[PATCH v14 08/23] drivers: add DPAA cgrid cleanup support

[Hemant Agrawal <hemant.agrawal@nxp.com>]

From: Jun Yang <jun.yang@nxp.com>

Add qman_pending_fq_by_cgrid() to find frame queues associated with
a given CGID. This allows the driver to verify that all FQs
using a CGR are shut down before releasing the CGR ID, preventing
use-after-free of CGR resources.

Signed-off-by: Jun Yang <jun.yang@nxp.com>
Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
---
 drivers/bus/dpaa/base/qbman/qman.c       | 64 ++++++++++++++++++++++
 drivers/bus/dpaa/dpaa_bus_base_symbols.c |  2 +
 drivers/bus/dpaa/include/fsl_qman.h      | 20 +++++++
 drivers/net/dpaa/dpaa_ethdev.c           | 67 +++++++++++++++++++++++-
 4 files changed, 151 insertions(+), 2 deletions(-)

diff --git a/drivers/bus/dpaa/base/qbman/qman.c b/drivers/bus/dpaa/base/qbman/qman.c
index 2315b81065..8dd55080d8 100644
--- a/drivers/bus/dpaa/base/qbman/qman.c
+++ b/drivers/bus/dpaa/base/qbman/qman.c
@@ -2977,3 +2977,67 @@ qman_shutdown_fq(struct qman_fq *fq)
 out:
 	return ret;
 }
+
+int qman_pending_fq_by_cgrid(u32 cgrid, u32 start_fqid, u32 *fqid)
+{
+	struct qman_fq fq = {
+		.fqid = start_fqid ? start_fqid : 1
+	};
+	struct qman_cgr cgr = {
+		.cgrid = cgrid
+	};
+	struct qm_mcr_querycgr cgrd;
+	struct qm_mcr_queryfq_np np;
+	struct qm_fqd fqd;
+	int err;
+
+	/*
+	 * Check CGR itself whether anything is still queued against it.
+	 * An idle CGR has no frames from any member FQ, which is
+	 * the normal case on a clean shutdown, and let's skip the scan.
+	 *
+	 * Note qman_query_cgr() leaves i_bcnt in big endian, so only test it
+	 * against zero, which is endianness neutral.
+	 */
+	err = qman_query_cgr(&cgr, &cgrd);
+	if (err) {
+		DPAA_BUS_WARN("Failed(%d) to query cgrid(0x%x)", err, cgrid);
+		return err;
+	}
+	if (!cgrd.i_bcnt) {
+		DPAA_BUS_DEBUG("cgrid(0x%x) is idle, skip FQ scan", cgrid);
+		return -ERANGE;
+	}
+
+	DPAA_BUS_DEBUG("cgrid(0x%x) is not idle, scanning FQs", cgrid);
+
+	/* FQID space is 24 bits wide; stop before wrapping. */
+	for (; fq.fqid <= QMAN_MAX_FQID; fq.fqid++) {
+		err = qman_query_fq_np(&fq, &np);
+		if (err == -ERANGE) {
+			/*
+			 * FQID is not implemented on this device, so there is
+			 * nothing beyond it either.
+			 */
+			break;
+		} else if (err) {
+			DPAA_BUS_WARN("Failed(%d) to Query np FQ(fqid=0x%x)",
+				err, fq.fqid);
+			return err;
+		}
+		if ((np.state & QM_MCR_NP_STATE_MASK) != QM_MCR_NP_STATE_OOS) {
+			err = qman_query_fq(&fq, &fqd);
+			if (err) {
+				DPAA_BUS_WARN("Failed(%d) to Query FQ(fqid=0x%x)",
+					err, fq.fqid);
+			} else if ((fqd.fq_ctrl & QM_FQCTRL_CGE) &&
+				fqd.cgid == cgrid) {
+				if (fqid)
+					*fqid = fq.fqid;
+				return 0;
+			}
+		}
+	}
+	DPAA_BUS_INFO("No FQ found with cgrid(0x%x)", cgrid);
+	return -ERANGE;
+}
diff --git a/drivers/bus/dpaa/dpaa_bus_base_symbols.c b/drivers/bus/dpaa/dpaa_bus_base_symbols.c
index 522cdca27e..b1e5d445e3 100644
--- a/drivers/bus/dpaa/dpaa_bus_base_symbols.c
+++ b/drivers/bus/dpaa/dpaa_bus_base_symbols.c
@@ -51,10 +51,12 @@ RTE_EXPORT_INTERNAL_SYMBOL(bman_acquire)
 RTE_EXPORT_INTERNAL_SYMBOL(bman_query_free_buffers)
 RTE_EXPORT_INTERNAL_SYMBOL(bman_thread_irq)
 RTE_EXPORT_INTERNAL_SYMBOL(qman_alloc_fqid_range)
+RTE_EXPORT_INTERNAL_SYMBOL(qman_release_fqid_range)
 RTE_EXPORT_INTERNAL_SYMBOL(qman_reserve_fqid_range)
 RTE_EXPORT_INTERNAL_SYMBOL(qman_alloc_pool_range)
 RTE_EXPORT_INTERNAL_SYMBOL(qman_alloc_cgrid_range)
 RTE_EXPORT_INTERNAL_SYMBOL(qman_release_cgrid_range)
+RTE_EXPORT_INTERNAL_SYMBOL(qman_pending_fq_by_cgrid)
 RTE_EXPORT_INTERNAL_SYMBOL(dpaa_intr_enable)
 RTE_EXPORT_INTERNAL_SYMBOL(dpaa_intr_disable)
 RTE_EXPORT_INTERNAL_SYMBOL(dpaa_get_ioctl_version_number)
diff --git a/drivers/bus/dpaa/include/fsl_qman.h b/drivers/bus/dpaa/include/fsl_qman.h
index 673859ed2e..871cafb832 100644
--- a/drivers/bus/dpaa/include/fsl_qman.h
+++ b/drivers/bus/dpaa/include/fsl_qman.h
@@ -1276,6 +1276,9 @@ struct qman_cgr {
 	struct list_head node;
 };
 
+/* Maximum FQID value: frame queue IDs are 24 bits wide. */
+#define QMAN_MAX_FQID			0x00FFFFFFu
+
 /* Flags to qman_create_fq() */
 #define QMAN_FQ_FLAG_NO_ENQUEUE      0x00000001 /* can't enqueue */
 #define QMAN_FQ_FLAG_NO_MODIFY       0x00000002 /* can only enqueue */
@@ -1887,6 +1890,7 @@ static inline int qman_alloc_fqid(u32 *result)
  * This function can also be used to seed the allocator with ranges of FQIDs
  * that it can subsequently allocate from.
  */
+__rte_internal
 void qman_release_fqid_range(u32 fqid, unsigned int count);
 static inline void qman_release_fqid(u32 fqid)
 {
@@ -1907,6 +1911,22 @@ static inline int qman_shutdown_fq_by_fqid(u32 fqid)
 	return qman_shutdown_fq(&fq);
 }
 
+/**
+ * qman_pending_fq_by_cgrid - Find an FQ still attached to a CGR.
+ *
+ * @cgrid: the congestion group id to search for.
+ * @start_fqid: FQID to begin the scan from (0 or 1 means scan from the
+ *   start). A caller shutting down several stale FQs can pass the previously
+ *   returned FQID + 1 to resume the scan instead of restarting from the
+ *   beginning each time, avoiding an O(N^2) rescan.
+ * @fqid: on success, holds the FQID that is still attached to @cgrid.
+ *
+ * Return 0 and set *fqid when a matching FQ is found, -ERANGE when none is
+ * left, or a negative error code on query failure.
+ */
+__rte_internal
+int qman_pending_fq_by_cgrid(u32 cgrid, u32 start_fqid, u32 *fqid);
+
 /**
  * qman_reserve_fqid_range - Reserve the specified range of frame queue IDs
  * @fqid: the base FQID of the range to deallocate
diff --git a/drivers/net/dpaa/dpaa_ethdev.c b/drivers/net/dpaa/dpaa_ethdev.c
index 5d8fb062e2..0425288ca1 100644
--- a/drivers/net/dpaa/dpaa_ethdev.c
+++ b/drivers/net/dpaa/dpaa_ethdev.c
@@ -494,6 +494,39 @@ static int dpaa_eth_dev_stop(struct rte_eth_dev *dev)
 	return 0;
 }
 
+/* Shut down any frame queue still linked to this CGR.
+ *
+ * A CGR must have no members left when it is deleted. FQs left behind by a
+ * previous run of the application are not owned by this process, so they can
+ * only be found by asking QMan. There may be more than one, hence the loop.
+ */
+static void
+dpaa_cgr_stale_fq_cleanup(struct rte_eth_dev *dev, uint32_t cgrid,
+			  const char *dir, uint32_t idx)
+{
+	uint32_t start_fqid = 1;
+	uint32_t fqid;
+	int ret;
+
+	while (qman_pending_fq_by_cgrid(cgrid, start_fqid, &fqid) == 0) {
+		/* Should be FQ not cleaned in previous program. */
+		DPAA_PMD_DEBUG("FQ(fqid=0x%x) with %s cgid=%d is still alive?",
+			fqid, dir, cgrid);
+		ret = qman_shutdown_fq_by_fqid(fqid);
+		if (ret) {
+			DPAA_PMD_WARN("%s: Failed(%d) to shutdown %sq%d's fq(fqid=0x%x)",
+				dev->data->name, ret, dir, idx, fqid);
+			/* Do not spin on an FQ that refuses to shut down. */
+			break;
+		}
+		/* Resume the scan past the FQ just handled instead of
+		 * restarting from the beginning, which would be O(N^2) for
+		 * N stale FQs.
+		 */
+		start_fqid = fqid + 1;
+	}
+}
+
 static int dpaa_eth_dev_close(struct rte_eth_dev *dev)
 {
 	struct fman_if *fif = dev->process_private;
@@ -503,7 +536,7 @@ static int dpaa_eth_dev_close(struct rte_eth_dev *dev)
 	struct rte_eth_link *link = &dev->data->dev_link;
 	struct dpaa_if *dpaa_intf = dev->data->dev_private;
 	struct qman_fq *fq;
-	int loop;
+	uint32_t loop;
 	int ret;
 
 	PMD_INIT_FUNC_TRACE();
@@ -569,12 +602,15 @@ static int dpaa_eth_dev_close(struct rte_eth_dev *dev)
 	/* Release RX congestion Groups */
 	if (dpaa_intf->cgr_rx) {
 		for (loop = 0; loop < dpaa_intf->nb_rx_queues; loop++) {
+			dpaa_cgr_stale_fq_cleanup(dev,
+				dpaa_intf->cgr_rx[loop].cgrid, "rx", loop);
 			ret = qman_delete_cgr(&dpaa_intf->cgr_rx[loop]);
 			if (ret) {
 				DPAA_PMD_WARN("%s: delete rxq%d's cgr err(%d)",
 					dev->data->name, loop, ret);
 			}
 		}
+		qman_release_cgrid_range(dpaa_intf->cgr_rx[0].cgrid, dpaa_intf->nb_rx_queues);
 		rte_free(dpaa_intf->cgr_rx);
 		dpaa_intf->cgr_rx = NULL;
 	}
@@ -582,12 +618,16 @@ static int dpaa_eth_dev_close(struct rte_eth_dev *dev)
 	/* Release TX congestion Groups */
 	if (dpaa_intf->cgr_tx) {
 		for (loop = 0; loop < MAX_DPAA_CORES; loop++) {
+			dpaa_cgr_stale_fq_cleanup(dev,
+				dpaa_intf->cgr_tx[loop].cgrid, "tx", loop);
 			ret = qman_delete_cgr(&dpaa_intf->cgr_tx[loop]);
 			if (ret) {
 				DPAA_PMD_WARN("%s: delete txq%d's cgr err(%d)",
 					dev->data->name, loop, ret);
 			}
 		}
+		qman_release_cgrid_range(dpaa_intf->cgr_tx[0].cgrid,
+					 MAX_DPAA_CORES);
 		rte_free(dpaa_intf->cgr_tx);
 		dpaa_intf->cgr_tx = NULL;
 	}
@@ -2221,6 +2261,8 @@ dpaa_dev_init(struct rte_eth_dev *eth_dev)
 	int num_rx_fqs, fqid;
 	int loop, ret = 0;
 	int dev_id;
+	int nb_rx_cgr = 0, nb_tx_cgr = 0;
+	bool rx_cgrid_allocated = false, tx_cgrid_allocated = false;
 	struct rte_dpaa_device *dpaa_device;
 	struct dpaa_if *dpaa_intf;
 	struct fm_eth_port_cfg *cfg;
@@ -2341,6 +2383,7 @@ dpaa_dev_init(struct rte_eth_dev *eth_dev)
 			ret = -EINVAL;
 			goto free_rx;
 		}
+		rx_cgrid_allocated = true;
 	} else {
 		dpaa_intf->cgr_rx = NULL;
 	}
@@ -2370,6 +2413,8 @@ dpaa_dev_init(struct rte_eth_dev *eth_dev)
 			fqid);
 		if (ret)
 			goto free_rx;
+		if (dpaa_intf->cgr_rx)
+			nb_rx_cgr++;
 		dpaa_intf->rx_queues[loop].vsp_id = vsp_id;
 		dpaa_intf->rx_queues[loop].dpaa_intf = dpaa_intf;
 	}
@@ -2410,11 +2455,11 @@ dpaa_dev_init(struct rte_eth_dev *eth_dev)
 			ret = -EINVAL;
 			goto free_rx;
 		}
+		tx_cgrid_allocated = true;
 	} else {
 		dpaa_intf->cgr_tx = NULL;
 	}
 
-
 	for (loop = 0; loop < MAX_DPAA_CORES; loop++) {
 		if (dpaa_intf->cgr_tx)
 			dpaa_intf->cgr_tx[loop].cgrid = cgrid_tx[loop];
@@ -2425,6 +2470,8 @@ dpaa_dev_init(struct rte_eth_dev *eth_dev)
 			dpaa_intf->cgr_tx ? &dpaa_intf->cgr_tx[loop] : NULL);
 		if (ret)
 			goto free_tx;
+		if (dpaa_intf->cgr_tx)
+			nb_tx_cgr++;
 
 		if (dpaa_intf->ts_enable) {
 			ret = dpaa_tx_conf_queue_init(&dpaa_intf->tx_conf_queues[loop]);
@@ -2504,6 +2551,15 @@ dpaa_dev_init(struct rte_eth_dev *eth_dev)
 	return 0;
 
 free_tx:
+	/* Every created Tx CGR was linked into the QMan portal's cgr_cbs
+	 * list by qman_create_cgr(). Delete them before freeing cgr_tx so
+	 * the portal does not retain dangling pointers into freed memory,
+	 * then release the reserved CGRID range.
+	 */
+	for (loop = 0; loop < nb_tx_cgr; loop++)
+		qman_delete_cgr(&dpaa_intf->cgr_tx[loop]);
+	if (tx_cgrid_allocated)
+		qman_release_cgrid_range(cgrid_tx[0], MAX_DPAA_CORES);
 	rte_free(dpaa_intf->tx_conf_queues);
 	dpaa_intf->tx_conf_queues = NULL;
 	rte_free(dpaa_intf->tx_queues);
@@ -2511,8 +2567,15 @@ dpaa_dev_init(struct rte_eth_dev *eth_dev)
 	dpaa_intf->nb_tx_queues = 0;
 
 free_rx:
+	/* Same as above for the Rx CGRs. */
+	for (loop = 0; loop < nb_rx_cgr; loop++)
+		qman_delete_cgr(&dpaa_intf->cgr_rx[loop]);
+	if (rx_cgrid_allocated)
+		qman_release_cgrid_range(cgrid[0], num_rx_fqs);
 	rte_free(dpaa_intf->cgr_rx);
+	dpaa_intf->cgr_rx = NULL;
 	rte_free(dpaa_intf->cgr_tx);
+	dpaa_intf->cgr_tx = NULL;
 	rte_free(dpaa_intf->rx_queues);
 	dpaa_intf->rx_queues = NULL;
 	dpaa_intf->nb_rx_queues = 0;
-- 
2.25.1