ethdev: fix port data mismatched in multiple process model

Assume we have two virtio ports, 00:03.0 and 00:04.0. The first one is
managed by the kernel driver, while the later one is managed by DPDK.

Now we start the primary process. 00:03.0 will be skipped by DPDK virtio
PMD driver (since it's being used by the kernel). 00:04.0 would be
successfully initiated by DPDK virtio PMD (if nothing abnormal happens).
After that, we would get a port id 0, and all the related info needed
by virtio (virtio_hw) is stored at rte_eth_dev_data[0].

Then we start the secondary process. As usual, 00:03.0 will be firstly
probed. It firstly tries to get a local eth_dev structure for it (by
rte_eth_dev_allocate):

        port_id = rte_eth_dev_find_free_port();
        ...

        eth_dev = &rte_eth_devices[port_id];
        eth_dev->data = &rte_eth_dev_data[port_id];
        ...

        return eth_dev;

Since it's a first PCI device, port_id will be 0. eth_dev->data would
then point to rte_eth_dev_data[0]. And here things start going wrong,
as rte_eth_dev_data[0] actually stores the virtio_hw for 00:04.0.

That said, in the secondary process, DPDK will continue to drive PCI
device 00.03.0 (despite the fact it's been managed by kernel), with
the info from PCI device 00:04.0. Which is wrong.

The fix is to attach the port already registered by the primary process.
That is, iterate the rte_eth_dev_data[], and get the port id who's PCI
ID matches the current PCI device.

This would let us maintain same port ID for the same PCI device, keeping
the chance of referencing to wrong data minimal.

Fixes: af75078fece3 ("first public release")
Cc: stable@dpdk.org
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>

diff --git a/lib/librte_ether/rte_ethdev.c b/lib/librte_ether/rte_ethdev.c
index 222e267..0b039e1 100644 (file)
--- a/lib/librte_ether/rte_ethdev.c
+++ b/lib/librte_ether/rte_ethdev.c
@@ -189,6 +189,21 @@ rte_eth_dev_find_free_port(void)
        return RTE_MAX_ETHPORTS;
 }
 
+static struct rte_eth_dev *
+eth_dev_get(uint8_t port_id)
+{
+       struct rte_eth_dev *eth_dev = &rte_eth_devices[port_id];
+
+       eth_dev->data = &rte_eth_dev_data[port_id];
+       eth_dev->attached = DEV_ATTACHED;
+       TAILQ_INIT(&(eth_dev->link_intr_cbs));
+
+       eth_dev_last_created_port = port_id;
+       nb_ports++;
+
+       return eth_dev;
+}
+
 struct rte_eth_dev *
 rte_eth_dev_allocate(const char *name)
 {
@@ -210,17 +225,43 @@ rte_eth_dev_allocate(const char *name)
                return NULL;
        }
 
-       eth_dev = &rte_eth_devices[port_id];
-       eth_dev->data = &rte_eth_dev_data[port_id];
-       memset(eth_dev->data, 0, sizeof(*eth_dev->data));
+       memset(&rte_eth_devices[port_id], 0, sizeof(*eth_dev->data));
+       eth_dev = eth_dev_get(port_id);
        snprintf(eth_dev->data->name, sizeof(eth_dev->data->name), "%s", name);
        eth_dev->data->port_id = port_id;
        eth_dev->data->mtu = ETHER_MTU;
-       TAILQ_INIT(&(eth_dev->link_intr_cbs));
 
-       eth_dev->attached = DEV_ATTACHED;
-       eth_dev_last_created_port = port_id;
-       nb_ports++;
+       return eth_dev;
+}
+
+/*
+ * Attach to a port already registered by the primary process, which
+ * makes sure that the same device would have the same port id both
+ * in the primary and secondary process.
+ */
+static struct rte_eth_dev *
+eth_dev_attach_secondary(const char *name)
+{
+       uint8_t i;
+       struct rte_eth_dev *eth_dev;
+
+       if (rte_eth_dev_data == NULL)
+               rte_eth_dev_data_alloc();
+
+       for (i = 0; i < RTE_MAX_ETHPORTS; i++) {
+               if (strcmp(rte_eth_dev_data[i].name, name) == 0)
+                       break;
+       }
+       if (i == RTE_MAX_ETHPORTS) {
+               RTE_PMD_DEBUG_TRACE(
+                       "device %s is not driven by the primary process\n",
+                       name);
+               return NULL;
+       }
+
+       eth_dev = eth_dev_get(i);
+       RTE_ASSERT(eth_dev->data->port_id == i);
+
        return eth_dev;
 }
 
@@ -250,16 +291,28 @@ rte_eth_dev_pci_probe(struct rte_pci_driver *pci_drv,
        rte_eal_pci_device_name(&pci_dev->addr, ethdev_name,
                        sizeof(ethdev_name));
 
-       eth_dev = rte_eth_dev_allocate(ethdev_name);
-       if (eth_dev == NULL)
-               return -ENOMEM;
-
        if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+               eth_dev = rte_eth_dev_allocate(ethdev_name);
+               if (eth_dev == NULL)
+                       return -ENOMEM;
+
                eth_dev->data->dev_private = rte_zmalloc("ethdev private structure",
                                  eth_drv->dev_private_size,
                                  RTE_CACHE_LINE_SIZE);
                if (eth_dev->data->dev_private == NULL)
                        rte_panic("Cannot allocate memzone for private port data\n");
+       } else {
+               eth_dev = eth_dev_attach_secondary(ethdev_name);
+               if (eth_dev == NULL) {
+                       /*
+                        * if we failed to attach a device, it means the
+                        * device is skipped in primary process, due to
+                        * some errors. If so, we return a positive value,
+                        * to let EAL skip it for the secondary process
+                        * as well.
+                        */
+                       return 1;
+               }
        }
        eth_dev->device = &pci_dev->device;
        eth_dev->intr_handle = &pci_dev->intr_handle;