[PATCH net-next 0/8] xen-netback/core: packet hashing

[PATCH net-next 0/8] xen-netback/core: packet hashing

[Paul Durrant]

This series adds xen-netback support for hash negotiation with a frontend
driver, and an implementation of toeplitz hashing as the initial negotiable
algorithm.

Patch #1 re-imports the canonical netif header from Xen, which contains
the necessary definitions and a type required by subsequent patches.
(Note that this patch is not completely style-clean since the header
includes typedefs).

Patch #2 is some cleanup in xen-netback.

Patch #3 adds code to allow multiple extra_info segments to be passed from a
frontend to xen-netback.

Patch #4 adds code to allow xen-netback to accept new hash extra_info
segments from a frontend and set the skb hash information appropriately. 

Patch #5 makes a change to struct sk_buff: one extra bit is used to allow
full hash type information to be stored, rather than just the l4_hash
boolean value.

Patch #6 adds code to xen-netback to pass L3 or L4 skb hash values to
capable frontends.

Patch #7 adds code to xen-netback to provide a configurable (by the
frontend) mapping from hash values to queue numbers.

Patch #8 adds code to xen-netback to provide toeplitz hashing of skbs.

Re: [PATCH net-next 0/8] xen-netback/core: packet hashing

[David Miller]

From: David Vrabel <david.vrabel@citrix.com>
Date: Mon, 26 Oct 2015 10:38:50 +0000

> On 24/10/15 12:55, David Miller wrote:
>> From: Paul Durrant <paul.durrant@citrix.com>
>> Date: Wed, 21 Oct 2015 11:36:17 +0100
>> 
>>> This series adds xen-netback support for hash negotiation with a frontend
>>> driver, and an implementation of toeplitz hashing as the initial negotiable
>>> algorithm.
>> 
>> Ping, I want to see some review from some other xen networking folks.
> 
> There's been some review of the front/back protocol (on a different
> thread) and some significant changes have been suggested.

Ok, I'll mark this series as "changes requested" then, thanks.

Re: [PATCH net-next 0/8] xen-netback/core: packet hashing

[David Vrabel]

On 24/10/15 12:55, David Miller wrote:
> From: Paul Durrant <paul.durrant@citrix.com>
> Date: Wed, 21 Oct 2015 11:36:17 +0100
> 
>> This series adds xen-netback support for hash negotiation with a frontend
>> driver, and an implementation of toeplitz hashing as the initial negotiable
>> algorithm.
> 
> Ping, I want to see some review from some other xen networking folks.

There's been some review of the front/back protocol (on a different
thread) and some significant changes have been suggested.

David

Re: [PATCH net-next 0/8] xen-netback/core: packet hashing

[David Miller]

From: Paul Durrant <paul.durrant@citrix.com>
Date: Wed, 21 Oct 2015 11:36:17 +0100

> This series adds xen-netback support for hash negotiation with a frontend
> driver, and an implementation of toeplitz hashing as the initial negotiable
> algorithm.

Ping, I want to see some review from some other xen networking folks.

Thanks.

Re: [PATCH net-next 0/8] xen-netback/core: packet hashing

[David Miller]

From: Paul Durrant <paul.durrant@citrix.com>
Date: Wed, 21 Oct 2015 11:36:17 +0100

> This series adds xen-netback support for hash negotiation with a frontend
> driver, and an implementation of toeplitz hashing as the initial negotiable
> algorithm.

Ping, I want to see some review from some other xen networking folks.

Thanks.

Re: [PATCH net-next 0/8] xen-netback/core: packet hashing

[David Miller]

From: Paul Durrant <paul.durrant@citrix.com>
Date: Wed, 21 Oct 2015 11:36:17 +0100

> This series adds xen-netback support for hash negotiation with a frontend
> driver, and an implementation of toeplitz hashing as the initial negotiable
> algorithm.

I'd definitely like to see some XEN networking experts review this
before I apply it.

Re: [PATCH net-next 0/8] xen-netback/core: packet hashing

[David Miller]

From: Paul Durrant <paul.durrant@citrix.com>
Date: Wed, 21 Oct 2015 11:36:17 +0100

> This series adds xen-netback support for hash negotiation with a frontend
> driver, and an implementation of toeplitz hashing as the initial negotiable
> algorithm.

I'd definitely like to see some XEN networking experts review this
before I apply it.

[PATCH net-next 0/8] xen-netback/core: packet hashing

[Paul Durrant]

This series adds xen-netback support for hash negotiation with a frontend
driver, and an implementation of toeplitz hashing as the initial negotiable
algorithm.

Patch #1 re-imports the canonical netif header from Xen, which contains
the necessary definitions and a type required by subsequent patches.
(Note that this patch is not completely style-clean since the header
includes typedefs).

Patch #2 is some cleanup in xen-netback.

Patch #3 adds code to allow multiple extra_info segments to be passed from a
frontend to xen-netback.

Patch #4 adds code to allow xen-netback to accept new hash extra_info
segments from a frontend and set the skb hash information appropriately. 

Patch #5 makes a change to struct sk_buff: one extra bit is used to allow
full hash type information to be stored, rather than just the l4_hash
boolean value.

Patch #6 adds code to xen-netback to pass L3 or L4 skb hash values to
capable frontends.

Patch #7 adds code to xen-netback to provide a configurable (by the
frontend) mapping from hash values to queue numbers.

Patch #8 adds code to xen-netback to provide toeplitz hashing of skbs.