Re: [Qemu-devel] [RFC PATCH] vfio: VFIO Driver core framework

[Alexey Kardashevskiy]

Hi!

I tried (successfully) to run it on POWER and while doing that I found some 
issues. I'll try to
explain them in separate mails.

IOMMU domain setup. On POWER, the linux drivers capable of DMA transfer want to 
know
a DMA window, i.e. its start and length in the PHB address space. This comes 
from
hardware. On X86 (correct if I am wrong), every device driver in the guest 
allocates
memory from the same pool. On POWER, device drivers get DMA window and allocate 
pages
for DMA within this window. In the case of VFIO, that means that QEMU has to
preallocate this DMA window before running a quest, pass it to a guest (via
device tree) and then a guest tells the host what pages are taken/released by
calling map/unmap callbacks of iommu_ops. Deallocation is made in a device 
detach
callback as I did not want to add more ioctls.
So, there are 2 patches:

- new VFIO_IOMMU_SETUP ioctl introduced which allocates a DMA window via IOMMU 
API on
POWER.
btw do we need an additional capability bit for it?

KERNEL PATCH:

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 10615ad..a882e08 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -247,3 +247,12 @@ int iommu_device_group(struct device *dev, unsigned int 
*groupid)
        return -ENODEV;
 }
 EXPORT_SYMBOL_GPL(iommu_device_group);
+
+int iommu_setup(struct iommu_domain *domain,
+               size_t requested_size, size_t *allocated_size,
+               phys_addr_t *start_address)
+{
+       return domain->ops->setup(domain, requested_size, allocated_size,
+                       start_address);
+}
+EXPORT_SYMBOL_GPL(iommu_setup);
diff --git a/drivers/vfio/vfio_iommu.c b/drivers/vfio/vfio_iommu.c
index 029dae3..57fb70d 100644
--- a/drivers/vfio/vfio_iommu.c
+++ b/drivers/vfio/vfio_iommu.c
@@ -507,6 +507,23 @@ static long vfio_iommu_unl_ioctl(struct file *filep,

                if (!ret && copy_to_user((void __user *)arg, &dm, sizeof dm))
                        ret = -EFAULT;
+
+       } else if (cmd == VFIO_IOMMU_SETUP) {
+               struct vfio_setup setup;
+               size_t allocated_size = 0;
+               phys_addr_t start_address = 0;
+
+               if (copy_from_user(&setup, (void __user *)arg, sizeof setup))
+                       return -EFAULT;
+
+               printk("udomain %p, priv=%p\n", iommu->domain, 
iommu->domain->priv);
+               ret = iommu_setup(iommu->domain, setup.requested_size,
+                               &allocated_size, &start_address);
+               setup.allocated_size = allocated_size;
+               setup.start_address = start_address;
+
+               if (!ret && copy_to_user((void __user *)arg, &setup, sizeof 
setup))
+                       ret = -EFAULT;
        }
        return ret;
 }
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 93617e7..355cf8b 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -45,6 +45,7 @@ struct iommu_domain {

 #define IOMMU_CAP_CACHE_COHERENCY      0x1
 #define IOMMU_CAP_INTR_REMAP           0x2     /* isolates device intrs */
+#define IOMMU_CAP_SETUP_REQUIRED       0x3     /* requires setup to be called 
*/

 #ifdef CONFIG_IOMMU_API

@@ -62,6 +63,9 @@ struct iommu_ops {
        int (*domain_has_cap)(struct iommu_domain *domain,
                              unsigned long cap);
        int (*device_group)(struct device *dev, unsigned int *groupid);
+       int (*setup)(struct iommu_domain *domain,
+                    size_t requested_size, size_t *allocated_size,
+                    phys_addr_t *start_address);
 };

 extern int bus_set_iommu(struct bus_type *bus, struct iommu_ops *ops);
@@ -80,6 +84,9 @@ extern phys_addr_t iommu_iova_to_phys(struct iommu_domain 
*domain,
                                      unsigned long iova);
 extern int iommu_domain_has_cap(struct iommu_domain *domain,
                                unsigned long cap);
+extern int iommu_setup(struct iommu_domain *domain,
+                      size_t requested_size, size_t *allocated_size,
+                      phys_addr_t *start_address);
 extern void iommu_set_fault_handler(struct iommu_domain *domain,
                                        iommu_fault_handler_t handler);
 extern int iommu_device_group(struct device *dev, unsigned int *groupid);
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 971e3b1..5e0ee75 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -26,6 +26,7 @@
  * Author: Michael S. Tsirkin <address@hidden>
  */
 #include <linux/types.h>
+#include <linux/ioctl.h>

 #ifndef VFIO_H
 #define VFIO_H
@@ -172,4 +173,13 @@ enum {
        VFIO_PCI_NUM_IRQS
 };

+/* Setup domain */
+#define VFIO_IOMMU_SETUP               _IOWR(';', 150, struct vfio_setup)
+
+struct vfio_setup {
+       __u64   requested_size;
+       __u64   allocated_size;
+       __u64   start_address;
+};
+
  #endif /* VFIO_H */

=== end ===


QEMU PATCH:

diff --git a/hw/linux-vfio.h b/hw/linux-vfio.h
index ac48d85..a2c719f 100644
--- a/hw/linux-vfio.h
+++ b/hw/linux-vfio.h
@@ -172,4 +172,13 @@ enum {
        VFIO_PCI_NUM_IRQS
 };

+/* Setup domain */
+#define VFIO_IOMMU_SETUP                _IOWR(';', 150, struct vfio_setup)
+
+struct vfio_setup {
+       __u64   requested_size;
+       __u64   allocated_size;
+       __u64   start_address;
+};
+
 #endif /* VFIO_H */
diff --git a/hw/vfio_pci.c b/hw/vfio_pci.c
index 1c97c35..b438bbe 100644
--- a/hw/vfio_pci.c
+++ b/hw/vfio_pci.c
@@ -1501,6 +1503,17 @@ static int vfio_initfn(struct PCIDevice *pdev)
     if (vfio_map_resources(vdev))
         goto out_disable_msi;

+    struct vfio_setup setup = { 1 << 26, 0, 0 };
+    if ((ret =  ioctl(vdev->group->iommu->fd, VFIO_IOMMU_SETUP, &setup))) {
+        return ret;
+    }
+    printf("SETUP: requested %lluMB, allocated %lluMB at %llx\n",
+        (unsigned long long)setup.requested_size,
+        (unsigned long long)setup.allocated_size,
+        (unsigned long long)setup.start_address);
+    vdev->start_address = setup.start_address;
+    vdev->window_size = setup.allocated_size;
+
     if (vfio_enable_intx(vdev))
         goto out_unmap_resources;

diff --git a/hw/vfio_pci.h b/hw/vfio_pci.h
index 96b09bb..6b7ab6f 100644
--- a/hw/vfio_pci.h
+++ b/hw/vfio_pci.h
@@ -79,6 +79,10 @@ typedef struct VFIODevice {
     bool msix;
     uint8_t msix_bar;
     uint16_t msix_entries;
+#ifdef TARGET_PPC
+    uint64_t start_address;
+    uint32_t window_size;
+#endif
 } VFIODevice;

 typedef struct VFIOGroup {

=== end ===



- changed __vfio_close_iommu function to do unmapall first and detach devices 
then
as actual deallocation happens on device detach callback of IOMMU ops.

diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
index 6169356..f78f411 100644
--- a/drivers/vfio/vfio_main.c
+++ b/drivers/vfio/vfio_main.c
@@ -28,6 +28,7 @@
 #include <linux/uaccess.h>
 #include <linux/vfio.h>
 #include <linux/wait.h>
+#include <linux/pci.h>

 #include "vfio_private.h"

@@ -242,6 +243,13 @@ static void __vfio_close_iommu(struct vfio_iommu *iommu)
        if (!iommu->domain)
                return;

+       /*
+        * On POWER, device detaching (which is done by 
__vfio_iommu_detach_group)
+        * should happen after all pages unmapped because
+        * the only way to do actual iommu_unmap_page a device detach callback
+        */
+       vfio_iommu_unmapall(iommu);
+
        list_for_each(pos, &iommu->group_list) {
                struct vfio_group *group;
                group = list_entry(pos, struct vfio_group, iommu_next);
@@ -249,7 +257,7 @@ static void __vfio_close_iommu(struct vfio_iommu *iommu)
                __vfio_iommu_detach_group(iommu, group);
        }

-       vfio_iommu_unmapall(iommu);
+       /* vfio_iommu_unmapall(iommu); */

        iommu_domain_free(iommu->domain);
        iommu->domain = NULL;





On 04/11/11 07:12, Alex Williamson wrote:
> VFIO provides a secure, IOMMU based interface for user space
> drivers, including device assignment to virtual machines.
> This provides the base management of IOMMU groups, devices,
> and IOMMU objects.  See Documentation/vfio.txt included in
> this patch for user and kernel API description.
> 
> Note, this implements the new API discussed at KVM Forum
> 2011, as represented by the drvier version 0.2.  It's hoped
> that this provides a modular enough interface to support PCI
> and non-PCI userspace drivers across various architectures
> and IOMMU implementations.
> 
> Signed-off-by: Alex Williamson <address@hidden>
> ---
> 
> Fingers crossed, this is the last RFC for VFIO, but we need
> the iommu group support before this can go upstream
> (http://lkml.indiana.edu/hypermail/linux/kernel/1110.2/02303.html),
> hoping this helps push that along.
> 
> Since the last posting, this version completely modularizes
> the device backends and better defines the APIs between the
> core VFIO code and the device backends.  I expect that we
> might also adopt a modular IOMMU interface as iommu_ops learns
> about different types of hardware.  Also many, many cleanups.
> Check the complete git history for details:
> 
> git://github.com/awilliam/linux-vfio.git vfio-ng
> 
> (matching qemu tree: git://github.com/awilliam/qemu-vfio.git)
> 
> This version, along with the supporting VFIO PCI backend can
> be found here:
> 
> git://github.com/awilliam/linux-vfio.git vfio-next-20111103
> 
> I've held off on implementing a kernel->user signaling
> mechanism for now since the previous netlink version produced
> too many gag reflexes.  It's easy enough to set a bit in the
> group flags too indicate such support in the future, so I
> think we can move ahead without it.
> 
> Appreciate any feedback or suggestions.  Thanks,
> 
> Alex
> 


-- 
Alexey Kardashevskiy
IBM OzLabs, LTC Team

e-mail: address@hidden
notes: Alexey Kardashevskiy/Australia/IBM