From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:56683) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Ymvq5-0005vU-6a for qemu-devel@nongnu.org; Mon, 27 Apr 2015 23:05:38 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1Ymvq1-0007T4-Ve for qemu-devel@nongnu.org; Mon, 27 Apr 2015 23:05:37 -0400 Date: Tue, 28 Apr 2015 11:05:18 +0800 From: Jason Wang Message-Id: <1430190318.9163.0@smtp.corp.redhat.com> In-Reply-To: <20150423132447.67bdedf8.cornelia.huck@de.ibm.com> References: <1429770109-23873-1-git-send-email-jasowang@redhat.com> <1429770109-23873-16-git-send-email-jasowang@redhat.com> <20150423132447.67bdedf8.cornelia.huck@de.ibm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Subject: Re: [Qemu-devel] [PATCH V7 15/16] virtio-pci: increase the maximum number of virtqueues to 513 List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Cornelia Huck Cc: mst@redhat.com, Alexander Graf , qemu-devel@nongnu.org, qemu-ppc@nongnu.org, Paolo Bonzini , Richard Henderson On Thu, Apr 23, 2015 at 7:24 PM, Cornelia Huck wrote: > On Thu, 23 Apr 2015 14:21:48 +0800 > Jason Wang wrote: > >> This patch increases the maximum number of virtqueues for pci from >> 64 >> to 513. This will allow booting a virtio-net-pci device with 256 >> queue > ^^^ > >> pairs on recent Linux host (which supports up to 256 tuntap queue >> pairs). >> >> To keep migration compatibility, 64 was kept for legacy machine >> types. This is because qemu in fact allows guest to probe the limit >> of >> virtqueues through trying to set queue_sel. So for legacy machine >> type, we should make sure setting queue_sel to more than 63 won't >> make effect. >> >> Cc: Paolo Bonzini >> Cc: Richard Henderson >> Cc: Michael S. Tsirkin >> Cc: Alexander Graf >> Cc: qemu-ppc@nongnu.org >> Signed-off-by: Jason Wang >> --- >> hw/i386/pc_piix.c | 5 +++++ >> hw/i386/pc_q35.c | 5 +++++ >> hw/ppc/spapr.c | 5 +++++ >> hw/virtio/virtio-pci.c | 6 +++++- >> 4 files changed, 20 insertions(+), 1 deletion(-) >> > (...) >> diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c >> index 7d01500..c510cb7 100644 >> --- a/hw/virtio/virtio-pci.c >> +++ b/hw/virtio/virtio-pci.c >> @@ -42,7 +42,11 @@ >> * configuration space */ >> #define VIRTIO_PCI_CONFIG_SIZE(dev) >> VIRTIO_PCI_CONFIG_OFF(msix_enabled(dev)) >> >> -#define VIRTIO_PCI_QUEUE_MAX 64 >> +/* The number was chose to be greater than both the the number of >> max >> + * vcpus supported by host and the number of max tuntap queues >> support >> + * by host and also leave some spaces for future. >> + */ >> +#define VIRTIO_PCI_QUEUE_MAX 1024 > ^^^^ > > I think you need to fixup subject and patch description :) Yes, will fix this. Thanks > >> >> static void virtio_pci_bus_new(VirtioBusState *bus, size_t >> bus_size, >> VirtIOPCIProxy *dev); >