xen/26731-AMD-IOMMU-Process-softirqs-while-building-dom0-iommu-mappings.patch
Charles Arnold 387129caad - bnc#797014 - no way to control live migrations
- bnc#803712 - after live migration rcu_sched_state detected stalls
  xen.migrate.tools-xend_move_assert_to_exception_block.patch
  xen.migrate.tools-libxc_print_stats_if_migration_is_aborted.patch
  xen.migrate.tools_set_number_of_dirty_pages_during_migration.patch
  xen.migrate.tools_notify_restore_to_hangup_during_migration_--abort_if_busy.patch

- bnc#811764 - XEN (hypervisor or kernel) has a problem with EFI
  variable services
  x86-EFI-set-variable-permit-attrs.patch
- Upstream patches from Jan
  26060-ACPI-ERST-table-size-checks.patch
  26692-x86-fully-protect-MSI-X-table-from-PV-guest-accesses.patch
  26702-powernow-add-fixups-for-AMD-P-state-figures.patch
  26704-x86-MCA-suppress-bank-clearing-for-certain-injected-events.patch (bnc#805579)
  26731-AMD-IOMMU-Process-softirqs-while-building-dom0-iommu-mappings.patch
  26733-VT-d-Enumerate-IOMMUs-when-listing-capabilities.patch
  26734-ACPI-ERST-Name-table-in-otherwise-opaque-error-messages.patch
  26736-ACPI-APEI-Unlock-apei_iomaps_lock-on-error-path.patch
  26737-ACPI-APEI-Add-apei_exec_run_optional.patch
  26742-IOMMU-properly-check-whether-interrupt-remapping-is-enabled.patch
  26743-VT-d-deal-with-5500-5520-X58-errata.patch (bnc#801910)
  26744-AMD-IOMMU-allow-disabling-only-interrupt-remapping.patch 
- PVonHVM: __devinit was removed in linux-3.8

OBS-URL: https://build.opensuse.org/package/show/Virtualization/xen?expand=0&rev=234
2013-04-04 17:05:57 +00:00

33 lines
1.3 KiB
Diff

# Commit 0f7b6f91ac1bbfd33b23c291b14874b9561909d2
# Date 2013-03-20 10:00:01 +0100
# Author Andrew Cooper <andrew.cooper3@citrix.com>
# Committer Jan Beulich <jbeulich@suse.com>
AMD/IOMMU: Process softirqs while building dom0 iommu mappings
Recent changes which have made their way into xen-4.2 stable have pushed the
runtime of construct_dom0() over 5 seconds, which has caused regressions in
XenServer testing because of our 5 second watchdog.
The root cause is that amd_iommu_dom0_init() does not process softirqs and in
particular the nmi_timer which causes the watchdog to decide that no useful
progress is being made.
This patch adds periodic calls to process_pending_softirqs() at the same
interval as the Intel variant of this function. The server which was failing
with the watchdog test now boots reliably with a timeout of 1 second.
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
--- a/xen/drivers/passthrough/amd/pci_amd_iommu.c
+++ b/xen/drivers/passthrough/amd/pci_amd_iommu.c
@@ -285,6 +285,9 @@ static void __init amd_iommu_dom0_init(s
if ( mfn_valid(pfn) )
amd_iommu_map_page(d, pfn, pfn,
IOMMUF_readable|IOMMUF_writable);
+
+ if ( !(i & 0xfffff) )
+ process_pending_softirqs();
}
}