From: Tamas K Lengyel
Working altp2m test-case. Extended the test tool to support singlestepping
to better highlight the core feature of altp2m view switching.
Signed-off-by: Tamas K Lengyel
Signed-off-by: Ed White
Reviewed-by: Razvan Cojocaru
Acked-by: Wei Liu
---
Changes since v6
From: Tamas K Lengyel
Wrappers to issue altp2m hvmops.
Signed-off-by: Tamas K Lengyel
Signed-off-by: Ravi Sahita
Acked-by: Ian Campbell
---
Changes since v6:
no changes
tools/libxc/Makefile | 1 +
tools/libxc/include/xenctrl.h | 22
tools/libxc/xc_altp2m.c |
From: Ravi Sahita
Signed-off-by: Ravi Sahita
Acked-by: Daniel De Graaf
---
Changes since v6:
no changes
tools/flask/policy/policy/modules/xen/xen.if | 4 ++--
xen/arch/x86/hvm/hvm.c | 6 ++
xen/include/xsm/dummy.h | 12
xe
The altp2mhvm and nestedhvm parameters are mutually
exclusive and cannot be set together.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
Acked-by: Wei Liu
---
Changes since v6:
no changes
docs/man/xl.cfg.pod.5 | 12
tools/libxl/libxl.h | 6
Signed-off-by: Ed White
Acked-by: Jan Beulich
---
Changes since v6:
fix cmd range check
rework domain locking
add Jan's ack
xen/arch/x86/hvm/hvm.c | 138
xen/include/public/hvm/hvm_op.h
Add the remaining routines required to support enabling the alternate
p2m functionality.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
---
Changes since v6:
rename altp2m lazy copier, make bool_t, use __put_gfn throughout,
and move to p2m.c, eliminating altp2m_hap.c
From: George Dunlap
The existing ept_set_entry() and ept_get_entry() routines are extended
to optionally set/get suppress_ve. Passing -1 will set suppress_ve on
new p2m entries, or retain suppress_ve flag on existing entries.
Signed-off-by: George Dunlap
Signed-off-by: Ravi Sahita
Reviewed-b
Add a flag to indicate that a memory event occurred in an alternate p2m
and a field containing the p2m index. Allow any event response to switch
to a different alternate p2m using the same flag and field.
Modify p2m_mem_access_check() to handle alternate p2m's.
Signed-off-by: Ed White
Ack
From: Ravi Sahita
Signed-off-by: Ravi Sahita
Acked-by: Jan Beulich
---
Changes since v6:
remove incorrect cast
add Jan's ack
xen/arch/x86/hvm/emulate.c | 18 +++--
xen/arch/x86/hvm/vmx/vmx.c | 36 ++
xen/arch
lso splits the p2m lock into one lock type for altp2m's
and another type for all other p2m's. The purpose of this is to place
the altp2m list lock between the types, so the list lock can be
acquired whilst holding the host p2m lock.
Signed-off-by: Ed White
---
Changes since v6:
t EPT violations only
the hypervisor is able to handle the violation.
Signed-off-by: Ed White
Acked-by: George Dunlap
Acked-by: Jun Nakajima
---
Changes since v6:
add Jun's ack
xen/arch/x86/mm/p2m-ept.c | 17 -
1 file changed, 16 insertions(+), 1 deletion(-)
diff -
Implement and hook up the code to enable VMX support of VMFUNC and #VE.
VMFUNC leaf 0 (EPTP switching) emulation is added in a later patch.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
Acked-by: Jun Nakajima
---
Changes since v6:
remove casts around p2midx handling
fix
Currently, neither is enabled globally but may be enabled on a per-VCPU
basis by the altp2m code.
Remove the check for EPTE bit 63 == zero in ept_split_super_page(), as
that bit is now hardware-defined.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
Acked-by: George Dunlap
Acked-by: Jun
As implemented here, only supported on platforms with VMX HAP.
By default this functionality is force-disabled, it can be enabled
by specifying altp2m=1 on the Xen command line.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
---
Changes since v6:
no changes
docs/misc/xen-command
From: Andrew Cooper
For use on codepaths which would need to use domain_pause() but might be in
the target domain's context. In the case that the target domain is in
context, all other vcpus are paused.
Signed-off-by: Andrew Cooper
Reviewed-by: George Dunlap
---
Changes since v6:
add
on toolstack support for cross-domain testing with a slightly
earlier patch series, and we hope he will submit that support.
Not all of the patches will be of interest to everyone copied here. I've
copied everyone on this initial mailing to give context.
Andrew Cooper (1):
common/do
From: Ravi Sahita
Signed-off-by: Ravi Sahita
Acked-by: Daniel De Graaf
---
tools/flask/policy/policy/modules/xen/xen.if | 4 ++--
xen/arch/x86/hvm/hvm.c | 6 ++
xen/include/xsm/dummy.h | 12
xen/include/xsm/xsm.h
From: Tamas K Lengyel
Wrappers to issue altp2m hvmops.
Signed-off-by: Tamas K Lengyel
Signed-off-by: Ravi Sahita
Acked-by: Ian Campbell
---
tools/libxc/Makefile | 1 +
tools/libxc/include/xenctrl.h | 22
tools/libxc/xc_altp2m.c | 248 ++
The altp2mhvm and nestedhvm parameters are mutually
exclusive and cannot be set together.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
Acked-by: Wei Liu
---
docs/man/xl.cfg.pod.5 | 12
tools/libxl/libxl.h | 6 ++
tools/libxl/libxl_create.c
Add the remaining routines required to support enabling the alternate
p2m functionality.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
---
xen/arch/x86/hvm/hvm.c | 58 +-
xen/arch/x86/mm/hap/Makefile | 1 +
xen/arch/x86/mm/hap/altp2m_hap.c | 98 ++
xen/arch
From: Tamas K Lengyel
Working altp2m test-case. Extended the test tool to support singlestepping
to better highlight the core feature of altp2m view switching.
Signed-off-by: Tamas K Lengyel
Signed-off-by: Ed White
Reviewed-by: Razvan Cojocaru
Acked-by: Wei Liu
---
tools/tests/xen-access
Signed-off-by: Ed White
---
xen/arch/x86/hvm/hvm.c | 139
xen/include/public/hvm/hvm_op.h | 89 +
2 files changed, 228 insertions(+)
diff --git a/xen/arch/x86/hvm/hvm.c b/xen/arch/x86/hvm/hvm.c
index 38cf0c6..15973b4
From: George Dunlap
The existing ept_set_entry() and ept_get_entry() routines are extended
to optionally set/get suppress_ve. Passing -1 will set suppress_ve on
new p2m entries, or retain suppress_ve flag on existing entries.
Signed-off-by: George Dunlap
Signed-off-by: Ravi Sahita
Reviewed-b
Add a flag to indicate that a memory event occurred in an alternate p2m
and a field containing the p2m index. Allow any event response to switch
to a different alternate p2m using the same flag and field.
Modify p2m_mem_access_check() to handle alternate p2m's.
Signed-off-by: Ed White
Ack
From: Ravi Sahita
Signed-off-by: Ravi Sahita
---
xen/arch/x86/hvm/emulate.c | 18 +++--
xen/arch/x86/hvm/vmx/vmx.c | 36 ++
xen/arch/x86/x86_emulate/x86_emulate.c | 19 --
xen/arch/x86/x86_emulate/x86_emulate.h
Implement and hook up the code to enable VMX support of VMFUNC and #VE.
VMFUNC leaf 0 (EPTP switching) emulation is added in a later patch.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
Acked-by: Jun Nakajima
---
xen/arch/x86/hvm/vmx/vmx.c | 139
t EPT violations only
the hypervisor is able to handle the violation.
Signed-off-by: Ed White
Acked-by: George Dunlap
---
xen/arch/x86/mm/p2m-ept.c | 17 -
1 file changed, 16 insertions(+), 1 deletion(-)
diff --git a/xen/arch/x86/mm/p2m-ept.c b/xen/arch/x86/mm/p2m-ept.c
index 9a
Currently, neither is enabled globally but may be enabled on a per-VCPU
basis by the altp2m code.
Remove the check for EPTE bit 63 == zero in ept_split_super_page(), as
that bit is now hardware-defined.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
Acked-by: George Dunlap
Acked-by: Jun
holding the host p2m lock.
Signed-off-by: Ed White
---
xen/arch/x86/hvm/Makefile| 1 +
xen/arch/x86/hvm/altp2m.c| 77 +
xen/arch/x86/hvm/hvm.c | 21
xen/arch/x86/mm/hap/hap.c| 38 ++-
xen/arch/x86/mm/mm
As implemented here, only supported on platforms with VMX HAP.
By default this functionality is force-disabled, it can be enabled
by specifying altp2m=1 on the Xen command line.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
---
docs/misc/xen-command-line.markdown | 7 +++
xen/arch
ve context.
Andrew Cooper (1):
common/domain: Helpers to pause a domain while in context
Ed White (9):
VMX: VMFUNC and #VE definitions and detection.
VMX: implement suppress #VE.
x86/HVM: Hardware alternate p2m support detection.
x86/altp2m: basic data structures and support routin
From: Andrew Cooper
For use on codepaths which would need to use domain_pause() but might be in
the target domain's context. In the case that the target domain is in
context, all other vcpus are paused.
Signed-off-by: Andrew Cooper
---
xen/common/domain.c | 28
From: Tamas K Lengyel
Working altp2m test-case. Extended the test tool to support singlestepping
to better highlight the core feature of altp2m view switching.
Signed-off-by: Tamas K Lengyel
Signed-off-by: Ed White
Reviewed-by: Razvan Cojocaru
---
tools/tests/xen-access/xen-access.c | 173
From: Ravi Sahita
Signed-off-by: Ravi Sahita
Acked-by: Daniel De Graaf
---
tools/flask/policy/policy/modules/xen/xen.if | 4 ++--
xen/arch/x86/hvm/hvm.c | 6 ++
xen/include/xsm/dummy.h | 12
xen/include/xsm/xsm.h
From: Tamas K Lengyel
Wrappers to issue altp2m hvmops.
Signed-off-by: Tamas K Lengyel
Signed-off-by: Ravi Sahita
Acked-by: Ian Campbell
---
tools/libxc/Makefile | 1 +
tools/libxc/include/xenctrl.h | 21
tools/libxc/xc_altp2m.c | 237 +++
The altp2mhvm and nestedhvm parameters are mutually
exclusive and cannot be set together.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
Acked-by: Wei Liu
---
docs/man/xl.cfg.pod.5 | 12
tools/libxl/libxl.h | 6 ++
tools/libxl/libxl_create.c
Signed-off-by: Ed White
---
xen/arch/x86/hvm/hvm.c | 142
xen/include/public/hvm/hvm_op.h | 82 +++
2 files changed, 224 insertions(+)
diff --git a/xen/arch/x86/hvm/hvm.c b/xen/arch/x86/hvm/hvm.c
index a9f4b1b..df6c6b6
Add the remaining routines required to support enabling the alternate
p2m functionality.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
---
xen/arch/x86/hvm/hvm.c | 58 +-
xen/arch/x86/mm/hap/Makefile | 1 +
xen/arch/x86/mm/hap/altp2m_hap.c | 98 ++
xen/arch
holding the host p2m lock.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
---
xen/arch/x86/hvm/Makefile| 1 +
xen/arch/x86/hvm/altp2m.c| 77 +
xen/arch/x86/hvm/hvm.c | 21
xen/arch/x86/mm/hap/hap.c| 38 ++-
From: Ravi Sahita
Signed-off-by: Ravi Sahita
---
xen/arch/x86/hvm/emulate.c | 19 +++--
xen/arch/x86/hvm/vmx/vmx.c | 38 ++
xen/arch/x86/x86_emulate/x86_emulate.c | 19 +++--
xen/arch/x86/x86_emulate/x86_emulate.h |
From: George Dunlap
The existing ept_set_entry() and ept_get_entry() routines are extended
to optionally set/get suppress_ve. Passing -1 will set suppress_ve on
new p2m entries, or retain suppress_ve flag on existing entries.
Signed-off-by: George Dunlap
Signed-off-by: Ravi Sahita
Reviewed-b
Add a flag to indicate that a memory event occurred in an alternate p2m
and a field containing the p2m index. Allow any event response to switch
to a different alternate p2m using the same flag and field.
Modify p2m_mem_access_check() to handle alternate p2m's.
Signed-off-by: Ed White
Ack
Implement and hook up the code to enable VMX support of VMFUNC and #VE.
VMFUNC leaf 0 (EPTP switching) emulation is added in a later patch.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
Acked-by: Jun Nakajima
---
xen/arch/x86/hvm/vmx/vmx.c | 138
As implemented here, only supported on platforms with VMX HAP.
By default this functionality is force-disabled, it can be enabled
by specifying altp2m=1 on the Xen command line.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
---
docs/misc/xen-command-line.markdown | 7 +++
xen/arch
ll be of interest to everyone copied here. I've
copied everyone on this initial mailing to give context.
Andrew Cooper (1):
common/domain: Helpers to pause a domain while in context
Ed White (9):
VMX: VMFUNC and #VE definitions and detection.
VMX: implement suppress #VE.
x86/HVM: Hardwar
Currently, neither is enabled globally but may be enabled on a per-VCPU
basis by the altp2m code.
Remove the check for EPTE bit 63 == zero in ept_split_super_page(), as
that bit is now hardware-defined.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
Acked-by: George Dunlap
Acked-by: Jun
From: Andrew Cooper
For use on codepaths which would need to use domain_pause() but might be in
the target domain's context. In the case that the target domain is in
context, all other vcpus are paused.
Signed-off-by: Andrew Cooper
---
xen/common/domain.c | 28
t EPT violations only
the hypervisor is able to handle the violation.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
Reviewed-by: George Dunlap
Acked-by: Jun Nakajima
---
xen/arch/x86/mm/p2m-ept.c | 17 -
1 file changed, 16 insertions(+), 1 deletion(-)
diff --git a/xen/arch/x
From: Tamas K Lengyel
Working altp2m test-case. Extended the test tool to support singlestepping
to better highlight the core feature of altp2m view switching.
Signed-off-by: Tamas K Lengyel
Signed-off-by: Ed White
---
tools/tests/xen-access/xen-access.c | 173
From: Tamas K Lengyel
Wrappers to issue altp2m hvmops.
Signed-off-by: Tamas K Lengyel
Signed-off-by: Ravi Sahita
---
tools/libxc/Makefile | 1 +
tools/libxc/include/xenctrl.h | 21
tools/libxc/xc_altp2m.c | 237 ++
3 files changed
From: Ravi Sahita
Signed-off-by: Ravi Sahita
Acked-by: Daniel De Graaf
---
tools/flask/policy/policy/modules/xen/xen.if | 4 ++--
xen/arch/x86/hvm/hvm.c | 6 ++
xen/include/xsm/dummy.h | 12
xen/include/xsm/xsm.h
The altp2mhvm and nestedhvm parameters are mutually
exclusive and cannot be set together.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper for the hypervisor bits.
---
docs/man/xl.cfg.pod.5 | 12
tools/libxl/libxl.h | 6 ++
tools/libxl/libxl_create.c
Signed-off-by: Ed White
---
xen/arch/x86/hvm/hvm.c | 138
xen/include/public/hvm/hvm_op.h | 82
2 files changed, 220 insertions(+)
diff --git a/xen/arch/x86/hvm/hvm.c b/xen/arch/x86/hvm/hvm.c
index bda6c1e..23cd507
Add the remaining routines required to support enabling the alternate
p2m functionality.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
---
xen/arch/x86/hvm/hvm.c | 58 +-
xen/arch/x86/mm/hap/Makefile | 1 +
xen/arch/x86/mm/hap/altp2m_hap.c | 98 ++
xen/arch
Add a flag to indicate that a memory event occurred in an alternate p2m
and a field containing the p2m index. Allow any event response to switch
to a different alternate p2m using the same flag and field.
Modify p2m_mem_access_check() to handle alternate p2m's.
Signed-off-by: Ed White
Ack
From: George Dunlap
The existing ept_set_entry() and ept_get_entry() routines are extended
to optionally set/get suppress_ve. Passing -1 will set suppress_ve on
new p2m entries, or retain suppress_ve flag on existing entries.
Signed-off-by: George Dunlap
---
xen/arch/x86/mm/mem_sharing.c | 5
From: Ravi Sahita
Signed-off-by: Ravi Sahita
---
xen/arch/x86/hvm/emulate.c | 19 +--
xen/arch/x86/hvm/vmx/vmx.c | 29 +
xen/arch/x86/x86_emulate/x86_emulate.c | 20 +++-
xen/arch/x86/x86_emulate/x86_emulate.h |
holding the host p2m lock.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
---
xen/arch/x86/hvm/Makefile| 1 +
xen/arch/x86/hvm/altp2m.c| 92 +
xen/arch/x86/hvm/hvm.c | 21 +
xen/arch/x86/mm/hap/hap.c| 32 ++
Implement and hook up the code to enable VMX support of VMFUNC and #VE.
VMFUNC leaf 0 (EPTP switching) emulation is added in a later patch.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
Acked-by: Jun Nakajima
---
xen/arch/x86/hvm/vmx/vmx.c | 138
As implemented here, only supported on platforms with VMX HAP.
By default this functionality is force-disabled, it can be enabled
by specifying altp2m=1 on the Xen command line.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
---
docs/misc/xen-command-line.markdown | 7 +++
xen/arch
Currently, neither is enabled globally but may be enabled on a per-VCPU
basis by the altp2m code.
Remove the check for EPTE bit 63 == zero in ept_split_super_page(), as
that bit is now hardware-defined.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
Acked-by: George Dunlap
Acked-by: Jun
domain testing with a slightly
earlier patch series, and we hope he will submit that support.
Not all of the patches will be of interest to everyone copied here. I've
copied everyone on this initial mailing to give context.
Andrew Cooper (1):
common/domain: Helpers to pause a domain whil
t EPT violations only
the hypervisor is able to handle the violation.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
Reviewed-by: George Dunlap
Acked-by: Jun Nakajima
---
xen/arch/x86/mm/p2m-ept.c | 26 +-
1 file changed, 25 insertions(+), 1 deletion(-)
diff --git
From: Andrew Cooper
For use on codepaths which would need to use domain_pause() but might be in
the target domain's context. In the case that the target domain is in
context, all other vcpus are paused.
Signed-off-by: Andrew Cooper
---
xen/common/domain.c | 28
On 07/07/2015 03:10 AM, George Dunlap wrote:
> On 07/06/2015 07:43 PM, Ed White wrote:
>>> Introducing yet another layer -- particularly in a hooked interface like
>>> this -- just seems clunky. It's not the worst thing in the world; if I
>>> thought this would
On 07/07/2015 08:22 AM, Tim Deegan wrote:
> At 16:04 +0100 on 07 Jul (1436285059), George Dunlap wrote:
>> On 07/01/2015 07:09 PM, Ed White wrote:
>>> diff --git a/xen/arch/x86/mm/mm-locks.h b/xen/arch/x86/mm/mm-locks.h
>>> index b4f035e..301ca59 100644
>>&
On 07/06/2015 11:18 AM, Wei Liu wrote:
> On Mon, Jul 06, 2015 at 11:01:27AM -0700, Ed White wrote:
>> On 07/06/2015 10:49 AM, Wei Liu wrote:
>>>> diff --git a/tools/libxl/libxl_types.idl b/tools/libxl/libxl_types.idl
>>>> index 23f27d4..66a89cf 100644
>&
On 07/06/2015 11:29 AM, George Dunlap wrote:
> On 07/06/2015 06:35 PM, Ed White wrote:
>> On 07/06/2015 10:12 AM, George Dunlap wrote:
>>> On Fri, Jun 26, 2015 at 5:27 PM, Ed White wrote:
>>>> On 06/25/2015 11:04 PM, Jan Beulich wrote:
>>>>>>>&
On 07/06/2015 10:08 AM, Ian Jackson wrote:
> Ed White writes ("Re: [Xen-devel] [PATCH v3 11/13] x86/altp2m: define and
> implement alternate p2m HVMOP types."):
>> On 07/06/2015 03:09 AM, Andrew Cooper wrote:
>>> I am still very much unconvinced by the a
On 07/06/2015 10:49 AM, Wei Liu wrote:
>> diff --git a/tools/libxl/libxl_types.idl b/tools/libxl/libxl_types.idl
>> index 23f27d4..66a89cf 100644
>> --- a/tools/libxl/libxl_types.idl
>> +++ b/tools/libxl/libxl_types.idl
>> @@ -437,6 +437,7 @@ libxl_domain_build_info = Struct("domain_build_info",[
>
On 07/06/2015 10:12 AM, George Dunlap wrote:
> On Fri, Jun 26, 2015 at 5:27 PM, Ed White wrote:
>> On 06/25/2015 11:04 PM, Jan Beulich wrote:
>>>>>> On 25.06.15 at 18:36, wrote:
>>>> On 06/25/2015 01:12 AM, Jan Beulich wrote:
>>>>>>>&
On 07/06/2015 02:56 AM, Jan Beulich wrote:
>>>> On 03.07.15 at 18:22, wrote:
>> On 01/07/15 19:09, Ed White wrote:
>>> Add the basic data structures needed to support alternate p2m's and
>>> the functions to initialise them and tear them down.
>>>
On 07/06/2015 03:09 AM, Andrew Cooper wrote:
> On 01/07/15 19:09, Ed White wrote:
>> Signed-off-by: Ed White
>
> I am still very much unconvinced by the argument against having a single
> HVMOP_altp2m and a set of subops. do_domctl() and do_sysctl() are
> examples of a
On 07/03/2015 09:22 AM, Andrew Cooper wrote:
> On 01/07/15 19:09, Ed White wrote:
>> Add the basic data structures needed to support alternate p2m's and
>> the functions to initialise them and tear them down.
>>
>> Although Intel hardware can handle 512 EPTP'
From: Ravi Sahita
Signed-off-by: Ravi Sahita
---
tools/flask/policy/policy/modules/xen/xen.if | 4 +-
xen/arch/x86/hvm/hvm.c | 118 ---
xen/include/xsm/dummy.h | 12 +++
xen/include/xsm/xsm.h| 12 +++
The altp2mhvm and nestedhvm parameters are mutually
exclusive and cannot be set together.
Signed-off-by: Ed White
---
docs/man/xl.cfg.pod.5 | 12
tools/libxl/libxl_create.c | 1 +
tools/libxl/libxl_dom.c | 2 ++
tools/libxl/libxl_types.idl | 1 +
tools
Add the remaining routines required to support enabling the alternate
p2m functionality.
Signed-off-by: Ed White
---
xen/arch/x86/hvm/hvm.c | 58 +-
xen/arch/x86/mm/hap/Makefile | 1 +
xen/arch/x86/mm/hap/altp2m_hap.c | 98 ++
xen/arch/x86/mm/p2m-ept.c| 3
pointers are added to p2m_domain to allow direct
access to the extended routines.
Signed-off-by: Ed White
---
xen/arch/x86/mm/p2m-ept.c | 40 +---
xen/include/asm-x86/p2m.h | 13 +
2 files changed, 46 insertions(+), 7 deletions(-)
diff --git a/xen
Add a flag to indicate that a memory event occurred in an alternate p2m
and a field containing the p2m index. Allow any event response to switch
to a different alternate p2m using the same flag and field.
Modify p2m_memory_access_check() to handle alternate p2m's.
Signed-off-by: Ed
Signed-off-by: Ed White
---
xen/arch/x86/hvm/hvm.c | 201
xen/include/public/hvm/hvm_op.h | 69 ++
2 files changed, 270 insertions(+)
diff --git a/xen/arch/x86/hvm/hvm.c b/xen/arch/x86/hvm/hvm.c
index d2d90c8..0d81050 100644
--- a
t EPT violations only
the hypervisor is able to handle the violation.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
---
xen/arch/x86/mm/p2m-ept.c | 26 +-
1 file changed, 25 insertions(+), 1 deletion(-)
diff --git a/xen/arch/x86/mm/p2m-ept.c b/xen/arch/x86/mm/p2m-
t support.
Not all of the patches will be of interest to everyone copied here. I've
copied everyone on this initial mailing to give context.
Andrew Cooper (1):
common/domain: Helpers to pause a domain while in context
Ed White (10):
VMX: VMFUNC and #VE definitions and detection.
holding the host p2m lock.
Signed-off-by: Ed White
---
xen/arch/x86/hvm/Makefile| 1 +
xen/arch/x86/hvm/altp2m.c| 92 +
xen/arch/x86/hvm/hvm.c | 21 +
xen/arch/x86/mm/hap/hap.c| 31 -
xen/arch/x86/mm/m
From: Ravi Sahita
Signed-off-by: Ravi Sahita
---
xen/arch/x86/hvm/emulate.c | 12 +++--
xen/arch/x86/hvm/vmx/vmx.c | 30 +
xen/arch/x86/x86_emulate/x86_emulate.c | 48 +-
xen/arch/x86/x86_emulate/x86_emulate.h | 4
Implement and hook up the code to enable VMX support of VMFUNC and #VE.
VMFUNC leaf 0 (EPTP switching) emulation is added in a later patch.
Signed-off-by: Ed White
---
xen/arch/x86/hvm/vmx/vmx.c | 138 +
1 file changed, 138 insertions(+)
diff --git
From: Andrew Cooper
For use on codepaths which would need to use domain_pause() but might be in
the target domain's context. In the case that the target domain is in
context, all other vcpus are paused.
Signed-off-by: Andrew Cooper
---
xen/common/domain.c | 28
As implemented here, only supported on platforms with VMX HAP.
By default this functionality is force-disabled, it can be enabled
by specifying altp2m=1 on the Xen command line.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
---
docs/misc/xen-command-line.markdown | 7 +++
xen/arch
Currently, neither is enabled globally but may be enabled on a per-VCPU
basis by the altp2m code.
Remove the check for EPTE bit 63 == zero in ept_split_super_page(), as
that bit is now hardware-defined.
Signed-off-by: Ed White
Reviewed-by: Andrew Cooper
---
xen/arch/x86/hvm/vmx/vmcs.c
On 06/29/2015 06:03 AM, Andrew Cooper wrote:
> On 26/06/15 17:30, Ed White wrote:
>> On 06/24/2015 11:19 AM, Andrew Cooper wrote:
>>> On 24/06/15 18:47, Ed White wrote:
>>>>>> This looks like some hoop jumping around the assertions in
>>>>>> do
On 06/29/2015 06:00 AM, Andrew Cooper wrote:
> On 26/06/15 22:17, Ed White wrote:
>> On 06/24/2015 03:29 AM, Andrew Cooper wrote:
>>> On 22/06/15 19:56, Ed White wrote:
>>>> diff --git a/xen/include/asm-x86/hvm/vcpu.h
>>>> b/xen/include/asm-x86/hvm
On 06/29/2015 08:03 AM, George Dunlap wrote:
> On Mon, Jun 29, 2015 at 3:31 PM, Andrew Cooper
> wrote:
>> On 29/06/15 15:20, George Dunlap wrote:
>>> On Mon, Jun 22, 2015 at 7:56 PM, Ed White wrote:
>>>> In preparation for selectively enabling #VE in a later pa
On 06/26/2015 02:17 PM, Ed White wrote:
> On 06/24/2015 03:29 AM, Andrew Cooper wrote:
>> On 22/06/15 19:56, Ed White wrote:
>>> diff --git a/xen/include/asm-x86/hvm/vcpu.h b/xen/include/asm-x86/hvm/vcpu.h
>>> index 3d8f4dc..a1529c0 100644
>>> --- a/xen/incl
On 06/24/2015 03:29 AM, Andrew Cooper wrote:
> On 22/06/15 19:56, Ed White wrote:
>> diff --git a/xen/include/asm-x86/hvm/vcpu.h b/xen/include/asm-x86/hvm/vcpu.h
>> index 3d8f4dc..a1529c0 100644
>> --- a/xen/include/asm-x86/hvm/vcpu.h
>> +++ b/xen/include/asm-x86/hvm/
On 06/26/2015 12:24 PM, Daniel De Graaf wrote:
> On 06/22/2015 02:56 PM, Ed White wrote:
>> From: Ravi Sahita
>>
>> Signed-off-by: Ravi Sahita
>
> One comment, below.
>
> [...]
>> diff --git a/tools/flask/policy/policy/modules/xen/xen.if
>> b
On 06/24/2015 11:19 AM, Andrew Cooper wrote:
> On 24/06/15 18:47, Ed White wrote:
>>>> This looks like some hoop jumping around the assertions in
>>>> domain_pause() and vcpu_pause().
>>>>
>>>> We should probably have some new helpers where th
On 06/25/2015 11:04 PM, Jan Beulich wrote:
On 25.06.15 at 18:36, wrote:
>> On 06/25/2015 01:12 AM, Jan Beulich wrote:
>> On 24.06.15 at 19:53, wrote:
On 06/24/2015 07:38 AM, Jan Beulich wrote:
On 22.06.15 at 20:56, wrote:
>> --- a/xen/include/asm-x86/p2m.h
>> +++ b
On 06/25/2015 03:45 PM, Lengyel, Tamas wrote:
> On Thu, Jun 25, 2015 at 4:46 PM, Ed White wrote:
>
>> On 06/25/2015 11:23 AM, Lengyel, Tamas wrote:
>>> On Thu, Jun 25, 2015 at 12:48 PM, Ed White
>> wrote:
>>>
>>>> On 06/25/2015 06:40 AM, Raz
On 06/25/2015 11:23 AM, Lengyel, Tamas wrote:
> On Thu, Jun 25, 2015 at 12:48 PM, Ed White wrote:
>
>> On 06/25/2015 06:40 AM, Razvan Cojocaru wrote:
>>> On 06/25/2015 03:44 PM, Lengyel, Tamas wrote:
>>>> On Wed, Jun 24, 2015 at 2:06 PM, Ed White >>>
On 06/25/2015 10:29 AM, Lengyel, Tamas wrote:
>>
>> I plan to fix the bug, such that unshare will always occur before a copy.
>> I don't plan to make the altp2m's able to have shared pages.
>>
>> Ed
>>
>
> For now that is of course fine, memsharing is experimental and that's what
> I meant above.
On 06/25/2015 10:42 AM, Lengyel, Tamas wrote:
> On Thu, Jun 25, 2015 at 12:31 PM, Ed White wrote:
>
>> On 06/24/2015 07:44 PM, Lengyel, Tamas wrote:
>>>> +if ( altp2m_active )
>>>> +{
>>>> +if ( altp2mhvm_hap_nested_p
1 - 100 of 205 matches
Mail list logo
