x86: properly handle MSI-X unmask operation from guests

For a pass-through device with MSI-x capability, when guest tries
to unmask the MSI-x interrupt for the passed through device, xen
doesn't clear the mask bit for MSI-x in hardware in the following
scenario, which will cause network disconnection:

1. Guest masks the MSI-x interrupt
2. Guest updates the address and data for it
3. Guest unmasks the MSI-x interrupt (This is the problematic step)

In the step #3 above, Xen doesn't handle it well. When guest tries
to unmask MSI-X interrupt, it traps to Xen, Xen just returns to Qemu
if it notices that address or data has been modified by guest before,
then Qemu will update Xen with the latest value of address/data by
hypercall. However, in this whole process, the MSI-X interrupt unmask
operation is missing, which means Xen doesn't clear the mask bit in
hardware for the MSI-X interrupt, so it remains disabled, that is why
it loses the network connection.

This patch fixes this issue.

Signed-off-by: Feng Wu <feng.wu@intel.com>
Only latch the address if the guest really is unmasking the entry.

Clean up the entire change.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>

diff --git a/xen/arch/x86/hvm/io.c b/xen/arch/x86/hvm/io.c
index 15e0b4c0ae0545e4b3ce6fe2c3776fcdb298d2de..bf6309de266d23b8c3544d756d3b487387b1ecef 100644 (file)
--- a/xen/arch/x86/hvm/io.c
+++ b/xen/arch/x86/hvm/io.c
@@ -300,7 +300,10 @@ void hvm_io_assist(ioreq_t *p)
     }
 
     if ( p->state == STATE_IOREQ_NONE )
+    {
+        msix_write_completion(curr);
         vcpu_end_shutdown_deferral(curr);
+    }
 }
 
 static int dpci_ioport_read(uint32_t mport, ioreq_t *p)

diff --git a/xen/arch/x86/hvm/vmsi.c b/xen/arch/x86/hvm/vmsi.c
index 4826b4ad77eca59027e1a112454b97d7791a0b69..10e5f34954d5d1569e897614cbddfd54cfc4df4e 100644 (file)
--- a/xen/arch/x86/hvm/vmsi.c
+++ b/xen/arch/x86/hvm/vmsi.c
@@ -293,7 +293,11 @@ static int msixtbl_write(struct vcpu *v, unsigned long address,
 
     /* exit to device model if address/data has been modified */
     if ( test_and_clear_bit(nr_entry, &entry->table_flags) )
+    {
+        if ( !(val & PCI_MSIX_VECTOR_BITMASK) )
+            v->arch.hvm_vcpu.hvm_io.msix_unmask_address = address;
         goto out;
+    }
 
     virt = msixtbl_addr_to_virt(entry, address);
     if ( !virt )
@@ -528,3 +532,15 @@ void msixtbl_pt_cleanup(struct domain *d)
     spin_unlock(&d->arch.hvm_domain.msixtbl_list_lock);
     local_irq_restore(flags);
 }
+
+void msix_write_completion(struct vcpu *v)
+{
+    unsigned long ctrl_address = v->arch.hvm_vcpu.hvm_io.msix_unmask_address;
+
+    if ( !ctrl_address )
+        return;
+
+    v->arch.hvm_vcpu.hvm_io.msix_unmask_address = 0;
+    if ( msixtbl_write(v, ctrl_address, 4, 0) != X86EMUL_OKAY )
+        gdprintk(XENLOG_WARNING, "MSI-X write completion failure\n");
+}

diff --git a/xen/include/asm-x86/hvm/io.h b/xen/include/asm-x86/hvm/io.h
index 6f4cb9640819608be1363056c328ed307e283b8d..86db58de0a3778a7c45ac4de83bb09b297c0f98e 100644 (file)
--- a/xen/include/asm-x86/hvm/io.h
+++ b/xen/include/asm-x86/hvm/io.h
@@ -124,6 +124,7 @@ void hvm_interrupt_post(struct vcpu *v, int vector, int type);
 void hvm_io_assist(ioreq_t *p);
 void hvm_dpci_eoi(struct domain *d, unsigned int guest_irq,
                   union vioapic_redir_entry *ent);
+void msix_write_completion(struct vcpu *);
 
 struct hvm_hw_stdvga {
     uint8_t sr_index;

diff --git a/xen/include/asm-x86/hvm/vcpu.h b/xen/include/asm-x86/hvm/vcpu.h
index a309389187f2133bb4e90e9086d05b5c50f0032f..4f45060e7f63040a8bb9bd367f0470a04f6856b1 100644 (file)
--- a/xen/include/asm-x86/hvm/vcpu.h
+++ b/xen/include/asm-x86/hvm/vcpu.h
@@ -74,6 +74,8 @@ struct hvm_vcpu_io {
      * necessary retry through other than function return codes.
      */
     bool_t mmio_retry, mmio_retrying;
+
+    unsigned long msix_unmask_address;
 };
 
 #define VMCX_EADDR    (~0ULL)