tmio_mmc_pio: prevent endless loop in tmio_mmc_set_clock()
Subsystems (2)
PATCH v2 1/1 tmio_mmc_pio: prevent endless loop in tmio_mmc_set_clock()
I spent a couple of days with the driver just hanging due to me forgetting to specify the external crystal frequency, so that clk_get_rate() returned 0 and thus the loop in tmio_mmc_set_clock() never ended. I don't think that's an acceptable behavior, so I suggest that the minimum frequency is checked for 0 in tmio_mmc_host_probe().
---
The patch is against Ulf Hansson's 'mmc.git' repo's 'fixes' branch.
Changes in version 2:
- fixed grammar in the changelog.
drivers/mmc/host/tmio_mmc_pio.c | 9 +++++++++ 1 file changed, 9 insertions(+)
Index: mmc/drivers/mmc/host/tmio_mmc_pio.c =================================--- mmc.orig/drivers/mmc/host/tmio_mmc_pio.c +++ mmc/drivers/mmc/host/tmio_mmc_pio.c
@@ -1044,6 +1044,15 @@ int tmio_mmc_host_probe(struct tmio_mmc_
}
/*
+ * Check the sanity of mmc->f_min to prevent tmio_mmc_set_clock() from
+ * looping forever...
+ */
+ if (mmc->f_min = 0) {
+ ret = -EINVAL;
+ goto pm_disable;
+ }
+
+ /*
* There are 4 different scenarios for the card detection:
* 1) an external gpio irq handles the cd (best for power savings)
* 2) internal sdhi irq handles the cd
Quoted 10 lines · Sergei Shtylyov
I spent a couple of days with the driver just hanging due to me forgetting to specify the external crystal frequency, so that
clk_get_rate()returned 0 and thus the loop intmio_mmc_set_clock()never ended. I don't think that's an acceptable behavior, so I suggest that the minimum frequency is checked for 0 intmio_mmc_host_probe().Signed-off-by Sergei Shtylyov <[email protected]>---
The patch is against Ulf Hansson's 'mmc.git' repo's 'fixes' branch.
Hi Sergei,
Could you please base it towards "next" instead, it doesn't apply. If you think this is important to go stable, I suggest you to add a stable tag for it.
Kind regards
Uffe
Quoted 28 lines
Changes in version 2:
- fixed grammar in the changelog.drivers/mmc/host/tmio_mmc_pio.c | 9 +++++++++ 1 file changed, 9 insertions(+)Index:
mmc/drivers/mmc/host/tmio_mmc_pio.c
===================================================================drivers/mmc/host/tmio_mmc_pio.c +9
-0@@ -1044,6 +1044,15 @@ int tmio_mmc_host_probe(struct tmio_mmc_ }/* +* Check the sanity of mmc->f_min to prevent tmio_mmc_set_clock() from +* looping forever... +*/ +if (mmc->f_min ==0 ) { + ret = -EINVAL ; + goto pm_disable; + } + +/* * There are 4 different scenarios for the card detection: * 1) an external gpio irq handles the cd (best for power savings) * 2) internal sdhi irq handles the cd
Hello.
Sorry for delay: I'm on vacations and WiFi didn't work well here...
Quoted 8 lines · Ulf Hansson
Quoted 7 lines
I spent a couple of days with the driver just hanging due to me forgetting to specify the external crystal frequency, so that
clk_get_rate()returned 0 and thus the loop intmio_mmc_set_clock()never ended. I don't think that's an acceptable behavior, so I suggest that the minimum frequency is checked for 0 intmio_mmc_host_probe().Signed-off-by Sergei Shtylyov <[email protected]>
Quoted 8 lines
Quoted 2 lines
---
The patch is against Ulf Hansson's 'mmc.git' repo's 'fixes' branch.Hi Sergei,
Could you please base it towards "next" instead, it doesn't apply. If you think this is important to go stable, I suggest you to add a stable tag for it.
It's a bit of a corner case, of course, but the consequences are just too
disastrous: AFAIR, an ARM kernel just silently hangs on boot, with no hints of where. So I'm going to CC: -stable.
Quoted 2 lines
Kind regards
Uffe
WBR, Sergei