From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ian Campbell Subject: Re: [PATCH v6 4/6] xen/arm: vgic: Optimize the way to store the target vCPU in the rank Date: Wed, 25 Nov 2015 11:37:42 +0000 Message-ID: <1448451462.17688.73.camel@citrix.com> References: <1447864963-21577-1-git-send-email-julien.grall@citrix.com> <1447864963-21577-5-git-send-email-julien.grall@citrix.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Received: from mail6.bemta3.messagelabs.com ([195.245.230.39]) by lists.xen.org with esmtp (Exim 4.72) (envelope-from ) id 1a1YP2-0003YY-Rr for xen-devel@lists.xenproject.org; Wed, 25 Nov 2015 11:38:24 +0000 In-Reply-To: <1447864963-21577-5-git-send-email-julien.grall@citrix.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Julien Grall , xen-devel@lists.xenproject.org Cc: stefano.stabellini@eu.citrix.com List-Id: xen-devel@lists.xenproject.org On Wed, 2015-11-18 at 16:42 +0000, Julien Grall wrote: > Xen is currently directly storing the value of GICD_ITARGETSR register > (for GICv2) and GICD_IROUTER (for GICv3) in the rank. This makes the > emulation of the registers access very simple but makes the code to get > the target vCPU for a given vIRQ more complex. > > While the target vCPU of an vIRQ is retrieved every time an vIRQ is > injected to the guest, the access to the register occurs less often. > > So the data structure should be optimized for the most common case > rather than the inverse. > > This patch introduces the usage of an array to store the target vCPU for > every interrupt in the rank. This will make the code to get the target > very quick. The emulation code will now have to generate the > GICD_ITARGETSR > and GICD_IROUTER register for read access and split it to store in a > convenient way. > > With the new way to store the target vCPU, the structure vgic_irq_rank > is shrunk down from 320 bytes to 92 bytes. This is saving about 228 > bytes of memory allocated separately per vCPU. > > Note that with these changes, any read to those register will list only > the target vCPU used by Xen. As the spec is not clear whether this is a > valid choice or not, OSes which have a different interpretation of the > spec (i.e OSes which perform read-modify-write operations on these > registers) may not boot anymore on Xen. Although, I think this is fair > trade between memory usage in Xen (1KB less on a domain using 4 vCPUs > with no SPIs) and a strict interpretation of the spec (though all the > cases are not clearly defined). > > Furthermore, the implementation of the callback get_target_vcpu is now > exactly the same. Consolidate the implementation in the common vGIC code > and drop the callback. > > Finally take the opportunity to fix coding style and replace "irq" by > "virq" to make clear that we are dealing with virtual IRQ in section we > are modifying. > > Signed-off-by: Julien Grall Acked-by: Ian Campbell I have one clarifying question, which may or may not be worth a followup: > + * Fetch an ITARGETSR register based on the offset from ITARGETSR0. Is the offset here in terms of bytes or in terms of entire ITARGETSR registers (i.e. 4 bytes)? Might be worth clarifying the comment? Ian.