qemu-devel
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Qemu-devel] [PATCH] vfio/pci: Lazy PBA emulation


From: Alex Williamson
Subject: [Qemu-devel] [PATCH] vfio/pci: Lazy PBA emulation
Date: Tue, 12 Jan 2016 08:56:14 -0700
User-agent: StGit/0.17.1-dirty

The PCI spec recommends devices use additional alignment for MSI-X
data structures to allow software to map them to separate processor
pages.  One advantage of doing this is that we can emulate those data
structures without a significant performance impact to the operation
of the device.  Some devices fail to implement that suggestion and
assigned device performance suffers.

One such case of this is a Mellanox MT27500 series, ConnectX-3 VF,
where the MSI-X vector table and PBA are aligned on separate 4K
pages.  If PBA emulation is enabled, performance suffers.  It's not
clear how much value we get from PBA emulation, but the solution here
is to only lazily enable the emulated PBA when a masked MSI-X vector
fires.  We then attempt to more aggresively disable the PBA memory
region any time a vector is unmasked.  The expectation is then that
a typical VM will run entirely with PBA emulation disabled, and only
when used is that emulation re-enabled.

Reported-by: Shyam Kaushik <address@hidden>
Tested-by: Shyam Kaushik <address@hidden>
Signed-off-by: Alex Williamson <address@hidden>
---

Posting formally for review and comments after Shyam's successful
testing in another thread.

 hw/vfio/pci.c |   39 +++++++++++++++++++++++++++++++++++++++
 hw/vfio/pci.h |    1 +
 trace-events  |    2 ++
 3 files changed, 42 insertions(+)

diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 1fb868c..e66c47f 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -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);
     }
 }
 
diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
index f004d52..6256587 100644
--- a/hw/vfio/pci.h
+++ b/hw/vfio/pci.h
@@ -95,6 +95,7 @@ typedef struct VFIOMSIXInfo {
     uint32_t pba_offset;
     MemoryRegion mmap_mem;
     void *mmap;
+    unsigned long *pending;
 } VFIOMSIXInfo;
 
 typedef struct VFIOPCIDevice {
diff --git a/trace-events b/trace-events
index 934a7b6..c9ac144 100644
--- a/trace-events
+++ b/trace-events
@@ -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)"




reply via email to

[Prev in Thread] Current Thread [Next in Thread]