diff options
Diffstat (limited to 'drivers/net/netdevsim')
| -rw-r--r-- | drivers/net/netdevsim/Makefile | 6 | ||||
| -rw-r--r-- | drivers/net/netdevsim/bpf.c | 28 | ||||
| -rw-r--r-- | drivers/net/netdevsim/bus.c | 108 | ||||
| -rw-r--r-- | drivers/net/netdevsim/dev.c | 1104 | ||||
| -rw-r--r-- | drivers/net/netdevsim/ethtool.c | 199 | ||||
| -rw-r--r-- | drivers/net/netdevsim/fib.c | 1132 | ||||
| -rw-r--r-- | drivers/net/netdevsim/health.c | 48 | ||||
| -rw-r--r-- | drivers/net/netdevsim/hwstats.c | 486 | ||||
| -rw-r--r-- | drivers/net/netdevsim/ipsec.c | 40 | ||||
| -rw-r--r-- | drivers/net/netdevsim/netdev.c | 173 | ||||
| -rw-r--r-- | drivers/net/netdevsim/netdevsim.h | 177 | ||||
| -rw-r--r-- | drivers/net/netdevsim/psample.c | 265 | ||||
| -rw-r--r-- | drivers/net/netdevsim/udp_tunnels.c | 217 |
13 files changed, 3410 insertions, 573 deletions
diff --git a/drivers/net/netdevsim/Makefile b/drivers/net/netdevsim/Makefile index f4d8f62f28c2..5735e5b1a2cb 100644 --- a/drivers/net/netdevsim/Makefile +++ b/drivers/net/netdevsim/Makefile @@ -3,7 +3,7 @@ obj-$(CONFIG_NETDEVSIM) += netdevsim.o netdevsim-objs := \ - netdev.o dev.o fib.o bus.o health.o + netdev.o dev.o ethtool.o fib.o bus.o health.o hwstats.o udp_tunnels.o ifeq ($(CONFIG_BPF_SYSCALL),y) netdevsim-objs += \ @@ -13,3 +13,7 @@ endif ifneq ($(CONFIG_XFRM_OFFLOAD),) netdevsim-objs += ipsec.o endif + +ifneq ($(CONFIG_PSAMPLE),) +netdevsim-objs += psample.o +endif diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index 0b362b8dac17..50854265864d 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -63,15 +63,20 @@ static int nsim_bpf_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn) { struct nsim_bpf_bound_prog *state; + int ret = 0; state = env->prog->aux->offload->dev_priv; if (state->nsim_dev->bpf_bind_verifier_delay && !insn_idx) msleep(state->nsim_dev->bpf_bind_verifier_delay); - if (insn_idx == env->prog->len - 1) + if (insn_idx == env->prog->len - 1) { pr_vlog(env, "Hello from netdevsim!\n"); - return 0; + if (!state->nsim_dev->bpf_bind_verifier_accept) + ret = -EOPNOTSUPP; + } + + return ret; } static int nsim_bpf_finalize(struct bpf_verifier_env *env) @@ -190,9 +195,6 @@ nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf, { int err; - if (!xdp_attachment_flags_ok(xdp, bpf)) - return -EBUSY; - if (bpf->command == XDP_SETUP_PROG && !ns->bpf_xdpdrv_accept) { NSIM_EA(bpf->extack, "driver XDP disabled in DebugFS"); return -EOPNOTSUPP; @@ -349,10 +351,12 @@ nsim_map_alloc_elem(struct bpf_offloaded_map *offmap, unsigned int idx) { struct nsim_bpf_bound_map *nmap = offmap->dev_priv; - nmap->entry[idx].key = kmalloc(offmap->map.key_size, GFP_USER); + nmap->entry[idx].key = kmalloc(offmap->map.key_size, + GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!nmap->entry[idx].key) return -ENOMEM; - nmap->entry[idx].value = kmalloc(offmap->map.value_size, GFP_USER); + nmap->entry[idx].value = kmalloc(offmap->map.value_size, + GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!nmap->entry[idx].value) { kfree(nmap->entry[idx].key); nmap->entry[idx].key = NULL; @@ -494,7 +498,7 @@ nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap) if (offmap->map.map_flags) return -EINVAL; - nmap = kzalloc(sizeof(*nmap), GFP_USER); + nmap = kzalloc(sizeof(*nmap), GFP_KERNEL_ACCOUNT); if (!nmap) return -ENOMEM; @@ -512,6 +516,7 @@ nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap) goto err_free; key = nmap->entry[i].key; *key = i; + memset(nmap->entry[i].value, 0, offmap->map.value_size); } } @@ -551,10 +556,6 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf) ASSERT_RTNL(); switch (bpf->command) { - case XDP_QUERY_PROG: - return xdp_attachment_query(&ns->xdp, bpf); - case XDP_QUERY_PROG_HW: - return xdp_attachment_query(&ns->xdp_hw, bpf); case XDP_SETUP_PROG: err = nsim_setup_prog_checks(ns, bpf); if (err) @@ -602,6 +603,9 @@ int nsim_bpf_dev_init(struct nsim_dev *nsim_dev) &nsim_dev->bpf_bind_accept); debugfs_create_u32("bpf_bind_verifier_delay", 0600, nsim_dev->ddir, &nsim_dev->bpf_bind_verifier_delay); + nsim_dev->bpf_bind_verifier_accept = true; + debugfs_create_bool("bpf_bind_verifier_accept", 0600, nsim_dev->ddir, + &nsim_dev->bpf_bind_verifier_accept); return 0; } diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c index 7971dc4f54f1..0052968e881e 100644 --- a/drivers/net/netdevsim/bus.c +++ b/drivers/net/netdevsim/bus.c @@ -8,7 +8,6 @@ #include <linux/kernel.h> #include <linux/list.h> #include <linux/mutex.h> -#include <linux/rtnetlink.h> #include <linux/slab.h> #include <linux/sysfs.h> @@ -24,26 +23,6 @@ static struct nsim_bus_dev *to_nsim_bus_dev(struct device *dev) return container_of(dev, struct nsim_bus_dev, 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->vfconfigs) - return -ENOMEM; - nsim_bus_dev->num_vfs = num_vfs; - - return 0; -} - -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; -} - static ssize_t nsim_bus_dev_numvfs_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -56,27 +35,13 @@ nsim_bus_dev_numvfs_store(struct device *dev, struct device_attribute *attr, if (ret) return ret; - rtnl_lock(); - if (nsim_bus_dev->num_vfs == num_vfs) - goto exit_good; - if (nsim_bus_dev->num_vfs && num_vfs) { - ret = -EBUSY; - goto exit_unlock; - } - - if (num_vfs) { - ret = nsim_bus_dev_vfs_enable(nsim_bus_dev, num_vfs); - if (ret) - goto exit_unlock; - } else { - nsim_bus_dev_vfs_disable(nsim_bus_dev); - } -exit_good: - ret = count; -exit_unlock: - rtnl_unlock(); + device_lock(dev); + ret = -ENOENT; + if (dev_get_drvdata(dev)) + ret = nsim_drv_configure_vfs(nsim_bus_dev, num_vfs); + device_unlock(dev); - return ret; + return ret ? ret : count; } static ssize_t @@ -97,8 +62,6 @@ new_port_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); - struct nsim_dev *nsim_dev = dev_get_drvdata(dev); - struct devlink *devlink; unsigned int port_index; int ret; @@ -109,13 +72,7 @@ new_port_store(struct device *dev, struct device_attribute *attr, if (ret) return ret; - devlink = priv_to_devlink(nsim_dev); - - mutex_lock(&nsim_bus_dev->nsim_bus_reload_lock); - devlink_reload_disable(devlink); - ret = nsim_dev_port_add(nsim_bus_dev, port_index); - devlink_reload_enable(devlink); - mutex_unlock(&nsim_bus_dev->nsim_bus_reload_lock); + ret = nsim_drv_port_add(nsim_bus_dev, NSIM_DEV_PORT_TYPE_PF, port_index); return ret ? ret : count; } @@ -126,8 +83,6 @@ del_port_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); - struct nsim_dev *nsim_dev = dev_get_drvdata(dev); - struct devlink *devlink; unsigned int port_index; int ret; @@ -138,13 +93,7 @@ del_port_store(struct device *dev, struct device_attribute *attr, if (ret) return ret; - devlink = priv_to_devlink(nsim_dev); - - mutex_lock(&nsim_bus_dev->nsim_bus_reload_lock); - devlink_reload_disable(devlink); - ret = nsim_dev_port_del(nsim_bus_dev, port_index); - devlink_reload_enable(devlink); - mutex_unlock(&nsim_bus_dev->nsim_bus_reload_lock); + ret = nsim_drv_port_del(nsim_bus_dev, NSIM_DEV_PORT_TYPE_PF, port_index); return ret ? ret : count; } @@ -168,9 +117,10 @@ static const struct attribute_group *nsim_bus_dev_attr_groups[] = { static void nsim_bus_dev_release(struct device *dev) { - struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); + struct nsim_bus_dev *nsim_bus_dev; - nsim_bus_dev_vfs_disable(nsim_bus_dev); + nsim_bus_dev = container_of(dev, struct nsim_bus_dev, dev); + kfree(nsim_bus_dev); } static struct device_type nsim_bus_dev_type = { @@ -179,29 +129,31 @@ static struct device_type nsim_bus_dev_type = { }; static struct nsim_bus_dev * -nsim_bus_dev_new(unsigned int id, unsigned int port_count); +nsim_bus_dev_new(unsigned int id, unsigned int port_count, unsigned int num_queues); static ssize_t new_device_store(struct bus_type *bus, const char *buf, size_t count) { + unsigned int id, port_count, num_queues; struct nsim_bus_dev *nsim_bus_dev; - unsigned int port_count; - unsigned int id; int err; - err = sscanf(buf, "%u %u", &id, &port_count); + err = sscanf(buf, "%u %u %u", &id, &port_count, &num_queues); switch (err) { case 1: port_count = 1; - /* fall through */ + fallthrough; case 2: + num_queues = 1; + fallthrough; + case 3: if (id > INT_MAX) { pr_err("Value of \"id\" is too big.\n"); return -EINVAL; } break; default: - pr_err("Format for adding new device is \"id port_count\" (uint uint).\n"); + pr_err("Format for adding new device is \"id port_count num_queues\" (uint uint unit).\n"); return -EINVAL; } @@ -212,7 +164,7 @@ new_device_store(struct bus_type *bus, const char *buf, size_t count) goto err; } - nsim_bus_dev = nsim_bus_dev_new(id, port_count); + nsim_bus_dev = nsim_bus_dev_new(id, port_count, num_queues); if (IS_ERR(nsim_bus_dev)) { err = PTR_ERR(nsim_bus_dev); goto err; @@ -284,15 +236,14 @@ static int nsim_bus_probe(struct device *dev) { struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); - return nsim_dev_probe(nsim_bus_dev); + return nsim_drv_probe(nsim_bus_dev); } -static int nsim_bus_remove(struct device *dev) +static void nsim_bus_remove(struct device *dev) { struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); - nsim_dev_remove(nsim_bus_dev); - return 0; + nsim_drv_remove(nsim_bus_dev); } static int nsim_num_vf(struct device *dev) @@ -311,8 +262,10 @@ static struct bus_type nsim_bus = { .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) +nsim_bus_dev_new(unsigned int id, unsigned int port_count, unsigned int num_queues) { struct nsim_bus_dev *nsim_bus_dev; int err; @@ -328,18 +281,22 @@ nsim_bus_dev_new(unsigned int id, unsigned int port_count) nsim_bus_dev->dev.bus = &nsim_bus; nsim_bus_dev->dev.type = &nsim_bus_dev_type; nsim_bus_dev->port_count = port_count; + nsim_bus_dev->num_queues = num_queues; nsim_bus_dev->initial_net = current->nsproxy->net_ns; - mutex_init(&nsim_bus_dev->nsim_bus_reload_lock); + nsim_bus_dev->max_vfs = NSIM_BUS_DEV_MAX_VFS; /* Disallow using nsim_bus_dev */ smp_store_release(&nsim_bus_dev->init, false); err = device_register(&nsim_bus_dev->dev); if (err) goto err_nsim_bus_dev_id_free; + return nsim_bus_dev; err_nsim_bus_dev_id_free: ida_free(&nsim_bus_dev_ids, nsim_bus_dev->dev.id); + put_device(&nsim_bus_dev->dev); + nsim_bus_dev = NULL; err_nsim_bus_dev_free: kfree(nsim_bus_dev); return ERR_PTR(err); @@ -349,9 +306,8 @@ static void nsim_bus_dev_del(struct nsim_bus_dev *nsim_bus_dev) { /* Disallow using 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); + device_unregister(&nsim_bus_dev->dev); } static struct device_driver nsim_driver = { diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index d7706a0346f2..a7880c7ce94c 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -28,34 +28,96 @@ #include <linux/workqueue.h> #include <net/devlink.h> #include <net/ip.h> +#include <net/flow_offload.h> #include <uapi/linux/devlink.h> #include <uapi/linux/ip.h> #include <uapi/linux/udp.h> #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; +unsigned int nsim_dev_get_vfs(struct nsim_dev *nsim_dev) +{ + WARN_ON(!lockdep_rtnl_is_held() && + !devl_lock_is_held(priv_to_devlink(nsim_dev))); + + return nsim_dev->nsim_bus_dev->num_vfs; +} + +static void +nsim_bus_dev_set_vfs(struct nsim_bus_dev *nsim_bus_dev, unsigned int num_vfs) +{ + rtnl_lock(); + nsim_bus_dev->num_vfs = num_vfs; + rtnl_unlock(); +} + #define NSIM_DEV_DUMMY_REGION_SIZE (1024 * 32) +static int +nsim_dev_take_snapshot(struct devlink *devlink, + const struct devlink_region_ops *ops, + struct netlink_ext_ack *extack, + u8 **data) +{ + void *dummy_data; + + dummy_data = kmalloc(NSIM_DEV_DUMMY_REGION_SIZE, GFP_KERNEL); + if (!dummy_data) + return -ENOMEM; + + get_random_bytes(dummy_data, NSIM_DEV_DUMMY_REGION_SIZE); + + *data = dummy_data; + + return 0; +} + static ssize_t nsim_dev_take_snapshot_write(struct file *file, const char __user *data, size_t count, loff_t *ppos) { struct nsim_dev *nsim_dev = file->private_data; - void *dummy_data; + struct devlink *devlink; + u8 *dummy_data; int err; u32 id; - dummy_data = kmalloc(NSIM_DEV_DUMMY_REGION_SIZE, GFP_KERNEL); - if (!dummy_data) - return -ENOMEM; + devlink = priv_to_devlink(nsim_dev); - get_random_bytes(dummy_data, NSIM_DEV_DUMMY_REGION_SIZE); + err = nsim_dev_take_snapshot(devlink, NULL, NULL, &dummy_data); + if (err) + return err; - id = devlink_region_snapshot_id_get(priv_to_devlink(nsim_dev)); + err = devlink_region_snapshot_id_get(devlink, &id); + if (err) { + pr_err("Failed to get snapshot id\n"); + kfree(dummy_data); + return err; + } err = devlink_region_snapshot_create(nsim_dev->dummy_region, - dummy_data, id, kfree); + dummy_data, id); + devlink_region_snapshot_id_put(devlink, id); if (err) { pr_err("Failed to create region snapshot\n"); kfree(dummy_data); @@ -69,21 +131,192 @@ static const struct file_operations nsim_dev_take_snapshot_fops = { .open = simple_open, .write = nsim_dev_take_snapshot_write, .llseek = generic_file_llseek, + .owner = THIS_MODULE, +}; + +static ssize_t nsim_dev_trap_fa_cookie_read(struct file *file, + char __user *data, + size_t count, loff_t *ppos) +{ + struct nsim_dev *nsim_dev = file->private_data; + struct flow_action_cookie *fa_cookie; + unsigned int buf_len; + ssize_t ret; + char *buf; + + spin_lock(&nsim_dev->fa_cookie_lock); + fa_cookie = nsim_dev->fa_cookie; + if (!fa_cookie) { + ret = -EINVAL; + goto errout; + } + buf_len = fa_cookie->cookie_len * 2; + buf = kmalloc(buf_len, GFP_ATOMIC); + if (!buf) { + ret = -ENOMEM; + goto errout; + } + bin2hex(buf, fa_cookie->cookie, fa_cookie->cookie_len); + spin_unlock(&nsim_dev->fa_cookie_lock); + + ret = simple_read_from_buffer(data, count, ppos, buf, buf_len); + + kfree(buf); + return ret; + +errout: + spin_unlock(&nsim_dev->fa_cookie_lock); + return ret; +} + +static ssize_t nsim_dev_trap_fa_cookie_write(struct file *file, + const char __user *data, + size_t count, loff_t *ppos) +{ + struct nsim_dev *nsim_dev = file->private_data; + struct flow_action_cookie *fa_cookie; + size_t cookie_len; + ssize_t ret; + char *buf; + + if (*ppos != 0) + return -EINVAL; + cookie_len = (count - 1) / 2; + if ((count - 1) % 2) + return -EINVAL; + buf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN); + if (!buf) + return -ENOMEM; + + ret = simple_write_to_buffer(buf, count, ppos, data, count); + if (ret < 0) + goto free_buf; + + fa_cookie = kmalloc(sizeof(*fa_cookie) + cookie_len, + GFP_KERNEL | __GFP_NOWARN); + if (!fa_cookie) { + ret = -ENOMEM; + goto free_buf; + } + + fa_cookie->cookie_len = cookie_len; + ret = hex2bin(fa_cookie->cookie, buf, cookie_len); + if (ret) + goto free_fa_cookie; + kfree(buf); + + spin_lock(&nsim_dev->fa_cookie_lock); + kfree(nsim_dev->fa_cookie); + nsim_dev->fa_cookie = fa_cookie; + spin_unlock(&nsim_dev->fa_cookie_lock); + + return count; + +free_fa_cookie: + kfree(fa_cookie); +free_buf: + kfree(buf); + return ret; +} + +static const struct file_operations nsim_dev_trap_fa_cookie_fops = { + .open = simple_open, + .read = nsim_dev_trap_fa_cookie_read, + .write = nsim_dev_trap_fa_cookie_write, + .llseek = generic_file_llseek, + .owner = THIS_MODULE, +}; + +static ssize_t nsim_bus_dev_max_vfs_read(struct file *file, char __user *data, + size_t count, loff_t *ppos) +{ + struct nsim_dev *nsim_dev = file->private_data; + char buf[11]; + ssize_t len; + + len = scnprintf(buf, sizeof(buf), "%u\n", + READ_ONCE(nsim_dev->nsim_bus_dev->max_vfs)); + + return simple_read_from_buffer(data, count, ppos, buf, len); +} + +static ssize_t nsim_bus_dev_max_vfs_write(struct file *file, + const char __user *data, + size_t count, loff_t *ppos) +{ + struct nsim_vf_config *vfconfigs; + struct nsim_dev *nsim_dev; + char buf[10]; + ssize_t ret; + u32 val; + + if (*ppos != 0) + return 0; + + if (count >= sizeof(buf)) + return -ENOSPC; + + ret = copy_from_user(buf, data, count); + if (ret) + return -EFAULT; + buf[count] = '\0'; + + ret = kstrtouint(buf, 10, &val); + if (ret) + return -EINVAL; + + /* 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) + return -ERANGE; + + vfconfigs = kcalloc(val, sizeof(struct nsim_vf_config), + GFP_KERNEL | __GFP_NOWARN); + if (!vfconfigs) + return -ENOMEM; + + nsim_dev = file->private_data; + devl_lock(priv_to_devlink(nsim_dev)); + /* Reject if VFs are configured */ + if (nsim_dev_get_vfs(nsim_dev)) { + ret = -EBUSY; + } else { + swap(nsim_dev->vfconfigs, vfconfigs); + WRITE_ONCE(nsim_dev->nsim_bus_dev->max_vfs, val); + *ppos += count; + ret = count; + } + devl_unlock(priv_to_devlink(nsim_dev)); + + kfree(vfconfigs); + return ret; +} + +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]; + 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); if (IS_ERR(nsim_dev->ddir)) return PTR_ERR(nsim_dev->ddir); nsim_dev->ports_ddir = debugfs_create_dir("ports", nsim_dev->ddir); - if (IS_ERR(nsim_dev->ports_ddir)) - return PTR_ERR(nsim_dev->ports_ddir); + if (IS_ERR(nsim_dev->ports_ddir)) { + err = PTR_ERR(nsim_dev->ports_ddir); + goto err_ddir; + } debugfs_create_bool("fw_update_status", 0600, nsim_dev->ddir, &nsim_dev->fw_update_status); + debugfs_create_u32("fw_update_overwrite_mask", 0600, nsim_dev->ddir, + &nsim_dev->fw_update_overwrite_mask); debugfs_create_u32("max_macs", 0600, nsim_dev->ddir, &nsim_dev->max_macs); debugfs_create_bool("test1", 0600, nsim_dev->ddir, @@ -97,29 +330,95 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) &nsim_dev->dont_allow_reload); debugfs_create_bool("fail_reload", 0600, nsim_dev->ddir, &nsim_dev->fail_reload); + debugfs_create_file("trap_flow_action_cookie", 0600, nsim_dev->ddir, + nsim_dev, &nsim_dev_trap_fa_cookie_fops); + debugfs_create_bool("fail_trap_group_set", 0600, + nsim_dev->ddir, + &nsim_dev->fail_trap_group_set); + debugfs_create_bool("fail_trap_policer_set", 0600, + nsim_dev->ddir, + &nsim_dev->fail_trap_policer_set); + debugfs_create_bool("fail_trap_policer_counter_get", 0600, + nsim_dev->ddir, + &nsim_dev->fail_trap_policer_counter_get); + /* caution, dev_max_vfs write takes devlink lock */ + debugfs_create_file("max_vfs", 0600, nsim_dev->ddir, + nsim_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)) { + err = PTR_ERR(nsim_dev->nodes_ddir); + goto err_ports_ddir; + } + debugfs_create_bool("fail_trap_drop_counter_get", 0600, + nsim_dev->ddir, + &nsim_dev->fail_trap_drop_counter_get); + nsim_udp_tunnels_debugfs_create(nsim_dev); return 0; + +err_ports_ddir: + debugfs_remove_recursive(nsim_dev->ports_ddir); +err_ddir: + debugfs_remove_recursive(nsim_dev->ddir); + return err; } 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); } +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) { + 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_dev->vfconfigs[vf_id].min_tx_rate); + debugfs_create_u16("tx_max", 0400, nsim_dev_port->ddir, + &nsim_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); return 0; @@ -140,58 +439,70 @@ static int nsim_dev_resources_register(struct devlink *devlink) int err; /* Resources for IPv4 */ - err = devlink_resource_register(devlink, "IPv4", (u64)-1, - NSIM_RESOURCE_IPV4, - DEVLINK_RESOURCE_ID_PARENT_TOP, - ¶ms); + err = devl_resource_register(devlink, "IPv4", (u64)-1, + NSIM_RESOURCE_IPV4, + DEVLINK_RESOURCE_ID_PARENT_TOP, + ¶ms); if (err) { pr_err("Failed to register IPv4 top resource\n"); - goto out; + goto err_out; } - err = devlink_resource_register(devlink, "fib", (u64)-1, - NSIM_RESOURCE_IPV4_FIB, - NSIM_RESOURCE_IPV4, ¶ms); + err = devl_resource_register(devlink, "fib", (u64)-1, + NSIM_RESOURCE_IPV4_FIB, + NSIM_RESOURCE_IPV4, ¶ms); if (err) { pr_err("Failed to register IPv4 FIB resource\n"); - return err; + goto err_out; } - err = devlink_resource_register(devlink, "fib-rules", (u64)-1, - NSIM_RESOURCE_IPV4_FIB_RULES, - NSIM_RESOURCE_IPV4, ¶ms); + err = devl_resource_register(devlink, "fib-rules", (u64)-1, + NSIM_RESOURCE_IPV4_FIB_RULES, + NSIM_RESOURCE_IPV4, ¶ms); if (err) { pr_err("Failed to register IPv4 FIB rules resource\n"); - return err; + goto err_out; } /* Resources for IPv6 */ - err = devlink_resource_register(devlink, "IPv6", (u64)-1, - NSIM_RESOURCE_IPV6, - DEVLINK_RESOURCE_ID_PARENT_TOP, - ¶ms); + err = devl_resource_register(devlink, "IPv6", (u64)-1, + NSIM_RESOURCE_IPV6, + DEVLINK_RESOURCE_ID_PARENT_TOP, + ¶ms); if (err) { pr_err("Failed to register IPv6 top resource\n"); - goto out; + goto err_out; } - err = devlink_resource_register(devlink, "fib", (u64)-1, - NSIM_RESOURCE_IPV6_FIB, - NSIM_RESOURCE_IPV6, ¶ms); + err = devl_resource_register(devlink, "fib", (u64)-1, + NSIM_RESOURCE_IPV6_FIB, + NSIM_RESOURCE_IPV6, ¶ms); if (err) { pr_err("Failed to register IPv6 FIB resource\n"); - return err; + goto err_out; } - err = devlink_resource_register(devlink, "fib-rules", (u64)-1, - NSIM_RESOURCE_IPV6_FIB_RULES, - NSIM_RESOURCE_IPV6, ¶ms); + err = devl_resource_register(devlink, "fib-rules", (u64)-1, + NSIM_RESOURCE_IPV6_FIB_RULES, + NSIM_RESOURCE_IPV6, ¶ms); if (err) { pr_err("Failed to register IPv6 FIB rules resource\n"); - return err; + goto err_out; + } + + /* Resources for nexthops */ + err = devl_resource_register(devlink, "nexthops", (u64)-1, + NSIM_RESOURCE_NEXTHOPS, + DEVLINK_RESOURCE_ID_PARENT_TOP, + ¶ms); + if (err) { + pr_err("Failed to register NEXTHOPS resource\n"); + goto err_out; } + return 0; -out: +err_out: + devl_resources_unregister(devlink); return err; } @@ -245,19 +556,92 @@ static void nsim_devlink_param_load_driverinit_values(struct devlink *devlink) #define NSIM_DEV_DUMMY_REGION_SNAPSHOT_MAX 16 +static const struct devlink_region_ops dummy_region_ops = { + .name = "dummy", + .destructor = &kfree, + .snapshot = nsim_dev_take_snapshot, +}; + static int nsim_dev_dummy_region_init(struct nsim_dev *nsim_dev, struct devlink *devlink) { nsim_dev->dummy_region = - devlink_region_create(devlink, "dummy", - NSIM_DEV_DUMMY_REGION_SNAPSHOT_MAX, - NSIM_DEV_DUMMY_REGION_SIZE); + devl_region_create(devlink, &dummy_region_ops, + NSIM_DEV_DUMMY_REGION_SNAPSHOT_MAX, + NSIM_DEV_DUMMY_REGION_SIZE); return PTR_ERR_OR_ZERO(nsim_dev->dummy_region); } static void nsim_dev_dummy_region_exit(struct nsim_dev *nsim_dev) { - devlink_region_destroy(nsim_dev->dummy_region); + devl_region_destroy(nsim_dev->dummy_region); +} + +static int +__nsim_dev_port_add(struct nsim_dev *nsim_dev, enum nsim_dev_port_type type, + unsigned int port_index); +static void __nsim_dev_port_del(struct nsim_dev_port *nsim_dev_port); + +static 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; + + devl_rate_nodes_destroy(devlink); + 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); + nsim_dev->esw_mode = DEVLINK_ESWITCH_MODE_LEGACY; + return 0; +} + +static int nsim_esw_switchdev_enable(struct nsim_dev *nsim_dev, + struct netlink_ext_ack *extack) +{ + struct nsim_dev_port *nsim_dev_port, *tmp; + int i, err; + + for (i = 0; i < nsim_dev_get_vfs(nsim_dev); i++) { + err = __nsim_dev_port_add(nsim_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: + 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); + 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); + + if (mode == nsim_dev->esw_mode) + return 0; + + if (mode == DEVLINK_ESWITCH_MODE_LEGACY) + return nsim_esw_legacy_enable(nsim_dev, extack); + if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) + return nsim_esw_switchdev_enable(nsim_dev, extack); + + return -EINVAL; +} + +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 { @@ -268,6 +652,8 @@ struct nsim_trap_item { struct nsim_trap_data { struct delayed_work trap_report_dw; struct nsim_trap_item *trap_items_arr; + u64 *trap_policers_cnt_arr; + u64 trap_pkt_cnt; struct nsim_dev *nsim_dev; spinlock_t trap_lock; /* Protects trap_items_arr */ }; @@ -286,18 +672,53 @@ enum { #define NSIM_TRAP_DROP(_id, _group_id) \ DEVLINK_TRAP_GENERIC(DROP, DROP, _id, \ - DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ + DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, \ NSIM_TRAP_METADATA) +#define NSIM_TRAP_DROP_EXT(_id, _group_id, _metadata) \ + DEVLINK_TRAP_GENERIC(DROP, DROP, _id, \ + DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, \ + NSIM_TRAP_METADATA | (_metadata)) #define NSIM_TRAP_EXCEPTION(_id, _group_id) \ DEVLINK_TRAP_GENERIC(EXCEPTION, TRAP, _id, \ - DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ + DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, \ + NSIM_TRAP_METADATA) +#define NSIM_TRAP_CONTROL(_id, _group_id, _action) \ + DEVLINK_TRAP_GENERIC(CONTROL, _action, _id, \ + DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, \ NSIM_TRAP_METADATA) #define NSIM_TRAP_DRIVER_EXCEPTION(_id, _group_id) \ DEVLINK_TRAP_DRIVER(EXCEPTION, TRAP, NSIM_TRAP_ID_##_id, \ NSIM_TRAP_NAME_##_id, \ - DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ + DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, \ NSIM_TRAP_METADATA) +#define NSIM_DEV_TRAP_POLICER_MIN_RATE 1 +#define NSIM_DEV_TRAP_POLICER_MAX_RATE 8000 +#define NSIM_DEV_TRAP_POLICER_MIN_BURST 8 +#define NSIM_DEV_TRAP_POLICER_MAX_BURST 65536 + +#define NSIM_TRAP_POLICER(_id, _rate, _burst) \ + DEVLINK_TRAP_POLICER(_id, _rate, _burst, \ + NSIM_DEV_TRAP_POLICER_MAX_RATE, \ + NSIM_DEV_TRAP_POLICER_MIN_RATE, \ + NSIM_DEV_TRAP_POLICER_MAX_BURST, \ + NSIM_DEV_TRAP_POLICER_MIN_BURST) + +static const struct devlink_trap_policer nsim_trap_policers_arr[] = { + NSIM_TRAP_POLICER(1, 1000, 128), + NSIM_TRAP_POLICER(2, 2000, 256), + NSIM_TRAP_POLICER(3, 3000, 512), +}; + +static const struct devlink_trap_group nsim_trap_groups_arr[] = { + DEVLINK_TRAP_GROUP_GENERIC(L2_DROPS, 0), + DEVLINK_TRAP_GROUP_GENERIC(L3_DROPS, 1), + DEVLINK_TRAP_GROUP_GENERIC(L3_EXCEPTIONS, 1), + DEVLINK_TRAP_GROUP_GENERIC(BUFFER_DROPS, 2), + DEVLINK_TRAP_GROUP_GENERIC(ACL_DROPS, 3), + DEVLINK_TRAP_GROUP_GENERIC(MC_SNOOPING, 3), +}; + static const struct devlink_trap nsim_traps_arr[] = { NSIM_TRAP_DROP(SMAC_MC, L2_DROPS), NSIM_TRAP_DROP(VLAN_TAG_MISMATCH, L2_DROPS), @@ -307,8 +728,14 @@ static const struct devlink_trap nsim_traps_arr[] = { NSIM_TRAP_DROP(PORT_LOOPBACK_FILTER, L2_DROPS), NSIM_TRAP_DRIVER_EXCEPTION(FID_MISS, L2_DROPS), NSIM_TRAP_DROP(BLACKHOLE_ROUTE, L3_DROPS), - NSIM_TRAP_EXCEPTION(TTL_ERROR, L3_DROPS), + NSIM_TRAP_EXCEPTION(TTL_ERROR, L3_EXCEPTIONS), NSIM_TRAP_DROP(TAIL_DROP, BUFFER_DROPS), + NSIM_TRAP_DROP_EXT(INGRESS_FLOW_ACTION_DROP, ACL_DROPS, + DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE), + NSIM_TRAP_DROP_EXT(EGRESS_FLOW_ACTION_DROP, ACL_DROPS, + DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE), + NSIM_TRAP_CONTROL(IGMP_QUERY, MC_SNOOPING, MIRROR), + NSIM_TRAP_CONTROL(IGMP_V1_REPORT, MC_SNOOPING, TRAP), }; #define NSIM_TRAP_L4_DATA_LEN 100 @@ -366,8 +793,13 @@ static void nsim_dev_trap_report(struct nsim_dev_port *nsim_dev_port) spin_lock(&nsim_trap_data->trap_lock); for (i = 0; i < ARRAY_SIZE(nsim_traps_arr); i++) { + struct flow_action_cookie *fa_cookie = NULL; struct nsim_trap_item *nsim_trap_item; struct sk_buff *skb; + bool has_fa_cookie; + + has_fa_cookie = nsim_traps_arr[i].metadata_cap & + DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE; nsim_trap_item = &nsim_trap_data->trap_items_arr[i]; if (nsim_trap_item->action == DEVLINK_TRAP_ACTION_DROP) @@ -383,10 +815,12 @@ static void nsim_dev_trap_report(struct nsim_dev_port *nsim_dev_port) * softIRQs to prevent lockdep from complaining about * "incosistent lock state". */ - local_bh_disable(); + + spin_lock_bh(&nsim_dev->fa_cookie_lock); + fa_cookie = has_fa_cookie ? nsim_dev->fa_cookie : NULL; devlink_trap_report(devlink, skb, nsim_trap_item->trap_ctx, - &nsim_dev_port->devlink_port); - local_bh_enable(); + &nsim_dev_port->devlink_port, fa_cookie); + spin_unlock_bh(&nsim_dev->fa_cookie_lock); consume_skb(skb); } spin_unlock(&nsim_trap_data->trap_lock); @@ -407,14 +841,18 @@ static void nsim_dev_trap_report_work(struct work_struct *work) /* For each running port and enabled packet trap, generate a UDP * packet with a random 5-tuple and report it. */ - mutex_lock(&nsim_dev->port_list_lock); + if (!devl_trylock(priv_to_devlink(nsim_dev))) { + schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, 0); + return; + } + list_for_each_entry(nsim_dev_port, &nsim_dev->port_list, list) { if (!netif_running(nsim_dev_port->ns->netdev)) continue; nsim_dev_trap_report(nsim_dev_port); } - mutex_unlock(&nsim_dev->port_list_lock); + devl_unlock(priv_to_devlink(nsim_dev)); schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, msecs_to_jiffies(NSIM_TRAP_REPORT_INTERVAL_MS)); @@ -422,6 +860,7 @@ static void nsim_dev_trap_report_work(struct work_struct *work) static int nsim_dev_traps_init(struct devlink *devlink) { + size_t policers_count = ARRAY_SIZE(nsim_trap_policers_arr); struct nsim_dev *nsim_dev = devlink_priv(devlink); struct nsim_trap_data *nsim_trap_data; int err; @@ -438,6 +877,14 @@ static int nsim_dev_traps_init(struct devlink *devlink) goto err_trap_data_free; } + nsim_trap_data->trap_policers_cnt_arr = kcalloc(policers_count, + sizeof(u64), + GFP_KERNEL); + if (!nsim_trap_data->trap_policers_cnt_arr) { + err = -ENOMEM; + goto err_trap_items_free; + } + /* The lock is used to protect the action state of the registered * traps. The value is written by user and read in delayed work when * iterating over all the traps. @@ -446,10 +893,20 @@ static int nsim_dev_traps_init(struct devlink *devlink) nsim_trap_data->nsim_dev = nsim_dev; nsim_dev->trap_data = nsim_trap_data; - err = devlink_traps_register(devlink, nsim_traps_arr, - ARRAY_SIZE(nsim_traps_arr), NULL); + err = devl_trap_policers_register(devlink, nsim_trap_policers_arr, + policers_count); if (err) - goto err_trap_items_free; + goto err_trap_policers_cnt_free; + + err = devl_trap_groups_register(devlink, nsim_trap_groups_arr, + ARRAY_SIZE(nsim_trap_groups_arr)); + if (err) + goto err_trap_policers_unregister; + + err = devl_traps_register(devlink, nsim_traps_arr, + ARRAY_SIZE(nsim_traps_arr), NULL); + if (err) + goto err_trap_groups_unregister; INIT_DELAYED_WORK(&nsim_dev->trap_data->trap_report_dw, nsim_dev_trap_report_work); @@ -458,6 +915,14 @@ static int nsim_dev_traps_init(struct devlink *devlink) return 0; +err_trap_groups_unregister: + devl_trap_groups_unregister(devlink, nsim_trap_groups_arr, + ARRAY_SIZE(nsim_trap_groups_arr)); +err_trap_policers_unregister: + devl_trap_policers_unregister(devlink, nsim_trap_policers_arr, + ARRAY_SIZE(nsim_trap_policers_arr)); +err_trap_policers_cnt_free: + kfree(nsim_trap_data->trap_policers_cnt_arr); err_trap_items_free: kfree(nsim_trap_data->trap_items_arr); err_trap_data_free: @@ -469,9 +934,15 @@ static void nsim_dev_traps_exit(struct devlink *devlink) { struct nsim_dev *nsim_dev = devlink_priv(devlink); + /* caution, trap work takes devlink lock */ cancel_delayed_work_sync(&nsim_dev->trap_data->trap_report_dw); - devlink_traps_unregister(devlink, nsim_traps_arr, - ARRAY_SIZE(nsim_traps_arr)); + devl_traps_unregister(devlink, nsim_traps_arr, + ARRAY_SIZE(nsim_traps_arr)); + devl_trap_groups_unregister(devlink, nsim_trap_groups_arr, + ARRAY_SIZE(nsim_trap_groups_arr)); + devl_trap_policers_unregister(devlink, nsim_trap_policers_arr, + ARRAY_SIZE(nsim_trap_policers_arr)); + kfree(nsim_dev->trap_data->trap_policers_cnt_arr); kfree(nsim_dev->trap_data->trap_items_arr); kfree(nsim_dev->trap_data); } @@ -481,6 +952,7 @@ static int nsim_dev_reload_create(struct nsim_dev *nsim_dev, static void nsim_dev_reload_destroy(struct nsim_dev *nsim_dev); static int nsim_dev_reload_down(struct devlink *devlink, bool netns_change, + enum devlink_reload_action action, enum devlink_reload_limit limit, struct netlink_ext_ack *extack) { struct nsim_dev *nsim_dev = devlink_priv(devlink); @@ -497,7 +969,8 @@ static int nsim_dev_reload_down(struct devlink *devlink, bool netns_change, return 0; } -static int nsim_dev_reload_up(struct devlink *devlink, +static int nsim_dev_reload_up(struct devlink *devlink, enum devlink_reload_action action, + enum devlink_reload_limit limit, u32 *actions_performed, struct netlink_ext_ack *extack) { struct nsim_dev *nsim_dev = devlink_priv(devlink); @@ -510,6 +983,8 @@ static int nsim_dev_reload_up(struct devlink *devlink, return -EINVAL; } + *actions_performed = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT); + return nsim_dev_reload_create(nsim_dev, extack); } @@ -517,31 +992,43 @@ static int nsim_dev_info_get(struct devlink *devlink, struct devlink_info_req *req, struct netlink_ext_ack *extack) { - return devlink_info_driver_name_put(req, DRV_NAME); + int err; + + err = devlink_info_driver_name_put(req, DRV_NAME); + if (err) + return err; + err = devlink_info_version_stored_put_ext(req, "fw.mgmt", "10.20.30", + DEVLINK_INFO_VERSION_TYPE_COMPONENT); + if (err) + return err; + return devlink_info_version_running_put_ext(req, "fw.mgmt", "10.20.30", + DEVLINK_INFO_VERSION_TYPE_COMPONENT); } #define NSIM_DEV_FLASH_SIZE 500000 #define NSIM_DEV_FLASH_CHUNK_SIZE 1000 #define NSIM_DEV_FLASH_CHUNK_TIME_MS 10 -static int nsim_dev_flash_update(struct devlink *devlink, const char *file_name, - const char *component, +static int nsim_dev_flash_update(struct devlink *devlink, + struct devlink_flash_update_params *params, struct netlink_ext_ack *extack) { struct nsim_dev *nsim_dev = devlink_priv(devlink); int i; + if ((params->overwrite_mask & ~nsim_dev->fw_update_overwrite_mask) != 0) + return -EOPNOTSUPP; + if (nsim_dev->fw_update_status) { - devlink_flash_update_begin_notify(devlink); devlink_flash_update_status_notify(devlink, "Preparing to flash", - component, 0, 0); + params->component, 0, 0); } for (i = 0; i < NSIM_DEV_FLASH_SIZE / NSIM_DEV_FLASH_CHUNK_SIZE; i++) { if (nsim_dev->fw_update_status) devlink_flash_update_status_notify(devlink, "Flashing", - component, + params->component, i * NSIM_DEV_FLASH_CHUNK_SIZE, NSIM_DEV_FLASH_SIZE); msleep(NSIM_DEV_FLASH_CHUNK_TIME_MS); @@ -549,12 +1036,13 @@ static int nsim_dev_flash_update(struct devlink *devlink, const char *file_name, if (nsim_dev->fw_update_status) { devlink_flash_update_status_notify(devlink, "Flashing", - component, + params->component, NSIM_DEV_FLASH_SIZE, NSIM_DEV_FLASH_SIZE); + devlink_flash_update_timeout_notify(devlink, "Flash select", + params->component, 81); devlink_flash_update_status_notify(devlink, "Flashing done", - component, 0, 0); - devlink_flash_update_end_notify(devlink); + params->component, 0, 0); } return 0; @@ -594,7 +1082,8 @@ static int nsim_dev_devlink_trap_init(struct devlink *devlink, static int nsim_dev_devlink_trap_action_set(struct devlink *devlink, const struct devlink_trap *trap, - enum devlink_trap_action action) + enum devlink_trap_action action, + struct netlink_ext_ack *extack) { struct nsim_dev *nsim_dev = devlink_priv(devlink); struct nsim_trap_item *nsim_trap_item; @@ -610,37 +1099,293 @@ nsim_dev_devlink_trap_action_set(struct devlink *devlink, return 0; } +static int +nsim_dev_devlink_trap_group_set(struct devlink *devlink, + const struct devlink_trap_group *group, + const struct devlink_trap_policer *policer, + struct netlink_ext_ack *extack) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + + if (nsim_dev->fail_trap_group_set) + return -EINVAL; + + return 0; +} + +static int +nsim_dev_devlink_trap_policer_set(struct devlink *devlink, + const struct devlink_trap_policer *policer, + u64 rate, u64 burst, + struct netlink_ext_ack *extack) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + + if (nsim_dev->fail_trap_policer_set) { + NL_SET_ERR_MSG_MOD(extack, "User setup the operation to fail for testing purposes"); + return -EINVAL; + } + + return 0; +} + +static int +nsim_dev_devlink_trap_policer_counter_get(struct devlink *devlink, + const struct devlink_trap_policer *policer, + u64 *p_drops) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + u64 *cnt; + + if (nsim_dev->fail_trap_policer_counter_get) + return -EINVAL; + + cnt = &nsim_dev->trap_data->trap_policers_cnt_arr[policer->id - 1]; + *p_drops = (*cnt)++; + + 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_dev *nsim_dev = nsim_dev_port->ns->nsim_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_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_dev *nsim_dev = nsim_dev_port->ns->nsim_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_dev->vfconfigs[vf_id].max_tx_rate = tx_max; + return 0; +} + +struct nsim_rate_node { + struct dentry *ddir; + struct dentry *rate_parent; + char *parent_name; + 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); + + 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); + + *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(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 int +nsim_dev_devlink_trap_drop_counter_get(struct devlink *devlink, + const struct devlink_trap *trap, + u64 *p_drops) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + u64 *cnt; + + if (nsim_dev->fail_trap_drop_counter_get) + return -EINVAL; + + cnt = &nsim_dev->trap_data->trap_pkt_cnt; + *p_drops = (*cnt)++; + + 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, + .supported_flash_update_params = DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK, + .reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT), .reload_down = nsim_dev_reload_down, .reload_up = nsim_dev_reload_up, .info_get = nsim_dev_info_get, .flash_update = nsim_dev_flash_update, .trap_init = nsim_dev_devlink_trap_init, .trap_action_set = nsim_dev_devlink_trap_action_set, + .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, + .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, + .rate_leaf_parent_set = nsim_rate_leaf_parent_set, + .rate_node_parent_set = nsim_rate_node_parent_set, + .trap_drop_counter_get = nsim_dev_devlink_trap_drop_counter_get, }; #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 = {}; struct nsim_dev_port *nsim_dev_port; struct devlink_port *devlink_port; int err; + if (type == NSIM_DEV_PORT_TYPE_VF && !nsim_dev_get_vfs(nsim_dev)) + return -EINVAL; + 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; - devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PHYSICAL, - port_index + 1, 0, 0, - nsim_dev->switch_id.id, - nsim_dev->switch_id.id_len); - err = devlink_port_register(priv_to_devlink(nsim_dev), devlink_port, - port_index); + 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); + err = devl_port_register(priv_to_devlink(nsim_dev), devlink_port, + nsim_dev_port->port_index); if (err) goto err_port_free; @@ -654,15 +1399,24 @@ static int __nsim_dev_port_add(struct nsim_dev *nsim_dev, goto err_port_debugfs_exit; } + if (nsim_dev_port_is_vf(nsim_dev_port)) { + err = devl_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: - devlink_port_unregister(devlink_port); + devl_port_unregister(devlink_port); err_port_free: kfree(nsim_dev_port); return err; @@ -673,10 +1427,12 @@ 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)) + devl_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); - devlink_port_unregister(devlink_port); + devl_port_unregister(devlink_port); kfree(nsim_dev_port); } @@ -684,11 +1440,9 @@ static void nsim_dev_port_del_all(struct nsim_dev *nsim_dev) { 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) __nsim_dev_port_del(nsim_dev_port); - mutex_unlock(&nsim_dev->port_list_lock); } static int nsim_dev_port_add_all(struct nsim_dev *nsim_dev, @@ -697,7 +1451,7 @@ 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; } @@ -718,31 +1472,41 @@ static int nsim_dev_reload_create(struct nsim_dev *nsim_dev, devlink = priv_to_devlink(nsim_dev); nsim_dev = devlink_priv(devlink); INIT_LIST_HEAD(&nsim_dev->port_list); - mutex_init(&nsim_dev->port_list_lock); nsim_dev->fw_update_status = true; - - nsim_dev->fib_data = nsim_fib_create(devlink, extack); - if (IS_ERR(nsim_dev->fib_data)) - return PTR_ERR(nsim_dev->fib_data); + nsim_dev->fw_update_overwrite_mask = 0; nsim_devlink_param_load_driverinit_values(devlink); err = nsim_dev_dummy_region_init(nsim_dev, devlink); if (err) - goto err_fib_destroy; + return err; err = nsim_dev_traps_init(devlink); if (err) goto err_dummy_region_exit; + nsim_dev->fib_data = nsim_fib_create(devlink, extack); + if (IS_ERR(nsim_dev->fib_data)) { + err = PTR_ERR(nsim_dev->fib_data); + goto err_traps_exit; + } + err = nsim_dev_health_init(nsim_dev, devlink); if (err) - goto err_traps_exit; + goto err_fib_destroy; - err = nsim_dev_port_add_all(nsim_dev, nsim_bus_dev->port_count); + err = nsim_dev_psample_init(nsim_dev); if (err) goto err_health_exit; + err = nsim_dev_hwstats_init(nsim_dev); + if (err) + goto err_psample_exit; + + err = nsim_dev_port_add_all(nsim_dev, nsim_bus_dev->port_count); + if (err) + goto err_hwstats_exit; + nsim_dev->take_snapshot = debugfs_create_file("take_snapshot", 0200, nsim_dev->ddir, @@ -750,52 +1514,56 @@ static int nsim_dev_reload_create(struct nsim_dev *nsim_dev, &nsim_dev_take_snapshot_fops); return 0; +err_hwstats_exit: + nsim_dev_hwstats_exit(nsim_dev); +err_psample_exit: + nsim_dev_psample_exit(nsim_dev); err_health_exit: nsim_dev_health_exit(nsim_dev); +err_fib_destroy: + nsim_fib_destroy(devlink, nsim_dev->fib_data); err_traps_exit: nsim_dev_traps_exit(devlink); err_dummy_region_exit: nsim_dev_dummy_region_exit(nsim_dev); -err_fib_destroy: - nsim_fib_destroy(devlink, nsim_dev->fib_data); return err; } -int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev) +int nsim_drv_probe(struct nsim_bus_dev *nsim_bus_dev) { struct nsim_dev *nsim_dev; struct devlink *devlink; int err; - devlink = devlink_alloc(&nsim_dev_devlink_ops, sizeof(*nsim_dev)); + devlink = devlink_alloc_ns(&nsim_dev_devlink_ops, sizeof(*nsim_dev), + nsim_bus_dev->initial_net, &nsim_bus_dev->dev); if (!devlink) return -ENOMEM; - devlink_net_set(devlink, nsim_bus_dev->initial_net); + devl_lock(devlink); nsim_dev = devlink_priv(devlink); nsim_dev->nsim_bus_dev = nsim_bus_dev; nsim_dev->switch_id.id_len = sizeof(nsim_dev->switch_id.id); get_random_bytes(nsim_dev->switch_id.id, nsim_dev->switch_id.id_len); INIT_LIST_HEAD(&nsim_dev->port_list); - mutex_init(&nsim_dev->port_list_lock); nsim_dev->fw_update_status = true; + nsim_dev->fw_update_overwrite_mask = 0; nsim_dev->max_macs = NSIM_DEV_MAX_MACS_DEFAULT; nsim_dev->test1 = NSIM_DEV_TEST1_DEFAULT; + spin_lock_init(&nsim_dev->fa_cookie_lock); dev_set_drvdata(&nsim_bus_dev->dev, nsim_dev); - err = nsim_dev_resources_register(devlink); - if (err) - goto err_devlink_free; - - nsim_dev->fib_data = nsim_fib_create(devlink, NULL); - if (IS_ERR(nsim_dev->fib_data)) { - err = PTR_ERR(nsim_dev->fib_data); - goto err_resources_unregister; + nsim_dev->vfconfigs = kcalloc(nsim_bus_dev->max_vfs, + sizeof(struct nsim_vf_config), + GFP_KERNEL | __GFP_NOWARN); + if (!nsim_dev->vfconfigs) { + err = -ENOMEM; + goto err_devlink_unlock; } - err = devlink_register(devlink, &nsim_bus_dev->dev); + err = nsim_dev_resources_register(devlink); if (err) - goto err_fib_destroy; + goto err_vfc_free; err = devlink_params_register(devlink, nsim_devlink_params, ARRAY_SIZE(nsim_devlink_params)); @@ -815,26 +1583,48 @@ int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev) if (err) goto err_traps_exit; + nsim_dev->fib_data = nsim_fib_create(devlink, NULL); + if (IS_ERR(nsim_dev->fib_data)) { + err = PTR_ERR(nsim_dev->fib_data); + goto err_debugfs_exit; + } + err = nsim_dev_health_init(nsim_dev, devlink); if (err) - goto err_debugfs_exit; + goto err_fib_destroy; err = nsim_bpf_dev_init(nsim_dev); if (err) goto err_health_exit; - err = nsim_dev_port_add_all(nsim_dev, nsim_bus_dev->port_count); + err = nsim_dev_psample_init(nsim_dev); if (err) goto err_bpf_dev_exit; - devlink_params_publish(devlink); - devlink_reload_enable(devlink); + err = nsim_dev_hwstats_init(nsim_dev); + if (err) + goto err_psample_exit; + + err = nsim_dev_port_add_all(nsim_dev, nsim_bus_dev->port_count); + if (err) + goto err_hwstats_exit; + + nsim_dev->esw_mode = DEVLINK_ESWITCH_MODE_LEGACY; + devlink_set_features(devlink, DEVLINK_F_RELOAD); + devl_unlock(devlink); + devlink_register(devlink); return 0; +err_hwstats_exit: + nsim_dev_hwstats_exit(nsim_dev); +err_psample_exit: + nsim_dev_psample_exit(nsim_dev); err_bpf_dev_exit: nsim_bpf_dev_exit(nsim_dev); err_health_exit: nsim_dev_health_exit(nsim_dev); +err_fib_destroy: + nsim_fib_destroy(devlink, nsim_dev->fib_data); err_debugfs_exit: nsim_dev_debugfs_exit(nsim_dev); err_traps_exit: @@ -845,13 +1635,13 @@ err_params_unregister: devlink_params_unregister(devlink, nsim_devlink_params, ARRAY_SIZE(nsim_devlink_params)); err_dl_unregister: - devlink_unregister(devlink); -err_fib_destroy: - nsim_fib_destroy(devlink, nsim_dev->fib_data); -err_resources_unregister: - devlink_resources_unregister(devlink, NULL); -err_devlink_free: + devl_resources_unregister(devlink); +err_vfc_free: + kfree(nsim_dev->vfconfigs); +err_devlink_unlock: + devl_unlock(devlink); devlink_free(devlink); + dev_set_drvdata(&nsim_bus_dev->dev, NULL); return err; } @@ -862,75 +1652,125 @@ static void nsim_dev_reload_destroy(struct nsim_dev *nsim_dev) if (devlink_is_reload_failed(devlink)) return; debugfs_remove(nsim_dev->take_snapshot); + + if (nsim_dev_get_vfs(nsim_dev)) { + nsim_bus_dev_set_vfs(nsim_dev->nsim_bus_dev, 0); + if (nsim_esw_mode_is_switchdev(nsim_dev)) + nsim_esw_legacy_enable(nsim_dev, NULL); + } + nsim_dev_port_del_all(nsim_dev); + nsim_dev_hwstats_exit(nsim_dev); + nsim_dev_psample_exit(nsim_dev); nsim_dev_health_exit(nsim_dev); + nsim_fib_destroy(devlink, nsim_dev->fib_data); nsim_dev_traps_exit(devlink); nsim_dev_dummy_region_exit(nsim_dev); - mutex_destroy(&nsim_dev->port_list_lock); - nsim_fib_destroy(devlink, nsim_dev->fib_data); } -void nsim_dev_remove(struct nsim_bus_dev *nsim_bus_dev) +void nsim_drv_remove(struct nsim_bus_dev *nsim_bus_dev) { struct nsim_dev *nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev); struct devlink *devlink = priv_to_devlink(nsim_dev); - devlink_reload_disable(devlink); - + devlink_unregister(devlink); + devl_lock(devlink); nsim_dev_reload_destroy(nsim_dev); nsim_bpf_dev_exit(nsim_dev); nsim_dev_debugfs_exit(nsim_dev); devlink_params_unregister(devlink, nsim_devlink_params, ARRAY_SIZE(nsim_devlink_params)); - devlink_unregister(devlink); - devlink_resources_unregister(devlink, NULL); + devl_resources_unregister(devlink); + kfree(nsim_dev->vfconfigs); + devl_unlock(devlink); devlink_free(devlink); + dev_set_drvdata(&nsim_bus_dev->dev, NULL); } 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_drv_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)) + devl_lock(priv_to_devlink(nsim_dev)); + if (__nsim_dev_port_lookup(nsim_dev, type, port_index)) err = -EEXIST; else - err = __nsim_dev_port_add(nsim_dev, port_index); - mutex_unlock(&nsim_dev->port_list_lock); + err = __nsim_dev_port_add(nsim_dev, type, port_index); + devl_unlock(priv_to_devlink(nsim_dev)); return err; } -int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev, +int nsim_drv_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); struct nsim_dev_port *nsim_dev_port; int err = 0; - mutex_lock(&nsim_dev->port_list_lock); - nsim_dev_port = __nsim_dev_port_lookup(nsim_dev, port_index); + devl_lock(priv_to_devlink(nsim_dev)); + nsim_dev_port = __nsim_dev_port_lookup(nsim_dev, type, port_index); if (!nsim_dev_port) err = -ENOENT; else __nsim_dev_port_del(nsim_dev_port); - mutex_unlock(&nsim_dev->port_list_lock); + devl_unlock(priv_to_devlink(nsim_dev)); return err; } +int nsim_drv_configure_vfs(struct nsim_bus_dev *nsim_bus_dev, + unsigned int num_vfs) +{ + struct nsim_dev *nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev); + struct devlink *devlink = priv_to_devlink(nsim_dev); + int ret = 0; + + devl_lock(devlink); + if (nsim_bus_dev->num_vfs == num_vfs) + goto exit_unlock; + if (nsim_bus_dev->num_vfs && num_vfs) { + ret = -EBUSY; + goto exit_unlock; + } + if (nsim_bus_dev->max_vfs < num_vfs) { + ret = -ENOMEM; + goto exit_unlock; + } + + nsim_bus_dev_set_vfs(nsim_bus_dev, num_vfs); + if (nsim_esw_mode_is_switchdev(nsim_dev)) { + if (num_vfs) { + ret = nsim_esw_switchdev_enable(nsim_dev, NULL); + if (ret) { + nsim_bus_dev_set_vfs(nsim_bus_dev, 0); + goto exit_unlock; + } + } else { + nsim_esw_legacy_enable(nsim_dev, NULL); + } + } + +exit_unlock: + devl_unlock(devlink); + + return ret; +} + int nsim_dev_init(void) { nsim_dev_ddir = debugfs_create_dir(DRV_NAME, NULL); diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c new file mode 100644 index 000000000000..ffd9f84b6644 --- /dev/null +++ b/drivers/net/netdevsim/ethtool.c @@ -0,0 +1,199 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/debugfs.h> +#include <linux/ethtool.h> +#include <linux/random.h> + +#include "netdevsim.h" + +static void +nsim_get_pause_stats(struct net_device *dev, + struct ethtool_pause_stats *pause_stats) +{ + struct netdevsim *ns = netdev_priv(dev); + + if (ns->ethtool.pauseparam.report_stats_rx) + pause_stats->rx_pause_frames = 1; + if (ns->ethtool.pauseparam.report_stats_tx) + pause_stats->tx_pause_frames = 2; +} + +static void +nsim_get_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause) +{ + struct netdevsim *ns = netdev_priv(dev); + + pause->autoneg = 0; /* We don't support ksettings, so can't pretend */ + pause->rx_pause = ns->ethtool.pauseparam.rx; + pause->tx_pause = ns->ethtool.pauseparam.tx; +} + +static int +nsim_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause) +{ + struct netdevsim *ns = netdev_priv(dev); + + if (pause->autoneg) + return -EINVAL; + + ns->ethtool.pauseparam.rx = pause->rx_pause; + ns->ethtool.pauseparam.tx = pause->tx_pause; + return 0; +} + +static int nsim_get_coalesce(struct net_device *dev, + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct netdevsim *ns = netdev_priv(dev); + + memcpy(coal, &ns->ethtool.coalesce, sizeof(ns->ethtool.coalesce)); + return 0; +} + +static int nsim_set_coalesce(struct net_device *dev, + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct netdevsim *ns = netdev_priv(dev); + + memcpy(&ns->ethtool.coalesce, coal, sizeof(ns->ethtool.coalesce)); + return 0; +} + +static void nsim_get_ringparam(struct net_device *dev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) +{ + struct netdevsim *ns = netdev_priv(dev); + + memcpy(ring, &ns->ethtool.ring, sizeof(ns->ethtool.ring)); +} + +static int nsim_set_ringparam(struct net_device *dev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) +{ + struct netdevsim *ns = netdev_priv(dev); + + ns->ethtool.ring.rx_pending = ring->rx_pending; + ns->ethtool.ring.rx_jumbo_pending = ring->rx_jumbo_pending; + ns->ethtool.ring.rx_mini_pending = ring->rx_mini_pending; + ns->ethtool.ring.tx_pending = ring->tx_pending; + return 0; +} + +static void +nsim_get_channels(struct net_device *dev, struct ethtool_channels *ch) +{ + struct netdevsim *ns = netdev_priv(dev); + + ch->max_combined = ns->nsim_bus_dev->num_queues; + ch->combined_count = ns->ethtool.channels; +} + +static int +nsim_set_channels(struct net_device *dev, struct ethtool_channels *ch) +{ + struct netdevsim *ns = netdev_priv(dev); + int err; + + err = netif_set_real_num_queues(dev, ch->combined_count, + ch->combined_count); + if (err) + return err; + + ns->ethtool.channels = ch->combined_count; + return 0; +} + +static int +nsim_get_fecparam(struct net_device *dev, struct ethtool_fecparam *fecparam) +{ + struct netdevsim *ns = netdev_priv(dev); + + if (ns->ethtool.get_err) + return -ns->ethtool.get_err; + memcpy(fecparam, &ns->ethtool.fec, sizeof(ns->ethtool.fec)); + return 0; +} + +static int +nsim_set_fecparam(struct net_device *dev, struct ethtool_fecparam *fecparam) +{ + struct netdevsim *ns = netdev_priv(dev); + u32 fec; + + if (ns->ethtool.set_err) + return -ns->ethtool.set_err; + memcpy(&ns->ethtool.fec, fecparam, sizeof(ns->ethtool.fec)); + fec = fecparam->fec; + if (fec == ETHTOOL_FEC_AUTO) + fec |= ETHTOOL_FEC_OFF; + fec |= ETHTOOL_FEC_NONE; + ns->ethtool.fec.active_fec = 1 << (fls(fec) - 1); + return 0; +} + +static const struct ethtool_ops nsim_ethtool_ops = { + .supported_coalesce_params = ETHTOOL_COALESCE_ALL_PARAMS, + .get_pause_stats = nsim_get_pause_stats, + .get_pauseparam = nsim_get_pauseparam, + .set_pauseparam = nsim_set_pauseparam, + .set_coalesce = nsim_set_coalesce, + .get_coalesce = nsim_get_coalesce, + .get_ringparam = nsim_get_ringparam, + .set_ringparam = nsim_set_ringparam, + .get_channels = nsim_get_channels, + .set_channels = nsim_set_channels, + .get_fecparam = nsim_get_fecparam, + .set_fecparam = nsim_set_fecparam, +}; + +static void nsim_ethtool_ring_init(struct netdevsim *ns) +{ + ns->ethtool.ring.rx_max_pending = 4096; + ns->ethtool.ring.rx_jumbo_max_pending = 4096; + ns->ethtool.ring.rx_mini_max_pending = 4096; + ns->ethtool.ring.tx_max_pending = 4096; +} + +void nsim_ethtool_init(struct netdevsim *ns) +{ + struct dentry *ethtool, *dir; + + ns->netdev->ethtool_ops = &nsim_ethtool_ops; + + nsim_ethtool_ring_init(ns); + + ns->ethtool.fec.fec = ETHTOOL_FEC_NONE; + ns->ethtool.fec.active_fec = ETHTOOL_FEC_NONE; + + ns->ethtool.channels = ns->nsim_bus_dev->num_queues; + + ethtool = debugfs_create_dir("ethtool", ns->nsim_dev_port->ddir); + + debugfs_create_u32("get_err", 0600, ethtool, &ns->ethtool.get_err); + debugfs_create_u32("set_err", 0600, ethtool, &ns->ethtool.set_err); + + dir = debugfs_create_dir("pause", ethtool); + debugfs_create_bool("report_stats_rx", 0600, dir, + &ns->ethtool.pauseparam.report_stats_rx); + debugfs_create_bool("report_stats_tx", 0600, dir, + &ns->ethtool.pauseparam.report_stats_tx); + + dir = debugfs_create_dir("ring", ethtool); + debugfs_create_u32("rx_max_pending", 0600, dir, + &ns->ethtool.ring.rx_max_pending); + debugfs_create_u32("rx_jumbo_max_pending", 0600, dir, + &ns->ethtool.ring.rx_jumbo_max_pending); + debugfs_create_u32("rx_mini_max_pending", 0600, dir, + &ns->ethtool.ring.rx_mini_max_pending); + debugfs_create_u32("tx_max_pending", 0600, dir, + &ns->ethtool.ring.tx_max_pending); +} diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index f32d56ac3e80..a1f91ff8ec56 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -14,6 +14,7 @@ * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. */ +#include <linux/bitmap.h> #include <linux/in6.h> #include <linux/kernel.h> #include <linux/list.h> @@ -21,16 +22,19 @@ #include <linux/spinlock_types.h> #include <linux/types.h> #include <net/fib_notifier.h> +#include <net/inet_dscp.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/fib_rules.h> #include <net/net_namespace.h> +#include <net/nexthop.h> +#include <linux/debugfs.h> #include "netdevsim.h" struct nsim_fib_entry { u64 max; - u64 num; + atomic64_t num; }; struct nsim_per_fib_data { @@ -42,10 +46,23 @@ struct nsim_fib_data { struct notifier_block fib_nb; struct nsim_per_fib_data ipv4; struct nsim_per_fib_data ipv6; + struct nsim_fib_entry nexthops; struct rhashtable fib_rt_ht; struct list_head fib_rt_list; - spinlock_t fib_lock; /* Protects hashtable, list and accounting */ + struct mutex fib_lock; /* Protects FIB HT and list */ + struct notifier_block nexthop_nb; + struct rhashtable nexthop_ht; struct devlink *devlink; + struct work_struct fib_event_work; + struct work_struct fib_flush_work; + struct list_head fib_event_queue; + spinlock_t fib_event_queue_lock; /* Protects fib event queue list */ + struct mutex nh_lock; /* Protects NH HT */ + struct dentry *ddir; + bool fail_route_offload; + bool fail_res_nexthop_group_replace; + bool fail_nexthop_bucket_replace; + bool fail_route_delete; }; struct nsim_fib_rt_key { @@ -64,7 +81,7 @@ struct nsim_fib_rt { struct nsim_fib4_rt { struct nsim_fib_rt common; struct fib_info *fi; - u8 tos; + dscp_t dscp; u8 type; }; @@ -79,6 +96,22 @@ struct nsim_fib6_rt_nh { struct fib6_info *rt; }; +struct nsim_fib6_event { + struct fib6_info **rt_arr; + unsigned int nrt6; +}; + +struct nsim_fib_event { + struct list_head list; /* node in fib queue */ + union { + struct fib_entry_notifier_info fen_info; + struct nsim_fib6_event fib6_event; + }; + struct nsim_fib_data *data; + unsigned long event; + int family; +}; + static const struct rhashtable_params nsim_fib_rt_ht_params = { .key_offset = offsetof(struct nsim_fib_rt, key), .head_offset = offsetof(struct nsim_fib_rt, ht_node), @@ -86,6 +119,20 @@ static const struct rhashtable_params nsim_fib_rt_ht_params = { .automatic_shrinking = true, }; +struct nsim_nexthop { + struct rhash_head ht_node; + u64 occ; + u32 id; + bool is_resilient; +}; + +static const struct rhashtable_params nsim_nexthop_ht_params = { + .key_offset = offsetof(struct nsim_nexthop, id), + .head_offset = offsetof(struct nsim_nexthop, ht_node), + .key_len = sizeof(u32), + .automatic_shrinking = true, +}; + u64 nsim_fib_get_val(struct nsim_fib_data *fib_data, enum nsim_resource_id res_id, bool max) { @@ -104,11 +151,14 @@ u64 nsim_fib_get_val(struct nsim_fib_data *fib_data, case NSIM_RESOURCE_IPV6_FIB_RULES: entry = &fib_data->ipv6.rules; break; + case NSIM_RESOURCE_NEXTHOPS: + entry = &fib_data->nexthops; + break; default: return 0; } - return max ? entry->max : entry->num; + return max ? entry->max : atomic64_read(&entry->num); } static void nsim_fib_set_max(struct nsim_fib_data *fib_data, @@ -129,6 +179,9 @@ static void nsim_fib_set_max(struct nsim_fib_data *fib_data, case NSIM_RESOURCE_IPV6_FIB_RULES: entry = &fib_data->ipv6.rules; break; + case NSIM_RESOURCE_NEXTHOPS: + entry = &fib_data->nexthops; + break; default: WARN_ON(1); return; @@ -142,14 +195,12 @@ static int nsim_fib_rule_account(struct nsim_fib_entry *entry, bool add, int err = 0; if (add) { - if (entry->num < entry->max) { - entry->num++; - } else { + if (!atomic64_add_unless(&entry->num, 1, entry->max)) { err = -ENOSPC; NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported fib rule entries"); } } else { - entry->num--; + atomic64_dec_if_positive(&entry->num); } return err; @@ -173,20 +224,15 @@ static int nsim_fib_rule_event(struct nsim_fib_data *data, return err; } -static int nsim_fib_account(struct nsim_fib_entry *entry, bool add, - struct netlink_ext_ack *extack) +static int nsim_fib_account(struct nsim_fib_entry *entry, bool add) { int err = 0; if (add) { - if (entry->num < entry->max) { - entry->num++; - } else { + if (!atomic64_add_unless(&entry->num, 1, entry->max)) err = -ENOSPC; - NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported fib entries"); - } } else { - entry->num--; + atomic64_dec_if_positive(&entry->num); } return err; @@ -231,7 +277,7 @@ nsim_fib4_rt_create(struct nsim_fib_data *data, { struct nsim_fib4_rt *fib4_rt; - fib4_rt = kzalloc(sizeof(*fib4_rt), GFP_ATOMIC); + fib4_rt = kzalloc(sizeof(*fib4_rt), GFP_KERNEL); if (!fib4_rt) return NULL; @@ -240,7 +286,7 @@ nsim_fib4_rt_create(struct nsim_fib_data *data, fib4_rt->fi = fen_info->fi; fib_info_hold(fib4_rt->fi); - fib4_rt->tos = fen_info->tos; + fib4_rt->dscp = fen_info->dscp; fib4_rt->type = fen_info->type; return fib4_rt; @@ -268,6 +314,25 @@ nsim_fib4_rt_lookup(struct rhashtable *fib_rt_ht, return container_of(fib_rt, struct nsim_fib4_rt, common); } +static void +nsim_fib4_rt_offload_failed_flag_set(struct net *net, + struct fib_entry_notifier_info *fen_info) +{ + u32 *p_dst = (u32 *)&fen_info->dst; + struct fib_rt_info fri; + + fri.fi = fen_info->fi; + fri.tb_id = fen_info->tb_id; + fri.dst = cpu_to_be32(*p_dst); + fri.dst_len = fen_info->dst_len; + fri.dscp = fen_info->dscp; + fri.type = fen_info->type; + fri.offload = false; + fri.trap = false; + fri.offload_failed = true; + fib_alias_hw_flags_set(net, &fri); +} + static void nsim_fib4_rt_hw_flags_set(struct net *net, const struct nsim_fib4_rt *fib4_rt, bool trap) @@ -280,59 +345,61 @@ static void nsim_fib4_rt_hw_flags_set(struct net *net, fri.tb_id = fib4_rt->common.key.tb_id; fri.dst = cpu_to_be32(*p_dst); fri.dst_len = dst_len; - fri.tos = fib4_rt->tos; + fri.dscp = fib4_rt->dscp; fri.type = fib4_rt->type; fri.offload = false; fri.trap = trap; + fri.offload_failed = false; fib_alias_hw_flags_set(net, &fri); } static int nsim_fib4_rt_add(struct nsim_fib_data *data, - struct nsim_fib4_rt *fib4_rt, - struct netlink_ext_ack *extack) + struct nsim_fib4_rt *fib4_rt) { struct net *net = devlink_net(data->devlink); int err; - err = nsim_fib_account(&data->ipv4.fib, true, extack); - if (err) - return err; - err = rhashtable_insert_fast(&data->fib_rt_ht, &fib4_rt->common.ht_node, nsim_fib_rt_ht_params); - if (err) { - NL_SET_ERR_MSG_MOD(extack, "Failed to insert IPv4 route"); + if (err) goto err_fib_dismiss; - } + /* Simulate hardware programming latency. */ + msleep(1); nsim_fib4_rt_hw_flags_set(net, fib4_rt, true); return 0; err_fib_dismiss: - nsim_fib_account(&data->ipv4.fib, false, extack); + /* Drop the accounting that was increased from the notification + * context when FIB_EVENT_ENTRY_REPLACE was triggered. + */ + nsim_fib_account(&data->ipv4.fib, false); return err; } static int nsim_fib4_rt_replace(struct nsim_fib_data *data, struct nsim_fib4_rt *fib4_rt, - struct nsim_fib4_rt *fib4_rt_old, - struct netlink_ext_ack *extack) + struct nsim_fib4_rt *fib4_rt_old) { struct net *net = devlink_net(data->devlink); int err; - /* We are replacing a route, so no need to change the accounting. */ + /* We are replacing a route, so need to remove the accounting which + * was increased when FIB_EVENT_ENTRY_REPLACE was triggered. + */ + err = nsim_fib_account(&data->ipv4.fib, false); + if (err) + return err; err = rhashtable_replace_fast(&data->fib_rt_ht, &fib4_rt_old->common.ht_node, &fib4_rt->common.ht_node, nsim_fib_rt_ht_params); - if (err) { - NL_SET_ERR_MSG_MOD(extack, "Failed to replace IPv4 route"); + if (err) return err; - } + msleep(1); nsim_fib4_rt_hw_flags_set(net, fib4_rt, true); nsim_fib4_rt_hw_flags_set(net, fib4_rt_old, false); @@ -344,19 +411,27 @@ static int nsim_fib4_rt_replace(struct nsim_fib_data *data, static int nsim_fib4_rt_insert(struct nsim_fib_data *data, struct fib_entry_notifier_info *fen_info) { - struct netlink_ext_ack *extack = fen_info->info.extack; struct nsim_fib4_rt *fib4_rt, *fib4_rt_old; int err; + if (data->fail_route_offload) { + /* For testing purposes, user set debugfs fail_route_offload + * value to true. Simulate hardware programming latency and then + * fail. + */ + msleep(1); + return -EINVAL; + } + fib4_rt = nsim_fib4_rt_create(data, fen_info); if (!fib4_rt) return -ENOMEM; fib4_rt_old = nsim_fib4_rt_lookup(&data->fib_rt_ht, fen_info); if (!fib4_rt_old) - err = nsim_fib4_rt_add(data, fib4_rt, extack); + err = nsim_fib4_rt_add(data, fib4_rt); else - err = nsim_fib4_rt_replace(data, fib4_rt, fib4_rt_old, extack); + err = nsim_fib4_rt_replace(data, fib4_rt, fib4_rt_old); if (err) nsim_fib4_rt_destroy(fib4_rt); @@ -367,36 +442,31 @@ static int nsim_fib4_rt_insert(struct nsim_fib_data *data, static void nsim_fib4_rt_remove(struct nsim_fib_data *data, const struct fib_entry_notifier_info *fen_info) { - struct netlink_ext_ack *extack = fen_info->info.extack; struct nsim_fib4_rt *fib4_rt; fib4_rt = nsim_fib4_rt_lookup(&data->fib_rt_ht, fen_info); - if (WARN_ON_ONCE(!fib4_rt)) + if (!fib4_rt) return; rhashtable_remove_fast(&data->fib_rt_ht, &fib4_rt->common.ht_node, nsim_fib_rt_ht_params); - nsim_fib_account(&data->ipv4.fib, false, extack); nsim_fib4_rt_destroy(fib4_rt); } static int nsim_fib4_event(struct nsim_fib_data *data, - struct fib_notifier_info *info, + struct fib_entry_notifier_info *fen_info, unsigned long event) { - struct fib_entry_notifier_info *fen_info; int err = 0; - fen_info = container_of(info, struct fib_entry_notifier_info, info); - - if (fen_info->fi->nh) { - NL_SET_ERR_MSG_MOD(info->extack, "IPv4 route with nexthop objects is not supported"); - return 0; - } - switch (event) { case FIB_EVENT_ENTRY_REPLACE: err = nsim_fib4_rt_insert(data, fen_info); + if (err) { + struct net *net = devlink_net(data->devlink); + + nsim_fib4_rt_offload_failed_flag_set(net, fen_info); + } break; case FIB_EVENT_ENTRY_DEL: nsim_fib4_rt_remove(data, fen_info); @@ -427,7 +497,7 @@ static int nsim_fib6_rt_nh_add(struct nsim_fib6_rt *fib6_rt, { struct nsim_fib6_rt_nh *fib6_rt_nh; - fib6_rt_nh = kzalloc(sizeof(*fib6_rt_nh), GFP_ATOMIC); + fib6_rt_nh = kzalloc(sizeof(*fib6_rt_nh), GFP_KERNEL); if (!fib6_rt_nh) return -ENOMEM; @@ -439,33 +509,42 @@ static int nsim_fib6_rt_nh_add(struct nsim_fib6_rt *fib6_rt, return 0; } +#if IS_ENABLED(CONFIG_IPV6) +static void nsim_rt6_release(struct fib6_info *rt) +{ + fib6_info_release(rt); +} +#else +static void nsim_rt6_release(struct fib6_info *rt) +{ +} +#endif + static void nsim_fib6_rt_nh_del(struct nsim_fib6_rt *fib6_rt, const struct fib6_info *rt) { struct nsim_fib6_rt_nh *fib6_rt_nh; fib6_rt_nh = nsim_fib6_rt_nh_find(fib6_rt, rt); - if (WARN_ON_ONCE(!fib6_rt_nh)) + if (!fib6_rt_nh) return; fib6_rt->nhs--; list_del(&fib6_rt_nh->list); -#if IS_ENABLED(CONFIG_IPV6) - fib6_info_release(fib6_rt_nh->rt); -#endif + nsim_rt6_release(fib6_rt_nh->rt); kfree(fib6_rt_nh); } static struct nsim_fib6_rt * nsim_fib6_rt_create(struct nsim_fib_data *data, - struct fib6_entry_notifier_info *fen6_info) + struct fib6_info **rt_arr, unsigned int nrt6) { - struct fib6_info *iter, *rt = fen6_info->rt; + struct fib6_info *rt = rt_arr[0]; struct nsim_fib6_rt *fib6_rt; int i = 0; int err; - fib6_rt = kzalloc(sizeof(*fib6_rt), GFP_ATOMIC); + fib6_rt = kzalloc(sizeof(*fib6_rt), GFP_KERNEL); if (!fib6_rt) return ERR_PTR(-ENOMEM); @@ -479,32 +558,18 @@ nsim_fib6_rt_create(struct nsim_fib_data *data, */ INIT_LIST_HEAD(&fib6_rt->nh_list); - err = nsim_fib6_rt_nh_add(fib6_rt, rt); - if (err) - goto err_fib_rt_fini; - - if (!fen6_info->nsiblings) - return fib6_rt; - - list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) { - if (i == fen6_info->nsiblings) - break; - - err = nsim_fib6_rt_nh_add(fib6_rt, iter); + for (i = 0; i < nrt6; i++) { + err = nsim_fib6_rt_nh_add(fib6_rt, rt_arr[i]); if (err) goto err_fib6_rt_nh_del; - i++; } - WARN_ON_ONCE(i != fen6_info->nsiblings); return fib6_rt; err_fib6_rt_nh_del: - list_for_each_entry_continue_reverse(iter, &rt->fib6_siblings, - fib6_siblings) - nsim_fib6_rt_nh_del(fib6_rt, iter); - nsim_fib6_rt_nh_del(fib6_rt, rt); -err_fib_rt_fini: + for (i--; i >= 0; i--) { + nsim_fib6_rt_nh_del(fib6_rt, rt_arr[i]); + } nsim_fib_rt_fini(&fib6_rt->common); kfree(fib6_rt); return ERR_PTR(err); @@ -537,127 +602,163 @@ nsim_fib6_rt_lookup(struct rhashtable *fib_rt_ht, const struct fib6_info *rt) } static int nsim_fib6_rt_append(struct nsim_fib_data *data, - struct fib6_entry_notifier_info *fen6_info) + struct nsim_fib6_event *fib6_event) { - struct fib6_info *iter, *rt = fen6_info->rt; + struct fib6_info *rt = fib6_event->rt_arr[0]; struct nsim_fib6_rt *fib6_rt; - int i = 0; - int err; + int i, err; + + if (data->fail_route_offload) { + /* For testing purposes, user set debugfs fail_route_offload + * value to true. Simulate hardware programming latency and then + * fail. + */ + msleep(1); + return -EINVAL; + } fib6_rt = nsim_fib6_rt_lookup(&data->fib_rt_ht, rt); - if (WARN_ON_ONCE(!fib6_rt)) + if (!fib6_rt) return -EINVAL; - err = nsim_fib6_rt_nh_add(fib6_rt, rt); - if (err) - return err; - rt->trap = true; - - if (!fen6_info->nsiblings) - return 0; - - list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) { - if (i == fen6_info->nsiblings) - break; - - err = nsim_fib6_rt_nh_add(fib6_rt, iter); + for (i = 0; i < fib6_event->nrt6; i++) { + err = nsim_fib6_rt_nh_add(fib6_rt, fib6_event->rt_arr[i]); if (err) goto err_fib6_rt_nh_del; - iter->trap = true; - i++; + + WRITE_ONCE(fib6_event->rt_arr[i]->trap, true); } - WARN_ON_ONCE(i != fen6_info->nsiblings); return 0; err_fib6_rt_nh_del: - list_for_each_entry_continue_reverse(iter, &rt->fib6_siblings, - fib6_siblings) { - iter->trap = false; - nsim_fib6_rt_nh_del(fib6_rt, iter); + for (i--; i >= 0; i--) { + WRITE_ONCE(fib6_event->rt_arr[i]->trap, false); + nsim_fib6_rt_nh_del(fib6_rt, fib6_event->rt_arr[i]); } - rt->trap = false; - nsim_fib6_rt_nh_del(fib6_rt, rt); return err; } -static void nsim_fib6_rt_hw_flags_set(const struct nsim_fib6_rt *fib6_rt, +#if IS_ENABLED(CONFIG_IPV6) +static void nsim_fib6_rt_offload_failed_flag_set(struct nsim_fib_data *data, + struct fib6_info **rt_arr, + unsigned int nrt6) + +{ + struct net *net = devlink_net(data->devlink); + int i; + + for (i = 0; i < nrt6; i++) + fib6_info_hw_flags_set(net, rt_arr[i], false, false, true); +} +#else +static void nsim_fib6_rt_offload_failed_flag_set(struct nsim_fib_data *data, + struct fib6_info **rt_arr, + unsigned int nrt6) +{ +} +#endif + +#if IS_ENABLED(CONFIG_IPV6) +static void nsim_fib6_rt_hw_flags_set(struct nsim_fib_data *data, + const struct nsim_fib6_rt *fib6_rt, bool trap) { + struct net *net = devlink_net(data->devlink); struct nsim_fib6_rt_nh *fib6_rt_nh; list_for_each_entry(fib6_rt_nh, &fib6_rt->nh_list, list) - fib6_info_hw_flags_set(fib6_rt_nh->rt, false, trap); + fib6_info_hw_flags_set(net, fib6_rt_nh->rt, false, trap, false); +} +#else +static void nsim_fib6_rt_hw_flags_set(struct nsim_fib_data *data, + const struct nsim_fib6_rt *fib6_rt, + bool trap) +{ } +#endif static int nsim_fib6_rt_add(struct nsim_fib_data *data, - struct nsim_fib6_rt *fib6_rt, - struct netlink_ext_ack *extack) + struct nsim_fib6_rt *fib6_rt) { int err; - err = nsim_fib_account(&data->ipv6.fib, true, extack); - if (err) - return err; - err = rhashtable_insert_fast(&data->fib_rt_ht, &fib6_rt->common.ht_node, nsim_fib_rt_ht_params); - if (err) { - NL_SET_ERR_MSG_MOD(extack, "Failed to insert IPv6 route"); + + if (err) goto err_fib_dismiss; - } - nsim_fib6_rt_hw_flags_set(fib6_rt, true); + msleep(1); + nsim_fib6_rt_hw_flags_set(data, fib6_rt, true); return 0; err_fib_dismiss: - nsim_fib_account(&data->ipv6.fib, false, extack); + /* Drop the accounting that was increased from the notification + * context when FIB_EVENT_ENTRY_REPLACE was triggered. + */ + nsim_fib_account(&data->ipv6.fib, false); return err; } static int nsim_fib6_rt_replace(struct nsim_fib_data *data, struct nsim_fib6_rt *fib6_rt, - struct nsim_fib6_rt *fib6_rt_old, - struct netlink_ext_ack *extack) + struct nsim_fib6_rt *fib6_rt_old) { int err; - /* We are replacing a route, so no need to change the accounting. */ + /* We are replacing a route, so need to remove the accounting which + * was increased when FIB_EVENT_ENTRY_REPLACE was triggered. + */ + err = nsim_fib_account(&data->ipv6.fib, false); + if (err) + return err; + err = rhashtable_replace_fast(&data->fib_rt_ht, &fib6_rt_old->common.ht_node, &fib6_rt->common.ht_node, nsim_fib_rt_ht_params); - if (err) { - NL_SET_ERR_MSG_MOD(extack, "Failed to replace IPv6 route"); + + if (err) return err; - } - nsim_fib6_rt_hw_flags_set(fib6_rt, true); + msleep(1); + nsim_fib6_rt_hw_flags_set(data, fib6_rt, true); - nsim_fib6_rt_hw_flags_set(fib6_rt_old, false); + nsim_fib6_rt_hw_flags_set(data, fib6_rt_old, false); nsim_fib6_rt_destroy(fib6_rt_old); return 0; } static int nsim_fib6_rt_insert(struct nsim_fib_data *data, - struct fib6_entry_notifier_info *fen6_info) + struct nsim_fib6_event *fib6_event) { - struct netlink_ext_ack *extack = fen6_info->info.extack; + struct fib6_info *rt = fib6_event->rt_arr[0]; struct nsim_fib6_rt *fib6_rt, *fib6_rt_old; int err; - fib6_rt = nsim_fib6_rt_create(data, fen6_info); + if (data->fail_route_offload) { + /* For testing purposes, user set debugfs fail_route_offload + * value to true. Simulate hardware programming latency and then + * fail. + */ + msleep(1); + return -EINVAL; + } + + fib6_rt = nsim_fib6_rt_create(data, fib6_event->rt_arr, + fib6_event->nrt6); if (IS_ERR(fib6_rt)) return PTR_ERR(fib6_rt); - fib6_rt_old = nsim_fib6_rt_lookup(&data->fib_rt_ht, fen6_info->rt); + fib6_rt_old = nsim_fib6_rt_lookup(&data->fib_rt_ht, rt); if (!fib6_rt_old) - err = nsim_fib6_rt_add(data, fib6_rt, extack); + err = nsim_fib6_rt_add(data, fib6_rt); else - err = nsim_fib6_rt_replace(data, fib6_rt, fib6_rt_old, extack); + err = nsim_fib6_rt_replace(data, fib6_rt, fib6_rt_old); if (err) nsim_fib6_rt_destroy(fib6_rt); @@ -665,87 +766,261 @@ static int nsim_fib6_rt_insert(struct nsim_fib_data *data, return err; } -static void -nsim_fib6_rt_remove(struct nsim_fib_data *data, - const struct fib6_entry_notifier_info *fen6_info) +static void nsim_fib6_rt_remove(struct nsim_fib_data *data, + struct nsim_fib6_event *fib6_event) { - struct netlink_ext_ack *extack = fen6_info->info.extack; + struct fib6_info *rt = fib6_event->rt_arr[0]; struct nsim_fib6_rt *fib6_rt; + int i; /* Multipath routes are first added to the FIB trie and only then * notified. If we vetoed the addition, we will get a delete * notification for a route we do not have. Therefore, do not warn if * route was not found. */ - fib6_rt = nsim_fib6_rt_lookup(&data->fib_rt_ht, fen6_info->rt); + fib6_rt = nsim_fib6_rt_lookup(&data->fib_rt_ht, rt); if (!fib6_rt) return; /* If not all the nexthops are deleted, then only reduce the nexthop * group. */ - if (fen6_info->nsiblings + 1 != fib6_rt->nhs) { - nsim_fib6_rt_nh_del(fib6_rt, fen6_info->rt); + if (fib6_event->nrt6 != fib6_rt->nhs) { + for (i = 0; i < fib6_event->nrt6; i++) + nsim_fib6_rt_nh_del(fib6_rt, fib6_event->rt_arr[i]); return; } rhashtable_remove_fast(&data->fib_rt_ht, &fib6_rt->common.ht_node, nsim_fib_rt_ht_params); - nsim_fib_account(&data->ipv6.fib, false, extack); nsim_fib6_rt_destroy(fib6_rt); } -static int nsim_fib6_event(struct nsim_fib_data *data, - struct fib_notifier_info *info, - unsigned long event) +static int nsim_fib6_event_init(struct nsim_fib6_event *fib6_event, + struct fib6_entry_notifier_info *fen6_info) { - struct fib6_entry_notifier_info *fen6_info; - int err = 0; + struct fib6_info *rt = fen6_info->rt; + struct fib6_info **rt_arr; + struct fib6_info *iter; + unsigned int nrt6; + int i = 0; + + nrt6 = fen6_info->nsiblings + 1; + + rt_arr = kcalloc(nrt6, sizeof(struct fib6_info *), GFP_ATOMIC); + if (!rt_arr) + return -ENOMEM; - fen6_info = container_of(info, struct fib6_entry_notifier_info, info); + fib6_event->rt_arr = rt_arr; + fib6_event->nrt6 = nrt6; - if (fen6_info->rt->nh) { - NL_SET_ERR_MSG_MOD(info->extack, "IPv6 route with nexthop objects is not supported"); + rt_arr[0] = rt; + fib6_info_hold(rt); + + if (!fen6_info->nsiblings) return 0; + + list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) { + if (i == fen6_info->nsiblings) + break; + + rt_arr[i + 1] = iter; + fib6_info_hold(iter); + i++; } + WARN_ON_ONCE(i != fen6_info->nsiblings); - if (fen6_info->rt->fib6_src.plen) { - NL_SET_ERR_MSG_MOD(info->extack, "IPv6 source-specific route is not supported"); + return 0; +} + +static void nsim_fib6_event_fini(struct nsim_fib6_event *fib6_event) +{ + int i; + + for (i = 0; i < fib6_event->nrt6; i++) + nsim_rt6_release(fib6_event->rt_arr[i]); + kfree(fib6_event->rt_arr); +} + +static int nsim_fib6_event(struct nsim_fib_data *data, + struct nsim_fib6_event *fib6_event, + unsigned long event) +{ + int err; + + if (fib6_event->rt_arr[0]->fib6_src.plen) return 0; - } switch (event) { case FIB_EVENT_ENTRY_REPLACE: - err = nsim_fib6_rt_insert(data, fen6_info); + err = nsim_fib6_rt_insert(data, fib6_event); + if (err) + goto err_rt_offload_failed_flag_set; break; case FIB_EVENT_ENTRY_APPEND: - err = nsim_fib6_rt_append(data, fen6_info); + err = nsim_fib6_rt_append(data, fib6_event); + if (err) + goto err_rt_offload_failed_flag_set; break; case FIB_EVENT_ENTRY_DEL: - nsim_fib6_rt_remove(data, fen6_info); + nsim_fib6_rt_remove(data, fib6_event); break; default: break; } + return 0; + +err_rt_offload_failed_flag_set: + nsim_fib6_rt_offload_failed_flag_set(data, fib6_event->rt_arr, + fib6_event->nrt6); return err; } -static int nsim_fib_event(struct nsim_fib_data *data, - struct fib_notifier_info *info, unsigned long event) +static void nsim_fib_event(struct nsim_fib_event *fib_event) { + switch (fib_event->family) { + case AF_INET: + nsim_fib4_event(fib_event->data, &fib_event->fen_info, + fib_event->event); + fib_info_put(fib_event->fen_info.fi); + break; + case AF_INET6: + nsim_fib6_event(fib_event->data, &fib_event->fib6_event, + fib_event->event); + nsim_fib6_event_fini(&fib_event->fib6_event); + break; + } +} + +static int nsim_fib4_prepare_event(struct fib_notifier_info *info, + struct nsim_fib_event *fib_event, + unsigned long event) +{ + struct nsim_fib_data *data = fib_event->data; + struct fib_entry_notifier_info *fen_info; + struct netlink_ext_ack *extack; int err = 0; + fen_info = container_of(info, struct fib_entry_notifier_info, + info); + fib_event->fen_info = *fen_info; + extack = info->extack; + + switch (event) { + case FIB_EVENT_ENTRY_REPLACE: + err = nsim_fib_account(&data->ipv4.fib, true); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported fib entries"); + return err; + } + break; + case FIB_EVENT_ENTRY_DEL: + if (data->fail_route_delete) { + NL_SET_ERR_MSG_MOD(extack, "Failed to process route deletion"); + return -EINVAL; + } + nsim_fib_account(&data->ipv4.fib, false); + break; + } + + /* Take reference on fib_info to prevent it from being + * freed while event is queued. Release it afterwards. + */ + fib_info_hold(fib_event->fen_info.fi); + + return 0; +} + +static int nsim_fib6_prepare_event(struct fib_notifier_info *info, + struct nsim_fib_event *fib_event, + unsigned long event) +{ + struct nsim_fib_data *data = fib_event->data; + struct fib6_entry_notifier_info *fen6_info; + struct netlink_ext_ack *extack; + int err = 0; + + fen6_info = container_of(info, struct fib6_entry_notifier_info, + info); + + err = nsim_fib6_event_init(&fib_event->fib6_event, fen6_info); + if (err) + return err; + + extack = info->extack; + switch (event) { + case FIB_EVENT_ENTRY_REPLACE: + err = nsim_fib_account(&data->ipv6.fib, true); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported fib entries"); + goto err_fib6_event_fini; + } + break; + case FIB_EVENT_ENTRY_DEL: + if (data->fail_route_delete) { + err = -EINVAL; + NL_SET_ERR_MSG_MOD(extack, "Failed to process route deletion"); + goto err_fib6_event_fini; + } + nsim_fib_account(&data->ipv6.fib, false); + break; + } + + return 0; + +err_fib6_event_fini: + nsim_fib6_event_fini(&fib_event->fib6_event); + return err; +} + +static int nsim_fib_event_schedule_work(struct nsim_fib_data *data, + struct fib_notifier_info *info, + unsigned long event) +{ + struct nsim_fib_event *fib_event; + int err; + + if (info->family != AF_INET && info->family != AF_INET6) + /* netdevsim does not support 'RTNL_FAMILY_IP6MR' and + * 'RTNL_FAMILY_IPMR' and should ignore them. + */ + return NOTIFY_DONE; + + fib_event = kzalloc(sizeof(*fib_event), GFP_ATOMIC); + if (!fib_event) + goto err_fib_event_alloc; + + fib_event->data = data; + fib_event->event = event; + fib_event->family = info->family; + switch (info->family) { case AF_INET: - err = nsim_fib4_event(data, info, event); + err = nsim_fib4_prepare_event(info, fib_event, event); break; case AF_INET6: - err = nsim_fib6_event(data, info, event); + err = nsim_fib6_prepare_event(info, fib_event, event); break; } - return err; + if (err) + goto err_fib_prepare_event; + + /* Enqueue the event and trigger the work */ + spin_lock_bh(&data->fib_event_queue_lock); + list_add_tail(&fib_event->list, &data->fib_event_queue); + spin_unlock_bh(&data->fib_event_queue_lock); + schedule_work(&data->fib_event_work); + + return NOTIFY_DONE; + +err_fib_prepare_event: + kfree(fib_event); +err_fib_event_alloc: + if (event == FIB_EVENT_ENTRY_DEL) + schedule_work(&data->fib_flush_work); + return NOTIFY_BAD; } static int nsim_fib_event_nb(struct notifier_block *nb, unsigned long event, @@ -754,28 +1029,21 @@ static int nsim_fib_event_nb(struct notifier_block *nb, unsigned long event, struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data, fib_nb); struct fib_notifier_info *info = ptr; - int err = 0; - - /* IPv6 routes can be added via RAs from softIRQ. */ - spin_lock_bh(&data->fib_lock); + int err; switch (event) { - case FIB_EVENT_RULE_ADD: /* fall through */ + case FIB_EVENT_RULE_ADD: case FIB_EVENT_RULE_DEL: err = nsim_fib_rule_event(data, info, event == FIB_EVENT_RULE_ADD); - break; - - case FIB_EVENT_ENTRY_REPLACE: /* fall through */ - case FIB_EVENT_ENTRY_APPEND: /* fall through */ + return notifier_from_errno(err); + case FIB_EVENT_ENTRY_REPLACE: + case FIB_EVENT_ENTRY_APPEND: case FIB_EVENT_ENTRY_DEL: - err = nsim_fib_event(data, info, event); - break; + return nsim_fib_event_schedule_work(data, info, event); } - spin_unlock_bh(&data->fib_lock); - - return notifier_from_errno(err); + return NOTIFY_DONE; } static void nsim_fib4_rt_free(struct nsim_fib_rt *fib_rt, @@ -786,7 +1054,7 @@ static void nsim_fib4_rt_free(struct nsim_fib_rt *fib_rt, fib4_rt = container_of(fib_rt, struct nsim_fib4_rt, common); nsim_fib4_rt_hw_flags_set(devlink_net(devlink), fib4_rt, false); - nsim_fib_account(&data->ipv4.fib, false, NULL); + nsim_fib_account(&data->ipv4.fib, false); nsim_fib4_rt_destroy(fib4_rt); } @@ -796,8 +1064,8 @@ static void nsim_fib6_rt_free(struct nsim_fib_rt *fib_rt, struct nsim_fib6_rt *fib6_rt; fib6_rt = container_of(fib_rt, struct nsim_fib6_rt, common); - nsim_fib6_rt_hw_flags_set(fib6_rt, false); - nsim_fib_account(&data->ipv6.fib, false, NULL); + nsim_fib6_rt_hw_flags_set(data, fib6_rt, false); + nsim_fib_account(&data->ipv6.fib, false); nsim_fib6_rt_destroy(fib6_rt); } @@ -825,6 +1093,9 @@ static void nsim_fib_dump_inconsistent(struct notifier_block *nb) fib_nb); struct nsim_fib_rt *fib_rt, *fib_rt_tmp; + /* Flush the work to make sure there is no race with notifications. */ + flush_work(&data->fib_event_work); + /* The notifier block is still not registered, so we do not need to * take any locks here. */ @@ -834,10 +1105,319 @@ static void nsim_fib_dump_inconsistent(struct notifier_block *nb) nsim_fib_rt_free(fib_rt, data); } - data->ipv4.rules.num = 0ULL; - data->ipv6.rules.num = 0ULL; + atomic64_set(&data->ipv4.rules.num, 0ULL); + atomic64_set(&data->ipv6.rules.num, 0ULL); +} + +static struct nsim_nexthop *nsim_nexthop_create(struct nsim_fib_data *data, + struct nh_notifier_info *info) +{ + struct nsim_nexthop *nexthop; + u64 occ = 0; + int i; + + nexthop = kzalloc(sizeof(*nexthop), GFP_KERNEL); + if (!nexthop) + return ERR_PTR(-ENOMEM); + + nexthop->id = info->id; + + /* Determine the number of nexthop entries the new nexthop will + * occupy. + */ + + switch (info->type) { + case NH_NOTIFIER_INFO_TYPE_SINGLE: + occ = 1; + break; + case NH_NOTIFIER_INFO_TYPE_GRP: + for (i = 0; i < info->nh_grp->num_nh; i++) + occ += info->nh_grp->nh_entries[i].weight; + break; + case NH_NOTIFIER_INFO_TYPE_RES_TABLE: + occ = info->nh_res_table->num_nh_buckets; + nexthop->is_resilient = true; + break; + default: + NL_SET_ERR_MSG_MOD(info->extack, "Unsupported nexthop type"); + kfree(nexthop); + return ERR_PTR(-EOPNOTSUPP); + } + + nexthop->occ = occ; + return nexthop; +} + +static void nsim_nexthop_destroy(struct nsim_nexthop *nexthop) +{ + kfree(nexthop); +} + +static int nsim_nexthop_account(struct nsim_fib_data *data, u64 occ, + bool add, struct netlink_ext_ack *extack) +{ + int i, err = 0; + + if (add) { + for (i = 0; i < occ; i++) + if (!atomic64_add_unless(&data->nexthops.num, 1, + data->nexthops.max)) { + err = -ENOSPC; + NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported nexthops"); + goto err_num_decrease; + } + } else { + if (WARN_ON(occ > atomic64_read(&data->nexthops.num))) + return -EINVAL; + atomic64_sub(occ, &data->nexthops.num); + } + + return err; + +err_num_decrease: + atomic64_sub(i, &data->nexthops.num); + return err; + +} + +static void nsim_nexthop_hw_flags_set(struct net *net, + const struct nsim_nexthop *nexthop, + bool trap) +{ + int i; + + nexthop_set_hw_flags(net, nexthop->id, false, trap); + + if (!nexthop->is_resilient) + return; + + for (i = 0; i < nexthop->occ; i++) + nexthop_bucket_set_hw_flags(net, nexthop->id, i, false, trap); +} + +static int nsim_nexthop_add(struct nsim_fib_data *data, + struct nsim_nexthop *nexthop, + struct netlink_ext_ack *extack) +{ + struct net *net = devlink_net(data->devlink); + int err; + + err = nsim_nexthop_account(data, nexthop->occ, true, extack); + if (err) + return err; + + err = rhashtable_insert_fast(&data->nexthop_ht, &nexthop->ht_node, + nsim_nexthop_ht_params); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to insert nexthop"); + goto err_nexthop_dismiss; + } + + nsim_nexthop_hw_flags_set(net, nexthop, true); + + return 0; + +err_nexthop_dismiss: + nsim_nexthop_account(data, nexthop->occ, false, extack); + return err; +} + +static int nsim_nexthop_replace(struct nsim_fib_data *data, + struct nsim_nexthop *nexthop, + struct nsim_nexthop *nexthop_old, + struct netlink_ext_ack *extack) +{ + struct net *net = devlink_net(data->devlink); + int err; + + err = nsim_nexthop_account(data, nexthop->occ, true, extack); + if (err) + return err; + + err = rhashtable_replace_fast(&data->nexthop_ht, + &nexthop_old->ht_node, &nexthop->ht_node, + nsim_nexthop_ht_params); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to replace nexthop"); + goto err_nexthop_dismiss; + } + + nsim_nexthop_hw_flags_set(net, nexthop, true); + nsim_nexthop_account(data, nexthop_old->occ, false, extack); + nsim_nexthop_destroy(nexthop_old); + + return 0; + +err_nexthop_dismiss: + nsim_nexthop_account(data, nexthop->occ, false, extack); + return err; +} + +static int nsim_nexthop_insert(struct nsim_fib_data *data, + struct nh_notifier_info *info) +{ + struct nsim_nexthop *nexthop, *nexthop_old; + int err; + + nexthop = nsim_nexthop_create(data, info); + if (IS_ERR(nexthop)) + return PTR_ERR(nexthop); + + nexthop_old = rhashtable_lookup_fast(&data->nexthop_ht, &info->id, + nsim_nexthop_ht_params); + if (!nexthop_old) + err = nsim_nexthop_add(data, nexthop, info->extack); + else + err = nsim_nexthop_replace(data, nexthop, nexthop_old, + info->extack); + + if (err) + nsim_nexthop_destroy(nexthop); + + return err; +} + +static void nsim_nexthop_remove(struct nsim_fib_data *data, + struct nh_notifier_info *info) +{ + struct nsim_nexthop *nexthop; + + nexthop = rhashtable_lookup_fast(&data->nexthop_ht, &info->id, + nsim_nexthop_ht_params); + if (!nexthop) + return; + + rhashtable_remove_fast(&data->nexthop_ht, &nexthop->ht_node, + nsim_nexthop_ht_params); + nsim_nexthop_account(data, nexthop->occ, false, info->extack); + nsim_nexthop_destroy(nexthop); +} + +static int nsim_nexthop_res_table_pre_replace(struct nsim_fib_data *data, + struct nh_notifier_info *info) +{ + if (data->fail_res_nexthop_group_replace) { + NL_SET_ERR_MSG_MOD(info->extack, "Failed to replace a resilient nexthop group"); + return -EINVAL; + } + + return 0; +} + +static int nsim_nexthop_bucket_replace(struct nsim_fib_data *data, + struct nh_notifier_info *info) +{ + if (data->fail_nexthop_bucket_replace) { + NL_SET_ERR_MSG_MOD(info->extack, "Failed to replace nexthop bucket"); + return -EINVAL; + } + + nexthop_bucket_set_hw_flags(info->net, info->id, + info->nh_res_bucket->bucket_index, + false, true); + + return 0; +} + +static int nsim_nexthop_event_nb(struct notifier_block *nb, unsigned long event, + void *ptr) +{ + struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data, + nexthop_nb); + struct nh_notifier_info *info = ptr; + int err = 0; + + mutex_lock(&data->nh_lock); + switch (event) { + case NEXTHOP_EVENT_REPLACE: + err = nsim_nexthop_insert(data, info); + break; + case NEXTHOP_EVENT_DEL: + nsim_nexthop_remove(data, info); + break; + case NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE: + err = nsim_nexthop_res_table_pre_replace(data, info); + break; + case NEXTHOP_EVENT_BUCKET_REPLACE: + err = nsim_nexthop_bucket_replace(data, info); + break; + default: + break; + } + + mutex_unlock(&data->nh_lock); + return notifier_from_errno(err); } +static void nsim_nexthop_free(void *ptr, void *arg) +{ + struct nsim_nexthop *nexthop = ptr; + struct nsim_fib_data *data = arg; + struct net *net; + + net = devlink_net(data->devlink); + nsim_nexthop_hw_flags_set(net, nexthop, false); + nsim_nexthop_account(data, nexthop->occ, false, NULL); + nsim_nexthop_destroy(nexthop); +} + +static ssize_t nsim_nexthop_bucket_activity_write(struct file *file, + const char __user *user_buf, + size_t size, loff_t *ppos) +{ + struct nsim_fib_data *data = file->private_data; + struct net *net = devlink_net(data->devlink); + struct nsim_nexthop *nexthop; + unsigned long *activity; + loff_t pos = *ppos; + u16 bucket_index; + char buf[128]; + int err = 0; + u32 nhid; + + if (pos != 0) + return -EINVAL; + if (size > sizeof(buf)) + return -EINVAL; + if (copy_from_user(buf, user_buf, size)) + return -EFAULT; + if (sscanf(buf, "%u %hu", &nhid, &bucket_index) != 2) + return -EINVAL; + + rtnl_lock(); + + nexthop = rhashtable_lookup_fast(&data->nexthop_ht, &nhid, + nsim_nexthop_ht_params); + if (!nexthop || !nexthop->is_resilient || + bucket_index >= nexthop->occ) { + err = -EINVAL; + goto out; + } + + activity = bitmap_zalloc(nexthop->occ, GFP_KERNEL); + if (!activity) { + err = -ENOMEM; + goto out; + } + + bitmap_set(activity, bucket_index, 1); + nexthop_res_grp_activity_update(net, nhid, nexthop->occ, activity); + bitmap_free(activity); + +out: + rtnl_unlock(); + + *ppos = size; + return err ?: size; +} + +static const struct file_operations nsim_nexthop_bucket_activity_fops = { + .open = simple_open, + .write = nsim_nexthop_bucket_activity_write, + .llseek = no_llseek, + .owner = THIS_MODULE, +}; + static u64 nsim_fib_ipv4_resource_occ_get(void *priv) { struct nsim_fib_data *data = priv; @@ -866,12 +1446,20 @@ static u64 nsim_fib_ipv6_rules_res_occ_get(void *priv) return nsim_fib_get_val(data, NSIM_RESOURCE_IPV6_FIB_RULES, false); } +static u64 nsim_fib_nexthops_res_occ_get(void *priv) +{ + struct nsim_fib_data *data = priv; + + return nsim_fib_get_val(data, NSIM_RESOURCE_NEXTHOPS, false); +} + static void nsim_fib_set_max_all(struct nsim_fib_data *data, struct devlink *devlink) { - enum nsim_resource_id res_ids[] = { + static const enum nsim_resource_id res_ids[] = { NSIM_RESOURCE_IPV4_FIB, NSIM_RESOURCE_IPV4_FIB_RULES, - NSIM_RESOURCE_IPV6_FIB, NSIM_RESOURCE_IPV6_FIB_RULES + NSIM_RESOURCE_IPV6_FIB, NSIM_RESOURCE_IPV6_FIB_RULES, + NSIM_RESOURCE_NEXTHOPS, }; int i; @@ -879,17 +1467,92 @@ static void nsim_fib_set_max_all(struct nsim_fib_data *data, int err; u64 val; - err = devlink_resource_size_get(devlink, res_ids[i], &val); + err = devl_resource_size_get(devlink, res_ids[i], &val); if (err) val = (u64) -1; nsim_fib_set_max(data, res_ids[i], val); } } +static void nsim_fib_event_work(struct work_struct *work) +{ + struct nsim_fib_data *data = container_of(work, struct nsim_fib_data, + fib_event_work); + struct nsim_fib_event *fib_event, *next_fib_event; + + LIST_HEAD(fib_event_queue); + + spin_lock_bh(&data->fib_event_queue_lock); + list_splice_init(&data->fib_event_queue, &fib_event_queue); + spin_unlock_bh(&data->fib_event_queue_lock); + + mutex_lock(&data->fib_lock); + list_for_each_entry_safe(fib_event, next_fib_event, &fib_event_queue, + list) { + nsim_fib_event(fib_event); + list_del(&fib_event->list); + kfree(fib_event); + cond_resched(); + } + mutex_unlock(&data->fib_lock); +} + +static void nsim_fib_flush_work(struct work_struct *work) +{ + struct nsim_fib_data *data = container_of(work, struct nsim_fib_data, + fib_flush_work); + struct nsim_fib_rt *fib_rt, *fib_rt_tmp; + + /* Process pending work. */ + flush_work(&data->fib_event_work); + + mutex_lock(&data->fib_lock); + list_for_each_entry_safe(fib_rt, fib_rt_tmp, &data->fib_rt_list, list) { + rhashtable_remove_fast(&data->fib_rt_ht, &fib_rt->ht_node, + nsim_fib_rt_ht_params); + nsim_fib_rt_free(fib_rt, data); + } + mutex_unlock(&data->fib_lock); +} + +static int +nsim_fib_debugfs_init(struct nsim_fib_data *data, struct nsim_dev *nsim_dev) +{ + data->ddir = debugfs_create_dir("fib", nsim_dev->ddir); + if (IS_ERR(data->ddir)) + return PTR_ERR(data->ddir); + + data->fail_route_offload = false; + debugfs_create_bool("fail_route_offload", 0600, data->ddir, + &data->fail_route_offload); + + data->fail_res_nexthop_group_replace = false; + debugfs_create_bool("fail_res_nexthop_group_replace", 0600, data->ddir, + &data->fail_res_nexthop_group_replace); + + data->fail_nexthop_bucket_replace = false; + debugfs_create_bool("fail_nexthop_bucket_replace", 0600, data->ddir, + &data->fail_nexthop_bucket_replace); + + debugfs_create_file("nexthop_bucket_activity", 0200, data->ddir, + data, &nsim_nexthop_bucket_activity_fops); + + data->fail_route_delete = false; + debugfs_create_bool("fail_route_delete", 0600, data->ddir, + &data->fail_route_delete); + return 0; +} + +static void nsim_fib_debugfs_exit(struct nsim_fib_data *data) +{ + debugfs_remove_recursive(data->ddir); +} + struct nsim_fib_data *nsim_fib_create(struct devlink *devlink, struct netlink_ext_ack *extack) { struct nsim_fib_data *data; + struct nsim_dev *nsim_dev; int err; data = kzalloc(sizeof(*data), GFP_KERNEL); @@ -897,43 +1560,81 @@ struct nsim_fib_data *nsim_fib_create(struct devlink *devlink, return ERR_PTR(-ENOMEM); data->devlink = devlink; - spin_lock_init(&data->fib_lock); + nsim_dev = devlink_priv(devlink); + err = nsim_fib_debugfs_init(data, nsim_dev); + if (err) + goto err_data_free; + + mutex_init(&data->nh_lock); + err = rhashtable_init(&data->nexthop_ht, &nsim_nexthop_ht_params); + if (err) + goto err_debugfs_exit; + + mutex_init(&data->fib_lock); INIT_LIST_HEAD(&data->fib_rt_list); err = rhashtable_init(&data->fib_rt_ht, &nsim_fib_rt_ht_params); if (err) - goto err_data_free; + goto err_rhashtable_nexthop_destroy; + + INIT_WORK(&data->fib_event_work, nsim_fib_event_work); + INIT_WORK(&data->fib_flush_work, nsim_fib_flush_work); + INIT_LIST_HEAD(&data->fib_event_queue); + spin_lock_init(&data->fib_event_queue_lock); nsim_fib_set_max_all(data, devlink); + data->nexthop_nb.notifier_call = nsim_nexthop_event_nb; + err = register_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb, + extack); + if (err) { + pr_err("Failed to register nexthop notifier\n"); + goto err_rhashtable_fib_destroy; + } + data->fib_nb.notifier_call = nsim_fib_event_nb; err = register_fib_notifier(devlink_net(devlink), &data->fib_nb, nsim_fib_dump_inconsistent, extack); if (err) { pr_err("Failed to register fib notifier\n"); - goto err_rhashtable_destroy; - } - - devlink_resource_occ_get_register(devlink, - NSIM_RESOURCE_IPV4_FIB, - nsim_fib_ipv4_resource_occ_get, - data); - devlink_resource_occ_get_register(devlink, - NSIM_RESOURCE_IPV4_FIB_RULES, - nsim_fib_ipv4_rules_res_occ_get, - data); - devlink_resource_occ_get_register(devlink, - NSIM_RESOURCE_IPV6_FIB, - nsim_fib_ipv6_resource_occ_get, - data); - devlink_resource_occ_get_register(devlink, - NSIM_RESOURCE_IPV6_FIB_RULES, - nsim_fib_ipv6_rules_res_occ_get, - data); + goto err_nexthop_nb_unregister; + } + + devl_resource_occ_get_register(devlink, + NSIM_RESOURCE_IPV4_FIB, + nsim_fib_ipv4_resource_occ_get, + data); + devl_resource_occ_get_register(devlink, + NSIM_RESOURCE_IPV4_FIB_RULES, + nsim_fib_ipv4_rules_res_occ_get, + data); + devl_resource_occ_get_register(devlink, + NSIM_RESOURCE_IPV6_FIB, + nsim_fib_ipv6_resource_occ_get, + data); + devl_resource_occ_get_register(devlink, + NSIM_RESOURCE_IPV6_FIB_RULES, + nsim_fib_ipv6_rules_res_occ_get, + data); + devl_resource_occ_get_register(devlink, + NSIM_RESOURCE_NEXTHOPS, + nsim_fib_nexthops_res_occ_get, + data); return data; -err_rhashtable_destroy: +err_nexthop_nb_unregister: + unregister_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb); +err_rhashtable_fib_destroy: + cancel_work_sync(&data->fib_flush_work); + flush_work(&data->fib_event_work); rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free, data); +err_rhashtable_nexthop_destroy: + rhashtable_free_and_destroy(&data->nexthop_ht, nsim_nexthop_free, + data); + mutex_destroy(&data->fib_lock); +err_debugfs_exit: + mutex_destroy(&data->nh_lock); + nsim_fib_debugfs_exit(data); err_data_free: kfree(data); return ERR_PTR(err); @@ -941,17 +1642,28 @@ err_data_free: void nsim_fib_destroy(struct devlink *devlink, struct nsim_fib_data *data) { - devlink_resource_occ_get_unregister(devlink, - NSIM_RESOURCE_IPV6_FIB_RULES); - devlink_resource_occ_get_unregister(devlink, - NSIM_RESOURCE_IPV6_FIB); - devlink_resource_occ_get_unregister(devlink, - NSIM_RESOURCE_IPV4_FIB_RULES); - devlink_resource_occ_get_unregister(devlink, - NSIM_RESOURCE_IPV4_FIB); + devl_resource_occ_get_unregister(devlink, + NSIM_RESOURCE_NEXTHOPS); + devl_resource_occ_get_unregister(devlink, + NSIM_RESOURCE_IPV6_FIB_RULES); + devl_resource_occ_get_unregister(devlink, + NSIM_RESOURCE_IPV6_FIB); + devl_resource_occ_get_unregister(devlink, + NSIM_RESOURCE_IPV4_FIB_RULES); + devl_resource_occ_get_unregister(devlink, + NSIM_RESOURCE_IPV4_FIB); unregister_fib_notifier(devlink_net(devlink), &data->fib_nb); + unregister_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb); + cancel_work_sync(&data->fib_flush_work); + flush_work(&data->fib_event_work); rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free, data); + rhashtable_free_and_destroy(&data->nexthop_ht, nsim_nexthop_free, + data); + WARN_ON_ONCE(!list_empty(&data->fib_event_queue)); WARN_ON_ONCE(!list_empty(&data->fib_rt_list)); + mutex_destroy(&data->fib_lock); + mutex_destroy(&data->nh_lock); + nsim_fib_debugfs_exit(data); kfree(data); } diff --git a/drivers/net/netdevsim/health.c b/drivers/net/netdevsim/health.c index ba8d9ad60feb..aa77af4a68df 100644 --- a/drivers/net/netdevsim/health.c +++ b/drivers/net/netdevsim/health.c @@ -110,26 +110,6 @@ static int nsim_dev_dummy_fmsg_put(struct devlink_fmsg *fmsg, u32 binary_len) if (err) return err; - err = devlink_fmsg_arr_pair_nest_start(fmsg, "test_bool_array"); - if (err) - return err; - for (i = 0; i < 10; i++) { - err = devlink_fmsg_bool_put(fmsg, true); - if (err) - return err; - } - err = devlink_fmsg_arr_pair_nest_end(fmsg); - if (err) - return err; - - err = devlink_fmsg_arr_pair_nest_start(fmsg, "test_u8_array"); - if (err) - return err; - for (i = 0; i < 10; i++) { - err = devlink_fmsg_u8_put(fmsg, i); - if (err) - return err; - } err = devlink_fmsg_arr_pair_nest_end(fmsg); if (err) return err; @@ -146,18 +126,6 @@ static int nsim_dev_dummy_fmsg_put(struct devlink_fmsg *fmsg, u32 binary_len) if (err) return err; - err = devlink_fmsg_arr_pair_nest_start(fmsg, "test_u64_array"); - if (err) - return err; - for (i = 0; i < 10; i++) { - err = devlink_fmsg_u64_put(fmsg, i); - if (err) - return err; - } - err = devlink_fmsg_arr_pair_nest_end(fmsg); - if (err) - return err; - err = devlink_fmsg_arr_pair_nest_start(fmsg, "test_array_of_objects"); if (err) return err; @@ -235,15 +203,10 @@ static ssize_t nsim_dev_health_break_write(struct file *file, char *break_msg; int err; - break_msg = kmalloc(count + 1, GFP_KERNEL); - if (!break_msg) - return -ENOMEM; + break_msg = memdup_user_nul(data, count); + if (IS_ERR(break_msg)) + return PTR_ERR(break_msg); - if (copy_from_user(break_msg, data, count)) { - err = -EFAULT; - goto out; - } - break_msg[count] = '\0'; if (break_msg[count - 1] == '\n') break_msg[count - 1] = '\0'; @@ -261,6 +224,7 @@ static const struct file_operations nsim_dev_health_break_fops = { .open = simple_open, .write = nsim_dev_health_break_write, .llseek = generic_file_llseek, + .owner = THIS_MODULE, }; int nsim_dev_health_init(struct nsim_dev *nsim_dev, struct devlink *devlink) @@ -271,14 +235,14 @@ int nsim_dev_health_init(struct nsim_dev *nsim_dev, struct devlink *devlink) health->empty_reporter = devlink_health_reporter_create(devlink, &nsim_dev_empty_reporter_ops, - 0, false, health); + 0, health); if (IS_ERR(health->empty_reporter)) return PTR_ERR(health->empty_reporter); health->dummy_reporter = devlink_health_reporter_create(devlink, &nsim_dev_dummy_reporter_ops, - 0, false, health); + 0, health); if (IS_ERR(health->dummy_reporter)) { err = PTR_ERR(health->dummy_reporter); goto err_empty_reporter_destroy; diff --git a/drivers/net/netdevsim/hwstats.c b/drivers/net/netdevsim/hwstats.c new file mode 100644 index 000000000000..0e58aa7f0374 --- /dev/null +++ b/drivers/net/netdevsim/hwstats.c @@ -0,0 +1,486 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/debugfs.h> + +#include "netdevsim.h" + +#define NSIM_DEV_HWSTATS_TRAFFIC_MS 100 + +static struct list_head * +nsim_dev_hwstats_get_list_head(struct nsim_dev_hwstats *hwstats, + enum netdev_offload_xstats_type type) +{ + switch (type) { + case NETDEV_OFFLOAD_XSTATS_TYPE_L3: + return &hwstats->l3_list; + } + + WARN_ON_ONCE(1); + return NULL; +} + +static void nsim_dev_hwstats_traffic_bump(struct nsim_dev_hwstats *hwstats, + enum netdev_offload_xstats_type type) +{ + struct nsim_dev_hwstats_netdev *hwsdev; + struct list_head *hwsdev_list; + + hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, type); + if (WARN_ON(!hwsdev_list)) + return; + + list_for_each_entry(hwsdev, hwsdev_list, list) { + if (hwsdev->enabled) { + hwsdev->stats.rx_packets += 1; + hwsdev->stats.tx_packets += 2; + hwsdev->stats.rx_bytes += 100; + hwsdev->stats.tx_bytes += 300; + } + } +} + +static void nsim_dev_hwstats_traffic_work(struct work_struct *work) +{ + struct nsim_dev_hwstats *hwstats; + + hwstats = container_of(work, struct nsim_dev_hwstats, traffic_dw.work); + mutex_lock(&hwstats->hwsdev_list_lock); + nsim_dev_hwstats_traffic_bump(hwstats, NETDEV_OFFLOAD_XSTATS_TYPE_L3); + mutex_unlock(&hwstats->hwsdev_list_lock); + + schedule_delayed_work(&hwstats->traffic_dw, + msecs_to_jiffies(NSIM_DEV_HWSTATS_TRAFFIC_MS)); +} + +static struct nsim_dev_hwstats_netdev * +nsim_dev_hwslist_find_hwsdev(struct list_head *hwsdev_list, + int ifindex) +{ + struct nsim_dev_hwstats_netdev *hwsdev; + + list_for_each_entry(hwsdev, hwsdev_list, list) { + if (hwsdev->netdev->ifindex == ifindex) + return hwsdev; + } + + return NULL; +} + +static int nsim_dev_hwsdev_enable(struct nsim_dev_hwstats_netdev *hwsdev, + struct netlink_ext_ack *extack) +{ + if (hwsdev->fail_enable) { + hwsdev->fail_enable = false; + NL_SET_ERR_MSG_MOD(extack, "Stats enablement set to fail"); + return -ECANCELED; + } + + hwsdev->enabled = true; + return 0; +} + +static void nsim_dev_hwsdev_disable(struct nsim_dev_hwstats_netdev *hwsdev) +{ + hwsdev->enabled = false; + memset(&hwsdev->stats, 0, sizeof(hwsdev->stats)); +} + +static int +nsim_dev_hwsdev_report_delta(struct nsim_dev_hwstats_netdev *hwsdev, + struct netdev_notifier_offload_xstats_info *info) +{ + netdev_offload_xstats_report_delta(info->report_delta, &hwsdev->stats); + memset(&hwsdev->stats, 0, sizeof(hwsdev->stats)); + return 0; +} + +static void +nsim_dev_hwsdev_report_used(struct nsim_dev_hwstats_netdev *hwsdev, + struct netdev_notifier_offload_xstats_info *info) +{ + if (hwsdev->enabled) + netdev_offload_xstats_report_used(info->report_used); +} + +static int nsim_dev_hwstats_event_off_xstats(struct nsim_dev_hwstats *hwstats, + struct net_device *dev, + unsigned long event, void *ptr) +{ + struct netdev_notifier_offload_xstats_info *info; + struct nsim_dev_hwstats_netdev *hwsdev; + struct list_head *hwsdev_list; + int err = 0; + + info = ptr; + hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, info->type); + if (!hwsdev_list) + return 0; + + mutex_lock(&hwstats->hwsdev_list_lock); + + hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, dev->ifindex); + if (!hwsdev) + goto out; + + switch (event) { + case NETDEV_OFFLOAD_XSTATS_ENABLE: + err = nsim_dev_hwsdev_enable(hwsdev, info->info.extack); + break; + case NETDEV_OFFLOAD_XSTATS_DISABLE: + nsim_dev_hwsdev_disable(hwsdev); + break; + case NETDEV_OFFLOAD_XSTATS_REPORT_USED: + nsim_dev_hwsdev_report_used(hwsdev, info); + break; + case NETDEV_OFFLOAD_XSTATS_REPORT_DELTA: + err = nsim_dev_hwsdev_report_delta(hwsdev, info); + break; + } + +out: + mutex_unlock(&hwstats->hwsdev_list_lock); + return err; +} + +static void nsim_dev_hwsdev_fini(struct nsim_dev_hwstats_netdev *hwsdev) +{ + dev_put(hwsdev->netdev); + kfree(hwsdev); +} + +static void +__nsim_dev_hwstats_event_unregister(struct nsim_dev_hwstats *hwstats, + struct net_device *dev, + enum netdev_offload_xstats_type type) +{ + struct nsim_dev_hwstats_netdev *hwsdev; + struct list_head *hwsdev_list; + + hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, type); + if (WARN_ON(!hwsdev_list)) + return; + + hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, dev->ifindex); + if (!hwsdev) + return; + + list_del(&hwsdev->list); + nsim_dev_hwsdev_fini(hwsdev); +} + +static void nsim_dev_hwstats_event_unregister(struct nsim_dev_hwstats *hwstats, + struct net_device *dev) +{ + mutex_lock(&hwstats->hwsdev_list_lock); + __nsim_dev_hwstats_event_unregister(hwstats, dev, + NETDEV_OFFLOAD_XSTATS_TYPE_L3); + mutex_unlock(&hwstats->hwsdev_list_lock); +} + +static int nsim_dev_hwstats_event(struct nsim_dev_hwstats *hwstats, + struct net_device *dev, + unsigned long event, void *ptr) +{ + switch (event) { + case NETDEV_OFFLOAD_XSTATS_ENABLE: + case NETDEV_OFFLOAD_XSTATS_DISABLE: + case NETDEV_OFFLOAD_XSTATS_REPORT_USED: + case NETDEV_OFFLOAD_XSTATS_REPORT_DELTA: + return nsim_dev_hwstats_event_off_xstats(hwstats, dev, + event, ptr); + case NETDEV_UNREGISTER: + nsim_dev_hwstats_event_unregister(hwstats, dev); + break; + } + + return 0; +} + +static int nsim_dev_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct nsim_dev_hwstats *hwstats; + int err = 0; + + hwstats = container_of(nb, struct nsim_dev_hwstats, netdevice_nb); + err = nsim_dev_hwstats_event(hwstats, dev, event, ptr); + if (err) + return notifier_from_errno(err); + + return NOTIFY_OK; +} + +static int +nsim_dev_hwstats_enable_ifindex(struct nsim_dev_hwstats *hwstats, + int ifindex, + enum netdev_offload_xstats_type type, + struct list_head *hwsdev_list) +{ + struct nsim_dev_hwstats_netdev *hwsdev; + struct nsim_dev *nsim_dev; + struct net_device *netdev; + bool notify = false; + struct net *net; + int err = 0; + + nsim_dev = container_of(hwstats, struct nsim_dev, hwstats); + net = nsim_dev_net(nsim_dev); + + rtnl_lock(); + mutex_lock(&hwstats->hwsdev_list_lock); + hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, ifindex); + if (hwsdev) + goto out_unlock_list; + + netdev = dev_get_by_index(net, ifindex); + if (!netdev) { + err = -ENODEV; + goto out_unlock_list; + } + + hwsdev = kzalloc(sizeof(*hwsdev), GFP_KERNEL); + if (!hwsdev) { + err = -ENOMEM; + goto out_put_netdev; + } + + hwsdev->netdev = netdev; + list_add_tail(&hwsdev->list, hwsdev_list); + mutex_unlock(&hwstats->hwsdev_list_lock); + + if (netdev_offload_xstats_enabled(netdev, type)) { + nsim_dev_hwsdev_enable(hwsdev, NULL); + notify = true; + } + + if (notify) + rtnl_offload_xstats_notify(netdev); + rtnl_unlock(); + return err; + +out_put_netdev: + dev_put(netdev); +out_unlock_list: + mutex_unlock(&hwstats->hwsdev_list_lock); + rtnl_unlock(); + return err; +} + +static int +nsim_dev_hwstats_disable_ifindex(struct nsim_dev_hwstats *hwstats, + int ifindex, + enum netdev_offload_xstats_type type, + struct list_head *hwsdev_list) +{ + struct nsim_dev_hwstats_netdev *hwsdev; + int err = 0; + + rtnl_lock(); + mutex_lock(&hwstats->hwsdev_list_lock); + hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, ifindex); + if (hwsdev) + list_del(&hwsdev->list); + mutex_unlock(&hwstats->hwsdev_list_lock); + + if (!hwsdev) { + err = -ENOENT; + goto unlock_out; + } + + if (netdev_offload_xstats_enabled(hwsdev->netdev, type)) { + netdev_offload_xstats_push_delta(hwsdev->netdev, type, + &hwsdev->stats); + rtnl_offload_xstats_notify(hwsdev->netdev); + } + nsim_dev_hwsdev_fini(hwsdev); + +unlock_out: + rtnl_unlock(); + return err; +} + +static int +nsim_dev_hwstats_fail_ifindex(struct nsim_dev_hwstats *hwstats, + int ifindex, + enum netdev_offload_xstats_type type, + struct list_head *hwsdev_list) +{ + struct nsim_dev_hwstats_netdev *hwsdev; + int err = 0; + + mutex_lock(&hwstats->hwsdev_list_lock); + + hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, ifindex); + if (!hwsdev) { + err = -ENOENT; + goto err_hwsdev_list_unlock; + } + + hwsdev->fail_enable = true; + +err_hwsdev_list_unlock: + mutex_unlock(&hwstats->hwsdev_list_lock); + return err; +} + +enum nsim_dev_hwstats_do { + NSIM_DEV_HWSTATS_DO_DISABLE, + NSIM_DEV_HWSTATS_DO_ENABLE, + NSIM_DEV_HWSTATS_DO_FAIL, +}; + +struct nsim_dev_hwstats_fops { + const struct file_operations fops; + enum nsim_dev_hwstats_do action; + enum netdev_offload_xstats_type type; +}; + +static ssize_t +nsim_dev_hwstats_do_write(struct file *file, + const char __user *data, + size_t count, loff_t *ppos) +{ + struct nsim_dev_hwstats *hwstats = file->private_data; + struct nsim_dev_hwstats_fops *hwsfops; + struct list_head *hwsdev_list; + int ifindex; + int err; + + hwsfops = container_of(debugfs_real_fops(file), + struct nsim_dev_hwstats_fops, fops); + + err = kstrtoint_from_user(data, count, 0, &ifindex); + if (err) + return err; + + hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, hwsfops->type); + if (WARN_ON(!hwsdev_list)) + return -EINVAL; + + switch (hwsfops->action) { + case NSIM_DEV_HWSTATS_DO_DISABLE: + err = nsim_dev_hwstats_disable_ifindex(hwstats, ifindex, + hwsfops->type, + hwsdev_list); + break; + case NSIM_DEV_HWSTATS_DO_ENABLE: + err = nsim_dev_hwstats_enable_ifindex(hwstats, ifindex, + hwsfops->type, + hwsdev_list); + break; + case NSIM_DEV_HWSTATS_DO_FAIL: + err = nsim_dev_hwstats_fail_ifindex(hwstats, ifindex, + hwsfops->type, + hwsdev_list); + break; + } + if (err) + return err; + + return count; +} + +#define NSIM_DEV_HWSTATS_FOPS(ACTION, TYPE) \ + { \ + .fops = { \ + .open = simple_open, \ + .write = nsim_dev_hwstats_do_write, \ + .llseek = generic_file_llseek, \ + .owner = THIS_MODULE, \ + }, \ + .action = ACTION, \ + .type = TYPE, \ + } + +static const struct nsim_dev_hwstats_fops nsim_dev_hwstats_l3_disable_fops = + NSIM_DEV_HWSTATS_FOPS(NSIM_DEV_HWSTATS_DO_DISABLE, + NETDEV_OFFLOAD_XSTATS_TYPE_L3); + +static const struct nsim_dev_hwstats_fops nsim_dev_hwstats_l3_enable_fops = + NSIM_DEV_HWSTATS_FOPS(NSIM_DEV_HWSTATS_DO_ENABLE, + NETDEV_OFFLOAD_XSTATS_TYPE_L3); + +static const struct nsim_dev_hwstats_fops nsim_dev_hwstats_l3_fail_fops = + NSIM_DEV_HWSTATS_FOPS(NSIM_DEV_HWSTATS_DO_FAIL, + NETDEV_OFFLOAD_XSTATS_TYPE_L3); + +#undef NSIM_DEV_HWSTATS_FOPS + +int nsim_dev_hwstats_init(struct nsim_dev *nsim_dev) +{ + struct nsim_dev_hwstats *hwstats = &nsim_dev->hwstats; + struct net *net = nsim_dev_net(nsim_dev); + int err; + + mutex_init(&hwstats->hwsdev_list_lock); + INIT_LIST_HEAD(&hwstats->l3_list); + + hwstats->netdevice_nb.notifier_call = nsim_dev_netdevice_event; + err = register_netdevice_notifier_net(net, &hwstats->netdevice_nb); + if (err) + goto err_mutex_destroy; + + hwstats->ddir = debugfs_create_dir("hwstats", nsim_dev->ddir); + if (IS_ERR(hwstats->ddir)) { + err = PTR_ERR(hwstats->ddir); + goto err_unregister_notifier; + } + + hwstats->l3_ddir = debugfs_create_dir("l3", hwstats->ddir); + if (IS_ERR(hwstats->l3_ddir)) { + err = PTR_ERR(hwstats->l3_ddir); + goto err_remove_hwstats_recursive; + } + + debugfs_create_file("enable_ifindex", 0200, hwstats->l3_ddir, hwstats, + &nsim_dev_hwstats_l3_enable_fops.fops); + debugfs_create_file("disable_ifindex", 0200, hwstats->l3_ddir, hwstats, + &nsim_dev_hwstats_l3_disable_fops.fops); + debugfs_create_file("fail_next_enable", 0200, hwstats->l3_ddir, hwstats, + &nsim_dev_hwstats_l3_fail_fops.fops); + + INIT_DELAYED_WORK(&hwstats->traffic_dw, + &nsim_dev_hwstats_traffic_work); + schedule_delayed_work(&hwstats->traffic_dw, + msecs_to_jiffies(NSIM_DEV_HWSTATS_TRAFFIC_MS)); + return 0; + +err_remove_hwstats_recursive: + debugfs_remove_recursive(hwstats->ddir); +err_unregister_notifier: + unregister_netdevice_notifier_net(net, &hwstats->netdevice_nb); +err_mutex_destroy: + mutex_destroy(&hwstats->hwsdev_list_lock); + return err; +} + +static void nsim_dev_hwsdev_list_wipe(struct nsim_dev_hwstats *hwstats, + enum netdev_offload_xstats_type type) +{ + struct nsim_dev_hwstats_netdev *hwsdev, *tmp; + struct list_head *hwsdev_list; + + hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, type); + if (WARN_ON(!hwsdev_list)) + return; + + mutex_lock(&hwstats->hwsdev_list_lock); + list_for_each_entry_safe(hwsdev, tmp, hwsdev_list, list) { + list_del(&hwsdev->list); + nsim_dev_hwsdev_fini(hwsdev); + } + mutex_unlock(&hwstats->hwsdev_list_lock); +} + +void nsim_dev_hwstats_exit(struct nsim_dev *nsim_dev) +{ + struct nsim_dev_hwstats *hwstats = &nsim_dev->hwstats; + struct net *net = nsim_dev_net(nsim_dev); + + cancel_delayed_work_sync(&hwstats->traffic_dw); + debugfs_remove_recursive(hwstats->ddir); + unregister_netdevice_notifier_net(net, &hwstats->netdevice_nb); + nsim_dev_hwsdev_list_wipe(hwstats, NETDEV_OFFLOAD_XSTATS_TYPE_L3); + mutex_destroy(&hwstats->hwsdev_list_lock); +} diff --git a/drivers/net/netdevsim/ipsec.c b/drivers/net/netdevsim/ipsec.c index e27fc1a4516d..386336a38f34 100644 --- a/drivers/net/netdevsim/ipsec.c +++ b/drivers/net/netdevsim/ipsec.c @@ -29,9 +29,9 @@ static ssize_t nsim_dbg_netdev_ops_read(struct file *filp, return -ENOMEM; p = buf; - p += snprintf(p, bufsize - (p - buf), - "SA count=%u tx=%u\n", - ipsec->count, ipsec->tx); + p += scnprintf(p, bufsize - (p - buf), + "SA count=%u tx=%u\n", + ipsec->count, ipsec->tx); for (i = 0; i < NSIM_IPSEC_MAX_SA_COUNT; i++) { struct nsim_sa *sap = &ipsec->sa[i]; @@ -39,18 +39,18 @@ static ssize_t nsim_dbg_netdev_ops_read(struct file *filp, if (!sap->used) continue; - p += snprintf(p, bufsize - (p - buf), - "sa[%i] %cx ipaddr=0x%08x %08x %08x %08x\n", - i, (sap->rx ? 'r' : 't'), sap->ipaddr[0], - sap->ipaddr[1], sap->ipaddr[2], sap->ipaddr[3]); - p += snprintf(p, bufsize - (p - buf), - "sa[%i] spi=0x%08x proto=0x%x salt=0x%08x crypt=%d\n", - i, be32_to_cpu(sap->xs->id.spi), - sap->xs->id.proto, sap->salt, sap->crypt); - p += snprintf(p, bufsize - (p - buf), - "sa[%i] key=0x%08x %08x %08x %08x\n", - i, sap->key[0], sap->key[1], - sap->key[2], sap->key[3]); + p += scnprintf(p, bufsize - (p - buf), + "sa[%i] %cx ipaddr=0x%08x %08x %08x %08x\n", + i, (sap->rx ? 'r' : 't'), sap->ipaddr[0], + sap->ipaddr[1], sap->ipaddr[2], sap->ipaddr[3]); + p += scnprintf(p, bufsize - (p - buf), + "sa[%i] spi=0x%08x proto=0x%x salt=0x%08x crypt=%d\n", + i, be32_to_cpu(sap->xs->id.spi), + sap->xs->id.proto, sap->salt, sap->crypt); + p += scnprintf(p, bufsize - (p - buf), + "sa[%i] key=0x%08x %08x %08x %08x\n", + i, sap->key[0], sap->key[1], + sap->key[2], sap->key[3]); } len = simple_read_from_buffer(buffer, count, ppos, buf, p - buf); @@ -85,7 +85,7 @@ static int nsim_ipsec_parse_proto_keys(struct xfrm_state *xs, u32 *mykey, u32 *mysalt) { const char aes_gcm_name[] = "rfc4106(gcm(aes))"; - struct net_device *dev = xs->xso.dev; + struct net_device *dev = xs->xso.real_dev; unsigned char *key_data; char *alg_name = NULL; int key_len; @@ -134,7 +134,7 @@ static int nsim_ipsec_add_sa(struct xfrm_state *xs) u16 sa_idx; int ret; - dev = xs->xso.dev; + dev = xs->xso.real_dev; ns = netdev_priv(dev); ipsec = &ns->ipsec; @@ -171,7 +171,7 @@ static int nsim_ipsec_add_sa(struct xfrm_state *xs) return ret; } - if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) { + if (xs->xso.dir == XFRM_DEV_OFFLOAD_IN) { sa.rx = true; if (xs->props.family == AF_INET6) @@ -194,7 +194,7 @@ static int nsim_ipsec_add_sa(struct xfrm_state *xs) static void nsim_ipsec_del_sa(struct xfrm_state *xs) { - struct netdevsim *ns = netdev_priv(xs->xso.dev); + struct netdevsim *ns = netdev_priv(xs->xso.real_dev); struct nsim_ipsec *ipsec = &ns->ipsec; u16 sa_idx; @@ -211,7 +211,7 @@ static void nsim_ipsec_del_sa(struct xfrm_state *xs) static bool nsim_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) { - struct netdevsim *ns = netdev_priv(xs->xso.dev); + struct netdevsim *ns = netdev_priv(xs->xso.real_dev); struct nsim_ipsec *ipsec = &ns->ipsec; ipsec->ok++; diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 2908e0a0d6e1..9a1a5b203624 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -22,6 +22,7 @@ #include <net/netlink.h> #include <net/pkt_cls.h> #include <net/rtnetlink.h> +#include <net/udp_tunnel.h> #include "netdevsim.h" @@ -66,10 +67,10 @@ nsim_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) unsigned int start; do { - start = u64_stats_fetch_begin(&ns->syncp); + start = u64_stats_fetch_begin_irq(&ns->syncp); stats->tx_bytes = ns->tx_bytes; stats->tx_packets = ns->tx_packets; - } while (u64_stats_fetch_retry(&ns->syncp, start)); + } while (u64_stats_fetch_retry_irq(&ns->syncp, start)); } static int @@ -81,12 +82,12 @@ nsim_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv) static int nsim_set_vf_mac(struct net_device *dev, int vf, u8 *mac) { struct netdevsim *ns = netdev_priv(dev); - struct nsim_bus_dev *nsim_bus_dev = ns->nsim_bus_dev; + struct nsim_dev *nsim_dev = ns->nsim_dev; /* Only refuse multicast addresses, zero address can mean unset/any. */ - if (vf >= nsim_bus_dev->num_vfs || is_multicast_ether_addr(mac)) + if (vf >= nsim_dev_get_vfs(nsim_dev) || is_multicast_ether_addr(mac)) return -EINVAL; - memcpy(nsim_bus_dev->vfconfigs[vf].vf_mac, mac, ETH_ALEN); + memcpy(nsim_dev->vfconfigs[vf].vf_mac, mac, ETH_ALEN); return 0; } @@ -95,14 +96,14 @@ static int nsim_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos, __be16 vlan_proto) { struct netdevsim *ns = netdev_priv(dev); - struct nsim_bus_dev *nsim_bus_dev = ns->nsim_bus_dev; + struct nsim_dev *nsim_dev = ns->nsim_dev; - if (vf >= nsim_bus_dev->num_vfs || vlan > 4095 || qos > 7) + if (vf >= nsim_dev_get_vfs(nsim_dev) || vlan > 4095 || qos > 7) return -EINVAL; - nsim_bus_dev->vfconfigs[vf].vlan = vlan; - nsim_bus_dev->vfconfigs[vf].qos = qos; - nsim_bus_dev->vfconfigs[vf].vlan_proto = vlan_proto; + nsim_dev->vfconfigs[vf].vlan = vlan; + nsim_dev->vfconfigs[vf].qos = qos; + nsim_dev->vfconfigs[vf].vlan_proto = vlan_proto; return 0; } @@ -110,13 +111,18 @@ static int nsim_set_vf_vlan(struct net_device *dev, int vf, 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; + struct nsim_dev *nsim_dev = ns->nsim_dev; - if (vf >= nsim_bus_dev->num_vfs) + 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_dev_get_vfs(nsim_dev)) return -EINVAL; - nsim_bus_dev->vfconfigs[vf].min_tx_rate = min; - nsim_bus_dev->vfconfigs[vf].max_tx_rate = max; + nsim_dev->vfconfigs[vf].min_tx_rate = min; + nsim_dev->vfconfigs[vf].max_tx_rate = max; return 0; } @@ -124,11 +130,11 @@ static int nsim_set_vf_rate(struct net_device *dev, int vf, int min, int max) static int nsim_set_vf_spoofchk(struct net_device *dev, int vf, bool val) { struct netdevsim *ns = netdev_priv(dev); - struct nsim_bus_dev *nsim_bus_dev = ns->nsim_bus_dev; + struct nsim_dev *nsim_dev = ns->nsim_dev; - if (vf >= nsim_bus_dev->num_vfs) + if (vf >= nsim_dev_get_vfs(nsim_dev)) return -EINVAL; - nsim_bus_dev->vfconfigs[vf].spoofchk_enabled = val; + nsim_dev->vfconfigs[vf].spoofchk_enabled = val; return 0; } @@ -136,11 +142,11 @@ static int nsim_set_vf_spoofchk(struct net_device *dev, int vf, bool val) static int nsim_set_vf_rss_query_en(struct net_device *dev, int vf, bool val) { struct netdevsim *ns = netdev_priv(dev); - struct nsim_bus_dev *nsim_bus_dev = ns->nsim_bus_dev; + struct nsim_dev *nsim_dev = ns->nsim_dev; - if (vf >= nsim_bus_dev->num_vfs) + if (vf >= nsim_dev_get_vfs(nsim_dev)) return -EINVAL; - nsim_bus_dev->vfconfigs[vf].rss_query_enabled = val; + nsim_dev->vfconfigs[vf].rss_query_enabled = val; return 0; } @@ -148,11 +154,11 @@ static int nsim_set_vf_rss_query_en(struct net_device *dev, int vf, bool val) static int nsim_set_vf_trust(struct net_device *dev, int vf, bool val) { struct netdevsim *ns = netdev_priv(dev); - struct nsim_bus_dev *nsim_bus_dev = ns->nsim_bus_dev; + struct nsim_dev *nsim_dev = ns->nsim_dev; - if (vf >= nsim_bus_dev->num_vfs) + if (vf >= nsim_dev_get_vfs(nsim_dev)) return -EINVAL; - nsim_bus_dev->vfconfigs[vf].trusted = val; + nsim_dev->vfconfigs[vf].trusted = val; return 0; } @@ -161,22 +167,22 @@ static int nsim_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivi) { struct netdevsim *ns = netdev_priv(dev); - struct nsim_bus_dev *nsim_bus_dev = ns->nsim_bus_dev; + struct nsim_dev *nsim_dev = ns->nsim_dev; - if (vf >= nsim_bus_dev->num_vfs) + if (vf >= nsim_dev_get_vfs(nsim_dev)) return -EINVAL; ivi->vf = vf; - ivi->linkstate = nsim_bus_dev->vfconfigs[vf].link_state; - ivi->min_tx_rate = nsim_bus_dev->vfconfigs[vf].min_tx_rate; - ivi->max_tx_rate = nsim_bus_dev->vfconfigs[vf].max_tx_rate; - ivi->vlan = nsim_bus_dev->vfconfigs[vf].vlan; - ivi->vlan_proto = nsim_bus_dev->vfconfigs[vf].vlan_proto; - ivi->qos = nsim_bus_dev->vfconfigs[vf].qos; - memcpy(&ivi->mac, nsim_bus_dev->vfconfigs[vf].vf_mac, ETH_ALEN); - ivi->spoofchk = nsim_bus_dev->vfconfigs[vf].spoofchk_enabled; - ivi->trusted = nsim_bus_dev->vfconfigs[vf].trusted; - ivi->rss_query_en = nsim_bus_dev->vfconfigs[vf].rss_query_enabled; + ivi->linkstate = nsim_dev->vfconfigs[vf].link_state; + ivi->min_tx_rate = nsim_dev->vfconfigs[vf].min_tx_rate; + ivi->max_tx_rate = nsim_dev->vfconfigs[vf].max_tx_rate; + ivi->vlan = nsim_dev->vfconfigs[vf].vlan; + ivi->vlan_proto = nsim_dev->vfconfigs[vf].vlan_proto; + ivi->qos = nsim_dev->vfconfigs[vf].qos; + memcpy(&ivi->mac, nsim_dev->vfconfigs[vf].vf_mac, ETH_ALEN); + ivi->spoofchk = nsim_dev->vfconfigs[vf].spoofchk_enabled; + ivi->trusted = nsim_dev->vfconfigs[vf].trusted; + ivi->rss_query_en = nsim_dev->vfconfigs[vf].rss_query_enabled; return 0; } @@ -184,9 +190,9 @@ nsim_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivi) static int nsim_set_vf_link_state(struct net_device *dev, int vf, int state) { struct netdevsim *ns = netdev_priv(dev); - struct nsim_bus_dev *nsim_bus_dev = ns->nsim_bus_dev; + struct nsim_dev *nsim_dev = ns->nsim_dev; - if (vf >= nsim_bus_dev->num_vfs) + if (vf >= nsim_dev_get_vfs(nsim_dev)) return -EINVAL; switch (state) { @@ -198,7 +204,7 @@ static int nsim_set_vf_link_state(struct net_device *dev, int vf, int state) return -EINVAL; } - nsim_bus_dev->vfconfigs[vf].link_state = state; + nsim_dev->vfconfigs[vf].link_state = state; return 0; } @@ -260,6 +266,18 @@ static const struct net_device_ops nsim_netdev_ops = { .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); @@ -279,6 +297,49 @@ 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) { @@ -286,37 +347,28 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port) struct netdevsim *ns; int err; - dev = alloc_netdev(sizeof(*ns), "eth%d", NET_NAME_UNKNOWN, nsim_setup); + dev = alloc_netdev_mq(sizeof(*ns), "eth%d", NET_NAME_UNKNOWN, nsim_setup, + nsim_dev->nsim_bus_dev->num_queues); if (!dev) return ERR_PTR(-ENOMEM); dev_net_set(dev, nsim_dev_net(nsim_dev)); ns = netdev_priv(dev); ns->netdev = dev; + u64_stats_init(&ns->syncp); ns->nsim_dev = nsim_dev; 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; - - rtnl_lock(); - err = nsim_bpf_init(ns); + nsim_ethtool_init(ns); + 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; - - 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); - rtnl_unlock(); err_free_netdev: free_netdev(dev); return ERR_PTR(err); @@ -328,16 +380,21 @@ 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(); + if (nsim_dev_port_is_pf(ns->nsim_dev_port)) + nsim_udp_tunnels_info_destroy(dev); free_netdev(dev); } static int nsim_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { - NL_SET_ERR_MSG_MOD(extack, "Please use: echo \"[ID] [PORT_COUNT]\" > /sys/bus/netdevsim/new_device"); + NL_SET_ERR_MSG_MOD(extack, + "Please use: echo \"[ID] [PORT_COUNT] [NUM_QUEUES]\" > /sys/bus/netdevsim/new_device"); return -EOPNOTSUPP; } diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 2eb7b0dc1594..7d8ed8d8df5c 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -13,12 +13,15 @@ * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. */ +#include <linux/debugfs.h> #include <linux/device.h> +#include <linux/ethtool.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/netdevice.h> #include <linux/u64_stats_sync.h> #include <net/devlink.h> +#include <net/udp_tunnel.h> #include <net/xdp.h> #define DRV_NAME "netdevsim" @@ -29,6 +32,7 @@ #define NSIM_IPSEC_MAX_SA_COUNT 33 #define NSIM_IPSEC_VALID BIT(31) +#define NSIM_UDP_TUNNEL_N_PORTS 4 struct nsim_sa { struct xfrm_state *xs; @@ -48,6 +52,23 @@ struct nsim_ipsec { u32 ok; }; +struct nsim_ethtool_pauseparam { + bool rx; + bool tx; + bool report_stats_rx; + bool report_stats_tx; +}; + +struct nsim_ethtool { + u32 get_err; + u32 set_err; + u32 channels; + struct nsim_ethtool_pauseparam pauseparam; + struct ethtool_coalesce coalesce; + struct ethtool_ringparam ring; + struct ethtool_fecparam fec; +}; + struct netdevsim { struct net_device *netdev; struct nsim_dev *nsim_dev; @@ -72,12 +93,28 @@ struct netdevsim { bool bpf_map_accept; struct nsim_ipsec ipsec; + struct { + u32 inject_error; + u32 sleep; + u32 __ports[2][NSIM_UDP_TUNNEL_N_PORTS]; + u32 (*ports)[NSIM_UDP_TUNNEL_N_PORTS]; + struct debugfs_u32_array dfs_ports[2]; + } udp_ports; + + struct nsim_ethtool ethtool; }; struct netdevsim * nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port); void nsim_destroy(struct netdevsim *ns); +void nsim_ethtool_init(struct netdevsim *ns); + +void nsim_udp_tunnels_debugfs_create(struct nsim_dev *nsim_dev); +int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev, + struct net_device *dev); +void nsim_udp_tunnels_info_destroy(struct net_device *dev); + #ifdef CONFIG_BPF_SYSCALL int nsim_bpf_dev_init(struct nsim_dev *nsim_dev); void nsim_bpf_dev_exit(struct nsim_dev *nsim_dev); @@ -108,7 +145,7 @@ static inline void nsim_bpf_uninit(struct netdevsim *ns) static inline int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf) { - return bpf->command == XDP_QUERY_PROG ? 0 : -EOPNOTSUPP; + return -EOPNOTSUPP; } static inline int nsim_bpf_disable_tc(struct netdevsim *ns) @@ -132,6 +169,7 @@ enum nsim_resource_id { NSIM_RESOURCE_IPV6, NSIM_RESOURCE_IPV6_FIB, NSIM_RESOURCE_IPV6_FIB_RULES, + NSIM_RESOURCE_NEXTHOPS, }; struct nsim_dev_health { @@ -146,14 +184,74 @@ struct nsim_dev_health { int nsim_dev_health_init(struct nsim_dev *nsim_dev, struct devlink *devlink); void nsim_dev_health_exit(struct nsim_dev *nsim_dev); +struct nsim_dev_hwstats_netdev { + struct list_head list; + struct net_device *netdev; + struct rtnl_hw_stats64 stats; + bool enabled; + bool fail_enable; +}; + +struct nsim_dev_hwstats { + struct dentry *ddir; + struct dentry *l3_ddir; + + struct mutex hwsdev_list_lock; /* protects hwsdev list(s) */ + struct list_head l3_list; + + struct notifier_block netdevice_nb; + struct delayed_work traffic_dw; +}; + +int nsim_dev_hwstats_init(struct nsim_dev *nsim_dev); +void nsim_dev_hwstats_exit(struct nsim_dev *nsim_dev); + +#if IS_ENABLED(CONFIG_PSAMPLE) +int nsim_dev_psample_init(struct nsim_dev *nsim_dev); +void nsim_dev_psample_exit(struct nsim_dev *nsim_dev); +#else +static inline int nsim_dev_psample_init(struct nsim_dev *nsim_dev) +{ + return 0; +} + +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 dentry *rate_parent; + char *parent_name; struct netdevsim *ns; }; +struct nsim_vf_config { + int link_state; + u16 min_tx_rate; + u16 max_tx_rate; + u16 vlan; + __be16 vlan_proto; + u16 qos; + u8 vf_mac[ETH_ALEN]; + bool spoofchk_enabled; + bool trusted; + bool rss_query_enabled; +}; + struct nsim_dev { struct nsim_bus_dev *nsim_bus_dev; struct nsim_fib_data *fib_data; @@ -161,8 +259,13 @@ struct nsim_dev { struct dentry *ddir; struct dentry *ports_ddir; struct dentry *take_snapshot; + struct dentry *nodes_ddir; + + struct nsim_vf_config *vfconfigs; + struct bpf_offload_dev *bpf_dev; bool bpf_bind_accept; + bool bpf_bind_verifier_accept; u32 bpf_bind_verifier_delay; struct dentry *ddir_bpf_bound_progs; u32 prog_id_gen; @@ -170,16 +273,45 @@ struct nsim_dev { struct list_head bpf_bound_maps; struct netdev_phys_item_id switch_id; struct list_head port_list; - struct mutex port_list_lock; /* protects port list */ bool fw_update_status; + u32 fw_update_overwrite_mask; u32 max_macs; bool test1; bool dont_allow_reload; bool fail_reload; struct devlink_region *dummy_region; struct nsim_dev_health health; + struct nsim_dev_hwstats hwstats; + struct flow_action_cookie *fa_cookie; + spinlock_t fa_cookie_lock; /* protects fa_cookie */ + bool fail_trap_group_set; + bool fail_trap_policer_set; + bool fail_trap_policer_counter_get; + bool fail_trap_drop_counter_get; + struct { + struct udp_tunnel_nic_shared utn_shared; + u32 __ports[2][NSIM_UDP_TUNNEL_N_PORTS]; + bool sync_all; + bool open_only; + bool ipv4_only; + bool shared; + bool static_iana_vxlan; + u32 sleep; + } udp_ports; + struct nsim_dev_psample *psample; + u16 esw_mode; }; +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)); @@ -187,12 +319,18 @@ static inline struct net *nsim_dev_net(struct nsim_dev *nsim_dev) int nsim_dev_init(void); void nsim_dev_exit(void); -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, +int nsim_drv_probe(struct nsim_bus_dev *nsim_bus_dev); +void nsim_drv_remove(struct nsim_bus_dev *nsim_bus_dev); +int nsim_drv_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, +int nsim_drv_port_del(struct nsim_bus_dev *nsim_bus_dev, + enum nsim_dev_port_type type, unsigned int port_index); +int nsim_drv_configure_vfs(struct nsim_bus_dev *nsim_bus_dev, + unsigned int num_vfs); + +unsigned int nsim_dev_get_vfs(struct nsim_dev *nsim_dev); struct nsim_fib_data *nsim_fib_create(struct devlink *devlink, struct netlink_ext_ack *extack); @@ -200,6 +338,15 @@ void nsim_fib_destroy(struct devlink *devlink, struct nsim_fib_data *fib_data); u64 nsim_fib_get_val(struct nsim_fib_data *fib_data, enum nsim_resource_id res_id, bool max); +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); @@ -219,30 +366,16 @@ static inline bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb) } #endif -struct nsim_vf_config { - int link_state; - u16 min_tx_rate; - u16 max_tx_rate; - u16 vlan; - __be16 vlan_proto; - u16 qos; - u8 vf_mac[ETH_ALEN]; - bool spoofchk_enabled; - bool trusted; - bool rss_query_enabled; -}; - struct nsim_bus_dev { struct device dev; struct list_head list; unsigned int port_count; + unsigned int num_queues; /* Number of queues for each port on this bus */ 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 nsim_vf_config *vfconfigs; - /* Lock for devlink->reload_enabled in netdevsim module */ - struct mutex nsim_bus_reload_lock; bool init; }; diff --git a/drivers/net/netdevsim/psample.c b/drivers/net/netdevsim/psample.c new file mode 100644 index 000000000000..f0c6477dd0ae --- /dev/null +++ b/drivers/net/netdevsim/psample.c @@ -0,0 +1,265 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Mellanox Technologies. All rights reserved */ + +#include <linux/debugfs.h> +#include <linux/err.h> +#include <linux/etherdevice.h> +#include <linux/inet.h> +#include <linux/kernel.h> +#include <linux/random.h> +#include <linux/slab.h> +#include <net/devlink.h> +#include <net/ip.h> +#include <net/psample.h> +#include <uapi/linux/ip.h> +#include <uapi/linux/udp.h> + +#include "netdevsim.h" + +#define NSIM_PSAMPLE_REPORT_INTERVAL_MS 100 +#define NSIM_PSAMPLE_INVALID_TC 0xFFFF +#define NSIM_PSAMPLE_L4_DATA_LEN 100 + +struct nsim_dev_psample { + struct delayed_work psample_dw; + struct dentry *ddir; + struct psample_group *group; + u32 rate; + u32 group_num; + u32 trunc_size; + int in_ifindex; + int out_ifindex; + u16 out_tc; + u64 out_tc_occ_max; + u64 latency_max; + bool is_active; +}; + +static struct sk_buff *nsim_dev_psample_skb_build(void) +{ + int tot_len, data_len = NSIM_PSAMPLE_L4_DATA_LEN; + struct sk_buff *skb; + struct udphdr *udph; + struct ethhdr *eth; + struct iphdr *iph; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return NULL; + tot_len = sizeof(struct iphdr) + sizeof(struct udphdr) + data_len; + + skb_reset_mac_header(skb); + eth = skb_put(skb, sizeof(struct ethhdr)); + eth_random_addr(eth->h_dest); + eth_random_addr(eth->h_source); + eth->h_proto = htons(ETH_P_IP); + skb->protocol = htons(ETH_P_IP); + + skb_set_network_header(skb, skb->len); + iph = skb_put(skb, sizeof(struct iphdr)); + iph->protocol = IPPROTO_UDP; + iph->saddr = in_aton("192.0.2.1"); + iph->daddr = in_aton("198.51.100.1"); + iph->version = 0x4; + iph->frag_off = 0; + iph->ihl = 0x5; + iph->tot_len = htons(tot_len); + iph->id = 0; + iph->ttl = 100; + iph->check = 0; + iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); + + skb_set_transport_header(skb, skb->len); + udph = skb_put_zero(skb, sizeof(struct udphdr) + data_len); + get_random_bytes(&udph->source, sizeof(u16)); + get_random_bytes(&udph->dest, sizeof(u16)); + udph->len = htons(sizeof(struct udphdr) + data_len); + + return skb; +} + +static void nsim_dev_psample_md_prepare(const struct nsim_dev_psample *psample, + struct psample_metadata *md, + unsigned int len) +{ + md->trunc_size = psample->trunc_size ? psample->trunc_size : len; + md->in_ifindex = psample->in_ifindex; + md->out_ifindex = psample->out_ifindex; + + if (psample->out_tc != NSIM_PSAMPLE_INVALID_TC) { + md->out_tc = psample->out_tc; + md->out_tc_valid = 1; + } + + if (psample->out_tc_occ_max) { + u64 out_tc_occ; + + get_random_bytes(&out_tc_occ, sizeof(u64)); + md->out_tc_occ = out_tc_occ & (psample->out_tc_occ_max - 1); + md->out_tc_occ_valid = 1; + } + + if (psample->latency_max) { + u64 latency; + + get_random_bytes(&latency, sizeof(u64)); + md->latency = latency & (psample->latency_max - 1); + md->latency_valid = 1; + } +} + +static void nsim_dev_psample_report_work(struct work_struct *work) +{ + struct nsim_dev_psample *psample; + struct psample_metadata md = {}; + struct sk_buff *skb; + unsigned long delay; + + psample = container_of(work, struct nsim_dev_psample, psample_dw.work); + + skb = nsim_dev_psample_skb_build(); + if (!skb) + goto out; + + nsim_dev_psample_md_prepare(psample, &md, skb->len); + psample_sample_packet(psample->group, skb, psample->rate, &md); + consume_skb(skb); + +out: + delay = msecs_to_jiffies(NSIM_PSAMPLE_REPORT_INTERVAL_MS); + schedule_delayed_work(&psample->psample_dw, delay); +} + +static int nsim_dev_psample_enable(struct nsim_dev *nsim_dev) +{ + struct nsim_dev_psample *psample = nsim_dev->psample; + struct devlink *devlink; + unsigned long delay; + + if (psample->is_active) + return -EBUSY; + + devlink = priv_to_devlink(nsim_dev); + psample->group = psample_group_get(devlink_net(devlink), + psample->group_num); + if (!psample->group) + return -EINVAL; + + delay = msecs_to_jiffies(NSIM_PSAMPLE_REPORT_INTERVAL_MS); + schedule_delayed_work(&psample->psample_dw, delay); + + psample->is_active = true; + + return 0; +} + +static int nsim_dev_psample_disable(struct nsim_dev *nsim_dev) +{ + struct nsim_dev_psample *psample = nsim_dev->psample; + + if (!psample->is_active) + return -EINVAL; + + psample->is_active = false; + + cancel_delayed_work_sync(&psample->psample_dw); + psample_group_put(psample->group); + + return 0; +} + +static ssize_t nsim_dev_psample_enable_write(struct file *file, + const char __user *data, + size_t count, loff_t *ppos) +{ + struct nsim_dev *nsim_dev = file->private_data; + bool enable; + int err; + + err = kstrtobool_from_user(data, count, &enable); + if (err) + return err; + + if (enable) + err = nsim_dev_psample_enable(nsim_dev); + else + err = nsim_dev_psample_disable(nsim_dev); + + return err ? err : count; +} + +static const struct file_operations nsim_psample_enable_fops = { + .open = simple_open, + .write = nsim_dev_psample_enable_write, + .llseek = generic_file_llseek, + .owner = THIS_MODULE, +}; + +int nsim_dev_psample_init(struct nsim_dev *nsim_dev) +{ + struct nsim_dev_psample *psample; + int err; + + psample = kzalloc(sizeof(*psample), GFP_KERNEL); + if (!psample) + return -ENOMEM; + nsim_dev->psample = psample; + + INIT_DELAYED_WORK(&psample->psample_dw, nsim_dev_psample_report_work); + + psample->ddir = debugfs_create_dir("psample", nsim_dev->ddir); + if (IS_ERR(psample->ddir)) { + err = PTR_ERR(psample->ddir); + goto err_psample_free; + } + + /* Populate sampling parameters with sane defaults. */ + psample->rate = 100; + debugfs_create_u32("rate", 0600, psample->ddir, &psample->rate); + + psample->group_num = 10; + debugfs_create_u32("group_num", 0600, psample->ddir, + &psample->group_num); + + psample->trunc_size = 0; + debugfs_create_u32("trunc_size", 0600, psample->ddir, + &psample->trunc_size); + + psample->in_ifindex = 1; + debugfs_create_u32("in_ifindex", 0600, psample->ddir, + &psample->in_ifindex); + + psample->out_ifindex = 2; + debugfs_create_u32("out_ifindex", 0600, psample->ddir, + &psample->out_ifindex); + + psample->out_tc = 0; + debugfs_create_u16("out_tc", 0600, psample->ddir, &psample->out_tc); + + psample->out_tc_occ_max = 10000; + debugfs_create_u64("out_tc_occ_max", 0600, psample->ddir, + &psample->out_tc_occ_max); + + psample->latency_max = 50; + debugfs_create_u64("latency_max", 0600, psample->ddir, + &psample->latency_max); + + debugfs_create_file("enable", 0200, psample->ddir, nsim_dev, + &nsim_psample_enable_fops); + + return 0; + +err_psample_free: + kfree(nsim_dev->psample); + return err; +} + +void nsim_dev_psample_exit(struct nsim_dev *nsim_dev) +{ + debugfs_remove_recursive(nsim_dev->psample->ddir); + if (nsim_dev->psample->is_active) { + cancel_delayed_work_sync(&nsim_dev->psample->psample_dw); + psample_group_put(nsim_dev->psample->group); + } + kfree(nsim_dev->psample); +} diff --git a/drivers/net/netdevsim/udp_tunnels.c b/drivers/net/netdevsim/udp_tunnels.c new file mode 100644 index 000000000000..02dc3123eb6c --- /dev/null +++ b/drivers/net/netdevsim/udp_tunnels.c @@ -0,0 +1,217 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (c) 2020 Facebook Inc. + +#include <linux/debugfs.h> +#include <linux/netdevice.h> +#include <linux/slab.h> +#include <net/udp_tunnel.h> + +#include "netdevsim.h" + +static int +nsim_udp_tunnel_set_port(struct net_device *dev, unsigned int table, + unsigned int entry, struct udp_tunnel_info *ti) +{ + struct netdevsim *ns = netdev_priv(dev); + int ret; + + ret = -ns->udp_ports.inject_error; + ns->udp_ports.inject_error = 0; + + if (ns->udp_ports.sleep) + msleep(ns->udp_ports.sleep); + + if (!ret) { + if (ns->udp_ports.ports[table][entry]) { + WARN(1, "entry already in use\n"); + ret = -EBUSY; + } else { + ns->udp_ports.ports[table][entry] = + be16_to_cpu(ti->port) << 16 | ti->type; + } + } + + netdev_info(dev, "set [%d, %d] type %d family %d port %d - %d\n", + table, entry, ti->type, ti->sa_family, ntohs(ti->port), + ret); + return ret; +} + +static int +nsim_udp_tunnel_unset_port(struct net_device *dev, unsigned int table, + unsigned int entry, struct udp_tunnel_info *ti) +{ + struct netdevsim *ns = netdev_priv(dev); + int ret; + + ret = -ns->udp_ports.inject_error; + ns->udp_ports.inject_error = 0; + + if (ns->udp_ports.sleep) + msleep(ns->udp_ports.sleep); + if (!ret) { + u32 val = be16_to_cpu(ti->port) << 16 | ti->type; + + if (val == ns->udp_ports.ports[table][entry]) { + ns->udp_ports.ports[table][entry] = 0; + } else { + WARN(1, "entry not installed %x vs %x\n", + val, ns->udp_ports.ports[table][entry]); + ret = -ENOENT; + } + } + + netdev_info(dev, "unset [%d, %d] type %d family %d port %d - %d\n", + table, entry, ti->type, ti->sa_family, ntohs(ti->port), + ret); + return ret; +} + +static int +nsim_udp_tunnel_sync_table(struct net_device *dev, unsigned int table) +{ + struct netdevsim *ns = netdev_priv(dev); + struct udp_tunnel_info ti; + unsigned int i; + int ret; + + ret = -ns->udp_ports.inject_error; + ns->udp_ports.inject_error = 0; + + for (i = 0; i < NSIM_UDP_TUNNEL_N_PORTS; i++) { + udp_tunnel_nic_get_port(dev, table, i, &ti); + ns->udp_ports.ports[table][i] = + be16_to_cpu(ti.port) << 16 | ti.type; + } + + return ret; +} + +static const struct udp_tunnel_nic_info nsim_udp_tunnel_info = { + .set_port = nsim_udp_tunnel_set_port, + .unset_port = nsim_udp_tunnel_unset_port, + .sync_table = nsim_udp_tunnel_sync_table, + + .tables = { + { + .n_entries = NSIM_UDP_TUNNEL_N_PORTS, + .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, + }, + { + .n_entries = NSIM_UDP_TUNNEL_N_PORTS, + .tunnel_types = UDP_TUNNEL_TYPE_GENEVE | + UDP_TUNNEL_TYPE_VXLAN_GPE, + }, + }, +}; + +static ssize_t +nsim_udp_tunnels_info_reset_write(struct file *file, const char __user *data, + size_t count, loff_t *ppos) +{ + struct net_device *dev = file->private_data; + struct netdevsim *ns = netdev_priv(dev); + + memset(ns->udp_ports.ports, 0, sizeof(ns->udp_ports.__ports)); + rtnl_lock(); + udp_tunnel_nic_reset_ntf(dev); + rtnl_unlock(); + + return count; +} + +static const struct file_operations nsim_udp_tunnels_info_reset_fops = { + .open = simple_open, + .write = nsim_udp_tunnels_info_reset_write, + .llseek = generic_file_llseek, + .owner = THIS_MODULE, +}; + +int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev, + struct net_device *dev) +{ + struct netdevsim *ns = netdev_priv(dev); + struct udp_tunnel_nic_info *info; + + if (nsim_dev->udp_ports.shared && nsim_dev->udp_ports.open_only) { + dev_err(&nsim_dev->nsim_bus_dev->dev, + "shared can't be used in conjunction with open_only\n"); + return -EINVAL; + } + + if (!nsim_dev->udp_ports.shared) + ns->udp_ports.ports = ns->udp_ports.__ports; + else + ns->udp_ports.ports = nsim_dev->udp_ports.__ports; + + debugfs_create_u32("udp_ports_inject_error", 0600, + ns->nsim_dev_port->ddir, + &ns->udp_ports.inject_error); + + ns->udp_ports.dfs_ports[0].array = ns->udp_ports.ports[0]; + ns->udp_ports.dfs_ports[0].n_elements = NSIM_UDP_TUNNEL_N_PORTS; + debugfs_create_u32_array("udp_ports_table0", 0400, + ns->nsim_dev_port->ddir, + &ns->udp_ports.dfs_ports[0]); + + ns->udp_ports.dfs_ports[1].array = ns->udp_ports.ports[1]; + ns->udp_ports.dfs_ports[1].n_elements = NSIM_UDP_TUNNEL_N_PORTS; + debugfs_create_u32_array("udp_ports_table1", 0400, + ns->nsim_dev_port->ddir, + &ns->udp_ports.dfs_ports[1]); + + debugfs_create_file("udp_ports_reset", 0200, ns->nsim_dev_port->ddir, + dev, &nsim_udp_tunnels_info_reset_fops); + + /* Note: it's not normal to allocate the info struct like this! + * Drivers are expected to use a static const one, here we're testing. + */ + info = kmemdup(&nsim_udp_tunnel_info, sizeof(nsim_udp_tunnel_info), + GFP_KERNEL); + if (!info) + return -ENOMEM; + ns->udp_ports.sleep = nsim_dev->udp_ports.sleep; + + if (nsim_dev->udp_ports.sync_all) { + info->set_port = NULL; + info->unset_port = NULL; + } else { + info->sync_table = NULL; + } + + if (ns->udp_ports.sleep) + info->flags |= UDP_TUNNEL_NIC_INFO_MAY_SLEEP; + if (nsim_dev->udp_ports.open_only) + info->flags |= UDP_TUNNEL_NIC_INFO_OPEN_ONLY; + if (nsim_dev->udp_ports.ipv4_only) + info->flags |= UDP_TUNNEL_NIC_INFO_IPV4_ONLY; + if (nsim_dev->udp_ports.shared) + info->shared = &nsim_dev->udp_ports.utn_shared; + if (nsim_dev->udp_ports.static_iana_vxlan) + info->flags |= UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN; + + dev->udp_tunnel_nic_info = info; + return 0; +} + +void nsim_udp_tunnels_info_destroy(struct net_device *dev) +{ + kfree(dev->udp_tunnel_nic_info); + dev->udp_tunnel_nic_info = NULL; +} + +void nsim_udp_tunnels_debugfs_create(struct nsim_dev *nsim_dev) +{ + debugfs_create_bool("udp_ports_sync_all", 0600, nsim_dev->ddir, + &nsim_dev->udp_ports.sync_all); + debugfs_create_bool("udp_ports_open_only", 0600, nsim_dev->ddir, + &nsim_dev->udp_ports.open_only); + debugfs_create_bool("udp_ports_ipv4_only", 0600, nsim_dev->ddir, + &nsim_dev->udp_ports.ipv4_only); + debugfs_create_bool("udp_ports_shared", 0600, nsim_dev->ddir, + &nsim_dev->udp_ports.shared); + debugfs_create_bool("udp_ports_static_iana_vxlan", 0600, nsim_dev->ddir, + &nsim_dev->udp_ports.static_iana_vxlan); + debugfs_create_u32("udp_ports_sleep", 0600, nsim_dev->ddir, + &nsim_dev->udp_ports.sleep); +} |