diff options
Diffstat (limited to 'include')
112 files changed, 1820 insertions, 796 deletions
diff --git a/include/asm-generic/compat.h b/include/asm-generic/compat.h index 30f7b18a36f9..d46c0201cc34 100644 --- a/include/asm-generic/compat.h +++ b/include/asm-generic/compat.h @@ -20,7 +20,18 @@ typedef u16 compat_ushort_t; typedef u32 compat_uint_t; typedef u32 compat_ulong_t; typedef u32 compat_uptr_t; +typedef u32 compat_caddr_t; typedef u32 compat_aio_context_t; +typedef u32 compat_old_sigset_t; + +#ifndef __compat_uid32_t +typedef u32 __compat_uid32_t; +typedef u32 __compat_gid32_t; +#endif + +#ifndef compat_mode_t +typedef u32 compat_mode_t; +#endif #ifdef CONFIG_COMPAT_FOR_U64_ALIGNMENT typedef s64 __attribute__((aligned(4))) compat_s64; @@ -30,4 +41,10 @@ typedef s64 compat_s64; typedef u64 compat_u64; #endif +#ifndef _COMPAT_NSIG +typedef u32 compat_sigset_word; +#define _COMPAT_NSIG _NSIG +#define _COMPAT_NSIG_BPW 32 +#endif + #endif diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 26bf15e6cd35..5e62e2383b7f 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -4,6 +4,7 @@ #include <asm/types.h> #include <linux/bits.h> +#include <linux/typecheck.h> #include <uapi/linux/kernel.h> @@ -253,6 +254,55 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, __clear_bit(nr, addr); } +/** + * __ptr_set_bit - Set bit in a pointer's value + * @nr: the bit to set + * @addr: the address of the pointer variable + * + * Example: + * void *p = foo(); + * __ptr_set_bit(bit, &p); + */ +#define __ptr_set_bit(nr, addr) \ + ({ \ + typecheck_pointer(*(addr)); \ + __set_bit(nr, (unsigned long *)(addr)); \ + }) + +/** + * __ptr_clear_bit - Clear bit in a pointer's value + * @nr: the bit to clear + * @addr: the address of the pointer variable + * + * Example: + * void *p = foo(); + * __ptr_clear_bit(bit, &p); + */ +#define __ptr_clear_bit(nr, addr) \ + ({ \ + typecheck_pointer(*(addr)); \ + __clear_bit(nr, (unsigned long *)(addr)); \ + }) + +/** + * __ptr_test_bit - Test bit in a pointer's value + * @nr: the bit to test + * @addr: the address of the pointer variable + * + * Example: + * void *p = foo(); + * if (__ptr_test_bit(bit, &p)) { + * ... + * } else { + * ... + * } + */ +#define __ptr_test_bit(nr, addr) \ + ({ \ + typecheck_pointer(*(addr)); \ + test_bit(nr, (unsigned long *)(addr)); \ + }) + #ifdef __KERNEL__ #ifndef set_mask_bits diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 6c9b10d82c80..a74cd1c3bd87 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -27,19 +27,6 @@ struct task_struct; extern struct static_key_false cgroup_bpf_enabled_key[MAX_BPF_ATTACH_TYPE]; #define cgroup_bpf_enabled(type) static_branch_unlikely(&cgroup_bpf_enabled_key[type]) -#define BPF_CGROUP_STORAGE_NEST_MAX 8 - -struct bpf_cgroup_storage_info { - struct task_struct *task; - struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; -}; - -/* For each cpu, permit maximum BPF_CGROUP_STORAGE_NEST_MAX number of tasks - * to use bpf cgroup storage simultaneously. - */ -DECLARE_PER_CPU(struct bpf_cgroup_storage_info, - bpf_cgroup_storage_info[BPF_CGROUP_STORAGE_NEST_MAX]); - #define for_each_cgroup_storage_type(stype) \ for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) @@ -172,44 +159,6 @@ static inline enum bpf_cgroup_storage_type cgroup_storage_type( return BPF_CGROUP_STORAGE_SHARED; } -static inline int bpf_cgroup_storage_set(struct bpf_cgroup_storage - *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) -{ - enum bpf_cgroup_storage_type stype; - int i, err = 0; - - preempt_disable(); - for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { - if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != NULL)) - continue; - - this_cpu_write(bpf_cgroup_storage_info[i].task, current); - for_each_cgroup_storage_type(stype) - this_cpu_write(bpf_cgroup_storage_info[i].storage[stype], - storage[stype]); - goto out; - } - err = -EBUSY; - WARN_ON_ONCE(1); - -out: - preempt_enable(); - return err; -} - -static inline void bpf_cgroup_storage_unset(void) -{ - int i; - - for (i = BPF_CGROUP_STORAGE_NEST_MAX - 1; i >= 0; i--) { - if (likely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) - continue; - - this_cpu_write(bpf_cgroup_storage_info[i].task, NULL); - return; - } -} - struct bpf_cgroup_storage * cgroup_storage_lookup(struct bpf_cgroup_storage_map *map, void *key, bool locked); @@ -487,9 +436,6 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, return -EINVAL; } -static inline int bpf_cgroup_storage_set( - struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) { return 0; } -static inline void bpf_cgroup_storage_unset(void) {} static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map) { return 0; } static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e8e2b0393ca9..c8cc09013210 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -168,6 +168,7 @@ struct bpf_map { u32 max_entries; u32 map_flags; int spin_lock_off; /* >=0 valid offset, <0 error */ + int timer_off; /* >=0 valid offset, <0 error */ u32 id; int numa_node; u32 btf_key_type_id; @@ -197,30 +198,53 @@ static inline bool map_value_has_spin_lock(const struct bpf_map *map) return map->spin_lock_off >= 0; } -static inline void check_and_init_map_lock(struct bpf_map *map, void *dst) +static inline bool map_value_has_timer(const struct bpf_map *map) { - if (likely(!map_value_has_spin_lock(map))) - return; - *(struct bpf_spin_lock *)(dst + map->spin_lock_off) = - (struct bpf_spin_lock){}; + return map->timer_off >= 0; } -/* copy everything but bpf_spin_lock */ +static inline void check_and_init_map_value(struct bpf_map *map, void *dst) +{ + if (unlikely(map_value_has_spin_lock(map))) + *(struct bpf_spin_lock *)(dst + map->spin_lock_off) = + (struct bpf_spin_lock){}; + if (unlikely(map_value_has_timer(map))) + *(struct bpf_timer *)(dst + map->timer_off) = + (struct bpf_timer){}; +} + +/* copy everything but bpf_spin_lock and bpf_timer. There could be one of each. */ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) { + u32 s_off = 0, s_sz = 0, t_off = 0, t_sz = 0; + if (unlikely(map_value_has_spin_lock(map))) { - u32 off = map->spin_lock_off; + s_off = map->spin_lock_off; + s_sz = sizeof(struct bpf_spin_lock); + } else if (unlikely(map_value_has_timer(map))) { + t_off = map->timer_off; + t_sz = sizeof(struct bpf_timer); + } - memcpy(dst, src, off); - memcpy(dst + off + sizeof(struct bpf_spin_lock), - src + off + sizeof(struct bpf_spin_lock), - map->value_size - off - sizeof(struct bpf_spin_lock)); + if (unlikely(s_sz || t_sz)) { + if (s_off < t_off || !s_sz) { + swap(s_off, t_off); + swap(s_sz, t_sz); + } + memcpy(dst, src, t_off); + memcpy(dst + t_off + t_sz, + src + t_off + t_sz, + s_off - t_off - t_sz); + memcpy(dst + s_off + s_sz, + src + s_off + s_sz, + map->value_size - s_off - s_sz); } else { memcpy(dst, src, map->value_size); } } void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); +void bpf_timer_cancel_and_free(void *timer); int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size); struct bpf_offload_dev; @@ -314,6 +338,7 @@ enum bpf_arg_type { ARG_PTR_TO_FUNC, /* pointer to a bpf program function */ ARG_PTR_TO_STACK_OR_NULL, /* pointer to stack or NULL */ ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ + ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ __BPF_ARG_TYPE_MAX, }; @@ -554,6 +579,11 @@ struct btf_func_model { */ #define BPF_TRAMP_F_SKIP_FRAME BIT(2) +/* Store IP address of the caller on the trampoline stack, + * so it's available for trampoline's programs. + */ +#define BPF_TRAMP_F_IP_ARG BIT(3) + /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 */ @@ -1112,38 +1142,40 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *include_prog, struct bpf_prog_array **new_array); +struct bpf_run_ctx {}; + +struct bpf_cg_run_ctx { + struct bpf_run_ctx run_ctx; + struct bpf_prog_array_item *prog_item; +}; + /* BPF program asks to bypass CAP_NET_BIND_SERVICE in bind. */ #define BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE (1 << 0) /* BPF program asks to set CN on the packet. */ #define BPF_RET_SET_CN (1 << 0) -/* For BPF_PROG_RUN_ARRAY_FLAGS and __BPF_PROG_RUN_ARRAY, - * if bpf_cgroup_storage_set() failed, the rest of programs - * will not execute. This should be a really rare scenario - * as it requires BPF_CGROUP_STORAGE_NEST_MAX number of - * preemptions all between bpf_cgroup_storage_set() and - * bpf_cgroup_storage_unset() on the same cpu. - */ #define BPF_PROG_RUN_ARRAY_FLAGS(array, ctx, func, ret_flags) \ ({ \ struct bpf_prog_array_item *_item; \ struct bpf_prog *_prog; \ struct bpf_prog_array *_array; \ + struct bpf_run_ctx *old_run_ctx; \ + struct bpf_cg_run_ctx run_ctx; \ u32 _ret = 1; \ u32 func_ret; \ migrate_disable(); \ rcu_read_lock(); \ _array = rcu_dereference(array); \ _item = &_array->items[0]; \ + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); \ while ((_prog = READ_ONCE(_item->prog))) { \ - if (unlikely(bpf_cgroup_storage_set(_item->cgroup_storage))) \ - break; \ + run_ctx.prog_item = _item; \ func_ret = func(_prog, ctx); \ _ret &= (func_ret & 1); \ - *(ret_flags) |= (func_ret >> 1); \ - bpf_cgroup_storage_unset(); \ + *(ret_flags) |= (func_ret >> 1); \ _item++; \ } \ + bpf_reset_run_ctx(old_run_ctx); \ rcu_read_unlock(); \ migrate_enable(); \ _ret; \ @@ -1154,6 +1186,8 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog_array_item *_item; \ struct bpf_prog *_prog; \ struct bpf_prog_array *_array; \ + struct bpf_run_ctx *old_run_ctx; \ + struct bpf_cg_run_ctx run_ctx; \ u32 _ret = 1; \ migrate_disable(); \ rcu_read_lock(); \ @@ -1161,17 +1195,13 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, if (unlikely(check_non_null && !_array))\ goto _out; \ _item = &_array->items[0]; \ - while ((_prog = READ_ONCE(_item->prog))) { \ - if (!set_cg_storage) { \ - _ret &= func(_prog, ctx); \ - } else { \ - if (unlikely(bpf_cgroup_storage_set(_item->cgroup_storage))) \ - break; \ - _ret &= func(_prog, ctx); \ - bpf_cgroup_storage_unset(); \ - } \ + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);\ + while ((_prog = READ_ONCE(_item->prog))) { \ + run_ctx.prog_item = _item; \ + _ret &= func(_prog, ctx); \ _item++; \ } \ + bpf_reset_run_ctx(old_run_ctx); \ _out: \ rcu_read_unlock(); \ migrate_enable(); \ @@ -1254,6 +1284,20 @@ static inline void bpf_enable_instrumentation(void) migrate_enable(); } +static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx) +{ + struct bpf_run_ctx *old_ctx; + + old_ctx = current->bpf_ctx; + current->bpf_ctx = new_ctx; + return old_ctx; +} + +static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) +{ + current->bpf_ctx = old_ctx; +} + extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; extern const struct file_operations bpf_iter_fops; @@ -1398,6 +1442,9 @@ typedef void (*bpf_iter_show_fdinfo_t) (const struct bpf_iter_aux_info *aux, struct seq_file *seq); typedef int (*bpf_iter_fill_link_info_t)(const struct bpf_iter_aux_info *aux, struct bpf_link_info *info); +typedef const struct bpf_func_proto * +(*bpf_iter_get_func_proto_t)(enum bpf_func_id func_id, + const struct bpf_prog *prog); enum bpf_iter_feature { BPF_ITER_RESCHED = BIT(0), @@ -1410,6 +1457,7 @@ struct bpf_iter_reg { bpf_iter_detach_target_t detach_target; bpf_iter_show_fdinfo_t show_fdinfo; bpf_iter_fill_link_info_t fill_link_info; + bpf_iter_get_func_proto_t get_func_proto; u32 ctx_arg_info_size; u32 feature; struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; @@ -1432,6 +1480,8 @@ struct bpf_iter__bpf_map_elem { int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info); bool bpf_iter_prog_supported(struct bpf_prog *prog); +const struct bpf_func_proto * +bpf_iter_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog); int bpf_iter_new_fd(struct bpf_link *link); bool bpf_link_is_iter(struct bpf_link *link); @@ -1509,12 +1559,12 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress); -bool dev_map_can_have_prog(struct bpf_map *map); void __cpu_map_flush(void); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx); -bool cpu_map_prog_allowed(struct bpf_map *map); +int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, + struct sk_buff *skb); /* Return map's numa specified by userspace */ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) @@ -1711,6 +1761,12 @@ static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, return 0; } +static inline int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, + struct sk_buff *skb) +{ + return -EOPNOTSUPP; +} + static inline bool cpu_map_prog_allowed(struct bpf_map *map) { return false; @@ -1852,6 +1908,12 @@ void bpf_map_offload_map_free(struct bpf_map *map); int bpf_prog_test_run_syscall(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); + +int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); +int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); +int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); +void sock_map_unhash(struct sock *sk); +void sock_map_close(struct sock *sk, long timeout); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) @@ -1884,24 +1946,6 @@ static inline int bpf_prog_test_run_syscall(struct bpf_prog *prog, { return -ENOTSUPP; } -#endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ - -#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) -int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); -int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); -int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); -void sock_map_unhash(struct sock *sk); -void sock_map_close(struct sock *sk, long timeout); - -void bpf_sk_reuseport_detach(struct sock *sk); -int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, - void *value); -int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags); -#else -static inline void bpf_sk_reuseport_detach(struct sock *sk) -{ -} #ifdef CONFIG_BPF_SYSCALL static inline int sock_map_get_from_fd(const union bpf_attr *attr, @@ -1921,7 +1965,21 @@ static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void { return -EOPNOTSUPP; } +#endif /* CONFIG_BPF_SYSCALL */ +#endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ +#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) +void bpf_sk_reuseport_detach(struct sock *sk); +int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, + void *value); +int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags); +#else +static inline void bpf_sk_reuseport_detach(struct sock *sk) +{ +} + +#ifdef CONFIG_BPF_SYSCALL static inline int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, void *value) { @@ -1998,6 +2056,8 @@ extern const struct bpf_func_proto bpf_task_storage_get_proto; extern const struct bpf_func_proto bpf_task_storage_delete_proto; extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; +extern const struct bpf_func_proto bpf_sk_setsockopt_proto; +extern const struct bpf_func_proto bpf_sk_getsockopt_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 828d08afeee0..5424124dbe36 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -53,7 +53,14 @@ struct bpf_reg_state { /* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE | * PTR_TO_MAP_VALUE_OR_NULL */ - struct bpf_map *map_ptr; + struct { + struct bpf_map *map_ptr; + /* To distinguish map lookups from outer map + * the map_uid is non-zero for registers + * pointing to inner maps. + */ + u32 map_uid; + }; /* for PTR_TO_BTF_ID */ struct { @@ -201,12 +208,19 @@ struct bpf_func_state { * zero == main subprog */ u32 subprogno; + /* Every bpf_timer_start will increment async_entry_cnt. + * It's used to distinguish: + * void foo(void) { for(;;); } + * void foo(void) { bpf_timer_set_callback(,foo); } + */ + u32 async_entry_cnt; + bool in_callback_fn; + bool in_async_callback_fn; /* The following fields should be last. See copy_func_state() */ int acquired_refs; struct bpf_reference_state *refs; int allocated_stack; - bool in_callback_fn; struct bpf_stack_state *stack; }; @@ -392,6 +406,7 @@ struct bpf_subprog_info { bool has_tail_call; bool tail_call_reachable; bool has_ld_abs; + bool is_async_cb; }; /* single container for all structs diff --git a/include/linux/btf.h b/include/linux/btf.h index 94a0c976c90f..214fde93214b 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -99,6 +99,7 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size); int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); +int btf_find_timer(const struct btf *btf, const struct btf_type *t); bool btf_type_is_void(const struct btf_type *t); s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind); const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h index ae7a3411167c..9de6e9053e34 100644 --- a/include/linux/can/bittiming.h +++ b/include/linux/can/bittiming.h @@ -37,7 +37,7 @@ * quanta, from when the bit is sent on the TX pin to when it is * received on the RX pin of the transmitter. Possible options: * - * O: automatic mode. The controller dynamically measure @tdcv + * 0: automatic mode. The controller dynamically measures @tdcv * for each transmitted CAN FD frame. * * Other values: manual mode. Use the fixed provided value. @@ -45,7 +45,7 @@ * @tdco: Transmitter Delay Compensation Offset. Offset value, in time * quanta, defining the distance between the start of the bit * reception on the RX pin of the transceiver and the SSP - * position such as SSP = @tdcv + @tdco. + * position such that SSP = @tdcv + @tdco. * * If @tdco is zero, then TDC is disabled and both @tdcv and * @tdcf should be ignored. diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 27b275e463da..2413253e54c7 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -32,6 +32,12 @@ enum can_mode { CAN_MODE_SLEEP }; +enum can_termination_gpio { + CAN_TERMINATION_GPIO_DISABLED = 0, + CAN_TERMINATION_GPIO_ENABLED, + CAN_TERMINATION_GPIO_MAX, +}; + /* * CAN common private data */ @@ -55,6 +61,8 @@ struct can_priv { unsigned int termination_const_cnt; const u16 *termination_const; u16 termination; + struct gpio_desc *termination_gpio; + u16 termination_gpio_ohms[CAN_TERMINATION_GPIO_MAX]; enum can_state state; diff --git a/include/linux/can/platform/flexcan.h b/include/linux/can/platform/flexcan.h new file mode 100644 index 000000000000..1b536fb999de --- /dev/null +++ b/include/linux/can/platform/flexcan.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Angelo Dureghello <angelo@kernel-space.org> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _CAN_PLATFORM_FLEXCAN_H +#define _CAN_PLATFORM_FLEXCAN_H + +struct flexcan_platform_data { + u32 clock_frequency; + u8 clk_src; +}; + +#endif /* _CAN_PLATFORM_FLEXCAN_H */ diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index 40882df7105e..c11477620403 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -20,6 +20,7 @@ struct can_rx_offload { bool drop); struct sk_buff_head skb_queue; + struct sk_buff_head skb_irq_queue; u32 skb_queue_len_max; unsigned int mb_first; @@ -48,14 +49,11 @@ unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, unsigned int *frame_len_ptr); int can_rx_offload_queue_tail(struct can_rx_offload *offload, struct sk_buff *skb); +void can_rx_offload_irq_finish(struct can_rx_offload *offload); +void can_rx_offload_threaded_irq_finish(struct can_rx_offload *offload); void can_rx_offload_del(struct can_rx_offload *offload); void can_rx_offload_enable(struct can_rx_offload *offload); -static inline void can_rx_offload_schedule(struct can_rx_offload *offload) -{ - napi_schedule(&offload->napi); -} - static inline void can_rx_offload_disable(struct can_rx_offload *offload) { napi_disable(&offload->napi); diff --git a/include/linux/compat.h b/include/linux/compat.h index c270124e4402..8e0598c7d1d1 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -20,11 +20,8 @@ #include <linux/unistd.h> #include <asm/compat.h> - -#ifdef CONFIG_COMPAT #include <asm/siginfo.h> #include <asm/signal.h> -#endif #ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER /* @@ -95,8 +92,6 @@ struct compat_iovec { compat_size_t iov_len; }; -#ifdef CONFIG_COMPAT - #ifndef compat_user_stack_pointer #define compat_user_stack_pointer() current_user_stack_pointer() #endif @@ -131,9 +126,11 @@ struct compat_tms { #define _COMPAT_NSIG_WORDS (_COMPAT_NSIG / _COMPAT_NSIG_BPW) +#ifndef compat_sigset_t typedef struct { compat_sigset_word sig[_COMPAT_NSIG_WORDS]; } compat_sigset_t; +#endif int set_compat_user_sigmask(const compat_sigset_t __user *umask, size_t sigsetsize); @@ -384,6 +381,7 @@ struct compat_keyctl_kdf_params { __u32 __spare[8]; }; +struct compat_stat; struct compat_statfs; struct compat_statfs64; struct compat_old_linux_dirent; @@ -428,7 +426,7 @@ put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, unsigned int size) { /* size <= sizeof(compat_sigset_t) <= sizeof(sigset_t) */ -#ifdef __BIG_ENDIAN +#if defined(__BIG_ENDIAN) && defined(CONFIG_64BIT) compat_sigset_t v; switch (_NSIG_WORDS) { case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3]; @@ -929,17 +927,6 @@ asmlinkage long compat_sys_socketcall(int call, u32 __user *args); #endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ - -/* - * For most but not all architectures, "am I in a compat syscall?" and - * "am I a compat task?" are the same question. For architectures on which - * they aren't the same question, arch code can override in_compat_syscall. - */ - -#ifndef in_compat_syscall -static inline bool in_compat_syscall(void) { return is_compat_task(); } -#endif - /** * ns_to_old_timeval32 - Compat version of ns_to_timeval * @nsec: the nanoseconds value to be converted @@ -969,6 +956,17 @@ int kcompat_sys_statfs64(const char __user * pathname, compat_size_t sz, int kcompat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user * buf); +#ifdef CONFIG_COMPAT + +/* + * For most but not all architectures, "am I in a compat syscall?" and + * "am I a compat task?" are the same question. For architectures on which + * they aren't the same question, arch code can override in_compat_syscall. + */ +#ifndef in_compat_syscall +static inline bool in_compat_syscall(void) { return is_compat_task(); } +#endif + #else /* !CONFIG_COMPAT */ #define is_compat_task() (0) diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 1587961f1a7b..c7fa4a3498fe 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -11,60 +11,48 @@ struct dsa_switch; struct sk_buff; struct net_device; -struct packet_type; -struct dsa_8021q_context; -struct dsa_8021q_crosschip_link { +struct dsa_tag_8021q_vlan { struct list_head list; int port; - struct dsa_8021q_context *other_ctx; - int other_port; + u16 vid; refcount_t refcount; }; -struct dsa_8021q_ops { - int (*vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags); - int (*vlan_del)(struct dsa_switch *ds, int port, u16 vid); -}; - struct dsa_8021q_context { - const struct dsa_8021q_ops *ops; struct dsa_switch *ds; - struct list_head crosschip_links; + struct list_head vlans; /* EtherType of RX VID, used for filtering on master interface */ __be16 proto; }; -#define DSA_8021Q_N_SUBVLAN 8 - -int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled); +int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto); -int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, - int other_port); - -int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, - int other_port); +void dsa_tag_8021q_unregister(struct dsa_switch *ds); struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci); -void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, - int *subvlan); +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id); + +int dsa_tag_8021q_bridge_tx_fwd_offload(struct dsa_switch *ds, int port, + struct net_device *br, + int bridge_num); + +void dsa_tag_8021q_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port, + struct net_device *br, + int bridge_num); + +u16 dsa_8021q_bridge_tx_fwd_offload_vid(int bridge_num); u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port); u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port); -u16 dsa_8021q_rx_vid_subvlan(struct dsa_switch *ds, int port, u16 subvlan); - int dsa_8021q_rx_switch_id(u16 vid); int dsa_8021q_rx_source_port(u16 vid); -u16 dsa_8021q_rx_subvlan(u16 vid); - bool vid_is_dsa_8021q_rxvlan(u16 vid); bool vid_is_dsa_8021q_txvlan(u16 vid); diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index b6089b88314c..6b0dc9ff92d1 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -59,7 +59,6 @@ struct sja1105_skb_cb { ((struct sja1105_skb_cb *)((skb)->cb)) struct sja1105_port { - u16 subvlan_map[DSA_8021Q_N_SUBVLAN]; struct kthread_worker *xmit_worker; struct kthread_work xmit_work; struct sk_buff_head xmit_queue; @@ -89,4 +88,22 @@ static inline void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, #endif /* IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) */ +#if IS_ENABLED(CONFIG_NET_DSA_SJA1105) + +extern const struct dsa_switch_ops sja1105_switch_ops; + +static inline bool dsa_port_is_sja1105(struct dsa_port *dp) +{ + return dp->ds->ops == &sja1105_switch_ops; +} + +#else + +static inline bool dsa_port_is_sja1105(struct dsa_port *dp) +{ + return false; +} + +#endif + #endif /* _NET_DSA_SJA1105_H */ diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 232daaec56e4..4711b96dae0c 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -17,8 +17,6 @@ #include <linux/compat.h> #include <uapi/linux/ethtool.h> -#ifdef CONFIG_COMPAT - struct compat_ethtool_rx_flow_spec { u32 flow_type; union ethtool_flow_union h_u; @@ -38,8 +36,6 @@ struct compat_ethtool_rxnfc { u32 rule_locs[]; }; -#endif /* CONFIG_COMPAT */ - #include <linux/rculist.h> /** diff --git a/include/linux/filter.h b/include/linux/filter.h index 83b896044e79..1797e8506929 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -574,7 +574,8 @@ struct bpf_prog { kprobe_override:1, /* Do we override a kprobe? */ has_callchain_buf:1, /* callchain buffer allocated? */ enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ - call_get_stack:1; /* Do we call bpf_get_stack() or bpf_get_stackid() */ + call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ + call_get_func_ip:1; /* Do we call get_func_ip() */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ @@ -775,6 +776,10 @@ static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, DECLARE_BPF_DISPATCHER(xdp) +DECLARE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key); + +u32 xdp_master_redirect(struct xdp_buff *xdp); + static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, struct xdp_buff *xdp) { @@ -782,7 +787,14 @@ static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, * under local_bh_disable(), which provides the needed RCU protection * for accessing map entries. */ - return __BPF_PROG_RUN(prog, xdp, BPF_DISPATCHER_FUNC(xdp)); + u32 act = __BPF_PROG_RUN(prog, xdp, BPF_DISPATCHER_FUNC(xdp)); + + if (static_branch_unlikely(&bpf_master_redirect_enabled_key)) { + if (act == XDP_TX && netif_is_bond_slave(xdp->rxq->dev)) + act = xdp_master_redirect(xdp); + } + + return act; } void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog); diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 63b56aba925a..30ece3ae6df7 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -423,7 +423,8 @@ int __must_check fsl_mc_allocate_irqs(struct fsl_mc_device *mc_dev); void fsl_mc_free_irqs(struct fsl_mc_device *mc_dev); -struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev); +struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev, + u16 if_id); extern struct bus_type fsl_mc_bus_type; diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h index bc738504ab4a..c285968e437a 100644 --- a/include/linux/genetlink.h +++ b/include/linux/genetlink.h @@ -8,34 +8,11 @@ /* All generic netlink requests are serialized by a global lock. */ extern void genl_lock(void); extern void genl_unlock(void); -#ifdef CONFIG_LOCKDEP -extern bool lockdep_genl_is_held(void); -#endif /* for synchronisation between af_netlink and genetlink */ extern atomic_t genl_sk_destructing_cnt; extern wait_queue_head_t genl_sk_destructing_waitq; -/** - * rcu_dereference_genl - rcu_dereference with debug checking - * @p: The pointer to read, prior to dereferencing - * - * Do an rcu_dereference(p), but check caller either holds rcu_read_lock() - * or genl mutex. Note : Please prefer genl_dereference() or rcu_dereference() - */ -#define rcu_dereference_genl(p) \ - rcu_dereference_check(p, lockdep_genl_is_held()) - -/** - * genl_dereference - fetch RCU pointer when updates are prevented by genl mutex - * @p: The pointer to read, prior to dereferencing - * - * Return the value of the specified RCU-protected pointer, but omit - * the READ_ONCE(), because caller holds genl mutex. - */ -#define genl_dereference(p) \ - rcu_dereference_protected(p, lockdep_genl_is_held()) - #define MODULE_ALIAS_GENL_FAMILY(family)\ MODULE_ALIAS_NET_PF_PROTO_NAME(PF_NETLINK, NETLINK_GENERIC, "-family-" family) diff --git a/include/linux/hdlc.h b/include/linux/hdlc.h index cacc4dd27794..630a388035f1 100644 --- a/include/linux/hdlc.h +++ b/include/linux/hdlc.h @@ -22,7 +22,7 @@ struct hdlc_proto { void (*start)(struct net_device *dev); /* if open & DCD */ void (*stop)(struct net_device *dev); /* if open & !DCD */ void (*detach)(struct net_device *dev); - int (*ioctl)(struct net_device *dev, struct ifreq *ifr); + int (*ioctl)(struct net_device *dev, struct if_settings *ifs); __be16 (*type_trans)(struct sk_buff *skb, struct net_device *dev); int (*netif_rx)(struct sk_buff *skb); netdev_tx_t (*xmit)(struct sk_buff *skb, struct net_device *dev); @@ -54,7 +54,7 @@ typedef struct hdlc_device { /* Exported from hdlc module */ /* Called by hardware driver when a user requests HDLC service */ -int hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); +int hdlc_ioctl(struct net_device *dev, struct if_settings *ifs); /* Must be used by hardware driver on module startup/exit */ #define register_hdlc_device(dev) register_netdev(dev) diff --git a/include/linux/hdlcdrv.h b/include/linux/hdlcdrv.h index d4d633a49d36..5d70c3f98f5b 100644 --- a/include/linux/hdlcdrv.h +++ b/include/linux/hdlcdrv.h @@ -79,7 +79,7 @@ struct hdlcdrv_ops { */ int (*open)(struct net_device *); int (*close)(struct net_device *); - int (*ioctl)(struct net_device *, struct ifreq *, + int (*ioctl)(struct net_device *, void __user *, struct hdlcdrv_ioctl *, int); }; diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index b651c5e32a28..509e18c7e740 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -57,10 +57,16 @@ struct br_ip_list { #define BR_MRP_AWARE BIT(17) #define BR_MRP_LOST_CONT BIT(18) #define BR_MRP_LOST_IN_CONT BIT(19) +#define BR_TX_FWD_OFFLOAD BIT(20) #define BR_DEFAULT_AGEING_TIME (300 * HZ) -extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); +struct net_bridge; +void brioctl_set(int (*hook)(struct net *net, struct net_bridge *br, + unsigned int cmd, struct ifreq *ifr, + void __user *uarg)); +int br_ioctl_call(struct net *net, struct net_bridge *br, unsigned int cmd, + struct ifreq *ifr, void __user *uarg); #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING) int br_multicast_list_adjacent(struct net_device *dev, @@ -70,9 +76,6 @@ bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto); bool br_multicast_has_router_adjacent(struct net_device *dev, int proto); bool br_multicast_enabled(const struct net_device *dev); bool br_multicast_router(const struct net_device *dev); -int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, - const void *ctx, bool adding, struct notifier_block *nb, - struct netlink_ext_ack *extack); #else static inline int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list) @@ -104,13 +107,6 @@ static inline bool br_multicast_router(const struct net_device *dev) { return false; } -static inline int br_mdb_replay(const struct net_device *br_dev, - const struct net_device *dev, const void *ctx, - bool adding, struct notifier_block *nb, - struct netlink_ext_ack *extack) -{ - return -EOPNOTSUPP; -} #endif #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING) @@ -120,9 +116,8 @@ int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid); int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto); int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); -int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, - const void *ctx, bool adding, struct notifier_block *nb, - struct netlink_ext_ack *extack); +int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, + struct bridge_vlan_info *p_vinfo); #else static inline bool br_vlan_enabled(const struct net_device *dev) { @@ -150,12 +145,10 @@ static inline int br_vlan_get_info(const struct net_device *dev, u16 vid, return -EINVAL; } -static inline int br_vlan_replay(struct net_device *br_dev, - struct net_device *dev, const void *ctx, - bool adding, struct notifier_block *nb, - struct netlink_ext_ack *extack) +static inline int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, + struct bridge_vlan_info *p_vinfo) { - return -EOPNOTSUPP; + return -EINVAL; } #endif @@ -167,8 +160,6 @@ void br_fdb_clear_offload(const struct net_device *dev, u16 vid); bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag); u8 br_port_get_stp_state(const struct net_device *dev); clock_t br_get_ageing_time(const struct net_device *br_dev); -int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, - const void *ctx, bool adding, struct notifier_block *nb); #else static inline struct net_device * br_fdb_find_port(const struct net_device *br_dev, @@ -197,13 +188,6 @@ static inline clock_t br_get_ageing_time(const struct net_device *br_dev) { return 0; } - -static inline int br_fdb_replay(const struct net_device *br_dev, - const struct net_device *dev, const void *ctx, - bool adding, struct notifier_block *nb) -{ - return -EOPNOTSUPP; -} #endif #endif diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 64ce8cd1cfaf..93c262ecbdc9 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -41,9 +41,6 @@ struct ip_sf_socklist { __be32 sl_addr[]; }; -#define IP_SFLSIZE(count) (sizeof(struct ip_sf_socklist) + \ - (count) * sizeof(__be32)) - #define IP_SFBLOCK 10 /* allocate this many at once */ /* ip_mc_socklist is real list now. Speed is not argument; diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index aaf4f1b4c277..a038feb63f23 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -178,6 +178,15 @@ static inline struct net_device *ip_dev_find(struct net *net, __be32 addr) int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b); int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *); +#ifdef CONFIG_INET +int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size); +#else +static inline int inet_gifconf(struct net_device *dev, char __user *buf, + int len, int size) +{ + return 0; +} +#endif void devinet_init(void); struct in_device *inetdev_by_index(struct net *, int); __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope); diff --git a/include/linux/ioam6.h b/include/linux/ioam6.h new file mode 100644 index 000000000000..94a24b36998f --- /dev/null +++ b/include/linux/ioam6.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * IPv6 IOAM + * + * Author: + * Justin Iurman <justin.iurman@uliege.be> + */ +#ifndef _LINUX_IOAM6_H +#define _LINUX_IOAM6_H + +#include <uapi/linux/ioam6.h> + +#endif /* _LINUX_IOAM6_H */ diff --git a/include/linux/ioam6_genl.h b/include/linux/ioam6_genl.h new file mode 100644 index 000000000000..176e67919de3 --- /dev/null +++ b/include/linux/ioam6_genl.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * IPv6 IOAM Generic Netlink API + * + * Author: + * Justin Iurman <justin.iurman@uliege.be> + */ +#ifndef _LINUX_IOAM6_GENL_H +#define _LINUX_IOAM6_GENL_H + +#include <uapi/linux/ioam6_genl.h> + +#endif /* _LINUX_IOAM6_GENL_H */ diff --git a/include/linux/ioam6_iptunnel.h b/include/linux/ioam6_iptunnel.h new file mode 100644 index 000000000000..07d9dfedd29d --- /dev/null +++ b/include/linux/ioam6_iptunnel.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * IPv6 IOAM Lightweight Tunnel API + * + * Author: + * Justin Iurman <justin.iurman@uliege.be> + */ +#ifndef _LINUX_IOAM6_IPTUNNEL_H +#define _LINUX_IOAM6_IPTUNNEL_H + +#include <uapi/linux/ioam6_iptunnel.h> + +#endif /* _LINUX_IOAM6_IPTUNNEL_H */ diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 70b2ad3b9884..ef4a69865737 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -76,6 +76,9 @@ struct ipv6_devconf { __s32 disable_policy; __s32 ndisc_tclass; __s32 rpl_seg_enabled; + __u32 ioam6_id; + __u32 ioam6_id_wide; + __u8 ioam6_enabled; struct ctl_table_header *sysctl_header; }; diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index bfe5c486f4ad..f0ee30881ca9 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1581,7 +1581,8 @@ static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb) #endif /* CONFIG_CGROUP_WRITEBACK */ struct sock; -bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); +bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages, + gfp_t gfp_mask); void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); #ifdef CONFIG_MEMCG extern struct static_key_false memcg_sockets_enabled_key; diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 5e08468854db..c493a80cb453 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -356,6 +356,7 @@ struct mhi_controller_config { * @fbc_download: MHI host needs to do complete image transfer (optional) * @wake_set: Device wakeup set flag * @irq_flags: irq flags passed to request_irq (optional) + * @mru: the default MRU for the MHI device * * Fields marked as (required) need to be populated by the controller driver * before calling mhi_register_controller(). For the fields marked as (optional) @@ -448,6 +449,7 @@ struct mhi_controller { bool fbc_download; bool wake_set; unsigned long irq_flags; + u32 mru; }; /** diff --git a/include/linux/mii.h b/include/linux/mii.h index 219b93cad1dd..12ea29e04293 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -32,7 +32,7 @@ struct mii_if_info { extern int mii_link_ok (struct mii_if_info *mii); extern int mii_nway_restart (struct mii_if_info *mii); -extern int mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd); +extern void mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd); extern void mii_ethtool_get_link_ksettings( struct mii_if_info *mii, struct ethtool_link_ksettings *cmd); extern int mii_ethtool_sset(struct mii_if_info *mii, struct ethtool_cmd *ecmd); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 0025913505ab..66eaf0aa7f69 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1038,7 +1038,7 @@ enum { struct mlx5_mkey_seg { /* This is a two bit field occupying bits 31-30. * bit 31 is always 0, - * bit 30 is zero for regular MRs and 1 (e.g free) for UMRs that do not have tanslation + * bit 30 is zero for regular MRs and 1 (e.g free) for UMRs that do not have translation */ u8 status; u8 pcie_control; @@ -1157,6 +1157,9 @@ enum mlx5_cap_mode { HCA_CAP_OPMOD_GET_CUR = 1, }; +/* Any new cap addition must update mlx5_hca_caps_alloc() to allocate + * capability memory. + */ enum mlx5_cap_type { MLX5_CAP_GENERAL = 0, MLX5_CAP_ETHERNET_OFFLOADS, @@ -1213,55 +1216,55 @@ enum mlx5_qcam_feature_groups { /* GET Dev Caps macros */ #define MLX5_CAP_GEN(mdev, cap) \ - MLX5_GET(cmd_hca_cap, mdev->caps.hca_cur[MLX5_CAP_GENERAL], cap) + MLX5_GET(cmd_hca_cap, mdev->caps.hca[MLX5_CAP_GENERAL]->cur, cap) #define MLX5_CAP_GEN_64(mdev, cap) \ - MLX5_GET64(cmd_hca_cap, mdev->caps.hca_cur[MLX5_CAP_GENERAL], cap) + MLX5_GET64(cmd_hca_cap, mdev->caps.hca[MLX5_CAP_GENERAL]->cur, cap) #define MLX5_CAP_GEN_MAX(mdev, cap) \ - MLX5_GET(cmd_hca_cap, mdev->caps.hca_max[MLX5_CAP_GENERAL], cap) + MLX5_GET(cmd_hca_cap, mdev->caps.hca[MLX5_CAP_GENERAL]->max, cap) #define MLX5_CAP_GEN_2(mdev, cap) \ - MLX5_GET(cmd_hca_cap_2, mdev->caps.hca_cur[MLX5_CAP_GENERAL_2], cap) + MLX5_GET(cmd_hca_cap_2, mdev->caps.hca[MLX5_CAP_GENERAL_2]->cur, cap) #define MLX5_CAP_GEN_2_64(mdev, cap) \ - MLX5_GET64(cmd_hca_cap_2, mdev->caps.hca_cur[MLX5_CAP_GENERAL_2], cap) + MLX5_GET64(cmd_hca_cap_2, mdev->caps.hca[MLX5_CAP_GENERAL_2]->cur, cap) #define MLX5_CAP_GEN_2_MAX(mdev, cap) \ - MLX5_GET(cmd_hca_cap_2, mdev->caps.hca_max[MLX5_CAP_GENERAL_2], cap) + MLX5_GET(cmd_hca_cap_2, mdev->caps.hca[MLX5_CAP_GENERAL_2]->max, cap) #define MLX5_CAP_ETH(mdev, cap) \ MLX5_GET(per_protocol_networking_offload_caps,\ - mdev->caps.hca_cur[MLX5_CAP_ETHERNET_OFFLOADS], cap) + mdev->caps.hca[MLX5_CAP_ETHERNET_OFFLOADS]->cur, cap) #define MLX5_CAP_ETH_MAX(mdev, cap) \ MLX5_GET(per_protocol_networking_offload_caps,\ - mdev->caps.hca_max[MLX5_CAP_ETHERNET_OFFLOADS], cap) + mdev->caps.hca[MLX5_CAP_ETHERNET_OFFLOADS]->max, cap) #define MLX5_CAP_IPOIB_ENHANCED(mdev, cap) \ MLX5_GET(per_protocol_networking_offload_caps,\ - mdev->caps.hca_cur[MLX5_CAP_IPOIB_ENHANCED_OFFLOADS], cap) + mdev->caps.hca[MLX5_CAP_IPOIB_ENHANCED_OFFLOADS]->cur, cap) #define MLX5_CAP_ROCE(mdev, cap) \ - MLX5_GET(roce_cap, mdev->caps.hca_cur[MLX5_CAP_ROCE], cap) + MLX5_GET(roce_cap, mdev->caps.hca[MLX5_CAP_ROCE]->cur, cap) #define MLX5_CAP_ROCE_MAX(mdev, cap) \ - MLX5_GET(roce_cap, mdev->caps.hca_max[MLX5_CAP_ROCE], cap) + MLX5_GET(roce_cap, mdev->caps.hca[MLX5_CAP_ROCE]->max, cap) #define MLX5_CAP_ATOMIC(mdev, cap) \ - MLX5_GET(atomic_caps, mdev->caps.hca_cur[MLX5_CAP_ATOMIC], cap) + MLX5_GET(atomic_caps, mdev->caps.hca[MLX5_CAP_ATOMIC]->cur, cap) #define MLX5_CAP_ATOMIC_MAX(mdev, cap) \ - MLX5_GET(atomic_caps, mdev->caps.hca_max[MLX5_CAP_ATOMIC], cap) + MLX5_GET(atomic_caps, mdev->caps.hca[MLX5_CAP_ATOMIC]->max, cap) #define MLX5_CAP_FLOWTABLE(mdev, cap) \ - MLX5_GET(flow_table_nic_cap, mdev->caps.hca_cur[MLX5_CAP_FLOW_TABLE], cap) + MLX5_GET(flow_table_nic_cap, mdev->caps.hca[MLX5_CAP_FLOW_TABLE]->cur, cap) #define MLX5_CAP64_FLOWTABLE(mdev, cap) \ - MLX5_GET64(flow_table_nic_cap, (mdev)->caps.hca_cur[MLX5_CAP_FLOW_TABLE], cap) + MLX5_GET64(flow_table_nic_cap, (mdev)->caps.hca[MLX5_CAP_FLOW_TABLE]->cur, cap) #define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \ - MLX5_GET(flow_table_nic_cap, mdev->caps.hca_max[MLX5_CAP_FLOW_TABLE], cap) + MLX5_GET(flow_table_nic_cap, mdev->caps.hca[MLX5_CAP_FLOW_TABLE]->max, cap) #define MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.cap) @@ -1301,11 +1304,11 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \ MLX5_GET(flow_table_eswitch_cap, \ - mdev->caps.hca_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap) + mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->cur, cap) #define MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, cap) \ MLX5_GET(flow_table_eswitch_cap, \ - mdev->caps.hca_max[MLX5_CAP_ESWITCH_FLOW_TABLE], cap) + mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->max, cap) #define MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_nic_esw_fdb.cap) @@ -1327,31 +1330,31 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_ESW(mdev, cap) \ MLX5_GET(e_switch_cap, \ - mdev->caps.hca_cur[MLX5_CAP_ESWITCH], cap) + mdev->caps.hca[MLX5_CAP_ESWITCH]->cur, cap) #define MLX5_CAP64_ESW_FLOWTABLE(mdev, cap) \ MLX5_GET64(flow_table_eswitch_cap, \ - (mdev)->caps.hca_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap) + (mdev)->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->cur, cap) #define MLX5_CAP_ESW_MAX(mdev, cap) \ MLX5_GET(e_switch_cap, \ - mdev->caps.hca_max[MLX5_CAP_ESWITCH], cap) + mdev->caps.hca[MLX5_CAP_ESWITCH]->max, cap) #define MLX5_CAP_ODP(mdev, cap)\ - MLX5_GET(odp_cap, mdev->caps.hca_cur[MLX5_CAP_ODP], cap) + MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap) #define MLX5_CAP_ODP_MAX(mdev, cap)\ - MLX5_GET(odp_cap, mdev->caps.hca_max[MLX5_CAP_ODP], cap) + MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->max, cap) #define MLX5_CAP_VECTOR_CALC(mdev, cap) \ MLX5_GET(vector_calc_cap, \ - mdev->caps.hca_cur[MLX5_CAP_VECTOR_CALC], cap) + mdev->caps.hca[MLX5_CAP_VECTOR_CALC]->cur, cap) #define MLX5_CAP_QOS(mdev, cap)\ - MLX5_GET(qos_cap, mdev->caps.hca_cur[MLX5_CAP_QOS], cap) + MLX5_GET(qos_cap, mdev->caps.hca[MLX5_CAP_QOS]->cur, cap) #define MLX5_CAP_DEBUG(mdev, cap)\ - MLX5_GET(debug_cap, mdev->caps.hca_cur[MLX5_CAP_DEBUG], cap) + MLX5_GET(debug_cap, mdev->caps.hca[MLX5_CAP_DEBUG]->cur, cap) #define MLX5_CAP_PCAM_FEATURE(mdev, fld) \ MLX5_GET(pcam_reg, (mdev)->caps.pcam, feature_cap_mask.enhanced_features.fld) @@ -1387,27 +1390,27 @@ enum mlx5_qcam_feature_groups { MLX5_GET64(fpga_cap, (mdev)->caps.fpga, cap) #define MLX5_CAP_DEV_MEM(mdev, cap)\ - MLX5_GET(device_mem_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_MEM], cap) + MLX5_GET(device_mem_cap, mdev->caps.hca[MLX5_CAP_DEV_MEM]->cur, cap) #define MLX5_CAP64_DEV_MEM(mdev, cap)\ - MLX5_GET64(device_mem_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_MEM], cap) + MLX5_GET64(device_mem_cap, mdev->caps.hca[MLX5_CAP_DEV_MEM]->cur, cap) #define MLX5_CAP_TLS(mdev, cap) \ - MLX5_GET(tls_cap, (mdev)->caps.hca_cur[MLX5_CAP_TLS], cap) + MLX5_GET(tls_cap, (mdev)->caps.hca[MLX5_CAP_TLS]->cur, cap) #define MLX5_CAP_DEV_EVENT(mdev, cap)\ - MLX5_ADDR_OF(device_event_cap, (mdev)->caps.hca_cur[MLX5_CAP_DEV_EVENT], cap) + MLX5_ADDR_OF(device_event_cap, (mdev)->caps.hca[MLX5_CAP_DEV_EVENT]->cur, cap) #define MLX5_CAP_DEV_VDPA_EMULATION(mdev, cap)\ MLX5_GET(virtio_emulation_cap, \ - (mdev)->caps.hca_cur[MLX5_CAP_VDPA_EMULATION], cap) + (mdev)->caps.hca[MLX5_CAP_VDPA_EMULATION]->cur, cap) #define MLX5_CAP64_DEV_VDPA_EMULATION(mdev, cap)\ MLX5_GET64(virtio_emulation_cap, \ - (mdev)->caps.hca_cur[MLX5_CAP_VDPA_EMULATION], cap) + (mdev)->caps.hca[MLX5_CAP_VDPA_EMULATION]->cur, cap) #define MLX5_CAP_IPSEC(mdev, cap)\ - MLX5_GET(ipsec_cap, (mdev)->caps.hca_cur[MLX5_CAP_IPSEC], cap) + MLX5_GET(ipsec_cap, (mdev)->caps.hca[MLX5_CAP_IPSEC]->cur, cap) enum { MLX5_CMD_STAT_OK = 0x0, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 25a8be58d289..e23417424373 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -581,7 +581,7 @@ struct mlx5_priv { /* end: qp staff */ /* start: alloc staff */ - /* protect buffer alocation according to numa node */ + /* protect buffer allocation according to numa node */ struct mutex alloc_mutex; int numa_node; @@ -623,8 +623,7 @@ struct mlx5_priv { }; enum mlx5_device_state { - MLX5_DEVICE_STATE_UNINITIALIZED, - MLX5_DEVICE_STATE_UP, + MLX5_DEVICE_STATE_UP = 1, MLX5_DEVICE_STATE_INTERNAL_ERROR, }; @@ -730,6 +729,11 @@ struct mlx5_profile { } mr_cache[MAX_MR_CACHE_ENTRIES]; }; +struct mlx5_hca_cap { + u32 cur[MLX5_UN_SZ_DW(hca_cap_union)]; + u32 max[MLX5_UN_SZ_DW(hca_cap_union)]; +}; + struct mlx5_core_dev { struct device *device; enum mlx5_coredev_type coredev_type; @@ -741,8 +745,7 @@ struct mlx5_core_dev { char board_id[MLX5_BOARD_ID_LEN]; struct mlx5_cmd cmd; struct { - u32 hca_cur[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; - u32 hca_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; + struct mlx5_hca_cap *hca[MLX5_CAP_NUM]; u32 pcam[MLX5_ST_SZ_DW(pcam_reg)]; u32 mcam[MLX5_MCAM_REGS_NUM][MLX5_ST_SZ_DW(mcam_reg)]; u32 fpga[MLX5_ST_SZ_DW(fpga_cap)]; @@ -1110,7 +1113,7 @@ static inline u8 mlx5_mkey_variant(u32 mkey) } /* Async-atomic event notifier used by mlx5 core to forward FW - * evetns recived from event queue to mlx5 consumers. + * evetns received from event queue to mlx5 consumers. * Optimise event queue dipatching. */ int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb); @@ -1137,6 +1140,8 @@ bool mlx5_lag_is_roce(struct mlx5_core_dev *dev); bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev); bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev); bool mlx5_lag_is_active(struct mlx5_core_dev *dev); +bool mlx5_lag_is_master(struct mlx5_core_dev *dev); +bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev); struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev); u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev, struct net_device *slave); @@ -1144,6 +1149,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, u64 *values, int num_counters, size_t *offsets); +struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev); struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev); void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up); int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index bc7db2e059eb..4ab5c1fc1270 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -29,11 +29,20 @@ enum { REP_LOADED, }; +enum mlx5_switchdev_event { + MLX5_SWITCHDEV_EVENT_PAIR, + MLX5_SWITCHDEV_EVENT_UNPAIR, +}; + struct mlx5_eswitch_rep; struct mlx5_eswitch_rep_ops { int (*load)(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep); void (*unload)(struct mlx5_eswitch_rep *rep); void *(*get_proto_dev)(struct mlx5_eswitch_rep *rep); + int (*event)(struct mlx5_eswitch *esw, + struct mlx5_eswitch_rep *rep, + enum mlx5_switchdev_event event, + void *data); }; struct mlx5_eswitch_rep_data { @@ -63,6 +72,7 @@ struct mlx5_eswitch_rep *mlx5_eswitch_vport_rep(struct mlx5_eswitch *esw, void *mlx5_eswitch_uplink_get_proto_dev(struct mlx5_eswitch *esw, u8 rep_type); struct mlx5_flow_handle * mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, + struct mlx5_eswitch *from_esw, struct mlx5_eswitch_rep *rep, u32 sqn); #ifdef CONFIG_MLX5_ESWITCH @@ -128,6 +138,7 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev); u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev); +struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw); #else /* CONFIG_MLX5_ESWITCH */ @@ -171,6 +182,11 @@ static inline u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev) return 0; } +static inline struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw) +{ + return NULL; +} + #endif /* CONFIG_MLX5_ESWITCH */ static inline bool is_mdev_switchdev_mode(struct mlx5_core_dev *dev) diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 77746f7e35b8..0106c67e8ccb 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -38,6 +38,8 @@ #define MLX5_FS_DEFAULT_FLOW_TAG 0x0 +#define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v) + enum { MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO = 1 << 16, MLX5_FLOW_CONTEXT_ACTION_ENCRYPT = 1 << 17, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index b0009aa3647f..fce3cbae0b99 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -921,7 +921,8 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 scatter_fcs[0x1]; u8 enhanced_multi_pkt_send_wqe[0x1]; u8 tunnel_lso_const_out_ip_id[0x1]; - u8 reserved_at_1c[0x2]; + u8 tunnel_lro_gre[0x1]; + u8 tunnel_lro_vxlan[0x1]; u8 tunnel_stateless_gre[0x1]; u8 tunnel_stateless_vxlan[0x1]; @@ -1651,7 +1652,13 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 max_geneve_tlv_option_data_len[0x5]; u8 reserved_at_570[0x10]; - u8 reserved_at_580[0x33]; + u8 reserved_at_580[0xb]; + u8 log_max_dci_stream_channels[0x5]; + u8 reserved_at_590[0x3]; + u8 log_max_dci_errored_streams[0x5]; + u8 reserved_at_598[0x8]; + + u8 reserved_at_5a0[0x13]; u8 log_max_dek[0x5]; u8 reserved_at_5b8[0x4]; u8 mini_cqe_resp_stride_index[0x1]; @@ -3020,10 +3027,12 @@ struct mlx5_ifc_qpc_bits { u8 reserved_at_3c0[0x8]; u8 next_send_psn[0x18]; - u8 reserved_at_3e0[0x8]; + u8 reserved_at_3e0[0x3]; + u8 log_num_dci_stream_channels[0x5]; u8 cqn_snd[0x18]; - u8 reserved_at_400[0x8]; + u8 reserved_at_400[0x3]; + u8 log_num_dci_errored_streams[0x5]; u8 deth_sqpn[0x18]; u8 reserved_at_420[0x20]; @@ -3911,7 +3920,7 @@ struct mlx5_ifc_cqc_bits { u8 status[0x4]; u8 reserved_at_4[0x2]; u8 dbr_umem_valid[0x1]; - u8 apu_thread_cq[0x1]; + u8 apu_cq[0x1]; u8 cqe_sz[0x3]; u8 cc[0x1]; u8 reserved_at_c[0x1]; @@ -3937,8 +3946,7 @@ struct mlx5_ifc_cqc_bits { u8 cq_period[0xc]; u8 cq_max_count[0x10]; - u8 reserved_at_a0[0x18]; - u8 c_eqn[0x8]; + u8 c_eqn_or_apu_element[0x20]; u8 reserved_at_c0[0x3]; u8 log_page_size[0x5]; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 52bbd2b7cb46..7f8ee09c711f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -103,11 +103,19 @@ struct page { unsigned long pp_magic; struct page_pool *pp; unsigned long _pp_mapping_pad; - /** - * @dma_addr: might require a 64-bit value on - * 32-bit architectures. - */ - unsigned long dma_addr[2]; + unsigned long dma_addr; + union { + /** + * dma_addr_upper: might require a 64-bit + * value on 32-bit architectures. + */ + unsigned long dma_addr_upper; + /** + * For frag page support, not supported in + * 32-bit architectures with 64-bit DMA. + */ + atomic_long_t pp_frag_count; + }; }; struct { /* slab, slob and slub */ union { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index eaf5bb008aa9..2f03cd9e371a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -295,18 +295,6 @@ enum netdev_state_t { }; -/* - * This structure holds boot-time configured netdevice settings. They - * are then used in the device probing. - */ -struct netdev_boot_setup { - char name[IFNAMSIZ]; - struct ifmap map; -}; -#define NETDEV_BOOT_SETUP_MAX 8 - -int __init netdev_boot_setup(char *str); - struct gro_list { struct list_head list; int count; @@ -1086,9 +1074,18 @@ struct netdev_net_notifier { * Test if Media Access Control address is valid for the device. * * int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); - * Called when a user requests an ioctl which can't be handled by - * the generic interface code. If not defined ioctls return - * not supported error code. + * Old-style ioctl entry point. This is used internally by the + * appletalk and ieee802154 subsystems but is no longer called by + * the device ioctl handler. + * + * int (*ndo_siocbond)(struct net_device *dev, struct ifreq *ifr, int cmd); + * Used by the bonding driver for its device specific ioctls: + * SIOCBONDENSLAVE, SIOCBONDRELEASE, SIOCBONDSETHWADDR, SIOCBONDCHANGEACTIVE, + * SIOCBONDSLAVEINFOQUERY, and SIOCBONDINFOQUERY + * + * * int (*ndo_eth_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); + * Called for ethernet specific ioctls: SIOCGMIIPHY, SIOCGMIIREG, + * SIOCSMIIREG, SIOCSHWTSTAMP and SIOCGHWTSTAMP. * * int (*ndo_set_config)(struct net_device *dev, struct ifmap *map); * Used to set network devices bus interface parameters. This interface @@ -1321,6 +1318,9 @@ struct netdev_net_notifier { * that got dropped are freed/returned via xdp_return_frame(). * Returns negative number, means general error invoking ndo, meaning * no frames were xmit'ed and core-caller will free all frames. + * struct net_device *(*ndo_xdp_get_xmit_slave)(struct net_device *dev, + * struct xdp_buff *xdp); + * Get the xmit slave of master device based on the xdp_buff. * int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); * This function is used to wake up the softirq, ksoftirqd or kthread * responsible for sending and/or receiving packets on a specific @@ -1361,6 +1361,15 @@ struct net_device_ops { int (*ndo_validate_addr)(struct net_device *dev); int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); + int (*ndo_eth_ioctl)(struct net_device *dev, + struct ifreq *ifr, int cmd); + int (*ndo_siocbond)(struct net_device *dev, + struct ifreq *ifr, int cmd); + int (*ndo_siocwandev)(struct net_device *dev, + struct if_settings *ifs); + int (*ndo_siocdevprivate)(struct net_device *dev, + struct ifreq *ifr, + void __user *data, int cmd); int (*ndo_set_config)(struct net_device *dev, struct ifmap *map); int (*ndo_change_mtu)(struct net_device *dev, @@ -1539,6 +1548,8 @@ struct net_device_ops { int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp, u32 flags); + struct net_device * (*ndo_xdp_get_xmit_slave)(struct net_device *dev, + struct xdp_buff *xdp); int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); struct devlink_port * (*ndo_get_devlink_port)(struct net_device *dev); @@ -1805,6 +1816,7 @@ enum netdev_ml_priv_type { * @ieee802154_ptr: IEEE 802.15.4 low-rate Wireless Personal Area Network * device struct * @mpls_ptr: mpls_dev struct pointer + * @mctp_ptr: MCTP specific data * * @dev_addr: Hw address (before bcast, * because most packets are unicast) @@ -2092,6 +2104,9 @@ struct net_device { #if IS_ENABLED(CONFIG_MPLS_ROUTING) struct mpls_dev __rcu *mpls_ptr; #endif +#if IS_ENABLED(CONFIG_MCTP) + struct mctp_dev __rcu *mctp_ptr; +#endif /* * Cache lines mostly used on receive path (including eth_type_trans()) @@ -2917,7 +2932,6 @@ static inline struct net_device *first_net_device_rcu(struct net *net) } int netdev_boot_setup_check(struct net_device *dev); -unsigned long netdev_boot_base(const char *prefix, int unit); struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, const char *hwaddr); struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type); @@ -3289,14 +3303,6 @@ static inline bool dev_has_header(const struct net_device *dev) return dev->header_ops && dev->header_ops->create; } -typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, - int len, int size); -int register_gifconf(unsigned int family, gifconf_func_t *gifconf); -static inline int unregister_gifconf(unsigned int family) -{ - return register_gifconf(family, NULL); -} - #ifdef CONFIG_NET_FLOW_LIMIT #define FLOW_LIMIT_HISTORY (1 << 7) /* must be ^2 and !overflow buckets */ struct sd_flow_limit { @@ -3915,6 +3921,8 @@ static inline int netif_set_real_num_rx_queues(struct net_device *dev, return 0; } #endif +int netif_set_real_num_queues(struct net_device *dev, + unsigned int txq, unsigned int rxq); static inline struct netdev_rx_queue * __netif_get_rx_queue(struct net_device *dev, unsigned int rxq) @@ -3948,7 +3956,7 @@ void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason); /* * It is not allowed to call kfree_skb() or consume_skb() from hardware * interrupt context or with hardware interrupts being disabled. - * (in_irq() || irqs_disabled()) + * (in_hardirq() || irqs_disabled()) * * We provide four helpers that can be used in following contexts : * @@ -3984,6 +3992,8 @@ static inline void dev_consume_skb_any(struct sk_buff *skb) __dev_kfree_skb_any(skb, SKB_REASON_CONSUMED); } +u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, + struct bpf_prog *xdp_prog); void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog); int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); int netif_rx(struct sk_buff *skb); @@ -4012,10 +4022,12 @@ int netdev_rx_handler_register(struct net_device *dev, void netdev_rx_handler_unregister(struct net_device *dev); bool dev_valid_name(const char *name); +int get_user_ifreq(struct ifreq *ifr, void __user **ifrdata, void __user *arg); +int put_user_ifreq(struct ifreq *ifr, void __user *arg); int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, - bool *need_copyout); -int dev_ifconf(struct net *net, struct ifconf *, int); -int dev_ethtool(struct net *net, struct ifreq *); + void __user *data, bool *need_copyout); +int dev_ifconf(struct net *net, struct ifconf __user *ifc); +int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata); unsigned int dev_get_flags(const struct net_device *); int __dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); @@ -4069,6 +4081,7 @@ typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf); int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, int expected_fd, u32 flags); int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); +u8 dev_xdp_prog_count(struct net_device *dev); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); @@ -4136,11 +4149,13 @@ void netdev_run_todo(void); */ static inline void dev_put(struct net_device *dev) { + if (dev) { #ifdef CONFIG_PCPU_DEV_REFCNT - this_cpu_dec(*dev->pcpu_refcnt); + this_cpu_dec(*dev->pcpu_refcnt); #else - refcount_dec(&dev->dev_refcnt); + refcount_dec(&dev->dev_refcnt); #endif + } } /** @@ -4151,11 +4166,13 @@ static inline void dev_put(struct net_device *dev) */ static inline void dev_hold(struct net_device *dev) { + if (dev) { #ifdef CONFIG_PCPU_DEV_REFCNT - this_cpu_inc(*dev->pcpu_refcnt); + this_cpu_inc(*dev->pcpu_refcnt); #else - refcount_inc(&dev->dev_refcnt); + refcount_inc(&dev->dev_refcnt); #endif + } } /* Carrier loss detection, dial on demand. The functions netif_carrier_on diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 28d7027cd460..5897f3dbaf7c 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -238,9 +238,6 @@ struct xt_table { u_int8_t af; /* address/protocol family */ int priority; /* hook order */ - /* called when table is needed in the given netns */ - int (*table_init)(struct net *net); - /* A unique name... */ const char name[XT_TABLE_MAXNAMELEN]; }; @@ -452,6 +449,9 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *); +int xt_register_template(const struct xt_table *t, int(*table_init)(struct net *net)); +void xt_unregister_template(const struct xt_table *t); + #ifdef CONFIG_NETFILTER_XTABLES_COMPAT #include <net/compat.h> diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index a8178253ce53..10a01978bc0d 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -127,4 +127,6 @@ static inline bool ebt_invalid_target(int target) return (target < -NUM_STANDARD_TARGETS || target >= 0); } +int ebt_register_template(const struct ebt_table *t, int(*table_init)(struct net *net)); +void ebt_unregister_template(const struct ebt_table *t); #endif diff --git a/include/linux/phy.h b/include/linux/phy.h index 3b80dc3ed68b..736e1d1a47c4 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1431,6 +1431,7 @@ static inline int phy_device_register(struct phy_device *phy) static inline void phy_device_free(struct phy_device *phydev) { } #endif /* CONFIG_PHYLIB */ void phy_device_remove(struct phy_device *phydev); +int phy_get_c45_ids(struct phy_device *phydev); int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 71fac9237725..2e5565067355 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -215,7 +215,7 @@ static inline long scaled_ppm_to_ppb(long ppm) return (long)ppb; } -#if IS_REACHABLE(CONFIG_PTP_1588_CLOCK) +#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) /** * ptp_clock_register() - register a PTP hardware clock driver @@ -307,6 +307,33 @@ int ptp_schedule_worker(struct ptp_clock *ptp, unsigned long delay); */ void ptp_cancel_worker_sync(struct ptp_clock *ptp); +#else +static inline struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, + struct device *parent) +{ return NULL; } +static inline int ptp_clock_unregister(struct ptp_clock *ptp) +{ return 0; } +static inline void ptp_clock_event(struct ptp_clock *ptp, + struct ptp_clock_event *event) +{ } +static inline int ptp_clock_index(struct ptp_clock *ptp) +{ return -1; } +static inline int ptp_find_pin(struct ptp_clock *ptp, + enum ptp_pin_function func, unsigned int chan) +{ return -1; } +static inline int ptp_schedule_worker(struct ptp_clock *ptp, + unsigned long delay) +{ return -EOPNOTSUPP; } +static inline void ptp_cancel_worker_sync(struct ptp_clock *ptp) +{ } +#endif + +#if IS_BUILTIN(CONFIG_PTP_1588_CLOCK) +/* + * These are called by the network core, and don't work if PTP is in + * a loadable module. + */ + /** * ptp_get_vclocks_index() - get all vclocks index on pclock, and * caller is responsible to free memory @@ -327,26 +354,7 @@ int ptp_get_vclocks_index(int pclock_index, int **vclock_index); */ void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, int vclock_index); - #else -static inline struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, - struct device *parent) -{ return NULL; } -static inline int ptp_clock_unregister(struct ptp_clock *ptp) -{ return 0; } -static inline void ptp_clock_event(struct ptp_clock *ptp, - struct ptp_clock_event *event) -{ } -static inline int ptp_clock_index(struct ptp_clock *ptp) -{ return -1; } -static inline int ptp_find_pin(struct ptp_clock *ptp, - enum ptp_pin_function func, unsigned int chan) -{ return -1; } -static inline int ptp_schedule_worker(struct ptp_clock *ptp, - unsigned long delay) -{ return -EOPNOTSUPP; } -static inline void ptp_cancel_worker_sync(struct ptp_clock *ptp) -{ } static inline int ptp_get_vclocks_index(int pclock_index, int **vclock_index) { return 0; } static inline void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, diff --git a/include/linux/sched.h b/include/linux/sched.h index ec8d07d88641..c64119aa2e60 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -42,6 +42,7 @@ struct backing_dev_info; struct bio_list; struct blk_plug; struct bpf_local_storage; +struct bpf_run_ctx; struct capture_control; struct cfs_rq; struct fs_struct; @@ -1379,6 +1380,8 @@ struct task_struct { #ifdef CONFIG_BPF_SYSCALL /* Used by BPF task local storage */ struct bpf_local_storage __rcu *bpf_storage; + /* Used for BPF run context */ + struct bpf_run_ctx *bpf_ctx; #endif #ifdef CONFIG_GCC_PLUGIN_STACKLEAK diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b2db9cd9a73f..6bdb0db3e825 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -689,6 +689,7 @@ typedef unsigned char *sk_buff_data_t; * CHECKSUM_UNNECESSARY (max 3) * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB + * @slow_gro: state present at GRO time, slower prepare step required * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @secmark: security marking @@ -863,13 +864,14 @@ struct sk_buff { __u8 tc_skip_classify:1; __u8 tc_at_ingress:1; #endif -#ifdef CONFIG_NET_REDIRECT __u8 redirected:1; +#ifdef CONFIG_NET_REDIRECT __u8 from_ingress:1; #endif #ifdef CONFIG_TLS_DEVICE __u8 decrypted:1; #endif + __u8 slow_gro:1; #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ @@ -990,6 +992,7 @@ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) */ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) { + skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst; } @@ -1006,6 +1009,7 @@ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst) { WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); + skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF; } @@ -1179,6 +1183,7 @@ static inline struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask); struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom); +struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t priority); int __must_check skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, @@ -4216,6 +4221,7 @@ static inline unsigned long skb_get_nfct(const struct sk_buff *skb) static inline void skb_set_nfct(struct sk_buff *skb, unsigned long nfct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) + skb->slow_gro |= !!nfct; skb->_nfct = nfct; #endif } @@ -4375,6 +4381,7 @@ static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src) #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb_nfct(dst)); #endif + dst->slow_gro = src->slow_gro; __nf_copy(dst, src, true); } @@ -4664,17 +4671,13 @@ static inline __wsum lco_csum(struct sk_buff *skb) static inline bool skb_is_redirected(const struct sk_buff *skb) { -#ifdef CONFIG_NET_REDIRECT return skb->redirected; -#else - return false; -#endif } static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress) { -#ifdef CONFIG_NET_REDIRECT skb->redirected = 1; +#ifdef CONFIG_NET_REDIRECT skb->from_ingress = from_ingress; if (skb->from_ingress) skb->tstamp = 0; @@ -4683,9 +4686,7 @@ static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress) static inline void skb_reset_redirect(struct sk_buff *skb) { -#ifdef CONFIG_NET_REDIRECT skb->redirected = 0; -#endif } static inline bool skb_csum_is_sctp(struct sk_buff *skb) @@ -4711,11 +4712,9 @@ static inline u64 skb_get_kcov_handle(struct sk_buff *skb) } #ifdef CONFIG_PAGE_POOL -static inline void skb_mark_for_recycle(struct sk_buff *skb, struct page *page, - struct page_pool *pp) +static inline void skb_mark_for_recycle(struct sk_buff *skb) { skb->pp_recycle = 1; - page_pool_store_mem_info(page, pp); } #endif diff --git a/include/linux/socket.h b/include/linux/socket.h index 0d8e3dcb7f88..fd9ce51582d8 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -223,8 +223,11 @@ struct ucred { * reuses AF_INET address family */ #define AF_XDP 44 /* XDP sockets */ +#define AF_MCTP 45 /* Management component + * transport protocol + */ -#define AF_MAX 45 /* For now.. */ +#define AF_MAX 46 /* For now.. */ /* Protocol families, same as address families. */ #define PF_UNSPEC AF_UNSPEC @@ -274,6 +277,7 @@ struct ucred { #define PF_QIPCRTR AF_QIPCRTR #define PF_SMC AF_SMC #define PF_XDP AF_XDP +#define PF_MCTP AF_MCTP #define PF_MAX AF_MAX /* Maximum queue length specifiable by listen. */ diff --git a/include/linux/typecheck.h b/include/linux/typecheck.h index 20d310331eb5..46b15e2aaefb 100644 --- a/include/linux/typecheck.h +++ b/include/linux/typecheck.h @@ -22,4 +22,13 @@ (void)__tmp; \ }) +/* + * Check at compile time that something is a pointer type. + */ +#define typecheck_pointer(x) \ +({ typeof(x) __dummy; \ + (void)sizeof(*__dummy); \ + 1; \ +}) + #endif /* TYPECHECK_H_INCLUDED */ diff --git a/include/net/Space.h b/include/net/Space.h index 9cce0d80d37a..08ca9cef0213 100644 --- a/include/net/Space.h +++ b/include/net/Space.h @@ -8,23 +8,13 @@ struct net_device *ultra_probe(int unit); struct net_device *wd_probe(int unit); struct net_device *ne_probe(int unit); struct net_device *fmv18x_probe(int unit); -struct net_device *i82596_probe(int unit); struct net_device *ni65_probe(int unit); struct net_device *sonic_probe(int unit); struct net_device *smc_init(int unit); -struct net_device *atarilance_probe(int unit); -struct net_device *sun3lance_probe(int unit); -struct net_device *sun3_82586_probe(int unit); -struct net_device *apne_probe(int unit); struct net_device *cs89x0_probe(int unit); -struct net_device *mvme147lance_probe(int unit); struct net_device *tc515_probe(int unit); struct net_device *lance_probe(int unit); struct net_device *cops_probe(int unit); -struct net_device *ltpc_probe(void); /* Fibre Channel adapters */ int iph5526_probe(struct net_device *dev); - -/* SBNI adapters */ -int sbni_probe(int unit); diff --git a/include/net/act_api.h b/include/net/act_api.h index 086b291e9530..f19f7f4a463c 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -58,6 +58,14 @@ struct tc_action { #define TCA_ACT_HW_STATS_ANY (TCA_ACT_HW_STATS_IMMEDIATE | \ TCA_ACT_HW_STATS_DELAYED) +/* Reserve 16 bits for user-space. See TCA_ACT_FLAGS_NO_PERCPU_STATS. */ +#define TCA_ACT_FLAGS_USER_BITS 16 +#define TCA_ACT_FLAGS_USER_MASK 0xffff +#define TCA_ACT_FLAGS_POLICE (1U << TCA_ACT_FLAGS_USER_BITS) +#define TCA_ACT_FLAGS_BIND (1U << (TCA_ACT_FLAGS_USER_BITS + 1)) +#define TCA_ACT_FLAGS_REPLACE (1U << (TCA_ACT_FLAGS_USER_BITS + 2)) +#define TCA_ACT_FLAGS_NO_RTNL (1U << (TCA_ACT_FLAGS_USER_BITS + 3)) + /* Update lastuse only if needed, to avoid dirtying a cache line. * We use a temp variable to avoid fetching jiffies twice. */ @@ -99,8 +107,8 @@ struct tc_action_ops { void (*cleanup)(struct tc_action *); int (*lookup)(struct net *net, struct tc_action **a, u32 index); int (*init)(struct net *net, struct nlattr *nla, - struct nlattr *est, struct tc_action **act, int ovr, - int bind, bool rtnl_held, struct tcf_proto *tp, + struct nlattr *est, struct tc_action **act, + struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack); int (*walk)(struct net *, struct sk_buff *, struct netlink_callback *, int, @@ -179,18 +187,16 @@ int tcf_action_destroy(struct tc_action *actions[], int bind); int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, int nr_actions, struct tcf_result *res); int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, - struct nlattr *est, char *name, int ovr, int bind, + struct nlattr *est, struct tc_action *actions[], int init_res[], size_t *attr_size, - bool rtnl_held, struct netlink_ext_ack *extack); -struct tc_action_ops *tc_action_load_ops(char *name, struct nlattr *nla, + u32 flags, struct netlink_ext_ack *extack); +struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, bool police, bool rtnl_held, struct netlink_ext_ack *extack); struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, - char *name, int ovr, int bind, struct tc_action_ops *a_o, int *init_res, - bool rtnl_held, - struct netlink_ext_ack *extack); + u32 flags, struct netlink_ext_ack *extack); int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind, int ref, bool terse); int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); diff --git a/include/net/af_unix.h b/include/net/af_unix.h index f42fdddecd41..4757d7f53f13 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -70,6 +70,9 @@ struct unix_sock { struct socket_wq peer_wq; wait_queue_entry_t peer_wake; struct scm_stat scm_stat; +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + struct sk_buff *oob_skb; +#endif }; static inline struct unix_sock *unix_sk(const struct sock *sk) @@ -82,6 +85,8 @@ static inline struct unix_sock *unix_sk(const struct sock *sk) long unix_inq_len(struct sock *sk); long unix_outq_len(struct sock *sk); +int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, + int flags); #ifdef CONFIG_SYSCTL int unix_sysctl_register(struct net *net); void unix_sysctl_unregister(struct net *net); @@ -89,4 +94,14 @@ void unix_sysctl_unregister(struct net *net); static inline int unix_sysctl_register(struct net *net) { return 0; } static inline void unix_sysctl_unregister(struct net *net) {} #endif + +#ifdef CONFIG_BPF_SYSCALL +extern struct proto unix_proto; + +int unix_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); +void __init unix_bpf_build_proto(void); +#else +static inline void __init unix_bpf_build_proto(void) +{} +#endif #endif diff --git a/include/net/ax88796.h b/include/net/ax88796.h index aa52b2e8ff7b..2ed23a368602 100644 --- a/include/net/ax88796.h +++ b/include/net/ax88796.h @@ -38,4 +38,7 @@ struct ax_plat_data { int (*check_irq)(struct platform_device *pdev); }; +/* exported from ax88796.c for xsurf100.c */ +extern void ax_NS8390_reinit(struct net_device *dev); + #endif /* __NET_AX88796_PLAT_H */ diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index c8696a230b7d..38785d48baff 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -303,6 +303,7 @@ int __bond_3ad_get_active_agg_info(struct bonding *bond, int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); int bond_3ad_set_carrier(struct bonding *bond); +void bond_3ad_update_lacp_active(struct bonding *bond); void bond_3ad_update_lacp_rate(struct bonding *bond); void bond_3ad_update_ad_actor_settings(struct bonding *bond); int bond_3ad_stats_fill(struct sk_buff *skb, struct bond_3ad_stats *stats); diff --git a/include/net/bond_options.h b/include/net/bond_options.h index 9d382f2f0bc5..e64833a674eb 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -64,6 +64,7 @@ enum { BOND_OPT_AD_USER_PORT_KEY, BOND_OPT_NUM_PEER_NOTIF_ALIAS, BOND_OPT_PEER_NOTIF_DELAY, + BOND_OPT_LACP_ACTIVE, BOND_OPT_LAST }; diff --git a/include/net/bonding.h b/include/net/bonding.h index 625d9c72dee3..15e083e18f75 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -129,6 +129,7 @@ struct bond_params { int updelay; int downdelay; int peer_notif_delay; + int lacp_active; int lacp_fast; unsigned int min_links; int ad_select; @@ -149,11 +150,6 @@ struct bond_params { u8 ad_actor_system[ETH_ALEN + 2]; }; -struct bond_parm_tbl { - char *modename; - int mode; -}; - struct slave { struct net_device *dev; /* first - useful for panic debug */ struct bonding *bond; /* our master */ @@ -258,6 +254,7 @@ struct bonding { /* protecting ipsec_list */ spinlock_t ipsec_lock; #endif /* CONFIG_XFRM_OFFLOAD */ + struct bpf_prog *xdp_prog; }; #define bond_slave_get_rcu(dev) \ @@ -753,13 +750,6 @@ static inline int bond_get_targets_ip(__be32 *targets, __be32 ip) /* exported from bond_main.c */ extern unsigned int bond_net_id; -extern const struct bond_parm_tbl bond_lacp_tbl[]; -extern const struct bond_parm_tbl xmit_hashtype_tbl[]; -extern const struct bond_parm_tbl arp_validate_tbl[]; -extern const struct bond_parm_tbl arp_all_targets_tbl[]; -extern const struct bond_parm_tbl fail_over_mac_tbl[]; -extern const struct bond_parm_tbl pri_reselect_tbl[]; -extern struct bond_parm_tbl ad_select_tbl[]; /* exported from bond_netlink.c */ extern struct rtnl_link_ops bond_link_ops; diff --git a/include/net/compat.h b/include/net/compat.h index 84805bdc4435..595fee069b82 100644 --- a/include/net/compat.h +++ b/include/net/compat.h @@ -71,13 +71,26 @@ struct compat_group_source_req { } __packed; struct compat_group_filter { - __u32 gf_interface; - struct __kernel_sockaddr_storage gf_group - __aligned(4); - __u32 gf_fmode; - __u32 gf_numsrc; - struct __kernel_sockaddr_storage gf_slist[1] - __aligned(4); + union { + struct { + __u32 gf_interface_aux; + struct __kernel_sockaddr_storage gf_group_aux + __aligned(4); + __u32 gf_fmode_aux; + __u32 gf_numsrc_aux; + struct __kernel_sockaddr_storage gf_slist[1] + __aligned(4); + } __packed; + struct { + __u32 gf_interface; + struct __kernel_sockaddr_storage gf_group + __aligned(4); + __u32 gf_fmode; + __u32 gf_numsrc; + struct __kernel_sockaddr_storage gf_slist_flex[] + __aligned(4); + } __packed; + }; } __packed; #endif /* NET_COMPAT_H */ diff --git a/include/net/devlink.h b/include/net/devlink.h index 57b738b78073..154cf0dbca37 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -32,7 +32,7 @@ struct devlink_dev_stats { struct devlink_ops; struct devlink { - struct list_head list; + u32 index; struct list_head port_list; struct list_head rate_list; struct list_head sb_list; @@ -55,8 +55,9 @@ struct devlink { * port, sb, dpipe, resource, params, region, traps and more. */ u8 reload_failed:1, - reload_enabled:1, - registered:1; + reload_enabled:1; + refcount_t refcount; + struct completion comp; char priv[0] __aligned(NETDEV_ALIGN); }; @@ -158,7 +159,6 @@ struct devlink_port { struct list_head region_list; struct devlink *devlink; unsigned int index; - bool registered; spinlock_t type_lock; /* Protects type and type_dev * pointer consistency. */ @@ -521,6 +521,9 @@ enum devlink_param_generic_id { DEVLINK_PARAM_GENERIC_ID_RESET_DEV_ON_DRV_PROBE, DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, DEVLINK_PARAM_GENERIC_ID_ENABLE_REMOTE_DEV_RESET, + DEVLINK_PARAM_GENERIC_ID_ENABLE_ETH, + DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA, + DEVLINK_PARAM_GENERIC_ID_ENABLE_VNET, /* add new param generic ids above here*/ __DEVLINK_PARAM_GENERIC_ID_MAX, @@ -561,6 +564,15 @@ enum devlink_param_generic_id { #define DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_NAME "enable_remote_dev_reset" #define DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_TYPE DEVLINK_PARAM_TYPE_BOOL +#define DEVLINK_PARAM_GENERIC_ENABLE_ETH_NAME "enable_eth" +#define DEVLINK_PARAM_GENERIC_ENABLE_ETH_TYPE DEVLINK_PARAM_TYPE_BOOL + +#define DEVLINK_PARAM_GENERIC_ENABLE_RDMA_NAME "enable_rdma" +#define DEVLINK_PARAM_GENERIC_ENABLE_RDMA_TYPE DEVLINK_PARAM_TYPE_BOOL + +#define DEVLINK_PARAM_GENERIC_ENABLE_VNET_NAME "enable_vnet" +#define DEVLINK_PARAM_GENERIC_ENABLE_VNET_TYPE DEVLINK_PARAM_TYPE_BOOL + #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \ { \ .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ @@ -1398,8 +1410,8 @@ struct devlink_ops { * * Note: @extack can be NULL when port notifier queries the port function. */ - int (*port_function_hw_addr_get)(struct devlink *devlink, struct devlink_port *port, - u8 *hw_addr, int *hw_addr_len, + int (*port_function_hw_addr_get)(struct devlink_port *port, u8 *hw_addr, + int *hw_addr_len, struct netlink_ext_ack *extack); /** * @port_function_hw_addr_set: Port function's hardware address set function. @@ -1408,7 +1420,7 @@ struct devlink_ops { * by the devlink port. Driver should return -EOPNOTSUPP if it doesn't support port * function handling for a particular port. */ - int (*port_function_hw_addr_set)(struct devlink *devlink, struct devlink_port *port, + int (*port_function_hw_addr_set)(struct devlink_port *port, const u8 *hw_addr, int hw_addr_len, struct netlink_ext_ack *extack); /** @@ -1464,8 +1476,7 @@ struct devlink_ops { * * Return: 0 on success, negative value otherwise. */ - int (*port_fn_state_get)(struct devlink *devlink, - struct devlink_port *port, + int (*port_fn_state_get)(struct devlink_port *port, enum devlink_port_fn_state *state, enum devlink_port_fn_opstate *opstate, struct netlink_ext_ack *extack); @@ -1480,8 +1491,7 @@ struct devlink_ops { * * Return: 0 on success, negative value otherwise. */ - int (*port_fn_state_set)(struct devlink *devlink, - struct devlink_port *port, + int (*port_fn_state_set)(struct devlink_port *port, enum devlink_port_fn_state state, struct netlink_ext_ack *extack); @@ -1542,9 +1552,21 @@ static inline struct devlink *netdev_to_devlink(struct net_device *dev) struct ib_device; struct net *devlink_net(const struct devlink *devlink); -void devlink_net_set(struct devlink *devlink, struct net *net); -struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size); -int devlink_register(struct devlink *devlink, struct device *dev); +/* This call is intended for software devices that can create + * devlink instances in other namespaces than init_net. + * + * Drivers that operate on real HW must use devlink_alloc() instead. + */ +struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, + size_t priv_size, struct net *net, + struct device *dev); +static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, + size_t priv_size, + struct device *dev) +{ + return devlink_alloc_ns(ops, priv_size, &init_net, dev); +} +int devlink_register(struct devlink *devlink); void devlink_unregister(struct devlink *devlink); void devlink_reload_enable(struct devlink *devlink); void devlink_reload_disable(struct devlink *devlink); @@ -1625,8 +1647,16 @@ int devlink_params_register(struct devlink *devlink, void devlink_params_unregister(struct devlink *devlink, const struct devlink_param *params, size_t params_count); +int devlink_param_register(struct devlink *devlink, + const struct devlink_param *param); +void devlink_param_unregister(struct devlink *devlink, + const struct devlink_param *param); void devlink_params_publish(struct devlink *devlink); void devlink_params_unpublish(struct devlink *devlink); +void devlink_param_publish(struct devlink *devlink, + const struct devlink_param *param); +void devlink_param_unpublish(struct devlink *devlink, + const struct devlink_param *param); int devlink_port_params_register(struct devlink_port *devlink_port, const struct devlink_param *params, size_t params_count); diff --git a/include/net/dn_fib.h b/include/net/dn_fib.h index ccc6e9df178b..ddd6565957b3 100644 --- a/include/net/dn_fib.h +++ b/include/net/dn_fib.h @@ -29,7 +29,7 @@ struct dn_fib_nh { struct dn_fib_info { struct dn_fib_info *fib_next; struct dn_fib_info *fib_prev; - int fib_treeref; + refcount_t fib_treeref; refcount_t fib_clntref; int fib_dead; unsigned int fib_flags; diff --git a/include/net/dsa.h b/include/net/dsa.h index 33f40c1ec379..0c2cba45fa79 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -79,20 +79,13 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, }; -struct packet_type; struct dsa_switch; struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); - struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt); + struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); void (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, int *offset); - /* Used to determine which traffic should match the DSA filter in - * eth_type_trans, and which, if any, should bypass it and be processed - * as regular on the master net device. - */ - bool (*filter)(const struct sk_buff *skb, struct net_device *dev); unsigned int needed_headroom; unsigned int needed_tailroom; const char *name; @@ -111,8 +104,8 @@ struct dsa_device_ops { * function pointers. */ struct dsa_netdevice_ops { - int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, - int cmd); + int (*ndo_eth_ioctl)(struct net_device *dev, struct ifreq *ifr, + int cmd); }; #define DSA_TAG_DRIVER_ALIAS "dsa_tag-" @@ -159,6 +152,12 @@ struct dsa_switch_tree { */ struct net_device **lags; unsigned int lags_len; + + /* Track the largest switch index within a tree */ + unsigned int last_switch; + + /* Track the bridges with forwarding offload enabled */ + unsigned long fwd_offloading_bridges; }; #define dsa_lags_foreach_id(_id, _dst) \ @@ -238,9 +237,7 @@ struct dsa_port { /* Copies for faster access in master receive hot path */ struct dsa_switch_tree *dst; - struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt); - bool (*filter)(const struct sk_buff *skb, struct net_device *dev); + struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); enum { DSA_PORT_TYPE_UNUSED = 0, @@ -257,8 +254,11 @@ struct dsa_port { struct device_node *dn; unsigned int ageing_time; bool vlan_filtering; + /* Managed by DSA on user ports and by drivers on CPU and DSA ports */ + bool learning; u8 stp_state; struct net_device *bridge_dev; + int bridge_num; struct devlink_port devlink_port; bool devlink_port_setup; struct phylink *pl; @@ -352,6 +352,9 @@ struct dsa_switch { unsigned int ageing_time_min; unsigned int ageing_time_max; + /* Storage for drivers using tag_8021q */ + struct dsa_8021q_context *tag_8021q_ctx; + /* devlink used to represent this switch device */ struct devlink *devlink; @@ -407,6 +410,12 @@ struct dsa_switch { */ unsigned int num_lag_ids; + /* Drivers that support bridge forwarding offload should set this to + * the maximum number of bridges spanning the same switch tree that can + * be offloaded. + */ + unsigned int num_fwd_offloading_bridges; + size_t num_ports; }; @@ -690,6 +699,14 @@ struct dsa_switch_ops { struct net_device *bridge); void (*port_bridge_leave)(struct dsa_switch *ds, int port, struct net_device *bridge); + /* Called right after .port_bridge_join() */ + int (*port_bridge_tx_fwd_offload)(struct dsa_switch *ds, int port, + struct net_device *bridge, + int bridge_num); + /* Called right before .port_bridge_leave() */ + void (*port_bridge_tx_fwd_unoffload)(struct dsa_switch *ds, int port, + struct net_device *bridge, + int bridge_num); void (*port_stp_state_set)(struct dsa_switch *ds, int port, u8 state); void (*port_fast_age)(struct dsa_switch *ds, int port); @@ -699,8 +716,6 @@ struct dsa_switch_ops { int (*port_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); - int (*port_set_mrouter)(struct dsa_switch *ds, int port, bool mrouter, - struct netlink_ext_ack *extack); /* * VLAN support @@ -869,6 +884,13 @@ struct dsa_switch_ops { const struct switchdev_obj_ring_role_mrp *mrp); int (*port_mrp_del_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); + + /* + * tag_8021q operations + */ + int (*tag_8021q_vlan_add)(struct dsa_switch *ds, int port, u16 vid, + u16 flags); + int (*tag_8021q_vlan_del)(struct dsa_switch *ds, int port, u16 vid); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ @@ -954,15 +976,6 @@ static inline bool netdev_uses_dsa(const struct net_device *dev) return false; } -static inline bool dsa_can_decode(const struct sk_buff *skb, - struct net_device *dev) -{ -#if IS_ENABLED(CONFIG_NET_DSA) - return !dev->dsa_ptr->filter || dev->dsa_ptr->filter(skb, dev); -#endif - return false; -} - /* All DSA tags that push the EtherType to the right (basically all except tail * tags, which don't break dissection) can be treated the same from the * perspective of the flow dissector. @@ -1003,8 +1016,8 @@ static inline int __dsa_netdevice_ops_check(struct net_device *dev) return 0; } -static inline int dsa_ndo_do_ioctl(struct net_device *dev, struct ifreq *ifr, - int cmd) +static inline int dsa_ndo_eth_ioctl(struct net_device *dev, struct ifreq *ifr, + int cmd) { const struct dsa_netdevice_ops *ops; int err; @@ -1015,11 +1028,11 @@ static inline int dsa_ndo_do_ioctl(struct net_device *dev, struct ifreq *ifr, ops = dev->dsa_ptr->netdev_ops; - return ops->ndo_do_ioctl(dev, ifr, cmd); + return ops->ndo_eth_ioctl(dev, ifr, cmd); } #else -static inline int dsa_ndo_do_ioctl(struct net_device *dev, struct ifreq *ifr, - int cmd) +static inline int dsa_ndo_eth_ioctl(struct net_device *dev, struct ifreq *ifr, + int cmd) { return -EOPNOTSUPP; } diff --git a/include/net/dst.h b/include/net/dst.h index 75b1e734e9c2..a057319aabef 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -277,6 +277,7 @@ static inline void skb_dst_drop(struct sk_buff *skb) static inline void __skb_dst_copy(struct sk_buff *nskb, unsigned long refdst) { + nskb->slow_gro |= !!refdst; nskb->_skb_refdst = refdst; if (!(nskb->_skb_refdst & SKB_DST_NOREF)) dst_clone(skb_dst(nskb)); @@ -316,6 +317,7 @@ static inline bool skb_dst_force(struct sk_buff *skb) dst = NULL; skb->_skb_refdst = (unsigned long)dst; + skb->slow_gro |= !!dst; } return skb->_skb_refdst != 0UL; diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 1b9d75aedb22..3961461d9c8b 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -451,6 +451,7 @@ struct flow_block_offload { struct list_head *driver_block_list; struct netlink_ext_ack *extack; struct Qdisc *sch; + struct list_head *cb_list_head; }; enum tc_setup_type; diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 71bb4cc4d05d..42235c178b06 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -82,9 +82,6 @@ struct ip6_sf_socklist { struct in6_addr sl_addr[]; }; -#define IP6_SFLSIZE(count) (sizeof(struct ip6_sf_socklist) + \ - (count) * sizeof(struct in6_addr)) - #define IP6_SFBLOCK 10 /* allocate this many at once */ struct ipv6_mc_socklist { diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index ca6a3ea9057e..f72ec113ae56 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -160,6 +160,12 @@ struct inet_hashinfo { ____cacheline_aligned_in_smp; }; +#define inet_lhash2_for_each_icsk_continue(__icsk) \ + hlist_for_each_entry_continue(__icsk, icsk_listen_portaddr_node) + +#define inet_lhash2_for_each_icsk(__icsk, list) \ + hlist_for_each_entry(__icsk, list, icsk_listen_portaddr_node) + #define inet_lhash2_for_each_icsk_rcu(__icsk, list) \ hlist_for_each_entry_rcu(__icsk, list, icsk_listen_portaddr_node) diff --git a/include/net/ioam6.h b/include/net/ioam6.h new file mode 100644 index 000000000000..3c2993bc48c8 --- /dev/null +++ b/include/net/ioam6.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * IPv6 IOAM implementation + * + * Author: + * Justin Iurman <justin.iurman@uliege.be> + */ + +#ifndef _NET_IOAM6_H +#define _NET_IOAM6_H + +#include <linux/net.h> +#include <linux/ipv6.h> +#include <linux/ioam6.h> +#include <linux/rhashtable-types.h> + +struct ioam6_namespace { + struct rhash_head head; + struct rcu_head rcu; + + struct ioam6_schema __rcu *schema; + + __be16 id; + __be32 data; + __be64 data_wide; +}; + +struct ioam6_schema { + struct rhash_head head; + struct rcu_head rcu; + + struct ioam6_namespace __rcu *ns; + + u32 id; + int len; + __be32 hdr; + + u8 data[0]; +}; + +struct ioam6_pernet_data { + struct mutex lock; + struct rhashtable namespaces; + struct rhashtable schemas; +}; + +static inline struct ioam6_pernet_data *ioam6_pernet(struct net *net) +{ +#if IS_ENABLED(CONFIG_IPV6) + return net->ipv6.ioam6_data; +#else + return NULL; +#endif +} + +struct ioam6_namespace *ioam6_namespace(struct net *net, __be16 id); +void ioam6_fill_trace_data(struct sk_buff *skb, + struct ioam6_namespace *ns, + struct ioam6_trace_hdr *trace); + +int ioam6_init(void); +void ioam6_exit(void); + +int ioam6_iptunnel_init(void); +void ioam6_iptunnel_exit(void); + +#endif /* _NET_IOAM6_H */ diff --git a/include/net/ip.h b/include/net/ip.h index d9683bef8684..9192444f2964 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -436,18 +436,32 @@ static inline bool ip_sk_ignore_df(const struct sock *sk) static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, bool forwarding) { + const struct rtable *rt = container_of(dst, struct rtable, dst); struct net *net = dev_net(dst->dev); unsigned int mtu; if (net->ipv4.sysctl_ip_fwd_use_pmtu || ip_mtu_locked(dst) || - !forwarding) - return dst_mtu(dst); + !forwarding) { + mtu = rt->rt_pmtu; + if (mtu && time_before(jiffies, rt->dst.expires)) + goto out; + } /* 'forwarding = true' case should always honour route mtu */ mtu = dst_metric_raw(dst, RTAX_MTU); - if (!mtu) - mtu = min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU); + if (mtu) + goto out; + + mtu = READ_ONCE(dst->dev->mtu); + + if (unlikely(ip_mtu_locked(dst))) { + if (rt->rt_uses_gateway && mtu > 576) + mtu = 576; + } + +out: + mtu = min_t(unsigned int, mtu, IP_MAX_MTU); return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 0bf09a9bca4e..5efd0b71dc67 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -316,12 +316,13 @@ static inline bool rt6_duplicate_nexthop(struct fib6_info *a, struct fib6_info * !lwtunnel_cmp_encap(nha->fib_nh_lws, nhb->fib_nh_lws); } -static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) +static inline unsigned int ip6_dst_mtu_maybe_forward(const struct dst_entry *dst, + bool forwarding) { struct inet6_dev *idev; unsigned int mtu; - if (dst_metric_locked(dst, RTAX_MTU)) { + if (!forwarding || dst_metric_locked(dst, RTAX_MTU)) { mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) goto out; diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 3ab2563b1a23..21c5386d4a6d 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -133,7 +133,7 @@ struct fib_info { struct hlist_node fib_lhash; struct list_head nh_list; struct net *fib_net; - int fib_treeref; + refcount_t fib_treeref; refcount_t fib_clntref; unsigned int fib_flags; unsigned char fib_dead; diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 548b65bd3973..bc3b13ec93c9 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -270,7 +270,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const u8 proto, int tunnel_hlen); int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); -int ip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); +int ip_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, + void __user *data, int cmd); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu); diff --git a/include/net/ipx.h b/include/net/ipx.h deleted file mode 100644 index 9d1342807b59..000000000000 --- a/include/net/ipx.h +++ /dev/null @@ -1,171 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NET_INET_IPX_H_ -#define _NET_INET_IPX_H_ -/* - * The following information is in its entirety obtained from: - * - * Novell 'IPX Router Specification' Version 1.10 - * Part No. 107-000029-001 - * - * Which is available from ftp.novell.com - */ - -#include <linux/netdevice.h> -#include <net/datalink.h> -#include <linux/ipx.h> -#include <linux/list.h> -#include <linux/slab.h> -#include <linux/refcount.h> - -struct ipx_address { - __be32 net; - __u8 node[IPX_NODE_LEN]; - __be16 sock; -}; - -#define ipx_broadcast_node "\377\377\377\377\377\377" -#define ipx_this_node "\0\0\0\0\0\0" - -#define IPX_MAX_PPROP_HOPS 8 - -struct ipxhdr { - __be16 ipx_checksum __packed; -#define IPX_NO_CHECKSUM cpu_to_be16(0xFFFF) - __be16 ipx_pktsize __packed; - __u8 ipx_tctrl; - __u8 ipx_type; -#define IPX_TYPE_UNKNOWN 0x00 -#define IPX_TYPE_RIP 0x01 /* may also be 0 */ -#define IPX_TYPE_SAP 0x04 /* may also be 0 */ -#define IPX_TYPE_SPX 0x05 /* SPX protocol */ -#define IPX_TYPE_NCP 0x11 /* $lots for docs on this (SPIT) */ -#define IPX_TYPE_PPROP 0x14 /* complicated flood fill brdcast */ - struct ipx_address ipx_dest __packed; - struct ipx_address ipx_source __packed; -}; - -/* From af_ipx.c */ -extern int sysctl_ipx_pprop_broadcasting; - -struct ipx_interface { - /* IPX address */ - __be32 if_netnum; - unsigned char if_node[IPX_NODE_LEN]; - refcount_t refcnt; - - /* physical device info */ - struct net_device *if_dev; - struct datalink_proto *if_dlink; - __be16 if_dlink_type; - - /* socket support */ - unsigned short if_sknum; - struct hlist_head if_sklist; - spinlock_t if_sklist_lock; - - /* administrative overhead */ - int if_ipx_offset; - unsigned char if_internal; - unsigned char if_primary; - - struct list_head node; /* node in ipx_interfaces list */ -}; - -struct ipx_route { - __be32 ir_net; - struct ipx_interface *ir_intrfc; - unsigned char ir_routed; - unsigned char ir_router_node[IPX_NODE_LEN]; - struct list_head node; /* node in ipx_routes list */ - refcount_t refcnt; -}; - -struct ipx_cb { - u8 ipx_tctrl; - __be32 ipx_dest_net; - __be32 ipx_source_net; - struct { - __be32 netnum; - int index; - } last_hop; -}; - -#include <net/sock.h> - -struct ipx_sock { - /* struct sock has to be the first member of ipx_sock */ - struct sock sk; - struct ipx_address dest_addr; - struct ipx_interface *intrfc; - __be16 port; -#ifdef CONFIG_IPX_INTERN - unsigned char node[IPX_NODE_LEN]; -#endif - unsigned short type; - /* - * To handle special ncp connection-handling sockets for mars_nwe, - * the connection number must be stored in the socket. - */ - unsigned short ipx_ncp_conn; -}; - -static inline struct ipx_sock *ipx_sk(struct sock *sk) -{ - return (struct ipx_sock *)sk; -} - -#define IPX_SKB_CB(__skb) ((struct ipx_cb *)&((__skb)->cb[0])) - -#define IPX_MIN_EPHEMERAL_SOCKET 0x4000 -#define IPX_MAX_EPHEMERAL_SOCKET 0x7fff - -extern struct list_head ipx_routes; -extern rwlock_t ipx_routes_lock; - -extern struct list_head ipx_interfaces; -struct ipx_interface *ipx_interfaces_head(void); -extern spinlock_t ipx_interfaces_lock; - -extern struct ipx_interface *ipx_primary_net; - -int ipx_proc_init(void); -void ipx_proc_exit(void); - -const char *ipx_frame_name(__be16); -const char *ipx_device_name(struct ipx_interface *intrfc); - -static __inline__ void ipxitf_hold(struct ipx_interface *intrfc) -{ - refcount_inc(&intrfc->refcnt); -} - -void ipxitf_down(struct ipx_interface *intrfc); -struct ipx_interface *ipxitf_find_using_net(__be32 net); -int ipxitf_send(struct ipx_interface *intrfc, struct sk_buff *skb, char *node); -__be16 ipx_cksum(struct ipxhdr *packet, int length); -int ipxrtr_add_route(__be32 network, struct ipx_interface *intrfc, - unsigned char *node); -void ipxrtr_del_routes(struct ipx_interface *intrfc); -int ipxrtr_route_packet(struct sock *sk, struct sockaddr_ipx *usipx, - struct msghdr *msg, size_t len, int noblock); -int ipxrtr_route_skb(struct sk_buff *skb); -struct ipx_route *ipxrtr_lookup(__be32 net); -int ipxrtr_ioctl(unsigned int cmd, void __user *arg); - -static __inline__ void ipxitf_put(struct ipx_interface *intrfc) -{ - if (refcount_dec_and_test(&intrfc->refcnt)) - ipxitf_down(intrfc); -} - -static __inline__ void ipxrtr_hold(struct ipx_route *rt) -{ - refcount_inc(&rt->refcnt); -} - -static __inline__ void ipxrtr_put(struct ipx_route *rt) -{ - if (refcount_dec_and_test(&rt->refcnt)) - kfree(rt); -} -#endif /* _NET_INET_IPX_H_ */ diff --git a/include/net/mctp.h b/include/net/mctp.h new file mode 100644 index 000000000000..a824d47c3c6d --- /dev/null +++ b/include/net/mctp.h @@ -0,0 +1,232 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Management Component Transport Protocol (MCTP) + * + * Copyright (c) 2021 Code Construct + * Copyright (c) 2021 Google + */ + +#ifndef __NET_MCTP_H +#define __NET_MCTP_H + +#include <linux/bits.h> +#include <linux/mctp.h> +#include <net/net_namespace.h> +#include <net/sock.h> + +/* MCTP packet definitions */ +struct mctp_hdr { + u8 ver; + u8 dest; + u8 src; + u8 flags_seq_tag; +}; + +#define MCTP_VER_MIN 1 +#define MCTP_VER_MAX 1 + +/* Definitions for flags_seq_tag field */ +#define MCTP_HDR_FLAG_SOM BIT(7) +#define MCTP_HDR_FLAG_EOM BIT(6) +#define MCTP_HDR_FLAG_TO BIT(3) +#define MCTP_HDR_FLAGS GENMASK(5, 3) +#define MCTP_HDR_SEQ_SHIFT 4 +#define MCTP_HDR_SEQ_MASK GENMASK(1, 0) +#define MCTP_HDR_TAG_SHIFT 0 +#define MCTP_HDR_TAG_MASK GENMASK(2, 0) + +#define MCTP_HEADER_MAXLEN 4 + +#define MCTP_INITIAL_DEFAULT_NET 1 + +static inline bool mctp_address_ok(mctp_eid_t eid) +{ + return eid >= 8 && eid < 255; +} + +static inline struct mctp_hdr *mctp_hdr(struct sk_buff *skb) +{ + return (struct mctp_hdr *)skb_network_header(skb); +} + +/* socket implementation */ +struct mctp_sock { + struct sock sk; + + /* bind() params */ + int bind_net; + mctp_eid_t bind_addr; + __u8 bind_type; + + /* list of mctp_sk_key, for incoming tag lookup. updates protected + * by sk->net->keys_lock + */ + struct hlist_head keys; +}; + +/* Key for matching incoming packets to sockets or reassembly contexts. + * Packets are matched on (src,dest,tag). + * + * Lifetime requirements: + * + * - keys are free()ed via RCU + * + * - a mctp_sk_key contains a reference to a struct sock; this is valid + * for the life of the key. On sock destruction (through unhash), the key is + * removed from lists (see below), and will not be observable after a RCU + * grace period. + * + * any RX occurring within that grace period may still queue to the socket, + * but will hit the SOCK_DEAD case before the socket is freed. + * + * - these mctp_sk_keys appear on two lists: + * 1) the struct mctp_sock->keys list + * 2) the struct netns_mctp->keys list + * + * updates to either list are performed under the netns_mctp->keys + * lock. + * + * - a key may have a sk_buff attached as part of an in-progress message + * reassembly (->reasm_head). The reassembly context is protected by + * reasm_lock, which may be acquired with the keys lock (above) held, if + * necessary. Consequently, keys lock *cannot* be acquired with the + * reasm_lock held. + * + * - there are two destruction paths for a mctp_sk_key: + * + * - through socket unhash (see mctp_sk_unhash). This performs the list + * removal under keys_lock. + * + * - where a key is established to receive a reply message: after receiving + * the (complete) reply, or during reassembly errors. Here, we clean up + * the reassembly context (marking reasm_dead, to prevent another from + * starting), and remove the socket from the netns & socket lists. + */ +struct mctp_sk_key { + mctp_eid_t peer_addr; + mctp_eid_t local_addr; + __u8 tag; /* incoming tag match; invert TO for local */ + + /* we hold a ref to sk when set */ + struct sock *sk; + + /* routing lookup list */ + struct hlist_node hlist; + + /* per-socket list */ + struct hlist_node sklist; + + /* incoming fragment reassembly context */ + spinlock_t reasm_lock; + struct sk_buff *reasm_head; + struct sk_buff **reasm_tailp; + bool reasm_dead; + u8 last_seq; + + struct rcu_head rcu; +}; + +struct mctp_skb_cb { + unsigned int magic; + unsigned int net; + mctp_eid_t src; +}; + +/* skb control-block accessors with a little extra debugging for initial + * development. + * + * TODO: remove checks & mctp_skb_cb->magic; replace callers of __mctp_cb + * with mctp_cb(). + * + * __mctp_cb() is only for the initial ingress code; we should see ->magic set + * at all times after this. + */ +static inline struct mctp_skb_cb *__mctp_cb(struct sk_buff *skb) +{ + struct mctp_skb_cb *cb = (void *)skb->cb; + + cb->magic = 0x4d435450; + return cb; +} + +static inline struct mctp_skb_cb *mctp_cb(struct sk_buff *skb) +{ + struct mctp_skb_cb *cb = (void *)skb->cb; + + WARN_ON(cb->magic != 0x4d435450); + return (void *)(skb->cb); +} + +/* Route definition. + * + * These are held in the pernet->mctp.routes list, with RCU protection for + * removed routes. We hold a reference to the netdev; routes need to be + * dropped on NETDEV_UNREGISTER events. + * + * Updates to the route table are performed under rtnl; all reads under RCU, + * so routes cannot be referenced over a RCU grace period. Specifically: A + * caller cannot block between mctp_route_lookup and passing the route to + * mctp_do_route. + */ +struct mctp_route { + mctp_eid_t min, max; + + struct mctp_dev *dev; + unsigned int mtu; + unsigned char type; + int (*output)(struct mctp_route *route, + struct sk_buff *skb); + + struct list_head list; + refcount_t refs; + struct rcu_head rcu; +}; + +/* route interfaces */ +struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet, + mctp_eid_t daddr); + +int mctp_do_route(struct mctp_route *rt, struct sk_buff *skb); + +int mctp_local_output(struct sock *sk, struct mctp_route *rt, + struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag); + +/* routing <--> device interface */ +unsigned int mctp_default_net(struct net *net); +int mctp_default_net_set(struct net *net, unsigned int index); +int mctp_route_add_local(struct mctp_dev *mdev, mctp_eid_t addr); +int mctp_route_remove_local(struct mctp_dev *mdev, mctp_eid_t addr); +void mctp_route_remove_dev(struct mctp_dev *mdev); + +/* neighbour definitions */ +enum mctp_neigh_source { + MCTP_NEIGH_STATIC, + MCTP_NEIGH_DISCOVER, +}; + +struct mctp_neigh { + struct mctp_dev *dev; + mctp_eid_t eid; + enum mctp_neigh_source source; + + unsigned char ha[MAX_ADDR_LEN]; + + struct list_head list; + struct rcu_head rcu; +}; + +int mctp_neigh_init(void); +void mctp_neigh_exit(void); + +// ret_hwaddr may be NULL, otherwise must have space for MAX_ADDR_LEN +int mctp_neigh_lookup(struct mctp_dev *dev, mctp_eid_t eid, + void *ret_hwaddr); +void mctp_neigh_remove_dev(struct mctp_dev *mdev); + +int mctp_routes_init(void); +void mctp_routes_exit(void); + +void mctp_device_init(void); +void mctp_device_exit(void); + +#endif /* __NET_MCTP_H */ diff --git a/include/net/mctpdevice.h b/include/net/mctpdevice.h new file mode 100644 index 000000000000..57e773ff08bb --- /dev/null +++ b/include/net/mctpdevice.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Management Component Transport Protocol (MCTP) - device + * definitions. + * + * Copyright (c) 2021 Code Construct + * Copyright (c) 2021 Google + */ + +#ifndef __NET_MCTPDEVICE_H +#define __NET_MCTPDEVICE_H + +#include <linux/list.h> +#include <linux/types.h> +#include <linux/refcount.h> + +struct mctp_dev { + struct net_device *dev; + + unsigned int net; + + /* Only modified under RTNL. Reads have addrs_lock held */ + u8 *addrs; + size_t num_addrs; + spinlock_t addrs_lock; + + struct rcu_head rcu; +}; + +#define MCTP_INITIAL_DEFAULT_NET 1 + +struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev); +struct mctp_dev *__mctp_dev_get(const struct net_device *dev); +struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev); + +#endif /* __NET_MCTPDEVICE_H */ diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 12cf6d7ea62c..bb5fa5914032 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -23,7 +23,6 @@ #include <net/netns/ieee802154_6lowpan.h> #include <net/netns/sctp.h> #include <net/netns/netfilter.h> -#include <net/netns/x_tables.h> #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) #include <net/netns/conntrack.h> #endif @@ -34,6 +33,7 @@ #include <net/netns/xdp.h> #include <net/netns/smc.h> #include <net/netns/bpf.h> +#include <net/netns/mctp.h> #include <linux/ns_common.h> #include <linux/idr.h> #include <linux/skbuff.h> @@ -132,7 +132,6 @@ struct net { #endif #ifdef CONFIG_NETFILTER struct netns_nf nf; - struct netns_xt xt; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) struct netns_ct ct; #endif @@ -167,6 +166,9 @@ struct net { #ifdef CONFIG_XDP_SOCKETS struct netns_xdp xdp; #endif +#if IS_ENABLED(CONFIG_MCTP) + struct netns_mctp mctp; +#endif #if IS_ENABLED(CONFIG_CRYPTO_USER) struct sock *crypto_nlsk; #endif diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index e770bba00066..9eed51e920e8 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -33,8 +33,8 @@ struct nf_queue_handler { void (*nf_hook_drop)(struct net *net); }; -void nf_register_queue_handler(struct net *net, const struct nf_queue_handler *qh); -void nf_unregister_queue_handler(struct net *net); +void nf_register_queue_handler(const struct nf_queue_handler *qh); +void nf_unregister_queue_handler(void); void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict); void nf_queue_entry_get_refs(struct nf_queue_entry *entry); diff --git a/include/net/netlink.h b/include/net/netlink.h index 1ceec518ab49..7a2a9d3144ba 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -885,7 +885,7 @@ static inline int nlmsg_validate_deprecated(const struct nlmsghdr *nlh, */ static inline int nlmsg_report(const struct nlmsghdr *nlh) { - return !!(nlh->nlmsg_flags & NLM_F_ECHO); + return nlh ? !!(nlh->nlmsg_flags & NLM_F_ECHO) : 0; } /** diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index b8620519eace..2f65701a43c9 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -174,7 +174,6 @@ struct netns_ipv4 { int sysctl_tcp_fastopen; const struct tcp_congestion_ops __rcu *tcp_congestion_control; struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; - spinlock_t tcp_fastopen_ctx_lock; unsigned int sysctl_tcp_fastopen_blackhole_timeout; atomic_t tfo_active_disable_times; unsigned long tfo_active_disable_stamp; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index bde0b7adb4a3..a4b550380316 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -51,6 +51,8 @@ struct netns_sysctl_ipv6 { int max_dst_opts_len; int max_hbh_opts_len; int seg6_flowlabel; + u32 ioam6_id; + u64 ioam6_id_wide; bool skip_notify_on_dev_down; u8 fib_notify_on_flag_change; }; @@ -110,6 +112,7 @@ struct netns_ipv6 { spinlock_t lock; u32 seq; } ip6addrlbl_table; + struct ioam6_pernet_data *ioam6_data; }; #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) diff --git a/include/net/netns/mctp.h b/include/net/netns/mctp.h new file mode 100644 index 000000000000..acedef12a35e --- /dev/null +++ b/include/net/netns/mctp.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * MCTP per-net structures + */ + +#ifndef __NETNS_MCTP_H__ +#define __NETNS_MCTP_H__ + +#include <linux/types.h> + +struct netns_mctp { + /* Only updated under RTNL, entries freed via RCU */ + struct list_head routes; + + /* Bound sockets: list of sockets bound by type. + * This list is updated from non-atomic contexts (under bind_lock), + * and read (under rcu) in packet rx + */ + struct mutex bind_lock; + struct hlist_head binds; + + /* tag allocations. This list is read and updated from atomic contexts, + * but elements are free()ed after a RCU grace-period + */ + spinlock_t keys_lock; + struct hlist_head keys; + + /* MCTP network */ + unsigned int default_net; + + /* neighbour table */ + struct mutex neigh_lock; + struct list_head neighbours; +}; + +#endif /* __NETNS_MCTP_H__ */ diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h index 15e2b13fb0c0..986a2a9cfdfa 100644 --- a/include/net/netns/netfilter.h +++ b/include/net/netns/netfilter.h @@ -12,7 +12,6 @@ struct netns_nf { #if defined CONFIG_PROC_FS struct proc_dir_entry *proc_netfilter; #endif - const struct nf_queue_handler __rcu *queue_handler; const struct nf_logger __rcu *nf_loggers[NFPROTO_NUMPROTO]; #ifdef CONFIG_SYSCTL struct ctl_table_header *nf_log_dir_header; diff --git a/include/net/netns/x_tables.h b/include/net/netns/x_tables.h deleted file mode 100644 index d02316ec2906..000000000000 --- a/include/net/netns/x_tables.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __NETNS_X_TABLES_H -#define __NETNS_X_TABLES_H - -#include <linux/list.h> -#include <linux/netfilter_defs.h> - -struct netns_xt { - bool notrack_deprecated_warning; - bool clusterip_deprecated_warning; -}; -#endif diff --git a/include/net/nfc/digital.h b/include/net/nfc/digital.h index 963db96bcbbb..bb3e8fdc0692 100644 --- a/include/net/nfc/digital.h +++ b/include/net/nfc/digital.h @@ -191,7 +191,7 @@ struct digital_poll_tech { struct nfc_digital_dev { struct nfc_dev *nfc_dev; - struct nfc_digital_ops *ops; + const struct nfc_digital_ops *ops; u32 protocols; @@ -236,7 +236,7 @@ struct nfc_digital_dev { void (*skb_add_crc)(struct sk_buff *skb); }; -struct nfc_digital_dev *nfc_digital_allocate_device(struct nfc_digital_ops *ops, +struct nfc_digital_dev *nfc_digital_allocate_device(const struct nfc_digital_ops *ops, __u32 supported_protocols, __u32 driver_capabilities, int tx_headroom, diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h index b35f37a57686..756c11084f65 100644 --- a/include/net/nfc/hci.h +++ b/include/net/nfc/hci.h @@ -118,7 +118,7 @@ struct nfc_hci_dev { struct sk_buff_head msg_rx_queue; - struct nfc_hci_ops *ops; + const struct nfc_hci_ops *ops; struct nfc_llc *llc; @@ -151,7 +151,7 @@ struct nfc_hci_dev { }; /* hci device allocation */ -struct nfc_hci_dev *nfc_hci_allocate_device(struct nfc_hci_ops *ops, +struct nfc_hci_dev *nfc_hci_allocate_device(const struct nfc_hci_ops *ops, struct nfc_hci_init_data *init_data, unsigned long quirks, u32 protocols, @@ -168,7 +168,7 @@ void nfc_hci_set_clientdata(struct nfc_hci_dev *hdev, void *clientdata); void *nfc_hci_get_clientdata(struct nfc_hci_dev *hdev); static inline int nfc_hci_set_vendor_cmds(struct nfc_hci_dev *hdev, - struct nfc_vendor_cmd *cmds, + const struct nfc_vendor_cmd *cmds, int n_cmds) { return nfc_set_vendor_cmds(hdev->ndev, cmds, n_cmds); diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index 1df0f8074c9d..a964daedc17b 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -82,10 +82,10 @@ struct nci_ops { void (*hci_cmd_received)(struct nci_dev *ndev, u8 pipe, u8 cmd, struct sk_buff *skb); - struct nci_driver_ops *prop_ops; + const struct nci_driver_ops *prop_ops; size_t n_prop_ops; - struct nci_driver_ops *core_ops; + const struct nci_driver_ops *core_ops; size_t n_core_ops; }; @@ -194,7 +194,7 @@ struct nci_hci_dev { /* NCI Core structures */ struct nci_dev { struct nfc_dev *nfc_dev; - struct nci_ops *ops; + const struct nci_ops *ops; struct nci_hci_dev *hci_dev; int tx_headroom; @@ -267,7 +267,7 @@ struct nci_dev { }; /* ----- NCI Devices ----- */ -struct nci_dev *nci_allocate_device(struct nci_ops *ops, +struct nci_dev *nci_allocate_device(const struct nci_ops *ops, __u32 supported_protocols, int tx_headroom, int tx_tailroom); @@ -276,25 +276,27 @@ int nci_register_device(struct nci_dev *ndev); void nci_unregister_device(struct nci_dev *ndev); int nci_request(struct nci_dev *ndev, void (*req)(struct nci_dev *ndev, - unsigned long opt), - unsigned long opt, __u32 timeout); -int nci_prop_cmd(struct nci_dev *ndev, __u8 oid, size_t len, __u8 *payload); -int nci_core_cmd(struct nci_dev *ndev, __u16 opcode, size_t len, __u8 *payload); + const void *opt), + const void *opt, __u32 timeout); +int nci_prop_cmd(struct nci_dev *ndev, __u8 oid, size_t len, + const __u8 *payload); +int nci_core_cmd(struct nci_dev *ndev, __u16 opcode, size_t len, + const __u8 *payload); int nci_core_reset(struct nci_dev *ndev); int nci_core_init(struct nci_dev *ndev); int nci_recv_frame(struct nci_dev *ndev, struct sk_buff *skb); int nci_send_frame(struct nci_dev *ndev, struct sk_buff *skb); -int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, __u8 *val); +int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, const __u8 *val); int nci_nfcee_discover(struct nci_dev *ndev, u8 action); int nci_nfcee_mode_set(struct nci_dev *ndev, u8 nfcee_id, u8 nfcee_mode); int nci_core_conn_create(struct nci_dev *ndev, u8 destination_type, u8 number_destination_params, size_t params_len, - struct core_conn_create_dest_spec_params *params); + const struct core_conn_create_dest_spec_params *params); int nci_core_conn_close(struct nci_dev *ndev, u8 conn_id); -int nci_nfcc_loopback(struct nci_dev *ndev, void *data, size_t data_len, +int nci_nfcc_loopback(struct nci_dev *ndev, const void *data, size_t data_len, struct sk_buff **resp); struct nci_hci_dev *nci_hci_allocate(struct nci_dev *ndev); @@ -343,7 +345,7 @@ static inline void *nci_get_drvdata(struct nci_dev *ndev) } static inline int nci_set_vendor_cmds(struct nci_dev *ndev, - struct nfc_vendor_cmd *cmds, + const struct nfc_vendor_cmd *cmds, int n_cmds) { return nfc_set_vendor_cmds(ndev->nfc_dev, cmds, n_cmds); @@ -360,7 +362,7 @@ int nci_core_rsp_packet(struct nci_dev *ndev, __u16 opcode, int nci_core_ntf_packet(struct nci_dev *ndev, __u16 opcode, struct sk_buff *skb); void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb); -int nci_send_cmd(struct nci_dev *ndev, __u16 opcode, __u8 plen, void *payload); +int nci_send_cmd(struct nci_dev *ndev, __u16 opcode, __u8 plen, const void *payload); int nci_send_data(struct nci_dev *ndev, __u8 conn_id, struct sk_buff *skb); int nci_conn_max_data_pkt_payload_size(struct nci_dev *ndev, __u8 conn_id); void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb, @@ -378,7 +380,7 @@ void nci_req_complete(struct nci_dev *ndev, int result); struct nci_conn_info *nci_get_conn_info_by_conn_id(struct nci_dev *ndev, int conn_id); int nci_get_conn_info_by_dest_type_params(struct nci_dev *ndev, u8 dest_type, - struct dest_spec_params *params); + const struct dest_spec_params *params); /* ----- NCI status code ----- */ int nci_to_errno(__u8 code); diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 2cd3a261bcbc..5dee575fbe86 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -188,17 +188,17 @@ struct nfc_dev { struct rfkill *rfkill; - struct nfc_vendor_cmd *vendor_cmds; + const struct nfc_vendor_cmd *vendor_cmds; int n_vendor_cmds; - struct nfc_ops *ops; + const struct nfc_ops *ops; struct genl_info *cur_cmd_info; }; #define to_nfc_dev(_dev) container_of(_dev, struct nfc_dev, dev) extern struct class nfc_class; -struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, +struct nfc_dev *nfc_allocate_device(const struct nfc_ops *ops, u32 supported_protocols, int tx_headroom, int tx_tailroom); @@ -245,7 +245,7 @@ static inline void nfc_set_drvdata(struct nfc_dev *dev, void *data) * * @dev: The nfc device */ -static inline void *nfc_get_drvdata(struct nfc_dev *dev) +static inline void *nfc_get_drvdata(const struct nfc_dev *dev) { return dev_get_drvdata(&dev->dev); } @@ -255,7 +255,7 @@ static inline void *nfc_get_drvdata(struct nfc_dev *dev) * * @dev: The nfc device whose name to return */ -static inline const char *nfc_device_name(struct nfc_dev *dev) +static inline const char *nfc_device_name(const struct nfc_dev *dev) { return dev_name(&dev->dev); } @@ -266,7 +266,7 @@ struct sk_buff *nfc_alloc_send_skb(struct nfc_dev *dev, struct sock *sk, struct sk_buff *nfc_alloc_recv_skb(unsigned int size, gfp_t gfp); int nfc_set_remote_general_bytes(struct nfc_dev *dev, - u8 *gt, u8 gt_len); + const u8 *gt, u8 gt_len); u8 *nfc_get_local_general_bytes(struct nfc_dev *dev, size_t *gb_len); int nfc_fw_download_done(struct nfc_dev *dev, const char *firmware_name, @@ -280,7 +280,7 @@ int nfc_dep_link_is_up(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode); int nfc_tm_activated(struct nfc_dev *dev, u32 protocol, u8 comm_mode, - u8 *gb, size_t gb_len); + const u8 *gb, size_t gb_len); int nfc_tm_deactivated(struct nfc_dev *dev); int nfc_tm_data_received(struct nfc_dev *dev, struct sk_buff *skb); @@ -297,7 +297,7 @@ void nfc_send_to_raw_sock(struct nfc_dev *dev, struct sk_buff *skb, u8 payload_type, u8 direction); static inline int nfc_set_vendor_cmds(struct nfc_dev *dev, - struct nfc_vendor_cmd *cmds, + const struct nfc_vendor_cmd *cmds, int n_cmds) { if (dev->vendor_cmds || dev->n_vendor_cmds) diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 3dd62dd73027..a4082406a003 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -45,7 +45,10 @@ * Please note DMA-sync-for-CPU is still * device driver responsibility */ -#define PP_FLAG_ALL (PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV) +#define PP_FLAG_PAGE_FRAG BIT(2) /* for page frag feature */ +#define PP_FLAG_ALL (PP_FLAG_DMA_MAP |\ + PP_FLAG_DMA_SYNC_DEV |\ + PP_FLAG_PAGE_FRAG) /* * Fast allocation side cache array/stack @@ -88,6 +91,9 @@ struct page_pool { unsigned long defer_warn; u32 pages_state_hold_cnt; + unsigned int frag_offset; + struct page *frag_page; + long frag_users; /* * Data structure for allocation side @@ -137,6 +143,18 @@ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool) return page_pool_alloc_pages(pool, gfp); } +struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int *offset, + unsigned int size, gfp_t gfp); + +static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool, + unsigned int *offset, + unsigned int size) +{ + gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); + + return page_pool_alloc_frag(pool, offset, size, gfp); +} + /* get the stored dma direction. A driver might decide to treat this locally and * avoid the extra cache line from page_pool to determine the direction */ @@ -198,19 +216,48 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, page_pool_put_full_page(pool, page, true); } +#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT \ + (sizeof(dma_addr_t) > sizeof(unsigned long)) + static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - dma_addr_t ret = page->dma_addr[0]; - if (sizeof(dma_addr_t) > sizeof(unsigned long)) - ret |= (dma_addr_t)page->dma_addr[1] << 16 << 16; + dma_addr_t ret = page->dma_addr; + + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) + ret |= (dma_addr_t)page->dma_addr_upper << 16 << 16; + return ret; } static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) { - page->dma_addr[0] = addr; - if (sizeof(dma_addr_t) > sizeof(unsigned long)) - page->dma_addr[1] = upper_32_bits(addr); + page->dma_addr = addr; + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) + page->dma_addr_upper = upper_32_bits(addr); +} + +static inline void page_pool_set_frag_count(struct page *page, long nr) +{ + atomic_long_set(&page->pp_frag_count, nr); +} + +static inline long page_pool_atomic_sub_frag_count_return(struct page *page, + long nr) +{ + long ret; + + /* As suggested by Alexander, atomic_long_read() may cover up the + * reference count errors, so avoid calling atomic_long_read() in + * the cases of freeing or draining the page_frags, where we would + * not expect it to match or that are slowpath anyway. + */ + if (__builtin_constant_p(nr) && + atomic_long_read(&page->pp_frag_count) == nr) + return 0; + + ret = atomic_long_sub_return(nr, &page->pp_frag_count); + WARN_ON(ret < 0); + return ret; } static inline bool is_page_pool_compiled_in(void) @@ -253,11 +300,4 @@ static inline void page_pool_ring_unlock(struct page_pool *pool) spin_unlock_bh(&pool->ring.producer_lock); } -/* Store mem_info on struct page and use it while recycling skb frags */ -static inline -void page_pool_store_mem_info(struct page *page, struct page_pool *pp) -{ - page->pp = pp; -} - #endif /* _NET_PAGE_POOL_H */ diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 298a8d10168b..8fb47fc61097 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -76,12 +76,10 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block) return block->q; } -int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res, bool compat_mode); -int tcf_classify_ingress(struct sk_buff *skb, - const struct tcf_block *ingress_block, - const struct tcf_proto *tp, struct tcf_result *res, - bool compat_mode); +int tcf_classify(struct sk_buff *skb, + const struct tcf_block *block, + const struct tcf_proto *tp, struct tcf_result *res, + bool compat_mode); #else static inline bool tcf_block_shared(struct tcf_block *block) @@ -138,20 +136,14 @@ void tc_setup_cb_block_unregister(struct tcf_block *block, flow_setup_cb_t *cb, { } -static inline int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, +static inline int tcf_classify(struct sk_buff *skb, + const struct tcf_block *block, + const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode) { return TC_ACT_UNSPEC; } -static inline int tcf_classify_ingress(struct sk_buff *skb, - const struct tcf_block *ingress_block, - const struct tcf_proto *tp, - struct tcf_result *res, bool compat_mode) -{ - return TC_ACT_UNSPEC; -} - #endif static inline unsigned long @@ -327,7 +319,7 @@ tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts, int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, - struct tcf_exts *exts, bool ovr, bool rtnl_held, + struct tcf_exts *exts, u32 flags, struct netlink_ext_ack *extack); void tcf_exts_destroy(struct tcf_exts *exts); void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src); diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 384e800665f2..9f48733bfd21 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -153,7 +153,8 @@ struct rtnl_af_ops { u32 ext_filter_mask); int (*validate_link_af)(const struct net_device *dev, - const struct nlattr *attr); + const struct nlattr *attr, + struct netlink_ext_ack *extack); int (*set_link_af)(struct net_device *dev, const struct nlattr *attr, struct netlink_ext_ack *extack); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 9ed33e6840bd..c0069ac00e62 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -357,7 +357,7 @@ struct tcf_proto_ops { int (*change)(struct net *net, struct sk_buff *, struct tcf_proto*, unsigned long, u32 handle, struct nlattr **, - void **, bool, bool, + void **, u32, struct netlink_ext_ack *); int (*delete)(struct tcf_proto *tp, void *arg, bool *last, bool rtnl_held, diff --git a/include/net/sock.h b/include/net/sock.h index f23cb259b0e2..95b25777b53e 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -68,6 +68,7 @@ #include <net/tcp_states.h> #include <linux/net_tstamp.h> #include <net/l3mdev.h> +#include <uapi/linux/socket.h> /* * This structure really needs to be cleaned up. @@ -1438,8 +1439,6 @@ static inline int __sk_prot_rehash(struct sock *sk) #define RCV_SHUTDOWN 1 #define SEND_SHUTDOWN 2 -#define SOCK_SNDBUF_LOCK 1 -#define SOCK_RCVBUF_LOCK 2 #define SOCK_BINDADDR_LOCK 4 #define SOCK_BINDPORT_LOCK 8 @@ -2249,6 +2248,15 @@ static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struc return false; } +static inline void skb_prepare_for_gro(struct sk_buff *skb) +{ + if (skb->destructor != sock_wfree) { + skb_orphan(skb); + return; + } + skb->slow_gro = 1; +} + void sk_reset_timer(struct sock *sk, struct timer_list *timer, unsigned long expires); @@ -2392,6 +2400,11 @@ static inline gfp_t gfp_any(void) return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; } +static inline gfp_t gfp_memcg_charge(void) +{ + return in_softirq() ? GFP_NOWAIT : GFP_KERNEL; +} + static inline long sock_rcvtimeo(const struct sock *sk, bool noblock) { return noblock ? 0 : sk->sk_rcvtimeo; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index e4cac9218ce1..60d806b6a5ae 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -180,6 +180,14 @@ struct switchdev_obj_in_state_mrp { typedef int switchdev_obj_dump_cb_t(struct switchdev_obj *obj); +struct switchdev_brport { + struct net_device *dev; + const void *ctx; + struct notifier_block *atomic_nb; + struct notifier_block *blocking_nb; + bool tx_fwd_offload; +}; + enum switchdev_notifier_type { SWITCHDEV_FDB_ADD_TO_BRIDGE = 1, SWITCHDEV_FDB_DEL_TO_BRIDGE, @@ -197,6 +205,9 @@ enum switchdev_notifier_type { SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE, SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE, SWITCHDEV_VXLAN_FDB_OFFLOADED, + + SWITCHDEV_BRPORT_OFFLOADED, + SWITCHDEV_BRPORT_UNOFFLOADED, }; struct switchdev_notifier_info { @@ -226,6 +237,11 @@ struct switchdev_notifier_port_attr_info { bool handled; }; +struct switchdev_notifier_brport_info { + struct switchdev_notifier_info info; /* must be first */ + const struct switchdev_brport brport; +}; + static inline struct net_device * switchdev_notifier_info_to_dev(const struct switchdev_notifier_info *info) { @@ -238,8 +254,25 @@ switchdev_notifier_info_to_extack(const struct switchdev_notifier_info *info) return info->extack; } +static inline bool +switchdev_fdb_is_dynamically_learned(const struct switchdev_notifier_fdb_info *fdb_info) +{ + return !fdb_info->added_by_user && !fdb_info->is_local; +} + #ifdef CONFIG_NET_SWITCHDEV +int switchdev_bridge_port_offload(struct net_device *brport_dev, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + bool tx_fwd_offload, + struct netlink_ext_ack *extack); +void switchdev_bridge_port_unoffload(struct net_device *brport_dev, + const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb); + void switchdev_deferred_process(void); int switchdev_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, @@ -266,6 +299,30 @@ void switchdev_port_fwd_mark_set(struct net_device *dev, struct net_device *group_dev, bool joining); +int switchdev_handle_fdb_add_to_device(struct net_device *dev, + const struct switchdev_notifier_fdb_info *fdb_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*add_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info), + int (*lag_add_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info)); + +int switchdev_handle_fdb_del_to_device(struct net_device *dev, + const struct switchdev_notifier_fdb_info *fdb_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*del_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info), + int (*lag_del_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info)); + int switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), @@ -286,6 +343,25 @@ int switchdev_handle_port_attr_set(struct net_device *dev, struct netlink_ext_ack *extack)); #else +static inline int +switchdev_bridge_port_offload(struct net_device *brport_dev, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + bool tx_fwd_offload, + struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} + +static inline void +switchdev_bridge_port_unoffload(struct net_device *brport_dev, + const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb) +{ +} + static inline void switchdev_deferred_process(void) { } @@ -350,6 +426,38 @@ call_switchdev_blocking_notifiers(unsigned long val, } static inline int +switchdev_handle_fdb_add_to_device(struct net_device *dev, + const struct switchdev_notifier_fdb_info *fdb_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*add_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info), + int (*lag_add_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info)) +{ + return 0; +} + +static inline int +switchdev_handle_fdb_del_to_device(struct net_device *dev, + const struct switchdev_notifier_fdb_info *fdb_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*del_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info), + int (*lag_del_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info)) +{ + return 0; +} + +static inline int switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), diff --git a/include/net/tcp.h b/include/net/tcp.h index 784d5c3ef1c5..3166dc15d7d6 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1958,7 +1958,6 @@ struct tcp_iter_state { struct seq_net_private p; enum tcp_seq_states state; struct sock *syn_wait_sk; - struct tcp_seq_afinfo *bpf_seq_afinfo; int bucket, offset, sbucket, num; loff_t last_pos; }; diff --git a/include/net/xdp.h b/include/net/xdp.h index 5533f0ab2afc..ad5b02dcb6f4 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -276,6 +276,11 @@ xdp_data_meta_unsupported(const struct xdp_buff *xdp) return unlikely(xdp->data_meta > xdp->data); } +static inline bool xdp_metalen_invalid(unsigned long metalen) +{ + return (metalen & (sizeof(__u32) - 1)) || (metalen > 32); +} + struct xdp_attachment_info { struct bpf_prog *prog; u32 flags; diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 2f5ce4d4fdbf..fb5681f7e61b 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -589,6 +589,9 @@ enum ocelot_sb_pool { OCELOT_SB_POOL_NUM, }; +#define OCELOT_QUIRK_PCS_PERFORMS_RATE_ADAPTATION BIT(0) +#define OCELOT_QUIRK_QSGMII_PORTS_MUST_BE_UP BIT(1) + struct ocelot_port { struct ocelot *ocelot; @@ -798,18 +801,12 @@ void ocelot_init_port(struct ocelot *ocelot, int port); void ocelot_deinit_port(struct ocelot *ocelot, int port); /* DSA callbacks */ -void ocelot_port_enable(struct ocelot *ocelot, int port, - struct phy_device *phy); -void ocelot_port_disable(struct ocelot *ocelot, int port); void ocelot_get_strings(struct ocelot *ocelot, int port, u32 sset, u8 *data); void ocelot_get_ethtool_stats(struct ocelot *ocelot, int port, u64 *data); int ocelot_get_sset_count(struct ocelot *ocelot, int port, int sset); int ocelot_get_ts_info(struct ocelot *ocelot, int port, struct ethtool_ts_info *info); void ocelot_set_ageing_time(struct ocelot *ocelot, unsigned int msecs); -int ocelot_port_flush(struct ocelot *ocelot, int port); -void ocelot_adjust_link(struct ocelot *ocelot, int port, - struct phy_device *phydev); int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, bool enabled); void ocelot_bridge_stp_state_set(struct ocelot *ocelot, int port, u8 state); void ocelot_apply_bridge_fwd_mask(struct ocelot *ocelot); @@ -894,6 +891,18 @@ int ocelot_sb_occ_tc_port_bind_get(struct ocelot *ocelot, int port, enum devlink_sb_pool_type pool_type, u32 *p_cur, u32 *p_max); +void ocelot_phylink_mac_link_down(struct ocelot *ocelot, int port, + unsigned int link_an_mode, + phy_interface_t interface, + unsigned long quirks); +void ocelot_phylink_mac_link_up(struct ocelot *ocelot, int port, + struct phy_device *phydev, + unsigned int link_an_mode, + phy_interface_t interface, + int speed, int duplex, + bool tx_pause, bool rx_pause, + unsigned long quirks); + #if IS_ENABLED(CONFIG_BRIDGE_MRP) int ocelot_mrp_add(struct ocelot *ocelot, int port, const struct switchdev_obj_mrp *mrp); diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h index c3006c6b4a87..59c945b66f9c 100644 --- a/include/trace/events/qdisc.h +++ b/include/trace/events/qdisc.h @@ -54,6 +54,7 @@ TRACE_EVENT(qdisc_enqueue, TP_STRUCT__entry( __field(struct Qdisc *, qdisc) + __field(const struct netdev_queue *, txq) __field(void *, skbaddr) __field(int, ifindex) __field(u32, handle) @@ -62,6 +63,7 @@ TRACE_EVENT(qdisc_enqueue, TP_fast_assign( __entry->qdisc = qdisc; + __entry->txq = txq; __entry->skbaddr = skb; __entry->ifindex = txq->dev ? txq->dev->ifindex : 0; __entry->handle = qdisc->handle; diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index d588c244ec2f..1f0a2b4864e4 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -124,6 +124,8 @@ #define SO_NETNS_COOKIE 71 +#define SO_BUF_LOCK 72 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bf9252c7381e..2db6925e04f4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -324,9 +324,6 @@ union bpf_iter_link_info { * **BPF_PROG_TYPE_SK_LOOKUP** * *data_in* and *data_out* must be NULL. * - * **BPF_PROG_TYPE_XDP** - * *ctx_in* and *ctx_out* must be NULL. - * * **BPF_PROG_TYPE_RAW_TRACEPOINT**, * **BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE** * @@ -3249,7 +3246,7 @@ union bpf_attr { * long bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags) * Description * Select a **SO_REUSEPORT** socket from a - * **BPF_MAP_TYPE_REUSEPORT_ARRAY** *map*. + * **BPF_MAP_TYPE_REUSEPORT_SOCKARRAY** *map*. * It checks the selected socket is matching the incoming * request in the socket buffer. * Return @@ -4780,6 +4777,76 @@ union bpf_attr { * Execute close syscall for given FD. * Return * A syscall result. + * + * long bpf_timer_init(struct bpf_timer *timer, struct bpf_map *map, u64 flags) + * Description + * Initialize the timer. + * First 4 bits of *flags* specify clockid. + * Only CLOCK_MONOTONIC, CLOCK_REALTIME, CLOCK_BOOTTIME are allowed. + * All other bits of *flags* are reserved. + * The verifier will reject the program if *timer* is not from + * the same *map*. + * Return + * 0 on success. + * **-EBUSY** if *timer* is already initialized. + * **-EINVAL** if invalid *flags* are passed. + * **-EPERM** if *timer* is in a map that doesn't have any user references. + * The user space should either hold a file descriptor to a map with timers + * or pin such map in bpffs. When map is unpinned or file descriptor is + * closed all timers in the map will be cancelled and freed. + * + * long bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn) + * Description + * Configure the timer to call *callback_fn* static function. + * Return + * 0 on success. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier. + * **-EPERM** if *timer* is in a map that doesn't have any user references. + * The user space should either hold a file descriptor to a map with timers + * or pin such map in bpffs. When map is unpinned or file descriptor is + * closed all timers in the map will be cancelled and freed. + * + * long bpf_timer_start(struct bpf_timer *timer, u64 nsecs, u64 flags) + * Description + * Set timer expiration N nanoseconds from the current time. The + * configured callback will be invoked in soft irq context on some cpu + * and will not repeat unless another bpf_timer_start() is made. + * In such case the next invocation can migrate to a different cpu. + * Since struct bpf_timer is a field inside map element the map + * owns the timer. The bpf_timer_set_callback() will increment refcnt + * of BPF program to make sure that callback_fn code stays valid. + * When user space reference to a map reaches zero all timers + * in a map are cancelled and corresponding program's refcnts are + * decremented. This is done to make sure that Ctrl-C of a user + * process doesn't leave any timers running. If map is pinned in + * bpffs the callback_fn can re-arm itself indefinitely. + * bpf_map_update/delete_elem() helpers and user space sys_bpf commands + * cancel and free the timer in the given map element. + * The map can contain timers that invoke callback_fn-s from different + * programs. The same callback_fn can serve different timers from + * different maps if key/value layout matches across maps. + * Every bpf_timer_set_callback() can have different callback_fn. + * + * Return + * 0 on success. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier + * or invalid *flags* are passed. + * + * long bpf_timer_cancel(struct bpf_timer *timer) + * Description + * Cancel the timer and wait for callback_fn to finish if it was running. + * Return + * 0 if the timer was not active. + * 1 if the timer was active. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier. + * **-EDEADLK** if callback_fn tried to call bpf_timer_cancel() on its + * own timer which would have led to a deadlock otherwise. + * + * u64 bpf_get_func_ip(void *ctx) + * Description + * Get address of the traced function (for tracing and kprobe programs). + * Return + * Address of the traced function. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -4951,6 +5018,11 @@ union bpf_attr { FN(sys_bpf), \ FN(btf_find_by_name_kind), \ FN(sys_close), \ + FN(timer_init), \ + FN(timer_set_callback), \ + FN(timer_start), \ + FN(timer_cancel), \ + FN(get_func_ip), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -6077,6 +6149,11 @@ struct bpf_spin_lock { __u32 val; }; +struct bpf_timer { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + struct bpf_sysctl { __u32 write; /* Sysctl is being read (= 0) or written (= 1). * Allows 1,2,4-byte read, but no write. diff --git a/include/uapi/linux/can/j1939.h b/include/uapi/linux/can/j1939.h index df6e821075c1..38936460f668 100644 --- a/include/uapi/linux/can/j1939.h +++ b/include/uapi/linux/can/j1939.h @@ -78,11 +78,20 @@ enum { enum { J1939_NLA_PAD, J1939_NLA_BYTES_ACKED, + J1939_NLA_TOTAL_SIZE, + J1939_NLA_PGN, + J1939_NLA_SRC_NAME, + J1939_NLA_DEST_NAME, + J1939_NLA_SRC_ADDR, + J1939_NLA_DEST_ADDR, }; enum { J1939_EE_INFO_NONE, J1939_EE_INFO_TX_ABORT, + J1939_EE_INFO_RX_RTS, + J1939_EE_INFO_RX_DPO, + J1939_EE_INFO_RX_ABORT, }; struct j1939_filter { diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 67aa7134b301..b6db6590baf0 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -639,6 +639,8 @@ enum ethtool_link_ext_substate_link_logical_mismatch { enum ethtool_link_ext_substate_bad_signal_integrity { ETHTOOL_LINK_EXT_SUBSTATE_BSI_LARGE_NUMBER_OF_PHYSICAL_ERRORS = 1, ETHTOOL_LINK_EXT_SUBSTATE_BSI_UNSUPPORTED_RATE, + ETHTOOL_LINK_EXT_SUBSTATE_BSI_SERDES_REFERENCE_CLOCK_LOST, + ETHTOOL_LINK_EXT_SUBSTATE_BSI_SERDES_ALOS, }; /* More information in addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE. */ diff --git a/include/uapi/linux/if_arp.h b/include/uapi/linux/if_arp.h index c3cc5a9e5eaf..4783af9fe520 100644 --- a/include/uapi/linux/if_arp.h +++ b/include/uapi/linux/if_arp.h @@ -54,6 +54,7 @@ #define ARPHRD_X25 271 /* CCITT X.25 */ #define ARPHRD_HWX25 272 /* Boards with X.25 in firmware */ #define ARPHRD_CAN 280 /* Controller Area Network */ +#define ARPHRD_MCTP 290 #define ARPHRD_PPP 512 #define ARPHRD_CISCO 513 /* Cisco HDLC */ #define ARPHRD_HDLC ARPHRD_CISCO diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 6b56a7549531..f71a81fdbbc6 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -479,16 +479,22 @@ enum { /* flags used in BRIDGE_VLANDB_DUMP_FLAGS attribute to affect dumps */ #define BRIDGE_VLANDB_DUMPF_STATS (1 << 0) /* Include stats in the dump */ +#define BRIDGE_VLANDB_DUMPF_GLOBAL (1 << 1) /* Dump global vlan options only */ /* Bridge vlan RTM attributes * [BRIDGE_VLANDB_ENTRY] = { * [BRIDGE_VLANDB_ENTRY_INFO] * ... * } + * [BRIDGE_VLANDB_GLOBAL_OPTIONS] = { + * [BRIDGE_VLANDB_GOPTS_ID] + * ... + * } */ enum { BRIDGE_VLANDB_UNSPEC, BRIDGE_VLANDB_ENTRY, + BRIDGE_VLANDB_GLOBAL_OPTIONS, __BRIDGE_VLANDB_MAX, }; #define BRIDGE_VLANDB_MAX (__BRIDGE_VLANDB_MAX - 1) @@ -538,6 +544,30 @@ enum { }; #define BRIDGE_VLANDB_STATS_MAX (__BRIDGE_VLANDB_STATS_MAX - 1) +enum { + BRIDGE_VLANDB_GOPTS_UNSPEC, + BRIDGE_VLANDB_GOPTS_ID, + BRIDGE_VLANDB_GOPTS_RANGE, + BRIDGE_VLANDB_GOPTS_MCAST_SNOOPING, + BRIDGE_VLANDB_GOPTS_MCAST_IGMP_VERSION, + BRIDGE_VLANDB_GOPTS_MCAST_MLD_VERSION, + BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_CNT, + BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_CNT, + BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_INTVL, + BRIDGE_VLANDB_GOPTS_PAD, + BRIDGE_VLANDB_GOPTS_MCAST_MEMBERSHIP_INTVL, + BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_INTVL, + BRIDGE_VLANDB_GOPTS_MCAST_QUERY_INTVL, + BRIDGE_VLANDB_GOPTS_MCAST_QUERY_RESPONSE_INTVL, + BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_INTVL, + BRIDGE_VLANDB_GOPTS_MCAST_QUERIER, + BRIDGE_VLANDB_GOPTS_MCAST_ROUTER, + BRIDGE_VLANDB_GOPTS_MCAST_ROUTER_PORTS, + BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_STATE, + __BRIDGE_VLANDB_GOPTS_MAX +}; +#define BRIDGE_VLANDB_GOPTS_MAX (__BRIDGE_VLANDB_GOPTS_MAX - 1) + /* Bridge multicast database attributes * [MDBA_MDB] = { * [MDBA_MDB_ENTRY] = { @@ -629,6 +659,7 @@ enum { MDBA_ROUTER_PATTR_TYPE, MDBA_ROUTER_PATTR_INET_TIMER, MDBA_ROUTER_PATTR_INET6_TIMER, + MDBA_ROUTER_PATTR_VID, __MDBA_ROUTER_PATTR_MAX }; #define MDBA_ROUTER_PATTR_MAX (__MDBA_ROUTER_PATTR_MAX - 1) @@ -720,12 +751,14 @@ struct br_mcast_stats { /* bridge boolean options * BR_BOOLOPT_NO_LL_LEARN - disable learning from link-local packets + * BR_BOOLOPT_MCAST_VLAN_SNOOPING - control vlan multicast snooping * * IMPORTANT: if adding a new option do not forget to handle * it in br_boolopt_toggle/get and bridge sysfs */ enum br_boolopt_id { BR_BOOLOPT_NO_LL_LEARN, + BR_BOOLOPT_MCAST_VLAN_SNOOPING, BR_BOOLOPT_MAX }; @@ -738,4 +771,17 @@ struct br_boolopt_multi { __u32 optval; __u32 optmask; }; + +enum { + BRIDGE_QUERIER_UNSPEC, + BRIDGE_QUERIER_IP_ADDRESS, + BRIDGE_QUERIER_IP_PORT, + BRIDGE_QUERIER_IP_OTHER_TIMER, + BRIDGE_QUERIER_PAD, + BRIDGE_QUERIER_IPV6_ADDRESS, + BRIDGE_QUERIER_IPV6_PORT, + BRIDGE_QUERIER_IPV6_OTHER_TIMER, + __BRIDGE_QUERIER_MAX +}; +#define BRIDGE_QUERIER_MAX (__BRIDGE_QUERIER_MAX - 1) #endif /* _UAPI_LINUX_IF_BRIDGE_H */ diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index a0b637911d3c..5f589c7a8382 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -151,6 +151,9 @@ #define ETH_P_MAP 0x00F9 /* Qualcomm multiplexing and * aggregation protocol */ +#define ETH_P_MCTP 0x00FA /* Management component transport + * protocol packets + */ /* * This is an Ethernet frame header. diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 4882e81514b6..8aad65b69054 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -479,6 +479,7 @@ enum { IFLA_BR_MCAST_MLD_VERSION, IFLA_BR_VLAN_STATS_PER_PORT, IFLA_BR_MULTI_BOOLOPT, + IFLA_BR_MCAST_QUERIER_STATE, __IFLA_BR_MAX, }; @@ -855,6 +856,7 @@ enum { IFLA_BOND_AD_ACTOR_SYSTEM, IFLA_BOND_TLB_DYNAMIC_LB, IFLA_BOND_PEER_NOTIF_DELAY, + IFLA_BOND_AD_LACP_ACTIVE, __IFLA_BOND_MAX, }; @@ -1260,4 +1262,14 @@ struct ifla_rmnet_flags { __u32 mask; }; +/* MCTP section */ + +enum { + IFLA_MCTP_UNSPEC, + IFLA_MCTP_NET, + __IFLA_MCTP_MAX, +}; + +#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1) + #endif /* _UAPI_LINUX_IF_LINK_H */ diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index d1b327036ae4..14168225cecd 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -188,11 +188,22 @@ struct ip_mreq_source { }; struct ip_msfilter { - __be32 imsf_multiaddr; - __be32 imsf_interface; - __u32 imsf_fmode; - __u32 imsf_numsrc; - __be32 imsf_slist[1]; + union { + struct { + __be32 imsf_multiaddr_aux; + __be32 imsf_interface_aux; + __u32 imsf_fmode_aux; + __u32 imsf_numsrc_aux; + __be32 imsf_slist[1]; + }; + struct { + __be32 imsf_multiaddr; + __be32 imsf_interface; + __u32 imsf_fmode; + __u32 imsf_numsrc; + __be32 imsf_slist_flex[]; + }; + }; }; #define IP_MSFILTER_SIZE(numsrc) \ @@ -211,11 +222,22 @@ struct group_source_req { }; struct group_filter { - __u32 gf_interface; /* interface index */ - struct __kernel_sockaddr_storage gf_group; /* multicast address */ - __u32 gf_fmode; /* filter mode */ - __u32 gf_numsrc; /* number of sources */ - struct __kernel_sockaddr_storage gf_slist[1]; /* interface index */ + union { + struct { + __u32 gf_interface_aux; /* interface index */ + struct __kernel_sockaddr_storage gf_group_aux; /* multicast address */ + __u32 gf_fmode_aux; /* filter mode */ + __u32 gf_numsrc_aux; /* number of sources */ + struct __kernel_sockaddr_storage gf_slist[1]; /* interface index */ + }; + struct { + __u32 gf_interface; /* interface index */ + struct __kernel_sockaddr_storage gf_group; /* multicast address */ + __u32 gf_fmode; /* filter mode */ + __u32 gf_numsrc; /* number of sources */ + struct __kernel_sockaddr_storage gf_slist_flex[]; /* interface index */ + }; + }; }; #define GROUP_FILTER_SIZE(numsrc) \ diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index 5ad396a57eb3..c4c53a9ab959 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -145,6 +145,7 @@ struct in6_flowlabel_req { #define IPV6_TLV_PADN 1 #define IPV6_TLV_ROUTERALERT 5 #define IPV6_TLV_CALIPSO 7 /* RFC 5570 */ +#define IPV6_TLV_IOAM 49 /* TEMPORARY IANA allocation for IOAM */ #define IPV6_TLV_JUMBO 194 #define IPV6_TLV_HAO 201 /* home address option */ diff --git a/include/uapi/linux/ioam6.h b/include/uapi/linux/ioam6.h new file mode 100644 index 000000000000..ac4de376f0ce --- /dev/null +++ b/include/uapi/linux/ioam6.h @@ -0,0 +1,133 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * IPv6 IOAM implementation + * + * Author: + * Justin Iurman <justin.iurman@uliege.be> + */ + +#ifndef _UAPI_LINUX_IOAM6_H +#define _UAPI_LINUX_IOAM6_H + +#include <asm/byteorder.h> +#include <linux/types.h> + +#define IOAM6_U16_UNAVAILABLE U16_MAX +#define IOAM6_U32_UNAVAILABLE U32_MAX +#define IOAM6_U64_UNAVAILABLE U64_MAX + +#define IOAM6_DEFAULT_ID (IOAM6_U32_UNAVAILABLE >> 8) +#define IOAM6_DEFAULT_ID_WIDE (IOAM6_U64_UNAVAILABLE >> 8) +#define IOAM6_DEFAULT_IF_ID IOAM6_U16_UNAVAILABLE +#define IOAM6_DEFAULT_IF_ID_WIDE IOAM6_U32_UNAVAILABLE + +/* + * IPv6 IOAM Option Header + */ +struct ioam6_hdr { + __u8 opt_type; + __u8 opt_len; + __u8 :8; /* reserved */ +#define IOAM6_TYPE_PREALLOC 0 + __u8 type; +} __attribute__((packed)); + +/* + * IOAM Trace Header + */ +struct ioam6_trace_hdr { + __be16 namespace_id; + +#if defined(__LITTLE_ENDIAN_BITFIELD) + + __u8 :1, /* unused */ + :1, /* unused */ + overflow:1, + nodelen:5; + + __u8 remlen:7, + :1; /* unused */ + + union { + __be32 type_be32; + + struct { + __u32 bit7:1, + bit6:1, + bit5:1, + bit4:1, + bit3:1, + bit2:1, + bit1:1, + bit0:1, + bit15:1, /* unused */ + bit14:1, /* unused */ + bit13:1, /* unused */ + bit12:1, /* unused */ + bit11:1, + bit10:1, + bit9:1, + bit8:1, + bit23:1, /* reserved */ + bit22:1, + bit21:1, /* unused */ + bit20:1, /* unused */ + bit19:1, /* unused */ + bit18:1, /* unused */ + bit17:1, /* unused */ + bit16:1, /* unused */ + :8; /* reserved */ + } type; + }; + +#elif defined(__BIG_ENDIAN_BITFIELD) + + __u8 nodelen:5, + overflow:1, + :1, /* unused */ + :1; /* unused */ + + __u8 :1, /* unused */ + remlen:7; + + union { + __be32 type_be32; + + struct { + __u32 bit0:1, + bit1:1, + bit2:1, + bit3:1, + bit4:1, + bit5:1, + bit6:1, + bit7:1, + bit8:1, + bit9:1, + bit10:1, + bit11:1, + bit12:1, /* unused */ + bit13:1, /* unused */ + bit14:1, /* unused */ + bit15:1, /* unused */ + bit16:1, /* unused */ + bit17:1, /* unused */ + bit18:1, /* unused */ + bit19:1, /* unused */ + bit20:1, /* unused */ + bit21:1, /* unused */ + bit22:1, + bit23:1, /* reserved */ + :8; /* reserved */ + } type; + }; + +#else +#error "Please fix <asm/byteorder.h>" +#endif + +#define IOAM6_TRACE_DATA_SIZE_MAX 244 + __u8 data[0]; +} __attribute__((packed)); + +#endif /* _UAPI_LINUX_IOAM6_H */ diff --git a/include/uapi/linux/ioam6_genl.h b/include/uapi/linux/ioam6_genl.h new file mode 100644 index 000000000000..ca4b22833754 --- /dev/null +++ b/include/uapi/linux/ioam6_genl.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * IPv6 IOAM Generic Netlink API + * + * Author: + * Justin Iurman <justin.iurman@uliege.be> + */ + +#ifndef _UAPI_LINUX_IOAM6_GENL_H +#define _UAPI_LINUX_IOAM6_GENL_H + +#define IOAM6_GENL_NAME "IOAM6" +#define IOAM6_GENL_VERSION 0x1 + +enum { + IOAM6_ATTR_UNSPEC, + + IOAM6_ATTR_NS_ID, /* u16 */ + IOAM6_ATTR_NS_DATA, /* u32 */ + IOAM6_ATTR_NS_DATA_WIDE,/* u64 */ + +#define IOAM6_MAX_SCHEMA_DATA_LEN (255 * 4) + IOAM6_ATTR_SC_ID, /* u32 */ + IOAM6_ATTR_SC_DATA, /* Binary */ + IOAM6_ATTR_SC_NONE, /* Flag */ + + IOAM6_ATTR_PAD, + + __IOAM6_ATTR_MAX, +}; + +#define IOAM6_ATTR_MAX (__IOAM6_ATTR_MAX - 1) + +enum { + IOAM6_CMD_UNSPEC, + + IOAM6_CMD_ADD_NAMESPACE, + IOAM6_CMD_DEL_NAMESPACE, + IOAM6_CMD_DUMP_NAMESPACES, + + IOAM6_CMD_ADD_SCHEMA, + IOAM6_CMD_DEL_SCHEMA, + IOAM6_CMD_DUMP_SCHEMAS, + + IOAM6_CMD_NS_SET_SCHEMA, + + __IOAM6_CMD_MAX, +}; + +#define IOAM6_CMD_MAX (__IOAM6_CMD_MAX - 1) + +#endif /* _UAPI_LINUX_IOAM6_GENL_H */ diff --git a/include/uapi/linux/ioam6_iptunnel.h b/include/uapi/linux/ioam6_iptunnel.h new file mode 100644 index 000000000000..bae14636a8c8 --- /dev/null +++ b/include/uapi/linux/ioam6_iptunnel.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * IPv6 IOAM Lightweight Tunnel API + * + * Author: + * Justin Iurman <justin.iurman@uliege.be> + */ + +#ifndef _UAPI_LINUX_IOAM6_IPTUNNEL_H +#define _UAPI_LINUX_IOAM6_IPTUNNEL_H + +enum { + IOAM6_IPTUNNEL_UNSPEC, + IOAM6_IPTUNNEL_TRACE, /* struct ioam6_trace_hdr */ + __IOAM6_IPTUNNEL_MAX, +}; + +#define IOAM6_IPTUNNEL_MAX (__IOAM6_IPTUNNEL_MAX - 1) + +#endif /* _UAPI_LINUX_IOAM6_IPTUNNEL_H */ diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 70603775fe91..b243a53fa985 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -190,6 +190,9 @@ enum { DEVCONF_NDISC_TCLASS, DEVCONF_RPL_SEG_ENABLED, DEVCONF_RA_DEFRTR_METRIC, + DEVCONF_IOAM6_ENABLED, + DEVCONF_IOAM6_ID, + DEVCONF_IOAM6_ID_WIDE, DEVCONF_MAX }; diff --git a/include/uapi/linux/ipx.h b/include/uapi/linux/ipx.h deleted file mode 100644 index 3168137adae8..000000000000 --- a/include/uapi/linux/ipx.h +++ /dev/null @@ -1,87 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _IPX_H_ -#define _IPX_H_ -#include <linux/libc-compat.h> /* for compatibility with glibc netipx/ipx.h */ -#include <linux/types.h> -#include <linux/sockios.h> -#include <linux/socket.h> -#define IPX_NODE_LEN 6 -#define IPX_MTU 576 - -#if __UAPI_DEF_SOCKADDR_IPX -struct sockaddr_ipx { - __kernel_sa_family_t sipx_family; - __be16 sipx_port; - __be32 sipx_network; - unsigned char sipx_node[IPX_NODE_LEN]; - __u8 sipx_type; - unsigned char sipx_zero; /* 16 byte fill */ -}; -#endif /* __UAPI_DEF_SOCKADDR_IPX */ - -/* - * So we can fit the extra info for SIOCSIFADDR into the address nicely - */ -#define sipx_special sipx_port -#define sipx_action sipx_zero -#define IPX_DLTITF 0 -#define IPX_CRTITF 1 - -#if __UAPI_DEF_IPX_ROUTE_DEFINITION -struct ipx_route_definition { - __be32 ipx_network; - __be32 ipx_router_network; - unsigned char ipx_router_node[IPX_NODE_LEN]; -}; -#endif /* __UAPI_DEF_IPX_ROUTE_DEFINITION */ - -#if __UAPI_DEF_IPX_INTERFACE_DEFINITION -struct ipx_interface_definition { - __be32 ipx_network; - unsigned char ipx_device[16]; - unsigned char ipx_dlink_type; -#define IPX_FRAME_NONE 0 -#define IPX_FRAME_SNAP 1 -#define IPX_FRAME_8022 2 -#define IPX_FRAME_ETHERII 3 -#define IPX_FRAME_8023 4 -#define IPX_FRAME_TR_8022 5 /* obsolete */ - unsigned char ipx_special; -#define IPX_SPECIAL_NONE 0 -#define IPX_PRIMARY 1 -#define IPX_INTERNAL 2 - unsigned char ipx_node[IPX_NODE_LEN]; -}; -#endif /* __UAPI_DEF_IPX_INTERFACE_DEFINITION */ - -#if __UAPI_DEF_IPX_CONFIG_DATA -struct ipx_config_data { - unsigned char ipxcfg_auto_select_primary; - unsigned char ipxcfg_auto_create_interfaces; -}; -#endif /* __UAPI_DEF_IPX_CONFIG_DATA */ - -/* - * OLD Route Definition for backward compatibility. - */ - -#if __UAPI_DEF_IPX_ROUTE_DEF -struct ipx_route_def { - __be32 ipx_network; - __be32 ipx_router_network; -#define IPX_ROUTE_NO_ROUTER 0 - unsigned char ipx_router_node[IPX_NODE_LEN]; - unsigned char ipx_device[16]; - unsigned short ipx_flags; -#define IPX_RT_SNAP 8 -#define IPX_RT_8022 4 -#define IPX_RT_BLUEBOOK 2 -#define IPX_RT_ROUTED 1 -}; -#endif /* __UAPI_DEF_IPX_ROUTE_DEF */ - -#define SIOCAIPXITFCRT (SIOCPROTOPRIVATE) -#define SIOCAIPXPRISLT (SIOCPROTOPRIVATE + 1) -#define SIOCIPXCFGDATA (SIOCPROTOPRIVATE + 2) -#define SIOCIPXNCPCONN (SIOCPROTOPRIVATE + 3) -#endif /* _IPX_H_ */ diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h index 568a4303ccce..2e206919125c 100644 --- a/include/uapi/linux/lwtunnel.h +++ b/include/uapi/linux/lwtunnel.h @@ -14,6 +14,7 @@ enum lwtunnel_encap_types { LWTUNNEL_ENCAP_BPF, LWTUNNEL_ENCAP_SEG6_LOCAL, LWTUNNEL_ENCAP_RPL, + LWTUNNEL_ENCAP_IOAM6, __LWTUNNEL_ENCAP_MAX, }; diff --git a/include/uapi/linux/mctp.h b/include/uapi/linux/mctp.h new file mode 100644 index 000000000000..52b54d13f385 --- /dev/null +++ b/include/uapi/linux/mctp.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Management Component Transport Protocol (MCTP) + * + * Copyright (c) 2021 Code Construct + * Copyright (c) 2021 Google + */ + +#ifndef __UAPI_MCTP_H +#define __UAPI_MCTP_H + +#include <linux/types.h> + +typedef __u8 mctp_eid_t; + +struct mctp_addr { + mctp_eid_t s_addr; +}; + +struct sockaddr_mctp { + unsigned short int smctp_family; + int smctp_network; + struct mctp_addr smctp_addr; + __u8 smctp_type; + __u8 smctp_tag; +}; + +#define MCTP_NET_ANY 0x0 + +#define MCTP_ADDR_NULL 0x00 +#define MCTP_ADDR_ANY 0xff + +#define MCTP_TAG_MASK 0x07 +#define MCTP_TAG_OWNER 0x08 + +#endif /* __UAPI_MCTP_H */ diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 7b05f7102321..f66038b9551f 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -73,6 +73,7 @@ enum { #define MPTCP_PM_ADDR_FLAG_SIGNAL (1 << 0) #define MPTCP_PM_ADDR_FLAG_SUBFLOW (1 << 1) #define MPTCP_PM_ADDR_FLAG_BACKUP (1 << 2) +#define MPTCP_PM_ADDR_FLAG_FULLMESH (1 << 3) enum { MPTCP_PM_CMD_UNSPEC, diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h index d8484be72fdc..c6e6d7d7d538 100644 --- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h +++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h @@ -56,6 +56,7 @@ enum ctattr_type { CTA_LABELS_MASK, CTA_SYNPROXY, CTA_FILTER, + CTA_STATUS_MASK, __CTA_MAX }; #define CTA_MAX (__CTA_MAX - 1) diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 8d16744edc31..150bcff49b1c 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -70,6 +70,8 @@ enum ovs_datapath_cmd { * set on the datapath port (for OVS_ACTION_ATTR_MISS). Only valid on * %OVS_DP_CMD_NEW requests. A value of zero indicates that upcalls should * not be sent. + * @OVS_DP_ATTR_PER_CPU_PIDS: Per-cpu array of PIDs for upcalls when + * OVS_DP_F_DISPATCH_UPCALL_PER_CPU feature is set. * @OVS_DP_ATTR_STATS: Statistics about packets that have passed through the * datapath. Always present in notifications. * @OVS_DP_ATTR_MEGAFLOW_STATS: Statistics about mega flow masks usage for the @@ -87,6 +89,9 @@ enum ovs_datapath_attr { OVS_DP_ATTR_USER_FEATURES, /* OVS_DP_F_* */ OVS_DP_ATTR_PAD, OVS_DP_ATTR_MASKS_CACHE_SIZE, + OVS_DP_ATTR_PER_CPU_PIDS, /* Netlink PIDS to receive upcalls in + * per-cpu dispatch mode + */ __OVS_DP_ATTR_MAX }; @@ -127,6 +132,9 @@ struct ovs_vport_stats { /* Allow tc offload recirc sharing */ #define OVS_DP_F_TC_RECIRC_SHARING (1 << 2) +/* Allow per-cpu dispatch of upcalls */ +#define OVS_DP_F_DISPATCH_UPCALL_PER_CPU (1 << 3) + /* Fixed logical ports. */ #define OVSP_LOCAL ((__u32)0) diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 025c40fef93d..6836ccb9c45d 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -22,6 +22,7 @@ enum { __TCA_ACT_MAX }; +/* See other TCA_ACT_FLAGS_ * flags in include/net/act_api.h. */ #define TCA_ACT_FLAGS_NO_PERCPU_STATS 1 /* Don't use percpu allocator for * actions stats. */ diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h index c3409c8ec0dd..eb0a9a5b6e71 100644 --- a/include/uapi/linux/socket.h +++ b/include/uapi/linux/socket.h @@ -26,4 +26,9 @@ struct __kernel_sockaddr_storage { }; }; +#define SOCK_SNDBUF_LOCK 1 +#define SOCK_RCVBUF_LOCK 2 + +#define SOCK_BUF_LOCK_MASK (SOCK_SNDBUF_LOCK | SOCK_RCVBUF_LOCK) + #endif /* _UAPI_LINUX_SOCKET_H */ diff --git a/include/uapi/linux/tc_act/tc_skbmod.h b/include/uapi/linux/tc_act/tc_skbmod.h index c525b3503797..af6ef2cfbf3d 100644 --- a/include/uapi/linux/tc_act/tc_skbmod.h +++ b/include/uapi/linux/tc_act/tc_skbmod.h @@ -17,6 +17,7 @@ #define SKBMOD_F_SMAC 0x2 #define SKBMOD_F_ETYPE 0x4 #define SKBMOD_F_SWAPMAC 0x8 +#define SKBMOD_F_ECN 0x10 struct tc_skbmod { tc_gen; |