Merge branch 'octeontx2-af-Debugfs-support-and-updates-to-parser-profile'

Sunil Goutham says:

====================
octeontx2-af: Debugfs support and updates to parser profile

This patchset adds debugfs support to dump various HW state machine info
which helps in debugging issues. Info includes
- Current queue context, stats, resource utilization etc
- MCAM entry utilization, miss and pkt drop counter
- CGX ingress and egress stats
- Current RVU block allocation status
- etc.

Rest patches has changes wrt
- Updated packet parsing profile for parsing more protocols.
- RSS algorithms to include inner protocols while generating hash
- Handle current version of silicon's limitations wrt shaping, coloring
  and fixed mapping of transmit limiter queue's configuration.
- Enable broadcast packet replication to PF and it's VFs.
- Support for configurable NDC cache waymask
- etc

Changes from v1:
   Removed inline keyword for newly introduced APIs in few patches.
   - Suggested by David Miller.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/marvell/octeontx2/Kconfig

@@ -16,3 +16,12 @@ config OCTEONTX2_AF
 	  Unit's admin function manager which manages all RVU HW resources
 	  and provides a medium to other PF/VFs to configure HW. Should be
 	  enabled for other RVU device drivers to work.
+
+config NDC_DIS_DYNAMIC_CACHING
+	bool "Disable caching of dynamic entries in NDC"
+	depends on OCTEONTX2_AF
+	default n
+	---help---
+	  This config option disables caching of dynamic entries such as NIX SQEs
+	  , NPA stack pages etc in NDC. Also locks down NIX SQ/CQ/RQ/RSS and
+	  NPA Aura/Pool contexts.

drivers/net/ethernet/marvell/octeontx2/af/Makefile

@@ -8,4 +8,4 @@ obj-$(CONFIG_OCTEONTX2_AF) += octeontx2_af.o
 
 octeontx2_mbox-y := mbox.o
 octeontx2_af-y := cgx.o rvu.o rvu_cgx.o rvu_npa.o rvu_nix.o \
-		  rvu_reg.o rvu_npc.o
+		  rvu_reg.o rvu_npc.o rvu_debugfs.o

drivers/net/ethernet/marvell/octeontx2/af/cgx.c

@@ -138,6 +138,16 @@ void *cgx_get_pdata(int cgx_id)
 }
 EXPORT_SYMBOL(cgx_get_pdata);
 
+int cgx_get_cgxid(void *cgxd)
+{
+	struct cgx *cgx = cgxd;
+
+	if (!cgx)
+		return -EINVAL;
+
+	return cgx->cgx_id;
+}
+
 /* Ensure the required lock for event queue(where asynchronous events are
  * posted) is acquired before calling this API. Else an asynchronous event(with
  * latest link status) can reach the destination before this function returns
@@ -281,6 +291,35 @@ void cgx_lmac_promisc_config(int cgx_id, int lmac_id, bool enable)
 }
 EXPORT_SYMBOL(cgx_lmac_promisc_config);
 
+/* Enable or disable forwarding received pause frames to Tx block */
+void cgx_lmac_enadis_rx_pause_fwding(void *cgxd, int lmac_id, bool enable)
+{
+	struct cgx *cgx = cgxd;
+	u64 cfg;
+
+	if (!cgx)
+		return;
+
+	if (enable) {
+		cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL);
+		cfg |= CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK;
+		cgx_write(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL, cfg);
+
+		cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL);
+		cfg |= CGX_SMUX_RX_FRM_CTL_CTL_BCK;
+		cgx_write(cgx, lmac_id,	CGXX_SMUX_RX_FRM_CTL, cfg);
+	} else {
+		cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL);
+		cfg &= ~CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK;
+		cgx_write(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL, cfg);
+
+		cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL);
+		cfg &= ~CGX_SMUX_RX_FRM_CTL_CTL_BCK;
+		cgx_write(cgx, lmac_id,	CGXX_SMUX_RX_FRM_CTL, cfg);
+	}
+}
+EXPORT_SYMBOL(cgx_lmac_enadis_rx_pause_fwding);
+
 int cgx_get_rx_stats(void *cgxd, int lmac_id, int idx, u64 *rx_stat)
 {
 	struct cgx *cgx = cgxd;
@@ -321,6 +360,27 @@ int cgx_lmac_rx_tx_enable(void *cgxd, int lmac_id, bool enable)
 }
 EXPORT_SYMBOL(cgx_lmac_rx_tx_enable);
 
+int cgx_lmac_tx_enable(void *cgxd, int lmac_id, bool enable)
+{
+	struct cgx *cgx = cgxd;
+	u64 cfg, last;
+
+	if (!cgx || lmac_id >= cgx->lmac_count)
+		return -ENODEV;
+
+	cfg = cgx_read(cgx, lmac_id, CGXX_CMRX_CFG);
+	last = cfg;
+	if (enable)
+		cfg |= DATA_PKT_TX_EN;
+	else
+		cfg &= ~DATA_PKT_TX_EN;
+
+	if (cfg != last)
+		cgx_write(cgx, lmac_id, CGXX_CMRX_CFG, cfg);
+	return !!(last & DATA_PKT_TX_EN);
+}
+EXPORT_SYMBOL(cgx_lmac_tx_enable);
+
 /* CGX Firmware interface low level support */
 static int cgx_fwi_cmd_send(u64 req, u64 *resp, struct lmac *lmac)
 {

drivers/net/ethernet/marvell/octeontx2/af/cgx.h

@@ -56,6 +56,11 @@
 #define CGXX_GMP_PCS_MRX_CTL		0x30000
 #define CGXX_GMP_PCS_MRX_CTL_LBK	BIT_ULL(14)
 
+#define CGXX_SMUX_RX_FRM_CTL		0x20020
+#define CGX_SMUX_RX_FRM_CTL_CTL_BCK	BIT_ULL(3)
+#define CGXX_GMP_GMI_RXX_FRM_CTL	0x38028
+#define CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK	BIT_ULL(3)
+
 #define CGX_COMMAND_REG			CGXX_SCRATCH1_REG
 #define CGX_EVENT_REG			CGXX_SCRATCH0_REG
 #define CGX_CMD_TIMEOUT			2200 /* msecs */
@@ -63,6 +68,11 @@
 #define CGX_NVEC			37
 #define CGX_LMAC_FWI			0
 
+enum  cgx_nix_stat_type {
+	NIX_STATS_RX,
+	NIX_STATS_TX,
+};
+
 enum LMAC_TYPE {
 	LMAC_MODE_SGMII		= 0,
 	LMAC_MODE_XAUI		= 1,
@@ -96,6 +106,7 @@ struct cgx_event_cb {
 extern struct pci_driver cgx_driver;
 
 int cgx_get_cgxcnt_max(void);
+int cgx_get_cgxid(void *cgxd);
 int cgx_get_lmac_cnt(void *cgxd);
 void *cgx_get_pdata(int cgx_id);
 int cgx_set_pkind(void *cgxd, u8 lmac_id, int pkind);
@@ -104,9 +115,11 @@ int cgx_lmac_evh_unregister(void *cgxd, int lmac_id);
 int cgx_get_tx_stats(void *cgxd, int lmac_id, int idx, u64 *tx_stat);
 int cgx_get_rx_stats(void *cgxd, int lmac_id, int idx, u64 *rx_stat);
 int cgx_lmac_rx_tx_enable(void *cgxd, int lmac_id, bool enable);
+int cgx_lmac_tx_enable(void *cgxd, int lmac_id, bool enable);
 int cgx_lmac_addr_set(u8 cgx_id, u8 lmac_id, u8 *mac_addr);
 u64 cgx_lmac_addr_get(u8 cgx_id, u8 lmac_id);
 void cgx_lmac_promisc_config(int cgx_id, int lmac_id, bool enable);
+void cgx_lmac_enadis_rx_pause_fwding(void *cgxd, int lmac_id, bool enable);
 int cgx_lmac_internal_loopback(void *cgxd, int lmac_id, bool enable);
 int cgx_get_link_info(void *cgxd, int lmac_id,
 		      struct cgx_link_user_info *linfo);

drivers/net/ethernet/marvell/octeontx2/af/common.h

@@ -196,4 +196,20 @@ enum nix_scheduler {
 #define DEFAULT_RSS_CONTEXT_GROUP	0
 #define MAX_RSS_INDIR_TBL_SIZE		256 /* 1 << Max adder bits */
 
+/* NDC info */
+enum ndc_idx_e {
+	NIX0_RX = 0x0,
+	NIX0_TX = 0x1,
+	NPA0_U  = 0x2,
+};
+
+enum ndc_ctype_e {
+	CACHING = 0x0,
+	BYPASS = 0x1,
+};
+
+#define NDC_MAX_PORT 6
+#define NDC_READ_TRANS 0
+#define NDC_WRITE_TRANS 1
+
 #endif /* COMMON_H */

drivers/net/ethernet/marvell/octeontx2/af/mbox.c

@@ -19,17 +19,20 @@ static const u16 msgs_offset = ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN);
 
 void otx2_mbox_reset(struct otx2_mbox *mbox, int devid)
 {
+	void *hw_mbase = mbox->hwbase + (devid * MBOX_SIZE);
 	struct otx2_mbox_dev *mdev = &mbox->dev[devid];
 	struct mbox_hdr *tx_hdr, *rx_hdr;
 
-	tx_hdr = mdev->mbase + mbox->tx_start;
-	rx_hdr = mdev->mbase + mbox->rx_start;
+	tx_hdr = hw_mbase + mbox->tx_start;
+	rx_hdr = hw_mbase + mbox->rx_start;
 
 	spin_lock(&mdev->mbox_lock);
 	mdev->msg_size = 0;
 	mdev->rsp_size = 0;
 	tx_hdr->num_msgs = 0;
+	tx_hdr->msg_size = 0;
 	rx_hdr->num_msgs = 0;
+	rx_hdr->msg_size = 0;
 	spin_unlock(&mdev->mbox_lock);
 }
 EXPORT_SYMBOL(otx2_mbox_reset);
@@ -133,16 +136,17 @@ EXPORT_SYMBOL(otx2_mbox_init);
 
 int otx2_mbox_wait_for_rsp(struct otx2_mbox *mbox, int devid)
 {
+	unsigned long timeout = jiffies + msecs_to_jiffies(MBOX_RSP_TIMEOUT);
 	struct otx2_mbox_dev *mdev = &mbox->dev[devid];
-	int timeout = 0, sleep = 1;
+	struct device *sender = &mbox->pdev->dev;
 
-	while (mdev->num_msgs != mdev->msgs_acked) {
-		msleep(sleep);
-		timeout += sleep;
-		if (timeout >= MBOX_RSP_TIMEOUT)
-			return -EIO;
+	while (!time_after(jiffies, timeout)) {
+		if (mdev->num_msgs == mdev->msgs_acked)
+			return 0;
+		usleep_range(800, 1000);
 	}
-	return 0;
+	dev_dbg(sender, "timed out while waiting for rsp\n");
+	return -EIO;
 }
 EXPORT_SYMBOL(otx2_mbox_wait_for_rsp);
 
@@ -162,13 +166,25 @@ EXPORT_SYMBOL(otx2_mbox_busy_poll_for_rsp);
 
 void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid)
 {
+	void *hw_mbase = mbox->hwbase + (devid * MBOX_SIZE);
 	struct otx2_mbox_dev *mdev = &mbox->dev[devid];
 	struct mbox_hdr *tx_hdr, *rx_hdr;
 
-	tx_hdr = mdev->mbase + mbox->tx_start;
-	rx_hdr = mdev->mbase + mbox->rx_start;
+	tx_hdr = hw_mbase + mbox->tx_start;
+	rx_hdr = hw_mbase + mbox->rx_start;
+
+	/* If bounce buffer is implemented copy mbox messages from
+	 * bounce buffer to hw mbox memory.
+	 */
+	if (mdev->mbase != hw_mbase)
+		memcpy(hw_mbase + mbox->tx_start + msgs_offset,
+		       mdev->mbase + mbox->tx_start + msgs_offset,
+		       mdev->msg_size);
 
 	spin_lock(&mdev->mbox_lock);
+
+	tx_hdr->msg_size = mdev->msg_size;
+
 	/* Reset header for next messages */
 	mdev->msg_size = 0;
 	mdev->rsp_size = 0;
@@ -215,7 +231,7 @@ struct mbox_msghdr *otx2_mbox_alloc_msg_rsp(struct otx2_mbox *mbox, int devid,
 	msghdr = mdev->mbase + mbox->tx_start + msgs_offset + mdev->msg_size;
 
 	/* Clear the whole msg region */
-	memset(msghdr, 0, sizeof(*msghdr) + size);
+	memset(msghdr, 0, size);
 	/* Init message header with reset values */
 	msghdr->ver = OTX2_MBOX_VERSION;
 	mdev->msg_size += size;
@@ -236,8 +252,10 @@ struct mbox_msghdr *otx2_mbox_get_rsp(struct otx2_mbox *mbox, int devid,
 	struct otx2_mbox_dev *mdev = &mbox->dev[devid];
 	u16 msgs;
 
+	spin_lock(&mdev->mbox_lock);
+
 	if (mdev->num_msgs != mdev->msgs_acked)
-		return ERR_PTR(-ENODEV);
+		goto error;
 
 	for (msgs = 0; msgs < mdev->msgs_acked; msgs++) {
 		struct mbox_msghdr *pmsg = mdev->mbase + imsg;
@@ -245,18 +263,55 @@ struct mbox_msghdr *otx2_mbox_get_rsp(struct otx2_mbox *mbox, int devid,
 
 		if (msg == pmsg) {
 			if (pmsg->id != prsp->id)
-				return ERR_PTR(-ENODEV);
+				goto error;
+			spin_unlock(&mdev->mbox_lock);
 			return prsp;
 		}
 
-		imsg = pmsg->next_msgoff;
-		irsp = prsp->next_msgoff;
+		imsg = mbox->tx_start + pmsg->next_msgoff;
+		irsp = mbox->rx_start + prsp->next_msgoff;
 	}
 
+error:
+	spin_unlock(&mdev->mbox_lock);
 	return ERR_PTR(-ENODEV);
 }
 EXPORT_SYMBOL(otx2_mbox_get_rsp);
 
+int otx2_mbox_check_rsp_msgs(struct otx2_mbox *mbox, int devid)
+{
+	unsigned long ireq = mbox->tx_start + msgs_offset;
+	unsigned long irsp = mbox->rx_start + msgs_offset;
+	struct otx2_mbox_dev *mdev = &mbox->dev[devid];
+	int rc = -ENODEV;
+	u16 msgs;
+
+	spin_lock(&mdev->mbox_lock);
+
+	if (mdev->num_msgs != mdev->msgs_acked)
+		goto exit;
+
+	for (msgs = 0; msgs < mdev->msgs_acked; msgs++) {
+		struct mbox_msghdr *preq = mdev->mbase + ireq;
+		struct mbox_msghdr *prsp = mdev->mbase + irsp;
+
+		if (preq->id != prsp->id)
+			goto exit;
+		if (prsp->rc) {
+			rc = prsp->rc;
+			goto exit;
+		}
+
+		ireq = mbox->tx_start + preq->next_msgoff;
+		irsp = mbox->rx_start + prsp->next_msgoff;
+	}
+	rc = 0;
+exit:
+	spin_unlock(&mdev->mbox_lock);
+	return rc;
+}
+EXPORT_SYMBOL(otx2_mbox_check_rsp_msgs);
+
 int
 otx2_reply_invalid_msg(struct otx2_mbox *mbox, int devid, u16 pcifunc, u16 id)
 {

drivers/net/ethernet/marvell/octeontx2/af/mbox.h

@@ -36,7 +36,7 @@
 
 #define INTR_MASK(pfvfs) ((pfvfs < 64) ? (BIT_ULL(pfvfs) - 1) : (~0ull))
 
-#define MBOX_RSP_TIMEOUT	1000 /* in ms, Time to wait for mbox response */
+#define MBOX_RSP_TIMEOUT	2000 /* Time(ms) to wait for mbox response */
 
 #define MBOX_MSG_ALIGN		16  /* Align mbox msg start to 16bytes */
 
@@ -75,6 +75,7 @@ struct otx2_mbox {
 
 /* Header which preceeds all mbox messages */
 struct mbox_hdr {
+	u64 msg_size;	/* Total msgs size embedded */
 	u16  num_msgs;   /* No of msgs embedded */
 };
 
@@ -103,6 +104,7 @@ struct mbox_msghdr *otx2_mbox_alloc_msg_rsp(struct otx2_mbox *mbox, int devid,
 					    int size, int size_rsp);
 struct mbox_msghdr *otx2_mbox_get_rsp(struct otx2_mbox *mbox, int devid,
 				      struct mbox_msghdr *msg);
+int otx2_mbox_check_rsp_msgs(struct otx2_mbox *mbox, int devid);
 int otx2_reply_invalid_msg(struct otx2_mbox *mbox, int devid,
 			   u16 pcifunc, u16 id);
 bool otx2_mbox_nonempty(struct otx2_mbox *mbox, int devid);
@@ -125,6 +127,7 @@ M(ATTACH_RESOURCES,	0x002, attach_resources, rsrc_attach, msg_rsp)	\
 M(DETACH_RESOURCES,	0x003, detach_resources, rsrc_detach, msg_rsp)	\
 M(MSIX_OFFSET,		0x004, msix_offset, msg_req, msix_offset_rsp)	\
 M(VF_FLR,		0x006, vf_flr, msg_req, msg_rsp)		\
+M(GET_HW_CAP,		0x008, get_hw_cap, msg_req, get_hw_cap_rsp)	\
 /* CGX mbox IDs (range 0x200 - 0x3FF) */				\
 M(CGX_START_RXTX,	0x200, cgx_start_rxtx, msg_req, msg_rsp)	\
 M(CGX_STOP_RXTX,	0x201, cgx_stop_rxtx, msg_req, msg_rsp)		\
@@ -300,6 +303,12 @@ struct msix_offset_rsp {
 	u16  cptlf_msixoff[MAX_RVU_BLKLF_CNT];
 };
 
+struct get_hw_cap_rsp {
+	struct mbox_msghdr hdr;
+	u8 nix_fixed_txschq_mapping; /* Schq mapping fixed or flexible */
+	u8 nix_shaping;		     /* Is shaping and coloring supported */
+};
+
 /* CGX mbox message formats */
 
 struct cgx_stats_rsp {
@@ -352,6 +361,7 @@ struct npa_lf_alloc_req {
 	int node;
 	int aura_sz;  /* No of auras */
 	u32 nr_pools; /* No of pools */
+	u64 way_mask;
 };
 
 struct npa_lf_alloc_rsp {
@@ -442,6 +452,7 @@ struct nix_lf_alloc_req {
 	u16 npa_func;
 	u16 sso_func;
 	u64 rx_cfg;   /* See NIX_AF_LF(0..127)_RX_CFG */
+	u64 way_mask;
 };
 
 struct nix_lf_alloc_rsp {
@@ -512,6 +523,9 @@ struct nix_txsch_alloc_rsp {
 	/* Scheduler queue list allocated at each level */
 	u16 schq_contig_list[NIX_TXSCH_LVL_CNT][MAX_TXSCHQ_PER_FUNC];
 	u16 schq_list[NIX_TXSCH_LVL_CNT][MAX_TXSCHQ_PER_FUNC];
+	u8  aggr_level; /* Traffic aggregation scheduler level */
+	u8  aggr_lvl_rr_prio; /* Aggregation lvl's RR_PRIO config */
+	u8  link_cfg_lvl; /* LINKX_CFG CSRs mapped to TL3 or TL2's index ? */
 };
 
 struct nix_txsch_free_req {
@@ -578,6 +592,18 @@ struct nix_rss_flowkey_cfg {
 #define NIX_FLOW_KEY_TYPE_TCP	BIT(3)
 #define NIX_FLOW_KEY_TYPE_UDP	BIT(4)
 #define NIX_FLOW_KEY_TYPE_SCTP	BIT(5)
+#define NIX_FLOW_KEY_TYPE_NVGRE    BIT(6)
+#define NIX_FLOW_KEY_TYPE_VXLAN    BIT(7)
+#define NIX_FLOW_KEY_TYPE_GENEVE   BIT(8)
+#define NIX_FLOW_KEY_TYPE_ETH_DMAC BIT(9)
+#define NIX_FLOW_KEY_TYPE_IPV6_EXT BIT(10)
+#define NIX_FLOW_KEY_TYPE_GTPU       BIT(11)
+#define NIX_FLOW_KEY_TYPE_INNR_IPV4     BIT(12)
+#define NIX_FLOW_KEY_TYPE_INNR_IPV6     BIT(13)
+#define NIX_FLOW_KEY_TYPE_INNR_TCP      BIT(14)
+#define NIX_FLOW_KEY_TYPE_INNR_UDP      BIT(15)
+#define NIX_FLOW_KEY_TYPE_INNR_SCTP     BIT(16)
+#define NIX_FLOW_KEY_TYPE_INNR_ETH_DMAC BIT(17)
 	u32	flowkey_cfg; /* Flowkey types selected */
 	u8	group;       /* RSS context or group */
 };

drivers/net/ethernet/marvell/octeontx2/af/npc.h

@@ -27,26 +27,45 @@ enum NPC_LID_E {
 enum npc_kpu_la_ltype {
 	NPC_LT_LA_8023 = 1,
 	NPC_LT_LA_ETHER,
+	NPC_LT_LA_IH_NIX_ETHER,
+	NPC_LT_LA_IH_8_ETHER,
+	NPC_LT_LA_IH_4_ETHER,
+	NPC_LT_LA_IH_2_ETHER,
+	NPC_LT_LA_HIGIG2_ETHER,
+	NPC_LT_LA_IH_NIX_HIGIG2_ETHER,
+	NPC_LT_LA_CUSTOM0 = 0xE,
+	NPC_LT_LA_CUSTOM1 = 0xF,
 };
 
 enum npc_kpu_lb_ltype {
 	NPC_LT_LB_ETAG = 1,
 	NPC_LT_LB_CTAG,
-	NPC_LT_LB_STAG,
+	NPC_LT_LB_STAG_QINQ,
 	NPC_LT_LB_BTAG,
-	NPC_LT_LB_QINQ,
 	NPC_LT_LB_ITAG,
+	NPC_LT_LB_DSA,
+	NPC_LT_LB_DSA_VLAN,
+	NPC_LT_LB_EDSA,
+	NPC_LT_LB_EDSA_VLAN,
+	NPC_LT_LB_EXDSA,
+	NPC_LT_LB_EXDSA_VLAN,
+	NPC_LT_LB_CUSTOM0 = 0xE,
+	NPC_LT_LB_CUSTOM1 = 0xF,
 };
 
 enum npc_kpu_lc_ltype {
 	NPC_LT_LC_IP = 1,
+	NPC_LT_LC_IP_OPT,
 	NPC_LT_LC_IP6,
+	NPC_LT_LC_IP6_EXT,
 	NPC_LT_LC_ARP,
 	NPC_LT_LC_RARP,
 	NPC_LT_LC_MPLS,
 	NPC_LT_LC_NSH,
 	NPC_LT_LC_PTP,
 	NPC_LT_LC_FCOE,
+	NPC_LT_LC_CUSTOM0 = 0xE,
+	NPC_LT_LC_CUSTOM1 = 0xF,
 };
 
 /* Don't modify Ltypes upto SCTP, otherwise it will
@@ -57,49 +76,67 @@ enum npc_kpu_ld_ltype {
 	NPC_LT_LD_UDP,
 	NPC_LT_LD_ICMP,
 	NPC_LT_LD_SCTP,
-	NPC_LT_LD_IGMP,
 	NPC_LT_LD_ICMP6,
+	NPC_LT_LD_IGMP = 8,
 	NPC_LT_LD_ESP,
 	NPC_LT_LD_AH,
 	NPC_LT_LD_GRE,
-	NPC_LT_LD_GRE_MPLS,
-	NPC_LT_LD_GRE_NSH,
-	NPC_LT_LD_TU_MPLS,
+	NPC_LT_LD_NVGRE,
+	NPC_LT_LD_NSH,
+	NPC_LT_LD_TU_MPLS_IN_NSH,
+	NPC_LT_LD_TU_MPLS_IN_IP,
+	NPC_LT_LD_CUSTOM0 = 0xE,
+	NPC_LT_LD_CUSTOM1 = 0xF,
 };
 
 enum npc_kpu_le_ltype {
-	NPC_LT_LE_TU_ETHER = 1,
-	NPC_LT_LE_TU_PPP,
-	NPC_LT_LE_TU_MPLS_IN_NSH,
-	NPC_LT_LE_TU_3RD_NSH,
+	NPC_LT_LE_VXLAN = 1,
+	NPC_LT_LE_GENEVE,
+	NPC_LT_LE_GTPU = 4,
+	NPC_LT_LE_VXLANGPE,
+	NPC_LT_LE_GTPC,
+	NPC_LT_LE_NSH,
+	NPC_LT_LE_TU_MPLS_IN_GRE,
+	NPC_LT_LE_TU_NSH_IN_GRE,
+	NPC_LT_LE_TU_MPLS_IN_UDP,
+	NPC_LT_LE_CUSTOM0 = 0xE,
+	NPC_LT_LE_CUSTOM1 = 0xF,
 };
 
 enum npc_kpu_lf_ltype {
-	NPC_LT_LF_TU_IP = 1,
-	NPC_LT_LF_TU_IP6,
-	NPC_LT_LF_TU_ARP,
-	NPC_LT_LF_TU_MPLS_IP,
-	NPC_LT_LF_TU_MPLS_IP6,
-	NPC_LT_LF_TU_MPLS_ETHER,
+	NPC_LT_LF_TU_ETHER = 1,
+	NPC_LT_LF_TU_PPP,
+	NPC_LT_LF_TU_MPLS_IN_VXLANGPE,
+	NPC_LT_LF_TU_NSH_IN_VXLANGPE,
+	NPC_LT_LF_TU_MPLS_IN_NSH,
+	NPC_LT_LF_TU_3RD_NSH,
+	NPC_LT_LF_CUSTOM0 = 0xE,
+	NPC_LT_LF_CUSTOM1 = 0xF,
 };
 
 enum npc_kpu_lg_ltype {
-	NPC_LT_LG_TU_TCP = 1,
-	NPC_LT_LG_TU_UDP,
-	NPC_LT_LG_TU_SCTP,
-	NPC_LT_LG_TU_ICMP,
-	NPC_LT_LG_TU_IGMP,
-	NPC_LT_LG_TU_ICMP6,
-	NPC_LT_LG_TU_ESP,
-	NPC_LT_LG_TU_AH,
+	NPC_LT_LG_TU_IP = 1,
+	NPC_LT_LG_TU_IP6,
+	NPC_LT_LG_TU_ARP,
+	NPC_LT_LG_TU_ETHER_IN_NSH,
+	NPC_LT_LG_CUSTOM0 = 0xE,
+	NPC_LT_LG_CUSTOM1 = 0xF,
 };
 
+/* Don't modify Ltypes upto SCTP, otherwise it will
+ * effect flow tag calculation and thus RSS.
+ */
 enum npc_kpu_lh_ltype {
-	NPC_LT_LH_TCP_DATA = 1,
-	NPC_LT_LH_HTTP_DATA,
-	NPC_LT_LH_HTTPS_DATA,
-	NPC_LT_LH_PPTP_DATA,
-	NPC_LT_LH_UDP_DATA,
+	NPC_LT_LH_TU_TCP = 1,
+	NPC_LT_LH_TU_UDP,
+	NPC_LT_LH_TU_ICMP,
+	NPC_LT_LH_TU_SCTP,
+	NPC_LT_LH_TU_ICMP6,
+	NPC_LT_LH_TU_IGMP = 8,
+	NPC_LT_LH_TU_ESP,
+	NPC_LT_LH_TU_AH,
+	NPC_LT_LH_CUSTOM0 = 0xE,
+	NPC_LT_LH_CUSTOM1 = 0xF,
 };
 
 struct npc_kpu_profile_cam {

drivers/net/ethernet/marvell/octeontx2/af/rvu.c

@@ -56,12 +56,34 @@ static char *mkex_profile; /* MKEX profile name */
 module_param(mkex_profile, charp, 0000);
 MODULE_PARM_DESC(mkex_profile, "MKEX profile name string");
 
+static void rvu_setup_hw_capabilities(struct rvu *rvu)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+
+	hw->cap.nix_tx_aggr_lvl = NIX_TXSCH_LVL_TL1;
+	hw->cap.nix_fixed_txschq_mapping = false;
+	hw->cap.nix_shaping = true;
+	hw->cap.nix_tx_link_bp = true;
+	hw->cap.nix_rx_multicast = true;
+
+	if (is_rvu_96xx_B0(rvu)) {
+		hw->cap.nix_fixed_txschq_mapping = true;
+		hw->cap.nix_txsch_per_cgx_lmac = 4;
+		hw->cap.nix_txsch_per_lbk_lmac = 132;
+		hw->cap.nix_txsch_per_sdp_lmac = 76;
+		hw->cap.nix_shaping = false;
+		hw->cap.nix_tx_link_bp = false;
+		if (is_rvu_96xx_A0(rvu))
+			hw->cap.nix_rx_multicast = false;
+	}
+}
+
 /* Poll a RVU block's register 'offset', for a 'zero'
  * or 'nonzero' at bits specified by 'mask'
  */
 int rvu_poll_reg(struct rvu *rvu, u64 block, u64 offset, u64 mask, bool zero)
 {
-	unsigned long timeout = jiffies + usecs_to_jiffies(100);
+	unsigned long timeout = jiffies + usecs_to_jiffies(10000);
 	void __iomem *reg;
 	u64 reg_val;
 
@@ -73,7 +95,6 @@ int rvu_poll_reg(struct rvu *rvu, u64 block, u64 offset, u64 mask, bool zero)
 		if (!zero && (reg_val & mask))
 			return 0;
 		usleep_range(1, 5);
-		timeout--;
 	}
 	return -EBUSY;
 }
@@ -433,9 +454,9 @@ static void rvu_reset_all_blocks(struct rvu *rvu)
 	rvu_block_reset(rvu, BLKADDR_SSO, SSO_AF_BLK_RST);
 	rvu_block_reset(rvu, BLKADDR_TIM, TIM_AF_BLK_RST);
 	rvu_block_reset(rvu, BLKADDR_CPT0, CPT_AF_BLK_RST);
-	rvu_block_reset(rvu, BLKADDR_NDC0, NDC_AF_BLK_RST);
-	rvu_block_reset(rvu, BLKADDR_NDC1, NDC_AF_BLK_RST);
-	rvu_block_reset(rvu, BLKADDR_NDC2, NDC_AF_BLK_RST);
+	rvu_block_reset(rvu, BLKADDR_NDC_NIX0_RX, NDC_AF_BLK_RST);
+	rvu_block_reset(rvu, BLKADDR_NDC_NIX0_TX, NDC_AF_BLK_RST);
+	rvu_block_reset(rvu, BLKADDR_NDC_NPA0, NDC_AF_BLK_RST);
 }
 
 static void rvu_scan_block(struct rvu *rvu, struct rvu_block *block)
@@ -877,8 +898,8 @@ int rvu_aq_alloc(struct rvu *rvu, struct admin_queue **ad_queue,
 	return 0;
 }
 
-static int rvu_mbox_handler_ready(struct rvu *rvu, struct msg_req *req,
-				  struct ready_msg_rsp *rsp)
+int rvu_mbox_handler_ready(struct rvu *rvu, struct msg_req *req,
+			   struct ready_msg_rsp *rsp)
 {
 	return 0;
 }
@@ -1023,9 +1044,9 @@ static int rvu_detach_rsrcs(struct rvu *rvu, struct rsrc_detach *detach,
 	return 0;
 }
 
-static int rvu_mbox_handler_detach_resources(struct rvu *rvu,
-					     struct rsrc_detach *detach,
-					     struct msg_rsp *rsp)
+int rvu_mbox_handler_detach_resources(struct rvu *rvu,
+				      struct rsrc_detach *detach,
+				      struct msg_rsp *rsp)
 {
 	return rvu_detach_rsrcs(rvu, detach, detach->hdr.pcifunc);
 }
@@ -1171,9 +1192,9 @@ static int rvu_check_rsrc_availability(struct rvu *rvu,
 	return -ENOSPC;
 }
 
-static int rvu_mbox_handler_attach_resources(struct rvu *rvu,
-					     struct rsrc_attach *attach,
-					     struct msg_rsp *rsp)
+int rvu_mbox_handler_attach_resources(struct rvu *rvu,
+				      struct rsrc_attach *attach,
+				      struct msg_rsp *rsp)
 {
 	u16 pcifunc = attach->hdr.pcifunc;
 	int err;
@@ -1294,8 +1315,8 @@ static void rvu_clear_msix_offset(struct rvu *rvu, struct rvu_pfvf *pfvf,
 	rvu_free_rsrc_contig(&pfvf->msix, nvecs, offset);
 }
 
-static int rvu_mbox_handler_msix_offset(struct rvu *rvu, struct msg_req *req,
-					struct msix_offset_rsp *rsp)
+int rvu_mbox_handler_msix_offset(struct rvu *rvu, struct msg_req *req,
+				 struct msix_offset_rsp *rsp)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
 	u16 pcifunc = req->hdr.pcifunc;
@@ -1343,8 +1364,8 @@ static int rvu_mbox_handler_msix_offset(struct rvu *rvu, struct msg_req *req,
 	return 0;
 }
 
-static int rvu_mbox_handler_vf_flr(struct rvu *rvu, struct msg_req *req,
-				   struct msg_rsp *rsp)
+int rvu_mbox_handler_vf_flr(struct rvu *rvu, struct msg_req *req,
+			    struct msg_rsp *rsp)
 {
 	u16 pcifunc = req->hdr.pcifunc;
 	u16 vf, numvfs;
@@ -1363,6 +1384,17 @@ static int rvu_mbox_handler_vf_flr(struct rvu *rvu, struct msg_req *req,
 	return 0;
 }
 
+int rvu_mbox_handler_get_hw_cap(struct rvu *rvu, struct msg_req *req,
+				struct get_hw_cap_rsp *rsp)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+
+	rsp->nix_fixed_txschq_mapping = hw->cap.nix_fixed_txschq_mapping;
+	rsp->nix_shaping = hw->cap.nix_shaping;
+
+	return 0;
+}
+
 static int rvu_process_mbox_msg(struct otx2_mbox *mbox, int devid,
 				struct mbox_msghdr *req)
 {
@@ -1440,12 +1472,12 @@ static void __rvu_mbox_handler(struct rvu_work *mwork, int type)
 
 	/* Process received mbox messages */
 	req_hdr = mdev->mbase + mbox->rx_start;
-	if (req_hdr->num_msgs == 0)
+	if (mw->mbox_wrk[devid].num_msgs == 0)
 		return;
 
 	offset = mbox->rx_start + ALIGN(sizeof(*req_hdr), MBOX_MSG_ALIGN);
 
-	for (id = 0; id < req_hdr->num_msgs; id++) {
+	for (id = 0; id < mw->mbox_wrk[devid].num_msgs; id++) {
 		msg = mdev->mbase + offset;
 
 		/* Set which PF/VF sent this message based on mbox IRQ */
@@ -1471,13 +1503,14 @@ static void __rvu_mbox_handler(struct rvu_work *mwork, int type)
 		if (msg->pcifunc & RVU_PFVF_FUNC_MASK)
 			dev_warn(rvu->dev, "Error %d when processing message %s (0x%x) from PF%d:VF%d\n",
 				 err, otx2_mbox_id2name(msg->id),
-				 msg->id, devid,
+				 msg->id, rvu_get_pf(msg->pcifunc),
 				 (msg->pcifunc & RVU_PFVF_FUNC_MASK) - 1);
 		else
 			dev_warn(rvu->dev, "Error %d when processing message %s (0x%x) from PF%d\n",
 				 err, otx2_mbox_id2name(msg->id),
 				 msg->id, devid);
 	}
+	mw->mbox_wrk[devid].num_msgs = 0;
 
 	/* Send mbox responses to VF/PF */
 	otx2_mbox_msg_send(mbox, devid);
@@ -1523,14 +1556,14 @@ static void __rvu_mbox_up_handler(struct rvu_work *mwork, int type)
 	mdev = &mbox->dev[devid];
 
 	rsp_hdr = mdev->mbase + mbox->rx_start;
-	if (rsp_hdr->num_msgs == 0) {
+	if (mw->mbox_wrk_up[devid].up_num_msgs == 0) {
 		dev_warn(rvu->dev, "mbox up handler: num_msgs = 0\n");
 		return;
 	}
 
 	offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN);
 
-	for (id = 0; id < rsp_hdr->num_msgs; id++) {
+	for (id = 0; id < mw->mbox_wrk_up[devid].up_num_msgs; id++) {
 		msg = mdev->mbase + offset;
 
 		if (msg->id >= MBOX_MSG_MAX) {
@@ -1560,6 +1593,7 @@ static void __rvu_mbox_up_handler(struct rvu_work *mwork, int type)
 		offset = mbox->rx_start + msg->next_msgoff;
 		mdev->msgs_acked++;
 	}
+	mw->mbox_wrk_up[devid].up_num_msgs = 0;
 
 	otx2_mbox_reset(mbox, devid);
 }
@@ -1697,14 +1731,28 @@ static void rvu_queue_work(struct mbox_wq_info *mw, int first,
 		mbox = &mw->mbox;
 		mdev = &mbox->dev[i];
 		hdr = mdev->mbase + mbox->rx_start;
-		if (hdr->num_msgs)
-			queue_work(mw->mbox_wq, &mw->mbox_wrk[i].work);
 
+		/*The hdr->num_msgs is set to zero immediately in the interrupt
+		 * handler to  ensure that it holds a correct value next time
+		 * when the interrupt handler is called.
+		 * pf->mbox.num_msgs holds the data for use in pfaf_mbox_handler
+		 * pf>mbox.up_num_msgs holds the data for use in
+		 * pfaf_mbox_up_handler.
+		 */
+
+		if (hdr->num_msgs) {
+			mw->mbox_wrk[i].num_msgs = hdr->num_msgs;
+			hdr->num_msgs = 0;
+			queue_work(mw->mbox_wq, &mw->mbox_wrk[i].work);
+		}
 		mbox = &mw->mbox_up;
 		mdev = &mbox->dev[i];
 		hdr = mdev->mbase + mbox->rx_start;
-		if (hdr->num_msgs)
+		if (hdr->num_msgs) {
+			mw->mbox_wrk_up[i].up_num_msgs = hdr->num_msgs;
+			hdr->num_msgs = 0;
 			queue_work(mw->mbox_wq, &mw->mbox_wrk_up[i].work);
+		}
 	}
 }
 
@@ -2316,18 +2364,6 @@ static int rvu_enable_sriov(struct rvu *rvu)
 	if (vfs > chans)
 		vfs = chans;
 
-	/* AF's VFs work in pairs and talk over consecutive loopback channels.
-	 * Thus we want to enable maximum even number of VFs. In case
-	 * odd number of VFs are available then the last VF on the list
-	 * remains disabled.
-	 */
-	if (vfs & 0x1) {
-		dev_warn(&pdev->dev,
-			 "Number of VFs should be even. Enabling %d out of %d.\n",
-			 vfs - 1, vfs);
-		vfs--;
-	}
-
 	if (!vfs)
 		return 0;
 
@@ -2432,6 +2468,8 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	rvu_reset_all_blocks(rvu);
 
+	rvu_setup_hw_capabilities(rvu);
+
 	err = rvu_setup_hw_resources(rvu);
 	if (err)
 		goto err_release_regions;
@@ -2456,6 +2494,9 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_irq;
 
+	/* Initialize debugfs */
+	rvu_dbg_init(rvu);
+
 	return 0;
 err_irq:
 	rvu_unregister_interrupts(rvu);
@@ -2482,6 +2523,7 @@ static void rvu_remove(struct pci_dev *pdev)
 {
 	struct rvu *rvu = pci_get_drvdata(pdev);
 
+	rvu_dbg_exit(rvu);
 	rvu_unregister_interrupts(rvu);
 	rvu_flr_wq_destroy(rvu);
 	rvu_cgx_exit(rvu);

drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c

@@ -14,6 +14,7 @@
 
 #include "rvu.h"
 #include "cgx.h"
+#include "rvu_reg.h"
 
 struct cgx_evq_entry {
 	struct list_head evq_node;
@@ -40,12 +41,25 @@ MBOX_UP_CGX_MESSAGES
 #undef M
 
 /* Returns bitmap of mapped PFs */
-static inline u16 cgxlmac_to_pfmap(struct rvu *rvu, u8 cgx_id, u8 lmac_id)
+static u16 cgxlmac_to_pfmap(struct rvu *rvu, u8 cgx_id, u8 lmac_id)
 {
 	return rvu->cgxlmac2pf_map[CGX_OFFSET(cgx_id) + lmac_id];
 }
 
-static inline u8 cgxlmac_id_to_bmap(u8 cgx_id, u8 lmac_id)
+static int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id)
+{
+	unsigned long pfmap;
+
+	pfmap = cgxlmac_to_pfmap(rvu, cgx_id, lmac_id);
+
+	/* Assumes only one pf mapped to a cgx lmac port */
+	if (!pfmap)
+		return -ENODEV;
+	else
+		return find_first_bit(&pfmap, 16);
+}
+
+static u8 cgxlmac_id_to_bmap(u8 cgx_id, u8 lmac_id)
 {
 	return ((cgx_id & 0xF) << 4) | (lmac_id & 0xF);
 }
@@ -294,6 +308,8 @@ int rvu_cgx_init(struct rvu *rvu)
 	if (err)
 		return err;
 
+	mutex_init(&rvu->cgx_cfg_lock);
+
 	/* Ensure event handler registration is completed, before
 	 * we turn on the links
 	 */
@@ -334,6 +350,24 @@ int rvu_cgx_exit(struct rvu *rvu)
 	return 0;
 }
 
+void rvu_cgx_enadis_rx_bp(struct rvu *rvu, int pf, bool enable)
+{
+	u8 cgx_id, lmac_id;
+	void *cgxd;
+
+	if (!is_pf_cgxmapped(rvu, pf))
+		return;
+
+	rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
+	cgxd = rvu_cgx_pdata(cgx_id, rvu);
+
+	/* Set / clear CTL_BCK to control pause frame forwarding to NIX */
+	if (enable)
+		cgx_lmac_enadis_rx_pause_fwding(cgxd, lmac_id, true);
+	else
+		cgx_lmac_enadis_rx_pause_fwding(cgxd, lmac_id, false);
+}
+
 int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start)
 {
 	int pf = rvu_get_pf(pcifunc);
@@ -562,3 +596,94 @@ int rvu_mbox_handler_cgx_intlbk_disable(struct rvu *rvu, struct msg_req *req,
 	rvu_cgx_config_intlbk(rvu, req->hdr.pcifunc, false);
 	return 0;
 }
+
+/* Finds cumulative status of NIX rx/tx counters from LF of a PF and those
+ * from its VFs as well. ie. NIX rx/tx counters at the CGX port level
+ */
+int rvu_cgx_nix_cuml_stats(struct rvu *rvu, void *cgxd, int lmac_id,
+			   int index, int rxtxflag, u64 *stat)
+{
+	struct rvu_block *block;
+	int blkaddr;
+	u16 pcifunc;
+	int pf, lf;
+
+	if (!cgxd || !rvu)
+		return -EINVAL;
+
+	pf = cgxlmac_to_pf(rvu, cgx_get_cgxid(cgxd), lmac_id);
+	if (pf < 0)
+		return pf;
+
+	/* Assumes LF of a PF and all of its VF belongs to the same
+	 * NIX block
+	 */
+	pcifunc = pf << RVU_PFVF_PF_SHIFT;
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (blkaddr < 0)
+		return 0;
+	block = &rvu->hw->block[blkaddr];
+
+	*stat = 0;
+	for (lf = 0; lf < block->lf.max; lf++) {
+		/* Check if a lf is attached to this PF or one of its VFs */
+		if (!((block->fn_map[lf] & ~RVU_PFVF_FUNC_MASK) == (pcifunc &
+			 ~RVU_PFVF_FUNC_MASK)))
+			continue;
+		if (rxtxflag == NIX_STATS_RX)
+			*stat += rvu_read64(rvu, blkaddr,
+					    NIX_AF_LFX_RX_STATX(lf, index));
+		else
+			*stat += rvu_read64(rvu, blkaddr,
+					    NIX_AF_LFX_TX_STATX(lf, index));
+	}
+
+	return 0;
+}
+
+int rvu_cgx_start_stop_io(struct rvu *rvu, u16 pcifunc, bool start)
+{
+	struct rvu_pfvf *parent_pf, *pfvf;
+	int cgx_users, err = 0;
+
+	if (!is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc)))
+		return 0;
+
+	parent_pf = &rvu->pf[rvu_get_pf(pcifunc)];
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+
+	mutex_lock(&rvu->cgx_cfg_lock);
+
+	if (start && pfvf->cgx_in_use)
+		goto exit;  /* CGX is already started hence nothing to do */
+	if (!start && !pfvf->cgx_in_use)
+		goto exit; /* CGX is already stopped hence nothing to do */
+
+	if (start) {
+		cgx_users = parent_pf->cgx_users;
+		parent_pf->cgx_users++;
+	} else {
+		parent_pf->cgx_users--;
+		cgx_users = parent_pf->cgx_users;
+	}
+
+	/* Start CGX when first of all NIXLFs is started.
+	 * Stop CGX when last of all NIXLFs is stopped.
+	 */
+	if (!cgx_users) {
+		err = rvu_cgx_config_rxtx(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK,
+					  start);
+		if (err) {
+			dev_err(rvu->dev, "Unable to %s CGX\n",
+				start ? "start" : "stop");
+			/* Revert the usage count in case of error */
+			parent_pf->cgx_users = start ? parent_pf->cgx_users  - 1
+					       : parent_pf->cgx_users  + 1;
+			goto exit;
+		}
+	}
+	pfvf->cgx_in_use = start;
+exit:
+	mutex_unlock(&rvu->cgx_cfg_lock);
+	return err;
+}

drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c

@@ -52,8 +52,8 @@ static int npa_aq_enqueue_wait(struct rvu *rvu, struct rvu_block *block,
 	return 0;
 }
 
-static int rvu_npa_aq_enq_inst(struct rvu *rvu, struct npa_aq_enq_req *req,
-			       struct npa_aq_enq_rsp *rsp)
+int rvu_npa_aq_enq_inst(struct rvu *rvu, struct npa_aq_enq_req *req,
+			struct npa_aq_enq_rsp *rsp)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
 	u16 pcifunc = req->hdr.pcifunc;
@@ -241,12 +241,50 @@ static int npa_lf_hwctx_disable(struct rvu *rvu, struct hwctx_disable_req *req)
 	return err;
 }
 
+#ifdef CONFIG_NDC_DIS_DYNAMIC_CACHING
+static int npa_lf_hwctx_lockdown(struct rvu *rvu, struct npa_aq_enq_req *req)
+{
+	struct npa_aq_enq_req lock_ctx_req;
+	int err;
+
+	if (req->op != NPA_AQ_INSTOP_INIT)
+		return 0;
+
+	memset(&lock_ctx_req, 0, sizeof(struct npa_aq_enq_req));
+	lock_ctx_req.hdr.pcifunc = req->hdr.pcifunc;
+	lock_ctx_req.ctype = req->ctype;
+	lock_ctx_req.op = NPA_AQ_INSTOP_LOCK;
+	lock_ctx_req.aura_id = req->aura_id;
+	err = rvu_npa_aq_enq_inst(rvu, &lock_ctx_req, NULL);
+	if (err)
+		dev_err(rvu->dev,
+			"PFUNC 0x%x: Failed to lock NPA context %s:%d\n",
+			req->hdr.pcifunc,
+			(req->ctype == NPA_AQ_CTYPE_AURA) ?
+			"Aura" : "Pool", req->aura_id);
+	return err;
+}
+
+int rvu_mbox_handler_npa_aq_enq(struct rvu *rvu,
+				struct npa_aq_enq_req *req,
+				struct npa_aq_enq_rsp *rsp)
+{
+	int err;
+
+	err = rvu_npa_aq_enq_inst(rvu, req, rsp);
+	if (!err)
+		err = npa_lf_hwctx_lockdown(rvu, req);
+	return err;
+}
+#else
+
 int rvu_mbox_handler_npa_aq_enq(struct rvu *rvu,
 				struct npa_aq_enq_req *req,
 				struct npa_aq_enq_rsp *rsp)
 {
 	return rvu_npa_aq_enq_inst(rvu, req, rsp);
 }
+#endif
 
 int rvu_mbox_handler_npa_hwctx_disable(struct rvu *rvu,
 				       struct hwctx_disable_req *req,
@@ -289,6 +327,9 @@ int rvu_mbox_handler_npa_lf_alloc(struct rvu *rvu,
 	    req->aura_sz == NPA_AURA_SZ_0 || !req->nr_pools)
 		return NPA_AF_ERR_PARAM;
 
+	if (req->way_mask)
+		req->way_mask &= 0xFFFF;
+
 	pfvf = rvu_get_pfvf(rvu, pcifunc);
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPA, pcifunc);
 	if (!pfvf->npalf || blkaddr < 0)
@@ -345,7 +386,8 @@ int rvu_mbox_handler_npa_lf_alloc(struct rvu *rvu,
 	/* Clear way partition mask and set aura offset to '0' */
 	cfg &= ~(BIT_ULL(34) - 1);
 	/* Set aura size & enable caching of contexts */
-	cfg |= (req->aura_sz << 16) | BIT_ULL(34);
+	cfg |= (req->aura_sz << 16) | BIT_ULL(34) | req->way_mask;
+
 	rvu_write64(rvu, blkaddr, NPA_AF_LFX_AURAS_CFG(npalf), cfg);
 
 	/* Configure aura HW context's base */
@@ -353,7 +395,8 @@ int rvu_mbox_handler_npa_lf_alloc(struct rvu *rvu,
 		    (u64)pfvf->aura_ctx->iova);
 
 	/* Enable caching of qints hw context */
-	rvu_write64(rvu, blkaddr, NPA_AF_LFX_QINTS_CFG(npalf), BIT_ULL(36));
+	rvu_write64(rvu, blkaddr, NPA_AF_LFX_QINTS_CFG(npalf),
+		    BIT_ULL(36) | req->way_mask << 20);
 	rvu_write64(rvu, blkaddr, NPA_AF_LFX_QINTS_BASE(npalf),
 		    (u64)pfvf->npa_qints_ctx->iova);
 
@@ -422,6 +465,10 @@ static int npa_aq_init(struct rvu *rvu, struct rvu_block *block)
 	/* Do not bypass NDC cache */
 	cfg = rvu_read64(rvu, block->addr, NPA_AF_NDC_CFG);
 	cfg &= ~0x03DULL;
+#ifdef CONFIG_NDC_DIS_DYNAMIC_CACHING
+	/* Disable caching of stack pages */
+	cfg |= 0x10ULL;
+#endif
 	rvu_write64(rvu, block->addr, NPA_AF_NDC_CFG, cfg);
 
 	/* Result structure can be followed by Aura/Pool context at

drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c

@@ -120,6 +120,31 @@ static void npc_enable_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
 	}
 }
 
+static void npc_clear_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
+				 int blkaddr, int index)
+{
+	int bank = npc_get_bank(mcam, index);
+	int actbank = bank;
+
+	index &= (mcam->banksize - 1);
+	for (; bank < (actbank + mcam->banks_per_entry); bank++) {
+		rvu_write64(rvu, blkaddr,
+			    NPC_AF_MCAMEX_BANKX_CAMX_INTF(index, bank, 1), 0);
+		rvu_write64(rvu, blkaddr,
+			    NPC_AF_MCAMEX_BANKX_CAMX_INTF(index, bank, 0), 0);
+
+		rvu_write64(rvu, blkaddr,
+			    NPC_AF_MCAMEX_BANKX_CAMX_W0(index, bank, 1), 0);
+		rvu_write64(rvu, blkaddr,
+			    NPC_AF_MCAMEX_BANKX_CAMX_W0(index, bank, 0), 0);
+
+		rvu_write64(rvu, blkaddr,
+			    NPC_AF_MCAMEX_BANKX_CAMX_W1(index, bank, 1), 0);
+		rvu_write64(rvu, blkaddr,
+			    NPC_AF_MCAMEX_BANKX_CAMX_W1(index, bank, 0), 0);
+	}
+}
+
 static void npc_get_keyword(struct mcam_entry *entry, int idx,
 			    u64 *cam0, u64 *cam1)
 {
@@ -211,6 +236,12 @@ static void npc_config_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
 	actindex = index;
 	index &= (mcam->banksize - 1);
 
+	/* Disable before mcam entry update */
+	npc_enable_mcam_entry(rvu, mcam, blkaddr, actindex, false);
+
+	/* Clear mcam entry to avoid writes being suppressed by NPC */
+	npc_clear_mcam_entry(rvu, mcam, blkaddr, actindex);
+
 	/* CAM1 takes the comparison value and
 	 * CAM0 specifies match for a bit in key being '0' or '1' or 'dontcare'.
 	 * CAM1<n> = 0 & CAM0<n> = 1 => match if key<n> = 0
@@ -251,8 +282,6 @@ static void npc_config_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
 	/* Enable the entry */
 	if (enable)
 		npc_enable_mcam_entry(rvu, mcam, blkaddr, actindex, true);
-	else
-		npc_enable_mcam_entry(rvu, mcam, blkaddr, actindex, false);
 }
 
 static void npc_copy_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
@@ -354,8 +383,8 @@ void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc,
 			      NIX_INTF_RX, &entry, true);
 
 	/* add VLAN matching, setup action and save entry back for later */
-	entry.kw[0] |= (NPC_LT_LB_STAG | NPC_LT_LB_CTAG) << 20;
-	entry.kw_mask[0] |= (NPC_LT_LB_STAG & NPC_LT_LB_CTAG) << 20;
+	entry.kw[0] |= (NPC_LT_LB_STAG_QINQ | NPC_LT_LB_CTAG) << 20;
+	entry.kw_mask[0] |= (NPC_LT_LB_STAG_QINQ & NPC_LT_LB_CTAG) << 20;
 
 	entry.vtag_action = VTAG0_VALID_BIT |
 			    FIELD_PREP(VTAG0_TYPE_MASK, 0) |
@@ -448,68 +477,75 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	struct mcam_entry entry = { {0} };
+	struct rvu_hwinfo *hw = rvu->hw;
 	struct nix_rx_action action;
-#ifdef MCAST_MCE
 	struct rvu_pfvf *pfvf;
-#endif
 	int blkaddr, index;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
 	if (blkaddr < 0)
 		return;
 
-	/* Only PF can add a bcast match entry */
-	if (pcifunc & RVU_PFVF_FUNC_MASK)
+	/* Skip LBK VFs */
+	if (is_afvf(pcifunc))
 		return;
-#ifdef MCAST_MCE
-	pfvf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK);
-#endif
 
+	/* If pkt replication is not supported,
+	 * then only PF is allowed to add a bcast match entry.
+	 */
+	if (!hw->cap.nix_rx_multicast && pcifunc & RVU_PFVF_FUNC_MASK)
+		return;
+
+	/* Get 'pcifunc' of PF device */
+	pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK;
 	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
 					 nixlf, NIXLF_BCAST_ENTRY);
 
-	/* Check for L2B bit and LMAC channel
-	 * NOTE: Since MKEX default profile(a reduced version intended to
-	 * accommodate more capability but igoring few bits) a stap-gap
-	 * approach.
-	 * Since we care for L2B which by HRM NPC_PARSE_KEX_S at BIT_POS[25], So
-	 * moved to BIT_POS[13], ignoring ERRCODE, ERRLEV as we'll loose out
-	 * on capability features needed for CoS (/from ODP PoV) e.g: VLAN,
-	 * DSCP.
-	 *
-	 * Reduced layout of MKEX default profile -
-	 * Includes following are (i.e.CHAN, L2/3{B/M}, LA, LB, LC, LD):
-	 *
-	 * BIT_POS[31:28] : LD
-	 * BIT_POS[27:24] : LC
-	 * BIT_POS[23:20] : LB
-	 * BIT_POS[19:16] : LA
-	 * BIT_POS[15:12] : L3B, L3M, L2B, L2M
-	 * BIT_POS[11:00] : CHAN
-	 *
+	/* Match ingress channel */
+	entry.kw[0] = chan;
+	entry.kw_mask[0] = 0xfffull;
+
+	/* Match broadcast MAC address.
+	 * DMAC is extracted at 0th bit of PARSE_KEX::KW1
 	 */
-	entry.kw[0] = BIT_ULL(13) | chan;
-	entry.kw_mask[0] = BIT_ULL(13) | 0xFFFULL;
+	entry.kw[1] = 0xffffffffffffull;
+	entry.kw_mask[1] = 0xffffffffffffull;
 
 	*(u64 *)&action = 0x00;
-#ifdef MCAST_MCE
-	/* Early silicon doesn't support pkt replication,
-	 * so install entry with UCAST action, so that PF
-	 * receives all broadcast packets.
-	 */
-	action.op = NIX_RX_ACTIONOP_MCAST;
-	action.pf_func = pcifunc;
-	action.index = pfvf->bcast_mce_idx;
-#else
-	action.op = NIX_RX_ACTIONOP_UCAST;
-	action.pf_func = pcifunc;
-#endif
+	if (!hw->cap.nix_rx_multicast) {
+		/* Early silicon doesn't support pkt replication,
+		 * so install entry with UCAST action, so that PF
+		 * receives all broadcast packets.
+		 */
+		action.op = NIX_RX_ACTIONOP_UCAST;
+		action.pf_func = pcifunc;
+	} else {
+		pfvf = rvu_get_pfvf(rvu, pcifunc);
+		action.index = pfvf->bcast_mce_idx;
+		action.op = NIX_RX_ACTIONOP_MCAST;
+	}
 
 	entry.action = *(u64 *)&action;
 	npc_config_mcam_entry(rvu, mcam, blkaddr, index,
 			      NIX_INTF_RX, &entry, true);
 }
 
+void rvu_npc_disable_bcast_entry(struct rvu *rvu, u16 pcifunc)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	int blkaddr, index;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return;
+
+	/* Get 'pcifunc' of PF device */
+	pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK;
+
+	index = npc_get_nixlf_mcam_index(mcam, pcifunc, 0, NIXLF_BCAST_ENTRY);
+	npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false);
+}
+
 void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
 				    int group, int alg_idx, int mcam_index)
 {
@@ -704,8 +740,7 @@ static void npc_config_ldata_extract(struct rvu *rvu, int blkaddr)
 	/* Layer B: Stacked VLAN (STAG|QinQ) */
 	/* CTAG VLAN[2..3] + Ethertype, 4 bytes, KW0[63:32] */
 	cfg = KEX_LD_CFG(0x03, 0x4, 0x1, 0x0, 0x4);
-	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LB, NPC_LT_LB_STAG, 0, cfg);
-	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LB, NPC_LT_LB_QINQ, 0, cfg);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, 0, cfg);
 
 	/* Layer C: IPv4 */
 	/* SIP+DIP: 8 bytes, KW2[63:0] */
@@ -806,11 +841,11 @@ static void npc_load_mkex_profile(struct rvu *rvu, int blkaddr)
 		/* Compare with mkex mod_param name string */
 		if (mcam_kex->mkex_sign == MKEX_SIGN &&
 		    !strncmp(mcam_kex->name, mkex_profile, MKEX_NAME_LEN)) {
-			/* Due to an errata (35786) in A0 pass silicon,
+			/* Due to an errata (35786) in A0/B0 pass silicon,
 			 * parse nibble enable configuration has to be
 			 * identical for both Rx and Tx interfaces.
 			 */
-			if (is_rvu_9xxx_A0(rvu) &&
+			if (is_rvu_96xx_B0(rvu) &&
 			    mcam_kex->keyx_cfg[NIX_INTF_RX] !=
 			    mcam_kex->keyx_cfg[NIX_INTF_TX])
 				goto load_default;
@@ -1064,6 +1099,13 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 	mcam->hprio_count = mcam->lprio_count;
 	mcam->hprio_end = mcam->hprio_count;
 
+	/* Reserve last counter for MCAM RX miss action which is set to
+	 * drop pkt. This way we will know how many pkts didn't match
+	 * any MCAM entry.
+	 */
+	mcam->counters.max--;
+	mcam->rx_miss_act_cntr = mcam->counters.max;
+
 	/* Allocate bitmap for managing MCAM counters and memory
 	 * for saving counter to RVU PFFUNC allocation mapping.
 	 */
@@ -1101,6 +1143,7 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 int rvu_npc_init(struct rvu *rvu)
 {
 	struct npc_pkind *pkind = &rvu->hw->pkind;
+	struct npc_mcam *mcam = &rvu->hw->mcam;
 	u64 keyz = NPC_MCAM_KEY_X2;
 	int blkaddr, entry, bank, err;
 	u64 cfg, nibble_ena;
@@ -1143,7 +1186,7 @@ int rvu_npc_init(struct rvu *rvu)
 
 	/* Config Inner IPV4 NPC layer info */
 	rvu_write64(rvu, blkaddr, NPC_AF_PCK_DEF_IIP4,
-		    (NPC_LID_LF << 8) | (NPC_LT_LF_TU_IP << 4) | 0x0F);
+		    (NPC_LID_LG << 8) | (NPC_LT_LG_TU_IP << 4) | 0x0F);
 
 	/* Enable below for Rx pkts.
 	 * - Outer IPv4 header checksum validation.
@@ -1165,7 +1208,7 @@ int rvu_npc_init(struct rvu *rvu)
 	/* Due to an errata (35786) in A0 pass silicon, parse nibble enable
 	 * configuration has to be identical for both Rx and Tx interfaces.
 	 */
-	if (!is_rvu_9xxx_A0(rvu))
+	if (!is_rvu_96xx_B0(rvu))
 		nibble_ena = (1ULL << 19) - 1;
 	rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_TX),
 			((keyz & 0x3) << 32) | nibble_ena);
@@ -1183,9 +1226,13 @@ int rvu_npc_init(struct rvu *rvu)
 	rvu_write64(rvu, blkaddr, NPC_AF_INTFX_MISS_ACT(NIX_INTF_TX),
 		    NIX_TX_ACTIONOP_UCAST_DEFAULT);
 
-	/* If MCAM lookup doesn't result in a match, drop the received packet */
+	/* If MCAM lookup doesn't result in a match, drop the received packet.
+	 * And map this action to a counter to count dropped pkts.
+	 */
 	rvu_write64(rvu, blkaddr, NPC_AF_INTFX_MISS_ACT(NIX_INTF_RX),
 		    NIX_RX_ACTIONOP_DROP);
+	rvu_write64(rvu, blkaddr, NPC_AF_INTFX_MISS_STAT_ACT(NIX_INTF_RX),
+		    BIT_ULL(9) | mcam->rx_miss_act_cntr);
 
 	return 0;
 }
@@ -1200,6 +1247,44 @@ void rvu_npc_freemem(struct rvu *rvu)
 	mutex_destroy(&mcam->lock);
 }
 
+void rvu_npc_get_mcam_entry_alloc_info(struct rvu *rvu, u16 pcifunc,
+				       int blkaddr, int *alloc_cnt,
+				       int *enable_cnt)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	int entry;
+
+	*alloc_cnt = 0;
+	*enable_cnt = 0;
+
+	for (entry = 0; entry < mcam->bmap_entries; entry++) {
+		if (mcam->entry2pfvf_map[entry] == pcifunc) {
+			(*alloc_cnt)++;
+			if (is_mcam_entry_enabled(rvu, mcam, blkaddr, entry))
+				(*enable_cnt)++;
+		}
+	}
+}
+
+void rvu_npc_get_mcam_counter_alloc_info(struct rvu *rvu, u16 pcifunc,
+					 int blkaddr, int *alloc_cnt,
+					 int *enable_cnt)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	int cntr;
+
+	*alloc_cnt = 0;
+	*enable_cnt = 0;
+
+	for (cntr = 0; cntr < mcam->counters.max; cntr++) {
+		if (mcam->cntr2pfvf_map[cntr] == pcifunc) {
+			(*alloc_cnt)++;
+			if (mcam->cntr_refcnt[cntr])
+				(*enable_cnt)++;
+		}
+	}
+}
+
 static int npc_mcam_verify_entry(struct npc_mcam *mcam,
 				 u16 pcifunc, int entry)
 {

drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h

@@ -246,6 +246,7 @@
 
 #define NIX_AF_DEBUG_NPC_RESP_DATAX(a)          (0x680 | (a) << 3)
 #define NIX_AF_SMQX_CFG(a)                      (0x700 | (a) << 16)
+#define NIX_AF_SQM_DBG_CTL_STATUS               (0x750)
 #define NIX_AF_PSE_CHANNEL_LEVEL                (0x800)
 #define NIX_AF_PSE_SHAPER_CFG                   (0x810)
 #define NIX_AF_TX_EXPR_CREDIT			(0x830)
@@ -435,7 +436,6 @@
 #define CPT_AF_LF_RST			(0x44000)
 #define CPT_AF_BLK_RST			(0x46000)
 
-#define NDC_AF_BLK_RST                  (0x002F0)
 #define NPC_AF_BLK_RST                  (0x00040)
 
 /* NPC */
@@ -499,4 +499,30 @@
 #define NPC_AF_DBG_DATAX(a)		(0x3001400 | (a) << 4)
 #define NPC_AF_DBG_RESULTX(a)		(0x3001800 | (a) << 4)
 
+/* NDC */
+#define NDC_AF_CONST			(0x00000)
+#define NDC_AF_CLK_EN			(0x00020)
+#define NDC_AF_CTL			(0x00030)
+#define NDC_AF_BANK_CTL			(0x00040)
+#define NDC_AF_BANK_CTL_DONE		(0x00048)
+#define NDC_AF_INTR			(0x00058)
+#define NDC_AF_INTR_W1S			(0x00060)
+#define NDC_AF_INTR_ENA_W1S		(0x00068)
+#define NDC_AF_INTR_ENA_W1C		(0x00070)
+#define NDC_AF_ACTIVE_PC		(0x00078)
+#define NDC_AF_BP_TEST_ENABLE		(0x001F8)
+#define NDC_AF_BP_TEST(a)		(0x00200 | (a) << 3)
+#define NDC_AF_BLK_RST			(0x002F0)
+#define NDC_PRIV_AF_INT_CFG		(0x002F8)
+#define NDC_AF_HASHX(a)			(0x00300 | (a) << 3)
+#define NDC_AF_PORTX_RTX_RWX_REQ_PC(a, b, c) \
+		(0x00C00 | (a) << 5 | (b) << 4 | (c) << 3)
+#define NDC_AF_PORTX_RTX_RWX_OSTDN_PC(a, b, c) \
+		(0x00D00 | (a) << 5 | (b) << 4 | (c) << 3)
+#define NDC_AF_PORTX_RTX_RWX_LAT_PC(a, b, c) \
+		(0x00E00 | (a) << 5 | (b) << 4 | (c) << 3)
+#define NDC_AF_PORTX_RTX_CANT_ALLOC_PC(a, b) \
+		(0x00F00 | (a) << 5 | (b) << 4)
+#define NDC_AF_BANKX_HIT_PC(a)		(0x01000 | (a) << 3)
+#define NDC_AF_BANKX_MISS_PC(a)		(0x01100 | (a) << 3)
 #endif /* RVU_REG_H */

drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h

@@ -13,22 +13,22 @@
 
 /* RVU Block Address Enumeration */
 enum rvu_block_addr_e {
-	BLKADDR_RVUM    = 0x0ULL,
-	BLKADDR_LMT     = 0x1ULL,
-	BLKADDR_MSIX    = 0x2ULL,
-	BLKADDR_NPA     = 0x3ULL,
-	BLKADDR_NIX0    = 0x4ULL,
-	BLKADDR_NIX1    = 0x5ULL,
-	BLKADDR_NPC     = 0x6ULL,
-	BLKADDR_SSO     = 0x7ULL,
-	BLKADDR_SSOW    = 0x8ULL,
-	BLKADDR_TIM     = 0x9ULL,
-	BLKADDR_CPT0    = 0xaULL,
-	BLKADDR_CPT1    = 0xbULL,
-	BLKADDR_NDC0    = 0xcULL,
-	BLKADDR_NDC1    = 0xdULL,
-	BLKADDR_NDC2    = 0xeULL,
-	BLK_COUNT	= 0xfULL,
+	BLKADDR_RVUM		= 0x0ULL,
+	BLKADDR_LMT		= 0x1ULL,
+	BLKADDR_MSIX		= 0x2ULL,
+	BLKADDR_NPA		= 0x3ULL,
+	BLKADDR_NIX0		= 0x4ULL,
+	BLKADDR_NIX1		= 0x5ULL,
+	BLKADDR_NPC		= 0x6ULL,
+	BLKADDR_SSO		= 0x7ULL,
+	BLKADDR_SSOW		= 0x8ULL,
+	BLKADDR_TIM		= 0x9ULL,
+	BLKADDR_CPT0		= 0xaULL,
+	BLKADDR_CPT1		= 0xbULL,
+	BLKADDR_NDC_NIX0_RX	= 0xcULL,
+	BLKADDR_NDC_NIX0_TX	= 0xdULL,
+	BLKADDR_NDC_NPA0	= 0xeULL,
+	BLK_COUNT		= 0xfULL,
 };
 
 /* RVU Block Type Enumeration */
@@ -474,9 +474,9 @@ struct nix_cq_ctx_s {
 	u64 ena			: 1;
 	u64 drop_ena		: 1;
 	u64 drop		: 8;
-	u64 dp			: 8;
+	u64 bp			: 8;
 #else
-	u64 dp			: 8;
+	u64 bp			: 8;
 	u64 drop		: 8;
 	u64 drop_ena		: 1;
 	u64 ena			: 1;