kvm: test for ioeventfd support on old kernels

There used to be a limit of 6 KVM io bus devices in the kernel.
On such a kernel, we can't use many ioeventfds for host notification
since the limit is reached too easily.

Add an API to test for this condition.

Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

3 files changed, 55 insertions, 0 deletions

diff --git a/kvm-all.c b/kvm-all.c
index cae24bb87c..255b6fad9c 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 5384a4b9a4..33d4476fa3 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 60a9b425c8..ce08d42756 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);