@@ -292,6 +292,17 @@ struct kvm_guest_debug {
struct kvm_guest_debug_arch arch;
};
+#define KVM_IOFD_FLAG_DEASSIGN (1 << 0)
+#define KVM_IOFD_FLAG_PIO (1 << 1)
+
+struct kvm_iofd {
+ __u64 addr;
+ __u32 len;
+ __u32 fd;
+ __u32 flags;
+ __u8 pad[12];
+};
+
#define KVM_TRC_SHIFT 16
/*
* kvm trace categories
@@ -508,6 +519,7 @@ struct kvm_irqfd {
#define KVM_DEASSIGN_DEV_IRQ _IOW(KVMIO, 0x75, struct kvm_assigned_irq)
#define KVM_ASSIGN_IRQFD _IOW(KVMIO, 0x76, struct kvm_irqfd)
#define KVM_DEASSIGN_IRQFD _IOW(KVMIO, 0x77, __u32)
+#define KVM_IOFD _IOW(KVMIO, 0x78, struct kvm_iofd)
/*
* ioctls for vcpu fds
@@ -529,5 +529,7 @@ static inline void kvm_free_irq_routing(struct kvm *kvm) {}
int kvm_assign_irqfd(struct kvm *kvm, int fd, int gsi, int flags);
int kvm_deassign_irqfd(struct kvm *kvm, int fd);
void kvm_irqfd_release(struct kvm *kvm);
+int kvm_iofd(struct kvm *kvm, unsigned long addr, size_t len,
+ int fd, int flags);
#endif
@@ -21,12 +21,16 @@
*/
#include <linux/kvm_host.h>
+#include <linux/kvm.h>
#include <linux/workqueue.h>
#include <linux/syscalls.h>
#include <linux/wait.h>
#include <linux/poll.h>
#include <linux/file.h>
#include <linux/list.h>
+#include <linux/eventfd.h>
+
+#include "iodev.h"
/*
* --------------------------------------------------------------------
@@ -185,3 +189,106 @@ kvm_irqfd_release(struct kvm *kvm)
list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds, list)
irqfd_release(irqfd);
}
+
+/*
+ * --------------------------------------------------------------------
+ * iofd: translate a PIO/MMIO memory write to an eventfd signal.
+ *
+ * userspace can register a PIO/MMIO address with an eventfd for recieving
+ * notification when the memory has been touched.
+ * --------------------------------------------------------------------
+ */
+
+struct _iofd {
+ u64 addr;
+ size_t length;
+ struct file *file;
+ struct kvm_io_device dev;
+};
+
+static int
+iofd_in_range(struct kvm_io_device *this, gpa_t addr, int len, int is_write)
+{
+ struct _iofd *iofd = (struct _iofd *)this->private;
+
+ return ((addr >= iofd->addr && (addr < iofd->addr + iofd->length)));
+}
+
+/* writes trigger an event */
+static void
+iofd_write(struct kvm_io_device *this, gpa_t addr, int len, const void *val)
+{
+ struct _iofd *iofd = (struct _iofd *)this->private;
+
+ eventfd_signal(iofd->file, 1);
+}
+
+/* reads return all zeros */
+static void
+iofd_read(struct kvm_io_device *this, gpa_t addr, int len, void *val)
+{
+ memset(val, 0, len);
+}
+
+static void
+iofd_destructor(struct kvm_io_device *this)
+{
+ struct _iofd *iofd = (struct _iofd *)this->private;
+
+ fput(iofd->file);
+ kfree(iofd);
+}
+
+static int
+kvm_assign_iofd(struct kvm *kvm, unsigned long addr, size_t len,
+ int fd, int flags)
+{
+ int pio = flags & KVM_IOFD_FLAG_PIO;
+ struct kvm_io_bus *bus = pio ? &kvm->pio_bus : &kvm->mmio_bus;
+ struct _iofd *iofd;
+ struct file *file;
+
+ file = eventfd_fget(fd);
+ if (IS_ERR(file))
+ return PTR_ERR(file);
+
+ iofd = kzalloc(sizeof(*iofd), GFP_KERNEL);
+ if (!iofd) {
+ fput(file);
+ return -ENOMEM;
+ }
+
+ iofd->dev.read = iofd_read;
+ iofd->dev.write = iofd_write;
+ iofd->dev.in_range = iofd_in_range;
+ iofd->dev.destructor = iofd_destructor;
+ iofd->dev.private = iofd;
+
+ iofd->addr = addr;
+ iofd->length = len;
+ iofd->file = file;
+
+ kvm_io_bus_register_dev(bus, &iofd->dev);
+
+ printk(KERN_DEBUG "registering %s iofd at %lx of size %d\n",
+ pio ? "PIO" : "MMIO", addr, (int)len);
+
+ return 0;
+}
+
+static int
+kvm_deassign_iofd(struct kvm *kvm, unsigned long addr, size_t len,
+ int fd, int flags)
+{
+ /* FIXME: We need an io_bus_unregister() function */
+ return -EINVAL;
+}
+
+int
+kvm_iofd(struct kvm *kvm, unsigned long addr, size_t len, int fd, int flags)
+{
+ if (flags & KVM_IOFD_FLAG_DEASSIGN)
+ return kvm_deassign_iofd(kvm, addr, len, fd, flags);
+
+ return kvm_assign_iofd(kvm, addr, len, fd, flags);
+}
@@ -2228,6 +2228,19 @@ static long kvm_vm_ioctl(struct file *filp,
r = kvm_deassign_irqfd(kvm, data);
break;
}
+ case KVM_IOFD: {
+ struct kvm_iofd entry;
+
+ r = -EFAULT;
+ if (copy_from_user(&entry, argp, sizeof entry))
+ goto out;
+
+ r = kvm_iofd(kvm, entry.addr, entry.len, entry.fd,
+ entry.flags);
+ if (r)
+ goto out;
+ break;
+ }
default:
r = kvm_arch_vm_ioctl(filp, ioctl, arg);
}
[ here is the updated header ] iofd is a mechanism to register PIO/MMIO regions to trigger an eventfd signal when written to. Userspace can register any arbitrary address with a corresponding eventfd. Normal IO requires a synchronous/blocking round-trip since the operation may cause side-effects in the emulated model or may return data to the caller. 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 because they are done within the same context as the VCPU thread and therefore cause a VMX/SVM "heavy-weight" exit, a transition back to userspace, and overhead with the qemu locking and decoding operations. Therefore providing the registration of an in-kernel trigger point allows the VCPU to take a very brief lightweight exit only long enough to signal the eventfd. This also means that any clients compatible with the eventfd interface (which includes userspace and kernelspace equally well) can now register for asynchronous notification when one of these signals are generated in the guest. The end result should be a more flexible and higher performance notification API for the backend KVM hypervisor and perhipheral components. Signed-off-by: Gregory Haskins <ghaskins@novell.com> --- include/linux/kvm.h | 12 +++++ include/linux/kvm_host.h | 2 + virt/kvm/eventfd.c | 107 ++++++++++++++++++++++++++++++++++++++++++++++ virt/kvm/kvm_main.c | 13 ++++++ 4 files changed, 134 insertions(+), 0 deletions(-) -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html