xen-devel.lists.xenproject.org archive mirror
 help / color / mirror / Atom feed
From: Quan Xu <quan.xu@intel.com>
To: jbeulich@suse.com, kevin.tian@intel.com
Cc: feng.wu@intel.com, ian.campbell@citrix.com,
	george.dunlap@eu.citrix.com, andrew.cooper3@citrix.com,
	dario.faggioli@citrix.com, tim@xen.org, xen-devel@lists.xen.org,
	stefano.stabellini@citrix.com, Aravind.Gopalakrishnan@amd.com,
	jun.nakajima@intel.com, jinsong.liu@alibaba-inc.com,
	Quan Xu <quan.xu@intel.com>,
	keir@xen.org, suravee.suthikulpanit@amd.com
Subject: [PATCH v6 5/5] VT-d: Fix vt-d Device-TLB flush timeout issue
Date: Wed,  2 Mar 2016 22:31:29 +0800	[thread overview]
Message-ID: <1456929089-17414-6-git-send-email-quan.xu@intel.com> (raw)
In-Reply-To: <1456929089-17414-1-git-send-email-quan.xu@intel.com>

If Device-TLB flush is timeout, we'll hide the target ATS device
and crash the domain owning this ATS device. If impacted domain
is hardware domain, just throw out a warning. The hidden device
will be disallowed to be further assigned to any domain.

Signed-off-by: Quan Xu <quan.xu@intel.com>
---
 xen/drivers/passthrough/pci.c         |  6 ++--
 xen/drivers/passthrough/vtd/extern.h  |  2 ++
 xen/drivers/passthrough/vtd/qinval.c  | 65 ++++++++++++++++++++++++++++++++---
 xen/drivers/passthrough/vtd/x86/ats.c | 12 +++++++
 xen/include/xen/pci.h                 |  1 +
 5 files changed, 78 insertions(+), 8 deletions(-)

diff --git a/xen/drivers/passthrough/pci.c b/xen/drivers/passthrough/pci.c
index d7e94e1..53b382a 100644
--- a/xen/drivers/passthrough/pci.c
+++ b/xen/drivers/passthrough/pci.c
@@ -414,7 +414,7 @@ static void free_pdev(struct pci_seg *pseg, struct pci_dev *pdev)
     xfree(pdev);
 }
 
-static void _pci_hide_device(struct pci_dev *pdev)
+void pci_hide_existing_device(struct pci_dev *pdev)
 {
     if ( pdev->domain )
         return;
@@ -431,7 +431,7 @@ int __init pci_hide_device(int bus, int devfn)
     pdev = alloc_pdev(get_pseg(0), bus, devfn);
     if ( pdev )
     {
-        _pci_hide_device(pdev);
+        pci_hide_existing_device(pdev);
         rc = 0;
     }
     pcidevs_unlock();
@@ -461,7 +461,7 @@ int __init pci_ro_device(int seg, int bus, int devfn)
     }
 
     __set_bit(PCI_BDF2(bus, devfn), pseg->ro_map);
-    _pci_hide_device(pdev);
+    pci_hide_existing_device(pdev);
 
     return 0;
 }
diff --git a/xen/drivers/passthrough/vtd/extern.h b/xen/drivers/passthrough/vtd/extern.h
index 507c2e9..dac1e5a 100644
--- a/xen/drivers/passthrough/vtd/extern.h
+++ b/xen/drivers/passthrough/vtd/extern.h
@@ -58,6 +58,8 @@ int ats_device(const struct pci_dev *, const struct acpi_drhd_unit *);
 
 int dev_invalidate_iotlb(struct iommu *iommu, u16 did,
                          u64 addr, unsigned int size_order, u64 type);
+int dev_invalidate_iotlb_sync(struct iommu *iommu, u16 did,
+                              u16 seg, u8 bus, u8 devfn);
 
 int qinval_device_iotlb(struct iommu *iommu,
                         u32 max_invs_pend, u16 sid, u16 size, u64 addr);
diff --git a/xen/drivers/passthrough/vtd/qinval.c b/xen/drivers/passthrough/vtd/qinval.c
index 882b9f4..8ff2d94 100644
--- a/xen/drivers/passthrough/vtd/qinval.c
+++ b/xen/drivers/passthrough/vtd/qinval.c
@@ -233,6 +233,57 @@ int qinval_device_iotlb(struct iommu *iommu,
     return 0;
 }
 
+static void dev_invalidate_iotlb_timeout(struct iommu *iommu, u16 did,
+                                         u16 seg, u8 bus, u8 devfn)
+{
+    struct domain *d = NULL;
+    struct pci_dev *pdev;
+
+    if ( test_bit(did, iommu->domid_bitmap) )
+        d = rcu_lock_domain_by_id(iommu->domid_map[did]);
+
+    if ( d == NULL )
+        return;
+
+    pcidevs_lock();
+    for_each_pdev(d, pdev)
+    {
+        if ( ( pdev->seg == seg ) &&
+             ( pdev->bus == bus ) &&
+             ( pdev->devfn == devfn ) )
+        {
+            ASSERT ( pdev->domain );
+            list_del(&pdev->domain_list);
+            pdev->domain = NULL;
+            pci_hide_existing_device(pdev);
+            break;
+        }
+    }
+
+    pcidevs_unlock();
+
+    if ( !is_hardware_domain(d) )
+        domain_crash(d);
+
+    rcu_unlock_domain(d);
+}
+
+int dev_invalidate_iotlb_sync(struct iommu *iommu, u16 did,
+                              u16 seg, u8 bus, u8 devfn)
+{
+    struct qi_ctrl *qi_ctrl = iommu_qi_ctrl(iommu);
+    int rc = 0;
+
+    if ( qi_ctrl->qinval_maddr )
+    {
+        rc = queue_invalidate_wait(iommu, 0, 1, 1);
+        if ( rc == -ETIMEDOUT )
+            dev_invalidate_iotlb_timeout(iommu, did, seg, bus, devfn);
+    }
+
+    return rc;
+}
+
 static void queue_invalidate_iec(struct iommu *iommu, u8 granu, u8 im, u16 iidx)
 {
     unsigned long flags;
@@ -342,8 +393,6 @@ static int flush_iotlb_qi(
 
     if ( qi_ctrl->qinval_maddr != 0 )
     {
-        int rc;
-
         /* use queued invalidation */
         if (cap_write_drain(iommu->cap))
             dw = 1;
@@ -353,11 +402,17 @@ static int flush_iotlb_qi(
         queue_invalidate_iotlb(iommu,
                                type >> DMA_TLB_FLUSH_GRANU_OFFSET, dr,
                                dw, did, size_order, 0, addr);
+
+        /*
+         * Before Device-TLB invalidation we need to synchronize
+         * invalidation completions with hardware.
+         */
+        ret = invalidate_sync(iommu);
+        if ( ret )
+             return ret;
+
         if ( flush_dev_iotlb )
             ret = dev_invalidate_iotlb(iommu, did, addr, size_order, type);
-        rc = invalidate_sync(iommu);
-        if ( !ret )
-            ret = rc;
     }
     return ret;
 }
diff --git a/xen/drivers/passthrough/vtd/x86/ats.c b/xen/drivers/passthrough/vtd/x86/ats.c
index 7c797f6..a79a95a 100644
--- a/xen/drivers/passthrough/vtd/x86/ats.c
+++ b/xen/drivers/passthrough/vtd/x86/ats.c
@@ -162,6 +162,18 @@ int dev_invalidate_iotlb(struct iommu *iommu, u16 did,
             return -EOPNOTSUPP;
         }
 
+        /*
+         * Synchronize with hardware for Device-TLB invalidate
+         * descriptor.
+         */
+        rc = dev_invalidate_iotlb_sync(iommu, did, pdev->seg,
+                                       pdev->bus, pdev->devfn);
+        if ( rc )
+            printk(XENLOG_ERR
+                   "Flush error %d on device %04x:%02x:%02x.%u.\n",
+                   ret, pdev->seg, pdev->bus, PCI_SLOT(pdev->devfn),
+                   PCI_FUNC(pdev->devfn));
+
         if ( !ret )
             ret = rc;
     }
diff --git a/xen/include/xen/pci.h b/xen/include/xen/pci.h
index 017aa0b..118d8fd 100644
--- a/xen/include/xen/pci.h
+++ b/xen/include/xen/pci.h
@@ -115,6 +115,7 @@ const unsigned long *pci_get_ro_map(u16 seg);
 int pci_add_device(u16 seg, u8 bus, u8 devfn,
                    const struct pci_dev_info *, nodeid_t node);
 int pci_remove_device(u16 seg, u8 bus, u8 devfn);
+void pci_hide_existing_device(struct pci_dev *pdev);
 int pci_ro_device(int seg, int bus, int devfn);
 int pci_hide_device(int bus, int devfn);
 struct pci_dev *pci_get_pdev(int seg, int bus, int devfn);
-- 
1.9.1


_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel

      parent reply	other threads:[~2016-03-02 14:31 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-03-02 14:31 [PATCH v6 0/5] VT-d Device-TLB flush issue Quan Xu
2016-03-02 14:31 ` [PATCH v6 1/5] IOMMU/MMU: Adjust top level functions for VT-d Device-TLB flush error Quan Xu
2016-03-02 14:31 ` [PATCH v6 2/5] IOMMU/MMU: Adjust low " Quan Xu
2016-03-02 14:31 ` [PATCH v6 3/5] IOMMU: Make the pcidevs_lock a recursive one Quan Xu
2016-03-03 23:59   ` Dario Faggioli
2016-03-04  2:45     ` Xu, Quan
2016-03-04  9:29       ` Jan Beulich
2016-03-04 11:54         ` Xu, Quan
2016-03-04 13:59           ` Dario Faggioli
2016-03-04 14:09             ` Jan Beulich
2016-03-07  7:05             ` Xu, Quan
2016-03-07 11:14               ` Jan Beulich
2016-03-07 11:23                 ` Xu, Quan
2016-03-07 11:36                   ` Jan Beulich
2016-03-07 11:42                     ` Xu, Quan
2016-03-07 11:49                       ` Jan Beulich
2016-03-07 11:55                         ` Xu, Quan
2016-03-02 14:31 ` [PATCH v6 4/5] VT-d: Reduce spin timeout to 1ms, which can be boot-time changed Quan Xu
2016-03-04  0:11   ` Dario Faggioli
2016-03-04  9:32     ` Jan Beulich
2016-03-02 14:31 ` Quan Xu [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1456929089-17414-6-git-send-email-quan.xu@intel.com \
    --to=quan.xu@intel.com \
    --cc=Aravind.Gopalakrishnan@amd.com \
    --cc=andrew.cooper3@citrix.com \
    --cc=dario.faggioli@citrix.com \
    --cc=feng.wu@intel.com \
    --cc=george.dunlap@eu.citrix.com \
    --cc=ian.campbell@citrix.com \
    --cc=jbeulich@suse.com \
    --cc=jinsong.liu@alibaba-inc.com \
    --cc=jun.nakajima@intel.com \
    --cc=keir@xen.org \
    --cc=kevin.tian@intel.com \
    --cc=stefano.stabellini@citrix.com \
    --cc=suravee.suthikulpanit@amd.com \
    --cc=tim@xen.org \
    --cc=xen-devel@lists.xen.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).