summaryrefslogtreecommitdiffstats
path: root/scripts/sorttable.c
diff options
context:
space:
mode:
authorFabrice Gasnier <fabrice.gasnier@st.com>2020-02-14 17:23:57 +0100
committerJonathan Cameron <Jonathan.Cameron@huawei.com>2020-03-08 17:28:35 +0000
commit3192ade7b6f6306b66139109e0d455f98a7f695f (patch)
tree13e67ca5df29483979999cb0ebd1ff3ec0e91b10 /scripts/sorttable.c
parent9c088c020d8181a0c8376444b740c99366eec04d (diff)
downloadlinux-stable-3192ade7b6f6306b66139109e0d455f98a7f695f.tar.gz
linux-stable-3192ade7b6f6306b66139109e0d455f98a7f695f.tar.bz2
linux-stable-3192ade7b6f6306b66139109e0d455f98a7f695f.zip
iio: trigger: stm32-timer: enable clock when in master mode
Clock should be enabled as soon as using master modes, even before enabling timer. Or, this may provoke bad behavior on the other end (slave timer). Then, introduce 'clk_enabled' flag, instead of relying on CR1 EN bit, to keep track of clock being enabled (balanced refcount). Propagate this anywhere else in the driver. Also add 'remove' routine to stop timer and disable clock in case it has been left enabled. Enforce the user interface has been unregistered in the remove routine, before disabling the hardware to avoid possible race. So, remove use of devm_ variant to register triggers and unregister them before the hardware gets disabled [1]. [1] https://patchwork.kernel.org/patch/9956247/ Signed-off-by: Fabrice Gasnier <fabrice.gasnier@st.com> Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Diffstat (limited to 'scripts/sorttable.c')
0 files changed, 0 insertions, 0 deletions