Merge branch 'net-qed-qede-various-stability-fixes'

Alexander Lobakin says:

====================
net: qed/qede: various stability fixes

This set addresses several near-critical issues that were observed
and reproduced on different test and production configurations.

v2:
 - don't split the "Fixes:" tag across several lines in patch 9;
 - no functional changes.
====================

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

drivers/net/ethernet/qlogic/qed/qed_cxt.c

@@ -271,7 +271,7 @@ static void qed_cxt_qm_iids(struct qed_hwfn *p_hwfn,
 		vf_tids += segs[NUM_TASK_PF_SEGMENTS].count;
 	}
 
-	iids->vf_cids += vf_cids * p_mngr->vf_count;
+	iids->vf_cids = vf_cids;
 	iids->tids += vf_tids * p_mngr->vf_count;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_ILT,
@@ -465,6 +465,20 @@ static struct qed_ilt_cli_blk *qed_cxt_set_blk(struct qed_ilt_cli_blk *p_blk)
 	return p_blk;
 }
 
+static void qed_cxt_ilt_blk_reset(struct qed_hwfn *p_hwfn)
+{
+	struct qed_ilt_client_cfg *clients = p_hwfn->p_cxt_mngr->clients;
+	u32 cli_idx, blk_idx;
+
+	for (cli_idx = 0; cli_idx < MAX_ILT_CLIENTS; cli_idx++) {
+		for (blk_idx = 0; blk_idx < ILT_CLI_PF_BLOCKS; blk_idx++)
+			clients[cli_idx].pf_blks[blk_idx].total_size = 0;
+
+		for (blk_idx = 0; blk_idx < ILT_CLI_VF_BLOCKS; blk_idx++)
+			clients[cli_idx].vf_blks[blk_idx].total_size = 0;
+	}
+}
+
 int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn, u32 *line_count)
 {
 	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
@@ -484,6 +498,11 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn, u32 *line_count)
 
 	p_mngr->pf_start_line = RESC_START(p_hwfn, QED_ILT);
 
+	/* Reset all ILT blocks at the beginning of ILT computing in order
+	 * to prevent memory allocation for irrelevant blocks afterwards.
+	 */
+	qed_cxt_ilt_blk_reset(p_hwfn);
+
 	DP_VERBOSE(p_hwfn, QED_MSG_ILT,
 		   "hwfn [%d] - Set context manager starting line to be 0x%08x\n",
 		   p_hwfn->my_id, p_hwfn->p_cxt_mngr->pf_start_line);

drivers/net/ethernet/qlogic/qed/qed_dev.c

@@ -980,7 +980,7 @@ int qed_llh_add_mac_filter(struct qed_dev *cdev,
 	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
 	struct qed_ptt *p_ptt = qed_ptt_acquire(p_hwfn);
 	union qed_llh_filter filter = {};
-	u8 filter_idx, abs_ppfid;
+	u8 filter_idx, abs_ppfid = 0;
 	u32 high, low, ref_cnt;
 	int rc = 0;
 
@@ -1368,6 +1368,8 @@ static void qed_dbg_user_data_free(struct qed_hwfn *p_hwfn)
 
 void qed_resc_free(struct qed_dev *cdev)
 {
+	struct qed_rdma_info *rdma_info;
+	struct qed_hwfn *p_hwfn;
 	int i;
 
 	if (IS_VF(cdev)) {
@@ -1385,7 +1387,8 @@ void qed_resc_free(struct qed_dev *cdev)
 	qed_llh_free(cdev);
 
 	for_each_hwfn(cdev, i) {
-		struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
+		p_hwfn = cdev->hwfns + i;
+		rdma_info = p_hwfn->p_rdma_info;
 
 		qed_cxt_mngr_free(p_hwfn);
 		qed_qm_info_free(p_hwfn);
@@ -1404,8 +1407,10 @@ void qed_resc_free(struct qed_dev *cdev)
 			qed_ooo_free(p_hwfn);
 		}
 
-		if (QED_IS_RDMA_PERSONALITY(p_hwfn))
+		if (QED_IS_RDMA_PERSONALITY(p_hwfn) && rdma_info) {
+			qed_spq_unregister_async_cb(p_hwfn, rdma_info->proto);
 			qed_rdma_info_free(p_hwfn);
+		}
 
 		qed_iov_free(p_hwfn);
 		qed_l2_free(p_hwfn);

drivers/net/ethernet/qlogic/qed/qed_iwarp.c

@@ -2836,8 +2836,6 @@ int qed_iwarp_stop(struct qed_hwfn *p_hwfn)
 	if (rc)
 		return rc;
 
-	qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_IWARP);
-
 	return qed_iwarp_ll2_stop(p_hwfn);
 }
 

drivers/net/ethernet/qlogic/qed/qed_roce.c

@@ -113,7 +113,6 @@ void qed_roce_stop(struct qed_hwfn *p_hwfn)
 			break;
 		}
 	}
-	qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_ROCE);
 }
 
 static void qed_rdma_copy_gids(struct qed_rdma_qp *qp, __le32 *src_gid,

drivers/net/ethernet/qlogic/qed/qed_vf.c

@@ -81,12 +81,17 @@ static void qed_vf_pf_req_end(struct qed_hwfn *p_hwfn, int req_status)
 	mutex_unlock(&(p_hwfn->vf_iov_info->mutex));
 }
 
+#define QED_VF_CHANNEL_USLEEP_ITERATIONS	90
+#define QED_VF_CHANNEL_USLEEP_DELAY		100
+#define QED_VF_CHANNEL_MSLEEP_ITERATIONS	10
+#define QED_VF_CHANNEL_MSLEEP_DELAY		25
+
 static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done, u32 resp_size)
 {
 	union vfpf_tlvs *p_req = p_hwfn->vf_iov_info->vf2pf_request;
 	struct ustorm_trigger_vf_zone trigger;
 	struct ustorm_vf_zone *zone_data;
-	int rc = 0, time = 100;
+	int iter, rc = 0;
 
 	zone_data = (struct ustorm_vf_zone *)PXP_VF_BAR0_START_USDM_ZONE_B;
 
@@ -126,11 +131,19 @@ static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done, u32 resp_size)
 	REG_WR(p_hwfn, (uintptr_t)&zone_data->trigger, *((u32 *)&trigger));
 
 	/* When PF would be done with the response, it would write back to the
-	 * `done' address. Poll until then.
+	 * `done' address from a coherent DMA zone. Poll until then.
 	 */
-	while ((!*done) && time) {
+
-		msleep(25);
+	iter = QED_VF_CHANNEL_USLEEP_ITERATIONS;
-		time--;
+	while (!*done && iter--) {
+		udelay(QED_VF_CHANNEL_USLEEP_DELAY);
+		dma_rmb();
+	}
+
+	iter = QED_VF_CHANNEL_MSLEEP_ITERATIONS;
+	while (!*done && iter--) {
+		msleep(QED_VF_CHANNEL_MSLEEP_DELAY);
+		dma_rmb();
 	}
 
 	if (!*done) {

drivers/net/ethernet/qlogic/qede/qede_main.c

@@ -1229,7 +1229,7 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
 
 	/* PTP not supported on VFs */
 	if (!is_vf)
-		qede_ptp_enable(edev, (mode == QEDE_PROBE_NORMAL));
+		qede_ptp_enable(edev);
 
 	edev->ops->register_ops(cdev, &qede_ll_ops, edev);
 
@@ -1318,6 +1318,7 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
 	if (system_state == SYSTEM_POWER_OFF)
 		return;
 	qed_ops->common->remove(cdev);
+	edev->cdev = NULL;
 
 	/* Since this can happen out-of-sync with other flows,
 	 * don't release the netdevice until after slowpath stop

drivers/net/ethernet/qlogic/qede/qede_ptp.c

@@ -412,6 +412,7 @@ void qede_ptp_disable(struct qede_dev *edev)
 	if (ptp->tx_skb) {
 		dev_kfree_skb_any(ptp->tx_skb);
 		ptp->tx_skb = NULL;
+		clear_bit_unlock(QEDE_FLAGS_PTP_TX_IN_PRORGESS, &edev->flags);
 	}
 
 	/* Disable PTP in HW */
@@ -423,7 +424,7 @@ void qede_ptp_disable(struct qede_dev *edev)
 	edev->ptp = NULL;
 }
 
-static int qede_ptp_init(struct qede_dev *edev, bool init_tc)
+static int qede_ptp_init(struct qede_dev *edev)
 {
 	struct qede_ptp *ptp;
 	int rc;
@@ -444,25 +445,19 @@ static int qede_ptp_init(struct qede_dev *edev, bool init_tc)
 	/* Init work queue for Tx timestamping */
 	INIT_WORK(&ptp->work, qede_ptp_task);
 
-	/* Init cyclecounter and timecounter. This is done only in the first
+	/* Init cyclecounter and timecounter */
-	 * load. If done in every load, PTP application will fail when doing
+	memset(&ptp->cc, 0, sizeof(ptp->cc));
-	 * unload / load (e.g. MTU change) while it is running.
+	ptp->cc.read = qede_ptp_read_cc;
-	 */
+	ptp->cc.mask = CYCLECOUNTER_MASK(64);
-	if (init_tc) {
+	ptp->cc.shift = 0;
-		memset(&ptp->cc, 0, sizeof(ptp->cc));
+	ptp->cc.mult = 1;
-		ptp->cc.read = qede_ptp_read_cc;
-		ptp->cc.mask = CYCLECOUNTER_MASK(64);
-		ptp->cc.shift = 0;
-		ptp->cc.mult = 1;
 
-		timecounter_init(&ptp->tc, &ptp->cc,
+	timecounter_init(&ptp->tc, &ptp->cc, ktime_to_ns(ktime_get_real()));
-				 ktime_to_ns(ktime_get_real()));
-	}
 
-	return rc;
+	return 0;
 }
 
-int qede_ptp_enable(struct qede_dev *edev, bool init_tc)
+int qede_ptp_enable(struct qede_dev *edev)
 {
 	struct qede_ptp *ptp;
 	int rc;
@@ -483,7 +478,7 @@ int qede_ptp_enable(struct qede_dev *edev, bool init_tc)
 
 	edev->ptp = ptp;
 
-	rc = qede_ptp_init(edev, init_tc);
+	rc = qede_ptp_init(edev);
 	if (rc)
 		goto err1;
 

drivers/net/ethernet/qlogic/qede/qede_ptp.h

@@ -41,7 +41,7 @@ void qede_ptp_rx_ts(struct qede_dev *edev, struct sk_buff *skb);
 void qede_ptp_tx_ts(struct qede_dev *edev, struct sk_buff *skb);
 int qede_ptp_hw_ts(struct qede_dev *edev, struct ifreq *req);
 void qede_ptp_disable(struct qede_dev *edev);
-int qede_ptp_enable(struct qede_dev *edev, bool init_tc);
+int qede_ptp_enable(struct qede_dev *edev);
 int qede_ptp_get_ts_info(struct qede_dev *edev, struct ethtool_ts_info *ts);
 
 static inline void qede_ptp_record_rx_ts(struct qede_dev *edev,

drivers/net/ethernet/qlogic/qede/qede_rdma.c

@@ -105,6 +105,7 @@ static void qede_rdma_destroy_wq(struct qede_dev *edev)
 
 	qede_rdma_cleanup_event(edev);
 	destroy_workqueue(edev->rdma_info.rdma_wq);
+	edev->rdma_info.rdma_wq = NULL;
 }
 
 int qede_rdma_dev_add(struct qede_dev *edev, bool recovery)
@@ -325,7 +326,7 @@ static void qede_rdma_add_event(struct qede_dev *edev,
 	if (edev->rdma_info.exp_recovery)
 		return;
 
-	if (!edev->rdma_info.qedr_dev)
+	if (!edev->rdma_info.qedr_dev || !edev->rdma_info.rdma_wq)
 		return;
 
 	/* We don't want the cleanup flow to start while we're allocating and

include/linux/qed/qed_chain.h

@@ -207,28 +207,34 @@ static inline u32 qed_chain_get_cons_idx_u32(struct qed_chain *p_chain)
 
 static inline u16 qed_chain_get_elem_left(struct qed_chain *p_chain)
 {
+	u16 elem_per_page = p_chain->elem_per_page;
+	u32 prod = p_chain->u.chain16.prod_idx;
+	u32 cons = p_chain->u.chain16.cons_idx;
 	u16 used;
 
-	used = (u16) (((u32)0x10000 +
+	if (prod < cons)
-		       (u32)p_chain->u.chain16.prod_idx) -
+		prod += (u32)U16_MAX + 1;
-		      (u32)p_chain->u.chain16.cons_idx);
+
+	used = (u16)(prod - cons);
 	if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR)
-		used -= p_chain->u.chain16.prod_idx / p_chain->elem_per_page -
+		used -= prod / elem_per_page - cons / elem_per_page;
-		    p_chain->u.chain16.cons_idx / p_chain->elem_per_page;
 
 	return (u16)(p_chain->capacity - used);
 }
 
 static inline u32 qed_chain_get_elem_left_u32(struct qed_chain *p_chain)
 {
+	u16 elem_per_page = p_chain->elem_per_page;
+	u64 prod = p_chain->u.chain32.prod_idx;
+	u64 cons = p_chain->u.chain32.cons_idx;
 	u32 used;
 
-	used = (u32) (((u64)0x100000000ULL +
+	if (prod < cons)
-		       (u64)p_chain->u.chain32.prod_idx) -
+		prod += (u64)U32_MAX + 1;
-		      (u64)p_chain->u.chain32.cons_idx);
+
+	used = (u32)(prod - cons);
 	if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR)
-		used -= p_chain->u.chain32.prod_idx / p_chain->elem_per_page -
+		used -= (u32)(prod / elem_per_page - cons / elem_per_page);
-		    p_chain->u.chain32.cons_idx / p_chain->elem_per_page;
 
 	return p_chain->capacity - used;
 }