qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
* [Qemu-devel] [PATCH qemu] vfio, spapr: Fix levels calculation
@ 2017-09-12  2:53 Alexey Kardashevskiy
  2017-09-12  3:59 ` David Gibson
  0 siblings, 1 reply; 2+ messages in thread
From: Alexey Kardashevskiy @ 2017-09-12  2:53 UTC (permalink / raw)
  To: qemu-devel; +Cc: Alexey Kardashevskiy, qemu-ppc, David Gibson, Alex Williamson

The existing tries to round up the number of pages but @pages is always
calculated as the rounded up value minus one  which makes ctz64() always
return 0 and have create.levels always set 1.

This removes wrong "-1" and allows having more than 1 levels. This becomes
handy for >128GB guests with standard 64K pages as this requires blocks
with zone order 9 and the popular limit of CONFIG_FORCE_MAX_ZONEORDER=9
means that only blocks up to order 8 are allowed.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
 hw/vfio/spapr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/hw/vfio/spapr.c b/hw/vfio/spapr.c
index 32fd6a9b54..259397c002 100644
--- a/hw/vfio/spapr.c
+++ b/hw/vfio/spapr.c
@@ -163,7 +163,7 @@ int vfio_spapr_create_window(VFIOContainer *container,
      */
     entries = create.window_size >> create.page_shift;
     pages = MAX((entries * sizeof(uint64_t)) / getpagesize(), 1);
-    pages = MAX(pow2ceil(pages) - 1, 1); /* Round up */
+    pages = MAX(pow2ceil(pages), 1); /* Round up */
     create.levels = ctz64(pages) / 6 + 1;
 
     ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_TCE_CREATE, &create);
-- 
2.11.0

^ permalink raw reply related	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2017-09-12  4:29 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2017-09-12  2:53 [Qemu-devel] [PATCH qemu] vfio, spapr: Fix levels calculation Alexey Kardashevskiy
2017-09-12  3:59 ` David Gibson

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).