Imported Upstream version 16.11

Change-Id: I1944c65ddc88a9ad70f8c0eb6731552b84fbcb77
Signed-off-by: Christian Ehrhardt <christian.ehrhardt@canonical.com>

3 files changed, 29 insertions, 33 deletions

diff --git a/drivers/net/fm10k/fm10k_ethdev.c b/drivers/net/fm10k/fm10k_ethdev.c
index 35cbe086..923690c0 100644
--- a/drivers/net/fm10k/fm10k_ethdev.c
+++ b/drivers/net/fm10k/fm10k_ethdev.c
@@ -677,7 +677,7 @@ fm10k_dev_tx_init(struct rte_eth_dev *dev)
 		/* Enable use of FTAG bit in TX descriptor, PFVTCTL
 		 * register is read-only for VF.
 		 */
-		if (fm10k_check_ftag(dev->pci_dev->devargs)) {
+		if (fm10k_check_ftag(dev->pci_dev->device.devargs)) {
 			if (hw->mac.type == fm10k_mac_pf) {
 				FM10K_WRITE_REG(hw, FM10K_PFVTCTL(i),
 						FM10K_PFVTCTL_FTAG_DESC_ENABLE);
@@ -2737,7 +2737,7 @@ fm10k_set_tx_function(struct rte_eth_dev *dev)
 	int use_sse = 1;
 	uint16_t tx_ftag_en = 0;
 
-	if (fm10k_check_ftag(dev->pci_dev->devargs))
+	if (fm10k_check_ftag(dev->pci_dev->device.devargs))
 		tx_ftag_en = 1;
 
 	for (i = 0; i < dev->data->nb_tx_queues; i++) {
@@ -2768,7 +2768,7 @@ fm10k_set_rx_function(struct rte_eth_dev *dev)
 	uint16_t i, rx_using_sse;
 	uint16_t rx_ftag_en = 0;
 
-	if (fm10k_check_ftag(dev->pci_dev->devargs))
+	if (fm10k_check_ftag(dev->pci_dev->device.devargs))
 		rx_ftag_en = 1;
 
 	/* In order to allow Vector Rx there are a few configuration
@@ -3061,34 +3061,16 @@ static const struct rte_pci_id pci_id_fm10k_map[] = {
 
 static struct eth_driver rte_pmd_fm10k = {
 	.pci_drv = {
-		.name = "rte_pmd_fm10k",
 		.id_table = pci_id_fm10k_map,
 		.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
 			RTE_PCI_DRV_DETACHABLE,
+		.probe = rte_eth_dev_pci_probe,
+		.remove = rte_eth_dev_pci_remove,
 	},
 	.eth_dev_init = eth_fm10k_dev_init,
 	.eth_dev_uninit = eth_fm10k_dev_uninit,
 	.dev_private_size = sizeof(struct fm10k_adapter),
 };
 
-/*
- * Driver initialization routine.
- * Invoked once at EAL init time.
- * Register itself as the [Poll Mode] Driver of PCI FM10K devices.
- */
-static int
-rte_pmd_fm10k_init(__rte_unused const char *name,
-	__rte_unused const char *params)
-{
-	PMD_INIT_FUNC_TRACE();
-	rte_eth_driver_register(&rte_pmd_fm10k);
-	return 0;
-}
-
-static struct rte_driver rte_fm10k_driver = {
-	.type = PMD_PDEV,
-	.init = rte_pmd_fm10k_init,
-};
-
-PMD_REGISTER_DRIVER(rte_fm10k_driver, fm10k);
-DRIVER_REGISTER_PCI_TABLE(fm10k, pci_id_fm10k_map);
+RTE_PMD_REGISTER_PCI(net_fm10k, rte_pmd_fm10k.pci_drv);
+RTE_PMD_REGISTER_PCI_TABLE(net_fm10k, pci_id_fm10k_map);
diff --git a/drivers/net/fm10k/fm10k_rxtx.c b/drivers/net/fm10k/fm10k_rxtx.c
index bf5888b0..32cc7ff9 100644
--- a/drivers/net/fm10k/fm10k_rxtx.c
+++ b/drivers/net/fm10k/fm10k_rxtx.c
@@ -101,11 +101,15 @@ rx_desc_to_ol_flags(struct rte_mbuf *m, const union fm10k_rx_desc *d)
 		(FM10K_RXD_STATUS_IPCS | FM10K_RXD_STATUS_IPE)) ==
 		(FM10K_RXD_STATUS_IPCS | FM10K_RXD_STATUS_IPE)))
 		m->ol_flags |= PKT_RX_IP_CKSUM_BAD;
+	else
+		m->ol_flags |= PKT_RX_IP_CKSUM_GOOD;
 
 	if (unlikely((d->d.staterr &
 		(FM10K_RXD_STATUS_L4CS | FM10K_RXD_STATUS_L4E)) ==
 		(FM10K_RXD_STATUS_L4CS | FM10K_RXD_STATUS_L4E)))
 		m->ol_flags |= PKT_RX_L4_CKSUM_BAD;
+	else
+		m->ol_flags |= PKT_RX_L4_CKSUM_GOOD;
 }
 
 uint16_t
diff --git a/drivers/net/fm10k/fm10k_rxtx_vec.c b/drivers/net/fm10k/fm10k_rxtx_vec.c
index c9a49e36..27f3e43f 100644
--- a/drivers/net/fm10k/fm10k_rxtx_vec.c
+++ b/drivers/net/fm10k/fm10k_rxtx_vec.c
@@ -67,6 +67,8 @@ fm10k_reset_tx_queue(struct fm10k_tx_queue *txq);
 #define RXEFLAG_SHIFT     (13)
 /* IPE/L4E flag shift */
 #define L3L4EFLAG_SHIFT     (14)
+/* shift PKT_RX_L4_CKSUM_GOOD into one byte by 1 bit */
+#define CKSUM_SHIFT     (1)
 
 static inline void
 fm10k_desc_to_olflags_v(__m128i descs[4], struct rte_mbuf **rx_pkts)
@@ -92,11 +94,18 @@ fm10k_desc_to_olflags_v(__m128i descs[4], struct rte_mbuf **rx_pkts)
 			0x0000, 0x0000, 0x0000, 0x0000,
 			0x0001, 0x0001, 0x0001, 0x0001);
 
+	/* mask the lower byte of ol_flags */
+	const __m128i ol_flags_msk = _mm_set_epi16(
+			0x0000, 0x0000, 0x0000, 0x0000,
+			0x00FF, 0x00FF, 0x00FF, 0x00FF);
+
 	const __m128i l3l4cksum_flag = _mm_set_epi8(0, 0, 0, 0,
 			0, 0, 0, 0,
 			0, 0, 0, 0,
-			PKT_RX_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD,
-			PKT_RX_IP_CKSUM_BAD, PKT_RX_L4_CKSUM_BAD, 0);
+			(PKT_RX_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD) >> CKSUM_SHIFT,
+			(PKT_RX_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD) >> CKSUM_SHIFT,
+			(PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD) >> CKSUM_SHIFT,
+			(PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_GOOD) >> CKSUM_SHIFT);
 
 	const __m128i rxe_flag = _mm_set_epi8(0, 0, 0, 0,
 			0, 0, 0, 0,
@@ -139,6 +148,10 @@ fm10k_desc_to_olflags_v(__m128i descs[4], struct rte_mbuf **rx_pkts)
 	/* Process L4/L3 checksum error flags */
 	cksumflag = _mm_srli_epi16(cksumflag, L3L4EFLAG_SHIFT);
 	cksumflag = _mm_shuffle_epi8(l3l4cksum_flag, cksumflag);
+
+	/* clean the higher byte and shift back the flag bits */
+	cksumflag = _mm_and_si128(cksumflag, ol_flags_msk);
+	cksumflag = _mm_slli_epi16(cksumflag, CKSUM_SHIFT);
 	vtag1 = _mm_or_si128(cksumflag, vtag1);
 
 	vol.dword = _mm_cvtsi128_si64(vtag1);
@@ -234,11 +247,8 @@ fm10k_rx_vec_condition_check(struct rte_eth_dev *dev)
 	if (fconf->mode != RTE_FDIR_MODE_NONE)
 		return -1;
 
-	/* - no csum error report support
-	 * - no header split support
-	 */
-	if (rxmode->hw_ip_checksum == 1 ||
-	    rxmode->header_split == 1)
+	/* no header split support */
+	if (rxmode->header_split == 1)
 		return -1;
 
 	return 0;
@@ -406,7 +416,7 @@ fm10k_recv_raw_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 	 */
 	rxdp = rxq->hw_ring + next_dd;
 
-	_mm_prefetch((const void *)rxdp, _MM_HINT_T0);
+	rte_prefetch0(rxdp);
 
 	/* See if we need to rearm the RX queue - gives the prefetch a bit
 	 * of time to act