提交 1cf81ea2 编写于 作者: P Peter Maydell

Merge remote-tracking branch 'remotes/awilliam/tags/vfio-update-20160119.0' into staging

VFIO updates 2016-01-19

 - Performance fix for devices with poorly placed MSI-X PBA regions
 - Quirk fix for hosts with broken MMCONFIG access

# gpg: Signature made Tue 19 Jan 2016 19:00:21 GMT using RSA key ID 3BB08B22
# gpg: Good signature from "Alex Williamson <alex.williamson@redhat.com>"
# gpg:                 aka "Alex Williamson <alex@shazbot.org>"
# gpg:                 aka "Alex Williamson <alwillia@redhat.com>"
# gpg:                 aka "Alex Williamson <alex.l.williamson@gmail.com>"

* remotes/awilliam/tags/vfio-update-20160119.0:
  vfio/pci: Lazy PBA emulation
  vfio/pci-quirks: Only quirk to size of PCI config space
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>
......@@ -328,7 +328,7 @@ static void vfio_probe_ati_bar4_quirk(VFIOPCIDevice *vdev, int nr)
window->data_offset = 4;
window->nr_matches = 1;
window->matches[0].match = 0x4000;
window->matches[0].mask = PCIE_CONFIG_SPACE_SIZE - 1;
window->matches[0].mask = vdev->config_size - 1;
window->bar = nr;
window->addr_mem = &quirk->mem[0];
window->data_mem = &quirk->mem[1];
......@@ -674,7 +674,7 @@ static void vfio_probe_nvidia_bar5_quirk(VFIOPCIDevice *vdev, int nr)
window->matches[0].match = 0x1800;
window->matches[0].mask = PCI_CONFIG_SPACE_SIZE - 1;
window->matches[1].match = 0x88000;
window->matches[1].mask = PCIE_CONFIG_SPACE_SIZE - 1;
window->matches[1].mask = vdev->config_size - 1;
window->bar = nr;
window->addr_mem = bar5->addr_mem = &quirk->mem[0];
window->data_mem = bar5->data_mem = &quirk->mem[1];
......@@ -765,7 +765,7 @@ static void vfio_probe_nvidia_bar0_quirk(VFIOPCIDevice *vdev, int nr)
memory_region_init_io(mirror->mem, OBJECT(vdev),
&vfio_nvidia_mirror_quirk, mirror,
"vfio-nvidia-bar0-88000-mirror-quirk",
PCIE_CONFIG_SPACE_SIZE);
vdev->config_size);
memory_region_add_subregion_overlap(&vdev->bars[nr].region.mem,
mirror->offset, mirror->mem, 1);
......
......@@ -356,6 +356,13 @@ static void vfio_msi_interrupt(void *opaque)
if (vdev->interrupt == VFIO_INT_MSIX) {
get_msg = msix_get_message;
notify = msix_notify;
/* A masked vector firing needs to use the PBA, enable it */
if (msix_is_masked(&vdev->pdev, nr)) {
set_bit(nr, vdev->msix->pending);
memory_region_set_enabled(&vdev->pdev.msix_pba_mmio, true);
trace_vfio_msix_pba_enable(vdev->vbasedev.name);
}
} else if (vdev->interrupt == VFIO_INT_MSI) {
get_msg = msi_get_message;
notify = msi_notify;
......@@ -535,6 +542,14 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr,
}
}
/* Disable PBA emulation when nothing more is pending. */
clear_bit(nr, vdev->msix->pending);
if (find_first_bit(vdev->msix->pending,
vdev->nr_vectors) == vdev->nr_vectors) {
memory_region_set_enabled(&vdev->pdev.msix_pba_mmio, false);
trace_vfio_msix_pba_disable(vdev->vbasedev.name);
}
return 0;
}
......@@ -738,6 +753,9 @@ static void vfio_msix_disable(VFIOPCIDevice *vdev)
vfio_msi_disable_common(vdev);
memset(vdev->msix->pending, 0,
BITS_TO_LONGS(vdev->msix->entries) * sizeof(unsigned long));
trace_vfio_msix_disable(vdev->vbasedev.name);
}
......@@ -1251,6 +1269,8 @@ static int vfio_msix_setup(VFIOPCIDevice *vdev, int pos)
{
int ret;
vdev->msix->pending = g_malloc0(BITS_TO_LONGS(vdev->msix->entries) *
sizeof(unsigned long));
ret = msix_init(&vdev->pdev, vdev->msix->entries,
&vdev->bars[vdev->msix->table_bar].region.mem,
vdev->msix->table_bar, vdev->msix->table_offset,
......@@ -1264,6 +1284,24 @@ static int vfio_msix_setup(VFIOPCIDevice *vdev, int pos)
return ret;
}
/*
* The PCI spec suggests that devices provide additional alignment for
* MSI-X structures and avoid overlapping non-MSI-X related registers.
* For an assigned device, this hopefully means that emulation of MSI-X
* structures does not affect the performance of the device. If devices
* fail to provide that alignment, a significant performance penalty may
* result, for instance Mellanox MT27500 VFs:
* http://www.spinics.net/lists/kvm/msg125881.html
*
* The PBA is simply not that important for such a serious regression and
* most drivers do not appear to look at it. The solution for this is to
* disable the PBA MemoryRegion unless it's being used. We disable it
* here and only enable it if a masked vector fires through QEMU. As the
* vector-use notifier is called, which occurs on unmask, we test whether
* PBA emulation is needed and again disable if not.
*/
memory_region_set_enabled(&vdev->pdev.msix_pba_mmio, false);
return 0;
}
......@@ -1275,6 +1313,7 @@ static void vfio_teardown_msi(VFIOPCIDevice *vdev)
msix_uninit(&vdev->pdev,
&vdev->bars[vdev->msix->table_bar].region.mem,
&vdev->bars[vdev->msix->pba_bar].region.mem);
g_free(vdev->msix->pending);
}
}
......
......@@ -95,6 +95,7 @@ typedef struct VFIOMSIXInfo {
uint32_t pba_offset;
MemoryRegion mmap_mem;
void *mmap;
unsigned long *pending;
} VFIOMSIXInfo;
typedef struct VFIOPCIDevice {
......
......@@ -1631,6 +1631,8 @@ vfio_msi_interrupt(const char *name, int index, uint64_t addr, int data) " (%s)
vfio_msix_vector_do_use(const char *name, int index) " (%s) vector %d used"
vfio_msix_vector_release(const char *name, int index) " (%s) vector %d released"
vfio_msix_enable(const char *name) " (%s)"
vfio_msix_pba_disable(const char *name) " (%s)"
vfio_msix_pba_enable(const char *name) " (%s)"
vfio_msix_disable(const char *name) " (%s)"
vfio_msi_enable(const char *name, int nr_vectors) " (%s) Enabled %d MSI vectors"
vfio_msi_disable(const char *name) " (%s)"
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册