[v1] net/mlx5: fix probe failure with secondary bonding member
Checks
Commit Message
Users can probe primary or secondary PCIe id when bonding is
configured.
1. -a 0a:00.0,representor=pf[0-1]vf[0-1], PMD probes 5 ports
totally: bonding device plus 4 representor ports.
2. -a 0a:00.1,representor=pf[0-1]vf[0-1], PMD only probes 2
representor ports.
Under the 2nd condition, bonding IB device doesn't have the same
PCIe id and PMD needs to check bonding relationship otherwise
probe failure.
Fixes: 6856efa54eea ("net/mlx5: fix PF leak on PCI probing failure")
Cc: stable@dpdk.org
Signed-off-by: Rongwei Liu <rongweil@nvidia.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
---
drivers/common/mlx5/linux/mlx5_common_os.c | 26 ++++++++++++++++------
drivers/net/mlx5/linux/mlx5_os.c | 24 ++++++++++----------
2 files changed, 31 insertions(+), 19 deletions(-)
Comments
Hi,
> -----Original Message-----
> From: Rongwei Liu <rongweil@nvidia.com>
> Sent: Wednesday, April 6, 2022 10:12 AM
> To: Matan Azrad <matan@nvidia.com>; Slava Ovsiienko
> <viacheslavo@nvidia.com>; Ori Kam <orika@nvidia.com>; NBU-Contact-
> Thomas Monjalon (EXTERNAL) <thomas@monjalon.net>; Michael Baum
> <michaelba@nvidia.com>
> Cc: dev@dpdk.org; Raslan Darawsheh <rasland@nvidia.com>;
> stable@dpdk.org
> Subject: [PATCH v1] net/mlx5: fix probe failure with secondary bonding
> member
>
> Users can probe primary or secondary PCIe id when bonding is
> configured.
> 1. -a 0a:00.0,representor=pf[0-1]vf[0-1], PMD probes 5 ports
> totally: bonding device plus 4 representor ports.
> 2. -a 0a:00.1,representor=pf[0-1]vf[0-1], PMD only probes 2
> representor ports.
>
> Under the 2nd condition, bonding IB device doesn't have the same
> PCIe id and PMD needs to check bonding relationship otherwise
> probe failure.
>
> Fixes: 6856efa54eea ("net/mlx5: fix PF leak on PCI probing failure")
> Cc: stable@dpdk.org
>
> Signed-off-by: Rongwei Liu <rongweil@nvidia.com>
> Acked-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
Patch applied to next-net-mlx,
Kindest regards,
Raslan Darawsheh
@@ -559,21 +559,33 @@ mlx5_os_get_ibv_device(const struct rte_pci_addr *addr)
int n;
struct ibv_device **ibv_list = mlx5_glue->get_device_list(&n);
struct ibv_device *ibv_match = NULL;
+ uint8_t guid1[32] = {0};
+ uint8_t guid2[32] = {0};
+ int ret1, ret2 = -1;
+ struct rte_pci_addr paddr;
- if (ibv_list == NULL) {
+ if (ibv_list == NULL || !n) {
rte_errno = ENOSYS;
+ if (ibv_list)
+ mlx5_glue->free_device_list(ibv_list);
return NULL;
}
+ ret1 = mlx5_get_device_guid(addr, guid1, sizeof(guid1));
while (n-- > 0) {
- struct rte_pci_addr paddr;
-
DRV_LOG(DEBUG, "Checking device \"%s\"..", ibv_list[n]->name);
if (mlx5_get_pci_addr(ibv_list[n]->ibdev_path, &paddr) != 0)
continue;
- if (rte_pci_addr_cmp(addr, &paddr) != 0)
- continue;
- ibv_match = ibv_list[n];
- break;
+ if (ret1 > 0)
+ ret2 = mlx5_get_device_guid(&paddr, guid2, sizeof(guid2));
+ /* Bond device can bond secondary PCIe */
+ if ((strstr(ibv_list[n]->name, "bond") &&
+ ((ret1 > 0 && ret2 > 0 && !memcmp(guid1, guid2, sizeof(guid1))) ||
+ (addr->domain == paddr.domain && addr->bus == paddr.bus &&
+ addr->devid == paddr.devid))) ||
+ !rte_pci_addr_cmp(addr, &paddr)) {
+ ibv_match = ibv_list[n];
+ break;
+ }
}
if (ibv_match == NULL) {
DRV_LOG(WARNING,
@@ -1979,9 +1979,9 @@ mlx5_os_pci_probe_pf(struct mlx5_common_device *cdev,
if (!nd) {
/* No device matches, just complain and bail out. */
DRV_LOG(WARNING,
- "No Verbs device matches PCI device " PCI_PRI_FMT ","
+ "PF %u doesn't have Verbs device matches PCI device " PCI_PRI_FMT ","
" are kernel drivers loaded?",
- owner_pci.domain, owner_pci.bus,
+ owner_id, owner_pci.domain, owner_pci.bus,
owner_pci.devid, owner_pci.function);
rte_errno = ENOENT;
ret = -rte_errno;
@@ -2387,16 +2387,16 @@ mlx5_os_pci_probe(struct mlx5_common_device *cdev,
for (p = 0; p < eth_da.nb_ports; p++) {
ret = mlx5_os_pci_probe_pf(cdev, ð_da,
eth_da.ports[p], mkvlist);
- if (ret)
- break;
- }
- if (ret) {
- DRV_LOG(ERR, "Probe of PCI device " PCI_PRI_FMT " "
- "aborted due to prodding failure of PF %u",
- pci_dev->addr.domain, pci_dev->addr.bus,
- pci_dev->addr.devid, pci_dev->addr.function,
- eth_da.ports[p]);
- mlx5_net_remove(cdev);
+ if (ret) {
+ DRV_LOG(INFO, "Probe of PCI device " PCI_PRI_FMT " "
+ "aborted due to proding failure of PF %u",
+ pci_dev->addr.domain, pci_dev->addr.bus,
+ pci_dev->addr.devid, pci_dev->addr.function,
+ eth_da.ports[p]);
+ mlx5_net_remove(cdev);
+ if (p != 0)
+ break;
+ }
}
} else {
ret = mlx5_os_pci_probe_pf(cdev, ð_da, 0, mkvlist);