| Message ID | 20190506151656.47494e56@endymion |
|---|---|
| State | Awaiting Upstream |
| Headers | show |
| Series | [1/2] eeprom: ee1004: Move selected page detection to a separate function | expand |
On 5/6/19 4:16 PM, Jean Delvare wrote: > Some EE1004 implementations will not properly ack page selection > commands. They still set the page correctly, so there is no actual > error. Deal with this case gracefully by checking the currently > selected page after we receive a nack. If the page is set right then > we can continue. > > Signed-off-by: Jean Delvare <jdelvare@suse.de> > Tested-by: Jarkko Nikula <jarkko.nikula@linux.intel.com> > Cc: Arnd Bergmann <arnd@arndb.de> > Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> > --- > drivers/misc/eeprom/ee1004.c | 12 +++++++++++- > 1 file changed, 11 insertions(+), 1 deletion(-) > Does Dreamcat4 deserve reported and tested by tags here? I guess anonymous address is fine with those tags? (I re-tested these two patches on top of v5.1 and they make decode-dimms working on a machine with 2-4 * Crucial DD4 dimms)
Don't mind either way, please do as you see fit On Mon, May 6, 2019 at 3:04 PM Jarkko Nikula <jarkko.nikula@linux.intel.com> wrote: > > On 5/6/19 4:16 PM, Jean Delvare wrote: > > Some EE1004 implementations will not properly ack page selection > > commands. They still set the page correctly, so there is no actual > > error. Deal with this case gracefully by checking the currently > > selected page after we receive a nack. If the page is set right then > > we can continue. > > > > Signed-off-by: Jean Delvare <jdelvare@suse.de> > > Tested-by: Jarkko Nikula <jarkko.nikula@linux.intel.com> > > Cc: Arnd Bergmann <arnd@arndb.de> > > Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> > > --- > > drivers/misc/eeprom/ee1004.c | 12 +++++++++++- > > 1 file changed, 11 insertions(+), 1 deletion(-) > > > Does Dreamcat4 deserve reported and tested by tags here? I guess > anonymous address is fine with those tags? > > (I re-tested these two patches on top of v5.1 and they make decode-dimms > working on a machine with 2-4 * Crucial DD4 dimms) > > -- > Jarkko
On Mon, 6 May 2019 17:03:20 +0300, Jarkko Nikula wrote: > On 5/6/19 4:16 PM, Jean Delvare wrote: > > Some EE1004 implementations will not properly ack page selection > > commands. They still set the page correctly, so there is no actual > > error. Deal with this case gracefully by checking the currently > > selected page after we receive a nack. If the page is set right then > > we can continue. > > > > Signed-off-by: Jean Delvare <jdelvare@suse.de> > > Tested-by: Jarkko Nikula <jarkko.nikula@linux.intel.com> > > Cc: Arnd Bergmann <arnd@arndb.de> > > Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> > > --- > > drivers/misc/eeprom/ee1004.c | 12 +++++++++++- > > 1 file changed, 11 insertions(+), 1 deletion(-) > > Does Dreamcat4 deserve reported and tested by tags here? I guess > anonymous address is fine with those tags? My assumption is that someone who posts anonymously in the first place has no desire to be credited for anything or even mentioned anywhere. > (I re-tested these two patches on top of v5.1 and they make decode-dimms > working on a machine with 2-4 * Crucial DD4 dimms) Thank you very much.
--- linux-5.0.orig/drivers/misc/eeprom/ee1004.c 2019-05-06 11:57:14.333572368 +0200 +++ linux-5.0/drivers/misc/eeprom/ee1004.c 2019-05-06 15:11:06.009718220 +0200 @@ -1,7 +1,7 @@ /* * ee1004 - driver for DDR4 SPD EEPROMs * - * Copyright (C) 2017 Jean Delvare + * Copyright (C) 2017-2019 Jean Delvare * * Based on the at24 driver: * Copyright (C) 2005-2007 David Brownell @@ -124,6 +124,16 @@ static ssize_t ee1004_read(struct file * /* Data is ignored */ status = i2c_smbus_write_byte(ee1004_set_page[page], 0x00); + if (status == -ENXIO) { + /* + * Don't give up just yet. Some memory + * modules will select the page but not + * ack the command. Check which page is + * selected now. + */ + if (ee1004_get_current_page() == page) + status = 0; + } if (status < 0) { dev_err(dev, "Failed to select page %d (%d)\n", page, status);