i40e: Separate kernel allocated rx_bi rings from AF_XDP rings

Björn Töpel · Alexei Starovoitov · commit be1222b585fd · 2020-05-21T17:31:26.000-07:00
Continuing the path to support MEM_TYPE_XSK_BUFF_POOL, the AF_XDP zero-copy/sk_buff rx_bi rings are now separate. Functions to properly allocate the different rings are added as well. v3->v4: Made i40e_fd_handle_status() static. (kbuild test robot) v4->v5: Fix kdoc for i40e_clean_programming_status(). (Jakub) Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Cc: intel-wired-lan@lists.osuosl.org Link: https://lore.kernel.org/bpf/20200520192103.355233-8-bjorn.topel@gmail.com
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3260,8 +3260,12 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	if (ring->vsi->type == I40E_VSI_MAIN)
 		xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
 
+	kfree(ring->rx_bi);
 	ring->xsk_umem = i40e_xsk_umem(ring);
 	if (ring->xsk_umem) {
+		ret = i40e_alloc_rx_bi_zc(ring);
+		if (ret)
+			return ret;
 		ring->rx_buf_len = ring->xsk_umem->chunk_size_nohr -
 				   XDP_PACKET_HEADROOM;
 		/* For AF_XDP ZC, we disallow packets to span on
@@ -3280,6 +3284,9 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 			 ring->queue_index);
 
 	} else {
+		ret = i40e_alloc_rx_bi(ring);
+		if (ret)
+			return ret;
 		ring->rx_buf_len = vsi->rx_buf_len;
 		if (ring->vsi->type == I40E_VSI_MAIN) {
 			ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -521,28 +521,29 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi,
 /**
  * i40e_fd_handle_status - check the Programming Status for FD
  * @rx_ring: the Rx ring for this descriptor
- * @rx_desc: the Rx descriptor for programming Status, not a packet descriptor.
+ * @qword0_raw: qword0
+ * @qword1: qword1 after le_to_cpu
  * @prog_id: the id originally used for programming
  *
  * This is used to verify if the FD programming or invalidation
  * requested by SW to the HW is successful or not and take actions accordingly.
  **/
-void i40e_fd_handle_status(struct i40e_ring *rx_ring,
-			   union i40e_rx_desc *rx_desc, u8 prog_id)
+static void i40e_fd_handle_status(struct i40e_ring *rx_ring, u64 qword0_raw,
+				  u64 qword1, u8 prog_id)
 {
 	struct i40e_pf *pf = rx_ring->vsi->back;
 	struct pci_dev *pdev = pf->pdev;
+	struct i40e_32b_rx_wb_qw0 *qw0;
 	u32 fcnt_prog, fcnt_avail;
 	u32 error;
-	u64 qw;
 
-	qw = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-	error = (qw & I40E_RX_PROG_STATUS_DESC_QW1_ERROR_MASK) >>
+	qw0 = (struct i40e_32b_rx_wb_qw0 *)&qword0_raw;
+	error = (qword1 & I40E_RX_PROG_STATUS_DESC_QW1_ERROR_MASK) >>
 		I40E_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT;
 
 	if (error == BIT(I40E_RX_PROG_STATUS_DESC_FD_TBL_FULL_SHIFT)) {
-		pf->fd_inv = le32_to_cpu(rx_desc->wb.qword0.hi_dword.fd_id);
-		if ((rx_desc->wb.qword0.hi_dword.fd_id != 0) ||
+		pf->fd_inv = le32_to_cpu(qw0->hi_dword.fd_id);
+		if (qw0->hi_dword.fd_id != 0 ||
 		    (I40E_DEBUG_FD & pf->hw.debug_mask))
 			dev_warn(&pdev->dev, "ntuple filter loc = %d, could not be added\n",
 				 pf->fd_inv);
@@ -560,7 +561,7 @@ void i40e_fd_handle_status(struct i40e_ring *rx_ring,
 		/* store the current atr filter count */
 		pf->fd_atr_cnt = i40e_get_current_atr_cnt(pf);
 
-		if ((rx_desc->wb.qword0.hi_dword.fd_id == 0) &&
+		if (qw0->hi_dword.fd_id == 0 &&
 		    test_bit(__I40E_FD_SB_AUTO_DISABLED, pf->state)) {
 			/* These set_bit() calls aren't atomic with the
 			 * test_bit() here, but worse case we potentially
@@ -589,7 +590,7 @@ void i40e_fd_handle_status(struct i40e_ring *rx_ring,
 	} else if (error == BIT(I40E_RX_PROG_STATUS_DESC_NO_FD_ENTRY_SHIFT)) {
 		if (I40E_DEBUG_FD & pf->hw.debug_mask)
 			dev_info(&pdev->dev, "ntuple filter fd_id = %d, could not be removed\n",
-				 rx_desc->wb.qword0.hi_dword.fd_id);
+				 qw0->hi_dword.fd_id);
 	}
 }
 
@@ -1232,64 +1233,27 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring,
 }
 
 /**
- * i40e_rx_is_programming_status - check for programming status descriptor
- * @qw: qword representing status_error_len in CPU ordering
- *
- * The value of in the descriptor length field indicate if this
- * is a programming status descriptor for flow director or FCoE
- * by the value of I40E_RX_PROG_STATUS_DESC_LENGTH, otherwise
- * it is a packet descriptor.
- **/
-static inline bool i40e_rx_is_programming_status(u64 qw)
-{
-	/* The Rx filter programming status and SPH bit occupy the same
-	 * spot in the descriptor. Since we don't support packet split we
-	 * can just reuse the bit as an indication that this is a
-	 * programming status descriptor.
-	 */
-	return qw & I40E_RXD_QW1_LENGTH_SPH_MASK;
-}
-
-/**
- * i40e_clean_programming_status - try clean the programming status descriptor
+ * i40e_clean_programming_status - clean the programming status descriptor
  * @rx_ring: the rx ring that has this descriptor
- * @rx_desc: the rx descriptor written back by HW
- * @qw: qword representing status_error_len in CPU ordering
+ * @qword0_raw: qword0
+ * @qword1: qword1 representing status_error_len in CPU ordering
  *
  * Flow director should handle FD_FILTER_STATUS to check its filter programming
  * status being successful or not and take actions accordingly. FCoE should
  * handle its context/filter programming/invalidation status and take actions.
  *
  * Returns an i40e_rx_buffer to reuse if the cleanup occurred, otherwise NULL.
  **/
-struct i40e_rx_buffer *i40e_clean_programming_status(
-	struct i40e_ring *rx_ring,
-	union i40e_rx_desc *rx_desc,
-	u64 qw)
+void i40e_clean_programming_status(struct i40e_ring *rx_ring, u64 qword0_raw,
+				   u64 qword1)
 {
-	struct i40e_rx_buffer *rx_buffer;
-	u32 ntc;
 	u8 id;
 
-	if (!i40e_rx_is_programming_status(qw))
-		return NULL;
-
-	ntc = rx_ring->next_to_clean;
-
-	/* fetch, update, and store next to clean */
-	rx_buffer = i40e_rx_bi(rx_ring, ntc++);
-	ntc = (ntc < rx_ring->count) ? ntc : 0;
-	rx_ring->next_to_clean = ntc;
-
-	prefetch(I40E_RX_DESC(rx_ring, ntc));
-
-	id = (qw & I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK) >>
+	id = (qword1 & I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK) >>
 		  I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT;
 
 	if (id == I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS)
-		i40e_fd_handle_status(rx_ring, rx_desc, id);
-
-	return rx_buffer;
+		i40e_fd_handle_status(rx_ring, qword0_raw, qword1, id);
 }
 
 /**
@@ -1341,13 +1305,25 @@ int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring)
 	return -ENOMEM;
 }
 
+int i40e_alloc_rx_bi(struct i40e_ring *rx_ring)
+{
+	unsigned long sz = sizeof(*rx_ring->rx_bi) * rx_ring->count;
+
+	rx_ring->rx_bi = kzalloc(sz, GFP_KERNEL);
+	return rx_ring->rx_bi ? 0 : -ENOMEM;
+}
+
+static void i40e_clear_rx_bi(struct i40e_ring *rx_ring)
+{
+	memset(rx_ring->rx_bi, 0, sizeof(*rx_ring->rx_bi) * rx_ring->count);
+}
+
 /**
  * i40e_clean_rx_ring - Free Rx buffers
  * @rx_ring: ring to be cleaned
  **/
 void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 {
-	unsigned long bi_size;
 	u16 i;
 
 	/* ring already cleared, nothing to do */
@@ -1393,8 +1369,10 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 	}
 
 skip_free:
-	bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count;
-	memset(rx_ring->rx_bi, 0, bi_size);
+	if (rx_ring->xsk_umem)
+		i40e_clear_rx_bi_zc(rx_ring);
+	else
+		i40e_clear_rx_bi(rx_ring);
 
 	/* Zero out the descriptor ring */
 	memset(rx_ring->desc, 0, rx_ring->size);
@@ -1435,15 +1413,7 @@ void i40e_free_rx_resources(struct i40e_ring *rx_ring)
 int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
 {
 	struct device *dev = rx_ring->dev;
-	int err = -ENOMEM;
-	int bi_size;
-
-	/* warn if we are about to overwrite the pointer */
-	WARN_ON(rx_ring->rx_bi);
-	bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count;
-	rx_ring->rx_bi = kzalloc(bi_size, GFP_KERNEL);
-	if (!rx_ring->rx_bi)
-		goto err;
+	int err;
 
 	u64_stats_init(&rx_ring->syncp);
 
@@ -1456,7 +1426,7 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
 	if (!rx_ring->desc) {
 		dev_info(dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n",
 			 rx_ring->size);
-		goto err;
+		return -ENOMEM;
 	}
 
 	rx_ring->next_to_alloc = 0;
@@ -1468,16 +1438,12 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
 		err = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
 				       rx_ring->queue_index);
 		if (err < 0)
-			goto err;
+			return err;
 	}
 
 	rx_ring->xdp_prog = rx_ring->vsi->xdp_prog;
 
 	return 0;
-err:
-	kfree(rx_ring->rx_bi);
-	rx_ring->rx_bi = NULL;
-	return err;
 }
 
 /**
@@ -2387,9 +2353,12 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		 */
 		dma_rmb();
 
-		rx_buffer = i40e_clean_programming_status(rx_ring, rx_desc,
-							  qword);
-		if (unlikely(rx_buffer)) {
+		if (i40e_rx_is_programming_status(qword)) {
+			i40e_clean_programming_status(rx_ring,
+						      rx_desc->raw.qword[0],
+						      qword);
+			rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
+			i40e_inc_ntc(rx_ring);
 			i40e_reuse_rx_page(rx_ring, rx_buffer);
 			cleaned_count++;
 			continue;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -296,17 +296,15 @@ struct i40e_tx_buffer {
 
 struct i40e_rx_buffer {
 	dma_addr_t dma;
-	union {
-		struct {
-			struct page *page;
-			__u32 page_offset;
-			__u16 pagecnt_bias;
-		};
-		struct {
-			void *addr;
-			u64 handle;
-		};
-	};
+	struct page *page;
+	__u32 page_offset;
+	__u16 pagecnt_bias;
+};
+
+struct i40e_rx_buffer_zc {
+	dma_addr_t dma;
+	void *addr;
+	u64 handle;
 };
 
 struct i40e_queue_stats {
@@ -358,6 +356,7 @@ struct i40e_ring {
 	union {
 		struct i40e_tx_buffer *tx_bi;
 		struct i40e_rx_buffer *rx_bi;
+		struct i40e_rx_buffer_zc *rx_bi_zc;
 	};
 	DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS);
 	u16 queue_index;		/* Queue number of ring */
@@ -495,6 +494,7 @@ int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size);
 bool __i40e_chk_linearize(struct sk_buff *skb);
 int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		  u32 flags);
+int i40e_alloc_rx_bi(struct i40e_ring *rx_ring);
 
 /**
  * i40e_get_head - Retrieve head from head writeback
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
@@ -4,13 +4,9 @@
 #ifndef I40E_TXRX_COMMON_
 #define I40E_TXRX_COMMON_
 
-void i40e_fd_handle_status(struct i40e_ring *rx_ring,
-			   union i40e_rx_desc *rx_desc, u8 prog_id);
 int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring);
-struct i40e_rx_buffer *i40e_clean_programming_status(
-	struct i40e_ring *rx_ring,
-	union i40e_rx_desc *rx_desc,
-	u64 qw);
+void i40e_clean_programming_status(struct i40e_ring *rx_ring, u64 qword0_raw,
+				   u64 qword1);
 void i40e_process_skb_fields(struct i40e_ring *rx_ring,
 			     union i40e_rx_desc *rx_desc, struct sk_buff *skb);
 void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring);
@@ -84,6 +80,38 @@ static inline void i40e_arm_wb(struct i40e_ring *tx_ring,
 	}
 }
 
+/**
+ * i40e_rx_is_programming_status - check for programming status descriptor
+ * @qword1: qword1 representing status_error_len in CPU ordering
+ *
+ * The value of in the descriptor length field indicate if this
+ * is a programming status descriptor for flow director or FCoE
+ * by the value of I40E_RX_PROG_STATUS_DESC_LENGTH, otherwise
+ * it is a packet descriptor.
+ **/
+static inline bool i40e_rx_is_programming_status(u64 qword1)
+{
+	/* The Rx filter programming status and SPH bit occupy the same
+	 * spot in the descriptor. Since we don't support packet split we
+	 * can just reuse the bit as an indication that this is a
+	 * programming status descriptor.
+	 */
+	return qword1 & I40E_RXD_QW1_LENGTH_SPH_MASK;
+}
+
+/**
+ * i40e_inc_ntc: Advance the next_to_clean index
+ * @rx_ring: Rx ring
+ **/
+static inline void i40e_inc_ntc(struct i40e_ring *rx_ring)
+{
+	u32 ntc = rx_ring->next_to_clean + 1;
+
+	ntc = (ntc < rx_ring->count) ? ntc : 0;
+	rx_ring->next_to_clean = ntc;
+	prefetch(I40E_RX_DESC(rx_ring, ntc));
+}
+
 void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring);
 void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring);
 bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -689,7 +689,7 @@ union i40e_32byte_rx_desc {
 		__le64  rsvd2;
 	} read;
 	struct {
-		struct {
+		struct i40e_32b_rx_wb_qw0 {
 			struct {
 				union {
 					__le16 mirroring_status;
@@ -727,6 +727,9 @@ union i40e_32byte_rx_desc {
 			} hi_dword;
 		} qword3;
 	} wb;  /* writeback */
+	struct {
+		u64 qword[4];
+	} raw;
 };
 
 enum i40e_rx_desc_status_bits {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
