Re: [KVM PATCH v7.2] kvm: add iofd support

[Gregory Haskins]

Gregory Haskins wrote:
> [ updated with figures, graphs, performance-test-harness info ]
>
> iofd is a mechanism to register PIO/MMIO regions to trigger an eventfd
> signal when written to by a guest.  Userspace can register any arbitrary
> 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 iofd.
>
> 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
> iofd-mmio: 200100 iops, 5.00us rtt
> iofd-pio:  367300 iops, 2.72us rtt
>
> I didn't measure qemu-pio, because I have to figure out how to register a
> PIO region, 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
> iofd-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@xxxxxxxxxx>
> ---
>
>  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(-)
>
> diff --git a/include/linux/kvm.h b/include/linux/kvm.h
> index dfc4bcc..99b6e45 100644
> --- a/include/linux/kvm.h
> +++ b/include/linux/kvm.h
> @@ -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
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index 1acc528..d53cb70 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -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
> diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
> index 71afd62..8b23317 100644
> --- a/virt/kvm/eventfd.c
> +++ b/virt/kvm/eventfd.c
> @@ -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);
>   

Hmm..this needs to get beefed up too.  It can BUG_ON() if there are too
many io-devs registered, which would be an attack vector from
userspace.  Will fix to return an error (and to check the error in this
function).


> +
> +	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);
> +}
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index 7aa9f0a..a443974 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -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);
>  	}
>
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>

Attachment: signature.asc
Description: OpenPGP digital signature