diff options
author | Sarah Sharp <sarah.a.sharp@linux.intel.com> | 2012-02-13 14:42:11 -0800 |
---|---|---|
committer | Sarah Sharp <sarah.a.sharp@linux.intel.com> | 2012-02-21 15:48:46 -0800 |
commit | 340a3504fd39dad753ba908fb6f894ee81fc3ae2 (patch) | |
tree | 304eb27f688f4420ce82b5689a1f1e74aab4ae0f /net/rds/rdma_transport.h | |
parent | a45aa3b30583e7d54e7cf4fbcd0aa699348a6e5c (diff) |
xhci: Fix encoding for HS bulk/control NAK rate.
The xHCI 0.96 spec says that HS bulk and control endpoint NAK rate must
be encoded as an exponent of two number of microframes. The endpoint
descriptor has the NAK rate encoded in number of microframes. We were
just copying the value from the endpoint descriptor into the endpoint
context interval field, which was not correct. This lead to the VIA
host rejecting the add of a bulk OUT endpoint from any USB 2.0 mass
storage device.
The fix is to use the correct encoding. Refactor the code to convert
number of frames to an exponential number of microframes, and make sure
we convert the number of microframes in HS bulk and control endpoints to
an exponent.
This should be back ported to kernels as old as 2.6.31, that contain the
commit dfa49c4ad120a784ef1ff0717168aa79f55a483a "USB: xhci - fix math
in xhci_get_endpoint_interval"
Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Tested-by: Felipe Contreras <felipe.contreras@gmail.com>
Suggested-by: Andiry Xu <andiry.xu@amd.com>
Cc: stable@vger.kernel.org
Diffstat (limited to 'net/rds/rdma_transport.h')
0 files changed, 0 insertions, 0 deletions