qcacmn: Add fastpath Rx support

With dedicated CE for Rx and Tx completion HTT messages, skip processing
in Host Target Communication layer.
Do special handling in HIF-CE and HTT layer, this optimization results
in 3-4% CPU utilization gain.

Change-Id: I400148a0e24ac62dd09e2a95d5f35d94d83fe2df
CRs-Fixed: 987182
This commit is contained in:
Manjunathappa Prakash
2016-04-13 23:38:16 -07:00
committed by Gerrit - the friendly Code Review server
szülő c7d5429428
commit 7399f148b5
7 fájl változott, egészen pontosan 442 új sor hozzáadva és 14 régi sor törölve

Fájl megtekintése

@@ -184,4 +184,16 @@ static inline unsigned char *os_malloc(osdev_t nic_dev,
#define SET_NETDEV_DEV(ndev, pdev)
#endif
#define OS_SYNC_SINGLE_FOR_CPU(pdev, paddr_lo, len, oprn) \
{ \
dma_sync_single_for_cpu(pdev, paddr_lo, len, oprn); \
}
#define OS_SYNC_SINGLE_FOR_DEVICE(pdev, paddr_lo, len, oprn) \
{ \
dma_sync_single_for_device(pdev, paddr_lo, len, oprn);\
}
#define SLOTS_PER_TX 2
#endif /* end of _OSDEP_H */