From: Michael S. Tsirkin Avoid taking the CQ table lock in the fast path path by using synchronize_irq() after removing a CQ from the table to make sure that no completion events are still in progress. This gets a nice speedup (about 4%) in IP over IB on my hardware. Signed-off-by: Michael S. Tsirkin Signed-off-by: Roland Dreier Signed-off-by: Andrew Morton --- 25-akpm/drivers/infiniband/hw/mthca/mthca_cq.c | 13 ++++++------- 1 files changed, 6 insertions(+), 7 deletions(-) diff -puN drivers/infiniband/hw/mthca/mthca_cq.c~ib-mthca-improve-cq-locking-part-1 drivers/infiniband/hw/mthca/mthca_cq.c --- 25/drivers/infiniband/hw/mthca/mthca_cq.c~ib-mthca-improve-cq-locking-part-1 2005-03-03 17:39:53.000000000 -0800 +++ 25-akpm/drivers/infiniband/hw/mthca/mthca_cq.c 2005-03-03 17:39:53.000000000 -0800 @@ -33,6 +33,7 @@ */ #include +#include #include @@ -181,11 +182,7 @@ void mthca_cq_event(struct mthca_dev *de { struct mthca_cq *cq; - spin_lock(&dev->cq_table.lock); cq = mthca_array_get(&dev->cq_table.cq, cqn & (dev->limits.num_cqs - 1)); - if (cq) - atomic_inc(&cq->refcount); - spin_unlock(&dev->cq_table.lock); if (!cq) { mthca_warn(dev, "Completion event for bogus CQ %08x\n", cqn); @@ -193,9 +190,6 @@ void mthca_cq_event(struct mthca_dev *de } cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context); - - if (atomic_dec_and_test(&cq->refcount)) - wake_up(&cq->wait); } void mthca_cq_clean(struct mthca_dev *dev, u32 cqn, u32 qpn) @@ -783,6 +777,11 @@ void mthca_free_cq(struct mthca_dev *dev cq->cqn & (dev->limits.num_cqs - 1)); spin_unlock_irq(&dev->cq_table.lock); + if (dev->mthca_flags & MTHCA_FLAG_MSI_X) + synchronize_irq(dev->eq_table.eq[MTHCA_EQ_COMP].msi_x_vector); + else + synchronize_irq(dev->pdev->irq); + atomic_dec(&cq->refcount); wait_event(cq->wait, !atomic_read(&cq->refcount)); _