UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

IB/qib: Optimize locking for get_txreq() 

The current code locks the QP s_lock, followed by the pending_lock, I
guess to to protect against the allocate failing.

This patch only locks the pending_lock, assuming that the empty case
is an exeception, in which case the pending_lock is dropped, and the
original code is executed.  This will save a lock of s_lock in the
normal case.

The observation is that the sdma descriptors will deplete at twice the
rate of txreq's, so this should be rare.

Signed-off-by: Mike Marciniszyn <mike.marciniszyn@qlogic.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
This commit is contained in:
Mike Marciniszyn 2011-12-23 08:03:41 -05:00 committed by Roland Dreier
parent eddfb67525
commit 4894710951
1 changed files with 33 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
drivers/infiniband/hw/qib/qib_verbs.c
View File

@ -913,8 +913,8 @@ static void copy_io(u32 __iomem *piobuf, struct qib_sge_state *ss,
__raw_writel(last, piobuf);
}
static struct qib_verbs_txreq *get_txreq(struct qib_ibdev *dev,
struct qib_qp *qp, int *retp)
static noinline struct qib_verbs_txreq *__get_txreq(struct qib_ibdev *dev,
struct qib_qp *qp)
{
struct qib_verbs_txreq *tx;
unsigned long flags;
@ -926,8 +926,9 @@ static struct qib_verbs_txreq *get_txreq(struct qib_ibdev *dev,
struct list_head *l = dev->txreq_free.next;
list_del(l);
spin_unlock(&dev->pending_lock);
spin_unlock_irqrestore(&qp->s_lock, flags);
tx = list_entry(l, struct qib_verbs_txreq, txreq.list);
*retp = 0;
} else {
if (ib_qib_state_ops[qp->state] & QIB_PROCESS_RECV_OK &&
list_empty(&qp->iowait)) {
@ -935,14 +936,33 @@ static struct qib_verbs_txreq *get_txreq(struct qib_ibdev *dev,
qp->s_flags |= QIB_S_WAIT_TX;
list_add_tail(&qp->iowait, &dev->txwait);
}
tx = NULL;
qp->s_flags &= ~QIB_S_BUSY;
*retp = -EBUSY;
spin_unlock(&dev->pending_lock);
spin_unlock_irqrestore(&qp->s_lock, flags);
tx = ERR_PTR(-EBUSY);
}
return tx;
}
spin_unlock(&dev->pending_lock);
spin_unlock_irqrestore(&qp->s_lock, flags);
static inline struct qib_verbs_txreq *get_txreq(struct qib_ibdev *dev,
struct qib_qp *qp)
{
struct qib_verbs_txreq *tx;
unsigned long flags;
spin_lock_irqsave(&dev->pending_lock, flags);
/* assume the list non empty */
if (likely(!list_empty(&dev->txreq_free))) {
struct list_head *l = dev->txreq_free.next;
list_del(l);
spin_unlock_irqrestore(&dev->pending_lock, flags);
tx = list_entry(l, struct qib_verbs_txreq, txreq.list);
} else {
/* call slow path to get the extra lock */
spin_unlock_irqrestore(&dev->pending_lock, flags);
tx = __get_txreq(dev, qp);
}
return tx;
}
@ -1122,9 +1142,9 @@ static int qib_verbs_send_dma(struct qib_qp *qp, struct qib_ib_header *hdr,
goto bail;
}
tx = get_txreq(dev, qp, &ret);
if (!tx)
goto bail;
tx = get_txreq(dev, qp);
if (IS_ERR(tx))
goto bail_tx;
control = dd->f_setpbc_control(ppd, plen, qp->s_srate,
be16_to_cpu(hdr->lrh[0]) >> 12);
@ -1195,6 +1215,9 @@ unaligned:
ibp->n_unaligned++;
bail:
return ret;
bail_tx:
ret = PTR_ERR(tx);
goto bail;
}
/*