[RFC,v2] eal: add VFIO-PCI SR-IOV support
Checks
Commit Message
The kernel module vfio-pci introduces the VF token to enable SR-IOV
support.
The VF token can be set by a vfio-pci based PF driver and must be known
by the vfio-pci based VF driver in order to gain access to the device.
An example VF token option would take this form:
1. ./usertools/dpdk-devbind.py -b vfio-pci 0000:87:00.0
2. echo 2 > /sys/bus/pci/devices/0000:87:00.0/sriov_numvfs
3. Start the PF:
./x86_64-native-linux-gcc/app/testpmd -l 22-25 -n 4 \
-w 87:00.0,vf_token=2ab74924-c335-45f4-9b16-8569e5b08258 \
--file-prefix=pf -- -i
4. Start the VF:
./x86_64-native-linux-gcc/app/testpmd -l 26-29 -n 4 \
-w 87:02.0,vf_token=2ab74924-c335-45f4-9b16-8569e5b08258 \
--file-prefix=vf1 -- -i
Test based on vfio-pci patch: https://patchwork.ozlabs.org/cover/1253222/
Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
---
Based on RFC v1: https://patchwork.dpdk.org/patch/66281/
---
drivers/bus/pci/linux/pci_vfio.c | 56 +++++++++++++++++++++++++++++--
lib/librte_eal/freebsd/eal.c | 3 +-
lib/librte_eal/include/rte_vfio.h | 8 ++++-
lib/librte_eal/linux/eal_vfio.c | 20 +++++++++--
4 files changed, 80 insertions(+), 7 deletions(-)
Comments
> -----Original Message-----
> From: Haiyue Wang <haiyue.wang@intel.com>
> Sent: Friday, April 10, 2020 1:03 PM
> To: dev@dpdk.org; thomas@monjalon.net; Vamsi Krishna Attunuru
> <vattunuru@marvell.com>; Jerin Jacob Kollanukkaran <jerinj@marvell.com>;
> alex.williamson@redhat.com; david.marchand@redhat.com
> Cc: Haiyue Wang <haiyue.wang@intel.com>
> Subject: [EXT] [RFC v2] eal: add VFIO-PCI SR-IOV support
>
> External Email
>
> ----------------------------------------------------------------------
> The kernel module vfio-pci introduces the VF token to enable SR-IOV
> support.
>
> The VF token can be set by a vfio-pci based PF driver and must be known by
> the vfio-pci based VF driver in order to gain access to the device.
>
> An example VF token option would take this form:
>
> 1. ./usertools/dpdk-devbind.py -b vfio-pci 0000:87:00.0
>
> 2. echo 2 > /sys/bus/pci/devices/0000:87:00.0/sriov_numvfs
>
> 3. Start the PF:
> ./x86_64-native-linux-gcc/app/testpmd -l 22-25 -n 4 \
> -w 87:00.0,vf_token=2ab74924-c335-45f4-9b16-8569e5b08258 \
> --file-prefix=pf -- -i
>
> 4. Start the VF:
> ./x86_64-native-linux-gcc/app/testpmd -l 26-29 -n 4 \
> -w 87:02.0,vf_token=2ab74924-c335-45f4-9b16-8569e5b08258 \
> --file-prefix=vf1 -- -i
>
> Test based on vfio-pci patch:
> https://urldefense.proofpoint.com/v2/url?u=https-
> 3A__patchwork.ozlabs.org_cover_1253222_&d=DwIDAg&c=nKjWec2b6R0m
> OyPaz7xtfQ&r=WllrYaumVkxaWjgKto6E_rtDQshhIhik2jkvzFyRhW8&m=SFD0o
> TfFgnU88wT2X7qMWRDen3KFV8oSOlqz3WQm3nI&s=CU2jxKUsy4oiI26apob
> DF8BJebDrheBiu3eKlF3e76E&e=
>
> Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
> ---
> Based on RFC v1: https://urldefense.proofpoint.com/v2/url?u=https-
> 3A__patchwork.dpdk.org_patch_66281_&d=DwIDAg&c=nKjWec2b6R0mOyP
> az7xtfQ&r=WllrYaumVkxaWjgKto6E_rtDQshhIhik2jkvzFyRhW8&m=SFD0oTfFg
> nU88wT2X7qMWRDen3KFV8oSOlqz3WQm3nI&s=3dHnLcXpkRVOZs6wdZQylc
> Je0oNNBs77hXE6SOuLO7o&e=
> ---
> drivers/bus/pci/linux/pci_vfio.c | 56 +++++++++++++++++++++++++++++--
> lib/librte_eal/freebsd/eal.c | 3 +-
> lib/librte_eal/include/rte_vfio.h | 8 ++++-
> lib/librte_eal/linux/eal_vfio.c | 20 +++++++++--
> 4 files changed, 80 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/bus/pci/linux/pci_vfio.c b/drivers/bus/pci/linux/pci_vfio.c
> index 64cd84a68..7f99337c7 100644
> --- a/drivers/bus/pci/linux/pci_vfio.c
> +++ b/drivers/bus/pci/linux/pci_vfio.c
> @@ -11,6 +11,7 @@
> #include <sys/mman.h>
> #include <stdbool.h>
>
> +#include <rte_devargs.h>
> #include <rte_log.h>
> #include <rte_pci.h>
> #include <rte_bus_pci.h>
> @@ -644,11 +645,59 @@ pci_vfio_msix_is_mappable(int vfio_dev_fd, int
> msix_region)
> return ret;
> }
>
> +static void
> +vfio_pci_vf_token_arg(struct rte_devargs *devargs, rte_uuid_t uu) {
> +#define VF_TOKEN_ARG "vf_token="
> + char c, *p, *vf_token;
> +
> + if (devargs == NULL)
> + return;
> +
> + p = strstr(devargs->args, VF_TOKEN_ARG);
> + if (!p)
> + return;
> +
> + vf_token = p + strlen(VF_TOKEN_ARG);
> + if (strlen(vf_token) < (RTE_UUID_STRLEN - 1))
> + return;
> +
> + c = vf_token[RTE_UUID_STRLEN - 1];
> + if (c != '\0' && c != ',')
> + return;
> +
> + vf_token[RTE_UUID_STRLEN - 1] = '\0';
> + if (rte_uuid_parse(vf_token, uu)) {
> + RTE_LOG(ERR, EAL,
> + "The VF token is not a valid uuid : %s\n", vf_token);
> + vf_token[RTE_UUID_STRLEN - 1] = c;
> + return;
> + }
> +
> + RTE_LOG(DEBUG, EAL,
> + "The VF token is found : %s\n", vf_token);
> +
> + vf_token[RTE_UUID_STRLEN - 1] = c;
> +
> + /* Purge this vfio-pci specific token from the device arguments */
> + if (c != '\0') {
> + /* 1. Handle the case : 'vf_token=uuid,arg1=val1' */
> + memmove(p, vf_token + RTE_UUID_STRLEN,
> + strlen(vf_token + RTE_UUID_STRLEN) + 1);
> + } else {
> + /* 2. Handle the case : 'arg1=val1,vf_token=uuid' */
> + if (p != devargs->args)
> + p--;
> +
> + *p = '\0';
> + }
> +}
>
> static int
> pci_vfio_map_resource_primary(struct rte_pci_device *dev) {
> struct vfio_device_info device_info = { .argsz = sizeof(device_info) };
> + rte_uuid_t vf_token = RTE_UUID_INIT(0, 0, 0, 0, 0ULL);
> char pci_addr[PATH_MAX] = {0};
> int vfio_dev_fd;
> struct rte_pci_addr *loc = &dev->addr; @@ -668,8 +717,9 @@
> pci_vfio_map_resource_primary(struct rte_pci_device *dev)
> snprintf(pci_addr, sizeof(pci_addr), PCI_PRI_FMT,
> loc->domain, loc->bus, loc->devid, loc->function);
>
> + vfio_pci_vf_token_arg(dev->device.devargs, vf_token);
> ret = rte_vfio_setup_device(rte_pci_get_sysfs_path(), pci_addr,
> - &vfio_dev_fd, &device_info);
> + &vfio_dev_fd, &device_info,
> vf_token);
> if (ret)
> return ret;
>
> @@ -797,6 +847,7 @@ static int
> pci_vfio_map_resource_secondary(struct rte_pci_device *dev) {
> struct vfio_device_info device_info = { .argsz = sizeof(device_info) };
> + rte_uuid_t vf_token = RTE_UUID_INIT(0, 0, 0, 0, 0ULL);
> char pci_addr[PATH_MAX] = {0};
> int vfio_dev_fd;
> struct rte_pci_addr *loc = &dev->addr; @@ -830,8 +881,9 @@
> pci_vfio_map_resource_secondary(struct rte_pci_device *dev)
> return -1;
> }
>
> + vfio_pci_vf_token_arg(dev->device.devargs, vf_token);
> ret = rte_vfio_setup_device(rte_pci_get_sysfs_path(), pci_addr,
> - &vfio_dev_fd, &device_info);
> + &vfio_dev_fd, &device_info,
> vf_token);
> if (ret)
> return ret;
>
> diff --git a/lib/librte_eal/freebsd/eal.c b/lib/librte_eal/freebsd/eal.c index
> 6ae37e7e6..cbb4c400e 100644
> --- a/lib/librte_eal/freebsd/eal.c
> +++ b/lib/librte_eal/freebsd/eal.c
> @@ -995,7 +995,8 @@ rte_eal_vfio_intr_mode(void) int
> rte_vfio_setup_device(__rte_unused const char *sysfs_base,
> __rte_unused const char *dev_addr,
> __rte_unused int *vfio_dev_fd,
> - __rte_unused struct vfio_device_info *device_info)
> + __rte_unused struct vfio_device_info *device_info
> + __rte_unused rte_uuid_t vf_token)
> {
> return -1;
> }
> diff --git a/lib/librte_eal/include/rte_vfio.h b/lib/librte_eal/include/rte_vfio.h
> index 20ed8c45a..1f9e22d82 100644
> --- a/lib/librte_eal/include/rte_vfio.h
> +++ b/lib/librte_eal/include/rte_vfio.h
> @@ -16,6 +16,8 @@ extern "C" {
>
> #include <stdint.h>
>
> +#include <rte_uuid.h>
> +
> /*
> * determine if VFIO is present on the system
> */
> @@ -102,13 +104,17 @@ struct vfio_device_info;
> * @param device_info
> * Device information.
> *
> + * @param vf_token
> + * VF token.
> + *
> * @return
> * 0 on success.
> * <0 on failure.
> * >1 if the device cannot be managed this way.
> */
> int rte_vfio_setup_device(const char *sysfs_base, const char *dev_addr,
> - int *vfio_dev_fd, struct vfio_device_info *device_info);
> + int *vfio_dev_fd, struct vfio_device_info *device_info,
> + rte_uuid_t vf_token);
>
> /**
> * Release a device mapped to a VFIO-managed I/O MMU group.
> diff --git a/lib/librte_eal/linux/eal_vfio.c b/lib/librte_eal/linux/eal_vfio.c
> index 4502aefed..8c0ad04e5 100644
> --- a/lib/librte_eal/linux/eal_vfio.c
> +++ b/lib/librte_eal/linux/eal_vfio.c
> @@ -702,7 +702,8 @@ rte_vfio_clear_group(int vfio_group_fd)
>
> int
> rte_vfio_setup_device(const char *sysfs_base, const char *dev_addr,
> - int *vfio_dev_fd, struct vfio_device_info *device_info)
> + int *vfio_dev_fd, struct vfio_device_info *device_info,
> + rte_uuid_t vf_token)
> {
> struct vfio_group_status group_status = {
> .argsz = sizeof(group_status)
> @@ -712,6 +713,7 @@ rte_vfio_setup_device(const char *sysfs_base, const
> char *dev_addr,
> int vfio_container_fd;
> int vfio_group_fd;
> int iommu_group_num;
> + char dev[PATH_MAX];
> int i, ret;
>
> /* get group number */
> @@ -895,8 +897,19 @@ rte_vfio_setup_device(const char *sysfs_base,
> const char *dev_addr,
> t->type_id, t->name);
> }
>
> + if (!rte_uuid_is_null(vf_token)) {
> + char vf_token_str[RTE_UUID_STRLEN];
> +
> + rte_uuid_unparse(vf_token, vf_token_str,
> sizeof(vf_token_str));
> + snprintf(dev, sizeof(dev),
> + "%s vf_token=%s", dev_addr, vf_token_str);
> + } else {
> + snprintf(dev, sizeof(dev),
> + "%s", dev_addr);
> + }
> +
> /* get a file descriptor for the device */
> - *vfio_dev_fd = ioctl(vfio_group_fd, VFIO_GROUP_GET_DEVICE_FD,
> dev_addr);
> + *vfio_dev_fd = ioctl(vfio_group_fd, VFIO_GROUP_GET_DEVICE_FD,
> dev);
> if (*vfio_dev_fd < 0) {
> /* if we cannot get a device fd, this implies a problem with
> * the VFIO group or the container not having IOMMU
> configured.
> @@ -2081,7 +2094,8 @@ int
> rte_vfio_setup_device(__rte_unused const char *sysfs_base,
> __rte_unused const char *dev_addr,
> __rte_unused int *vfio_dev_fd,
> - __rte_unused struct vfio_device_info *device_info)
> + __rte_unused struct vfio_device_info *device_info
> + __rte_unused rte_uuid_t vf_token)
> {
> return -1;
> }
> --
> 2.26.0
Acked-by: Vamsi Attunuru <vattunuru@marvell.com>
@@ -11,6 +11,7 @@
#include <sys/mman.h>
#include <stdbool.h>
+#include <rte_devargs.h>
#include <rte_log.h>
#include <rte_pci.h>
#include <rte_bus_pci.h>
@@ -644,11 +645,59 @@ pci_vfio_msix_is_mappable(int vfio_dev_fd, int msix_region)
return ret;
}
+static void
+vfio_pci_vf_token_arg(struct rte_devargs *devargs, rte_uuid_t uu)
+{
+#define VF_TOKEN_ARG "vf_token="
+ char c, *p, *vf_token;
+
+ if (devargs == NULL)
+ return;
+
+ p = strstr(devargs->args, VF_TOKEN_ARG);
+ if (!p)
+ return;
+
+ vf_token = p + strlen(VF_TOKEN_ARG);
+ if (strlen(vf_token) < (RTE_UUID_STRLEN - 1))
+ return;
+
+ c = vf_token[RTE_UUID_STRLEN - 1];
+ if (c != '\0' && c != ',')
+ return;
+
+ vf_token[RTE_UUID_STRLEN - 1] = '\0';
+ if (rte_uuid_parse(vf_token, uu)) {
+ RTE_LOG(ERR, EAL,
+ "The VF token is not a valid uuid : %s\n", vf_token);
+ vf_token[RTE_UUID_STRLEN - 1] = c;
+ return;
+ }
+
+ RTE_LOG(DEBUG, EAL,
+ "The VF token is found : %s\n", vf_token);
+
+ vf_token[RTE_UUID_STRLEN - 1] = c;
+
+ /* Purge this vfio-pci specific token from the device arguments */
+ if (c != '\0') {
+ /* 1. Handle the case : 'vf_token=uuid,arg1=val1' */
+ memmove(p, vf_token + RTE_UUID_STRLEN,
+ strlen(vf_token + RTE_UUID_STRLEN) + 1);
+ } else {
+ /* 2. Handle the case : 'arg1=val1,vf_token=uuid' */
+ if (p != devargs->args)
+ p--;
+
+ *p = '\0';
+ }
+}
static int
pci_vfio_map_resource_primary(struct rte_pci_device *dev)
{
struct vfio_device_info device_info = { .argsz = sizeof(device_info) };
+ rte_uuid_t vf_token = RTE_UUID_INIT(0, 0, 0, 0, 0ULL);
char pci_addr[PATH_MAX] = {0};
int vfio_dev_fd;
struct rte_pci_addr *loc = &dev->addr;
@@ -668,8 +717,9 @@ pci_vfio_map_resource_primary(struct rte_pci_device *dev)
snprintf(pci_addr, sizeof(pci_addr), PCI_PRI_FMT,
loc->domain, loc->bus, loc->devid, loc->function);
+ vfio_pci_vf_token_arg(dev->device.devargs, vf_token);
ret = rte_vfio_setup_device(rte_pci_get_sysfs_path(), pci_addr,
- &vfio_dev_fd, &device_info);
+ &vfio_dev_fd, &device_info, vf_token);
if (ret)
return ret;
@@ -797,6 +847,7 @@ static int
pci_vfio_map_resource_secondary(struct rte_pci_device *dev)
{
struct vfio_device_info device_info = { .argsz = sizeof(device_info) };
+ rte_uuid_t vf_token = RTE_UUID_INIT(0, 0, 0, 0, 0ULL);
char pci_addr[PATH_MAX] = {0};
int vfio_dev_fd;
struct rte_pci_addr *loc = &dev->addr;
@@ -830,8 +881,9 @@ pci_vfio_map_resource_secondary(struct rte_pci_device *dev)
return -1;
}
+ vfio_pci_vf_token_arg(dev->device.devargs, vf_token);
ret = rte_vfio_setup_device(rte_pci_get_sysfs_path(), pci_addr,
- &vfio_dev_fd, &device_info);
+ &vfio_dev_fd, &device_info, vf_token);
if (ret)
return ret;
@@ -995,7 +995,8 @@ rte_eal_vfio_intr_mode(void)
int rte_vfio_setup_device(__rte_unused const char *sysfs_base,
__rte_unused const char *dev_addr,
__rte_unused int *vfio_dev_fd,
- __rte_unused struct vfio_device_info *device_info)
+ __rte_unused struct vfio_device_info *device_info
+ __rte_unused rte_uuid_t vf_token)
{
return -1;
}
@@ -16,6 +16,8 @@ extern "C" {
#include <stdint.h>
+#include <rte_uuid.h>
+
/*
* determine if VFIO is present on the system
*/
@@ -102,13 +104,17 @@ struct vfio_device_info;
* @param device_info
* Device information.
*
+ * @param vf_token
+ * VF token.
+ *
* @return
* 0 on success.
* <0 on failure.
* >1 if the device cannot be managed this way.
*/
int rte_vfio_setup_device(const char *sysfs_base, const char *dev_addr,
- int *vfio_dev_fd, struct vfio_device_info *device_info);
+ int *vfio_dev_fd, struct vfio_device_info *device_info,
+ rte_uuid_t vf_token);
/**
* Release a device mapped to a VFIO-managed I/O MMU group.
@@ -702,7 +702,8 @@ rte_vfio_clear_group(int vfio_group_fd)
int
rte_vfio_setup_device(const char *sysfs_base, const char *dev_addr,
- int *vfio_dev_fd, struct vfio_device_info *device_info)
+ int *vfio_dev_fd, struct vfio_device_info *device_info,
+ rte_uuid_t vf_token)
{
struct vfio_group_status group_status = {
.argsz = sizeof(group_status)
@@ -712,6 +713,7 @@ rte_vfio_setup_device(const char *sysfs_base, const char *dev_addr,
int vfio_container_fd;
int vfio_group_fd;
int iommu_group_num;
+ char dev[PATH_MAX];
int i, ret;
/* get group number */
@@ -895,8 +897,19 @@ rte_vfio_setup_device(const char *sysfs_base, const char *dev_addr,
t->type_id, t->name);
}
+ if (!rte_uuid_is_null(vf_token)) {
+ char vf_token_str[RTE_UUID_STRLEN];
+
+ rte_uuid_unparse(vf_token, vf_token_str, sizeof(vf_token_str));
+ snprintf(dev, sizeof(dev),
+ "%s vf_token=%s", dev_addr, vf_token_str);
+ } else {
+ snprintf(dev, sizeof(dev),
+ "%s", dev_addr);
+ }
+
/* get a file descriptor for the device */
- *vfio_dev_fd = ioctl(vfio_group_fd, VFIO_GROUP_GET_DEVICE_FD, dev_addr);
+ *vfio_dev_fd = ioctl(vfio_group_fd, VFIO_GROUP_GET_DEVICE_FD, dev);
if (*vfio_dev_fd < 0) {
/* if we cannot get a device fd, this implies a problem with
* the VFIO group or the container not having IOMMU configured.
@@ -2081,7 +2094,8 @@ int
rte_vfio_setup_device(__rte_unused const char *sysfs_base,
__rte_unused const char *dev_addr,
__rte_unused int *vfio_dev_fd,
- __rte_unused struct vfio_device_info *device_info)
+ __rte_unused struct vfio_device_info *device_info
+ __rte_unused rte_uuid_t vf_token)
{
return -1;
}