Isaku Yamahata wrote:
On Tue, Mar 03, 2009 at 05:32:42PM +0800, Zhang, Xiantao wrote:
Isaku Yamahata wrote:
Could you elaborate on the concrete issue which you're seeing?
I guess the issue occurs when passed through pci device
is unplugged. But in that case, the region was occupied by
the
add suport for mov = ar.itc to pvchecker.
Signed-off-by: Isaku Yamahata yamah...@valinux.co.jp
---
arch/ia64/include/asm/native/pvchk_inst.h |5 +
arch/ia64/scripts/pvcheck.sed |1 +
2 files changed, 6 insertions(+), 0 deletions(-)
diff --git
paravirtualize gate.S.
Signed-off-by: Isaku Yamahata yamah...@valinux.co.jp
---
arch/ia64/include/asm/native/inst.h |5 +
arch/ia64/include/asm/native/pvchk_inst.h |3 +++
arch/ia64/kernel/gate.S | 17 +
3 files changed, 21 insertions(+), 4
paravirtualize mov reg = ar.itc.
Signed-off-by: Isaku Yamahata yamah...@valinux.co.jp
---
arch/ia64/include/asm/native/inst.h |5 +
arch/ia64/kernel/entry.S|4 ++--
arch/ia64/kernel/fsys.S |4 ++--
arch/ia64/kernel/ivt.S |2 +-
4 files
Move down __kernel_syscall_via_epc to the end of the page.
We want to paravirtualize only __kernel_syscall_via_epc because
it includes privileged instructions. Its paravirtualization increases
its symbols size.
On the other hand, each paravirtualized gate must have e symbols of
same value and
xen gate page paravirtualization
Signed-off-by: Isaku Yamahata yamah...@valinux.co.jp
---
arch/ia64/include/asm/xen/inst.h |4
arch/ia64/xen/Makefile |1 +
2 files changed, 5 insertions(+), 0 deletions(-)
diff --git a/arch/ia64/include/asm/xen/inst.h
use __initconst instead of __initdata for const data like
ec8148de85a73a3be397a59b6d8f4f32cf2dd254
Signed-off-by: Isaku Yamahata yamah...@valinux.co.jp
---
arch/ia64/xen/xen_pv_ops.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/arch/ia64/xen/xen_pv_ops.c
paravirtualize ar.itc and ar.itm in order to support save/restore.
Signed-off-by: Isaku Yamahata yamah...@valinux.co.jp
---
arch/ia64/include/asm/xen/inst.h | 21 +
arch/ia64/include/asm/xen/interface.h |9
arch/ia64/include/asm/xen/minstate.h | 11 -
This patch is ia64 counter part of clean up of the xen predicates.
Signed-off-by: Isaku Yamahata yamah...@valinux.co.jp
---
arch/ia64/include/asm/xen/hypervisor.h | 39 ++-
1 files changed, 18 insertions(+), 21 deletions(-)
diff --git
This is a preliminary patch to paravirtualizing fsys.S.
compile fsys.S twice one for native and one for xen, and switch
them at run tine.
Later fsys.S will be paravirtualized.
Signed-off-by: Isaku Yamahata yamah...@valinux.co.jp
---
arch/ia64/include/asm/xen/inst.h |3 +++
paravirtualize sched_clock.
Signed-off-by: Isaku Yamahata yamah...@valinux.co.jp
---
arch/ia64/xen/time.c | 48
1 files changed, 48 insertions(+), 0 deletions(-)
diff --git a/arch/ia64/xen/time.c b/arch/ia64/xen/time.c
index 68d6204..fb83326
This patch set is for the next merge window.
They are just enhancements of the already merged patches or ia64
porting from x86 paravirt techniques and that their quality is enough
for merge.
This patch set is for more paravirtualization on ia64/xen domU.
This patch set does
- remove existing
paravirtualize fsys.S.
Signed-off-by: Isaku Yamahata yamah...@valinux.co.jp
---
arch/ia64/kernel/fsys.S | 14 +++---
1 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S
index 788319f..3544d75 100644
---
Add two hooks, paravirt_get_fsyscall_table() and
paravirt_get_fsys_bubble_doen() to paravirtualize fsyscall implementation.
This patch just add the hooks fsyscall and don't paravirtualize it.
Signed-off-by: Isaku Yamahata yamah...@valinux.co.jp
---
arch/ia64/include/asm/native/inst.h |3 +++
define xen specific gate page.
At this phase bits in the gate page is same to native.
At the next phase, it will be paravirtualized.
Signed-off-by: Isaku Yamahata yamah...@valinux.co.jp
---
arch/ia64/include/asm/xen/patchlist.h | 38 +
paravirtualize gate page by allowing each pv_ops instances
to define its own gate page.
Signed-off-by: Isaku Yamahata yamah...@valinux.co.jp
---
arch/ia64/include/asm/native/patchlist.h | 38 ++
arch/ia64/include/asm/paravirt.h | 35 +
support binary patching for kernel module.
Signed-off-by: Isaku Yamahata yamah...@valinux.co.jp
---
arch/ia64/include/asm/module.h |6 ++
arch/ia64/kernel/module.c | 32
2 files changed, 38 insertions(+), 0 deletions(-)
diff --git
This patch set is for the next merge window.
They are just enhancements of the already merged patches or ia64 porting
from x86 paravirt techniques and that their quality is enough for merge.
This patch set is for binary patch optimization for paravirt_ops which
depends on the patch series I sent
define paravirt_dv_serialize_data() and insert it to suppress
false positive warnings.
Signed-off-by: Isaku Yamahata yamah...@valinux.co.jp
---
arch/ia64/include/asm/paravirt_privop.h |6 ++
arch/ia64/kernel/efi.c |1 +
arch/ia64/kvm/vtlb.c|2
implemented xen binary patch for pv_cpu_ops.
Signed-off-by: Isaku Yamahata yamah...@valinux.co.jp
---
arch/ia64/include/asm/xen/privop.h |4 +
arch/ia64/xen/hypercall.S |2 +
arch/ia64/xen/xen_pv_ops.c | 665
3 files changed, 671
add helper functions to support binary patching for paravirt_ops.
Signed-off-by: Isaku Yamahata yamah...@valinux.co.jp
---
arch/ia64/include/asm/paravirt_patch.h | 143 +
arch/ia64/kernel/paravirt_patch.c | 514
arch/ia64/kernel/paravirtentry.S
implement binary patching optimization for pv_cpu_ops.
With this optimization, indirect call for pv_cpu_ops methods can be
converted into inline execution or direct call.
Signed-off-by: Isaku Yamahata yamah...@valinux.co.jp
---
arch/ia64/include/asm/intrinsics.h |6 +-
On Wed, Mar 04, 2009 at 05:26:41PM +0800, Zhang, Xiantao wrote:
So far, we just found the msi-x case. Maybe we will add msi-x support later,
so this fix is also required.
Okay, makes sense.
And why GPFN_LOW_MMIO independently of addr? Shouldn't it be aware
of io_ranges[]?
For the
Isaku Yamahata wrote:
On Wed, Mar 04, 2009 at 05:26:41PM +0800, Zhang, Xiantao wrote:
So far, we just found the msi-x case. Maybe we will add msi-x
support later, so this fix is also required.
Okay, makes sense.
And why GPFN_LOW_MMIO independently of addr? Shouldn't it be aware
of
On Thu, Mar 05, 2009 at 11:55:10AM +0800, Zhang, Xiantao wrote:
Isaku Yamahata wrote:
On Wed, Mar 04, 2009 at 05:26:41PM +0800, Zhang, Xiantao wrote:
So far, we just found the msi-x case. Maybe we will add msi-x
support later, so this fix is also required.
Okay, makes sense.
And
25 matches
Mail list logo
