summaryrefslogtreecommitdiffstats
path: root/include/linux/kvm.h
diff options
context:
space:
mode:
authorGregory Haskins <ghaskins@novell.com>2009-07-07 17:08:49 -0400
committerAvi Kivity <avi@redhat.com>2009-09-10 08:33:12 +0300
commitd34e6b175e61821026893ec5298cc8e7558df43a (patch)
tree8f2934bb0df05d18372509f9ac59aecee5884997 /include/linux/kvm.h
parent090b7aff27120cdae76a346a70db394844fea598 (diff)
downloadop-kernel-dev-d34e6b175e61821026893ec5298cc8e7558df43a.zip
op-kernel-dev-d34e6b175e61821026893ec5298cc8e7558df43a.tar.gz
KVM: add ioeventfd support
ioeventfd is a mechanism to register PIO/MMIO regions to trigger an eventfd signal when written to by a guest. Host userspace can register any arbitrary IO address with a corresponding eventfd and then pass the eventfd to a specific end-point of interest for handling. Normal IO requires a blocking round-trip since the operation may cause side-effects in the emulated model or may return data to the caller. Therefore, an IO in KVM traps from the guest to the host, causes a VMX/SVM "heavy-weight" exit back to userspace, and is ultimately serviced by qemu's device model synchronously before returning control back to the vcpu. However, there is a subclass of IO which acts purely as a trigger for other IO (such as to kick off an out-of-band DMA request, etc). For these patterns, the synchronous call is particularly expensive since we really only want to simply get our notification transmitted asychronously and return as quickly as possible. All the sychronous infrastructure to ensure proper data-dependencies are met in the normal IO case are just unecessary overhead for signalling. This adds additional computational load on the system, as well as latency to the signalling path. Therefore, we provide a mechanism for registration of an in-kernel trigger point that allows the VCPU to only require a very brief, lightweight exit just long enough to signal an eventfd. This also means that any clients compatible with the eventfd interface (which includes userspace and kernelspace equally well) can now register to be notified. The end result should be a more flexible and higher performance notification API for the backend KVM hypervisor and perhipheral components. To test this theory, we built a test-harness called "doorbell". This module has a function called "doorbell_ring()" which simply increments a counter for each time the doorbell is signaled. It supports signalling from either an eventfd, or an ioctl(). We then wired up two paths to the doorbell: One via QEMU via a registered io region and through the doorbell ioctl(). The other is direct via ioeventfd. You can download this test harness here: ftp://ftp.novell.com/dev/ghaskins/doorbell.tar.bz2 The measured results are as follows: qemu-mmio: 110000 iops, 9.09us rtt ioeventfd-mmio: 200100 iops, 5.00us rtt ioeventfd-pio: 367300 iops, 2.72us rtt I didn't measure qemu-pio, because I have to figure out how to register a PIO region with qemu's device model, and I got lazy. However, for now we can extrapolate based on the data from the NULLIO runs of +2.56us for MMIO, and -350ns for HC, we get: qemu-pio: 153139 iops, 6.53us rtt ioeventfd-hc: 412585 iops, 2.37us rtt these are just for fun, for now, until I can gather more data. Here is a graph for your convenience: http://developer.novell.com/wiki/images/7/76/Iofd-chart.png The conclusion to draw is that we save about 4us by skipping the userspace hop. -------------------- Signed-off-by: Gregory Haskins <ghaskins@novell.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Diffstat (limited to 'include/linux/kvm.h')
-rw-r--r--include/linux/kvm.h24
1 files changed, 24 insertions, 0 deletions
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index a74a1fc..230a91a 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -307,6 +307,28 @@ struct kvm_guest_debug {
struct kvm_guest_debug_arch arch;
};
+enum {
+ kvm_ioeventfd_flag_nr_datamatch,
+ kvm_ioeventfd_flag_nr_pio,
+ kvm_ioeventfd_flag_nr_deassign,
+ kvm_ioeventfd_flag_nr_max,
+};
+
+#define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch)
+#define KVM_IOEVENTFD_FLAG_PIO (1 << kvm_ioeventfd_flag_nr_pio)
+#define KVM_IOEVENTFD_FLAG_DEASSIGN (1 << kvm_ioeventfd_flag_nr_deassign)
+
+#define KVM_IOEVENTFD_VALID_FLAG_MASK ((1 << kvm_ioeventfd_flag_nr_max) - 1)
+
+struct kvm_ioeventfd {
+ __u64 datamatch;
+ __u64 addr; /* legal pio/mmio address */
+ __u32 len; /* 1, 2, 4, or 8 bytes */
+ __s32 fd;
+ __u32 flags;
+ __u8 pad[36];
+};
+
#define KVM_TRC_SHIFT 16
/*
* kvm trace categories
@@ -412,6 +434,7 @@ struct kvm_guest_debug {
#ifdef __KVM_HAVE_PIT_STATE2
#define KVM_CAP_PIT_STATE2 35
#endif
+#define KVM_CAP_IOEVENTFD 36
#ifdef KVM_CAP_IRQ_ROUTING
@@ -520,6 +543,7 @@ struct kvm_irqfd {
#define KVM_IRQFD _IOW(KVMIO, 0x76, struct kvm_irqfd)
#define KVM_CREATE_PIT2 _IOW(KVMIO, 0x77, struct kvm_pit_config)
#define KVM_SET_BOOT_CPU_ID _IO(KVMIO, 0x78)
+#define KVM_IOEVENTFD _IOW(KVMIO, 0x79, struct kvm_ioeventfd)
/*
* ioctls for vcpu fds
OpenPOWER on IntegriCloud