housekeeping_any_cpu() will return a housekeeping CPU. That's it. It'll
try to optimize for NUMA locality and to use the local CPU when
possible, but it's not a requisite.
So let's use raw_smp_processor_id() instead of its vanilla counterpart
in order to allow users to query for housekeeping CPUs without having to
disable preemption.
Signed-off-by: Nicolas Saenz Julienne <[email protected]>
---
NOTE: Resent as I forgot to CC the linux mailing list.
include/linux/sched/isolation.h | 2 +-
kernel/sched/isolation.c | 5 +++--
2 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index 8c15abd67aed..0c09ff1e4599 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -31,7 +31,7 @@ extern void __init housekeeping_init(void);
static inline int housekeeping_any_cpu(enum hk_type type)
{
- return smp_processor_id();
+ return raw_smp_processor_id();
}
static inline const struct cpumask *housekeeping_cpumask(enum hk_type type)
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index b4d10815c45a..3b8e1d47bbc0 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -43,14 +43,15 @@ int housekeeping_any_cpu(enum hk_type type)
if (static_branch_unlikely(&housekeeping_overridden)) {
if (housekeeping.flags & BIT(type)) {
- cpu = sched_numa_find_closest(housekeeping.cpumasks[type], smp_processor_id());
+ cpu = sched_numa_find_closest(housekeeping.cpumasks[type],
+ raw_smp_processor_id());
if (cpu < nr_cpu_ids)
return cpu;
return cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask);
}
}
- return smp_processor_id();
+ return raw_smp_processor_id();
}
EXPORT_SYMBOL_GPL(housekeeping_any_cpu);
--
2.35.1
Ftrace's fsnotify irq_work doesn't need to be run locally, so avoid
doing so when the CPU is isolated.
Note that this is especially bad when tracing an isolated CPU, as the
noise from running the irq_work might be bigger than what was actually
meant to be traced.
Signed-off-by: Nicolas Saenz Julienne <[email protected]>
---
kernel/trace/trace.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 7c85ce9ffdc3..2a3b969708a7 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -12,6 +12,7 @@
* Copyright (C) 2004-2006 Ingo Molnar
* Copyright (C) 2004 Nadia Yvette Chambers
*/
+#include <linux/sched/isolation.h>
#include <linux/ring_buffer.h>
#include <generated/utsrelease.h>
#include <linux/stacktrace.h>
@@ -1724,7 +1725,7 @@ void latency_fsnotify(struct trace_array *tr)
* possible that we are called from __schedule() or do_idle(), which
* could cause a deadlock.
*/
- irq_work_queue(&tr->fsnotify_irqwork);
+ irq_work_queue_on(&tr->fsnotify_irqwork, housekeeping_any_cpu(HK_FLAG_MISC));
}
#elif defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER) \
--
2.35.1
Hi Nicolas,
I love your patch! Yet something to improve:
[auto build test ERROR on tip/sched/core]
[also build test ERROR on next-20220225]
[cannot apply to rostedt-trace/for-next linus/master v5.17-rc6]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Nicolas-Saenz-Julienne/sched-isolation-Use-raw_smp_processor_id-in-housekeeping_any_cpu/20220228-221742
base: https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git 6255b48aebfd4dff375e97fc8b075a235848db0b
config: mips-allyesconfig (https://download.01.org/0day-ci/archive/20220301/[email protected]/config)
compiler: mips-linux-gcc (GCC) 11.2.0
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# https://github.com/0day-ci/linux/commit/e3ec0b4adfed05db0d559d2d5234d6d8f1034985
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review Nicolas-Saenz-Julienne/sched-isolation-Use-raw_smp_processor_id-in-housekeeping_any_cpu/20220228-221742
git checkout e3ec0b4adfed05db0d559d2d5234d6d8f1034985
# save the config file to linux build tree
mkdir build_dir
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-11.2.0 make.cross O=build_dir ARCH=mips SHELL=/bin/bash kernel/
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <[email protected]>
All errors (new ones prefixed by >>):
kernel/trace/trace.c: In function 'latency_fsnotify':
>> kernel/trace/trace.c:1728:71: error: 'HK_FLAG_MISC' undeclared (first use in this function); did you mean 'HK_TYPE_MISC'?
1728 | irq_work_queue_on(&tr->fsnotify_irqwork, housekeeping_any_cpu(HK_FLAG_MISC));
| ^~~~~~~~~~~~
| HK_TYPE_MISC
kernel/trace/trace.c:1728:71: note: each undeclared identifier is reported only once for each function it appears in
kernel/trace/trace.c: In function 'trace_check_vprintf':
kernel/trace/trace.c:3827:17: warning: function 'trace_check_vprintf' might be a candidate for 'gnu_printf' format attribute [-Wsuggest-attribute=format]
3827 | trace_seq_vprintf(&iter->seq, iter->fmt, ap);
| ^~~~~~~~~~~~~~~~~
kernel/trace/trace.c:3894:17: warning: function 'trace_check_vprintf' might be a candidate for 'gnu_printf' format attribute [-Wsuggest-attribute=format]
3894 | trace_seq_vprintf(&iter->seq, p, ap);
| ^~~~~~~~~~~~~~~~~
vim +1728 kernel/trace/trace.c
1718
1719 void latency_fsnotify(struct trace_array *tr)
1720 {
1721 if (!fsnotify_wq)
1722 return;
1723 /*
1724 * We cannot call queue_work(&tr->fsnotify_work) from here because it's
1725 * possible that we are called from __schedule() or do_idle(), which
1726 * could cause a deadlock.
1727 */
> 1728 irq_work_queue_on(&tr->fsnotify_irqwork, housekeeping_any_cpu(HK_FLAG_MISC));
1729 }
1730
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/[email protected]
On Tue, 2022-03-01 at 02:07 +0800, kernel test robot wrote:
> Hi Nicolas,
>
> I love your patch! Yet something to improve:
>
> [auto build test ERROR on tip/sched/core]
> [also build test ERROR on next-20220225]
> [cannot apply to rostedt-trace/for-next linus/master v5.17-rc6]
> [If your patch is applied to the wrong git tree, kindly drop us a note.
> And when submitting patch, we suggest to use '--base' as documented in
> https://git-scm.com/docs/git-format-patch]
>
> url: https://github.com/0day-ci/linux/commits/Nicolas-Saenz-Julienne/sched-isolation-Use-raw_smp_processor_id-in-housekeeping_any_cpu/20220228-221742
> base: https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git 6255b48aebfd4dff375e97fc8b075a235848db0b
> config: mips-allyesconfig (https://download.01.org/0day-ci/archive/20220301/[email protected]/config)
> compiler: mips-linux-gcc (GCC) 11.2.0
> reproduce (this is a W=1 build):
> wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
> chmod +x ~/bin/make.cross
> # https://github.com/0day-ci/linux/commit/e3ec0b4adfed05db0d559d2d5234d6d8f1034985
> git remote add linux-review https://github.com/0day-ci/linux
> git fetch --no-tags linux-review Nicolas-Saenz-Julienne/sched-isolation-Use-raw_smp_processor_id-in-housekeeping_any_cpu/20220228-221742
> git checkout e3ec0b4adfed05db0d559d2d5234d6d8f1034985
> # save the config file to linux build tree
> mkdir build_dir
> COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-11.2.0 make.cross O=build_dir ARCH=mips SHELL=/bin/bash kernel/
>
> If you fix the issue, kindly add following tag as appropriate
> Reported-by: kernel test robot <[email protected]>
>
> All errors (new ones prefixed by >>):
>
> kernel/trace/trace.c: In function 'latency_fsnotify':
> > > kernel/trace/trace.c:1728:71: error: 'HK_FLAG_MISC' undeclared (first use in this function); did you mean 'HK_TYPE_MISC'?
> 1728 | irq_work_queue_on(&tr->fsnotify_irqwork, housekeeping_any_cpu(HK_FLAG_MISC));
> | ^~~~~~~~~~~~
> | HK_TYPE_MISC
> kernel/trace/trace.c:1728:71: note: each undeclared identifier is reported only once for each function it appears in
> kernel/trace/trace.c: In function 'trace_check_vprintf':
> kernel/trace/trace.c:3827:17: warning: function 'trace_check_vprintf' might be a candidate for 'gnu_printf' format attribute [-Wsuggest-attribute=format]
> 3827 | trace_seq_vprintf(&iter->seq, iter->fmt, ap);
> | ^~~~~~~~~~~~~~~~~
> kernel/trace/trace.c:3894:17: warning: function 'trace_check_vprintf' might be a candidate for 'gnu_printf' format attribute [-Wsuggest-attribute=format]
> 3894 | trace_seq_vprintf(&iter->seq, p, ap);
> | ^~~~~~~~~~~~~~~~~
>
>
> vim +1728 kernel/trace/trace.c
>
> 1718
> 1719 void latency_fsnotify(struct trace_array *tr)
> 1720 {
> 1721 if (!fsnotify_wq)
> 1722 return;
> 1723 /*
> 1724 * We cannot call queue_work(&tr->fsnotify_work) from here because it's
> 1725 * possible that we are called from __schedule() or do_idle(), which
> 1726 * could cause a deadlock.
> 1727 */
> > 1728 irq_work_queue_on(&tr->fsnotify_irqwork, housekeeping_any_cpu(HK_FLAG_MISC));
> 1729 }
> 1730
It seems my patch conflicts with:
04d4e665a609 ("sched/isolation: Use single feature type while referring to housekeeping cpumask")
I'll rebase and send a v2.
--
Nicolás Sáenz
Hi Nicolas,
I love your patch! Yet something to improve:
[auto build test ERROR on tip/sched/core]
[also build test ERROR on next-20220228]
[cannot apply to rostedt-trace/for-next linus/master v5.17-rc6]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Nicolas-Saenz-Julienne/sched-isolation-Use-raw_smp_processor_id-in-housekeeping_any_cpu/20220228-221742
base: https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git 6255b48aebfd4dff375e97fc8b075a235848db0b
config: i386-randconfig-a002-20220228 (https://download.01.org/0day-ci/archive/20220301/[email protected]/config)
compiler: clang version 15.0.0 (https://github.com/llvm/llvm-project d271fc04d5b97b12e6b797c6067d3c96a8d7470e)
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# https://github.com/0day-ci/linux/commit/e3ec0b4adfed05db0d559d2d5234d6d8f1034985
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review Nicolas-Saenz-Julienne/sched-isolation-Use-raw_smp_processor_id-in-housekeeping_any_cpu/20220228-221742
git checkout e3ec0b4adfed05db0d559d2d5234d6d8f1034985
# save the config file to linux build tree
mkdir build_dir
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross W=1 O=build_dir ARCH=i386 SHELL=/bin/bash
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <[email protected]>
All errors (new ones prefixed by >>):
>> kernel/trace/trace.c:1728:64: error: use of undeclared identifier 'HK_FLAG_MISC'; did you mean 'HK_TYPE_MISC'?
irq_work_queue_on(&tr->fsnotify_irqwork, housekeeping_any_cpu(HK_FLAG_MISC));
^~~~~~~~~~~~
HK_TYPE_MISC
include/linux/sched/isolation.h:11:2: note: 'HK_TYPE_MISC' declared here
HK_TYPE_MISC,
^
1 error generated.
vim +1728 kernel/trace/trace.c
1718
1719 void latency_fsnotify(struct trace_array *tr)
1720 {
1721 if (!fsnotify_wq)
1722 return;
1723 /*
1724 * We cannot call queue_work(&tr->fsnotify_work) from here because it's
1725 * possible that we are called from __schedule() or do_idle(), which
1726 * could cause a deadlock.
1727 */
> 1728 irq_work_queue_on(&tr->fsnotify_irqwork, housekeeping_any_cpu(HK_FLAG_MISC));
1729 }
1730
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/[email protected]