diff options
| author | Stefan Schmidt <stefan@datenfreihafen.org> | 2017-10-18 18:40:18 +0300 |
|---|---|---|
| committer | Stefan Schmidt <stefan@datenfreihafen.org> | 2017-10-18 18:40:18 +0300 |
| commit | 396665e8320987ff43b20a62a6a1cdae57aa1cc1 (patch) | |
| tree | bf778eab1ef1c9ff102bb235d9bca1a42bec7d0a /include/linux | |
| parent | d01174fcd2c1ffefdd0554f847c4045a5c731591 (diff) | |
| parent | b9f1f1ce866c28e3d9b86202441b220244754a69 (diff) | |
| download | linux-396665e8320987ff43b20a62a6a1cdae57aa1cc1.tar.xz | |
Merge remote-tracking branch 'net-next/master'
Diffstat (limited to 'include/linux')
51 files changed, 1272 insertions, 193 deletions
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 2b038442c352..3ce61342fa31 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -135,6 +135,7 @@ enum virtchnl_ops { VIRTCHNL_OP_SET_RSS_HENA = 26, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING = 27, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING = 28, + VIRTCHNL_OP_REQUEST_QUEUES = 29, }; /* This macro is used to generate a compilation error if a structure @@ -235,6 +236,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); #define VIRTCHNL_VF_OFFLOAD_RSS_AQ 0x00000008 #define VIRTCHNL_VF_OFFLOAD_RSS_REG 0x00000010 #define VIRTCHNL_VF_OFFLOAD_WB_ON_ITR 0x00000020 +#define VIRTCHNL_VF_OFFLOAD_REQ_QUEUES 0x00000040 #define VIRTCHNL_VF_OFFLOAD_VLAN 0x00010000 #define VIRTCHNL_VF_OFFLOAD_RX_POLLING 0x00020000 #define VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 0x00040000 @@ -325,6 +327,21 @@ struct virtchnl_vsi_queue_config_info { struct virtchnl_queue_pair_info qpair[1]; }; +/* VIRTCHNL_OP_REQUEST_QUEUES + * VF sends this message to request the PF to allocate additional queues to + * this VF. Each VF gets a guaranteed number of queues on init but asking for + * additional queues must be negotiated. This is a best effort request as it + * is possible the PF does not have enough queues left to support the request. + * If the PF cannot support the number requested it will respond with the + * maximum number it is able to support. If the request is successful, PF will + * then reset the VF to institute required changes. + */ + +/* VF resource request */ +struct virtchnl_vf_res_request { + u16 num_queue_pairs; +}; + VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_vsi_queue_config_info); /* VIRTCHNL_OP_CONFIG_IRQ_MAP @@ -691,6 +708,9 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: break; + case VIRTCHNL_OP_REQUEST_QUEUES: + valid_len = sizeof(struct virtchnl_vf_res_request); + break; /* These are always errors coming from the VF. */ case VIRTCHNL_OP_EVENT: case VIRTCHNL_OP_UNKNOWN: diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index fb44d6180ca0..18d05b5491f3 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -131,7 +131,7 @@ extern int setup_arg_pages(struct linux_binprm * bprm, int executable_stack); extern int transfer_args_to_stack(struct linux_binprm *bprm, unsigned long *sp_location); -extern int bprm_change_interp(char *interp, struct linux_binprm *bprm); +extern int bprm_change_interp(const char *interp, struct linux_binprm *bprm); extern int copy_strings_kernel(int argc, const char *const *argv, struct linux_binprm *bprm); extern int prepare_bprm_creds(struct linux_binprm *bprm); diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index 8b9d6fff002d..f2deb71958b2 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -92,7 +92,7 @@ /** * FIELD_GET() - extract a bitfield element * @_mask: shifted mask defining the field's length and position - * @_reg: 32bit value of entire bitfield + * @_reg: value of entire bitfield * * FIELD_GET() extracts the field specified by @_mask from the * bitfield passed in as @_reg by masking and shifting it down. diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 460294bb0fa5..02fa42d24b52 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -551,6 +551,7 @@ struct request_queue { int node; #ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace *blk_trace; + struct mutex blk_trace_mutex; #endif /* * for flush operations diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index d41d40ac3efd..359b6f5d3d90 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -14,27 +14,46 @@ struct bpf_sock_ops_kern; extern struct static_key_false cgroup_bpf_enabled_key; #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) +struct bpf_prog_list { + struct list_head node; + struct bpf_prog *prog; +}; + +struct bpf_prog_array; + struct cgroup_bpf { - /* - * Store two sets of bpf_prog pointers, one for programs that are - * pinned directly to this cgroup, and one for those that are effective - * when this cgroup is accessed. + /* array of effective progs in this cgroup */ + struct bpf_prog_array __rcu *effective[MAX_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 bpf_prog *prog[MAX_BPF_ATTACH_TYPE]; - struct bpf_prog __rcu *effective[MAX_BPF_ATTACH_TYPE]; - bool disallow_override[MAX_BPF_ATTACH_TYPE]; + struct list_head progs[MAX_BPF_ATTACH_TYPE]; + u32 flags[MAX_BPF_ATTACH_TYPE]; + + /* temp storage for effective prog array used by prog_attach/detach */ + struct bpf_prog_array __rcu *inactive; }; void cgroup_bpf_put(struct cgroup *cgrp); -void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent); - -int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent, - struct bpf_prog *prog, enum bpf_attach_type type, - bool overridable); - -/* Wrapper for __cgroup_bpf_update() protected by cgroup_mutex */ -int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type, bool overridable); +int cgroup_bpf_inherit(struct cgroup *cgrp); + +int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); +int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); +int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr); + +/* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */ +int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); +int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); +int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr); int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, @@ -96,8 +115,7 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct cgroup_bpf {}; static inline void cgroup_bpf_put(struct cgroup *cgrp) {} -static inline void cgroup_bpf_inherit(struct cgroup *cgrp, - struct cgroup *parent) {} +static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8390859e79e7..d67ccdc0099f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -56,6 +56,7 @@ struct bpf_map { struct work_struct work; atomic_t usercnt; struct bpf_map *inner_map_meta; + char name[BPF_OBJ_NAME_LEN]; }; /* function argument constraints */ @@ -137,6 +138,7 @@ enum bpf_reg_type { PTR_TO_MAP_VALUE, /* reg points to map element value */ PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ PTR_TO_STACK, /* reg == frame_pointer + offset */ + PTR_TO_PACKET_META, /* skb->data - meta_len */ PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ }; @@ -155,6 +157,11 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size) aux->ctx_field_size = size; } +struct bpf_prog_ops { + int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr); +}; + struct bpf_verifier_ops { /* return eBPF function prototype for verification */ const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id); @@ -170,8 +177,6 @@ struct bpf_verifier_ops { const struct bpf_insn *src, struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); - int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, - union bpf_attr __user *uattr); }; struct bpf_prog_aux { @@ -182,10 +187,12 @@ struct bpf_prog_aux { u32 id; struct latch_tree_node ksym_tnode; struct list_head ksym_lnode; - const struct bpf_verifier_ops *ops; + const struct bpf_prog_ops *ops; struct bpf_map **used_maps; struct bpf_prog *prog; struct user_struct *user; + u64 load_time; /* ns since boottime */ + char name[BPF_OBJ_NAME_LEN]; union { struct work_struct work; struct rcu_head rcu; @@ -237,17 +244,56 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); +/* an array of programs to be executed under rcu_lock. + * + * Typical usage: + * 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. + * The user has to keep refcnt on the program and make sure the program + * is removed from the array before bpf_prog_put(). + * The 'struct bpf_prog_array *' should only be replaced with xchg() + * since other cpus are walking the array of pointers in parallel. + */ +struct bpf_prog_array { + struct rcu_head rcu; + struct bpf_prog *progs[0]; +}; + +struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); +void bpf_prog_array_free(struct bpf_prog_array __rcu *progs); +int bpf_prog_array_length(struct bpf_prog_array __rcu *progs); +int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, + __u32 __user *prog_ids, u32 cnt); + +#define BPF_PROG_RUN_ARRAY(array, ctx, func) \ + ({ \ + struct bpf_prog **_prog; \ + u32 _ret = 1; \ + rcu_read_lock(); \ + _prog = rcu_dereference(array)->progs; \ + for (; *_prog; _prog++) \ + _ret &= func(*_prog, ctx); \ + rcu_read_unlock(); \ + _ret; \ + }) + #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); -#define BPF_PROG_TYPE(_id, _ops) \ - extern const struct bpf_verifier_ops _ops; +#define BPF_PROG_TYPE(_id, _name) \ + extern const struct bpf_prog_ops _name ## _prog_ops; \ + extern const struct bpf_verifier_ops _name ## _verifier_ops; #define BPF_MAP_TYPE(_id, _ops) \ extern const struct bpf_map_ops _ops; #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE +extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops; +extern const struct bpf_verifier_ops xdp_analyzer_ops; + struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type); struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i); @@ -316,6 +362,13 @@ struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); void __dev_map_insert_ctx(struct bpf_map *map, u32 index); void __dev_map_flush(struct bpf_map *map); +struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); +void __cpu_map_insert_ctx(struct bpf_map *map, u32 index); +void __cpu_map_flush(struct bpf_map *map); +struct xdp_buff; +int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, + struct net_device *dev_rx); + /* Return map's numa specified by userspace */ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) { @@ -323,7 +376,7 @@ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) attr->numa_node : NUMA_NO_NODE; } -#else +#else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { return ERR_PTR(-EOPNOTSUPP); @@ -368,6 +421,11 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) { } +static inline int bpf_obj_get_user(const char __user *pathname) +{ + return -EOPNOTSUPP; +} + static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { @@ -381,6 +439,28 @@ static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index) static inline void __dev_map_flush(struct bpf_map *map) { } + +static inline +struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) +{ + return NULL; +} + +static inline void __cpu_map_insert_ctx(struct bpf_map *map, u32 index) +{ +} + +static inline void __cpu_map_flush(struct bpf_map *map) +{ +} + +struct xdp_buff; +static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, + struct xdp_buff *xdp, + struct net_device *dev_rx) +{ + return 0; +} #endif /* CONFIG_BPF_SYSCALL */ #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 6f1a567667b8..36418ad43245 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -1,22 +1,22 @@ /* internal file - do not include directly */ #ifdef CONFIG_NET -BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter) +BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act) +BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act) +BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit) +BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb) #endif #ifdef CONFIG_BPF_EVENTS -BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe) +BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint) +BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) @@ -41,4 +41,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) #ifdef CONFIG_STREAM_PARSER BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) #endif +BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) #endif diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index b8d200f60a40..feeaea93d959 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -115,6 +115,21 @@ struct bpf_insn_aux_data { #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ +#define BPF_VERIFIER_TMP_LOG_SIZE 1024 + +struct bpf_verifer_log { + u32 level; + char kbuf[BPF_VERIFIER_TMP_LOG_SIZE]; + char __user *ubuf; + u32 len_used; + u32 len_total; +}; + +static inline bool bpf_verifier_log_full(const struct bpf_verifer_log *log) +{ + return log->len_used >= log->len_total - 1; +} + struct bpf_verifier_env; struct bpf_ext_analyzer_ops { int (*insn_hook)(struct bpf_verifier_env *env, @@ -126,6 +141,7 @@ struct bpf_ext_analyzer_ops { */ struct bpf_verifier_env { struct bpf_prog *prog; /* eBPF program being verified */ + const struct bpf_verifier_ops *ops; struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */ int stack_size; /* number of states to be processed */ bool strict_alignment; /* perform strict pointer alignment checks */ @@ -139,6 +155,8 @@ struct bpf_verifier_env { bool allow_ptr_leaks; bool seen_direct_write; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ + + struct bpf_verifer_log log; }; int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index abcda9b458ab..9ac9e3e3d1e5 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -63,6 +63,7 @@ #define PHY_BRCM_EXT_IBND_TX_ENABLE 0x00002000 #define PHY_BRCM_CLEAR_RGMII_MODE 0x00004000 #define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00008000 +#define PHY_BRCM_EN_MASTER_MODE 0x00010000 /* Broadcom BCM7xxx specific workarounds */ #define PHY_BRCM_7XXX_REV(x) (((x) >> 8) & 0xff) diff --git a/include/linux/byteorder/generic.h b/include/linux/byteorder/generic.h index 89f67c1c3160..805d16654459 100644 --- a/include/linux/byteorder/generic.h +++ b/include/linux/byteorder/generic.h @@ -170,4 +170,20 @@ static inline void be64_add_cpu(__be64 *var, u64 val) *var = cpu_to_be64(be64_to_cpu(*var) + val); } +static inline void cpu_to_be32_array(__be32 *dst, const u32 *src, size_t len) +{ + int i; + + for (i = 0; i < len; i++) + dst[i] = cpu_to_be32(src[i]); +} + +static inline void be32_to_cpu_array(u32 *dst, const __be32 *src, size_t len) +{ + int i; + + for (i = 0; i < len; i++) + dst[i] = be32_to_cpu(src[i]); +} + #endif /* _LINUX_BYTEORDER_GENERIC_H */ diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index f24bfb2b9a2d..6d508767e144 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -3,8 +3,27 @@ #include <linux/types.h> +/* + * CPU-up CPU-down + * + * BP AP BP AP + * + * OFFLINE OFFLINE + * | ^ + * v | + * BRINGUP_CPU->AP_OFFLINE BRINGUP_CPU <- AP_IDLE_DEAD (idle thread/play_dead) + * | AP_OFFLINE + * v (IRQ-off) ,---------------^ + * AP_ONLNE | (stop_machine) + * | TEARDOWN_CPU <- AP_ONLINE_IDLE + * | ^ + * v | + * AP_ACTIVE AP_ACTIVE + */ + enum cpuhp_state { - CPUHP_OFFLINE, + CPUHP_INVALID = -1, + CPUHP_OFFLINE = 0, CPUHP_CREATE_THREADS, CPUHP_PERF_PREPARE, CPUHP_PERF_X86_PREPARE, diff --git a/include/linux/device.h b/include/linux/device.h index 1d2607923a24..66fe271c2544 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -307,8 +307,6 @@ struct driver_attribute { size_t count); }; -#define DRIVER_ATTR(_name, _mode, _show, _store) \ - struct driver_attribute driver_attr_##_name = __ATTR(_name, _mode, _show, _store) #define DRIVER_ATTR_RW(_name) \ struct driver_attribute driver_attr_##_name = __ATTR_RW(_name) #define DRIVER_ATTR_RO(_name) \ diff --git a/include/linux/filter.h b/include/linux/filter.h index d29e58fde364..2d2db394b0ca 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -481,30 +481,36 @@ struct sk_filter { struct bpf_prog *prog; }; -#define BPF_PROG_RUN(filter, ctx) (*filter->bpf_func)(ctx, filter->insnsi) +#define BPF_PROG_RUN(filter, ctx) (*(filter)->bpf_func)(ctx, (filter)->insnsi) #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN struct bpf_skb_data_end { struct qdisc_skb_cb qdisc_cb; + void *data_meta; void *data_end; }; struct xdp_buff { void *data; void *data_end; + void *data_meta; void *data_hard_start; }; -/* compute the linear packet data range [data, data_end) which - * will be accessed by cls_bpf, act_bpf and lwt programs +/* Compute the linear packet data range [data, data_end) which + * will be accessed by various program types (cls_bpf, act_bpf, + * lwt, ...). Subsystems allowing direct data access must (!) + * ensure that cb[] area can be written to when BPF program is + * invoked (otherwise cb[] save/restore is necessary). */ -static inline void bpf_compute_data_end(struct sk_buff *skb) +static inline void bpf_compute_data_pointers(struct sk_buff *skb) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; BUILD_BUG_ON(sizeof(*cb) > FIELD_SIZEOF(struct sk_buff, cb)); - cb->data_end = skb->data + skb_headlen(skb); + cb->data_meta = skb->data - skb_metadata_len(skb); + cb->data_end = skb->data + skb_headlen(skb); } static inline u8 *bpf_skb_cb(struct sk_buff *skb) @@ -725,8 +731,22 @@ int xdp_do_redirect(struct net_device *dev, struct bpf_prog *prog); void xdp_do_flush_map(void); +/* Drivers not supporting XDP metadata can use this helper, which + * rejects any room expansion for metadata as a result. + */ +static __always_inline void +xdp_set_data_meta_invalid(struct xdp_buff *xdp) +{ + xdp->data_meta = xdp->data + 1; +} + +static __always_inline bool +xdp_data_meta_unsupported(const struct xdp_buff *xdp) +{ + return unlikely(xdp->data_meta > xdp->data); +} + void bpf_warn_invalid_xdp_action(u32 act); -void bpf_warn_invalid_xdp_redirect(u32 ifindex); struct sock *do_sk_redirect_map(void); diff --git a/include/linux/fs.h b/include/linux/fs.h index 339e73742e73..13dab191a23e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -403,7 +403,7 @@ struct address_space { unsigned long flags; /* error bits */ spinlock_t private_lock; /* for use by the address_space */ gfp_t gfp_mask; /* implicit gfp mask for allocations */ - struct list_head private_list; /* ditto */ + struct list_head private_list; /* for use by the address_space */ void *private_data; /* ditto */ errseq_t wb_err; } __attribute__((aligned(sizeof(long)))) __randomize_layout; diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 55a604ad459f..ee6657a0ed69 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2445,6 +2445,7 @@ enum ieee80211_sa_query_action { #define WLAN_OUI_TYPE_MICROSOFT_WPA 1 #define WLAN_OUI_TYPE_MICROSOFT_WMM 2 #define WLAN_OUI_TYPE_MICROSOFT_WPS 4 +#define WLAN_OUI_TYPE_MICROSOFT_TPC 8 /* * WMM/802.11e Tspec Element diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index 3355efc89781..6756fea18b69 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -31,7 +31,7 @@ static inline struct arphdr *arp_hdr(const struct sk_buff *skb) return (struct arphdr *)skb_network_header(skb); } -static inline int arp_hdr_len(struct net_device *dev) +static inline unsigned int arp_hdr_len(const struct net_device *dev) { switch (dev->type) { #if IS_ENABLED(CONFIG_FIREWIRE_NET) diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 3cd18ac0697f..02639ebea2f0 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -49,6 +49,7 @@ struct br_ip_list { #define BR_MULTICAST_TO_UNICAST BIT(12) #define BR_VLAN_TUNNEL BIT(13) #define BR_BCAST_FLOOD BIT(14) +#define BR_NEIGH_SUPPRESS BIT(15) #define BR_DEFAULT_AGEING_TIME (300 * HZ) @@ -63,6 +64,7 @@ int br_multicast_list_adjacent(struct net_device *dev, bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto); bool br_multicast_has_querier_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); #else static inline int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list) @@ -83,6 +85,10 @@ static inline bool br_multicast_enabled(const struct net_device *dev) { return false; } +static inline bool br_multicast_router(const struct net_device *dev) +{ + return false; +} #endif #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING) diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index c9ec1343d187..10e319f41fb1 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -72,7 +72,8 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, extern void macvlan_common_setup(struct net_device *dev); extern int macvlan_common_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]); + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack); extern void macvlan_count_rx(const struct macvlan_dev *vlan, unsigned int len, bool success, diff --git a/include/linux/if_phonet.h b/include/linux/if_phonet.h index bbcdb0a767d8..a118ee4a8428 100644 --- a/include/linux/if_phonet.h +++ b/include/linux/if_phonet.h @@ -10,5 +10,5 @@ #include <uapi/linux/if_phonet.h> -extern struct header_ops phonet_header_ops; +extern const struct header_ops phonet_header_ops; #endif diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index 5ba430cc9a87..1fc7abd28b0b 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -111,6 +111,9 @@ int ad_sd_write_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg, int ad_sd_read_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg, unsigned int size, unsigned int *val); +int ad_sd_reset(struct ad_sigma_delta *sigma_delta, + unsigned int reset_length); + int ad_sigma_delta_single_conversion(struct iio_dev *indio_dev, const struct iio_chan_spec *chan, int *val); int ad_sd_calibrate_all(struct ad_sigma_delta *sigma_delta, diff --git a/include/linux/iommu.h b/include/linux/iommu.h index a7f2ac689d29..41b8c5757859 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -167,11 +167,11 @@ struct iommu_resv_region { * @map: map a physically contiguous memory region to an iommu domain * @unmap: unmap a physically contiguous memory region from an iommu domain * @map_sg: map a scatter-gather list of physically contiguous memory chunks + * to an iommu domain * @flush_tlb_all: Synchronously flush all hardware TLBs for this domain * @tlb_range_add: Add a given iova range to the flush queue for this domain * @tlb_sync: Flush all queued ranges from the hardware TLBs and empty flush * queue - * to an iommu domain * @iova_to_phys: translate iova to physical address * @add_device: add device to iommu grouping * @remove_device: remove device from iommu grouping diff --git a/include/linux/irq.h b/include/linux/irq.h index b99a784635ff..d4728bf6a537 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -783,10 +783,7 @@ static inline struct cpumask *irq_data_get_affinity_mask(struct irq_data *d) static inline struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d) { - if (!cpumask_empty(d->common->effective_affinity)) - return d->common->effective_affinity; - - return d->common->affinity; + return d->common->effective_affinity; } static inline void irq_data_update_effective_affinity(struct irq_data *d, const struct cpumask *m) diff --git a/include/linux/key.h b/include/linux/key.h index 044114185120..e315e16b6ff8 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -187,6 +187,7 @@ struct key { #define KEY_FLAG_BUILTIN 8 /* set if key is built in to the kernel */ #define KEY_FLAG_ROOT_CAN_INVAL 9 /* set if key can be invalidated by root without permission */ #define KEY_FLAG_KEEP 10 /* set if key should not be removed */ +#define KEY_FLAG_UID_KEYRING 11 /* set if key is a user or user session keyring */ /* the key type and key description string * - the desc is used to match a key against search criteria @@ -243,6 +244,7 @@ extern struct key *key_alloc(struct key_type *type, #define KEY_ALLOC_NOT_IN_QUOTA 0x0002 /* not in quota */ #define KEY_ALLOC_BUILT_IN 0x0004 /* Key is built into kernel */ #define KEY_ALLOC_BYPASS_RESTRICTION 0x0008 /* Override the check on restricted keyrings */ +#define KEY_ALLOC_UID_KEYRING 0x0010 /* allocating a user or user session keyring */ extern void key_revoke(struct key *key); extern void key_invalidate(struct key *key); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index eaf4ad209c8f..e32dbc4934db 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -980,7 +980,6 @@ enum mlx5_cap_type { MLX5_CAP_RESERVED, MLX5_CAP_VECTOR_CALC, MLX5_CAP_QOS, - MLX5_CAP_FPGA, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1110,10 +1109,10 @@ enum mlx5_mcam_feature_groups { MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_feature_cap_mask.enhanced_features.fld) #define MLX5_CAP_FPGA(mdev, cap) \ - MLX5_GET(fpga_cap, (mdev)->caps.hca_cur[MLX5_CAP_FPGA], cap) + MLX5_GET(fpga_cap, (mdev)->caps.fpga, cap) #define MLX5_CAP64_FPGA(mdev, cap) \ - MLX5_GET64(fpga_cap, (mdev)->caps.hca_cur[MLX5_CAP_FPGA], cap) + MLX5_GET64(fpga_cap, (mdev)->caps.fpga, cap) enum { MLX5_CMD_STAT_OK = 0x0, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 02ff700e4f30..08c77b7e59cb 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -49,6 +49,8 @@ #include <linux/mlx5/device.h> #include <linux/mlx5/doorbell.h> #include <linux/mlx5/srq.h> +#include <linux/timecounter.h> +#include <linux/ptp_clock_kernel.h> enum { MLX5_BOARD_ID_LEN = 64, @@ -760,6 +762,27 @@ struct mlx5_rsvd_gids { struct ida ida; }; +#define MAX_PIN_NUM 8 +struct mlx5_pps { + u8 pin_caps[MAX_PIN_NUM]; + struct work_struct out_work; + u64 start[MAX_PIN_NUM]; + u8 enabled; +}; + +struct mlx5_clock { + rwlock_t lock; + struct cyclecounter cycles; + struct timecounter tc; + struct hwtstamp_config hwtstamp_config; + u32 nominal_c_mult; + unsigned long overflow_period; + struct delayed_work overflow_work; + struct ptp_clock *ptp; + struct ptp_clock_info ptp_info; + struct mlx5_pps pps_info; +}; + struct mlx5_core_dev { struct pci_dev *pdev; /* sync pci state */ @@ -774,6 +797,7 @@ struct mlx5_core_dev { u32 hca_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; u32 pcam[MLX5_ST_SZ_DW(pcam_reg)]; u32 mcam[MLX5_ST_SZ_DW(mcam_reg)]; + u32 fpga[MLX5_ST_SZ_DW(fpga_cap)]; } caps; phys_addr_t iseg_base; struct mlx5_init_seg __iomem *iseg; @@ -799,6 +823,7 @@ struct mlx5_core_dev { #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *rmap; #endif + struct mlx5_clock clock; }; struct mlx5_db { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index a528b35a022e..69772347f866 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -327,7 +327,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reserved_at_80[0x18]; u8 log_max_destination[0x8]; - u8 reserved_at_a0[0x18]; + u8 log_max_flow_counter[0x8]; + u8 reserved_at_a8[0x10]; u8 log_max_flow[0x8]; u8 reserved_at_c0[0x40]; diff --git a/include/linux/mm.h b/include/linux/mm.h index f8c10d336e42..065d99deb847 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -240,7 +240,7 @@ extern unsigned int kobjsize(const void *objp); #if defined(CONFIG_X86_INTEL_MPX) /* MPX specific bounds table or bounds directory */ -# define VM_MPX VM_HIGH_ARCH_BIT_4 +# define VM_MPX VM_HIGH_ARCH_4 #else # define VM_MPX VM_NONE #endif diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index f3f2d07feb2a..9a43763a68ad 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -316,7 +316,7 @@ struct mmc_host { #define MMC_CAP_UHS_SDR50 (1 << 18) /* Host supports UHS SDR50 mode */ #define MMC_CAP_UHS_SDR104 (1 << 19) /* Host supports UHS SDR104 mode */ #define MMC_CAP_UHS_DDR50 (1 << 20) /* Host supports UHS DDR50 mode */ -#define MMC_CAP_NO_BOUNCE_BUFF (1 << 21) /* Disable bounce buffers on host */ +/* (1 << 21) is free for reuse */ #define MMC_CAP_DRIVER_TYPE_A (1 << 23) /* Host supports Driver Type A */ #define MMC_CAP_DRIVER_TYPE_C (1 << 24) /* Host supports Driver Type C */ #define MMC_CAP_DRIVER_TYPE_D (1 << 25) /* Host supports Driver Type D */ diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 7b2e31b1745a..6866e8126982 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -400,6 +400,11 @@ extern void mmu_notifier_synchronize(void); #else /* CONFIG_MMU_NOTIFIER */ +static inline int mm_has_notifiers(struct mm_struct *mm) +{ + return 0; +} + static inline void mmu_notifier_release(struct mm_struct *mm) { } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 356a814e7c8e..c8f89417740b 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1094,8 +1094,14 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn) #error Allocator MAX_ORDER exceeds SECTION_SIZE #endif -#define pfn_to_section_nr(pfn) ((pfn) >> PFN_SECTION_SHIFT) -#define section_nr_to_pfn(sec) ((sec) << PFN_SECTION_SHIFT) +static inline unsigned long pfn_to_section_nr(unsigned long pfn) +{ + return pfn >> PFN_SECTION_SHIFT; +} +static inline unsigned long section_nr_to_pfn(unsigned long sec) +{ + return sec << PFN_SECTION_SHIFT; +} #define SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK) #define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK) diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 694cebb50f72..7625c3b81f84 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -683,5 +683,31 @@ struct fsl_mc_device_id { const char obj_type[16]; }; +/** + * struct tb_service_id - Thunderbolt service identifiers + * @match_flags: Flags used to match the structure + * @protocol_key: Protocol key the service supports + * @protocol_id: Protocol id the service supports + * @protocol_version: Version of the protocol + * @protocol_revision: Revision of the protocol software + * @driver_data: Driver specific data + * + * Thunderbolt XDomain services are exposed as devices where each device + * carries the protocol information the service supports. Thunderbolt + * XDomain service drivers match against that information. + */ +struct tb_service_id { + __u32 match_flags; + char protocol_key[8 + 1]; + __u32 protocol_id; + __u32 protocol_version; + __u32 protocol_revision; + kernel_ulong_t driver_data; +}; + +#define TBSVC_MATCH_PROTOCOL_KEY 0x0001 +#define TBSVC_MATCH_PROTOCOL_ID 0x0002 +#define TBSVC_MATCH_PROTOCOL_VERSION 0x0004 +#define TBSVC_MATCH_PROTOCOL_REVISION 0x0008 #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/include/linux/mroute.h b/include/linux/mroute.h index d7f63339ef0b..8242d05df35e 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -5,6 +5,8 @@ #include <linux/pim.h> #include <linux/rhashtable.h> #include <net/sock.h> +#include <net/fib_rules.h> +#include <net/fib_notifier.h> #include <uapi/linux/mroute.h> #ifdef CONFIG_IP_MROUTE @@ -18,6 +20,7 @@ int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *); int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg); int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); int ip_mr_init(void); +bool ipmr_rule_default(const struct fib_rule *rule); #else static inline int ip_mroute_setsockopt(struct sock *sock, int optname, char __user *optval, unsigned int optlen) @@ -45,10 +48,16 @@ static inline int ip_mroute_opt(int opt) { return 0; } + +static inline bool ipmr_rule_default(const struct fib_rule *rule) +{ + return true; +} #endif struct vif_device { struct net_device *dev; /* Device we are using */ + struct netdev_phys_item_id dev_parent_id; /* Device parent ID */ unsigned long bytes_in,bytes_out; unsigned long pkt_in,pkt_out; /* Statistics */ unsigned long rate_limit; /* Traffic shaping (NI) */ @@ -58,6 +67,14 @@ struct vif_device { int link; /* Physical interface index */ }; +struct vif_entry_notifier_info { + struct fib_notifier_info info; + struct net_device *dev; + vifi_t vif_index; + unsigned short vif_flags; + u32 tb_id; +}; + #define VIFF_STATIC 0x8000 #define VIF_EXISTS(_mrt, _idx) ((_mrt)->vif_table[_idx].dev != NULL) @@ -81,9 +98,11 @@ struct mr_table { /* mfc_flags: * MFC_STATIC - the entry was added statically (not by a routing daemon) + * MFC_OFFLOAD - the entry was offloaded to the hardware */ enum { MFC_STATIC = BIT(0), + MFC_OFFLOAD = BIT(1), }; struct mfc_cache_cmp_arg { @@ -109,6 +128,7 @@ struct mfc_cache_cmp_arg { * @wrong_if: number of wrong source interface hits * @lastuse: time of last use of the group (traffic or update) * @ttls: OIF TTL threshold array + * @refcount: reference count for this entry * @list: global entry list * @rcu: used for entry destruction */ @@ -138,14 +158,40 @@ struct mfc_cache { unsigned long wrong_if; unsigned long lastuse; unsigned char ttls[MAXVIFS]; + refcount_t refcount; } res; } mfc_un; struct list_head list; struct rcu_head rcu; }; +struct mfc_entry_notifier_info { + struct fib_notifier_info info; + struct mfc_cache *mfc; + u32 tb_id; +}; + struct rtmsg; int ipmr_get_route(struct net *net, struct sk_buff *skb, __be32 saddr, __be32 daddr, struct rtmsg *rtm, u32 portid); + +#ifdef CONFIG_IP_MROUTE +void ipmr_cache_free(struct mfc_cache *mfc_cache); +#else +static inline void ipmr_cache_free(struct mfc_cache *mfc_cache) +{ +} +#endif + +static inline void ipmr_cache_put(struct mfc_cache *c) +{ + if (refcount_dec_and_test(&c->mfc_un.res.refcount)) + ipmr_cache_free(c); +} +static inline void ipmr_cache_hold(struct mfc_cache *c) +{ + refcount_inc(&c->mfc_un.res.refcount); +} + #endif diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f535779d9dc1..bf014afcb914 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -55,7 +55,7 @@ struct netpoll_info; struct device; struct phy_device; -struct dsa_switch_tree; +struct dsa_port; /* 802.11 specific */ struct wireless_dev; @@ -826,6 +826,11 @@ struct xfrmdev_ops { }; #endif +struct dev_ifalias { + struct rcu_head rcuhead; + char ifalias[]; +}; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1241,7 +1246,8 @@ struct net_device_ops { u32 flow_id); #endif int (*ndo_add_slave)(struct net_device *dev, - struct net_device *slave_dev); + struct net_device *slave_dev, + struct netlink_ext_ack *extack); int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); netdev_features_t (*ndo_fix_features)(struct net_device *dev, @@ -1632,7 +1638,7 @@ enum netdev_priv_flags { struct net_device { char name[IFNAMSIZ]; struct hlist_node name_hlist; - char *ifalias; + struct dev_ifalias __rcu *ifalias; /* * I/O specific fields * FIXME: Merge these and struct ifmap into one @@ -1752,7 +1758,7 @@ struct net_device { struct vlan_info __rcu *vlan_info; #endif #if IS_ENABLED(CONFIG_NET_DSA) - struct dsa_switch_tree *dsa_ptr; + struct dsa_port *dsa_ptr; #endif #if IS_ENABLED(CONFIG_TIPC) struct tipc_bearer __rcu *tipc_ptr; @@ -2304,7 +2310,8 @@ int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); struct netdev_notifier_info { - struct net_device *dev; + struct net_device *dev; + struct netlink_ext_ack *extack; }; struct netdev_notifier_change_info { @@ -2329,6 +2336,7 @@ static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, struct net_device *dev) { info->dev = dev; + info->extack = NULL; } static inline struct net_device * @@ -2337,6 +2345,12 @@ netdev_notifier_info_to_dev(const struct netdev_notifier_info *info) return info->dev; } +static inline struct netlink_ext_ack * +netdev_notifier_info_to_extack(const struct netdev_notifier_info *info) +{ + return info->extack; +} + int call_netdevice_notifiers(unsigned long val, struct net_device *dev); @@ -3246,6 +3260,7 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); int netif_rx(struct sk_buff *skb); int netif_rx_ni(struct sk_buff *skb); int netif_receive_skb(struct sk_buff *skb); +int netif_receive_skb_core(struct sk_buff *skb); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); @@ -3275,6 +3290,7 @@ void __dev_notify_flags(struct net_device *, unsigned int old_flags, unsigned int gchanges); int dev_change_name(struct net_device *, const char *); int dev_set_alias(struct net_device *, const char *, size_t); +int dev_get_alias(const struct net_device *, char *, size_t); int dev_change_net_namespace(struct net_device *, struct net *, const char *); int __dev_set_mtu(struct net_device *, int); int dev_set_mtu(struct net_device *, int); @@ -3904,10 +3920,12 @@ void *netdev_adjacent_get_private(struct list_head *adj_list); void *netdev_lower_get_first_private_rcu(struct net_device *dev); struct net_device *netdev_master_upper_dev_get(struct net_device *dev); struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev); -int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev); +int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, + struct netlink_ext_ack *extack); int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, - void *upper_priv, void *upper_info); + void *upper_priv, void *upper_info, + struct netlink_ext_ack *extack); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 2c2a5514b0df..528b24c78308 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -108,9 +108,10 @@ struct ebt_table { #define EBT_ALIGN(s) (((s) + (__alignof__(struct _xt_align)-1)) & \ ~(__alignof__(struct _xt_align)-1)) -extern struct ebt_table *ebt_register_table(struct net *net, - const struct ebt_table *table, - const struct nf_hook_ops *); +extern int ebt_register_table(struct net *net, + const struct ebt_table *table, + const struct nf_hook_ops *ops, + struct ebt_table **res); extern void ebt_unregister_table(struct net *net, struct ebt_table *table, const struct nf_hook_ops *); extern unsigned int ebt_do_table(struct sk_buff *skb, diff --git a/include/linux/nmi.h b/include/linux/nmi.h index a36abe2da13e..27e249ed7c5c 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -12,11 +12,31 @@ #ifdef CONFIG_LOCKUP_DETECTOR void lockup_detector_init(void); +void lockup_detector_soft_poweroff(void); +void lockup_detector_cleanup(void); +bool is_hardlockup(void); + +extern int watchdog_user_enabled; +extern int nmi_watchdog_user_enabled; +extern int soft_watchdog_user_enabled; +extern int watchdog_thresh; +extern unsigned long watchdog_enabled; + +extern struct cpumask watchdog_cpumask; +extern unsigned long *watchdog_cpumask_bits; +#ifdef CONFIG_SMP +extern int sysctl_softlockup_all_cpu_backtrace; +extern int sysctl_hardlockup_all_cpu_backtrace; #else -static inline void lockup_detector_init(void) -{ -} -#endif +#define sysctl_softlockup_all_cpu_backtrace 0 +#define sysctl_hardlockup_all_cpu_backtrace 0 +#endif /* !CONFIG_SMP */ + +#else /* CONFIG_LOCKUP_DETECTOR */ +static inline void lockup_detector_init(void) { } +static inline void lockup_detector_soft_poweroff(void) { } +static inline void lockup_detector_cleanup(void) { } +#endif /* !CONFIG_LOCKUP_DETECTOR */ #ifdef CONFIG_SOFTLOCKUP_DETECTOR extern void touch_softlockup_watchdog_sched(void); @@ -24,29 +44,17 @@ extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); extern unsigned int softlockup_panic; -extern int soft_watchdog_enabled; -extern atomic_t watchdog_park_in_progress; #else -static inline void touch_softlockup_watchdog_sched(void) -{ -} -static inline void touch_softlockup_watchdog(void) -{ -} -static inline void touch_softlockup_watchdog_sync(void) -{ -} -static inline void touch_all_softlockup_watchdogs(void) -{ -} +static inline void touch_softlockup_watchdog_sched(void) { } +static inline void touch_softlockup_watchdog(void) { } +static inline void touch_softlockup_watchdog_sync(void) { } +static inline void touch_all_softlockup_watchdogs(void) { } #endif #ifdef CONFIG_DETECT_HUNG_TASK void reset_hung_task_detector(void); #else -static inline void reset_hung_task_detector(void) -{ -} +static inline void reset_hung_task_detector(void) { } #endif /* @@ -54,12 +62,12 @@ static inline void reset_hung_task_detector(void) * 'watchdog_enabled' variable. Each lockup detector has its dedicated bit - * bit 0 for the hard lockup detector and bit 1 for the soft lockup detector. * - * 'watchdog_user_enabled', 'nmi_watchdog_enabled' and 'soft_watchdog_enabled' - * are variables that are only used as an 'interface' between the parameters - * in /proc/sys/kernel and the internal state bits in 'watchdog_enabled'. The - * 'watchdog_thresh' variable is handled differently because its value is not - * boolean, and the lockup detectors are 'suspended' while 'watchdog_thresh' - * is equal zero. + * 'watchdog_user_enabled', 'nmi_watchdog_user_enabled' and + * 'soft_watchdog_user_enabled' are variables that are only used as an + * 'interface' between the parameters in /proc/sys/kernel and the internal + * state bits in 'watchdog_enabled'. The 'watchdog_thresh' variable is + * handled differently because its value is not boolean, and the lockup + * detectors are 'suspended' while 'watchdog_thresh' is equal zero. */ #define NMI_WATCHDOG_ENABLED_BIT 0 #define SOFT_WATCHDOG_ENABLED_BIT 1 @@ -73,17 +81,41 @@ extern unsigned int hardlockup_panic; static inline void hardlockup_detector_disable(void) {} #endif +#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) +# define NMI_WATCHDOG_SYSCTL_PERM 0644 +#else +# define NMI_WATCHDOG_SYSCTL_PERM 0444 +#endif + #if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF) extern void arch_touch_nmi_watchdog(void); +extern void hardlockup_detector_perf_stop(void); +extern void hardlockup_detector_perf_restart(void); +extern void hardlockup_detector_perf_disable(void); +extern void hardlockup_detector_perf_enable(void); +extern void hardlockup_detector_perf_cleanup(void); +extern int hardlockup_detector_perf_init(void); #else -#if !defined(CONFIG_HAVE_NMI_WATCHDOG) +static inline void hardlockup_detector_perf_stop(void) { } +static inline void hardlockup_detector_perf_restart(void) { } +static inline void hardlockup_detector_perf_disable(void) { } +static inline void hardlockup_detector_perf_enable(void) { } +static inline void hardlockup_detector_perf_cleanup(void) { } +# if !defined(CONFIG_HAVE_NMI_WATCHDOG) +static inline int hardlockup_detector_perf_init(void) { return -ENODEV; } static inline void arch_touch_nmi_watchdog(void) {} +# else +static inline int hardlockup_detector_perf_init(void) { return 0; } +# endif #endif -#endif + +void watchdog_nmi_stop(void); +void watchdog_nmi_start(void); +int watchdog_nmi_probe(void); /** * touch_nmi_watchdog - restart NMI watchdog timeout. - * + * * If the architecture supports the NMI watchdog, touch_nmi_watchdog() * may be used to reset the timeout - for code which intentionally * disables interrupts for a long time. This call is stateless. @@ -153,22 +185,6 @@ static inline bool trigger_single_cpu_backtrace(int cpu) u64 hw_nmi_get_sample_period(int watchdog_thresh); #endif -#ifdef CONFIG_LOCKUP_DETECTOR -extern int nmi_watchdog_enabled; -extern int watchdog_user_enabled; -extern int watchdog_thresh; -extern unsigned long watchdog_enabled; -extern struct cpumask watchdog_cpumask; -extern unsigned long *watchdog_cpumask_bits; -extern int __read_mostly watchdog_suspended; -#ifdef CONFIG_SMP -extern int sysctl_softlockup_all_cpu_backtrace; -extern int sysctl_hardlockup_all_cpu_backtrace; -#else -#define sysctl_softlockup_all_cpu_backtrace 0 -#define sysctl_hardlockup_all_cpu_backtrace 0 -#endif - #if defined(CONFIG_HARDLOCKUP_CHECK_TIMESTAMP) && \ defined(CONFIG_HARDLOCKUP_DETECTOR) void watchdog_update_hrtimer_threshold(u64 period); @@ -176,7 +192,6 @@ void watchdog_update_hrtimer_threshold(u64 period); static inline void watchdog_update_hrtimer_threshold(u64 period) { } #endif -extern bool is_hardlockup(void); struct ctl_table; extern int proc_watchdog(struct ctl_table *, int , void __user *, size_t *, loff_t *); @@ -188,18 +203,6 @@ extern int proc_watchdog_thresh(struct ctl_table *, int , void __user *, size_t *, loff_t *); extern int proc_watchdog_cpumask(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int lockup_detector_suspend(void); -extern void lockup_detector_resume(void); -#else -static inline int lockup_detector_suspend(void) -{ - return 0; -} - -static inline void lockup_detector_resume(void) -{ -} -#endif #ifdef CONFIG_HAVE_ACPI_APEI_NMI #include <asm/nmi.h> diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 9c5cb4480806..a726f96010d5 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -346,11 +346,6 @@ struct nvme_fc_remote_port { * indicating an FC transport Aborted status. * Entrypoint is Mandatory. * - * @defer_rcv: Called by the transport to signal the LLLD that it has - * begun processing of a previously received NVME CMD IU. The LLDD - * is now free to re-use the rcv buffer associated with the - * nvmefc_tgt_fcp_req. - * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. * Value is Mandatory. Must be at least 1. @@ -806,11 +801,19 @@ struct nvmet_fc_target_port { * outstanding operation (if there was one) to complete, then will * call the fcp_req_release() callback to return the command's * exchange context back to the LLDD. + * Entrypoint is Mandatory. * * @fcp_req_release: Called by the transport to return a nvmefc_tgt_fcp_req * to the LLDD after all operations on the fcp operation are complete. * This may be due to the command completing or upon completion of * abort cleanup. + * Entrypoint is Mandatory. + * + * @defer_rcv: Called by the transport to signal the LLLD that it has + * begun processing of a previously received NVME CMD IU. The LLDD + * is now free to re-use the rcv buffer associated with the + * nvmefc_tgt_fcp_req. + * Entrypoint is Optional. * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 87723c86f136..9310ce77d8e1 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -471,12 +471,14 @@ enum nvme_opcode { * * @NVME_SGL_FMT_ADDRESS: absolute address of the data block * @NVME_SGL_FMT_OFFSET: relative offset of the in-capsule data block + * @NVME_SGL_FMT_TRANSPORT_A: transport defined format, value 0xA * @NVME_SGL_FMT_INVALIDATE: RDMA transport specific remote invalidation * request subtype */ enum { NVME_SGL_FMT_ADDRESS = 0x00, NVME_SGL_FMT_OFFSET = 0x01, + NVME_SGL_FMT_TRANSPORT_A = 0x0A, NVME_SGL_FMT_INVALIDATE = 0x0f, }; @@ -490,12 +492,16 @@ enum { * * For struct nvme_keyed_sgl_desc: * @NVME_KEY_SGL_FMT_DATA_DESC: keyed data block descriptor + * + * Transport-specific SGL types: + * @NVME_TRANSPORT_SGL_DATA_DESC: Transport SGL data dlock descriptor */ enum { NVME_SGL_FMT_DATA_DESC = 0x00, NVME_SGL_FMT_SEG_DESC = 0x02, NVME_SGL_FMT_LAST_SEG_DESC = 0x03, NVME_KEY_SGL_FMT_DATA_DESC = 0x04, + NVME_TRANSPORT_SGL_DATA_DESC = 0x05, }; struct nvme_sgl_desc { @@ -1127,19 +1133,6 @@ enum { NVME_SC_UNWRITTEN_BLOCK = 0x287, NVME_SC_DNR = 0x4000, - - - /* - * FC Transport-specific error status values for NVME commands - * - * Transport-specific status code values must be in the range 0xB0..0xBF - */ - - /* Generic FC failure - catchall */ - NVME_SC_FC_TRANSPORT_ERROR = 0x00B0, - - /* I/O failure due to FC ABTS'd */ - NVME_SC_FC_TRANSPORT_ABORTED = 0x00B1, }; struct nvme_completion { diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index e0d1946270f3..fb908e598348 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -57,7 +57,14 @@ extern const struct of_device_id of_default_bus_match_table[]; extern struct platform_device *of_device_alloc(struct device_node *np, const char *bus_id, struct device *parent); +#ifdef CONFIG_OF extern struct platform_device *of_find_device_by_node(struct device_node *np); +#else +static inline struct platform_device *of_find_device_by_node(struct device_node *np) +{ + return NULL; +} +#endif /* Platform devices and busses creation */ extern struct platform_device *of_platform_device_create(struct device_node *np, diff --git a/include/linux/once.h b/include/linux/once.h index 9c98aaa87cbc..724724918e8b 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -5,7 +5,7 @@ #include <linux/jump_label.h> bool __do_once_start(bool *done, unsigned long *flags); -void __do_once_done(bool *done, struct static_key *once_key, +void __do_once_done(bool *done, struct static_key_true *once_key, unsigned long *flags); /* Call a function exactly once. The idea of DO_ONCE() is to perform @@ -38,8 +38,8 @@ void __do_once_done(bool *done, struct static_key *once_key, ({ \ bool ___ret = false; \ static bool ___done = false; \ - static struct static_key ___once_key = STATIC_KEY_INIT_TRUE; \ - if (static_key_true(&___once_key)) { \ + static DEFINE_STATIC_KEY_TRUE(___once_key); \ + if (static_branch_unlikely(&___once_key)) { \ unsigned long ___flags; \ ___ret = __do_once_start(&___done, &___flags); \ if (unlikely(___ret)) { \ diff --git a/include/linux/pci.h b/include/linux/pci.h index f68c58a93dd0..f4f8ee5a7362 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1685,6 +1685,8 @@ static inline int pci_get_new_domain_nr(void) { return -ENOSYS; } #define dev_is_pci(d) (false) #define dev_is_pf(d) (false) +static inline bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags) +{ return false; } #endif /* CONFIG_PCI */ /* Include architecture-dependent settings and functions */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 8e22f24ded6a..79b18a20cf5d 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -806,6 +806,7 @@ struct perf_output_handle { struct bpf_perf_event_data_kern { struct pt_regs *regs; struct perf_sample_data *data; + struct perf_event *event; }; #ifdef CONFIG_CGROUP_PERF @@ -884,7 +885,8 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); -int perf_event_read_local(struct perf_event *event, u64 *value); +int perf_event_read_local(struct perf_event *event, u64 *value, + u64 *enabled, u64 *running); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); @@ -1286,7 +1288,8 @@ static inline const struct perf_event_attr *perf_event_attrs(struct perf_event * { return ERR_PTR(-EINVAL); } -static inline int perf_event_read_local(struct perf_event *event, u64 *value) +static inline int perf_event_read_local(struct perf_event *event, u64 *value, + u64 *enabled, u64 *running) { return -EINVAL; } diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index dd7a3b86bb9e..e755954d85fd 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -64,6 +64,7 @@ enum qed_ll2_roce_flavor_type { enum qed_ll2_tx_dest { QED_LL2_TX_DEST_NW, /* Light L2 TX Destination to the Network */ QED_LL2_TX_DEST_LB, /* Light L2 TX Destination to the Loopback */ + QED_LL2_TX_DEST_DROP, /* Light L2 Drop the TX packet */ QED_LL2_TX_DEST_MAX }; @@ -101,6 +102,7 @@ struct qed_ll2_comp_rx_data { void *cookie; dma_addr_t rx_buf_addr; u16 parse_flags; + u16 err_flags; u16 vlan; bool b_last_packet; u8 connection_handle; @@ -149,11 +151,16 @@ void (*qed_ll2_release_tx_packet_cb)(void *cxt, dma_addr_t first_frag_addr, bool b_last_fragment, bool b_last_packet); +typedef +void (*qed_ll2_slowpath_cb)(void *cxt, u8 connection_handle, + u32 opaque_data_0, u32 opaque_data_1); + struct qed_ll2_cbs { qed_ll2_complete_rx_packet_cb rx_comp_cb; qed_ll2_release_rx_packet_cb rx_release_cb; qed_ll2_complete_tx_packet_cb tx_comp_cb; qed_ll2_release_tx_packet_cb tx_release_cb; + qed_ll2_slowpath_cb slowpath_cb; void *cookie; }; @@ -170,6 +177,7 @@ struct qed_ll2_acquire_data_inputs { enum qed_ll2_tx_dest tx_dest; enum qed_ll2_error_handle ai_err_packet_too_big; enum qed_ll2_error_handle ai_err_no_buf; + bool secondary_queue; u8 gsi_enable; }; diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index dea59c8eec54..1251638e60d3 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -17,9 +17,11 @@ extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, long expires, u32 error); void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change, gfp_t flags); +void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, + gfp_t flags, int *new_nsid); struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned change, u32 event, - gfp_t flags); + gfp_t flags, int *new_nsid); void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags); diff --git a/include/linux/sched.h b/include/linux/sched.h index 92fb8dd5a9e4..26a7df4e558c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -65,25 +65,23 @@ struct task_group; */ /* Used in tsk->state: */ -#define TASK_RUNNING 0 -#define TASK_INTERRUPTIBLE 1 -#define TASK_UNINTERRUPTIBLE 2 -#define __TASK_STOPPED 4 -#define __TASK_TRACED 8 +#define TASK_RUNNING 0x0000 +#define TASK_INTERRUPTIBLE 0x0001 +#define TASK_UNINTERRUPTIBLE 0x0002 +#define __TASK_STOPPED 0x0004 +#define __TASK_TRACED 0x0008 /* Used in tsk->exit_state: */ -#define EXIT_DEAD 16 -#define EXIT_ZOMBIE 32 +#define EXIT_DEAD 0x0010 +#define EXIT_ZOMBIE 0x0020 #define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) /* Used in tsk->state again: */ -#define TASK_DEAD 64 -#define TASK_WAKEKILL 128 -#define TASK_WAKING 256 -#define TASK_PARKED 512 -#define TASK_NOLOAD 1024 -#define TASK_NEW 2048 -#define TASK_STATE_MAX 4096 - -#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPNn" +#define TASK_PARKED 0x0040 +#define TASK_DEAD 0x0080 +#define TASK_WAKEKILL 0x0100 +#define TASK_WAKING 0x0200 +#define TASK_NOLOAD 0x0400 +#define TASK_NEW 0x0800 +#define TASK_STATE_MAX 0x1000 /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) @@ -99,7 +97,8 @@ struct task_group; /* get_task_state(): */ #define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \ TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \ - __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD) + __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ + TASK_PARKED) #define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) @@ -1243,17 +1242,34 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) return task_pgrp_nr_ns(tsk, &init_pid_ns); } -static inline char task_state_to_char(struct task_struct *task) +#define TASK_REPORT_IDLE (TASK_REPORT + 1) +#define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) + +static inline unsigned int __get_task_state(struct task_struct *tsk) +{ + unsigned int tsk_state = READ_ONCE(tsk->state); + unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT; + + BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); + + if (tsk_state == TASK_IDLE) + state = TASK_REPORT_IDLE; + + return fls(state); +} + +static inline char __task_state_to_char(unsigned int state) { - const char stat_nam[] = TASK_STATE_TO_CHAR_STR; - unsigned long state = task->state; + static const char state_char[] = "RSDTtXZPI"; - state = state ? __ffs(state) + 1 : 0; + BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != sizeof(state_char) - 1); - /* Make sure the string lines up properly with the number of task states: */ - BUILD_BUG_ON(sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1); + return state_char[state]; +} - return state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?'; +static inline char task_state_to_char(struct task_struct *tsk) +{ + return __task_state_to_char(__get_task_state(tsk)); } /** diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 3a19c253bdb1..ae53e413fb13 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -84,6 +84,12 @@ static inline bool mmget_not_zero(struct mm_struct *mm) /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); +#ifdef CONFIG_MMU +/* same as above but performs the slow path from the async context. Can + * be called from the atomic context as well + */ +void mmput_async(struct mm_struct *); +#endif /* Grab a reference to a task's mm, if it is not already going away */ extern struct mm_struct *get_task_mm(struct task_struct *task); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f9db5539a6fb..03634ec2f918 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -489,8 +489,9 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, * the end of the header data, ie. at skb->end. */ struct skb_shared_info { - unsigned short _unused; - unsigned char nr_frags; + __u8 __unused; + __u8 meta_len; + __u8 nr_frags; __u8 tx_flags; unsigned short gso_size; /* Warning: this field is not always filled in (UFO)! */ @@ -616,6 +617,7 @@ typedef unsigned char *sk_buff_data_t; * @nf_trace: netfilter packet trace flag * @protocol: Packet protocol from driver * @destructor: Destruct function + * @tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue) * @_nfct: Associated connection, if any (with nfctinfo bits) * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c * @skb_iif: ifindex of device we arrived on @@ -685,8 +687,14 @@ struct sk_buff { */ char cb[48] __aligned(8); - unsigned long _skb_refdst; - void (*destructor)(struct sk_buff *skb); + union { + struct { + unsigned long _skb_refdst; + void (*destructor)(struct sk_buff *skb); + }; + struct list_head tcp_tsorted_anchor; + }; + #ifdef CONFIG_XFRM struct sec_path *sp; #endif @@ -771,6 +779,7 @@ struct sk_buff { __u8 remcsum_offload:1; #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; + __u8 offload_mr_fwd_mark:1; #endif #ifdef CONFIG_NET_CLS_ACT __u8 tc_skip_classify:1; @@ -3149,6 +3158,12 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len) return __skb_grow(skb, len); } +#define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode) +#define skb_rb_first(root) rb_to_skb(rb_first(root)) +#define skb_rb_last(root) rb_to_skb(rb_last(root)) +#define skb_rb_next(skb) rb_to_skb(rb_next(&(skb)->rbnode)) +#define skb_rb_prev(skb) rb_to_skb(rb_prev(&(skb)->rbnode)) + #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ skb != (struct sk_buff *)(queue); \ @@ -3163,6 +3178,18 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len) for (; skb != (struct sk_buff *)(queue); \ skb = skb->next) +#define skb_rbtree_walk(skb, root) \ + for (skb = skb_rb_first(root); skb != NULL; \ + skb = skb_rb_next(skb)) + +#define skb_rbtree_walk_from(skb) \ + for (; skb != NULL; \ + skb = skb_rb_next(skb)) + +#define skb_rbtree_walk_from_safe(skb, tmp) \ + for (; tmp = skb ? skb_rb_next(skb) : NULL, (skb != NULL); \ + skb = tmp) + #define skb_queue_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ @@ -3400,6 +3427,69 @@ static inline ktime_t net_invalid_timestamp(void) return 0; } +static inline u8 skb_metadata_len(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->meta_len; +} + +static inline void *skb_metadata_end(const struct sk_buff *skb) +{ + return skb_mac_header(skb); +} + +static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, + const struct sk_buff *skb_b, + u8 meta_len) +{ + const void *a = skb_metadata_end(skb_a); + const void *b = skb_metadata_end(skb_b); + /* Using more efficient varaiant than plain call to memcmp(). */ +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 + u64 diffs = 0; + + switch (meta_len) { +#define __it(x, op) (x -= sizeof(u##op)) +#define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) + case 32: diffs |= __it_diff(a, b, 64); + case 24: diffs |= __it_diff(a, b, 64); + case 16: diffs |= __it_diff(a, b, 64); + case 8: diffs |= __it_diff(a, b, 64); + break; + case 28: diffs |= __it_diff(a, b, 64); + case 20: diffs |= __it_diff(a, b, 64); + case 12: diffs |= __it_diff(a, b, 64); + case 4: diffs |= __it_diff(a, b, 32); + break; + } + return diffs; +#else + return memcmp(a - meta_len, b - meta_len, meta_len); +#endif +} + +static inline bool skb_metadata_differs(const struct sk_buff *skb_a, + const struct sk_buff *skb_b) +{ + u8 len_a = skb_metadata_len(skb_a); + u8 len_b = skb_metadata_len(skb_b); + + if (!(len_a | len_b)) + return false; + + return len_a != len_b ? + true : __skb_metadata_differs(skb_a, skb_b, len_a); +} + +static inline void skb_metadata_set(struct sk_buff *skb, u8 meta_len) +{ + skb_shinfo(skb)->meta_len = meta_len; +} + +static inline void skb_metadata_clear(struct sk_buff *skb) +{ + skb_metadata_set(skb, 0); +} + struct sk_buff *skb_clone_sk(struct sk_buff *skb); #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h index 12910cf19869..c149aa7bedf3 100644 --- a/include/linux/smpboot.h +++ b/include/linux/smpboot.h @@ -55,7 +55,7 @@ smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) } void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread); -int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *); +void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, + const struct cpumask *); #endif diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 95606a2d556f..a78186d826d7 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -221,21 +221,25 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) } \ static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) -#ifdef TIF_FSCHECK /* * Called before coming back to user-mode. Returning to user-mode with an * address limit different than USER_DS can allow to overwrite kernel memory. */ static inline void addr_limit_user_check(void) { - +#ifdef TIF_FSCHECK if (!test_thread_flag(TIF_FSCHECK)) return; +#endif - BUG_ON(!segment_eq(get_fs(), USER_DS)); + if (CHECK_DATA_CORRUPTION(!segment_eq(get_fs(), USER_DS), + "Invalid address limit on user-mode return")) + force_sig(SIGKILL, current); + +#ifdef TIF_FSCHECK clear_thread_flag(TIF_FSCHECK); -} #endif +} asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special, qid_t id, void __user *addr); diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 4aa40ef02d32..1d2c44e09e31 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -191,6 +191,7 @@ struct tcp_sock { u32 tsoffset; /* timestamp offset */ struct list_head tsq_node; /* anchor in tsq_tasklet.head list */ + struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */ u32 snd_wl1; /* Sequence for window update */ u32 snd_wnd; /* The window we expect to receive */ diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h new file mode 100644 index 000000000000..7b69853188b1 --- /dev/null +++ b/include/linux/thunderbolt.h @@ -0,0 +1,598 @@ +/* + * Thunderbolt service API + * + * Copyright (C) 2014 Andreas Noever <andreas.noever@gmail.com> + * Copyright (C) 2017, Intel Corporation + * Authors: Michael Jamet <michael.jamet@intel.com> + * Mika Westerberg <mika.westerberg@linux.intel.com> + * + * 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. + */ + +#ifndef THUNDERBOLT_H_ +#define THUNDERBOLT_H_ + +#include <linux/device.h> +#include <linux/idr.h> +#include <linux/list.h> +#include <linux/mutex.h> +#include <linux/mod_devicetable.h> +#include <linux/pci.h> +#include <linux/uuid.h> +#include <linux/workqueue.h> + +enum tb_cfg_pkg_type { + TB_CFG_PKG_READ = 1, + TB_CFG_PKG_WRITE = 2, + TB_CFG_PKG_ERROR = 3, + TB_CFG_PKG_NOTIFY_ACK = 4, + TB_CFG_PKG_EVENT = 5, + TB_CFG_PKG_XDOMAIN_REQ = 6, + TB_CFG_PKG_XDOMAIN_RESP = 7, + TB_CFG_PKG_OVERRIDE = 8, + TB_CFG_PKG_RESET = 9, + TB_CFG_PKG_ICM_EVENT = 10, + TB_CFG_PKG_ICM_CMD = 11, + TB_CFG_PKG_ICM_RESP = 12, + TB_CFG_PKG_PREPARE_TO_SLEEP = 13, +}; + +/** + * enum tb_security_level - Thunderbolt security level + * @TB_SECURITY_NONE: No security, legacy mode + * @TB_SECURITY_USER: User approval required at minimum + * @TB_SECURITY_SECURE: One time saved key required at minimum + * @TB_SECURITY_DPONLY: Only tunnel Display port (and USB) + */ +enum tb_security_level { + TB_SECURITY_NONE, + TB_SECURITY_USER, + TB_SECURITY_SECURE, + TB_SECURITY_DPONLY, +}; + +/** + * struct tb - main thunderbolt bus structure + * @dev: Domain device + * @lock: Big lock. Must be held when accessing any struct + * tb_switch / struct tb_port. + * @nhi: Pointer to the NHI structure + * @ctl: Control channel for this domain + * @wq: Ordered workqueue for all domain specific work + * @root_switch: Root switch of this domain + * @cm_ops: Connection manager specific operations vector + * @index: Linux assigned domain number + * @security_level: Current security level + * @privdata: Private connection manager specific data + */ +struct tb { + struct device dev; + struct mutex lock; + struct tb_nhi *nhi; + struct tb_ctl *ctl; + struct workqueue_struct *wq; + struct tb_switch *root_switch; + const struct tb_cm_ops *cm_ops; + int index; + enum tb_security_level security_level; + unsigned long privdata[0]; +}; + +extern struct bus_type tb_bus_type; +extern struct device_type tb_service_type; +extern struct device_type tb_xdomain_type; + +#define TB_LINKS_PER_PHY_PORT 2 + +static inline unsigned int tb_phy_port_from_link(unsigned int link) +{ + return (link - 1) / TB_LINKS_PER_PHY_PORT; +} + +/** + * struct tb_property_dir - XDomain property directory + * @uuid: Directory UUID or %NULL if root directory + * @properties: List of properties in this directory + * + * User needs to provide serialization if needed. + */ +struct tb_property_dir { + const uuid_t *uuid; + struct list_head properties; +}; + +enum tb_property_type { + TB_PROPERTY_TYPE_UNKNOWN = 0x00, + TB_PROPERTY_TYPE_DIRECTORY = 0x44, + TB_PROPERTY_TYPE_DATA = 0x64, + TB_PROPERTY_TYPE_TEXT = 0x74, + TB_PROPERTY_TYPE_VALUE = 0x76, +}; + +#define TB_PROPERTY_KEY_SIZE 8 + +/** + * struct tb_property - XDomain property + * @list: Used to link properties together in a directory + * @key: Key for the property (always terminated). + * @type: Type of the property + * @length: Length of the property data in dwords + * @value: Property value + * + * Users use @type to determine which field in @value is filled. + */ +struct tb_property { + struct list_head list; + char key[TB_PROPERTY_KEY_SIZE + 1]; + enum tb_property_type type; + size_t length; + union { + struct tb_property_dir *dir; + u8 *data; + char *text; + u32 immediate; + } value; +}; + +struct tb_property_dir *tb_property_parse_dir(const u32 *block, + size_t block_len); +ssize_t tb_property_format_dir(const struct tb_property_dir *dir, u32 *block, + size_t block_len); +struct tb_property_dir *tb_property_create_dir(const uuid_t *uuid); +void tb_property_free_dir(struct tb_property_dir *dir); +int tb_property_add_immediate(struct tb_property_dir *parent, const char *key, + u32 value); +int tb_property_add_data(struct tb_property_dir *parent, const char *key, + const void *buf, size_t buflen); +int tb_property_add_text(struct tb_property_dir *parent, const char *key, + const char *text); +int tb_property_add_dir(struct tb_property_dir *parent, const char *key, + struct tb_property_dir *dir); +void tb_property_remove(struct tb_property *tb_property); +struct tb_property *tb_property_find(struct tb_property_dir *dir, + const char *key, enum tb_property_type type); +struct tb_property *tb_property_get_next(struct tb_property_dir *dir, + struct tb_property *prev); + +#define tb_property_for_each(dir, property) \ + for (property = tb_property_get_next(dir, NULL); \ + property; \ + property = tb_property_get_next(dir, property)) + +int tb_register_property_dir(const char *key, struct tb_property_dir *dir); +void tb_unregister_property_dir(const char *key, struct tb_property_dir *dir); + +/** + * struct tb_xdomain - Cross-domain (XDomain) connection + * @dev: XDomain device + * @tb: Pointer to the domain + * @remote_uuid: UUID of the remote domain (host) + * @local_uuid: Cached local UUID + * @route: Route string the other domain can be reached + * @vendor: Vendor ID of the remote domain + * @device: Device ID of the demote domain + * @lock: Lock to serialize access to the following fields of this structure + * @vendor_name: Name of the vendor (or %NULL if not known) + * @device_name: Name of the device (or %NULL if not known) + * @is_unplugged: The XDomain is unplugged + * @resume: The XDomain is being resumed + * @transmit_path: HopID which the remote end expects us to transmit + * @transmit_ring: Local ring (hop) where outgoing packets are pushed + * @receive_path: HopID which we expect the remote end to transmit + * @receive_ring: Local ring (hop) where incoming packets arrive + * @service_ids: Used to generate IDs for the services + * @properties: Properties exported by the remote domain + * @property_block_gen: Generation of @properties + * @properties_lock: Lock protecting @properties. + * @get_properties_work: Work used to get remote domain properties + * @properties_retries: Number of times left to read properties + * @properties_changed_work: Work used to notify the remote domain that + * our properties have changed + * @properties_changed_retries: Number of times left to send properties + * changed notification + * @link: Root switch link the remote domain is connected (ICM only) + * @depth: Depth in the chain the remote domain is connected (ICM only) + * + * This structure represents connection across two domains (hosts). + * Each XDomain contains zero or more services which are exposed as + * &struct tb_service objects. + * + * Service drivers may access this structure if they need to enumerate + * non-standard properties but they need hold @lock when doing so + * because properties can be changed asynchronously in response to + * changes in the remote domain. + */ +struct tb_xdomain { + struct device dev; + struct tb *tb; + uuid_t *remote_uuid; + const uuid_t *local_uuid; + u64 route; + u16 vendor; + u16 device; + struct mutex lock; + const char *vendor_name; + const char *device_name; + bool is_unplugged; + bool resume; + u16 transmit_path; + u16 transmit_ring; + u16 receive_path; + u16 receive_ring; + struct ida service_ids; + struct tb_property_dir *properties; + u32 property_block_gen; + struct delayed_work get_properties_work; + int properties_retries; + struct delayed_work properties_changed_work; + int properties_changed_retries; + u8 link; + u8 depth; +}; + +int tb_xdomain_enable_paths(struct tb_xdomain *xd, u16 transmit_path, + u16 transmit_ring, u16 receive_path, + u16 receive_ring); +int tb_xdomain_disable_paths(struct tb_xdomain *xd); +struct tb_xdomain *tb_xdomain_find_by_uuid(struct tb *tb, const uuid_t *uuid); + +static inline struct tb_xdomain * +tb_xdomain_find_by_uuid_locked(struct tb *tb, const uuid_t *uuid) +{ + struct tb_xdomain *xd; + + mutex_lock(&tb->lock); + xd = tb_xdomain_find_by_uuid(tb, uuid); + mutex_unlock(&tb->lock); + + return xd; +} + +static inline struct tb_xdomain *tb_xdomain_get(struct tb_xdomain *xd) +{ + if (xd) + get_device(&xd->dev); + return xd; +} + +static inline void tb_xdomain_put(struct tb_xdomain *xd) +{ + if (xd) + put_device(&xd->dev); +} + +static inline bool tb_is_xdomain(const struct device *dev) +{ + return dev->type == &tb_xdomain_type; +} + +static inline struct tb_xdomain *tb_to_xdomain(struct device *dev) +{ + if (tb_is_xdomain(dev)) + return container_of(dev, struct tb_xdomain, dev); + return NULL; +} + +int tb_xdomain_response(struct tb_xdomain *xd, const void *response, + size_t size, enum tb_cfg_pkg_type type); +int tb_xdomain_request(struct tb_xdomain *xd, const void *request, + size_t request_size, enum tb_cfg_pkg_type request_type, + void *response, size_t response_size, + enum tb_cfg_pkg_type response_type, + unsigned int timeout_msec); + +/** + * tb_protocol_handler - Protocol specific handler + * @uuid: XDomain messages with this UUID are dispatched to this handler + * @callback: Callback called with the XDomain message. Returning %1 + * here tells the XDomain core that the message was handled + * by this handler and should not be forwared to other + * handlers. + * @data: Data passed with the callback + * @list: Handlers are linked using this + * + * Thunderbolt services can hook into incoming XDomain requests by + * registering protocol handler. Only limitation is that the XDomain + * discovery protocol UUID cannot be registered since it is handled by + * the core XDomain code. + * + * The @callback must check that the message is really directed to the + * service the driver implements. + */ +struct tb_protocol_handler { + const uuid_t *uuid; + int (*callback)(const void *buf, size_t size, void *data); + void *data; + struct list_head list; +}; + +int tb_register_protocol_handler(struct tb_protocol_handler *handler); +void tb_unregister_protocol_handler(struct tb_protocol_handler *handler); + +/** + * struct tb_service - Thunderbolt service + * @dev: XDomain device + * @id: ID of the service (shown in sysfs) + * @key: Protocol key from the properties directory + * @prtcid: Protocol ID from the properties directory + * @prtcvers: Protocol version from the properties directory + * @prtcrevs: Protocol software revision from the properties directory + * @prtcstns: Protocol settings mask from the properties directory + * + * Each domain exposes set of services it supports as collection of + * properties. For each service there will be one corresponding + * &struct tb_service. Service drivers are bound to these. + */ +struct tb_service { + struct device dev; + int id; + const char *key; + u32 prtcid; + u32 prtcvers; + u32 prtcrevs; + u32 prtcstns; +}; + +static inline struct tb_service *tb_service_get(struct tb_service *svc) +{ + if (svc) + get_device(&svc->dev); + return svc; +} + +static inline void tb_service_put(struct tb_service *svc) +{ + if (svc) + put_device(&svc->dev); +} + +static inline bool tb_is_service(const struct device *dev) +{ + return dev->type == &tb_service_type; +} + +static inline struct tb_service *tb_to_service(struct device *dev) +{ + if (tb_is_service(dev)) + return container_of(dev, struct tb_service, dev); + return NULL; +} + +/** + * tb_service_driver - Thunderbolt service driver + * @driver: Driver structure + * @probe: Called when the driver is probed + * @remove: Called when the driver is removed (optional) + * @shutdown: Called at shutdown time to stop the service (optional) + * @id_table: Table of service identifiers the driver supports + */ +struct tb_service_driver { + struct device_driver driver; + int (*probe)(struct tb_service *svc, const struct tb_service_id *id); + void (*remove)(struct tb_service *svc); + void (*shutdown)(struct tb_service *svc); + const struct tb_service_id *id_table; +}; + +#define TB_SERVICE(key, id) \ + .match_flags = TBSVC_MATCH_PROTOCOL_KEY | \ + TBSVC_MATCH_PROTOCOL_ID, \ + .protocol_key = (key), \ + .protocol_id = (id) + +int tb_register_service_driver(struct tb_service_driver *drv); +void tb_unregister_service_driver(struct tb_service_driver *drv); + +static inline void *tb_service_get_drvdata(const struct tb_service *svc) +{ + return dev_get_drvdata(&svc->dev); +} + +static inline void tb_service_set_drvdata(struct tb_service *svc, void *data) +{ + dev_set_drvdata(&svc->dev, data); +} + +static inline struct tb_xdomain *tb_service_parent(struct tb_service *svc) +{ + return tb_to_xdomain(svc->dev.parent); +} + +/** + * struct tb_nhi - thunderbolt native host interface + * @lock: Must be held during ring creation/destruction. Is acquired by + * interrupt_work when dispatching interrupts to individual rings. + * @pdev: Pointer to the PCI device + * @iobase: MMIO space of the NHI + * @tx_rings: All Tx rings available on this host controller + * @rx_rings: All Rx rings available on this host controller + * @msix_ida: Used to allocate MSI-X vectors for rings + * @going_away: The host controller device is about to disappear so when + * this flag is set, avoid touching the hardware anymore. + * @interrupt_work: Work scheduled to handle ring interrupt when no + * MSI-X is used. + * @hop_count: Number of rings (end point hops) supported by NHI. + */ +struct tb_nhi { + spinlock_t lock; + struct pci_dev *pdev; + void __iomem *iobase; + struct tb_ring **tx_rings; + struct tb_ring **rx_rings; + struct ida msix_ida; + bool going_away; + struct work_struct interrupt_work; + u32 hop_count; +}; + +/** + * struct tb_ring - thunderbolt TX or RX ring associated with a NHI + * @lock: Lock serializing actions to this ring. Must be acquired after + * nhi->lock. + * @nhi: Pointer to the native host controller interface + * @size: Size of the ring + * @hop: Hop (DMA channel) associated with this ring + * @head: Head of the ring (write next descriptor here) + * @tail: Tail of the ring (complete next descriptor here) + * @descriptors: Allocated descriptors for this ring + * @queue: Queue holding frames to be transferred over this ring + * @in_flight: Queue holding frames that are currently in flight + * @work: Interrupt work structure + * @is_tx: Is the ring Tx or Rx + * @running: Is the ring running + * @irq: MSI-X irq number if the ring uses MSI-X. %0 otherwise. + * @vector: MSI-X vector number the ring uses (only set if @irq is > 0) + * @flags: Ring specific flags + * @sof_mask: Bit mask used to detect start of frame PDF + * @eof_mask: Bit mask used to detect end of frame PDF + * @start_poll: Called when ring interrupt is triggered to start + * polling. Passing %NULL keeps the ring in interrupt mode. + * @poll_data: Data passed to @start_poll + */ +struct tb_ring { + spinlock_t lock; + struct tb_nhi *nhi; + int size; + int hop; + int head; + int tail; + struct ring_desc *descriptors; + dma_addr_t descriptors_dma; + struct list_head queue; + struct list_head in_flight; + struct work_struct work; + bool is_tx:1; + bool running:1; + int irq; + u8 vector; + unsigned int flags; + u16 sof_mask; + u16 eof_mask; + void (*start_poll)(void *data); + void *poll_data; +}; + +/* Leave ring interrupt enabled on suspend */ +#define RING_FLAG_NO_SUSPEND BIT(0) +/* Configure the ring to be in frame mode */ +#define RING_FLAG_FRAME BIT(1) +/* Enable end-to-end flow control */ +#define RING_FLAG_E2E BIT(2) + +struct ring_frame; +typedef void (*ring_cb)(struct tb_ring *, struct ring_frame *, bool canceled); + +/** + * enum ring_desc_flags - Flags for DMA ring descriptor + * %RING_DESC_ISOCH: Enable isonchronous DMA (Tx only) + * %RING_DESC_CRC_ERROR: In frame mode CRC check failed for the frame (Rx only) + * %RING_DESC_COMPLETED: Descriptor completed (set by NHI) + * %RING_DESC_POSTED: Always set this + * %RING_DESC_BUFFER_OVERRUN: RX buffer overrun + * %RING_DESC_INTERRUPT: Request an interrupt on completion + */ +enum ring_desc_flags { + RING_DESC_ISOCH = 0x1, + RING_DESC_CRC_ERROR = 0x1, + RING_DESC_COMPLETED = 0x2, + RING_DESC_POSTED = 0x4, + RING_DESC_BUFFER_OVERRUN = 0x04, + RING_DESC_INTERRUPT = 0x8, +}; + +/** + * struct ring_frame - For use with ring_rx/ring_tx + * @buffer_phy: DMA mapped address of the frame + * @callback: Callback called when the frame is finished (optional) + * @list: Frame is linked to a queue using this + * @size: Size of the frame in bytes (%0 means %4096) + * @flags: Flags for the frame (see &enum ring_desc_flags) + * @eof: End of frame protocol defined field + * @sof: Start of frame protocol defined field + */ +struct ring_frame { + dma_addr_t buffer_phy; + ring_cb callback; + struct list_head list; + u32 size:12; + u32 flags:12; + u32 eof:4; + u32 sof:4; +}; + +/* Minimum size for ring_rx */ +#define TB_FRAME_SIZE 0x100 + +struct tb_ring *tb_ring_alloc_tx(struct tb_nhi *nhi, int hop, int size, + unsigned int flags); +struct tb_ring *tb_ring_alloc_rx(struct tb_nhi *nhi, int hop, int size, + unsigned int flags, u16 sof_mask, u16 eof_mask, + void (*start_poll)(void *), void *poll_data); +void tb_ring_start(struct tb_ring *ring); +void tb_ring_stop(struct tb_ring *ring); +void tb_ring_free(struct tb_ring *ring); + +int __tb_ring_enqueue(struct tb_ring *ring, struct ring_frame *frame); + +/** + * tb_ring_rx() - enqueue a frame on an RX ring + * @ring: Ring to enqueue the frame + * @frame: Frame to enqueue + * + * @frame->buffer, @frame->buffer_phy have to be set. The buffer must + * contain at least %TB_FRAME_SIZE bytes. + * + * @frame->callback will be invoked with @frame->size, @frame->flags, + * @frame->eof, @frame->sof set once the frame has been received. + * + * If ring_stop() is called after the packet has been enqueued + * @frame->callback will be called with canceled set to true. + * + * Return: Returns %-ESHUTDOWN if ring_stop has been called. Zero otherwise. + */ +static inline int tb_ring_rx(struct tb_ring *ring, struct ring_frame *frame) +{ + WARN_ON(ring->is_tx); + return __tb_ring_enqueue(ring, frame); +} + +/** + * tb_ring_tx() - enqueue a frame on an TX ring + * @ring: Ring the enqueue the frame + * @frame: Frame to enqueue + * + * @frame->buffer, @frame->buffer_phy, @frame->size, @frame->eof and + * @frame->sof have to be set. + * + * @frame->callback will be invoked with once the frame has been transmitted. + * + * If ring_stop() is called after the packet has been enqueued @frame->callback + * will be called with canceled set to true. + * + * Return: Returns %-ESHUTDOWN if ring_stop has been called. Zero otherwise. + */ +static inline int tb_ring_tx(struct tb_ring *ring, struct ring_frame *frame) +{ + WARN_ON(!ring->is_tx); + return __tb_ring_enqueue(ring, frame); +} + +/* Used only when the ring is in polling mode */ +struct ring_frame *tb_ring_poll(struct tb_ring *ring); +void tb_ring_poll_complete(struct tb_ring *ring); + +/** + * tb_ring_dma_device() - Return device used for DMA mapping + * @ring: Ring whose DMA device is retrieved + * + * Use this function when you are mapping DMA for buffers that are + * passed to the ring for sending/receiving. + */ +static inline struct device *tb_ring_dma_device(struct tb_ring *ring) +{ + return &ring->nhi->pdev->dev; +} + +#endif /* THUNDERBOLT_H_ */ diff --git a/include/linux/timer.h b/include/linux/timer.h index e6789b8757d5..6383c528b148 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -168,6 +168,20 @@ static inline void init_timer_on_stack_key(struct timer_list *timer, #define setup_pinned_deferrable_timer_on_stack(timer, fn, data) \ __setup_timer_on_stack((timer), (fn), (data), TIMER_DEFERRABLE | TIMER_PINNED) +#define TIMER_DATA_TYPE unsigned long +#define TIMER_FUNC_TYPE void (*)(TIMER_DATA_TYPE) + +static inline void timer_setup(struct timer_list *timer, + void (*callback)(struct timer_list *), + unsigned int flags) +{ + __setup_timer(timer, (TIMER_FUNC_TYPE)callback, + (TIMER_DATA_TYPE)timer, flags); +} + +#define from_timer(var, callback_timer, timer_fieldname) \ + container_of(callback_timer, typeof(*var), timer_fieldname) + /** * timer_pending - is a timer pending? * @timer: the timer in question |
