openkylin
/
platform_kernel-5.15
mirror of https://gitee.com/openkylin/platform_kernel-5.15.git
9
0
Fork 0
Code Issues Projects Releases Wiki Activity

IB/ipath: Wait for PIO available interrupt 

The send function is called when posting new send work requests.
There is no point in trying to send a packet if the QP is already
waiting for a HW send buffer so don't clear the busy bit until the
buffer available interrupt happens.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
This commit is contained in:
Ralph Campbell 2007-06-18 14:24:43 -07:00 committed by Roland Dreier
parent 06ee109002
commit db5518cd09
2 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
drivers/infiniband/hw/ipath/ipath_ruc.c
View File

@ -503,11 +503,9 @@ void ipath_no_bufs_available(struct ipath_qp *qp, struct ipath_ibdev *dev)
* could be called. If we are still in the tasklet function, * could be called. If we are still in the tasklet function,
* tasklet_hi_schedule() will not call us until the next time * tasklet_hi_schedule() will not call us until the next time
* tasklet_hi_schedule() is called. * tasklet_hi_schedule() is called.
* We clear the tasklet flag now since we are committing to return * We leave the busy flag set so that another post send doesn't
* from the tasklet function. * try to put the same QP on the piowait list again.
*/ */
clear_bit(IPATH_S_BUSY, &qp->s_busy);
tasklet_unlock(&qp->s_task);
want_buffer(dev->dd); want_buffer(dev->dd);
dev->n_piowait++; dev->n_piowait++;
} }

1
drivers/infiniband/hw/ipath/ipath_verbs.c
View File

@ -948,6 +948,7 @@ int ipath_ib_piobufavail(struct ipath_ibdev *dev)
qp = list_entry(dev->piowait.next, struct ipath_qp, qp = list_entry(dev->piowait.next, struct ipath_qp,
piowait); piowait);
list_del_init(&qp->piowait); list_del_init(&qp->piowait);
clear_bit(IPATH_S_BUSY, &qp->s_busy);
tasklet_hi_schedule(&qp->s_task); tasklet_hi_schedule(&qp->s_task);
} }
spin_unlock_irqrestore(&dev->pending_lock, flags); spin_unlock_irqrestore(&dev->pending_lock, flags);