lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20230426054731.5720-4-hkelam@marvell.com>
Date:   Wed, 26 Apr 2023 11:17:26 +0530
From:   Hariprasad Kelam <hkelam@...vell.com>
To:     <netdev@...r.kernel.org>, <linux-kernel@...r.kernel.org>
CC:     <kuba@...nel.org>, <davem@...emloft.net>,
        <willemdebruijn.kernel@...il.com>, <andrew@...n.ch>,
        <sgoutham@...vell.com>, <lcherian@...vell.com>,
        <gakula@...vell.com>, <jerinj@...vell.com>, <sbhatta@...vell.com>,
        <hkelam@...vell.com>, <naveenm@...vell.com>, <edumazet@...gle.com>,
        <pabeni@...hat.com>, <jhs@...atatu.com>,
        <xiyou.wangcong@...il.com>, <jiri@...nulli.us>,
        <maxtram95@...il.com>, <corbet@....net>
Subject: [net-next Patch v10 3/8] octeontx2-pf: qos send queues management

From: Subbaraya Sundeep <sbhatta@...vell.com>

Current implementation is such that the number of Send queues (SQs)
are decided on the device probe which is equal to the number of online
cpus. These SQs are allocated and deallocated in interface open and c
lose calls respectively.

This patch defines new APIs for initializing and deinitializing Send
queues dynamically and allocates more number of transmit queues for
QOS feature.

Signed-off-by: Subbaraya Sundeep <sbhatta@...vell.com>
Signed-off-by: Hariprasad Kelam <hkelam@...vell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@...vell.com>
Reviewed-by: Simon Horman <simon.horman@...igine.com>
Reviewed-by: Jacob Keller <jacob.e.keller@...el.com>
---
 .../marvell/octeontx2/af/rvu_debugfs.c        |   5 +
 .../ethernet/marvell/octeontx2/nic/Makefile   |   2 +-
 .../marvell/octeontx2/nic/otx2_common.c       |  43 ++-
 .../marvell/octeontx2/nic/otx2_common.h       |  39 ++-
 .../ethernet/marvell/octeontx2/nic/otx2_pf.c  |  44 ++-
 .../marvell/octeontx2/nic/otx2_txrx.c         |  24 +-
 .../marvell/octeontx2/nic/otx2_txrx.h         |   3 +-
 .../ethernet/marvell/octeontx2/nic/otx2_vf.c  |   7 +-
 .../net/ethernet/marvell/octeontx2/nic/qos.h  |  19 ++
 .../ethernet/marvell/octeontx2/nic/qos_sq.c   | 282 ++++++++++++++++++
 10 files changed, 426 insertions(+), 42 deletions(-)
 create mode 100644 drivers/net/ethernet/marvell/octeontx2/nic/qos.h
 create mode 100644 drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index 26cfa501f1a1..66d3354e02b2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -1221,6 +1221,11 @@ static int rvu_dbg_npa_ctx_display(struct seq_file *m, void *unused, int ctype)
 
 	for (aura = id; aura < max_id; aura++) {
 		aq_req.aura_id = aura;
+
+		/* Skip if queue is uninitialized */
+		if (ctype == NPA_AQ_CTYPE_POOL && !test_bit(aura, pfvf->pool_bmap))
+			continue;
+
 		seq_printf(m, "======%s : %d=======\n",
 			   (ctype == NPA_AQ_CTYPE_AURA) ? "AURA" : "POOL",
 			aq_req.aura_id);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
index 73fdb8798614..3d31ddf7c652 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
@@ -8,7 +8,7 @@ obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o otx2_ptp.o
 
 rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \
                otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \
-               otx2_devlink.o
+               otx2_devlink.o qos_sq.o
 rvu_nicvf-y := otx2_vf.o otx2_devlink.o
 
 rvu_nicpf-$(CONFIG_DCB) += otx2_dcbnl.o
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 43bc56fb3c33..adbcc087d2a8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -513,8 +513,8 @@ void otx2_config_irq_coalescing(struct otx2_nic *pfvf, int qidx)
 		     (pfvf->hw.cq_ecount_wait - 1));
 }
 
-int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
-		      dma_addr_t *dma)
+static int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
+			     dma_addr_t *dma)
 {
 	u8 *buf;
 
@@ -532,8 +532,8 @@ int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
 	return 0;
 }
 
-static int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
-			   dma_addr_t *dma)
+int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
+		    dma_addr_t *dma)
 {
 	int ret;
 
@@ -758,11 +758,16 @@ int otx2_txschq_stop(struct otx2_nic *pfvf)
 void otx2_sqb_flush(struct otx2_nic *pfvf)
 {
 	int qidx, sqe_tail, sqe_head;
+	struct otx2_snd_queue *sq;
 	u64 incr, *ptr, val;
 	int timeout = 1000;
 
 	ptr = (u64 *)otx2_get_regaddr(pfvf, NIX_LF_SQ_OP_STATUS);
-	for (qidx = 0; qidx < pfvf->hw.non_qos_queues; qidx++) {
+	for (qidx = 0; qidx < otx2_get_total_tx_queues(pfvf); qidx++) {
+		sq = &pfvf->qset.sq[qidx];
+		if (!sq->sqb_ptrs)
+			continue;
+
 		incr = (u64)qidx << 32;
 		while (timeout) {
 			val = otx2_atomic64_add(incr, ptr);
@@ -862,7 +867,7 @@ int otx2_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura)
 	return otx2_sync_mbox_msg(&pfvf->mbox);
 }
 
-static int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura)
+int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura)
 {
 	struct otx2_qset *qset = &pfvf->qset;
 	struct otx2_snd_queue *sq;
@@ -935,9 +940,17 @@ static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx)
 		cq->cint_idx = qidx - pfvf->hw.rx_queues;
 		cq->cqe_cnt = qset->sqe_cnt;
 	} else {
-		cq->cq_type = CQ_XDP;
-		cq->cint_idx = qidx - non_xdp_queues;
-		cq->cqe_cnt = qset->sqe_cnt;
+		if (pfvf->hw.xdp_queues &&
+		    qidx < non_xdp_queues + pfvf->hw.xdp_queues) {
+			cq->cq_type = CQ_XDP;
+			cq->cint_idx = qidx - non_xdp_queues;
+			cq->cqe_cnt = qset->sqe_cnt;
+		} else {
+			cq->cq_type = CQ_QOS;
+			cq->cint_idx = qidx - non_xdp_queues -
+				       pfvf->hw.xdp_queues;
+			cq->cqe_cnt = qset->sqe_cnt;
+		}
 	}
 	cq->cqe_size = pfvf->qset.xqe_size;
 
@@ -1095,7 +1108,7 @@ int otx2_config_nix(struct otx2_nic *pfvf)
 
 	/* Set RQ/SQ/CQ counts */
 	nixlf->rq_cnt = pfvf->hw.rx_queues;
-	nixlf->sq_cnt = pfvf->hw.non_qos_queues;
+	nixlf->sq_cnt = otx2_get_total_tx_queues(pfvf);
 	nixlf->cq_cnt = pfvf->qset.cq_cnt;
 	nixlf->rss_sz = MAX_RSS_INDIR_TBL_SIZE;
 	nixlf->rss_grps = MAX_RSS_GROUPS;
@@ -1133,7 +1146,7 @@ void otx2_sq_free_sqbs(struct otx2_nic *pfvf)
 	int sqb, qidx;
 	u64 iova, pa;
 
-	for (qidx = 0; qidx < hw->non_qos_queues; qidx++) {
+	for (qidx = 0; qidx < otx2_get_total_tx_queues(pfvf); qidx++) {
 		sq = &qset->sq[qidx];
 		if (!sq->sqb_ptrs)
 			continue;
@@ -1201,8 +1214,8 @@ void otx2_aura_pool_free(struct otx2_nic *pfvf)
 	pfvf->qset.pool = NULL;
 }
 
-static int otx2_aura_init(struct otx2_nic *pfvf, int aura_id,
-			  int pool_id, int numptrs)
+int otx2_aura_init(struct otx2_nic *pfvf, int aura_id,
+		   int pool_id, int numptrs)
 {
 	struct npa_aq_enq_req *aq;
 	struct otx2_pool *pool;
@@ -1278,8 +1291,8 @@ static int otx2_aura_init(struct otx2_nic *pfvf, int aura_id,
 	return 0;
 }
 
-static int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id,
-			  int stack_pages, int numptrs, int buf_size)
+int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id,
+		   int stack_pages, int numptrs, int buf_size)
 {
 	struct npa_aq_enq_req *aq;
 	struct otx2_pool *pool;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index b926a50138cc..383a6716dbb9 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -27,6 +27,7 @@
 #include "otx2_txrx.h"
 #include "otx2_devlink.h"
 #include <rvu_trace.h>
+#include "qos.h"
 
 /* IPv4 flag more fragment bit */
 #define IPV4_FLAG_MORE				0x20
@@ -189,6 +190,7 @@ struct otx2_hw {
 	u16                     rx_queues;
 	u16                     tx_queues;
 	u16                     xdp_queues;
+	u16			tc_tx_queues;
 	u16                     non_qos_queues; /* tx queues plus xdp queues */
 	u16			max_queues;
 	u16			pool_cnt;
@@ -501,6 +503,8 @@ struct otx2_nic {
 	u16			pfc_schq_list[NIX_TXSCH_LVL_CNT][MAX_TXSCHQ_PER_FUNC];
 	bool			pfc_alloc_status[NIX_PF_PFC_PRIO_MAX];
 #endif
+	/* qos */
+	struct otx2_qos		qos;
 
 	/* napi event count. It is needed for adaptive irq coalescing. */
 	u32 napi_events;
@@ -745,8 +749,7 @@ static inline void cn10k_aura_freeptr(void *dev, int aura, u64 buf)
 /* Alloc pointer from pool/aura */
 static inline u64 otx2_aura_allocptr(struct otx2_nic *pfvf, int aura)
 {
-	u64 *ptr = (u64 *)otx2_get_regaddr(pfvf,
-			   NPA_LF_AURA_OP_ALLOCX(0));
+	u64 *ptr = (__force u64 *)otx2_get_regaddr(pfvf, NPA_LF_AURA_OP_ALLOCX(0));
 	u64 incr = (u64)aura | BIT_ULL(63);
 
 	return otx2_atomic64_add(incr, ptr);
@@ -888,12 +891,23 @@ static inline void otx2_dma_unmap_page(struct otx2_nic *pfvf,
 
 static inline u16 otx2_get_smq_idx(struct otx2_nic *pfvf, u16 qidx)
 {
+	u16 smq;
 #ifdef CONFIG_DCB
 	if (qidx < NIX_PF_PFC_PRIO_MAX && pfvf->pfc_alloc_status[qidx])
 		return pfvf->pfc_schq_list[NIX_TXSCH_LVL_SMQ][qidx];
 #endif
+	/* check if qidx falls under QOS queues */
+	if (qidx >= pfvf->hw.non_qos_queues)
+		smq = pfvf->qos.qid_to_sqmap[qidx - pfvf->hw.non_qos_queues];
+	else
+		smq = pfvf->hw.txschq_list[NIX_TXSCH_LVL_SMQ][0];
 
-	return pfvf->hw.txschq_list[NIX_TXSCH_LVL_SMQ][0];
+	return smq;
+}
+
+static inline u16 otx2_get_total_tx_queues(struct otx2_nic *pfvf)
+{
+	return pfvf->hw.non_qos_queues + pfvf->hw.tc_tx_queues;
 }
 
 /* MSI-X APIs */
@@ -922,17 +936,22 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl, int prio, bool pfc_en);
 int otx2_txsch_alloc(struct otx2_nic *pfvf);
 int otx2_txschq_stop(struct otx2_nic *pfvf);
 void otx2_sqb_flush(struct otx2_nic *pfvf);
-int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
-		      dma_addr_t *dma);
+int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
+		    dma_addr_t *dma);
 int otx2_rxtx_enable(struct otx2_nic *pfvf, bool enable);
 void otx2_ctx_disable(struct mbox *mbox, int type, bool npa);
 int otx2_nix_config_bp(struct otx2_nic *pfvf, bool enable);
 void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq);
 void otx2_cleanup_tx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq);
+int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura);
 int otx2_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura);
 int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura);
 int otx2_alloc_buffer(struct otx2_nic *pfvf, struct otx2_cq_queue *cq,
 		      dma_addr_t *dma);
+int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id,
+		   int stack_pages, int numptrs, int buf_size);
+int otx2_aura_init(struct otx2_nic *pfvf, int aura_id,
+		   int pool_id, int numptrs);
 
 /* RSS configuration APIs*/
 int otx2_rss_init(struct otx2_nic *pfvf);
@@ -1040,4 +1059,14 @@ static inline void cn10k_handle_mcs_event(struct otx2_nic *pfvf,
 {}
 #endif /* CONFIG_MACSEC */
 
+/* qos support */
+static inline void otx2_qos_init(struct otx2_nic *pfvf, int qos_txqs)
+{
+	struct otx2_hw *hw = &pfvf->hw;
+
+	hw->tc_tx_queues = qos_txqs;
+}
+
+u16 otx2_select_queue(struct net_device *netdev, struct sk_buff *skb,
+		      struct net_device *sb_dev);
 #endif /* OTX2_COMMON_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index 33d677849aa9..c9141d608342 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -23,6 +23,7 @@
 #include "otx2_struct.h"
 #include "otx2_ptp.h"
 #include "cn10k.h"
+#include "qos.h"
 #include <rvu_trace.h>
 
 #define DRV_NAME	"rvu_nicpf"
@@ -1228,6 +1229,7 @@ static char *nix_snd_status_e_str[NIX_SND_STATUS_MAX] =  {
 static irqreturn_t otx2_q_intr_handler(int irq, void *data)
 {
 	struct otx2_nic *pf = data;
+	struct otx2_snd_queue *sq;
 	u64 val, *ptr;
 	u64 qidx = 0;
 
@@ -1257,10 +1259,14 @@ static irqreturn_t otx2_q_intr_handler(int irq, void *data)
 	}
 
 	/* SQ */
-	for (qidx = 0; qidx < pf->hw.non_qos_queues; qidx++) {
+	for (qidx = 0; qidx < otx2_get_total_tx_queues(pf); qidx++) {
 		u64 sq_op_err_dbg, mnq_err_dbg, snd_err_dbg;
 		u8 sq_op_err_code, mnq_err_code, snd_err_code;
 
+		sq = &pf->qset.sq[qidx];
+		if (!sq->sqb_ptrs)
+			continue;
+
 		/* Below debug registers captures first errors corresponding to
 		 * those registers. We don't have to check against SQ qid as
 		 * these are fatal errors.
@@ -1383,7 +1389,7 @@ static void otx2_free_sq_res(struct otx2_nic *pf)
 	otx2_ctx_disable(&pf->mbox, NIX_AQ_CTYPE_SQ, false);
 	/* Free SQB pointers */
 	otx2_sq_free_sqbs(pf);
-	for (qidx = 0; qidx < pf->hw.non_qos_queues; qidx++) {
+	for (qidx = 0; qidx < otx2_get_total_tx_queues(pf); qidx++) {
 		sq = &qset->sq[qidx];
 		qmem_free(pf->dev, sq->sqe);
 		qmem_free(pf->dev, sq->tso_hdrs);
@@ -1433,7 +1439,7 @@ static int otx2_init_hw_resources(struct otx2_nic *pf)
 	 * so, aura count = pool count.
 	 */
 	hw->rqpool_cnt = hw->rx_queues;
-	hw->sqpool_cnt = hw->non_qos_queues;
+	hw->sqpool_cnt = otx2_get_total_tx_queues(pf);
 	hw->pool_cnt = hw->rqpool_cnt + hw->sqpool_cnt;
 
 	/* Maximum hardware supported transmit length */
@@ -1688,11 +1694,14 @@ int otx2_open(struct net_device *netdev)
 
 	netif_carrier_off(netdev);
 
-	pf->qset.cq_cnt = pf->hw.rx_queues + pf->hw.non_qos_queues;
 	/* RQ and SQs are mapped to different CQs,
 	 * so find out max CQ IRQs (i.e CINTs) needed.
 	 */
-	pf->hw.cint_cnt = max(pf->hw.rx_queues, pf->hw.tx_queues);
+	pf->hw.cint_cnt = max3(pf->hw.rx_queues, pf->hw.tx_queues,
+			       pf->hw.tc_tx_queues);
+
+	pf->qset.cq_cnt = pf->hw.rx_queues + otx2_get_total_tx_queues(pf);
+
 	qset->napi = kcalloc(pf->hw.cint_cnt, sizeof(*cq_poll), GFP_KERNEL);
 	if (!qset->napi)
 		return -ENOMEM;
@@ -1743,6 +1752,11 @@ int otx2_open(struct net_device *netdev)
 		else
 			cq_poll->cq_ids[CQ_XDP] = CINT_INVALID_CQ;
 
+		cq_poll->cq_ids[CQ_QOS] = (qidx < pf->hw.tc_tx_queues) ?
+					  (qidx + pf->hw.rx_queues +
+					   pf->hw.non_qos_queues) :
+					  CINT_INVALID_CQ;
+
 		cq_poll->dev = (void *)pf;
 		cq_poll->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_CQE;
 		INIT_WORK(&cq_poll->dim.work, otx2_dim_work);
@@ -1938,6 +1952,12 @@ static netdev_tx_t otx2_xmit(struct sk_buff *skb, struct net_device *netdev)
 	int qidx = skb_get_queue_mapping(skb);
 	struct otx2_snd_queue *sq;
 	struct netdev_queue *txq;
+	int sq_idx;
+
+	/* XDP SQs are not mapped with TXQs
+	 * advance qid to derive correct sq mapped with QOS
+	 */
+	sq_idx = (qidx >= pf->hw.tx_queues) ? (qidx + pf->hw.xdp_queues) : qidx;
 
 	/* Check for minimum and maximum packet length */
 	if (skb->len <= ETH_HLEN ||
@@ -1946,7 +1966,7 @@ static netdev_tx_t otx2_xmit(struct sk_buff *skb, struct net_device *netdev)
 		return NETDEV_TX_OK;
 	}
 
-	sq = &pf->qset.sq[qidx];
+	sq = &pf->qset.sq[sq_idx];
 	txq = netdev_get_tx_queue(netdev, qidx);
 
 	if (!otx2_sq_append_skb(netdev, sq, skb, qidx)) {
@@ -1964,8 +1984,8 @@ static netdev_tx_t otx2_xmit(struct sk_buff *skb, struct net_device *netdev)
 	return NETDEV_TX_OK;
 }
 
-static u16 otx2_select_queue(struct net_device *netdev, struct sk_buff *skb,
-			     struct net_device *sb_dev)
+u16 otx2_select_queue(struct net_device *netdev, struct sk_buff *skb,
+		      struct net_device *sb_dev)
 {
 #ifdef CONFIG_DCB
 	struct otx2_nic *pf = netdev_priv(netdev);
@@ -1987,6 +2007,7 @@ static u16 otx2_select_queue(struct net_device *netdev, struct sk_buff *skb,
 #endif
 	return netdev_pick_tx(netdev, skb, NULL);
 }
+EXPORT_SYMBOL(otx2_select_queue);
 
 static netdev_features_t otx2_fix_features(struct net_device *dev,
 					   netdev_features_t features)
@@ -2703,10 +2724,10 @@ static void otx2_sriov_vfcfg_cleanup(struct otx2_nic *pf)
 static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct device *dev = &pdev->dev;
+	int err, qcount, qos_txqs;
 	struct net_device *netdev;
 	struct otx2_nic *pf;
 	struct otx2_hw *hw;
-	int err, qcount;
 	int num_vec;
 
 	err = pcim_enable_device(pdev);
@@ -2731,8 +2752,9 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	/* Set number of queues */
 	qcount = min_t(int, num_online_cpus(), OTX2_MAX_CQ_CNT);
+	qos_txqs = min_t(int, qcount, OTX2_QOS_MAX_LEAF_NODES);
 
-	netdev = alloc_etherdev_mqs(sizeof(*pf), qcount, qcount);
+	netdev = alloc_etherdev_mqs(sizeof(*pf), qcount + qos_txqs, qcount);
 	if (!netdev) {
 		err = -ENOMEM;
 		goto err_release_regions;
@@ -2920,6 +2942,8 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_pf_sriov_init;
 #endif
 
+	otx2_qos_init(pf, qos_txqs);
+
 	return 0;
 
 err_pf_sriov_init:
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 7045fedfd73a..e288f46b23a8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -464,12 +464,13 @@ static int otx2_tx_napi_handler(struct otx2_nic *pfvf,
 			break;
 		}
 
-		if (cq->cq_type == CQ_XDP) {
+		qidx = cq->cq_idx - pfvf->hw.rx_queues;
+
+		if (cq->cq_type == CQ_XDP)
 			otx2_xdp_snd_pkt_handler(pfvf, sq, cqe);
-		} else {
-			otx2_snd_pkt_handler(pfvf, cq, sq, cqe, budget,
-					     &tx_pkts, &tx_bytes);
-		}
+		else
+			otx2_snd_pkt_handler(pfvf, cq, &pfvf->qset.sq[qidx],
+					     cqe, budget, &tx_pkts, &tx_bytes);
 
 		cqe->hdr.cqe_type = NIX_XQE_TYPE_INVALID;
 		processed_cqe++;
@@ -486,7 +487,11 @@ static int otx2_tx_napi_handler(struct otx2_nic *pfvf,
 	if (likely(tx_pkts)) {
 		struct netdev_queue *txq;
 
-		txq = netdev_get_tx_queue(pfvf->netdev, cq->cint_idx);
+		qidx = cq->cq_idx - pfvf->hw.rx_queues;
+
+		if (qidx >= pfvf->hw.tx_queues)
+			qidx -= pfvf->hw.xdp_queues;
+		txq = netdev_get_tx_queue(pfvf->netdev, qidx);
 		netdev_tx_completed_queue(txq, tx_pkts, tx_bytes);
 		/* Check if queue was stopped earlier due to ring full */
 		smp_mb();
@@ -736,7 +741,8 @@ static void otx2_sqe_add_hdr(struct otx2_nic *pfvf, struct otx2_snd_queue *sq,
 		sqe_hdr->aura = sq->aura_id;
 		/* Post a CQE Tx after pkt transmission */
 		sqe_hdr->pnc = 1;
-		sqe_hdr->sq = qidx;
+		sqe_hdr->sq = (qidx >=  pfvf->hw.tx_queues) ?
+			       qidx + pfvf->hw.xdp_queues : qidx;
 	}
 	sqe_hdr->total = skb->len;
 	/* Set SQE identifier which will be used later for freeing SKB */
@@ -1221,8 +1227,10 @@ void otx2_cleanup_tx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq)
 	struct nix_cqe_tx_s *cqe;
 	int processed_cqe = 0;
 	struct sg_list *sg;
+	int qidx;
 
-	sq = &pfvf->qset.sq[cq->cint_idx];
+	qidx = cq->cq_idx - pfvf->hw.rx_queues;
+	sq = &pfvf->qset.sq[qidx];
 
 	if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe)
 		return;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
index 93cac2c2664c..7ab6db9a986f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
@@ -102,7 +102,8 @@ enum cq_type {
 	CQ_RX,
 	CQ_TX,
 	CQ_XDP,
-	CQS_PER_CINT = 3, /* RQ + SQ + XDP */
+	CQ_QOS,
+	CQS_PER_CINT = 4, /* RQ + SQ + XDP + QOS_SQ */
 };
 
 struct otx2_cq_poll {
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
index a078949430ce..5dddf067a810 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
@@ -479,6 +479,7 @@ static const struct net_device_ops otx2vf_netdev_ops = {
 	.ndo_open = otx2vf_open,
 	.ndo_stop = otx2vf_stop,
 	.ndo_start_xmit = otx2vf_xmit,
+	.ndo_select_queue = otx2_select_queue,
 	.ndo_set_rx_mode = otx2vf_set_rx_mode,
 	.ndo_set_mac_address = otx2_set_mac_address,
 	.ndo_change_mtu = otx2vf_change_mtu,
@@ -524,10 +525,10 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	int num_vec = pci_msix_vec_count(pdev);
 	struct device *dev = &pdev->dev;
+	int err, qcount, qos_txqs;
 	struct net_device *netdev;
 	struct otx2_nic *vf;
 	struct otx2_hw *hw;
-	int err, qcount;
 
 	err = pcim_enable_device(pdev);
 	if (err) {
@@ -550,7 +551,8 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	pci_set_master(pdev);
 
 	qcount = num_online_cpus();
-	netdev = alloc_etherdev_mqs(sizeof(*vf), qcount, qcount);
+	qos_txqs = min_t(int, qcount, OTX2_QOS_MAX_LEAF_NODES);
+	netdev = alloc_etherdev_mqs(sizeof(*vf), qcount + qos_txqs, qcount);
 	if (!netdev) {
 		err = -ENOMEM;
 		goto err_release_regions;
@@ -699,6 +701,7 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_shutdown_tc;
 #endif
+	otx2_qos_init(vf, qos_txqs);
 
 	return 0;
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.h b/drivers/net/ethernet/marvell/octeontx2/nic/qos.h
new file mode 100644
index 000000000000..73a62d092e99
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Marvell RVU Ethernet driver
+ *
+ * Copyright (C) 2023 Marvell.
+ *
+ */
+#ifndef OTX2_QOS_H
+#define OTX2_QOS_H
+
+#define OTX2_QOS_MAX_LEAF_NODES                16
+
+int otx2_qos_enable_sq(struct otx2_nic *pfvf, int qidx, u16 smq);
+void otx2_qos_disable_sq(struct otx2_nic *pfvf, int qidx, u16 mdq);
+
+struct otx2_qos {
+	       u16 qid_to_sqmap[OTX2_QOS_MAX_LEAF_NODES];
+	};
+
+#endif
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c
new file mode 100644
index 000000000000..e142d43f5a62
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c
@@ -0,0 +1,282 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell RVU Physical Function ethernet driver
+ *
+ * Copyright (C) 2023 Marvell.
+ *
+ */
+
+#include <linux/netdevice.h>
+#include <net/tso.h>
+
+#include "cn10k.h"
+#include "otx2_reg.h"
+#include "otx2_common.h"
+#include "otx2_txrx.h"
+#include "otx2_struct.h"
+
+#define OTX2_QOS_MAX_LEAF_NODES 16
+
+static void otx2_qos_aura_pool_free(struct otx2_nic *pfvf, int pool_id)
+{
+	struct otx2_pool *pool;
+
+	if (!pfvf->qset.pool)
+		return;
+
+	pool = &pfvf->qset.pool[pool_id];
+	qmem_free(pfvf->dev, pool->stack);
+	qmem_free(pfvf->dev, pool->fc_addr);
+	pool->stack = NULL;
+	pool->fc_addr = NULL;
+}
+
+static int otx2_qos_sq_aura_pool_init(struct otx2_nic *pfvf, int qidx)
+{
+	struct otx2_qset *qset = &pfvf->qset;
+	int pool_id, stack_pages, num_sqbs;
+	struct otx2_hw *hw = &pfvf->hw;
+	struct otx2_snd_queue *sq;
+	struct otx2_pool *pool;
+	dma_addr_t bufptr;
+	int err, ptr;
+	u64 iova, pa;
+
+	/* Calculate number of SQBs needed.
+	 *
+	 * For a 128byte SQE, and 4K size SQB, 31 SQEs will fit in one SQB.
+	 * Last SQE is used for pointing to next SQB.
+	 */
+	num_sqbs = (hw->sqb_size / 128) - 1;
+	num_sqbs = (qset->sqe_cnt + num_sqbs) / num_sqbs;
+
+	/* Get no of stack pages needed */
+	stack_pages =
+		(num_sqbs + hw->stack_pg_ptrs - 1) / hw->stack_pg_ptrs;
+
+	pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_SQ, qidx);
+	pool = &pfvf->qset.pool[pool_id];
+
+	/* Initialize aura context */
+	err = otx2_aura_init(pfvf, pool_id, pool_id, num_sqbs);
+	if (err)
+		return err;
+
+	/* Initialize pool context */
+	err = otx2_pool_init(pfvf, pool_id, stack_pages,
+			     num_sqbs, hw->sqb_size);
+	if (err)
+		goto aura_free;
+
+	/* Flush accumulated messages */
+	err = otx2_sync_mbox_msg(&pfvf->mbox);
+	if (err)
+		goto pool_free;
+
+	/* Allocate pointers and free them to aura/pool */
+	sq = &qset->sq[qidx];
+	sq->sqb_count = 0;
+	sq->sqb_ptrs = kcalloc(num_sqbs, sizeof(*sq->sqb_ptrs), GFP_KERNEL);
+	if (!sq->sqb_ptrs) {
+		err = -ENOMEM;
+		goto pool_free;
+	}
+
+	for (ptr = 0; ptr < num_sqbs; ptr++) {
+		err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
+		if (err)
+			goto sqb_free;
+		pfvf->hw_ops->aura_freeptr(pfvf, pool_id, bufptr);
+		sq->sqb_ptrs[sq->sqb_count++] = (u64)bufptr;
+	}
+
+	return 0;
+
+sqb_free:
+	while (ptr--) {
+		if (!sq->sqb_ptrs[ptr])
+			continue;
+		iova = sq->sqb_ptrs[ptr];
+		pa = otx2_iova_to_phys(pfvf->iommu_domain, iova);
+		dma_unmap_page_attrs(pfvf->dev, iova, hw->sqb_size,
+				     DMA_FROM_DEVICE,
+				     DMA_ATTR_SKIP_CPU_SYNC);
+		put_page(virt_to_page(phys_to_virt(pa)));
+		otx2_aura_allocptr(pfvf, pool_id);
+	}
+	sq->sqb_count = 0;
+	kfree(sq->sqb_ptrs);
+pool_free:
+	qmem_free(pfvf->dev, pool->stack);
+aura_free:
+	qmem_free(pfvf->dev, pool->fc_addr);
+	otx2_mbox_reset(&pfvf->mbox.mbox, 0);
+	return err;
+}
+
+static void otx2_qos_sq_free_sqbs(struct otx2_nic *pfvf, int qidx)
+{
+	struct otx2_qset *qset = &pfvf->qset;
+	struct otx2_hw *hw = &pfvf->hw;
+	struct otx2_snd_queue *sq;
+	u64 iova, pa;
+	int sqb;
+
+	sq = &qset->sq[qidx];
+	if (!sq->sqb_ptrs)
+		return;
+	for (sqb = 0; sqb < sq->sqb_count; sqb++) {
+		if (!sq->sqb_ptrs[sqb])
+			continue;
+		iova = sq->sqb_ptrs[sqb];
+		pa = otx2_iova_to_phys(pfvf->iommu_domain, iova);
+		dma_unmap_page_attrs(pfvf->dev, iova, hw->sqb_size,
+				     DMA_FROM_DEVICE,
+				     DMA_ATTR_SKIP_CPU_SYNC);
+		put_page(virt_to_page(phys_to_virt(pa)));
+	}
+
+	sq->sqb_count = 0;
+
+	sq = &qset->sq[qidx];
+	qmem_free(pfvf->dev, sq->sqe);
+	qmem_free(pfvf->dev, sq->tso_hdrs);
+	kfree(sq->sg);
+	kfree(sq->sqb_ptrs);
+	qmem_free(pfvf->dev, sq->timestamps);
+
+	memset((void *)sq, 0, sizeof(*sq));
+}
+
+/* send queue id */
+static void otx2_qos_sqb_flush(struct otx2_nic *pfvf, int qidx)
+{
+	int sqe_tail, sqe_head;
+	u64 incr, *ptr, val;
+
+	ptr = (__force u64 *)otx2_get_regaddr(pfvf, NIX_LF_SQ_OP_STATUS);
+	incr = (u64)qidx << 32;
+	val = otx2_atomic64_add(incr, ptr);
+	sqe_head = (val >> 20) & 0x3F;
+	sqe_tail = (val >> 28) & 0x3F;
+	if (sqe_head != sqe_tail)
+		usleep_range(50, 60);
+}
+
+static int otx2_qos_ctx_disable(struct otx2_nic *pfvf, u16 qidx, int aura_id)
+{
+	struct nix_cn10k_aq_enq_req *cn10k_sq_aq;
+	struct npa_aq_enq_req *aura_aq;
+	struct npa_aq_enq_req *pool_aq;
+	struct nix_aq_enq_req *sq_aq;
+
+	if (test_bit(CN10K_LMTST, &pfvf->hw.cap_flag)) {
+		cn10k_sq_aq = otx2_mbox_alloc_msg_nix_cn10k_aq_enq(&pfvf->mbox);
+		if (!cn10k_sq_aq)
+			return -ENOMEM;
+		cn10k_sq_aq->qidx = qidx;
+		cn10k_sq_aq->sq.ena = 0;
+		cn10k_sq_aq->sq_mask.ena = 1;
+		cn10k_sq_aq->ctype = NIX_AQ_CTYPE_SQ;
+		cn10k_sq_aq->op = NIX_AQ_INSTOP_WRITE;
+	} else {
+		sq_aq = otx2_mbox_alloc_msg_nix_aq_enq(&pfvf->mbox);
+		if (!sq_aq)
+			return -ENOMEM;
+		sq_aq->qidx = qidx;
+		sq_aq->sq.ena = 0;
+		sq_aq->sq_mask.ena = 1;
+		sq_aq->ctype = NIX_AQ_CTYPE_SQ;
+		sq_aq->op = NIX_AQ_INSTOP_WRITE;
+	}
+
+	aura_aq = otx2_mbox_alloc_msg_npa_aq_enq(&pfvf->mbox);
+	if (!aura_aq) {
+		otx2_mbox_reset(&pfvf->mbox.mbox, 0);
+		return -ENOMEM;
+	}
+
+	aura_aq->aura_id = aura_id;
+	aura_aq->aura.ena = 0;
+	aura_aq->aura_mask.ena = 1;
+	aura_aq->ctype = NPA_AQ_CTYPE_AURA;
+	aura_aq->op = NPA_AQ_INSTOP_WRITE;
+
+	pool_aq = otx2_mbox_alloc_msg_npa_aq_enq(&pfvf->mbox);
+	if (!pool_aq) {
+		otx2_mbox_reset(&pfvf->mbox.mbox, 0);
+		return -ENOMEM;
+	}
+
+	pool_aq->aura_id = aura_id;
+	pool_aq->pool.ena = 0;
+	pool_aq->pool_mask.ena = 1;
+
+	pool_aq->ctype = NPA_AQ_CTYPE_POOL;
+	pool_aq->op = NPA_AQ_INSTOP_WRITE;
+
+	return otx2_sync_mbox_msg(&pfvf->mbox);
+}
+
+int otx2_qos_enable_sq(struct otx2_nic *pfvf, int qidx, u16 smq)
+{
+	struct otx2_hw *hw = &pfvf->hw;
+	int pool_id, sq_idx, err;
+
+	if (pfvf->flags & OTX2_FLAG_INTF_DOWN)
+		return -EPERM;
+
+	sq_idx = hw->non_qos_queues + qidx;
+
+	mutex_lock(&pfvf->mbox.lock);
+	err = otx2_qos_sq_aura_pool_init(pfvf, sq_idx);
+	if (err)
+		goto out;
+
+	pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_SQ, sq_idx);
+	pfvf->qos.qid_to_sqmap[qidx] = smq;
+	err = otx2_sq_init(pfvf, sq_idx, pool_id);
+	if (err)
+		goto out;
+out:
+	mutex_unlock(&pfvf->mbox.lock);
+	return err;
+}
+
+void otx2_qos_disable_sq(struct otx2_nic *pfvf, int qidx, u16 mdq)
+{
+	struct otx2_qset *qset = &pfvf->qset;
+	struct otx2_hw *hw = &pfvf->hw;
+	struct otx2_snd_queue *sq;
+	struct otx2_cq_queue *cq;
+	int pool_id, sq_idx;
+
+	sq_idx = hw->non_qos_queues + qidx;
+
+	/* If the DOWN flag is set SQs are already freed */
+	if (pfvf->flags & OTX2_FLAG_INTF_DOWN)
+		return;
+
+	sq = &pfvf->qset.sq[sq_idx];
+	if (!sq->sqb_ptrs)
+		return;
+
+	if (sq_idx < hw->non_qos_queues ||
+	    sq_idx >= otx2_get_total_tx_queues(pfvf)) {
+		netdev_err(pfvf->netdev, "Send Queue is not a QoS queue\n");
+		return;
+	}
+
+	cq = &qset->cq[pfvf->hw.rx_queues + sq_idx];
+	pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_SQ, sq_idx);
+
+	otx2_qos_sqb_flush(pfvf, sq_idx);
+	otx2_smq_flush(pfvf, otx2_get_smq_idx(pfvf, sq_idx));
+	otx2_cleanup_tx_cqes(pfvf, cq);
+
+	mutex_lock(&pfvf->mbox.lock);
+	otx2_qos_ctx_disable(pfvf, sq_idx, pool_id);
+	mutex_unlock(&pfvf->mbox.lock);
+
+	otx2_qos_sq_free_sqbs(pfvf, sq_idx);
+	otx2_qos_aura_pool_free(pfvf, pool_id);
+}
-- 
2.17.1

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ