| Message ID | 9235101.CDJkKcVGEf@kreacher (mailing list archive) |
|---|---|
| State | Not Applicable |
| Delegated to: | Johannes Berg |
| Headers | show |
| Series | thermal: Writable trip points handling rework | expand |
On 12/02/2024 19:40, Rafael J. Wysocki wrote: > From: Rafael J. Wysocki <rafael.j.wysocki@intel.com> > > It is now possible to flag trip points with THERMAL_TRIP_FLAG_RW_TEMP > to allow their temperature to be set from user space via sysfs instead > of using a nonzero writable trips mask during thermal zone registration, > so make the OF thermal code do that. > > No intentional functional impact. > > Note that this change is requisite for dropping the mask argument from > thermal_zone_device_register_with_trips() going forward. > > Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> > --- > > v1 -> v2: Rename trip flag (Stanislaw). > > --- > drivers/thermal/thermal_of.c | 8 ++++---- > 1 file changed, 4 insertions(+), 4 deletions(-) > > Index: linux-pm/drivers/thermal/thermal_of.c > =================================================================== > --- linux-pm.orig/drivers/thermal/thermal_of.c > +++ linux-pm/drivers/thermal/thermal_of.c > @@ -117,6 +117,8 @@ static int thermal_of_populate_trip(stru > return ret; > } > > + trip->flags = THERMAL_TRIP_FLAG_RW_TEMP; > + > return 0; > } Even if you are not at the origin of this default behavior. I'm wondering if we should be more protective against changes from userspace when the firmware is telling us to protect the silicon at a specific temperature. What do you think if we set the THERMAL_TRIP_FLAG_RW_TEMP only if the trip point is not bound to a cooling device? So trip points without associated cooling device can be writable but others can be considered as managed by the kernel and no modifiable. (This comment does not put in question this patch BTW) > @@ -477,7 +479,7 @@ static struct thermal_zone_device *therm > struct device_node *np; > const char *action; > int delay, pdelay; > - int ntrips, mask; > + int ntrips; > int ret; > > of_ops = kmemdup(ops, sizeof(*ops), GFP_KERNEL); > @@ -510,15 +512,13 @@ static struct thermal_zone_device *therm > of_ops->bind = thermal_of_bind; > of_ops->unbind = thermal_of_unbind; > > - mask = GENMASK_ULL((ntrips) - 1, 0); > - > ret = of_property_read_string(np, "critical-action", &action); > if (!ret) > if (!of_ops->critical && !strcasecmp(action, "reboot")) > of_ops->critical = thermal_zone_device_critical_reboot; > > tz = thermal_zone_device_register_with_trips(np->name, trips, ntrips, > - mask, data, of_ops, &tzp, > + 0, data, of_ops, &tzp, > pdelay, delay); > if (IS_ERR(tz)) { > ret = PTR_ERR(tz); > > >
On Thu, Feb 22, 2024 at 2:48 PM Daniel Lezcano <daniel.lezcano@linaro.org> wrote: > > On 12/02/2024 19:40, Rafael J. Wysocki wrote: > > From: Rafael J. Wysocki <rafael.j.wysocki@intel.com> > > > > It is now possible to flag trip points with THERMAL_TRIP_FLAG_RW_TEMP > > to allow their temperature to be set from user space via sysfs instead > > of using a nonzero writable trips mask during thermal zone registration, > > so make the OF thermal code do that. > > > > No intentional functional impact. > > > > Note that this change is requisite for dropping the mask argument from > > thermal_zone_device_register_with_trips() going forward. > > > > Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> > > --- > > > > v1 -> v2: Rename trip flag (Stanislaw). > > > > --- > > drivers/thermal/thermal_of.c | 8 ++++---- > > 1 file changed, 4 insertions(+), 4 deletions(-) > > > > Index: linux-pm/drivers/thermal/thermal_of.c > > =================================================================== > > --- linux-pm.orig/drivers/thermal/thermal_of.c > > +++ linux-pm/drivers/thermal/thermal_of.c > > @@ -117,6 +117,8 @@ static int thermal_of_populate_trip(stru > > return ret; > > } > > > > + trip->flags = THERMAL_TRIP_FLAG_RW_TEMP; > > + > > return 0; > > } > > Even if you are not at the origin of this default behavior. I'm > wondering if we should be more protective against changes from userspace > when the firmware is telling us to protect the silicon at a specific > temperature. > > What do you think if we set the THERMAL_TRIP_FLAG_RW_TEMP only if the > trip point is not bound to a cooling device? > > So trip points without associated cooling device can be writable but > others can be considered as managed by the kernel and no modifiable. This sounds reasonable to me. This is mostly relevant to thermal_of anyway, because the other drivers asking for writable trip temperature seem to want it regardless. > (This comment does not put in question this patch BTW) OK
On 12/02/2024 19:40, Rafael J. Wysocki wrote: > From: Rafael J. Wysocki <rafael.j.wysocki@intel.com> > > It is now possible to flag trip points with THERMAL_TRIP_FLAG_RW_TEMP > to allow their temperature to be set from user space via sysfs instead > of using a nonzero writable trips mask during thermal zone registration, > so make the OF thermal code do that. > > No intentional functional impact. > > Note that this change is requisite for dropping the mask argument from > thermal_zone_device_register_with_trips() going forward. > > Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Reviewed-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Index: linux-pm/drivers/thermal/thermal_of.c =================================================================== --- linux-pm.orig/drivers/thermal/thermal_of.c +++ linux-pm/drivers/thermal/thermal_of.c @@ -117,6 +117,8 @@ static int thermal_of_populate_trip(stru return ret; } + trip->flags = THERMAL_TRIP_FLAG_RW_TEMP; + return 0; } @@ -477,7 +479,7 @@ static struct thermal_zone_device *therm struct device_node *np; const char *action; int delay, pdelay; - int ntrips, mask; + int ntrips; int ret; of_ops = kmemdup(ops, sizeof(*ops), GFP_KERNEL); @@ -510,15 +512,13 @@ static struct thermal_zone_device *therm of_ops->bind = thermal_of_bind; of_ops->unbind = thermal_of_unbind; - mask = GENMASK_ULL((ntrips) - 1, 0); - ret = of_property_read_string(np, "critical-action", &action); if (!ret) if (!of_ops->critical && !strcasecmp(action, "reboot")) of_ops->critical = thermal_zone_device_critical_reboot; tz = thermal_zone_device_register_with_trips(np->name, trips, ntrips, - mask, data, of_ops, &tzp, + 0, data, of_ops, &tzp, pdelay, delay); if (IS_ERR(tz)) { ret = PTR_ERR(tz);