kvm/x86 : add coalesced pio support

Coalesced pio is based on coalesced mmio and can be used for some port
like rtc port, pci-host config port and so on.

Specially in case of rtc as coalesced pio, some versions of windows guest
access rtc frequently because of rtc as system tick. guest access rtc like
this: write register index to 0x70, then write or read data from 0x71.
writing 0x70 port is just as index and do nothing else. So we can use
coalesced pio to handle this scene to reduce VM-EXIT time.

When starting and closing a virtual machine, it will access pci-host config
port frequently. So setting these port as coalesced pio can reduce startup
and shutdown time.

without my patch, get the vm-exit time of accessing rtc 0x70 and piix 0xcf8
using perf tools: (guest OS : windows 7 64bit)
IO Port Access  Samples Samples%  Time%  Min Time  Max Time  Avg time
0x70:POUT        86     30.99%    74.59%   9us      29us    10.75us (+- 3.41%)
0xcf8:POUT     1119     2.60%     2.12%   2.79us    56.83us 3.41us (+- 2.23%)

with my patch
IO Port Access  Samples Samples%  Time%   Min Time  Max Time   Avg time
0x70:POUT       106    32.02%    29.47%    0us      10us     1.57us (+- 7.38%)
0xcf8:POUT      1065    1.67%     0.28%   0.41us    65.44us   0.66us (+- 10.55%)

Signed-off-by: Peng Hao <peng.hao2@zte.com.cn>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

4 files changed, 30 insertions, 11 deletions

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 10d48eb67da9..70f9c8bb1840 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -3683,27 +3683,31 @@ the definition of struct kvm_nested_state, see KVM_GET_NESTED_STATE.
 
 4.116 KVM_(UN)REGISTER_COALESCED_MMIO
 
-Capability: KVM_CAP_COALESCED_MMIO
+Capability: KVM_CAP_COALESCED_MMIO (for coalesced mmio)
+	    KVM_CAP_COALESCED_PIO (for coalesced pio)
 Architectures: all
 Type: vm ioctl
 Parameters: struct kvm_coalesced_mmio_zone
 Returns: 0 on success, < 0 on error
 
-Coalesced mmio is a performance optimization that defers hardware
+Coalesced I/O is a performance optimization that defers hardware
 register write emulation so that userspace exits are avoided.  It is
 typically used to reduce the overhead of emulating frequently accessed
 hardware registers.
 
-When a hardware register is configured for coalesced mmio, write accesses
+When a hardware register is configured for coalesced I/O, write accesses
 do not exit to userspace and their value is recorded in a ring buffer
 that is shared between kernel and userspace.
 
-Coalesced mmio is used if one or more write accesses to a hardware
+Coalesced I/O is used if one or more write accesses to a hardware
 register can be deferred until a read or a write to another hardware
 register on the same device.  This last access will cause a vmexit and
 userspace will process accesses from the ring buffer before emulating
-it. That will avoid exiting to userspace on repeated writes to the
-first register.
+it. That will avoid exiting to userspace on repeated writes.
+
+Coalesced pio is based on coalesced mmio. There is little difference
+between coalesced mmio and pio except that coalesced pio records accesses
+to I/O ports.
 
 5. The kvm_run structure
 ------------------------
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 7785678caedb..97780a0277fe 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -420,13 +420,19 @@ struct kvm_run {
 struct kvm_coalesced_mmio_zone {
 	__u64 addr;
 	__u32 size;
-	__u32 pad;
+	union {
+		__u32 pad;
+		__u32 pio;
+	};
 };
 
 struct kvm_coalesced_mmio {
 	__u64 phys_addr;
 	__u32 len;
-	__u32 pad;
+	union {
+		__u32 pad;
+		__u32 pio;
+	};
 	__u8  data[8];
 };
 
@@ -956,6 +962,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_MSR_PLATFORM_INFO 159
 #define KVM_CAP_PPC_NESTED_HV 160
 #define KVM_CAP_HYPERV_SEND_IPI 161
+#define KVM_CAP_COALESCED_PIO 162
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
index 9e65feb6fa58..3710342cf6ad 100644
--- a/virt/kvm/coalesced_mmio.c
+++ b/virt/kvm/coalesced_mmio.c
@@ -83,6 +83,7 @@ static int coalesced_mmio_write(struct kvm_vcpu *vcpu,
 	ring->coalesced_mmio[ring->last].phys_addr = addr;
 	ring->coalesced_mmio[ring->last].len = len;
 	memcpy(ring->coalesced_mmio[ring->last].data, val, len);
+	ring->coalesced_mmio[ring->last].pio = dev->zone.pio;
 	smp_wmb();
 	ring->last = (ring->last + 1) % KVM_COALESCED_MMIO_MAX;
 	spin_unlock(&dev->kvm->ring_lock);
@@ -140,6 +141,9 @@ int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
 	int ret;
 	struct kvm_coalesced_mmio_dev *dev;
 
+	if (zone->pio != 1 && zone->pio != 0)
+		return -EINVAL;
+
 	dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev), GFP_KERNEL);
 	if (!dev)
 		return -ENOMEM;
@@ -149,8 +153,9 @@ int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
 	dev->zone = *zone;
 
 	mutex_lock(&kvm->slots_lock);
-	ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, zone->addr,
-				      zone->size, &dev->dev);
+	ret = kvm_io_bus_register_dev(kvm,
+				zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS,
+				zone->addr, zone->size, &dev->dev);
 	if (ret < 0)
 		goto out_free_dev;
 	list_add_tail(&dev->list, &kvm->coalesced_zones);
@@ -174,7 +179,8 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
 
 	list_for_each_entry_safe(dev, tmp, &kvm->coalesced_zones, list)
 		if (coalesced_mmio_in_range(dev, zone->addr, zone->size)) {
-			kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &dev->dev);
+			kvm_io_bus_unregister_dev(kvm,
+				zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev);
 			kvm_iodevice_destructor(&dev->dev);
 		}
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index acc951cc2663..067b71abae00 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2949,6 +2949,8 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 #ifdef CONFIG_KVM_MMIO
 	case KVM_CAP_COALESCED_MMIO:
 		return KVM_COALESCED_MMIO_PAGE_OFFSET;
+	case KVM_CAP_COALESCED_PIO:
+		return 1;
 #endif
 #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 	case KVM_CAP_IRQ_ROUTING: