Re: [dpdk-dev] [PATCH v8 2/5] add IOVA -VA support in KNI lib

[Andrew Rybchenko <arybchenko@solarflare.com>]

On 7/23/19 8:38 AM, vattunuru@marvell.com wrote:
> From: Vamsi Attunuru <vattunuru@marvell.com>
>
> Current KNI implementation only operates in IOVA=PA mode, patch adds
> required functionality in KNI lib to support IOVA=VA mode.
>
> KNI kernel module requires device info to get iommu domain related
> information for IOVA addr related translations. Patch defines device
> related info in rte_kni_device_info struct and passes device info to
> kernel KNI module when IOVA=VA mode is enabled.
>
> Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
> Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>

<...>

> diff --git a/lib/librte_kni/Makefile b/lib/librte_kni/Makefile
> index cbd6599..ab15d10 100644
> --- a/lib/librte_kni/Makefile
> +++ b/lib/librte_kni/Makefile
> @@ -7,6 +7,7 @@ include $(RTE_SDK)/mk/rte.vars.mk
>   LIB = librte_kni.a
>   
>   CFLAGS += $(WERROR_FLAGS) -I$(SRCDIR) -O3 -fno-strict-aliasing
> +CFLAGS += -I$(RTE_SDK)/drivers/bus/pci
>   LDLIBS += -lrte_eal -lrte_mempool -lrte_mbuf -lrte_ethdev
>   
>   EXPORT_MAP := rte_kni_version.map
> diff --git a/lib/librte_kni/meson.build b/lib/librte_kni/meson.build
> index 41fa2e3..fd46f87 100644
> --- a/lib/librte_kni/meson.build
> +++ b/lib/librte_kni/meson.build
> @@ -9,3 +9,4 @@ version = 2
>   sources = files('rte_kni.c')
>   headers = files('rte_kni.h')
>   deps += ['ethdev', 'pci']

Not directly related to the patch, but are mempool and mbuf
dependencies lost here. Cc Bruce to comment.
The library uses rte_mempool_obj_iter() and rte_pktmbuf_free()
(which uses rte_mbuf_sanity_check()).

> +includes += include_directories('../../drivers/bus/pci')
> diff --git a/lib/librte_kni/rte_kni.c b/lib/librte_kni/rte_kni.c
> index 4b51fb4..ae17075 100644
> --- a/lib/librte_kni/rte_kni.c
> +++ b/lib/librte_kni/rte_kni.c
> @@ -14,6 +14,7 @@
>   #include <rte_spinlock.h>
>   #include <rte_string_fns.h>
>   #include <rte_ethdev.h>
> +#include <rte_bus_pci.h>
>   #include <rte_malloc.h>
>   #include <rte_log.h>
>   #include <rte_kni.h>
> @@ -199,6 +200,26 @@ kni_release_mz(struct rte_kni *kni)
>   	rte_memzone_free(kni->m_sync_addr);
>   }
>   
> +static void
> +kni_dev_pci_addr_get(struct rte_pci_addr *addr,
> +		    struct rte_pci_id *id, uint16_t port_id)

Please, consider to make port_id the first argument.
It is mandatory input argument which is used as a key
to fill in other two output arguments.

> +{
> +	const struct rte_pci_device *pci_dev;
> +	const struct rte_bus *bus = NULL;
> +	struct rte_eth_dev_info dev_info;
> +
> +	memset(&dev_info, 0, sizeof(dev_info));

Most likely not required even now, but for sure not required
if the patch [1] applied.

[1] http://patches.dpdk.org/patch/56959/

> +	rte_eth_dev_info_get(port_id, &dev_info);
> +
> +	if (dev_info.device)
> +		bus = rte_bus_find_by_device(dev_info.device);
> +	if (bus && !strcmp(bus->name, "pci")) {
> +		pci_dev = RTE_DEV_TO_PCI(dev_info.device);
> +		*addr = pci_dev->addr;
> +		*id = pci_dev->id;

I think it would be better to always init addr and id in
the function. Otherwise caller does not know when it is
initialized or not.

> +	}
> +}
> +
>   struct rte_kni *
>   rte_kni_alloc(struct rte_mempool *pktmbuf_pool,
>   	      const struct rte_kni_conf *conf,
> @@ -247,6 +268,19 @@ rte_kni_alloc(struct rte_mempool *pktmbuf_pool,
>   		kni->ops.port_id = UINT16_MAX;
>   
>   	memset(&dev_info, 0, sizeof(dev_info));
> +
> +	if (rte_eal_iova_mode() == RTE_IOVA_VA) {
> +		uint16_t port_id = conf->group_id;
> +		struct rte_pci_addr addr = { 0 };
> +		struct rte_pci_id id = { 0 };

If addr and id are always initialized in kni_dev_pci_addr_get()
init here would be not required.

> +
> +		kni_dev_pci_addr_get(&addr, &id, port_id);
> +		dev_info.bus = addr.bus;
> +		dev_info.devid = addr.devid;
> +		dev_info.function = addr.function;
> +		dev_info.vendor_id = id.vendor_id;
> +		dev_info.device_id = id.device_id;
> +	}
>   	dev_info.core_id = conf->core_id;
>   	dev_info.force_bind = conf->force_bind;
>   	dev_info.group_id = conf->group_id;
> @@ -300,6 +334,8 @@ rte_kni_alloc(struct rte_mempool *pktmbuf_pool,
>   	kni->group_id = conf->group_id;
>   	kni->mbuf_size = conf->mbuf_size;
>   
> +	dev_info.iova_mode = (rte_eal_iova_mode() == RTE_IOVA_VA) ? 1 : 0;
> +
>   	ret = ioctl(kni_fd, RTE_KNI_IOCTL_CREATE, &dev_info);
>   	if (ret < 0)
>   		goto ioctl_fail;