diff options
Diffstat (limited to 'drivers/net/netdevsim')
-rw-r--r-- | drivers/net/netdevsim/Makefile | 2 | ||||
-rw-r--r-- | drivers/net/netdevsim/bpf.c | 10 | ||||
-rw-r--r-- | drivers/net/netdevsim/bus.c | 65 | ||||
-rw-r--r-- | drivers/net/netdevsim/dev.c | 763 | ||||
-rw-r--r-- | drivers/net/netdevsim/fib.c | 837 | ||||
-rw-r--r-- | drivers/net/netdevsim/health.c | 319 | ||||
-rw-r--r-- | drivers/net/netdevsim/netdev.c | 10 | ||||
-rw-r--r-- | drivers/net/netdevsim/netdevsim.h | 41 | ||||
-rw-r--r-- | drivers/net/netdevsim/sdev.c | 69 |
9 files changed, 1803 insertions, 313 deletions
diff --git a/drivers/net/netdevsim/Makefile b/drivers/net/netdevsim/Makefile index 09f1315d2f2a..f4d8f62f28c2 100644 --- a/drivers/net/netdevsim/Makefile +++ b/drivers/net/netdevsim/Makefile @@ -3,7 +3,7 @@ obj-$(CONFIG_NETDEVSIM) += netdevsim.o netdevsim-objs := \ - netdev.o dev.o fib.o bus.o + netdev.o dev.o fib.o bus.o health.o ifeq ($(CONFIG_BPF_SYSCALL),y) netdevsim-objs += \ diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index 2b74425822ab..0b362b8dac17 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -218,6 +218,7 @@ static int nsim_bpf_create_prog(struct nsim_dev *nsim_dev, { struct nsim_bpf_bound_prog *state; char name[16]; + int ret; state = kzalloc(sizeof(*state), GFP_KERNEL); if (!state) @@ -230,9 +231,10 @@ static int nsim_bpf_create_prog(struct nsim_dev *nsim_dev, /* Program id is not populated yet when we create the state. */ sprintf(name, "%u", nsim_dev->prog_id_gen++); state->ddir = debugfs_create_dir(name, nsim_dev->ddir_bpf_bound_progs); - if (IS_ERR_OR_NULL(state->ddir)) { + if (IS_ERR(state->ddir)) { + ret = PTR_ERR(state->ddir); kfree(state); - return -ENOMEM; + return ret; } debugfs_create_u32("id", 0400, state->ddir, &prog->aux->id); @@ -587,8 +589,8 @@ int nsim_bpf_dev_init(struct nsim_dev *nsim_dev) nsim_dev->ddir_bpf_bound_progs = debugfs_create_dir("bpf_bound_progs", nsim_dev->ddir); - if (IS_ERR_OR_NULL(nsim_dev->ddir_bpf_bound_progs)) - return -ENOMEM; + if (IS_ERR(nsim_dev->ddir_bpf_bound_progs)) + return PTR_ERR(nsim_dev->ddir_bpf_bound_progs); nsim_dev->bpf_dev = bpf_offload_dev_create(&nsim_bpf_dev_ops, nsim_dev); err = PTR_ERR_OR_ZERO(nsim_dev->bpf_dev); diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c index 1a0ff3d7747b..7971dc4f54f1 100644 --- a/drivers/net/netdevsim/bus.c +++ b/drivers/net/netdevsim/bus.c @@ -17,6 +17,7 @@ static DEFINE_IDA(nsim_bus_dev_ids); static LIST_HEAD(nsim_bus_dev_list); static DEFINE_MUTEX(nsim_bus_dev_list_lock); +static bool nsim_bus_enable; static struct nsim_bus_dev *to_nsim_bus_dev(struct device *dev) { @@ -28,7 +29,7 @@ static int nsim_bus_dev_vfs_enable(struct nsim_bus_dev *nsim_bus_dev, { nsim_bus_dev->vfconfigs = kcalloc(num_vfs, sizeof(struct nsim_vf_config), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (!nsim_bus_dev->vfconfigs) return -ENOMEM; nsim_bus_dev->num_vfs = num_vfs; @@ -96,13 +97,25 @@ 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; + /* Prevent to use nsim_bus_dev before initialization. */ + if (!smp_load_acquire(&nsim_bus_dev->init)) + return -EBUSY; ret = kstrtouint(buf, 0, &port_index); 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); return ret ? ret : count; } @@ -113,13 +126,25 @@ 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; + /* Prevent to use nsim_bus_dev before initialization. */ + if (!smp_load_acquire(&nsim_bus_dev->init)) + return -EBUSY; ret = kstrtouint(buf, 0, &port_index); 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); return ret ? ret : count; } @@ -179,15 +204,30 @@ new_device_store(struct bus_type *bus, const char *buf, size_t count) pr_err("Format for adding new device is \"id port_count\" (uint uint).\n"); return -EINVAL; } - nsim_bus_dev = nsim_bus_dev_new(id, port_count); - if (IS_ERR(nsim_bus_dev)) - return PTR_ERR(nsim_bus_dev); mutex_lock(&nsim_bus_dev_list_lock); + /* Prevent to use resource before initialization. */ + if (!smp_load_acquire(&nsim_bus_enable)) { + err = -EBUSY; + goto err; + } + + nsim_bus_dev = nsim_bus_dev_new(id, port_count); + if (IS_ERR(nsim_bus_dev)) { + err = PTR_ERR(nsim_bus_dev); + goto err; + } + + /* Allow using nsim_bus_dev */ + smp_store_release(&nsim_bus_dev->init, true); + list_add_tail(&nsim_bus_dev->list, &nsim_bus_dev_list); mutex_unlock(&nsim_bus_dev_list_lock); return count; +err: + mutex_unlock(&nsim_bus_dev_list_lock); + return err; } static BUS_ATTR_WO(new_device); @@ -215,6 +255,11 @@ del_device_store(struct bus_type *bus, const char *buf, size_t count) err = -ENOENT; mutex_lock(&nsim_bus_dev_list_lock); + /* Prevent to use resource before initialization. */ + if (!smp_load_acquire(&nsim_bus_enable)) { + mutex_unlock(&nsim_bus_dev_list_lock); + return -EBUSY; + } list_for_each_entry_safe(nsim_bus_dev, tmp, &nsim_bus_dev_list, list) { if (nsim_bus_dev->dev.id != id) continue; @@ -283,6 +328,10 @@ 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->initial_net = current->nsproxy->net_ns; + mutex_init(&nsim_bus_dev->nsim_bus_reload_lock); + /* Disallow using nsim_bus_dev */ + smp_store_release(&nsim_bus_dev->init, false); err = device_register(&nsim_bus_dev->dev); if (err) @@ -298,6 +347,8 @@ err_nsim_bus_dev_free: 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); @@ -319,6 +370,8 @@ int nsim_bus_init(void) err = driver_register(&nsim_driver); if (err) goto err_bus_unregister; + /* Allow using resources */ + smp_store_release(&nsim_bus_enable, true); return 0; err_bus_unregister: @@ -330,12 +383,16 @@ void nsim_bus_exit(void) { struct nsim_bus_dev *nsim_bus_dev, *tmp; + /* Disallow using resources */ + smp_store_release(&nsim_bus_enable, false); + mutex_lock(&nsim_bus_dev_list_lock); list_for_each_entry_safe(nsim_bus_dev, tmp, &nsim_bus_dev_list, list) { list_del(&nsim_bus_dev->list); nsim_bus_dev_del(nsim_bus_dev); } mutex_unlock(&nsim_bus_dev_list_lock); + driver_unregister(&nsim_driver); bus_unregister(&nsim_bus); } diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index bcc40a236624..d7706a0346f2 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -17,29 +17,86 @@ #include <linux/debugfs.h> #include <linux/device.h> +#include <linux/etherdevice.h> +#include <linux/inet.h> +#include <linux/jiffies.h> +#include <linux/kernel.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/random.h> #include <linux/rtnetlink.h> +#include <linux/workqueue.h> #include <net/devlink.h> +#include <net/ip.h> +#include <uapi/linux/devlink.h> +#include <uapi/linux/ip.h> +#include <uapi/linux/udp.h> #include "netdevsim.h" static struct dentry *nsim_dev_ddir; +#define NSIM_DEV_DUMMY_REGION_SIZE (1024 * 32) + +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; + int err; + u32 id; + + 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); + + id = devlink_region_snapshot_id_get(priv_to_devlink(nsim_dev)); + err = devlink_region_snapshot_create(nsim_dev->dummy_region, + dummy_data, id, kfree); + if (err) { + pr_err("Failed to create region snapshot\n"); + kfree(dummy_data); + return err; + } + + return count; +} + +static const struct file_operations nsim_dev_take_snapshot_fops = { + .open = simple_open, + .write = nsim_dev_take_snapshot_write, + .llseek = generic_file_llseek, +}; + static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) { - char dev_ddir_name[16]; + char dev_ddir_name[sizeof(DRV_NAME) + 10]; 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_OR_NULL(nsim_dev->ddir)) - return PTR_ERR_OR_ZERO(nsim_dev->ddir) ?: -EINVAL; + 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_OR_NULL(nsim_dev->ports_ddir)) - return PTR_ERR_OR_ZERO(nsim_dev->ports_ddir) ?: -EINVAL; + if (IS_ERR(nsim_dev->ports_ddir)) + return PTR_ERR(nsim_dev->ports_ddir); debugfs_create_bool("fw_update_status", 0600, nsim_dev->ddir, &nsim_dev->fw_update_status); + debugfs_create_u32("max_macs", 0600, nsim_dev->ddir, + &nsim_dev->max_macs); + debugfs_create_bool("test1", 0600, nsim_dev->ddir, + &nsim_dev->test1); + nsim_dev->take_snapshot = debugfs_create_file("take_snapshot", + 0200, + nsim_dev->ddir, + nsim_dev, + &nsim_dev_take_snapshot_fops); + debugfs_create_bool("dont_allow_reload", 0600, nsim_dev->ddir, + &nsim_dev->dont_allow_reload); + debugfs_create_bool("fail_reload", 0600, nsim_dev->ddir, + &nsim_dev->fail_reload); return 0; } @@ -58,8 +115,8 @@ static int nsim_dev_port_debugfs_init(struct nsim_dev *nsim_dev, sprintf(port_ddir_name, "%u", nsim_dev_port->port_index); nsim_dev_port->ddir = debugfs_create_dir(port_ddir_name, nsim_dev->ports_ddir); - if (IS_ERR_OR_NULL(nsim_dev_port->ddir)) - return -ENOMEM; + 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); @@ -73,39 +130,6 @@ static void nsim_dev_port_debugfs_exit(struct nsim_dev_port *nsim_dev_port) debugfs_remove_recursive(nsim_dev_port->ddir); } -static struct net *nsim_devlink_net(struct devlink *devlink) -{ - return &init_net; -} - -static u64 nsim_dev_ipv4_fib_resource_occ_get(void *priv) -{ - struct net *net = priv; - - return nsim_fib_get_val(net, NSIM_RESOURCE_IPV4_FIB, false); -} - -static u64 nsim_dev_ipv4_fib_rules_res_occ_get(void *priv) -{ - struct net *net = priv; - - return nsim_fib_get_val(net, NSIM_RESOURCE_IPV4_FIB_RULES, false); -} - -static u64 nsim_dev_ipv6_fib_resource_occ_get(void *priv) -{ - struct net *net = priv; - - return nsim_fib_get_val(net, NSIM_RESOURCE_IPV6_FIB, false); -} - -static u64 nsim_dev_ipv6_fib_rules_res_occ_get(void *priv) -{ - struct net *net = priv; - - return nsim_fib_get_val(net, NSIM_RESOURCE_IPV6_FIB_RULES, false); -} - static int nsim_dev_resources_register(struct devlink *devlink) { struct devlink_resource_size_params params = { @@ -113,9 +137,7 @@ static int nsim_dev_resources_register(struct devlink *devlink) .size_granularity = 1, .unit = DEVLINK_RESOURCE_UNIT_ENTRY }; - struct net *net = nsim_devlink_net(devlink); int err; - u64 n; /* Resources for IPv4 */ err = devlink_resource_register(devlink, "IPv4", (u64)-1, @@ -127,8 +149,7 @@ static int nsim_dev_resources_register(struct devlink *devlink) goto out; } - n = nsim_fib_get_val(net, NSIM_RESOURCE_IPV4_FIB, true); - err = devlink_resource_register(devlink, "fib", n, + err = devlink_resource_register(devlink, "fib", (u64)-1, NSIM_RESOURCE_IPV4_FIB, NSIM_RESOURCE_IPV4, ¶ms); if (err) { @@ -136,8 +157,7 @@ static int nsim_dev_resources_register(struct devlink *devlink) return err; } - n = nsim_fib_get_val(net, NSIM_RESOURCE_IPV4_FIB_RULES, true); - err = devlink_resource_register(devlink, "fib-rules", n, + err = devlink_resource_register(devlink, "fib-rules", (u64)-1, NSIM_RESOURCE_IPV4_FIB_RULES, NSIM_RESOURCE_IPV4, ¶ms); if (err) { @@ -155,8 +175,7 @@ static int nsim_dev_resources_register(struct devlink *devlink) goto out; } - n = nsim_fib_get_val(net, NSIM_RESOURCE_IPV6_FIB, true); - err = devlink_resource_register(devlink, "fib", n, + err = devlink_resource_register(devlink, "fib", (u64)-1, NSIM_RESOURCE_IPV6_FIB, NSIM_RESOURCE_IPV6, ¶ms); if (err) { @@ -164,8 +183,7 @@ static int nsim_dev_resources_register(struct devlink *devlink) return err; } - n = nsim_fib_get_val(net, NSIM_RESOURCE_IPV6_FIB_RULES, true); - err = devlink_resource_register(devlink, "fib-rules", n, + err = devlink_resource_register(devlink, "fib-rules", (u64)-1, NSIM_RESOURCE_IPV6_FIB_RULES, NSIM_RESOURCE_IPV6, ¶ms); if (err) { @@ -173,49 +191,333 @@ static int nsim_dev_resources_register(struct devlink *devlink) return err; } - devlink_resource_occ_get_register(devlink, - NSIM_RESOURCE_IPV4_FIB, - nsim_dev_ipv4_fib_resource_occ_get, - net); - devlink_resource_occ_get_register(devlink, - NSIM_RESOURCE_IPV4_FIB_RULES, - nsim_dev_ipv4_fib_rules_res_occ_get, - net); - devlink_resource_occ_get_register(devlink, - NSIM_RESOURCE_IPV6_FIB, - nsim_dev_ipv6_fib_resource_occ_get, - net); - devlink_resource_occ_get_register(devlink, - NSIM_RESOURCE_IPV6_FIB_RULES, - nsim_dev_ipv6_fib_rules_res_occ_get, - net); out: return err; } -static int nsim_dev_reload(struct devlink *devlink, - struct netlink_ext_ack *extack) +enum nsim_devlink_param_id { + NSIM_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, + NSIM_DEVLINK_PARAM_ID_TEST1, +}; + +static const struct devlink_param nsim_devlink_params[] = { + DEVLINK_PARAM_GENERIC(MAX_MACS, + BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, NULL), + DEVLINK_PARAM_DRIVER(NSIM_DEVLINK_PARAM_ID_TEST1, + "test1", DEVLINK_PARAM_TYPE_BOOL, + BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, NULL), +}; + +static void nsim_devlink_set_params_init_values(struct nsim_dev *nsim_dev, + struct devlink *devlink) +{ + union devlink_param_value value; + + value.vu32 = nsim_dev->max_macs; + devlink_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_MAX_MACS, + value); + value.vbool = nsim_dev->test1; + devlink_param_driverinit_value_set(devlink, + NSIM_DEVLINK_PARAM_ID_TEST1, + value); +} + +static void nsim_devlink_param_load_driverinit_values(struct devlink *devlink) { - enum nsim_resource_id res_ids[] = { - NSIM_RESOURCE_IPV4_FIB, NSIM_RESOURCE_IPV4_FIB_RULES, - NSIM_RESOURCE_IPV6_FIB, NSIM_RESOURCE_IPV6_FIB_RULES - }; - struct net *net = nsim_devlink_net(devlink); + struct nsim_dev *nsim_dev = devlink_priv(devlink); + union devlink_param_value saved_value; + int err; + + err = devlink_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_MAX_MACS, + &saved_value); + if (!err) + nsim_dev->max_macs = saved_value.vu32; + err = devlink_param_driverinit_value_get(devlink, + NSIM_DEVLINK_PARAM_ID_TEST1, + &saved_value); + if (!err) + nsim_dev->test1 = saved_value.vbool; +} + +#define NSIM_DEV_DUMMY_REGION_SNAPSHOT_MAX 16 + +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); + 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); +} + +struct nsim_trap_item { + void *trap_ctx; + enum devlink_trap_action action; +}; + +struct nsim_trap_data { + struct delayed_work trap_report_dw; + struct nsim_trap_item *trap_items_arr; + struct nsim_dev *nsim_dev; + spinlock_t trap_lock; /* Protects trap_items_arr */ +}; + +/* All driver-specific traps must be documented in + * Documentation/networking/devlink/netdevsim.rst + */ +enum { + NSIM_TRAP_ID_BASE = DEVLINK_TRAP_GENERIC_ID_MAX, + NSIM_TRAP_ID_FID_MISS, +}; + +#define NSIM_TRAP_NAME_FID_MISS "fid_miss" + +#define NSIM_TRAP_METADATA DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT + +#define NSIM_TRAP_DROP(_id, _group_id) \ + DEVLINK_TRAP_GENERIC(DROP, DROP, _id, \ + DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ + NSIM_TRAP_METADATA) +#define NSIM_TRAP_EXCEPTION(_id, _group_id) \ + DEVLINK_TRAP_GENERIC(EXCEPTION, TRAP, _id, \ + DEVLINK_TRAP_GROUP_GENERIC(_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), \ + NSIM_TRAP_METADATA) + +static const struct devlink_trap nsim_traps_arr[] = { + NSIM_TRAP_DROP(SMAC_MC, L2_DROPS), + NSIM_TRAP_DROP(VLAN_TAG_MISMATCH, L2_DROPS), + NSIM_TRAP_DROP(INGRESS_VLAN_FILTER, L2_DROPS), + NSIM_TRAP_DROP(INGRESS_STP_FILTER, L2_DROPS), + NSIM_TRAP_DROP(EMPTY_TX_LIST, L2_DROPS), + 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_DROP(TAIL_DROP, BUFFER_DROPS), +}; + +#define NSIM_TRAP_L4_DATA_LEN 100 + +static struct sk_buff *nsim_dev_trap_skb_build(void) +{ + int tot_len, data_len = NSIM_TRAP_L4_DATA_LEN; + struct sk_buff *skb; + struct udphdr *udph; + struct ethhdr *eth; + struct iphdr *iph; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); + 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->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_trap_report(struct nsim_dev_port *nsim_dev_port) +{ + struct nsim_dev *nsim_dev = nsim_dev_port->ns->nsim_dev; + struct devlink *devlink = priv_to_devlink(nsim_dev); + struct nsim_trap_data *nsim_trap_data; int i; - for (i = 0; i < ARRAY_SIZE(res_ids); ++i) { - int err; - u64 val; + nsim_trap_data = nsim_dev->trap_data; + + spin_lock(&nsim_trap_data->trap_lock); + for (i = 0; i < ARRAY_SIZE(nsim_traps_arr); i++) { + struct nsim_trap_item *nsim_trap_item; + struct sk_buff *skb; + + nsim_trap_item = &nsim_trap_data->trap_items_arr[i]; + if (nsim_trap_item->action == DEVLINK_TRAP_ACTION_DROP) + continue; + + skb = nsim_dev_trap_skb_build(); + if (!skb) + continue; + skb->dev = nsim_dev_port->ns->netdev; + + /* Trapped packets are usually passed to devlink in softIRQ, + * but in this case they are generated in a workqueue. Disable + * softIRQs to prevent lockdep from complaining about + * "incosistent lock state". + */ + local_bh_disable(); + devlink_trap_report(devlink, skb, nsim_trap_item->trap_ctx, + &nsim_dev_port->devlink_port); + local_bh_enable(); + consume_skb(skb); + } + spin_unlock(&nsim_trap_data->trap_lock); +} + +#define NSIM_TRAP_REPORT_INTERVAL_MS 100 - err = devlink_resource_size_get(devlink, res_ids[i], &val); - if (!err) { - err = nsim_fib_set_max(net, res_ids[i], val, extack); - if (err) - return err; - } +static void nsim_dev_trap_report_work(struct work_struct *work) +{ + struct nsim_trap_data *nsim_trap_data; + struct nsim_dev_port *nsim_dev_port; + struct nsim_dev *nsim_dev; + + nsim_trap_data = container_of(work, struct nsim_trap_data, + trap_report_dw.work); + nsim_dev = nsim_trap_data->nsim_dev; + + /* 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); + 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); + + schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, + msecs_to_jiffies(NSIM_TRAP_REPORT_INTERVAL_MS)); +} + +static int nsim_dev_traps_init(struct devlink *devlink) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + struct nsim_trap_data *nsim_trap_data; + int err; + + nsim_trap_data = kzalloc(sizeof(*nsim_trap_data), GFP_KERNEL); + if (!nsim_trap_data) + return -ENOMEM; + + nsim_trap_data->trap_items_arr = kcalloc(ARRAY_SIZE(nsim_traps_arr), + sizeof(struct nsim_trap_item), + GFP_KERNEL); + if (!nsim_trap_data->trap_items_arr) { + err = -ENOMEM; + goto err_trap_data_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. + */ + spin_lock_init(&nsim_trap_data->trap_lock); + 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); + if (err) + goto err_trap_items_free; + + INIT_DELAYED_WORK(&nsim_dev->trap_data->trap_report_dw, + nsim_dev_trap_report_work); + schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, + msecs_to_jiffies(NSIM_TRAP_REPORT_INTERVAL_MS)); return 0; + +err_trap_items_free: + kfree(nsim_trap_data->trap_items_arr); +err_trap_data_free: + kfree(nsim_trap_data); + return err; +} + +static void nsim_dev_traps_exit(struct devlink *devlink) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + + cancel_delayed_work_sync(&nsim_dev->trap_data->trap_report_dw); + devlink_traps_unregister(devlink, nsim_traps_arr, + ARRAY_SIZE(nsim_traps_arr)); + kfree(nsim_dev->trap_data->trap_items_arr); + kfree(nsim_dev->trap_data); +} + +static int nsim_dev_reload_create(struct nsim_dev *nsim_dev, + struct netlink_ext_ack *extack); +static void nsim_dev_reload_destroy(struct nsim_dev *nsim_dev); + +static int nsim_dev_reload_down(struct devlink *devlink, bool netns_change, + struct netlink_ext_ack *extack) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + + if (nsim_dev->dont_allow_reload) { + /* For testing purposes, user set debugfs dont_allow_reload + * value to true. So forbid it. + */ + NL_SET_ERR_MSG_MOD(extack, "User forbid the reload for testing purposes"); + return -EOPNOTSUPP; + } + + nsim_dev_reload_destroy(nsim_dev); + return 0; +} + +static int nsim_dev_reload_up(struct devlink *devlink, + struct netlink_ext_ack *extack) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + + if (nsim_dev->fail_reload) { + /* For testing purposes, user set debugfs fail_reload + * value to true. Fail right away. + */ + NL_SET_ERR_MSG_MOD(extack, "User setup the reload to fail for testing purposes"); + return -EINVAL; + } + + return nsim_dev_reload_create(nsim_dev, extack); +} + +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); } #define NSIM_DEV_FLASH_SIZE 500000 @@ -258,70 +560,68 @@ static int nsim_dev_flash_update(struct devlink *devlink, const char *file_name, return 0; } -static const struct devlink_ops nsim_dev_devlink_ops = { - .reload = nsim_dev_reload, - .flash_update = nsim_dev_flash_update, -}; - -static struct nsim_dev * -nsim_dev_create(struct nsim_bus_dev *nsim_bus_dev, unsigned int port_count) +static struct nsim_trap_item * +nsim_dev_trap_item_lookup(struct nsim_dev *nsim_dev, u16 trap_id) { - struct nsim_dev *nsim_dev; - struct devlink *devlink; - int err; - - devlink = devlink_alloc(&nsim_dev_devlink_ops, sizeof(*nsim_dev)); - if (!devlink) - return ERR_PTR(-ENOMEM); - 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; + struct nsim_trap_data *nsim_trap_data = nsim_dev->trap_data; + int i; - err = nsim_dev_resources_register(devlink); - if (err) - goto err_devlink_free; + for (i = 0; i < ARRAY_SIZE(nsim_traps_arr); i++) { + if (nsim_traps_arr[i].id == trap_id) + return &nsim_trap_data->trap_items_arr[i]; + } - err = devlink_register(devlink, &nsim_bus_dev->dev); - if (err) - goto err_resources_unregister; + return NULL; +} - err = nsim_dev_debugfs_init(nsim_dev); - if (err) - goto err_dl_unregister; +static int nsim_dev_devlink_trap_init(struct devlink *devlink, + const struct devlink_trap *trap, + void *trap_ctx) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + struct nsim_trap_item *nsim_trap_item; - err = nsim_bpf_dev_init(nsim_dev); - if (err) - goto err_debugfs_exit; + nsim_trap_item = nsim_dev_trap_item_lookup(nsim_dev, trap->id); + if (WARN_ON(!nsim_trap_item)) + return -ENOENT; - return nsim_dev; + nsim_trap_item->trap_ctx = trap_ctx; + nsim_trap_item->action = trap->init_action; -err_debugfs_exit: - nsim_dev_debugfs_exit(nsim_dev); -err_dl_unregister: - devlink_unregister(devlink); -err_resources_unregister: - devlink_resources_unregister(devlink, NULL); -err_devlink_free: - devlink_free(devlink); - return ERR_PTR(err); + return 0; } -static void nsim_dev_destroy(struct nsim_dev *nsim_dev) +static int +nsim_dev_devlink_trap_action_set(struct devlink *devlink, + const struct devlink_trap *trap, + enum devlink_trap_action action) { - struct devlink *devlink = priv_to_devlink(nsim_dev); + struct nsim_dev *nsim_dev = devlink_priv(devlink); + struct nsim_trap_item *nsim_trap_item; - nsim_bpf_dev_exit(nsim_dev); - nsim_dev_debugfs_exit(nsim_dev); - devlink_unregister(devlink); - devlink_resources_unregister(devlink, NULL); - mutex_destroy(&nsim_dev->port_list_lock); - devlink_free(devlink); + nsim_trap_item = nsim_dev_trap_item_lookup(nsim_dev, trap->id); + if (WARN_ON(!nsim_trap_item)) + return -ENOENT; + + spin_lock(&nsim_dev->trap_data->trap_lock); + nsim_trap_item->action = action; + spin_unlock(&nsim_dev->trap_data->trap_lock); + + return 0; } +static const struct devlink_ops nsim_dev_devlink_ops = { + .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, +}; + +#define NSIM_DEV_MAX_MACS_DEFAULT 32 +#define NSIM_DEV_TEST1_DEFAULT true + static int __nsim_dev_port_add(struct nsim_dev *nsim_dev, unsigned int port_index) { @@ -384,23 +684,19 @@ 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); } -int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev) +static int nsim_dev_port_add_all(struct nsim_dev *nsim_dev, + unsigned int port_count) { - struct nsim_dev *nsim_dev; - int i; - int err; + int i, err; - nsim_dev = nsim_dev_create(nsim_bus_dev, nsim_bus_dev->port_count); - if (IS_ERR(nsim_dev)) - return PTR_ERR(nsim_dev); - dev_set_drvdata(&nsim_bus_dev->dev, nsim_dev); - - for (i = 0; i < nsim_bus_dev->port_count; i++) { + for (i = 0; i < port_count; i++) { err = __nsim_dev_port_add(nsim_dev, i); if (err) goto err_port_del_all; @@ -409,16 +705,187 @@ int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev) err_port_del_all: nsim_dev_port_del_all(nsim_dev); - nsim_dev_destroy(nsim_dev); return err; } +static int nsim_dev_reload_create(struct nsim_dev *nsim_dev, + struct netlink_ext_ack *extack) +{ + struct nsim_bus_dev *nsim_bus_dev = nsim_dev->nsim_bus_dev; + struct devlink *devlink; + int err; + + 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_devlink_param_load_driverinit_values(devlink); + + err = nsim_dev_dummy_region_init(nsim_dev, devlink); + if (err) + goto err_fib_destroy; + + err = nsim_dev_traps_init(devlink); + if (err) + goto err_dummy_region_exit; + + err = nsim_dev_health_init(nsim_dev, devlink); + if (err) + goto err_traps_exit; + + err = nsim_dev_port_add_all(nsim_dev, nsim_bus_dev->port_count); + if (err) + goto err_health_exit; + + nsim_dev->take_snapshot = debugfs_create_file("take_snapshot", + 0200, + nsim_dev->ddir, + nsim_dev, + &nsim_dev_take_snapshot_fops); + return 0; + +err_health_exit: + nsim_dev_health_exit(nsim_dev); +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) +{ + struct nsim_dev *nsim_dev; + struct devlink *devlink; + int err; + + devlink = devlink_alloc(&nsim_dev_devlink_ops, sizeof(*nsim_dev)); + if (!devlink) + return -ENOMEM; + devlink_net_set(devlink, nsim_bus_dev->initial_net); + 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->max_macs = NSIM_DEV_MAX_MACS_DEFAULT; + nsim_dev->test1 = NSIM_DEV_TEST1_DEFAULT; + + 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; + } + + err = devlink_register(devlink, &nsim_bus_dev->dev); + if (err) + goto err_fib_destroy; + + err = devlink_params_register(devlink, nsim_devlink_params, + ARRAY_SIZE(nsim_devlink_params)); + if (err) + goto err_dl_unregister; + nsim_devlink_set_params_init_values(nsim_dev, devlink); + + err = nsim_dev_dummy_region_init(nsim_dev, devlink); + if (err) + goto err_params_unregister; + + err = nsim_dev_traps_init(devlink); + if (err) + goto err_dummy_region_exit; + + err = nsim_dev_debugfs_init(nsim_dev); + if (err) + goto err_traps_exit; + + err = nsim_dev_health_init(nsim_dev, devlink); + if (err) + goto err_debugfs_exit; + + 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); + if (err) + goto err_bpf_dev_exit; + + devlink_params_publish(devlink); + devlink_reload_enable(devlink); + return 0; + +err_bpf_dev_exit: + nsim_bpf_dev_exit(nsim_dev); +err_health_exit: + nsim_dev_health_exit(nsim_dev); +err_debugfs_exit: + nsim_dev_debugfs_exit(nsim_dev); +err_traps_exit: + nsim_dev_traps_exit(devlink); +err_dummy_region_exit: + nsim_dev_dummy_region_exit(nsim_dev); +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: + devlink_free(devlink); + return err; +} + +static void nsim_dev_reload_destroy(struct nsim_dev *nsim_dev) +{ + struct devlink *devlink = priv_to_devlink(nsim_dev); + + if (devlink_is_reload_failed(devlink)) + return; + debugfs_remove(nsim_dev->take_snapshot); + nsim_dev_port_del_all(nsim_dev); + nsim_dev_health_exit(nsim_dev); + 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) { struct nsim_dev *nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev); + struct devlink *devlink = priv_to_devlink(nsim_dev); - nsim_dev_port_del_all(nsim_dev); - nsim_dev_destroy(nsim_dev); + devlink_reload_disable(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); + devlink_free(devlink); } static struct nsim_dev_port * @@ -467,9 +934,7 @@ int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev, int nsim_dev_init(void) { nsim_dev_ddir = debugfs_create_dir(DRV_NAME, NULL); - if (IS_ERR_OR_NULL(nsim_dev_ddir)) - return -ENOMEM; - return 0; + return PTR_ERR_OR_ZERO(nsim_dev_ddir); } void nsim_dev_exit(void) diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index f61d094746c0..f32d56ac3e80 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -14,11 +14,17 @@ * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. */ +#include <linux/in6.h> +#include <linux/kernel.h> +#include <linux/list.h> +#include <linux/rhashtable.h> +#include <linux/spinlock_types.h> +#include <linux/types.h> #include <net/fib_notifier.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/fib_rules.h> -#include <net/netns/generic.h> +#include <net/net_namespace.h> #include "netdevsim.h" @@ -33,15 +39,56 @@ struct nsim_per_fib_data { }; struct nsim_fib_data { + struct notifier_block fib_nb; struct nsim_per_fib_data ipv4; struct nsim_per_fib_data ipv6; + struct rhashtable fib_rt_ht; + struct list_head fib_rt_list; + spinlock_t fib_lock; /* Protects hashtable, list and accounting */ + struct devlink *devlink; }; -static unsigned int nsim_fib_net_id; +struct nsim_fib_rt_key { + unsigned char addr[sizeof(struct in6_addr)]; + unsigned char prefix_len; + int family; + u32 tb_id; +}; + +struct nsim_fib_rt { + struct nsim_fib_rt_key key; + struct rhash_head ht_node; + struct list_head list; /* Member of fib_rt_list */ +}; + +struct nsim_fib4_rt { + struct nsim_fib_rt common; + struct fib_info *fi; + u8 tos; + u8 type; +}; + +struct nsim_fib6_rt { + struct nsim_fib_rt common; + struct list_head nh_list; + unsigned int nhs; +}; + +struct nsim_fib6_rt_nh { + struct list_head list; /* Member of nh_list */ + struct fib6_info *rt; +}; -u64 nsim_fib_get_val(struct net *net, enum nsim_resource_id res_id, bool max) +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), + .key_len = sizeof(struct nsim_fib_rt_key), + .automatic_shrinking = true, +}; + +u64 nsim_fib_get_val(struct nsim_fib_data *fib_data, + enum nsim_resource_id res_id, bool max) { - struct nsim_fib_data *fib_data = net_generic(net, nsim_fib_net_id); struct nsim_fib_entry *entry; switch (res_id) { @@ -64,12 +111,10 @@ u64 nsim_fib_get_val(struct net *net, enum nsim_resource_id res_id, bool max) return max ? entry->max : entry->num; } -int nsim_fib_set_max(struct net *net, enum nsim_resource_id res_id, u64 val, - struct netlink_ext_ack *extack) +static void nsim_fib_set_max(struct nsim_fib_data *fib_data, + enum nsim_resource_id res_id, u64 val) { - struct nsim_fib_data *fib_data = net_generic(net, nsim_fib_net_id); struct nsim_fib_entry *entry; - int err = 0; switch (res_id) { case NSIM_RESOURCE_IPV4_FIB: @@ -85,20 +130,10 @@ int nsim_fib_set_max(struct net *net, enum nsim_resource_id res_id, u64 val, entry = &fib_data->ipv6.rules; break; default: - return 0; - } - - /* not allowing a new max to be less than curren occupancy - * --> no means of evicting entries - */ - if (val < entry->num) { - NL_SET_ERR_MSG_MOD(extack, "New size is less than current occupancy"); - err = -EINVAL; - } else { - entry->max = val; + WARN_ON(1); + return; } - - return err; + entry->max = val; } static int nsim_fib_rule_account(struct nsim_fib_entry *entry, bool add, @@ -120,9 +155,9 @@ static int nsim_fib_rule_account(struct nsim_fib_entry *entry, bool add, return err; } -static int nsim_fib_rule_event(struct fib_notifier_info *info, bool add) +static int nsim_fib_rule_event(struct nsim_fib_data *data, + struct fib_notifier_info *info, bool add) { - struct nsim_fib_data *data = net_generic(info->net, nsim_fib_net_id); struct netlink_ext_ack *extack = info->extack; int err = 0; @@ -157,18 +192,556 @@ static int nsim_fib_account(struct nsim_fib_entry *entry, bool add, return err; } -static int nsim_fib_event(struct fib_notifier_info *info, bool add) +static void nsim_fib_rt_init(struct nsim_fib_data *data, + struct nsim_fib_rt *fib_rt, const void *addr, + size_t addr_len, unsigned int prefix_len, + int family, u32 tb_id) +{ + memcpy(fib_rt->key.addr, addr, addr_len); + fib_rt->key.prefix_len = prefix_len; + fib_rt->key.family = family; + fib_rt->key.tb_id = tb_id; + list_add(&fib_rt->list, &data->fib_rt_list); +} + +static void nsim_fib_rt_fini(struct nsim_fib_rt *fib_rt) +{ + list_del(&fib_rt->list); +} + +static struct nsim_fib_rt *nsim_fib_rt_lookup(struct rhashtable *fib_rt_ht, + const void *addr, size_t addr_len, + unsigned int prefix_len, + int family, u32 tb_id) +{ + struct nsim_fib_rt_key key; + + memset(&key, 0, sizeof(key)); + memcpy(key.addr, addr, addr_len); + key.prefix_len = prefix_len; + key.family = family; + key.tb_id = tb_id; + + return rhashtable_lookup_fast(fib_rt_ht, &key, nsim_fib_rt_ht_params); +} + +static struct nsim_fib4_rt * +nsim_fib4_rt_create(struct nsim_fib_data *data, + struct fib_entry_notifier_info *fen_info) +{ + struct nsim_fib4_rt *fib4_rt; + + fib4_rt = kzalloc(sizeof(*fib4_rt), GFP_ATOMIC); + if (!fib4_rt) + return NULL; + + nsim_fib_rt_init(data, &fib4_rt->common, &fen_info->dst, sizeof(u32), + fen_info->dst_len, AF_INET, fen_info->tb_id); + + fib4_rt->fi = fen_info->fi; + fib_info_hold(fib4_rt->fi); + fib4_rt->tos = fen_info->tos; + fib4_rt->type = fen_info->type; + + return fib4_rt; +} + +static void nsim_fib4_rt_destroy(struct nsim_fib4_rt *fib4_rt) +{ + fib_info_put(fib4_rt->fi); + nsim_fib_rt_fini(&fib4_rt->common); + kfree(fib4_rt); +} + +static struct nsim_fib4_rt * +nsim_fib4_rt_lookup(struct rhashtable *fib_rt_ht, + const struct fib_entry_notifier_info *fen_info) +{ + struct nsim_fib_rt *fib_rt; + + fib_rt = nsim_fib_rt_lookup(fib_rt_ht, &fen_info->dst, sizeof(u32), + fen_info->dst_len, AF_INET, + fen_info->tb_id); + if (!fib_rt) + return NULL; + + return container_of(fib_rt, struct nsim_fib4_rt, common); +} + +static void nsim_fib4_rt_hw_flags_set(struct net *net, + const struct nsim_fib4_rt *fib4_rt, + bool trap) +{ + u32 *p_dst = (u32 *) fib4_rt->common.key.addr; + int dst_len = fib4_rt->common.key.prefix_len; + struct fib_rt_info fri; + + fri.fi = fib4_rt->fi; + 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.type = fib4_rt->type; + fri.offload = false; + fri.trap = trap; + 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 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"); + goto err_fib_dismiss; + } + + nsim_fib4_rt_hw_flags_set(net, fib4_rt, true); + + return 0; + +err_fib_dismiss: + nsim_fib_account(&data->ipv4.fib, false, extack); + 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 net *net = devlink_net(data->devlink); + int err; + + /* We are replacing a route, so no need to change the accounting. */ + 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"); + return err; + } + + nsim_fib4_rt_hw_flags_set(net, fib4_rt, true); + + nsim_fib4_rt_hw_flags_set(net, fib4_rt_old, false); + nsim_fib4_rt_destroy(fib4_rt_old); + + return 0; +} + +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; + + 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); + else + err = nsim_fib4_rt_replace(data, fib4_rt, fib4_rt_old, extack); + + if (err) + nsim_fib4_rt_destroy(fib4_rt); + + return err; +} + +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)) + 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, + 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); + break; + case FIB_EVENT_ENTRY_DEL: + nsim_fib4_rt_remove(data, fen_info); + break; + default: + break; + } + + return err; +} + +static struct nsim_fib6_rt_nh * +nsim_fib6_rt_nh_find(const struct nsim_fib6_rt *fib6_rt, + const struct fib6_info *rt) +{ + struct nsim_fib6_rt_nh *fib6_rt_nh; + + list_for_each_entry(fib6_rt_nh, &fib6_rt->nh_list, list) { + if (fib6_rt_nh->rt == rt) + return fib6_rt_nh; + } + + return NULL; +} + +static int nsim_fib6_rt_nh_add(struct nsim_fib6_rt *fib6_rt, + struct fib6_info *rt) +{ + struct nsim_fib6_rt_nh *fib6_rt_nh; + + fib6_rt_nh = kzalloc(sizeof(*fib6_rt_nh), GFP_ATOMIC); + if (!fib6_rt_nh) + return -ENOMEM; + + fib6_info_hold(rt); + fib6_rt_nh->rt = rt; + list_add_tail(&fib6_rt_nh->list, &fib6_rt->nh_list); + fib6_rt->nhs++; + + return 0; +} + +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)) + return; + + fib6_rt->nhs--; + list_del(&fib6_rt_nh->list); +#if IS_ENABLED(CONFIG_IPV6) + fib6_info_release(fib6_rt_nh->rt); +#endif + 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 *iter, *rt = fen6_info->rt; + struct nsim_fib6_rt *fib6_rt; + int i = 0; + int err; + + fib6_rt = kzalloc(sizeof(*fib6_rt), GFP_ATOMIC); + if (!fib6_rt) + return ERR_PTR(-ENOMEM); + + nsim_fib_rt_init(data, &fib6_rt->common, &rt->fib6_dst.addr, + sizeof(rt->fib6_dst.addr), rt->fib6_dst.plen, AF_INET6, + rt->fib6_table->tb6_id); + + /* We consider a multipath IPv6 route as one entry, but it can be made + * up from several fib6_info structs (one for each nexthop), so we + * add them all to the same list under the entry. + */ + 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); + 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: + nsim_fib_rt_fini(&fib6_rt->common); + kfree(fib6_rt); + return ERR_PTR(err); +} + +static void nsim_fib6_rt_destroy(struct nsim_fib6_rt *fib6_rt) +{ + struct nsim_fib6_rt_nh *iter, *tmp; + + list_for_each_entry_safe(iter, tmp, &fib6_rt->nh_list, list) + nsim_fib6_rt_nh_del(fib6_rt, iter->rt); + WARN_ON_ONCE(!list_empty(&fib6_rt->nh_list)); + nsim_fib_rt_fini(&fib6_rt->common); + kfree(fib6_rt); +} + +static struct nsim_fib6_rt * +nsim_fib6_rt_lookup(struct rhashtable *fib_rt_ht, const struct fib6_info *rt) +{ + struct nsim_fib_rt *fib_rt; + + fib_rt = nsim_fib_rt_lookup(fib_rt_ht, &rt->fib6_dst.addr, + sizeof(rt->fib6_dst.addr), + rt->fib6_dst.plen, AF_INET6, + rt->fib6_table->tb6_id); + if (!fib_rt) + return NULL; + + return container_of(fib_rt, struct nsim_fib6_rt, common); +} + +static int nsim_fib6_rt_append(struct nsim_fib_data *data, + struct fib6_entry_notifier_info *fen6_info) +{ + struct fib6_info *iter, *rt = fen6_info->rt; + struct nsim_fib6_rt *fib6_rt; + int i = 0; + int err; + + fib6_rt = nsim_fib6_rt_lookup(&data->fib_rt_ht, rt); + if (WARN_ON_ONCE(!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); + if (err) + goto err_fib6_rt_nh_del; + iter->trap = true; + i++; + } + 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); + } + 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, + bool trap) +{ + 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); +} + +static int nsim_fib6_rt_add(struct nsim_fib_data *data, + struct nsim_fib6_rt *fib6_rt, + struct netlink_ext_ack *extack) +{ + 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"); + goto err_fib_dismiss; + } + + nsim_fib6_rt_hw_flags_set(fib6_rt, true); + + return 0; + +err_fib_dismiss: + nsim_fib_account(&data->ipv6.fib, false, extack); + 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) +{ + int err; + + /* We are replacing a route, so no need to change the accounting. */ + 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"); + return err; + } + + nsim_fib6_rt_hw_flags_set(fib6_rt, true); + + nsim_fib6_rt_hw_flags_set(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 netlink_ext_ack *extack = fen6_info->info.extack; + struct nsim_fib6_rt *fib6_rt, *fib6_rt_old; + int err; + + fib6_rt = nsim_fib6_rt_create(data, fen6_info); + if (IS_ERR(fib6_rt)) + return PTR_ERR(fib6_rt); + + fib6_rt_old = nsim_fib6_rt_lookup(&data->fib_rt_ht, fen6_info->rt); + if (!fib6_rt_old) + err = nsim_fib6_rt_add(data, fib6_rt, extack); + else + err = nsim_fib6_rt_replace(data, fib6_rt, fib6_rt_old, extack); + + if (err) + nsim_fib6_rt_destroy(fib6_rt); + + return err; +} + +static void +nsim_fib6_rt_remove(struct nsim_fib_data *data, + const struct fib6_entry_notifier_info *fen6_info) +{ + struct netlink_ext_ack *extack = fen6_info->info.extack; + struct nsim_fib6_rt *fib6_rt; + + /* 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); + 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); + 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) +{ + struct fib6_entry_notifier_info *fen6_info; + int err = 0; + + fen6_info = container_of(info, struct fib6_entry_notifier_info, info); + + if (fen6_info->rt->nh) { + NL_SET_ERR_MSG_MOD(info->extack, "IPv6 route with nexthop objects is not supported"); + return 0; + } + + if (fen6_info->rt->fib6_src.plen) { + NL_SET_ERR_MSG_MOD(info->extack, "IPv6 source-specific route is not supported"); + return 0; + } + + switch (event) { + case FIB_EVENT_ENTRY_REPLACE: + err = nsim_fib6_rt_insert(data, fen6_info); + break; + case FIB_EVENT_ENTRY_APPEND: + err = nsim_fib6_rt_append(data, fen6_info); + break; + case FIB_EVENT_ENTRY_DEL: + nsim_fib6_rt_remove(data, fen6_info); + break; + default: + break; + } + + return err; +} + +static int nsim_fib_event(struct nsim_fib_data *data, + struct fib_notifier_info *info, unsigned long event) { - struct nsim_fib_data *data = net_generic(info->net, nsim_fib_net_id); - struct netlink_ext_ack *extack = info->extack; int err = 0; switch (info->family) { case AF_INET: - err = nsim_fib_account(&data->ipv4.fib, add, extack); + err = nsim_fib4_event(data, info, event); break; case AF_INET6: - err = nsim_fib_account(&data->ipv6.fib, add, extack); + err = nsim_fib6_event(data, info, event); break; } @@ -178,89 +751,207 @@ static int nsim_fib_event(struct fib_notifier_info *info, bool add) static int nsim_fib_event_nb(struct notifier_block *nb, unsigned long event, void *ptr) { + 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); + switch (event) { case FIB_EVENT_RULE_ADD: /* fall through */ case FIB_EVENT_RULE_DEL: - err = nsim_fib_rule_event(info, event == FIB_EVENT_RULE_ADD); + err = nsim_fib_rule_event(data, info, + event == FIB_EVENT_RULE_ADD); break; - case FIB_EVENT_ENTRY_ADD: /* fall through */ + case FIB_EVENT_ENTRY_REPLACE: /* fall through */ + case FIB_EVENT_ENTRY_APPEND: /* fall through */ case FIB_EVENT_ENTRY_DEL: - err = nsim_fib_event(info, event == FIB_EVENT_ENTRY_ADD); + err = nsim_fib_event(data, info, event); break; } + spin_unlock_bh(&data->fib_lock); + return notifier_from_errno(err); } -/* inconsistent dump, trying again */ -static void nsim_fib_dump_inconsistent(struct notifier_block *nb) +static void nsim_fib4_rt_free(struct nsim_fib_rt *fib_rt, + struct nsim_fib_data *data) { - struct nsim_fib_data *data; - struct net *net; + struct devlink *devlink = data->devlink; + struct nsim_fib4_rt *fib4_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_fib4_rt_destroy(fib4_rt); +} + +static void nsim_fib6_rt_free(struct nsim_fib_rt *fib_rt, + struct nsim_fib_data *data) +{ + struct nsim_fib6_rt *fib6_rt; - rcu_read_lock(); - for_each_net_rcu(net) { - data = net_generic(net, nsim_fib_net_id); + 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_destroy(fib6_rt); +} - data->ipv4.fib.num = 0ULL; - data->ipv4.rules.num = 0ULL; +static void nsim_fib_rt_free(void *ptr, void *arg) +{ + struct nsim_fib_rt *fib_rt = ptr; + struct nsim_fib_data *data = arg; - data->ipv6.fib.num = 0ULL; - data->ipv6.rules.num = 0ULL; + switch (fib_rt->key.family) { + case AF_INET: + nsim_fib4_rt_free(fib_rt, data); + break; + case AF_INET6: + nsim_fib6_rt_free(fib_rt, data); + break; + default: + WARN_ON_ONCE(1); } - rcu_read_unlock(); } -static struct notifier_block nsim_fib_nb = { - .notifier_call = nsim_fib_event_nb, -}; +/* inconsistent dump, trying again */ +static void nsim_fib_dump_inconsistent(struct notifier_block *nb) +{ + struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data, + fib_nb); + struct nsim_fib_rt *fib_rt, *fib_rt_tmp; -/* Initialize per network namespace state */ -static int __net_init nsim_fib_netns_init(struct net *net) + /* The notifier block is still not registered, so we do not need to + * take any locks here. + */ + 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); + } + + data->ipv4.rules.num = 0ULL; + data->ipv6.rules.num = 0ULL; +} + +static u64 nsim_fib_ipv4_resource_occ_get(void *priv) { - struct nsim_fib_data *data = net_generic(net, nsim_fib_net_id); + struct nsim_fib_data *data = priv; - data->ipv4.fib.max = (u64)-1; - data->ipv4.rules.max = (u64)-1; + return nsim_fib_get_val(data, NSIM_RESOURCE_IPV4_FIB, false); +} - data->ipv6.fib.max = (u64)-1; - data->ipv6.rules.max = (u64)-1; +static u64 nsim_fib_ipv4_rules_res_occ_get(void *priv) +{ + struct nsim_fib_data *data = priv; - return 0; + return nsim_fib_get_val(data, NSIM_RESOURCE_IPV4_FIB_RULES, false); } -static struct pernet_operations nsim_fib_net_ops = { - .init = nsim_fib_netns_init, - .id = &nsim_fib_net_id, - .size = sizeof(struct nsim_fib_data), -}; +static u64 nsim_fib_ipv6_resource_occ_get(void *priv) +{ + struct nsim_fib_data *data = priv; + + return nsim_fib_get_val(data, NSIM_RESOURCE_IPV6_FIB, false); +} + +static u64 nsim_fib_ipv6_rules_res_occ_get(void *priv) +{ + struct nsim_fib_data *data = priv; + + return nsim_fib_get_val(data, NSIM_RESOURCE_IPV6_FIB_RULES, false); +} -void nsim_fib_exit(void) +static void nsim_fib_set_max_all(struct nsim_fib_data *data, + struct devlink *devlink) { - unregister_pernet_subsys(&nsim_fib_net_ops); - unregister_fib_notifier(&nsim_fib_nb); + enum nsim_resource_id res_ids[] = { + NSIM_RESOURCE_IPV4_FIB, NSIM_RESOURCE_IPV4_FIB_RULES, + NSIM_RESOURCE_IPV6_FIB, NSIM_RESOURCE_IPV6_FIB_RULES + }; + int i; + + for (i = 0; i < ARRAY_SIZE(res_ids); i++) { + int err; + u64 val; + + err = devlink_resource_size_get(devlink, res_ids[i], &val); + if (err) + val = (u64) -1; + nsim_fib_set_max(data, res_ids[i], val); + } } -int nsim_fib_init(void) +struct nsim_fib_data *nsim_fib_create(struct devlink *devlink, + struct netlink_ext_ack *extack) { + struct nsim_fib_data *data; int err; - err = register_pernet_subsys(&nsim_fib_net_ops); - if (err < 0) { - pr_err("Failed to register pernet subsystem\n"); - goto err_out; - } + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return ERR_PTR(-ENOMEM); + data->devlink = devlink; + + spin_lock_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; + + nsim_fib_set_max_all(data, devlink); - err = register_fib_notifier(&nsim_fib_nb, nsim_fib_dump_inconsistent); - if (err < 0) { + 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_out; + goto err_rhashtable_destroy; } -err_out: - return err; + 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); + return data; + +err_rhashtable_destroy: + rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free, + data); +err_data_free: + kfree(data); + return ERR_PTR(err); +} + +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); + unregister_fib_notifier(devlink_net(devlink), &data->fib_nb); + rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free, + data); + WARN_ON_ONCE(!list_empty(&data->fib_rt_list)); + kfree(data); } diff --git a/drivers/net/netdevsim/health.c b/drivers/net/netdevsim/health.c new file mode 100644 index 000000000000..ba8d9ad60feb --- /dev/null +++ b/drivers/net/netdevsim/health.c @@ -0,0 +1,319 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Mellanox Technologies. All rights reserved */ + +#include <linux/debugfs.h> +#include <linux/err.h> +#include <linux/kernel.h> +#include <linux/slab.h> + +#include "netdevsim.h" + +static int +nsim_dev_empty_reporter_dump(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack) +{ + return 0; +} + +static int +nsim_dev_empty_reporter_diagnose(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) +{ + return 0; +} + +static const +struct devlink_health_reporter_ops nsim_dev_empty_reporter_ops = { + .name = "empty", + .dump = nsim_dev_empty_reporter_dump, + .diagnose = nsim_dev_empty_reporter_diagnose, +}; + +struct nsim_dev_dummy_reporter_ctx { + char *break_msg; +}; + +static int +nsim_dev_dummy_reporter_recover(struct devlink_health_reporter *reporter, + void *priv_ctx, + struct netlink_ext_ack *extack) +{ + struct nsim_dev_health *health = devlink_health_reporter_priv(reporter); + struct nsim_dev_dummy_reporter_ctx *ctx = priv_ctx; + + if (health->fail_recover) { + /* For testing purposes, user set debugfs fail_recover + * value to true. Fail right away. + */ + NL_SET_ERR_MSG_MOD(extack, "User setup the recover to fail for testing purposes"); + return -EINVAL; + } + if (ctx) { + kfree(health->recovered_break_msg); + health->recovered_break_msg = kstrdup(ctx->break_msg, + GFP_KERNEL); + if (!health->recovered_break_msg) + return -ENOMEM; + } + return 0; +} + +static int nsim_dev_dummy_fmsg_put(struct devlink_fmsg *fmsg, u32 binary_len) +{ + char *binary; + int err; + int i; + + err = devlink_fmsg_bool_pair_put(fmsg, "test_bool", true); + if (err) + return err; + err = devlink_fmsg_u8_pair_put(fmsg, "test_u8", 1); + if (err) + return err; + err = devlink_fmsg_u32_pair_put(fmsg, "test_u32", 3); + if (err) + return err; + err = devlink_fmsg_u64_pair_put(fmsg, "test_u64", 4); + if (err) + return err; + err = devlink_fmsg_string_pair_put(fmsg, "test_string", "somestring"); + if (err) + return err; + + binary = kmalloc(binary_len, GFP_KERNEL | __GFP_NOWARN); + if (!binary) + return -ENOMEM; + get_random_bytes(binary, binary_len); + err = devlink_fmsg_binary_pair_put(fmsg, "test_binary", binary, binary_len); + kfree(binary); + if (err) + return err; + + err = devlink_fmsg_pair_nest_start(fmsg, "test_nest"); + if (err) + return err; + err = devlink_fmsg_obj_nest_start(fmsg); + if (err) + return err; + err = devlink_fmsg_bool_pair_put(fmsg, "nested_test_bool", false); + if (err) + return err; + err = devlink_fmsg_u8_pair_put(fmsg, "nested_test_u8", false); + if (err) + return err; + err = devlink_fmsg_obj_nest_end(fmsg); + if (err) + return err; + err = devlink_fmsg_pair_nest_end(fmsg); + 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; + + err = devlink_fmsg_arr_pair_nest_start(fmsg, "test_u32_array"); + if (err) + return err; + for (i = 0; i < 10; i++) { + err = devlink_fmsg_u32_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_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; + for (i = 0; i < 10; i++) { + err = devlink_fmsg_obj_nest_start(fmsg); + if (err) + return err; + err = devlink_fmsg_bool_pair_put(fmsg, + "in_array_nested_test_bool", + false); + if (err) + return err; + err = devlink_fmsg_u8_pair_put(fmsg, + "in_array_nested_test_u8", + i); + if (err) + return err; + err = devlink_fmsg_obj_nest_end(fmsg); + if (err) + return err; + } + return devlink_fmsg_arr_pair_nest_end(fmsg); +} + +static int +nsim_dev_dummy_reporter_dump(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack) +{ + struct nsim_dev_health *health = devlink_health_reporter_priv(reporter); + struct nsim_dev_dummy_reporter_ctx *ctx = priv_ctx; + int err; + + if (ctx) { + err = devlink_fmsg_string_pair_put(fmsg, "break_message", + ctx->break_msg); + if (err) + return err; + } + return nsim_dev_dummy_fmsg_put(fmsg, health->binary_len); +} + +static int +nsim_dev_dummy_reporter_diagnose(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) +{ + struct nsim_dev_health *health = devlink_health_reporter_priv(reporter); + int err; + + if (health->recovered_break_msg) { + err = devlink_fmsg_string_pair_put(fmsg, + "recovered_break_message", + health->recovered_break_msg); + if (err) + return err; + } + return nsim_dev_dummy_fmsg_put(fmsg, health->binary_len); +} + +static const +struct devlink_health_reporter_ops nsim_dev_dummy_reporter_ops = { + .name = "dummy", + .recover = nsim_dev_dummy_reporter_recover, + .dump = nsim_dev_dummy_reporter_dump, + .diagnose = nsim_dev_dummy_reporter_diagnose, +}; + +static ssize_t nsim_dev_health_break_write(struct file *file, + const char __user *data, + size_t count, loff_t *ppos) +{ + struct nsim_dev_health *health = file->private_data; + struct nsim_dev_dummy_reporter_ctx ctx; + char *break_msg; + int err; + + break_msg = kmalloc(count + 1, GFP_KERNEL); + if (!break_msg) + return -ENOMEM; + + 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'; + + ctx.break_msg = break_msg; + err = devlink_health_report(health->dummy_reporter, break_msg, &ctx); + if (err) + goto out; + +out: + kfree(break_msg); + return err ?: count; +} + +static const struct file_operations nsim_dev_health_break_fops = { + .open = simple_open, + .write = nsim_dev_health_break_write, + .llseek = generic_file_llseek, +}; + +int nsim_dev_health_init(struct nsim_dev *nsim_dev, struct devlink *devlink) +{ + struct nsim_dev_health *health = &nsim_dev->health; + int err; + + health->empty_reporter = + devlink_health_reporter_create(devlink, + &nsim_dev_empty_reporter_ops, + 0, false, 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); + if (IS_ERR(health->dummy_reporter)) { + err = PTR_ERR(health->dummy_reporter); + goto err_empty_reporter_destroy; + } + + health->ddir = debugfs_create_dir("health", nsim_dev->ddir); + if (IS_ERR(health->ddir)) { + err = PTR_ERR(health->ddir); + goto err_dummy_reporter_destroy; + } + + health->recovered_break_msg = NULL; + debugfs_create_file("break_health", 0200, health->ddir, health, + &nsim_dev_health_break_fops); + health->binary_len = 16; + debugfs_create_u32("binary_len", 0600, health->ddir, + &health->binary_len); + health->fail_recover = false; + debugfs_create_bool("fail_recover", 0600, health->ddir, + &health->fail_recover); + return 0; + +err_dummy_reporter_destroy: + devlink_health_reporter_destroy(health->dummy_reporter); +err_empty_reporter_destroy: + devlink_health_reporter_destroy(health->empty_reporter); + return err; +} + +void nsim_dev_health_exit(struct nsim_dev *nsim_dev) +{ + struct nsim_dev_health *health = &nsim_dev->health; + + debugfs_remove_recursive(health->ddir); + kfree(health->recovered_break_msg); + devlink_health_reporter_destroy(health->dummy_reporter); + devlink_health_reporter_destroy(health->empty_reporter); +} diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 55f57f76d01b..2908e0a0d6e1 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -290,6 +290,7 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port) if (!dev) return ERR_PTR(-ENOMEM); + dev_net_set(dev, nsim_dev_net(nsim_dev)); ns = netdev_priv(dev); ns->netdev = dev; ns->nsim_dev = nsim_dev; @@ -357,18 +358,12 @@ static int __init nsim_module_init(void) if (err) goto err_dev_exit; - err = nsim_fib_init(); - if (err) - goto err_bus_exit; - err = rtnl_link_register(&nsim_link_ops); if (err) - goto err_fib_exit; + goto err_bus_exit; return 0; -err_fib_exit: - nsim_fib_exit(); err_bus_exit: nsim_bus_exit(); err_dev_exit: @@ -379,7 +374,6 @@ err_dev_exit: static void __exit nsim_module_exit(void) { rtnl_link_unregister(&nsim_link_ops); - nsim_fib_exit(); nsim_bus_exit(); nsim_dev_exit(); } diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 9404637d34b7..2eb7b0dc1594 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -134,6 +134,18 @@ enum nsim_resource_id { NSIM_RESOURCE_IPV6_FIB_RULES, }; +struct nsim_dev_health { + struct devlink_health_reporter *empty_reporter; + struct devlink_health_reporter *dummy_reporter; + struct dentry *ddir; + char *recovered_break_msg; + u32 binary_len; + bool fail_recover; +}; + +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_port { struct list_head list; struct devlink_port devlink_port; @@ -145,8 +157,10 @@ struct nsim_dev_port { struct nsim_dev { struct nsim_bus_dev *nsim_bus_dev; struct nsim_fib_data *fib_data; + struct nsim_trap_data *trap_data; struct dentry *ddir; struct dentry *ports_ddir; + struct dentry *take_snapshot; struct bpf_offload_dev *bpf_dev; bool bpf_bind_accept; u32 bpf_bind_verifier_delay; @@ -158,8 +172,19 @@ struct nsim_dev { struct list_head port_list; struct mutex port_list_lock; /* protects port list */ bool fw_update_status; + u32 max_macs; + bool test1; + bool dont_allow_reload; + bool fail_reload; + struct devlink_region *dummy_region; + struct nsim_dev_health health; }; +static inline struct net *nsim_dev_net(struct nsim_dev *nsim_dev) +{ + return devlink_net(priv_to_devlink(nsim_dev)); +} + int nsim_dev_init(void); void nsim_dev_exit(void); int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev); @@ -169,11 +194,11 @@ int nsim_dev_port_add(struct nsim_bus_dev *nsim_bus_dev, int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev, unsigned int port_index); -int nsim_fib_init(void); -void nsim_fib_exit(void); -u64 nsim_fib_get_val(struct net *net, enum nsim_resource_id res_id, bool max); -int nsim_fib_set_max(struct net *net, enum nsim_resource_id res_id, u64 val, - struct netlink_ext_ack *extack); +struct nsim_fib_data *nsim_fib_create(struct devlink *devlink, + struct netlink_ext_ack *extack); +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); #if IS_ENABLED(CONFIG_XFRM_OFFLOAD) void nsim_ipsec_init(struct netdevsim *ns); @@ -211,8 +236,14 @@ struct nsim_bus_dev { struct device dev; struct list_head list; unsigned int port_count; + struct net *initial_net; /* Purpose of this is to carry net pointer + * during the probe time only. + */ 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; }; int nsim_bus_init(void); diff --git a/drivers/net/netdevsim/sdev.c b/drivers/net/netdevsim/sdev.c deleted file mode 100644 index 6712da3340d6..000000000000 --- a/drivers/net/netdevsim/sdev.c +++ /dev/null @@ -1,69 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2019 Mellanox Technologies. All rights reserved */ - -#include <linux/debugfs.h> -#include <linux/err.h> -#include <linux/kernel.h> -#include <linux/slab.h> - -#include "netdevsim.h" - -static struct dentry *nsim_sdev_ddir; - -static u32 nsim_sdev_id; - -struct netdevsim_shared_dev *nsim_sdev_get(struct netdevsim *joinns) -{ - struct netdevsim_shared_dev *sdev; - char sdev_ddir_name[10]; - int err; - - if (joinns) { - if (WARN_ON(!joinns->sdev)) - return ERR_PTR(-EINVAL); - sdev = joinns->sdev; - sdev->refcnt++; - return sdev; - } - - sdev = kzalloc(sizeof(*sdev), GFP_KERNEL); - if (!sdev) - return ERR_PTR(-ENOMEM); - sdev->refcnt = 1; - sdev->switch_id = nsim_sdev_id++; - - sprintf(sdev_ddir_name, "%u", sdev->switch_id); - sdev->ddir = debugfs_create_dir(sdev_ddir_name, nsim_sdev_ddir); - if (IS_ERR_OR_NULL(sdev->ddir)) { - err = PTR_ERR_OR_ZERO(sdev->ddir) ?: -EINVAL; - goto err_sdev_free; - } - - return sdev; - -err_sdev_free: - nsim_sdev_id--; - kfree(sdev); - return ERR_PTR(err); -} - -void nsim_sdev_put(struct netdevsim_shared_dev *sdev) -{ - if (--sdev->refcnt) - return; - debugfs_remove_recursive(sdev->ddir); - kfree(sdev); -} - -int nsim_sdev_init(void) -{ - nsim_sdev_ddir = debugfs_create_dir(DRV_NAME "_sdev", NULL); - if (IS_ERR_OR_NULL(nsim_sdev_ddir)) - return -ENOMEM; - return 0; -} - -void nsim_sdev_exit(void) -{ - debugfs_remove_recursive(nsim_sdev_ddir); -} |