From: Avi Kivity a...@redhat.com
'pop esp' destroys the stack, avoid it
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/kvm/test/x86/realmode.c b/kvm/test/x86/realmode.c
index bd79348..d0cc3dc 100644
--- a/kvm/test/x86/realmode.c
+++
From: Alex Williamson alex.william...@redhat.com
When supported by the host kernel, we can use read/write on the
PCI sysfs resource file for I/O port regions. This allows us to
avoid raw in/out commands and works with deprivileged guests via
libvirt.
Signed-off-by: Alex Williamson
From: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
Separate pool from the ac_test_t struct, later we will use multiple ac_test_t
units, those units should allocate pte from the same pool to avoid mapping to
the same pte
Signed-off-by: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
Signed-off-by:
From: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
Separate expect status updates operation, later we can just modify the access
way(i,e the AC_ACCESS_* flags)
Signed-off-by: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/kvm/test/lib/libcflat.h b/kvm/test/lib/libcflat.h
index 1da4013..7274fed 100644
--- a/kvm/test/lib/libcflat.h
+++ b/kvm/test/lib/libcflat.h
@@ -39,4 +39,6 @@
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/kvm/test/x86/emulator.c b/kvm/test/x86/emulator.c
index db6a134..476f86f 100644
--- a/kvm/test/x86/emulator.c
+++ b/kvm/test/x86/emulator.c
@@ -220,9 +220,10
From: Avi Kivity a...@redhat.com
pusha needs some stack space, or it will fault. The supplied value of 7 is too
small.
Provide a real stack for pusha.
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/kvm/test/x86/realmode.c
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/kvm/test/lib/libcflat.h b/kvm/test/lib/libcflat.h
index 2e2a8bf..d0d3df2 100644
--- a/kvm/test/lib/libcflat.h
+++ b/kvm/test/lib/libcflat.h
@@ -28,6 +28,10
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/kvm/test/lib/libcflat.h b/kvm/test/lib/libcflat.h
index 7274fed..2e2a8bf 100644
--- a/kvm/test/lib/libcflat.h
+++ b/kvm/test/lib/libcflat.h
@@ -27,6 +27,7 @@
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/kvm/test/lib/x86/processor.h b/kvm/test/lib/x86/processor.h
new file mode 100644
index 000..ea44a9d
--- /dev/null
+++ b/kvm/test/lib/x86/processor.h
@@
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/kvm/test/x86/svm.h b/kvm/test/x86/svm.h
new file mode 100644
index 000..3fdc0d3
--- /dev/null
+++ b/kvm/test/x86/svm.h
@@ -0,0 +1,328 @@
+#ifndef __SVM_H
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/kvm/test/x86/svm.c b/kvm/test/x86/svm.c
index af0e60c..5bb64ff 100644
--- a/kvm/test/x86/svm.c
+++ b/kvm/test/x86/svm.c
@@ -63,6 +63,7 @@ struct test {
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/kvm/test/lib/x86/processor.h b/kvm/test/lib/x86/processor.h
index ea44a9d..0376d04 100644
--- a/kvm/test/lib/x86/processor.h
+++
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/kvm/test/x86/svm.c b/kvm/test/x86/svm.c
index 222356d..3c30118 100644
--- a/kvm/test/x86/svm.c
+++ b/kvm/test/x86/svm.c
@@ -110,6 +110,7 @@ static bool
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/kvm/test/lib/x86/processor.h b/kvm/test/lib/x86/processor.h
index 0376d04..67d7ca5 100644
--- a/kvm/test/lib/x86/processor.h
+++
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/kvm/test/config-x86-common.mak b/kvm/test/config-x86-common.mak
index 00817dc..19bffd4 100644
--- a/kvm/test/config-x86-common.mak
+++
From: Roedel, Joerg joerg.roe...@amd.com
Signed-off-by: Joerg Roedel joerg.roe...@amd.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/kvm/test/x86/svm.c b/kvm/test/x86/svm.c
index cb26af6..628f3aa 100644
--- a/kvm/test/x86/svm.c
+++ b/kvm/test/x86/svm.c
@@ -58,6 +58,7 @@
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/kvm/test/x86/svm.c b/kvm/test/x86/svm.c
index 3c30118..cb26af6 100644
--- a/kvm/test/x86/svm.c
+++ b/kvm/test/x86/svm.c
@@ -3,6 +3,7 @@
#include processor.h
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/kvm/test/x86/svm.c b/kvm/test/x86/svm.c
index 5bb64ff..222356d 100644
--- a/kvm/test/x86/svm.c
+++ b/kvm/test/x86/svm.c
@@ -146,12 +146,36 @@ static bool
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index f774ce3..d84f1f7 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -147,10 +147,8 @@
From: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
Fix:
arch/x86/kvm/mmu.c: In function 'kvm_mmu_pte_write':
arch/x86/kvm/mmu.c:2908: warning: suggest parentheses around operand of '!'
or change '' to '' or '!' to '~'
Reported-by: Stephen Rothwell s...@canb.auug.org.au
Signed-off-by: Xiao
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 00bc73d..373dea3 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -161,12 +161,8 @@
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 5b1d3fb..5106acc 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -238,16 +238,8 @@
From: Avi Kivity a...@redhat.com
vmx does not restore GDT.LIMIT to the host value, instead it sets it to 64KB.
This means host userspace can learn a few bits of host memory.
Fix by reloading GDTR when we load other host state.
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 049d63d..485528b 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -105,7 +105,7 @@
From: Avi Kivity a...@redhat.com
This will hold all the information known about the opcode. Currently, this
is just the decode flags.
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index
From: Avi Kivity a...@redhat.com
The parenthese make is impossible to use the macros with initializers that
require braces.
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index
From: Avi Kivity a...@redhat.com
No code changes.
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 52399c8..2078fb7 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@
From: Avi Kivity a...@redhat.com
Now that we have the host gdt conveniently stored in a variable, make use
of it instead of querying the cpu.
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index
From: Mohammed Gamal m.gamal...@gmail.com
Ths patch adds IRET instruction (opcode 0xcf).
Currently, only IRET in real mode is emulated. Protected mode support is to be
added later if needed.
Signed-off-by: Mohammed Gamal m.gamal...@gmail.com
Reviewed-by: Avi Kivity a...@redhat.com
Reviewed-by:
From: Gleb Natapov g...@redhat.com
No need to update vcpu state since instruction is in the middle of the
emulation.
Signed-off-by: Gleb Natapov g...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7308bb8..c5878d8 100644
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 4d59bb6..dc1ecff 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2017,6 +2017,12
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 8d03a64..576cd9d 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -105,7 +105,7 @@
From: Avi Kivity a...@redhat.com
It doesn't ever change, so we don't need to pass it around everywhere.
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/arch/x86/include/asm/kvm_emulate.h
b/arch/x86/include/asm/kvm_emulate.h
index
From: Avi Kivity a...@redhat.com
Now that the group index no longer exists, the space is free.
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 460e30d..8c75410 100644
---
From: Avi Kivity a...@redhat.com
Instead of having a group number, store the group table pointer directly in
the opcode.
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index
From: Avi Kivity a...@redhat.com
Add a decode flag to indicate the instruction is invalid. Will come in useful
later, when we mix decode bits from the opcode and group table.
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 373dea3..5b1d3fb 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -188,15 +188,9 @@
From: Avi Kivity a...@redhat.com
Move operand decoding to the opcode table, keep lock decoding in the group
table. This allows us to get consolidate the four variants of Group 1 into one
group.
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff
From: Avi Kivity a...@redhat.com
Some instructions are repetitive in the opcode space, add macros for
consolidating them.
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index d84f1f7..00bc73d 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -150,11 +150,9 @@
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 5106acc..ab0845c 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -247,8 +247,7 @@
From: Avi Kivity a...@redhat.com
* upstream: (43 commits)
Initialize a variable in all cases
Fix uint8_t comparison with negative value
Fix a warning on OpenSolaris
Correctly identify multiple cpus in SMP systems
Remove unused constant
jazz led: Fix debug prints
xilinx-s3adsp: Add
From: Joerg Roedel joerg.roe...@amd.com
Signed-off-by: Joerg Roedel joerg.roe...@amd.com
Signed-off-by: Avi Kivity a...@redhat.com
diff --git a/kvm/test/x86/svm.c b/kvm/test/x86/svm.c
index fd98505..2f1c900 100644
--- a/kvm/test/x86/svm.c
+++ b/kvm/test/x86/svm.c
@@ -342,6 +342,21 @@ static bool
From: Joerg Roedel joerg.roe...@amd.com
Signed-off-by: Joerg Roedel joerg.roe...@amd.com
Signed-off-by: Avi Kivity a...@redhat.com
diff --git a/kvm/test/x86/cstart64.S b/kvm/test/x86/cstart64.S
index f1a9d09..46e9d5c 100644
--- a/kvm/test/x86/cstart64.S
+++ b/kvm/test/x86/cstart64.S
@@ -51,6
From: Avi Kivity a...@redhat.com
Test behaviour both with svm enabled and with svm disabled.
Signed-off-by: Avi Kivity a...@redhat.com
diff --git a/kvm/test/x86/unittests.cfg b/kvm/test/x86/unittests.cfg
index f39c5bd..7796e41 100644
--- a/kvm/test/x86/unittests.cfg
+++
From: Joerg Roedel joerg.roe...@amd.com
Signed-off-by: Joerg Roedel joerg.roe...@amd.com
Signed-off-by: Avi Kivity a...@redhat.com
diff --git a/kvm/test/x86/svm.c b/kvm/test/x86/svm.c
index dd4a8da..4a7a662 100644
--- a/kvm/test/x86/svm.c
+++ b/kvm/test/x86/svm.c
@@ -209,6 +209,32 @@ static void
From: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
Mark page dirty only when this page is really written, it's more exacter,
and also can fix dirty page marking in speculation path
Signed-off-by: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
Signed-off-by: Avi Kivity a...@redhat.com
diff --git
From: Gleb Natapov g...@redhat.com
Do not recheck io permission on every iteration.
Signed-off-by: Gleb Natapov g...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
diff --git a/arch/x86/include/asm/kvm_emulate.h
b/arch/x86/include/asm/kvm_emulate.h
index f397b79..3c7dd29 100644
---
From: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
Introduce spte_has_volatile_bits() function to judge whether spte
bits will miss, it's more readable and can help us to cleanup code
later
Signed-off-by: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
Signed-off-by: Avi Kivity a...@redhat.com
diff
From: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
It's a small cleanup that using using kvm_set_pfn_accessed() instead
of mark_page_accessed()
Signed-off-by: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
Signed-off-by: Avi Kivity a...@redhat.com
diff --git a/arch/x86/kvm/mmu.c
On 08/01/2010 04:23 PM, Avi Kivity wrote:
if (c-src.type == OP_MEM) {
+ if (c-d NoAccess)
+ goto no_fetch;
rc = read_emulated(ctxt, ops, c-src.addr.mem,
c-src.valptr, c-src.bytes);
On 08/02/2010 10:28 AM, Paolo Bonzini wrote:
On 08/01/2010 04:23 PM, Avi Kivity wrote:
if (c-src.type == OP_MEM) {
+if (c-d NoAccess)
+goto no_fetch;
rc = read_emulated(ctxt, ops, c-src.addr.mem,
c-src.valptr, c-src.bytes);
On 08/01/2010 05:23 PM, Avi Kivity wrote:
Signed-off-by: Avi Kivitya...@redhat.com
---
arch/x86/kvm/emulate.c |4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index d7d95de..d1a6cd7 100644
--- a/arch/x86/kvm/emulate.c
On 07/27/2010 06:33 AM, Xiao Guangrong wrote:
Introduce spte_bits_lost() function to judge whether spte bits will
miss, it's more readable and can help us to cleanup code later
Signed-off-by: Xiao Guangrongxiaoguangr...@cn.fujitsu.com
---
arch/x86/kvm/mmu.c | 20 +---
1
On 08/02/2010 05:35 AM, Avi Kivity wrote:
LMSW is documented not to be able to set cr0.pe; make it so.
The code is correct, but LMSW is documented not to be able to _clear_
cr0.pe. :)
Paolo
Signed-off-by: Avi Kivitya...@redhat.com
---
arch/x86/kvm/emulate.c |2 +-
1 files changed,
On 07/27/2010 06:35 AM, Xiao Guangrong wrote:
Mark page dirty only when this page is really written, it's more exacter,
and also can fix dirty page marking in speculation path
Signed-off-by: Xiao Guangrongxiaoguangr...@cn.fujitsu.com
---
arch/x86/kvm/mmu.c | 47
On 08/02/2010 10:48 AM, Paolo Bonzini wrote:
On 08/02/2010 05:35 AM, Avi Kivity wrote:
LMSW is documented not to be able to set cr0.pe; make it so.
The code is correct, but LMSW is documented not to be able to _clear_
cr0.pe. :)
Right, thinko.
--
error compiling committee.c: too many
Avi Kivity wrote:
On 07/27/2010 06:33 AM, Xiao Guangrong wrote:
Introduce spte_bits_lost() function to judge whether spte bits will
miss, it's more readable and can help us to cleanup code later
Signed-off-by: Xiao Guangrongxiaoguangr...@cn.fujitsu.com
---
arch/x86/kvm/mmu.c | 20
Avi Kivity wrote:
On 07/27/2010 06:35 AM, Xiao Guangrong wrote:
Mark page dirty only when this page is really written, it's more exacter,
and also can fix dirty page marking in speculation path
Signed-off-by: Xiao Guangrongxiaoguangr...@cn.fujitsu.com
---
arch/x86/kvm/mmu.c | 47
On Mon, Aug 02, 2010 at 08:04:20AM +0300, Avi Kivity wrote:
On 08/01/2010 04:27 PM, Gleb Natapov wrote:
When we are going to enable e_i_g_s by default?
Optimistically, 2.6.37, so six months.
May be we have enough
time to fix userspace?
Sure we do, but will users update?
0.12 is
On 08/02/2010 10:58 AM, Gleb Natapov wrote:
On Mon, Aug 02, 2010 at 08:04:20AM +0300, Avi Kivity wrote:
On 08/01/2010 04:27 PM, Gleb Natapov wrote:
When we are going to enable e_i_g_s by default?
Optimistically, 2.6.37, so six months.
May be we have enough
time to fix userspace?
Sure we
On 02.08.2010, at 07:49, Kevin O'Connor wrote:
On Mon, Aug 02, 2010 at 10:41:39AM +0800, Liu, Jinsong wrote:
Kevin,
This patch still has issue, It can boot Windows 2008 DataCenter,
however, when run cpu_set cpu online command, windows 2008
Datacenter system shutdown at once.
Thanks for
It's a small cleanup that using using kvm_set_pfn_accessed() instead
of mark_page_accessed()
Signed-off-by: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
---
arch/x86/kvm/mmu.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index
On Mon, Aug 02, 2010 at 11:03:26AM +0300, Avi Kivity wrote:
On 08/02/2010 10:58 AM, Gleb Natapov wrote:
On Mon, Aug 02, 2010 at 08:04:20AM +0300, Avi Kivity wrote:
On 08/01/2010 04:27 PM, Gleb Natapov wrote:
When we are going to enable e_i_g_s by default?
Optimistically, 2.6.37, so six
Introduce spte_has_volatile_bits() function to judge whether spte
bits will miss, it's more readable and can help us to cleanup code
later
Signed-off-by: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
---
arch/x86/kvm/mmu.c | 20 +---
1 files changed, 17 insertions(+), 3
Mark page dirty only when this page is really written, it's more exacter,
and also can fix dirty page marking in speculation path
Signed-off-by: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
---
arch/x86/kvm/mmu.c | 47 ---
1 files changed, 28
On 08/02/2010 11:17 AM, Gleb Natapov wrote:
We don't know what they'll do. API stability means we only change
things to fix bugs.
Is this API documented? Do we guaranty somewhere anywhere that rip during io
point past the instruction? I think it should be documented that cpu
state cannot be
On 07/26/2010 08:19 PM, Jeremy Fitzhardinge wrote:
On 07/25/2010 11:14 PM, Srivatsa Vaddagiri wrote:
Add KVM hypercall for yielding vcpu timeslice.
Can you do a directed yield?
A problem with directed yield is figuring out who to yield to. One idea
is to look for a random vcpu that is
On Mon, Aug 02, 2010 at 11:24:14AM +0300, Avi Kivity wrote:
On 08/02/2010 11:17 AM, Gleb Natapov wrote:
We don't know what they'll do. API stability means we only change
things to fix bugs.
Is this API documented? Do we guaranty somewhere anywhere that rip during io
point past the
On 07/28/2010 05:55 PM, Srivatsa Vaddagiri wrote:
On Mon, Jul 26, 2010 at 10:19:41AM -0700, Jeremy Fitzhardinge wrote:
On 07/25/2010 11:14 PM, Srivatsa Vaddagiri wrote:
Add KVM hypercall for yielding vcpu timeslice.
Can you do a directed yield?
We don't have that support yet in Linux
On 07/26/2010 09:15 AM, Srivatsa Vaddagiri wrote:
Paravirtual spinlock implementation for KVM guests, based heavily on Xen guest's
spinlock implementation.
+
+static struct spinlock_stats
+{
+ u64 taken;
+ u32 taken_slow;
+
+ u64 released;
+
+#define HISTO_BUCKETS 30
+
On 07/26/2010 09:11 AM, Srivatsa Vaddagiri wrote:
This patch-series implements paravirt-spinlock implementation for KVM guests,
based heavily on Xen's implementation. I tried to refactor Xen's spinlock
implementation to make it common for both Xen and KVM - but found that
few differences
On 07/26/2010 09:15 AM, Srivatsa Vaddagiri wrote:
Paravirtual spinlock implementation for KVM guests, based heavily on Xen guest's
spinlock implementation.
+static void kvm_spin_unlock(struct arch_spinlock *lock)
+{
+ struct kvm_spinlock *sl = (struct kvm_spinlock *)lock;
+
+
On 08/02/2010 11:34 AM, Gleb Natapov wrote:
On Mon, Aug 02, 2010 at 11:24:14AM +0300, Avi Kivity wrote:
On 08/02/2010 11:17 AM, Gleb Natapov wrote:
We don't know what they'll do. API stability means we only change
things to fix bugs.
Is this API documented? Do we guaranty somewhere
On Sun, Aug 01, 2010, Gleb Natapov wrote about Re: [PATCH 7/24] Understanding
guest pointers to vmcs12 structures:
Guest can use any valid virtual address. There is UNMAPPED_GVA (~(gpa_t)0)
which
at least cannot be valid if address that your function returns have to be
page aligned.
Thanks.
On Mon, Aug 02, 2010 at 11:54:58AM +0300, Avi Kivity wrote:
On 08/02/2010 11:34 AM, Gleb Natapov wrote:
On Mon, Aug 02, 2010 at 11:24:14AM +0300, Avi Kivity wrote:
On 08/02/2010 11:17 AM, Gleb Natapov wrote:
We don't know what they'll do. API stability means we only change
things to fix
I'm hitting some migration issues merging qemu.git into qemu-kvm.git:
1. Crash in mig_cancel test:
(gdb) bt
#0 0x003a91c83dbb in memcpy () from /lib64/libc.so.6
#1 0x0049c2ff in qemu_get_buffer (f=0x302d870, buf=value
optimized out, size1=4096) at /usr/include/bits/string3.h:52
On 08/02/2010 12:05 PM, Gleb Natapov wrote:
We did it with unmapped pages in the middles of the slot recently.
What guests did we break?
The one that uses device assignment with old qemu-kvm userspace. Old
qemu-kvm copied assigned card's ROM into memory and made it read
only (mprotect(RO))
Hello,
From: pradeepkumar psuri...@linux.vnet.ibm.com
Subject: Re: Disable EPT
On Mon, 02 Aug 2010 10:46:13 +0900 (JST)
Kuniyasu Suzaki k.suz...@aist.go.jp wrote:
Please tell me how to disable EPT of KVM.
Can I disable EPT in BIOS menu? I did not find the option in BIOS menu
of
My linux is rhel 5.4. In it, the version of kvm is 83 and the qemu is
0.9.1. Virt-manager use /usr/libexec/qemu-kvm to manage VMs.
Now, I want to use the higher version of kvm, so I download
qemu-kvm-0.12.4.tar.gz.
tar xvf qemu-kvm-0.12.4.tar.gz
cd qemu-kvm-0.12.4
./configure --prefix=/usr/
make
On 08/02/2010 12:06 PM, Avi Kivity wrote:
I'm hitting some migration issues merging qemu.git into qemu-kvm.git:
1. Crash in mig_cancel test:
(gdb) bt
#0 0x003a91c83dbb in memcpy () from /lib64/libc.so.6
#1 0x0049c2ff in qemu_get_buffer (f=0x302d870, buf=value
optimized out,
Kuniyasu Suzaki wrote:
Hello,
From: pradeepkumar psuri...@linux.vnet.ibm.com
Subject: Re: Disable EPT
On Mon, 02 Aug 2010 10:46:13 +0900 (JST)
Kuniyasu Suzaki k.suz...@aist.go.jp wrote:
Please tell me how to disable EPT of KVM.
Can I disable EPT in BIOS menu? I did not
On 08/02/2010 11:12 AM, Xiao Guangrong wrote:
It's a small cleanup that using using kvm_set_pfn_accessed() instead
of mark_page_accessed()
Applied all of v2, thanks.
--
error compiling committee.c: too many arguments to function
--
To unsubscribe from this list: send the line unsubscribe
Zachary Amsden wrote:
On 07/28/2010 02:25 AM, Andre Przywara wrote:
Andre Przywara wrote:
Andre Przywara wrote:
Avi Kivity wrote:
On 07/27/2010 04:48 PM, Andre Przywara wrote:
Wierd. Maybe the clock goes crazy.
Let's see if it jumps forward alot:
} while (unlikely(last !=
Hi guys,
I'm having a problem with kvm, my physical machine have 2 processor
Xeon E5520, with 8 mb cache size, when i run cat /proc/cpuinfo the
linux shows 16 processors equal.
processor : 15
vendor_id : GenuineIntel
cpu family : 6
model : 26
model name : Intel(R)
Hi,
On Mon, Jun 14, 2010, Avi Kivity wrote about Re: [PATCH 7/24] Understanding
guest pointers to vmcs12 structures:
On 06/13/2010 03:26 PM, Nadav Har'El wrote:
This patch includes a couple of utility functions for extracting pointer
operands of VMX instructions issued by L1 (a guest
Ricardo Martins wrote:
Hi guys,
I'm having a problem with kvm, my physical machine have 2 processor
Xeon E5520, with 8 mb cache size, when i run cat /proc/cpuinfo the
linux shows 16 processors equal.
processor : 15
vendor_id : GenuineIntel
cpu family : 6
model : 26
On 08/02/2010 03:51 PM, Andre Przywara wrote:
Ricardo Martins wrote:
Hi guys,
I'm having a problem with kvm, my physical machine have 2 processor
Xeon E5520, with 8 mb cache size, when i run cat /proc/cpuinfo the
linux shows 16 processors equal.
processor : 15
vendor_id :
On Mon, 2010-08-02 at 12:42 +0300, Avi Kivity wrote:
On 08/02/2010 12:06 PM, Avi Kivity wrote:
I'm hitting some migration issues merging qemu.git into qemu-kvm.git:
1. Crash in mig_cancel test:
(gdb) bt
#0 0x003a91c83dbb in memcpy () from /lib64/libc.so.6
#1
On 08/02/2010 04:12 PM, Alex Williamson wrote:
On Mon, 2010-08-02 at 12:42 +0300, Avi Kivity wrote:
On 08/02/2010 12:06 PM, Avi Kivity wrote:
I'm hitting some migration issues merging qemu.git into qemu-kvm.git:
1. Crash in mig_cancel test:
(gdb) bt
#0 0x003a91c83dbb in memcpy ()
On 08/02/2010 12:06 PM, Avi Kivity wrote:
2. Intermittent migration failures
Likely suspect is the IDE migration fixes. A merge of the commit just
before these changes passes the test, I'm now testing the commit
immediately after the changes.
Looks like this was a byproduct of the
This patch cleanups rmap_write_protect() as follows:
1.
The BUG_ON(!spte)'s right after while(spte) have been there unchanged for
a long time. Since we don't see any special reason why we do this double
check, we remove these BUG_ON's.
2.
In the case of Y and Z are single-bit-set masks,
Signed-off-by: Joerg Roedel joerg.roe...@amd.com
---
kvm/test/x86/svm.c | 29 +
1 files changed, 29 insertions(+), 0 deletions(-)
diff --git a/kvm/test/x86/svm.c b/kvm/test/x86/svm.c
index dd4a8da..4a7a662 100644
--- a/kvm/test/x86/svm.c
+++ b/kvm/test/x86/svm.c
@@
Hi Avi, Marcelo,
here are 3 additional nested svm tests. The first two test the
features/fixes I posted last week for nested svm. To keep the rate of
only 66.7% passing tests I added the asid_zero test which currently
fails ;-)
I will post patches to fix the vmrun_intercept and asid_zero test
Signed-off-by: Joerg Roedel joerg.roe...@amd.com
---
kvm/test/x86/cstart64.S |5 ++
kvm/test/x86/svm.c | 109 +++
kvm/test/x86/types.h| 20 +
3 files changed, 134 insertions(+), 0 deletions(-)
create mode 100644
Signed-off-by: Joerg Roedel joerg.roe...@amd.com
---
kvm/test/x86/svm.c | 17 +
1 files changed, 17 insertions(+), 0 deletions(-)
diff --git a/kvm/test/x86/svm.c b/kvm/test/x86/svm.c
index fd98505..2f1c900 100644
--- a/kvm/test/x86/svm.c
+++ b/kvm/test/x86/svm.c
@@ -342,6
This is correct since vmrun with asid 0 is not allowed.
Signed-off-by: Joerg Roedel joerg.roe...@amd.com
---
kvm/test/x86/svm.c |1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/kvm/test/x86/svm.c b/kvm/test/x86/svm.c
index 628f3aa..dd4a8da 100644
--- a/kvm/test/x86/svm.c
On 08/02/2010 03:25 PM, Nadav Har'El wrote:
+ /* offfset = Base + [Index * Scale] + Displacement */
+ addr = vmx_get_segment_base(vcpu, seg_reg);
+ if (base_is_valid)
+ addr += kvm_register_read(vcpu, base_reg);
+ if (index_is_valid)
+ addr
On Tue, Jul 06, 2010, Dong, Eddie wrote about RE: [PATCH 8/24] Hold a vmcs02
for each vmcs12:
+/* Allocate an L0 VMCS (vmcs02) for the current L1 VMCS (vmcs12), if
one + * does not already exist. The allocation is done in L0 memory,
...
+static int nested_create_current_vmcs(struct kvm_vcpu
1 - 100 of 194 matches
Mail list logo