pinctrl: use dev_info instead of pr_info in pinctrl_select_state_locked
PATCH 1/3 pinctrl: use dev_info instead of pr_info in pinctrl_select_state_locked
And remove superfluous brackets.
---
If it's not too late, it can be squashed with commit:3102a76cfbf9ac4ae0cf54c7452f7ba4292a4760
"pinctrl: disable and free setting in select_state in case of error"
drivers/pinctrl/core.c | 5 ++--- 1 files changed, 2 insertions(+), 3 deletions(-)
drivers/pinctrl/core.c +2 -3
@@ -912,9 +912,8 @@ static int pinctrl_select_state_locked(struct pinctrl *p,break ; } -if (ret <0 ) { +if (ret <0 ) goto unapply_new_state; - } } p->state = state;
@@ -922,7 +921,7 @@ static int pinctrl_select_state_locked(struct pinctrl *p,return 0 ; unapply_new_state: -pr_info ("Error applying setting, reverse things back\n" ); +dev_err (p->dev,"Error applying setting, reverse things back\n" );/* * If the loop stopped on the 1st entry, nothing has been enabled,
Signature · 1 line
1.7.2.5
PATCH 2/3 pinctrl: remove superfluous optimization in pinctrl_select_state_locked
As Stephen Warren suggested, checking first if the setting->node entry is the first in the list or not is superfluous, as it is checked again in the list_for_each_entry bellow.
So, remove it, the code will be simpler and lighter !
---
If can also be squashed whit commit:3102a76cfbf9ac4ae0cf54c7452f7ba4292a4760
"pinctrl: disable and free setting in select_state in case of error" (But there will be a conflict on "if (old_state)" vs "FIXME comment")
drivers/pinctrl/core.c | 10 +--------- 1 files changed, 1 insertions(+), 9 deletions(-)
drivers/pinctrl/core.c +1 -9
@@ -923,20 +923,12 @@ static int pinctrl_select_state_locked(struct pinctrl *p, unapply_new_state:dev_err (p->dev,"Error applying setting, reverse things back\n" ); -/* -* If the loop stopped on the 1st entry, nothing has been enabled, -* so jump directly to the 2nd phase -*/ -if (list_entry (&setting->node,typeof (*setting), node) == -list_first_entry (&state->settings,typeof (*setting), node)) - goto reapply_old_state; -list_for_each_entry (setting2, &state->settings, node) {if (&setting2->node == &setting->node)break ;pinctrl_free_setting (true, setting2); } -reapply_old_state: +if (old_state) {list_for_each_entry (setting, &old_state->settings, node) {bool found = false;
Signature · 1 line
1.7.2.5
Re: [PATCH 2/3] pinctrl: remove superfluous optimization in pinctrl_select_state_locked
Quoted 4 lines · Richard Genoud
As Stephen Warren suggested, checking first if the
setting->nodeentry is the first in the list or not is superfluous, as it is checked again in thelist_for_each_entrybellow.
So, remove it, the code will be simpler and lighter !
Re: [PATCH 2/3] pinctrl: remove superfluous optimization in pinctrl_select_state_locked
In reply to Richard GenoudQuoted 11 lines · Richard Genoud
As Stephen Warren suggested, checking first if the
setting->nodeentry is the first in the list or not is superfluous, as it is checked again in thelist_for_each_entrybellow.
So, remove it, the code will be simpler and lighter !Signed-off-by Richard Genoud <[email protected]>---
If can also be squashed whit commit:3102a76cfbf9ac4ae0cf54c7452f7ba4292a4760
"pinctrl: disable and free setting inselect_statein case of error" (But there will be a conflict on "if (old_state)" vs "FIXME comment")
Applied with Stephen's Reviewed tag.
Thanks,
Linus Walleij
PATCH 3/3 pinctrl: pinctrl_select_state: set the old_state back on error
In reply to Richard GenoudIn unapply_new_state, the old state is re-applied, but p->state is not set back as it should.
---
This one can be squshed with commit:50cf7c8ab324de348990bb028ad9ed10872d527a
pinctrl: re-enable old state in case of error in pinctrl_select_state If needed.
drivers/pinctrl/core.c | 2 ++ 1 files changed, 2 insertions(+), 0 deletions(-)
drivers/pinctrl/core.c +2 -0
@@ -947,6 +947,8 @@ unapply_new_state:pinmux_enable_setting (setting); } } + + p->state = old_state;return ret; }
Signature · 1 line
1.7.2.5
Re: [PATCH 3/3] pinctrl: pinctrl_select_state: set the old_state back on error
Quoted 2 lines · Richard Genoud
In
unapply_new_state, the old state is re-applied, butp->stateis not set back as it should.
Re: [PATCH 3/3] pinctrl: pinctrl_select_state: set the old_state back on error
In reply to Richard GenoudQuoted 9 lines · Richard Genoud
In
unapply_new_state, the old state is re-applied, butp->stateis not set back as it should.Signed-off-by Richard Genoud <[email protected]>---
This one can be squshed with commit:50cf7c8ab324de348990bb028ad9ed10872d527a
pinctrl: re-enable old state in case of error inpinctrl_select_stateIf needed.
Applied with Stepgen's Review-tag.
Thanks,
Linus Walleij
Quoted 1 line · Richard Genoud
And remove superfluous brackets.
(Seems like those unrelated changes might have benefited from being two separate patches, but not a big deal, especially if this actually gets squashed)
Quoted 7 lines · Richard Genoud
And remove superfluous brackets.
Signed-off-by Richard Genoud <[email protected]>---
If it's not too late, it can be squashed with commit:3102a76cfbf9ac4ae0cf54c7452f7ba4292a4760
"pinctrl: disable and free setting inselect_statein case of error"
Bah, applied as-is with Stephen's Review-tag.
Yours,
Linus Walleij