| Message ID | 4DC6E8F3.3050307@gmail.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
> From: Cyrill Gorcunov <gorcunov@gmail.com> > Subject: [PATCH] kvm tools: PCI -- Make PCI device numbers being unique v2 > > PCI device numbers must be unique on a bus (as a part > of Bus/Device/Function tuple).Make it so. Note the patch > is rather a fast fix since we need a bit more smart pci device > manager (in particular multiple virtio block devices most > probably should lay on a separate pci bus). > > v2: Sasha spotted the nit in virtio_rng__init, ioport > function was touched insted of irq__register_device. Hey, I don't like the new patch subject trend you're trying to start at all. You can make it kvm tools,pci: Make PCI device numbers unique but in this particular case "PCI" already appears in the title so kmv tools: Make PCI device numbers unique is the right thing to do. In addition, the changelog doesn't really tell me much. Does it fix something? Why would we need a "smart pci device manager" and why is that relevant for this patch? Hmmh? Pekka -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On 05/09/2011 11:53 PM, Pekka Enberg wrote: >> From: Cyrill Gorcunov <gorcunov@gmail.com> >> Subject: [PATCH] kvm tools: PCI -- Make PCI device numbers being unique v2 >> >> PCI device numbers must be unique on a bus (as a part >> of Bus/Device/Function tuple).Make it so. Note the patch >> is rather a fast fix since we need a bit more smart pci device >> manager (in particular multiple virtio block devices most >> probably should lay on a separate pci bus). >> >> v2: Sasha spotted the nit in virtio_rng__init, ioport >> function was touched insted of irq__register_device. > > Hey, I don't like the new patch subject trend you're trying to start at all. You can make it > > kvm tools,pci: Make PCI device numbers unique > > but in this particular case "PCI" already appears in the title so > > kmv tools: Make PCI device numbers unique > > is the right thing to do. PCI stands for kvm tools subsystem, but if you like more the last -- I'm fine with it. > > In addition, the changelog doesn't really tell me much. Does it fix something? > Why would we need a "smart pci device manager" and why is that relevant for this > patch? Hmmh? > > Pekka The thing is that at moment the id's passed to MP table is incorrect, they are to be 5 bits long (mp spec). The smart manager we need -- it's because there could be multiple virtio block device and they _are_ to be separated pci devices, ie with own numbers and intx# assignents. As result we probably should have such virtio devices to lay on a separate pci bus, or if the number of pci devices exceed the width of address line then we should pass them to another pci bus. That is what I had in mind but I'm not sure all this should come to the changelog.
Index: linux-2.6.git/tools/kvm/include/kvm/virtio-pci-dev.h ===================================================================== --- linux-2.6.git.orig/tools/kvm/include/kvm/virtio-pci-dev.h +++ linux-2.6.git/tools/kvm/include/kvm/virtio-pci-dev.h @@ -16,4 +16,9 @@ #define PCI_SUBSYSTEM_ID_VIRTIO_CONSOLE 0x0003 #define PCI_SUBSYSTEM_ID_VIRTIO_RNG 0x0004 +#define PCI_DEVICE_VIRTIO_NET 0x2 +#define PCI_DEVICE_VIRTIO_BLK 0x1 +#define PCI_DEVICE_VIRTIO_CONSOLE 0x3 +#define PCI_DEVICE_VIRTIO_RNG 0x4 + #endif /* VIRTIO_PCI_DEV_H_ */ Index: linux-2.6.git/tools/kvm/virtio/blk.c ===================================================================== --- linux-2.6.git.orig/tools/kvm/virtio/blk.c +++ linux-2.6.git/tools/kvm/virtio/blk.c @@ -295,7 +295,7 @@ void virtio_blk__init(struct kvm *self, }, }; - if (irq__register_device(PCI_DEVICE_ID_VIRTIO_BLK, &dev, &pin, &line) < 0) + if (irq__register_device(PCI_DEVICE_VIRTIO_BLK, &dev, &pin, &line) < 0) return; bdev->pci_hdr.irq_pin = pin; Index: linux-2.6.git/tools/kvm/virtio/console.c ===================================================================== --- linux-2.6.git.orig/tools/kvm/virtio/console.c +++ linux-2.6.git/tools/kvm/virtio/console.c @@ -238,7 +238,7 @@ void virtio_console__init(struct kvm *se { u8 dev, line, pin; - if (irq__register_device(PCI_DEVICE_ID_VIRTIO_CONSOLE, &dev, &pin, &line) < 0) + if (irq__register_device(PCI_DEVICE_VIRTIO_CONSOLE, &dev, &pin, &line) < 0) return; virtio_console_pci_device.irq_pin = pin; Index: linux-2.6.git/tools/kvm/virtio/net.c ===================================================================== --- linux-2.6.git.orig/tools/kvm/virtio/net.c +++ linux-2.6.git/tools/kvm/virtio/net.c @@ -385,7 +385,7 @@ void virtio_net__init(const struct virti if (virtio_net__tap_init(params)) { u8 dev, line, pin; - if (irq__register_device(PCI_DEVICE_ID_VIRTIO_NET, &dev, &pin, &line) < 0) + if (irq__register_device(PCI_DEVICE_VIRTIO_NET, &dev, &pin, &line) < 0) return; virtio_net_pci_device.irq_pin = pin; Index: linux-2.6.git/tools/kvm/virtio/rng.c ===================================================================== --- linux-2.6.git.orig/tools/kvm/virtio/rng.c +++ linux-2.6.git/tools/kvm/virtio/rng.c @@ -171,7 +171,7 @@ void virtio_rng__init(struct kvm *kvm) if (rdev.fd < 0) die("Failed initializing RNG"); - if (irq__register_device(PCI_DEVICE_ID_VIRTIO_RNG, &dev, &pin, &line) < 0) + if (irq__register_device(PCI_DEVICE_VIRTIO_RNG, &dev, &pin, &line) < 0) return; virtio_rng_pci_device.irq_pin = pin;