@@ -186,7 +186,13 @@ static int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data,
/* Mark the data descriptor to be watched */
first->next_to_watch = tx_desc;
- writel(tx_ring->next_to_use, tx_ring->tail);
+ writel_relaxed(tx_ring->next_to_use, tx_ring->tail);
+
+ /* We need this if more than one processor can write to our tail
+ * at a time, it synchronizes IO on IA64/Altix systems
+ */
+ mmiowb();
+
return 0;
dma_fail:
@@ -1523,12 +1529,6 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val)
/* update next to alloc since we have filled the ring */
rx_ring->next_to_alloc = val;
- /* Force memory writes to complete before letting h/w
- * know there are new descriptors to fetch. (Only
- * applicable for weak-ordered memory model archs,
- * such as IA-64).
- */
- wmb();
writel(val, rx_ring->tail);
}
@@ -2274,11 +2274,7 @@ static void i40e_rx_buffer_flip(struct i40e_ring *rx_ring,
static inline void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring)
{
- /* Force memory writes to complete before letting h/w
- * know there are new descriptors to fetch.
- */
- wmb();
- writel_relaxed(xdp_ring->next_to_use, xdp_ring->tail);
+ writel(xdp_ring->next_to_use, xdp_ring->tail);
}
/**
@@ -3444,7 +3440,7 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
/* notify HW of packet */
if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
- writel(i, tx_ring->tail);
+ writel_relaxed(i, tx_ring->tail);
/* we need this if more than one processor can write to our tail
* at a time, it synchronizes IO on IA64/Altix systems
@@ -804,12 +804,6 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val)
/* update next to alloc since we have filled the ring */
rx_ring->next_to_alloc = val;
- /* Force memory writes to complete before letting h/w
- * know there are new descriptors to fetch. (Only
- * applicable for weak-ordered memory model archs,
- * such as IA-64).
- */
- wmb();
writel(val, rx_ring->tail);
}
@@ -2379,7 +2373,7 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
/* notify HW of packet */
if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
- writel(i, tx_ring->tail);
+ writel_relaxed(i, tx_ring->tail);
/* we need this if more than one processor can write to our tail
* at a time, it synchronizes IO on IA64/Altix systems
memory-barriers.txt has been updated as follows: "When using writel(), a prior wmb() is not needed to guarantee that the cache coherent memory writes have completed before writing to the MMIO region." Remove old IA-64 comments in the code along with unneeded wmb() in front of writel(). There are places in the code where wmb() has been used as a double barrier for CPU and IO in place of smp_wmb() and wmb() as an optimization. For such places, keep the wmb() but replace the following writel() with writel_relaxed() to have a sequence as wmb() writel_relaxed() mmio_wb() Signed-off-by: Sinan Kaya <okaya@codeaurora.org> --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 22 +++++++++------------- drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 8 +------- 2 files changed, 10 insertions(+), 20 deletions(-)