Merge branch 'octeontx2-misc-fixes'

Sunil Goutham says:

====================
octeontx2: Miscellaneous fixes

This patch series contains a bunch of miscellaneous fixes
for various issues like
- Free unallocated memory during driver unload
- HW reading transmit descriptor from wrong address
- VF VLAN strip offload MCAM entry installation failure
- Pkts not being distributed across queues in RSS context
- Wrong interface backpressure configuration for NIX1 block on 98xx
- etc
====================

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

10 files changed, 75 insertions, 31 deletions

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h
index 752ba6b4b919..da824805c2ba 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h
@@ -64,8 +64,8 @@ static inline int qmem_alloc(struct device *dev, struct qmem **q,
 
 	qmem->entry_sz = entry_sz;
 	qmem->alloc_sz = (qsize * entry_sz) + OTX2_ALIGN;
-	qmem->base = dma_alloc_coherent(dev, qmem->alloc_sz,
-					 &qmem->iova, GFP_KERNEL);
+	qmem->base = dma_alloc_attrs(dev, qmem->alloc_sz, &qmem->iova,
+				     GFP_KERNEL, DMA_ATTR_FORCE_CONTIGUOUS);
 	if (!qmem->base)
 		return -ENOMEM;
 
@@ -84,9 +84,10 @@ static inline void qmem_free(struct device *dev, struct qmem *qmem)
 		return;
 
 	if (qmem->base)
-		dma_free_coherent(dev, qmem->alloc_sz,
-				  qmem->base - qmem->align,
-				  qmem->iova - qmem->align);
+		dma_free_attrs(dev, qmem->alloc_sz,
+			       qmem->base - qmem->align,
+			       qmem->iova - qmem->align,
+			       DMA_ATTR_FORCE_CONTIGUOUS);
 	devm_kfree(dev, qmem);
 }
 
@@ -192,8 +193,6 @@ enum nix_scheduler {
 #define NIX_CHAN_LBK_CHX(a, b)		(0 + 0x100 * (a) + (b))
 #define NIX_CHAN_SDP_CH_START		(0x700ull)
 
-#define SDP_CHANNELS			256
-
 /* The mask is to extract lower 10-bits of channel number
  * which CPT will pass to X2P.
  */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index c2438ba5e2ec..84f0aaa8665d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -498,12 +498,15 @@ int rvu_lf_reset(struct rvu *rvu, struct rvu_block *block, int lf)
 static void rvu_block_reset(struct rvu *rvu, int blkaddr, u64 rst_reg)
 {
 	struct rvu_block *block = &rvu->hw->block[blkaddr];
+	int err;
 
 	if (!block->implemented)
 		return;
 
 	rvu_write64(rvu, blkaddr, rst_reg, BIT_ULL(0));
-	rvu_poll_reg(rvu, blkaddr, rst_reg, BIT_ULL(63), true);
+	err = rvu_poll_reg(rvu, blkaddr, rst_reg, BIT_ULL(63), true);
+	if (err)
+		dev_err(rvu->dev, "HW block:%d reset failed\n", blkaddr);
 }
 
 static void rvu_reset_all_blocks(struct rvu *rvu)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
index 8d48b64485c6..dbe9149a215e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
@@ -82,10 +82,10 @@ static int rvu_get_lmtaddr(struct rvu *rvu, u16 pcifunc,
 		dev_err(rvu->dev, "%s LMTLINE iova transulation failed err:%llx\n", __func__, val);
 		return -EIO;
 	}
-	/* PA[51:12] = RVU_AF_SMMU_TLN_FLIT1[60:21]
+	/* PA[51:12] = RVU_AF_SMMU_TLN_FLIT0[57:18]
 	 * PA[11:0] = IOVA[11:0]
 	 */
-	pa = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TLN_FLIT1) >> 21;
+	pa = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TLN_FLIT0) >> 18;
 	pa &= GENMASK_ULL(39, 0);
 	*lmt_addr = (pa << 12) | (iova  & 0xFFF);
 
@@ -212,9 +212,10 @@ void rvu_reset_lmt_map_tbl(struct rvu *rvu, u16 pcifunc)
 
 int rvu_set_channels_base(struct rvu *rvu)
 {
+	u16 nr_lbk_chans, nr_sdp_chans, nr_cgx_chans, nr_cpt_chans;
+	u16 sdp_chan_base, cgx_chan_base, cpt_chan_base;
 	struct rvu_hwinfo *hw = rvu->hw;
-	u16 cpt_chan_base;
-	u64 nix_const;
+	u64 nix_const, nix_const1;
 	int blkaddr;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, 0);
@@ -222,6 +223,7 @@ int rvu_set_channels_base(struct rvu *rvu)
 		return blkaddr;
 
 	nix_const = rvu_read64(rvu, blkaddr, NIX_AF_CONST);
+	nix_const1 = rvu_read64(rvu, blkaddr, NIX_AF_CONST1);
 
 	hw->cgx = (nix_const >> 12) & 0xFULL;
 	hw->lmac_per_cgx = (nix_const >> 8) & 0xFULL;
@@ -244,14 +246,24 @@ int rvu_set_channels_base(struct rvu *rvu)
 	 * channels such that all channel numbers are contiguous
 	 * leaving no holes. This way the new CPT channels can be
 	 * accomodated. The order of channel numbers assigned is
-	 * LBK, SDP, CGX and CPT.
+	 * LBK, SDP, CGX and CPT. Also the base channel number
+	 * of a block must be multiple of number of channels
+	 * of the block.
 	 */
-	hw->sdp_chan_base = hw->lbk_chan_base + hw->lbk_links *
-				((nix_const >> 16) & 0xFFULL);
-	hw->cgx_chan_base = hw->sdp_chan_base + hw->sdp_links * SDP_CHANNELS;
+	nr_lbk_chans = (nix_const >> 16) & 0xFFULL;
+	nr_sdp_chans = nix_const1 & 0xFFFULL;
+	nr_cgx_chans = nix_const & 0xFFULL;
+	nr_cpt_chans = (nix_const >> 32) & 0xFFFULL;
 
-	cpt_chan_base = hw->cgx_chan_base + hw->cgx_links *
-				(nix_const & 0xFFULL);
+	sdp_chan_base = hw->lbk_chan_base + hw->lbk_links * nr_lbk_chans;
+	/* Round up base channel to multiple of number of channels */
+	hw->sdp_chan_base = ALIGN(sdp_chan_base, nr_sdp_chans);
+
+	cgx_chan_base = hw->sdp_chan_base + hw->sdp_links * nr_sdp_chans;
+	hw->cgx_chan_base = ALIGN(cgx_chan_base, nr_cgx_chans);
+
+	cpt_chan_base = hw->cgx_chan_base + hw->cgx_links * nr_cgx_chans;
+	hw->cpt_chan_base = ALIGN(cpt_chan_base, nr_cpt_chans);
 
 	/* Out of 4096 channels start CPT from 2048 so
 	 * that MSB for CPT channels is always set
@@ -355,6 +367,7 @@ err_put:
 
 static void __rvu_nix_set_channels(struct rvu *rvu, int blkaddr)
 {
+	u64 nix_const1 = rvu_read64(rvu, blkaddr, NIX_AF_CONST1);
 	u64 nix_const = rvu_read64(rvu, blkaddr, NIX_AF_CONST);
 	u16 cgx_chans, lbk_chans, sdp_chans, cpt_chans;
 	struct rvu_hwinfo *hw = rvu->hw;
@@ -364,7 +377,7 @@ static void __rvu_nix_set_channels(struct rvu *rvu, int blkaddr)
 
 	cgx_chans = nix_const & 0xFFULL;
 	lbk_chans = (nix_const >> 16) & 0xFFULL;
-	sdp_chans = SDP_CHANNELS;
+	sdp_chans = nix_const1 & 0xFFFULL;
 	cpt_chans = (nix_const >> 32) & 0xFFFULL;
 
 	start = hw->cgx_chan_base;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 22039d9ce70a..c5e3f90e562d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -25,7 +25,7 @@ static int nix_update_mce_rule(struct rvu *rvu, u16 pcifunc,
 			       int type, bool add);
 static int nix_setup_ipolicers(struct rvu *rvu,
 			       struct nix_hw *nix_hw, int blkaddr);
-static void nix_ipolicer_freemem(struct nix_hw *nix_hw);
+static void nix_ipolicer_freemem(struct rvu *rvu, struct nix_hw *nix_hw);
 static int nix_verify_bandprof(struct nix_cn10k_aq_enq_req *req,
 			       struct nix_hw *nix_hw, u16 pcifunc);
 static int nix_free_all_bandprof(struct rvu *rvu, u16 pcifunc);
@@ -3965,7 +3965,7 @@ static void rvu_nix_block_freemem(struct rvu *rvu, int blkaddr,
 			kfree(txsch->schq.bmap);
 		}
 
-		nix_ipolicer_freemem(nix_hw);
+		nix_ipolicer_freemem(rvu, nix_hw);
 
 		vlan = &nix_hw->txvlan;
 		kfree(vlan->rsrc.bmap);
@@ -4341,11 +4341,14 @@ static int nix_setup_ipolicers(struct rvu *rvu,
 	return 0;
 }
 
-static void nix_ipolicer_freemem(struct nix_hw *nix_hw)
+static void nix_ipolicer_freemem(struct rvu *rvu, struct nix_hw *nix_hw)
 {
 	struct nix_ipolicer *ipolicer;
 	int layer;
 
+	if (!rvu->hw->cap.ipolicer)
+		return;
+
 	for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) {
 		ipolicer = &nix_hw->ipolicer[layer];
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
index 6efcf3afff40..960ee1c2e178 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
@@ -53,7 +53,7 @@
 #define RVU_AF_SMMU_TXN_REQ		    (0x6008)
 #define RVU_AF_SMMU_ADDR_RSP_STS	    (0x6010)
 #define RVU_AF_SMMU_ADDR_TLN		    (0x6018)
-#define RVU_AF_SMMU_TLN_FLIT1		    (0x6030)
+#define RVU_AF_SMMU_TLN_FLIT0		    (0x6020)
 
 /* Admin function's privileged PF/VF registers */
 #define RVU_PRIV_CONST                      (0x8000000)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index ce799b7a8449..f630e5713025 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -208,7 +208,8 @@ int otx2_set_mac_address(struct net_device *netdev, void *p)
 	if (!otx2_hw_set_mac_addr(pfvf, addr->sa_data)) {
 		memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
 		/* update dmac field in vlan offload rule */
-		if (pfvf->flags & OTX2_FLAG_RX_VLAN_SUPPORT)
+		if (netif_running(netdev) &&
+		    pfvf->flags & OTX2_FLAG_RX_VLAN_SUPPORT)
 			otx2_install_rxvlan_offload_flow(pfvf);
 		/* update dmac address in ntuple and DMAC filter list */
 		if (pfvf->flags & OTX2_FLAG_DMACFLTR_SUPPORT)
@@ -268,6 +269,7 @@ unlock:
 int otx2_set_flowkey_cfg(struct otx2_nic *pfvf)
 {
 	struct otx2_rss_info *rss = &pfvf->hw.rss_info;
+	struct nix_rss_flowkey_cfg_rsp *rsp;
 	struct nix_rss_flowkey_cfg *req;
 	int err;
 
@@ -282,6 +284,16 @@ int otx2_set_flowkey_cfg(struct otx2_nic *pfvf)
 	req->group = DEFAULT_RSS_CONTEXT_GROUP;
 
 	err = otx2_sync_mbox_msg(&pfvf->mbox);
+	if (err)
+		goto fail;
+
+	rsp = (struct nix_rss_flowkey_cfg_rsp *)
+			otx2_mbox_get_rsp(&pfvf->mbox.mbox, 0, &req->hdr);
+	if (IS_ERR(rsp))
+		goto fail;
+
+	pfvf->hw.flowkey_alg_idx = rsp->alg_idx;
+fail:
 	mutex_unlock(&pfvf->mbox.lock);
 	return err;
 }
@@ -1196,7 +1208,22 @@ static int otx2_aura_init(struct otx2_nic *pfvf, int aura_id,
 	/* Enable backpressure for RQ aura */
 	if (aura_id < pfvf->hw.rqpool_cnt && !is_otx2_lbkvf(pfvf->pdev)) {
 		aq->aura.bp_ena = 0;
+		/* If NIX1 LF is attached then specify NIX1_RX.
+		 *
+		 * Below NPA_AURA_S[BP_ENA] is set according to the
+		 * NPA_BPINTF_E enumeration given as:
+		 * 0x0 + a*0x1 where 'a' is 0 for NIX0_RX and 1 for NIX1_RX so
+		 * NIX0_RX is 0x0 + 0*0x1 = 0
+		 * NIX1_RX is 0x0 + 1*0x1 = 1
+		 * But in HRM it is given that
+		 * "NPA_AURA_S[BP_ENA](w1[33:32]) - Enable aura backpressure to
+		 * NIX-RX based on [BP] level. One bit per NIX-RX; index
+		 * enumerated by NPA_BPINTF_E."
+		 */
+		if (pfvf->nix_blkaddr == BLKADDR_NIX1)
+			aq->aura.bp_ena = 1;
 		aq->aura.nix0_bpid = pfvf->bpid[0];
+
 		/* Set backpressure level for RQ's Aura */
 		aq->aura.bp = RQ_BP_LVL_AURA;
 	}
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index c4147b64e059..1a97b76a12e1 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -199,6 +199,9 @@ struct otx2_hw {
 	u8			lso_udpv4_idx;
 	u8			lso_udpv6_idx;
 
+	/* RSS */
+	u8			flowkey_alg_idx;
+
 	/* MSI-X */
 	u8			cint_cnt; /* CQ interrupt count */
 	u16			npa_msixoff; /* Offset of NPA vectors */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index 620da08db317..0151d6d939d4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@@ -33,9 +33,6 @@ struct otx2_stat {
 	.index = offsetof(struct otx2_dev_stats, stat) / sizeof(u64), \
 }
 
-/* Physical link config */
-#define OTX2_ETHTOOL_SUPPORTED_MODES 0x638CCBF //110001110001100110010111111
-
 enum link_mode {
 	OTX2_MODE_SUPPORTED,
 	OTX2_MODE_ADVERTISED
@@ -1086,8 +1083,6 @@ static void otx2_get_link_mode_info(u64 link_mode_bmap,
 	};
 	u8 bit;
 
-	link_mode_bmap = link_mode_bmap & OTX2_ETHTOOL_SUPPORTED_MODES;
-
 	for_each_set_bit(bit, (unsigned long *)&link_mode_bmap, 27) {
 		/* SGMII mode is set */
 		if (bit == 0)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
index 55802b56e3b9..e949001a6e55 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
@@ -907,6 +907,7 @@ static int otx2_add_flow_msg(struct otx2_nic *pfvf, struct otx2_flow *flow)
 		if (flow->flow_spec.flow_type & FLOW_RSS) {
 			req->op = NIX_RX_ACTIONOP_RSS;
 			req->index = flow->rss_ctx_id;
+			req->flow_key_alg = pfvf->hw.flowkey_alg_idx;
 		} else {
 			req->op = NIX_RX_ACTIONOP_UCAST;
 			req->index = ethtool_get_flow_spec_ring(ring_cookie);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index 81840b625c68..0aa2149ae968 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -508,8 +508,8 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
 				   match.key->vlan_priority << 13;
 
 			vlan_tci_mask = match.mask->vlan_id |
-					match.key->vlan_dei << 12 |
-					match.key->vlan_priority << 13;
+					match.mask->vlan_dei << 12 |
+					match.mask->vlan_priority << 13;
 
 			flow_spec->vlan_tci = htons(vlan_tci);
 			flow_mask->vlan_tci = htons(vlan_tci_mask);