diff options
Diffstat (limited to 'include/linux')
40 files changed, 821 insertions, 219 deletions
diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index 4bbb5f1c8b5b..48ea093ff04c 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -56,6 +56,19 @@ }) /** + * FIELD_MAX() - produce the maximum value representable by a field + * @_mask: shifted mask defining the field's length and position + * + * FIELD_MAX() returns the maximum value that can be held in the field + * specified by @_mask. + */ +#define FIELD_MAX(_mask) \ + ({ \ + __BF_FIELD_CHECK(_mask, 0ULL, 0ULL, "FIELD_MAX: "); \ + (typeof(_mask))((_mask) >> __bf_shf(_mask)); \ + }) + +/** * FIELD_FIT() - check if value fits in the field * @_mask: shifted mask defining the field's length and position * @_val: value to test against the field @@ -110,6 +123,7 @@ static __always_inline u64 field_mask(u64 field) { return field / field_multiplier(field); } +#define field_max(field) ((typeof(field))field_mask(field)) #define ____MAKE_OP(type,base,to,from) \ static __always_inline __##type type##_encode_bits(base v, base field) \ { \ diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index a11d5b7dbbf3..a7cd5c7a2509 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -36,7 +36,7 @@ struct bpf_cgroup_storage_map; struct bpf_storage_buffer { struct rcu_head rcu; - char data[0]; + char data[]; }; struct bpf_cgroup_storage { diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 49b1a70e12c8..bdb981c204fa 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -18,6 +18,7 @@ #include <linux/refcount.h> #include <linux/mutex.h> #include <linux/module.h> +#include <linux/kallsyms.h> struct bpf_verifier_env; struct bpf_verifier_log; @@ -433,6 +434,16 @@ struct btf_func_model { */ #define BPF_TRAMP_F_SKIP_FRAME BIT(2) +/* 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 + */ +#define BPF_MAX_TRAMP_PROGS 40 + +struct bpf_tramp_progs { + struct bpf_prog *progs[BPF_MAX_TRAMP_PROGS]; + int nr_progs; +}; + /* Different use cases for BPF trampoline: * 1. replace nop at the function entry (kprobe equivalent) * flags = BPF_TRAMP_F_RESTORE_REGS @@ -455,16 +466,25 @@ struct btf_func_model { */ int arch_prepare_bpf_trampoline(void *image, void *image_end, const struct btf_func_model *m, u32 flags, - struct bpf_prog **fentry_progs, int fentry_cnt, - struct bpf_prog **fexit_progs, int fexit_cnt, + struct bpf_tramp_progs *tprogs, void *orig_call); /* these two functions are called from generated trampoline */ u64 notrace __bpf_prog_enter(void); void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); +struct bpf_ksym { + unsigned long start; + unsigned long end; + char name[KSYM_NAME_LEN]; + struct list_head lnode; + struct latch_tree_node tnode; + bool prog; +}; + enum bpf_tramp_prog_type { BPF_TRAMP_FENTRY, BPF_TRAMP_FEXIT, + BPF_TRAMP_MODIFY_RETURN, BPF_TRAMP_MAX, BPF_TRAMP_REPLACE, /* more than MAX */ }; @@ -493,6 +513,7 @@ struct bpf_trampoline { /* Executable image of trampoline */ void *image; u64 selector; + struct bpf_ksym ksym; }; #define BPF_DISPATCHER_MAX 48 /* Fits in 2048B */ @@ -510,9 +531,10 @@ struct bpf_dispatcher { int num_progs; void *image; u32 image_off; + struct bpf_ksym ksym; }; -static __always_inline unsigned int bpf_dispatcher_nopfunc( +static __always_inline unsigned int bpf_dispatcher_nop_func( const void *ctx, const struct bpf_insn *insnsi, unsigned int (*bpf_func)(const void *, @@ -525,17 +547,21 @@ struct bpf_trampoline *bpf_trampoline_lookup(u64 key); int bpf_trampoline_link_prog(struct bpf_prog *prog); int bpf_trampoline_unlink_prog(struct bpf_prog *prog); void bpf_trampoline_put(struct bpf_trampoline *tr); -#define BPF_DISPATCHER_INIT(name) { \ - .mutex = __MUTEX_INITIALIZER(name.mutex), \ - .func = &name##func, \ - .progs = {}, \ - .num_progs = 0, \ - .image = NULL, \ - .image_off = 0 \ +#define BPF_DISPATCHER_INIT(_name) { \ + .mutex = __MUTEX_INITIALIZER(_name.mutex), \ + .func = &_name##_func, \ + .progs = {}, \ + .num_progs = 0, \ + .image = NULL, \ + .image_off = 0, \ + .ksym = { \ + .name = #_name, \ + .lnode = LIST_HEAD_INIT(_name.ksym.lnode), \ + }, \ } #define DEFINE_BPF_DISPATCHER(name) \ - noinline unsigned int name##func( \ + noinline unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ unsigned int (*bpf_func)(const void *, \ @@ -543,26 +569,26 @@ void bpf_trampoline_put(struct bpf_trampoline *tr); { \ return bpf_func(ctx, insnsi); \ } \ - EXPORT_SYMBOL(name##func); \ - struct bpf_dispatcher name = BPF_DISPATCHER_INIT(name); + EXPORT_SYMBOL(bpf_dispatcher_##name##_func); \ + struct bpf_dispatcher bpf_dispatcher_##name = \ + BPF_DISPATCHER_INIT(bpf_dispatcher_##name); #define DECLARE_BPF_DISPATCHER(name) \ - unsigned int name##func( \ + unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ unsigned int (*bpf_func)(const void *, \ const struct bpf_insn *)); \ - extern struct bpf_dispatcher name; -#define BPF_DISPATCHER_FUNC(name) name##func -#define BPF_DISPATCHER_PTR(name) (&name) + extern struct bpf_dispatcher bpf_dispatcher_##name; +#define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_##name##_func +#define BPF_DISPATCHER_PTR(name) (&bpf_dispatcher_##name) void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to); -struct bpf_image { - struct latch_tree_node tnode; - unsigned char data[]; -}; -#define BPF_IMAGE_SIZE (PAGE_SIZE - sizeof(struct bpf_image)) -bool is_bpf_image_address(unsigned long address); -void *bpf_image_alloc(void); +/* Called only from JIT-enabled code, so there's no need for stubs. */ +void *bpf_jit_alloc_exec_page(void); +void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym); +void bpf_image_ksym_del(struct bpf_ksym *ksym); +void bpf_ksym_add(struct bpf_ksym *ksym); +void bpf_ksym_del(struct bpf_ksym *ksym); #else static inline struct bpf_trampoline *bpf_trampoline_lookup(u64 key) { @@ -579,7 +605,7 @@ static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog) static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {} #define DEFINE_BPF_DISPATCHER(name) #define DECLARE_BPF_DISPATCHER(name) -#define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_nopfunc +#define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_nop_func #define BPF_DISPATCHER_PTR(name) NULL static inline void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, @@ -640,8 +666,7 @@ struct bpf_prog_aux { void *jit_data; /* JIT specific data. arch dependent */ struct bpf_jit_poke_descriptor *poke_tab; u32 size_poke_tab; - struct latch_tree_node ksym_tnode; - struct list_head ksym_lnode; + struct bpf_ksym ksym; const struct bpf_prog_ops *ops; struct bpf_map **used_maps; struct bpf_prog *prog; @@ -859,7 +884,7 @@ struct bpf_prog_array_item { struct bpf_prog_array { struct rcu_head rcu; - struct bpf_prog_array_item items[0]; + struct bpf_prog_array_item items[]; }; struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); @@ -885,7 +910,7 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *_prog; \ struct bpf_prog_array *_array; \ u32 _ret = 1; \ - preempt_disable(); \ + migrate_disable(); \ rcu_read_lock(); \ _array = rcu_dereference(array); \ if (unlikely(check_non_null && !_array))\ @@ -898,7 +923,7 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, } \ _out: \ rcu_read_unlock(); \ - preempt_enable(); \ + migrate_enable(); \ _ret; \ }) @@ -932,7 +957,7 @@ _out: \ u32 ret; \ u32 _ret = 1; \ u32 _cn = 0; \ - preempt_disable(); \ + migrate_disable(); \ rcu_read_lock(); \ _array = rcu_dereference(array); \ _item = &_array->items[0]; \ @@ -944,7 +969,7 @@ _out: \ _item++; \ } \ rcu_read_unlock(); \ - preempt_enable(); \ + migrate_enable(); \ if (_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ else \ @@ -961,6 +986,36 @@ _out: \ #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); +/* + * Block execution of BPF programs attached to instrumentation (perf, + * kprobes, tracepoints) to prevent deadlocks on map operations as any of + * these events can happen inside a region which holds a map bucket lock + * and can deadlock on it. + * + * Use the preemption safe inc/dec variants on RT because migrate disable + * is preemptible on RT and preemption in the middle of the RMW operation + * might lead to inconsistent state. Use the raw variants for non RT + * kernels as migrate_disable() maps to preempt_disable() so the slightly + * more expensive save operation can be avoided. + */ +static inline void bpf_disable_instrumentation(void) +{ + migrate_disable(); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + this_cpu_inc(bpf_prog_active); + else + __this_cpu_inc(bpf_prog_active); +} + +static inline void bpf_enable_instrumentation(void) +{ + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + this_cpu_dec(bpf_prog_active); + else + __this_cpu_dec(bpf_prog_active); + migrate_enable(); +} + extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; @@ -993,6 +1048,7 @@ void __bpf_free_used_maps(struct bpf_prog_aux *aux, void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock); void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); +struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); void bpf_map_inc(struct bpf_map *map); @@ -1025,6 +1081,21 @@ extern int sysctl_unprivileged_bpf_disabled; int bpf_map_new_fd(struct bpf_map *map, int flags); int bpf_prog_new_fd(struct bpf_prog *prog); +struct bpf_link; + +struct bpf_link_ops { + void (*release)(struct bpf_link *link); + void (*dealloc)(struct bpf_link *link); +}; + +void bpf_link_init(struct bpf_link *link, const struct bpf_link_ops *ops, + struct bpf_prog *prog); +void bpf_link_inc(struct bpf_link *link); +void bpf_link_put(struct bpf_link *link); +int bpf_link_new_fd(struct bpf_link *link); +struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd); +struct bpf_link *bpf_link_get_from_fd(u32 ufd); + int bpf_obj_pin_user(u32 ufd, const char __user *pathname); int bpf_obj_get_user(const char __user *pathname, int flags); @@ -1102,6 +1173,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); +int bpf_prog_test_run_tracing(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr); int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); @@ -1259,6 +1333,13 @@ static inline int bpf_prog_test_run_skb(struct bpf_prog *prog, return -ENOTSUPP; } +static inline int bpf_prog_test_run_tracing(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + return -ENOTSUPP; +} + static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) @@ -1355,6 +1436,8 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map) #if defined(CONFIG_BPF_STREAM_PARSER) int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which); int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); +void sock_map_unhash(struct sock *sk); +void sock_map_close(struct sock *sk, long timeout); #else static inline int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which) @@ -1367,7 +1450,7 @@ static inline int sock_map_get_from_fd(const union bpf_attr *attr, { return -EINVAL; } -#endif +#endif /* CONFIG_BPF_STREAM_PARSER */ #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) void bpf_sk_reuseport_detach(struct sock *sk); @@ -1428,6 +1511,7 @@ extern const struct bpf_func_proto bpf_strtol_proto; extern const struct bpf_func_proto bpf_strtoul_proto; extern const struct bpf_func_proto bpf_tcp_sock_proto; extern const struct bpf_func_proto bpf_jiffies64_proto; +extern const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 6b64b6cc2175..07e547c02fd8 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -198,7 +198,7 @@ enum dccp_role { struct dccp_service_list { __u32 dccpsl_nr; - __be32 dccpsl_list[0]; + __be32 dccpsl_list[]; }; #define DCCP_SERVICE_INVALID_VALUE htonl((__u32)-1) diff --git a/include/linux/device.h b/include/linux/device.h index fa04dfd22bbc..1311f276f533 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -828,6 +828,7 @@ extern struct device *device_find_child_by_name(struct device *parent, extern int device_rename(struct device *dev, const char *new_name); extern int device_move(struct device *dev, struct device *new_parent, enum dpm_order dpm_order); +extern int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid); extern const char *device_get_devnode(struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid, const char **tmp); diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 95991e4300bf..c1d379bf6ee1 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -177,8 +177,57 @@ void ethtool_convert_legacy_u32_to_link_mode(unsigned long *dst, bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, const unsigned long *src); +#define ETHTOOL_COALESCE_RX_USECS BIT(0) +#define ETHTOOL_COALESCE_RX_MAX_FRAMES BIT(1) +#define ETHTOOL_COALESCE_RX_USECS_IRQ BIT(2) +#define ETHTOOL_COALESCE_RX_MAX_FRAMES_IRQ BIT(3) +#define ETHTOOL_COALESCE_TX_USECS BIT(4) +#define ETHTOOL_COALESCE_TX_MAX_FRAMES BIT(5) +#define ETHTOOL_COALESCE_TX_USECS_IRQ BIT(6) +#define ETHTOOL_COALESCE_TX_MAX_FRAMES_IRQ BIT(7) +#define ETHTOOL_COALESCE_STATS_BLOCK_USECS BIT(8) +#define ETHTOOL_COALESCE_USE_ADAPTIVE_RX BIT(9) +#define ETHTOOL_COALESCE_USE_ADAPTIVE_TX BIT(10) +#define ETHTOOL_COALESCE_PKT_RATE_LOW BIT(11) +#define ETHTOOL_COALESCE_RX_USECS_LOW BIT(12) +#define ETHTOOL_COALESCE_RX_MAX_FRAMES_LOW BIT(13) +#define ETHTOOL_COALESCE_TX_USECS_LOW BIT(14) +#define ETHTOOL_COALESCE_TX_MAX_FRAMES_LOW BIT(15) +#define ETHTOOL_COALESCE_PKT_RATE_HIGH BIT(16) +#define ETHTOOL_COALESCE_RX_USECS_HIGH BIT(17) +#define ETHTOOL_COALESCE_RX_MAX_FRAMES_HIGH BIT(18) +#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_USECS \ + (ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_TX_USECS) +#define ETHTOOL_COALESCE_MAX_FRAMES \ + (ETHTOOL_COALESCE_RX_MAX_FRAMES | ETHTOOL_COALESCE_TX_MAX_FRAMES) +#define ETHTOOL_COALESCE_USECS_IRQ \ + (ETHTOOL_COALESCE_RX_USECS_IRQ | ETHTOOL_COALESCE_TX_USECS_IRQ) +#define ETHTOOL_COALESCE_MAX_FRAMES_IRQ \ + (ETHTOOL_COALESCE_RX_MAX_FRAMES_IRQ | \ + ETHTOOL_COALESCE_TX_MAX_FRAMES_IRQ) +#define ETHTOOL_COALESCE_USE_ADAPTIVE \ + (ETHTOOL_COALESCE_USE_ADAPTIVE_RX | ETHTOOL_COALESCE_USE_ADAPTIVE_TX) +#define ETHTOOL_COALESCE_USECS_LOW_HIGH \ + (ETHTOOL_COALESCE_RX_USECS_LOW | ETHTOOL_COALESCE_TX_USECS_LOW | \ + ETHTOOL_COALESCE_RX_USECS_HIGH | ETHTOOL_COALESCE_TX_USECS_HIGH) +#define ETHTOOL_COALESCE_MAX_FRAMES_LOW_HIGH \ + (ETHTOOL_COALESCE_RX_MAX_FRAMES_LOW | \ + ETHTOOL_COALESCE_TX_MAX_FRAMES_LOW | \ + ETHTOOL_COALESCE_RX_MAX_FRAMES_HIGH | \ + ETHTOOL_COALESCE_TX_MAX_FRAMES_HIGH) +#define ETHTOOL_COALESCE_PKT_RATE_RX_USECS \ + (ETHTOOL_COALESCE_USE_ADAPTIVE_RX | \ + 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) + /** * struct ethtool_ops - optional netdev operations + * @supported_coalesce_params: supported types of interrupt coalescing. * @get_drvinfo: Report driver/device information. Should only set the * @driver, @version, @fw_version and @bus_info fields. If not * implemented, the @driver and @bus_info fields will be filled in @@ -207,8 +256,9 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, * or zero. * @get_coalesce: Get interrupt coalescing parameters. Returns a negative * error code or zero. - * @set_coalesce: Set interrupt coalescing parameters. Returns a negative - * error code or zero. + * @set_coalesce: Set interrupt coalescing parameters. Supported coalescing + * types should be set in @supported_coalesce_params. + * Returns a negative error code or zero. * @get_ringparam: Report ring sizes * @set_ringparam: Set ring sizes. Returns a negative error code or zero. * @get_pauseparam: Report pause parameters @@ -292,7 +342,8 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, * @set_per_queue_coalesce: Set interrupt coalescing parameters per queue. * It must check that the given queue number is valid. If neither a RX nor * a TX queue has this number, return -EINVAL. If only a RX queue or a TX - * queue has this number, ignore the inapplicable fields. + * queue has this number, ignore the inapplicable fields. Supported + * coalescing types should be set in @supported_coalesce_params. * Returns a negative error code or zero. * @get_link_ksettings: Get various device settings including Ethernet link * settings. The %cmd and %link_mode_masks_nwords fields should be @@ -323,6 +374,7 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, * of the generic netdev features interface. */ struct ethtool_ops { + u32 supported_coalesce_params; void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); int (*get_regs_len)(struct net_device *); void (*get_regs)(struct net_device *, struct ethtool_regs *, void *); @@ -406,6 +458,8 @@ struct ethtool_ops { struct ethtool_stats *, u64 *); }; +int ethtool_check_ops(const struct ethtool_ops *ops); + struct ethtool_rx_flow_rule { struct flow_rule *rule; unsigned long priv[0]; @@ -420,4 +474,10 @@ struct ethtool_rx_flow_rule * ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input); void ethtool_rx_flow_rule_destroy(struct ethtool_rx_flow_rule *rule); +bool ethtool_virtdev_validate_cmd(const struct ethtool_link_ksettings *cmd); +int ethtool_virtdev_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd, + u32 *dev_speed, u8 *dev_duplex); + + #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/linux/filter.h b/include/linux/filter.h index f349e2c0884c..9b5aa5c483cc 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -561,7 +561,7 @@ DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); #define __BPF_PROG_RUN(prog, ctx, dfunc) ({ \ u32 ret; \ - cant_sleep(); \ + cant_migrate(); \ if (static_branch_unlikely(&bpf_stats_enabled_key)) { \ struct bpf_prog_stats *stats; \ u64 start = sched_clock(); \ @@ -576,8 +576,30 @@ DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); } \ ret; }) -#define BPF_PROG_RUN(prog, ctx) __BPF_PROG_RUN(prog, ctx, \ - bpf_dispatcher_nopfunc) +#define BPF_PROG_RUN(prog, ctx) \ + __BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func) + +/* + * Use in preemptible and therefore migratable context to make sure that + * the execution of the BPF program runs on one CPU. + * + * This uses migrate_disable/enable() explicitly to document that the + * invocation of a BPF program does not require reentrancy protection + * against a BPF program which is invoked from a preempting task. + * + * For non RT enabled kernels migrate_disable/enable() maps to + * preempt_disable/enable(), i.e. it disables also preemption. + */ +static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog, + const void *ctx) +{ + u32 ret; + + migrate_disable(); + ret = __BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func); + migrate_enable(); + return ret; +} #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN @@ -655,6 +677,7 @@ static inline u8 *bpf_skb_cb(struct sk_buff *skb) return qdisc_skb_cb(skb)->data; } +/* Must be invoked with migration disabled */ static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog, struct sk_buff *skb) { @@ -680,9 +703,9 @@ static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, { u32 res; - preempt_disable(); + migrate_disable(); res = __bpf_prog_run_save_cb(prog, skb); - preempt_enable(); + migrate_enable(); return res; } @@ -695,13 +718,11 @@ static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, if (unlikely(prog->cb_access)) memset(cb_data, 0, BPF_SKB_CB_LEN); - preempt_disable(); - res = BPF_PROG_RUN(prog, skb); - preempt_enable(); + res = bpf_prog_run_pin_on_cpu(prog, skb); return res; } -DECLARE_BPF_DISPATCHER(bpf_dispatcher_xdp) +DECLARE_BPF_DISPATCHER(xdp) static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, struct xdp_buff *xdp) @@ -712,8 +733,7 @@ static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, * already takes rcu_read_lock() when fetching the program, so * it's not necessary here anymore. */ - return __BPF_PROG_RUN(prog, xdp, - BPF_DISPATCHER_FUNC(bpf_dispatcher_xdp)); + return __BPF_PROG_RUN(prog, xdp, BPF_DISPATCHER_FUNC(xdp)); } void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog); @@ -1063,7 +1083,6 @@ bpf_address_lookup(unsigned long addr, unsigned long *size, void bpf_prog_kallsyms_add(struct bpf_prog *fp); void bpf_prog_kallsyms_del(struct bpf_prog *fp); -void bpf_get_prog_name(const struct bpf_prog *prog, char *sym); #else /* CONFIG_BPF_JIT */ @@ -1132,11 +1151,6 @@ static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp) { } -static inline void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) -{ - sym[0] = '\0'; -} - #endif /* CONFIG_BPF_JIT */ void bpf_prog_kallsyms_del_all(struct bpf_prog *fp); diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h index b0b743563f43..75884563059f 100644 --- a/include/linux/fsl/ptp_qoriq.h +++ b/include/linux/fsl/ptp_qoriq.h @@ -149,8 +149,6 @@ struct ptp_qoriq { bool extts_fifo_support; int irq; int phc_index; - u64 alarm_interval; /* for periodic alarm */ - u64 alarm_value; u32 tclk_period; /* nanoseconds */ u32 tmr_prsc; u32 tmr_add; diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 7d3f2ced92d1..33d907eec0b6 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -620,6 +620,15 @@ static inline bool ieee80211_is_qos_nullfunc(__le16 fc) } /** + * ieee80211_is_any_nullfunc - check if frame is regular or QoS nullfunc frame + * @fc: frame control bytes in little-endian byteorder + */ +static inline bool ieee80211_is_any_nullfunc(__le16 fc) +{ + return (ieee80211_is_nullfunc(fc) || ieee80211_is_qos_nullfunc(fc)); +} + +/** * ieee80211_is_bufferable_mmpdu - check if frame is bufferable MMPDU * @fc: frame control field in little-endian byteorder */ @@ -2047,13 +2056,13 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) #define IEEE80211_HE_OPERATION_ER_SU_DISABLE 0x00010000 #define IEEE80211_HE_OPERATION_6GHZ_OP_INFO 0x00020000 #define IEEE80211_HE_OPERATION_BSS_COLOR_MASK 0x3f000000 -#define IEEE80211_HE_OPERATION_BSS_COLOR_OFFSET 24 +#define IEEE80211_HE_OPERATION_BSS_COLOR_OFFSET 24 #define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x40000000 #define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x80000000 /* * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size - * @he_oper_ie: byte data of the He Operations IE, stating from the the byte + * @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 * sizeof(struct ieee80211_he_operation) bytes, the caller must have * validated this. @@ -2091,7 +2100,7 @@ ieee80211_he_oper_size(const u8 *he_oper_ie) /* * ieee80211_he_spr_size - calculate 802.11ax HE Spatial Reuse IE size - * @he_spr_ie: byte data of the He Spatial Reuse IE, stating from the the byte + * @he_spr_ie: byte data of the He Spatial Reuse IE, stating from the byte * after the ext ID byte. It is assumed that he_spr_ie has at least * sizeof(struct ieee80211_he_spr) bytes, the caller must have validated * this @@ -2523,6 +2532,7 @@ enum ieee80211_eid { WLAN_EID_FILS_INDICATION = 240, WLAN_EID_DILS = 241, WLAN_EID_FRAGMENT = 242, + WLAN_EID_RSNX = 244, WLAN_EID_EXTENSION = 255 }; @@ -2734,7 +2744,7 @@ enum ieee80211_tdls_actioncode { */ #define WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT BIT(6) -/* TDLS capabilities in the the 4th byte of @WLAN_EID_EXT_CAPABILITY */ +/* TDLS capabilities in the 4th byte of @WLAN_EID_EXT_CAPABILITY */ #define WLAN_EXT_CAPA4_TDLS_BUFFER_STA BIT(4) #define WLAN_EXT_CAPA4_TDLS_PEER_PSM BIT(5) #define WLAN_EXT_CAPA4_TDLS_CHAN_SWITCH BIT(6) @@ -3034,6 +3044,7 @@ struct ieee80211_multiple_bssid_configuration { #define WLAN_AKM_SUITE_FILS_SHA384 SUITE(0x000FAC, 15) #define WLAN_AKM_SUITE_FT_FILS_SHA256 SUITE(0x000FAC, 16) #define WLAN_AKM_SUITE_FT_FILS_SHA384 SUITE(0x000FAC, 17) +#define WLAN_AKM_SUITE_OWE SUITE(0x000FAC, 18) #define WLAN_MAX_KEY_LEN 32 @@ -3412,4 +3423,11 @@ static inline bool for_each_element_completed(const struct element *element, return (const u8 *)element == (const u8 *)data + datalen; } +/** + * RSNX Capabilities: + * bits 0-3: Field length (n-1) + */ +#define WLAN_RSNX_CAPA_PROTECTED_TWT BIT(4) +#define WLAN_RSNX_CAPA_SAE_H2E BIT(5) + #endif /* LINUX_IEEE80211_H */ diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index c91cf2dee12a..ce9ed1c0602f 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -10,11 +10,9 @@ struct inet_hashinfo; struct inet_diag_handler { void (*dump)(struct sk_buff *skb, struct netlink_callback *cb, - const struct inet_diag_req_v2 *r, - struct nlattr *bc); + const struct inet_diag_req_v2 *r); - int (*dump_one)(struct sk_buff *in_skb, - const struct nlmsghdr *nlh, + int (*dump_one)(struct netlink_callback *cb, const struct inet_diag_req_v2 *req); void (*idiag_get_info)(struct sock *sk, @@ -35,18 +33,25 @@ struct inet_diag_handler { __u16 idiag_info_size; }; +struct bpf_sk_storage_diag; +struct inet_diag_dump_data { + struct nlattr *req_nlas[__INET_DIAG_REQ_MAX]; +#define inet_diag_nla_bc req_nlas[INET_DIAG_REQ_BYTECODE] +#define inet_diag_nla_bpf_stgs req_nlas[INET_DIAG_REQ_SK_BPF_STORAGES] + + struct bpf_sk_storage_diag *bpf_stg_diag; +}; + struct inet_connection_sock; int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, - struct sk_buff *skb, const struct inet_diag_req_v2 *req, - struct user_namespace *user_ns, - u32 pid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh, bool net_admin); + struct sk_buff *skb, struct netlink_callback *cb, + const struct inet_diag_req_v2 *req, + u16 nlmsg_flags, bool net_admin); void inet_diag_dump_icsk(struct inet_hashinfo *h, struct sk_buff *skb, struct netlink_callback *cb, - const struct inet_diag_req_v2 *r, - struct nlattr *bc); + const struct inet_diag_req_v2 *r); int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, - struct sk_buff *in_skb, const struct nlmsghdr *nlh, + struct netlink_callback *cb, const struct inet_diag_req_v2 *req); struct sock *inet_diag_find_one_icsk(struct net *net, diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h index 35e15dfd4155..cb20c733b15a 100644 --- a/include/linux/iopoll.h +++ b/include/linux/iopoll.h @@ -14,36 +14,41 @@ #include <linux/io.h> /** - * readx_poll_timeout - Periodically poll an address until a condition is met or a timeout occurs - * @op: accessor function (takes @addr as its only argument) - * @addr: Address to poll + * read_poll_timeout - Periodically poll an address until a condition is + * met or a timeout occurs + * @op: accessor function (takes @args as its arguments) * @val: Variable to read the value into * @cond: Break condition (usually involving @val) * @sleep_us: Maximum time to sleep between reads in us (0 * tight-loops). Should be less than ~20ms since usleep_range * is used (see Documentation/timers/timers-howto.rst). * @timeout_us: Timeout in us, 0 means never timeout + * @sleep_before_read: if it is true, sleep @sleep_us before read. + * @args: arguments for @op poll * * Returns 0 on success and -ETIMEDOUT upon a timeout. In either - * case, the last read value at @addr is stored in @val. Must not + * case, the last read value at @args is stored in @val. Must not * be called from atomic context if sleep_us or timeout_us are used. * * When available, you'll probably want to use one of the specialized * macros defined below rather than this macro directly. */ -#define readx_poll_timeout(op, addr, val, cond, sleep_us, timeout_us) \ +#define read_poll_timeout(op, val, cond, sleep_us, timeout_us, \ + sleep_before_read, args...) \ ({ \ u64 __timeout_us = (timeout_us); \ unsigned long __sleep_us = (sleep_us); \ ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \ might_sleep_if((__sleep_us) != 0); \ + if (sleep_before_read && __sleep_us) \ + usleep_range((__sleep_us >> 2) + 1, __sleep_us); \ for (;;) { \ - (val) = op(addr); \ + (val) = op(args); \ if (cond) \ break; \ if (__timeout_us && \ ktime_compare(ktime_get(), __timeout) > 0) { \ - (val) = op(addr); \ + (val) = op(args); \ break; \ } \ if (__sleep_us) \ @@ -53,6 +58,27 @@ }) /** + * readx_poll_timeout - Periodically poll an address until a condition is met or a timeout occurs + * @op: accessor function (takes @addr as its only argument) + * @addr: Address to poll + * @val: Variable to read the value into + * @cond: Break condition (usually involving @val) + * @sleep_us: Maximum time to sleep between reads in us (0 + * tight-loops). Should be less than ~20ms since usleep_range + * is used (see Documentation/timers/timers-howto.rst). + * @timeout_us: Timeout in us, 0 means never timeout + * + * Returns 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @addr is stored in @val. Must not + * be called from atomic context if sleep_us or timeout_us are used. + * + * When available, you'll probably want to use one of the specialized + * macros defined below rather than this macro directly. + */ +#define readx_poll_timeout(op, addr, val, cond, sleep_us, timeout_us) \ + read_poll_timeout(op, val, cond, sleep_us, timeout_us, false, addr) + +/** * readx_poll_timeout_atomic - Periodically poll an address until a condition is met or a timeout occurs * @op: accessor function (takes @addr as its only argument) * @addr: Address to poll diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 0d9db2a14f44..9b7a8d74a9d6 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -257,6 +257,13 @@ extern void __cant_sleep(const char *file, int line, int preempt_offset); #define might_sleep_if(cond) do { if (cond) might_sleep(); } while (0) +#ifndef CONFIG_PREEMPT_RT +# define cant_migrate() cant_sleep() +#else + /* Placeholder for now */ +# define cant_migrate() do { } while (0) +#endif + /** * abs - return absolute value of an argument * @x: the value. If it is unsigned type, it is converted to signed type first. diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index fe740031339d..c664c27a29a0 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -71,7 +71,7 @@ static inline void linkmode_change_bit(int nr, volatile unsigned long *addr) __change_bit(nr, addr); } -static inline int linkmode_test_bit(int nr, volatile unsigned long *addr) +static inline int linkmode_test_bit(int nr, const volatile unsigned long *addr) { return test_bit(nr, addr); } @@ -88,4 +88,10 @@ static inline int linkmode_subset(const unsigned long *src1, return bitmap_subset(src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); } +void linkmode_resolve_pause(const unsigned long *local_adv, + const unsigned long *partner_adv, + bool *tx_pause, bool *rx_pause); + +void linkmode_set_pause(unsigned long *advertisement, bool tx, bool rx); + #endif /* __LINKMODE_H */ diff --git a/include/linux/mdio-xpcs.h b/include/linux/mdio-xpcs.h new file mode 100644 index 000000000000..9a841aa5982d --- /dev/null +++ b/include/linux/mdio-xpcs.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020 Synopsys, Inc. and/or its affiliates. + * Synopsys DesignWare XPCS helpers + */ + +#ifndef __LINUX_MDIO_XPCS_H +#define __LINUX_MDIO_XPCS_H + +#include <linux/phy.h> +#include <linux/phylink.h> + +struct mdio_xpcs_args { + __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); + struct mii_bus *bus; + int addr; +}; + +struct mdio_xpcs_ops { + int (*validate)(struct mdio_xpcs_args *xpcs, + unsigned long *supported, + struct phylink_link_state *state); + int (*config)(struct mdio_xpcs_args *xpcs, + const struct phylink_link_state *state); + int (*get_state)(struct mdio_xpcs_args *xpcs, + struct phylink_link_state *state); + int (*link_up)(struct mdio_xpcs_args *xpcs, int speed, + phy_interface_t interface); + int (*probe)(struct mdio_xpcs_args *xpcs, phy_interface_t interface); +}; + +#if IS_ENABLED(CONFIG_MDIO_XPCS) +struct mdio_xpcs_ops *mdio_xpcs_get_ops(void); +#else +static inline struct mdio_xpcs_ops *mdio_xpcs_get_ops(void) +{ + return NULL; +} +#endif + +#endif /* __LINUX_MDIO_XPCS_H */ diff --git a/include/linux/mdio.h b/include/linux/mdio.h index a7604248777b..917e4bb2ed71 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -316,11 +316,15 @@ static inline void mii_10gbt_stat_mod_linkmode_lpa_t(unsigned long *advertising, int __mdiobus_read(struct mii_bus *bus, int addr, u32 regnum); int __mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val); +int __mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum, + u16 mask, u16 set); int mdiobus_read(struct mii_bus *bus, int addr, u32 regnum); int mdiobus_read_nested(struct mii_bus *bus, int addr, u32 regnum); int mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val); int mdiobus_write_nested(struct mii_bus *bus, int addr, u32 regnum, u16 val); +int mdiobus_modify(struct mii_bus *bus, int addr, u32 regnum, u16 mask, + u16 set); int mdiobus_register_device(struct mdio_device *mdiodev); int mdiobus_unregister_device(struct mdio_device *mdiodev); diff --git a/include/linux/mii.h b/include/linux/mii.h index 18c6208f56fc..219b93cad1dd 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -355,24 +355,6 @@ static inline u32 mii_adv_to_ethtool_adv_x(u32 adv) } /** - * mii_lpa_to_ethtool_lpa_x - * @adv: value of the MII_LPA register - * - * A small helper function that translates MII_LPA - * bits, when in 1000Base-X mode, to ethtool - * LP advertisement settings. - */ -static inline u32 mii_lpa_to_ethtool_lpa_x(u32 lpa) -{ - u32 result = 0; - - if (lpa & LPA_LPACK) - result |= ADVERTISED_Autoneg; - - return result | mii_adv_to_ethtool_adv_x(lpa); -} - -/** * mii_lpa_mod_linkmode_adv_sgmii * @lp_advertising: pointer to destination link mode. * @lpa: value of the MII_LPA register @@ -536,6 +518,45 @@ static inline u32 linkmode_adv_to_lcl_adv_t(unsigned long *advertising) } /** + * mii_lpa_mod_linkmode_x - decode the link partner's config_reg to linkmodes + * @linkmodes: link modes array + * @lpa: config_reg word from link partner + * @fd_bit: link mode for 1000XFULL bit + */ +static inline void mii_lpa_mod_linkmode_x(unsigned long *linkmodes, u16 lpa, + int fd_bit) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, linkmodes, + lpa & LPA_LPACK); + linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT, linkmodes, + lpa & LPA_1000XPAUSE); + linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, linkmodes, + lpa & LPA_1000XPAUSE_ASYM); + linkmode_mod_bit(fd_bit, linkmodes, + lpa & LPA_1000XFULL); +} + +/** + * linkmode_adv_to_mii_adv_x - encode a linkmode to config_reg + * @linkmodes: linkmodes + * @fd_bit: full duplex bit + */ +static inline u16 linkmode_adv_to_mii_adv_x(const unsigned long *linkmodes, + int fd_bit) +{ + u16 adv = 0; + + if (linkmode_test_bit(fd_bit, linkmodes)) + adv |= ADVERTISE_1000XFULL; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, linkmodes)) + adv |= ADVERTISE_1000XPAUSE; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, linkmodes)) + adv |= ADVERTISE_1000XPSE_ASYM; + + return adv; +} + +/** * mii_advertise_flowctrl - get flow control advertisement flags * @cap: Flow control capabilities (FLOW_CTRL_RX, FLOW_CTRL_TX or both) */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 277a51d3ec40..44bf95d63677 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -518,9 +518,11 @@ struct mlx5_rate_limit { }; struct mlx5_rl_entry { - struct mlx5_rate_limit rl; - u16 index; - u16 refcount; + u8 rl_raw[MLX5_ST_SZ_BYTES(set_pp_rate_limit_context)]; + u16 index; + u64 refcount; + u16 uid; + u8 dedicated : 1; }; struct mlx5_rl_table { @@ -722,6 +724,7 @@ struct mlx5_core_dev { struct mlx5_clock clock; struct mlx5_ib_clock_info *clock_info; struct mlx5_fw_tracer *tracer; + struct mlx5_rsc_dump *rsc_dump; u32 vsc_addr; struct mlx5_hv_vhca *hv_vhca; }; @@ -1007,6 +1010,9 @@ int mlx5_rl_add_rate(struct mlx5_core_dev *dev, u16 *index, struct mlx5_rate_limit *rl); void mlx5_rl_remove_rate(struct mlx5_core_dev *dev, struct mlx5_rate_limit *rl); bool mlx5_rl_is_in_range(struct mlx5_core_dev *dev, u32 rate); +int mlx5_rl_add_rate_raw(struct mlx5_core_dev *dev, void *rl_in, u16 uid, + bool dedicated_entry, u16 *index); +void mlx5_rl_remove_rate_raw(struct mlx5_core_dev *dev, u16 index); bool mlx5_rl_are_equal(struct mlx5_rate_limit *rl_0, struct mlx5_rate_limit *rl_1); int mlx5_alloc_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg, diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 98e667b176ef..c16827eeba9c 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -70,8 +70,30 @@ u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev); enum devlink_eswitch_encap_mode mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev); +bool mlx5_eswitch_reg_c1_loopback_enabled(const struct mlx5_eswitch *esw); bool mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw); -u32 mlx5_eswitch_get_vport_metadata_for_match(const struct mlx5_eswitch *esw, + +/* Reg C0 usage: + * Reg C0 = < ESW_VHCA_ID_BITS(8) | ESW_VPORT BITS(8) | ESW_CHAIN_TAG(16) > + * + * Highest 8 bits of the reg c0 is the vhca_id, next 8 bits is vport_num, + * the rest (lowest 16 bits) is left for tc chain tag restoration. + * VHCA_ID + VPORT comprise the SOURCE_PORT matching. + */ +#define ESW_VHCA_ID_BITS 8 +#define ESW_VPORT_BITS 8 +#define ESW_SOURCE_PORT_METADATA_BITS (ESW_VHCA_ID_BITS + ESW_VPORT_BITS) +#define ESW_SOURCE_PORT_METADATA_OFFSET (32 - ESW_SOURCE_PORT_METADATA_BITS) +#define ESW_CHAIN_TAG_METADATA_BITS (32 - ESW_SOURCE_PORT_METADATA_BITS) +#define ESW_CHAIN_TAG_METADATA_MASK GENMASK(ESW_CHAIN_TAG_METADATA_BITS - 1,\ + 0) + +static inline u32 mlx5_eswitch_get_vport_metadata_mask(void) +{ + return GENMASK(31, 32 - ESW_SOURCE_PORT_METADATA_BITS); +} + +u32 mlx5_eswitch_get_vport_metadata_for_match(struct mlx5_eswitch *esw, u16 vport_num); u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw); #else /* CONFIG_MLX5_ESWITCH */ @@ -88,17 +110,29 @@ mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev) } static inline bool +mlx5_eswitch_reg_c1_loopback_enabled(const struct mlx5_eswitch *esw) +{ + return false; +}; + +static inline bool mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw) { return false; }; static inline u32 -mlx5_eswitch_get_vport_metadata_for_match(const struct mlx5_eswitch *esw, +mlx5_eswitch_get_vport_metadata_for_match(struct mlx5_eswitch *esw, int vport_num) { return 0; }; + +static inline u32 +mlx5_eswitch_get_vport_metadata_mask(void) +{ + return 0; +} #endif /* CONFIG_MLX5_ESWITCH */ #endif diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 4cae16016b2b..a5cf5c76f348 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -84,6 +84,7 @@ enum { FDB_TC_OFFLOAD, FDB_FT_OFFLOAD, FDB_SLOW_PATH, + FDB_PER_VPORT, }; struct mlx5_pkt_reformat; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index bfdf41537cf1..cc55cee3b53c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -414,8 +414,10 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reserved_at_16[0x1]; u8 table_miss_action_domain[0x1]; u8 termination_table[0x1]; - u8 reserved_at_19[0x7]; - u8 reserved_at_20[0x2]; + u8 reformat_and_fwd_to_table[0x1]; + u8 reserved_at_1a[0x6]; + u8 termination_table_raw_traffic[0x1]; + u8 reserved_at_21[0x1]; u8 log_max_ft_size[0x6]; u8 log_max_modify_header_context[0x8]; u8 max_modify_header_actions[0x8]; @@ -741,7 +743,7 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits { u8 flow_source[0x1]; u8 reserved_at_18[0x2]; u8 multi_fdb_encap[0x1]; - u8 reserved_at_1b[0x1]; + u8 egress_acl_forward_to_vport[0x1]; u8 fdb_multi_path_to_table[0x1]; u8 reserved_at_1d[0x3]; @@ -813,7 +815,9 @@ struct mlx5_ifc_qos_cap_bits { u8 reserved_at_4[0x1]; u8 packet_pacing_burst_bound[0x1]; u8 packet_pacing_typical_size[0x1]; - u8 reserved_at_7[0x19]; + u8 reserved_at_7[0x4]; + u8 packet_pacing_uid[0x1]; + u8 reserved_at_c[0x14]; u8 reserved_at_20[0x20]; @@ -8265,9 +8269,20 @@ struct mlx5_ifc_set_pp_rate_limit_out_bits { u8 reserved_at_40[0x40]; }; +struct mlx5_ifc_set_pp_rate_limit_context_bits { + u8 rate_limit[0x20]; + + u8 burst_upper_bound[0x20]; + + u8 reserved_at_40[0x10]; + u8 typical_packet_size[0x10]; + + u8 reserved_at_60[0x120]; +}; + struct mlx5_ifc_set_pp_rate_limit_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -8277,14 +8292,7 @@ struct mlx5_ifc_set_pp_rate_limit_in_bits { u8 reserved_at_60[0x20]; - u8 rate_limit[0x20]; - - u8 burst_upper_bound[0x20]; - - u8 reserved_at_c0[0x10]; - u8 typical_packet_size[0x10]; - - u8 reserved_at_e0[0x120]; + struct mlx5_ifc_set_pp_rate_limit_context_bits ctx; }; struct mlx5_ifc_access_register_out_bits { @@ -8420,7 +8428,8 @@ struct mlx5_ifc_ptys_reg_bits { u8 proto_mask[0x3]; u8 an_status[0x4]; - u8 reserved_at_24[0x1c]; + u8 reserved_at_24[0xc]; + u8 data_rate_oper[0x10]; u8 ext_eth_proto_capability[0x20]; @@ -10486,7 +10495,8 @@ enum { }; enum { - MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_TYPE_DEK = 0x1, + MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_TYPE_TLS = 0x1, + MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_TYPE_IPSEC = 0x2, }; struct mlx5_ifc_tls_static_params_bits { diff --git a/include/linux/mlx5/mlx5_ifc_fpga.h b/include/linux/mlx5/mlx5_ifc_fpga.h index 37e065a80a43..07d77323f78a 100644 --- a/include/linux/mlx5/mlx5_ifc_fpga.h +++ b/include/linux/mlx5/mlx5_ifc_fpga.h @@ -608,7 +608,7 @@ struct mlx5_ifc_tls_cmd_bits { struct mlx5_ifc_tls_resp_bits { u8 syndrome[0x20]; u8 stream_id[0x20]; - u8 reserverd[0x40]; + u8 reserved[0x40]; }; #define MLX5_TLS_COMMAND_SIZE (0x100) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6c3f7032e8d9..654808bfad83 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -664,7 +664,7 @@ static inline void netdev_queue_numa_node_write(struct netdev_queue *q, int node struct rps_map { unsigned int len; struct rcu_head rcu; - u16 cpus[0]; + u16 cpus[]; }; #define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + ((_num) * sizeof(u16))) @@ -686,7 +686,7 @@ struct rps_dev_flow { struct rps_dev_flow_table { unsigned int mask; struct rcu_head rcu; - struct rps_dev_flow flows[0]; + struct rps_dev_flow flows[]; }; #define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \ ((_num) * sizeof(struct rps_dev_flow))) @@ -704,7 +704,7 @@ struct rps_dev_flow_table { struct rps_sock_flow_table { u32 mask; - u32 ents[0] ____cacheline_aligned_in_smp; + u32 ents[] ____cacheline_aligned_in_smp; }; #define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num])) @@ -767,7 +767,7 @@ struct xps_map { unsigned int len; unsigned int alloc_len; struct rcu_head rcu; - u16 queues[0]; + u16 queues[]; }; #define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + ((_num) * sizeof(u16))) #define XPS_MIN_MAP_ALLOC ((L1_CACHE_ALIGN(offsetof(struct xps_map, queues[1])) \ @@ -778,7 +778,7 @@ struct xps_map { */ struct xps_dev_maps { struct rcu_head rcu; - struct xps_map __rcu *attr_map[0]; /* Either CPUs map or RXQs map */ + struct xps_map __rcu *attr_map[]; /* Either CPUs map or RXQs map */ }; #define XPS_CPU_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \ @@ -853,6 +853,7 @@ enum tc_setup_type { TC_SETUP_FT, TC_SETUP_QDISC_ETS, TC_SETUP_QDISC_TBF, + TC_SETUP_QDISC_FIFO, }; /* These structures hold the attributes of bpf state that are being passed diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 5448c8b443db..ab192720e2d6 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -98,7 +98,7 @@ struct ip_set_counter { struct ip_set_comment_rcu { struct rcu_head rcu; - char str[0]; + char str[]; }; struct ip_set_comment { diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 1b261c51b3a3..5da88451853b 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -264,7 +264,7 @@ struct xt_table_info { unsigned int stacksize; void ***jumpstack; - unsigned char entries[0] __aligned(8); + unsigned char entries[] __aligned(8); }; int xt_register_target(struct xt_target *target); @@ -464,7 +464,7 @@ struct compat_xt_entry_match { } kernel; u_int16_t match_size; } u; - unsigned char data[0]; + unsigned char data[]; }; struct compat_xt_entry_target { @@ -480,7 +480,7 @@ struct compat_xt_entry_target { } kernel; u_int16_t target_size; } u; - unsigned char data[0]; + unsigned char data[]; }; /* FIXME: this works only on 32 bit tasks @@ -494,7 +494,7 @@ struct compat_xt_counters { struct compat_xt_counters_info { char name[XT_TABLE_MAXNAMELEN]; compat_uint_t num_counters; - struct compat_xt_counters counters[0]; + struct compat_xt_counters counters[]; }; struct _compat_xt_align { diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index e98028f00e47..7d3537c40ec9 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -67,7 +67,7 @@ struct compat_arpt_entry { __u16 next_offset; compat_uint_t comefrom; struct compat_xt_counters counters; - unsigned char elems[0]; + unsigned char elems[]; }; static inline struct xt_entry_target * diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 162f59d0d17a..2f5c4e6ecd8a 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -85,7 +85,7 @@ struct ebt_table_info { /* room to maintain the stack used for jumping from and into udc */ struct ebt_chainstack **chainstack; char *entries; - struct ebt_counter counters[0] ____cacheline_aligned; + struct ebt_counter counters[] ____cacheline_aligned; }; struct ebt_table { diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index e9e1ed74cdf1..b394bd4f68a3 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -76,7 +76,7 @@ struct compat_ipt_entry { __u16 next_offset; compat_uint_t comefrom; struct compat_xt_counters counters; - unsigned char elems[0]; + unsigned char elems[]; }; /* Helper functions */ diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 78ab959c4575..8225f7821a29 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -43,7 +43,7 @@ struct compat_ip6t_entry { __u16 next_offset; compat_uint_t comefrom; struct compat_xt_counters counters; - unsigned char elems[0]; + unsigned char elems[]; }; static inline struct xt_entry_target * diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 60739d0cbf93..e3e49f0e5c13 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -201,10 +201,10 @@ struct netlink_callback { struct module *module; struct netlink_ext_ack *extack; u16 family; - u16 min_dump_alloc; - bool strict_check; u16 answer_flags; + u32 min_dump_alloc; unsigned int prev_seq, seq; + bool strict_check; union { u8 ctx[48]; diff --git a/include/linux/pci.h b/include/linux/pci.h index 3840a541a9de..fc54b8922e66 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -42,6 +42,13 @@ #include <linux/pci_ids.h> +#define PCI_STATUS_ERROR_BITS (PCI_STATUS_DETECTED_PARITY | \ + PCI_STATUS_SIG_SYSTEM_ERROR | \ + PCI_STATUS_REC_MASTER_ABORT | \ + PCI_STATUS_REC_TARGET_ABORT | \ + PCI_STATUS_SIG_TARGET_ABORT | \ + PCI_STATUS_PARITY) + /* * The PCI interface treats multi-function devices as independent * devices. The slot/function address of each device is encoded @@ -1045,6 +1052,8 @@ int pci_find_ht_capability(struct pci_dev *dev, int ht_cap); int pci_find_next_ht_capability(struct pci_dev *dev, int pos, int ht_cap); struct pci_bus *pci_find_next_bus(const struct pci_bus *from); +u64 pci_get_dsn(struct pci_dev *dev); + struct pci_dev *pci_get_device(unsigned int vendor, unsigned int device, struct pci_dev *from); struct pci_dev *pci_get_subsys(unsigned int vendor, unsigned int device, @@ -1203,6 +1212,7 @@ int pci_select_bars(struct pci_dev *dev, unsigned long flags); bool pci_device_is_present(struct pci_dev *pdev); void pci_ignore_hotplug(struct pci_dev *dev); struct pci_dev *pci_real_dma_dev(struct pci_dev *dev); +int pci_status_get_and_clear_errors(struct pci_dev *pdev); int __printf(6, 7) pci_request_irq(struct pci_dev *dev, unsigned int nr, irq_handler_t handler, irq_handler_t thread_fn, void *dev_id, @@ -1699,6 +1709,9 @@ static inline int pci_find_next_capability(struct pci_dev *dev, u8 post, static inline int pci_find_ext_capability(struct pci_dev *dev, int cap) { return 0; } +static inline u64 pci_get_dsn(struct pci_dev *dev) +{ return 0; } + /* Power management related routines */ static inline int pci_save_state(struct pci_dev *dev) { return 0; } static inline void pci_restore_state(struct pci_dev *dev) { } diff --git a/include/linux/phy.h b/include/linux/phy.h index 452e8ba8665f..2432ca463ddc 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -23,6 +23,8 @@ #include <linux/workqueue.h> #include <linux/mod_devicetable.h> #include <linux/u64_stats_sync.h> +#include <linux/irqreturn.h> +#include <linux/iopoll.h> #include <linux/atomic.h> @@ -94,6 +96,7 @@ typedef enum { PHY_INTERFACE_MODE_RTBI, PHY_INTERFACE_MODE_SMII, PHY_INTERFACE_MODE_XGMII, + PHY_INTERFACE_MODE_XLGMII, PHY_INTERFACE_MODE_MOCA, PHY_INTERFACE_MODE_QSGMII, PHY_INTERFACE_MODE_TRGMII, @@ -165,6 +168,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "smii"; case PHY_INTERFACE_MODE_XGMII: return "xgmii"; + case PHY_INTERFACE_MODE_XLGMII: + return "xlgmii"; case PHY_INTERFACE_MODE_MOCA: return "moca"; case PHY_INTERFACE_MODE_QSGMII: @@ -289,6 +294,7 @@ static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev) return devm_mdiobus_alloc_size(dev, 0); } +struct mii_bus *mdio_find_bus(const char *mdio_name); void devm_mdiobus_free(struct device *dev, struct mii_bus *bus); struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); @@ -360,6 +366,7 @@ struct macsec_ops; * suspended_by_mdio_bus: Set to true if this phy was suspended by MDIO bus. * sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal. * loopback_enabled: Set true if this phy has been loopbacked successfully. + * downshifted_rate: Set true if link speed has been downshifted. * state: state of the PHY for management purposes * dev_flags: Device-specific flags used by the PHY driver. * irq: IRQ number of the PHY's interrupt (-1 if none) @@ -400,6 +407,7 @@ struct phy_device { unsigned suspended_by_mdio_bus:1; unsigned sysfs_links:1; unsigned loopback_enabled:1; + unsigned downshifted_rate:1; unsigned autoneg:1; /* The most recently read link state */ @@ -564,7 +572,7 @@ struct phy_driver { int (*did_interrupt)(struct phy_device *phydev); /* Override default interrupt handling */ - int (*handle_interrupt)(struct phy_device *phydev); + irqreturn_t (*handle_interrupt)(struct phy_device *phydev); /* Clears up any memory if needed */ void (*remove)(struct phy_device *phydev); @@ -693,6 +701,7 @@ static inline bool phy_is_started(struct phy_device *phydev) void phy_resolve_aneg_pause(struct phy_device *phydev); void phy_resolve_aneg_linkmode(struct phy_device *phydev); +void phy_check_downshift(struct phy_device *phydev); /** * phy_read - Convenience function for reading a given PHY register @@ -708,6 +717,19 @@ static inline int phy_read(struct phy_device *phydev, u32 regnum) return mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, regnum); } +#define phy_read_poll_timeout(phydev, regnum, val, cond, sleep_us, \ + timeout_us, sleep_before_read) \ +({ \ + int __ret = read_poll_timeout(phy_read, val, (cond) || val < 0, \ + sleep_us, timeout_us, sleep_before_read, phydev, regnum); \ + if (val < 0) \ + __ret = val; \ + if (__ret) \ + phydev_err(phydev, "%s failed: %d\n", __func__, __ret); \ + __ret; \ +}) + + /** * __phy_read - convenience function for reading a given PHY register * @phydev: the phy_device struct @@ -750,6 +772,25 @@ static inline int __phy_write(struct phy_device *phydev, u32 regnum, u16 val) } /** + * __phy_modify_changed() - Convenience function for modifying a PHY register + * @phydev: a pointer to a &struct phy_device + * @regnum: register number + * @mask: bit mask of bits to clear + * @set: bit mask of bits to set + * + * Unlocked helper function which allows a PHY register to be modified as + * new register value = (old register value & ~mask) | set + * + * Returns negative errno, 0 if there was no change, and 1 in case of change + */ +static inline int __phy_modify_changed(struct phy_device *phydev, u32 regnum, + u16 mask, u16 set) +{ + return __mdiobus_modify_changed(phydev->mdio.bus, phydev->mdio.addr, + regnum, mask, set); +} + +/** * phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. * @phydev: The phy_device struct @@ -760,6 +801,19 @@ static inline int __phy_write(struct phy_device *phydev, u32 regnum, u16 val) */ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); +#define phy_read_mmd_poll_timeout(phydev, devaddr, regnum, val, cond, \ + sleep_us, timeout_us, sleep_before_read) \ +({ \ + int __ret = read_poll_timeout(phy_read_mmd, val, (cond) || val < 0, \ + sleep_us, timeout_us, sleep_before_read, \ + phydev, devaddr, regnum); \ + if (val < 0) \ + __ret = val; \ + if (__ret) \ + phydev_err(phydev, "%s failed: %d\n", __func__, __ret); \ + __ret; \ +}) + /** * __phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. @@ -1260,6 +1314,9 @@ void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); bool phy_validate_pause(struct phy_device *phydev, struct ethtool_pauseparam *pp); +void phy_get_pause(struct phy_device *phydev, bool *tx_pause, bool *rx_pause); +void phy_resolve_pause(unsigned long *local_adv, unsigned long *partner_adv, + bool *tx_pause, bool *rx_pause); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 523209e70947..8fa6df3b881b 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -12,12 +12,10 @@ struct net_device; enum { MLO_PAUSE_NONE, - MLO_PAUSE_ASYM = BIT(0), - MLO_PAUSE_SYM = BIT(1), - MLO_PAUSE_RX = BIT(2), - MLO_PAUSE_TX = BIT(3), + MLO_PAUSE_RX = BIT(0), + MLO_PAUSE_TX = BIT(1), MLO_PAUSE_TXRX_MASK = MLO_PAUSE_TX | MLO_PAUSE_RX, - MLO_PAUSE_AN = BIT(4), + MLO_PAUSE_AN = BIT(2), MLO_AN_PHY = 0, /* Conventional PHY */ MLO_AN_FIXED, /* Fixed-link mode */ @@ -93,9 +91,10 @@ struct phylink_mac_ops { void (*mac_an_restart)(struct phylink_config *config); void (*mac_link_down)(struct phylink_config *config, unsigned int mode, phy_interface_t interface); - void (*mac_link_up)(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, - struct phy_device *phy); + void (*mac_link_up)(struct phylink_config *config, + struct phy_device *phy, unsigned int mode, + phy_interface_t interface, int speed, int duplex, + bool tx_pause, bool rx_pause); }; #if 0 /* For kernel-doc purposes only. */ @@ -154,15 +153,33 @@ void mac_pcs_get_state(struct phylink_config *config, * guaranteed to be correct, and so any mac_config() implementation must * never reference these fields. * + * (this requires a rewrite - please refer to mac_link_up() for situations + * where the PCS and MAC are not tightly integrated.) + * + * In all negotiation modes, as defined by @mode, @state->pause indicates the + * pause settings which should be applied as follows. If %MLO_PAUSE_AN is not + * set, %MLO_PAUSE_TX and %MLO_PAUSE_RX indicate whether the MAC should send + * pause frames and/or act on received pause frames respectively. Otherwise, + * the results of in-band negotiation/status from the MAC PCS should be used + * to control the MAC pause mode settings. + * * The action performed depends on the currently selected mode: * * %MLO_AN_FIXED, %MLO_AN_PHY: - * Configure the specified @state->speed, @state->duplex and - * @state->pause (%MLO_PAUSE_TX / %MLO_PAUSE_RX) modes over a link - * specified by @state->interface. @state->advertising may be used, - * but is not required. Other members of @state must be ignored. + * Configure for non-inband negotiation mode, where the link settings + * are completely communicated via mac_link_up(). The physical link + * protocol from the MAC is specified by @state->interface. + * + * @state->advertising may be used, but is not required. + * + * Older drivers (prior to the mac_link_up() change) may use @state->speed, + * @state->duplex and @state->pause to configure the MAC, but this is + * deprecated; such drivers should be converted to use mac_link_up(). * - * Valid state members: interface, speed, duplex, pause, advertising. + * Other members of @state must be ignored. + * + * Valid state members: interface, advertising. + * Deprecated state members: speed, duplex, pause. * * %MLO_AN_INBAND: * place the link in an inband negotiation mode (such as 802.3z @@ -172,11 +189,14 @@ void mac_pcs_get_state(struct phylink_config *config, * mac_pcs_get_state() callback. Changes in link state must be made * by calling phylink_mac_change(). * + * Interface mode specific details are mentioned below. + * * If in 802.3z mode, the link speed is fixed, dependent on the - * @state->interface. Duplex is negotiated, and pause is advertised - * according to @state->an_enabled, @state->pause and - * @state->advertising flags. Beware of MACs which only support full - * duplex at gigabit and higher speeds. + * @state->interface. Duplex and pause modes are negotiated via + * the in-band configuration word. Advertised pause modes are set + * according to the @state->an_enabled and @state->advertising + * flags. Beware of MACs which only support full duplex at gigabit + * and higher speeds. * * If in Cisco SGMII mode, the link speed and duplex mode are passed * in the serial bitstream 16-bit configuration word, and the MAC @@ -220,19 +240,34 @@ void mac_link_down(struct phylink_config *config, unsigned int mode, /** * mac_link_up() - allow the link to come up * @config: a pointer to a &struct phylink_config. + * @phy: any attached phy * @mode: link autonegotiation mode * @interface: link &typedef phy_interface_t mode - * @phy: any attached phy + * @speed: link speed + * @duplex: link duplex + * @tx_pause: link transmit pause enablement status + * @rx_pause: link receive pause enablement status * - * If @mode is not an in-band negotiation mode (as defined by - * phylink_autoneg_inband()), allow the link to come up. If @phy - * is non-%NULL, configure Energy Efficient Ethernet by calling + * Configure the MAC for an established link. + * + * @speed, @duplex, @tx_pause and @rx_pause indicate the finalised link + * settings, and should be used to configure the MAC block appropriately + * where these settings are not automatically conveyed from the PCS block, + * or if in-band negotiation (as defined by phylink_autoneg_inband(@mode)) + * is disabled. + * + * Note that when 802.3z in-band negotiation is in use, it is possible + * that the user wishes to override the pause settings, and this should + * be allowed when considering the implementation of this method. + * + * If in-band negotiation mode is disabled, allow the link to come up. If + * @phy is non-%NULL, configure Energy Efficient Ethernet by calling * phy_init_eee() and perform appropriate MAC configuration for EEE. * Interface type selection must be done in mac_config(). */ -void mac_link_up(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, - struct phy_device *phy); +void mac_link_up(struct phylink_config *config, struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, bool tx_pause, bool rx_pause); #endif struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *, @@ -282,4 +317,12 @@ int phylink_mii_ioctl(struct phylink *, struct ifreq *, int); void phylink_set_port_modes(unsigned long *bits); void phylink_helper_basex_speed(struct phylink_link_state *state); +void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, + struct phylink_link_state *state); +int phylink_mii_c22_pcs_set_advertisement(struct mdio_device *pcs, + const struct phylink_link_state *state); +void phylink_mii_c22_pcs_an_restart(struct mdio_device *pcs); + +void phylink_mii_c45_pcs_get_state(struct mdio_device *pcs, + struct phylink_link_state *state); #endif diff --git a/include/linux/preempt.h b/include/linux/preempt.h index bbb68dba37cc..bc3f1aecaa19 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -322,4 +322,34 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier, #endif +/** + * migrate_disable - Prevent migration of the current task + * + * Maps to preempt_disable() which also disables preemption. Use + * migrate_disable() to annotate that the intent is to prevent migration, + * but not necessarily preemption. + * + * Can be invoked nested like preempt_disable() and needs the corresponding + * number of migrate_enable() invocations. + */ +static __always_inline void migrate_disable(void) +{ + preempt_disable(); +} + +/** + * migrate_enable - Allow migration of the current task + * + * Counterpart to migrate_disable(). + * + * As migrate_disable() can be invoked nested, only the outermost invocation + * reenables migration. + * + * Currently mapped to preempt_enable(). + */ +static __always_inline void migrate_enable(void) +{ + preempt_enable(); +} + #endif /* __LINUX_PREEMPT_H */ diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 4626b1ac3b6c..adff08bfecf9 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -85,6 +85,8 @@ typedef struct ns_common *ns_get_path_helper_t(void *); extern int ns_get_path_cb(struct path *path, ns_get_path_helper_t ns_get_cb, void *private_data); +extern bool ns_match(const struct ns_common *ns, dev_t dev, ino_t ino); + extern int ns_get_name(char *buf, size_t size, struct task_struct *task, const struct proc_ns_operations *ns_ops); extern void nsfs_init(void); diff --git a/include/linux/remoteproc/qcom_q6v5_ipa_notify.h b/include/linux/remoteproc/qcom_q6v5_ipa_notify.h new file mode 100644 index 000000000000..0820edc0ab7d --- /dev/null +++ b/include/linux/remoteproc/qcom_q6v5_ipa_notify.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Copyright (C) 2019 Linaro Ltd. */ + +#ifndef __QCOM_Q6V5_IPA_NOTIFY_H__ +#define __QCOM_Q6V5_IPA_NOTIFY_H__ + +#if IS_ENABLED(CONFIG_QCOM_Q6V5_IPA_NOTIFY) + +#include <linux/remoteproc.h> + +enum qcom_rproc_event { + MODEM_STARTING = 0, /* Modem is about to be started */ + MODEM_RUNNING = 1, /* Startup complete; modem is operational */ + MODEM_STOPPING = 2, /* Modem is about to shut down */ + MODEM_CRASHED = 3, /* Modem has crashed (implies stopping) */ + MODEM_OFFLINE = 4, /* Modem is now offline */ + MODEM_REMOVING = 5, /* Modem is about to be removed */ +}; + +typedef void (*qcom_ipa_notify_t)(void *data, enum qcom_rproc_event event); + +struct qcom_rproc_ipa_notify { + struct rproc_subdev subdev; + + qcom_ipa_notify_t notify; + void *data; +}; + +/** + * qcom_add_ipa_notify_subdev() - Register IPA notification subdevice + * @rproc: rproc handle + * @ipa_notify: IPA notification subdevice handle + * + * Register the @ipa_notify subdevice with the @rproc so modem events + * can be sent to IPA when they occur. + * + * This is defined in "qcom_q6v5_ipa_notify.c". + */ +void qcom_add_ipa_notify_subdev(struct rproc *rproc, + struct qcom_rproc_ipa_notify *ipa_notify); + +/** + * qcom_remove_ipa_notify_subdev() - Remove IPA SSR subdevice + * @rproc: rproc handle + * @ipa_notify: IPA notification subdevice handle + * + * This is defined in "qcom_q6v5_ipa_notify.c". + */ +void qcom_remove_ipa_notify_subdev(struct rproc *rproc, + struct qcom_rproc_ipa_notify *ipa_notify); + +/** + * qcom_register_ipa_notify() - Register IPA notification function + * @rproc: Remote processor handle + * @notify: Non-null IPA notification callback function pointer + * @data: Data supplied to IPA notification callback function + * + * @Return: 0 if successful, or a negative error code otherwise + * + * This is defined in "qcom_q6v5_mss.c". + */ +int qcom_register_ipa_notify(struct rproc *rproc, qcom_ipa_notify_t notify, + void *data); +/** + * qcom_deregister_ipa_notify() - Deregister IPA notification function + * @rproc: Remote processor handle + * + * This is defined in "qcom_q6v5_mss.c". + */ +void qcom_deregister_ipa_notify(struct rproc *rproc); + +#else /* !IS_ENABLED(CONFIG_QCOM_Q6V5_IPA_NOTIFY) */ + +struct qcom_rproc_ipa_notify { /* empty */ }; + +#define qcom_add_ipa_notify_subdev(rproc, ipa_notify) /* no-op */ +#define qcom_remove_ipa_notify_subdev(rproc, ipa_notify) /* no-op */ + +#endif /* !IS_ENABLED(CONFIG_QCOM_Q6V5_IPA_NOTIFY) */ + +#endif /* !__QCOM_Q6V5_IPA_NOTIFY_H__ */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e59620234415..e47895082b4b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3516,23 +3516,15 @@ int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue, struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, struct sk_buff_head *queue, unsigned int flags, - void (*destructor)(struct sock *sk, - struct sk_buff *skb), int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_try_recv_datagram(struct sock *sk, struct sk_buff_head *queue, - unsigned int flags, - void (*destructor)(struct sock *sk, - struct sk_buff *skb), - int *off, int *err, + unsigned int flags, int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_recv_datagram(struct sock *sk, struct sk_buff_head *sk_queue, - unsigned int flags, - void (*destructor)(struct sock *sk, - struct sk_buff *skb), - int *off, int *err); + unsigned int flags, int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock, int *err); __poll_t datagram_poll(struct file *file, struct socket *sock, diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 14d61bba0b79..8a709f63c5e5 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -323,14 +323,6 @@ static inline void sk_psock_free_link(struct sk_psock_link *link) } struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock); -#if defined(CONFIG_BPF_STREAM_PARSER) -void sk_psock_unlink(struct sock *sk, struct sk_psock_link *link); -#else -static inline void sk_psock_unlink(struct sock *sk, - struct sk_psock_link *link) -{ -} -#endif void __sk_psock_purge_ingress_msg(struct sk_psock *psock); @@ -347,33 +339,37 @@ static inline void sk_psock_update_proto(struct sock *sk, struct sk_psock *psock, struct proto *ops) { - psock->saved_unhash = sk->sk_prot->unhash; - psock->saved_close = sk->sk_prot->close; - psock->saved_write_space = sk->sk_write_space; + /* Initialize saved callbacks and original proto only once, since this + * function may be called multiple times for a psock, e.g. when + * psock->progs.msg_parser is updated. + * + * Since we've not installed the new proto, psock is not yet in use and + * we can initialize it without synchronization. + */ + if (!psock->sk_proto) { + struct proto *orig = READ_ONCE(sk->sk_prot); - psock->sk_proto = sk->sk_prot; - sk->sk_prot = ops; + psock->saved_unhash = orig->unhash; + psock->saved_close = orig->close; + psock->saved_write_space = sk->sk_write_space; + + psock->sk_proto = orig; + } + + /* Pairs with lockless read in sk_clone_lock() */ + WRITE_ONCE(sk->sk_prot, ops); } static inline void sk_psock_restore_proto(struct sock *sk, struct sk_psock *psock) { sk->sk_prot->unhash = psock->saved_unhash; - - if (psock->sk_proto) { - struct inet_connection_sock *icsk = inet_csk(sk); - bool has_ulp = !!icsk->icsk_ulp_data; - - if (has_ulp) { - tcp_update_ulp(sk, psock->sk_proto, - psock->saved_write_space); - } else { - sk->sk_prot = psock->sk_proto; - sk->sk_write_space = psock->saved_write_space; - } - psock->sk_proto = NULL; + if (inet_csk_has_ulp(sk)) { + tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space); } else { sk->sk_write_space = psock->saved_write_space; + /* Pairs with lockless read in sk_clone_lock() */ + WRITE_ONCE(sk->sk_prot, psock->sk_proto); } } @@ -395,26 +391,6 @@ static inline bool sk_psock_test_state(const struct sk_psock *psock, return test_bit(bit, &psock->state); } -static inline struct sk_psock *sk_psock_get_checked(struct sock *sk) -{ - struct sk_psock *psock; - - rcu_read_lock(); - psock = sk_psock(sk); - if (psock) { - if (sk->sk_prot->recvmsg != tcp_bpf_recvmsg) { - psock = ERR_PTR(-EBUSY); - goto out; - } - - if (!refcount_inc_not_zero(&psock->refcnt)) - psock = ERR_PTR(-EBUSY); - } -out: - rcu_read_unlock(); - return psock; -} - static inline struct sk_psock *sk_psock_get(struct sock *sk) { struct sk_psock *psock; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 19190c609282..fbafb353e9be 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -80,6 +80,7 @@ struct stmmac_mdio_bus_data { unsigned int phy_mask; + unsigned int has_xpcs; int *irqs; int probed_phy_irq; bool needs_reset; diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index fa7ee503fb76..4beb51009b62 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -310,6 +310,18 @@ static inline void sysfs_enable_ns(struct kernfs_node *kn) return kernfs_enable_ns(kn); } +int sysfs_file_change_owner(struct kobject *kobj, const char *name, kuid_t kuid, + kgid_t kgid); +int sysfs_change_owner(struct kobject *kobj, kuid_t kuid, kgid_t kgid); +int sysfs_link_change_owner(struct kobject *kobj, struct kobject *targ, + const char *name, kuid_t kuid, kgid_t kgid); +int sysfs_groups_change_owner(struct kobject *kobj, + const struct attribute_group **groups, + kuid_t kuid, kgid_t kgid); +int sysfs_group_change_owner(struct kobject *kobj, + const struct attribute_group *groups, kuid_t kuid, + kgid_t kgid); + #else /* CONFIG_SYSFS */ static inline int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) @@ -522,6 +534,40 @@ static inline void sysfs_enable_ns(struct kernfs_node *kn) { } +static inline int sysfs_file_change_owner(struct kobject *kobj, + const char *name, kuid_t kuid, + kgid_t kgid) +{ + return 0; +} + +static inline int sysfs_link_change_owner(struct kobject *kobj, + struct kobject *targ, + const char *name, kuid_t kuid, + kgid_t kgid) +{ + return 0; +} + +static inline int sysfs_change_owner(struct kobject *kobj, kuid_t kuid, kgid_t kgid) +{ + return 0; +} + +static inline int sysfs_groups_change_owner(struct kobject *kobj, + const struct attribute_group **groups, + kuid_t kuid, kgid_t kgid) +{ + return 0; +} + +static inline int sysfs_group_change_owner(struct kobject *kobj, + const struct attribute_group *groups, + kuid_t kuid, kgid_t kgid) +{ + return 0; +} + #endif /* CONFIG_SYSFS */ static inline int __must_check sysfs_create_file(struct kobject *kobj, diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 1646c06989df..0ce4377545f8 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -46,9 +46,12 @@ #define CDC_NCM_DATA_ALTSETTING_NCM 1 #define CDC_NCM_DATA_ALTSETTING_MBIM 2 -/* CDC NCM subclass 3.2.1 */ +/* CDC NCM subclass 3.3.1 */ #define USB_CDC_NCM_NDP16_LENGTH_MIN 0x10 +/* CDC NCM subclass 3.3.2 */ +#define USB_CDC_NCM_NDP32_LENGTH_MIN 0x20 + /* Maximum NTB length */ #define CDC_NCM_NTB_MAX_SIZE_TX 32768 /* bytes */ #define CDC_NCM_NTB_MAX_SIZE_RX 32768 /* bytes */ @@ -84,7 +87,7 @@ /* Driver flags */ #define CDC_NCM_FLAG_NDP_TO_END 0x02 /* NDP is placed at end of frame */ #define CDC_MBIM_FLAG_AVOID_ALTSETTING_TOGGLE 0x04 /* Avoid altsetting toggle during init */ -#define CDC_NCM_FLAG_RESET_NTB16 0x08 /* set NDP16 one more time after altsetting switch */ +#define CDC_NCM_FLAG_PREFER_NTB32 0x08 /* prefer NDP32 over NDP16 */ #define cdc_ncm_comm_intf_is_mbim(x) ((x)->desc.bInterfaceSubClass == USB_CDC_SUBCLASS_MBIM && \ (x)->desc.bInterfaceProtocol == USB_CDC_PROTO_NONE) @@ -113,7 +116,11 @@ struct cdc_ncm_ctx { u32 timer_interval; u32 max_ndp_size; - struct usb_cdc_ncm_ndp16 *delayed_ndp16; + u8 is_ndp16; + union { + struct usb_cdc_ncm_ndp16 *delayed_ndp16; + struct usb_cdc_ncm_ndp32 *delayed_ndp32; + }; u32 tx_timer_pending; u32 tx_curr_frame_num; @@ -150,6 +157,8 @@ void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf); struct sk_buff *cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign); int cdc_ncm_rx_verify_nth16(struct cdc_ncm_ctx *ctx, struct sk_buff *skb_in); int cdc_ncm_rx_verify_ndp16(struct sk_buff *skb_in, int ndpoffset); +int cdc_ncm_rx_verify_nth32(struct cdc_ncm_ctx *ctx, struct sk_buff *skb_in); +int cdc_ncm_rx_verify_ndp32(struct sk_buff *skb_in, int ndpoffset); struct sk_buff * cdc_ncm_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags); int cdc_ncm_rx_fixup(struct usbnet *dev, struct sk_buff *skb_in); |