diff options
Diffstat (limited to 'include')
30 files changed, 434 insertions, 49 deletions
diff --git a/include/asm-generic/error-injection.h b/include/asm-generic/error-injection.h new file mode 100644 index 000000000000..296c65442f00 --- /dev/null +++ b/include/asm-generic/error-injection.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_GENERIC_ERROR_INJECTION_H +#define _ASM_GENERIC_ERROR_INJECTION_H + +#if defined(__KERNEL__) && !defined(__ASSEMBLY__) +enum { + EI_ETYPE_NONE, /* Dummy value for undefined case */ + EI_ETYPE_NULL, /* Return NULL if failure */ + EI_ETYPE_ERRNO, /* Return -ERRNO if failure */ + EI_ETYPE_ERRNO_NULL, /* Return -ERRNO or NULL if failure */ +}; + +struct error_injection_entry { + unsigned long addr; + int etype; +}; + +#ifdef CONFIG_FUNCTION_ERROR_INJECTION +/* + * Whitelist ganerating macro. Specify functions which can be + * error-injectable using this macro. + */ +#define ALLOW_ERROR_INJECTION(fname, _etype) \ +static struct error_injection_entry __used \ + __attribute__((__section__("_error_injection_whitelist"))) \ + _eil_addr_##fname = { \ + .addr = (unsigned long)fname, \ + .etype = EI_ETYPE_##_etype, \ + }; +#else +#define ALLOW_ERROR_INJECTION(fname, _etype) +#endif +#endif + +#endif /* _ASM_GENERIC_ERROR_INJECTION_H */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index a2e8582d094a..ebe544e048cd 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -136,13 +136,13 @@ #define KPROBE_BLACKLIST() #endif -#ifdef CONFIG_BPF_KPROBE_OVERRIDE -#define ERROR_INJECT_LIST() . = ALIGN(8); \ - VMLINUX_SYMBOL(__start_kprobe_error_inject_list) = .; \ - KEEP(*(_kprobe_error_inject_list)) \ - VMLINUX_SYMBOL(__stop_kprobe_error_inject_list) = .; +#ifdef CONFIG_FUNCTION_ERROR_INJECTION +#define ERROR_INJECT_WHITELIST() STRUCT_ALIGN(); \ + VMLINUX_SYMBOL(__start_error_injection_whitelist) = .;\ + KEEP(*(_error_injection_whitelist)) \ + VMLINUX_SYMBOL(__stop_error_injection_whitelist) = .; #else -#define ERROR_INJECT_LIST() +#define ERROR_INJECT_WHITELIST() #endif #ifdef CONFIG_EVENT_TRACING @@ -573,7 +573,7 @@ FTRACE_EVENTS() \ TRACE_SYSCALLS() \ KPROBE_BLACKLIST() \ - ERROR_INJECT_LIST() \ + ERROR_INJECT_WHITELIST() \ MEM_DISCARD(init.rodata) \ CLK_OF_TABLES() \ RESERVEDMEM_OF_TABLES() \ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 44f26f6df8fc..5c2c104dc2c5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -25,6 +25,7 @@ struct bpf_map; /* map is generic key/value storage optionally accesible by eBPF programs */ struct bpf_map_ops { /* funcs callable from userspace (via syscall) */ + int (*map_alloc_check)(union bpf_attr *attr); struct bpf_map *(*map_alloc)(union bpf_attr *attr); void (*map_release)(struct bpf_map *map, struct file *map_file); void (*map_free)(struct bpf_map *map); @@ -73,6 +74,33 @@ struct bpf_map { char name[BPF_OBJ_NAME_LEN]; }; +struct bpf_offloaded_map; + +struct bpf_map_dev_ops { + int (*map_get_next_key)(struct bpf_offloaded_map *map, + void *key, void *next_key); + int (*map_lookup_elem)(struct bpf_offloaded_map *map, + void *key, void *value); + int (*map_update_elem)(struct bpf_offloaded_map *map, + void *key, void *value, u64 flags); + int (*map_delete_elem)(struct bpf_offloaded_map *map, void *key); +}; + +struct bpf_offloaded_map { + struct bpf_map map; + struct net_device *netdev; + const struct bpf_map_dev_ops *dev_ops; + void *dev_priv; + struct list_head offloads; +}; + +static inline struct bpf_offloaded_map *map_to_offmap(struct bpf_map *map) +{ + return container_of(map, struct bpf_offloaded_map, map); +} + +extern const struct bpf_map_ops bpf_map_offload_ops; + /* function argument constraints */ enum bpf_arg_type { ARG_DONTCARE = 0, /* unused argument in helper function */ @@ -199,7 +227,7 @@ struct bpf_prog_offload_ops { int insn_idx, int prev_insn_idx); }; -struct bpf_dev_offload { +struct bpf_prog_offload { struct bpf_prog *prog; struct net_device *netdev; void *dev_priv; @@ -229,7 +257,7 @@ struct bpf_prog_aux { #ifdef CONFIG_SECURITY void *security; #endif - struct bpf_dev_offload *offload; + struct bpf_prog_offload *offload; union { struct work_struct work; struct rcu_head rcu; @@ -368,6 +396,7 @@ int __bpf_prog_charge(struct user_struct *user, u32 pages); void __bpf_prog_uncharge(struct user_struct *user, u32 pages); void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock); +void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); @@ -377,6 +406,7 @@ void bpf_map_put(struct bpf_map *map); int bpf_map_precharge_memlock(u32 pages); void *bpf_map_area_alloc(size_t size, int numa_node); void bpf_map_area_free(void *base); +void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); extern int sysctl_unprivileged_bpf_disabled; @@ -554,6 +584,15 @@ void bpf_prog_offload_destroy(struct bpf_prog *prog); int bpf_prog_offload_info_fill(struct bpf_prog_info *info, struct bpf_prog *prog); +int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value); +int bpf_map_offload_update_elem(struct bpf_map *map, + void *key, void *value, u64 flags); +int bpf_map_offload_delete_elem(struct bpf_map *map, void *key); +int bpf_map_offload_get_next_key(struct bpf_map *map, + void *key, void *next_key); + +bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map); + #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); @@ -561,6 +600,14 @@ static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux) { return aux->offload_requested; } + +static inline bool bpf_map_is_dev_bound(struct bpf_map *map) +{ + return unlikely(map->ops == &bpf_map_offload_ops); +} + +struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr); +void bpf_map_offload_map_free(struct bpf_map *map); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) @@ -572,6 +619,20 @@ static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux) { return false; } + +static inline bool bpf_map_is_dev_bound(struct bpf_map *map) +{ + return false; +} + +static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void bpf_map_offload_map_free(struct bpf_map *map) +{ +} #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_INET) @@ -613,15 +674,4 @@ extern const struct bpf_func_proto bpf_sock_map_update_proto; void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); -#if defined(__KERNEL__) && !defined(__ASSEMBLY__) -#ifdef CONFIG_BPF_KPROBE_OVERRIDE -#define BPF_ALLOW_ERROR_INJECTION(fname) \ -static unsigned long __used \ - __attribute__((__section__("_kprobe_error_inject_list"))) \ - _eil_addr_##fname = (unsigned long)fname; -#else -#define BPF_ALLOW_ERROR_INJECTION(fname) -#endif -#endif - #endif /* _LINUX_BPF_H */ diff --git a/include/linux/completion.h b/include/linux/completion.h index 94a59ba7d422..519e94915d18 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -32,7 +32,6 @@ struct completion { #define init_completion(x) __init_completion(x) static inline void complete_acquire(struct completion *x) {} static inline void complete_release(struct completion *x) {} -static inline void complete_release_commit(struct completion *x) {} #define COMPLETION_INITIALIZER(work) \ { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) } diff --git a/include/linux/cpu.h b/include/linux/cpu.h index a04ef7c15c6a..7b01bc11c692 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -47,6 +47,13 @@ extern void cpu_remove_dev_attr(struct device_attribute *attr); extern int cpu_add_dev_attr_group(struct attribute_group *attrs); extern void cpu_remove_dev_attr_group(struct attribute_group *attrs); +extern ssize_t cpu_show_meltdown(struct device *dev, + struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_spectre_v1(struct device *dev, + struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_spectre_v2(struct device *dev, + struct device_attribute *attr, char *buf); + extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, const struct attribute_group **groups, diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 06097ef30449..b511f6d24b42 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -42,6 +42,8 @@ phys_addr_t paddr_vmcoreinfo_note(void); vmcoreinfo_append_str("PAGESIZE=%ld\n", value) #define VMCOREINFO_SYMBOL(name) \ vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)&name) +#define VMCOREINFO_SYMBOL_ARRAY(name) \ + vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)name) #define VMCOREINFO_SIZE(name) \ vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ (unsigned long)sizeof(name)) diff --git a/include/linux/error-injection.h b/include/linux/error-injection.h new file mode 100644 index 000000000000..280c61ecbf20 --- /dev/null +++ b/include/linux/error-injection.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_ERROR_INJECTION_H +#define _LINUX_ERROR_INJECTION_H + +#ifdef CONFIG_FUNCTION_ERROR_INJECTION + +#include <asm/error-injection.h> + +extern bool within_error_injection_list(unsigned long addr); +extern int get_injectable_error_type(unsigned long addr); + +#else /* !CONFIG_FUNCTION_ERROR_INJECTION */ + +#include <asm-generic/error-injection.h> +static inline bool within_error_injection_list(unsigned long addr) +{ + return false; +} + +static inline int get_injectable_error_type(unsigned long addr) +{ + return EI_ETYPE_NONE; +} + +#endif + +#endif /* _LINUX_ERROR_INJECTION_H */ diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 46cb57d5eb13..1b3996ff3f16 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -27,22 +27,18 @@ # define trace_hardirq_enter() \ do { \ current->hardirq_context++; \ - crossrelease_hist_start(XHLOCK_HARD); \ } while (0) # define trace_hardirq_exit() \ do { \ current->hardirq_context--; \ - crossrelease_hist_end(XHLOCK_HARD); \ } while (0) # define lockdep_softirq_enter() \ do { \ current->softirq_context++; \ - crossrelease_hist_start(XHLOCK_SOFT); \ } while (0) # define lockdep_softirq_exit() \ do { \ current->softirq_context--; \ - crossrelease_hist_end(XHLOCK_SOFT); \ } while (0) # define INIT_TRACE_IRQFLAGS .softirqs_enabled = 1, #else diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 963fd364f3d6..9440a2fc8893 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -271,7 +271,6 @@ extern bool arch_kprobe_on_func_entry(unsigned long offset); extern bool kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset); extern bool within_kprobe_blacklist(unsigned long addr); -extern bool within_kprobe_error_injection_list(unsigned long addr); struct kprobe_insn_cache { struct mutex mutex; diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 2e75dc34bff5..3251d9c0d313 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -475,8 +475,6 @@ enum xhlock_context_t { #define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ { .name = (_name), .key = (void *)(_key), } -static inline void crossrelease_hist_start(enum xhlock_context_t c) {} -static inline void crossrelease_hist_end(enum xhlock_context_t c) {} static inline void lockdep_invariant_state(bool force) {} static inline void lockdep_init_task(struct task_struct *task) {} static inline void lockdep_free_task(struct task_struct *task) {} diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1f509d072026..a0610427e168 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -36,6 +36,7 @@ #include <linux/kernel.h> #include <linux/completion.h> #include <linux/pci.h> +#include <linux/irq.h> #include <linux/spinlock_types.h> #include <linux/semaphore.h> #include <linux/slab.h> @@ -1231,7 +1232,23 @@ enum { static inline const struct cpumask * mlx5_get_vector_affinity(struct mlx5_core_dev *dev, int vector) { - return pci_irq_get_affinity(dev->pdev, MLX5_EQ_VEC_COMP_BASE + vector); + const struct cpumask *mask; + struct irq_desc *desc; + unsigned int irq; + int eqn; + int err; + + err = mlx5_vector2eqn(dev, vector, &eqn, &irq); + if (err) + return NULL; + + desc = irq_to_desc(irq); +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + mask = irq_data_get_effective_affinity_mask(&desc->irq_data); +#else + mask = desc->irq_common_data.affinity; +#endif + return mask; } #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 78e36fc2609e..acd829d8613b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1035,8 +1035,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_wq_sz[0x5]; u8 nic_vport_change_event[0x1]; - u8 disable_local_lb[0x1]; - u8 reserved_at_3e2[0x1]; + u8 disable_local_lb_uc[0x1]; + u8 disable_local_lb_mc[0x1]; u8 log_min_hairpin_wq_data_sz[0x5]; u8 reserved_at_3e8[0x3]; u8 log_max_vlan_list[0x5]; diff --git a/include/linux/module.h b/include/linux/module.h index 548fa09fa806..9642d3116718 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -19,6 +19,7 @@ #include <linux/jump_label.h> #include <linux/export.h> #include <linux/rbtree_latch.h> +#include <linux/error-injection.h> #include <linux/percpu.h> #include <asm/module.h> @@ -476,9 +477,9 @@ struct module { unsigned int num_ctors; #endif -#ifdef CONFIG_BPF_KPROBE_OVERRIDE - unsigned int num_kprobe_ei_funcs; - unsigned long *kprobe_ei_funcs; +#ifdef CONFIG_FUNCTION_ERROR_INJECTION + struct error_injection_entry *ei_funcs; + unsigned int num_ei_funcs; #endif } ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6d95477b962c..ed0799a12bf2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -805,6 +805,8 @@ enum bpf_netdev_command { BPF_OFFLOAD_VERIFIER_PREP, BPF_OFFLOAD_TRANSLATE, BPF_OFFLOAD_DESTROY, + BPF_OFFLOAD_MAP_ALLOC, + BPF_OFFLOAD_MAP_FREE, }; struct bpf_prog_offload_ops; @@ -835,6 +837,10 @@ struct netdev_bpf { struct { struct bpf_prog *prog; } offload; + /* BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE */ + struct { + struct bpf_offloaded_map *offmap; + }; }; }; diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 49b4257ce1ea..f3075d6c7e82 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -85,7 +85,7 @@ struct netlink_ext_ack { * to the lack of an output buffer.) */ #define NL_SET_ERR_MSG(extack, msg) do { \ - static const char __msg[] = (msg); \ + static const char __msg[] = msg; \ struct netlink_ext_ack *__extack = (extack); \ \ if (__extack) \ @@ -101,7 +101,7 @@ struct netlink_ext_ack { } while (0) #define NL_SET_ERR_MSG_ATTR(extack, attr, msg) do { \ - static const char __msg[] = (msg); \ + static const char __msg[] = msg; \ struct netlink_ext_ack *__extack = (extack); \ \ if (__extack) { \ diff --git a/include/linux/phy.h b/include/linux/phy.h index 47715a3115b0..5a0c3e53e7c2 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -765,6 +765,55 @@ int __phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); /** + * __phy_set_bits - Convenience function for setting bits in a PHY register + * @phydev: the phy_device struct + * @regnum: register number to write + * @val: bits to set + * + * The caller must have taken the MDIO bus lock. + */ +static inline int __phy_set_bits(struct phy_device *phydev, u32 regnum, u16 val) +{ + return __phy_modify(phydev, regnum, 0, val); +} + +/** + * __phy_clear_bits - Convenience function for clearing bits in a PHY register + * @phydev: the phy_device struct + * @regnum: register number to write + * @val: bits to clear + * + * The caller must have taken the MDIO bus lock. + */ +static inline int __phy_clear_bits(struct phy_device *phydev, u32 regnum, + u16 val) +{ + return __phy_modify(phydev, regnum, val, 0); +} + +/** + * phy_set_bits - Convenience function for setting bits in a PHY register + * @phydev: the phy_device struct + * @regnum: register number to write + * @val: bits to set + */ +static inline int phy_set_bits(struct phy_device *phydev, u32 regnum, u16 val) +{ + return phy_modify(phydev, regnum, 0, val); +} + +/** + * phy_clear_bits - Convenience function for clearing bits in a PHY register + * @phydev: the phy_device struct + * @regnum: register number to write + * @val: bits to clear + */ +static inline int phy_clear_bits(struct phy_device *phydev, u32 regnum, u16 val) +{ + return phy_modify(phydev, regnum, val, 0); +} + +/** * phy_interrupt_is_valid - Convenience function for testing a given PHY irq * @phydev: the phy_device struct * diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index 13fb06a103c6..9ca1726ff963 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -174,6 +174,15 @@ static inline int ptr_ring_produce_bh(struct ptr_ring *r, void *ptr) * if they dereference the pointer - see e.g. PTR_RING_PEEK_CALL. * If ring is never resized, and if the pointer is merely * tested, there's no need to take the lock - see e.g. __ptr_ring_empty. + * However, if called outside the lock, and if some other CPU + * consumes ring entries at the same time, the value returned + * is not guaranteed to be correct. + * In this case - to avoid incorrectly detecting the ring + * as empty - the CPU consuming the ring entries is responsible + * for either consuming all ring entries until the ring is empty, + * or synchronizing with some other CPU and causing it to + * execute __ptr_ring_peek and/or consume the ring enteries + * after the synchronization point. */ static inline void *__ptr_ring_peek(struct ptr_ring *r) { @@ -182,10 +191,7 @@ static inline void *__ptr_ring_peek(struct ptr_ring *r) return NULL; } -/* Note: callers invoking this in a loop must use a compiler barrier, - * for example cpu_relax(). Callers must take consumer_lock - * if the ring is ever resized - see e.g. ptr_ring_empty. - */ +/* See __ptr_ring_peek above for locking rules. */ static inline bool __ptr_ring_empty(struct ptr_ring *r) { return !__ptr_ring_peek(r); diff --git a/include/net/arp.h b/include/net/arp.h index dc8cd47f883b..977aabfcdc03 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -20,6 +20,9 @@ static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32 static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) { + if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) + key = INADDR_ANY; + return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev); } diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index ab30a22ef4fd..81174f9b8d14 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -815,6 +815,8 @@ struct cfg80211_csa_settings { u8 count; }; +#define CFG80211_MAX_NUM_DIFFERENT_CHANNELS 10 + /** * struct iface_combination_params - input parameters for interface combinations * diff --git a/include/net/devlink.h b/include/net/devlink.h index b9654e133599..6545b03e97f7 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -26,10 +26,12 @@ struct devlink { struct list_head port_list; struct list_head sb_list; struct list_head dpipe_table_list; + struct list_head resource_list; struct devlink_dpipe_headers *dpipe_headers; const struct devlink_ops *ops; struct device *dev; possible_net_t _net; + struct mutex lock; char priv[0] __aligned(NETDEV_ALIGN); }; @@ -181,6 +183,9 @@ struct devlink_dpipe_table_ops; * @counters_enabled: indicates if counters are active * @counter_control_extern: indicates if counter control is in dpipe or * external tool + * @resource_valid: Indicate that the resource id is valid + * @resource_id: relative resource this table is related to + * @resource_units: number of resource's unit consumed per table's entry * @table_ops: table operations * @rcu: rcu */ @@ -190,6 +195,9 @@ struct devlink_dpipe_table { const char *name; bool counters_enabled; bool counter_control_extern; + bool resource_valid; + u64 resource_id; + u64 resource_units; struct devlink_dpipe_table_ops *table_ops; struct rcu_head rcu; }; @@ -223,7 +231,63 @@ struct devlink_dpipe_headers { unsigned int headers_count; }; +/** + * struct devlink_resource_ops - resource ops + * @occ_get: get the occupied size + * @size_validate: validate the size of the resource before update, reload + * is needed for changes to take place + */ +struct devlink_resource_ops { + u64 (*occ_get)(struct devlink *devlink); + int (*size_validate)(struct devlink *devlink, u64 size, + struct netlink_ext_ack *extack); +}; + +/** + * struct devlink_resource_size_params - resource's size parameters + * @size_min: minimum size which can be set + * @size_max: maximum size which can be set + * @size_granularity: size granularity + * @size_unit: resource's basic unit + */ +struct devlink_resource_size_params { + u64 size_min; + u64 size_max; + u64 size_granularity; + enum devlink_resource_unit unit; +}; + +/** + * struct devlink_resource - devlink resource + * @name: name of the resource + * @id: id, per devlink instance + * @size: size of the resource + * @size_new: updated size of the resource, reload is needed + * @size_valid: valid in case the total size of the resource is valid + * including its children + * @parent: parent resource + * @size_params: size parameters + * @list: parent list + * @resource_list: list of child resources + * @resource_ops: resource ops + */ +struct devlink_resource { + const char *name; + u64 id; + u64 size; + u64 size_new; + bool size_valid; + struct devlink_resource *parent; + struct devlink_resource_size_params *size_params; + struct list_head list; + struct list_head resource_list; + const struct devlink_resource_ops *resource_ops; +}; + +#define DEVLINK_RESOURCE_ID_PARENT_TOP 0 + struct devlink_ops { + int (*reload)(struct devlink *devlink); int (*port_type_set)(struct devlink_port *devlink_port, enum devlink_port_type port_type); int (*port_split)(struct devlink *devlink, unsigned int port_index, @@ -332,6 +396,23 @@ extern struct devlink_dpipe_header devlink_dpipe_header_ethernet; extern struct devlink_dpipe_header devlink_dpipe_header_ipv4; extern struct devlink_dpipe_header devlink_dpipe_header_ipv6; +int devlink_resource_register(struct devlink *devlink, + const char *resource_name, + bool top_hierarchy, + u64 resource_size, + u64 resource_id, + u64 parent_resource_id, + struct devlink_resource_size_params *size_params, + const struct devlink_resource_ops *resource_ops); +void devlink_resources_unregister(struct devlink *devlink, + struct devlink_resource *resource); +int devlink_resource_size_get(struct devlink *devlink, + u64 resource_id, + u64 *p_resource_size); +int devlink_dpipe_table_resource_set(struct devlink *devlink, + const char *table_name, u64 resource_id, + u64 resource_units); + #else static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, @@ -468,6 +549,40 @@ devlink_dpipe_match_put(struct sk_buff *skb, return 0; } +static inline int +devlink_resource_register(struct devlink *devlink, + const char *resource_name, + bool top_hierarchy, + u64 resource_size, + u64 resource_id, + u64 parent_resource_id, + struct devlink_resource_size_params *size_params, + const struct devlink_resource_ops *resource_ops) +{ + return 0; +} + +static inline void +devlink_resources_unregister(struct devlink *devlink, + struct devlink_resource *resource) +{ +} + +static inline int +devlink_resource_size_get(struct devlink *devlink, u64 resource_id, + u64 *p_resource_size) +{ + return -EOPNOTSUPP; +} + +static inline int +devlink_dpipe_table_resource_set(struct devlink *devlink, + const char *table_name, u64 resource_id, + u64 resource_units) +{ + return -EOPNOTSUPP; +} + #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 9c341f003091..789d818c4a61 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -29,6 +29,7 @@ struct tcf_block_ext_info { enum tcf_block_binder_type binder_type; tcf_chain_head_change_t *chain_head_change; void *chain_head_change_priv; + u32 block_index; }; struct tcf_block_cb; @@ -38,6 +39,7 @@ bool tcf_queue_work(struct work_struct *work); struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, bool create); void tcf_chain_put(struct tcf_chain *chain); +void tcf_block_netif_keep_dst(struct tcf_block *block); int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q, struct netlink_ext_ack *extack); @@ -48,8 +50,14 @@ void tcf_block_put(struct tcf_block *block); void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, struct tcf_block_ext_info *ei); +static inline bool tcf_block_shared(struct tcf_block *block) +{ + return block->index; +} + static inline struct Qdisc *tcf_block_q(struct tcf_block *block) { + WARN_ON(tcf_block_shared(block)); return block->q; } @@ -748,6 +756,7 @@ struct tc_red_qopt_offload_params { u32 max; u32 probability; bool is_ecn; + struct gnet_stats_queue *qstats; }; struct tc_red_qopt_offload { diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index e2c75f52557b..815b92a23936 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -100,7 +100,6 @@ int qdisc_set_default(const char *id); void qdisc_hash_add(struct Qdisc *q, bool invisible); void qdisc_hash_del(struct Qdisc *q); struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle); -struct Qdisc *qdisc_lookup_class(struct net_device *dev, u32 handle); struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab, struct netlink_ext_ack *extack); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index ac029d5d88e4..cfc19d0ba2ad 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -204,6 +204,13 @@ struct Qdisc_ops { int (*dump)(struct Qdisc *, struct sk_buff *); int (*dump_stats)(struct Qdisc *, struct gnet_dump *); + void (*ingress_block_set)(struct Qdisc *sch, + u32 block_index); + void (*egress_block_set)(struct Qdisc *sch, + u32 block_index); + u32 (*ingress_block_get)(struct Qdisc *sch); + u32 (*egress_block_get)(struct Qdisc *sch); + struct module *owner; }; @@ -255,8 +262,6 @@ struct tcf_proto { /* All the rest */ u32 prio; - u32 classid; - struct Qdisc *q; void *data; const struct tcf_proto_ops *ops; struct tcf_chain *chain; @@ -275,8 +280,7 @@ typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv); struct tcf_chain { struct tcf_proto __rcu *filter_chain; - tcf_chain_head_change_t *chain_head_change; - void *chain_head_change_priv; + struct list_head filter_chain_list; struct list_head list; struct tcf_block *block; u32 index; /* chain index */ @@ -285,11 +289,33 @@ struct tcf_chain { struct tcf_block { struct list_head chain_list; + u32 index; /* block index for shared blocks */ + unsigned int refcnt; struct net *net; struct Qdisc *q; struct list_head cb_list; + struct list_head owner_list; + bool keep_dst; + unsigned int offloadcnt; /* Number of oddloaded filters */ + unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */ }; +static inline void tcf_block_offload_inc(struct tcf_block *block, u32 *flags) +{ + if (*flags & TCA_CLS_FLAGS_IN_HW) + return; + *flags |= TCA_CLS_FLAGS_IN_HW; + block->offloadcnt++; +} + +static inline void tcf_block_offload_dec(struct tcf_block *block, u32 *flags) +{ + if (!(*flags & TCA_CLS_FLAGS_IN_HW)) + return; + *flags &= ~TCA_CLS_FLAGS_IN_HW; + block->offloadcnt--; +} + static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) { struct qdisc_skb_cb *qcb; @@ -473,6 +499,7 @@ void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n, struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, struct netlink_ext_ack *extack); +void qdisc_free(struct Qdisc *qdisc); struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, u32 parentid, struct netlink_ext_ack *extack); diff --git a/include/net/tls.h b/include/net/tls.h index 936cfc5cab7d..9185e53a743c 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -170,7 +170,7 @@ static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx) static inline void tls_err_abort(struct sock *sk) { - sk->sk_err = -EBADMSG; + sk->sk_err = EBADMSG; sk->sk_error_report(sk); } diff --git a/include/net/vxlan.h b/include/net/vxlan.h index f96391e84a8a..ad73d8b3fcc2 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -301,7 +301,7 @@ static inline netdev_features_t vxlan_features_check(struct sk_buff *skb, l4_hdr = ipv6_hdr(skb)->nexthdr; break; default: - return features;; + return features; } if ((l4_hdr == IPPROTO_UDP) && diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 405317f9c064..7c2259e8bc54 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -245,6 +245,7 @@ union bpf_attr { * BPF_F_NUMA_NODE is set). */ char map_name[BPF_OBJ_NAME_LEN]; + __u32 map_ifindex; /* ifindex of netdev to create on */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -899,7 +900,7 @@ struct xdp_md { __u32 data; __u32 data_end; __u32 data_meta; - /* Below access go though struct xdp_rxq_info */ + /* Below access go through struct xdp_rxq_info */ __u32 ingress_ifindex; /* rxq->dev->ifindex */ __u32 rx_queue_index; /* rxq->queue_index */ }; diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 6665df69e26a..1df65a4c2044 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -70,6 +70,13 @@ enum devlink_command { DEVLINK_CMD_DPIPE_ENTRIES_GET, DEVLINK_CMD_DPIPE_HEADERS_GET, DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET, + DEVLINK_CMD_RESOURCE_SET, + DEVLINK_CMD_RESOURCE_DUMP, + + /* Hot driver reload, makes configuration changes take place. The + * devlink instance is not released during the process. + */ + DEVLINK_CMD_RELOAD, /* add new commands above here */ __DEVLINK_CMD_MAX, @@ -202,6 +209,20 @@ enum devlink_attr { DEVLINK_ATTR_PAD, DEVLINK_ATTR_ESWITCH_ENCAP_MODE, /* u8 */ + DEVLINK_ATTR_RESOURCE_LIST, /* nested */ + DEVLINK_ATTR_RESOURCE, /* nested */ + DEVLINK_ATTR_RESOURCE_NAME, /* string */ + DEVLINK_ATTR_RESOURCE_ID, /* u64 */ + DEVLINK_ATTR_RESOURCE_SIZE, /* u64 */ + DEVLINK_ATTR_RESOURCE_SIZE_NEW, /* u64 */ + DEVLINK_ATTR_RESOURCE_SIZE_VALID, /* u8 */ + DEVLINK_ATTR_RESOURCE_SIZE_MIN, /* u64 */ + DEVLINK_ATTR_RESOURCE_SIZE_MAX, /* u64 */ + DEVLINK_ATTR_RESOURCE_SIZE_GRAN, /* u64 */ + DEVLINK_ATTR_RESOURCE_UNIT, /* u8 */ + DEVLINK_ATTR_RESOURCE_OCC, /* u64 */ + DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID, /* u64 */ + DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS,/* u64 */ /* add new attributes above here, update the policy in devlink.c */ @@ -245,4 +266,8 @@ enum devlink_dpipe_header_id { DEVLINK_DPIPE_HEADER_IPV6, }; +enum devlink_resource_unit { + DEVLINK_RESOURCE_UNIT_ENTRY, +}; + #endif /* _UAPI_LINUX_DEVLINK_H_ */ diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h index fb38c1797131..ee432cd3018c 100644 --- a/include/uapi/linux/if_tun.h +++ b/include/uapi/linux/if_tun.h @@ -58,6 +58,7 @@ #define TUNSETVNETBE _IOW('T', 222, int) #define TUNGETVNETBE _IOR('T', 223, int) #define TUNSETSTEERINGEBPF _IOR('T', 224, int) +#define TUNSETFILTEREBPF _IOR('T', 225, int) /* TUNSETIFF ifr flags */ #define IFF_TUN 0x0001 diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 4265d7f9e1f2..dcfab5e3b55c 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -363,7 +363,6 @@ enum ovs_tunnel_key_attr { OVS_TUNNEL_KEY_ATTR_IPV6_SRC, /* struct in6_addr src IPv6 address. */ OVS_TUNNEL_KEY_ATTR_IPV6_DST, /* struct in6_addr dst IPv6 address. */ OVS_TUNNEL_KEY_ATTR_PAD, - OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, /* be32 ERSPAN index. */ __OVS_TUNNEL_KEY_ATTR_MAX }; diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 843e29aa3cac..9b15005955fa 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -541,9 +541,19 @@ struct tcmsg { int tcm_ifindex; __u32 tcm_handle; __u32 tcm_parent; +/* tcm_block_index is used instead of tcm_parent + * in case tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK + */ +#define tcm_block_index tcm_parent __u32 tcm_info; }; +/* For manipulation of filters in shared block, tcm_ifindex is set to + * TCM_IFINDEX_MAGIC_BLOCK, and tcm_parent is aliased to tcm_block_index + * which is the block index. + */ +#define TCM_IFINDEX_MAGIC_BLOCK (0xFFFFFFFFU) + enum { TCA_UNSPEC, TCA_KIND, @@ -558,6 +568,8 @@ enum { TCA_DUMP_INVISIBLE, TCA_CHAIN, TCA_HW_OFFLOAD, + TCA_INGRESS_BLOCK, + TCA_EGRESS_BLOCK, __TCA_MAX }; |