Message ID | 1683092380-29551-1-git-send-email-quic_rohiagar@quicinc.com |
---|---|
Headers | show |
Series | Add pinctrl support for SDX75 | expand |
On Wed, May 3, 2023 at 8:39 AM Rohit Agarwal <quic_rohiagar@quicinc.com> wrote: > > Update the msm_function and msm_pingroup structure to reuse the generic structures > pinfunction and pingroup structures. Also refactor pinctrl drivers to adjust > the new macro and updated structure defined in pinctrl.h and pinctrl_msm.h > respectively. Thanks for this, my comments below. ... > #define FUNCTION(fname) \ > [APQ_MUX_##fname] = { \ > - .name = #fname, \ > - .groups = fname##_groups, \ > - .ngroups = ARRAY_SIZE(fname##_groups), \ > - } > + .func = PINCTRL_PINFUNCTION(#fname, \ > + fname##_groups, \ > + ARRAY_SIZE(fname##_groups)) \ > + } Does it really make sense to keep an additional wrapper data type that does not add any value? Can't we simply have #define FUNCTION(fname) [...fname] = PINCTRL_PINFUNCTION(...) ? ... > + .grp = PINCTRL_PINGROUP("gpio"#id, gpio##id##_pins, \ > + (unsigned int)ARRAY_SIZE(gpio##id##_pins)), \ Why do you need this casting? Same Q to all the rest of the similar cases. ... > +#include <linux/pinctrl/pinctrl.h> Keep it separate, and below the generic ones... > #include <linux/pm.h> > #include <linux/types.h> > ...like here (note also a blank line). ... > /** > * struct msm_function - a pinmux function > - * @name: Name of the pinmux function. > - * @groups: List of pingroups for this function. > - * @ngroups: Number of entries in @groups. > + * @func: Generic data of the pin function (name and groups of pins) > */ > struct msm_function { > - const char *name; > - const char * const *groups; > - unsigned ngroups; > + struct pinfunction func; > }; But why? Just kill the entire structure. ... > #define FUNCTION(fname) \ This definition appears in many files, instead you can make a generic to this drivers one and use it here #define QCOM_FUNCTION(_prefix_, _fname_) [_prefix_##_fname_] = PINCTRL_PINFUNCTION(...) #define FUNCTION(fname) QCOM_FUNCTION(msm_mux, fname) (this just a pseudocode, might not even be compilable) > [msm_mux_##fname] = { \ > - .name = #fname, \ > - .groups = fname##_groups, \ > - .ngroups = ARRAY_SIZE(fname##_groups), \ > + .func = PINCTRL_PINFUNCTION(#fname, \ > + fname##_groups, \ > + ARRAY_SIZE(fname##_groups)) \ > }
On 5/3/2023 7:23 PM, Andy Shevchenko wrote: > On Wed, May 3, 2023 at 2:14 PM Rohit Agarwal <quic_rohiagar@quicinc.com> wrote: >> On 5/3/2023 3:11 PM, Andy Shevchenko wrote: >>> On Wed, May 3, 2023 at 8:39 AM Rohit Agarwal <quic_rohiagar@quicinc.com> wrote: > ... > >>>> /** >>>> * struct msm_function - a pinmux function >>>> - * @name: Name of the pinmux function. >>>> - * @groups: List of pingroups for this function. >>>> - * @ngroups: Number of entries in @groups. >>>> + * @func: Generic data of the pin function (name and groups of pins) >>>> */ >>>> struct msm_function { >>>> - const char *name; >>>> - const char * const *groups; >>>> - unsigned ngroups; >>>> + struct pinfunction func; >>>> }; >>> But why? Just kill the entire structure. >> Got it. Can we have a typedef for pinfunction to msm_function in the msm >> header file? > But why? You can replace the type everywhere it needs to be replaced. > I can't expect many lines to change. > > Also consider splitting struct pingroup change out of this. We will > focus only on the struct pinfunction change and less code to review. Ok Will update all of this. Thanks, Rohit.