render / rpms / libvirt

Forked from rpms/libvirt 10 months ago
Clone
Blob Blame History Raw
From 02482db69537daa5a1235db00ece500fd7e1844d Mon Sep 17 00:00:00 2001
Message-Id: <02482db69537daa5a1235db00ece500fd7e1844d@dist-git>
From: Peter Krempa <pkrempa@redhat.com>
Date: Thu, 12 Nov 2015 08:40:45 +0100
Subject: [PATCH] qemu: Explain mlock limit size more in detail

https://bugzilla.redhat.com/show_bug.cgi?id=1280420

Based on Alex's explanation [1] in the recent discussion let's update
the comment explaining the memory lock limit calculation.

[1]
http://www.redhat.com/archives/libvir-list/2015-November/msg00329.html

(cherry picked from commit 63ed05d2410bfb9179b26bc3422ea5f9b546d7b3)

Signed-off-by: Jiri Denemark <jdenemar@redhat.com>
---
 src/qemu/qemu_domain.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c
index fd4449d..be3dcf6 100644
--- a/src/qemu/qemu_domain.c
+++ b/src/qemu/qemu_domain.c
@@ -3445,9 +3445,24 @@ qemuDomainGetMlockLimitBytes(virDomainDefPtr def)
         goto done;
     }
 
-    /* VFIO requires all of the guest's memory to be locked resident, plus some
-     * amount for IO space. Alex Williamson suggested adding 1GiB for IO space
-     * just to be safe (some finer tuning might be nice, though). */
+    /* For device passthrough using VFIO the guest memory and MMIO memory
+     * regions need to be locked persistent in order to allow DMA.
+     *
+     * Currently the below limit is based on assumptions about the x86 platform.
+     *
+     * The chosen value of 1GiB below originates from x86 systems where it was
+     * used as space reserved for the MMIO region for the whole system.
+     *
+     * On x86_64 systems the MMIO regions of the IOMMU mapped devices don't
+     * count towards the locked memory limit since the memory is owned by the
+     * device. Emulated devices though do count, but the regions are usually
+     * small. Although it's not guaranteed that the limit will be enough for all
+     * configurations it didn't pose a problem for now.
+     *
+     * http://www.redhat.com/archives/libvir-list/2015-November/msg00329.html
+     *
+     * Note that this may not be valid for all platforms.
+     */
     memKB = virDomainDefGetMemoryActual(def) + 1024 * 1024;
 
  done:
-- 
2.6.3