From 06917f753547e6bba8a5d17f79971d1c071a70dd Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Tue, 19 May 2015 16:45:46 -0400 Subject: [PATCH] NTB: Improve performance with write combining Changing the memory window BAR mappings to write combining significantly boosts the performance. We will also use memcpy that uses non-temporal store, which showed performance improvement when doing non-cached memcpys. Signed-off-by: Dave Jiang Signed-off-by: Jon Mason --- drivers/ntb/ntb_transport.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index dc14ec81c43e..7a765d3230d8 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -58,6 +58,7 @@ #include #include #include +#include #include "linux/ntb.h" #include "linux/ntb_transport.h" @@ -993,7 +994,7 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev) if (rc) goto err1; - mw->vbase = ioremap(mw->phys_addr, mw->phys_size); + mw->vbase = ioremap_wc(mw->phys_addr, mw->phys_size); if (!mw->vbase) { rc = -ENOMEM; goto err1; @@ -1375,7 +1376,15 @@ static void ntb_tx_copy_callback(void *data) static void ntb_memcpy_tx(struct ntb_queue_entry *entry, void __iomem *offset) { +#ifdef ARCH_HAS_NOCACHE_UACCESS + /* + * Using non-temporal mov to improve performance on non-cached + * writes, even though we aren't actually copying from user space. + */ + __copy_from_user_inatomic_nocache(offset, entry->buf, entry->len); +#else memcpy_toio(offset, entry->buf, entry->len); +#endif /* Ensure that the data is fully copied out before setting the flags */ wmb(); -- 2.34.1