When a Linux VM runs on Hyper-V, if the VM has CPUs with >255 APIC IDs,
the CPUs can't be the destination of IOAPIC interrupts, because the
IOAPIC RTE's Dest Field has only 8 bits. Currently the hackery driver
drivers/iommu/hyperv-iommu.c is used to ensure IOAPIC interrupts are
only routed to CPUs that don't have >255 APIC IDs. However, there is
an issue with kdump, because the kdump kernel can run on any CPU, and
hence IOAPIC interrupts can't work if the kdump kernel run on a CPU
with a >255 APIC ID.
The kdump issue can be fixed by the Extended Dest ID, which is introduced
recently by David Woodhouse (for IOAPIC, see the field virt_destid_8_14 in
struct IO_APIC_route_entry). Of course, the Extended Dest ID needs the
support of the underlying hypervisor. The latest Hyper-V has added the
support recently: with this commit, on such a Hyper-V host, Linux VM
does not use hyperv-iommu.c because hyperv_prepare_irq_remapping()
returns -ENODEV; instead, Linux kernel's generic support of Extended Dest
ID from David is used, meaning that Linux VM is able to support up to
32K CPUs, and IOAPIC interrupts can be routed to all the CPUs.
On an old Hyper-V host that doesn't support the Extended Dest ID, nothing
changes with this commit: Linux VM is still able to bring up the CPUs with
>255 APIC IDs with the help of hyperv-iommu.c, but IOAPIC interrupts still
can not go to such CPUs, and the kdump kernel still can not work properly
on such CPUs.
Signed-off-by: Dexuan Cui <decui@xxxxxxxxxxxxx>
---
arch/x86/include/asm/hyperv-tlfs.h | 7 +++++++
arch/x86/kernel/cpu/mshyperv.c | 30 ++++++++++++++++++++++++++++++
2 files changed, 37 insertions(+)
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 0ed20e8bba9e..6bf42aed387e 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -23,6 +23,13 @@
#define HYPERV_CPUID_IMPLEMENT_LIMITS 0x40000005
#define HYPERV_CPUID_NESTED_FEATURES 0x4000000A
+#define HYPERV_CPUID_VIRT_STACK_INTERFACE 0x40000081
+#define HYPERV_VS_INTERFACE_EAX_SIGNATURE 0x31235356 /* "VS#1" */
+
+#define HYPERV_CPUID_VIRT_STACK_PROPERTIES 0x40000082
+/* Support for the extended IOAPIC RTE format */
+#define HYPERV_VS_PROPERTIES_EAX_EXTENDED_IOAPIC_RTE BIT(2)
+
#define HYPERV_HYPERVISOR_PRESENT_BIT 0x80000000
#define HYPERV_CPUID_MIN 0x40000005
#define HYPERV_CPUID_MAX 0x4000ffff
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 05ef1f4550cb..cc4037d841df 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -366,9 +366,39 @@ static void __init ms_hyperv_init_platform(void)
#endif
}
+static bool __init ms_hyperv_x2apic_available(void)
+{
+ return x2apic_supported();
+}
+
+/*
+ * If ms_hyperv_msi_ext_dest_id() returns true, hyperv_prepare_irq_remapping()
+ * returns -ENODEV and the Hyper-V IOMMU driver is not used; instead, the
+ * generic support of the 15-bit APIC ID is used: see __irq_msi_compose_msg().
+ *
+ * Note: For a VM on Hyper-V, no emulated legacy device supports PCI MSI/MSI-X,
+ * and PCI MSI/MSI-X only come from the assigned physical PCIe device, and the
+ * PCI MSI/MSI-X interrupts are handled by the pci-hyperv driver. Here despite
+ * the word "msi" in the name "msi_ext_dest_id", actually the callback only
+ * affects how IOAPIC interrupts are routed.
+ */
+static bool __init ms_hyperv_msi_ext_dest_id(void)
+{
+ u32 eax;
+
+ eax = cpuid_eax(HYPERV_CPUID_VIRT_STACK_INTERFACE);
+ if (eax != HYPERV_VS_INTERFACE_EAX_SIGNATURE)
+ return false;
+
+ eax = cpuid_eax(HYPERV_CPUID_VIRT_STACK_PROPERTIES);
+ return eax & HYPERV_VS_PROPERTIES_EAX_EXTENDED_IOAPIC_RTE;
+}
+
const __initconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
.name = "Microsoft Hyper-V",
.detect = ms_hyperv_platform,
.type = X86_HYPER_MS_HYPERV,
+ .init.x2apic_available = ms_hyperv_x2apic_available,
+ .init.msi_ext_dest_id = ms_hyperv_msi_ext_dest_id,
.init.init_platform = ms_hyperv_init_platform,
};
--
2.25.1
