| Message ID | 20220321115059.21803-2-wsa+renesas@sang-engineering.com |
|---|---|
| State | New |
| Headers | show |
| Series | mmc: improve API to make clear {h|s}w_reset is for cards | expand |
Hi Ulf, > > To make it unambiguous that mmc_hw_reset() is for cards and not for > > controllers, we a) add 'card' to the function name and b) make the > > function argument mmc_card instead of mmc_host. A fallback is provided > > until all users are converted. > > In my opinion, I think b) is sufficient and would be a nice improvement. If you say so... but I do wonder why we can't be super clear with the function name alone without the function argument as an additional source of information? Kernel hacking is complicated enough. > In this regard, I suggest we make one big cross-subsystem patch (the > smallest change as possible) then I can pick it up and send it for the > v5.18-rc2. Ok, I can prepare this. > > -static void mmc_hw_reset_for_init(struct mmc_host *host) > > +/* we can't use mmc_card as a parameter, it is not populated yet */ > > Please drop this. The function is internal/static and at least to me, > rather self-explanatory. All other ?w_reset() functions have a card as a parameter. For people trying to get into the MMC core, this comment might be helpful to understand the anomaly? I know that you as the maintainer do know this by heart, this comment is meant for people learning the stuff. All the best, Wolfram
On Wed, 6 Apr 2022 at 09:58, Wolfram Sang <wsa+renesas@sang-engineering.com> wrote: > > Hi Ulf, > > > > To make it unambiguous that mmc_hw_reset() is for cards and not for > > > controllers, we a) add 'card' to the function name and b) make the > > > function argument mmc_card instead of mmc_host. A fallback is provided > > > until all users are converted. > > > > In my opinion, I think b) is sufficient and would be a nice improvement. > > If you say so... but I do wonder why we can't be super clear with the > function name alone without the function argument as an additional > source of information? Kernel hacking is complicated enough. > > > In this regard, I suggest we make one big cross-subsystem patch (the > > smallest change as possible) then I can pick it up and send it for the > > v5.18-rc2. > > Ok, I can prepare this. Great! > > > > -static void mmc_hw_reset_for_init(struct mmc_host *host) > > > +/* we can't use mmc_card as a parameter, it is not populated yet */ > > > > Please drop this. The function is internal/static and at least to me, > > rather self-explanatory. > > All other ?w_reset() functions have a card as a parameter. For people > trying to get into the MMC core, this comment might be helpful to > understand the anomaly? I know that you as the maintainer do know this > by heart, this comment is meant for people learning the stuff. I understand your point, however I don't think it makes much sense to try to clarify the names on mmc_hw|sw_reset() alone. There are simply lots of other functions that then would need to be changed too. Otherwise we would just end up with having even more in-consistency in function namings. To me, that's even worse. > > All the best, > > Wolfram Kind regards Uffe
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 4e67c1403cc9..74674a4650b0 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -993,7 +993,7 @@ static int mmc_blk_reset(struct mmc_blk_data *md, struct mmc_host *host, return -EEXIST; md->reset_done |= type; - err = mmc_hw_reset(host); + err = mmc_card_hw_reset(host->card); /* Ensure we switch back to the correct partition */ if (err) { struct mmc_blk_data *main_md = diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 368f10405e13..71e75196bc53 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -1984,7 +1984,8 @@ int mmc_set_blocklen(struct mmc_card *card, unsigned int blocklen) } EXPORT_SYMBOL(mmc_set_blocklen); -static void mmc_hw_reset_for_init(struct mmc_host *host) +/* we can't use mmc_card as a parameter, it is not populated yet */ +static void mmc_card_hw_reset_for_init(struct mmc_host *host) { mmc_pwrseq_reset(host); @@ -1994,8 +1995,8 @@ static void mmc_hw_reset_for_init(struct mmc_host *host) } /** - * mmc_hw_reset - reset the card in hardware - * @host: MMC host to which the card is attached + * mmc_card_hw_reset - reset the card in hardware + * @card: card to be reset * * Hard reset the card. This function is only for upper layers, like the * block layer or card drivers. You cannot use it in host drivers (struct @@ -2003,8 +2004,9 @@ static void mmc_hw_reset_for_init(struct mmc_host *host) * * Return: 0 on success, -errno on failure */ -int mmc_hw_reset(struct mmc_host *host) +int mmc_card_hw_reset(struct mmc_card *card) { + struct mmc_host *host = card->host; int ret; ret = host->bus_ops->hw_reset(host); @@ -2014,6 +2016,12 @@ int mmc_hw_reset(struct mmc_host *host) return ret; } +EXPORT_SYMBOL(mmc_card_hw_reset); + +int mmc_hw_reset(struct mmc_host *host) +{ + return mmc_card_hw_reset(host->card); +} EXPORT_SYMBOL(mmc_hw_reset); int mmc_sw_reset(struct mmc_host *host) @@ -2045,7 +2053,7 @@ static int mmc_rescan_try_freq(struct mmc_host *host, unsigned freq) * Some eMMCs (with VCCQ always on) may not be reset after power up, so * do a hardware reset if possible. */ - mmc_hw_reset_for_init(host); + mmc_card_hw_reset_for_init(host); /* * sdio_reset sends CMD52 to reset card. Since we do not know diff --git a/drivers/mmc/core/mmc_test.c b/drivers/mmc/core/mmc_test.c index e6a2fd2c6d5c..bfcae8f79cbd 100644 --- a/drivers/mmc/core/mmc_test.c +++ b/drivers/mmc/core/mmc_test.c @@ -2325,10 +2325,9 @@ static int mmc_test_profile_sglen_r_nonblock_perf(struct mmc_test_card *test) static int mmc_test_reset(struct mmc_test_card *test) { struct mmc_card *card = test->card; - struct mmc_host *host = card->host; int err; - err = mmc_hw_reset(host); + err = mmc_card_hw_reset(card); if (!err) { /* * Reset will re-enable the card's command queue, but tests diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 71101d1ec825..25a7cf69d919 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -176,6 +176,7 @@ int mmc_wait_for_cmd(struct mmc_host *host, struct mmc_command *cmd, int retries); int mmc_hw_reset(struct mmc_host *host); +int mmc_card_hw_reset(struct mmc_card *card); int mmc_sw_reset(struct mmc_host *host); void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card);
To make it unambiguous that mmc_hw_reset() is for cards and not for controllers, we a) add 'card' to the function name and b) make the function argument mmc_card instead of mmc_host. A fallback is provided until all users are converted. Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com> --- drivers/mmc/core/block.c | 2 +- drivers/mmc/core/core.c | 18 +++++++++++++----- drivers/mmc/core/mmc_test.c | 3 +-- include/linux/mmc/core.h | 1 + 4 files changed, 16 insertions(+), 8 deletions(-)