property: Use tidy for_each_named_* macros
Subsystems (3)
PATCH 1/1 property: Use tidy for_each_named_* macros
Implementing if-conditions inside for_each_x() macros requires some thinking to avoid side effects in the calling code. Resulting code may look somewhat awkward, and there are couple of different ways it is usually done.
Standardizing this to one way can help making it more obvious for a code reader and writer. The newly added for_each_if() is a way to achieve this.
Use for_each_if() to make these macros look like many others which should in the long run help reading the code.
---
The patch was crafted against the IIO/testing branch, and it depends on the 76125d7801e5 ("property: Add functions to iterate named child"). Hence I'd suggest taking this via IIO tree (if this gets accepted).
include/linux/property.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)
include/linux/property.h +4 -3
@@ -17,6 +17,7 @@#include <linux/fwnode.h> #include <linux/stddef.h> #include <linux/types.h> +#include <linux/util_macros.h> struct device ;
@@ -169,7 +170,7 @@ struct fwnode_handle *fwnode_get_next_available_child_node(#define fwnode_for_each_named_child_node (fwnode, child, name) \ fwnode_for_each_child_node(fwnode, child) \ - if (!fwnode_name_eq(child, name)) { } else + for_each_if(fwnode_name_eq(child, name))#define fwnode_for_each_available_child_node (fwnode, child) \ for (child = fwnode_get_next_available_child_node(fwnode, NULL); child;\
@@ -184,7 +185,7 @@ struct fwnode_handle *device_get_next_child_node(const struct device *dev,#define device_for_each_named_child_node (dev, child, name) \ device_for_each_child_node(dev, child) \ - if (!fwnode_name_eq(child, name)) { } else + for_each_if(fwnode_name_eq(child, name))#define device_for_each_child_node_scoped (dev, child) \ for (struct fwnode_handle *child __free(fwnode_handle) = \
@@ -193,7 +194,7 @@ struct fwnode_handle *device_get_next_child_node(const struct device *dev,#define device_for_each_named_child_node_scoped (dev, child, name) \ device_for_each_child_node_scoped(dev, child) \ - if (!fwnode_name_eq(child, name)) { } else + for_each_if(fwnode_name_eq(child, name))struct fwnode_handle *fwnode_get_named_child_node (const struct fwnode_handle *fwnode,const char *childname);
base-commit: 1c2409fe38d5c19015d69851d15ba543d1911932
Signature · 1 line
2.49.0
Quoted 5 lines · Matti Vaittinen
Implementing if-conditions inside
for_each_x()macros requires some thinking to avoid side effects in the calling code. Resulting code may look somewhat awkward, and there are couple of different ways it is usually done.
Quoted 7 lines
Standardizing this to one way can help making it more obvious for a code reader and writer. The newly added
for_each_if()is a way to achieve this.Use
for_each_if()to make these macros look like many others which should in the long run help reading the code.Signed-off-by Matti Vaittinen <[email protected]>
Signature · 1 line
Sakari Ailus
Quoted 10 lines · Matti Vaittinen
Implementing if-conditions inside
for_each_x()macros requires some thinking to avoid side effects in the calling code. Resulting code may look somewhat awkward, and there are couple of different ways it is usually done.Standardizing this to one way can help making it more obvious for a code reader and writer. The newly added
for_each_if()is a way to achieve this.Use
for_each_if()to make these macros look like many others which should in the long run help reading the code.
Thanks for cleaning these up!
Quoted 4 lines
---
The patch was crafted against the IIO/testing branch, and it depends on the76125d7801e5("property: Add functions to iterate named child"). Hence I'd suggest taking this via IIO tree (if this gets accepted).
I'm not sure why. The for_each_if() is part of v6.15-rc1.
Signature · 2 lines
With Best Regards, Andy Shevchenko
Andy Shevchenko
reviewerQuoted 13 lines · Andy Shevchenko
Quoted 10 lines · Matti Vaittinen
Implementing if-conditions inside
for_each_x()macros requires some thinking to avoid side effects in the calling code. Resulting code may look somewhat awkward, and there are couple of different ways it is usually done.Standardizing this to one way can help making it more obvious for a code reader and writer. The newly added
for_each_if()is a way to achieve this.Use
for_each_if()to make these macros look like many others which should in the long run help reading the code.Reviewed-by Andy Shevchenko <[email protected]>
Quoted 8 lines
Thanks for cleaning these up!
Quoted 4 lines
---
The patch was crafted against the IIO/testing branch, and it depends on the76125d7801e5("property: Add functions to iterate named child"). Hence I'd suggest taking this via IIO tree (if this gets accepted).I'm not sure why. The
for_each_if()is part of v6.15-rc1.
Ah, I see, you are trying to fix newly introduced stuff? I would rather suggest to make this straightforward against the current upstream and ask Jonathan to rebase the testing to fold the fixes into a new APIs.
Signature · 2 lines
With Best Regards, Andy Shevchenko
Quoted 21 lines · On Mon, 14 Apr 2025 09:47:44 +0300 Andy Shevchenko…
Quoted 20 lines · Andy Shevchenko
Quoted 10 lines · Matti Vaittinen
Implementing if-conditions inside
for_each_x()macros requires some thinking to avoid side effects in the calling code. Resulting code may look somewhat awkward, and there are couple of different ways it is usually done.Standardizing this to one way can help making it more obvious for a code reader and writer. The newly added
for_each_if()is a way to achieve this.Use
for_each_if()to make these macros look like many others which should in the long run help reading the code.Reviewed-by Andy Shevchenko <[email protected]>Thanks for cleaning these up!
Quoted 4 lines
---
The patch was crafted against the IIO/testing branch, and it depends on the76125d7801e5("property: Add functions to iterate named child"). Hence I'd suggest taking this via IIO tree (if this gets accepted).
Quoted 6 lines
Quoted 1 line
I'm not sure why. The
for_each_if()is part of v6.15-rc1.Ah, I see, you are trying to fix newly introduced stuff? I would rather suggest to make this straightforward against the current upstream and ask Jonathan to rebase the testing to fold the fixes into a new APIs.
Or we just do this next cycle maybe. Definitely not going to take anything through IIO that hasn't been on the iio list btw.
Jonathan
Quoted 24 lines · Jonathan Cameron
Quoted 21 lines · On Mon, 14 Apr 2025 09:47:44 +0300 Andy Shevchenko…
Quoted 20 lines · Andy Shevchenko
Quoted 10 lines · Matti Vaittinen
Implementing if-conditions inside
for_each_x()macros requires some thinking to avoid side effects in the calling code. Resulting code may look somewhat awkward, and there are couple of different ways it is usually done.Standardizing this to one way can help making it more obvious for a code reader and writer. The newly added
for_each_if()is a way to achieve this.Use
for_each_if()to make these macros look like many others which should in the long run help reading the code.Reviewed-by Andy Shevchenko <[email protected]>Thanks for cleaning these up!
Quoted 4 lines
---
The patch was crafted against the IIO/testing branch, and it depends on the76125d7801e5("property: Add functions to iterate named child"). Hence I'd suggest taking this via IIO tree (if this gets accepted).
Quoted 8 lines
Quoted 6 lines
Quoted 1 line
I'm not sure why. The
for_each_if()is part of v6.15-rc1.Ah, I see, you are trying to fix newly introduced stuff? I would rather suggest to make this straightforward against the current upstream and ask Jonathan to rebase the testing to fold the fixes into a new APIs.
Or we just do this next cycle maybe.
I'm not against either of the approaches. I'm (mostly) staying away from the computer for this and the next week, so re-spinning this will in any case get delayed. In that regard, the next cycle won't be that far away.
Quoted 2 lines
Definitely not going to take anything
through IIO that hasn't been on the iio list btw.
Ah. Thanks for pointing this out Jonathan! I just used the get_maintainer.pl - and added You. I definitely should have added the IIO-list!
Yours,
-- Matti
Andy Shevchenko
reviewerQuoted 1 line · Matti Vaittinen
On 14/04/2025 22:14, Jonathan Cameron wrote:
...
Quoted 5 lines
Quoted 2 lines
Definitely not going to take anything
through IIO that hasn't been on the iio list btw.Ah. Thanks for pointing this out Jonathan! I just used the get_maintainer.pl
- and added You. I definitely should have added the IIO-list!
Also a side note, the Subject should start with "device property: ...".
Signature · 2 lines
With Best Regards, Andy Shevchenko