On 09/26/2017 08:53 AM, Prarit Bhargava wrote:
> Sending to wider audience. I originally sent this to only the people Andi
> had cc'd.
Here's an example of the panic:
smpboot: Booting Node 1, Processors #1 OK
smpboot: Package 1 of CPU 1 exceeds BIO
On 09/26/2017 11:42 PM, Stephen Rothwell wrote:
> Hi all,
>
> After merging the tip tree, today's linux-next build (x86_64 allnoconfig)
> produced this warning:
>
> kernel/printk/printk.c:1983:12: warning: 'printk_time' defined but not used
> [-Wunused-variable]
> static int printk_time;
>
ime declaration for !CONFIG_PRINTK.
Reported-by: Petr Mladek
Signed-off-by: Prarit Bhargava
Cc: Thomas Gleixner
---
kernel/printk/printk.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 5e0bf2ef02f7..fe94246fa073 100644
--- a/ker
On 09/26/2017 11:33 AM, Thomas Gleixner wrote:
> On Tue, 26 Sep 2017, Prarit Bhargava wrote:
>> On 09/26/2017 11:26 AM, Thomas Gleixner wrote:
>>> On Tue, 26 Sep 2017, Prarit Bhargava wrote:
>>>
>>>> On 09/26/2017 04:42 AM, tip-bot for
On 09/26/2017 11:26 AM, Thomas Gleixner wrote:
> On Tue, 26 Sep 2017, Prarit Bhargava wrote:
>
>> On 09/26/2017 04:42 AM, tip-bot for Prarit Bhargava wrote:
>>> Commit-ID: 310b454a8653ea60d3eb21ce5ab03a282a32fbe1
>>> Gitweb:
On 09/26/2017 04:42 AM, tip-bot for Prarit Bhargava wrote:
> Commit-ID: 310b454a8653ea60d3eb21ce5ab03a282a32fbe1
> Gitweb: http://git.kernel.org/tip/310b454a8653ea60d3eb21ce5ab03a282a32fbe1
> Author: Prarit Bhargava
> AuthorDate: Mon, 18 Sep 2017 13:51:00 -0400
> Com
On 09/26/2017 07:48 AM, Petr Mladek wrote:
> On Mon 2017-09-18 13:51:00, Prarit Bhargava wrote:
>> printk.time=1/CONFIG_PRINTK_TIME=1 adds a unmodified local hardware clock
>> timestamp to printk messages. The local hardware clock loses time each
>> day making it difficult
ting the maximum logical package ID
after all the CPUs have been enumerated.
Signed-off-by: Prarit Bhargava
Cc: Thomas Gleixner
Cc: Ingo Molnar
Cc: "H. Peter Anvin"
Cc: x...@kernel.org
Cc: Peter Zijlstra
Cc: Andi Kleen
Cc: Dave Hansen
Cc: Piotr Luc
Cc: Kan Liang
Cc: Borislav Pe
stra
Cc: Andi Kleen
Cc: Dave Hansen
Cc: Piotr Luc
Cc: Kan Liang
Cc: Borislav Petkov
Cc: Stephane Eranian
Cc: Prarit Bhargava
Cc: Arvind Yadav
Cc: Andy Lutomirski
Cc: Christian Borntraeger
Cc: "Kirill A. Shutemov"
Cc: Tom Lendacky
Cc: He Chen
Cc: Mathias Krause
Cc: Tim Chen
C
ff-by: Prarit Bhargava
Cc: Thomas Gleixner
Cc: Ingo Molnar
Cc: "H. Peter Anvin"
Cc: x...@kernel.org
Cc: Peter Zijlstra
Cc: Andi Kleen
Cc: Dave Hansen
Cc: Piotr Luc
Cc: Kan Liang
Cc: Borislav Petkov
Cc: Stephane Eranian
Cc: Arvind Yadav
Cc: Andy Lutomirski
Cc: Christian
: "H. Peter Anvin"
Cc: x...@kernel.org
Cc: Peter Zijlstra
Cc: Andi Kleen
Cc: Dave Hansen
Cc: Piotr Luc
Cc: Kan Liang
Cc: Borislav Petkov
Cc: Stephane Eranian
Cc: Prarit Bhargava
Cc: Arvind Yadav
Cc: Andy Lutomirski
Cc: Christian Borntraeger
Cc: "Kirill A. Shutemov"
Commit-ID: a4c1a0002f4518363da9d9ecd7b805af152dcdf1
Gitweb: http://git.kernel.org/tip/a4c1a0002f4518363da9d9ecd7b805af152dcdf1
Author: Prarit Bhargava
AuthorDate: Mon, 28 Aug 2017 08:21:54 -0400
Committer: Thomas Gleixner
CommitDate: Mon, 25 Sep 2017 21:12:06 +0200
printk: Add
Commit-ID: 5df32107f609c1f621bcdac0a685c23677ef671e
Gitweb: http://git.kernel.org/tip/5df32107f609c1f621bcdac0a685c23677ef671e
Author: Prarit Bhargava
AuthorDate: Mon, 28 Aug 2017 08:21:53 -0400
Committer: Thomas Gleixner
CommitDate: Mon, 25 Sep 2017 21:05:59 +0200
timekeeping: Make
o fixes the test exiting with
>>> error code 0 if this was the only test failure.
>>>
>>> Cc: Thomas Gleixner
>>> Cc: Ingo Molnar
>>> Cc: Miroslav Lichvar
>>> Cc: Richard Cochran
>>> Cc: Prarit Bhargava
>>> Cc: Stephen Boyd
>
On 09/17/2017 06:46 AM, Sergey Senozhatsky wrote:
> I'm a bit uncomfortable with the "breaks user space" part. since this
> is a strictly debugging option, would it be sufficient to store those
> extended timestamps as prefixes of every message?
> see (sorry for "self-quoting"):
> lkml.ker
: Prarit Bhargava
Cc: Mark Salyzyn
Cc: Jonathan Corbet
Cc: Petr Mladek
Cc: Sergey Senozhatsky
Cc: Steven Rostedt
Cc: John Stultz
Cc: Thomas Gleixner
Cc: Stephen Boyd
Cc: Andrew Morton
Cc: Greg Kroah-Hartman
Cc: "Paul E. McKenney"
Cc: Christoffer Dall
Cc: Deepa Dinamani
Cc: Ingo
#x27;s real time patch
v12: Reword Kconfig names. Simplify timestamp logic and remove
recursive code.
Signed-off-by: Prarit Bhargava
Cc: Mark Salyzyn
Cc: Jonathan Corbet
Cc: Petr Mladek
Cc: Sergey Senozhatsky
Cc: Steven Rostedt
Cc: John Stultz
Cc: Thomas Gleixner
Cc: Stephen Boyd
Cc: A
timekeeping is initialized.
[v12]: Remove typecast.
Signed-off-by: Prarit Bhargava
Suggested-by: Peter Zijlstra
Cc: John Stultz
Cc: Thomas Gleixner
Cc: Stephen Boyd
---
kernel/time/timekeeping.c | 35 +--
1 file changed, 21 insertions(+), 14 deletions(-)
diff --git
From: Thomas Gleixner
The configurable printk timestamping wants access to clock realtime. Right
now there is no ktime_get_real_fast_ns() accessor because reading the
monotonic base and the realtime offset cannot be done atomically. Contrary
to boot time this offset can change during runtime and
On 09/15/2017 09:28 AM, Petr Mladek wrote:
>
> I am still slightly nervous that external tools would need updating.
> Also they might have troubles to interpret the time stamps especially
> when the source is changed at runtime via
> /sys/module/printk/parameters/time.
In earlier versions I had
On 09/05/2017 08:15 AM, Thomas Gleixner wrote:
> On Tue, 5 Sep 2017, Prarit Bhargava wrote:
>> +static struct tk_fast tk_fast_mono cacheline_aligned = {
>> +.base = {
>> +(struct tk_read_base){
>> +
From: Andi Kleen
The SNB-EP uncore driver is the only user of topology_phys_to_logical_pkg
in a performance critical path. Change it query the logical pkg ID
only once at initialization time and then cache it in box structure.
Signed-off-by: Andi Kleen
---
arch/x86/events/intel/uncore.c
ff-by: Prarit Bhargava
---
arch/x86/kernel/smpboot.c | 57 +--
1 file changed, 10 insertions(+), 47 deletions(-)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a6e9bd971b91..1b86ba57ab1a 100644
--- a/arch/x86/kernel/smpboot.c
From: Andi Kleen
I was looking at large early boot allocations and noticed that
since (1f12e32f x86/topology: Create logical package id)
every 64bit system allocates a 128k array to convert logical
package ids.
This happens because the array is sized for
MAX_LOCAL_APIC and that is always 32k on
Cleanup the logical package ID code by storing the logical package ID in
the cpuinfo_x86 struct and calculating the maximum logical package ID
after all the CPUs have been enumerated.
[v2]: Decrease logical_packages when the last thread in a socket is
removed.
Signed-off-by: Prarit Bhargava
On 09/11/2017 07:46 PM, kernel test robot wrote:
> FYI, we noticed the following commit:
>
> commit: 05aa90edc7910ec3d1ed791fa77371b3acb9bf08 ("x86/topology: Avoid
> wasting 128k for package id array")
> url:
> https://github.com/0day-ci/linux/commits/Andi-Kleen/perf-x86-intel-uncore-Cache-log
On 09/11/2017 07:46 PM, kernel test robot wrote:
> FYI, we noticed the following commit:
>
> commit: 05aa90edc7910ec3d1ed791fa77371b3acb9bf08 ("x86/topology: Avoid
> wasting 128k for package id array")
> url:
> https://github.com/0day-ci/linux/commits/Andi-Kleen/perf-x86-intel-uncore-Cache-log
From: Andi Kleen
I was looking at large early boot allocations and noticed that
since (1f12e32f x86/topology: Create logical package id)
every 64bit system allocates a 128k array to convert logical
package ids.
This happens because the array is sized for
MAX_LOCAL_APIC and that is always 32k on
-by: Prarit Bhargava
Andi Kleen (2):
perf/x86/intel/uncore: Cache logical pkg id in uncore driver
x86/topology: Avoid wasting 128k for package id array
Prarit Bhargava (1):
x86/smpboot: Fix __max_logical_packages estimate
arch/x86/events/intel/uncore.c | 1 +
arch/x86/events/in
From: Andi Kleen
The SNB-EP uncore driver is the only user of topology_phys_to_logical_pkg
in a performance critical path. Change it query the logical pkg ID
only once at initialization time and then cache it in box structure.
Signed-off-by: Andi Kleen
---
arch/x86/events/intel/uncore.c
ff-by: Prarit Bhargava
---
arch/x86/kernel/smpboot.c | 57 +--
1 file changed, 10 insertions(+), 47 deletions(-)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index ab588ff56650..51581a38543a 100644
--- a/arch/x86/kernel/smpboot.c
On 09/06/2017 02:36 PM, Prarit Bhargava wrote:
> A system booted with a small number of cores enabled per package
> panics because the estimate of __max_logical_packages is too low.
> This occurs when the total number of active cores across all packages
> is less than the maximum co
On 09/06/2017 07:17 PM, Andi Kleen wrote:
> From: Andi Kleen
>
> I was looking at large early boot allocations and noticed that
> since (1f12e32f x86/topology: Create logical package id)
> every 64bit system allocates a 128k array to convert logical
> package ids.
>
> This happens because the
__max_logical_packages is still insufficient during boot use the largest
possible value of Package ID.
Signed-off-by: Prarit Bhargava
Cc: Thomas Gleixner
Cc: Ingo Molnar
Cc: "H. Peter Anvin"
Cc: x...@kernel.org
Cc: Jean Delvare
Cc: Borislav Petkov
Cc: Andy Lutomirski
Cc: Tim Chen
timekeeping is initialized.
Signed-off-by: Prarit Bhargava
Suggested-by: Peter Zijlstra
Cc: John Stultz
Cc: Thomas Gleixner
Cc: Stephen Boyd
---
kernel/time/timekeeping.c | 47 +--
1 file changed, 33 insertions(+), 14 deletions(-)
diff --git a/kernel
and printk_get_first_ts() portions. Rename param
functions. Adjust configs, enum, and timestamp_sources_str to be 0-4.
Add mention realtime clock is UTC in Documentation.
v9: Fix typo. Add __ktime_get_real_fast_ns_unsafe().
v10: Remove time parameter restrictions.
Signed-off-by: Prarit Bha
issues relate to each other in real time.
Add monotonic, boottime, and real clock timestamps in addition to the existing
local hardware clock timestamp.
Signed-off-by: Prarit Bhargava
Cc: Mark Salyzyn
Cc: Jonathan Corbet
Cc: Petr Mladek
Cc: Sergey Senozhatsky
Cc: Steven Rostedt
Cc: John
From: Thomas Gleixner
The configurable printk timestamping wants access to clock realtime. Right
now there is no ktime_get_real_fast_ns() accessor because reading the
monotonic base and the realtime offset cannot be done atomically. Contrary
to boot time this offset can change during runtime and
issues relate to each other in real time.
Add monotonic, boottime, and real clock timestamps in addition to the existing
local hardware clock timestamp.
Signed-off-by: Prarit Bhargava
Cc: Mark Salyzyn
Cc: Jonathan Corbet
Cc: Petr Mladek
Cc: Sergey Senozhatsky
Cc: Steven Rostedt
Cc: John
_ts() portions. Rename param
functions. Adjust configs, enum, and timestamp_sources_str to be 0-4.
Add mention realtime clock is UTC in Documentation.
v9: Fix typo. Add __ktime_get_real_fast_ns_unsafe().
v10: Remove time parameter restrictions.
Signed-off-by: Prarit Bhargava
Cc: Mark Salyzyn
timekeeping is initialized.
Signed-off-by: Prarit Bhargava
Suggested-by: Peter Zijlstra
Cc: John Stultz
Cc: Thomas Gleixner
Cc: Stephen Boyd
---
kernel/time/timekeeping.c | 47 +--
1 file changed, 33 insertions(+), 14 deletions(-)
diff --git a/kernel
issues relate to each other in real time.
Add monotonic, boottime, and real clock timestamps in addition to the existing
local hardware clock timestamp.
Signed-off-by: Prarit Bhargava
Cc: Mark Salyzyn
Cc: Jonathan Corbet
Cc: Petr Mladek
Cc: Sergey Senozhatsky
Cc: Steven Rostedt
Cc: John
_ts() portions. Rename param
functions. Adjust configs, enum, and timestamp_sources_str to be 0-4.
Add mention realtime clock is UTC in Documentation.
v9: Fix typo. Add __ktime_get_real_fast_ns_unsafe().
Signed-off-by: Prarit Bhargava
Cc: Mark Salyzyn
Cc: Jonathan Corbet
Cc: Petr Mladek
Cc:
timekeeping is initialized.
Signed-off-by: Prarit Bhargava
Suggested-by: Peter Zijlstra
Cc: John Stultz
Cc: Thomas Gleixner
Cc: Stephen Boyd
---
kernel/time/timekeeping.c | 47 +--
1 file changed, 33 insertions(+), 14 deletions(-)
diff --git a/kernel
On 08/24/2017 02:50 PM, John Stultz wrote:
> On Thu, Aug 24, 2017 at 6:42 AM, Prarit Bhargava wrote:
>> --- a/include/linux/timekeeping.h
>> +++ b/include/linux/timekeeping.h
>> @@ -239,6 +239,7 @@ static inline u64 ktime_get_raw_ns(void)
>> extern u64 ktime_get_mon
issues relate to each other in real time.
Add monotonic, boottime, and real clock timestamps in addition to the existing
local hardware clock timestamp.
Signed-off-by: Prarit Bhargava
Cc: Mark Salyzyn
Cc: Jonathan Corbet
Cc: Petr Mladek
Cc: Sergey Senozhatsky
Cc: Steven Rostedt
Cc: John
name param
functions. Adjust configs, enum, and timestamp_sources_str to be 0-4.
Add mention realtime clock is UTC in Documentation.
Signed-off-by: Prarit Bhargava
Cc: Mark Salyzyn
Cc: Jonathan Corbet
Cc: Petr Mladek
Cc: Sergey Senozhatsky
Cc: Steven Rostedt
Cc: John Stultz
Cc: Thomas Gleixner
Cc:
timekeeping is initialized.
Signed-off-by: Prarit Bhargava
Suggested-by: Peter Zijlstra
Cc: John Stultz
Cc: Thomas Gleixner
Cc: Stephen Boyd
---
kernel/time/timekeeping.c | 47 +--
1 file changed, 33 insertions(+), 14 deletions(-)
diff --git a/kernel
On 08/23/2017 04:45 AM, Petr Mladek wrote:
> On Thu 2017-08-17 09:15:39, Prarit Bhargava wrote:
>> printk.time=1/CONFIG_PRINTK_TIME=1 adds a unmodified local hardware clock
>> timestamp to printk messages. The local hardware clock loses time each
>> day making it difficult
On 08/22/2017 10:23 AM, Petr Mladek wrote:
> On Tue 2017-08-22 10:09:40, Prarit Bhargava wrote:
>>
>>
>> On 08/17/2017 11:30 AM, Mark Salyzyn wrote:
>>> On 08/17/2017 06:15 AM, Prarit Bhargava wrote:
>>>> printk.time=1/CONFIG_PRINTK_TIME=1 adds a unmodif
On 08/17/2017 11:30 AM, Mark Salyzyn wrote:
> On 08/17/2017 06:15 AM, Prarit Bhargava wrote:
>> printk.time=1/CONFIG_PRINTK_TIME=1 adds a unmodified local hardware clock
>> timestamp to printk messages. The local hardware clock loses time each
>> day making it difficult
issues relate to each other in real time.
Add monotonic, boottime, and real clock timestamps in addition to the existing
local hardware clock timestamp.
Signed-off-by: Prarit Bhargava
Cc: Mark Salyzyn
Cc: Jonathan Corbet
Cc: Petr Mladek
Cc: Sergey Senozhatsky
Cc: Steven Rostedt
Cc: John
' Kconfig to avoid defconfig churn.
Signed-off-by: Prarit Bhargava
Cc: Mark Salyzyn
Cc: Jonathan Corbet
Cc: Petr Mladek
Cc: Sergey Senozhatsky
Cc: Steven Rostedt
Cc: John Stultz
Cc: Thomas Gleixner
Cc: Stephen Boyd
Cc: Andrew Morton
Cc: Greg Kroah-Hartman
Cc: "Paul E. McKenney
timekeeping is initialized.
Signed-off-by: Prarit Bhargava
Suggested-by: Peter Zijlstra
Cc: John Stultz
Cc: Thomas Gleixner
Cc: Stephen Boyd
---
kernel/time/timekeeping.c | 47 +--
1 file changed, 33 insertions(+), 14 deletions(-)
diff --git a/kernel
timekeeping is initialized.
v6: Separate these changes out into their own patch.
Signed-off-by: Prarit Bhargava
Suggested-by: Peter Zijlstra
Cc: John Stultz
Cc: Thomas Gleixner
Cc: Stephen Boyd
---
kernel/time/timekeeping.c | 47 +--
1 file changed, 33
NED).
v6: Define PRINTK_TIME_UNDEFINED for !CONFIG_PRINTK builds. Separate
timekeeping changes into separate patch. Minor include file cleanup.
Signed-off-by: Prarit Bhargava
Cc: Mark Salyzyn
Cc: Jonathan Corbet
Cc: Petr Mladek
Cc: Sergey Senozhatsky
Cc: Steven Rostedt
Cc: John Stultz
Cc: Th
issues relate to each other in real time.
Add monotonic, boottime, and real clock timestamps in addition to the existing
local hardware clock timestamp.
Signed-off-by: Prarit Bhargava
Cc: Mark Salyzyn
Cc: Jonathan Corbet
Cc: Petr Mladek
Cc: Sergey Senozhatsky
Cc: Steven Rostedt
Cc: John
r Dall
Cc: Deepa Dinamani
Cc: Ingo Molnar
Cc: Joel Fernandes
Cc: Prarit Bhargava
Cc: Kees Cook
Cc: Peter Zijlstra
Cc: Geert Uytterhoeven
Cc: "Luis R. Rodriguez"
Cc: Nicholas Piggin
Cc: "Jason A. Donenfeld"
Cc: Olof Johansson
Cc: Josh Poimboeuf
Cc: linux-...@vger
On 08/09/2017 02:24 PM, Luis R. Rodriguez wrote:
> On Mon, Aug 07, 2017 at 02:17:33PM -0400, Prarit Bhargava wrote:
>>
>>
>> On 08/07/2017 01:14 PM, Luis R. Rodriguez wrote:
>>
>>>
>>> Note printk_late_init() is a late_initcall(). This means if the
On 08/08/2017 04:28 AM, Peter Zijlstra wrote:
> On Mon, Aug 07, 2017 at 01:36:39PM -0700, Paul E. McKenney wrote:
>> On Mon, Aug 07, 2017 at 04:06:09PM -0400, Prarit Bhargava wrote:
>
>>> peterz? Want to offer a suggestion? The issue is that I'm changing a bool
>&
On 08/07/2017 08:19 PM, Sergey Senozhatsky wrote:
> On (08/07/17 11:52), Prarit Bhargava wrote:
> [..]
>> +if (strlen(param) == 1) {
>> +/* Preserve legacy boolean settings */
>> +if (!strcmp("0", param) || !strcmp("n&quo
On 08/07/2017 08:19 PM, Sergey Senozhatsky wrote:
> On (08/07/17 11:52), Prarit Bhargava wrote:
> [..]
>> +/**
>> + * enum printk_time_type - Timestamp types for printk() messages.
>> + * @PRINTK_TIME_DISABLE: No time stamp.
>> + * @PRINTK_TIME_LOCAL:
On 08/07/2017 02:47 PM, John Stultz wrote:
> On Mon, Aug 7, 2017 at 11:04 AM, Prarit Bhargava wrote:
>> On 08/07/2017 12:52 PM, John Stultz wrote:
>>> Still not quite following why you're updating all the defconfigs. I'd
>>> make sure the Kconfig default s
On 08/07/2017 01:14 PM, Luis R. Rodriguez wrote:
>
> Note printk_late_init() is a late_initcall(). This means if the
> printk_time_setting was disabled it will take a while to enable it. Enabling
> it
> is done at the device_initcall(), so if printk setting is disabled but a user
> enables it
On 08/07/2017 12:58 PM, Mark Salyzyn wrote:
> On 08/07/2017 08:52 AM, Prarit Bhargava wrote:
>> diff --git a/arch/arm/configs/aspeed_g4_defconfig
>> b/arch/arm/configs/aspeed_g4_defconfig
>> index cfc2465e8b77..5f3c50914e92 100644
>> --- a/arch/arm/configs/aspeed_g4_
On 08/07/2017 12:52 PM, John Stultz wrote:
> On Mon, Aug 7, 2017 at 8:52 AM, Prarit Bhargava wrote:
>> printk.time=1/CONFIG_PRINTK_TIME=1 adds a unmodified local hardware clock
>> timestamp to printk messages. The local hardware clock loses time each
>> day making it d
IME clock functionality.
v4: Fix messages, add additional printk.time options, and fix configs.
Signed-off-by: Prarit Bhargava
Cc: Mark Salyzyn
Cc: Jonathan Corbet
Cc: Petr Mladek
Cc: Sergey Senozhatsky
Cc: Steven Rostedt
Cc: John Stultz
Cc: Thomas Gleixner
Cc: Stephen Boyd
Cc: Andrew Morton
Cc: G
On 08/04/2017 11:36 AM, Mark Salyzyn wrote:
> On 08/03/2017 06:18 PM, Prarit Bhargava wrote:
>
>> diff --git a/arch/arm/configs/aspeed_g4_defconfig
>> b/arch/arm/configs/aspeed_g4_defconfig
>> index cfc2465e8b77..6c73c305ad17 100644
>> --- a/arch/arm/configs/asp
lock functionality.
Signed-off-by: Prarit Bhargava
Cc: Mark Salyzyn
Cc: Jonathan Corbet
Cc: Petr Mladek
Cc: Sergey Senozhatsky
Cc: Steven Rostedt
Cc: John Stultz
Cc: Thomas Gleixner
Cc: Stephen Boyd
Cc: Andrew Morton
Cc: Greg Kroah-Hartman
Cc: "Paul E. McKenney"
Cc: Christoffer
On 08/01/2017 12:29 PM, Luis R. Rodriguez wrote:
Thanks for the previous comments re: enum & kdoc'ifying. I will apply them to
v3.
>
> And since you are kdoc'ifying consider later adding proper rst format docs
> for printk and then pegging this kdoc entry into it. Unfortunately I only
> se
On 08/01/2017 01:00 PM, John Stultz wrote:
> On Tue, Aug 1, 2017 at 5:55 AM, Prarit Bhargava wrote:
>> printk.time=1/CONFIG_PRINTK_TIME=1 adds a unmodified local hardware clock
>> timestamp to printk messages. The local hardware clock loses time each
>> day making it d
k in the call to
ktime_get_log_ts() in printk_get_ts().
v2: Use peterz's suggested Kconfig options. Merge patchset together. Fix
i386 !CONFIG_PRINTK builds.
Signed-off-by: Prarit Bhargava
Cc: Mark Salyzyn
Cc: Jonathan Corbet
Cc: Petr Mladek
Cc: Sergey Senozhatsky
Cc: Steven Rostedt
On 07/25/2017 08:55 AM, Luis R. Rodriguez wrote:
> On Tue, Jul 25, 2017 at 08:17:26AM -0400, Prarit Bhargava wrote:
>> diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
>> index fc47863f629c..26cf6cadd267 100644
>> --- a/kernel/printk/printk.c
>> +
On 07/25/2017 09:00 AM, Peter Zijlstra wrote:
> On Tue, Jul 25, 2017 at 08:17:27AM -0400, Prarit Bhargava wrote:
>> diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
>> index 5b1662ec546f..6cd38a25f8ea 100644
>> --- a/lib/Kconfig.debug
>> +++ b/lib/Kconfig.debug
schuh
> wrote:
>> On Tue, 25 Jul 2017, Prarit Bhargava wrote:
>>> A common way of determining if the system is a virtual machine is to
>>> search /proc/cpuinfo flags entry for "hypervisor". turbostat must output
>>> a proper error message when found.
&g
On 07/26/2017 11:09 PM, Len Brown wrote:
> Henrique,
>
> I like your suggestion, thanks!
>
> BTW. let's discuss (and patch) turbostat on linux-pm, rather than on lkml.
Sure -- Len, can you add an entry to RHMAINTAINERS for that? I use the
get_maintainer.pl script to apply all cc's.
P.
if the system is a virtual machine is to
search /proc/cpuinfo flags entry for "hypervisor". turbostat must output
a proper error message when found.
Signed-off-by: Prarit Bhargava
Cc: Len Brown
Cc: Len Brown
---
tools/power/x86/turbostat/turbostat.c | 34 +++
.
Set max_num_cpus to the length of a cpumask.
Signed-off-by: Prarit Bhargava
Cc: Len Brown
---
tools/power/x86/turbostat/turbostat.c | 21 -
1 file changed, 16 insertions(+), 5 deletions(-)
diff --git a/tools/power/x86/turbostat/turbostat.c
b/tools/power/x86/turbostat
The code can be simplified if the cpu_topology *cpus tracks the thread
IDs. This removes an additional file lookup and simplifies the counter
initialization code.
Add thread ID to cpu_topology information and cleanup the counter
initialization code.
Signed-off-by: Prarit Bhargava
Cc: Len Brown
cannot
handle this configuration, and as a result only shows 1/2 the cores in its
output.
This patchset makes turbostate aware of nodes. It has been tested on
various AMD and Intel systems and no issues have been found.
Signed-off-by: Prarit Bhargava
Cc: Len Brown
Prarit Bhargava (7
turbostat incorrectly assumes that there is one node per package. As a
result num_cores_per_pkg is not correctly named and is actually
num_cores_per_node.
Rename num_cores_per_pkg to num_cores_per_node.
Signed-off-by: Prarit Bhargava
Cc: Len Brown
---
tools/power/x86/turbostat/turbostat.c
The previous patches have added node information to turbostat, but the
counters code does not take it into account.
Add node information from cpu_topology calculations to turbostat
counters.
Signed-off-by: Prarit Bhargava
Cc: Len Brown
---
tools/power/x86/turbostat/turbostat.c | 143
ssing Unit/Thread
IDs information to each cpu_topology struct. Confirm that the thread
is on the same core as indicated by thread_siblings_list.
Signed-off-by: Prarit Bhargava
Cc: Len Brown
---
tools/power/x86/turbostat/turbostat.c | 112 +++---
1 file change
er
to properly enumerate the cores we need to track both the physical and
logical node IDs.
Add physical_node_id to track the node ID assigned by the kernel, and
logical_node_id used by turbostat to track the nodes per package ie) a 0-based
count within the package.
Signed-off-by: Prarit Bhargava
Cc
Cleanup, remove num_ from num_nodes_per_pkg, num_cores_per_node, and
num_threads_per_node.
Signed-off-by: Prarit Bhargava
Cc: Len Brown
---
tools/power/x86/turbostat/turbostat.c | 46 +--
1 file changed, 23 insertions(+), 23 deletions(-)
diff --git a/tools
the protection of a sequence lock in the
call to ktime_get_log_ts() in printk_get_ts().
Signed-off-by: Prarit Bhargava
Cc: Mark Salyzyn
Cc: Jonathan Corbet
Cc: Petr Mladek
Cc: Sergey Senozhatsky
Cc: Steven Rostedt
Cc: John Stultz
Cc: Thomas Gleixner
Cc: Stephen Boyd
Cc: Andrew Morton
Cc:
CONFIG_PRINTK_TIME is a bool and in order to add timestamp options for
the monotonic and real time clock it must be expanded to an int.
Signed-off-by: Prarit Bhargava
Cc: Mark Salyzyn
Cc: Jonathan Corbet
Cc: Petr Mladek
Cc: Sergey Senozhatsky
Cc: Steven Rostedt
Cc: John Stultz
Cc: Thomas
otection of a sequence lock in the call to
ktime_get_log_ts() in printk_get_ts().
Signed-off-by: Prarit Bhargava
Cc: Mark Salyzyn
Cc: Jonathan Corbet
Cc: Petr Mladek
Cc: Sergey Senozhatsky
Cc: Steven Rostedt
Cc: John Stultz
Cc: Thomas Gleixner
Cc: Stephen Boyd
Cc: Andrew Morton
Cc: Greg Kroa
On 07/19/2017 08:28 AM, Thomas Gleixner wrote:
> On Wed, 19 Jul 2017, Prarit Bhargava wrote:
>> On 07/19/2017 03:23 AM, Thomas Gleixner wrote:
>>> There is another option to remedy this and the dmesg tooling issues:
>>>
>>> Instead of switching the time sta
Forgot to cc Len at his kernel.org address ...
P.
On 07/16/2017 04:49 PM, Prarit Bhargava wrote:
> AMD family processors do not show all cores in the output of turbostat. This
> occurs because AMD has multiple nodes per socket and enumerates cores
> within each node from 0. For exampl
On 07/19/2017 03:23 AM, Thomas Gleixner wrote:
> On Tue, 18 Jul 2017, Mark Salyzyn wrote:
>> On 07/18/2017 03:35 PM, Thomas Gleixner wrote:
>>> There was some discussion about making the clock source for dmesg time
>>> stamps selectable, so you can use MONOTONIC, REALTIME, BOOTTIME. The
>>> patch
cannot
handle this configuration, and as a result only shows 1/2 the cores in its
output.
This patchset makes turbostate aware of nodes. It has been tested on
various AMD and Intel systems and no issues have been found.
Signed-off-by: Prarit Bhargava
Cc: Len Brown
Prarit Bhargava (7
.
Set max_num_cpus to the length of a cpumask.
Signed-off-by: Prarit Bhargava
Cc: Len Brown
---
tools/power/x86/turbostat/turbostat.c | 21 -
1 file changed, 16 insertions(+), 5 deletions(-)
diff --git a/tools/power/x86/turbostat/turbostat.c
b/tools/power/x86/turbostat
The code can be simplified if the cpu_topology *cpus tracks the thread
IDs. This removes an additional file lookup and simplifies the counter
initialization code.
Add thread ID to cpu_topology information and cleanup the counter
initialization code.
Signed-off-by: Prarit Bhargava
Cc: Len Brown
ssing Unit/Thread
IDs information to each cpu_topology struct. Confirm that the thread
is on the same core as indicated by thread_siblings_list.
Signed-off-by: Prarit Bhargava
Cc: Len Brown
---
tools/power/x86/turbostat/turbostat.c | 112 +++---
1 file change
er
to properly enumerate the cores we need to track both the physical and
logical node IDs.
Add physical_node_id to track the node ID assigned by the kernel, and
logical_node_id used by turbostat to track the nodes per package ie) a 0-based
count within the package.
Signed-off-by: Prarit Bhargava
Cc
turbostat incorrectly assumes that there is one node per package. As a
result num_cores_per_pkg is not correctly named and is actually
num_cores_per_node.
Rename num_cores_per_pkg to num_cores_per_node.
Signed-off-by: Prarit Bhargava
Cc: Len Brown
---
tools/power/x86/turbostat/turbostat.c
The previous patches have added node information to turbostat, but the
counters code does not take it into account.
Add node information from cpu_topology calculations to turbostat
counters.
Signed-off-by: Prarit Bhargava
Cc: Len Brown
---
tools/power/x86/turbostat/turbostat.c | 143
Cleanup, remove num_ from num_nodes_per_pkg, num_cores_per_node, and
num_threads_per_node.
Signed-off-by: Prarit Bhargava
Cc: Len Brown
---
tools/power/x86/turbostat/turbostat.c | 46 +--
1 file changed, 23 insertions(+), 23 deletions(-)
diff --git a/tools
On 06/21/2017 11:47 AM, Liang, Kan wrote:
>
>
>> On Wed, 21 Jun 2017, kan.li...@intel.com wrote:
>>>
>>> #ifdef CONFIG_HARDLOCKUP_DETECTOR
>>> +/*
>>> + * The NMI watchdog relies on PERF_COUNT_HW_CPU_CYCLES event,
>> which
>>> + * can tick faster than the measured CPU Frequency due to Turbo mo
201 - 300 of 1060 matches
Mail list logo