cxgb4vf: Ingress Queue Entry Size needs to be 64 bytes
Subsystems (2)
PATCH 1/1 cxgb4vf: Ingress Queue Entry Size needs to be 64 bytes
Was using L1_CACHE_BYTES for the Ingress Queue Entry Size but it really needs to be 64 bytes in order to support the largest message sizes.
Signed-off-by Casey Leedom <[email protected]>
--- drivers/net/cxgb4vf/cxgb4vf_main.c | 15 +++++++++++---- 1 files changed, 11 insertions(+), 4 deletions(-)
drivers/net/cxgb4vf/cxgb4vf_main.c +11 -4
@@ -2269,6 +2269,7 @@ static void __devinit cfg_queues(struct adapter *adapter) {struct sge *s = &adapter->sge;int q10g, n10g, qidx, pidx, qs; +size_t iqe_size;/* * We should not be called till we know how many Queue Sets we can
@@ -2313,6 +2314,13 @@ static void __devinit cfg_queues(struct adapter *adapter) s->ethqsets = qidx;/* +* The Ingress Queue Entry Size for our various Response Queues needs +* to be big enough to accommodate the largest message we can receive +* from the chip/firmware; which is 64 bytes ... +*/ + iqe_size =64 ; + +/* * Set up default Queue Set parameters ... Start off with the * shortest interrupt holdoff timer. */
@@ -2320,7 +2328,7 @@ static void __devinit cfg_queues(struct adapter *adapter)struct sge_eth_rxq *rxq = &s->ethrxq[qs];struct sge_eth_txq *txq = &s->ethtxq[qs]; -init_rspq (&rxq->rspq,0 ,0 ,1024 ,L1_CACHE_BYTES ); +init_rspq (&rxq->rspq,0 ,0 ,1024 , iqe_size); rxq->fl.size =72 ; txq->q.size =1024 ; }
@@ -2329,8 +2337,7 @@ static void __devinit cfg_queues(struct adapter *adapter)* The firmware event queue is used for link state changes and * notifications of TX DMA completions. */ -init_rspq (&s->fw_evtq,SGE_TIMER_RSTRT_CNTR ,0 ,512 , -L1_CACHE_BYTES ); +init_rspq (&s->fw_evtq,SGE_TIMER_RSTRT_CNTR ,0 ,512 , iqe_size);/* * The forwarded interrupt queue is used when we're in MSI interrupt
@@ -2346,7 +2353,7 @@ static void __devinit cfg_queues(struct adapter *adapter)* any time ... */ init_rspq (&s->intrq,SGE_TIMER_RSTRT_CNTR ,0 ,MSIX_ENTRIES +1 , -L1_CACHE_BYTES ); + iqe_size); }/*
Signature · 1 line
1.7.0.4
Urk. Sorry about that: the subject prefix should have read "net-26" since
this is a fairly critical bug fix. Let me know if you'd like me to resubmit the patch.
Casey
David Miller
maintainerFrom: Casey Leedom <[email protected]>
Date: Thu, 9 Dec 2010 13:52:40 -0800
Quoted 3 lines
Urk. Sorry about that: the subject prefix should have read "net-26" since
this is a fairly critical bug fix. Let me know if you'd like me to resubmit the patch.
No need to resubmit, applied, thanks.