* Cyrill Gorcunov gorcu...@gmail.com wrote:
On Mon, Dec 19, 2011 at 09:13:28AM +0200, Pekka Enberg wrote:
- BUILD_BUG_ON(i E820_X_MAX);
+ assert(i = E820_X_MAX);
We should use BUG_ON() like tools/perf does.
We dont have it yet. So I'll introduce this helper later,
but note
On Mon, Dec 19, 2011 at 09:13:28AM +0200, Pekka Enberg wrote:
- BUILD_BUG_ON(i E820_X_MAX);
+ assert(i = E820_X_MAX);
We should use BUG_ON() like tools/perf does.
On Mon, Dec 19, 2011 at 9:57 AM, Cyrill Gorcunov gorcu...@gmail.com wrote:
We dont have it yet. So I'll introduce this
On Mon, Dec 19, 2011 at 10:19:43AM +0200, Pekka Enberg wrote:
On Mon, Dec 19, 2011 at 09:13:28AM +0200, Pekka Enberg wrote:
- BUILD_BUG_ON(i E820_X_MAX);
+ assert(i = E820_X_MAX);
We should use BUG_ON() like tools/perf does.
On Mon, Dec 19, 2011 at 9:57 AM, Cyrill Gorcunov
On 12/19/2011 04:39 AM, Takuya Yoshikawa wrote:
(2011/12/16 19:15), Xiao Guangrong wrote:
-static void mmu_page_add_parent_pte(struct kvm_vcpu *vcpu,
-struct kvm_mmu_page *sp, u64 *parent_pte)
+static void mmu_page_add_set_parent_pte(struct kvm_vcpu *vcpu,
+
On Mon, 19 Dec 2011 10:50:13 +0800, Amos Kong ak...@redhat.com wrote:
The format is broken in webpage, attached the result file.
it's also available here: http://amosk.info/download/rusty-fix-perf.txt
Thanks Amos.
Linus, please apply. Fixes virtio-mmio without breaking virtio_pci
performance.
On 14/12/11 09:06, Kevin O'Connor wrote:
On Tue, Dec 06, 2011 at 07:32:55PM -0500, Amos Kong wrote:
- Original Message -
On Tue, Dec 06, 2011 at 01:39:35PM +0800, Amos Kong wrote:
Only func 0 is registered to guest driver (we can
only found func 0 in slot-funcs list of driver),
the
On 12/16/2011 04:58 PM, Takuya Yoshikawa wrote:
I'm not sure this is a meaningful test to verify this change is
worthwhile, because while the shrinker tries to free a shadow page from
one vm, the vm's position in the kvm list is changed, so the over time
the shrinker will cycle over all
On Mon, Dec 19, 2011 at 10:25 AM, Cyrill Gorcunov gorcu...@gmail.com wrote:
You don't need to convert all of them at the same time but we're not
adding new assert() calls.
You both (Pekka and Ingo) know the way how to convince people ;)
Something like below?
Perfect! I'll apply it later
于 2011/12/19,星期一 15:26, Amit Shah 写道:
On (Mon) 19 Dec 2011 [14:09:43], Zang Hongyong wrote:
于 2011/12/16,星期五 17:39, Amit Shah 写道:
On (Fri) 16 Dec 2011 [09:14:26], zanghongy...@huawei.com wrote:
From: Hongyong Zangzanghongy...@huawei.com
In pci_enable_msix(), the guest's virtio-serial driver
(2011/12/19 17:43), Avi Kivity wrote:
Well, if one guest is twice as large as other guests, then it will want
twice as many shadow pages. So our goal should be to zap pages from the
guest with the highest (shadow pages / memory) ratio.
Can you measure whether there is a significant
On 12/19/2011 11:22 AM, Takuya Yoshikawa wrote:
Yes, it's very conservative. But on the other hand the shrinker is
tuned for dcache and icache, where there are usually tons of useless
objects. If we have to free something, I'd rather free them instead of
mmu pages which tend to get recreated
(2011/12/19 18:26), Avi Kivity wrote:
On 12/19/2011 11:22 AM, Takuya Yoshikawa wrote:
Yes, it's very conservative. But on the other hand the shrinker is
tuned for dcache and icache, where there are usually tons of useless
objects. If we have to free something, I'd rather free them instead of
On 12/19/2011 11:56 AM, Takuya Yoshikawa wrote:
(2011/12/19 18:26), Avi Kivity wrote:
On 12/19/2011 11:22 AM, Takuya Yoshikawa wrote:
Yes, it's very conservative. But on the other hand the shrinker is
tuned for dcache and icache, where there are usually tons of useless
objects. If we have
ping?
(still happens, latest git commit is
fcfeed4a398a8524ce8f84eaaba984bd9c27354e )
On 11/20/2011 09:01 PM, Yaniv Kaul wrote:
Latest git hash 1d1c8a498b7ce5c5636f1014f7ad18aa4e1acc0a (though I
think it happened before that).
./configure command line:
--target-list=x86_64-softmmu
(2011/12/19 19:03), Avi Kivity wrote:
IMO, The goal should be restricted to emergencies.
So possible solution may be:
- we set the tuning parameters as conservative as possible
- pick up a guest with relatively high ratio
(I have to think more how to achieve this)
- move
On 12/19/2011 12:21 PM, Takuya Yoshikawa wrote:
(2011/12/19 19:03), Avi Kivity wrote:
IMO, The goal should be restricted to emergencies.
So possible solution may be:
- we set the tuning parameters as conservative as possible
- pick up a guest with relatively high ratio
(I
* Cyrill Gorcunov gorcu...@gmail.com wrote:
+#
+#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 -
2*!!(condition)]))
+#define BUG_ON(condition)assert(!(condition))
Just a sidenote, the patch is fine but the above will result in
weird double negated assertion messages.
it's
On Mon, Dec 19, 2011 at 11:40:09AM +0100, Ingo Molnar wrote:
GDB will catch that signal.
Yeah, good point! Pekka, drop this patch please, I'll make new one at evening.
Cyrill
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to
* Cyrill Gorcunov gorcu...@gmail.com wrote:
On Mon, Dec 19, 2011 at 11:40:09AM +0100, Ingo Molnar wrote:
GDB will catch that signal.
Yeah, good point! Pekka, drop this patch please, I'll make new one at evening.
Patch is good as-is IMO - assert() was used before so it's not a
* Cyrill Gorcunov gorcu...@gmail.com wrote:
On Mon, Dec 19, 2011 at 11:40:09AM +0100, Ingo Molnar wrote:
GDB will catch that signal.
Yeah, good point! Pekka, drop this patch please, I'll make new one at evening.
On Mon, 19 Dec 2011, Ingo Molnar wrote:
Patch is good as-is IMO - assert()
On Mon, Dec 19, 2011 at 11:50:31AM +0100, Ingo Molnar wrote:
...
The tool-specific BUG() implementation can be added as a delta
on top of that. It's in fact better to keep those two steps
separate.
OK, will do on top.
Cyrill
--
To unsubscribe from this list: send the line
On 2011-12-19 11:14, Yaniv Kaul wrote:
ping?
(still happens, latest git commit is
fcfeed4a398a8524ce8f84eaaba984bd9c27354e )
Tried this on a clean build repositor? If that doesn't help, check out
of tree building.
Jan
--
Siemens AG, Corporate Technology, CT T DE IT 1
Corporate Competence
I have found a number of threads from 2007/2008 in the mailing list
archives discussing patches for PVDMA support in KVM. From looking at
the latest kernel source, it does not look like this feature is
present.
Can anybody provide a status on PVDMA support?
Thanks,
Steve
--
To unsubscribe from
On 12/19/2011 01:57 PM, Stephen Doyle wrote:
I have found a number of threads from 2007/2008 in the mailing list
archives discussing patches for PVDMA support in KVM. From looking at
the latest kernel source, it does not look like this feature is
present.
Can anybody provide a status on
On (Thu) 15 Dec 2011 [13:55:15], Avi Kivity wrote:
On 12/08/2011 01:34 PM, Amit Shah wrote:
On (Mon) 05 Dec 2011 [15:18:59], Eric B Munson wrote:
When a guest kernel is stopped by the host hypervisor it can look like a
soft
lockup to the guest kernel. This false warning can mask
On 23.11.2011, at 13:47, Marcelo Tosatti wrote:
On Wed, Nov 16, 2011 at 12:45:45AM +0100, Alexander Graf wrote:
On 10.11.2011, at 18:35, Marcelo Tosatti wrote:
On Thu, Nov 10, 2011 at 05:49:42PM +0100, Alexander Graf wrote:
Documentation/virtual/kvm/api.txt | 47
On 12/16/2011 11:31 AM, Marcelo Tosatti wrote:
Slow enough that progress of the watchdog thread is unable to keep up
with timer interrupt processing. This is considered a hang and
should be reported.
It's not a guest hang though!
No, but your host system is in such a load state
On 12/19/2011 02:52 PM, Amit Shah wrote:
On (Thu) 15 Dec 2011 [13:55:15], Avi Kivity wrote:
On 12/08/2011 01:34 PM, Amit Shah wrote:
On (Mon) 05 Dec 2011 [15:18:59], Eric B Munson wrote:
When a guest kernel is stopped by the host hypervisor it can look like
a soft
lockup to the
On 12/15/2011 08:53 PM, Eric B Munson wrote:
I am working on V7 to incorporate the __this_cpu_and suggestion, would you
consider that for inclusion and we can continue discussing the need for the
preemption notification work?
Okay.
I think that having a guest complain when the
host is so
Sometime, we need to test with guest(s) which have static ip
address(es).
eg. No real/emulated DHCP server in test environment.
eg. Test with old image we don't want to change the net config.
eg. Test when DHCP exists problem.
This is an example of using static ip address:
1. edit ifcfg-eth0 of
On 29.11.2011, at 02:20, Scott Wood wrote:
The associativity, not just total size, can differ from the host
hardware.
Signed-off-by: Scott Wood scottw...@freescale.com
Thanks, applied to kvm-ppc-next.
Alex
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a
On 29.11.2011, at 02:20, Scott Wood wrote:
From: Liu Yu yu@freescale.com
Missing patch description.
Alex
Signed-off-by: Liu Yu yu@freescale.com
[scottw...@freescale.com: made mas2 64-bit, and added mas8 init]
Signed-off-by: Scott Wood scottw...@freescale.com
---
On Sun, Dec 18, 2011 at 03:25:48PM -0600, Nate Custer wrote:
On Dec 16, 2011, at 2:29 PM, Vivek Goyal wrote:
Thanks for testing it Nate. I did some debugging and found out that patch
is doing double free on per cpu pointer hence the crash you are running
into. I could reproduce this
On 02.12.2011, at 07:22, Liu Yu wrote:
Currently we patch the whole code include paravirt template code.
This isn't safe for scratch area and has impact to performance.
Signed-off-by: Liu Yu yu@freescale.com
Thanks, applied to kvm-ppc-next. Please CC kvm@vger for KVM related patches in
On 04.12.2011, at 19:25, Raghavendra K T wrote:
Update the kvm kernel headers to the 3.2.0-rc1 post using
scripts/update-linux-headers.sh script.
Signed-off-by: Raghavendra K T raghavendra...@linux.vnet.ibm.com
---
diff --git a/linux-headers/asm-powerpc/kvm.h
On 04.12.2011, at 19:26, Raghavendra K T wrote:
Update the kernel header that adds a hypercall to support pv-ticketlocks.
Signed-off-by: Raghavendra K T raghavendra...@linux.vnet.ibm.com
---
diff --git a/linux-headers/asm-x86/kvm_para.h
b/linux-headers/asm-x86/kvm_para.h
You're patching
On 04.12.2011, at 19:26, Raghavendra K T wrote:
Extend the KVM Hypervisor to enable KICK_VCPU feature that allows
a vcpu to kick the halted vcpu to continue with execution in PV ticket
spinlock.
Signed-off-by: Srivatsa Vaddagiri va...@linux.vnet.ibm.com
Signed-off-by: Raghavendra K T
This patch series is really a work in progress, but is mature enough to
cover most of the different modules we have in the tool, and receive
comments regarding the work done so far and any future work.
There were three main goals while doing this work:
1. Less die(), more clean exits. We are not
Signed-off-by: Sasha Levin levinsasha...@gmail.com
---
tools/kvm/builtin-run.c | 38 ++
1 files changed, 30 insertions(+), 8 deletions(-)
diff --git a/tools/kvm/builtin-run.c b/tools/kvm/builtin-run.c
index 524ca16..0234879 100644
---
Fixes include:
- Error handling
- Cleanup
- Standard init/uninit
Signed-off-by: Sasha Levin levinsasha...@gmail.com
---
tools/kvm/builtin-run.c| 31 ++---
tools/kvm/include/kvm/symbol.h |7 +++-
tools/kvm/symbol.c | 59
Fixes include:
- Error handling
- Cleanup
- Standard init/uninit
Signed-off-by: Sasha Levin levinsasha...@gmail.com
---
tools/kvm/builtin-run.c | 10 +-
tools/kvm/include/kvm/irq.h |3 ++-
tools/kvm/x86/irq.c | 35 ---
3 files
Fixes include:
- Error handling
- Cleanup
- Standard init/uninit
Signed-off-by: Sasha Levin levinsasha...@gmail.com
---
tools/kvm/builtin-run.c | 35 ++-
tools/kvm/framebuffer.c |9 -
tools/kvm/hw/vesa.c |
Fixes include:
- Error handling
- Cleanup
- Standard init/uninit
Signed-off-by: Sasha Levin levinsasha...@gmail.com
---
tools/kvm/builtin-run.c | 11 ++
tools/kvm/hw/pci-shmem.c|7 +++-
tools/kvm/hw/vesa.c |6 +++-
Fixes include:
- Error handling
- Cleanup
- Standard init/uninit
Signed-off-by: Sasha Levin levinsasha...@gmail.com
---
tools/kvm/builtin-run.c | 12 ++-
tools/kvm/include/kvm/ioeventfd.h |8 +-
tools/kvm/ioeventfd.c | 158 ++---
Fixes include:
- Error handling
- Cleanup
- Standard init/uninit
Signed-off-by: Sasha Levin levinsasha...@gmail.com
---
tools/kvm/builtin-run.c | 11 -
tools/kvm/hw/serial.c | 43 ++
tools/kvm/include/kvm/8250-serial.h |
Fixes include:
- Error handling
- Cleanup
- Standard init/uninit
Signed-off-by: Sasha Levin levinsasha...@gmail.com
---
tools/kvm/builtin-run.c |8
tools/kvm/include/kvm/kvm.h |3 ++-
tools/kvm/powerpc/kvm.c |9 -
Fixes include:
- Error handling
- Cleanup
- Standard init/uninit
Signed-off-by: Sasha Levin levinsasha...@gmail.com
---
tools/kvm/builtin-run.c | 10 ++-
tools/kvm/include/kvm/pci.h |5 ++-
tools/kvm/pci.c | 58 +++
3 files
Fixes include:
- Error handling
- Cleanup
- Standard init/uninit
Signed-off-by: Sasha Levin levinsasha...@gmail.com
---
tools/kvm/builtin-run.c| 27 +---
tools/kvm/disk/blk.c | 13 --
tools/kvm/disk/core.c | 76
Fixes include:
- Error handling
- Cleanup
- Standard init/uninit
Signed-off-by: Sasha Levin levinsasha...@gmail.com
---
tools/kvm/builtin-run.c | 10 +-
tools/kvm/hw/rtc.c | 27 +++
tools/kvm/include/kvm/rtc.h |5 -
3 files changed, 36
On 12/19/2011 03:54 PM, Alexander Graf wrote:
On 04.12.2011, at 19:26, Raghavendra K T wrote:
Extend the KVM Hypervisor to enable KICK_VCPU feature that allows
a vcpu to kick the halted vcpu to continue with execution in PV ticket
spinlock.
Signed-off-by: Srivatsa Vaddagiri
Fixes include:
- Error handling
- Cleanup
- Standard init/uninit
Signed-off-by: Sasha Levin levinsasha...@gmail.com
---
tools/kvm/builtin-run.c |8 ++-
tools/kvm/include/kvm/kvm.h |6 +-
tools/kvm/include/kvm/virtio-pci.h |1 +
On 19.12.2011, at 14:59, Avi Kivity wrote:
On 12/19/2011 03:54 PM, Alexander Graf wrote:
On 04.12.2011, at 19:26, Raghavendra K T wrote:
Extend the KVM Hypervisor to enable KICK_VCPU feature that allows
a vcpu to kick the halted vcpu to continue with execution in PV ticket
spinlock.
On 2011-12-19 15:03, Alexander Graf wrote:
On 19.12.2011, at 14:59, Avi Kivity wrote:
On 12/19/2011 03:54 PM, Alexander Graf wrote:
On 04.12.2011, at 19:26, Raghavendra K T wrote:
Extend the KVM Hypervisor to enable KICK_VCPU feature that allows
a vcpu to kick the halted vcpu to continue
cpu_get_physical_page_desc() exposes the internals of the memory core to
callers; as such it prevents the refactoring planned there. This patchset
converts all callers memory API equivalents and removes the function.
The conversion leaves a lot of potential for further cleanups; the
Signed-off-by: Avi Kivity a...@redhat.com
---
memory.c |8
memory.h | 10 ++
2 files changed, 18 insertions(+), 0 deletions(-)
diff --git a/memory.c b/memory.c
index d8b7c27..6fd31d4 100644
--- a/memory.c
+++ b/memory.c
@@ -831,6 +831,7 @@ void
Given a bus device, retrieves the memory address space for its bus.
Signed-off-by: Avi Kivity a...@redhat.com
---
hw/sysbus.c |5 +
hw/sysbus.h |1 +
2 files changed, 6 insertions(+), 0 deletions(-)
diff --git a/hw/sysbus.c b/hw/sysbus.c
index b315a8c..492a7c6 100644
---
Add an API that allows a client to observe changes in the global
memory map:
- region added (possibly with logging enabled)
- region removed (possibly with logging enabled)
- logging started on a region
- logging stopped on a region
- global logging started
- global logging removed
This API
This is a layering violation, but needed while the code contains
naked calls to qemu_get_ram_ptr() and the like.
Signed-off-by: Avi Kivity a...@redhat.com
---
memory.c |6 ++
memory.h | 10 ++
2 files changed, 16 insertions(+), 0 deletions(-)
diff --git a/memory.c b/memory.c
Signed-off-by: Avi Kivity a...@redhat.com
---
memory.c |5 +
memory.h |9 +
2 files changed, 14 insertions(+), 0 deletions(-)
diff --git a/memory.c b/memory.c
index 6fd31d4..c57b7de 100644
--- a/memory.c
+++ b/memory.c
@@ -1073,6 +1073,11 @@ bool
cpu_get_physical_page_desc() is tied into the memory core's
innards, replace it with uses of the API.
Signed-off-by: Avi Kivity a...@redhat.com
---
hw/framebuffer.c | 30 +-
hw/framebuffer.h |3 +++
hw/milkymist-vgafb.c |2 +-
hw/omap_lcdc.c |
Given an address space (represented by the top-level memory region),
returns the memory region that maps a given range. Useful for implementing
DMA.
The implementation is a simplistic binary search. Once we have a tree
representation this can be optimized.
Signed-off-by: Avi Kivity
Replace with memory API equivalent.
Signed-off-by: Avi Kivity a...@redhat.com
---
hw/framebuffer.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/hw/framebuffer.c b/hw/framebuffer.c
index 3f4e773..b43bcdf 100644
--- a/hw/framebuffer.c
+++ b/hw/framebuffer.c
@@ -50,7
Signed-off-by: Avi Kivity a...@redhat.com
---
memory.c |5 +
memory.h |9 +
2 files changed, 14 insertions(+), 0 deletions(-)
diff --git a/memory.c b/memory.c
index ee9053a..2e5ff43 100644
--- a/memory.c
+++ b/memory.c
@@ -1107,6 +1107,11 @@ bool
Signed-off-by: Avi Kivity a...@redhat.com
---
trace-events |2 +-
xen-all.c| 137 ++
2 files changed, 81 insertions(+), 58 deletions(-)
diff --git a/trace-events b/trace-events
index bf1cf57..728df97 100644
--- a/trace-events
+++
This reaches into the innards of the memory core, which are being
changed. Switch to a memory API version.
Signed-off-by: Avi Kivity a...@redhat.com
---
target-sparc/mmu_helper.c |5 -
1 files changed, 4 insertions(+), 1 deletions(-)
diff --git a/target-sparc/mmu_helper.c
This reaches into the innards of the memory core, which are being
changed. Switch to a memory API version.
Signed-off-by: Avi Kivity a...@redhat.com
---
kvm-all.c | 27 ++-
1 files changed, 10 insertions(+), 17 deletions(-)
diff --git a/kvm-all.c b/kvm-all.c
index
Xen currently uses the name of a memory region to determine whether it
is the framebuffer. Replace with an explicit API.
Signed-off-by: Avi Kivity a...@redhat.com
---
hw/vga.c |2 ++
hw/xen.h |3 +++
xen-all.c |6 ++
xen-stub.c |4
4 files changed, 15
No longer used.
Signed-off-by: Avi Kivity a...@redhat.com
---
cpu-common.h |1 -
exec.c | 11 ---
2 files changed, 0 insertions(+), 12 deletions(-)
diff --git a/cpu-common.h b/cpu-common.h
index eee2faf..3fe44d2 100644
--- a/cpu-common.h
+++ b/cpu-common.h
@@ -38,7 +38,6 @@
This simplifies a later switch to the memory API in slot management.
Signed-off-by: Avi Kivity a...@redhat.com
---
kvm-all.c | 29 +
kvm.h |4 ++--
memory.c |6 +++---
target-i386/kvm.c |7 +++
4 files changed, 25
No longer used.
Signed-off-by: Avi Kivity a...@redhat.com
---
cpu-all.h |6 --
cpu-common.h| 23
exec-obsolete.h |3 -
exec.c | 169 ++-
memory.c| 12
5 files changed, 5 insertions(+), 208
This reaches into the innards of the memory core, which are being
changed. Switch to a memory API version.
Signed-off-by: Avi Kivity a...@redhat.com
---
hw/vhost.c | 47 +++
hw/vhost.h |2 ++
2 files changed, 41 insertions(+), 8 deletions(-)
This reaches into the innards of the memory core, which are being
changed. Switch to a memory API version.
Signed-off-by: Avi Kivity a...@redhat.com
---
hw/virtio-balloon.c | 14 ++
1 files changed, 10 insertions(+), 4 deletions(-)
diff --git a/hw/virtio-balloon.c
---
memory.c |7 ---
1 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/memory.c b/memory.c
index c08186d..2dcbf80 100644
--- a/memory.c
+++ b/memory.c
@@ -708,13 +708,13 @@ static void memory_listener_update_region(FlatRange *fr,
AddressSpace *as,
.address_space =
Drop the use of cpu_register_phys_memory_client() in favour of the new
MemoryListener API. The new API simplifies the caller, since there is no
need to deal with splitting and merging slots; however this is not exploited
in this patch.
Signed-off-by: Avi Kivity a...@redhat.com
---
kvm-all.c |
Drop the use of cpu_register_phys_memory_client() in favour of the new
MemoryListener API. The new API simplifies the caller, since there is no
need to deal with splitting and merging slots; however this is not exploited
in this patch.
Signed-off-by: Avi Kivity a...@redhat.com
---
hw/vhost.c |
cpu_get_physical_page_desc() is tied into the memory core's
innards, replace it with uses of the API.
Signed-off-by: Avi Kivity a...@redhat.com
---
hw/loader.c |9 +
1 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/hw/loader.c b/hw/loader.c
index 9bbcddd..7af5411 100644
The function is still used as the implementation.
Signed-off-by: Avi Kivity a...@redhat.com
---
arch_init.c |6 ++
cpu-all.h |3 ---
exec-obsolete.h |3 +++
memory.c|4
memory.h| 10 ++
5 files changed, 19 insertions(+), 7 deletions(-)
Hi,
I am running Ubuntu 10.10 (amd64) on a 2 socket nehalem based
server with IOH 5520. 5520 supports VTD.
I enabled DMAR with intel_iommu=on. The box has intel 82599 adapter
which I assigned through VT-D to FreeBSD 8.2 running
as guest os. The ixgbe driver detects the device and the
On Thu, Dec 15, 2011 at 2:23 PM, Hamo hamo...@gmail.com wrote:
by checking the return value from kvm_init_debug, we
can ensure that the entries under debugfs for KVM have
been created correctly.
Signed-off-by: Yang Bai hamo...@gmail.com
---
virt/kvm/kvm_main.c | 26
On 19 December 2011 14:13, Avi Kivity a...@redhat.com wrote:
---
This is a rather uninformative commit message -- was this patch
intended to be in this series?
-- PMM
memory.c | 7 ---
1 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/memory.c b/memory.c
index
On 12/19/2011 08:13 AM, Avi Kivity wrote:
Given an address space (represented by the top-level memory region),
returns the memory region that maps a given range. Useful for implementing
DMA.
The implementation is a simplistic binary search. Once we have a tree
representation this can be
On 12/19/2011 04:32 PM, Peter Maydell wrote:
On 19 December 2011 14:13, Avi Kivity a...@redhat.com wrote:
---
This is a rather uninformative commit message -- was this patch
intended to be in this series?
It was intended to be merged into patch 9. Will fix for the next round.
--
error
On 12/19/2011 08:13 AM, Avi Kivity wrote:
cpu_get_physical_page_desc() exposes the internals of the memory core to
callers; as such it prevents the refactoring planned there. This patchset
converts all callers memory API equivalents and removes the function.
The conversion leaves a lot of
On Mon, Dec 19, 2011 at 1:15 AM, Antonios Motakis
a.mota...@virtualopensystems.com wrote:
On 12/11/2011 11:25 AM, Christoffer Dall wrote:
WARNING: This code is in development and guests do not fully boot on SMP
hosts yet.
Hello,
What would still be needed to fully booted SMP? For example,
On 12/19/2011 04:50 PM, Anthony Liguori wrote:
+static int cmp_flatrange_addr(const void *_addr, const void *_fr)
+{
+const AddrRange *addr = _addr;
+const FlatRange *fr = _fr;
Please don't prefix with an underscore.
Why not? It's legal according to the standards, if that's your
On 12.12.2011, at 23:28, Paul Mackerras wrote:
This allocates an array for each memory slot that is added to store
the physical addresses of the pages in the slot. This array is
vmalloc'd and accessed in kvmppc_h_enter using real_vmalloc_addr().
This allows us to remove the ram_pginfo field
On 12/19/2011 09:04 AM, Avi Kivity wrote:
On 12/19/2011 04:50 PM, Anthony Liguori wrote:
+static int cmp_flatrange_addr(const void *_addr, const void *_fr)
+{
+const AddrRange *addr = _addr;
+const FlatRange *fr = _fr;
Please don't prefix with an underscore.
Why not? It's legal
On 12/19/2011 05:10 PM, Anthony Liguori wrote:
On 12/19/2011 09:04 AM, Avi Kivity wrote:
On 12/19/2011 04:50 PM, Anthony Liguori wrote:
+static int cmp_flatrange_addr(const void *_addr, const void *_fr)
+{
+const AddrRange *addr = _addr;
+const FlatRange *fr = _fr;
Please don't
On 19/12/11 14:57, Christoffer Dall wrote:
On Mon, Dec 19, 2011 at 1:15 AM, Antonios Motakis
a.mota...@virtualopensystems.com wrote:
On 12/11/2011 11:25 AM, Christoffer Dall wrote:
WARNING: This code is in development and guests do not fully boot on SMP
hosts yet.
Hello,
What would still
On 12/19/2011 09:17 AM, Avi Kivity wrote:
On 12/19/2011 05:10 PM, Anthony Liguori wrote:
On 12/19/2011 09:04 AM, Avi Kivity wrote:
On 12/19/2011 04:50 PM, Anthony Liguori wrote:
+static int cmp_flatrange_addr(const void *_addr, const void *_fr)
+{
+const AddrRange *addr = _addr;
+
On 12/19/2011 05:25 PM, Anthony Liguori wrote:
I rather like the pattern
void callback(void *_foo)
{
Foo *foo = _foo;
...
}
If the consensus is that we don't want it, I'll change it, but I do
think it's useful.
I dislike enforcing coding style but it's
On 12/19/2011 04:19 PM, Marc Zyngier wrote:
On 19/12/11 14:57, Christoffer Dall wrote:
You should simply start booting a UP guest on an SMP host, see where
it crashes and start tracking it down.
For the time being, I've yet to see UP guest crashing on SMP host. On
the model, that is...
On 19/12/11 15:30, Antonios Motakis wrote:
On 12/19/2011 04:19 PM, Marc Zyngier wrote:
On 19/12/11 14:57, Christoffer Dall wrote:
You should simply start booting a UP guest on an SMP host, see where
it crashes and start tracking it down.
For the time being, I've yet to see UP guest crashing
On Mon, Dec 19, 2011 at 10:37 AM, Marc Zyngier marc.zyng...@arm.com wrote:
On 19/12/11 15:30, Antonios Motakis wrote:
On 12/19/2011 04:19 PM, Marc Zyngier wrote:
On 19/12/11 14:57, Christoffer Dall wrote:
You should simply start booting a UP guest on an SMP host, see where
it crashes and
On 12/19/2011 04:40 PM, Christoffer Dall wrote:
On Mon, Dec 19, 2011 at 10:37 AM, Marc Zyngiermarc.zyng...@arm.com wrote:
On 19/12/11 15:30, Antonios Motakis wrote:
On 12/19/2011 04:19 PM, Marc Zyngier wrote:
On 19/12/11 14:57, Christoffer Dall wrote:
You should simply start booting a UP
On 19/12/11 15:42, Antonios Motakis wrote:
On 12/19/2011 04:40 PM, Christoffer Dall wrote:
On Mon, Dec 19, 2011 at 10:37 AM, Marc Zyngiermarc.zyng...@arm.com wrote:
On 19/12/11 15:30, Antonios Motakis wrote:
On 12/19/2011 04:19 PM, Marc Zyngier wrote:
On 19/12/11 14:57, Christoffer Dall
On 12/19/2011 05:28 PM, Avi Kivity wrote:
But it should be at least be documented and used consistently.
Will update both.
Updated patchset in qemu-kvm.git page_desc. Will refrain from reposting
until some time has passed for review.
--
error compiling committee.c: too many arguments to
On 12.12.2011, at 23:37, Paul Mackerras wrote:
This adds an smp_wmb in kvm_mmu_notifier_invalidate_range_end() and an
smp_rmb in mmu_notifier_retry() so that mmu_notifier_retry() will give
the correct answer when called without kvm-mmu_lock being held.
PowerPC Book3S HV KVM wants to use a
2011/12/19 Christoffer Dall cd...@cs.columbia.edu:
ok, just reproduced.
Using the AEM v7 model, 2 cores, attached guest and host config.
Host running on the v5 of the KVM/ARM branch, found here:
https://github.com/virtualopensystems/linux-kvm-arm
Guest kernel revision:
On 12/19/2011 07:18 PM, Alexander Graf wrote:
On 12.12.2011, at 23:37, Paul Mackerras wrote:
This adds an smp_wmb in kvm_mmu_notifier_invalidate_range_end() and an
smp_rmb in mmu_notifier_retry() so that mmu_notifier_retry() will give
the correct answer when called without kvm-mmu_lock
1 - 100 of 154 matches
Mail list logo