead is during allocation time.  Using vmalloc means all
> accesses are slowed down.  Allocation is not on data path, accesses are.
> "
> 
> Let's teach kvmalloc_node to handle __GFP_REPEAT properly. There are two
> things to be careful about. First we should prevent from the OOM killer
> and so have to involve __GFP_NORETRY by default and secondly override
> __GFP_REPEAT for !costly order requests as the __GFP_REPEAT is ignored
> for !costly orders.
> 
> This patch shouldn't introduce any functional change.

Which is because the converted usages are always used for costly order,
right.

> 
> Cc: "Michael S. Tsirkin" <mst@redhat.com>
> Signed-off-by: Michal Hocko <mhocko@suse.com>
> ---
>  drivers/vhost/net.c   | 9 +++------
>  drivers/vhost/vsock.c | 9 +++------
>  mm/util.c             | 9 +++++++--
>  3 files changed, 13 insertions(+), 14 deletions(-)
> 
> diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
> index 5dc34653274a..105cd04c7414 100644
> --- a/drivers/vhost/net.c
> +++ b/drivers/vhost/net.c
> @@ -797,12 +797,9 @@ static int vhost_net_open(struct inode *inode, struct file *f)
>  	struct vhost_virtqueue **vqs;
>  	int i;
>  
> -	n = kmalloc(sizeof *n, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
> -	if (!n) {
> -		n = vmalloc(sizeof *n);
> -		if (!n)
> -			return -ENOMEM;
> -	}
> +	n = kvmalloc(sizeof *n, GFP_KERNEL | __GFP_REPEAT);
> +	if (!n)
> +		return -ENOMEM;
>  	vqs = kmalloc(VHOST_NET_VQ_MAX * sizeof(*vqs), GFP_KERNEL);
>  	if (!vqs) {
>  		kvfree(n);
> diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
> index bbbf588540ed..7e0159867553 100644
> --- a/drivers/vhost/vsock.c
> +++ b/drivers/vhost/vsock.c
> @@ -455,12 +455,9 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
>  	/* This struct is large and allocation could fail, fall back to vmalloc
>  	 * if there is no other way.
>  	 */
> -	vsock = kzalloc(sizeof(*vsock), GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
> -	if (!vsock) {
> -		vsock = vmalloc(sizeof(*vsock));
> -		if (!vsock)
> -			return -ENOMEM;
> -	}
> +	vsock = kvmalloc(sizeof(*vsock), GFP_KERNEL | __GFP_REPEAT);
> +	if (!vsock)
> +		return -ENOMEM;
>  
>  	vqs = kmalloc_array(ARRAY_SIZE(vsock->vqs), sizeof(*vqs), GFP_KERNEL);
>  	if (!vqs) {
> diff --git a/mm/util.c b/mm/util.c
> index 8e4ea6cbe379..a2bfb85e60e5 100644
> --- a/mm/util.c
> +++ b/mm/util.c
> @@ -348,8 +348,13 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node)
>  	 * Make sure that larger requests are not too disruptive - no OOM
>  	 * killer and no allocation failure warnings as we have a fallback
>  	 */
> -	if (size > PAGE_SIZE)
> -		kmalloc_flags |= __GFP_NORETRY | __GFP_NOWARN;
> +	if (size > PAGE_SIZE) {
> +		kmalloc_flags |= __GFP_NOWARN;
> +
> +		if (!(kmalloc_flags & __GFP_REPEAT) ||
> +				(size <= PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
> +			kmalloc_flags |= __GFP_NORETRY;

I think this would be more understandable for me if it was written in
the opposite way, i.e. "if we have costly __GFP_REPEAT allocation, don't
use __GFP_NORETRY", but nevermind, seems correct to me wrt current
handling of both flags in the page allocator. And it serves as a good
argument to have this wrapper in mm/ as we are hopefully more likely to
keep it working as intended with future changes, than all the opencoded
variants.

Acked-by: Vlastimil Babka <vbabka@suse.cz>

> +	}
>  
>  	ret = kmalloc_node(size, kmalloc_flags, node);
>  
> 

--
To unsubscribe from this list: send the line "unsubscribe linux-security-module" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Michal Hocko Jan. 6, 2017, 12:31 p.m. UTC | #2
On Fri 06-01-17 13:09:36, Vlastimil Babka wrote:
> On 01/04/2017 07:12 PM, Michal Hocko wrote:
[...]
> > diff --git a/mm/util.c b/mm/util.c
> > index 8e4ea6cbe379..a2bfb85e60e5 100644
> > --- a/mm/util.c
> > +++ b/mm/util.c
> > @@ -348,8 +348,13 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node)
> >  	 * Make sure that larger requests are not too disruptive - no OOM
> >  	 * killer and no allocation failure warnings as we have a fallback
> >  	 */
> > -	if (size > PAGE_SIZE)
> > -		kmalloc_flags |= __GFP_NORETRY | __GFP_NOWARN;
> > +	if (size > PAGE_SIZE) {
> > +		kmalloc_flags |= __GFP_NOWARN;
> > +
> > +		if (!(kmalloc_flags & __GFP_REPEAT) ||
> > +				(size <= PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
> > +			kmalloc_flags |= __GFP_NORETRY;
> 
> I think this would be more understandable for me if it was written in
> the opposite way, i.e. "if we have costly __GFP_REPEAT allocation, don't
> use __GFP_NORETRY",

Dunno, doesn't look much simpler to me
		kmalloc_flags |= __GFP_NORETRY;
		if ((kmalloc_flags & __GFP_REPEAT) &&
				(size > PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
			kmalloc_flags &= ~__GFP_NORETRY;
		}

> but nevermind, seems correct to me wrt current
> handling of both flags in the page allocator. And it serves as a good
> argument to have this wrapper in mm/ as we are hopefully more likely to
> keep it working as intended with future changes, than all the opencoded
> variants.
> 
> Acked-by: Vlastimil Babka <vbabka@suse.cz>

Thanks!
Michal Hocko Jan. 9, 2017, 8:50 a.m. UTC | #3
On Fri 06-01-17 13:09:36, Vlastimil Babka wrote:
> On 01/04/2017 07:12 PM, Michal Hocko wrote:
> > While checking opencoded users I've encountered that vhost code would
> > really like to use kvmalloc with __GFP_REPEAT [1] so the following patch
> > adds support for __GFP_REPEAT and converts both vhost users.
> > 
> > So currently I am sitting on 3 patches. I will wait for more feedback -
> > especially about potential split ups or cleanups few more days and then
> > repost the whole series.
> > 
> > [1] http://lkml.kernel.org/r/20170104150800.GO25453@dhcp22.suse.cz
> > ---
> > From 0b92e4d2e040524b878d4e7b9ee88fbad5284b33 Mon Sep 17 00:00:00 2001
> > From: Michal Hocko <mhocko@suse.com>
> > Date: Wed, 4 Jan 2017 18:01:39 +0100
> > Subject: [PATCH] mm: support __GFP_REPEAT in kvmalloc_node
> > 
> > vhost code uses __GFP_REPEAT when allocating vhost_virtqueue resp.
> > vhost_vsock because it would really like to prefer kmalloc to the
> > vmalloc fallback - see 23cc5a991c7a ("vhost-net: extend device
> > allocation to vmalloc") for more context. Michael Tsirkin has also
> > noted:
> > "
> > __GFP_REPEAT overhead is during allocation time.  Using vmalloc means all
> > accesses are slowed down.  Allocation is not on data path, accesses are.
> > "
> > 
> > Let's teach kvmalloc_node to handle __GFP_REPEAT properly. There are two
> > things to be careful about. First we should prevent from the OOM killer
> > and so have to involve __GFP_NORETRY by default and secondly override
> > __GFP_REPEAT for !costly order requests as the __GFP_REPEAT is ignored
> > for !costly orders.
> > 
> > This patch shouldn't introduce any functional change.
> 
> Which is because the converted usages are always used for costly order,
> right.

I have overlooked this remark previously. You are right. And I've
updated the documentation and also the inline comment to be more
explicit about this. We do not have a good way to support __GFP_REPEAT
for !costly orders currently unfortunatelly. Maybe I should revive my
__GFP_RETRY_MAYFAIL patch, this would be another user (outside of xfs
which already wants something like that for KM_MAYFAIL.

Patch
diff mbox

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 5dc34653274a..105cd04c7414 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -797,12 +797,9 @@  static int vhost_net_open(struct inode *inode, struct file *f)
 	struct vhost_virtqueue **vqs;
 	int i;
 
-	n = kmalloc(sizeof *n, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
-	if (!n) {
-		n = vmalloc(sizeof *n);
-		if (!n)
-			return -ENOMEM;
-	}
+	n = kvmalloc(sizeof *n, GFP_KERNEL | __GFP_REPEAT);
+	if (!n)
+		return -ENOMEM;
 	vqs = kmalloc(VHOST_NET_VQ_MAX * sizeof(*vqs), GFP_KERNEL);
 	if (!vqs) {
 		kvfree(n);
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index bbbf588540ed..7e0159867553 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -455,12 +455,9 @@  static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
 	/* This struct is large and allocation could fail, fall back to vmalloc
 	 * if there is no other way.
 	 */
-	vsock = kzalloc(sizeof(*vsock), GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
-	if (!vsock) {
-		vsock = vmalloc(sizeof(*vsock));
-		if (!vsock)
-			return -ENOMEM;
-	}
+	vsock = kvmalloc(sizeof(*vsock), GFP_KERNEL | __GFP_REPEAT);
+	if (!vsock)
+		return -ENOMEM;
 
 	vqs = kmalloc_array(ARRAY_SIZE(vsock->vqs), sizeof(*vqs), GFP_KERNEL);
 	if (!vqs) {
diff --git a/mm/util.c b/mm/util.c
index 8e4ea6cbe379..a2bfb85e60e5 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -348,8 +348,13 @@  void *kvmalloc_node(size_t size, gfp_t flags, int node)
 	 * Make sure that larger requests are not too disruptive - no OOM
 	 * killer and no allocation failure warnings as we have a fallback
 	 */
-	if (size > PAGE_SIZE)
-		kmalloc_flags |= __GFP_NORETRY | __GFP_NOWARN;
+	if (size > PAGE_SIZE) {
+		kmalloc_flags |= __GFP_NOWARN;
+
+		if (!(kmalloc_flags & __GFP_REPEAT) ||
+				(size <= PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
+			kmalloc_flags |= __GFP_NORETRY;
+	}
 
 	ret = kmalloc_node(size, kmalloc_flags, node);