From mboxrd@z Thu Jan 1 00:00:00 1970 From: Wolfram Sang Subject: Re: [PATCH 2/2] i2c-mux-gpio: use reg value for i2c_add_mux_adapter Date: Wed, 30 Oct 2013 17:30:51 +0100 Message-ID: <20131030163050.GI3663@katana> References: <5257CE75.5000607@nsn.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="oxV4ZoPwBLqAyY+a" Return-path: Content-Disposition: inline In-Reply-To: <5257CE75.5000607-OYasijW0DpE@public.gmane.org> Sender: linux-i2c-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Ionut Nicu Cc: Peter Korsgaard , Alexander Sverdlin , linux-i2c-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-Id: linux-i2c@vger.kernel.org --oxV4ZoPwBLqAyY+a Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Fri, Oct 11, 2013 at 12:09:57PM +0200, Ionut Nicu wrote: > The i2c-mux driver requires that the chan_id parameter > passed to the i2c_add_mux_adapter() function is equal > to the reg value for that adapter: >=20 > for_each_child_of_node(mux_dev->of_node, child) { > ret =3D of_property_read_u32(child, "reg", ®); > if (ret) > continue; > if (chan_id =3D=3D reg) { > priv->adap.dev.of_node =3D child; > break; > } > } >=20 > The i2c-mux-gpio driver uses an internal logical index > for chan_id when calling i2c_add_mux_adapter() instead > of using the reg value. >=20 > Because of this, there will problems in selecting the > right adapter when the i2c-mux-gpio's index into > mux->data.values doesn't match the reg value. >=20 > An example of such a case: >=20 > mux->data.values =3D { 1, 0 } >=20 > For chan_id =3D 0, i2c-mux will bind the adapter to the > of_node with reg =3D <0>, but when it will call the > select() callback with chan_id set to 0, the i2c-mux-gpio > will use it as an index into mux->data.values and it will > actually select the bus with reg =3D <1>. >=20 > Signed-off-by: Ionut Nicu On Fri, Oct 11, 2013 at 02:17:10PM +0200, Ionut Nicu wrote: > Some gpio chips may have get/set operations that > can sleep. gpio_set_value() only works for chips > which do not sleep, for the others we will get a > kernel warning. Using gpio_set_value_cansleep() > will work for both chips that do sleep and those > who don't. >=20 > Signed-off-by: Ionut Nicu Applied to for-next, thanks! Added to stable, too. Also, please write the changes since last time. This really speeds up reviewing! --oxV4ZoPwBLqAyY+a Content-Type: application/pgp-signature; name="signature.asc" Content-Description: Digital signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.14 (GNU/Linux) iQIcBAEBAgAGBQJScTQ6AAoJEBQN5MwUoCm2OY4P/iZapF0vXWyREsVscBsWcghP ilBJJ43af0QkUbrQWzlIhhfjfis3T1uv4YbGFdBTtVG/0cXt8G3Ncaxy/vmJbl7d 4gv33dT5uPSvvTE+LlzFiVwHRi3Epg6n7Guu+TYXUDgJ9MvYv55r4VYdzlP3Ql0E +T2fQ1/67AaSMzlQvyEGaHxtqpSjG8WAh87f0yf8YGXPWuiJIMKjYClI+Y1m98WJ mFP0mpdmcPoFy9pIwEhIelem98eCK04SfG9802QO22B+w8dAWkIR7gdE33PVP8fW 77zFyI0XgzhEVG+3PD8ysI8GmIoxt1TyNIFEWka1XcI1nNIypPgIb/Pj0JbF2t6q v7HBRs6Q9rGH/kHjmoL+uxafbKa0AlOYUjUvPoIOAWQ3UsPqsOLX4At9pbVR8Wrr UUhrlx83Gei3LtGP0lulgG/EJpbCU5MiNoUcecDrQ8KQD+GbIeN7GFHvC2v3j5GP ORwlLJrcB8SjtLvrWOW+Qak6uQ3JWw6Yf0tPi2DEI2dalTBSaUgz3SdoLyIxouWH tWAgmbdTxLPCX4t8x20qpDerluEjxl9sy7PGDKMARsL4j0ogdxcjDAgN9YedJ98S iE8ll4xWE19ciXYHBfgiGYdboKbpKgSmEddK5INrqA9auNM7vn6RZoQNZvyUnkfU yreDb/4htBpbfOyxescD =M5/8 -----END PGP SIGNATURE----- --oxV4ZoPwBLqAyY+a--