| Message ID | 924d05fe41fb93fdc2013680fb220d4b171de303.1368431413.git.agordeev@redhat.com |
|---|---|
| State | Accepted |
| Headers | show |
On Mon, May 13, 2013 at 11:06:17AM +0200, Alexander Gordeev wrote: > Current multiple-MSI implementation does not take into account > actual number of requested MSIs and always rounds that number > to a closest power-of-two value. Yet, a number of MSIs a PCI > device could send (and therefore a number of messages a device > driver could request) may be a lesser power-of-two. As result, > resources allocated for extra MSIs just wasted. > > This update takes advantage of 'msi_desc::nvec' field introduced > with generic MSI code to track number of requested and used MSIs. > As result, resources associated with interrupts are conserved. > Of those resources most noticeable are x86 interrupt vectors. > > The initial version of this fix also consumed on IRTEs, but Jan > noticed that a malfunctioning PCI device might send a message > number it did not claim and thus refer an IRTE it does not own. > To avoid this security hole the old-way approach preserved and > as many IRTEs are reserved as the device could possibly send. > > Signed-off-by: Alexander Gordeev <agordeev@redhat.com> This does not look all that bad. Sebastian -- To unsubscribe from this list: send the line "unsubscribe linux-pci" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c index d56f8c1..9eeb6cf 100644 --- a/drivers/iommu/irq_remapping.c +++ b/drivers/iommu/irq_remapping.c @@ -51,26 +51,27 @@ static void irq_remapping_disable_io_apic(void) static int do_setup_msi_irqs(struct pci_dev *dev, int nvec) { - int node, ret, sub_handle, index = 0; + int node, ret, sub_handle, nvec_pow2, index = 0; unsigned int irq; struct msi_desc *msidesc; - nvec = __roundup_pow_of_two(nvec); - WARN_ON(!list_is_singular(&dev->msi_list)); msidesc = list_entry(dev->msi_list.next, struct msi_desc, list); WARN_ON(msidesc->irq); WARN_ON(msidesc->msi_attrib.multiple); + WARN_ON(msidesc->nvec); node = dev_to_node(&dev->dev); irq = __create_irqs(get_nr_irqs_gsi(), nvec, node); if (irq == 0) return -ENOSPC; - msidesc->msi_attrib.multiple = ilog2(nvec); + nvec_pow2 = __roundup_pow_of_two(nvec); + msidesc->nvec = nvec; + msidesc->msi_attrib.multiple = ilog2(nvec_pow2); for (sub_handle = 0; sub_handle < nvec; sub_handle++) { if (!sub_handle) { - index = msi_alloc_remapped_irq(dev, irq, nvec); + index = msi_alloc_remapped_irq(dev, irq, nvec_pow2); if (index < 0) { ret = index; goto error; @@ -95,6 +96,7 @@ error: * IRQs from tearing down again in default_teardown_msi_irqs() */ msidesc->irq = 0; + msidesc->nvec = 0; msidesc->msi_attrib.multiple = 0; return ret;
Current multiple-MSI implementation does not take into account actual number of requested MSIs and always rounds that number to a closest power-of-two value. Yet, a number of MSIs a PCI device could send (and therefore a number of messages a device driver could request) may be a lesser power-of-two. As result, resources allocated for extra MSIs just wasted. This update takes advantage of 'msi_desc::nvec' field introduced with generic MSI code to track number of requested and used MSIs. As result, resources associated with interrupts are conserved. Of those resources most noticeable are x86 interrupt vectors. The initial version of this fix also consumed on IRTEs, but Jan noticed that a malfunctioning PCI device might send a message number it did not claim and thus refer an IRTE it does not own. To avoid this security hole the old-way approach preserved and as many IRTEs are reserved as the device could possibly send. Signed-off-by: Alexander Gordeev <agordeev@redhat.com> --- drivers/iommu/irq_remapping.c | 12 +++++++----- 1 files changed, 7 insertions(+), 5 deletions(-)