summaryrefslogtreecommitdiffstats
path: root/usr
diff options
context:
space:
mode:
authorDavid Herrmann2011-08-26 14:06:02 +0200
committerGustavo F. Padovan2011-10-07 03:15:48 +0200
commit794d175698f0e78be7f2e3f4bdbe0e7cd3f2d6ae (patch)
treee96dcec6fc0ee32252ef51214348fa0066b1f637 /usr
parentBluetooth: EFS: add enable_hs kernel param (diff)
downloadkernel-qcow2-linux-794d175698f0e78be7f2e3f4bdbe0e7cd3f2d6ae.tar.gz
kernel-qcow2-linux-794d175698f0e78be7f2e3f4bdbe0e7cd3f2d6ae.tar.xz
kernel-qcow2-linux-794d175698f0e78be7f2e3f4bdbe0e7cd3f2d6ae.zip
Bluetooth: hidp: Stop I/O on shutdown
Current hidp driver purges the in/out queue on HID shutdown, but does not prevent further I/O. If a driver uses hidp_output_raw_report or hidp_get_raw_report during shutdown, the driver hangs for 5 or 10 seconds per call until it gets a timeout. That is, if the output queue of an HID driver has 10 messages pending, it will take 50s until hid_destroy_device() will return. The hidp_session_sem semaphore is held during shutdown so no other HID device may be added/removed during this time. This patch makes hidp_output_raw_report and hidp_get_raw_report fail if session->terminate is true. Also hidp_session will wakeup all current calls to these functions to cancel the current operations. We already purge the current I/O queues on hidp_stop(), so this data loss does not change the behaviour of the HID drivers. Signed-off-by: David Herrmann <dh.herrmann@googlemail.com> Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
Diffstat (limited to 'usr')
0 files changed, 0 insertions, 0 deletions