diff options
Diffstat (limited to 'include/linux')
53 files changed, 985 insertions, 492 deletions
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..2746fd804216 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -23,22 +23,73 @@ struct ctl_table_header; struct task_struct; #ifdef CONFIG_CGROUP_BPF +enum cgroup_bpf_attach_type { + CGROUP_BPF_ATTACH_TYPE_INVALID = -1, + CGROUP_INET_INGRESS = 0, + CGROUP_INET_EGRESS, + CGROUP_INET_SOCK_CREATE, + CGROUP_SOCK_OPS, + CGROUP_DEVICE, + CGROUP_INET4_BIND, + CGROUP_INET6_BIND, + CGROUP_INET4_CONNECT, + CGROUP_INET6_CONNECT, + CGROUP_INET4_POST_BIND, + CGROUP_INET6_POST_BIND, + CGROUP_UDP4_SENDMSG, + CGROUP_UDP6_SENDMSG, + CGROUP_SYSCTL, + CGROUP_UDP4_RECVMSG, + CGROUP_UDP6_RECVMSG, + CGROUP_GETSOCKOPT, + CGROUP_SETSOCKOPT, + CGROUP_INET4_GETPEERNAME, + CGROUP_INET6_GETPEERNAME, + CGROUP_INET4_GETSOCKNAME, + CGROUP_INET6_GETSOCKNAME, + CGROUP_INET_SOCK_RELEASE, + MAX_CGROUP_BPF_ATTACH_TYPE +}; -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 CGROUP_ATYPE(type) \ + case BPF_##type: return type -#define BPF_CGROUP_STORAGE_NEST_MAX 8 +static inline enum cgroup_bpf_attach_type +to_cgroup_bpf_attach_type(enum bpf_attach_type attach_type) +{ + switch (attach_type) { + CGROUP_ATYPE(CGROUP_INET_INGRESS); + CGROUP_ATYPE(CGROUP_INET_EGRESS); + CGROUP_ATYPE(CGROUP_INET_SOCK_CREATE); + CGROUP_ATYPE(CGROUP_SOCK_OPS); + CGROUP_ATYPE(CGROUP_DEVICE); + CGROUP_ATYPE(CGROUP_INET4_BIND); + CGROUP_ATYPE(CGROUP_INET6_BIND); + CGROUP_ATYPE(CGROUP_INET4_CONNECT); + CGROUP_ATYPE(CGROUP_INET6_CONNECT); + CGROUP_ATYPE(CGROUP_INET4_POST_BIND); + CGROUP_ATYPE(CGROUP_INET6_POST_BIND); + CGROUP_ATYPE(CGROUP_UDP4_SENDMSG); + CGROUP_ATYPE(CGROUP_UDP6_SENDMSG); + CGROUP_ATYPE(CGROUP_SYSCTL); + CGROUP_ATYPE(CGROUP_UDP4_RECVMSG); + CGROUP_ATYPE(CGROUP_UDP6_RECVMSG); + CGROUP_ATYPE(CGROUP_GETSOCKOPT); + CGROUP_ATYPE(CGROUP_SETSOCKOPT); + CGROUP_ATYPE(CGROUP_INET4_GETPEERNAME); + CGROUP_ATYPE(CGROUP_INET6_GETPEERNAME); + CGROUP_ATYPE(CGROUP_INET4_GETSOCKNAME); + CGROUP_ATYPE(CGROUP_INET6_GETSOCKNAME); + CGROUP_ATYPE(CGROUP_INET_SOCK_RELEASE); + default: + return CGROUP_BPF_ATTACH_TYPE_INVALID; + } +} -struct bpf_cgroup_storage_info { - struct task_struct *task; - struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; -}; +#undef CGROUP_ATYPE -/* 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]); +extern struct static_key_false cgroup_bpf_enabled_key[MAX_CGROUP_BPF_ATTACH_TYPE]; +#define cgroup_bpf_enabled(atype) static_branch_unlikely(&cgroup_bpf_enabled_key[atype]) #define for_each_cgroup_storage_type(stype) \ for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) @@ -80,15 +131,15 @@ struct bpf_prog_array; struct cgroup_bpf { /* array of effective progs in this cgroup */ - struct bpf_prog_array __rcu *effective[MAX_BPF_ATTACH_TYPE]; + struct bpf_prog_array __rcu *effective[MAX_CGROUP_BPF_ATTACH_TYPE]; /* attached progs to this cgroup and attach flags * when flags == 0 or BPF_F_ALLOW_OVERRIDE the progs list will * have either zero or one element * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS */ - struct list_head progs[MAX_BPF_ATTACH_TYPE]; - u32 flags[MAX_BPF_ATTACH_TYPE]; + struct list_head progs[MAX_CGROUP_BPF_ATTACH_TYPE]; + u32 flags[MAX_CGROUP_BPF_ATTACH_TYPE]; /* list of cgroup shared storages */ struct list_head storages; @@ -128,28 +179,28 @@ int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, - enum bpf_attach_type type); + enum cgroup_bpf_attach_type atype); int __cgroup_bpf_run_filter_sk(struct sock *sk, - enum bpf_attach_type type); + enum cgroup_bpf_attach_type atype); int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, - enum bpf_attach_type type, + enum cgroup_bpf_attach_type atype, void *t_ctx, u32 *flags); int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct bpf_sock_ops_kern *sock_ops, - enum bpf_attach_type type); + enum cgroup_bpf_attach_type atype); int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, - short access, enum bpf_attach_type type); + short access, enum cgroup_bpf_attach_type atype); int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, struct ctl_table *table, int write, char **buf, size_t *pcount, loff_t *ppos, - enum bpf_attach_type type); + enum cgroup_bpf_attach_type atype); int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level, int *optname, char __user *optval, @@ -172,44 +223,6 @@ 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); @@ -230,9 +243,9 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(BPF_CGROUP_INET_INGRESS)) \ + if (cgroup_bpf_enabled(CGROUP_INET_INGRESS)) \ __ret = __cgroup_bpf_run_filter_skb(sk, skb, \ - BPF_CGROUP_INET_INGRESS); \ + CGROUP_INET_INGRESS); \ \ __ret; \ }) @@ -240,54 +253,54 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(BPF_CGROUP_INET_EGRESS) && sk && sk == skb->sk) { \ + if (cgroup_bpf_enabled(CGROUP_INET_EGRESS) && sk && sk == skb->sk) { \ typeof(sk) __sk = sk_to_full_sk(sk); \ if (sk_fullsock(__sk)) \ __ret = __cgroup_bpf_run_filter_skb(__sk, skb, \ - BPF_CGROUP_INET_EGRESS); \ + CGROUP_INET_EGRESS); \ } \ __ret; \ }) -#define BPF_CGROUP_RUN_SK_PROG(sk, type) \ +#define BPF_CGROUP_RUN_SK_PROG(sk, atype) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(type)) { \ - __ret = __cgroup_bpf_run_filter_sk(sk, type); \ + if (cgroup_bpf_enabled(atype)) { \ + __ret = __cgroup_bpf_run_filter_sk(sk, atype); \ } \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) \ - BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET_SOCK_CREATE) + BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET_SOCK_CREATE) #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) \ - BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET_SOCK_RELEASE) + BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET_SOCK_RELEASE) #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) \ - BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET4_POST_BIND) + BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET4_POST_BIND) #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) \ - BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET6_POST_BIND) + BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET6_POST_BIND) -#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, type) \ +#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype) \ ({ \ u32 __unused_flags; \ int __ret = 0; \ - if (cgroup_bpf_enabled(type)) \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ + if (cgroup_bpf_enabled(atype)) \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ NULL, \ &__unused_flags); \ __ret; \ }) -#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) \ +#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) \ ({ \ u32 __unused_flags; \ int __ret = 0; \ - if (cgroup_bpf_enabled(type)) { \ + if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ t_ctx, \ &__unused_flags); \ release_sock(sk); \ @@ -300,13 +313,13 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, * (at bit position 0) is to indicate CAP_NET_BIND_SERVICE capability check * should be bypassed (BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE). */ -#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, type, bind_flags) \ +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, atype, bind_flags) \ ({ \ u32 __flags = 0; \ int __ret = 0; \ - if (cgroup_bpf_enabled(type)) { \ + if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ NULL, &__flags); \ release_sock(sk); \ if (__flags & BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE) \ @@ -316,33 +329,33 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, }) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) \ - ((cgroup_bpf_enabled(BPF_CGROUP_INET4_CONNECT) || \ - cgroup_bpf_enabled(BPF_CGROUP_INET6_CONNECT)) && \ + ((cgroup_bpf_enabled(CGROUP_INET4_CONNECT) || \ + cgroup_bpf_enabled(CGROUP_INET6_CONNECT)) && \ (sk)->sk_prot->pre_connect) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET4_CONNECT) + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, CGROUP_INET4_CONNECT) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET6_CONNECT) + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, CGROUP_INET6_CONNECT) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_CONNECT, NULL) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_INET4_CONNECT, NULL) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_CONNECT, NULL) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_INET6_CONNECT, NULL) #define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP4_SENDMSG, t_ctx) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP4_SENDMSG, t_ctx) #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP6_SENDMSG, t_ctx) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP6_SENDMSG, t_ctx) #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP4_RECVMSG, NULL) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP4_RECVMSG, NULL) #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP6_RECVMSG, NULL) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP6_RECVMSG, NULL) /* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a * fullsock and its parent fullsock cannot be traced by @@ -362,33 +375,33 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(sock_ops, sk) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(BPF_CGROUP_SOCK_OPS)) \ + if (cgroup_bpf_enabled(CGROUP_SOCK_OPS)) \ __ret = __cgroup_bpf_run_filter_sock_ops(sk, \ sock_ops, \ - BPF_CGROUP_SOCK_OPS); \ + CGROUP_SOCK_OPS); \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(BPF_CGROUP_SOCK_OPS) && (sock_ops)->sk) { \ + if (cgroup_bpf_enabled(CGROUP_SOCK_OPS) && (sock_ops)->sk) { \ typeof(sk) __sk = sk_to_full_sk((sock_ops)->sk); \ if (__sk && sk_fullsock(__sk)) \ __ret = __cgroup_bpf_run_filter_sock_ops(__sk, \ sock_ops, \ - BPF_CGROUP_SOCK_OPS); \ + CGROUP_SOCK_OPS); \ } \ __ret; \ }) -#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access) \ +#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(BPF_CGROUP_DEVICE)) \ - __ret = __cgroup_bpf_check_dev_permission(type, major, minor, \ + if (cgroup_bpf_enabled(CGROUP_DEVICE)) \ + __ret = __cgroup_bpf_check_dev_permission(atype, major, minor, \ access, \ - BPF_CGROUP_DEVICE); \ + CGROUP_DEVICE); \ \ __ret; \ }) @@ -397,10 +410,10 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, pos) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(BPF_CGROUP_SYSCTL)) \ + if (cgroup_bpf_enabled(CGROUP_SYSCTL)) \ __ret = __cgroup_bpf_run_filter_sysctl(head, table, write, \ buf, count, pos, \ - BPF_CGROUP_SYSCTL); \ + CGROUP_SYSCTL); \ __ret; \ }) @@ -408,7 +421,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, kernel_optval) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(BPF_CGROUP_SETSOCKOPT)) \ + if (cgroup_bpf_enabled(CGROUP_SETSOCKOPT)) \ __ret = __cgroup_bpf_run_filter_setsockopt(sock, level, \ optname, optval, \ optlen, \ @@ -419,7 +432,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(BPF_CGROUP_GETSOCKOPT)) \ + if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \ get_user(__ret, optlen); \ __ret; \ }) @@ -428,7 +441,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, max_optlen, retval) \ ({ \ int __ret = retval; \ - if (cgroup_bpf_enabled(BPF_CGROUP_GETSOCKOPT)) \ + if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \ if (!(sock)->sk_prot->bpf_bypass_getsockopt || \ !INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \ tcp_bpf_bypass_getsockopt, \ @@ -443,7 +456,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, optlen, retval) \ ({ \ int __ret = retval; \ - if (cgroup_bpf_enabled(BPF_CGROUP_GETSOCKOPT)) \ + if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \ __ret = __cgroup_bpf_run_filter_getsockopt_kern( \ sock, level, optname, optval, optlen, retval); \ __ret; \ @@ -487,9 +500,6 @@ 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( @@ -505,14 +515,14 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, return 0; } -#define cgroup_bpf_enabled(type) (0) -#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) ({ 0; }) +#define cgroup_bpf_enabled(atype) (0) +#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) ({ 0; }) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, type, flags) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, atype, flags) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) ({ 0; }) @@ -524,7 +534,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; }) #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e8e2b0393ca9..f4c16f19f83e 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 */ @@ -1073,7 +1103,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, /* an array of programs to be executed under rcu_lock. * * Typical usage: - * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, BPF_PROG_RUN); + * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, bpf_prog_run); * * the structure returned by bpf_prog_array_alloc() should be populated * with program pointers and the last pointer must be NULL. @@ -1084,7 +1114,10 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, */ struct bpf_prog_array_item { struct bpf_prog *prog; - struct bpf_cgroup_storage *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; + union { + struct bpf_cgroup_storage *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; + u64 bpf_cookie; + }; }; struct bpf_prog_array { @@ -1110,73 +1143,133 @@ int bpf_prog_array_copy_info(struct bpf_prog_array *array, int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, + u64 bpf_cookie, struct bpf_prog_array **new_array); +struct bpf_run_ctx {}; + +struct bpf_cg_run_ctx { + struct bpf_run_ctx run_ctx; + const struct bpf_prog_array_item *prog_item; +}; + +struct bpf_trace_run_ctx { + struct bpf_run_ctx run_ctx; + u64 bpf_cookie; +}; + +static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx) +{ + struct bpf_run_ctx *old_ctx = NULL; + +#ifdef CONFIG_BPF_SYSCALL + old_ctx = current->bpf_ctx; + current->bpf_ctx = new_ctx; +#endif + return old_ctx; +} + +static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) +{ +#ifdef CONFIG_BPF_SYSCALL + current->bpf_ctx = old_ctx; +#endif +} + /* 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; \ - u32 _ret = 1; \ - u32 func_ret; \ - migrate_disable(); \ - rcu_read_lock(); \ - _array = rcu_dereference(array); \ - _item = &_array->items[0]; \ - while ((_prog = READ_ONCE(_item->prog))) { \ - if (unlikely(bpf_cgroup_storage_set(_item->cgroup_storage))) \ - break; \ - func_ret = func(_prog, ctx); \ - _ret &= (func_ret & 1); \ - *(ret_flags) |= (func_ret >> 1); \ - bpf_cgroup_storage_unset(); \ - _item++; \ - } \ - rcu_read_unlock(); \ - migrate_enable(); \ - _ret; \ - }) - -#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null, set_cg_storage) \ - ({ \ - struct bpf_prog_array_item *_item; \ - struct bpf_prog *_prog; \ - struct bpf_prog_array *_array; \ - u32 _ret = 1; \ - migrate_disable(); \ - rcu_read_lock(); \ - _array = rcu_dereference(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(); \ - } \ - _item++; \ - } \ -_out: \ - rcu_read_unlock(); \ - migrate_enable(); \ - _ret; \ - }) +typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx); + +static __always_inline u32 +BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, + const void *ctx, bpf_prog_run_fn run_prog, + u32 *ret_flags) +{ + const struct bpf_prog_array_item *item; + const struct bpf_prog *prog; + const 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_rcu); + item = &array->items[0]; + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + while ((prog = READ_ONCE(item->prog))) { + run_ctx.prog_item = item; + func_ret = run_prog(prog, ctx); + ret &= (func_ret & 1); + *(ret_flags) |= (func_ret >> 1); + item++; + } + bpf_reset_run_ctx(old_run_ctx); + rcu_read_unlock(); + migrate_enable(); + return ret; +} + +static __always_inline u32 +BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, + const void *ctx, bpf_prog_run_fn run_prog) +{ + const struct bpf_prog_array_item *item; + const struct bpf_prog *prog; + const 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(); + array = rcu_dereference(array_rcu); + item = &array->items[0]; + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + while ((prog = READ_ONCE(item->prog))) { + run_ctx.prog_item = item; + ret &= run_prog(prog, ctx); + item++; + } + bpf_reset_run_ctx(old_run_ctx); + rcu_read_unlock(); + migrate_enable(); + return ret; +} + +static __always_inline u32 +BPF_PROG_RUN_ARRAY(const struct bpf_prog_array __rcu *array_rcu, + const void *ctx, bpf_prog_run_fn run_prog) +{ + const struct bpf_prog_array_item *item; + const struct bpf_prog *prog; + const struct bpf_prog_array *array; + struct bpf_run_ctx *old_run_ctx; + struct bpf_trace_run_ctx run_ctx; + u32 ret = 1; + + migrate_disable(); + rcu_read_lock(); + array = rcu_dereference(array_rcu); + if (unlikely(!array)) + goto out; + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + item = &array->items[0]; + while ((prog = READ_ONCE(item->prog))) { + run_ctx.bpf_cookie = item->bpf_cookie; + ret &= run_prog(prog, ctx); + item++; + } + bpf_reset_run_ctx(old_run_ctx); +out: + rcu_read_unlock(); + migrate_enable(); + return ret; +} /* To be used by __cgroup_bpf_run_filter_skb for EGRESS BPF progs * so BPF programs can request cwr for TCP packets. @@ -1205,7 +1298,7 @@ _out: \ u32 _flags = 0; \ bool _cn; \ u32 _ret; \ - _ret = BPF_PROG_RUN_ARRAY_FLAGS(array, ctx, func, &_flags); \ + _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, &_flags); \ _cn = _flags & BPF_RET_SET_CN; \ if (_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ @@ -1214,12 +1307,6 @@ _out: \ _ret; \ }) -#define BPF_PROG_RUN_ARRAY(array, ctx, func) \ - __BPF_PROG_RUN_ARRAY(array, ctx, func, false, true) - -#define BPF_PROG_RUN_ARRAY_CHECK(array, ctx, func) \ - __BPF_PROG_RUN_ARRAY(array, ctx, func, true, false) - #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); extern struct mutex bpf_stats_enabled_mutex; @@ -1398,6 +1485,9 @@ 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 +1500,7 @@ 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 +1523,8 @@ 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 +1602,12 @@ 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 +1804,12 @@ 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 +1951,12 @@ 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 +1989,6 @@ 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 +2008,21 @@ 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) { @@ -1998,9 +2099,8 @@ 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; - -const struct bpf_func_proto *bpf_tracing_func_proto( - enum bpf_func_id func_id, const struct bpf_prog *prog); +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 *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index ae3ac3a2018c..9c81724e4b98 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -136,3 +136,6 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter) BPF_LINK_TYPE(BPF_LINK_TYPE_NETNS, netns) BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp) #endif +#ifdef CONFIG_PERF_EVENTS +BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf) +#endif 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/bpfptr.h b/include/linux/bpfptr.h index 5cdeab497cb3..546e27fc6d46 100644 --- a/include/linux/bpfptr.h +++ b/include/linux/bpfptr.h @@ -62,9 +62,17 @@ static inline int copy_to_bpfptr_offset(bpfptr_t dst, size_t offset, return copy_to_sockptr_offset((sockptr_t) dst, offset, src, size); } -static inline void *memdup_bpfptr(bpfptr_t src, size_t len) +static inline void *kvmemdup_bpfptr(bpfptr_t src, size_t len) { - return memdup_sockptr((sockptr_t) src, len); + void *p = kvmalloc(len, GFP_USER | __GFP_NOWARN); + + if (!p) + return ERR_PTR(-ENOMEM); + if (copy_from_bpfptr(p, src, len)) { + kvfree(p); + return ERR_PTR(-EFAULT); + } + return p; } static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count) 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/btf_ids.h b/include/linux/btf_ids.h index 57890b357f85..47d9abfbdb55 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -82,6 +82,9 @@ __BTF_ID_LIST(name, globl) #define BTF_ID_LIST_SINGLE(name, prefix, typename) \ BTF_ID_LIST(name) \ BTF_ID(prefix, typename) +#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) \ + BTF_ID_LIST_GLOBAL(name) \ + BTF_ID(prefix, typename) /* * The BTF_ID_UNUSED macro defines 4 zero bytes. @@ -148,6 +151,7 @@ extern struct btf_id_set name; #define BTF_ID_UNUSED #define BTF_ID_LIST_GLOBAL(name) u32 name[1]; #define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1]; +#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 name[1]; #define BTF_SET_START(name) static struct btf_id_set name = { 0 }; #define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 }; #define BTF_SET_END(name) @@ -172,7 +176,8 @@ extern struct btf_id_set name; BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_TW, tcp_timewait_sock) \ BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock) \ BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock) \ - BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock) + BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock) enum { #define BTF_SOCK_TYPE(name, str) name, @@ -184,4 +189,6 @@ MAX_BTF_SOCK_TYPE, extern u32 btf_sock_ids[]; #endif +extern u32 btf_task_struct_ids[]; + #endif 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..171106202fe5 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -16,6 +16,8 @@ #define ETH_P_SJA1105_META 0x0008 #define ETH_P_SJA1110 0xdadc +#define SJA1105_DEFAULT_VLAN (VLAN_N_VID - 1) + /* IEEE 802.3 Annex 57A: Slow Protocols PDUs (01:80:C2:xx:xx:xx) */ #define SJA1105_LINKLOCAL_FILTER_A 0x0180C2000000ull #define SJA1105_LINKLOCAL_FILTER_A_MASK 0xFFFFFF000000ull @@ -59,14 +61,12 @@ 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; struct sja1105_tagger_data *data; struct dsa_port *dp; bool hwts_tx_en; - u16 xmit_tpid; }; enum sja1110_meta_tstamp { @@ -89,4 +89,22 @@ 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..849524b55d89 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -15,10 +15,9 @@ #include <linux/bitmap.h> #include <linux/compat.h> +#include <linux/netlink.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 +37,6 @@ struct compat_ethtool_rxnfc { u32 rule_locs[]; }; -#endif /* CONFIG_COMPAT */ - #include <linux/rculist.h> /** @@ -176,6 +173,11 @@ extern int __ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings); +struct kernel_ethtool_coalesce { + u8 use_cqe_mode_tx; + u8 use_cqe_mode_rx; +}; + /** * ethtool_intersect_link_masks - Given two link masks, AND them together * @dst: first mask and where result is stored @@ -215,7 +217,9 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, #define ETHTOOL_COALESCE_TX_USECS_HIGH BIT(19) #define ETHTOOL_COALESCE_TX_MAX_FRAMES_HIGH BIT(20) #define ETHTOOL_COALESCE_RATE_SAMPLE_INTERVAL BIT(21) -#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(21, 0) +#define ETHTOOL_COALESCE_USE_CQE_RX BIT(22) +#define ETHTOOL_COALESCE_USE_CQE_TX BIT(23) +#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(23, 0) #define ETHTOOL_COALESCE_USECS \ (ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_TX_USECS) @@ -241,6 +245,8 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, ETHTOOL_COALESCE_RX_USECS_LOW | ETHTOOL_COALESCE_RX_USECS_HIGH | \ ETHTOOL_COALESCE_PKT_RATE_LOW | ETHTOOL_COALESCE_PKT_RATE_HIGH | \ ETHTOOL_COALESCE_RATE_SAMPLE_INTERVAL) +#define ETHTOOL_COALESCE_USE_CQE \ + (ETHTOOL_COALESCE_USE_CQE_RX | ETHTOOL_COALESCE_USE_CQE_TX) #define ETHTOOL_STAT_NOT_SET (~0ULL) @@ -606,8 +612,14 @@ struct ethtool_ops { struct ethtool_eeprom *, u8 *); int (*set_eeprom)(struct net_device *, struct ethtool_eeprom *, u8 *); - int (*get_coalesce)(struct net_device *, struct ethtool_coalesce *); - int (*set_coalesce)(struct net_device *, struct ethtool_coalesce *); + int (*get_coalesce)(struct net_device *, + struct ethtool_coalesce *, + struct kernel_ethtool_coalesce *, + struct netlink_ext_ack *); + int (*set_coalesce)(struct net_device *, + struct ethtool_coalesce *, + struct kernel_ethtool_coalesce *, + struct netlink_ext_ack *); void (*get_ringparam)(struct net_device *, struct ethtool_ringparam *); int (*set_ringparam)(struct net_device *, diff --git a/include/linux/filter.h b/include/linux/filter.h index 83b896044e79..7d248941ecea 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 */ @@ -599,25 +600,38 @@ struct sk_filter { DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); -#define __BPF_PROG_RUN(prog, ctx, dfunc) ({ \ - u32 __ret; \ - cant_migrate(); \ - if (static_branch_unlikely(&bpf_stats_enabled_key)) { \ - struct bpf_prog_stats *__stats; \ - u64 __start = sched_clock(); \ - __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ - __stats = this_cpu_ptr(prog->stats); \ - u64_stats_update_begin(&__stats->syncp); \ - __stats->cnt++; \ - __stats->nsecs += sched_clock() - __start; \ - u64_stats_update_end(&__stats->syncp); \ - } else { \ - __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ - } \ - __ret; }) - -#define BPF_PROG_RUN(prog, ctx) \ - __BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func) +typedef unsigned int (*bpf_dispatcher_fn)(const void *ctx, + const struct bpf_insn *insnsi, + unsigned int (*bpf_func)(const void *, + const struct bpf_insn *)); + +static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog, + const void *ctx, + bpf_dispatcher_fn dfunc) +{ + u32 ret; + + cant_migrate(); + if (static_branch_unlikely(&bpf_stats_enabled_key)) { + struct bpf_prog_stats *stats; + u64 start = sched_clock(); + + ret = dfunc(ctx, prog->insnsi, prog->bpf_func); + stats = this_cpu_ptr(prog->stats); + u64_stats_update_begin(&stats->syncp); + stats->cnt++; + stats->nsecs += sched_clock() - start; + u64_stats_update_end(&stats->syncp); + } else { + ret = dfunc(ctx, prog->insnsi, prog->bpf_func); + } + return ret; +} + +static __always_inline u32 bpf_prog_run(const struct bpf_prog *prog, const void *ctx) +{ + return __bpf_prog_run(prog, ctx, bpf_dispatcher_nop_func); +} /* * Use in preemptible and therefore migratable context to make sure that @@ -636,7 +650,7 @@ static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog, u32 ret; migrate_disable(); - ret = __BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func); + ret = bpf_prog_run(prog, ctx); migrate_enable(); return ret; } @@ -709,7 +723,7 @@ static inline void bpf_restore_data_end( cb->data_end = saved_data_end; } -static inline u8 *bpf_skb_cb(struct sk_buff *skb) +static inline u8 *bpf_skb_cb(const struct sk_buff *skb) { /* eBPF programs may read/write skb->cb[] area to transfer meta * data between tail calls. Since this also needs to work with @@ -730,8 +744,9 @@ static inline u8 *bpf_skb_cb(struct sk_buff *skb) /* Must be invoked with migration disabled */ static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog, - struct sk_buff *skb) + const void *ctx) { + const struct sk_buff *skb = ctx; u8 *cb_data = bpf_skb_cb(skb); u8 cb_saved[BPF_SKB_CB_LEN]; u32 res; @@ -741,7 +756,7 @@ static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog, memset(cb_data, 0, sizeof(cb_saved)); } - res = BPF_PROG_RUN(prog, skb); + res = bpf_prog_run(prog, skb); if (unlikely(prog->cb_access)) memcpy(cb_data, cb_saved, sizeof(cb_saved)); @@ -775,6 +790,10 @@ 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 +801,14 @@ 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); @@ -1428,7 +1454,7 @@ static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, }; u32 act; - act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, BPF_PROG_RUN); + act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, bpf_prog_run); if (act == SK_PASS) { selected_sk = ctx.selected_sk; no_reuseport = ctx.no_reuseport; @@ -1466,7 +1492,7 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, }; u32 act; - act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, BPF_PROG_RUN); + act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, bpf_prog_run); if (act == SK_PASS) { selected_sk = ctx.selected_sk; no_reuseport = ctx.no_reuseport; 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/ieee80211.h b/include/linux/ieee80211.h index a6730072d13a..694264503119 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1088,6 +1088,48 @@ struct ieee80211_ext { } u; } __packed __aligned(2); +#define IEEE80211_TWT_CONTROL_NDP BIT(0) +#define IEEE80211_TWT_CONTROL_RESP_MODE BIT(1) +#define IEEE80211_TWT_CONTROL_NEG_TYPE_BROADCAST BIT(3) +#define IEEE80211_TWT_CONTROL_RX_DISABLED BIT(4) +#define IEEE80211_TWT_CONTROL_WAKE_DUR_UNIT BIT(5) + +#define IEEE80211_TWT_REQTYPE_REQUEST BIT(0) +#define IEEE80211_TWT_REQTYPE_SETUP_CMD GENMASK(3, 1) +#define IEEE80211_TWT_REQTYPE_TRIGGER BIT(4) +#define IEEE80211_TWT_REQTYPE_IMPLICIT BIT(5) +#define IEEE80211_TWT_REQTYPE_FLOWTYPE BIT(6) +#define IEEE80211_TWT_REQTYPE_FLOWID GENMASK(9, 7) +#define IEEE80211_TWT_REQTYPE_WAKE_INT_EXP GENMASK(14, 10) +#define IEEE80211_TWT_REQTYPE_PROTECTION BIT(15) + +enum ieee80211_twt_setup_cmd { + TWT_SETUP_CMD_REQUEST, + TWT_SETUP_CMD_SUGGEST, + TWT_SETUP_CMD_DEMAND, + TWT_SETUP_CMD_GROUPING, + TWT_SETUP_CMD_ACCEPT, + TWT_SETUP_CMD_ALTERNATE, + TWT_SETUP_CMD_DICTATE, + TWT_SETUP_CMD_REJECT, +}; + +struct ieee80211_twt_params { + __le16 req_type; + __le64 twt; + u8 min_twt_dur; + __le16 mantissa; + u8 channel; +} __packed; + +struct ieee80211_twt_setup { + u8 dialog_token; + u8 element_id; + u8 length; + u8 control; + u8 params[]; +} __packed; + struct ieee80211_mgmt { __le16 frame_control; __le16 duration; @@ -1252,6 +1294,10 @@ struct ieee80211_mgmt { __le16 toa_error; u8 variable[0]; } __packed ftm; + struct { + u8 action_code; + u8 variable[]; + } __packed s1g; } u; } __packed action; } u; @@ -2266,6 +2312,9 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) #define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x40000000 #define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x80000000 +#define IEEE80211_6GHZ_CTRL_REG_LPI_AP 0 +#define IEEE80211_6GHZ_CTRL_REG_SP_AP 1 + /** * ieee80211_he_6ghz_oper - HE 6 GHz operation Information field * @primary: primary channel @@ -2282,6 +2331,7 @@ struct ieee80211_he_6ghz_oper { #define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_80MHZ 2 #define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ 3 #define IEEE80211_HE_6GHZ_OPER_CTRL_DUP_BEACON 0x4 +#define IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO 0x38 u8 control; u8 ccfs0; u8 ccfs1; @@ -2289,6 +2339,44 @@ struct ieee80211_he_6ghz_oper { } __packed; /* + * In "9.4.2.161 Transmit Power Envelope element" of "IEEE Std 802.11ax-2021", + * it show four types in "Table 9-275a-Maximum Transmit Power Interpretation + * subfield encoding", and two category for each type in "Table E-12-Regulatory + * Info subfield encoding in the United States". + * So it it totally max 8 Transmit Power Envelope element. + */ +#define IEEE80211_TPE_MAX_IE_COUNT 8 +/* + * In "Table 9-277—Meaning of Maximum Transmit Power Count subfield" + * of "IEEE Std 802.11ax™‐2021", the max power level is 8. + */ +#define IEEE80211_MAX_NUM_PWR_LEVEL 8 + +#define IEEE80211_TPE_MAX_POWER_COUNT 8 + +/* transmit power interpretation type of transmit power envelope element */ +enum ieee80211_tx_power_intrpt_type { + IEEE80211_TPE_LOCAL_EIRP, + IEEE80211_TPE_LOCAL_EIRP_PSD, + IEEE80211_TPE_REG_CLIENT_EIRP, + IEEE80211_TPE_REG_CLIENT_EIRP_PSD, +}; + +/** + * struct ieee80211_tx_pwr_env + * + * This structure represents the "Transmit Power Envelope element" + */ +struct ieee80211_tx_pwr_env { + u8 tx_power_info; + s8 tx_power[IEEE80211_TPE_MAX_POWER_COUNT]; +} __packed; + +#define IEEE80211_TX_PWR_ENV_INFO_COUNT 0x7 +#define IEEE80211_TX_PWR_ENV_INFO_INTERPRET 0x38 +#define IEEE80211_TX_PWR_ENV_INFO_CATEGORY 0xC0 + +/* * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size * @he_oper_ie: byte data of the He Operations IE, stating from the byte * after the ext ID byte. It is assumed that he_oper_ie has at least @@ -2869,7 +2957,7 @@ enum ieee80211_eid { WLAN_EID_VHT_OPERATION = 192, WLAN_EID_EXTENDED_BSS_LOAD = 193, WLAN_EID_WIDE_BW_CHANNEL_SWITCH = 194, - WLAN_EID_VHT_TX_POWER_ENVELOPE = 195, + WLAN_EID_TX_POWER_ENVELOPE = 195, WLAN_EID_CHANNEL_SWITCH_WRAPPER = 196, WLAN_EID_AID = 197, WLAN_EID_QUIET_CHANNEL = 198, @@ -2881,6 +2969,7 @@ enum ieee80211_eid { WLAN_EID_AID_RESPONSE = 211, WLAN_EID_S1G_BCN_COMPAT = 213, WLAN_EID_S1G_SHORT_BCN_INTERVAL = 214, + WLAN_EID_S1G_TWT = 216, WLAN_EID_S1G_CAPABILITIES = 217, WLAN_EID_VENDOR_SPECIFIC = 221, WLAN_EID_QOS_PARAMETER = 222, @@ -2950,6 +3039,7 @@ enum ieee80211_category { WLAN_CATEGORY_FST = 18, WLAN_CATEGORY_UNPROT_DMG = 20, WLAN_CATEGORY_VHT = 21, + WLAN_CATEGORY_S1G = 22, WLAN_CATEGORY_VENDOR_SPECIFIC_PROTECTED = 126, WLAN_CATEGORY_VENDOR_SPECIFIC = 127, }; @@ -3023,6 +3113,20 @@ enum ieee80211_key_len { WLAN_KEY_LEN_BIP_GMAC_256 = 32, }; +enum ieee80211_s1g_actioncode { + WLAN_S1G_AID_SWITCH_REQUEST, + WLAN_S1G_AID_SWITCH_RESPONSE, + WLAN_S1G_SYNC_CONTROL, + WLAN_S1G_STA_INFO_ANNOUNCE, + WLAN_S1G_EDCA_PARAM_SET, + WLAN_S1G_EL_OPERATION, + WLAN_S1G_TWT_SETUP, + WLAN_S1G_TWT_TEARDOWN, + WLAN_S1G_SECT_GROUP_ID_LIST, + WLAN_S1G_SECT_ID_FEEDBACK, + WLAN_S1G_TWT_INFORMATION = 11, +}; + #define IEEE80211_WEP_IV_LEN 4 #define IEEE80211_WEP_ICV_LEN 4 #define IEEE80211_CCMP_HDR_LEN 8 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 24797929d8a1..20151c4f1e0e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1582,7 +1582,8 @@ 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 944aa3aa3035..beb918328eef 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..f3638d09ba77 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -865,7 +865,8 @@ struct mlx5_ifc_qos_cap_bits { u8 nic_bw_share[0x1]; u8 nic_rate_limit[0x1]; u8 packet_pacing_uid[0x1]; - u8 reserved_at_c[0x14]; + u8 log_esw_max_sched_depth[0x4]; + u8 reserved_at_10[0x10]; u8 reserved_at_20[0xb]; u8 log_max_qos_nic_queue_group[0x5]; @@ -921,7 +922,8 @@ 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 +1653,13 @@ 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 +3028,12 @@ 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 +3921,7 @@ 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 +3947,7 @@ 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/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 12036619346c..a85c9f0bd470 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -75,6 +75,7 @@ #define SDIO_DEVICE_ID_BROADCOM_43364 0xa9a4 #define SDIO_DEVICE_ID_BROADCOM_43430 0xa9a6 #define SDIO_DEVICE_ID_BROADCOM_43455 0xa9bf +#define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43752 0xaae8 #define SDIO_VENDOR_ID_MARVELL 0x02df #define SDIO_DEVICE_ID_MARVELL_LIBERTAS 0x9103 diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index eaf5bb008aa9..7c41593c1d6a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -47,6 +47,7 @@ #include <uapi/linux/if_bonding.h> #include <uapi/linux/pkt_cls.h> #include <linux/hashtable.h> +#include <linux/rbtree.h> struct netpoll_info; struct device; @@ -208,6 +209,7 @@ struct sk_buff; struct netdev_hw_addr { struct list_head list; + struct rb_node node; unsigned char addr[MAX_ADDR_LEN]; unsigned char type; #define NETDEV_HW_ADDR_T_LAN 1 @@ -224,6 +226,9 @@ struct netdev_hw_addr { struct netdev_hw_addr_list { struct list_head list; int count; + + /* Auxiliary tree for faster lookup on addition and deletion */ + struct rb_root tree; }; #define netdev_hw_addr_list_count(l) ((l)->count) @@ -295,18 +300,6 @@ 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; @@ -734,13 +727,13 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id, /* This structure contains an instance of an RX queue. */ struct netdev_rx_queue { + struct xdp_rxq_info xdp_rxq; #ifdef CONFIG_RPS struct rps_map __rcu *rps_map; struct rps_dev_flow_table __rcu *rps_flow_table; #endif struct kobject kobj; struct net_device *dev; - struct xdp_rxq_info xdp_rxq; #ifdef CONFIG_XDP_SOCKETS struct xsk_buff_pool *pool; #endif @@ -1086,9 +1079,18 @@ 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 +1323,9 @@ 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 +1366,15 @@ 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 +1553,8 @@ 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 +1821,7 @@ 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 +2109,9 @@ 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 +2937,6 @@ 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 +3308,6 @@ 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 +3926,8 @@ 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 +3961,7 @@ 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 +3997,8 @@ 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 +4027,16 @@ 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); +static inline bool is_socket_ioctl_cmd(unsigned int cmd) +{ + return _IOC_TYPE(cmd) == SOCK_IOC_TYPE; +} +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 +4090,7 @@ 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 +4158,13 @@ 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 +4175,13 @@ 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/pci.h b/include/linux/pci.h index 540b377ca8f6..947430637cac 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1620,6 +1620,16 @@ static inline bool pci_aer_available(void) { return false; } bool pci_ats_disabled(void); +#ifdef CONFIG_PCIE_PTM +int pci_enable_ptm(struct pci_dev *dev, u8 *granularity); +bool pcie_ptm_enabled(struct pci_dev *dev); +#else +static inline int pci_enable_ptm(struct pci_dev *dev, u8 *granularity) +{ return -EINVAL; } +static inline bool pcie_ptm_enabled(struct pci_dev *dev) +{ return false; } +#endif + void pci_cfg_access_lock(struct pci_dev *dev); bool pci_cfg_access_trylock(struct pci_dev *dev); void pci_cfg_access_unlock(struct pci_dev *dev); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 2d510ad750ed..fe156a8170aa 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -762,6 +762,7 @@ struct perf_event { #ifdef CONFIG_BPF_SYSCALL perf_overflow_handler_t orig_overflow_handler; struct bpf_prog *prog; + u64 bpf_cookie; #endif #ifdef CONFIG_EVENT_TRACING 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 1780260f237b..e12b524426b0 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; @@ -1453,6 +1454,8 @@ 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 d3c1a42a2edd..041d6032a348 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/ssb/ssb.h b/include/linux/ssb/ssb.h index 0d5a2691e7e9..f9b53acb4e02 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -7,7 +7,7 @@ #include <linux/types.h> #include <linux/spinlock.h> #include <linux/pci.h> -#include <linux/gpio.h> +#include <linux/gpio/driver.h> #include <linux/mod_devicetable.h> #include <linux/dma-mapping.h> #include <linux/platform_device.h> diff --git a/include/linux/ssb/ssb_driver_extif.h b/include/linux/ssb/ssb_driver_extif.h index 3f8bc973d67d..19253bfacd1a 100644 --- a/include/linux/ssb/ssb_driver_extif.h +++ b/include/linux/ssb/ssb_driver_extif.h @@ -197,7 +197,7 @@ struct ssb_extif { static inline bool ssb_extif_available(struct ssb_extif *extif) { - return 0; + return false; } static inline diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index ad413b382a3c..8e0631a4b046 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -675,7 +675,7 @@ trace_trigger_soft_disabled(struct trace_event_file *file) #ifdef CONFIG_BPF_EVENTS unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx); -int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog); +int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie); void perf_event_detach_bpf_prog(struct perf_event *event); int perf_event_query_prog_array(struct perf_event *event, void __user *info); int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog); @@ -692,7 +692,7 @@ static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *c } static inline int -perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog) +perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie) { return -EOPNOTSUPP; } @@ -803,6 +803,9 @@ extern void ftrace_profile_free_filter(struct perf_event *event); void perf_trace_buf_update(void *record, u16 type); void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp); +int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie); +void perf_event_free_bpf_prog(struct perf_event *event); + void bpf_trace_run1(struct bpf_prog *prog, u64 arg1); void bpf_trace_run2(struct bpf_prog *prog, u64 arg1, u64 arg2); void bpf_trace_run3(struct bpf_prog *prog, u64 arg1, u64 arg2, 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 */ |