Sean Hefty wrote:
int ib_init_ah_from_path(struct ib_device *device, u8 port_num,
struct ib_sa_path_rec *rec, struct
ib_ah_attr *ah_attr)
{
int ret;
u16 gid_index;
memset(ah_attr, 0, sizeof *ah_attr);
ah_attr->dlid = be16_to_cpu(rec->dlid);
ah_attr->sl = rec->sl;
ah_attr->src_path_bits = be16_to_cpu(rec->slid) & 0x7f;
I looked at this more, and to be technically correct here, what we can
do is:
in update_sm_ah:
use port_attr.LMC to record a src_path_mask with ib_sa_port
in ib_init_ah_from_path:
use the src_path_mask from ib_sa_port to set src_path_bits
However, I'm not completely convinced that masking off the upper bits
of the SLID is necessary when setting the src_path_bits, which means
that the mask used above could be removed.
I think that this behavior is much better that current behavior ..
thanks
Dotan
_______________________________________________
general mailing list
[email protected]
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
