diff options
| author | Tom Herbert <therbert@google.com> | 2010-05-05 16:02:49 +0200 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2010-05-06 06:11:25 +0200 |
| commit | 50849d792b97c546c45a6652a16ba9be7d635c69 (patch) | |
| tree | 16f7ec1cb98909e8f9ac7e9c85065cc1c69e236d /drivers | |
| parent | e1000e: save skb counts in TX to avoid cache misses (diff) | |
| download | linux-50849d792b97c546c45a6652a16ba9be7d635c69.tar.xz linux-50849d792b97c546c45a6652a16ba9be7d635c69.zip | |
e1000e: reduce writes of RX producer ptr
Reduce number of writes to RX producer pointer. When alloc'ing RX
buffers, only write the RX producer pointer once every
E1000_RX_BUFFER_WRITE (16) buffers created.
Signed-off-by: Tom Herbert <therbert@google.com>
Acked-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'drivers')
| -rw-r--r-- | drivers/net/e1000e/netdev.c | 57 |
1 files changed, 23 insertions, 34 deletions
diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index 8de64ed8762c..b049d1a3c861 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -548,26 +548,23 @@ map_skb: rx_desc = E1000_RX_DESC(*rx_ring, i); rx_desc->buffer_addr = cpu_to_le64(buffer_info->dma); + if (unlikely(!(i & (E1000_RX_BUFFER_WRITE - 1)))) { + /* + * 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(i, adapter->hw.hw_addr + rx_ring->tail); + } i++; if (i == rx_ring->count) i = 0; buffer_info = &rx_ring->buffer_info[i]; } - if (rx_ring->next_to_use != i) { - rx_ring->next_to_use = i; - if (i-- == 0) - i = (rx_ring->count - 1); - - /* - * 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(i, adapter->hw.hw_addr + rx_ring->tail); - } + rx_ring->next_to_use = i; } /** @@ -649,6 +646,17 @@ static void e1000_alloc_rx_buffers_ps(struct e1000_adapter *adapter, rx_desc->read.buffer_addr[0] = cpu_to_le64(buffer_info->dma); + if (unlikely(!(i & (E1000_RX_BUFFER_WRITE - 1)))) { + /* + * 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(i<<1, adapter->hw.hw_addr + rx_ring->tail); + } + i++; if (i == rx_ring->count) i = 0; @@ -656,26 +664,7 @@ static void e1000_alloc_rx_buffers_ps(struct e1000_adapter *adapter, } no_buffers: - if (rx_ring->next_to_use != i) { - rx_ring->next_to_use = i; - - if (!(i--)) - i = (rx_ring->count - 1); - - /* - * 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(); - /* - * Hardware increments by 16 bytes, but packet split - * descriptors are 32 bytes...so we increment tail - * twice as much. - */ - writel(i<<1, adapter->hw.hw_addr + rx_ring->tail); - } + rx_ring->next_to_use = i; } /** |