[0/2] Deduplicate bin_attribute simple read() callbacks

For my upcoming PCI device authentication v2 patches, I have the need
to expose a simple buffer in virtual memory as a bin_attribute.

It turns out we've duplicated the ->read() callback for such simple
buffers a fair number of times across the tree.

So instead of reinventing the wheel, I decided to introduce a common
helper and eliminate all duplications I could find.

I'm open to a bikeshedding discussion on the sysfs_bin_attr_simple_read()
name. ;)

Lukas Wunner (2):
  sysfs: Add sysfs_bin_attr_simple_read() helper
  treewide: Use sysfs_bin_attr_simple_read() helper

 arch/powerpc/platforms/powernv/opal.c              | 10 +-------
 drivers/acpi/bgrt.c                                |  9 +-------
 drivers/firmware/dmi_scan.c                        | 12 ++--------
 drivers/firmware/efi/rci2-table.c                  | 10 +-------
 drivers/gpu/drm/i915/gvt/firmware.c                | 26 +++++----------------
 .../intel/int340x_thermal/int3400_thermal.c        |  9 +-------
 fs/sysfs/file.c                                    | 27 ++++++++++++++++++++++
 include/linux/sysfs.h                              | 15 ++++++++++++
 init/initramfs.c                                   | 10 +-------
 kernel/module/sysfs.c                              | 13 +----------
 10 files changed, 56 insertions(+), 85 deletions(-)

On Sat, 6 Apr 2024 at 15:52, Lukas Wunner <lukas@wunner.de> wrote:
>
> For my upcoming PCI device authentication v2 patches, I have the need
> to expose a simple buffer in virtual memory as a bin_attribute.
>
> It turns out we've duplicated the ->read() callback for such simple
> buffers a fair number of times across the tree.
>
> So instead of reinventing the wheel, I decided to introduce a common
> helper and eliminate all duplications I could find.
>
> I'm open to a bikeshedding discussion on the sysfs_bin_attr_simple_read()
> name. ;)
>
> Lukas Wunner (2):
>   sysfs: Add sysfs_bin_attr_simple_read() helper
>   treewide: Use sysfs_bin_attr_simple_read() helper
>

Acked-by: Ard Biesheuvel <ardb@kernel.org>

>  arch/powerpc/platforms/powernv/opal.c              | 10 +-------
>  drivers/acpi/bgrt.c                                |  9 +-------
>  drivers/firmware/dmi_scan.c                        | 12 ++--------
>  drivers/firmware/efi/rci2-table.c                  | 10 +-------
>  drivers/gpu/drm/i915/gvt/firmware.c                | 26 +++++----------------
>  .../intel/int340x_thermal/int3400_thermal.c        |  9 +-------
>  fs/sysfs/file.c                                    | 27 ++++++++++++++++++++++
>  include/linux/sysfs.h                              | 15 ++++++++++++
>  init/initramfs.c                                   | 10 +-------
>  kernel/module/sysfs.c                              | 13 +----------
>  10 files changed, 56 insertions(+), 85 deletions(-)
>
> --
> 2.43.0
>

On Sat, Apr 06, 2024 at 03:52:00PM +0200, Lukas Wunner wrote:
> For my upcoming PCI device authentication v2 patches, I have the need
> to expose a simple buffer in virtual memory as a bin_attribute.
> 
> It turns out we've duplicated the ->read() callback for such simple
> buffers a fair number of times across the tree.
> 
> So instead of reinventing the wheel, I decided to introduce a common
> helper and eliminate all duplications I could find.
> 
> I'm open to a bikeshedding discussion on the sysfs_bin_attr_simple_read()
> name. ;)

Seems like no one objects, should I just take this through my
driver-core tree for 6.10?

thanks,

greg k-h

On Thu, Apr 11, 2024 at 03:07:46PM +0200, Greg Kroah-Hartman wrote:
> On Sat, Apr 06, 2024 at 03:52:00PM +0200, Lukas Wunner wrote:
> > For my upcoming PCI device authentication v2 patches, I have the need
> > to expose a simple buffer in virtual memory as a bin_attribute.
> > 
> > It turns out we've duplicated the ->read() callback for such simple
> > buffers a fair number of times across the tree.
> > 
> > So instead of reinventing the wheel, I decided to introduce a common
> > helper and eliminate all duplications I could find.
> > 
> > I'm open to a bikeshedding discussion on the sysfs_bin_attr_simple_read()
> > name. ;)
> 
> Seems like no one objects, should I just take this through my
> driver-core tree for 6.10?

That would be awesome, thank you!

Lukas