| Message ID | 20220411233832.391817-4-dmitry.osipenko@collabora.com |
|---|---|
| State | New |
| Headers | show |
| Series | Introduce power-off+restart call chain API | expand |
On Tue, Apr 12, 2022 at 1:39 AM Dmitry Osipenko <dmitry.osipenko@collabora.com> wrote: > > Add sanity check which ensures that there are no two restart handlers > registered using the same priority. This requirement will become mandatory > once all drivers will be converted to the new API and such errors will be > fixed. > > Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com> The first two patches in the series are fine with me and there's only one minor nit regarding this one (below). > --- > kernel/reboot.c | 15 +++++++++++++++ > 1 file changed, 15 insertions(+) > > diff --git a/kernel/reboot.c b/kernel/reboot.c > index ed4e6dfb7d44..acdae4e95061 100644 > --- a/kernel/reboot.c > +++ b/kernel/reboot.c > @@ -182,6 +182,21 @@ static ATOMIC_NOTIFIER_HEAD(restart_handler_list); > */ > int register_restart_handler(struct notifier_block *nb) > { > + int ret; > + > + ret = atomic_notifier_chain_register_unique_prio(&restart_handler_list, nb); > + if (ret != -EBUSY) > + return ret; > + > + /* > + * Handler must have unique priority. Otherwise call order is > + * determined by registration order, which is unreliable. > + * > + * This requirement will become mandatory once all drivers > + * will be converted to use new sys-off API. > + */ > + pr_err("failed to register restart handler using unique priority\n"); I would use pr_info() here, because this is not a substantial error AFAICS. > + > return atomic_notifier_chain_register(&restart_handler_list, nb); > } > EXPORT_SYMBOL(register_restart_handler); > --
On 4/13/22 21:48, Rafael J. Wysocki wrote: > On Tue, Apr 12, 2022 at 1:39 AM Dmitry Osipenko > <dmitry.osipenko@collabora.com> wrote: >> >> Add sanity check which ensures that there are no two restart handlers >> registered using the same priority. This requirement will become mandatory >> once all drivers will be converted to the new API and such errors will be >> fixed. >> >> Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com> > > The first two patches in the series are fine with me and there's only > one minor nit regarding this one (below). > >> --- >> kernel/reboot.c | 15 +++++++++++++++ >> 1 file changed, 15 insertions(+) >> >> diff --git a/kernel/reboot.c b/kernel/reboot.c >> index ed4e6dfb7d44..acdae4e95061 100644 >> --- a/kernel/reboot.c >> +++ b/kernel/reboot.c >> @@ -182,6 +182,21 @@ static ATOMIC_NOTIFIER_HEAD(restart_handler_list); >> */ >> int register_restart_handler(struct notifier_block *nb) >> { >> + int ret; >> + >> + ret = atomic_notifier_chain_register_unique_prio(&restart_handler_list, nb); >> + if (ret != -EBUSY) >> + return ret; >> + >> + /* >> + * Handler must have unique priority. Otherwise call order is >> + * determined by registration order, which is unreliable. >> + * >> + * This requirement will become mandatory once all drivers >> + * will be converted to use new sys-off API. >> + */ >> + pr_err("failed to register restart handler using unique priority\n"); > > I would use pr_info() here, because this is not a substantial error AFAICS. It's indeed not a substantial error so far, but it will become substantial later on once only unique priorities will be allowed. The pr_warn() could be a good compromise here, pr_info() is too mild, IMO.
On Thu, Apr 14, 2022 at 12:24 AM Dmitry Osipenko <dmitry.osipenko@collabora.com> wrote: > > On 4/13/22 21:48, Rafael J. Wysocki wrote: > > On Tue, Apr 12, 2022 at 1:39 AM Dmitry Osipenko > > <dmitry.osipenko@collabora.com> wrote: > >> > >> Add sanity check which ensures that there are no two restart handlers > >> registered using the same priority. This requirement will become mandatory > >> once all drivers will be converted to the new API and such errors will be > >> fixed. > >> > >> Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com> > > > > The first two patches in the series are fine with me and there's only > > one minor nit regarding this one (below). > > > >> --- > >> kernel/reboot.c | 15 +++++++++++++++ > >> 1 file changed, 15 insertions(+) > >> > >> diff --git a/kernel/reboot.c b/kernel/reboot.c > >> index ed4e6dfb7d44..acdae4e95061 100644 > >> --- a/kernel/reboot.c > >> +++ b/kernel/reboot.c > >> @@ -182,6 +182,21 @@ static ATOMIC_NOTIFIER_HEAD(restart_handler_list); > >> */ > >> int register_restart_handler(struct notifier_block *nb) > >> { > >> + int ret; > >> + > >> + ret = atomic_notifier_chain_register_unique_prio(&restart_handler_list, nb); > >> + if (ret != -EBUSY) > >> + return ret; > >> + > >> + /* > >> + * Handler must have unique priority. Otherwise call order is > >> + * determined by registration order, which is unreliable. > >> + * > >> + * This requirement will become mandatory once all drivers > >> + * will be converted to use new sys-off API. > >> + */ > >> + pr_err("failed to register restart handler using unique priority\n"); > > > > I would use pr_info() here, because this is not a substantial error AFAICS. > > It's indeed not a substantial error so far, but it will become > substantial later on once only unique priorities will be allowed. The > pr_warn() could be a good compromise here, pr_info() is too mild, IMO. Well, I'm still unconvinced about requiring all of the users of this interface to use unique priorities. Arguably, there are some of them who don't really care about the ordering, so could there be an option for them to specify the lack of care by, say, passing 0 as the priority that would be regarded as a special case? IOW, if you pass 0, you'll be run along the others who've also passed 0, but if you pass anything different from 0, it must be unique. What do you think?
On 4/14/22 14:19, Rafael J. Wysocki wrote: > On Thu, Apr 14, 2022 at 12:24 AM Dmitry Osipenko > <dmitry.osipenko@collabora.com> wrote: >> >> On 4/13/22 21:48, Rafael J. Wysocki wrote: >>> On Tue, Apr 12, 2022 at 1:39 AM Dmitry Osipenko >>> <dmitry.osipenko@collabora.com> wrote: >>>> >>>> Add sanity check which ensures that there are no two restart handlers >>>> registered using the same priority. This requirement will become mandatory >>>> once all drivers will be converted to the new API and such errors will be >>>> fixed. >>>> >>>> Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com> >>> >>> The first two patches in the series are fine with me and there's only >>> one minor nit regarding this one (below). >>> >>>> --- >>>> kernel/reboot.c | 15 +++++++++++++++ >>>> 1 file changed, 15 insertions(+) >>>> >>>> diff --git a/kernel/reboot.c b/kernel/reboot.c >>>> index ed4e6dfb7d44..acdae4e95061 100644 >>>> --- a/kernel/reboot.c >>>> +++ b/kernel/reboot.c >>>> @@ -182,6 +182,21 @@ static ATOMIC_NOTIFIER_HEAD(restart_handler_list); >>>> */ >>>> int register_restart_handler(struct notifier_block *nb) >>>> { >>>> + int ret; >>>> + >>>> + ret = atomic_notifier_chain_register_unique_prio(&restart_handler_list, nb); >>>> + if (ret != -EBUSY) >>>> + return ret; >>>> + >>>> + /* >>>> + * Handler must have unique priority. Otherwise call order is >>>> + * determined by registration order, which is unreliable. >>>> + * >>>> + * This requirement will become mandatory once all drivers >>>> + * will be converted to use new sys-off API. >>>> + */ >>>> + pr_err("failed to register restart handler using unique priority\n"); >>> >>> I would use pr_info() here, because this is not a substantial error AFAICS. >> >> It's indeed not a substantial error so far, but it will become >> substantial later on once only unique priorities will be allowed. The >> pr_warn() could be a good compromise here, pr_info() is too mild, IMO. > > Well, I'm still unconvinced about requiring all of the users of this > interface to use unique priorities. > > Arguably, there are some of them who don't really care about the > ordering, so could there be an option for them to specify the lack of > care by, say, passing 0 as the priority that would be regarded as a > special case? > > IOW, if you pass 0, you'll be run along the others who've also passed > 0, but if you pass anything different from 0, it must be unique. What > do you think? There are indeed cases where ordering is unimportant. Like a case of PMIC and watchdog restart handlers for example, both handlers will produce equal effect from a user's perspective. Perhaps indeed it's more practical to have at least one shared level. In this patchset the level 0 is specified as an alias to the default level 128. If one user registers handler using unique level 128 and the other user uses non-unique level 0, then we have ambiguity. One potential option is to make the whole default level 128 non-unique. This will allow users to not care about the uniqueness by default like they always did it previously, but it will hide potential problems for users who actually need unique level and don't know about it yet due to a lucky registration ordering that they have today. Are you okay with this option?
On Mon, Apr 18, 2022 at 3:29 AM Dmitry Osipenko <dmitry.osipenko@collabora.com> wrote: > > On 4/14/22 14:19, Rafael J. Wysocki wrote: > > On Thu, Apr 14, 2022 at 12:24 AM Dmitry Osipenko > > <dmitry.osipenko@collabora.com> wrote: > >> > >> On 4/13/22 21:48, Rafael J. Wysocki wrote: > >>> On Tue, Apr 12, 2022 at 1:39 AM Dmitry Osipenko > >>> <dmitry.osipenko@collabora.com> wrote: > >>>> > >>>> Add sanity check which ensures that there are no two restart handlers > >>>> registered using the same priority. This requirement will become mandatory > >>>> once all drivers will be converted to the new API and such errors will be > >>>> fixed. > >>>> > >>>> Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com> > >>> > >>> The first two patches in the series are fine with me and there's only > >>> one minor nit regarding this one (below). > >>> > >>>> --- > >>>> kernel/reboot.c | 15 +++++++++++++++ > >>>> 1 file changed, 15 insertions(+) > >>>> > >>>> diff --git a/kernel/reboot.c b/kernel/reboot.c > >>>> index ed4e6dfb7d44..acdae4e95061 100644 > >>>> --- a/kernel/reboot.c > >>>> +++ b/kernel/reboot.c > >>>> @@ -182,6 +182,21 @@ static ATOMIC_NOTIFIER_HEAD(restart_handler_list); > >>>> */ > >>>> int register_restart_handler(struct notifier_block *nb) > >>>> { > >>>> + int ret; > >>>> + > >>>> + ret = atomic_notifier_chain_register_unique_prio(&restart_handler_list, nb); > >>>> + if (ret != -EBUSY) > >>>> + return ret; > >>>> + > >>>> + /* > >>>> + * Handler must have unique priority. Otherwise call order is > >>>> + * determined by registration order, which is unreliable. > >>>> + * > >>>> + * This requirement will become mandatory once all drivers > >>>> + * will be converted to use new sys-off API. > >>>> + */ > >>>> + pr_err("failed to register restart handler using unique priority\n"); > >>> > >>> I would use pr_info() here, because this is not a substantial error AFAICS. > >> > >> It's indeed not a substantial error so far, but it will become > >> substantial later on once only unique priorities will be allowed. The > >> pr_warn() could be a good compromise here, pr_info() is too mild, IMO. > > > > Well, I'm still unconvinced about requiring all of the users of this > > interface to use unique priorities. > > > > Arguably, there are some of them who don't really care about the > > ordering, so could there be an option for them to specify the lack of > > care by, say, passing 0 as the priority that would be regarded as a > > special case? > > > > IOW, if you pass 0, you'll be run along the others who've also passed > > 0, but if you pass anything different from 0, it must be unique. What > > do you think? > > There are indeed cases where ordering is unimportant. Like a case of > PMIC and watchdog restart handlers for example, both handlers will > produce equal effect from a user's perspective. Perhaps indeed it's more > practical to have at least one shared level. > > In this patchset the level 0 is specified as an alias to the default > level 128. If one user registers handler using unique level 128 and the > other user uses non-unique level 0, then we have ambiguity. > > One potential option is to make the whole default level 128 non-unique. > This will allow users to not care about the uniqueness by default like > they always did it previously, but it will hide potential problems for > users who actually need unique level and don't know about it yet due to > a lucky registration ordering that they have today. Are you okay with > this option? Yes, I am.
diff --git a/kernel/reboot.c b/kernel/reboot.c index ed4e6dfb7d44..acdae4e95061 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -182,6 +182,21 @@ static ATOMIC_NOTIFIER_HEAD(restart_handler_list); */ int register_restart_handler(struct notifier_block *nb) { + int ret; + + ret = atomic_notifier_chain_register_unique_prio(&restart_handler_list, nb); + if (ret != -EBUSY) + return ret; + + /* + * Handler must have unique priority. Otherwise call order is + * determined by registration order, which is unreliable. + * + * This requirement will become mandatory once all drivers + * will be converted to use new sys-off API. + */ + pr_err("failed to register restart handler using unique priority\n"); + return atomic_notifier_chain_register(&restart_handler_list, nb); } EXPORT_SYMBOL(register_restart_handler);
Add sanity check which ensures that there are no two restart handlers registered using the same priority. This requirement will become mandatory once all drivers will be converted to the new API and such errors will be fixed. Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com> --- kernel/reboot.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+)