|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [Xen-devel] [PATCH v14 3/3] IOMMU: fix vt-d Device-TLB flush timeout issue
From: Quan Xu <quan.xu@xxxxxxxxx>
If Device-TLB flush timed out, we hide the target ATS device
immediately. By hiding the device, we make sure it can't be
assigned to any domain any longer (see device_assigned).
Signed-off-by: Quan Xu <quan.xu@xxxxxxxxx>
CC: Jan Beulich <jbeulich@xxxxxxxx>
CC: Kevin Tian <kevin.tian@xxxxxxxxx>
CC: Feng Wu <feng.wu@xxxxxxxxx>
---
v14: release the lock before return.
---
xen/drivers/passthrough/iommu.c | 24 +++++++++++++++
xen/drivers/passthrough/pci.c | 6 ++--
xen/drivers/passthrough/vtd/extern.h | 5 ++--
xen/drivers/passthrough/vtd/qinval.c | 56 +++++++++++++++++++++++++++--------
xen/drivers/passthrough/vtd/x86/ats.c | 11 ++-----
xen/include/xen/iommu.h | 3 ++
xen/include/xen/pci.h | 1 +
7 files changed, 79 insertions(+), 27 deletions(-)
diff --git a/xen/drivers/passthrough/iommu.c b/xen/drivers/passthrough/iommu.c
index d793f5d..2353c7d 100644
--- a/xen/drivers/passthrough/iommu.c
+++ b/xen/drivers/passthrough/iommu.c
@@ -361,6 +361,30 @@ int iommu_iotlb_flush_all(struct domain *d)
return rc;
}
+void iommu_dev_iotlb_flush_timeout(struct domain *d,
+ struct pci_dev *pdev)
+{
+ pcidevs_lock();
+
+ ASSERT(pdev->domain);
+ if ( d != pdev->domain )
+ {
+ pcidevs_unlock();
+ return;
+ }
+
+ list_del(&pdev->domain_list);
+ pdev->domain = NULL;
+ pci_hide_existing_device(pdev);
+ if ( !d->is_shutting_down && printk_ratelimit() )
+ printk(XENLOG_ERR
+ "dom%d: ATS device %04x:%02x:%02x.%u flush failed\n",
+ d->domain_id, pdev->seg, pdev->bus, PCI_SLOT(pdev->devfn),
+ PCI_FUNC(pdev->devfn));
+
+ pcidevs_unlock();
+}
+
int __init iommu_setup(void)
{
int rc = -ENODEV;
diff --git a/xen/drivers/passthrough/pci.c b/xen/drivers/passthrough/pci.c
index bb5f344..58bfb79 100644
--- a/xen/drivers/passthrough/pci.c
+++ b/xen/drivers/passthrough/pci.c
@@ -419,7 +419,7 @@ 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;
@@ -436,7 +436,7 @@ 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();
@@ -466,7 +466,7 @@ 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 45357f2..efaff28 100644
--- a/xen/drivers/passthrough/vtd/extern.h
+++ b/xen/drivers/passthrough/vtd/extern.h
@@ -25,6 +25,7 @@
#define VTDPREFIX "[VT-D]"
+struct pci_ats_dev;
extern bool_t rwbf_quirk;
void print_iommu_regs(struct acpi_drhd_unit *drhd);
@@ -60,8 +61,8 @@ int dev_invalidate_iotlb(struct iommu *iommu, u16 did,
u64 addr, unsigned int size_order, u64 type);
int __must_check qinval_device_iotlb_sync(struct iommu *iommu,
- u32 max_invs_pend,
- u16 sid, u16 size, u64 addr);
+ struct pci_ats_dev *ats_dev,
+ u16 did, u16 size, u64 addr);
unsigned int get_cache_line_size(void);
void cacheline_flush(char *);
diff --git a/xen/drivers/passthrough/vtd/qinval.c
b/xen/drivers/passthrough/vtd/qinval.c
index 4492b29..7a5c433 100644
--- a/xen/drivers/passthrough/vtd/qinval.c
+++ b/xen/drivers/passthrough/vtd/qinval.c
@@ -27,11 +27,11 @@
#include "dmar.h"
#include "vtd.h"
#include "extern.h"
+#include "../ats.h"
#define VTD_QI_TIMEOUT 1
-static int __must_check invalidate_sync(struct iommu *iommu,
- bool_t flush_dev_iotlb);
+static int __must_check invalidate_sync(struct iommu *iommu);
static void print_qi_regs(struct iommu *iommu)
{
@@ -103,7 +103,7 @@ static int __must_check
queue_invalidate_context_sync(struct iommu *iommu,
unmap_vtd_domain_page(qinval_entries);
- return invalidate_sync(iommu, 0);
+ return invalidate_sync(iommu);
}
static int __must_check queue_invalidate_iotlb_sync(struct iommu *iommu,
@@ -140,7 +140,7 @@ static int __must_check queue_invalidate_iotlb_sync(struct
iommu *iommu,
qinval_update_qtail(iommu, index);
spin_unlock_irqrestore(&iommu->register_lock, flags);
- return invalidate_sync(iommu, 0);
+ return invalidate_sync(iommu);
}
static int __must_check queue_invalidate_wait(struct iommu *iommu,
@@ -199,25 +199,55 @@ static int __must_check queue_invalidate_wait(struct
iommu *iommu,
return -EOPNOTSUPP;
}
-static int __must_check invalidate_sync(struct iommu *iommu,
- bool_t flush_dev_iotlb)
+static int __must_check invalidate_sync(struct iommu *iommu)
{
struct qi_ctrl *qi_ctrl = iommu_qi_ctrl(iommu);
ASSERT(qi_ctrl->qinval_maddr);
- return queue_invalidate_wait(iommu, 0, 1, 1, flush_dev_iotlb);
+ return queue_invalidate_wait(iommu, 0, 1, 1, 0);
+}
+
+static int __must_check dev_invalidate_sync(struct iommu *iommu,
+ struct pci_dev *pdev, u16 did)
+{
+ struct qi_ctrl *qi_ctrl = iommu_qi_ctrl(iommu);
+ int rc;
+
+ ASSERT(qi_ctrl->qinval_maddr);
+ rc = queue_invalidate_wait(iommu, 0, 1, 1, 1);
+ if ( rc == -ETIMEDOUT )
+ {
+ struct domain *d = NULL;
+
+ if ( test_bit(did, iommu->domid_bitmap) )
+ d = rcu_lock_domain_by_id(iommu->domid_map[did]);
+
+ /*
+ * In case the domain has been freed or the IOMMU domid bitmap is
+ * not valid, the device no longer belongs to this domain.
+ */
+ if ( d == NULL )
+ return rc;
+
+ iommu_dev_iotlb_flush_timeout(d, pdev);
+ rcu_unlock_domain(d);
+ }
+
+ return rc;
}
int qinval_device_iotlb_sync(struct iommu *iommu,
- u32 max_invs_pend,
- u16 sid, u16 size, u64 addr)
+ struct pci_ats_dev *ats_dev,
+ u16 did, u16 size, u64 addr)
{
unsigned long flags;
unsigned int index;
u64 entry_base;
struct qinval_entry *qinval_entry, *qinval_entries;
+ struct pci_dev *pdev = ats_dev->pdev;
+ ASSERT(pdev);
spin_lock_irqsave(&iommu->register_lock, flags);
index = qinval_next_index(iommu);
entry_base = iommu_qi_ctrl(iommu)->qinval_maddr +
@@ -227,9 +257,9 @@ int qinval_device_iotlb_sync(struct iommu *iommu,
qinval_entry->q.dev_iotlb_inv_dsc.lo.type = TYPE_INVAL_DEVICE_IOTLB;
qinval_entry->q.dev_iotlb_inv_dsc.lo.res_1 = 0;
- qinval_entry->q.dev_iotlb_inv_dsc.lo.max_invs_pend = max_invs_pend;
+ qinval_entry->q.dev_iotlb_inv_dsc.lo.max_invs_pend =
ats_dev->ats_queue_depth;
qinval_entry->q.dev_iotlb_inv_dsc.lo.res_2 = 0;
- qinval_entry->q.dev_iotlb_inv_dsc.lo.sid = sid;
+ qinval_entry->q.dev_iotlb_inv_dsc.lo.sid = PCI_BDF2(pdev->bus,
pdev->devfn);
qinval_entry->q.dev_iotlb_inv_dsc.lo.res_3 = 0;
qinval_entry->q.dev_iotlb_inv_dsc.hi.size = size;
@@ -240,7 +270,7 @@ int qinval_device_iotlb_sync(struct iommu *iommu,
qinval_update_qtail(iommu, index);
spin_unlock_irqrestore(&iommu->register_lock, flags);
- return invalidate_sync(iommu, 1);
+ return dev_invalidate_sync(iommu, pdev, did);
}
static int __must_check queue_invalidate_iec_sync(struct iommu *iommu,
@@ -271,7 +301,7 @@ static int __must_check queue_invalidate_iec_sync(struct
iommu *iommu,
qinval_update_qtail(iommu, index);
spin_unlock_irqrestore(&iommu->register_lock, flags);
- ret = invalidate_sync(iommu, 0);
+ ret = invalidate_sync(iommu);
/*
* reading vt-d architecture register will ensure
diff --git a/xen/drivers/passthrough/vtd/x86/ats.c
b/xen/drivers/passthrough/vtd/x86/ats.c
index 11fe9bb..23e46b1 100644
--- a/xen/drivers/passthrough/vtd/x86/ats.c
+++ b/xen/drivers/passthrough/vtd/x86/ats.c
@@ -118,14 +118,9 @@ int dev_invalidate_iotlb(struct iommu *iommu, u16 did,
list_for_each_entry( ats_dev, &ats_devices, list )
{
- struct pci_dev *pdev = ats_dev->pdev;
- u16 sid;
bool_t sbit;
int rc = 0;
- ASSERT(pdev);
- sid = PCI_BDF2(pdev->bus, pdev->devfn);
-
/* Only invalidate devices that belong to this IOMMU */
if ( ats_dev->iommu != iommu )
continue;
@@ -140,8 +135,7 @@ int dev_invalidate_iotlb(struct iommu *iommu, u16 did,
/* invalidate all translations: sbit=1,bit_63=0,bit[62:12]=1 */
sbit = 1;
addr = (~0UL << PAGE_SHIFT_4K) & 0x7FFFFFFFFFFFFFFF;
- rc = qinval_device_iotlb_sync(iommu, ats_dev->ats_queue_depth,
- sid, sbit, addr);
+ rc = qinval_device_iotlb_sync(iommu, ats_dev, did, sbit, addr);
break;
case DMA_TLB_PSI_FLUSH:
if ( !device_in_domain(iommu, ats_dev, did) )
@@ -160,8 +154,7 @@ int dev_invalidate_iotlb(struct iommu *iommu, u16 did,
addr |= (((u64)1 << (size_order - 1)) - 1) << PAGE_SHIFT_4K;
}
- rc = qinval_device_iotlb_sync(iommu, ats_dev->ats_queue_depth,
- sid, sbit, addr);
+ rc = qinval_device_iotlb_sync(iommu, ats_dev, did, sbit, addr);
break;
default:
dprintk(XENLOG_WARNING VTDPREFIX, "invalid vt-d flush type\n");
diff --git a/xen/include/xen/iommu.h b/xen/include/xen/iommu.h
index a759f2b..e0f7d52 100644
--- a/xen/include/xen/iommu.h
+++ b/xen/include/xen/iommu.h
@@ -207,6 +207,9 @@ int __must_check iommu_iotlb_flush(struct domain *d,
unsigned long gfn,
unsigned int page_count);
int __must_check iommu_iotlb_flush_all(struct domain *d);
+void iommu_dev_iotlb_flush_timeout(struct domain *d,
+ struct pci_dev *pdev);
+
/*
* The purpose of the iommu_dont_flush_iotlb optional cpu flag is to
* avoid unecessary iotlb_flush in the low level IOMMU code.
diff --git a/xen/include/xen/pci.h b/xen/include/xen/pci.h
index 6ed29dd..e4940cd 100644
--- a/xen/include/xen/pci.h
+++ b/xen/include/xen/pci.h
@@ -118,6 +118,7 @@ int pci_add_device(u16 seg, u8 bus, u8 devfn,
int pci_remove_device(u16 seg, u8 bus, u8 devfn);
int pci_ro_device(int seg, int bus, int devfn);
int pci_hide_device(int bus, int devfn);
+void pci_hide_existing_device(struct pci_dev *pdev);
struct pci_dev *pci_get_pdev(int seg, int bus, int devfn);
struct pci_dev *pci_get_real_pdev(int seg, int bus, int devfn);
struct pci_dev *pci_get_pdev_by_domain(
--
1.9.1
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel
|
 |
Lists.xenproject.org is hosted with RackSpace, monitoring our |