[Qemu-devel] [PATCH v5 3/4] virtio-pci: Don't use ioeventfd on old kernels

[Stefan Hajnoczi <stefanha@gmail.com>]

There used to be a limit of 6 KVM io bus devices inside the kernel.  On
such a kernel, don't use ioeventfd for virtqueue host notification since
the limit is reached too easily.  This ensures that existing vhost-net
setups (which always use ioeventfd) have ioeventfds available so they
can continue to work.

Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
---
 hw/virtio-pci.c |    4 ++++
 kvm-all.c       |   49 +++++++++++++++++++++++++++++++++++++++++++++++++
 kvm-stub.c      |    5 +++++
 kvm.h           |    1 +
 4 files changed, 59 insertions(+), 0 deletions(-)

diff --git a/hw/virtio-pci.c b/hw/virtio-pci.c
index f57c45a..db0df67 100644
--- a/hw/virtio-pci.c
+++ b/hw/virtio-pci.c
@@ -690,6 +690,10 @@ static void virtio_init_pci(VirtIOPCIProxy *proxy, VirtIODevice *vdev,
     pci_register_bar(&proxy->pci_dev, 0, size, PCI_BASE_ADDRESS_SPACE_IO,
                            virtio_map);
 
+    if (!kvm_has_many_ioeventfds()) {
+        proxy->flags &= ~VIRTIO_PCI_FLAG_USE_IOEVENTFD;
+    }
+
     virtio_bind_device(vdev, &virtio_pci_bindings, proxy);
     proxy->host_features |= 0x1 << VIRTIO_F_NOTIFY_ON_EMPTY;
     proxy->host_features |= 0x1 << VIRTIO_F_BAD_FEATURE;
diff --git a/kvm-all.c b/kvm-all.c
index cae24bb..255b6fa 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -28,6 +28,11 @@
 #include "kvm.h"
 #include "bswap.h"
 
+/* This check must be after config-host.h is included */
+#ifdef CONFIG_EVENTFD
+#include <sys/eventfd.h>
+#endif
+
 /* KVM uses PAGE_SIZE in it's definition of COALESCED_MMIO_MAX */
 #define PAGE_SIZE TARGET_PAGE_SIZE
 
@@ -72,6 +77,7 @@ struct KVMState
     int irqchip_in_kernel;
     int pit_in_kernel;
     int xsave, xcrs;
+    int many_ioeventfds;
 };
 
 static KVMState *kvm_state;
@@ -441,6 +447,39 @@ int kvm_check_extension(KVMState *s, unsigned int extension)
     return ret;
 }
 
+static int kvm_check_many_ioeventfds(void)
+{
+    /* Older kernels have a 6 device limit on the KVM io bus.  Find out so we
+     * can avoid creating too many ioeventfds.
+     */
+#ifdef CONFIG_EVENTFD
+    int ioeventfds[7];
+    int i, ret = 0;
+    for (i = 0; i < ARRAY_SIZE(ioeventfds); i++) {
+        ioeventfds[i] = eventfd(0, EFD_CLOEXEC);
+        if (ioeventfds[i] < 0) {
+            break;
+        }
+        ret = kvm_set_ioeventfd_pio_word(ioeventfds[i], 0, i, true);
+        if (ret < 0) {
+            close(ioeventfds[i]);
+            break;
+        }
+    }
+
+    /* Decide whether many devices are supported or not */
+    ret = i == ARRAY_SIZE(ioeventfds);
+
+    while (i-- > 0) {
+        kvm_set_ioeventfd_pio_word(ioeventfds[i], 0, i, false);
+        close(ioeventfds[i]);
+    }
+    return ret;
+#else
+    return 0;
+#endif
+}
+
 static void kvm_set_phys_mem(target_phys_addr_t start_addr,
 			     ram_addr_t size,
 			     ram_addr_t phys_offset)
@@ -717,6 +756,8 @@ int kvm_init(int smp_cpus)
     kvm_state = s;
     cpu_register_phys_memory_client(&kvm_cpu_phys_memory_client);
 
+    s->many_ioeventfds = kvm_check_many_ioeventfds();
+
     return 0;
 
 err:
@@ -1046,6 +1087,14 @@ int kvm_has_xcrs(void)
     return kvm_state->xcrs;
 }
 
+int kvm_has_many_ioeventfds(void)
+{
+    if (!kvm_enabled()) {
+        return 0;
+    }
+    return kvm_state->many_ioeventfds;
+}
+
 void kvm_setup_guest_memory(void *start, size_t size)
 {
     if (!kvm_has_sync_mmu()) {
diff --git a/kvm-stub.c b/kvm-stub.c
index 5384a4b..33d4476 100644
--- a/kvm-stub.c
+++ b/kvm-stub.c
@@ -99,6 +99,11 @@ int kvm_has_robust_singlestep(void)
     return 0;
 }
 
+int kvm_has_many_ioeventfds(void)
+{
+    return 0;
+}
+
 void kvm_setup_guest_memory(void *start, size_t size)
 {
 }
diff --git a/kvm.h b/kvm.h
index 60a9b42..ce08d42 100644
--- a/kvm.h
+++ b/kvm.h
@@ -42,6 +42,7 @@ int kvm_has_robust_singlestep(void);
 int kvm_has_debugregs(void);
 int kvm_has_xsave(void);
 int kvm_has_xcrs(void);
+int kvm_has_many_ioeventfds(void);
 
 #ifdef NEED_CPU_H
 int kvm_init_vcpu(CPUState *env);
-- 
1.7.2.3