From: Hidetoshi Seto <[email protected]>
register_sched_domain_sysctl() copies the cpu_possible_mask into
sd_sysctl_cpus, but only if sd_sysctl_cpus hasn't already been
allocated (ie, CONFIG_CPUMASK_OFFSTACK is set). However, when
CONFIG_CPUMASK_OFFSTACK is not set, sd_sysctl_cpus is left uninitialized
(all zeroes) and the kernel may fail to initialize sched_domain sysctl
entries for all possible cpus.
This is visible to the user if the kernel is booted with maxcpus=n, or
if ACPI tables have been modified to leave cpus offline, and then
checking for missing /proc/sys/kernel/sched_domain/cpu* entries.
Fix this by separating the allocataion and initialization, and adding
a flag to initialize the possible cpu entries while system booting only.
Signed-off-by: Hidetoshi Seto <[email protected]>
Reviewed-by: Masayoshi Mizuma <[email protected]>
Tested-by: Syuuichirou Ishii <[email protected]>
Tested-by: Tarumizu, Kohei <[email protected]>
---
kernel/sched/debug.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index de3de997e245..9c6637f3e21d 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -310,6 +310,7 @@ static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu)
static cpumask_var_t sd_sysctl_cpus;
static struct ctl_table_header *sd_sysctl_header;
+static int register_sched_domain_sysctl_on_boot = 1;
void register_sched_domain_sysctl(void)
{
@@ -344,9 +345,12 @@ void register_sched_domain_sysctl(void)
if (!cpumask_available(sd_sysctl_cpus)) {
if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL))
return;
+ }
+ if (register_sched_domain_sysctl_on_boot) {
/* init to possible to not have holes in @cpu_entries */
cpumask_copy(sd_sysctl_cpus, cpu_possible_mask);
+ register_sched_domain_sysctl_on_boot = 0;
}
for_each_cpu(i, sd_sysctl_cpus) {
--
2.20.1
On 01/29/2019 10:12 AM, Masayoshi Mizuma wrote:
> From: Hidetoshi Seto <[email protected]>
>
> register_sched_domain_sysctl() copies the cpu_possible_mask into
> sd_sysctl_cpus, but only if sd_sysctl_cpus hasn't already been
> allocated (ie, CONFIG_CPUMASK_OFFSTACK is set). However, when
> CONFIG_CPUMASK_OFFSTACK is not set, sd_sysctl_cpus is left uninitialized
> (all zeroes) and the kernel may fail to initialize sched_domain sysctl
> entries for all possible cpus.
>
> This is visible to the user if the kernel is booted with maxcpus=n, or
> if ACPI tables have been modified to leave cpus offline, and then
> checking for missing /proc/sys/kernel/sched_domain/cpu* entries.
>
> Fix this by separating the allocataion and initialization, and adding
nit: s/allocataion/allocation (perhaps maintainer can fixup?)
> a flag to initialize the possible cpu entries while system booting only.
>
> Signed-off-by: Hidetoshi Seto <[email protected]>
> Reviewed-by: Masayoshi Mizuma <[email protected]>
> Tested-by: Syuuichirou Ishii <[email protected]>
> Tested-by: Tarumizu, Kohei <[email protected]>
> ---
> kernel/sched/debug.c | 4 ++++
> 1 file changed, 4 insertions(+)
>
> diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
> index de3de997e245..9c6637f3e21d 100644
> --- a/kernel/sched/debug.c
> +++ b/kernel/sched/debug.c
> @@ -310,6 +310,7 @@ static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu)
>
> static cpumask_var_t sd_sysctl_cpus;
> static struct ctl_table_header *sd_sysctl_header;
> +static int register_sched_domain_sysctl_on_boot = 1;
>
> void register_sched_domain_sysctl(void)
> {
> @@ -344,9 +345,12 @@ void register_sched_domain_sysctl(void)
> if (!cpumask_available(sd_sysctl_cpus)) {
> if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL))
> return;
> + }
>
> + if (register_sched_domain_sysctl_on_boot) {
> /* init to possible to not have holes in @cpu_entries */
> cpumask_copy(sd_sysctl_cpus, cpu_possible_mask);
> + register_sched_domain_sysctl_on_boot = 0;
> }
>
> for_each_cpu(i, sd_sysctl_cpus) {
>
Thanks for posting ... looks good on aarch64 where the issue mentioned
in the commit message was reported.
Acked-by: Joe Lawrence <[email protected]>
-- Joe
On Tue, Jan 29, 2019 at 10:12:45AM -0500, Masayoshi Mizuma wrote:
> From: Hidetoshi Seto <[email protected]>
>
> register_sched_domain_sysctl() copies the cpu_possible_mask into
> sd_sysctl_cpus, but only if sd_sysctl_cpus hasn't already been
> allocated (ie, CONFIG_CPUMASK_OFFSTACK is set). However, when
> CONFIG_CPUMASK_OFFSTACK is not set, sd_sysctl_cpus is left uninitialized
> (all zeroes) and the kernel may fail to initialize sched_domain sysctl
> entries for all possible cpus.
>
> This is visible to the user if the kernel is booted with maxcpus=n, or
> if ACPI tables have been modified to leave cpus offline, and then
> checking for missing /proc/sys/kernel/sched_domain/cpu* entries.
>
> Fix this by separating the allocataion and initialization, and adding
> a flag to initialize the possible cpu entries while system booting only.
>
> Signed-off-by: Hidetoshi Seto <[email protected]>
> Reviewed-by: Masayoshi Mizuma <[email protected]>
> Tested-by: Syuuichirou Ishii <[email protected]>
> Tested-by: Tarumizu, Kohei <[email protected]>
> ---
> kernel/sched/debug.c | 4 ++++
> 1 file changed, 4 insertions(+)
>
> diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
> index de3de997e245..9c6637f3e21d 100644
> --- a/kernel/sched/debug.c
> +++ b/kernel/sched/debug.c
> @@ -310,6 +310,7 @@ static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu)
>
> static cpumask_var_t sd_sysctl_cpus;
> static struct ctl_table_header *sd_sysctl_header;
> +static int register_sched_domain_sysctl_on_boot = 1;
>
> void register_sched_domain_sysctl(void)
> {
> @@ -344,9 +345,12 @@ void register_sched_domain_sysctl(void)
> if (!cpumask_available(sd_sysctl_cpus)) {
> if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL))
> return;
> + }
>
> + if (register_sched_domain_sysctl_on_boot) {
> /* init to possible to not have holes in @cpu_entries */
> cpumask_copy(sd_sysctl_cpus, cpu_possible_mask);
> + register_sched_domain_sysctl_on_boot = 0;
> }
>
> for_each_cpu(i, sd_sysctl_cpus) {
I change it like the below. By keeping the initial value 0 it can go
into .bss instead of .data.
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -315,6 +315,7 @@ void register_sched_domain_sysctl(void)
{
static struct ctl_table *cpu_entries;
static struct ctl_table **cpu_idx;
+ static bool init_done = false;
char buf[32];
int i;
@@ -344,7 +345,10 @@ void register_sched_domain_sysctl(void)
if (!cpumask_available(sd_sysctl_cpus)) {
if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL))
return;
+ }
+ if (!init_done) {
+ init_done = true;
/* init to possible to not have holes in @cpu_entries */
cpumask_copy(sd_sysctl_cpus, cpu_possible_mask);
}
On Wed, Jan 30, 2019 at 09:14:00PM +0100, Peter Zijlstra wrote:
> On Tue, Jan 29, 2019 at 10:12:45AM -0500, Masayoshi Mizuma wrote:
> > From: Hidetoshi Seto <[email protected]>
> >
> > register_sched_domain_sysctl() copies the cpu_possible_mask into
> > sd_sysctl_cpus, but only if sd_sysctl_cpus hasn't already been
> > allocated (ie, CONFIG_CPUMASK_OFFSTACK is set). However, when
> > CONFIG_CPUMASK_OFFSTACK is not set, sd_sysctl_cpus is left uninitialized
> > (all zeroes) and the kernel may fail to initialize sched_domain sysctl
> > entries for all possible cpus.
> >
> > This is visible to the user if the kernel is booted with maxcpus=n, or
> > if ACPI tables have been modified to leave cpus offline, and then
> > checking for missing /proc/sys/kernel/sched_domain/cpu* entries.
> >
> > Fix this by separating the allocataion and initialization, and adding
> > a flag to initialize the possible cpu entries while system booting only.
> >
> > Signed-off-by: Hidetoshi Seto <[email protected]>
> > Reviewed-by: Masayoshi Mizuma <[email protected]>
> > Tested-by: Syuuichirou Ishii <[email protected]>
> > Tested-by: Tarumizu, Kohei <[email protected]>
> > ---
> > kernel/sched/debug.c | 4 ++++
> > 1 file changed, 4 insertions(+)
> >
> > diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
> > index de3de997e245..9c6637f3e21d 100644
> > --- a/kernel/sched/debug.c
> > +++ b/kernel/sched/debug.c
> > @@ -310,6 +310,7 @@ static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu)
> >
> > static cpumask_var_t sd_sysctl_cpus;
> > static struct ctl_table_header *sd_sysctl_header;
> > +static int register_sched_domain_sysctl_on_boot = 1;
> >
> > void register_sched_domain_sysctl(void)
> > {
> > @@ -344,9 +345,12 @@ void register_sched_domain_sysctl(void)
> > if (!cpumask_available(sd_sysctl_cpus)) {
> > if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL))
> > return;
> > + }
> >
> > + if (register_sched_domain_sysctl_on_boot) {
> > /* init to possible to not have holes in @cpu_entries */
> > cpumask_copy(sd_sysctl_cpus, cpu_possible_mask);
> > + register_sched_domain_sysctl_on_boot = 0;
> > }
> >
> > for_each_cpu(i, sd_sysctl_cpus) {
>
> I change it like the below. By keeping the initial value 0 it can go
> into .bss instead of .data.
Great, thanks!
Should I re-post the patch as v2?
- Masa
>
> --- a/kernel/sched/debug.c
> +++ b/kernel/sched/debug.c
> @@ -315,6 +315,7 @@ void register_sched_domain_sysctl(void)
> {
> static struct ctl_table *cpu_entries;
> static struct ctl_table **cpu_idx;
> + static bool init_done = false;
> char buf[32];
> int i;
>
> @@ -344,7 +345,10 @@ void register_sched_domain_sysctl(void)
> if (!cpumask_available(sd_sysctl_cpus)) {
> if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL))
> return;
> + }
>
> + if (!init_done) {
> + init_done = true;
> /* init to possible to not have holes in @cpu_entries */
> cpumask_copy(sd_sysctl_cpus, cpu_possible_mask);
> }
On 1/31/19 8:44 AM, Masayoshi Mizuma wrote:
> On Wed, Jan 30, 2019 at 09:14:00PM +0100, Peter Zijlstra wrote:
>> On Tue, Jan 29, 2019 at 10:12:45AM -0500, Masayoshi Mizuma wrote:
>>> From: Hidetoshi Seto <[email protected]>
>>>
>>> register_sched_domain_sysctl() copies the cpu_possible_mask into
>>> sd_sysctl_cpus, but only if sd_sysctl_cpus hasn't already been
>>> allocated (ie, CONFIG_CPUMASK_OFFSTACK is set). However, when
>>> CONFIG_CPUMASK_OFFSTACK is not set, sd_sysctl_cpus is left uninitialized
>>> (all zeroes) and the kernel may fail to initialize sched_domain sysctl
>>> entries for all possible cpus.
>>>
>>> This is visible to the user if the kernel is booted with maxcpus=n, or
>>> if ACPI tables have been modified to leave cpus offline, and then
>>> checking for missing /proc/sys/kernel/sched_domain/cpu* entries.
>>>
>>> Fix this by separating the allocataion and initialization, and adding
>>> a flag to initialize the possible cpu entries while system booting only.
>>>
>>> Signed-off-by: Hidetoshi Seto <[email protected]>
>>> Reviewed-by: Masayoshi Mizuma <[email protected]>
>>> Tested-by: Syuuichirou Ishii <[email protected]>
>>> Tested-by: Tarumizu, Kohei <[email protected]>
>>> ---
>>> kernel/sched/debug.c | 4 ++++
>>> 1 file changed, 4 insertions(+)
>>>
>>> diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
>>> index de3de997e245..9c6637f3e21d 100644
>>> --- a/kernel/sched/debug.c
>>> +++ b/kernel/sched/debug.c
>>> @@ -310,6 +310,7 @@ static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu)
>>>
>>> static cpumask_var_t sd_sysctl_cpus;
>>> static struct ctl_table_header *sd_sysctl_header;
>>> +static int register_sched_domain_sysctl_on_boot = 1;
>>>
>>> void register_sched_domain_sysctl(void)
>>> {
>>> @@ -344,9 +345,12 @@ void register_sched_domain_sysctl(void)
>>> if (!cpumask_available(sd_sysctl_cpus)) {
>>> if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL))
>>> return;
>>> + }
>>>
>>> + if (register_sched_domain_sysctl_on_boot) {
>>> /* init to possible to not have holes in @cpu_entries */
>>> cpumask_copy(sd_sysctl_cpus, cpu_possible_mask);
>>> + register_sched_domain_sysctl_on_boot = 0;
>>> }
>>>
>>> for_each_cpu(i, sd_sysctl_cpus) {
>>
>> I change it like the below. By keeping the initial value 0 it can go
>> into .bss instead of .data.
>
> Great, thanks!
> Should I re-post the patch as v2?
>
> - Masa
>
Peter's revision tests fine on my aarch64 box and would get my ACK,
however it ends up getting re-posted :)
Thanks,
-- Joe
>>
>> --- a/kernel/sched/debug.c
>> +++ b/kernel/sched/debug.c
>> @@ -315,6 +315,7 @@ void register_sched_domain_sysctl(void)
>> {
>> static struct ctl_table *cpu_entries;
>> static struct ctl_table **cpu_idx;
>> + static bool init_done = false;
>> char buf[32];
>> int i;
>>
>> @@ -344,7 +345,10 @@ void register_sched_domain_sysctl(void)
>> if (!cpumask_available(sd_sysctl_cpus)) {
>> if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL))
>> return;
>> + }
>>
>> + if (!init_done) {
>> + init_done = true;
>> /* init to possible to not have holes in @cpu_entries */
>> cpumask_copy(sd_sysctl_cpus, cpu_possible_mask);
>> }
-- Joe
Commit-ID: 1ca4fa3ab604734e38e2a3000c9abf788512ffa7
Gitweb: https://git.kernel.org/tip/1ca4fa3ab604734e38e2a3000c9abf788512ffa7
Author: Hidetoshi Seto <[email protected]>
AuthorDate: Tue, 29 Jan 2019 10:12:45 -0500
Committer: Ingo Molnar <[email protected]>
CommitDate: Mon, 4 Feb 2019 09:13:21 +0100
sched/debug: Initialize sd_sysctl_cpus if !CONFIG_CPUMASK_OFFSTACK
register_sched_domain_sysctl() copies the cpu_possible_mask into
sd_sysctl_cpus, but only if sd_sysctl_cpus hasn't already been
allocated (ie, CONFIG_CPUMASK_OFFSTACK is set). However, when
CONFIG_CPUMASK_OFFSTACK is not set, sd_sysctl_cpus is left
uninitialized (all zeroes) and the kernel may fail to initialize
sched_domain sysctl entries for all possible CPUs.
This is visible to the user if the kernel is booted with maxcpus=n, or
if ACPI tables have been modified to leave CPUs offline, and then
checking for missing /proc/sys/kernel/sched_domain/cpu* entries.
Fix this by separating the allocation and initialization, and adding a
flag to initialize the possible CPU entries while system booting only.
Tested-by: Syuuichirou Ishii <[email protected]>
Tested-by: Tarumizu, Kohei <[email protected]>
Signed-off-by: Hidetoshi Seto <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Masayoshi Mizuma <[email protected]>
Acked-by: Joe Lawrence <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Masayoshi Mizuma <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
---
kernel/sched/debug.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index de3de997e245..8039d62ae36e 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -315,6 +315,7 @@ void register_sched_domain_sysctl(void)
{
static struct ctl_table *cpu_entries;
static struct ctl_table **cpu_idx;
+ static bool init_done = false;
char buf[32];
int i;
@@ -344,7 +345,10 @@ void register_sched_domain_sysctl(void)
if (!cpumask_available(sd_sysctl_cpus)) {
if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL))
return;
+ }
+ if (!init_done) {
+ init_done = true;
/* init to possible to not have holes in @cpu_entries */
cpumask_copy(sd_sysctl_cpus, cpu_possible_mask);
}