From 29b4433d991c88d86ca48a4c1cc33c671475be4b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 11 Oct 2010 10:22:12 +0000 Subject: net: percpu net_device refcount We tried very hard to remove all possible dev_hold()/dev_put() pairs in network stack, using RCU conversions. There is still an unavoidable device refcount change for every dst we create/destroy, and this can slow down some workloads (routers or some app servers, mmap af_packet) We can switch to a percpu refcount implementation, now dynamic per_cpu infrastructure is mature. On a 64 cpus machine, this consumes 256 bytes per device. On x86, dev_hold(dev) code : before lock incl 0x280(%ebx) after: movl 0x260(%ebx),%eax incl fs:(%eax) Stress bench : (Sending 160.000.000 UDP frames, IP route cache disabled, dual E5540 @2.53GHz, 32bit kernel, FIB_TRIE) Before: real 1m1.662s user 0m14.373s sys 12m55.960s After: real 0m51.179s user 0m15.329s sys 10m15.942s Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/infiniband/hw/nes/nes_cm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/infiniband/hw/nes/nes_cm.c') diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c index 61e0efd4ccfb..6220d9d75b58 100644 --- a/drivers/infiniband/hw/nes/nes_cm.c +++ b/drivers/infiniband/hw/nes/nes_cm.c @@ -2701,7 +2701,7 @@ static int nes_disconnect(struct nes_qp *nesqp, int abrupt) nesibdev = nesvnic->nesibdev; nes_debug(NES_DBG_CM, "netdev refcnt = %u.\n", - atomic_read(&nesvnic->netdev->refcnt)); + netdev_refcnt_read(nesvnic->netdev)); if (nesqp->active_conn) { @@ -2791,7 +2791,7 @@ int nes_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) atomic_inc(&cm_accepts); nes_debug(NES_DBG_CM, "netdev refcnt = %u.\n", - atomic_read(&nesvnic->netdev->refcnt)); + netdev_refcnt_read(nesvnic->netdev)); /* allocate the ietf frame and space for private data */ nesqp->ietf_frame = pci_alloc_consistent(nesdev->pcidev, -- cgit v1.2.3