PCI: hv: Use effective affinity mask

The effective_affinity_mask is always set when an interrupt is assigned in
__assign_irq_vector() -> apic->cpu_mask_to_apicid(), e.g. for struct apic
apic_physflat: -> default_cpu_mask_to_apicid() ->
irq_data_update_effective_affinity(), but it looks d->common->affinity
remains all-1's before the user space or the kernel changes it later.

In the early allocation/initialization phase of an IRQ, we should use the
effective_affinity_mask, otherwise Hyper-V may not deliver the interrupt to
the expected CPU.  Without the patch, if we assign 7 Mellanox ConnectX-3
VFs to a 32-vCPU VM, one of the VFs may fail to receive interrupts.

Tested-by: Adrian Suhov <v-adsuho@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jake Oshins <jakeo@microsoft.com>
Cc: stable@vger.kernel.org
Cc: Jork Loeser <jloeser@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>

diff --git a/drivers/pci/host/pci-hyperv.c b/drivers/pci/host/pci-hyperv.c
index 0fe3ea164ee53321b2a23aded63eeac6c68684fa..04dac6a42c9f287519379757a0cefd3c08e14e11 100644 (file)
--- a/drivers/pci/host/pci-hyperv.c
+++ b/drivers/pci/host/pci-hyperv.c
@@ -879,7 +879,7 @@ static void hv_irq_unmask(struct irq_data *data)
        int cpu;
        u64 res;
 
-       dest = irq_data_get_affinity_mask(data);
+       dest = irq_data_get_effective_affinity_mask(data);
        pdev = msi_desc_to_pci_dev(msi_desc);
        pbus = pdev->bus;
        hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
@@ -1042,6 +1042,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
        struct hv_pci_dev *hpdev;
        struct pci_bus *pbus;
        struct pci_dev *pdev;
+       struct cpumask *dest;
        struct compose_comp_ctxt comp;
        struct tran_int_desc *int_desc;
        struct {
@@ -1056,6 +1057,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
        int ret;
 
        pdev = msi_desc_to_pci_dev(irq_data_get_msi_desc(data));
+       dest = irq_data_get_effective_affinity_mask(data);
        pbus = pdev->bus;
        hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
        hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn));
@@ -1081,14 +1083,14 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
        switch (pci_protocol_version) {
        case PCI_PROTOCOL_VERSION_1_1:
                size = hv_compose_msi_req_v1(&ctxt.int_pkts.v1,
-                                       irq_data_get_affinity_mask(data),
+                                       dest,
                                        hpdev->desc.win_slot.slot,
                                        cfg->vector);
                break;
 
        case PCI_PROTOCOL_VERSION_1_2:
                size = hv_compose_msi_req_v2(&ctxt.int_pkts.v2,
-                                       irq_data_get_affinity_mask(data),
+                                       dest,
                                        hpdev->desc.win_slot.slot,
                                        cfg->vector);
                break;