* [PATCH RESEND net-next v3 01/18] netdevsim: Add max_vfs to bus_dev
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
@ 2021-06-02 12:17 ` dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 02/18] netdevsim: Disable VFs on nsim_dev_reload_destroy() call dlinkin
` (18 subsequent siblings)
19 siblings, 0 replies; 28+ messages in thread
From: dlinkin @ 2021-06-02 12:17 UTC (permalink / raw)
To: netdev
Cc: davem, kuba, jiri, stephen, dsahern, vladbu, parav, huyn,
Dmytro Linkin, Yuval Avnery
From: Dmytro Linkin <dlinkin@nvidia.com>
Currently there is no limit to the number of VFs netdevsim can enable.
In a real systems this value exist and used by the driver.
Fore example, some features might need to consider this value when
allocating memory.
Expose max_vfs variable to debugfs as configurable resource. If are VFs
configured (num_vfs != 0) then changing of max_vfs not allowed.
Co-developed-by: Yuval Avnery <yuvalav@nvidia.com>
Signed-off-by: Yuval Avnery <yuvalav@nvidia.com>
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
drivers/net/netdevsim/bus.c | 99 +++++++++++++++++++++++++++++++++++----
drivers/net/netdevsim/dev.c | 13 +++++
drivers/net/netdevsim/netdevsim.h | 10 ++++
3 files changed, 113 insertions(+), 9 deletions(-)
diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c
index 0e95116..4bd7ef3c 100644
--- a/drivers/net/netdevsim/bus.c
+++ b/drivers/net/netdevsim/bus.c
@@ -27,9 +27,9 @@ static struct nsim_bus_dev *to_nsim_bus_dev(struct device *dev)
static int nsim_bus_dev_vfs_enable(struct nsim_bus_dev *nsim_bus_dev,
unsigned int num_vfs)
{
- nsim_bus_dev->vfconfigs = kcalloc(num_vfs,
- sizeof(struct nsim_vf_config),
- GFP_KERNEL | __GFP_NOWARN);
+ if (nsim_bus_dev->max_vfs < num_vfs)
+ return -ENOMEM;
+
if (!nsim_bus_dev->vfconfigs)
return -ENOMEM;
nsim_bus_dev->num_vfs = num_vfs;
@@ -39,8 +39,6 @@ static int nsim_bus_dev_vfs_enable(struct nsim_bus_dev *nsim_bus_dev,
static void nsim_bus_dev_vfs_disable(struct nsim_bus_dev *nsim_bus_dev)
{
- kfree(nsim_bus_dev->vfconfigs);
- nsim_bus_dev->vfconfigs = NULL;
nsim_bus_dev->num_vfs = 0;
}
@@ -56,7 +54,7 @@ static void nsim_bus_dev_vfs_disable(struct nsim_bus_dev *nsim_bus_dev)
if (ret)
return ret;
- rtnl_lock();
+ mutex_lock(&nsim_bus_dev->vfs_lock);
if (nsim_bus_dev->num_vfs == num_vfs)
goto exit_good;
if (nsim_bus_dev->num_vfs && num_vfs) {
@@ -74,7 +72,7 @@ static void nsim_bus_dev_vfs_disable(struct nsim_bus_dev *nsim_bus_dev)
exit_good:
ret = count;
exit_unlock:
- rtnl_unlock();
+ mutex_unlock(&nsim_bus_dev->vfs_lock);
return ret;
}
@@ -92,6 +90,73 @@ static void nsim_bus_dev_vfs_disable(struct nsim_bus_dev *nsim_bus_dev)
__ATTR(sriov_numvfs, 0664, nsim_bus_dev_numvfs_show,
nsim_bus_dev_numvfs_store);
+ssize_t nsim_bus_dev_max_vfs_read(struct file *file,
+ char __user *data,
+ size_t count, loff_t *ppos)
+{
+ struct nsim_bus_dev *nsim_bus_dev = file->private_data;
+ char buf[11];
+ size_t len;
+
+ len = snprintf(buf, sizeof(buf), "%u\n", nsim_bus_dev->max_vfs);
+ if (len < 0)
+ return len;
+
+ return simple_read_from_buffer(data, count, ppos, buf, len);
+}
+
+ssize_t nsim_bus_dev_max_vfs_write(struct file *file,
+ const char __user *data,
+ size_t count, loff_t *ppos)
+{
+ struct nsim_bus_dev *nsim_bus_dev = file->private_data;
+ struct nsim_vf_config *vfconfigs;
+ ssize_t ret;
+ char buf[10];
+ u32 val;
+
+ if (*ppos != 0)
+ return 0;
+
+ if (count >= sizeof(buf))
+ return -ENOSPC;
+
+ mutex_lock(&nsim_bus_dev->vfs_lock);
+ /* Reject if VFs are configured */
+ if (nsim_bus_dev->num_vfs) {
+ ret = -EBUSY;
+ goto unlock;
+ }
+
+ ret = copy_from_user(buf, data, count);
+ if (ret) {
+ ret = -EFAULT;
+ goto unlock;
+ }
+
+ buf[count] = '\0';
+ ret = kstrtouint(buf, 10, &val);
+ if (ret) {
+ ret = -EIO;
+ goto unlock;
+ }
+
+ vfconfigs = kcalloc(val, sizeof(struct nsim_vf_config), GFP_KERNEL | __GFP_NOWARN);
+ if (!vfconfigs) {
+ ret = -ENOMEM;
+ goto unlock;
+ }
+
+ kfree(nsim_bus_dev->vfconfigs);
+ nsim_bus_dev->vfconfigs = vfconfigs;
+ nsim_bus_dev->max_vfs = val;
+ *ppos += count;
+ ret = count;
+unlock:
+ mutex_unlock(&nsim_bus_dev->vfs_lock);
+ return ret;
+}
+
static ssize_t
new_port_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
@@ -311,6 +376,8 @@ static int nsim_num_vf(struct device *dev)
.num_vf = nsim_num_vf,
};
+#define NSIM_BUS_DEV_MAX_VFS 4
+
static struct nsim_bus_dev *
nsim_bus_dev_new(unsigned int id, unsigned int port_count)
{
@@ -329,15 +396,28 @@ static int nsim_num_vf(struct device *dev)
nsim_bus_dev->dev.type = &nsim_bus_dev_type;
nsim_bus_dev->port_count = port_count;
nsim_bus_dev->initial_net = current->nsproxy->net_ns;
+ nsim_bus_dev->max_vfs = NSIM_BUS_DEV_MAX_VFS;
mutex_init(&nsim_bus_dev->nsim_bus_reload_lock);
+ mutex_init(&nsim_bus_dev->vfs_lock);
/* Disallow using nsim_bus_dev */
smp_store_release(&nsim_bus_dev->init, false);
- err = device_register(&nsim_bus_dev->dev);
- if (err)
+ nsim_bus_dev->vfconfigs = kcalloc(nsim_bus_dev->max_vfs,
+ sizeof(struct nsim_vf_config),
+ GFP_KERNEL | __GFP_NOWARN);
+ if (!nsim_bus_dev->vfconfigs) {
+ err = -ENOMEM;
goto err_nsim_bus_dev_id_free;
+ }
+
+ err = device_register(&nsim_bus_dev->dev);
+ if (err)
+ goto err_nsim_vfs_free;
+
return nsim_bus_dev;
+err_nsim_vfs_free:
+ kfree(nsim_bus_dev->vfconfigs);
err_nsim_bus_dev_id_free:
ida_free(&nsim_bus_dev_ids, nsim_bus_dev->dev.id);
err_nsim_bus_dev_free:
@@ -351,6 +431,7 @@ static void nsim_bus_dev_del(struct nsim_bus_dev *nsim_bus_dev)
smp_store_release(&nsim_bus_dev->init, false);
device_unregister(&nsim_bus_dev->dev);
ida_free(&nsim_bus_dev_ids, nsim_bus_dev->dev.id);
+ kfree(nsim_bus_dev->vfconfigs);
kfree(nsim_bus_dev);
}
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 6189a4c..12df93a 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -192,6 +192,14 @@ static ssize_t nsim_dev_trap_fa_cookie_write(struct file *file,
.owner = THIS_MODULE,
};
+static const struct file_operations nsim_dev_max_vfs_fops = {
+ .open = simple_open,
+ .read = nsim_bus_dev_max_vfs_read,
+ .write = nsim_bus_dev_max_vfs_write,
+ .llseek = generic_file_llseek,
+ .owner = THIS_MODULE,
+};
+
static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev)
{
char dev_ddir_name[sizeof(DRV_NAME) + 10];
@@ -231,6 +239,11 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev)
debugfs_create_bool("fail_trap_policer_counter_get", 0600,
nsim_dev->ddir,
&nsim_dev->fail_trap_policer_counter_get);
+ nsim_dev->max_vfs = debugfs_create_file("max_vfs",
+ 0600,
+ nsim_dev->ddir,
+ nsim_dev->nsim_bus_dev,
+ &nsim_dev_max_vfs_fops);
nsim_udp_tunnels_debugfs_create(nsim_dev);
return 0;
}
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 7ff24e0..12f56f2 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -212,6 +212,7 @@ struct nsim_dev {
struct dentry *ddir;
struct dentry *ports_ddir;
struct dentry *take_snapshot;
+ struct dentry *max_vfs;
struct bpf_offload_dev *bpf_dev;
bool bpf_bind_accept;
bool bpf_bind_verifier_accept;
@@ -269,6 +270,13 @@ struct nsim_fib_data *nsim_fib_create(struct devlink *devlink,
u64 nsim_fib_get_val(struct nsim_fib_data *fib_data,
enum nsim_resource_id res_id, bool max);
+ssize_t nsim_bus_dev_max_vfs_read(struct file *file,
+ char __user *data,
+ size_t count, loff_t *ppos);
+ssize_t nsim_bus_dev_max_vfs_write(struct file *file,
+ const char __user *data,
+ size_t count, loff_t *ppos);
+
#if IS_ENABLED(CONFIG_XFRM_OFFLOAD)
void nsim_ipsec_init(struct netdevsim *ns);
void nsim_ipsec_teardown(struct netdevsim *ns);
@@ -308,7 +316,9 @@ struct nsim_bus_dev {
struct net *initial_net; /* Purpose of this is to carry net pointer
* during the probe time only.
*/
+ unsigned int max_vfs;
unsigned int num_vfs;
+ struct mutex vfs_lock; /* Protects vfconfigs */
struct nsim_vf_config *vfconfigs;
/* Lock for devlink->reload_enabled in netdevsim module */
struct mutex nsim_bus_reload_lock;
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND net-next v3 02/18] netdevsim: Disable VFs on nsim_dev_reload_destroy() call
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 01/18] netdevsim: Add max_vfs to bus_dev dlinkin
@ 2021-06-02 12:17 ` dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 03/18] netdevsim: Implement port types and indexing dlinkin
` (17 subsequent siblings)
19 siblings, 0 replies; 28+ messages in thread
From: dlinkin @ 2021-06-02 12:17 UTC (permalink / raw)
To: netdev
Cc: davem, kuba, jiri, stephen, dsahern, vladbu, parav, huyn, Dmytro Linkin
From: Dmytro Linkin <dlinkin@nvidia.com>
Move VFs disabling from device release() to nsim_dev_reload_destroy() to
make VFs disabling and ports removal simultaneous.
This is a requirement for VFs ports implemented in next patches.
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
drivers/net/netdevsim/bus.c | 5 +----
drivers/net/netdevsim/dev.c | 6 ++++++
drivers/net/netdevsim/netdevsim.h | 1 +
3 files changed, 8 insertions(+), 4 deletions(-)
diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c
index 4bd7ef3c..d5c547c 100644
--- a/drivers/net/netdevsim/bus.c
+++ b/drivers/net/netdevsim/bus.c
@@ -37,7 +37,7 @@ static int nsim_bus_dev_vfs_enable(struct nsim_bus_dev *nsim_bus_dev,
return 0;
}
-static void nsim_bus_dev_vfs_disable(struct nsim_bus_dev *nsim_bus_dev)
+void nsim_bus_dev_vfs_disable(struct nsim_bus_dev *nsim_bus_dev)
{
nsim_bus_dev->num_vfs = 0;
}
@@ -233,9 +233,6 @@ ssize_t nsim_bus_dev_max_vfs_write(struct file *file,
static void nsim_bus_dev_release(struct device *dev)
{
- struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev);
-
- nsim_bus_dev_vfs_disable(nsim_bus_dev);
}
static struct device_type nsim_bus_dev_type = {
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 12df93a..cd50c05 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -1182,6 +1182,12 @@ static void nsim_dev_reload_destroy(struct nsim_dev *nsim_dev)
if (devlink_is_reload_failed(devlink))
return;
debugfs_remove(nsim_dev->take_snapshot);
+
+ mutex_lock(&nsim_dev->nsim_bus_dev->vfs_lock);
+ if (nsim_dev->nsim_bus_dev->num_vfs)
+ nsim_bus_dev_vfs_disable(nsim_dev->nsim_bus_dev);
+ mutex_unlock(&nsim_dev->nsim_bus_dev->vfs_lock);
+
nsim_dev_port_del_all(nsim_dev);
nsim_dev_psample_exit(nsim_dev);
nsim_dev_health_exit(nsim_dev);
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 12f56f2..a1b49c8 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -276,6 +276,7 @@ ssize_t nsim_bus_dev_max_vfs_read(struct file *file,
ssize_t nsim_bus_dev_max_vfs_write(struct file *file,
const char __user *data,
size_t count, loff_t *ppos);
+void nsim_bus_dev_vfs_disable(struct nsim_bus_dev *nsim_bus_dev);
#if IS_ENABLED(CONFIG_XFRM_OFFLOAD)
void nsim_ipsec_init(struct netdevsim *ns);
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND net-next v3 03/18] netdevsim: Implement port types and indexing
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 01/18] netdevsim: Add max_vfs to bus_dev dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 02/18] netdevsim: Disable VFs on nsim_dev_reload_destroy() call dlinkin
@ 2021-06-02 12:17 ` dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 04/18] netdevsim: Implement VFs dlinkin
` (16 subsequent siblings)
19 siblings, 0 replies; 28+ messages in thread
From: dlinkin @ 2021-06-02 12:17 UTC (permalink / raw)
To: netdev
Cc: davem, kuba, jiri, stephen, dsahern, vladbu, parav, huyn, Dmytro Linkin
From: Dmytro Linkin <dlinkin@nvidia.com>
Define type of ports, which netdevsim driver currently operates with as
PF. Define new port type - VF, which will be implemented in following
patches. Add helper functions to distinguish them. Add helper function
to get VF index from port index.
Add port indexing logic where PFs' indexes starts from 0, VFs' - from
NSIM_DEV_VF_PORT_INDEX_BASE.
All ports uses same index pool, which means that PF port may be created
with index from VFs' indexes range.
Maximum number of VFs, which the driver can allocate, is limited by
UINT_MAX - BASE.
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
drivers/net/netdevsim/bus.c | 10 ++++++++--
drivers/net/netdevsim/dev.c | 42 +++++++++++++++++++++++++++++----------
drivers/net/netdevsim/netdevsim.h | 20 +++++++++++++++++++
3 files changed, 60 insertions(+), 12 deletions(-)
diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c
index d5c547c..e29146d 100644
--- a/drivers/net/netdevsim/bus.c
+++ b/drivers/net/netdevsim/bus.c
@@ -141,6 +141,12 @@ ssize_t nsim_bus_dev_max_vfs_write(struct file *file,
goto unlock;
}
+ /* max_vfs limited by the maximum number of provided port indexes */
+ if (val > NSIM_DEV_VF_PORT_INDEX_MAX - NSIM_DEV_VF_PORT_INDEX_BASE) {
+ ret = -ERANGE;
+ goto unlock;
+ }
+
vfconfigs = kcalloc(val, sizeof(struct nsim_vf_config), GFP_KERNEL | __GFP_NOWARN);
if (!vfconfigs) {
ret = -ENOMEM;
@@ -178,7 +184,7 @@ ssize_t nsim_bus_dev_max_vfs_write(struct file *file,
mutex_lock(&nsim_bus_dev->nsim_bus_reload_lock);
devlink_reload_disable(devlink);
- ret = nsim_dev_port_add(nsim_bus_dev, port_index);
+ ret = nsim_dev_port_add(nsim_bus_dev, NSIM_DEV_PORT_TYPE_PF, port_index);
devlink_reload_enable(devlink);
mutex_unlock(&nsim_bus_dev->nsim_bus_reload_lock);
return ret ? ret : count;
@@ -207,7 +213,7 @@ ssize_t nsim_bus_dev_max_vfs_write(struct file *file,
mutex_lock(&nsim_bus_dev->nsim_bus_reload_lock);
devlink_reload_disable(devlink);
- ret = nsim_dev_port_del(nsim_bus_dev, port_index);
+ ret = nsim_dev_port_del(nsim_bus_dev, NSIM_DEV_PORT_TYPE_PF, port_index);
devlink_reload_enable(devlink);
mutex_unlock(&nsim_bus_dev->nsim_bus_reload_lock);
return ret ? ret : count;
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index cd50c05..93d6f3d 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -35,6 +35,25 @@
#include "netdevsim.h"
+static unsigned int
+nsim_dev_port_index(enum nsim_dev_port_type type, unsigned int port_index)
+{
+ switch (type) {
+ case NSIM_DEV_PORT_TYPE_VF:
+ port_index = NSIM_DEV_VF_PORT_INDEX_BASE + port_index;
+ break;
+ case NSIM_DEV_PORT_TYPE_PF:
+ break;
+ }
+
+ return port_index;
+}
+
+static inline unsigned int nsim_dev_port_index_to_vf_index(unsigned int port_index)
+{
+ return port_index - NSIM_DEV_VF_PORT_INDEX_BASE;
+}
+
static struct dentry *nsim_dev_ddir;
#define NSIM_DEV_DUMMY_REGION_SIZE (1024 * 32)
@@ -923,7 +942,7 @@ static int nsim_dev_devlink_trap_init(struct devlink *devlink,
#define NSIM_DEV_MAX_MACS_DEFAULT 32
#define NSIM_DEV_TEST1_DEFAULT true
-static int __nsim_dev_port_add(struct nsim_dev *nsim_dev,
+static int __nsim_dev_port_add(struct nsim_dev *nsim_dev, enum nsim_dev_port_type type,
unsigned int port_index)
{
struct devlink_port_attrs attrs = {};
@@ -934,7 +953,8 @@ static int __nsim_dev_port_add(struct nsim_dev *nsim_dev,
nsim_dev_port = kzalloc(sizeof(*nsim_dev_port), GFP_KERNEL);
if (!nsim_dev_port)
return -ENOMEM;
- nsim_dev_port->port_index = port_index;
+ nsim_dev_port->port_index = nsim_dev_port_index(type, port_index);
+ nsim_dev_port->port_type = type;
devlink_port = &nsim_dev_port->devlink_port;
attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
@@ -943,7 +963,7 @@ static int __nsim_dev_port_add(struct nsim_dev *nsim_dev,
attrs.switch_id.id_len = nsim_dev->switch_id.id_len;
devlink_port_attrs_set(devlink_port, &attrs);
err = devlink_port_register(priv_to_devlink(nsim_dev), devlink_port,
- port_index);
+ nsim_dev_port->port_index);
if (err)
goto err_port_free;
@@ -1000,7 +1020,7 @@ static int nsim_dev_port_add_all(struct nsim_dev *nsim_dev,
int i, err;
for (i = 0; i < port_count; i++) {
- err = __nsim_dev_port_add(nsim_dev, i);
+ err = __nsim_dev_port_add(nsim_dev, NSIM_DEV_PORT_TYPE_PF, i);
if (err)
goto err_port_del_all;
}
@@ -1216,32 +1236,34 @@ void nsim_dev_remove(struct nsim_bus_dev *nsim_bus_dev)
}
static struct nsim_dev_port *
-__nsim_dev_port_lookup(struct nsim_dev *nsim_dev, unsigned int port_index)
+__nsim_dev_port_lookup(struct nsim_dev *nsim_dev, enum nsim_dev_port_type type,
+ unsigned int port_index)
{
struct nsim_dev_port *nsim_dev_port;
+ port_index = nsim_dev_port_index(type, port_index);
list_for_each_entry(nsim_dev_port, &nsim_dev->port_list, list)
if (nsim_dev_port->port_index == port_index)
return nsim_dev_port;
return NULL;
}
-int nsim_dev_port_add(struct nsim_bus_dev *nsim_bus_dev,
+int nsim_dev_port_add(struct nsim_bus_dev *nsim_bus_dev, enum nsim_dev_port_type type,
unsigned int port_index)
{
struct nsim_dev *nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev);
int err;
mutex_lock(&nsim_dev->port_list_lock);
- if (__nsim_dev_port_lookup(nsim_dev, port_index))
+ if (__nsim_dev_port_lookup(nsim_dev, type, port_index))
err = -EEXIST;
else
- err = __nsim_dev_port_add(nsim_dev, port_index);
+ err = __nsim_dev_port_add(nsim_dev, type, port_index);
mutex_unlock(&nsim_dev->port_list_lock);
return err;
}
-int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev,
+int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev, enum nsim_dev_port_type type,
unsigned int port_index)
{
struct nsim_dev *nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev);
@@ -1249,7 +1271,7 @@ int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev,
int err = 0;
mutex_lock(&nsim_dev->port_list_lock);
- nsim_dev_port = __nsim_dev_port_lookup(nsim_dev, port_index);
+ nsim_dev_port = __nsim_dev_port_lookup(nsim_dev, type, port_index);
if (!nsim_dev_port)
err = -ENOENT;
else
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index a1b49c8..e025c1b 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -197,10 +197,19 @@ static inline void nsim_dev_psample_exit(struct nsim_dev *nsim_dev)
}
#endif
+enum nsim_dev_port_type {
+ NSIM_DEV_PORT_TYPE_PF,
+ NSIM_DEV_PORT_TYPE_VF,
+};
+
+#define NSIM_DEV_VF_PORT_INDEX_BASE 128
+#define NSIM_DEV_VF_PORT_INDEX_MAX UINT_MAX
+
struct nsim_dev_port {
struct list_head list;
struct devlink_port devlink_port;
unsigned int port_index;
+ enum nsim_dev_port_type port_type;
struct dentry *ddir;
struct netdevsim *ns;
};
@@ -260,8 +269,10 @@ static inline struct net *nsim_dev_net(struct nsim_dev *nsim_dev)
int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev);
void nsim_dev_remove(struct nsim_bus_dev *nsim_bus_dev);
int nsim_dev_port_add(struct nsim_bus_dev *nsim_bus_dev,
+ enum nsim_dev_port_type type,
unsigned int port_index);
int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev,
+ enum nsim_dev_port_type type,
unsigned int port_index);
struct nsim_fib_data *nsim_fib_create(struct devlink *devlink,
@@ -278,6 +289,15 @@ ssize_t nsim_bus_dev_max_vfs_write(struct file *file,
size_t count, loff_t *ppos);
void nsim_bus_dev_vfs_disable(struct nsim_bus_dev *nsim_bus_dev);
+static inline bool nsim_dev_port_is_pf(struct nsim_dev_port *nsim_dev_port)
+{
+ return nsim_dev_port->port_type == NSIM_DEV_PORT_TYPE_PF;
+}
+
+static inline bool nsim_dev_port_is_vf(struct nsim_dev_port *nsim_dev_port)
+{
+ return nsim_dev_port->port_type == NSIM_DEV_PORT_TYPE_VF;
+}
#if IS_ENABLED(CONFIG_XFRM_OFFLOAD)
void nsim_ipsec_init(struct netdevsim *ns);
void nsim_ipsec_teardown(struct netdevsim *ns);
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND net-next v3 04/18] netdevsim: Implement VFs
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
` (2 preceding siblings ...)
2021-06-02 12:17 ` [PATCH RESEND net-next v3 03/18] netdevsim: Implement port types and indexing dlinkin
@ 2021-06-02 12:17 ` dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 05/18] netdevsim: Implement legacy/switchdev mode for VFs dlinkin
` (15 subsequent siblings)
19 siblings, 0 replies; 28+ messages in thread
From: dlinkin @ 2021-06-02 12:17 UTC (permalink / raw)
To: netdev
Cc: davem, kuba, jiri, stephen, dsahern, vladbu, parav, huyn, Dmytro Linkin
From: Dmytro Linkin <dlinkin@nvidia.com>
Allow creation of netdevsim ports for VFs along with allocations of
corresponding net devices and devlink ports.
Add enums and helpers to distinguish PFs' ports from VFs' ports.
Ports creation/deletion debugfs API intended to be used with physical
ports only.
VFs instantiation will be done in one of the next patches.
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
drivers/net/netdevsim/dev.c | 14 ++++++-
drivers/net/netdevsim/netdev.c | 90 ++++++++++++++++++++++++++++++------------
2 files changed, 77 insertions(+), 27 deletions(-)
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 93d6f3d..8bd7654 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -945,11 +945,15 @@ static int nsim_dev_devlink_trap_init(struct devlink *devlink,
static int __nsim_dev_port_add(struct nsim_dev *nsim_dev, enum nsim_dev_port_type type,
unsigned int port_index)
{
+ struct nsim_bus_dev *nsim_bus_dev = nsim_dev->nsim_bus_dev;
struct devlink_port_attrs attrs = {};
struct nsim_dev_port *nsim_dev_port;
struct devlink_port *devlink_port;
int err;
+ if (type == NSIM_DEV_PORT_TYPE_VF && !nsim_bus_dev->num_vfs)
+ return -EINVAL;
+
nsim_dev_port = kzalloc(sizeof(*nsim_dev_port), GFP_KERNEL);
if (!nsim_dev_port)
return -ENOMEM;
@@ -957,8 +961,14 @@ static int __nsim_dev_port_add(struct nsim_dev *nsim_dev, enum nsim_dev_port_typ
nsim_dev_port->port_type = type;
devlink_port = &nsim_dev_port->devlink_port;
- attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
- attrs.phys.port_number = port_index + 1;
+ if (nsim_dev_port_is_pf(nsim_dev_port)) {
+ attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
+ attrs.phys.port_number = port_index + 1;
+ } else {
+ attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF;
+ attrs.pci_vf.pf = 0;
+ attrs.pci_vf.vf = port_index;
+ }
memcpy(attrs.switch_id.id, nsim_dev->switch_id.id, nsim_dev->switch_id.id_len);
attrs.switch_id.id_len = nsim_dev->switch_id.id_len;
devlink_port_attrs_set(devlink_port, &attrs);
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 659d3dc..9352e18 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -261,6 +261,18 @@ static struct devlink_port *nsim_get_devlink_port(struct net_device *dev)
.ndo_get_devlink_port = nsim_get_devlink_port,
};
+static const struct net_device_ops nsim_vf_netdev_ops = {
+ .ndo_start_xmit = nsim_start_xmit,
+ .ndo_set_rx_mode = nsim_set_rx_mode,
+ .ndo_set_mac_address = eth_mac_addr,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_change_mtu = nsim_change_mtu,
+ .ndo_get_stats64 = nsim_get_stats64,
+ .ndo_setup_tc = nsim_setup_tc,
+ .ndo_set_features = nsim_set_features,
+ .ndo_get_devlink_port = nsim_get_devlink_port,
+};
+
static void nsim_setup(struct net_device *dev)
{
ether_setup(dev);
@@ -280,6 +292,49 @@ static void nsim_setup(struct net_device *dev)
dev->max_mtu = ETH_MAX_MTU;
}
+static int nsim_init_netdevsim(struct netdevsim *ns)
+{
+ int err;
+
+ ns->netdev->netdev_ops = &nsim_netdev_ops;
+
+ err = nsim_udp_tunnels_info_create(ns->nsim_dev, ns->netdev);
+ if (err)
+ return err;
+
+ rtnl_lock();
+ err = nsim_bpf_init(ns);
+ if (err)
+ goto err_utn_destroy;
+
+ nsim_ipsec_init(ns);
+
+ err = register_netdevice(ns->netdev);
+ if (err)
+ goto err_ipsec_teardown;
+ rtnl_unlock();
+ return 0;
+
+err_ipsec_teardown:
+ nsim_ipsec_teardown(ns);
+ nsim_bpf_uninit(ns);
+err_utn_destroy:
+ rtnl_unlock();
+ nsim_udp_tunnels_info_destroy(ns->netdev);
+ return err;
+}
+
+static int nsim_init_netdevsim_vf(struct netdevsim *ns)
+{
+ int err;
+
+ ns->netdev->netdev_ops = &nsim_vf_netdev_ops;
+ rtnl_lock();
+ err = register_netdevice(ns->netdev);
+ rtnl_unlock();
+ return err;
+}
+
struct netdevsim *
nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port)
{
@@ -299,33 +354,15 @@ struct netdevsim *
ns->nsim_dev_port = nsim_dev_port;
ns->nsim_bus_dev = nsim_dev->nsim_bus_dev;
SET_NETDEV_DEV(dev, &ns->nsim_bus_dev->dev);
- dev->netdev_ops = &nsim_netdev_ops;
nsim_ethtool_init(ns);
-
- err = nsim_udp_tunnels_info_create(nsim_dev, dev);
+ if (nsim_dev_port_is_pf(nsim_dev_port))
+ err = nsim_init_netdevsim(ns);
+ else
+ err = nsim_init_netdevsim_vf(ns);
if (err)
goto err_free_netdev;
-
- rtnl_lock();
- err = nsim_bpf_init(ns);
- if (err)
- goto err_utn_destroy;
-
- nsim_ipsec_init(ns);
-
- err = register_netdevice(dev);
- if (err)
- goto err_ipsec_teardown;
- rtnl_unlock();
-
return ns;
-err_ipsec_teardown:
- nsim_ipsec_teardown(ns);
- nsim_bpf_uninit(ns);
-err_utn_destroy:
- rtnl_unlock();
- nsim_udp_tunnels_info_destroy(dev);
err_free_netdev:
free_netdev(dev);
return ERR_PTR(err);
@@ -337,10 +374,13 @@ void nsim_destroy(struct netdevsim *ns)
rtnl_lock();
unregister_netdevice(dev);
- nsim_ipsec_teardown(ns);
- nsim_bpf_uninit(ns);
+ if (nsim_dev_port_is_pf(ns->nsim_dev_port)) {
+ nsim_ipsec_teardown(ns);
+ nsim_bpf_uninit(ns);
+ }
rtnl_unlock();
- nsim_udp_tunnels_info_destroy(dev);
+ if (nsim_dev_port_is_pf(ns->nsim_dev_port))
+ nsim_udp_tunnels_info_destroy(dev);
free_netdev(dev);
}
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND net-next v3 05/18] netdevsim: Implement legacy/switchdev mode for VFs
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
` (3 preceding siblings ...)
2021-06-02 12:17 ` [PATCH RESEND net-next v3 04/18] netdevsim: Implement VFs dlinkin
@ 2021-06-02 12:17 ` dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 06/18] devlink: Introduce rate object dlinkin
` (14 subsequent siblings)
19 siblings, 0 replies; 28+ messages in thread
From: dlinkin @ 2021-06-02 12:17 UTC (permalink / raw)
To: netdev
Cc: davem, kuba, jiri, stephen, dsahern, vladbu, parav, huyn, Dmytro Linkin
From: Dmytro Linkin <dlinkin@nvidia.com>
Implement callbacks to set/get eswitch mode value. Add helpers to check
current mode.
Instantiate VFs' net devices and devlink ports on switchdev enabling and
remove them on legacy enabling. Changing number of VFs while in
switchdev mode triggers VFs creation/deletion.
Also disable NDO API callback to set VF rate, since it's legacy API.
Switchdev API to set VF rate will be implemented in one of the next
patches.
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
drivers/net/netdevsim/bus.c | 17 +++++++++-
drivers/net/netdevsim/dev.c | 69 +++++++++++++++++++++++++++++++++++++++
drivers/net/netdevsim/netdev.c | 5 +++
drivers/net/netdevsim/netdevsim.h | 14 ++++++++
4 files changed, 104 insertions(+), 1 deletion(-)
diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c
index e29146d..b56003d 100644
--- a/drivers/net/netdevsim/bus.c
+++ b/drivers/net/netdevsim/bus.c
@@ -27,6 +27,9 @@ static struct nsim_bus_dev *to_nsim_bus_dev(struct device *dev)
static int nsim_bus_dev_vfs_enable(struct nsim_bus_dev *nsim_bus_dev,
unsigned int num_vfs)
{
+ struct nsim_dev *nsim_dev;
+ int err = 0;
+
if (nsim_bus_dev->max_vfs < num_vfs)
return -ENOMEM;
@@ -34,12 +37,24 @@ static int nsim_bus_dev_vfs_enable(struct nsim_bus_dev *nsim_bus_dev,
return -ENOMEM;
nsim_bus_dev->num_vfs = num_vfs;
- return 0;
+ nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev);
+ if (nsim_esw_mode_is_switchdev(nsim_dev)) {
+ err = nsim_esw_switchdev_enable(nsim_dev, NULL);
+ if (err)
+ nsim_bus_dev->num_vfs = 0;
+ }
+
+ return err;
}
void nsim_bus_dev_vfs_disable(struct nsim_bus_dev *nsim_bus_dev)
{
+ struct nsim_dev *nsim_dev;
+
nsim_bus_dev->num_vfs = 0;
+ nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev);
+ if (nsim_esw_mode_is_switchdev(nsim_dev))
+ nsim_esw_legacy_enable(nsim_dev, NULL);
}
static ssize_t
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 8bd7654..ed9ce08 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -439,6 +439,72 @@ static void nsim_dev_dummy_region_exit(struct nsim_dev *nsim_dev)
devlink_region_destroy(nsim_dev->dummy_region);
}
+static void __nsim_dev_port_del(struct nsim_dev_port *nsim_dev_port);
+int nsim_esw_legacy_enable(struct nsim_dev *nsim_dev, struct netlink_ext_ack *extack)
+{
+ struct nsim_dev_port *nsim_dev_port, *tmp;
+
+ mutex_lock(&nsim_dev->port_list_lock);
+ list_for_each_entry_safe(nsim_dev_port, tmp, &nsim_dev->port_list, list)
+ if (nsim_dev_port_is_vf(nsim_dev_port))
+ __nsim_dev_port_del(nsim_dev_port);
+ mutex_unlock(&nsim_dev->port_list_lock);
+ nsim_dev->esw_mode = DEVLINK_ESWITCH_MODE_LEGACY;
+ return 0;
+}
+
+int nsim_esw_switchdev_enable(struct nsim_dev *nsim_dev, struct netlink_ext_ack *extack)
+{
+ struct nsim_bus_dev *nsim_bus_dev = nsim_dev->nsim_bus_dev;
+ int i, err;
+
+ for (i = 0; i < nsim_bus_dev->num_vfs; i++) {
+ err = nsim_dev_port_add(nsim_bus_dev, NSIM_DEV_PORT_TYPE_VF, i);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to initialize VFs' netdevsim ports");
+ pr_err("Failed to initialize VF id=%d. %d.\n", i, err);
+ goto err_port_add_vfs;
+ }
+ }
+ nsim_dev->esw_mode = DEVLINK_ESWITCH_MODE_SWITCHDEV;
+ return 0;
+
+err_port_add_vfs:
+ for (i--; i >= 0; i--)
+ nsim_dev_port_del(nsim_bus_dev, NSIM_DEV_PORT_TYPE_VF, i);
+ return err;
+}
+
+static int nsim_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
+ struct netlink_ext_ack *extack)
+{
+ struct nsim_dev *nsim_dev = devlink_priv(devlink);
+ int err = 0;
+
+ mutex_lock(&nsim_dev->nsim_bus_dev->vfs_lock);
+ if (mode == nsim_dev->esw_mode)
+ goto unlock;
+
+ if (mode == DEVLINK_ESWITCH_MODE_LEGACY)
+ err = nsim_esw_legacy_enable(nsim_dev, extack);
+ else if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV)
+ err = nsim_esw_switchdev_enable(nsim_dev, extack);
+ else
+ err = -EINVAL;
+
+unlock:
+ mutex_unlock(&nsim_dev->nsim_bus_dev->vfs_lock);
+ return err;
+}
+
+static int nsim_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
+{
+ struct nsim_dev *nsim_dev = devlink_priv(devlink);
+
+ *mode = nsim_dev->esw_mode;
+ return 0;
+}
+
struct nsim_trap_item {
void *trap_ctx;
enum devlink_trap_action action;
@@ -925,6 +991,8 @@ static int nsim_dev_devlink_trap_init(struct devlink *devlink,
}
static const struct devlink_ops nsim_dev_devlink_ops = {
+ .eswitch_mode_set = nsim_devlink_eswitch_mode_set,
+ .eswitch_mode_get = nsim_devlink_eswitch_mode_get,
.supported_flash_update_params = DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT |
DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK,
.reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT),
@@ -1177,6 +1245,7 @@ int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev)
devlink_params_publish(devlink);
devlink_reload_enable(devlink);
+ nsim_dev->esw_mode = DEVLINK_ESWITCH_MODE_LEGACY;
return 0;
err_psample_exit:
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 9352e18..c3aeb15 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -113,6 +113,11 @@ static int nsim_set_vf_rate(struct net_device *dev, int vf, int min, int max)
struct netdevsim *ns = netdev_priv(dev);
struct nsim_bus_dev *nsim_bus_dev = ns->nsim_bus_dev;
+ if (nsim_esw_mode_is_switchdev(ns->nsim_dev)) {
+ pr_err("Not supported in switchdev mode. Please use devlink API.\n");
+ return -EOPNOTSUPP;
+ }
+
if (vf >= nsim_bus_dev->num_vfs)
return -EINVAL;
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index e025c1b..13a0042 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -257,8 +257,22 @@ struct nsim_dev {
u32 sleep;
} udp_ports;
struct nsim_dev_psample *psample;
+ u16 esw_mode;
};
+int nsim_esw_legacy_enable(struct nsim_dev *nsim_dev, struct netlink_ext_ack *extack);
+int nsim_esw_switchdev_enable(struct nsim_dev *nsim_dev, struct netlink_ext_ack *extack);
+
+static inline bool nsim_esw_mode_is_legacy(struct nsim_dev *nsim_dev)
+{
+ return nsim_dev->esw_mode == DEVLINK_ESWITCH_MODE_LEGACY;
+}
+
+static inline bool nsim_esw_mode_is_switchdev(struct nsim_dev *nsim_dev)
+{
+ return nsim_dev->esw_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV;
+}
+
static inline struct net *nsim_dev_net(struct nsim_dev *nsim_dev)
{
return devlink_net(priv_to_devlink(nsim_dev));
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND net-next v3 06/18] devlink: Introduce rate object
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
` (4 preceding siblings ...)
2021-06-02 12:17 ` [PATCH RESEND net-next v3 05/18] netdevsim: Implement legacy/switchdev mode for VFs dlinkin
@ 2021-06-02 12:17 ` dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 07/18] netdevsim: Register devlink rate leaf objects per VF dlinkin
` (13 subsequent siblings)
19 siblings, 0 replies; 28+ messages in thread
From: dlinkin @ 2021-06-02 12:17 UTC (permalink / raw)
To: netdev
Cc: davem, kuba, jiri, stephen, dsahern, vladbu, parav, huyn, Dmytro Linkin
From: Dmytro Linkin <dlinkin@nvidia.com>
Allow registering rate object for devlink ports with dedicated
devlink_rate_leaf_{create|destroy}() API. Implement new netlink
DEVLINK_CMD_RATE_GET command that is used to retrieve rate object info.
Add new DEVLINK_CMD_RATE_{NEW|DEL} commands that are used for
notifications when creating/deleting leaf rate object.
Rate API is intended to be used for rate limiting of individual
devlink ports (leafs) and their aggregates (nodes).
Example:
$ devlink port show
pci/0000:03:00.0/0
pci/0000:03:00.0/1
$ devlink port function rate show
pci/0000:03:00.0/0: type leaf
pci/0000:03:00.0/1: type leaf
Co-developed-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
Notes:
v1->v2:
- s/func/function/ in commit message
- fixes kernel-doc for devlink_rate_leaf_{create|destroy}()
include/net/devlink.h | 14 +++
include/uapi/linux/devlink.h | 11 +++
net/core/devlink.c | 229 ++++++++++++++++++++++++++++++++++++++++++-
3 files changed, 253 insertions(+), 1 deletion(-)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 7c984ca..2f5954d 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -34,6 +34,7 @@ struct devlink_dev_stats {
struct devlink {
struct list_head list;
struct list_head port_list;
+ struct list_head rate_list;
struct list_head sb_list;
struct list_head dpipe_table_list;
struct list_head resource_list;
@@ -133,6 +134,15 @@ struct devlink_port_attrs {
};
};
+struct devlink_rate {
+ struct list_head list;
+ enum devlink_rate_type type;
+ struct devlink *devlink;
+ void *priv;
+
+ struct devlink_port *devlink_port;
+};
+
struct devlink_port {
struct list_head list;
struct list_head param_list;
@@ -152,6 +162,8 @@ struct devlink_port {
struct delayed_work type_warn_dw;
struct list_head reporter_list;
struct mutex reporters_lock; /* Protects reporter_list */
+
+ struct devlink_rate *devlink_rate;
};
struct devlink_port_new_attrs {
@@ -1512,6 +1524,8 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro
void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port,
u32 controller, u16 pf, u32 sf,
bool external);
+int devlink_rate_leaf_create(struct devlink_port *port, void *priv);
+void devlink_rate_leaf_destroy(struct devlink_port *devlink_port);
int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
u32 size, u16 ingress_pools_count,
u16 egress_pools_count, u16 ingress_tc_count,
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index f6008b2..0c27b45 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -126,6 +126,11 @@ enum devlink_command {
DEVLINK_CMD_HEALTH_REPORTER_TEST,
+ DEVLINK_CMD_RATE_GET, /* can dump */
+ DEVLINK_CMD_RATE_SET,
+ DEVLINK_CMD_RATE_NEW,
+ DEVLINK_CMD_RATE_DEL,
+
/* add new commands above here */
__DEVLINK_CMD_MAX,
DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
@@ -206,6 +211,10 @@ enum devlink_port_flavour {
*/
};
+enum devlink_rate_type {
+ DEVLINK_RATE_TYPE_LEAF,
+};
+
enum devlink_param_cmode {
DEVLINK_PARAM_CMODE_RUNTIME,
DEVLINK_PARAM_CMODE_DRIVERINIT,
@@ -534,6 +543,8 @@ enum devlink_attr {
DEVLINK_ATTR_RELOAD_ACTION_STATS, /* nested */
DEVLINK_ATTR_PORT_PCI_SF_NUMBER, /* u32 */
+
+ DEVLINK_ATTR_RATE_TYPE, /* u16 */
/* add new attributes above here, update the policy in devlink.c */
__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 4eb9695..28b2490 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -190,6 +190,25 @@ static struct devlink_port *devlink_port_get_from_info(struct devlink *devlink,
return devlink_port_get_from_attrs(devlink, info->attrs);
}
+static inline bool
+devlink_rate_is_leaf(struct devlink_rate *devlink_rate)
+{
+ return devlink_rate->type == DEVLINK_RATE_TYPE_LEAF;
+}
+
+static struct devlink_rate *
+devlink_rate_leaf_get_from_info(struct devlink *devlink, struct genl_info *info)
+{
+ struct devlink_rate *devlink_rate;
+ struct devlink_port *devlink_port;
+
+ devlink_port = devlink_port_get_from_attrs(devlink, info->attrs);
+ if (IS_ERR(devlink_port))
+ return ERR_CAST(devlink_port);
+ devlink_rate = devlink_port->devlink_rate;
+ return devlink_rate ?: ERR_PTR(-ENODEV);
+}
+
struct devlink_sb {
struct list_head list;
unsigned int index;
@@ -408,12 +427,13 @@ struct devlink_snapshot {
#define DEVLINK_NL_FLAG_NEED_PORT BIT(0)
#define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT BIT(1)
+#define DEVLINK_NL_FLAG_NEED_RATE BIT(2)
/* The per devlink instance lock is taken by default in the pre-doit
* operation, yet several commands do not require this. The global
* devlink lock is taken and protects from disruption by user-calls.
*/
-#define DEVLINK_NL_FLAG_NO_LOCK BIT(2)
+#define DEVLINK_NL_FLAG_NO_LOCK BIT(3)
static int devlink_nl_pre_doit(const struct genl_ops *ops,
struct sk_buff *skb, struct genl_info *info)
@@ -442,6 +462,15 @@ static int devlink_nl_pre_doit(const struct genl_ops *ops,
devlink_port = devlink_port_get_from_info(devlink, info);
if (!IS_ERR(devlink_port))
info->user_ptr[1] = devlink_port;
+ } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE) {
+ struct devlink_rate *devlink_rate;
+
+ devlink_rate = devlink_rate_leaf_get_from_info(devlink, info);
+ if (IS_ERR(devlink_rate)) {
+ err = PTR_ERR(devlink_rate);
+ goto unlock;
+ }
+ info->user_ptr[1] = devlink_rate;
}
return 0;
@@ -749,6 +778,39 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg,
return 0;
}
+static int devlink_nl_rate_fill(struct sk_buff *msg,
+ struct devlink *devlink,
+ struct devlink_rate *devlink_rate,
+ enum devlink_command cmd, u32 portid,
+ u32 seq, int flags,
+ struct netlink_ext_ack *extack)
+{
+ void *hdr;
+
+ hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ if (devlink_nl_put_handle(msg, devlink))
+ goto nla_put_failure;
+
+ if (nla_put_u16(msg, DEVLINK_ATTR_RATE_TYPE, devlink_rate->type))
+ goto nla_put_failure;
+
+ if (devlink_rate_is_leaf(devlink_rate)) {
+ if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
+ devlink_rate->devlink_port->index))
+ goto nla_put_failure;
+ }
+
+ genlmsg_end(msg, hdr);
+ return 0;
+
+nla_put_failure:
+ genlmsg_cancel(msg, hdr);
+ return -EMSGSIZE;
+}
+
static bool
devlink_port_fn_state_valid(enum devlink_port_fn_state state)
{
@@ -920,6 +982,99 @@ static void devlink_port_notify(struct devlink_port *devlink_port,
msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
}
+static void devlink_rate_notify(struct devlink_rate *devlink_rate,
+ enum devlink_command cmd)
+{
+ struct devlink *devlink = devlink_rate->devlink;
+ struct sk_buff *msg;
+ int err;
+
+ WARN_ON(cmd != DEVLINK_CMD_RATE_NEW &&
+ cmd != DEVLINK_CMD_RATE_DEL);
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return;
+
+ err = devlink_nl_rate_fill(msg, devlink, devlink_rate,
+ cmd, 0, 0, 0, NULL);
+ if (err) {
+ nlmsg_free(msg);
+ return;
+ }
+
+ genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+ msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+static int devlink_nl_cmd_rate_get_dumpit(struct sk_buff *msg,
+ struct netlink_callback *cb)
+{
+ struct devlink_rate *devlink_rate;
+ struct devlink *devlink;
+ int start = cb->args[0];
+ int idx = 0;
+ int err = 0;
+
+ mutex_lock(&devlink_mutex);
+ list_for_each_entry(devlink, &devlink_list, list) {
+ if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
+ continue;
+ mutex_lock(&devlink->lock);
+ list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
+ enum devlink_command cmd = DEVLINK_CMD_RATE_NEW;
+ u32 id = NETLINK_CB(cb->skb).portid;
+
+ if (idx < start) {
+ idx++;
+ continue;
+ }
+ err = devlink_nl_rate_fill(msg, devlink,
+ devlink_rate,
+ cmd, id,
+ cb->nlh->nlmsg_seq,
+ NLM_F_MULTI, NULL);
+ if (err) {
+ mutex_unlock(&devlink->lock);
+ goto out;
+ }
+ idx++;
+ }
+ mutex_unlock(&devlink->lock);
+ }
+out:
+ mutex_unlock(&devlink_mutex);
+ if (err != -EMSGSIZE)
+ return err;
+
+ cb->args[0] = idx;
+ return msg->len;
+}
+
+static int devlink_nl_cmd_rate_get_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink_rate *devlink_rate = info->user_ptr[1];
+ struct devlink *devlink = devlink_rate->devlink;
+ struct sk_buff *msg;
+ int err;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ err = devlink_nl_rate_fill(msg, devlink, devlink_rate,
+ DEVLINK_CMD_RATE_NEW,
+ info->snd_portid, info->snd_seq, 0,
+ info->extack);
+ if (err) {
+ nlmsg_free(msg);
+ return err;
+ }
+
+ return genlmsg_reply(msg, info);
+}
+
static int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info)
{
struct devlink *devlink = info->user_ptr[0];
@@ -7802,6 +7957,7 @@ static int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb,
[DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16 },
[DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32 },
[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_RATE_TYPE] = { .type = NLA_U16 },
};
static const struct genl_small_ops devlink_nl_ops[] = {
@@ -7828,6 +7984,13 @@ static int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb,
.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
},
{
+ .cmd = DEVLINK_CMD_RATE_GET,
+ .doit = devlink_nl_cmd_rate_get_doit,
+ .dumpit = devlink_nl_cmd_rate_get_dumpit,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_RATE,
+ /* can be retrieved by unprivileged users */
+ },
+ {
.cmd = DEVLINK_CMD_PORT_SPLIT,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = devlink_nl_cmd_port_split_doit,
@@ -8202,6 +8365,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
xa_init_flags(&devlink->snapshot_ids, XA_FLAGS_ALLOC);
__devlink_net_set(devlink, &init_net);
INIT_LIST_HEAD(&devlink->port_list);
+ INIT_LIST_HEAD(&devlink->rate_list);
INIT_LIST_HEAD(&devlink->sb_list);
INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list);
INIT_LIST_HEAD(&devlink->resource_list);
@@ -8304,6 +8468,7 @@ void devlink_free(struct devlink *devlink)
WARN_ON(!list_empty(&devlink->resource_list));
WARN_ON(!list_empty(&devlink->dpipe_table_list));
WARN_ON(!list_empty(&devlink->sb_list));
+ WARN_ON(!list_empty(&devlink->rate_list));
WARN_ON(!list_empty(&devlink->port_list));
xa_destroy(&devlink->snapshot_ids);
@@ -8620,6 +8785,68 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 contro
}
EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set);
+/**
+ * devlink_rate_leaf_create - create devlink rate leaf
+ *
+ * @devlink_port: devlink port object to create rate object on
+ * @priv: driver private data
+ *
+ * Create devlink rate object of type leaf on provided @devlink_port.
+ * Throws call trace if @devlink_port already has a devlink rate object.
+ *
+ * Context: Takes and release devlink->lock <mutex>.
+ *
+ * Return: -ENOMEM if failed to allocate rate object, 0 otherwise.
+ */
+int
+devlink_rate_leaf_create(struct devlink_port *devlink_port, void *priv)
+{
+ struct devlink *devlink = devlink_port->devlink;
+ struct devlink_rate *devlink_rate;
+
+ devlink_rate = kzalloc(sizeof(*devlink_rate), GFP_KERNEL);
+ if (!devlink_rate)
+ return -ENOMEM;
+
+ mutex_lock(&devlink->lock);
+ WARN_ON(devlink_port->devlink_rate);
+ devlink_rate->type = DEVLINK_RATE_TYPE_LEAF;
+ devlink_rate->devlink = devlink;
+ devlink_rate->devlink_port = devlink_port;
+ devlink_rate->priv = priv;
+ list_add_tail(&devlink_rate->list, &devlink->rate_list);
+ devlink_port->devlink_rate = devlink_rate;
+ devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW);
+ mutex_unlock(&devlink->lock);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_rate_leaf_create);
+
+/**
+ * devlink_rate_leaf_destroy - destroy devlink rate leaf
+ *
+ * @devlink_port: devlink port linked to the rate object
+ *
+ * Context: Takes and release devlink->lock <mutex>.
+ */
+void devlink_rate_leaf_destroy(struct devlink_port *devlink_port)
+{
+ struct devlink_rate *devlink_rate = devlink_port->devlink_rate;
+ struct devlink *devlink = devlink_port->devlink;
+
+ if (!devlink_rate)
+ return;
+
+ mutex_lock(&devlink->lock);
+ devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_DEL);
+ list_del(&devlink_rate->list);
+ devlink_port->devlink_rate = NULL;
+ mutex_unlock(&devlink->lock);
+ kfree(devlink_rate);
+}
+EXPORT_SYMBOL_GPL(devlink_rate_leaf_destroy);
+
static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
char *name, size_t len)
{
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND net-next v3 07/18] netdevsim: Register devlink rate leaf objects per VF
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
` (5 preceding siblings ...)
2021-06-02 12:17 ` [PATCH RESEND net-next v3 06/18] devlink: Introduce rate object dlinkin
@ 2021-06-02 12:17 ` dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 08/18] selftest: netdevsim: Add devlink rate test dlinkin
` (12 subsequent siblings)
19 siblings, 0 replies; 28+ messages in thread
From: dlinkin @ 2021-06-02 12:17 UTC (permalink / raw)
To: netdev
Cc: davem, kuba, jiri, stephen, dsahern, vladbu, parav, huyn, Dmytro Linkin
From: Dmytro Linkin <dlinkin@nvidia.com>
Register devlink rate leaf objects per VF.
Co-developed-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
drivers/net/netdevsim/dev.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index ed9ce08..356287a 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -1055,11 +1055,20 @@ static int __nsim_dev_port_add(struct nsim_dev *nsim_dev, enum nsim_dev_port_typ
goto err_port_debugfs_exit;
}
+ if (nsim_dev_port_is_vf(nsim_dev_port)) {
+ err = devlink_rate_leaf_create(&nsim_dev_port->devlink_port,
+ nsim_dev_port);
+ if (err)
+ goto err_nsim_destroy;
+ }
+
devlink_port_type_eth_set(devlink_port, nsim_dev_port->ns->netdev);
list_add(&nsim_dev_port->list, &nsim_dev->port_list);
return 0;
+err_nsim_destroy:
+ nsim_destroy(nsim_dev_port->ns);
err_port_debugfs_exit:
nsim_dev_port_debugfs_exit(nsim_dev_port);
err_dl_port_unregister:
@@ -1074,6 +1083,8 @@ static void __nsim_dev_port_del(struct nsim_dev_port *nsim_dev_port)
struct devlink_port *devlink_port = &nsim_dev_port->devlink_port;
list_del(&nsim_dev_port->list);
+ if (nsim_dev_port_is_vf(nsim_dev_port))
+ devlink_rate_leaf_destroy(&nsim_dev_port->devlink_port);
devlink_port_type_clear(devlink_port);
nsim_destroy(nsim_dev_port->ns);
nsim_dev_port_debugfs_exit(nsim_dev_port);
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND net-next v3 08/18] selftest: netdevsim: Add devlink rate test
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
` (6 preceding siblings ...)
2021-06-02 12:17 ` [PATCH RESEND net-next v3 07/18] netdevsim: Register devlink rate leaf objects per VF dlinkin
@ 2021-06-02 12:17 ` dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 09/18] devlink: Allow setting tx rate for devlink rate leaf objects dlinkin
` (11 subsequent siblings)
19 siblings, 0 replies; 28+ messages in thread
From: dlinkin @ 2021-06-02 12:17 UTC (permalink / raw)
To: netdev
Cc: davem, kuba, jiri, stephen, dsahern, vladbu, parav, huyn, Dmytro Linkin
From: Dmytro Linkin <dlinkin@nvidia.com>
Test verifies that all netdevsim VF ports have rate leaf object created
by default.
Co-developed-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
Notes:
v1->v2:
- s/func/function in devlink command
.../selftests/drivers/net/netdevsim/devlink.sh | 25 +++++++++++++++++++++-
1 file changed, 24 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
index 40909c2..c654be0 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
@@ -5,12 +5,13 @@ lib_dir=$(dirname $0)/../../../net/forwarding
ALL_TESTS="fw_flash_test params_test regions_test reload_test \
netns_reload_test resource_test dev_info_test \
- empty_reporter_test dummy_reporter_test"
+ empty_reporter_test dummy_reporter_test rate_test"
NUM_NETIFS=0
source $lib_dir/lib.sh
BUS_ADDR=10
PORT_COUNT=4
+VF_COUNT=4
DEV_NAME=netdevsim$BUS_ADDR
SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV_NAME/net/
DEBUGFS_DIR=/sys/kernel/debug/netdevsim/$DEV_NAME/
@@ -507,6 +508,28 @@ dummy_reporter_test()
log_test "dummy reporter test"
}
+rate_leafs_get()
+{
+ local handle=$1
+
+ cmd_jq "devlink port function rate show -j" \
+ '.[] | to_entries | .[] | select(.value.type == "leaf") | .key | select(contains("'$handle'"))'
+}
+
+rate_test()
+{
+ RET=0
+
+ echo $VF_COUNT > /sys/bus/netdevsim/devices/$DEV_NAME/sriov_numvfs
+ devlink dev eswitch set $DL_HANDLE mode switchdev
+ local leafs=`rate_leafs_get $DL_HANDLE`
+ local num_leafs=`echo $leafs | wc -w`
+ [ "$num_leafs" == "$VF_COUNT" ]
+ check_err $? "Expected $VF_COUNT rate leafs but got $num_leafs"
+
+ log_test "rate test"
+}
+
setup_prepare()
{
modprobe netdevsim
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND net-next v3 09/18] devlink: Allow setting tx rate for devlink rate leaf objects
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
` (7 preceding siblings ...)
2021-06-02 12:17 ` [PATCH RESEND net-next v3 08/18] selftest: netdevsim: Add devlink rate test dlinkin
@ 2021-06-02 12:17 ` dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 10/18] netdevsim: Implement devlink rate leafs tx rate support dlinkin
` (10 subsequent siblings)
19 siblings, 0 replies; 28+ messages in thread
From: dlinkin @ 2021-06-02 12:17 UTC (permalink / raw)
To: netdev
Cc: davem, kuba, jiri, stephen, dsahern, vladbu, parav, huyn, Dmytro Linkin
From: Dmytro Linkin <dlinkin@nvidia.com>
Implement support for DEVLINK_CMD_RATE_SET command with new attributes
DEVLINK_ATTR_RATE_TX_{SHARE|MAX} that are used to set devlink rate
shared/max tx rate values. Extend devlink ops with new callbacks
rate_leaf_tx_{share|max}_set() to allow supporting drivers to implement
rate control through devlink.
New attributes are optional. Driver implementations are allowed to
support either or both of them.
Shared rate example:
$ devlink port function rate set netdevsim/netdevsim10/0 tx_share 10mbit
$ devlink port function rate show netdevsim/netdevsim10/0
netdevsim/netdevsim10/0: type leaf tx_share 10mbit
Max rate example:
$ devlink port function rate set netdevsim/netdevsim10/0 tx_max 100mbit
$ devlink port function rate show netdevsim/netdevsim10/0
netdevsim/netdevsim10/0: type leaf tx_max 100mbit
Co-developed-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
Notes:
v1->v2:
- s/func/function/ in devlink commands of commit message
include/net/devlink.h | 10 ++++++
include/uapi/linux/devlink.h | 2 ++
net/core/devlink.c | 86 ++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 98 insertions(+)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 2f5954d..46d5535 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -139,6 +139,8 @@ struct devlink_rate {
enum devlink_rate_type type;
struct devlink *devlink;
void *priv;
+ u64 tx_share;
+ u64 tx_max;
struct devlink_port *devlink_port;
};
@@ -1465,6 +1467,14 @@ struct devlink_ops {
struct devlink_port *port,
enum devlink_port_fn_state state,
struct netlink_ext_ack *extack);
+
+ /**
+ * Rate control callbacks.
+ */
+ int (*rate_leaf_tx_share_set)(struct devlink_rate *devlink_rate, void *priv,
+ u64 tx_share, struct netlink_ext_ack *extack);
+ int (*rate_leaf_tx_max_set)(struct devlink_rate *devlink_rate, void *priv,
+ u64 tx_max, struct netlink_ext_ack *extack);
};
static inline void *devlink_priv(struct devlink *devlink)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 0c27b45..ae94cd2 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -545,6 +545,8 @@ enum devlink_attr {
DEVLINK_ATTR_PORT_PCI_SF_NUMBER, /* u32 */
DEVLINK_ATTR_RATE_TYPE, /* u16 */
+ DEVLINK_ATTR_RATE_TX_SHARE, /* u64 */
+ DEVLINK_ATTR_RATE_TX_MAX, /* u64 */
/* add new attributes above here, update the policy in devlink.c */
__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 28b2490..eea1f88 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -803,6 +803,14 @@ static int devlink_nl_rate_fill(struct sk_buff *msg,
goto nla_put_failure;
}
+ if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_SHARE,
+ devlink_rate->tx_share, DEVLINK_ATTR_PAD))
+ goto nla_put_failure;
+
+ if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_MAX,
+ devlink_rate->tx_max, DEVLINK_ATTR_PAD))
+ goto nla_put_failure;
+
genlmsg_end(msg, hdr);
return 0;
@@ -1495,6 +1503,76 @@ static int devlink_nl_cmd_port_del_doit(struct sk_buff *skb,
return devlink->ops->port_del(devlink, port_index, extack);
}
+static int devlink_nl_rate_set(struct devlink_rate *devlink_rate,
+ const struct devlink_ops *ops,
+ struct genl_info *info)
+{
+ struct nlattr **attrs = info->attrs;
+ u64 rate;
+ int err;
+
+ if (attrs[DEVLINK_ATTR_RATE_TX_SHARE]) {
+ rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_SHARE]);
+ err = ops->rate_leaf_tx_share_set(devlink_rate, devlink_rate->priv,
+ rate, info->extack);
+ if (err)
+ return err;
+ devlink_rate->tx_share = rate;
+ }
+
+ if (attrs[DEVLINK_ATTR_RATE_TX_MAX]) {
+ rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_MAX]);
+ err = ops->rate_leaf_tx_max_set(devlink_rate, devlink_rate->priv,
+ rate, info->extack);
+ if (err)
+ return err;
+ devlink_rate->tx_max = rate;
+ }
+
+ return 0;
+}
+
+static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops,
+ struct genl_info *info,
+ enum devlink_rate_type type)
+{
+ struct nlattr **attrs = info->attrs;
+
+ if (type == DEVLINK_RATE_TYPE_LEAF) {
+ if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_leaf_tx_share_set) {
+ NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the leafs");
+ return false;
+ }
+ if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_leaf_tx_max_set) {
+ NL_SET_ERR_MSG_MOD(info->extack, "TX max set isn't supported for the leafs");
+ return false;
+ }
+ } else {
+ WARN_ON("Unknown type of rate object");
+ return false;
+ }
+
+ return true;
+}
+
+static int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink_rate *devlink_rate = info->user_ptr[1];
+ struct devlink *devlink = devlink_rate->devlink;
+ const struct devlink_ops *ops = devlink->ops;
+ int err;
+
+ if (!ops || !devlink_rate_set_ops_supported(ops, info, devlink_rate->type))
+ return -EOPNOTSUPP;
+
+ err = devlink_nl_rate_set(devlink_rate, ops, info);
+
+ if (!err)
+ devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW);
+ return err;
+}
+
static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink,
struct devlink_sb *devlink_sb,
enum devlink_command cmd, u32 portid,
@@ -7958,6 +8036,8 @@ static int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb,
[DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32 },
[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32 },
[DEVLINK_ATTR_RATE_TYPE] = { .type = NLA_U16 },
+ [DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64 },
+ [DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64 },
};
static const struct genl_small_ops devlink_nl_ops[] = {
@@ -7991,6 +8071,12 @@ static int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb,
/* can be retrieved by unprivileged users */
},
{
+ .cmd = DEVLINK_CMD_RATE_SET,
+ .doit = devlink_nl_cmd_rate_set_doit,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_RATE,
+ },
+ {
.cmd = DEVLINK_CMD_PORT_SPLIT,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = devlink_nl_cmd_port_split_doit,
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND net-next v3 10/18] netdevsim: Implement devlink rate leafs tx rate support
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
` (8 preceding siblings ...)
2021-06-02 12:17 ` [PATCH RESEND net-next v3 09/18] devlink: Allow setting tx rate for devlink rate leaf objects dlinkin
@ 2021-06-02 12:17 ` dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 11/18] selftest: netdevsim: Add devlink port shared/max tx rate test dlinkin
` (9 subsequent siblings)
19 siblings, 0 replies; 28+ messages in thread
From: dlinkin @ 2021-06-02 12:17 UTC (permalink / raw)
To: netdev
Cc: davem, kuba, jiri, stephen, dsahern, vladbu, parav, huyn, Dmytro Linkin
From: Dmytro Linkin <dlinkin@nvidia.com>
Implement new devlink ops that allow shared and max tx rate control for
devlink port rate objects (leafs) through devlink API.
Expose rate values of VF ports to netdevsim debugfs.
Co-developed-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
drivers/net/netdevsim/dev.c | 78 +++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 75 insertions(+), 3 deletions(-)
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 356287a..5be6f7e 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -276,17 +276,26 @@ static void nsim_dev_debugfs_exit(struct nsim_dev *nsim_dev)
static int nsim_dev_port_debugfs_init(struct nsim_dev *nsim_dev,
struct nsim_dev_port *nsim_dev_port)
{
+ struct nsim_bus_dev *nsim_bus_dev = nsim_dev->nsim_bus_dev;
+ unsigned int port_index = nsim_dev_port->port_index;
char port_ddir_name[16];
char dev_link_name[32];
- sprintf(port_ddir_name, "%u", nsim_dev_port->port_index);
+ sprintf(port_ddir_name, "%u", port_index);
nsim_dev_port->ddir = debugfs_create_dir(port_ddir_name,
nsim_dev->ports_ddir);
if (IS_ERR(nsim_dev_port->ddir))
return PTR_ERR(nsim_dev_port->ddir);
- sprintf(dev_link_name, "../../../" DRV_NAME "%u",
- nsim_dev->nsim_bus_dev->dev.id);
+ sprintf(dev_link_name, "../../../" DRV_NAME "%u", nsim_bus_dev->dev.id);
+ if (nsim_dev_port_is_vf(nsim_dev_port)) {
+ unsigned int vf_id = nsim_dev_port_index_to_vf_index(port_index);
+
+ debugfs_create_u16("tx_share", 0400, nsim_dev_port->ddir,
+ &nsim_bus_dev->vfconfigs[vf_id].min_tx_rate);
+ debugfs_create_u16("tx_max", 0400, nsim_dev_port->ddir,
+ &nsim_bus_dev->vfconfigs[vf_id].max_tx_rate);
+ }
debugfs_create_symlink("dev", nsim_dev_port->ddir, dev_link_name);
return 0;
@@ -990,6 +999,67 @@ static int nsim_dev_devlink_trap_init(struct devlink *devlink,
return 0;
}
+#define NSIM_LINK_SPEED_MAX 5000 /* Mbps */
+#define NSIM_LINK_SPEED_UNIT 125000 /* 1 Mbps given in bytes/sec to avoid
+ * u64 overflow during conversion from
+ * bytes to bits.
+ */
+
+static int nsim_rate_bytes_to_units(char *name, u64 *rate, struct netlink_ext_ack *extack)
+{
+ u64 val;
+ u32 rem;
+
+ val = div_u64_rem(*rate, NSIM_LINK_SPEED_UNIT, &rem);
+ if (rem) {
+ pr_err("%s rate value %lluBps not in link speed units of 1Mbps.\n",
+ name, *rate);
+ NL_SET_ERR_MSG_MOD(extack, "TX rate value not in link speed units of 1Mbps.");
+ return -EINVAL;
+ }
+
+ if (val > NSIM_LINK_SPEED_MAX) {
+ pr_err("%s rate value %lluMbps exceed link maximum speed 5000Mbps.\n",
+ name, val);
+ NL_SET_ERR_MSG_MOD(extack, "TX rate value exceed link maximum speed 5000Mbps.");
+ return -EINVAL;
+ }
+ *rate = val;
+ return 0;
+}
+
+static int nsim_leaf_tx_share_set(struct devlink_rate *devlink_rate, void *priv,
+ u64 tx_share, struct netlink_ext_ack *extack)
+{
+ struct nsim_dev_port *nsim_dev_port = priv;
+ struct nsim_bus_dev *nsim_bus_dev = nsim_dev_port->ns->nsim_bus_dev;
+ int vf_id = nsim_dev_port_index_to_vf_index(nsim_dev_port->port_index);
+ int err;
+
+ err = nsim_rate_bytes_to_units("tx_share", &tx_share, extack);
+ if (err)
+ return err;
+
+ nsim_bus_dev->vfconfigs[vf_id].min_tx_rate = tx_share;
+ return 0;
+}
+
+static int nsim_leaf_tx_max_set(struct devlink_rate *devlink_rate, void *priv,
+ u64 tx_max, struct netlink_ext_ack *extack)
+{
+ struct nsim_dev_port *nsim_dev_port = priv;
+ struct nsim_bus_dev *nsim_bus_dev = nsim_dev_port->ns->nsim_bus_dev;
+ int vf_id = nsim_dev_port_index_to_vf_index(nsim_dev_port->port_index);
+ int err;
+
+ err = nsim_rate_bytes_to_units("tx_max", &tx_max, extack);
+ if (err)
+ return err;
+
+ nsim_bus_dev->vfconfigs[vf_id].max_tx_rate = tx_max;
+ return 0;
+}
+
static const struct devlink_ops nsim_dev_devlink_ops = {
.eswitch_mode_set = nsim_devlink_eswitch_mode_set,
.eswitch_mode_get = nsim_devlink_eswitch_mode_get,
@@ -1005,6 +1075,8 @@ static int nsim_dev_devlink_trap_init(struct devlink *devlink,
.trap_group_set = nsim_dev_devlink_trap_group_set,
.trap_policer_set = nsim_dev_devlink_trap_policer_set,
.trap_policer_counter_get = nsim_dev_devlink_trap_policer_counter_get,
+ .rate_leaf_tx_share_set = nsim_leaf_tx_share_set,
+ .rate_leaf_tx_max_set = nsim_leaf_tx_max_set,
};
#define NSIM_DEV_MAX_MACS_DEFAULT 32
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND net-next v3 11/18] selftest: netdevsim: Add devlink port shared/max tx rate test
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
` (9 preceding siblings ...)
2021-06-02 12:17 ` [PATCH RESEND net-next v3 10/18] netdevsim: Implement devlink rate leafs tx rate support dlinkin
@ 2021-06-02 12:17 ` dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 12/18] devlink: Introduce rate nodes dlinkin
` (8 subsequent siblings)
19 siblings, 0 replies; 28+ messages in thread
From: dlinkin @ 2021-06-02 12:17 UTC (permalink / raw)
To: netdev
Cc: davem, kuba, jiri, stephen, dsahern, vladbu, parav, huyn, Dmytro Linkin
From: Dmytro Linkin <dlinkin@nvidia.com>
Test verifies that netdevsim VFs can set and retrieve shared/max tx
rate through new devlink API.
Co-developed-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
Notes:
v1->v2:
- s/func/function/ in devlink commands
.../selftests/drivers/net/netdevsim/devlink.sh | 55 ++++++++++++++++++++++
1 file changed, 55 insertions(+)
diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
index c654be0..05dcefc 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
@@ -516,6 +516,45 @@ rate_leafs_get()
'.[] | to_entries | .[] | select(.value.type == "leaf") | .key | select(contains("'$handle'"))'
}
+rate_attr_set()
+{
+ local handle=$1
+ local name=$2
+ local value=$3
+ local units=$4
+
+ devlink port function rate set $handle $name $value$units
+}
+
+rate_attr_get()
+{
+ local handle=$1
+ local name=$2
+
+ cmd_jq "devlink port function rate show $handle -j" '.[][].'$name
+}
+
+rate_attr_tx_rate_check()
+{
+ local handle=$1
+ local name=$2
+ local rate=$3
+ local debug_file=$4
+
+ rate_attr_set $handle $name $rate mbit
+ check_err $? "Failed to set $name value"
+
+ local debug_value=$(cat $debug_file)
+ check_err $? "Failed to read $name value from debugfs"
+ [ "$debug_value" == "$rate" ]
+ check_err $? "Unexpected $name debug value $debug_value != $rate"
+
+ local api_value=$(( $(rate_attr_get $handle $name) * 8 / 1000000 ))
+ check_err $? "Failed to get $name attr value"
+ [ "$api_value" == "$rate" ]
+ check_err $? "Unexpected $name attr value $api_value != $rate"
+}
+
rate_test()
{
RET=0
@@ -527,6 +566,22 @@ rate_test()
[ "$num_leafs" == "$VF_COUNT" ]
check_err $? "Expected $VF_COUNT rate leafs but got $num_leafs"
+ rate=10
+ for r_obj in $leafs
+ do
+ rate_attr_tx_rate_check $r_obj tx_share $rate \
+ $DEBUGFS_DIR/ports/${r_obj##*/}/tx_share
+ rate=$(($rate+10))
+ done
+
+ rate=100
+ for r_obj in $leafs
+ do
+ rate_attr_tx_rate_check $r_obj tx_max $rate \
+ $DEBUGFS_DIR/ports/${r_obj##*/}/tx_max
+ rate=$(($rate+100))
+ done
+
log_test "rate test"
}
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND net-next v3 12/18] devlink: Introduce rate nodes
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
` (10 preceding siblings ...)
2021-06-02 12:17 ` [PATCH RESEND net-next v3 11/18] selftest: netdevsim: Add devlink port shared/max tx rate test dlinkin
@ 2021-06-02 12:17 ` dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 13/18] netdevsim: Implement support for devlink " dlinkin
` (7 subsequent siblings)
19 siblings, 0 replies; 28+ messages in thread
From: dlinkin @ 2021-06-02 12:17 UTC (permalink / raw)
To: netdev
Cc: davem, kuba, jiri, stephen, dsahern, vladbu, parav, huyn, Dmytro Linkin
From: Dmytro Linkin <dlinkin@nvidia.com>
Implement support for DEVLINK_CMD_RATE_{NEW|DEL} commands that are used
to create and delete devlink rate nodes. Add new attribute
DEVLINK_ATTR_RATE_NODE_NAME that specify node name string. The node name
is an alphanumeric identifier. No valid node name can be a devlink port
index, eg. decimal number. Extend devlink ops with new callbacks
rate_node_{new|del}() and rate_node_tx_{share|max}_set() to allow
supporting drivers to implement ports rate grouping and setting tx rate
of rate nodes through devlink.
Expose devlink_rate_nodes_destroy() function to allow vendor driver do
proper cleanup of internally allocated resources for the nodes if the
driver goes down or due to any other reasons which requires nodes to be
destroyed.
Disallow moving device from switchdev to legacy mode if any node exists
on that device. User must explicitly delete nodes before switching mode.
Example:
$ devlink port function rate add netdevsim/netdevsim10/group1
$ devlink port function rate set netdevsim/netdevsim10/group1 \
tx_share 10mbit tx_max 100mbit
Add + set command can be combined:
$ devlink port function rate add netdevsim/netdevsim10/group1 \
tx_share 10mbit tx_max 100mbit
$ devlink port function rate show netdevsim/netdevsim10/group1
netdevsim/netdevsim10/group1: type node tx_share 10mbit tx_max 100mbit
$ devlink port function rate del netdevsim/netdevsim10/group1
Co-developed-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
Notes:
v1->v2:
- s/func/function/ at commit message
v2->v3:
- added devlink_rate_nodes_destroy()
include/net/devlink.h | 14 ++-
include/uapi/linux/devlink.h | 3 +
net/core/devlink.c | 238 +++++++++++++++++++++++++++++++++++++++++--
3 files changed, 247 insertions(+), 8 deletions(-)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 46d5535..13162b5 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -142,7 +142,10 @@ struct devlink_rate {
u64 tx_share;
u64 tx_max;
- struct devlink_port *devlink_port;
+ union {
+ struct devlink_port *devlink_port;
+ char *name;
+ };
};
struct devlink_port {
@@ -1475,6 +1478,14 @@ struct devlink_ops {
u64 tx_share, struct netlink_ext_ack *extack);
int (*rate_leaf_tx_max_set)(struct devlink_rate *devlink_rate, void *priv,
u64 tx_max, struct netlink_ext_ack *extack);
+ int (*rate_node_tx_share_set)(struct devlink_rate *devlink_rate, void *priv,
+ u64 tx_share, struct netlink_ext_ack *extack);
+ int (*rate_node_tx_max_set)(struct devlink_rate *devlink_rate, void *priv,
+ u64 tx_max, struct netlink_ext_ack *extack);
+ int (*rate_node_new)(struct devlink_rate *rate_node, void **priv,
+ struct netlink_ext_ack *extack);
+ int (*rate_node_del)(struct devlink_rate *rate_node, void *priv,
+ struct netlink_ext_ack *extack);
};
static inline void *devlink_priv(struct devlink *devlink)
@@ -1536,6 +1547,7 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port,
bool external);
int devlink_rate_leaf_create(struct devlink_port *port, void *priv);
void devlink_rate_leaf_destroy(struct devlink_port *devlink_port);
+void devlink_rate_nodes_destroy(struct devlink *devlink);
int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
u32 size, u16 ingress_pools_count,
u16 egress_pools_count, u16 ingress_tc_count,
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index ae94cd2..7e15853 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -213,6 +213,7 @@ enum devlink_port_flavour {
enum devlink_rate_type {
DEVLINK_RATE_TYPE_LEAF,
+ DEVLINK_RATE_TYPE_NODE,
};
enum devlink_param_cmode {
@@ -547,6 +548,8 @@ enum devlink_attr {
DEVLINK_ATTR_RATE_TYPE, /* u16 */
DEVLINK_ATTR_RATE_TX_SHARE, /* u64 */
DEVLINK_ATTR_RATE_TX_MAX, /* u64 */
+ DEVLINK_ATTR_RATE_NODE_NAME, /* string */
+
/* add new attributes above here, update the policy in devlink.c */
__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index eea1f88..d520fb5 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -196,6 +196,12 @@ static struct devlink_port *devlink_port_get_from_info(struct devlink *devlink,
return devlink_rate->type == DEVLINK_RATE_TYPE_LEAF;
}
+static inline bool
+devlink_rate_is_node(struct devlink_rate *devlink_rate)
+{
+ return devlink_rate->type == DEVLINK_RATE_TYPE_NODE;
+}
+
static struct devlink_rate *
devlink_rate_leaf_get_from_info(struct devlink *devlink, struct genl_info *info)
{
@@ -209,6 +215,55 @@ static struct devlink_port *devlink_port_get_from_info(struct devlink *devlink,
return devlink_rate ?: ERR_PTR(-ENODEV);
}
+static struct devlink_rate *
+devlink_rate_node_get_by_name(struct devlink *devlink, const char *node_name)
+{
+ static struct devlink_rate *devlink_rate;
+
+ list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
+ if (devlink_rate_is_node(devlink_rate) &&
+ !strcmp(node_name, devlink_rate->name))
+ return devlink_rate;
+ }
+ return ERR_PTR(-ENODEV);
+}
+
+static struct devlink_rate *
+devlink_rate_node_get_from_attrs(struct devlink *devlink, struct nlattr **attrs)
+{
+ const char *rate_node_name;
+ size_t len;
+
+ if (!attrs[DEVLINK_ATTR_RATE_NODE_NAME])
+ return ERR_PTR(-EINVAL);
+ rate_node_name = nla_data(attrs[DEVLINK_ATTR_RATE_NODE_NAME]);
+ len = strlen(rate_node_name);
+ /* Name cannot be empty or decimal number */
+ if (!len || strspn(rate_node_name, "0123456789") == len)
+ return ERR_PTR(-EINVAL);
+
+ return devlink_rate_node_get_by_name(devlink, rate_node_name);
+}
+
+static struct devlink_rate *
+devlink_rate_node_get_from_info(struct devlink *devlink, struct genl_info *info)
+{
+ return devlink_rate_node_get_from_attrs(devlink, info->attrs);
+}
+
+static struct devlink_rate *
+devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info)
+{
+ struct nlattr **attrs = info->attrs;
+
+ if (attrs[DEVLINK_ATTR_PORT_INDEX])
+ return devlink_rate_leaf_get_from_info(devlink, info);
+ else if (attrs[DEVLINK_ATTR_RATE_NODE_NAME])
+ return devlink_rate_node_get_from_info(devlink, info);
+ else
+ return ERR_PTR(-EINVAL);
+}
+
struct devlink_sb {
struct list_head list;
unsigned int index;
@@ -428,12 +483,13 @@ struct devlink_snapshot {
#define DEVLINK_NL_FLAG_NEED_PORT BIT(0)
#define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT BIT(1)
#define DEVLINK_NL_FLAG_NEED_RATE BIT(2)
+#define DEVLINK_NL_FLAG_NEED_RATE_NODE BIT(3)
/* The per devlink instance lock is taken by default in the pre-doit
* operation, yet several commands do not require this. The global
* devlink lock is taken and protects from disruption by user-calls.
*/
-#define DEVLINK_NL_FLAG_NO_LOCK BIT(3)
+#define DEVLINK_NL_FLAG_NO_LOCK BIT(4)
static int devlink_nl_pre_doit(const struct genl_ops *ops,
struct sk_buff *skb, struct genl_info *info)
@@ -465,12 +521,21 @@ static int devlink_nl_pre_doit(const struct genl_ops *ops,
} else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE) {
struct devlink_rate *devlink_rate;
- devlink_rate = devlink_rate_leaf_get_from_info(devlink, info);
+ devlink_rate = devlink_rate_get_from_info(devlink, info);
if (IS_ERR(devlink_rate)) {
err = PTR_ERR(devlink_rate);
goto unlock;
}
info->user_ptr[1] = devlink_rate;
+ } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE_NODE) {
+ struct devlink_rate *rate_node;
+
+ rate_node = devlink_rate_node_get_from_info(devlink, info);
+ if (IS_ERR(rate_node)) {
+ err = PTR_ERR(rate_node);
+ goto unlock;
+ }
+ info->user_ptr[1] = rate_node;
}
return 0;
@@ -801,6 +866,10 @@ static int devlink_nl_rate_fill(struct sk_buff *msg,
if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
devlink_rate->devlink_port->index))
goto nla_put_failure;
+ } else if (devlink_rate_is_node(devlink_rate)) {
+ if (nla_put_string(msg, DEVLINK_ATTR_RATE_NODE_NAME,
+ devlink_rate->name))
+ goto nla_put_failure;
}
if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_SHARE,
@@ -1508,13 +1577,17 @@ static int devlink_nl_rate_set(struct devlink_rate *devlink_rate,
struct genl_info *info)
{
struct nlattr **attrs = info->attrs;
+ int err = -EOPNOTSUPP;
u64 rate;
- int err;
if (attrs[DEVLINK_ATTR_RATE_TX_SHARE]) {
rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_SHARE]);
- err = ops->rate_leaf_tx_share_set(devlink_rate, devlink_rate->priv,
- rate, info->extack);
+ if (devlink_rate_is_leaf(devlink_rate))
+ err = ops->rate_leaf_tx_share_set(devlink_rate, devlink_rate->priv,
+ rate, info->extack);
+ else if (devlink_rate_is_node(devlink_rate))
+ err = ops->rate_node_tx_share_set(devlink_rate, devlink_rate->priv,
+ rate, info->extack);
if (err)
return err;
devlink_rate->tx_share = rate;
@@ -1522,8 +1595,12 @@ static int devlink_nl_rate_set(struct devlink_rate *devlink_rate,
if (attrs[DEVLINK_ATTR_RATE_TX_MAX]) {
rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_MAX]);
- err = ops->rate_leaf_tx_max_set(devlink_rate, devlink_rate->priv,
- rate, info->extack);
+ if (devlink_rate_is_leaf(devlink_rate))
+ err = ops->rate_leaf_tx_max_set(devlink_rate, devlink_rate->priv,
+ rate, info->extack);
+ else if (devlink_rate_is_node(devlink_rate))
+ err = ops->rate_node_tx_max_set(devlink_rate, devlink_rate->priv,
+ rate, info->extack);
if (err)
return err;
devlink_rate->tx_max = rate;
@@ -1547,6 +1624,15 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops,
NL_SET_ERR_MSG_MOD(info->extack, "TX max set isn't supported for the leafs");
return false;
}
+ } else if (type == DEVLINK_RATE_TYPE_NODE) {
+ if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_node_tx_share_set) {
+ NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the nodes");
+ return false;
+ }
+ if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_node_tx_max_set) {
+ NL_SET_ERR_MSG_MOD(info->extack, "TX max set isn't supported for the nodes");
+ return false;
+ }
} else {
WARN_ON("Unknown type of rate object");
return false;
@@ -1573,6 +1659,78 @@ static int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb,
return err;
}
+static int devlink_nl_cmd_rate_new_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ struct devlink_rate *rate_node;
+ const struct devlink_ops *ops;
+ int err;
+
+ ops = devlink->ops;
+ if (!ops || !ops->rate_node_new || !ops->rate_node_del) {
+ NL_SET_ERR_MSG_MOD(info->extack, "Rate nodes aren't supported");
+ return -EOPNOTSUPP;
+ }
+
+ if (!devlink_rate_set_ops_supported(ops, info, DEVLINK_RATE_TYPE_NODE))
+ return -EOPNOTSUPP;
+
+ rate_node = devlink_rate_node_get_from_attrs(devlink, info->attrs);
+ if (!IS_ERR(rate_node))
+ return -EEXIST;
+ else if (rate_node == ERR_PTR(-EINVAL))
+ return -EINVAL;
+
+ rate_node = kzalloc(sizeof(*rate_node), GFP_KERNEL);
+ if (!rate_node)
+ return -ENOMEM;
+
+ rate_node->devlink = devlink;
+ rate_node->type = DEVLINK_RATE_TYPE_NODE;
+ rate_node->name = nla_strdup(info->attrs[DEVLINK_ATTR_RATE_NODE_NAME], GFP_KERNEL);
+ if (!rate_node->name) {
+ err = -ENOMEM;
+ goto err_strdup;
+ }
+
+ err = ops->rate_node_new(rate_node, &rate_node->priv, info->extack);
+ if (err)
+ goto err_node_new;
+
+ err = devlink_nl_rate_set(rate_node, ops, info);
+ if (err)
+ goto err_rate_set;
+
+ list_add(&rate_node->list, &devlink->rate_list);
+ devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
+ return 0;
+
+err_rate_set:
+ ops->rate_node_del(rate_node, rate_node->priv, info->extack);
+err_node_new:
+ kfree(rate_node->name);
+err_strdup:
+ kfree(rate_node);
+ return err;
+}
+
+static int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink_rate *rate_node = info->user_ptr[1];
+ struct devlink *devlink = rate_node->devlink;
+ const struct devlink_ops *ops = devlink->ops;
+ int err;
+
+ devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL);
+ err = ops->rate_node_del(rate_node, rate_node->priv, info->extack);
+ list_del(&rate_node->list);
+ kfree(rate_node->name);
+ kfree(rate_node);
+ return err;
+}
+
static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink,
struct devlink_sb *devlink_sb,
enum devlink_command cmd, u32 portid,
@@ -2441,6 +2599,30 @@ static int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb,
return genlmsg_reply(msg, info);
}
+static int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
+ struct netlink_ext_ack *extack)
+{
+ struct devlink_rate *devlink_rate;
+ u16 old_mode;
+ int err;
+
+ if (!devlink->ops->eswitch_mode_get)
+ return -EOPNOTSUPP;
+ err = devlink->ops->eswitch_mode_get(devlink, &old_mode);
+ if (err)
+ return err;
+
+ if (old_mode == mode)
+ return 0;
+
+ list_for_each_entry(devlink_rate, &devlink->rate_list, list)
+ if (devlink_rate_is_node(devlink_rate)) {
+ NL_SET_ERR_MSG_MOD(extack, "Rate node(s) exists.");
+ return -EBUSY;
+ }
+ return 0;
+}
+
static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb,
struct genl_info *info)
{
@@ -2455,6 +2637,9 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb,
if (!ops->eswitch_mode_set)
return -EOPNOTSUPP;
mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]);
+ err = devlink_rate_nodes_check(devlink, mode, info->extack);
+ if (err)
+ return err;
err = ops->eswitch_mode_set(devlink, mode, info->extack);
if (err)
return err;
@@ -8038,6 +8223,7 @@ static int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb,
[DEVLINK_ATTR_RATE_TYPE] = { .type = NLA_U16 },
[DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64 },
[DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64 },
+ [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING },
};
static const struct genl_small_ops devlink_nl_ops[] = {
@@ -8077,6 +8263,17 @@ static int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb,
.internal_flags = DEVLINK_NL_FLAG_NEED_RATE,
},
{
+ .cmd = DEVLINK_CMD_RATE_NEW,
+ .doit = devlink_nl_cmd_rate_new_doit,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = DEVLINK_CMD_RATE_DEL,
+ .doit = devlink_nl_cmd_rate_del_doit,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_RATE_NODE,
+ },
+ {
.cmd = DEVLINK_CMD_PORT_SPLIT,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = devlink_nl_cmd_port_split_doit,
@@ -8933,6 +9130,33 @@ void devlink_rate_leaf_destroy(struct devlink_port *devlink_port)
}
EXPORT_SYMBOL_GPL(devlink_rate_leaf_destroy);
+/**
+ * devlink_rate_nodes_destroy - destroy all devlink rate nodes on device
+ *
+ * @devlink: devlink instance
+ *
+ * Destroy all rate nodes on specified device
+ *
+ * Context: Takes and release devlink->lock <mutex>.
+ */
+void devlink_rate_nodes_destroy(struct devlink *devlink)
+{
+ static struct devlink_rate *devlink_rate, *tmp;
+ const struct devlink_ops *ops = devlink->ops;
+
+ mutex_lock(&devlink->lock);
+ list_for_each_entry_safe(devlink_rate, tmp, &devlink->rate_list, list) {
+ if (devlink_rate_is_node(devlink_rate)) {
+ ops->rate_node_del(devlink_rate, devlink_rate->priv, NULL);
+ list_del(&devlink_rate->list);
+ kfree(devlink_rate->name);
+ kfree(devlink_rate);
+ }
+ }
+ mutex_unlock(&devlink->lock);
+}
+EXPORT_SYMBOL_GPL(devlink_rate_nodes_destroy);
+
static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
char *name, size_t len)
{
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND net-next v3 13/18] netdevsim: Implement support for devlink rate nodes
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
` (11 preceding siblings ...)
2021-06-02 12:17 ` [PATCH RESEND net-next v3 12/18] devlink: Introduce rate nodes dlinkin
@ 2021-06-02 12:17 ` dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 14/18] selftest: netdevsim: Add devlink rate nodes test dlinkin
` (6 subsequent siblings)
19 siblings, 0 replies; 28+ messages in thread
From: dlinkin @ 2021-06-02 12:17 UTC (permalink / raw)
To: netdev
Cc: davem, kuba, jiri, stephen, dsahern, vladbu, parav, huyn, Dmytro Linkin
From: Dmytro Linkin <dlinkin@nvidia.com>
Implement new devlink ops that allow creation, deletion and setting of
shared/max tx rate of devlink rate nodes through devlink API.
Expose rate node and it's tx rates to netdevsim debugfs.
Co-developed-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
Notes:
v2->v3:
- added devlink_rate_nodes_destroy() call
drivers/net/netdevsim/dev.c | 80 +++++++++++++++++++++++++++++++++++++++
drivers/net/netdevsim/netdevsim.h | 1 +
2 files changed, 81 insertions(+)
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 5be6f7e..9f01b6c 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -263,12 +263,16 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev)
nsim_dev->ddir,
nsim_dev->nsim_bus_dev,
&nsim_dev_max_vfs_fops);
+ nsim_dev->nodes_ddir = debugfs_create_dir("rate_nodes", nsim_dev->ddir);
+ if (IS_ERR(nsim_dev->nodes_ddir))
+ return PTR_ERR(nsim_dev->nodes_ddir);
nsim_udp_tunnels_debugfs_create(nsim_dev);
return 0;
}
static void nsim_dev_debugfs_exit(struct nsim_dev *nsim_dev)
{
+ debugfs_remove_recursive(nsim_dev->nodes_ddir);
debugfs_remove_recursive(nsim_dev->ports_ddir);
debugfs_remove_recursive(nsim_dev->ddir);
}
@@ -451,8 +455,10 @@ static void nsim_dev_dummy_region_exit(struct nsim_dev *nsim_dev)
static void __nsim_dev_port_del(struct nsim_dev_port *nsim_dev_port);
int nsim_esw_legacy_enable(struct nsim_dev *nsim_dev, struct netlink_ext_ack *extack)
{
+ struct devlink *devlink = priv_to_devlink(nsim_dev);
struct nsim_dev_port *nsim_dev_port, *tmp;
+ devlink_rate_nodes_destroy(devlink);
mutex_lock(&nsim_dev->port_list_lock);
list_for_each_entry_safe(nsim_dev_port, tmp, &nsim_dev->port_list, list)
if (nsim_dev_port_is_vf(nsim_dev_port))
@@ -1060,6 +1066,76 @@ static int nsim_leaf_tx_max_set(struct devlink_rate *devlink_rate, void *priv,
return 0;
}
+struct nsim_rate_node {
+ struct dentry *ddir;
+ u16 tx_share;
+ u16 tx_max;
+};
+
+static int nsim_node_tx_share_set(struct devlink_rate *devlink_rate, void *priv,
+ u64 tx_share, struct netlink_ext_ack *extack)
+{
+ struct nsim_rate_node *nsim_node = priv;
+ int err;
+
+ err = nsim_rate_bytes_to_units("tx_share", &tx_share, extack);
+ if (err)
+ return err;
+
+ nsim_node->tx_share = tx_share;
+ return 0;
+}
+
+static int nsim_node_tx_max_set(struct devlink_rate *devlink_rate, void *priv,
+ u64 tx_max, struct netlink_ext_ack *extack)
+{
+ struct nsim_rate_node *nsim_node = priv;
+ int err;
+
+ err = nsim_rate_bytes_to_units("tx_max", &tx_max, extack);
+ if (err)
+ return err;
+
+ nsim_node->tx_max = tx_max;
+ return 0;
+}
+
+static int nsim_rate_node_new(struct devlink_rate *node, void **priv,
+ struct netlink_ext_ack *extack)
+{
+ struct nsim_dev *nsim_dev = devlink_priv(node->devlink);
+ struct nsim_rate_node *nsim_node;
+
+ if (!nsim_esw_mode_is_switchdev(nsim_dev)) {
+ NL_SET_ERR_MSG_MOD(extack, "Node creation allowed only in switchdev mode.");
+ return -EOPNOTSUPP;
+ }
+
+ nsim_node = kzalloc(sizeof(*nsim_node), GFP_KERNEL);
+ if (!nsim_node)
+ return -ENOMEM;
+
+ nsim_node->ddir = debugfs_create_dir(node->name, nsim_dev->nodes_ddir);
+ if (!nsim_node->ddir) {
+ kfree(nsim_node);
+ return -ENOMEM;
+ }
+ debugfs_create_u16("tx_share", 0400, nsim_node->ddir, &nsim_node->tx_share);
+ debugfs_create_u16("tx_max", 0400, nsim_node->ddir, &nsim_node->tx_max);
+ *priv = nsim_node;
+ return 0;
+}
+
+static int nsim_rate_node_del(struct devlink_rate *node, void *priv,
+ struct netlink_ext_ack *extack)
+{
+ struct nsim_rate_node *nsim_node = priv;
+
+ debugfs_remove_recursive(nsim_node->ddir);
+ kfree(nsim_node);
+ return 0;
+}
+
static const struct devlink_ops nsim_dev_devlink_ops = {
.eswitch_mode_set = nsim_devlink_eswitch_mode_set,
.eswitch_mode_get = nsim_devlink_eswitch_mode_get,
@@ -1077,6 +1153,10 @@ static int nsim_leaf_tx_max_set(struct devlink_rate *devlink_rate, void *priv,
.trap_policer_counter_get = nsim_dev_devlink_trap_policer_counter_get,
.rate_leaf_tx_share_set = nsim_leaf_tx_share_set,
.rate_leaf_tx_max_set = nsim_leaf_tx_max_set,
+ .rate_node_tx_share_set = nsim_node_tx_share_set,
+ .rate_node_tx_max_set = nsim_node_tx_max_set,
+ .rate_node_new = nsim_rate_node_new,
+ .rate_node_del = nsim_rate_node_del,
};
#define NSIM_DEV_MAX_MACS_DEFAULT 32
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 13a0042..d62a138 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -222,6 +222,7 @@ struct nsim_dev {
struct dentry *ports_ddir;
struct dentry *take_snapshot;
struct dentry *max_vfs;
+ struct dentry *nodes_ddir;
struct bpf_offload_dev *bpf_dev;
bool bpf_bind_accept;
bool bpf_bind_verifier_accept;
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND net-next v3 14/18] selftest: netdevsim: Add devlink rate nodes test
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
` (12 preceding siblings ...)
2021-06-02 12:17 ` [PATCH RESEND net-next v3 13/18] netdevsim: Implement support for devlink " dlinkin
@ 2021-06-02 12:17 ` dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 15/18] devlink: Allow setting parent node of rate objects dlinkin
` (5 subsequent siblings)
19 siblings, 0 replies; 28+ messages in thread
From: dlinkin @ 2021-06-02 12:17 UTC (permalink / raw)
To: netdev
Cc: davem, kuba, jiri, stephen, dsahern, vladbu, parav, huyn, Dmytro Linkin
From: Dmytro Linkin <dlinkin@nvidia.com>
Test verifies that it is possible to create, delete and set min/max tx
rate of devlink rate node on netdevsim VF.
Co-developed-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
Notes:
v1->v2:
- s/func/function/ in devlink commands
.../selftests/drivers/net/netdevsim/devlink.sh | 45 ++++++++++++++++++++++
1 file changed, 45 insertions(+)
diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
index 05dcefc..301d920 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
@@ -516,6 +516,14 @@ rate_leafs_get()
'.[] | to_entries | .[] | select(.value.type == "leaf") | .key | select(contains("'$handle'"))'
}
+rate_nodes_get()
+{
+ local handle=$1
+
+ cmd_jq "devlink port function rate show -j" \
+ '.[] | to_entries | .[] | select(.value.type == "node") | .key | select(contains("'$handle'"))'
+}
+
rate_attr_set()
{
local handle=$1
@@ -555,6 +563,20 @@ rate_attr_tx_rate_check()
check_err $? "Unexpected $name attr value $api_value != $rate"
}
+rate_node_add()
+{
+ local handle=$1
+
+ devlink port function rate add $handle
+}
+
+rate_node_del()
+{
+ local handle=$1
+
+ devlink port function rate del $handle
+}
+
rate_test()
{
RET=0
@@ -582,6 +604,29 @@ rate_test()
rate=$(($rate+100))
done
+ local node1_name='group1'
+ local node1="$DL_HANDLE/$node1_name"
+ rate_node_add "$node1"
+ check_err $? "Failed to add node $node1"
+
+ local num_nodes=`rate_nodes_get $DL_HANDLE | wc -w`
+ [ $num_nodes == 1 ]
+ check_err $? "Expected 1 rate node in output but got $num_nodes"
+
+ local node_tx_share=10
+ rate_attr_tx_rate_check $node1 tx_share $node_tx_share \
+ $DEBUGFS_DIR/rate_nodes/${node1##*/}/tx_share
+
+ local node_tx_max=100
+ rate_attr_tx_rate_check $node1 tx_max $node_tx_max \
+ $DEBUGFS_DIR/rate_nodes/${node1##*/}/tx_max
+
+ rate_node_del "$node1"
+ check_err $? "Failed to delete node $node1"
+ local num_nodes=`rate_nodes_get $DL_HANDLE | wc -w`
+ [ $num_nodes == 0 ]
+ check_err $? "Expected 0 rate node but got $num_nodes"
+
log_test "rate test"
}
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND net-next v3 15/18] devlink: Allow setting parent node of rate objects
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
` (13 preceding siblings ...)
2021-06-02 12:17 ` [PATCH RESEND net-next v3 14/18] selftest: netdevsim: Add devlink rate nodes test dlinkin
@ 2021-06-02 12:17 ` dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 16/18] netdevsim: " dlinkin
` (4 subsequent siblings)
19 siblings, 0 replies; 28+ messages in thread
From: dlinkin @ 2021-06-02 12:17 UTC (permalink / raw)
To: netdev
Cc: davem, kuba, jiri, stephen, dsahern, vladbu, parav, huyn, Dmytro Linkin
From: Dmytro Linkin <dlinkin@nvidia.com>
Refactor DEVLINK_CMD_RATE_{GET|SET} command handlers to support setting
a node as a parent for another rate object (leaf or node) by means of
new attribute DEVLINK_ATTR_RATE_PARENT_NODE_NAME. Extend devlink ops
with new callbacks rate_{leaf|node}_parent_set() to set node as a parent
for rate object to allow supporting drivers to implement rate grouping
through devlink. Driver implementations are allowed to support leafs
or node children only. Invoking callback with NULL as parent should be
threated by the driver as unset parent action.
Extend rate object struct with reference counter to disallow deleting a
node with any child pointing to it. User should unset parent for the
child explicitly.
Example:
$ devlink port function rate add netdevsim/netdevsim10/group1
$ devlink port function rate add netdevsim/netdevsim10/group2
$ devlink port function rate set netdevsim/netdevsim10/group1 parent group2
$ devlink port function rate show netdevsim/netdevsim10/group1
netdevsim/netdevsim10/group1: type node parent group2
$ devlink port function rate set netdevsim/netdevsim10/group1 noparent
Co-developed-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
Notes:
v1->v2:
- s/func/function/ at commit message
v2->v3:
- unset parents for all rate objects at devlink_rate_nodes_destroy()
include/net/devlink.h | 14 ++++-
include/uapi/linux/devlink.h | 1 +
net/core/devlink.c | 125 ++++++++++++++++++++++++++++++++++++++++++-
3 files changed, 137 insertions(+), 3 deletions(-)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 13162b5..eb045f1 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -142,9 +142,13 @@ struct devlink_rate {
u64 tx_share;
u64 tx_max;
+ struct devlink_rate *parent;
union {
struct devlink_port *devlink_port;
- char *name;
+ struct {
+ char *name;
+ refcount_t refcnt;
+ };
};
};
@@ -1486,6 +1490,14 @@ struct devlink_ops {
struct netlink_ext_ack *extack);
int (*rate_node_del)(struct devlink_rate *rate_node, void *priv,
struct netlink_ext_ack *extack);
+ int (*rate_leaf_parent_set)(struct devlink_rate *child,
+ struct devlink_rate *parent,
+ void *priv_child, void *priv_parent,
+ struct netlink_ext_ack *extack);
+ int (*rate_node_parent_set)(struct devlink_rate *child,
+ struct devlink_rate *parent,
+ void *priv_child, void *priv_parent,
+ struct netlink_ext_ack *extack);
};
static inline void *devlink_priv(struct devlink *devlink)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 7e15853..32f53a00 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -549,6 +549,7 @@ enum devlink_attr {
DEVLINK_ATTR_RATE_TX_SHARE, /* u64 */
DEVLINK_ATTR_RATE_TX_MAX, /* u64 */
DEVLINK_ATTR_RATE_NODE_NAME, /* string */
+ DEVLINK_ATTR_RATE_PARENT_NODE_NAME, /* string */
/* add new attributes above here, update the policy in devlink.c */
diff --git a/net/core/devlink.c b/net/core/devlink.c
index d520fb5..04cc5e5 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -880,6 +880,11 @@ static int devlink_nl_rate_fill(struct sk_buff *msg,
devlink_rate->tx_max, DEVLINK_ATTR_PAD))
goto nla_put_failure;
+ if (devlink_rate->parent)
+ if (nla_put_string(msg, DEVLINK_ATTR_RATE_PARENT_NODE_NAME,
+ devlink_rate->parent->name))
+ goto nla_put_failure;
+
genlmsg_end(msg, hdr);
return 0;
@@ -1152,6 +1157,18 @@ static int devlink_nl_cmd_rate_get_doit(struct sk_buff *skb,
return genlmsg_reply(msg, info);
}
+static bool
+devlink_rate_is_parent_node(struct devlink_rate *devlink_rate,
+ struct devlink_rate *parent)
+{
+ while (parent) {
+ if (parent == devlink_rate)
+ return true;
+ parent = parent->parent;
+ }
+ return false;
+}
+
static int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info)
{
struct devlink *devlink = info->user_ptr[0];
@@ -1572,11 +1589,75 @@ static int devlink_nl_cmd_port_del_doit(struct sk_buff *skb,
return devlink->ops->port_del(devlink, port_index, extack);
}
+static int
+devlink_nl_rate_parent_node_set(struct devlink_rate *devlink_rate,
+ struct genl_info *info,
+ struct nlattr *nla_parent)
+{
+ struct devlink *devlink = devlink_rate->devlink;
+ const char *parent_name = nla_data(nla_parent);
+ const struct devlink_ops *ops = devlink->ops;
+ size_t len = strlen(parent_name);
+ struct devlink_rate *parent;
+ int err = -EOPNOTSUPP;
+
+ parent = devlink_rate->parent;
+ if (parent && len) {
+ NL_SET_ERR_MSG_MOD(info->extack, "Rate object already has parent.");
+ return -EBUSY;
+ } else if (parent && !len) {
+ if (devlink_rate_is_leaf(devlink_rate))
+ err = ops->rate_leaf_parent_set(devlink_rate, NULL,
+ devlink_rate->priv, NULL,
+ info->extack);
+ else if (devlink_rate_is_node(devlink_rate))
+ err = ops->rate_node_parent_set(devlink_rate, NULL,
+ devlink_rate->priv, NULL,
+ info->extack);
+ if (err)
+ return err;
+
+ refcount_dec(&parent->refcnt);
+ devlink_rate->parent = NULL;
+ } else if (!parent && len) {
+ parent = devlink_rate_node_get_by_name(devlink, parent_name);
+ if (IS_ERR(parent))
+ return -ENODEV;
+
+ if (parent == devlink_rate) {
+ NL_SET_ERR_MSG_MOD(info->extack, "Parent to self is not allowed");
+ return -EINVAL;
+ }
+
+ if (devlink_rate_is_node(devlink_rate) &&
+ devlink_rate_is_parent_node(devlink_rate, parent->parent)) {
+ NL_SET_ERR_MSG_MOD(info->extack, "Node is already a parent of parent node.");
+ return -EEXIST;
+ }
+
+ if (devlink_rate_is_leaf(devlink_rate))
+ err = ops->rate_leaf_parent_set(devlink_rate, parent,
+ devlink_rate->priv, parent->priv,
+ info->extack);
+ else if (devlink_rate_is_node(devlink_rate))
+ err = ops->rate_node_parent_set(devlink_rate, parent,
+ devlink_rate->priv, parent->priv,
+ info->extack);
+ if (err)
+ return err;
+
+ refcount_inc(&parent->refcnt);
+ devlink_rate->parent = parent;
+ }
+
+ return 0;
+}
+
static int devlink_nl_rate_set(struct devlink_rate *devlink_rate,
const struct devlink_ops *ops,
struct genl_info *info)
{
- struct nlattr **attrs = info->attrs;
+ struct nlattr *nla_parent, **attrs = info->attrs;
int err = -EOPNOTSUPP;
u64 rate;
@@ -1606,6 +1687,14 @@ static int devlink_nl_rate_set(struct devlink_rate *devlink_rate,
devlink_rate->tx_max = rate;
}
+ nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME];
+ if (nla_parent) {
+ err = devlink_nl_rate_parent_node_set(devlink_rate, info,
+ nla_parent);
+ if (err)
+ return err;
+ }
+
return 0;
}
@@ -1624,6 +1713,11 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops,
NL_SET_ERR_MSG_MOD(info->extack, "TX max set isn't supported for the leafs");
return false;
}
+ if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] &&
+ !ops->rate_leaf_parent_set) {
+ NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the leafs");
+ return false;
+ }
} else if (type == DEVLINK_RATE_TYPE_NODE) {
if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_node_tx_share_set) {
NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the nodes");
@@ -1633,6 +1727,11 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops,
NL_SET_ERR_MSG_MOD(info->extack, "TX max set isn't supported for the nodes");
return false;
}
+ if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] &&
+ !ops->rate_node_parent_set) {
+ NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the nodes");
+ return false;
+ }
} else {
WARN_ON("Unknown type of rate object");
return false;
@@ -1702,6 +1801,7 @@ static int devlink_nl_cmd_rate_new_doit(struct sk_buff *skb,
if (err)
goto err_rate_set;
+ refcount_set(&rate_node->refcnt, 1);
list_add(&rate_node->list, &devlink->rate_list);
devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
return 0;
@@ -1723,8 +1823,15 @@ static int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb,
const struct devlink_ops *ops = devlink->ops;
int err;
+ if (refcount_read(&rate_node->refcnt) > 1) {
+ NL_SET_ERR_MSG_MOD(info->extack, "Node has children. Cannot delete node.");
+ return -EBUSY;
+ }
+
devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL);
err = ops->rate_node_del(rate_node, rate_node->priv, info->extack);
+ if (rate_node->parent)
+ refcount_dec(&rate_node->parent->refcnt);
list_del(&rate_node->list);
kfree(rate_node->name);
kfree(rate_node);
@@ -8224,6 +8331,7 @@ static int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb,
[DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64 },
[DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64 },
[DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING },
+ [DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING },
};
static const struct genl_small_ops devlink_nl_ops[] = {
@@ -9135,7 +9243,8 @@ void devlink_rate_leaf_destroy(struct devlink_port *devlink_port)
*
* @devlink: devlink instance
*
- * Destroy all rate nodes on specified device
+ * Unset parent for all rate objects and destroy all rate nodes
+ * on specified device.
*
* Context: Takes and release devlink->lock <mutex>.
*/
@@ -9145,6 +9254,18 @@ void devlink_rate_nodes_destroy(struct devlink *devlink)
const struct devlink_ops *ops = devlink->ops;
mutex_lock(&devlink->lock);
+ list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
+ if (!devlink_rate->parent)
+ continue;
+
+ refcount_dec(&devlink_rate->parent->refcnt);
+ if (devlink_rate_is_leaf(devlink_rate))
+ ops->rate_leaf_parent_set(devlink_rate, NULL, devlink_rate->priv,
+ NULL, NULL);
+ else if (devlink_rate_is_node(devlink_rate))
+ ops->rate_node_parent_set(devlink_rate, NULL, devlink_rate->priv,
+ NULL, NULL);
+ }
list_for_each_entry_safe(devlink_rate, tmp, &devlink->rate_list, list) {
if (devlink_rate_is_node(devlink_rate)) {
ops->rate_node_del(devlink_rate, devlink_rate->priv, NULL);
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND net-next v3 16/18] netdevsim: Allow setting parent node of rate objects
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
` (14 preceding siblings ...)
2021-06-02 12:17 ` [PATCH RESEND net-next v3 15/18] devlink: Allow setting parent node of rate objects dlinkin
@ 2021-06-02 12:17 ` dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 17/18] selftest: netdevsim: Add devlink rate grouping test dlinkin
` (3 subsequent siblings)
19 siblings, 0 replies; 28+ messages in thread
From: dlinkin @ 2021-06-02 12:17 UTC (permalink / raw)
To: netdev
Cc: davem, kuba, jiri, stephen, dsahern, vladbu, parav, huyn, Dmytro Linkin
From: Dmytro Linkin <dlinkin@nvidia.com>
Implement new devlink ops that allow setting rate node as a parent for
devlink port (leaf) or another devlink node through devlink API.
Expose parent names to netdevsim debugfs in read only mode.
Co-developed-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
drivers/net/netdevsim/dev.c | 91 +++++++++++++++++++++++++++++++++++++--
drivers/net/netdevsim/netdevsim.h | 2 +
2 files changed, 89 insertions(+), 4 deletions(-)
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 9f01b6c..527b019 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -222,6 +222,7 @@ static ssize_t nsim_dev_trap_fa_cookie_write(struct file *file,
static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev)
{
char dev_ddir_name[sizeof(DRV_NAME) + 10];
+ int err;
sprintf(dev_ddir_name, DRV_NAME "%u", nsim_dev->nsim_bus_dev->dev.id);
nsim_dev->ddir = debugfs_create_dir(dev_ddir_name, nsim_dev_ddir);
@@ -264,10 +265,17 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev)
nsim_dev->nsim_bus_dev,
&nsim_dev_max_vfs_fops);
nsim_dev->nodes_ddir = debugfs_create_dir("rate_nodes", nsim_dev->ddir);
- if (IS_ERR(nsim_dev->nodes_ddir))
- return PTR_ERR(nsim_dev->nodes_ddir);
+ if (IS_ERR(nsim_dev->nodes_ddir)) {
+ err = PTR_ERR(nsim_dev->nodes_ddir);
+ goto err_out;
+ }
nsim_udp_tunnels_debugfs_create(nsim_dev);
return 0;
+
+err_out:
+ debugfs_remove_recursive(nsim_dev->ports_ddir);
+ debugfs_remove_recursive(nsim_dev->ddir);
+ return err;
}
static void nsim_dev_debugfs_exit(struct nsim_dev *nsim_dev)
@@ -277,6 +285,27 @@ static void nsim_dev_debugfs_exit(struct nsim_dev *nsim_dev)
debugfs_remove_recursive(nsim_dev->ddir);
}
+static ssize_t nsim_dev_rate_parent_read(struct file *file,
+ char __user *data,
+ size_t count, loff_t *ppos)
+{
+ char **name_ptr = file->private_data;
+ size_t len;
+
+ if (!*name_ptr)
+ return 0;
+
+ len = strlen(*name_ptr);
+ return simple_read_from_buffer(data, count, ppos, *name_ptr, len);
+}
+
+static const struct file_operations nsim_dev_rate_parent_fops = {
+ .open = simple_open,
+ .read = nsim_dev_rate_parent_read,
+ .llseek = generic_file_llseek,
+ .owner = THIS_MODULE,
+};
+
static int nsim_dev_port_debugfs_init(struct nsim_dev *nsim_dev,
struct nsim_dev_port *nsim_dev_port)
{
@@ -299,6 +328,11 @@ static int nsim_dev_port_debugfs_init(struct nsim_dev *nsim_dev,
&nsim_bus_dev->vfconfigs[vf_id].min_tx_rate);
debugfs_create_u16("tx_max", 0400, nsim_dev_port->ddir,
&nsim_bus_dev->vfconfigs[vf_id].max_tx_rate);
+ nsim_dev_port->rate_parent = debugfs_create_file("rate_parent",
+ 0400,
+ nsim_dev_port->ddir,
+ &nsim_dev_port->parent_name,
+ &nsim_dev_rate_parent_fops);
}
debugfs_create_symlink("dev", nsim_dev_port->ddir, dev_link_name);
@@ -1068,6 +1102,8 @@ static int nsim_leaf_tx_max_set(struct devlink_rate *devlink_rate, void *priv,
struct nsim_rate_node {
struct dentry *ddir;
+ struct dentry *rate_parent;
+ char *parent_name;
u16 tx_share;
u16 tx_max;
};
@@ -1105,6 +1141,7 @@ static int nsim_rate_node_new(struct devlink_rate *node, void **priv,
{
struct nsim_dev *nsim_dev = devlink_priv(node->devlink);
struct nsim_rate_node *nsim_node;
+ int err;
if (!nsim_esw_mode_is_switchdev(nsim_dev)) {
NL_SET_ERR_MSG_MOD(extack, "Node creation allowed only in switchdev mode.");
@@ -1117,13 +1154,28 @@ static int nsim_rate_node_new(struct devlink_rate *node, void **priv,
nsim_node->ddir = debugfs_create_dir(node->name, nsim_dev->nodes_ddir);
if (!nsim_node->ddir) {
- kfree(nsim_node);
- return -ENOMEM;
+ err = -ENOMEM;
+ goto err_node;
}
debugfs_create_u16("tx_share", 0400, nsim_node->ddir, &nsim_node->tx_share);
debugfs_create_u16("tx_max", 0400, nsim_node->ddir, &nsim_node->tx_max);
+ nsim_node->rate_parent = debugfs_create_file("rate_parent", 0400,
+ nsim_node->ddir,
+ &nsim_node->parent_name,
+ &nsim_dev_rate_parent_fops);
+ if (IS_ERR(nsim_node->rate_parent)) {
+ err = PTR_ERR(nsim_node->rate_parent);
+ goto err_ddir;
+ }
+
*priv = nsim_node;
return 0;
+
+err_ddir:
+ debugfs_remove_recursive(nsim_node->ddir);
+err_node:
+ kfree(nsim_node);
+ return err;
}
static int nsim_rate_node_del(struct devlink_rate *node, void *priv,
@@ -1131,11 +1183,40 @@ static int nsim_rate_node_del(struct devlink_rate *node, void *priv,
{
struct nsim_rate_node *nsim_node = priv;
+ debugfs_remove(nsim_node->rate_parent);
debugfs_remove_recursive(nsim_node->ddir);
kfree(nsim_node);
return 0;
}
+static int nsim_rate_leaf_parent_set(struct devlink_rate *child,
+ struct devlink_rate *parent,
+ void *priv_child, void *priv_parent,
+ struct netlink_ext_ack *extack)
+{
+ struct nsim_dev_port *nsim_dev_port = priv_child;
+
+ if (parent)
+ nsim_dev_port->parent_name = parent->name;
+ else
+ nsim_dev_port->parent_name = NULL;
+ return 0;
+}
+
+static int nsim_rate_node_parent_set(struct devlink_rate *child,
+ struct devlink_rate *parent,
+ void *priv_child, void *priv_parent,
+ struct netlink_ext_ack *extack)
+{
+ struct nsim_rate_node *nsim_node = priv_child;
+
+ if (parent)
+ nsim_node->parent_name = parent->name;
+ else
+ nsim_node->parent_name = NULL;
+ return 0;
+}
+
static const struct devlink_ops nsim_dev_devlink_ops = {
.eswitch_mode_set = nsim_devlink_eswitch_mode_set,
.eswitch_mode_get = nsim_devlink_eswitch_mode_get,
@@ -1157,6 +1238,8 @@ static int nsim_rate_node_del(struct devlink_rate *node, void *priv,
.rate_node_tx_max_set = nsim_node_tx_max_set,
.rate_node_new = nsim_rate_node_new,
.rate_node_del = nsim_rate_node_del,
+ .rate_leaf_parent_set = nsim_rate_leaf_parent_set,
+ .rate_node_parent_set = nsim_rate_node_parent_set,
};
#define NSIM_DEV_MAX_MACS_DEFAULT 32
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index d62a138..cdfdf2a 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -211,6 +211,8 @@ struct nsim_dev_port {
unsigned int port_index;
enum nsim_dev_port_type port_type;
struct dentry *ddir;
+ struct dentry *rate_parent;
+ char *parent_name;
struct netdevsim *ns;
};
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND net-next v3 17/18] selftest: netdevsim: Add devlink rate grouping test
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
` (15 preceding siblings ...)
2021-06-02 12:17 ` [PATCH RESEND net-next v3 16/18] netdevsim: " dlinkin
@ 2021-06-02 12:17 ` dlinkin
2021-06-02 12:17 ` [PATCH RESEND net-next v3 18/18] Documentation: devlink rate objects dlinkin
` (2 subsequent siblings)
19 siblings, 0 replies; 28+ messages in thread
From: dlinkin @ 2021-06-02 12:17 UTC (permalink / raw)
To: netdev
Cc: davem, kuba, jiri, stephen, dsahern, vladbu, parav, huyn, Dmytro Linkin
From: Dmytro Linkin <dlinkin@nvidia.com>
Test verifies that netdevsim correctly implements devlink ops callbacks
that set node as a parent of devlink leaf or node rate object.
Co-developed-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
.../selftests/drivers/net/netdevsim/devlink.sh | 42 ++++++++++++++++++++++
1 file changed, 42 insertions(+)
diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
index 301d920..9de1d12 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
@@ -563,6 +563,26 @@ rate_attr_tx_rate_check()
check_err $? "Unexpected $name attr value $api_value != $rate"
}
+rate_attr_parent_check()
+{
+ local handle=$1
+ local parent=$2
+ local debug_file=$3
+
+ rate_attr_set $handle parent $parent
+ check_err $? "Failed to set parent"
+
+ debug_value=$(cat $debug_file)
+ check_err $? "Failed to get parent debugfs value"
+ [ "$debug_value" == "$parent" ]
+ check_err $? "Unexpected parent debug value $debug_value != $parent"
+
+ api_value=$(rate_attr_get $r_obj parent)
+ check_err $? "Failed to get parent attr value"
+ [ "$api_value" == "$parent" ]
+ check_err $? "Unexpected parent attr value $api_value != $parent"
+}
+
rate_node_add()
{
local handle=$1
@@ -627,6 +647,28 @@ rate_test()
[ $num_nodes == 0 ]
check_err $? "Expected 0 rate node but got $num_nodes"
+ local node1_name='group1'
+ local node1="$DL_HANDLE/$node1_name"
+ rate_node_add "$node1"
+ check_err $? "Failed to add node $node1"
+
+ rate_attr_parent_check $r_obj $node1_name \
+ $DEBUGFS_DIR/ports/${r_obj##*/}/rate_parent
+
+ local node2_name='group2'
+ local node2="$DL_HANDLE/$node2_name"
+ rate_node_add "$node2"
+ check_err $? "Failed to add node $node2"
+
+ rate_attr_parent_check $node2 $node1_name \
+ $DEBUGFS_DIR/rate_nodes/$node2_name/rate_parent
+ rate_node_del "$node2"
+ check_err $? "Failed to delete node $node2"
+ rate_attr_set "$r_obj" noparent
+ check_err $? "Failed to unset $r_obj parent node"
+ rate_node_del "$node1"
+ check_err $? "Failed to delete node $node1"
+
log_test "rate test"
}
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND net-next v3 18/18] Documentation: devlink rate objects
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
` (16 preceding siblings ...)
2021-06-02 12:17 ` [PATCH RESEND net-next v3 17/18] selftest: netdevsim: Add devlink rate grouping test dlinkin
@ 2021-06-02 12:17 ` dlinkin
2021-06-02 12:31 ` [PATCH RESEND iproute2 net-next 0/4] devlink rate support Dmytro Linkin
2021-06-02 16:58 ` [PATCH RESEND net-next v3 00/18] devlink: rate objects API Jakub Kicinski
19 siblings, 0 replies; 28+ messages in thread
From: dlinkin @ 2021-06-02 12:17 UTC (permalink / raw)
To: netdev
Cc: davem, kuba, jiri, stephen, dsahern, vladbu, parav, huyn, Dmytro Linkin
From: Dmytro Linkin <dlinkin@nvidia.com>
Add devlink rate objects section at devlink port documentation.
Add devlink rate support info at netdevsim devlink documentation.
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
Documentation/networking/devlink/devlink-port.rst | 35 +++++++++++++++++++++++
Documentation/networking/devlink/netdevsim.rst | 26 +++++++++++++++++
2 files changed, 61 insertions(+)
diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst
index ab790e7..7627b1d 100644
--- a/Documentation/networking/devlink/devlink-port.rst
+++ b/Documentation/networking/devlink/devlink-port.rst
@@ -164,6 +164,41 @@ device to instantiate the subfunction device on particular PCI function.
A subfunction device is created on the :ref:`Documentation/driver-api/auxiliary_bus.rst <auxiliary_bus>`.
At this point a matching subfunction driver binds to the subfunction's auxiliary device.
+Rate object management
+======================
+
+Devlink provides API to manage tx rates of single devlink port or a group.
+This is done through rate objects, which can be one of the two types:
+
+``leaf``
+ Represents a single devlink port; created/destroyed by the driver. Since leaf
+ have 1to1 mapping to its devlink port, in user space it is referred as
+ ``pci/<bus_addr>/<port_index>``;
+
+``node``
+ Represents a group of rate objects (leafs and/or nodes); created/deleted by
+ request from the userspace; initially empty (no rate objects added). In
+ userspace it is referred as ``pci/<bus_addr>/<node_name>``, where
+ ``node_name`` can be any identifier, except decimal number, to avoid
+ collisions with leafs.
+
+API allows to configure following rate object's parameters:
+
+``tx_share``
+ Minimum TX rate value shared among all other rate objects, or rate objects
+ that parts of the parent group, if it is a part of the same group.
+
+``tx_max``
+ Maximum TX rate value.
+
+``parent``
+ Parent node name. Parent node rate limits are considered as additional limits
+ to all node children limits. ``tx_max`` is an upper limit for children.
+ ``tx_share`` is a total bandwidth distributed among children.
+
+Driver implementations are allowed to support both or either rate object types
+and setting methods of their parameters.
+
Terms and Definitions
=====================
diff --git a/Documentation/networking/devlink/netdevsim.rst b/Documentation/networking/devlink/netdevsim.rst
index 02c2d20..8a292fb 100644
--- a/Documentation/networking/devlink/netdevsim.rst
+++ b/Documentation/networking/devlink/netdevsim.rst
@@ -57,6 +57,32 @@ entries, FIB rule entries and nexthops that the driver will allow.
$ devlink resource set netdevsim/netdevsim0 path /nexthops size 16
$ devlink dev reload netdevsim/netdevsim0
+Rate objects
+============
+
+The ``netdevsim`` driver supports rate objects management, which includes:
+
+- registerging/unregistering leaf rate objects per VF devlink port;
+- creation/deletion node rate objects;
+- setting tx_share and tx_max rate values for any rate object type;
+- setting parent node for any rate object type.
+
+Rate nodes and it's parameters are exposed in ``netdevsim`` debugfs in RO mode.
+For example created rate node with name ``some_group``:
+
+.. code:: shell
+
+ $ ls /sys/kernel/debug/netdevsim/netdevsim0/rate_groups/some_group
+ rate_parent tx_max tx_share
+
+Same parameters are exposed for leaf objects in corresponding ports directories.
+For ex.:
+
+.. code:: shell
+
+ $ ls /sys/kernel/debug/netdevsim/netdevsim0/ports/1
+ dev ethtool rate_parent tx_max tx_share
+
Driver-specific Traps
=====================
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND iproute2 net-next 0/4] devlink rate support
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
` (17 preceding siblings ...)
2021-06-02 12:17 ` [PATCH RESEND net-next v3 18/18] Documentation: devlink rate objects dlinkin
@ 2021-06-02 12:31 ` Dmytro Linkin
2021-06-02 12:31 ` [PATCH RESEND iproute2 net-next 1/4] uapi: update devlink kernel header Dmytro Linkin
` (3 more replies)
2021-06-02 16:58 ` [PATCH RESEND net-next v3 00/18] devlink: rate objects API Jakub Kicinski
19 siblings, 4 replies; 28+ messages in thread
From: Dmytro Linkin @ 2021-06-02 12:31 UTC (permalink / raw)
To: dlinkin; +Cc: davem, dsahern, huyn, jiri, kuba, netdev, parav, stephen, vladbu
Resending without RFC.
Serries implements devlink rate commands, which are:
- Dump particular or all rate objects (JSON or non-JSON)
- Add/Delete node rate object
- Set tx rate share/max values for rate object
- Set/Unset parent rate object for other rate object
Examples:
Display all rate objects:
# devlink port function rate show
pci/0000:03:00.0/1 type leaf parent some_group
pci/0000:03:00.0/2 type leaf tx_share 12Mbit
pci/0000:03:00.0/some_group type node tx_share 1Gbps tx_max 5Gbps
Display leaf rate object bound to the 1st devlink port of the
pci/0000:03:00.0 device:
# devlink port function rate show pci/0000:03:00.0/1
pci/0000:03:00.0/1 type leaf
Display node rate object with name some_group of the pci/0000:03:00.0
device:
# devlink port function rate show pci/0000:03:00.0/some_group
pci/0000:03:00.0/some_group type node
Display leaf rate object rate values using IEC units:
# devlink -i port function rate show pci/0000:03:00.0/2
pci/0000:03:00.0/2 type leaf 11718Kibit
Display pci/0000:03:00.0/2 leaf rate object as pretty JSON output:
# devlink -jp port function rate show pci/0000:03:00.0/2
{
"rate": {
"pci/0000:03:00.0/2": {
"type": "leaf",
"tx_share": 1500000
}
}
}
Create node rate object with name "1st_group" on pci/0000:03:00.0 device:
# devlink port function rate add pci/0000:03:00.0/1st_group
Create node rate object with specified parameters:
# devlink port function rate add pci/0000:03:00.0/2nd_group \
tx_share 10Mbit tx_max 30Mbit parent 1st_group
Set parameters to the specified leaf rate object:
# devlink port function rate set pci/0000:03:00.0/1 \
tx_share 2Mbit tx_max 10Mbit
Set leaf's parent to "1st_group":
# devlink port function rate set pci/0000:03:00.0/1 parent 1st_group
Unset leaf's parent:
# devlink port function rate set pci/0000:03:00.0/1 noparent
Delete node rate object:
# devlink port function rate del pci/0000:03:00.0/2nd_group
Rate values can be specified in bits or bytes per second (bit|bps), with
any SI (k, m, g, t) or IEC (ki, mi, gi, ti) prefix. Bare number means
bits per second. Units also printed in "show" command output, but not
necessarily the same which were specified with "set" or "add" command.
-i/--iec switch force output in IEC units. JSON output always print
values as bytes per sec.
Dmytro Linkin (4):
uapi: update devlink kernel header
devlink: Add helper function to validate object handler
devlink: Add port func rate support
devlink: Add ISO/IEC switch
devlink/devlink.c | 527 ++++++++++++++++++++++++++++++++++++++++---
include/uapi/linux/devlink.h | 17 ++
man/man8/devlink-port.8 | 8 +
man/man8/devlink-rate.8 | 270 ++++++++++++++++++++++
man/man8/devlink.8 | 4 +
5 files changed, 797 insertions(+), 29 deletions(-)
create mode 100644 man/man8/devlink-rate.8
--
1.8.3.1
^ permalink raw reply [flat|nested] 28+ messages in thread* [PATCH RESEND iproute2 net-next 1/4] uapi: update devlink kernel header
2021-06-02 12:31 ` [PATCH RESEND iproute2 net-next 0/4] devlink rate support Dmytro Linkin
@ 2021-06-02 12:31 ` Dmytro Linkin
2021-06-02 12:31 ` [PATCH RESEND iproute2 net-next 2/4] devlink: Add helper function to validate object handler Dmytro Linkin
` (2 subsequent siblings)
3 siblings, 0 replies; 28+ messages in thread
From: Dmytro Linkin @ 2021-06-02 12:31 UTC (permalink / raw)
To: dlinkin; +Cc: davem, dsahern, huyn, jiri, kuba, netdev, parav, stephen, vladbu
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
---
include/uapi/linux/devlink.h | 17 +++++++++++++++++
1 file changed, 17 insertions(+)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index a430775..6408b40 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -126,6 +126,11 @@ enum devlink_command {
DEVLINK_CMD_HEALTH_REPORTER_TEST,
+ DEVLINK_CMD_RATE_GET, /* can dump */
+ DEVLINK_CMD_RATE_SET,
+ DEVLINK_CMD_RATE_NEW,
+ DEVLINK_CMD_RATE_DEL,
+
/* add new commands above here */
__DEVLINK_CMD_MAX,
DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
@@ -206,6 +211,11 @@ enum devlink_port_flavour {
*/
};
+enum devlink_rate_type {
+ DEVLINK_RATE_TYPE_LEAF,
+ DEVLINK_RATE_TYPE_NODE,
+};
+
enum devlink_param_cmode {
DEVLINK_PARAM_CMODE_RUNTIME,
DEVLINK_PARAM_CMODE_DRIVERINIT,
@@ -534,6 +544,13 @@ enum devlink_attr {
DEVLINK_ATTR_RELOAD_ACTION_STATS, /* nested */
DEVLINK_ATTR_PORT_PCI_SF_NUMBER, /* u32 */
+
+ DEVLINK_ATTR_RATE_TYPE, /* u16 */
+ DEVLINK_ATTR_RATE_TX_SHARE, /* u64 */
+ DEVLINK_ATTR_RATE_TX_MAX, /* u64 */
+ DEVLINK_ATTR_RATE_NODE_NAME, /* string */
+ DEVLINK_ATTR_RATE_PARENT_NODE_NAME, /* string */
+
/* add new attributes above here, update the policy in devlink.c */
__DEVLINK_ATTR_MAX,
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND iproute2 net-next 2/4] devlink: Add helper function to validate object handler
2021-06-02 12:31 ` [PATCH RESEND iproute2 net-next 0/4] devlink rate support Dmytro Linkin
2021-06-02 12:31 ` [PATCH RESEND iproute2 net-next 1/4] uapi: update devlink kernel header Dmytro Linkin
@ 2021-06-02 12:31 ` Dmytro Linkin
2021-06-02 12:31 ` [PATCH RESEND iproute2 net-next 3/4] devlink: Add port func rate support Dmytro Linkin
2021-06-02 12:31 ` [PATCH RESEND iproute2 net-next 4/4] devlink: Add ISO/IEC switch Dmytro Linkin
3 siblings, 0 replies; 28+ messages in thread
From: Dmytro Linkin @ 2021-06-02 12:31 UTC (permalink / raw)
To: dlinkin; +Cc: davem, dsahern, huyn, jiri, kuba, netdev, parav, stephen, vladbu
Every handler argument validated in two steps, first of which, form
checking, expects identifier is few words separated by slashes.
For device and region handlers just checked if identifier have expected
number of slashes.
Add generic function to do that and make code cleaner & consistent.
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
devlink/devlink.c | 38 +++++++++++++++++++++-----------------
1 file changed, 21 insertions(+), 17 deletions(-)
diff --git a/devlink/devlink.c b/devlink/devlink.c
index 16eca4f..f435fc8 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -915,6 +915,19 @@ static int strtobool(const char *str, bool *p_val)
return 0;
}
+static int ident_str_validate(char *str, unsigned int expected)
+{
+ if (!str)
+ return -EINVAL;
+
+ if (get_str_char_count(str, '/') != expected) {
+ pr_err("Wrong identification string format.\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int __dl_argv_handle(char *str, char **p_bus_name, char **p_dev_name)
{
str_split_by_char(str, p_bus_name, p_dev_name, '/');
@@ -924,15 +937,12 @@ static int __dl_argv_handle(char *str, char **p_bus_name, char **p_dev_name)
static int dl_argv_handle(struct dl *dl, char **p_bus_name, char **p_dev_name)
{
char *str = dl_argv_next(dl);
+ int err;
- if (!str) {
+ err = ident_str_validate(str, 1);
+ if (err) {
pr_err("Devlink identification (\"bus_name/dev_name\") expected\n");
- return -EINVAL;
- }
- if (get_str_char_count(str, '/') != 1) {
- pr_err("Wrong devlink identification string format.\n");
- pr_err("Expected \"bus_name/dev_name\".\n");
- return -EINVAL;
+ return err;
}
return __dl_argv_handle(str, p_bus_name, p_dev_name);
}
@@ -1067,18 +1077,12 @@ static int dl_argv_handle_region(struct dl *dl, char **p_bus_name,
char **p_dev_name, char **p_region)
{
char *str = dl_argv_next(dl);
- unsigned int slash_count;
+ int err;
- if (!str) {
- pr_err("Expected \"bus_name/dev_name/region\" identification.\n");
- return -EINVAL;
- }
-
- slash_count = get_str_char_count(str, '/');
- if (slash_count != 2) {
- pr_err("Wrong region identification string format.\n");
+ err = ident_str_validate(str, 2);
+ if (err) {
pr_err("Expected \"bus_name/dev_name/region\" identification.\n"".\n");
- return -EINVAL;
+ return err;
}
return __dl_argv_handle_region(str, p_bus_name, p_dev_name, p_region);
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND iproute2 net-next 3/4] devlink: Add port func rate support
2021-06-02 12:31 ` [PATCH RESEND iproute2 net-next 0/4] devlink rate support Dmytro Linkin
2021-06-02 12:31 ` [PATCH RESEND iproute2 net-next 1/4] uapi: update devlink kernel header Dmytro Linkin
2021-06-02 12:31 ` [PATCH RESEND iproute2 net-next 2/4] devlink: Add helper function to validate object handler Dmytro Linkin
@ 2021-06-02 12:31 ` Dmytro Linkin
2021-06-02 12:31 ` [PATCH RESEND iproute2 net-next 4/4] devlink: Add ISO/IEC switch Dmytro Linkin
3 siblings, 0 replies; 28+ messages in thread
From: Dmytro Linkin @ 2021-06-02 12:31 UTC (permalink / raw)
To: dlinkin; +Cc: davem, dsahern, huyn, jiri, kuba, netdev, parav, stephen, vladbu
Implement user commands to manage devlink port func rate objects.
List all rate commands:
$ devlink port func rate help
or just
$ devlink port func rate
To list all OR particular rate object:
$ devlink port func rate show
pci/0000:03:00.0/some_group: type node
pci/0000:03:00.0/0: type leaf
pci/0000:03:00.0/1: type leaf
$ devlink prot func rate show pci/0000:03:00.0/1
pci/0000:03:00.0/0: type leaf
$ devlink prot func rate show pci/0000:03:00.0/some_group
pci/0000:03:00.0/some_group: type node
Rate object of type "leaf" created by it's driver where name is the name
of corresponding devlink port. Rate object of type "node" represents
rate group created by the user using commands:
$ devlink port func rate add pci/0000:03:00.0/some_group
or with defining tx rate limits
$ devlink port func rate add pci/0000:03:00.0/some_group \
tx_shara 10kbit tx_max 100mbit
NOTE: node name cannot be a decimal value because it conflicts with
devlink port indexes.
To delete node object:
$ devlink port func rate del pci/0000:03:00.0/some_group
Set rate limits of existing rate object:
$ devlink prot func rate set pci/0000:03:00.0/0 \
tx_share 5MBps tx_max 25GBps
$ devlink prot func rate set pci/0000:03:00.0/some_group \
tx_share 0
Both SET and ADD commands accept any units of rates defined in IEC
60027-2 standard.
NOTE: rate value 0 means that rate is unlimited. Such value is also
ommited in show command output.
NOTE: In SHOW command output rate values will be printed with suffixes
as well, but in JSON output they are always units of Bps.
Set or unset parent of existing rate object:
$ devlink prot func rate set pci/0000:03:00.0/0 parent some_group
$ devlink port func rate set pci/0000:03:00.0/0 noparent
NOTE: Setting parent to empty ("") name due to kernel logic means unset
parent and shouldn't be used to avoid unexpected parent unsets.
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
devlink/devlink.c | 489 ++++++++++++++++++++++++++++++++++++++++++++++--
man/man8/devlink-port.8 | 8 +
man/man8/devlink-rate.8 | 256 +++++++++++++++++++++++++
3 files changed, 738 insertions(+), 15 deletions(-)
create mode 100644 man/man8/devlink-rate.8
diff --git a/devlink/devlink.c b/devlink/devlink.c
index f435fc8..202359e 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -286,6 +286,11 @@ static void ifname_map_free(struct ifname_map *ifname_map)
#define DL_OPT_PORT_PFNUMBER BIT(43)
#define DL_OPT_PORT_SFNUMBER BIT(44)
#define DL_OPT_PORT_FUNCTION_STATE BIT(45)
+#define DL_OPT_PORT_FN_RATE_TYPE BIT(46)
+#define DL_OPT_PORT_FN_RATE_TX_SHARE BIT(47)
+#define DL_OPT_PORT_FN_RATE_TX_MAX BIT(48)
+#define DL_OPT_PORT_FN_RATE_NODE_NAME BIT(49)
+#define DL_OPT_PORT_FN_RATE_PARENT BIT(50)
struct dl_opts {
uint64_t present; /* flags of present items */
@@ -340,6 +345,11 @@ struct dl_opts {
uint16_t port_flavour;
uint16_t port_pfnumber;
uint8_t port_fn_state;
+ uint16_t rate_type;
+ uint64_t rate_tx_share;
+ uint64_t rate_tx_max;
+ char *rate_node_name;
+ const char *rate_parent_node;
};
struct dl {
@@ -1054,38 +1064,103 @@ static int dl_argv_handle_both(struct dl *dl, char **p_bus_name,
return 0;
}
-static int __dl_argv_handle_region(char *str, char **p_bus_name,
- char **p_dev_name, char **p_region)
+static int __dl_argv_handle_name(char *str, char **p_bus_name,
+ char **p_dev_name, char **p_name)
{
char *handlestr;
int err;
- err = str_split_by_char(str, &handlestr, p_region, '/');
- if (err) {
- pr_err("Region identification \"%s\" is invalid\n", str);
+ err = str_split_by_char(str, &handlestr, p_name, '/');
+ if (err)
return err;
- }
- err = str_split_by_char(handlestr, p_bus_name, p_dev_name, '/');
- if (err) {
- pr_err("Region identification \"%s\" is invalid\n", str);
- return err;
- }
- return 0;
+
+ return str_split_by_char(handlestr, p_bus_name, p_dev_name, '/');
}
static int dl_argv_handle_region(struct dl *dl, char **p_bus_name,
- char **p_dev_name, char **p_region)
+ char **p_dev_name, char **p_region)
{
char *str = dl_argv_next(dl);
int err;
err = ident_str_validate(str, 2);
if (err) {
- pr_err("Expected \"bus_name/dev_name/region\" identification.\n"".\n");
+ pr_err("Expected \"bus_name/dev_name/region\" identification.\n");
return err;
}
- return __dl_argv_handle_region(str, p_bus_name, p_dev_name, p_region);
+ err = __dl_argv_handle_name(str, p_bus_name, p_dev_name, p_region);
+ if (err)
+ pr_err("Region identification \"%s\" is invalid\n", str);
+ return err;
+}
+
+
+static int dl_argv_handle_rate_node(struct dl *dl, char **p_bus_name,
+ char **p_dev_name, char **p_node)
+{
+ char *str = dl_argv_next(dl);
+ int err;
+
+ err = ident_str_validate(str, 2);
+ if (err) {
+ pr_err("Expected \"bus_name/dev_name/node\" identification.\n");
+ return err;
+ }
+
+ err = __dl_argv_handle_name(str, p_bus_name, p_dev_name, p_node);
+ if (err) {
+ pr_err("Node identification \"%s\" is invalid\n", str);
+ return err;
+ }
+
+ if (!**p_node || strspn(*p_node, "0123456789") == strlen(*p_node)) {
+ err = -EINVAL;
+ pr_err("Node name cannot be a devlink port index or empty.\n");
+ }
+
+ return err;
+}
+
+static int dl_argv_handle_rate(struct dl *dl, char **p_bus_name,
+ char **p_dev_name, uint32_t *p_port_index,
+ char **p_node_name, uint64_t *p_handle_bit)
+{
+ char *str = dl_argv_next(dl);
+ char *identifier;
+ int err;
+
+ err = ident_str_validate(str, 2);
+ if (err) {
+ pr_err("Expected \"bus_name/dev_name/node\" or "
+ "\"bus_name/dev_name/port_index\" identification.\n");
+ return err;
+ }
+
+ err = __dl_argv_handle_name(str, p_bus_name, p_dev_name, &identifier);
+ if (err) {
+ pr_err("Identification \"%s\" is invalid\n", str);
+ return err;
+ }
+
+ if (!*identifier) {
+ pr_err("Identifier cannot be empty");
+ return -EINVAL;
+ }
+
+ if (strspn(identifier, "0123456789") == strlen(identifier)) {
+ err = strtouint32_t(identifier, p_port_index);
+ if (err) {
+ pr_err("Port index \"%s\" is not a number"
+ " or not within range\n", identifier);
+ return err;
+ }
+ *p_handle_bit = DL_OPT_HANDLEP;
+ } else {
+ *p_handle_bit = DL_OPT_PORT_FN_RATE_NODE_NAME;
+ *p_node_name = identifier;
+ }
+ return 0;
}
static int dl_argv_uint64_t(struct dl *dl, uint64_t *p_val)
@@ -1397,6 +1472,36 @@ static int port_fn_state_parse(const char *statestr, uint8_t *state)
return 0;
}
+static int port_fn_rate_type_get(const char *typestr, uint16_t *type)
+{
+ if (!strcmp(typestr, "leaf"))
+ *type = DEVLINK_RATE_TYPE_LEAF;
+ else if (!strcmp(typestr, "node"))
+ *type = DEVLINK_RATE_TYPE_NODE;
+ else
+ return -EINVAL;
+ return 0;
+}
+
+static int port_fn_rate_value_get(struct dl *dl, uint64_t *rate)
+{
+ const char *ratestr;
+ __u64 rate64;
+ int err;
+
+ err = dl_argv_str(dl, &ratestr);
+ if (err)
+ return err;
+ err = get_rate64(&rate64, ratestr);
+ if (err) {
+ pr_err("Invalid rate value: \"%s\"\n", ratestr);
+ return -EINVAL;
+ }
+
+ *rate = rate64;
+ return 0;
+}
+
struct dl_args_metadata {
uint64_t o_flag;
char err_msg[DL_ARGS_REQUIRED_MAX_ERR_LEN];
@@ -1469,6 +1574,19 @@ static int dl_argv_parse(struct dl *dl, uint64_t o_required,
return err;
o_required &= ~(DL_OPT_HANDLE | DL_OPT_HANDLEP) | handle_bit;
o_found |= handle_bit;
+ } else if (o_required & DL_OPT_HANDLEP &&
+ o_required & DL_OPT_PORT_FN_RATE_NODE_NAME) {
+ uint64_t handle_bit;
+
+ err = dl_argv_handle_rate(dl, &opts->bus_name, &opts->dev_name,
+ &opts->port_index,
+ &opts->rate_node_name,
+ &handle_bit);
+ if (err)
+ return err;
+ o_required &= ~(DL_OPT_HANDLEP | DL_OPT_PORT_FN_RATE_NODE_NAME) |
+ handle_bit;
+ o_found |= handle_bit;
} else if (o_required & DL_OPT_HANDLE) {
err = dl_argv_handle(dl, &opts->bus_name, &opts->dev_name);
if (err)
@@ -1487,6 +1605,13 @@ static int dl_argv_parse(struct dl *dl, uint64_t o_required,
if (err)
return err;
o_found |= DL_OPT_HANDLE_REGION;
+ } else if (o_required & DL_OPT_PORT_FN_RATE_NODE_NAME) {
+ err = dl_argv_handle_rate_node(dl, &opts->bus_name,
+ &opts->dev_name,
+ &opts->rate_node_name);
+ if (err)
+ return err;
+ o_found |= DL_OPT_PORT_FN_RATE_NODE_NAME;
}
while (dl_argc(dl)) {
@@ -1884,6 +2009,44 @@ static int dl_argv_parse(struct dl *dl, uint64_t o_required,
if (err)
return err;
o_found |= DL_OPT_PORT_SFNUMBER;
+ } else if (dl_argv_match(dl, "type") &&
+ (o_all & DL_OPT_PORT_FN_RATE_TYPE)) {
+ const char *typestr;
+
+ dl_arg_inc(dl);
+ err = dl_argv_str(dl, &typestr);
+ if (err)
+ return err;
+ err = port_fn_rate_type_get(typestr, &opts->rate_type);
+ if (err)
+ return err;
+ o_found |= DL_OPT_PORT_FN_RATE_TYPE;
+ } else if (dl_argv_match(dl, "tx_share") &&
+ (o_all & DL_OPT_PORT_FN_RATE_TX_SHARE)) {
+ dl_arg_inc(dl);
+ err = port_fn_rate_value_get(dl, &opts->rate_tx_share);
+ if (err)
+ return err;
+ o_found |= DL_OPT_PORT_FN_RATE_TX_SHARE;
+ } else if (dl_argv_match(dl, "tx_max") &&
+ (o_all & DL_OPT_PORT_FN_RATE_TX_MAX)) {
+ dl_arg_inc(dl);
+ err = port_fn_rate_value_get(dl, &opts->rate_tx_max);
+ if (err)
+ return err;
+ o_found |= DL_OPT_PORT_FN_RATE_TX_MAX;
+ } else if (dl_argv_match(dl, "parent") &&
+ (o_all & DL_OPT_PORT_FN_RATE_PARENT)) {
+ dl_arg_inc(dl);
+ err = dl_argv_str(dl, &opts->rate_parent_node);
+ if (err)
+ return err;
+ o_found |= DL_OPT_PORT_FN_RATE_PARENT;
+ } else if (dl_argv_match(dl, "noparent") &&
+ (o_all & DL_OPT_PORT_FN_RATE_PARENT)) {
+ dl_arg_inc(dl);
+ opts->rate_parent_node = "";
+ o_found |= DL_OPT_PORT_FN_RATE_PARENT;
} else {
pr_err("Unknown option \"%s\"\n", dl_argv(dl));
return -EINVAL;
@@ -1956,6 +2119,11 @@ static void dl_opts_put(struct nlmsghdr *nlh, struct dl *dl)
mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, opts->dev_name);
mnl_attr_put_strz(nlh, DEVLINK_ATTR_REGION_NAME,
opts->region_name);
+ } else if (opts->present & DL_OPT_PORT_FN_RATE_NODE_NAME) {
+ mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, opts->bus_name);
+ mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, opts->dev_name);
+ mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_NODE_NAME,
+ opts->rate_node_name);
}
if (opts->present & DL_OPT_PORT_TYPE)
mnl_attr_put_u16(nlh, DEVLINK_ATTR_PORT_TYPE,
@@ -2077,6 +2245,18 @@ static void dl_opts_put(struct nlmsghdr *nlh, struct dl *dl)
mnl_attr_put_u16(nlh, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, opts->port_pfnumber);
if (opts->present & DL_OPT_PORT_SFNUMBER)
mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_PCI_SF_NUMBER, opts->port_sfnumber);
+ if (opts->present & DL_OPT_PORT_FN_RATE_TYPE)
+ mnl_attr_put_u16(nlh, DEVLINK_ATTR_RATE_TYPE,
+ opts->rate_type);
+ if (opts->present & DL_OPT_PORT_FN_RATE_TX_SHARE)
+ mnl_attr_put_u64(nlh, DEVLINK_ATTR_RATE_TX_SHARE,
+ opts->rate_tx_share);
+ if (opts->present & DL_OPT_PORT_FN_RATE_TX_MAX)
+ mnl_attr_put_u64(nlh, DEVLINK_ATTR_RATE_TX_MAX,
+ opts->rate_tx_max);
+ if (opts->present & DL_OPT_PORT_FN_RATE_PARENT)
+ mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_PARENT_NODE_NAME,
+ opts->rate_parent_node);
}
static int dl_argv_parse_put(struct nlmsghdr *nlh, struct dl *dl,
@@ -3790,6 +3970,7 @@ static void cmd_port_help(void)
pr_err(" devlink port split DEV/PORT_INDEX count COUNT\n");
pr_err(" devlink port unsplit DEV/PORT_INDEX\n");
pr_err(" devlink port function set DEV/PORT_INDEX [ hw_addr ADDR ] [ state STATE ]\n");
+ pr_err(" devlink port function rate { help | show | add | del | set }\n");
pr_err(" devlink port param set DEV/PORT_INDEX name PARAMETER value VALUE cmode { permanent | driverinit | runtime }\n");
pr_err(" devlink port param show [DEV/PORT_INDEX name PARAMETER]\n");
pr_err(" devlink port health show [ DEV/PORT_INDEX reporter REPORTER_NAME ]\n");
@@ -4083,6 +4264,7 @@ static int cmd_port_param_show(struct dl *dl)
static void cmd_port_function_help(void)
{
pr_err("Usage: devlink port function set DEV/PORT_INDEX [ hw_addr ADDR ] [ state STATE ]\n");
+ pr_err(" devlink port function rate { help | show | add | del | set }\n");
}
static int cmd_port_function_set(struct dl *dl)
@@ -4304,6 +4486,280 @@ static int cmd_port_param(struct dl *dl)
return -ENOENT;
}
+static void
+pr_out_port_rate_handle_start(struct dl *dl, struct nlattr **tb, bool try_nice)
+{
+ const char *bus_name;
+ const char *dev_name;
+ const char *node_name;
+ static char buf[64];
+
+ bus_name = mnl_attr_get_str(tb[DEVLINK_ATTR_BUS_NAME]);
+ dev_name = mnl_attr_get_str(tb[DEVLINK_ATTR_DEV_NAME]);
+ node_name = mnl_attr_get_str(tb[DEVLINK_ATTR_RATE_NODE_NAME]);
+ sprintf(buf, "%s/%s/%s", bus_name, dev_name, node_name);
+ if (dl->json_output)
+ open_json_object(buf);
+ else
+ pr_out("%s:", buf);
+}
+
+static char *port_rate_type_name(uint16_t type)
+{
+ switch (type) {
+ case DEVLINK_RATE_TYPE_LEAF:
+ return "leaf";
+ case DEVLINK_RATE_TYPE_NODE:
+ return "node";
+ default:
+ return "<unknown type>";
+ }
+}
+
+static void pr_out_port_fn_rate(struct dl *dl, struct nlattr **tb)
+{
+
+ if (!tb[DEVLINK_ATTR_RATE_NODE_NAME])
+ pr_out_port_handle_start(dl, tb, false);
+ else
+ pr_out_port_rate_handle_start(dl, tb, false);
+ check_indent_newline(dl);
+
+ if (tb[DEVLINK_ATTR_RATE_TYPE]) {
+ uint16_t type =
+ mnl_attr_get_u16(tb[DEVLINK_ATTR_RATE_TYPE]);
+
+ print_string(PRINT_ANY, "type", "type %s",
+ port_rate_type_name(type));
+ }
+ if (tb[DEVLINK_ATTR_RATE_TX_SHARE]) {
+ uint64_t rate =
+ mnl_attr_get_u64(tb[DEVLINK_ATTR_RATE_TX_SHARE]);
+
+ if (rate)
+ print_rate(false, PRINT_ANY, "tx_share",
+ " tx_share %s", rate);
+ }
+ if (tb[DEVLINK_ATTR_RATE_TX_MAX]) {
+ uint64_t rate =
+ mnl_attr_get_u64(tb[DEVLINK_ATTR_RATE_TX_MAX]);
+
+ if (rate)
+ print_rate(false, PRINT_ANY, "tx_max",
+ " tx_max %s", rate);
+ }
+ if (tb[DEVLINK_ATTR_RATE_PARENT_NODE_NAME]) {
+ const char *parent =
+ mnl_attr_get_str(tb[DEVLINK_ATTR_RATE_PARENT_NODE_NAME]);
+
+ print_string(PRINT_ANY, "parent", " parent %s", parent);
+ }
+
+ pr_out_port_handle_end(dl);
+}
+
+static int cmd_port_fn_rate_show_cb(const struct nlmsghdr *nlh, void *data)
+{
+ struct dl *dl = data;
+ struct nlattr *tb[DEVLINK_ATTR_MAX + 1] = {};
+ struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+
+ mnl_attr_parse(nlh, sizeof(*genl), attr_cb, tb);
+ if ((!tb[DEVLINK_ATTR_BUS_NAME] || !tb[DEVLINK_ATTR_DEV_NAME] ||
+ !tb[DEVLINK_ATTR_PORT_INDEX]) &&
+ !tb[DEVLINK_ATTR_RATE_NODE_NAME]) {
+ return MNL_CB_ERROR;
+ }
+ pr_out_port_fn_rate(dl, tb);
+ return MNL_CB_OK;
+}
+
+static void cmd_port_fn_rate_help(void)
+{
+ pr_err("Usage: devlink port function rate help\n");
+ pr_err(" devlink port function rate show [ DEV/{ PORT_INDEX | NODE_NAME } ]\n");
+ pr_err(" devlink port function rate add DEV/NODE_NAME\n");
+ pr_err(" [ tx_share VAL ][ tx_max VAL ][ { parent NODE_NAME | noparent } ]\n");
+ pr_err(" devlink port function rate del DEV/NODE_NAME\n");
+ pr_err(" devlink port function rate set DEV/{ PORT_INDEX | NODE_NAME }\n");
+ pr_err(" [ tx_share VAL ][ tx_max VAL ][ { parent NODE_NAME | noparent } ]\n\n");
+ pr_err(" VAL - float or integer value in units of bits or bytes per second (bit|bps)\n");
+ pr_err(" and SI (k-, m-, g-, t-) or IEC (ki-, mi-, gi-, ti-) case-insensitive prefix.\n");
+ pr_err(" Bare number, means bits per second, is possible.\n\n");
+ pr_err(" For details refer to devlink-rate(8) man page.\n");
+}
+
+static int cmd_port_fn_rate_show(struct dl *dl)
+{
+ struct nlmsghdr *nlh;
+ uint16_t flags = NLM_F_REQUEST | NLM_F_ACK;
+ int err;
+
+ if (dl_argc(dl) == 0)
+ flags |= NLM_F_DUMP;
+
+ nlh = mnlu_gen_socket_cmd_prepare(&dl->nlg, DEVLINK_CMD_RATE_GET, flags);
+
+ if (dl_argc(dl) > 0) {
+ err = dl_argv_parse_put(nlh, dl, DL_OPT_HANDLEP |
+ DL_OPT_PORT_FN_RATE_NODE_NAME, 0);
+ if (err)
+ return err;
+ }
+
+ pr_out_section_start(dl, "rate");
+ err = mnlu_gen_socket_sndrcv(&dl->nlg, nlh, cmd_port_fn_rate_show_cb, dl);
+ pr_out_section_end(dl);
+ return err;
+}
+
+static int port_fn_check_tx_rates(uint64_t min_rate, uint64_t max_rate)
+{
+ if (max_rate && min_rate > max_rate) {
+ pr_err("Invalid. Expected tx_share <= tx_max or tx_share == 0.\n");
+ return -EINVAL;
+ }
+ return 0;
+}
+
+static int port_fn_get_and_check_tx_rates(struct dl_opts *reply,
+ struct dl_opts *request)
+{
+ uint64_t min = reply->rate_tx_share;
+ uint64_t max = reply->rate_tx_max;
+
+ if (request->present & DL_OPT_PORT_FN_RATE_TX_SHARE)
+ return port_fn_check_tx_rates(request->rate_tx_share, max);
+ return port_fn_check_tx_rates(min, request->rate_tx_max);
+}
+
+static int cmd_port_fn_rate_add(struct dl *dl)
+{
+ struct nlmsghdr *nlh;
+ int err;
+
+ nlh = mnlu_gen_socket_cmd_prepare(&dl->nlg, DEVLINK_CMD_RATE_NEW,
+ NLM_F_REQUEST | NLM_F_ACK);
+ err = dl_argv_parse_put(nlh, dl, DL_OPT_PORT_FN_RATE_NODE_NAME,
+ DL_OPT_PORT_FN_RATE_TX_SHARE |
+ DL_OPT_PORT_FN_RATE_TX_MAX);
+ if (err)
+ return err;
+
+ if ((dl->opts.present & DL_OPT_PORT_FN_RATE_TX_SHARE) &&
+ (dl->opts.present & DL_OPT_PORT_FN_RATE_TX_MAX)) {
+ err = port_fn_check_tx_rates(dl->opts.rate_tx_share,
+ dl->opts.rate_tx_max);
+ if (err)
+ return err;
+ }
+
+ return mnlu_gen_socket_sndrcv(&dl->nlg, nlh, NULL, NULL);
+}
+
+static int cmd_port_fn_rate_del(struct dl *dl)
+{
+ struct nlmsghdr *nlh;
+ int err;
+
+ nlh = mnlu_gen_socket_cmd_prepare(&dl->nlg, DEVLINK_CMD_RATE_DEL,
+ NLM_F_REQUEST | NLM_F_ACK);
+ err = dl_argv_parse_put(nlh, dl, DL_OPT_PORT_FN_RATE_NODE_NAME, 0);
+ if (err)
+ return err;
+
+ return mnlu_gen_socket_sndrcv(&dl->nlg, nlh, NULL, NULL);
+}
+
+static int port_fn_get_rates_cb(const struct nlmsghdr *nlh, void *data)
+{
+ struct dl_opts *opts = data;
+ struct nlattr *tb[DEVLINK_ATTR_MAX + 1] = {};
+ struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+
+ mnl_attr_parse(nlh, sizeof(*genl), attr_cb, tb);
+ if ((!tb[DEVLINK_ATTR_BUS_NAME] || !tb[DEVLINK_ATTR_DEV_NAME] ||
+ !tb[DEVLINK_ATTR_PORT_INDEX]) &&
+ !tb[DEVLINK_ATTR_RATE_NODE_NAME]) {
+ return MNL_CB_ERROR;
+ }
+
+ if (tb[DEVLINK_ATTR_RATE_TX_SHARE])
+ opts->rate_tx_share =
+ mnl_attr_get_u64(tb[DEVLINK_ATTR_RATE_TX_SHARE]);
+ if (tb[DEVLINK_ATTR_RATE_TX_MAX])
+ opts->rate_tx_max =
+ mnl_attr_get_u64(tb[DEVLINK_ATTR_RATE_TX_MAX]);
+ return MNL_CB_OK;
+}
+
+static int cmd_port_fn_rate_set(struct dl *dl)
+{
+ struct dl_opts tmp_opts = {0};
+ struct nlmsghdr *nlh;
+ int err;
+
+ err = dl_argv_parse(dl, DL_OPT_HANDLEP |
+ DL_OPT_PORT_FN_RATE_NODE_NAME,
+ DL_OPT_PORT_FN_RATE_TX_SHARE |
+ DL_OPT_PORT_FN_RATE_TX_MAX |
+ DL_OPT_PORT_FN_RATE_PARENT);
+ if (err)
+ return err;
+
+ if ((dl->opts.present & DL_OPT_PORT_FN_RATE_TX_SHARE) &&
+ (dl->opts.present & DL_OPT_PORT_FN_RATE_TX_MAX)) {
+ err = port_fn_check_tx_rates(dl->opts.rate_tx_share,
+ dl->opts.rate_tx_max);
+ if (err)
+ return err;
+ } else if (dl->opts.present &
+ (DL_OPT_PORT_FN_RATE_TX_SHARE | DL_OPT_PORT_FN_RATE_TX_MAX)) {
+ nlh = mnlu_gen_socket_cmd_prepare(&dl->nlg, DEVLINK_CMD_RATE_GET,
+ NLM_F_REQUEST | NLM_F_ACK);
+ tmp_opts = dl->opts;
+ dl->opts.present &= ~(DL_OPT_PORT_FN_RATE_TX_SHARE |
+ DL_OPT_PORT_FN_RATE_TX_MAX |
+ DL_OPT_PORT_FN_RATE_PARENT);
+ dl_opts_put(nlh, dl);
+ err = mnlu_gen_socket_sndrcv(&dl->nlg, nlh, port_fn_get_rates_cb,
+ &dl->opts);
+ if (err)
+ return err;
+ err = port_fn_get_and_check_tx_rates(&dl->opts, &tmp_opts);
+ if (err)
+ return err;
+ dl->opts = tmp_opts;
+ }
+
+ nlh = mnlu_gen_socket_cmd_prepare(&dl->nlg, DEVLINK_CMD_RATE_SET,
+ NLM_F_REQUEST | NLM_F_ACK);
+ dl_opts_put(nlh, dl);
+ return mnlu_gen_socket_sndrcv(&dl->nlg, nlh, NULL, NULL);
+}
+
+static int cmd_port_function_rate(struct dl *dl)
+{
+ if (dl_argv_match(dl, "help")) {
+ cmd_port_fn_rate_help();
+ return 0;
+ } else if (dl_argv_match(dl, "show") || dl_no_arg(dl)) {
+ dl_arg_inc(dl);
+ return cmd_port_fn_rate_show(dl);
+ } else if (dl_argv_match(dl, "add")) {
+ dl_arg_inc(dl);
+ return cmd_port_fn_rate_add(dl);
+ } else if (dl_argv_match(dl, "del")) {
+ dl_arg_inc(dl);
+ return cmd_port_fn_rate_del(dl);
+ } else if (dl_argv_match(dl, "set")) {
+ dl_arg_inc(dl);
+ return cmd_port_fn_rate_set(dl);
+ }
+ pr_err("Command \"%s\" not found\n", dl_argv(dl));
+ return -ENOENT;
+}
+
static int cmd_port_function(struct dl *dl)
{
if (dl_argv_match(dl, "help") || dl_no_arg(dl)) {
@@ -4312,6 +4768,9 @@ static int cmd_port_function(struct dl *dl)
} else if (dl_argv_match(dl, "set")) {
dl_arg_inc(dl);
return cmd_port_function_set(dl);
+ } else if (dl_argv_match(dl, "rate")) {
+ dl_arg_inc(dl);
+ return cmd_port_function_rate(dl);
}
pr_err("Command \"%s\" not found\n", dl_argv(dl));
return -ENOENT;
diff --git a/man/man8/devlink-port.8 b/man/man8/devlink-port.8
index 563c583..616f094 100644
--- a/man/man8/devlink-port.8
+++ b/man/man8/devlink-port.8
@@ -71,6 +71,10 @@ devlink-port \- devlink port configuration
.RI "STATE }"
.ti -8
+.BR "devlink port function rate "
+.RI "{ " show " | " set " | " add " | " del " | " help " }"
+
+.ti -8
.B devlink dev param set
.I DEV/PORT_INDEX
.B name
@@ -240,6 +244,10 @@ Configuration mode in which the new value is set.
Specify parameter name to show.
If this argument, as well as port index, are omitted - all parameters supported by devlink device ports are listed.
+.SS devlink port function rate - manage devlink rate objects
+Is an alias for
+.BR devlink-rate (8).
+
.SH "EXAMPLES"
.PP
devlink port show
diff --git a/man/man8/devlink-rate.8 b/man/man8/devlink-rate.8
new file mode 100644
index 0000000..a6e28ac
--- /dev/null
+++ b/man/man8/devlink-rate.8
@@ -0,0 +1,256 @@
+.TH DEVLINK\-RATE 8 "12 Mar 2021" "iproute2" "Linux"
+.SH NAME
+devlink-rate \- devlink rate management
+.SH SYNOPSIS
+.sp
+.ad l
+.in +8
+.ti -8
+.B devlink
+.RI "[ " OPTIONS " ]"
+.B port function rate
+.RI " { " COMMAND " | "
+.BR help " }"
+.sp
+
+.ti -8
+.IR OPTIONS " := { "
+.BR -j [ \fIson "] | " -p [ \fIretty "] }"
+
+.ti -8
+.B devlink port function rate show
+.RI "[ { " DEV/PORT_INDEX " | " DEV/NODE_NAME " } ]"
+
+.ti -8
+.B devlink port function rate set
+.RI "{ " DEV/PORT_INDEX " | " DEV/NODE_NAME " } "
+.RB [ " tx_share \fIVALUE " ]
+.RB [ " tx_max \fIVALUE " ]
+.RB "[ {" " parent \fINODE_NAME " | " noparent " "} ]"
+
+.ti -8
+.BI "devlink port function rate add " DEV/NODE_NAME
+.RB [ " tx_share \fIVALUE " ]
+.RB [ " tx_max \fIVALUE " ]
+.RB "[ {" " parent \fINODE_NAME " | " noparent " "} ]"
+
+.ti -8
+.BI "devlink port function rate del " DEV/NODE_NAME
+
+.ti -8
+.B devlink port function rate help
+
+.SH "DESCRIPTION"
+
+.SS devlink port function rate show - display rate objects.
+Displays specified rate object or, if not specified, all rate objects. Rate
+object can be presented by one of the two types:
+.TP 8
+.B leaf
+Represents a single devlink port; created/destroyed by the driver and bound to
+the devlink port. As example, some driver may create leaf rate object for every
+devlink port associated with VF. Since leaf have 1to1 mapping to it's devlink
+port, in user space it is referred as corresponding devlink port
+\fIDEV/PORT_INDEX\fR;
+.TP 8
+.B node
+Represents a group of rate objects; created/deleted by the user (see command
+below) and bound to the devlink device rather then to the devlink port. In
+userspace it is referred as \fIDEV/NODE_NAME\fR, where node name can be any,
+except decimal number, to avoid collisions with leafs.
+.PP
+Command output show rate object identifier, it's type and rate values along with
+parent node name. Rate values printed in SI units which are more suitable to
+represent specific value. JSON (\fB-j\fR) output always print rate values in
+bytes per second. Zero rate values means "unlimited" rates and ommited in
+output, as well as parent node name.
+
+.SS devlink port function rate set - set rate object parameters.
+Allows set rate object's parameters. If any parameter specified multiple times
+the last occurrence is used.
+.PP
+.I DEV/PORT_INDEX
+- specifies devlink leaf rate object.
+.br
+.I DEV/NODE_NAME
+- specifies devlink node rate object.
+.PP
+.BI tx_share " VALUE"
+- specifies minimal tx rate value shared among all rate objects. If rate object
+is a part of some rate group, then this value shared with rate objects of this
+rate group.
+.PP
+.BI tx_max " VALUE"
+- specifies maximum tx rate value.
+.TP 8
+.I VALUE
+These parameter accept a floating point number, possibly followed by either a
+unit.
+.RS
+.TP
+bit or a bare number
+Bits per second
+.TP
+kbit
+Kilobits per second
+.TP
+mbit
+Megabits per second
+.TP
+gbit
+Gigabits per second
+.TP
+tbit
+Terabits per second
+.TP
+bps
+Bytes per second
+.TP
+kbps
+Kilobytes per second
+.TP
+mbps
+Megabytes per second
+.TP
+gbps
+Gigabytes per second
+.TP
+tbps
+Terabytes per second
+.RE
+.PP
+.BI parent " NODE_NAME \fR| " noparent
+- set rate object parent to existing node with name \fINODE_NAME\fR or unset
+parent. Rate limits of the parent node applied to all it's children. Actual
+behaviour is details of driver's implementation. Setting parent to empty ("")
+name due to the kernel logic threated as parent unset.
+
+.SS devlink port function rate add - create node rate object with specified parameters.
+Creates rate object of type node and sets parameters. Parameters same as for the
+"set" command.
+.PP
+.I DEV/NODE_NAME
+- specifies the devlink node rate object to create.
+
+.SS devlink port function rate del - delete node rate object
+Delete specified devlink node rate object. Node can't be deleted if there is any
+child, user must explicitly unset the parent.
+.PP
+.I DEV/NODE_NAME
+- specifies devlink node rate object to delete.
+
+.SS devlink port function rate help - display usage information
+Display devlink rate usage information
+
+.SH "EXAMPLES"
+
+.PP
+\fB*\fR Display all rate objects:
+.RS 4
+.PP
+# devlink port function rate show
+.br
+pci/0000:03:00.0/1 type leaf parent some_group
+.br
+pci/0000:03:00.0/2 type leaf tx_share 12Mbit
+.br
+pci/0000:03:00.0/some_group type node tx_share 1Gbps tx_max 5Gbps
+.RE
+
+.PP
+\fB*\fR Display leaf rate object bound to the 1st devlink port of the
+pci/0000:03:00.0 device:
+.RS 4
+.PP
+# devlink port function rate show pci/0000:03:00.0/1
+.br
+pci/0000:03:00.0/1 type leaf
+.br
+.RE
+
+.PP
+\fB*\fR Display node rate object with name some_group of the pci/0000:03:00.0 device:
+.RS 4
+.PP
+# devlink port function rate show pci/0000:03:00.0/some_group
+.br
+pci/0000:03:00.0/some_group type node
+.br
+.RE
+
+.PP
+\fB*\fR Display pci/0000:03:00.0/2 leaf rate object as pretty JSON output:
+.RS 4
+.PP
+# devlink -jp port function rate show pci/0000:03:00.0/2
+.br
+{
+.br
+ "rate": {
+.br
+ "pci/0000:03:00.0/2": {
+.br
+ "type": "leaf",
+.br
+ "tx_share": 1500000
+.br
+ }
+.br
+ }
+.br
+}
+.RE
+
+.PP
+\fB*\fR Create node rate object with name "1st_group" on pci/0000:03:00.0 device:
+.RS 4
+.PP
+# devlink port function rate add pci/0000:03:00.0/1st_group
+.RE
+
+.PP
+\fB*\fR Create node rate object with specified parameters:
+.RS 4
+.PP
+# devlink port function rate add pci/0000:03:00.0/2nd_group \\
+.br
+ tx_share 10Mbit tx_max 30Mbit parent 1st_group
+.RE
+
+.PP
+\fB*\fR Set parameters to the specified leaf rate object:
+.RS 4
+.PP
+# devlink port function rate set pci/0000:03:00.0/1 \\
+.br
+ tx_share 2Mbit tx_max 10Mbit
+.RE
+
+.PP
+\fB*\fR Set leaf's parent to "1st_group":
+.RS 4
+.PP
+# devlink port function rate set pci/0000:03:00.0/1 parent 1st_group
+.RE
+
+.PP
+\fB*\fR Unset leaf's parent:
+.RS 4
+.PP
+# devlink port function rate set pci/0000:03:00.0/1 noparent
+.RE
+
+.PP
+\fB*\fR Delete node rate object:
+.RS 4
+.PP
+# devlink port function rate del pci/0000:03:00.0/2nd_group
+.RE
+
+.SH SEE ALSO
+.BR devlink (8),
+.BR devlink-port (8)
+.br
+
+.SH AUTHOR
+Dmytro Linkin <dlinkin@nvidia.com>
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH RESEND iproute2 net-next 4/4] devlink: Add ISO/IEC switch
2021-06-02 12:31 ` [PATCH RESEND iproute2 net-next 0/4] devlink rate support Dmytro Linkin
` (2 preceding siblings ...)
2021-06-02 12:31 ` [PATCH RESEND iproute2 net-next 3/4] devlink: Add port func rate support Dmytro Linkin
@ 2021-06-02 12:31 ` Dmytro Linkin
3 siblings, 0 replies; 28+ messages in thread
From: Dmytro Linkin @ 2021-06-02 12:31 UTC (permalink / raw)
To: dlinkin; +Cc: davem, dsahern, huyn, jiri, kuba, netdev, parav, stephen, vladbu
Add -i/--iec switch to print rate values using binary prefixes.
Update devlink(8) and devlink-rate(8) pages.
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
devlink/devlink.c | 12 +++++++++---
man/man8/devlink-rate.8 | 24 +++++++++++++++++++-----
man/man8/devlink.8 | 4 ++++
3 files changed, 32 insertions(+), 8 deletions(-)
diff --git a/devlink/devlink.c b/devlink/devlink.c
index 202359e..0347ac8 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -71,6 +71,8 @@ static bool g_indent_newline;
#define INDENT_STR_MAXLEN 32
static char g_indent_str[INDENT_STR_MAXLEN + 1] = "";
+static bool use_iec = false;
+
static void __attribute__((format(printf, 1, 2)))
pr_err(const char *fmt, ...)
{
@@ -4537,7 +4539,7 @@ static void pr_out_port_fn_rate(struct dl *dl, struct nlattr **tb)
mnl_attr_get_u64(tb[DEVLINK_ATTR_RATE_TX_SHARE]);
if (rate)
- print_rate(false, PRINT_ANY, "tx_share",
+ print_rate(use_iec, PRINT_ANY, "tx_share",
" tx_share %s", rate);
}
if (tb[DEVLINK_ATTR_RATE_TX_MAX]) {
@@ -4545,7 +4547,7 @@ static void pr_out_port_fn_rate(struct dl *dl, struct nlattr **tb)
mnl_attr_get_u64(tb[DEVLINK_ATTR_RATE_TX_MAX]);
if (rate)
- print_rate(false, PRINT_ANY, "tx_max",
+ print_rate(use_iec, PRINT_ANY, "tx_max",
" tx_max %s", rate);
}
if (tb[DEVLINK_ATTR_RATE_PARENT_NODE_NAME]) {
@@ -9066,6 +9068,7 @@ int main(int argc, char **argv)
{ "verbose", no_argument, NULL, 'v' },
{ "statistics", no_argument, NULL, 's' },
{ "Netns", required_argument, NULL, 'N' },
+ { "iec", no_argument, NULL, 'i' },
{ NULL, 0, NULL, 0 }
};
const char *batch_file = NULL;
@@ -9081,7 +9084,7 @@ int main(int argc, char **argv)
return EXIT_FAILURE;
}
- while ((opt = getopt_long(argc, argv, "Vfb:njpvsN:",
+ while ((opt = getopt_long(argc, argv, "Vfb:njpvsN:i",
long_options, NULL)) >= 0) {
switch (opt) {
@@ -9116,6 +9119,9 @@ int main(int argc, char **argv)
goto dl_free;
}
break;
+ case 'i':
+ use_iec = true;
+ break;
default:
pr_err("Unknown option.\n");
help();
diff --git a/man/man8/devlink-rate.8 b/man/man8/devlink-rate.8
index a6e28ac..76c65a3 100644
--- a/man/man8/devlink-rate.8
+++ b/man/man8/devlink-rate.8
@@ -15,7 +15,7 @@ devlink-rate \- devlink rate management
.ti -8
.IR OPTIONS " := { "
-.BR -j [ \fIson "] | " -p [ \fIretty "] }"
+.BR -j [ \fIson "] | " -p [ \fIretty "] | " -i [ \fIec "] }"
.ti -8
.B devlink port function rate show
@@ -61,9 +61,10 @@ except decimal number, to avoid collisions with leafs.
.PP
Command output show rate object identifier, it's type and rate values along with
parent node name. Rate values printed in SI units which are more suitable to
-represent specific value. JSON (\fB-j\fR) output always print rate values in
-bytes per second. Zero rate values means "unlimited" rates and ommited in
-output, as well as parent node name.
+represent specific value. To print values in IEC units \fB-i\fR switch is
+used. JSON (\fB-j\fR) output always print rate values in bytes per second. Zero
+rate values means "unlimited" rates and ommited in output, as well as parent
+node name.
.SS devlink port function rate set - set rate object parameters.
Allows set rate object's parameters. If any parameter specified multiple times
@@ -85,7 +86,7 @@ rate group.
.TP 8
.I VALUE
These parameter accept a floating point number, possibly followed by either a
-unit.
+unit (both SI and IEC units supported).
.RS
.TP
bit or a bare number
@@ -117,6 +118,9 @@ Gigabytes per second
.TP
tbps
Terabytes per second
+.P
+To specify in IEC units, replace the SI prefix (k-, m-, g-, t-) with IEC prefix
+(ki-, mi-, gi- and ti-) respectively. Input is case-insensitive.
.RE
.PP
.BI parent " NODE_NAME \fR| " noparent
@@ -169,6 +173,16 @@ pci/0000:03:00.0/1 type leaf
.RE
.PP
+\fB*\fR Display leaf rate object rate values using IEC units:
+.RS 4
+.PP
+# devlink -i port function rate show pci/0000:03:00.0/2
+.br
+pci/0000:03:00.0/2 type leaf 11718Kibit
+.br
+.RE
+
+.PP
\fB*\fR Display node rate object with name some_group of the pci/0000:03:00.0 device:
.RS 4
.PP
diff --git a/man/man8/devlink.8 b/man/man8/devlink.8
index 866fda5..840cf44 100644
--- a/man/man8/devlink.8
+++ b/man/man8/devlink.8
@@ -59,6 +59,10 @@ Output statistics.
.BR "\-N", " \-Netns " <NETNSNAME>
Switches to the specified network namespace.
+.TP
+.BR "\-i", " --iec"
+Print human readable rates in IEC units (e.g. 1Ki = 1024).
+
.SS
.I OBJECT
--
1.8.3.1
^ permalink raw reply related [flat|nested] 28+ messages in thread
* Re: [PATCH RESEND net-next v3 00/18] devlink: rate objects API
2021-06-02 12:17 [PATCH RESEND net-next v3 00/18] devlink: rate objects API dlinkin
` (18 preceding siblings ...)
2021-06-02 12:31 ` [PATCH RESEND iproute2 net-next 0/4] devlink rate support Dmytro Linkin
@ 2021-06-02 16:58 ` Jakub Kicinski
2021-06-03 8:53 ` Dmytro Linkin
2021-06-04 1:59 ` Yunsheng Lin
19 siblings, 2 replies; 28+ messages in thread
From: Jakub Kicinski @ 2021-06-02 16:58 UTC (permalink / raw)
To: dlinkin; +Cc: netdev, davem, jiri, stephen, dsahern, vladbu, parav, huyn
On Wed, 2 Jun 2021 15:17:13 +0300 dlinkin@nvidia.com wrote:
> From: Dmytro Linkin <dlinkin@nvidia.com>
>
> Resending without RFC.
>
> Currently kernel provides a way to change tx rate of single VF in
> switchdev mode via tc-police action. When lots of VFs are configured
> management of theirs rates becomes non-trivial task and some grouping
> mechanism is required. Implementing such grouping in tc-police will bring
> flow related limitations and unwanted complications, like:
> - tc-police is a policer and there is a user request for a traffic
> shaper, so shared tc-police action is not suitable;
> - flows requires net device to be placed on, means "groups" wouldn't
> have net device instance itself. Taking into the account previous
> point was reviewed a sollution, when representor have a policer and
> the driver use a shaper if qdisc contains group of VFs - such approach
> ugly, compilated and misleading;
> - TC is ingress only, while configuring "other" side of the wire looks
> more like a "real" picture where shaping is outside of the steering
> world, similar to "ip link" command;
>
> According to that devlink is the most appropriate place.
I don't think you researched TC well enough. But whatever, I'm tired
of being the only one who pushes back given I neither work on or use
any of these features.
You need to provide a real implementation for this new uAPI, tho.
netdevsim won't cut it.
^ permalink raw reply [flat|nested] 28+ messages in thread* Re: [PATCH RESEND net-next v3 00/18] devlink: rate objects API
2021-06-02 16:58 ` [PATCH RESEND net-next v3 00/18] devlink: rate objects API Jakub Kicinski
@ 2021-06-03 8:53 ` Dmytro Linkin
2021-06-04 1:59 ` Yunsheng Lin
1 sibling, 0 replies; 28+ messages in thread
From: Dmytro Linkin @ 2021-06-03 8:53 UTC (permalink / raw)
To: Jakub Kicinski
Cc: netdev, davem, Jiri Pirko, stephen, dsahern, Vlad Buslov,
Parav Pandit, Huy Nguyen, Saeed Mahameed
On 6/2/21 7:58 PM, Jakub Kicinski wrote:
> On Wed, 2 Jun 2021 15:17:13 +0300 dlinkin@nvidia.com wrote:
>> From: Dmytro Linkin <dlinkin@nvidia.com>
>>
>> Resending without RFC.
>>
>> Currently kernel provides a way to change tx rate of single VF in
>> switchdev mode via tc-police action. When lots of VFs are configured
>> management of theirs rates becomes non-trivial task and some grouping
>> mechanism is required. Implementing such grouping in tc-police will bring
>> flow related limitations and unwanted complications, like:
>> - tc-police is a policer and there is a user request for a traffic
>> shaper, so shared tc-police action is not suitable;
>> - flows requires net device to be placed on, means "groups" wouldn't
>> have net device instance itself. Taking into the account previous
>> point was reviewed a sollution, when representor have a policer and
>> the driver use a shaper if qdisc contains group of VFs - such approach
>> ugly, compilated and misleading;
>> - TC is ingress only, while configuring "other" side of the wire looks
>> more like a "real" picture where shaping is outside of the steering
>> world, similar to "ip link" command;
>>
>> According to that devlink is the most appropriate place.
>
> I don't think you researched TC well enough. But whatever, I'm tired
> of being the only one who pushes back given I neither work on or use
> any of these features.
>
> You need to provide a real implementation for this new uAPI, tho.
> netdevsim won't cut it.
>
+Saeed
The series is already big enough to add more patches to it and
implementation (mlx5_core) must go through Saeed. How would You like to
proceed?
^ permalink raw reply [flat|nested] 28+ messages in thread
* Re: [PATCH RESEND net-next v3 00/18] devlink: rate objects API
2021-06-02 16:58 ` [PATCH RESEND net-next v3 00/18] devlink: rate objects API Jakub Kicinski
2021-06-03 8:53 ` Dmytro Linkin
@ 2021-06-04 1:59 ` Yunsheng Lin
1 sibling, 0 replies; 28+ messages in thread
From: Yunsheng Lin @ 2021-06-04 1:59 UTC (permalink / raw)
To: Jakub Kicinski, dlinkin
Cc: netdev, davem, jiri, stephen, dsahern, vladbu, parav, huyn,
Simon Horman, louis.peens, baowen.zheng, idosch, mleitner, vlad,
Jamal Hadi Salim, jianbol
On 2021/6/3 0:58, Jakub Kicinski wrote:
> On Wed, 2 Jun 2021 15:17:13 +0300 dlinkin@nvidia.com wrote:
>> From: Dmytro Linkin <dlinkin@nvidia.com>
>>
>> Resending without RFC.
>>
>> Currently kernel provides a way to change tx rate of single VF in
>> switchdev mode via tc-police action. When lots of VFs are configured
>> management of theirs rates becomes non-trivial task and some grouping
>> mechanism is required. Implementing such grouping in tc-police will bring
>> flow related limitations and unwanted complications, like:
>> - tc-police is a policer and there is a user request for a traffic
>> shaper, so shared tc-police action is not suitable;
>> - flows requires net device to be placed on, means "groups" wouldn't
>> have net device instance itself. Taking into the account previous
>> point was reviewed a sollution, when representor have a policer and
>> the driver use a shaper if qdisc contains group of VFs - such approach
>> ugly, compilated and misleading;
>> - TC is ingress only, while configuring "other" side of the wire looks
>> more like a "real" picture where shaping is outside of the steering
>> world, similar to "ip link" command;
>>
>> According to that devlink is the most appropriate place.
>
> I don't think you researched TC well enough. But whatever, I'm tired
> of being the only one who pushes back given I neither work on or use
> any of these features.
tc action offload feature used in [1] seems to solve the
police action lifecycle problem?
And it seem to allow different flow to use the same action,
I am not sure if different function can use the same action,
it seems jianbo has mentioned about the same usecase?
1. https://lore.kernel.org/netdev/CALnP8ZaZQAbvm1girLUSLcFZTKV5MvBMEtN67OiA55OAvsO_1Q@mail.gmail.com/T/
^ permalink raw reply [flat|nested] 28+ messages in thread