raw/ioat: support limiting queues for idxd PCI device

When using a full device instance via vfio, allow the user to specify a
maximum number of queues to configure rather than always using the max
number of supported queues.

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>

diff --git a/doc/guides/rawdevs/ioat.rst b/doc/guides/rawdevs/ioat.rst
index 250cfc4..60438cc 100644 (file)
--- a/doc/guides/rawdevs/ioat.rst
+++ b/doc/guides/rawdevs/ioat.rst
@@ -106,6 +106,14 @@ For devices bound to a suitable DPDK-supported VFIO/UIO driver, the HW devices w
 be found as part of the device scan done at application initialization time without
 the need to pass parameters to the application.
 
+For Intel\ |reg| DSA devices, DPDK will automatically configure the device with the
+maximum number of workqueues available on it, partitioning all resources equally
+among the queues.
+If fewer workqueues are required, then the ``max_queues`` parameter may be passed to
+the device driver on the EAL commandline, via the ``allowlist`` or ``-a`` flag e.g.::
+
+       $ dpdk-test -a <b:d:f>,max_queues=4
+
 If the device is bound to the IDXD kernel driver (and previously configured with sysfs),
 then a specific work queue needs to be passed to the application via a vdev parameter.
 This vdev parameter take the driver name and work queue name as parameters.

diff --git a/drivers/raw/ioat/idxd_pci.c b/drivers/raw/ioat/idxd_pci.c
index 01623f3..b48e565 100644 (file)
--- a/drivers/raw/ioat/idxd_pci.c
+++ b/drivers/raw/ioat/idxd_pci.c
@@ -4,6 +4,7 @@
 
 #include <rte_bus_pci.h>
 #include <rte_memzone.h>
+#include <rte_devargs.h>
 
 #include "ioat_private.h"
 #include "ioat_spec.h"
@@ -123,7 +124,8 @@ static const struct rte_rawdev_ops idxd_pci_ops = {
 #define IDXD_PORTAL_SIZE (4096 * 4)
 
 static int
-init_pci_device(struct rte_pci_device *dev, struct idxd_rawdev *idxd)
+init_pci_device(struct rte_pci_device *dev, struct idxd_rawdev *idxd,
+               unsigned int max_queues)
 {
        struct idxd_pci_common *pci;
        uint8_t nb_groups, nb_engines, nb_wqs;
@@ -179,6 +181,16 @@ init_pci_device(struct rte_pci_device *dev, struct idxd_rawdev *idxd)
        for (i = 0; i < nb_wqs; i++)
                idxd_get_wq_cfg(pci, i)[0] = 0;
 
+       /* limit queues if necessary */
+       if (max_queues != 0 && nb_wqs > max_queues) {
+               nb_wqs = max_queues;
+               if (nb_engines > max_queues)
+                       nb_engines = max_queues;
+               if (nb_groups > max_queues)
+                       nb_engines = max_queues;
+               IOAT_PMD_DEBUG("Limiting queues to %u", nb_wqs);
+       }
+
        /* put each engine into a separate group to avoid reordering */
        if (nb_groups > nb_engines)
                nb_groups = nb_engines;
@@ -242,12 +254,23 @@ idxd_rawdev_probe_pci(struct rte_pci_driver *drv, struct rte_pci_device *dev)
        uint8_t nb_wqs;
        int qid, ret = 0;
        char name[PCI_PRI_STR_SIZE];
+       unsigned int max_queues = 0;
 
        rte_pci_device_name(&dev->addr, name, sizeof(name));
        IOAT_PMD_INFO("Init %s on NUMA node %d", name, dev->device.numa_node);
        dev->device.driver = &drv->driver;
 
-       ret = init_pci_device(dev, &idxd);
+       if (dev->device.devargs && dev->device.devargs->args[0] != '\0') {
+               /* if the number of devargs grows beyond just 1, use rte_kvargs */
+               if (sscanf(dev->device.devargs->args,
+                               "max_queues=%u", &max_queues) != 1) {
+                       IOAT_PMD_ERR("Invalid device parameter: '%s'",
+                                       dev->device.devargs->args);
+                       return -1;
+               }
+       }
+
+       ret = init_pci_device(dev, &idxd, max_queues);
        if (ret < 0) {
                IOAT_PMD_ERR("Error initializing PCI hardware");
                return ret;
@@ -353,3 +376,4 @@ RTE_PMD_REGISTER_PCI(IDXD_PMD_RAWDEV_NAME_PCI, idxd_pmd_drv_pci);
 RTE_PMD_REGISTER_PCI_TABLE(IDXD_PMD_RAWDEV_NAME_PCI, pci_id_idxd_map);
 RTE_PMD_REGISTER_KMOD_DEP(IDXD_PMD_RAWDEV_NAME_PCI,
                          "* igb_uio | uio_pci_generic | vfio-pci");
+RTE_PMD_REGISTER_PARAM_STRING(rawdev_idxd_pci, "max_queues=0");