Avi Kivity 0d551bb698
KVM: Make shadow pte updates atomic ...
With guest smp, a second vcpu might see partial updates when the first
vcpu services a page fault. So delay all updates until we have figured
out what the pte should look like.
Note that on i386, this is still not completely atomic as a 64-bit write
will be split into two on a 32-bit machine.
Signed-off-by: Avi Kivity <avi@qumranet.com >
2007-07-16 12:05:44 +03:00
2007-07-10 08:03:34 +02:00
2007-07-11 16:02:10 -07:00
2007-07-12 13:40:57 -07:00
2007-07-11 16:02:10 -07:00
2007-06-01 08:18:28 -07:00
2007-07-11 16:09:09 -07:00
2007-07-15 16:51:54 -07:00
2007-07-11 06:53:45 +02:00
2007-07-10 08:03:34 +02:00
2007-07-13 17:39:59 +01:00
2007-07-11 16:02:10 -07:00
2007-07-13 01:29:51 -04:00
2007-05-24 21:23:24 +10:00
2007-07-13 08:06:19 -07:00
2007-07-10 00:07:49 +02:00
2007-07-11 16:09:09 -07:00
2007-07-12 16:34:30 -07:00
2007-06-24 08:59:10 -07:00
2007-07-15 16:40:52 -07:00
2007-07-15 16:40:52 -07:00
2007-07-15 16:51:54 -07:00
2007-07-15 16:51:54 -07:00
2007-07-11 16:09:06 -07:00
2007-07-11 16:02:10 -07:00
2007-07-16 12:05:44 +03:00
2007-07-12 13:40:20 -07:00
2007-07-13 10:52:27 -07:00
2007-07-11 16:02:10 -07:00
2007-07-15 16:51:54 -07:00
2007-06-24 08:59:11 -07:00
2007-07-11 16:09:06 -07:00
2007-07-12 14:17:12 -07:00
2007-07-10 17:33:04 +01:00
2007-07-15 16:50:46 -07:00
2007-05-21 09:18:19 -07:00
2007-07-11 16:09:06 -07:00
2007-05-27 12:13:53 -04:00
2007-07-12 13:41:29 -07:00
2007-07-11 16:09:09 -07:00
2007-07-06 10:23:43 -07:00
2007-07-15 16:56:12 -07:00
2007-07-11 16:09:09 -07:00
2007-07-12 13:40:20 -07:00
2007-07-15 16:51:54 -07:00
2007-05-31 01:52:53 -07:00
2007-07-15 16:51:54 -07:00
2007-07-12 13:40:57 -07:00
2007-07-11 16:09:09 -07:00
2007-07-12 17:41:07 +01:00
2007-07-15 16:40:51 -07:00
2007-07-12 13:40:57 -07:00
2007-07-15 16:40:52 -07:00
2007-07-11 16:09:09 -07:00
2007-07-10 14:47:59 -07:00
2007-07-10 11:25:44 +01:00
0d551bb698