Re: [PATCH] clk, ti, LLVMLinux: Move __init outside of type definition

[Behan Webster]

On 09/26/14 17:55, Felipe Balbi wrote:
> On Fri, Sep 26, 2014 at 05:31:48PM -0700, Behan Webster wrote:
> > As written, the __init for ti_clk_get_div_table is in the middle of the return
> > type.
> >
> > The gcc documentation indicates that section attributes should be added to the
> > end of the function declaration:
> >
> >    extern void foobar (void) __attribute__ ((section ("bar")));
> >
> > However gcc seems to be very permissive with where attributes can be placed.
> > clang on the other hand isn't so permissive, and fails if you put the section
> > definition in the middle of the return type:
> >
> > drivers/clk/ti/divider.c:298:28: error: expected ';' after struct
> > static struct clk_div_table
> >                             ^
> >                             ;
> > drivers/clk/ti/divider.c:298:1: warning: 'static' ignored on this
> >        declaration [-Wmissing-declarations]
> > static struct clk_div_table
> > ^
> > drivers/clk/ti/divider.c:299:9: error: type specifier missing,
> >        defaults to 'int' [-Werror,-Wimplicit-int]
> > __init *ti_clk_get_div_table(struct device_node *node)
> > ~~~~~~  ^
> > drivers/clk/ti/divider.c:345:9: warning: incompatible pointer types
> >        returning 'struct clk_div_table *' from a function with result type 'int *' [-Wincompatible-pointer-types]
> >          return table;
> >                 ^~~~~
> > drivers/clk/ti/divider.c:419:9: warning: incompatible pointer types
> >        assigning to 'const struct clk_div_table *' from 'int *' [-Wincompatible-pointer-types]
> >          *table = ti_clk_get_div_table(node);
> >                 ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~
> > 3 warnings and 2 errors generated.
> >
> > By convention, most of the kernel code puts section attributes between the
> > return type and function name. In the case where the return type is a pointer,
> > it's important to place the '*' on left of the __init.
> >
> > This updated code works for both gcc and clang.
> >
> > Signed-off-by: Behan Webster <behanw@xxxxxxxxxxxxxxxxxx>
> > Reviewed-by: Mark Charlebois <charlebm@xxxxxxxxx>
> makes sense to me:
>
> Reviewed-by: Felipe Balbi <balbi@xxxxxx>
Thank you.

> I wonder if we should add this a Sparse or Coccinelle rule.
+1

I'm hoping it can be added to checkpatch as well.

Behan

--
Behan Webster
behanw@xxxxxxxxxxxxxxxxxx

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/