Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull another networking update from David Miller:
 "Small follow-up to the main merge pull from the other day:

  1) Alexander Duyck's DMA memory barrier patch set.

  2) cxgb4 driver fixes from Karen Xie.

  3) Add missing export of fixed_phy_register() to modules, from Mark
     Salter.

  4) DSA bug fixes from Florian Fainelli"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (24 commits)
  net/macb: add TX multiqueue support for gem
  linux/interrupt.h: remove the definition of unused tasklet_hi_enable
  jme: replace calls to redundant function
  net: ethernet: davicom: Allow to select DM9000 for nios2
  net: ethernet: smsc: Allow to select SMC91X for nios2
  cxgb4: Add support for QSA modules
  libcxgbi: fix freeing skb prematurely
  cxgb4i: use set_wr_txq() to set tx queues
  cxgb4i: handle non-pdu-aligned rx data
  cxgb4i: additional types of negative advice
  cxgb4/cxgb4i: set the max. pdu length in firmware
  cxgb4i: fix credit check for tx_data_wr
  cxgb4i: fix tx immediate data credit check
  net: phy: export fixed_phy_register()
  fib_trie: Fix trie balancing issue if new node pushes down existing node
  vlan: Add ability to always enable TSO/UFO
  r8169:update rtl8168g pcie ephy parameter
  net: dsa: bcm_sf2: force link for all fixed PHY devices
  fm10k/igb/ixgbe: Use dma_rmb on Rx descriptor reads
  r8169: Use dma_rmb() and dma_wmb() for DescOwn checks
  ...

3 files changed, 109 insertions, 43 deletions

diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
index 69fbfc8..a83d2ce 100644
--- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
+++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
@@ -75,6 +75,7 @@ typedef void (*cxgb4i_cplhandler_func)(struct cxgbi_device *, struct sk_buff *);
 static void *t4_uld_add(const struct cxgb4_lld_info *);
 static int t4_uld_rx_handler(void *, const __be64 *, const struct pkt_gl *);
 static int t4_uld_state_change(void *, enum cxgb4_state state);
+static inline int send_tx_flowc_wr(struct cxgbi_sock *);
 
 static const struct cxgb4_uld_info cxgb4i_uld_info = {
 	.name = DRV_MODULE_NAME,
@@ -157,12 +158,6 @@ static struct scsi_transport_template *cxgb4i_stt;
 #define RCV_BUFSIZ_MASK		0x3FFU
 #define MAX_IMM_TX_PKT_LEN	128
 
-static inline void set_queue(struct sk_buff *skb, unsigned int queue,
-				const struct cxgbi_sock *csk)
-{
-	skb->queue_mapping = queue;
-}
-
 static int push_tx_frames(struct cxgbi_sock *, int);
 
 /*
@@ -172,10 +167,14 @@ static int push_tx_frames(struct cxgbi_sock *, int);
  * Returns true if a packet can be sent as an offload WR with immediate
  * data.  We currently use the same limit as for Ethernet packets.
  */
-static inline int is_ofld_imm(const struct sk_buff *skb)
+static inline bool is_ofld_imm(const struct sk_buff *skb)
 {
-	return skb->len <= (MAX_IMM_TX_PKT_LEN -
-			sizeof(struct fw_ofld_tx_data_wr));
+	int len = skb->len;
+
+	if (likely(cxgbi_skcb_test_flag(skb, SKCBF_TX_NEED_HDR)))
+		len += sizeof(struct fw_ofld_tx_data_wr);
+
+	return len <= MAX_IMM_TX_PKT_LEN;
 }
 
 static void send_act_open_req(struct cxgbi_sock *csk, struct sk_buff *skb,
@@ -388,13 +387,19 @@ static void send_abort_req(struct cxgbi_sock *csk)
 
 	if (unlikely(csk->state == CTP_ABORTING) || !skb || !csk->cdev)
 		return;
+
+	if (!cxgbi_sock_flag(csk, CTPF_TX_DATA_SENT)) {
+		send_tx_flowc_wr(csk);
+		cxgbi_sock_set_flag(csk, CTPF_TX_DATA_SENT);
+	}
+
 	cxgbi_sock_set_state(csk, CTP_ABORTING);
 	cxgbi_sock_set_flag(csk, CTPF_ABORT_RPL_PENDING);
 	cxgbi_sock_purge_write_queue(csk);
 
 	csk->cpl_abort_req = NULL;
 	req = (struct cpl_abort_req *)skb->head;
-	set_queue(skb, CPL_PRIORITY_DATA, csk);
+	set_wr_txq(skb, CPL_PRIORITY_DATA, csk->port_id);
 	req->cmd = CPL_ABORT_SEND_RST;
 	t4_set_arp_err_handler(skb, csk, abort_arp_failure);
 	INIT_TP_WR(req, csk->tid);
@@ -420,7 +425,7 @@ static void send_abort_rpl(struct cxgbi_sock *csk, int rst_status)
 		csk, csk->state, csk->flags, csk->tid, rst_status);
 
 	csk->cpl_abort_rpl = NULL;
-	set_queue(skb, CPL_PRIORITY_DATA, csk);
+	set_wr_txq(skb, CPL_PRIORITY_DATA, csk->port_id);
 	INIT_TP_WR(rpl, csk->tid);
 	OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_ABORT_RPL, csk->tid));
 	rpl->cmd = rst_status;
@@ -491,20 +496,40 @@ static inline unsigned int calc_tx_flits_ofld(const struct sk_buff *skb)
 	return flits + sgl_len(cnt);
 }
 
-static inline void send_tx_flowc_wr(struct cxgbi_sock *csk)
+#define FLOWC_WR_NPARAMS_MIN	9
+static inline int tx_flowc_wr_credits(int *nparamsp, int *flowclenp)
+{
+	int nparams, flowclen16, flowclen;
+
+	nparams = FLOWC_WR_NPARAMS_MIN;
+	flowclen = offsetof(struct fw_flowc_wr, mnemval[nparams]);
+	flowclen16 = DIV_ROUND_UP(flowclen, 16);
+	flowclen = flowclen16 * 16;
+	/*
+	 * Return the number of 16-byte credits used by the FlowC request.
+	 * Pass back the nparams and actual FlowC length if requested.
+	 */
+	if (nparamsp)
+		*nparamsp = nparams;
+	if (flowclenp)
+		*flowclenp = flowclen;
+
+	return flowclen16;
+}
+
+static inline int send_tx_flowc_wr(struct cxgbi_sock *csk)
 {
 	struct sk_buff *skb;
 	struct fw_flowc_wr *flowc;
-	int flowclen, i;
+	int nparams, flowclen16, flowclen;
 
-	flowclen = 80;
+	flowclen16 = tx_flowc_wr_credits(&nparams, &flowclen);
 	skb = alloc_wr(flowclen, 0, GFP_ATOMIC);
 	flowc = (struct fw_flowc_wr *)skb->head;
 	flowc->op_to_nparams =
-		htonl(FW_WR_OP_V(FW_FLOWC_WR) | FW_FLOWC_WR_NPARAMS_V(8));
+		htonl(FW_WR_OP_V(FW_FLOWC_WR) | FW_FLOWC_WR_NPARAMS_V(nparams));
 	flowc->flowid_len16 =
-		htonl(FW_WR_LEN16_V(DIV_ROUND_UP(72, 16)) |
-				FW_WR_FLOWID_V(csk->tid));
+		htonl(FW_WR_LEN16_V(flowclen16) | FW_WR_FLOWID_V(csk->tid));
 	flowc->mnemval[0].mnemonic = FW_FLOWC_MNEM_PFNVFN;
 	flowc->mnemval[0].val = htonl(csk->cdev->pfvf);
 	flowc->mnemval[1].mnemonic = FW_FLOWC_MNEM_CH;
@@ -523,12 +548,10 @@ static inline void send_tx_flowc_wr(struct cxgbi_sock *csk)
 	flowc->mnemval[7].val = htonl(csk->advmss);
 	flowc->mnemval[8].mnemonic = 0;
 	flowc->mnemval[8].val = 0;
-	for (i = 0; i < 9; i++) {
-		flowc->mnemval[i].r4[0] = 0;
-		flowc->mnemval[i].r4[1] = 0;
-		flowc->mnemval[i].r4[2] = 0;
-	}
-	set_queue(skb, CPL_PRIORITY_DATA, csk);
+	flowc->mnemval[8].mnemonic = FW_FLOWC_MNEM_TXDATAPLEN_MAX;
+	flowc->mnemval[8].val = 16384;
+
+	set_wr_txq(skb, CPL_PRIORITY_DATA, csk->port_id);
 
 	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
 		"csk 0x%p, tid 0x%x, %u,%u,%u,%u,%u,%u,%u.\n",
@@ -537,6 +560,8 @@ static inline void send_tx_flowc_wr(struct cxgbi_sock *csk)
 		csk->advmss);
 
 	cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb);
+
+	return flowclen16;
 }
 
 static inline void make_tx_data_wr(struct cxgbi_sock *csk, struct sk_buff *skb,
@@ -545,10 +570,11 @@ static inline void make_tx_data_wr(struct cxgbi_sock *csk, struct sk_buff *skb,
 	struct fw_ofld_tx_data_wr *req;
 	unsigned int submode = cxgbi_skcb_ulp_mode(skb) & 3;
 	unsigned int wr_ulp_mode = 0, val;
+	bool imm = is_ofld_imm(skb);
 
 	req = (struct fw_ofld_tx_data_wr *)__skb_push(skb, sizeof(*req));
 
-	if (is_ofld_imm(skb)) {
+	if (imm) {
 		req->op_to_immdlen = htonl(FW_WR_OP_V(FW_OFLD_TX_DATA_WR) |
 					FW_WR_COMPL_F |
 					FW_WR_IMMDLEN_V(dlen));
@@ -597,16 +623,32 @@ static int push_tx_frames(struct cxgbi_sock *csk, int req_completion)
 		int dlen = skb->len;
 		int len = skb->len;
 		unsigned int credits_needed;
+		int flowclen16 = 0;
 
 		skb_reset_transport_header(skb);
 		if (is_ofld_imm(skb))
-			credits_needed = DIV_ROUND_UP(dlen +
-					sizeof(struct fw_ofld_tx_data_wr), 16);
+			credits_needed = DIV_ROUND_UP(dlen, 16);
 		else
-			credits_needed = DIV_ROUND_UP(8*calc_tx_flits_ofld(skb)
-					+ sizeof(struct fw_ofld_tx_data_wr),
+			credits_needed = DIV_ROUND_UP(
+						8 * calc_tx_flits_ofld(skb),
+						16);
+
+		if (likely(cxgbi_skcb_test_flag(skb, SKCBF_TX_NEED_HDR)))
+			credits_needed += DIV_ROUND_UP(
+					sizeof(struct fw_ofld_tx_data_wr),
 					16);
 
+		/*
+		 * Assumes the initial credits is large enough to support
+		 * fw_flowc_wr plus largest possible first payload
+		 */
+		if (!cxgbi_sock_flag(csk, CTPF_TX_DATA_SENT)) {
+			flowclen16 = send_tx_flowc_wr(csk);
+			csk->wr_cred -= flowclen16;
+			csk->wr_una_cred += flowclen16;
+			cxgbi_sock_set_flag(csk, CTPF_TX_DATA_SENT);
+		}
+
 		if (csk->wr_cred < credits_needed) {
 			log_debug(1 << CXGBI_DBG_PDU_TX,
 				"csk 0x%p, skb %u/%u, wr %d < %u.\n",
@@ -615,8 +657,8 @@ static int push_tx_frames(struct cxgbi_sock *csk, int req_completion)
 			break;
 		}
 		__skb_unlink(skb, &csk->write_queue);
-		set_queue(skb, CPL_PRIORITY_DATA, csk);
-		skb->csum = credits_needed;
+		set_wr_txq(skb, CPL_PRIORITY_DATA, csk->port_id);
+		skb->csum = credits_needed + flowclen16;
 		csk->wr_cred -= credits_needed;
 		csk->wr_una_cred += credits_needed;
 		cxgbi_sock_enqueue_wr(csk, skb);
@@ -627,12 +669,6 @@ static int push_tx_frames(struct cxgbi_sock *csk, int req_completion)
 			csk->wr_cred, csk->wr_una_cred);
 
 		if (likely(cxgbi_skcb_test_flag(skb, SKCBF_TX_NEED_HDR))) {
-			if (!cxgbi_sock_flag(csk, CTPF_TX_DATA_SENT)) {
-				send_tx_flowc_wr(csk);
-				skb->csum += 5;
-				csk->wr_cred -= 5;
-				csk->wr_una_cred += 5;
-			}
 			len += cxgbi_ulp_extra_len(cxgbi_skcb_ulp_mode(skb));
 			make_tx_data_wr(csk, skb, dlen, len, credits_needed,
 					req_completion);
@@ -807,6 +843,13 @@ static void csk_act_open_retry_timer(unsigned long data)
 
 }
 
+static inline bool is_neg_adv(unsigned int status)
+{
+	return status == CPL_ERR_RTX_NEG_ADVICE ||
+		status == CPL_ERR_KEEPALV_NEG_ADVICE ||
+		status == CPL_ERR_PERSIST_NEG_ADVICE;
+}
+
 static void do_act_open_rpl(struct cxgbi_device *cdev, struct sk_buff *skb)
 {
 	struct cxgbi_sock *csk;
@@ -828,7 +871,7 @@ static void do_act_open_rpl(struct cxgbi_device *cdev, struct sk_buff *skb)
 		       "csk 0x%p,%u,0x%lx. ", (&csk->saddr), (&csk->daddr),
 		       atid, tid, status, csk, csk->state, csk->flags);
 
-	if (status == CPL_ERR_RTX_NEG_ADVICE)
+	if (is_neg_adv(status))
 		goto rel_skb;
 
 	module_put(THIS_MODULE);
@@ -934,8 +977,7 @@ static void do_abort_req_rss(struct cxgbi_device *cdev, struct sk_buff *skb)
 		       (&csk->saddr), (&csk->daddr),
 		       csk, csk->state, csk->flags, csk->tid, req->status);
 
-	if (req->status == CPL_ERR_RTX_NEG_ADVICE ||
-	    req->status == CPL_ERR_PERSIST_NEG_ADVICE)
+	if (is_neg_adv(req->status))
 		goto rel_skb;
 
 	cxgbi_sock_get(csk);
@@ -989,6 +1031,27 @@ rel_skb:
 	__kfree_skb(skb);
 }
 
+static void do_rx_data(struct cxgbi_device *cdev, struct sk_buff *skb)
+{
+	struct cxgbi_sock *csk;
+	struct cpl_rx_data *cpl = (struct cpl_rx_data *)skb->data;
+	unsigned int tid = GET_TID(cpl);
+	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
+	struct tid_info *t = lldi->tids;
+
+	csk = lookup_tid(t, tid);
+	if (!csk) {
+		pr_err("can't find connection for tid %u.\n", tid);
+	} else {
+		/* not expecting this, reset the connection. */
+		pr_err("csk 0x%p, tid %u, rcv cpl_rx_data.\n", csk, tid);
+		spin_lock_bh(&csk->lock);
+		send_abort_req(csk);
+		spin_unlock_bh(&csk->lock);
+	}
+	__kfree_skb(skb);
+}
+
 static void do_rx_iscsi_hdr(struct cxgbi_device *cdev, struct sk_buff *skb)
 {
 	struct cxgbi_sock *csk;
@@ -1408,6 +1471,7 @@ cxgb4i_cplhandler_func cxgb4i_cplhandlers[NUM_CPL_CMDS] = {
 	[CPL_SET_TCB_RPL] = do_set_tcb_rpl,
 	[CPL_RX_DATA_DDP] = do_rx_data_ddp,
 	[CPL_RX_ISCSI_DDP] = do_rx_data_ddp,
+	[CPL_RX_DATA] = do_rx_data,
 };
 
 int cxgb4i_ofld_init(struct cxgbi_device *cdev)
@@ -1485,7 +1549,7 @@ static int ddp_ppod_write_idata(struct cxgbi_device *cdev, unsigned int port_id,
 		return -ENOMEM;
 	}
 	req = (struct ulp_mem_io *)skb->head;
-	set_queue(skb, CPL_PRIORITY_CONTROL, NULL);
+	set_wr_txq(skb, CPL_PRIORITY_CONTROL, 0);
 
 	ulp_mem_io_set_hdr(lldi, req, wr_len, dlen, pm_addr);
 	idata = (struct ulptx_idata *)(req + 1);
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
index 7da59c3..eb58afc 100644
--- a/drivers/scsi/cxgbi/libcxgbi.c
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -2294,10 +2294,12 @@ int cxgbi_conn_xmit_pdu(struct iscsi_task *task)
 		return err;
 	}
 
-	kfree_skb(skb);
 	log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_PDU_TX,
 		"itt 0x%x, skb 0x%p, len %u/%u, xmit err %d.\n",
 		task->itt, skb, skb->len, skb->data_len, err);
+
+	kfree_skb(skb);
+
 	iscsi_conn_printk(KERN_ERR, task->conn, "xmit err %d.\n", err);
 	iscsi_conn_failure(task->conn, ISCSI_ERR_XMIT_FAILED);
 	return err;
diff --git a/drivers/scsi/cxgbi/libcxgbi.h b/drivers/scsi/cxgbi/libcxgbi.h
index 2c7cb1c..aba1af7 100644
--- a/drivers/scsi/cxgbi/libcxgbi.h
+++ b/drivers/scsi/cxgbi/libcxgbi.h
@@ -317,8 +317,8 @@ static inline void cxgbi_skcb_clear_flag(struct sk_buff *skb,
 	__clear_bit(flag, &(cxgbi_skcb_flags(skb)));
 }
 
-static inline int cxgbi_skcb_test_flag(struct sk_buff *skb,
-					enum cxgbi_skcb_flags flag)
+static inline int cxgbi_skcb_test_flag(const struct sk_buff *skb,
+				       enum cxgbi_skcb_flags flag)
 {
 	return test_bit(flag, &(cxgbi_skcb_flags(skb)));
 }