Merge branch '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue

Jeff Kirsher says:

====================
40GbE Intel Wired LAN Driver Updates 2016-05-05

This series contains updates to i40e and i40evf.

The theme behind this series is code reduction, yeah!  Jesse provides
most of the changes starting with a refactor of the interpretation of
a tunnel which lets us start using the hardware's parsing.  Removed
the packet split receive routine and ancillary code in preparation
for the Rx-refactor.  The refactor of the receive routine,
aligns the receive routine with the one in ixgbe which was highly
optimized.  The hardware supports a 16 byte descriptor for receive,
but the driver was never using it in production.  There was no performance
benefit to the real driver of 16 byte descriptors, so drop a whole lot
of complexity while getting rid of the code.  Fixed a bug where while
changing the number of descriptors using ethtool, the driver did not
test the limits of the system memory before permanently assuming it
would be able to get receive buffer memory.

Mitch fixes a memory leak of one page each time the driver is opened by
allocating the correct number of receive buffers and do not fiddle with
next_to_use in the VF driver.

Arnd Bergmann fixed a indentation issue by adding the appropriate
curly braces in i40e_vc_config_promiscuous_mode_msg().

Julia Lawall fixed an issue found by Coccinelle, where i40e_client_ops
structure can be const since it is never modified.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 35 insertions, 34 deletions

diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index 54b52e8..0112277 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -102,8 +102,8 @@ enum i40e_dyn_idx_t {
 	(((pf)->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE) ? \
 	  I40E_DEFAULT_RSS_HENA_EXPANDED : I40E_DEFAULT_RSS_HENA)
 
-/* Supported Rx Buffer Sizes */
-#define I40E_RXBUFFER_512   512    /* Used for packet split */
+/* Supported Rx Buffer Sizes (a multiple of 128) */
+#define I40E_RXBUFFER_256   256
 #define I40E_RXBUFFER_2048  2048
 #define I40E_RXBUFFER_3072  3072   /* For FCoE MTU of 2158 */
 #define I40E_RXBUFFER_4096  4096
@@ -114,9 +114,28 @@ enum i40e_dyn_idx_t {
  * reserve 2 more, and skb_shared_info adds an additional 384 bytes more,
  * this adds up to 512 bytes of extra data meaning the smallest allocation
  * we could have is 1K.
- * i.e. RXBUFFER_512 --> size-1024 slab
+ * i.e. RXBUFFER_256 --> 960 byte skb (size-1024 slab)
+ * i.e. RXBUFFER_512 --> 1216 byte skb (size-2048 slab)
  */
-#define I40E_RX_HDR_SIZE  I40E_RXBUFFER_512
+#define I40E_RX_HDR_SIZE I40E_RXBUFFER_256
+#define i40e_rx_desc i40e_32byte_rx_desc
+
+/**
+ * i40e_test_staterr - tests bits in Rx descriptor status and error fields
+ * @rx_desc: pointer to receive descriptor (in le64 format)
+ * @stat_err_bits: value to mask
+ *
+ * This function does some fast chicanery in order to return the
+ * value of the mask which is really only used for boolean tests.
+ * The status_error_len doesn't need to be shifted because it begins
+ * at offset zero.
+ */
+static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc,
+				     const u64 stat_err_bits)
+{
+	return !!(rx_desc->wb.qword1.status_error_len &
+		  cpu_to_le64(stat_err_bits));
+}
 
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
 #define I40E_RX_BUFFER_WRITE	16	/* Must be power of 2 */
@@ -142,8 +161,6 @@ enum i40e_dyn_idx_t {
 		prefetch((n));				\
 	} while (0)
 
-#define i40e_rx_desc i40e_32byte_rx_desc
-
 #define I40E_MAX_BUFFER_TXD	8
 #define I40E_MIN_TX_LEN		17
 
@@ -212,10 +229,8 @@ struct i40e_tx_buffer {
 
 struct i40e_rx_buffer {
 	struct sk_buff *skb;
-	void *hdr_buf;
 	dma_addr_t dma;
 	struct page *page;
-	dma_addr_t page_dma;
 	unsigned int page_offset;
 };
 
@@ -244,22 +259,18 @@ struct i40e_rx_queue_stats {
 enum i40e_ring_state_t {
 	__I40E_TX_FDIR_INIT_DONE,
 	__I40E_TX_XPS_INIT_DONE,
-	__I40E_RX_PS_ENABLED,
-	__I40E_RX_16BYTE_DESC_ENABLED,
 };
 
-#define ring_is_ps_enabled(ring) \
-	test_bit(__I40E_RX_PS_ENABLED, &(ring)->state)
-#define set_ring_ps_enabled(ring) \
-	set_bit(__I40E_RX_PS_ENABLED, &(ring)->state)
-#define clear_ring_ps_enabled(ring) \
-	clear_bit(__I40E_RX_PS_ENABLED, &(ring)->state)
-#define ring_is_16byte_desc_enabled(ring) \
-	test_bit(__I40E_RX_16BYTE_DESC_ENABLED, &(ring)->state)
-#define set_ring_16byte_desc_enabled(ring) \
-	set_bit(__I40E_RX_16BYTE_DESC_ENABLED, &(ring)->state)
-#define clear_ring_16byte_desc_enabled(ring) \
-	clear_bit(__I40E_RX_16BYTE_DESC_ENABLED, &(ring)->state)
+/* some useful defines for virtchannel interface, which
+ * is the only remaining user of header split
+ */
+#define I40E_RX_DTYPE_NO_SPLIT      0
+#define I40E_RX_DTYPE_HEADER_SPLIT  1
+#define I40E_RX_DTYPE_SPLIT_ALWAYS  2
+#define I40E_RX_SPLIT_L2      0x1
+#define I40E_RX_SPLIT_IP      0x2
+#define I40E_RX_SPLIT_TCP_UDP 0x4
+#define I40E_RX_SPLIT_SCTP    0x8
 
 /* struct that defines a descriptor ring, associated with a VSI */
 struct i40e_ring {
@@ -278,16 +289,7 @@ struct i40e_ring {
 
 	u16 count;			/* Number of descriptors */
 	u16 reg_idx;			/* HW register index of the ring */
-	u16 rx_hdr_len;
 	u16 rx_buf_len;
-	u8  dtype;
-#define I40E_RX_DTYPE_NO_SPLIT      0
-#define I40E_RX_DTYPE_HEADER_SPLIT  1
-#define I40E_RX_DTYPE_SPLIT_ALWAYS  2
-#define I40E_RX_SPLIT_L2      0x1
-#define I40E_RX_SPLIT_IP      0x2
-#define I40E_RX_SPLIT_TCP_UDP 0x4
-#define I40E_RX_SPLIT_SCTP    0x8
 
 	/* used in interrupt processing */
 	u16 next_to_use;
@@ -319,6 +321,7 @@ struct i40e_ring {
 	struct i40e_q_vector *q_vector;	/* Backreference to associated vector */
 
 	struct rcu_head rcu;		/* to avoid race on free */
+	u16 next_to_alloc;
 } ____cacheline_internodealigned_in_smp;
 
 enum i40e_latency_range {
@@ -342,9 +345,7 @@ struct i40e_ring_container {
 #define i40e_for_each_ring(pos, head) \
 	for (pos = (head).ring; pos != NULL; pos = pos->next)
 
-bool i40evf_alloc_rx_buffers_ps(struct i40e_ring *rxr, u16 cleaned_count);
-bool i40evf_alloc_rx_buffers_1buf(struct i40e_ring *rxr, u16 cleaned_count);
-void i40evf_alloc_rx_headers(struct i40e_ring *rxr);
+bool i40evf_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count);
 netdev_tx_t i40evf_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
 void i40evf_clean_tx_ring(struct i40e_ring *tx_ring);
 void i40evf_clean_rx_ring(struct i40e_ring *rx_ring);