2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-19 18:53:52 +08:00

mmc: sdhci: Fix SDHCI_QUIRK_TIMEOUT_USES_SDCLK

Commit 373e6a (mmc: sdhci: R1B command handling + MMC_CAP_ERASE) moved the
handling of SDHCI_QUIRK_TIMEOUT_USES_SDCLK from sdhci_calc_timeout() to
sdhci_add_host(). This causes division by zero errors on at least the S3C
SDHCI controller as the quirk implementation needs host->clock set to work
but host->clock has not been set when sdhci_add_host() is called.

Fix this by backing out that portion of the change, the clock may vary at
runtime anyway. It does occur to me that we may want to move the quirk to
where we set the clock but this seems more invasive and I'm concerned
about undesirable side effects.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Cc: Andrei Warkentin <andreiw@motorola.com>
Signed-off-by: Chris Ball <cjb@laptop.org>
This commit is contained in:
Mark Brown 2011-04-19 18:44:17 +01:00 committed by Chris Ball
parent 24f5b53ba0
commit 4b01681c77

View File

@ -616,6 +616,9 @@ static u8 sdhci_calc_timeout(struct sdhci_host *host, struct mmc_command *cmd)
target_timeout = data->timeout_ns / 1000 +
data->timeout_clks / host->clock;
if (host->quirks & SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK)
host->timeout_clk = host->clock / 1000;
/*
* Figure out needed cycles.
* We do this in steps in order to fit inside a 32 bit int.
@ -626,6 +629,7 @@ static u8 sdhci_calc_timeout(struct sdhci_host *host, struct mmc_command *cmd)
* =>
* (1) / (2) > 2^6
*/
BUG_ON(!host->timeout_clk);
count = 0;
current_timeout = (1 << 13) * 1000 / host->timeout_clk;
while (current_timeout < target_timeout) {
@ -1901,9 +1905,6 @@ int sdhci_add_host(struct sdhci_host *host)
if (caps & SDHCI_TIMEOUT_CLK_UNIT)
host->timeout_clk *= 1000;
if (host->quirks & SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK)
host->timeout_clk = host->clock / 1000;
/*
* Set host parameters.
*/