RE: [PATCH for-next 03/11] IB/hns: Optimize the logic of allocating memory using APIs

-----Original Message-----
From: netdev-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org [mailto:netdev-
owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org] On Behalf Of Leon Romanovsky
Sent: Monday, November 21, 2016 5:14 PM
To: Salil Mehta
Cc: dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org; Huwei (Xavier); oulijun;
mehta.salil.lnk-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org; linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org;
netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; Linuxarm;
Zhangping (ZP)
Subject: Re: [PATCH for-next 03/11] IB/hns: Optimize the logic of
allocating memory using APIs

On Mon, Nov 21, 2016 at 04:12:38PM +0000, Salil Mehta wrote:

quoted

quoted

-----Original Message-----
From: Leon Romanovsky [mailto:leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org]
Sent: Wednesday, November 16, 2016 8:36 AM
To: Salil Mehta
Cc: dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org; Huwei (Xavier); oulijun;
mehta.salil.lnk-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org; linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org;
netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; Linuxarm;
Zhangping (ZP)
Subject: Re: [PATCH for-next 03/11] IB/hns: Optimize the logic of
allocating memory using APIs

On Tue, Nov 15, 2016 at 03:52:46PM +0000, Salil Mehta wrote:

quoted

quoted

-----Original Message-----
From: Leon Romanovsky [mailto:leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org]
Sent: Wednesday, November 09, 2016 7:22 AM
To: Salil Mehta
Cc: dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org; Huwei (Xavier); oulijun;
mehta.salil.lnk-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org; linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org;
netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; Linuxarm;
Zhangping (ZP)
Subject: Re: [PATCH for-next 03/11] IB/hns: Optimize the logic

of

quoted

quoted

quoted

quoted

allocating memory using APIs

On Fri, Nov 04, 2016 at 04:36:25PM +0000, Salil Mehta wrote:

quoted

From: "Wei Hu (Xavier)" <redacted>

This patch modified the logic of allocating memory using APIs

in

quoted

quoted

quoted

quoted

quoted

hns RoCE driver. We used kcalloc instead of kmalloc_array and
bitmap_zero. And When kcalloc failed, call vzalloc to alloc
memory.

Signed-off-by: Wei Hu (Xavier) <redacted>
Signed-off-by: Ping Zhang <redacted>
Signed-off-by: Salil Mehta  <redacted>
---
 drivers/infiniband/hw/hns/hns_roce_mr.c |   15 ++++++++-----

--

quoted

quoted

quoted

quoted

quoted

 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c

b/drivers/infiniband/hw/hns/hns_roce_mr.c

quoted

index fb87883..d3dfb5f 100644

--- a/drivers/infiniband/hw/hns/hns_roce_mr.c
+++ b/drivers/infiniband/hw/hns/hns_roce_mr.c

@@ -137,11 +137,12 @@ static int hns_roce_buddy_init(struct

hns_roce_buddy *buddy, int max_order)

quoted

 	for (i = 0; i <= buddy->max_order; ++i) {
 		s = BITS_TO_LONGS(1 << (buddy->max_order - i));
-		buddy->bits[i] = kmalloc_array(s, sizeof(long),

GFP_KERNEL);

quoted

-		if (!buddy->bits[i])
-			goto err_out_free;
-
-		bitmap_zero(buddy->bits[i], 1 << (buddy->max_order -

i));

quoted

quoted

quoted

+		buddy->bits[i] = kcalloc(s, sizeof(long),

GFP_KERNEL);

quoted

quoted

quoted

+		if (!buddy->bits[i]) {
+			buddy->bits[i] = vzalloc(s * sizeof(long));

I wonder, why don't you use directly vzalloc instead of kcalloc
fallback?

As we know we will have physical contiguous pages if the kcalloc
call succeeds. This will give us a chance to have better

performance

quoted

quoted

quoted

over the allocations which are just virtually contiguous through

the

quoted

quoted

quoted

function vzalloc(). Therefore, later has only been used as a

fallback

quoted

quoted

quoted

when our memory request cannot be entertained through kcalloc.

Are you suggesting that there will not be much performance

penalty

quoted

quoted

quoted

if we use just vzalloc ?

Not exactly,
I asked it, because we have similar code in our drivers and this
construction looks strange to me.

1. If performance is critical, we will use kmalloc.
2. If performance is not critical, we will use vmalloc.

But in this case, such construction shows me that we can live with
vmalloc performance and kmalloc allocation are not really needed.

In your specific case, I'm not sure that kcalloc will ever fail.

Performance is definitely critical here. Though, I agree this is bit
unusual way of memory allocation. In actual, we were encountering
memory alloc failures using kmalloc (if you see allocation amount
is on the higher side and is exponential) so we ended up using
vmalloc as fall back - It is very naïve allocation scheme.

I understand it, we did the same, see our mlx5_vzalloc call.
BTW, we used __GFP_NOWARN flag, which you should consider to use
in your case too.

Ok. Will add this flag and refloat patch V3. 

Thanks

quoted

Maybe we need to rethink this allocation scheme part? Also, I can

pull

quoted

back this particular patch for now or just live with vzalloc() till
we figure out proper solution to this?

It is up to you, I don't think that you should drop it, AFAIK, there is
no other proper solution.

Ok we will live with it for now and later maybe we can see how we can optimize
pre-allocation of physically contiguous memory. 

Thanks for your suggestions!
Salil

quoted

quoted

Thanks

quoted

quoted

quoted

+			if (!buddy->bits[i])
+				goto err_out_free;
+		}
 	}

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html