off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v4:
* since FlatView::rcu is used now to dispose FV, call_rcu() in
address_space_update_topology() is replaced with direct call to
flatview_unref()
---
include/exec/memory-internal.h | 12 +++-
include/exec/memory.h
This creates a new AS object without any FlatView as
memory_region_transaction_commit() may want to reuse the empty FV.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
I do not really want to add view!=NULL into
flatview_ref()/flatview_unref() as this is quite special case whe
() if there is
no registered listeners; this should improve starting time.
This should cause no behavioural change.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v4:
* address_space_update_topology_pass() is called now under
if (!QTAILQ_EMPTY(>listeners))
v3:
* inlined &am
This renames some helpers to reflect better what they do.
This should cause no behavioural change.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v3:
* s/flatview_mem_add/flatview_add_to_dispatch/
* s/phys_page_compact_all/address_space_dispatch_compac
So it is called (twice) from the same function. This is to make the next
patches a bit simpler.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
memory.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/memory.c b/memory.c
index eb730cd619..9868d0f57c
[];
} subpage_t;
struct MemoryRegionSection {
MemoryRegion *mr;
-AddressSpace *address_space;
+FlatView *fv;
hwaddr offset_within_region;
Int128 size;
hwaddr offset_within_address_space;
bool readonly;
};
This should cause no behavioural change.
Signed-off-by: Alexey
AS in ASD is only used to pass AS from mem_begin() to register_subpage()
to store it in MemoryRegionSection, we can do this directly now.
This should cause no behavioural change.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
exec.c | 15 +++
1 file changed, 7 inse
This moves a FlatView allocation and initialization to a helper.
While we are nere, replace g_new with g_new0 to not to bother if we add
new fields in the future.
This should cause no behavioural change.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v3:
* s/flatview
On 21/09/17 15:22, Alexey Kardashevskiy wrote:
> On 21/09/17 10:02, Alexey Kardashevskiy wrote:
>> On 21/09/17 03:15, Paolo Bonzini wrote:
>>> On 20/09/2017 13:46, Alexey Kardashevskiy wrote:
>>>> Address spaces get to keep a root MR (alias or not) but Flat
On 21/09/17 10:02, Alexey Kardashevskiy wrote:
> On 21/09/17 03:15, Paolo Bonzini wrote:
>> On 20/09/2017 13:46, Alexey Kardashevskiy wrote:
>>> Address spaces get to keep a root MR (alias or not) but FlatView stores
>>> the actual MR as this is going to be used
On 21/09/17 03:15, Paolo Bonzini wrote:
> On 20/09/2017 13:46, Alexey Kardashevskiy wrote:
>> Address spaces get to keep a root MR (alias or not) but FlatView stores
>> the actual MR as this is going to be used later on to decide whether to
>> share a particular FlatView or
On 21/09/17 03:14, Paolo Bonzini wrote:
> On 20/09/2017 13:46, Alexey Kardashevskiy wrote:
>> This extends memory_region_transaction_commit() to receive a MR as
>> if it is a root MR or its topmost parent is, then we can only rebuild
>> its FlatView and update it for a
On 21/09/17 03:18, Paolo Bonzini wrote:
> On 20/09/2017 13:46, Alexey Kardashevskiy wrote:
>> +QTAILQ_FOREACH(as, _spaces, address_spaces_link) {
>> +MemoryRegion *physmr = memory_region_get_flatview_root(as->root);
>> +FlatView *new_view = g_hash
On 21/09/17 03:13, Paolo Bonzini wrote:
> On 20/09/2017 13:46, Alexey Kardashevskiy wrote:
>> This shares an cached empty FlatView among address spaces. The empty
>> FV is used every time when a root MR renders into a FV without memory
>> sections which happens wh
ry FVs which are created
(and then released) to make sure that they are empty and can be replaced
with @empty_view.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
memory.c | 14 ++
1 file changed, 14 insertions(+)
diff --git a/memory.c b/memory.c
index 4add0fd030..92b13
Address spaces get to keep a root MR (alias or not) but FlatView stores
the actual MR as this is going to be used later on to decide whether to
share a particular FlatView or not.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v4:
* s/memory_region_unalias_
This creates a new AS object without any FlatView as
memory_region_transaction_commit() may want to reuse the empty FV.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
I do not really want to add view!=NULL into
flatview_ref()/flatview_unref() as this is quite special case whe
address_space_init_shareable() as
FlatViews are shared elsewhere and keeping as::ref_count correct seems
an unnecessary and useless complication.
This should cause no change and memory use or boot time yet.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v4:
* used g_hash_table_ne
off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v4:
* since FlatView::rcu is used now to dispose FV, call_rcu() in
address_space_update_topology() is replaced with direct call to
flatview_unref()
---
include/exec/memory-internal.h | 12 +++-
include/exec/memory.h
Since FlatViews are shared now and ASes not, this gets rid of
address_space_init_shareable().
This should cause no behavioural change.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v3:
* now removes @malloced and @ref_count, used to be in the previos patch
---
includ
This adds a new "-d" switch to "info mtree" to print dispatch tree
internals.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v3:
* reimplemented as there is no more global FlatView list
---
Example:
QEMU 2.10.50 monitor - type 'help' for more inform
So it is called (twice) from the same function. This is to make the next
patches a bit simpler.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
memory.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/memory.c b/memory.c
index eb730cd619..9868d0f57c
[];
} subpage_t;
struct MemoryRegionSection {
MemoryRegion *mr;
-AddressSpace *address_space;
+FlatView *fv;
hwaddr offset_within_region;
Int128 size;
hwaddr offset_within_address_space;
bool readonly;
};
This should cause no behavioural change.
Signed-off-by: Alexey
This is to make next patches simpler.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
memory.c | 18 +-
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/memory.c b/memory.c
index 98b0b95e6e..eb730cd619 100644
--- a/memory.c
+++ b/memory.c
@@ -742,6
unt of
temporary dispatch trees (~37 -> ~30), the total memory footprint
goes down (18G -> 17G).
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
memory.c | 18 +++---
1 file changed, 15 insertions(+), 3 deletions(-)
diff --git a/memory.c b/memory.c
i
AS in ASD is only used to pass AS from mem_begin() to register_subpage()
to store it in MemoryRegionSection, we can do this directly now.
This should cause no behavioural change.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
exec.c | 15 +++
1 file changed, 7 inse
.
memory_region_set_enabled() is a special case here, it does not use
a hint when MR is being disabled.
On POWER8 with 255 CPUs, 255 virtio-net, 40 PCI bridges guest this brings
down the boot time from 20s to 12s, the total memory footprint
goes down (17G -> 8G).
Signed-off-by: Alexey Kardashevskiy <a...@ozl
This moves a FlatView allocation and initialization to a helper.
While we are nere, replace g_new with g_new0 to not to bother if we add
new fields in the future.
This should cause no behavioural change.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v3:
* s/flatview
We store AddressSpaceDispatch* in FlatView anyway so there is no need
to carry it from mem_add() to register_subpage/register_multipage.
This should cause no behavioural change.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
exec.c | 16
1 file changed, 8 inse
rework
This is based on sha1
c51700273a Peter Maydell "Merge remote-tracking branch
'remotes/cohuck/tags/s390x-20170919-v2' into staging".
Please comment. Thanks.
Alexey Kardashevskiy (18):
exec: Explicitly export target AS from
address_space_translate_internal
memory:
This renames some helpers to reflect better what they do.
This should cause no behavioural change.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v3:
* s/flatview_mem_add/flatview_add_to_dispatch/
* s/phys_page_compact_all/address_space_dispatch_compac
() if there is
no registered listeners; this should improve starting time.
This should cause no behavioural change.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v4:
* address_space_update_topology_pass() is called now under
if (!QTAILQ_EMPTY(>listeners))
v3:
* inlined &am
This adds an AS** parameter to address_space_do_translate()
to make it easier for the next patch to share FlatViews.
This should cause no behavioural change.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
exec.c | 11 +++
1 file changed, 7 insertions(+), 4 deletions(-)
On 19/09/17 20:47, Paolo Bonzini wrote:
> On 19/09/2017 12:39, Alexey Kardashevskiy wrote:
>>> No, there's still
>>>
>>> as->dispatch = NULL;
>>> memory_region_update_pending |= root->enabled;
>>> memory_region_transaction_co
On 19/09/17 17:42, Paolo Bonzini wrote:
> On 19/09/2017 08:57, Alexey Kardashevskiy wrote:
>>>> 2) also, after patch 2 you know that the address space has no listeners
>>>> here, so the begin/commit isn't really needed. Instead you can use the
>>>&g
On 19/09/17 17:40, Paolo Bonzini wrote:
> On 19/09/2017 08:57, Alexey Kardashevskiy wrote:
>>>> 3) you can consult the list (or hash table :)) of live FlatViews (which
>>>> means you keep it live after memory_region_transaction_commit ends, and
>>>> onl
On 19/09/17 12:09, Alexey Kardashevskiy wrote:
> On 19/09/17 00:54, Paolo Bonzini wrote:
>> On 18/09/2017 12:16, Alexey Kardashevskiy wrote:
>>> Most devices use at least one address space and every time a new address
>>> space is added, flat views and dispatch trees
On 19/09/17 00:54, Paolo Bonzini wrote:
> On 18/09/2017 12:16, Alexey Kardashevskiy wrote:
>> Most devices use at least one address space and every time a new address
>> space is added, flat views and dispatch trees are rebuild for all address
>> spaces. This is not a pro
On 19/09/17 00:59, Paolo Bonzini wrote:
> On 18/09/2017 12:16, Alexey Kardashevskiy wrote:
>> This was inspired by https://bugzilla.redhat.com/show_bug.cgi?id=1481593
>> Previous versions:
>> v1: https://lists.gnu.org/archive/html/qemu-devel/2017-09/msg01559.html
>>
On 19/09/17 00:28, Eric Blake wrote:
> On 09/18/2017 05:16 AM, Alexey Kardashevskiy wrote:
>
> Subject line: s/Explicitely/Explicitly/
>
>> This is not so mechanical change in order to move to shared FlatViews
>> so make it a separate patch.
>
> Hard to un
On 18/09/17 20:17, Alexey Kardashevskiy wrote:
> FlatView's will be shared between AddressSpace's and subpage_t
> and MemoryRegionSection cannot store AS anymore, hence this change.
>
> In particular, for:
>
> typedef struct subpage_t {
> MemoryRegion iomem
ack and set to an AS atomically.
flatview_destroy() is executed under RCU instead of
address_space_dispatch_free() now.
This makes mem_begin/mem_commit to work with ASD and mem_add with FV
as later on mem_add will be taking FV as an argument anyway.
Signed-off-by: Alexey Kardashevskiy <a...@ozl
This is not so mechanical change in order to move to shared FlatViews
so make it a separate patch. The first argument of
address_space_do_translate() will become a FlatView, however since
address_space_get_iotlb_entry() still wants AS, hence this change.
Signed-off-by: Alexey Kardashevskiy
Since FlatViews are shared now and ASes not, this gets rid of
address_space_init_shareable().
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v3:
* now removes @malloced and @ref_count, used to be in the previos patch
---
include/exec/memory.h
This renames some helper to reflect better what they do.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v3:
* s/flatview_mem_add/flatview_add_to_dispatch/
* s/phys_page_compact_all/address_space_dispatch_compact/
* s/address_space_dispatch_alloc/address_space_dispat
Address spaces get to keep a root MR (alias or not) but FlatView stores
the actual MR as this is going to be used later on to decide whether to
share a particular FlatView or not.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
memory.c | 27 ++-
1 file c
This allows sharing flat views between address spaces when the same root
memory region is used when creating a new address space.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v3:
* got rid of global and per-AS lists of FlatView objects
---
I could also make all
This adds a new switch to "info mtree" to print dispatch tree internals.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v3:
* reimplemented as there is no more global FlatView list
---
Example:
aik@fstn1-p1:~$ echo "info mtree -f -d" | nc localhost
We store AddressSpaceDispatch* in FlatView anyway so there is no need
to carry it from mem_add() to register_subpage/register_multipage.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
exec.c | 16
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/ex
[];
} subpage_t;
struct MemoryRegionSection {
MemoryRegion *mr;
-AddressSpace *address_space;
+FlatView *fv;
hwaddr offset_within_region;
Int128 size;
hwaddr offset_within_address_space;
bool readonly;
};
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs
This moves a FlatView allocation and initialization to a helper.
While we are nere, replace g_new with g_new0 to not to bother if we add
new fields in the future.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v3:
* s/flatview_alloc/flatview_new/
---
memory.
aging".
Please comment. Thanks.
Alexey Kardashevskiy (13):
memory: Postpone flatview and dispatch tree building till all devices
are added
exec: Explicitely export target AS from
address_space_translate_internal
memory: Open code FlatView rendering
memory: Move FlatView
We are going to share FlatView's between AddressSpace's and per-AS
memory listeners won't suite the purpose anymore so open code
the dispatch tree rendering.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v3:
* inlined & simplified address_space_update_flatview
--
AS in ASD is only used to pass AS from mem_begin() to register_subpage()
to store it in MemoryRegionSection, we can do this directly now.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
exec.c | 15 +++
1 file changed, 7 insertions(+), 8 deletions(-)
diff --git a/ex
)allocations.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v2:
* wrapped qemu_run_machine_init_done_notifiers() as well
---
vl.c | 9 +
1 file changed, 9 insertions(+)
diff --git a/vl.c b/vl.c
index 9e62e92aea..e4f2ece590 100644
--- a/vl.c
+++ b/vl.c
@@ -4
On 15/09/17 19:25, Paolo Bonzini wrote:
> On 15/09/2017 10:40, Alexey Kardashevskiy wrote:
>> +
>> +static bool flatview_can_share(FlatView *old_view, FlatView *new_view)
>> +{
>> +MemoryRegion *old_root = memory_region_unalias_entire(old_view->root);
)allocations.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v2:
* wrapped qemu_run_machine_init_done_notifiers() as well
---
vl.c | 9 +
1 file changed, 9 insertions(+)
diff --git a/vl.c b/vl.c
index fb1f05b937..ee3cc7db48 100644
--- a/vl.c
+++ b/vl.c
@@ -4
ack and set to an AS atomically.
flatview_destroy() is executed under RCU instead of
address_space_dispatch_free() now.
This makes mem_begin/mem_commit to work with ASD and mem_add with FV
as later on mem_add will be taking FV as an argument anyway.
Signed-off-by: Alexey Kardashevskiy <a...@ozl
[];
} subpage_t;
struct MemoryRegionSection {
MemoryRegion *mr;
-AddressSpace *address_space;
+FlatView *fv;
hwaddr offset_within_region;
Int128 size;
hwaddr offset_within_address_space;
bool readonly;
};
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs
:
v2:
* total rework
This is based on sha1
3dabde1128 Peter Maydell "Merge remote-tracking branch
'remotes/dgilbert/tags/pull-hmp-20170914' into staging".
Please comment. Thanks.
Alexey Kardashevskiy (13):
memory: Postpone flatview and dispatch tree building till all devices
This allows sharing flat views between address spaces when the same root
memory region is used when creating a new address space.
This adds a global list of flat views and a list of attached address
spaces per a flat view. Each address space references a flat view.
Signed-off-by: Alexey
This is not so mechanical change in order to move to shared FlatViews
so make it a separate patch. The first argument of
address_space_do_translate() will become a FlatView, however since
address_space_get_iotlb_entry() still wants AS, hence this change.
Signed-off-by: Alexey Kardashevskiy
Since FlatViews are shared now and ASes not, this gets rid of
address_space_init_shareable().
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Squash to the previous one? It is a separate patch to make review easier,
mostly.
---
include/exec/memory.h | 17 -
incl
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
include/exec/memory.h | 2 +-
hw/pci/pci.c | 3 ++-
memory.c | 30 --
3 files changed, 19 insertions(+), 16 deletions(-)
diff --git a/include/exec/memory.h b/include/exec/memory.h
This adds a new switch to "info mtree" to print dispatch tree internals.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Example:
aik@fstn1-p1:~$ echo "info mtree -f -d" | nc localhost 3
QEMU 2.9.94 monitor - type 'help' for more information
(qemu) in
This renames some helper to reflect better what they do.
This drops AS in address_space_update_flatview() as it is not used anymore
and renames to flatview_render_new().
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
include/exec/memory-internal.h | 6 +++---
AS in ASD is only used to pass AS from mem_begin() to register_subpage()
to store it in MemoryRegionSection, we can do this directly now.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
exec.c | 15 +++
1 file changed, 7 insertions(+), 8 deletions(-)
diff --git a/ex
We are going to share FlatView's between AddressSpace's and per-AS
memory listeners won't suite the purpose anymore so open code
the dispatch tree rendering.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
include/exec/memory-internal.h | 6 +++--
include/exec/memory.h
This moves a FlatView allocation and initialization to a helper.
While we are nere, replace g_new with g_new0 to not to bother if we add
new fields in the future.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
memory.c | 16
1 file changed, 8 insertions(+), 8 del
We store AddressSpaceDispatch* in FlatView anyway so there is no need
to carry it from mem_add() to register_subpage/register_multipage.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
exec.c | 16
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/ex
This moves pci_dev->name initialization earlier so
pci_dev->bus_master_as could get a name instead of an empty string.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
Reviewed-by: Philippe Mathieu-Daudé <f4...@amsat.org>
---
Changes:
v2:
* fixed mistype in the commit log
*
On 13/09/17 02:46, Mark Cave-Ayland wrote:
> On 12/09/17 17:41, Mark Cave-Ayland wrote:
>
>> The commit message mentions that prior to the conversion some CPU state
>> was missing but it doesn't mention anything about dropping existing
>> fields as part of the conversion process so I suspect that
On 12/09/17 17:12, Paolo Bonzini wrote:
> On 12/09/2017 07:55, Alexey Kardashevskiy wrote:
>> On 12/09/17 01:30, Paolo Bonzini wrote:
>>> On 11/09/2017 14:08, Alexey Kardashevskiy wrote:
>>>>> Ok, this makes sense. Maybe it should be a flatview rather t
On 12/09/17 01:30, Paolo Bonzini wrote:
> On 11/09/2017 14:08, Alexey Kardashevskiy wrote:
>>> Ok, this makes sense. Maybe it should be a flatview rather than an
>>> AddressSpaceDispatch (a FlatView is essentially a list of
>>> MemoryRegionSections; attaching t
;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 <a...@ozlabs.ru>
---
hw/vfio/spapr.c | 2 +-
1 file changed, 1 insertion(+),
On 11/09/17 19:37, Paolo Bonzini wrote:
> On 11/09/2017 11:06, Alexey Kardashevskiy wrote:
>> On 11/09/17 17:40, Paolo Bonzini wrote:
>>> On 07/09/2017 11:20, Alexey Kardashevskiy wrote:
>>>>
>>>> /* Accessed via RCU. */
>>>>
On 11/09/17 17:40, Paolo Bonzini wrote:
> On 07/09/2017 11:20, Alexey Kardashevskiy wrote:
>>
>> /* Accessed via RCU. */
>> struct FlatView *current_map;
>>
>> int ioeventfd_nb;
>> struct MemoryRegionIoeventfd *ioeventfds;
>&g
Segment Table Size Register (ERSTSZ).
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
On pseries, the SLOF firmware initializes XHCI and sets non-zero value
to ERSTBA. Then, it jumps to the guest and the guest requests the SLOF
to quiesce devices, that includes XHCI. SLOF remov
On 09/09/17 17:18, David Gibson wrote:
> On Thu, Sep 07, 2017 at 07:20:08PM +1000, Alexey Kardashevskiy wrote:
>> We are going to share flat views and dispatch trees between address
>> spaces. This moves bits around but no change in behaviour is expected
>> here. The following
On 08/09/17 00:30, Peter Maydell wrote:
> On 7 September 2017 at 15:27, Alexey Kardashevskiy <a...@ozlabs.ru> wrote:
>> On 07/09/17 19:30, Peter Maydell wrote:
>>> What happens if something in a device realize function tries
>>> to do a read from an AddressSpa
On 08/09/17 12:08, Alexey Kardashevskiy wrote:
> On 08/09/17 00:54, Dr. David Alan Gilbert wrote:
>> * Alexey Kardashevskiy (a...@ozlabs.ru) wrote:
>>> On 07/09/17 19:51, Dr. David Alan Gilbert wrote:
>>>> * Alexey Kardashevskiy (a...@ozlabs.ru) wrote:
&g
On 08/09/17 00:54, Dr. David Alan Gilbert wrote:
> * Alexey Kardashevskiy (a...@ozlabs.ru) wrote:
>> On 07/09/17 19:51, Dr. David Alan Gilbert wrote:
>>> * Alexey Kardashevskiy (a...@ozlabs.ru) wrote:
>>>> This was inspired by https://bugzilla.redhat.com/show_bug
On 08/09/17 06:53, Philippe Mathieu-Daudé wrote:
> On 09/07/2017 06:20 AM, Alexey Kardashevskiy wrote:
>> This allows sharing flat views between address spaces when the same root
>> memory region is used when creating a new address space.
>>
>> This adds a global li
On 07/09/17 19:51, Dr. David Alan Gilbert wrote:
> * Alexey Kardashevskiy (a...@ozlabs.ru) wrote:
>> This was inspired by https://bugzilla.redhat.com/show_bug.cgi?id=1481593
>>
>> What happens ithere is that every virtio block device creates 2 address
>> spaces - for
On 07/09/17 19:30, Peter Maydell wrote:
> On 7 September 2017 at 10:20, Alexey Kardashevskiy <a...@ozlabs.ru> wrote:
>> Most devices use at least one address space and every time a new address
>> space is added, flat views and dispatch trees are rebuild for
address_space_get_iotlb_entry() work.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
include/exec/memory.h | 79 +++---
exec.c | 128 +++-
hw/alpha/typhoon.c | 2 +-
hw/dma/rc4030.c | 4 +-
h
one provides visible outcome.
There are still things to polish and double check the use of RCU,
I'd like to get any feedback before proceeding - is this going
the right way or way too ugly?
This is based on sha1
1ab5eb4efb Peter Maydell "Update version for v2.10.0 release".
Please comment. T
tree building instead of doing so via
a memory listener.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
This was suggested by Paolo in
https://lists.gnu.org/archive/html/qemu-devel/2017-08/msg05011.html
I am not putting "Suggested-by" as I want to make sure that th
)allocations.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
vl.c | 4
1 file changed, 4 insertions(+)
diff --git a/vl.c b/vl.c
index 8e247cc2a2..3c39cc8b3a 100644
--- a/vl.c
+++ b/vl.c
@@ -4655,12 +4655,16 @@ int main(int argc, char **argv, char **envp)
igd_gfx_pa
This adds a new switch to "info mtree" to print dispatch tree internals.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Example:
aik@fstn1-p1:~$ echo "info mtree -f -d" | nc localhost 3
QEMU 2.9.94 monitor - type 'help' for more information
(qemu) in
On 31/08/17 03:20, Stefan Hajnoczi wrote:
> On Tue, Aug 22, 2017 at 02:56:00PM +1000, Alexey Kardashevskiy wrote:
>> On 19/08/17 12:46, Alexey Kardashevskiy wrote:
>>> On 19/08/17 01:18, Eric Blake wrote:
>>>> On 08/18/2017 08:31 AM, Stefan Hajnoczi wrote:
>>&
On 25/08/17 18:53, Paolo Bonzini wrote:
> On 25/08/2017 10:31, Alexey Kardashevskiy wrote:
>> Otherwise old dispatch holds way too much memory before RCU gets
>> a chance to free old dispatches.
>>
>> Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
On 25/08/17 16:21, David Gibson wrote:
> On Thu, Jul 20, 2017 at 05:22:30PM +1000, Alexey Kardashevskiy wrote:
>> This implements a notification for a new IOMMU group attached to
>> sPAPR's logical IO bus (LIOBN) to enable in-kernel TCE acceleration.
>
On 25/08/17 19:01, Paolo Bonzini wrote:
> On 25/08/2017 10:31, Alexey Kardashevskiy wrote:
>> Each address_space_init() updates topology for _every_ address space.
>
> And finally, does this patch help with the above?
>
> diff --git a/memory.c b/memory.c
> index
Otherwise old dispatch holds way too much memory before RCU gets
a chance to free old dispatches.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
This is a follow-up to the "Memory use with >100 virtio devices"
thread.
I assume this is a dirty hack (which fixes
This moves pci_dev->name initialization earlier so
pci_dev->bus_master_as could get a name instead of empry string.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
hw/pci/pci.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/hw/pci/pci.c b/hw/pci
On 21/08/17 15:50, Alexey Kardashevskiy wrote:
> On 21/08/17 14:31, David Gibson wrote:
>> On Fri, Aug 18, 2017 at 02:18:53PM +0100, Stefan Hajnoczi wrote:
>>> On Fri, Aug 18, 2017 at 03:39:20PM +1000, Alexey Kardashevskiy wrote:
>>>> ==94451=
On 19/08/17 12:46, Alexey Kardashevskiy wrote:
> On 19/08/17 01:18, Eric Blake wrote:
>> On 08/18/2017 08:31 AM, Stefan Hajnoczi wrote:
>>> Most qcow2 files are uncompressed so it is wasteful to allocate (32 + 1)
>>> * cluster_size + 512 bytes upfront. Allocate
On 21/08/17 14:31, David Gibson wrote:
> On Fri, Aug 18, 2017 at 02:18:53PM +0100, Stefan Hajnoczi wrote:
>> On Fri, Aug 18, 2017 at 03:39:20PM +1000, Alexey Kardashevskiy wrote:
>>> ==94451== 4 of 10
>>> ==94451== max-live:
On 19/08/17 12:53, Alexey Kardashevskiy wrote:
> On 19/08/17 12:46, Alexey Kardashevskiy wrote:
>> On 19/08/17 01:18, Eric Blake wrote:
>>> On 08/18/2017 08:31 AM, Stefan Hajnoczi wrote:
>>>> Most qcow2 files are uncompressed so it is wasteful to allocate (32 + 1)
&
801 - 900 of 3692 matches
Mail list logo