d/numam-dpdk
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

eal: fix IOVA mode selection as VA for PCI drivers

Browse Source 
The incriminated commit broke the use of RTE_PCI_DRV_IOVA_AS_VA which
was intended to mean "driver only supports VA" but had been understood
as "driver supports both PA and VA" by most net drivers and used to let
dpdk processes to run as non root (which do not have access to physical
addresses on recent kernels).

The check on physical addresses actually closed the gap for those
drivers. We don't need to mark them with RTE_PCI_DRV_IOVA_AS_VA and this
flag can retain its intended meaning.
Document explicitly its meaning.

We can check that a driver requirement wrt to IOVA mode is fulfilled
before trying to probe a device.

Finally, document the heuristic used to select the IOVA mode and hope
that we won't break it again.

Fixes: 703458e19c ("bus/pci: consider only usable devices for IOVA mode")

Signed-off-by: David Marchand <david.marchand@redhat.com>
Reviewed-by: Jerin Jacob <jerinj@marvell.com>
Tested-by: Jerin Jacob <jerinj@marvell.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
This commit is contained in:
David Marchand 2019-07-22 14:56:51 +02:00 committed by Thomas Monjalon
parent 62f8f5ace5
commit b76fafb174
22 changed files with 110 additions and 62 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
doc/guides/prog_guide/env_abstraction_layer.rst
View File

@ -419,6 +419,37 @@ Misc Functions
Locks and atomic operations are per-architecture (i686 and x86_64).
IOVA Mode Detection
~~~~~~~~~~~~~~~~~~~
IOVA Mode is selected by considering what the current usable Devices on the
system require and/or support.
Below is the 2-step heuristic for this choice.
For the first step, EAL asks each bus its requirement in terms of IOVA mode
and decides on a preferred IOVA mode.
- if all buses report RTE_IOVA_PA, then the preferred IOVA mode is RTE_IOVA_PA,
- if all buses report RTE_IOVA_VA, then the preferred IOVA mode is RTE_IOVA_VA,
- if all buses report RTE_IOVA_DC, no bus expressed a preferrence, then the
preferred mode is RTE_IOVA_DC,
- if the buses disagree (at least one wants RTE_IOVA_PA and at least one wants
RTE_IOVA_VA), then the preferred IOVA mode is RTE_IOVA_DC (see below with the
check on Physical Addresses availability),
The second step checks if the preferred mode complies with the Physical
Addresses availability since those are only available to root user in recent
kernels.
- if the preferred mode is RTE_IOVA_PA but there is no access to Physical
Addresses, then EAL init fails early, since later probing of the devices
would fail anyway,
- if the preferred mode is RTE_IOVA_DC then based on the Physical Addresses
availability, the preferred mode is adjusted to RTE_IOVA_PA or RTE_IOVA_VA.
In the case when the buses had disagreed on the IOVA Mode at the first step,
part of the buses won't work because of this decision.
IOVA Mode Configuration
~~~~~~~~~~~~~~~~~~~~~~~

16
drivers/bus/pci/linux/pci.c
View File

@ -578,12 +578,10 @@ pci_device_iova_mode(const struct rte_pci_driver *pdrv,
else
is_vfio_noiommu_enabled = 0;
}
if ((pdrv->drv_flags & RTE_PCI_DRV_IOVA_AS_VA) == 0) {
if (is_vfio_noiommu_enabled != 0)
iova_mode = RTE_IOVA_PA;
} else if (is_vfio_noiommu_enabled != 0) {
RTE_LOG(DEBUG, EAL, "Forcing to 'PA', vfio-noiommu mode configured\n");
iova_mode = RTE_IOVA_PA;
}
else if ((pdrv->drv_flags & RTE_PCI_DRV_IOVA_AS_VA) != 0)
iova_mode = RTE_IOVA_VA;
#endif
break;
}
@ -594,8 +592,8 @@ pci_device_iova_mode(const struct rte_pci_driver *pdrv,
break;
default:
RTE_LOG(DEBUG, EAL, "Unsupported kernel driver? Defaulting to IOVA as 'PA'\n");
iova_mode = RTE_IOVA_PA;
if ((pdrv->drv_flags & RTE_PCI_DRV_IOVA_AS_VA) != 0)
iova_mode = RTE_IOVA_VA;
break;
}
@ -607,10 +605,8 @@ pci_device_iova_mode(const struct rte_pci_driver *pdrv,
if (iommu_no_va == -1)
iommu_no_va = pci_one_device_iommu_support_va(pdev)
? 0 : 1;
if (iommu_no_va != 0) {
RTE_LOG(DEBUG, EAL, "Forcing to 'PA', IOMMU does not support IOVA as 'VA'\n");
if (iommu_no_va != 0)
iova_mode = RTE_IOVA_PA;
}
}
return iova_mode;
}

30
drivers/bus/pci/pci_common.c
View File

@ -169,8 +169,22 @@ rte_pci_probe_one_driver(struct rte_pci_driver *dr,
* This needs to be before rte_pci_map_device(), as it enables to use
* driver flags for adjusting configuration.
*/
if (!already_probed)
if (!already_probed) {
enum rte_iova_mode dev_iova_mode;
enum rte_iova_mode iova_mode;
dev_iova_mode = pci_device_iova_mode(dr, dev);
iova_mode = rte_eal_iova_mode();
if (dev_iova_mode != RTE_IOVA_DC &&
dev_iova_mode != iova_mode) {
RTE_LOG(ERR, EAL, " Expecting '%s' IOVA mode but current mode is '%s', not initializing\n",
dev_iova_mode == RTE_IOVA_PA ? "PA" : "VA",
iova_mode == RTE_IOVA_PA ? "PA" : "VA");
return -EINVAL;
}
dev->driver = dr;
}
if (!already_probed && (dr->drv_flags & RTE_PCI_DRV_NEED_MAPPING)) {
/* map resources for devices that use igb_uio */
@ -629,12 +643,16 @@ rte_pci_get_iommu_class(void)
devices_want_va = true;
}
}
if (devices_want_pa) {
iova_mode = RTE_IOVA_PA;
if (devices_want_va)
RTE_LOG(WARNING, EAL, "Some devices want 'VA' but forcing 'PA' because other devices want it\n");
} else if (devices_want_va) {
if (devices_want_va && !devices_want_pa) {
iova_mode = RTE_IOVA_VA;
} else if (devices_want_pa && !devices_want_va) {
iova_mode = RTE_IOVA_PA;
} else {
iova_mode = RTE_IOVA_DC;
if (devices_want_va) {
RTE_LOG(WARNING, EAL, "Some devices want 'VA' but forcing 'DC' because other devices want 'PA'.\n");
RTE_LOG(WARNING, EAL, "Depending on the final decision by the EAL, not all devices may be able to initialize.\n");
}
}
return iova_mode;
}

4
drivers/bus/pci/rte_bus_pci.h
View File

@ -187,8 +187,8 @@ struct rte_pci_bus {
#define RTE_PCI_DRV_INTR_RMV 0x0010
/** Device driver needs to keep mapped resources if unsupported dev detected */
#define RTE_PCI_DRV_KEEP_MAPPED_RES 0x0020
/** Device driver supports IOVA as VA */
#define RTE_PCI_DRV_IOVA_AS_VA 0X0040
/** Device driver only supports IOVA as VA and cannot work with IOVA as PA */
#define RTE_PCI_DRV_IOVA_AS_VA 0x0040
/**
* Map the PCI device resources in user space virtual memory address

3
drivers/net/atlantic/atl_ethdev.c
View File

@ -157,8 +157,7 @@ static const struct rte_pci_id pci_id_atl_map[] = {
static struct rte_pci_driver rte_atl_pmd = {
.id_table = pci_id_atl_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
RTE_PCI_DRV_IOVA_AS_VA,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = eth_atl_pci_probe,
.remove = eth_atl_pci_remove,
};

3
drivers/net/bnxt/bnxt_ethdev.c
View File

@ -4028,8 +4028,7 @@ static int bnxt_pci_remove(struct rte_pci_device *pci_dev)
static struct rte_pci_driver bnxt_rte_pmd = {
.id_table = bnxt_pci_id_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING |
RTE_PCI_DRV_INTR_LSC | RTE_PCI_DRV_IOVA_AS_VA,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = bnxt_pci_probe,
.remove = bnxt_pci_remove,
};

3
drivers/net/e1000/em_ethdev.c
View File

@ -352,8 +352,7 @@ static int eth_em_pci_remove(struct rte_pci_device *pci_dev)
static struct rte_pci_driver rte_em_pmd = {
.id_table = pci_id_em_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
RTE_PCI_DRV_IOVA_AS_VA,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = eth_em_pci_probe,
.remove = eth_em_pci_remove,
};

5
drivers/net/e1000/igb_ethdev.c
View File

@ -1116,8 +1116,7 @@ static int eth_igb_pci_remove(struct rte_pci_device *pci_dev)
static struct rte_pci_driver rte_igb_pmd = {
.id_table = pci_id_igb_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
RTE_PCI_DRV_IOVA_AS_VA,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = eth_igb_pci_probe,
.remove = eth_igb_pci_remove,
};
@ -1140,7 +1139,7 @@ static int eth_igbvf_pci_remove(struct rte_pci_device *pci_dev)
*/
static struct rte_pci_driver rte_igbvf_pmd = {
.id_table = pci_id_igbvf_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_IOVA_AS_VA,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING,
.probe = eth_igbvf_pci_probe,
.remove = eth_igbvf_pci_remove,
};

3
drivers/net/enic/enic_ethdev.c
View File

@ -1247,8 +1247,7 @@ static int eth_enic_pci_remove(struct rte_pci_device *pci_dev)
static struct rte_pci_driver rte_enic_pmd = {
.id_table = pci_id_enic_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
RTE_PCI_DRV_IOVA_AS_VA,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = eth_enic_pci_probe,
.remove = eth_enic_pci_remove,
};

3
drivers/net/fm10k/fm10k_ethdev.c
View File

@ -3268,8 +3268,7 @@ static const struct rte_pci_id pci_id_fm10k_map[] = {
static struct rte_pci_driver rte_pmd_fm10k = {
.id_table = pci_id_fm10k_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
RTE_PCI_DRV_IOVA_AS_VA,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = eth_fm10k_pci_probe,
.remove = eth_fm10k_pci_remove,
};

3
drivers/net/i40e/i40e_ethdev.c
View File

@ -696,8 +696,7 @@ static int eth_i40e_pci_remove(struct rte_pci_device *pci_dev)
static struct rte_pci_driver rte_i40e_pmd = {
.id_table = pci_id_i40e_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
RTE_PCI_DRV_IOVA_AS_VA,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = eth_i40e_pci_probe,
.remove = eth_i40e_pci_remove,
};

2
drivers/net/i40e/i40e_ethdev_vf.c
View File

@ -1557,7 +1557,7 @@ static int eth_i40evf_pci_remove(struct rte_pci_device *pci_dev)
*/
static struct rte_pci_driver rte_i40evf_pmd = {
.id_table = pci_id_i40evf_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_IOVA_AS_VA,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING,
.probe = eth_i40evf_pci_probe,
.remove = eth_i40evf_pci_remove,
};

3
drivers/net/iavf/iavf_ethdev.c
View File

@ -1402,8 +1402,7 @@ static int eth_iavf_pci_remove(struct rte_pci_device *pci_dev)
/* Adaptive virtual function driver struct */
static struct rte_pci_driver rte_iavf_pmd = {
.id_table = pci_id_iavf_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
RTE_PCI_DRV_IOVA_AS_VA,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = eth_iavf_pci_probe,
.remove = eth_iavf_pci_remove,
};

3
drivers/net/ice/ice_ethdev.c
View File

@ -3737,8 +3737,7 @@ ice_pci_remove(struct rte_pci_device *pci_dev)
static struct rte_pci_driver rte_ice_pmd = {
.id_table = pci_id_ice_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
RTE_PCI_DRV_IOVA_AS_VA,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = ice_pci_probe,
.remove = ice_pci_remove,
};

5
drivers/net/ixgbe/ixgbe_ethdev.c
View File

@ -1869,8 +1869,7 @@ static int eth_ixgbe_pci_remove(struct rte_pci_device *pci_dev)
static struct rte_pci_driver rte_ixgbe_pmd = {
.id_table = pci_id_ixgbe_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
RTE_PCI_DRV_IOVA_AS_VA,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = eth_ixgbe_pci_probe,
.remove = eth_ixgbe_pci_remove,
};
@ -1892,7 +1891,7 @@ static int eth_ixgbevf_pci_remove(struct rte_pci_device *pci_dev)
*/
static struct rte_pci_driver rte_ixgbevf_pmd = {
.id_table = pci_id_ixgbevf_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_IOVA_AS_VA,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING,
.probe = eth_ixgbevf_pci_probe,
.remove = eth_ixgbevf_pci_remove,
};

3
drivers/net/mlx4/mlx4.c
View File

@ -1142,8 +1142,7 @@ static struct rte_pci_driver mlx4_driver = {
},
.id_table = mlx4_pci_id_map,
.probe = mlx4_pci_probe,
.drv_flags = RTE_PCI_DRV_INTR_LSC | RTE_PCI_DRV_INTR_RMV |
RTE_PCI_DRV_IOVA_AS_VA,
.drv_flags = RTE_PCI_DRV_INTR_LSC | RTE_PCI_DRV_INTR_RMV,
};
#ifdef RTE_IBVERBS_LINK_DLOPEN

2
drivers/net/mlx5/mlx5.c
View File

@ -2087,7 +2087,7 @@ static struct rte_pci_driver mlx5_driver = {
.dma_map = mlx5_dma_map,
.dma_unmap = mlx5_dma_unmap,
.drv_flags = RTE_PCI_DRV_INTR_LSC | RTE_PCI_DRV_INTR_RMV |
RTE_PCI_DRV_PROBE_AGAIN | RTE_PCI_DRV_IOVA_AS_VA,
RTE_PCI_DRV_PROBE_AGAIN,
};
#ifdef RTE_IBVERBS_LINK_DLOPEN

6
drivers/net/nfp/nfp_net.c
View File

@ -3760,16 +3760,14 @@ static int eth_nfp_pci_remove(struct rte_pci_device *pci_dev)
static struct rte_pci_driver rte_nfp_net_pf_pmd = {
.id_table = pci_id_nfp_pf_net_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
RTE_PCI_DRV_IOVA_AS_VA,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = nfp_pf_pci_probe,
.remove = eth_nfp_pci_remove,
};
static struct rte_pci_driver rte_nfp_net_vf_pmd = {
.id_table = pci_id_nfp_vf_net_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
RTE_PCI_DRV_IOVA_AS_VA,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = eth_nfp_pci_probe,
.remove = eth_nfp_pci_remove,
};

5
drivers/net/octeontx2/otx2_ethdev.c
View File

@ -1188,11 +1188,6 @@ otx2_nix_configure(struct rte_eth_dev *eth_dev)
goto fail;
}
if (rte_eal_iova_mode() != RTE_IOVA_VA) {
otx2_err("iova mode should be va");
goto fail;
}
if (conf->link_speeds & ETH_LINK_SPEED_FIXED) {
otx2_err("Setting link speed/duplex not supported");
goto fail;

6
drivers/net/qede/qede_ethdev.c
View File

@ -2737,8 +2737,7 @@ static int qedevf_eth_dev_pci_remove(struct rte_pci_device *pci_dev)
static struct rte_pci_driver rte_qedevf_pmd = {
.id_table = pci_id_qedevf_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
RTE_PCI_DRV_IOVA_AS_VA,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = qedevf_eth_dev_pci_probe,
.remove = qedevf_eth_dev_pci_remove,
};
@ -2757,8 +2756,7 @@ static int qede_eth_dev_pci_remove(struct rte_pci_device *pci_dev)
static struct rte_pci_driver rte_qede_pmd = {
.id_table = pci_id_qede_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
RTE_PCI_DRV_IOVA_AS_VA,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = qede_eth_dev_pci_probe,
.remove = qede_eth_dev_pci_remove,
};

3
drivers/raw/ioat/ioat_rawdev.c
View File

@ -338,8 +338,7 @@ static const struct rte_pci_id pci_id_ioat_map[] = {
static struct rte_pci_driver ioat_pmd_drv = {
.id_table = pci_id_ioat_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
RTE_PCI_DRV_IOVA_AS_VA,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = ioat_rawdev_probe,
.remove = ioat_rawdev_remove,
};

30
lib/librte_eal/common/eal_common_bus.c
View File

@ -228,13 +228,37 @@ rte_bus_find_by_device_name(const char *str)
enum rte_iova_mode
rte_bus_get_iommu_class(void)
{
int mode = RTE_IOVA_DC;
enum rte_iova_mode mode = RTE_IOVA_DC;
bool buses_want_va = false;
bool buses_want_pa = false;
struct rte_bus *bus;
TAILQ_FOREACH(bus, &rte_bus_list, next) {
enum rte_iova_mode bus_iova_mode;
if (bus->get_iommu_class)
mode |= bus->get_iommu_class();
if (bus->get_iommu_class == NULL)
continue;
bus_iova_mode = bus->get_iommu_class();
RTE_LOG(DEBUG, EAL, "Bus %s wants IOVA as '%s'\n",
bus->name,
bus_iova_mode == RTE_IOVA_DC ? "DC" :
(bus_iova_mode == RTE_IOVA_PA ? "PA" : "VA"));
if (bus_iova_mode == RTE_IOVA_PA)
buses_want_pa = true;
else if (bus_iova_mode == RTE_IOVA_VA)
buses_want_va = true;
}
if (buses_want_va && !buses_want_pa) {
mode = RTE_IOVA_VA;
} else if (buses_want_pa && !buses_want_va) {
mode = RTE_IOVA_PA;
} else {
mode = RTE_IOVA_DC;
if (buses_want_va) {
RTE_LOG(WARNING, EAL, "Some buses want 'VA' but forcing 'DC' because other buses want 'PA'.\n");
RTE_LOG(WARNING, EAL, "Depending on the final decision by the EAL, not all buses may be able to initialize.\n");
}
}
return mode;