the
problem. It allows functions common to some UV arches to use common defines
that might not be fully defined for all arches, as long as they do not
reference them on the unsupported arches.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Tested-by: John Estabrook
Tested-by: Gary
From: Dimitri Sivanich
Use no-op messages in place of cross-partition interrupts when nacking a
put message in the GRU. This allows us to remove MMR's as a destination
from the GRU driver.
Signed-off-by: Dimitri Sivanich
Signed-off-by: Mike Travis
Tested-by: John Estabrook
Tested-by:
This patch set primarily updates the Linux kernel to support the next
generation SGI Ultraviolet system, UV4. This architecture change is a
larger incremental change than previous UV updates because of a major
change to the addressing scheme. Previous UV architectures used a fixed
address width
The major portion of the hub info is common to all cpus on that hub.
This is step one of moving the per cpu hub info to a per node hub info
struct. This patch creates the small per cpu info struct that will
contain only information specific to each CPU.
Signed-off-by: Mike Travis
Reviewed-by
e hit rate when a group of cpus
on a node are all interrupted for a common task.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Reviewed-by: Andrew Banman
Tested-by: John Estabrook
Tested-by: Gary Kroening
---
arch/x86/include/asm/uv/uv_hub.h | 38 +--
arch/
definition.
This allows calling source code to be built for both pre-UV4 kernels as
well as post-UV4 kernels.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Tested-by: John Estabrook
Tested-by: Gary Kroening
---
arch/x86/include/asm/uv/uv_hub.h | 10 --
arch/x86/kernel/apic
From: Dimitri Sivanich
This patch fixes the problem of incorrect nodes and pnodes being returned when
referring to nodes that either have no cpus (AKA "headless") or no memory.
Signed-off-by: Dimitri Sivanich
Signed-off-by: Mike Travis
Tested-by: John Estabrook
Tested-by: Gar
An aspect of the UV4 system architecture changes involve changing the
way sockets, nodes, and pnodes are translated between one another.
Decode the information from the BIOS provided EFI system table to build
the needed conversion tables.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
UV
BIOS via the EFI UVsystab table. Support for older EFI UVsystab tables
is maintained.
Signed-off-by: Mike Travis
Tested-by: Dimitri Sivanich
Tested-by: John Estabrook
Tested-by: Gary Kroening
---
arch/x86/include/asm/uv/bios.h | 59 ++--
arch/
Since UV3 and UV4 MMIOH regions are setup the same, we can use a common
function to setup both.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Tested-by: John Estabrook
Tested-by: Gary Kroening
---
arch/x86/kernel/apic/x2apic_uv_x.c |3 ++-
1 file changed, 2 insertions(+), 1
Add UV4 specific defines to determine if current system type is a UV4 system.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Tested-by: John Estabrook
Tested-by: Gary Kroening
---
arch/x86/kernel/apic/x2apic_uv_x.c | 12 +---
1 file changed, 9 insertions(+), 3 deletions
Clean up any redundancies caused by new UV4 MMR definitions superseding
any previously definitions local to functions.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Reviewed-by: Andrew Banman
Tested-by: John Estabrook
Tested-by: Gary Kroening
---
arch/x86/include/asm/uv/uv_hub.h
measure execution time.
Signed-off-by: Mike Travis
Tested-by: Dimitri Sivanich
Tested-by: John Estabrook
Tested-by: Gary Kroening
---
arch/x86/include/asm/uv/uv_hub.h | 131 -
arch/x86/kernel/apic/x2apic_uv_x.c | 96 ++-
2 files
With the UV4 system architecture addressing changes, BIOS now provides
this information via an EFI system table. This is the initial decoding
of that system table. It also collects the sizing information for
later allocation of dynamic conversion tables.
Signed-off-by: Mike Travis
Reviewed-by
Change the references to the SCIR fields to the new per cpu info structs.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Tested-by: John Estabrook
Tested-by: Gary Kroening
---
arch/x86/include/asm/uv/uv_hub.h | 17 ++---
arch/x86/kernel/apic/x2apic_uv_x.c | 18
overlay addresses and NMI definitions to
allow for flexibility in newer UV architecture types.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Tested-by: John Estabrook
Tested-by: Gary Kroening
---
arch/x86/include/asm/uv/uv_hub.h |5
arch/x86/kernel/apic/x2apic_uv_x.c | 208
On 6/23/2015 2:01 AM, Ingo Molnar wrote:
>
> * Mike Travis wrote:
>
>> <<<
>> We have a large university system in the UK that is experiencing
>> very long delays modprobing the driver for a specific I/O device.
>> The delay is from 8-10 minutes per
On 6/22/2015 10:23 AM, Toshi Kani wrote:
> On Mon, 2015-06-22 at 09:21 -0700, Mike Travis wrote:
>>
>> On 6/19/2015 2:44 PM, Toshi Kani wrote:
>>> __ioremap_caller() calls region_is_ram() to look up the resource
>>> to check if a target range is RAM, which was a
On 6/19/2015 2:44 PM, Toshi Kani wrote:
> __ioremap_caller() calls region_is_ram() to look up the resource
> to check if a target range is RAM, which was added as an additinal
> check to improve the lookup performance over page_is_ram() (commit
> 906e36c5c717 "x86: use optimized ioresource lookup
On 5/1/2015 12:27 AM, Ingo Molnar wrote:
>
> * George Beshers wrote:
>
>> UV: NMI: simple dump failover if kdump fails
>>
>> The ability to trigger a kdump using the system NMI command
>> was added by
>>
>> commit 12ba6c990fab50fe568f3a
pport.
Signed-off-by: Mike Travis
Acked-by: Hedi Berriche
Acked-by: Dimitri Sivanich
---
arch/x86/kernel/apic/x2apic_uv_x.c | 74 -
1 file changed, 49 insertions(+), 25 deletions(-)
--- linux.orig/arch/x86/kernel/apic/x2apic_uv_x.c
+++ linux/arch/x86/kernel
Optimize the first "SGI" OEM check to return faster if the system is
not an SGI or UV system.
Signed-off-by: Mike Travis
Acked-by: Hedi Berriche
Acked-by: Dimitri Sivanich
---
arch/x86/kernel/apic/x2apic_uv_x.c |3 +++
1 file changed, 3 insertions(+)
--- linux.orig/arch/x86/k
In preparation for new UV systems, update various APIC checks
to prevent incompatible hardware/BIOS/kernel conflicts.
--
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org
Update check for UV2000/3000. Note when HUB is not recognized.
Signed-off-by: Mike Travis
Acked-by: Hedi Berriche
Acked-by: Dimitri Sivanich
---
arch/x86/kernel/apic/x2apic_uv_x.c | 10 +++---
1 file changed, 7 insertions(+), 3 deletions(-)
--- linux.orig/arch/x86/kernel/apic
On 3/23/2015 11:32 PM, Ingo Molnar wrote:
>
> * Mike Travis wrote:
>
>> Fix a bug in the oem check function that determines if the system
>> is a UV system and the BIOS is compatible with the kernel's UV apic
>> driver. This prevents some possibly obscure
pport. Also add update for new UV3000 system.
The first "OEM" check was also optimized to return faster if the
system is not an SGI or UV system.
Signed-off-by: Mike Travis
Acked-by: Hedi Berriche
Acked-by: Dimitri Sivanich
---
arch/x86/kernel/apic/x2api
On 8/29/2014 1:16 PM, Andrew Morton wrote:
> On Fri, 29 Aug 2014 14:53:28 -0500 Mike Travis wrote:
>
>>
>> We have a large university system in the UK that is experiencing
>> very long delays modprobing the driver for a specific I/O device.
>> The delay is fr
We have a large university system in the UK that is experiencing
very long delays modprobing the driver for a specific I/O device.
The delay is from 8-10 minutes per device and there are 31 devices
in the system. This 4 to 5 hour delay in starting up those I/O
devices is very much a burden on the
rted.
Otherwise, the ioremap operation continues.
Signed-off-by: Mike Travis
Acked-by: Alex Thorlton
Reviewed-by: Cliff Wickman
Cc:
---
v2: slight rearrangement of code
v3: added Cc: stable
---
arch/x86/mm/ioremap.c | 20
1 file changed, 16 insertions(+), 4 deletions(-)
--- li
result reflects if it was found or not (-1), and whether it is
RAM (1) or not (0). This allows the caller to fallback to the previous
page by page search if it was not found.
Signed-off-by: Mike Travis
Acked-by: Alex Thorlton
Reviewed-by: Cliff Wickman
Cc:
---
v2: remove 'weak
We have a large university system in the UK that is experiencing
very long delays modprobing the driver for a specific I/O device.
The delay is from 8-10 minutes per device and there are 31 devices
in the system. This 4 to 5 hour delay in starting up those I/O
devices is very much a burden on the
result reflects if it was found or not (-1), and whether it is
RAM (1) or not (0). This allows the caller to fallback to the previous
page by page search if it was not found.
Signed-off-by: Mike Travis
Acked-by: Alex Thorlton
Reviewed-by: Cliff Wickman
---
v2: remove 'weak' and EXPORT_
rted.
Otherwise, the ioremap operation continues.
Signed-off-by: Mike Travis
Acked-by: Alex Thorlton
Reviewed-by: Cliff Wickman
---
v2: slight rearrangement of code
---
arch/x86/mm/ioremap.c | 20
1 file changed, 16 insertions(+), 4 deletions(-)
--- linux.orig/arch/x86/mm/iore
On 8/27/2014 4:37 PM, Andrew Morton wrote:
> On Wed, 27 Aug 2014 16:25:24 -0700 Mike Travis wrote:
>
>>>
>>>
>>>
>>> Doing strcmp("System RAM") is rather a hack. Is there nothing in
>>> resource.flags which can be used? Or adde
On 8/27/2014 4:20 PM, Andrew Morton wrote:
> On Wed, 27 Aug 2014 16:15:28 -0700 Mike Travis wrote:
>
>>
>>>
>>>> There are two causes for requiring a restart/reload of the drivers.
>>>> First is periodic preventive maintenance (PM) and the seco
On 8/27/2014 4:18 PM, Andrew Morton wrote:
> On Wed, 27 Aug 2014 16:09:09 -0700 Mike Travis wrote:
>
>>
>>>>
>>>> ...
>>>>
>>>> --- linux.orig/kernel/resource.c
>>>> +++ linux/kernel/resource.c
>>>> @@ -494,6
On 8/27/2014 4:06 PM, Andrew Morton wrote:
> On Wed, 27 Aug 2014 17:59:27 -0500 Mike Travis wrote:
>
>>
>> We have a large university system in the UK that is experiencing
>> very long delays modprobing the driver for a specific I/O device.
>> The delay is fr
We have a large university system in the UK that is experiencing
very long delays modprobing the driver for a specific I/O device.
The delay is from 8-10 minutes per device and there are 31 devices
in the system. This 4 to 5 hour delay in starting up those I/O
devices is very much a burden on the
On 8/27/2014 4:05 PM, Andrew Morton wrote:
> On Wed, 27 Aug 2014 17:59:28 -0500 Mike Travis wrote:
>
>> Since the ioremap operation is verifying that the specified address range
>> is NOT RAM, it will search the entire ioresource list if the condition
>> is true. T
result reflects if it was found or not (-1), and whether it is
RAM (1) or not (0). This allows the caller to fallback to the previous
page by page search if it was not found.
Signed-off-by: Mike Travis
Acked-by: Alex Thorlton
Reviewed-by: Cliff Wickman
---
include/linux/mm.h |1 +
kernel
rted.
Otherwise, the ioremap operation continues.
Signed-off-by: Mike Travis
Acked-by: Alex Thorlton
Reviewed-by: Cliff Wickman
---
arch/x86/mm/ioremap.c | 22 +-
1 file changed, 17 insertions(+), 5 deletions(-)
--- linux.orig/arch/x86/mm/ioremap.c
+++ linux/arch/x86/mm/iore
On 3/5/2014 1:57 PM, Christoph Lameter wrote:
> The driver seems to use local64_t to define a single static instance of a
> counter and then seems to think that it is safe to increment the counter
> from multiple processors using local64_inc and friends. Common
> misunderstanding and a reason why
Commit-ID: fc8b13740b2978b34872650cc8e928392e3758aa
Gitweb: http://git.kernel.org/tip/fc8b13740b2978b34872650cc8e928392e3758aa
Author: Mike Travis
AuthorDate: Tue, 14 Jan 2014 10:25:52 -0600
Committer: Ingo Molnar
CommitDate: Sat, 25 Jan 2014 08:55:09 +0100
kgdb/kdb: Fix no KDB config
Commit-ID: 74c93f9d39b556ff9ac2340d568ad5caf8446c65
Gitweb: http://git.kernel.org/tip/74c93f9d39b556ff9ac2340d568ad5caf8446c65
Author: Mike Travis
AuthorDate: Tue, 14 Jan 2014 10:25:53 -0600
Committer: Ingo Molnar
CommitDate: Sat, 25 Jan 2014 08:55:10 +0100
x86/uv/nmi: Fix Sparse
Commit-ID: 64389998151214c71ba59ac893180744fd880052
Gitweb: http://git.kernel.org/tip/64389998151214c71ba59ac893180744fd880052
Author: Mike Travis
AuthorDate: Tue, 14 Jan 2014 10:25:54 -0600
Committer: Ingo Molnar
CommitDate: Sat, 25 Jan 2014 08:55:11 +0100
x86/uv/nmi, kgdb/kdb: Fix
v2: Update patch 2/3 to include which problems fixed. Other minor
changes detailed in the patches.
* 1/3: Change the fix for 'KDB not defined' build problem by changing
the kgdb_nmicallin() interface to include the KDB specific reason code.
This removes the dependency on KDB in the debug c
7;s
set to 'kdb' then an error message is displayed if KDB is not configured.
Also note that if both KGDB and KDB are enabled, then the action of 'kgdb'
or 'kdb' has no affect on which is used. See the KGDB documentation for
further information.
Signed-off-by: Mi
Make uv_register_nmi_notifier() and uv_handle_nmi_ping() static to
address sparse warnings.
Fix problem where uv_nmi_kexec_failed is unused when CONFIG_KEXEC
is not defined.
Signed-off-by: Mike Travis
Reviewed-by: Hedi Berriche
---
v2: update the description to include problems fixed
Some code added to the debug_core module had KDB dependencies that it
shouldn't have. Move the KDB dependent REASON back to the caller to
remove the dependency in the debug core code.
Update the call from the UV NMI handler to conform to the new interface.
Signed-off-by: Mike Travis
Rev
On 1/14/2014 3:00 AM, Peter Zijlstra wrote:
> On Mon, Jan 13, 2014 at 10:24:09PM -0600, Mike Travis wrote:
>> Fix some problems found by the kbuild test robot.
>>
>> Signed-off-by: Mike Travis
>> Reviewed-by: Hedi Berriche
>
> In general it is best to actu
* Change the fix for 'KDB not defined' build problem by changing
the kgdb_nmicallin() interface to include the KDB specific
reason code. This removes the dependency on KDB in the debug
core. It also requires a change to the kgdb call in from UV
NMI handler to avoid a compile error.
* Fi
Fix some problems found by the kbuild test robot.
Signed-off-by: Mike Travis
Reviewed-by: Hedi Berriche
---
arch/x86/include/asm/uv/uv.h |2 --
arch/x86/kernel/apic/x2apic_uv_x.c |1 -
arch/x86/platform/uv/uv_nmi.c |9 -
3 files changed, 4 insertions(+), 8
7;s
set to 'kdb' then an error message is displayed if KDB is not configured.
Note that if both KGDB and KDB are enabled, then the action of 'kgdb' or
'kdb' has no affect on which is used. See the KGDB documention for further
information.
Signed-off-by: Mike Trav
Some code added to the debug_core module had KDB dependencies that it
shouldn't have. Move the KDB dependent REASON back to the caller to
remove the dependency in the debug core code.
Signed-off-by: Mike Travis
Reviewed-by: Hedi Berriche
---
arch/x86/platform/uv/uv_nmi.c |2 +-
in
On 10/19/2013 1:56 AM, Ingo Molnar wrote:
>
> * Mike Travis wrote:
>
>>
>> * Change the fix for KDB not defined build problem by changing
>> the kgdb_nmicallin() interface to include the KDB specific
>> reason code. This removes a dependency on KDB in th
On 11/11/2013 10:53 AM, Ingo Molnar wrote:
>
> * tip-bot for Mike Travis wrote:
>
>> Commit-ID: 8eba18428ac926f436064ac281e76d36d51bd631
>> Gitweb:
>> http://git.kernel.org/tip/8eba18428ac926f436064ac281e76d36d51bd631
>> Author: Mike Travis
>>
Some code added to the debug_core module had KDB dependencies that it
shouldn't have. Move the KDB dependent REASON back to the caller to
remove the dependence in KGDB code.
Signed-off-by: Mike Travis
Reviewed-by: Hedi Berriche
---
arch/x86/platform/uv/uv_nmi.c |2 +-
include/linux/k
7;s
set to 'kdb' then an error message is displayed if KDB is not configured.
Note that if both KGDB and KDB are enabled, then the action of 'kgdb' or
'kdb' has no affect on which is used. See the KGDB documention for further
information.
Signed-off-by: Mike Trav
* Change the fix for KDB not defined build problem by changing
the kgdb_nmicallin() interface to include the KDB specific
reason code. This removes a dependency on KDB in the debug
core. Also requires a change the call in from UV NMI handler.
* Fix some problems found by the kbuild test r
Fix some problems found by the kbuild test robot.
Signed-off-by: Mike Travis
Reviewed-by: Hedi Berriche
---
arch/x86/include/asm/uv/uv.h |2 --
arch/x86/kernel/apic/x2apic_uv_x.c |1 -
arch/x86/platform/uv/uv_nmi.c |9 -
3 files changed, 4 insertions(+), 8
Commit-ID: 8daaa5f8261bffd2f6217a960f9182d0503a5c44
Gitweb: http://git.kernel.org/tip/8daaa5f8261bffd2f6217a960f9182d0503a5c44
Author: Mike Travis
AuthorDate: Wed, 2 Oct 2013 10:14:18 -0500
Committer: Ingo Molnar
CommitDate: Thu, 3 Oct 2013 18:47:54 +0200
kdb: Add support for external
Commit-ID: e379ea82dd53a5cc8e3ac0b7899a8012006c712c
Gitweb: http://git.kernel.org/tip/e379ea82dd53a5cc8e3ac0b7899a8012006c712c
Author: Mike Travis
AuthorDate: Wed, 2 Oct 2013 10:14:19 -0500
Committer: Ingo Molnar
CommitDate: Thu, 3 Oct 2013 18:48:09 +0200
x86/UV: Add call to KGDB/KDB
On 10/3/2013 10:53 AM, Mike Travis wrote:
>
>
> On 10/3/2013 10:15 AM, Ingo Molnar wrote:
>>
>> * Mike Travis wrote:
>>
>>>
>>>
>>> On 10/3/2013 9:51 AM, Ingo Molnar wrote:
>>>>
>>>> * Mike Travis wrote:
>>
On 10/3/2013 10:15 AM, Ingo Molnar wrote:
>
> * Mike Travis wrote:
>
>>
>>
>> On 10/3/2013 9:51 AM, Ingo Molnar wrote:
>>>
>>> * Mike Travis wrote:
>>>
>>>> Some code added to the debug_core module had KDB dependencies
On 10/3/2013 9:51 AM, Ingo Molnar wrote:
>
> * Mike Travis wrote:
>
>> Some code added to the debug_core module had KDB dependencies
>> that it shouldn't have.
>>
>> Signed-off-by: Mike Travis
>> ---
>> kernel/debug/debug_core.c |8
* Fix build problem when KDB is not defined.
--
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Some code added to the debug_core module had KDB dependencies
that it shouldn't have.
Signed-off-by: Mike Travis
---
kernel/debug/debug_core.c |8
kernel/debug/debug_core.h |2 ++
2 files changed, 6 insertions(+), 4 deletions(-)
--- linux.orig/kernel/debug/debug_c
The following two patches add the capability of calling KGDB/KDB after
receiving the NMI signal from the UV system 'power nmi' command. This
is mainly required because the system console on UV cannot send the
break signal so when the system I/O is not working, the power nmi
command from the CMC i
he slaves start entering.
The new argument "send_ready" was added for KGDB to signal the NMI handler
to release the slave CPUs for entry into KGDB.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Reviewed-by: Hedi Berriche
Acked-by: Jason Wessel
---
v3: make entry into SYSTEM_
quot; and the kernel is
built with CONFIG_KDB enabled. Note that if kgdb is connected that
interface will be used instead.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Reviewed-by: Hedi Berriche
---
arch/x86/platform/uv/uv_nmi.c | 47 +-
On 9/24/2013 12:52 AM, Ingo Molnar wrote:
>
> Hm, do you test-build your patches?
Both build and test incessantly...
This series produces the following
> annoying warning:
>
> arch/x86/platform/uv/uv_nmi.c: In function ‘uv_nmi_setup’:
> arch/x86/platform/uv/uv_nmi.c:664:2: warning: the add
Commit-ID: 0d12ef0c900078cc1f4e78dff2245521aa5d0c89
Gitweb: http://git.kernel.org/tip/0d12ef0c900078cc1f4e78dff2245521aa5d0c89
Author: Mike Travis
AuthorDate: Mon, 23 Sep 2013 16:25:01 -0500
Committer: Ingo Molnar
CommitDate: Tue, 24 Sep 2013 09:02:02 +0200
x86/UV: Update UV support
Commit-ID: 3c121d9a21dc16ef030ad6ca3ebb159b5726fab9
Gitweb: http://git.kernel.org/tip/3c121d9a21dc16ef030ad6ca3ebb159b5726fab9
Author: Mike Travis
AuthorDate: Mon, 23 Sep 2013 16:25:02 -0500
Committer: Ingo Molnar
CommitDate: Tue, 24 Sep 2013 09:02:03 +0200
x86/UV: Add summary of cpu
Commit-ID: 12ba6c990fab50fe568f3ad8715e81e356552428
Gitweb: http://git.kernel.org/tip/12ba6c990fab50fe568f3ad8715e81e356552428
Author: Mike Travis
AuthorDate: Mon, 23 Sep 2013 16:25:03 -0500
Committer: Ingo Molnar
CommitDate: Tue, 24 Sep 2013 09:02:03 +0200
x86/UV: Add kdump to UV NMI
Commit-ID: 8eba18428ac926f436064ac281e76d36d51bd631
Gitweb: http://git.kernel.org/tip/8eba18428ac926f436064ac281e76d36d51bd631
Author: Mike Travis
AuthorDate: Mon, 23 Sep 2013 16:25:06 -0500
Committer: Ingo Molnar
CommitDate: Tue, 24 Sep 2013 09:02:04 +0200
x86/UV: Add uvtrace support
Commit-ID: 1e019421bca68cfae1a61a09d9d49cf6a9e2143b
Gitweb: http://git.kernel.org/tip/1e019421bca68cfae1a61a09d9d49cf6a9e2143b
Author: Mike Travis
AuthorDate: Mon, 23 Sep 2013 16:25:00 -0500
Committer: Ingo Molnar
CommitDate: Tue, 24 Sep 2013 09:02:02 +0200
x86/UV: Move NMI support
EC enabled.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Reviewed-by: Hedi Berriche
---
arch/x86/platform/uv/uv_nmi.c | 41 +
1 file changed, 41 insertions(+)
--- linux.orig/arch/x86/platform/uv/uv_nmi.c
+++ linux/arch/x86/platform/uv/uv_nmi.c
@@ -
he slaves start entering.
The new argument "send_ready" was added for KGDB to signal the NMI handler
to release the slave CPUs for entry into KGDB.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Reviewed-by: Hedi Berriche
---
include/linux/kdb.h |
quot; and the kernel is
built with CONFIG_KDB enabled.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Reviewed-by: Hedi Berriche
---
arch/x86/platform/uv/uv_nmi.c | 47 +-
1 file changed, 46 insertions(+), 1 deletion(-)
--- linux.orig/arc
dress as well
as the command field and basic process information.
It is enabled when the nmi action is changed to "ips".
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Reviewed-by: Hedi Berriche
---
arch/x86/platform/uv/uv_nmi.c | 48
fic over
NumaLink.) Both types of UV NMIs from the SMI layer are supported.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Reviewed-by: Hedi Berriche
---
arch/x86/include/asm/uv/uv_hub.h | 57 +++
arch/x86/include/asm/uv/uv_mmrs.h | 31 ++
arch/x86/kernel/apic/x2apic_uv
instead of 'x2apic_uv_x', which was obscure.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Reviewed-by: Hedi Berriche
---
arch/x86/include/asm/uv/uv.h |2
arch/x86/kernel/apic/x2apic_uv_x.c | 69 -
arch/x86/platform/uv/Makefile |2
V3: Reduce number of changes to KGDB/KDB code to simplify special
handling of SYSTEM NMI. Remove disable UV NMI function.
V2: Split KDB updates from NMI updates. Broke up the big patch to
uv_nmi.c into smaller patches. Updated to the latest linux
kernel version.
The current U
This patch adds support for the uvtrace module by providing a skeleton
call to the registered trace function. It also provides another separate
'NMI' tracer that is triggered by the system wide 'power nmi' command.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanic
On 9/12/2013 10:27 AM, Paul E. McKenney wrote:
> On Tue, Sep 10, 2013 at 11:03:49AM +0200, Peter Zijlstra wrote:
>> On Mon, Sep 09, 2013 at 10:07:03AM -0700, Mike Travis wrote:
>>> On 9/9/2013 5:43 AM, Peter Zijlstra wrote:
>>>> On Thu, Sep 05, 2013 at 05:50
On 9/12/2013 11:35 AM, Paul E. McKenney wrote:
> On Thu, Sep 12, 2013 at 10:27:31AM -0700, Paul E. McKenney wrote:
>> On Tue, Sep 10, 2013 at 11:03:49AM +0200, Peter Zijlstra wrote:
>>> On Mon, Sep 09, 2013 at 10:07:03AM -0700, Mike Travis wrote:
>>>> On 9/9/2013
On 9/9/2013 5:43 AM, Peter Zijlstra wrote:
> On Thu, Sep 05, 2013 at 05:50:41PM -0500, Mike Travis wrote:
>> For performance reasons, the NMI handler may be disabled to lessen the
>> performance impact caused by the multiple perf tools running concurently.
>> If the system
On 9/5/2013 10:00 PM, Jason Wessel wrote:
> On 09/05/2013 05:50 PM, Mike Travis wrote:
>> This patch adds a new "KDB_REASON" code (KDB_REASON_SYSTEM_NMI). This
>> is purely cosmetic to distinguish it from the other various reasons that
>> NMI may occur and are
V2: Split KDB updates from NMI updates. Broke up the big patch to
uv_nmi.c into smaller patches. Updated to the latest linux
kernel version.
The current UV NMI handler has not been updated for the changes in the
system NMI handler and the perf operations. The UV NMI handler reads
an
instead of 'x2apic_uv_x', which was obscure.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Reviewed-by: Hedi Berriche
---
arch/x86/include/asm/uv/uv.h |2
arch/x86/kernel/apic/x2apic_uv_x.c | 69 -
arch/x86/platform/uv/Makefile |2
fic over
NumaLink.) Both types of UV NMIs from the SMI layer are supported.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Reviewed-by: Hedi Berriche
---
arch/x86/include/asm/uv/uv_hub.h | 57 +++
arch/x86/include/asm/uv/uv_mmrs.h | 31 ++
arch/x86/kernel/apic/x2apic_uv
quot; and the kernel is
built with CONFIG_KDB enabled.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Reviewed-by: Hedi Berriche
---
arch/x86/platform/uv/uv_nmi.c | 47 +-
1 file changed, 46 insertions(+), 1 deletion(-)
--- linux.orig/arc
handler is
disabled by setting the nmi disabled variable to '1'. Setting it back to
'0' will re-enable the NMI handler.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Reviewed-by: Hedi Berriche
---
arch/x86/platform/uv/uv_nmi.c | 69
EC enabled.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Reviewed-by: Hedi Berriche
---
arch/x86/platform/uv/uv_nmi.c | 41 +
1 file changed, 41 insertions(+)
--- linux.orig/arch/x86/platform/uv/uv_nmi.c
+++ linux/arch/x86/platform/uv/uv_nmi.c
@@ -
hen KDB
is entered manually via the sysreq 'g' key.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Reviewed-by: Hedi Berriche
---
include/linux/kdb.h |1 +
include/linux/kgdb.h|1 +
kernel/debug/debug_core.c |5 +
kernel/debug/kdb/k
he slaves start entering.
The new argument "send_ready" was added for KGDB to signal the NMI handler
to release the slave CPUs for entry into KGDB.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Reviewed-by: Hedi Berriche
---
include/linux/kgdb.h |1 +
kernel/
This patch adds support for the uvtrace module by providing a skeleton
call to the registered trace function. It also provides another separate
'NMI' tracer that is triggered by the system wide 'power nmi' command.
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanic
dress as well
as the command field and basic process information.
It is enabled when the nmi action is changed to "ips".
Signed-off-by: Mike Travis
Reviewed-by: Dimitri Sivanich
Reviewed-by: Hedi Berriche
---
arch/x86/platform/uv/uv_nmi.c | 48
On 8/13/2013 1:24 PM, Yinghai Lu wrote:
>> > FYI, the system at this time had 128 nodes each with 256GB of memory.
>> > About 252GB was inserted into the absent list from nodes 1 .. 126.
>> > Memory on nodes 0 and 128 was left fully present.
Actually, I was corrected, it was 256 nodes with 128GB
On 8/13/2013 11:04 AM, Mike Travis wrote:
>
>
> On 8/13/2013 10:51 AM, Linus Torvalds wrote:
>> by the time you can log in. And if it then takes another ten minutes
>> until you have the full 16TB initialized, and some things might be a
>> tad slower early on, doe
401 - 500 of 693 matches
Mail list logo
