diff options
Diffstat (limited to 'include/linux')
39 files changed, 1331 insertions, 278 deletions
diff --git a/include/linux/acpi_amd_wbrf.h b/include/linux/acpi_amd_wbrf.h new file mode 100644 index 000000000000..898f31d536d4 --- /dev/null +++ b/include/linux/acpi_amd_wbrf.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Wifi Band Exclusion Interface (AMD ACPI Implementation) + * Copyright (C) 2023 Advanced Micro Devices + */ + +#ifndef _ACPI_AMD_WBRF_H +#define _ACPI_AMD_WBRF_H + +#include <linux/device.h> +#include <linux/notifier.h> + +/* The maximum number of frequency band ranges */ +#define MAX_NUM_OF_WBRF_RANGES 11 + +/* Record actions */ +#define WBRF_RECORD_ADD 0x0 +#define WBRF_RECORD_REMOVE 0x1 + +/** + * struct freq_band_range - Wifi frequency band range definition + * @start: start frequency point (in Hz) + * @end: end frequency point (in Hz) + */ +struct freq_band_range { + u64 start; + u64 end; +}; + +/** + * struct wbrf_ranges_in_out - wbrf ranges info + * @num_of_ranges: total number of band ranges in this struct + * @band_list: array of Wifi band ranges + */ +struct wbrf_ranges_in_out { + u64 num_of_ranges; + struct freq_band_range band_list[MAX_NUM_OF_WBRF_RANGES]; +}; + +/** + * enum wbrf_notifier_actions - wbrf notifier actions index + * @WBRF_CHANGED: there was some frequency band updates. The consumers + * should retrieve the latest active frequency bands. + */ +enum wbrf_notifier_actions { + WBRF_CHANGED, +}; + +#if IS_ENABLED(CONFIG_AMD_WBRF) +bool acpi_amd_wbrf_supported_producer(struct device *dev); +int acpi_amd_wbrf_add_remove(struct device *dev, uint8_t action, struct wbrf_ranges_in_out *in); +bool acpi_amd_wbrf_supported_consumer(struct device *dev); +int amd_wbrf_retrieve_freq_band(struct device *dev, struct wbrf_ranges_in_out *out); +int amd_wbrf_register_notifier(struct notifier_block *nb); +int amd_wbrf_unregister_notifier(struct notifier_block *nb); +#else +static inline +bool acpi_amd_wbrf_supported_consumer(struct device *dev) +{ + return false; +} + +static inline +int acpi_amd_wbrf_add_remove(struct device *dev, uint8_t action, struct wbrf_ranges_in_out *in) +{ + return -ENODEV; +} + +static inline +bool acpi_amd_wbrf_supported_producer(struct device *dev) +{ + return false; +} +static inline +int amd_wbrf_retrieve_freq_band(struct device *dev, struct wbrf_ranges_in_out *out) +{ + return -ENODEV; +} +static inline +int amd_wbrf_register_notifier(struct notifier_block *nb) +{ + return -ENODEV; +} +static inline +int amd_wbrf_unregister_notifier(struct notifier_block *nb) +{ + return -ENODEV; +} +#endif /* CONFIG_AMD_WBRF */ + +#endif /* _ACPI_AMD_WBRF_H */ diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 6b3acf15be5c..a44d9dc7e3eb 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -118,6 +118,7 @@ enum virtchnl_ops { VIRTCHNL_OP_GET_STATS = 15, VIRTCHNL_OP_RSVD = 16, VIRTCHNL_OP_EVENT = 17, /* must ALWAYS be 17 */ + VIRTCHNL_OP_CONFIG_RSS_HFUNC = 18, /* opcode 19 is reserved */ VIRTCHNL_OP_IWARP = 20, /* advanced opcode */ VIRTCHNL_OP_RDMA = VIRTCHNL_OP_IWARP, @@ -911,6 +912,29 @@ struct virtchnl_rss_hena { VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_rss_hena); +/* Type of RSS algorithm */ +enum virtchnl_rss_algorithm { + VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC = 0, + VIRTCHNL_RSS_ALG_R_ASYMMETRIC = 1, + VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC = 2, + VIRTCHNL_RSS_ALG_XOR_SYMMETRIC = 3, +}; + +/* VIRTCHNL_OP_CONFIG_RSS_HFUNC + * VF sends this message to configure the RSS hash function. Only supported + * if both PF and VF drivers set the VIRTCHNL_VF_OFFLOAD_RSS_PF bit during + * configuration negotiation. + * The hash function is initialized to VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC + * by the PF. + */ +struct virtchnl_rss_hfunc { + u16 vsi_id; + u16 rss_algorithm; /* enum virtchnl_rss_algorithm */ + u32 reserved; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_rss_hfunc); + /* VIRTCHNL_OP_ENABLE_CHANNELS * VIRTCHNL_OP_DISABLE_CHANNELS * VF sends these messages to enable or disable channels based on @@ -1095,14 +1119,6 @@ enum virtchnl_vfr_states { VIRTCHNL_VFR_VFACTIVE, }; -/* Type of RSS algorithm */ -enum virtchnl_rss_algorithm { - VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC = 0, - VIRTCHNL_RSS_ALG_R_ASYMMETRIC = 1, - VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC = 2, - VIRTCHNL_RSS_ALG_XOR_SYMMETRIC = 3, -}; - #define VIRTCHNL_MAX_NUM_PROTO_HDRS 32 #define PROTO_HDR_SHIFT 5 #define PROTO_HDR_FIELD_START(proto_hdr_type) ((proto_hdr_type) << PROTO_HDR_SHIFT) @@ -1542,6 +1558,9 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, vrl->lut_entries); } break; + case VIRTCHNL_OP_CONFIG_RSS_HFUNC: + valid_len = sizeof(struct virtchnl_rss_hfunc); + break; case VIRTCHNL_OP_GET_RSS_HENA_CAPS: break; case VIRTCHNL_OP_SET_RSS_HENA: diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cff5bb08820e..7a8d4c81a39a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -29,6 +29,7 @@ #include <linux/rcupdate_trace.h> #include <linux/static_call.h> #include <linux/memcontrol.h> +#include <linux/cfi.h> struct bpf_verifier_env; struct bpf_verifier_log; @@ -106,7 +107,11 @@ struct bpf_map_ops { /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, int fd); - void (*map_fd_put_ptr)(void *ptr); + /* If need_defer is true, the implementation should guarantee that + * the to-be-put element is still alive before the bpf program, which + * may manipulate it, exists. + */ + void (*map_fd_put_ptr)(struct bpf_map *map, void *ptr, bool need_defer); int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_fd_sys_lookup_elem)(void *ptr); void (*map_seq_show_elem)(struct bpf_map *map, void *key, @@ -186,8 +191,8 @@ enum btf_field_type { BPF_LIST_NODE = (1 << 6), BPF_RB_ROOT = (1 << 7), BPF_RB_NODE = (1 << 8), - BPF_GRAPH_NODE_OR_ROOT = BPF_LIST_NODE | BPF_LIST_HEAD | - BPF_RB_NODE | BPF_RB_ROOT, + BPF_GRAPH_NODE = BPF_RB_NODE | BPF_LIST_NODE, + BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD, BPF_REFCOUNT = (1 << 9), }; @@ -272,7 +277,11 @@ struct bpf_map { */ atomic64_t refcnt ____cacheline_aligned; atomic64_t usercnt; - struct work_struct work; + /* rcu is used before freeing and work is only used during freeing */ + union { + struct work_struct work; + struct rcu_head rcu; + }; struct mutex freeze_mutex; atomic64_t writecnt; /* 'Ownership' of program-containing map is claimed by the first program @@ -288,6 +297,9 @@ struct bpf_map { } owner; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ + bool free_after_mult_rcu_gp; + bool free_after_rcu_gp; + atomic64_t sleepable_refcnt; s64 __percpu *elem_count; }; @@ -1044,6 +1056,17 @@ struct btf_func_model { */ #define BPF_TRAMP_F_TAIL_CALL_CTX BIT(7) +/* + * Indicate the trampoline should be suitable to receive indirect calls; + * without this indirectly calling the generated code can result in #UD/#CP, + * depending on the CFI options. + * + * Used by bpf_struct_ops. + * + * Incompatible with FENTRY usage, overloads @func_addr argument. + */ +#define BPF_TRAMP_F_INDIRECT BIT(8) + /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. */ @@ -1083,10 +1106,17 @@ struct bpf_tramp_run_ctx; * fexit = a set of program to run after original function */ struct bpf_tramp_image; -int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, - void *orig_call); + void *func_addr); +void *arch_alloc_bpf_trampoline(unsigned int size); +void arch_free_bpf_trampoline(void *image, unsigned int size); +void arch_protect_bpf_trampoline(void *image, unsigned int size); +void arch_unprotect_bpf_trampoline(void *image, unsigned int size); +int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *func_addr); + u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start, @@ -1119,6 +1149,7 @@ enum bpf_tramp_prog_type { struct bpf_tramp_image { void *image; + int size; struct bpf_ksym ksym; struct percpu_ref pcref; void *ip_after_call; @@ -1188,7 +1219,11 @@ struct bpf_dispatcher { #endif }; -static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func( +#ifndef __bpfcall +#define __bpfcall __nocfi +#endif + +static __always_inline __bpfcall unsigned int bpf_dispatcher_nop_func( const void *ctx, const struct bpf_insn *insnsi, bpf_func_t bpf_func) @@ -1226,6 +1261,8 @@ enum bpf_dynptr_type { int bpf_dynptr_check_size(u32 size); u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr); +const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len); +void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len); #ifdef CONFIG_BPF_JIT int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); @@ -1278,7 +1315,7 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func #define DEFINE_BPF_DISPATCHER(name) \ __BPF_DISPATCHER_SC(name); \ - noinline __nocfi unsigned int bpf_dispatcher_##name##_func( \ + noinline __bpfcall unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ bpf_func_t bpf_func) \ @@ -1301,7 +1338,7 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to); /* Called only from JIT-enabled code, so there's no need for stubs. */ -void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym); +void bpf_image_ksym_add(void *data, unsigned int size, 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); @@ -1345,6 +1382,8 @@ static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog) struct bpf_func_info_aux { u16 linkage; bool unreliable; + bool called : 1; + bool verified : 1; }; enum bpf_jit_poke_reason { @@ -1426,6 +1465,9 @@ struct bpf_prog_aux { struct bpf_kfunc_desc_tab *kfunc_tab; struct bpf_kfunc_btf_tab *kfunc_btf_tab; u32 size_poke_tab; +#ifdef CONFIG_FINEIBT + struct bpf_ksym ksym_prefix; +#endif struct bpf_ksym ksym; const struct bpf_prog_ops *ops; struct bpf_map **used_maps; @@ -1438,7 +1480,7 @@ struct bpf_prog_aux { int cgroup_atype; /* enum cgroup_bpf_attach_type */ struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; - unsigned int (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp); + u64 (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp, u64, u64); #ifdef CONFIG_SECURITY void *security; #endif @@ -1636,6 +1678,7 @@ struct bpf_struct_ops { struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS]; u32 type_id; u32 value_id; + void *cfi_stubs; }; #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) @@ -1649,6 +1692,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, struct bpf_tramp_link *link, const struct btf_func_model *model, + void *stub_func, void *image, void *image_end); static inline bool bpf_try_module_get(const void *data, struct module *owner) { @@ -2427,7 +2471,7 @@ int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs); int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *reg, bool is_ex_cb); + struct bpf_reg_state *reg, u32 *nargs); int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, struct btf *btf, const struct btf_type *t); const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index aa4d19d0bc94..c2819a6579a5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -275,6 +275,11 @@ struct bpf_reference_state { int callback_ref; }; +struct bpf_retval_range { + s32 minval; + s32 maxval; +}; + /* state of the program: * type of all registers and stack info */ @@ -297,8 +302,8 @@ struct bpf_func_state { * void foo(void) { bpf_timer_set_callback(,foo); } */ u32 async_entry_cnt; + struct bpf_retval_range callback_ret_range; bool in_callback_fn; - struct tnum callback_ret_range; bool in_async_callback_fn; bool in_exception_callback_fn; /* For callback calling functions that limit number of possible @@ -316,16 +321,48 @@ struct bpf_func_state { /* The following fields should be last. See copy_func_state() */ int acquired_refs; struct bpf_reference_state *refs; - int allocated_stack; + /* The state of the stack. Each element of the array describes BPF_REG_SIZE + * (i.e. 8) bytes worth of stack memory. + * stack[0] represents bytes [*(r10-8)..*(r10-1)] + * stack[1] represents bytes [*(r10-16)..*(r10-9)] + * ... + * stack[allocated_stack/8 - 1] represents [*(r10-allocated_stack)..*(r10-allocated_stack+7)] + */ struct bpf_stack_state *stack; + /* Size of the current stack, in bytes. The stack state is tracked below, in + * `stack`. allocated_stack is always a multiple of BPF_REG_SIZE. + */ + int allocated_stack; +}; + +#define MAX_CALL_FRAMES 8 + +/* instruction history flags, used in bpf_jmp_history_entry.flags field */ +enum { + /* instruction references stack slot through PTR_TO_STACK register; + * we also store stack's frame number in lower 3 bits (MAX_CALL_FRAMES is 8) + * and accessed stack slot's index in next 6 bits (MAX_BPF_STACK is 512, + * 8 bytes per slot, so slot index (spi) is [0, 63]) + */ + INSN_F_FRAMENO_MASK = 0x7, /* 3 bits */ + + INSN_F_SPI_MASK = 0x3f, /* 6 bits */ + INSN_F_SPI_SHIFT = 3, /* shifted 3 bits to the left */ + + INSN_F_STACK_ACCESS = BIT(9), /* we need 10 bits total */ }; -struct bpf_idx_pair { - u32 prev_idx; +static_assert(INSN_F_FRAMENO_MASK + 1 >= MAX_CALL_FRAMES); +static_assert(INSN_F_SPI_MASK + 1 >= MAX_BPF_STACK / 8); + +struct bpf_jmp_history_entry { u32 idx; + /* insn idx can't be bigger than 1 million */ + u32 prev_idx : 22; + /* special flags, e.g., whether insn is doing register stack spill/load */ + u32 flags : 10; }; -#define MAX_CALL_FRAMES 8 /* Maximum number of register states that can exist at once */ #define BPF_ID_MAP_SIZE ((MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) * MAX_CALL_FRAMES) struct bpf_verifier_state { @@ -408,7 +445,7 @@ struct bpf_verifier_state { * For most states jmp_history_cnt is [0-3]. * For loops can go up to ~40. */ - struct bpf_idx_pair *jmp_history; + struct bpf_jmp_history_entry *jmp_history; u32 jmp_history_cnt; u32 dfs_depth; u32 callback_unroll_depth; @@ -574,12 +611,12 @@ struct bpf_subprog_info { u32 start; /* insn idx of function entry point */ u32 linfo_idx; /* The idx to the main_prog->aux->linfo */ u16 stack_depth; /* max. stack depth used by this function */ - bool has_tail_call; - bool tail_call_reachable; - bool has_ld_abs; - bool is_cb; - bool is_async_cb; - bool is_exception_cb; + bool has_tail_call: 1; + bool tail_call_reachable: 1; + bool has_ld_abs: 1; + bool is_cb: 1; + bool is_async_cb: 1; + bool is_exception_cb: 1; }; struct bpf_verifier_env; @@ -618,6 +655,7 @@ struct bpf_verifier_env { int stack_size; /* number of states to be processed */ bool strict_alignment; /* perform strict pointer alignment checks */ bool test_state_freq; /* test verifier with different pruning frequency */ + bool test_reg_invariants; /* fail verification on register invariants violations */ struct bpf_verifier_state *cur_state; /* current verifier state */ struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ struct bpf_verifier_state_list *free_list; @@ -630,6 +668,10 @@ struct bpf_verifier_env { int exception_callback_subprog; bool explore_alu_limits; bool allow_ptr_leaks; + /* Allow access to uninitialized stack memory. Writes with fixed offset are + * always allowed, so this refers to reads (with fixed or variable offset), + * to writes with variable offset and to indirect (helper) accesses. + */ bool allow_uninit_stack; bool bpf_capable; bool bypass_spec_v1; @@ -650,6 +692,7 @@ struct bpf_verifier_env { int cur_stack; } cfg; struct backtrack_state bt; + struct bpf_jmp_history_entry *cur_hist_ent; u32 pass_cnt; /* number of times do_check() was called */ u32 subprog_cnt; /* number of instructions analyzed by the verifier */ @@ -695,6 +738,10 @@ int bpf_vlog_init(struct bpf_verifier_log *log, u32 log_level, void bpf_vlog_reset(struct bpf_verifier_log *log, u64 new_pos); int bpf_vlog_finalize(struct bpf_verifier_log *log, u32 *log_size_actual); +__printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env, + u32 insn_off, + const char *prefix_fmt, ...); + static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { struct bpf_verifier_state *cur = env->cur_state; @@ -794,4 +841,76 @@ static inline bool bpf_type_has_unsafe_modifiers(u32 type) return type_flag(type) & ~BPF_REG_TRUSTED_MODIFIERS; } +static inline bool type_is_ptr_alloc_obj(u32 type) +{ + return base_type(type) == PTR_TO_BTF_ID && type_flag(type) & MEM_ALLOC; +} + +static inline bool type_is_non_owning_ref(u32 type) +{ + return type_is_ptr_alloc_obj(type) && type_flag(type) & NON_OWN_REF; +} + +static inline bool type_is_pkt_pointer(enum bpf_reg_type type) +{ + type = base_type(type); + return type == PTR_TO_PACKET || + type == PTR_TO_PACKET_META; +} + +static inline bool type_is_sk_pointer(enum bpf_reg_type type) +{ + return type == PTR_TO_SOCKET || + type == PTR_TO_SOCK_COMMON || + type == PTR_TO_TCP_SOCK || + type == PTR_TO_XDP_SOCK; +} + +static inline void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno) +{ + env->scratched_regs |= 1U << regno; +} + +static inline void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi) +{ + env->scratched_stack_slots |= 1ULL << spi; +} + +static inline bool reg_scratched(const struct bpf_verifier_env *env, u32 regno) +{ + return (env->scratched_regs >> regno) & 1; +} + +static inline bool stack_slot_scratched(const struct bpf_verifier_env *env, u64 regno) +{ + return (env->scratched_stack_slots >> regno) & 1; +} + +static inline bool verifier_state_scratched(const struct bpf_verifier_env *env) +{ + return env->scratched_regs || env->scratched_stack_slots; +} + +static inline void mark_verifier_state_clean(struct bpf_verifier_env *env) +{ + env->scratched_regs = 0U; + env->scratched_stack_slots = 0ULL; +} + +/* Used for printing the entire verifier state. */ +static inline void mark_verifier_state_scratched(struct bpf_verifier_env *env) +{ + env->scratched_regs = ~0U; + env->scratched_stack_slots = ~0ULL; +} + +const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type); +const char *dynptr_type_str(enum bpf_dynptr_type type); +const char *iter_type_str(const struct btf *btf, u32 btf_id); +const char *iter_state_str(enum bpf_iter_state state); + +void print_verifier_state(struct bpf_verifier_env *env, + const struct bpf_func_state *state, bool print_all); +void print_insn_state(struct bpf_verifier_env *env, const struct bpf_func_state *state); + #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/cache.h b/include/linux/cache.h index 9900d20b76c2..0ecb17bb6883 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -85,6 +85,31 @@ #define cache_line_size() L1_CACHE_BYTES #endif +#ifndef __cacheline_group_begin +#define __cacheline_group_begin(GROUP) \ + __u8 __cacheline_group_begin__##GROUP[0] +#endif + +#ifndef __cacheline_group_end +#define __cacheline_group_end(GROUP) \ + __u8 __cacheline_group_end__##GROUP[0] +#endif + +#ifndef CACHELINE_ASSERT_GROUP_MEMBER +#define CACHELINE_ASSERT_GROUP_MEMBER(TYPE, GROUP, MEMBER) \ + BUILD_BUG_ON(!(offsetof(TYPE, MEMBER) >= \ + offsetofend(TYPE, __cacheline_group_begin__##GROUP) && \ + offsetofend(TYPE, MEMBER) <= \ + offsetof(TYPE, __cacheline_group_end__##GROUP))) +#endif + +#ifndef CACHELINE_ASSERT_GROUP_SIZE +#define CACHELINE_ASSERT_GROUP_SIZE(TYPE, GROUP, SIZE) \ + BUILD_BUG_ON(offsetof(TYPE, __cacheline_group_end__##GROUP) - \ + offsetofend(TYPE, __cacheline_group_begin__##GROUP) > \ + SIZE) +#endif + /* * Helper to add padding within a struct to ensure data fall into separate * cachelines. diff --git a/include/linux/cfi.h b/include/linux/cfi.h index 3552ec82b725..f0df518e11dd 100644 --- a/include/linux/cfi.h +++ b/include/linux/cfi.h @@ -9,6 +9,14 @@ #include <linux/bug.h> #include <linux/module.h> +#include <asm/cfi.h> + +#ifndef cfi_get_offset +static inline int cfi_get_offset(void) +{ + return 0; +} +#endif #ifdef CONFIG_CFI_CLANG enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr, @@ -38,4 +46,8 @@ static inline void module_cfi_finalize(const Elf_Ehdr *hdr, #endif /* CONFIG_ARCH_USES_CFI_TRAPS */ #endif /* CONFIG_MODULES */ +#ifndef CFI_NOSEAL +#define CFI_NOSEAL(x) +#endif + #endif /* _LINUX_CFI_H */ diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 4a6b6b77ccb6..4caab0c6b361 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -563,6 +563,7 @@ struct cgroup_root { /* A list running through the active hierarchies */ struct list_head root_list; + struct rcu_head rcu; /* Hierarchy-specific flags */ unsigned int flags; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 0ef0af66080e..34aaf0e87def 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -69,6 +69,7 @@ struct css_task_iter { extern struct file_system_type cgroup_fs_type; extern struct cgroup_root cgrp_dfl_root; extern struct css_set init_css_set; +extern spinlock_t css_set_lock; #define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys; #include <linux/cgroup_subsys.h> @@ -386,7 +387,6 @@ static inline void cgroup_unlock(void) * as locks used during the cgroup_subsys::attach() methods. */ #ifdef CONFIG_PROVE_RCU -extern spinlock_t css_set_lock; #define task_css_set_check(task, __c) \ rcu_dereference_check((task)->cgroups, \ rcu_read_lock_sched_held() || \ @@ -853,4 +853,6 @@ static inline void cgroup_bpf_put(struct cgroup *cgrp) {} #endif /* CONFIG_CGROUP_BPF */ +struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id); + #endif /* _LINUX_CGROUP_H */ diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 2ceba3fe4ec1..aebb65bf95a7 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -136,7 +136,7 @@ #endif #define __diag_ignore_all(option, comment) \ - __diag_GCC(8, ignore, option) + __diag(__diag_GCC_ignore option) /* * Prior to 9.1, -Wno-alloc-size-larger-than (and therefore the "alloc_size" diff --git a/include/linux/connector.h b/include/linux/connector.h index cec2d99ae902..70bc1160f3d8 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -100,8 +100,7 @@ void cn_del_callback(const struct cb_id *id); */ int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 group, gfp_t gfp_mask, - int (*filter)(struct sock *dsk, struct sk_buff *skb, - void *data), + netlink_filter_fn filter, void *filter_data); /** diff --git a/include/linux/dpll.h b/include/linux/dpll.h index 578fc5fa3750..b1a5f9ca8ee5 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -17,9 +17,6 @@ struct dpll_pin; struct dpll_device_ops { int (*mode_get)(const struct dpll_device *dpll, void *dpll_priv, enum dpll_mode *mode, struct netlink_ext_ack *extack); - bool (*mode_supported)(const struct dpll_device *dpll, void *dpll_priv, - const enum dpll_mode mode, - struct netlink_ext_ack *extack); int (*lock_status_get)(const struct dpll_device *dpll, void *dpll_priv, enum dpll_lock_status *status, struct netlink_ext_ack *extack); diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 689028257fcc..cfcd952a1d4f 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -95,6 +95,7 @@ struct kernel_ethtool_ringparam { * @ETHTOOL_RING_USE_TX_PUSH: capture for setting tx_push * @ETHTOOL_RING_USE_RX_PUSH: capture for setting rx_push * @ETHTOOL_RING_USE_TX_PUSH_BUF_LEN: capture for setting tx_push_buf_len + * @ETHTOOL_RING_USE_TCP_DATA_SPLIT: capture for setting tcp_data_split */ enum ethtool_supported_ring_param { ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), @@ -102,6 +103,7 @@ enum ethtool_supported_ring_param { ETHTOOL_RING_USE_TX_PUSH = BIT(2), ETHTOOL_RING_USE_RX_PUSH = BIT(3), ETHTOOL_RING_USE_TX_PUSH_BUF_LEN = BIT(4), + ETHTOOL_RING_USE_TCP_DATA_SPLIT = BIT(5), }; #define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit)) @@ -595,9 +597,46 @@ struct ethtool_mm_stats { }; /** + * struct ethtool_rxfh_param - RXFH (RSS) parameters + * @hfunc: Defines the current RSS hash function used by HW (or to be set to). + * Valid values are one of the %ETH_RSS_HASH_*. + * @indir_size: On SET, the array size of the user buffer for the + * indirection table, which may be zero, or + * %ETH_RXFH_INDIR_NO_CHANGE. On GET (read from the driver), + * the array size of the hardware indirection table. + * @indir: The indirection table of size @indir_size entries. + * @key_size: On SET, the array size of the user buffer for the hash key, + * which may be zero. On GET (read from the driver), the size of the + * hardware hash key. + * @key: The hash key of size @key_size bytes. + * @rss_context: RSS context identifier. Context 0 is the default for normal + * traffic; other contexts can be referenced as the destination for RX flow + * classification rules. On SET, %ETH_RXFH_CONTEXT_ALLOC is used + * to allocate a new RSS context; on return this field will + * contain the ID of the newly allocated context. + * @rss_delete: Set to non-ZERO to remove the @rss_context context. + * @input_xfrm: Defines how the input data is transformed. Valid values are one + * of %RXH_XFRM_*. + */ +struct ethtool_rxfh_param { + u8 hfunc; + u32 indir_size; + u32 *indir; + u32 key_size; + u8 *key; + u32 rss_context; + u8 rss_delete; + u8 input_xfrm; +}; + +/** * struct ethtool_ops - optional netdev operations * @cap_link_lanes_supported: indicates if the driver supports lanes * parameter. + * @cap_rss_ctx_supported: indicates if the driver supports RSS + * contexts. + * @cap_rss_sym_xor_supported: indicates if the driver supports symmetric-xor + * RSS. * @supported_coalesce_params: supported types of interrupt coalescing. * @supported_ring_params: supported ring params. * @get_drvinfo: Report driver/device information. Modern drivers no @@ -694,15 +733,6 @@ struct ethtool_mm_stats { * will remain unchanged. * Returns a negative error code or zero. An error code must be returned * if at least one unsupported change was requested. - * @get_rxfh_context: Get the contents of the RX flow hash indirection table, - * hash key, and/or hash function assiciated to the given rss context. - * Returns a negative error code or zero. - * @set_rxfh_context: Create, remove and configure RSS contexts. Allows setting - * the contents of the RX flow hash indirection table, hash key, and/or - * hash function associated to the given context. Arguments which are set - * to %NULL or zero will remain unchanged. - * Returns a negative error code or zero. An error code must be returned - * if at least one unsupported change was requested. * @get_channels: Get number of channels. * @set_channels: Set number of channels. Returns a negative error code or * zero. @@ -785,6 +815,8 @@ struct ethtool_mm_stats { */ struct ethtool_ops { u32 cap_link_lanes_supported:1; + u32 cap_rss_ctx_supported:1; + u32 cap_rss_sym_xor_supported:1; u32 supported_coalesce_params; u32 supported_ring_params; void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); @@ -844,15 +876,9 @@ struct ethtool_ops { int (*reset)(struct net_device *, u32 *); u32 (*get_rxfh_key_size)(struct net_device *); u32 (*get_rxfh_indir_size)(struct net_device *); - int (*get_rxfh)(struct net_device *, u32 *indir, u8 *key, - u8 *hfunc); - int (*set_rxfh)(struct net_device *, const u32 *indir, - const u8 *key, const u8 hfunc); - int (*get_rxfh_context)(struct net_device *, u32 *indir, u8 *key, - u8 *hfunc, u32 rss_context); - int (*set_rxfh_context)(struct net_device *, const u32 *indir, - const u8 *key, const u8 hfunc, - u32 *rss_context, bool delete); + int (*get_rxfh)(struct net_device *, struct ethtool_rxfh_param *); + int (*set_rxfh)(struct net_device *, struct ethtool_rxfh_param *, + struct netlink_ext_ack *extack); void (*get_channels)(struct net_device *, struct ethtool_channels *); int (*set_channels)(struct net_device *, struct ethtool_channels *); int (*get_dump_flag)(struct net_device *, struct ethtool_dump *); @@ -1044,6 +1070,14 @@ static inline int ethtool_mm_frag_size_min_to_add(u32 val_min, u32 *val_add, } /** + * ethtool_get_ts_info_by_layer - Obtains time stamping capabilities from the MAC or PHY layer. + * @dev: pointer to net_device structure + * @info: buffer to hold the result + * Returns zero on success, non-zero otherwise. + */ +int ethtool_get_ts_info_by_layer(struct net_device *dev, struct ethtool_ts_info *info); + +/** * ethtool_sprintf - Write formatted string to ethtool string data * @data: Pointer to a pointer to the start of string to update * @fmt: Format of string to write @@ -1053,6 +1087,19 @@ static inline int ethtool_mm_frag_size_min_to_add(u32 val_min, u32 *val_add, */ extern __printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...); +/** + * ethtool_puts - Write string to ethtool string data + * @data: Pointer to a pointer to the start of string to update + * @str: String to write + * + * Write string to *data without a trailing newline. Update *data + * to point at start of next string. + * + * Prefer this function to ethtool_sprintf() when given only + * two arguments or if @fmt is just "%s". + */ +extern void ethtool_puts(u8 **data, const char *str); + /* Link mode to forced speed capabilities maps */ struct ethtool_forced_speed_map { u32 speed; diff --git a/include/linux/filter.h b/include/linux/filter.h index a4953fafc8cb..68fb6c8142fe 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1067,7 +1067,7 @@ struct bpf_binary_header * bpf_jit_binary_pack_hdr(const struct bpf_prog *fp); void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns); -void bpf_prog_pack_free(struct bpf_binary_header *hdr); +void bpf_prog_pack_free(void *ptr, u32 size); static inline bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp) { diff --git a/include/linux/firmware.h b/include/linux/firmware.h index de7fea3bca51..0311858b46ce 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -27,6 +27,7 @@ struct firmware { * @FW_UPLOAD_ERR_INVALID_SIZE: invalid firmware image size * @FW_UPLOAD_ERR_RW_ERROR: read or write to HW failed, see kernel log * @FW_UPLOAD_ERR_WEAROUT: FLASH device is approaching wear-out, wait & retry + * @FW_UPLOAD_ERR_FW_INVALID: invalid firmware file * @FW_UPLOAD_ERR_MAX: Maximum error code marker */ enum fw_upload_err { @@ -38,6 +39,7 @@ enum fw_upload_err { FW_UPLOAD_ERR_INVALID_SIZE, FW_UPLOAD_ERR_RW_ERROR, FW_UPLOAD_ERR_WEAROUT, + FW_UPLOAD_ERR_FW_INVALID, FW_UPLOAD_ERR_MAX }; diff --git a/include/linux/framer/framer-provider.h b/include/linux/framer/framer-provider.h new file mode 100644 index 000000000000..782cd5fc83d5 --- /dev/null +++ b/include/linux/framer/framer-provider.h @@ -0,0 +1,194 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Generic framer profider header file + * + * Copyright 2023 CS GROUP France + * + * Author: Herve Codina <herve.codina@bootlin.com> + */ + +#ifndef __DRIVERS_PROVIDER_FRAMER_H +#define __DRIVERS_PROVIDER_FRAMER_H + +#include <linux/export.h> +#include <linux/framer/framer.h> +#include <linux/types.h> + +#define FRAMER_FLAG_POLL_STATUS BIT(0) + +/** + * struct framer_ops - set of function pointers for performing framer operations + * @init: operation to be performed for initializing the framer + * @exit: operation to be performed while exiting + * @power_on: powering on the framer + * @power_off: powering off the framer + * @flags: OR-ed flags (FRAMER_FLAG_*) to ask for core functionality + * - @FRAMER_FLAG_POLL_STATUS: + * Ask the core to perform a polling to get the framer status and + * notify consumers on change. + * The framer should call @framer_notify_status_change() when it + * detects a status change. This is usually done using interrupts. + * If the framer cannot detect this change, it can ask the core for + * a status polling. The core will call @get_status() periodically + * and, on change detected, it will notify the consumer. + * the @get_status() + * @owner: the module owner containing the ops + */ +struct framer_ops { + int (*init)(struct framer *framer); + void (*exit)(struct framer *framer); + int (*power_on)(struct framer *framer); + int (*power_off)(struct framer *framer); + + /** + * @get_status: + * + * Optional. + * + * Used to get the framer status. framer_init() must have + * been called on the framer. + * + * Returns: 0 if successful, an negative error code otherwise + */ + int (*get_status)(struct framer *framer, struct framer_status *status); + + /** + * @set_config: + * + * Optional. + * + * Used to set the framer configuration. framer_init() must have + * been called on the framer. + * + * Returns: 0 if successful, an negative error code otherwise + */ + int (*set_config)(struct framer *framer, const struct framer_config *config); + + /** + * @get_config: + * + * Optional. + * + * Used to get the framer configuration. framer_init() must have + * been called on the framer. + * + * Returns: 0 if successful, an negative error code otherwise + */ + int (*get_config)(struct framer *framer, struct framer_config *config); + + u32 flags; + struct module *owner; +}; + +/** + * struct framer_provider - represents the framer provider + * @dev: framer provider device + * @children: can be used to override the default (dev->of_node) child node + * @owner: the module owner having of_xlate + * @list: to maintain a linked list of framer providers + * @of_xlate: function pointer to obtain framer instance from framer pointer + */ +struct framer_provider { + struct device *dev; + struct module *owner; + struct list_head list; + struct framer * (*of_xlate)(struct device *dev, + struct of_phandle_args *args); +}; + +static inline void framer_set_drvdata(struct framer *framer, void *data) +{ + dev_set_drvdata(&framer->dev, data); +} + +static inline void *framer_get_drvdata(struct framer *framer) +{ + return dev_get_drvdata(&framer->dev); +} + +#if IS_ENABLED(CONFIG_GENERIC_FRAMER) + +/* Create and destroy a framer */ +struct framer *framer_create(struct device *dev, struct device_node *node, + const struct framer_ops *ops); +void framer_destroy(struct framer *framer); + +/* devm version */ +struct framer *devm_framer_create(struct device *dev, struct device_node *node, + const struct framer_ops *ops); + +struct framer *framer_provider_simple_of_xlate(struct device *dev, + struct of_phandle_args *args); + +struct framer_provider * +__framer_provider_of_register(struct device *dev, struct module *owner, + struct framer *(*of_xlate)(struct device *dev, + struct of_phandle_args *args)); + +void framer_provider_of_unregister(struct framer_provider *framer_provider); + +struct framer_provider * +__devm_framer_provider_of_register(struct device *dev, struct module *owner, + struct framer *(*of_xlate)(struct device *dev, + struct of_phandle_args *args)); + +void framer_notify_status_change(struct framer *framer); + +#else /* IS_ENABLED(CONFIG_GENERIC_FRAMER) */ + +static inline struct framer *framer_create(struct device *dev, struct device_node *node, + const struct framer_ops *ops) +{ + return ERR_PTR(-ENOSYS); +} + +static inline void framer_destroy(struct framer *framer) +{ +} + +/* devm version */ +static inline struct framer *devm_framer_create(struct device *dev, struct device_node *node, + const struct framer_ops *ops) +{ + return ERR_PTR(-ENOSYS); +} + +static inline struct framer *framer_provider_simple_of_xlate(struct device *dev, + struct of_phandle_args *args) +{ + return ERR_PTR(-ENOSYS); +} + +static inline struct framer_provider * +__framer_provider_of_register(struct device *dev, struct module *owner, + struct framer *(*of_xlate)(struct device *dev, + struct of_phandle_args *args)) +{ + return ERR_PTR(-ENOSYS); +} + +void framer_provider_of_unregister(struct framer_provider *framer_provider) +{ +} + +static inline struct framer_provider * +__devm_framer_provider_of_register(struct device *dev, struct module *owner, + struct framer *(*of_xlate)(struct device *dev, + struct of_phandle_args *args)) +{ + return ERR_PTR(-ENOSYS); +} + +void framer_notify_status_change(struct framer *framer) +{ +} + +#endif /* IS_ENABLED(CONFIG_GENERIC_FRAMER) */ + +#define framer_provider_of_register(dev, xlate) \ + __framer_provider_of_register((dev), THIS_MODULE, (xlate)) + +#define devm_framer_provider_of_register(dev, xlate) \ + __devm_framer_provider_of_register((dev), THIS_MODULE, (xlate)) + +#endif /* __DRIVERS_PROVIDER_FRAMER_H */ diff --git a/include/linux/framer/framer.h b/include/linux/framer/framer.h new file mode 100644 index 000000000000..9a9b88962c29 --- /dev/null +++ b/include/linux/framer/framer.h @@ -0,0 +1,205 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Generic framer header file + * + * Copyright 2023 CS GROUP France + * + * Author: Herve Codina <herve.codina@bootlin.com> + */ + +#ifndef __DRIVERS_FRAMER_H +#define __DRIVERS_FRAMER_H + +#include <linux/err.h> +#include <linux/mutex.h> +#include <linux/notifier.h> +#include <linux/of.h> +#include <linux/device.h> +#include <linux/workqueue.h> + +/** + * enum framer_iface - Framer interface + * @FRAMER_IFACE_E1: E1 interface + * @FRAMER_IFACE_T1: T1 interface + */ +enum framer_iface { + FRAMER_IFACE_E1, + FRAMER_IFACE_T1, +}; + +/** + * enum framer_clock_type - Framer clock type + * @FRAMER_CLOCK_EXT: External clock + * @FRAMER_CLOCK_INT: Internal clock + */ +enum framer_clock_type { + FRAMER_CLOCK_EXT, + FRAMER_CLOCK_INT, +}; + +/** + * struct framer_config - Framer configuration + * @iface: Framer line interface + * @clock_type: Framer clock type + * @line_clock_rate: Framer line clock rate + */ +struct framer_config { + enum framer_iface iface; + enum framer_clock_type clock_type; + unsigned long line_clock_rate; +}; + +/** + * struct framer_status - Framer status + * @link_is_on: Framer link state. true, the link is on, false, the link is off. + */ +struct framer_status { + bool link_is_on; +}; + +/** + * enum framer_event - Event available for notification + * @FRAMER_EVENT_STATUS: Event notified on framer_status changes + */ +enum framer_event { + FRAMER_EVENT_STATUS, +}; + +/** + * struct framer - represents the framer device + * @dev: framer device + * @id: id of the framer device + * @ops: function pointers for performing framer operations + * @mutex: mutex to protect framer_ops + * @init_count: used to protect when the framer is used by multiple consumers + * @power_count: used to protect when the framer is used by multiple consumers + * @pwr: power regulator associated with the framer + * @notify_status_work: work structure used for status notifications + * @notifier_list: notifier list used for notifications + * @polling_work: delayed work structure used for the polling task + * @prev_status: previous read status used by the polling task to detect changes + */ +struct framer { + struct device dev; + int id; + const struct framer_ops *ops; + struct mutex mutex; /* Protect framer */ + int init_count; + int power_count; + struct regulator *pwr; + struct work_struct notify_status_work; + struct blocking_notifier_head notifier_list; + struct delayed_work polling_work; + struct framer_status prev_status; +}; + +#if IS_ENABLED(CONFIG_GENERIC_FRAMER) +int framer_pm_runtime_get(struct framer *framer); +int framer_pm_runtime_get_sync(struct framer *framer); +int framer_pm_runtime_put(struct framer *framer); +int framer_pm_runtime_put_sync(struct framer *framer); +int framer_init(struct framer *framer); +int framer_exit(struct framer *framer); +int framer_power_on(struct framer *framer); +int framer_power_off(struct framer *framer); +int framer_get_status(struct framer *framer, struct framer_status *status); +int framer_get_config(struct framer *framer, struct framer_config *config); +int framer_set_config(struct framer *framer, const struct framer_config *config); +int framer_notifier_register(struct framer *framer, struct notifier_block *nb); +int framer_notifier_unregister(struct framer *framer, struct notifier_block *nb); + +struct framer *framer_get(struct device *dev, const char *con_id); +void framer_put(struct device *dev, struct framer *framer); + +struct framer *devm_framer_get(struct device *dev, const char *con_id); +struct framer *devm_framer_optional_get(struct device *dev, const char *con_id); +#else +static inline int framer_pm_runtime_get(struct framer *framer) +{ + return -ENOSYS; +} + +static inline int framer_pm_runtime_get_sync(struct framer *framer) +{ + return -ENOSYS; +} + +static inline int framer_pm_runtime_put(struct framer *framer) +{ + return -ENOSYS; +} + +static inline int framer_pm_runtime_put_sync(struct framer *framer) +{ + return -ENOSYS; +} + +static inline int framer_init(struct framer *framer) +{ + return -ENOSYS; +} + +static inline int framer_exit(struct framer *framer) +{ + return -ENOSYS; +} + +static inline int framer_power_on(struct framer *framer) +{ + return -ENOSYS; +} + +static inline int framer_power_off(struct framer *framer) +{ + return -ENOSYS; +} + +static inline int framer_get_status(struct framer *framer, struct framer_status *status) +{ + return -ENOSYS; +} + +static inline int framer_get_config(struct framer *framer, struct framer_config *config) +{ + return -ENOSYS; +} + +static inline int framer_set_config(struct framer *framer, const struct framer_config *config) +{ + return -ENOSYS; +} + +static inline int framer_notifier_register(struct framer *framer, + struct notifier_block *nb) +{ + return -ENOSYS; +} + +static inline int framer_notifier_unregister(struct framer *framer, + struct notifier_block *nb) +{ + return -ENOSYS; +} + +struct framer *framer_get(struct device *dev, const char *con_id) +{ + return ERR_PTR(-ENOSYS); +} + +void framer_put(struct device *dev, struct framer *framer) +{ +} + +static inline struct framer *devm_framer_get(struct device *dev, const char *con_id) +{ + return ERR_PTR(-ENOSYS); +} + +static inline struct framer *devm_framer_optional_get(struct device *dev, const char *con_id) +{ + return NULL; +} + +#endif + +#endif /* __DRIVERS_FRAMER_H */ diff --git a/include/linux/framer/pef2256.h b/include/linux/framer/pef2256.h new file mode 100644 index 000000000000..71d80af58c40 --- /dev/null +++ b/include/linux/framer/pef2256.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * PEF2256 consumer API + * + * Copyright 2023 CS GROUP France + * + * Author: Herve Codina <herve.codina@bootlin.com> + */ +#ifndef __PEF2256_H__ +#define __PEF2256_H__ + +#include <linux/types.h> + +struct pef2256; +struct regmap; + +/* Retrieve the PEF2256 regmap */ +struct regmap *pef2256_get_regmap(struct pef2256 *pef2256); + +/* PEF2256 hardware versions */ +enum pef2256_version { + PEF2256_VERSION_UNKNOWN, + PEF2256_VERSION_1_2, + PEF2256_VERSION_2_1, + PEF2256_VERSION_2_2, +}; + +/* Get the PEF2256 hardware version */ +enum pef2256_version pef2256_get_version(struct pef2256 *pef2256); + +#endif /* __PEF2256_H__ */ diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 2b5e500bf093..52808dd22513 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -172,11 +172,11 @@ #define IEEE80211_SN_MODULO (IEEE80211_MAX_SN + 1) -/* PV1 Layout 11ah 9.8.3.1 */ +/* PV1 Layout IEEE 802.11-2020 9.8.3.1 */ #define IEEE80211_PV1_FCTL_VERS 0x0003 #define IEEE80211_PV1_FCTL_FTYPE 0x001c #define IEEE80211_PV1_FCTL_STYPE 0x00e0 -#define IEEE80211_PV1_FCTL_TODS 0x0100 +#define IEEE80211_PV1_FCTL_FROMDS 0x0100 #define IEEE80211_PV1_FCTL_MOREFRAGS 0x0200 #define IEEE80211_PV1_FCTL_PM 0x0400 #define IEEE80211_PV1_FCTL_MOREDATA 0x0800 diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 3028af87716e..c1645c86eed9 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -540,7 +540,7 @@ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) struct vlan_ethhdr *veth = skb_vlan_eth_hdr(skb); if (!eth_type_vlan(veth->h_vlan_proto)) - return -EINVAL; + return -ENODATA; *vlan_tci = ntohs(veth->h_vlan_TCI); return 0; @@ -561,7 +561,7 @@ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, return 0; } else { *vlan_tci = 0; - return -EINVAL; + return -ENODATA; } } diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index c1c76a70a6ce..adb83a42a6b9 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -11,7 +11,7 @@ * @__VA_ARGS__: arguments for @f * * Avoid retpoline overhead for known builtin, checking @f vs each of them and - * eventually invoking directly the builtin function. The functions are check + * eventually invoking directly the builtin function. The functions are checked * in the given order. Fallback to the indirect call. */ #define INDIRECT_CALL_1(f, f1, ...) \ diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index 7303b4bc2ce0..287f590ed56b 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -10,6 +10,11 @@ static inline void linkmode_zero(unsigned long *dst) bitmap_zero(dst, __ETHTOOL_LINK_MODE_MASK_NBITS); } +static inline void linkmode_fill(unsigned long *dst) +{ + bitmap_fill(dst, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + static inline void linkmode_copy(unsigned long *dst, const unsigned long *src) { bitmap_copy(dst, src, __ETHTOOL_LINK_MODE_MASK_NBITS); diff --git a/include/linux/list.h b/include/linux/list.h index 1837caedf723..059aa1fff41e 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -1119,6 +1119,26 @@ static inline void hlist_move_list(struct hlist_head *old, old->first = NULL; } +/** + * hlist_splice_init() - move all entries from one list to another + * @from: hlist_head from which entries will be moved + * @last: last entry on the @from list + * @to: hlist_head to which entries will be moved + * + * @to can be empty, @from must contain at least @last. + */ +static inline void hlist_splice_init(struct hlist_head *from, + struct hlist_node *last, + struct hlist_head *to) +{ + if (to->first) + to->first->pprev = &last->next; + last->next = to->first; + to->first = from->first; + from->first->pprev = &to->first; + from->first = NULL; +} + #define hlist_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_for_each(pos, head) \ diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 007fd9c3e4b6..79ceee3c8673 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -38,6 +38,7 @@ struct mdio_device { /* Bus address of the MDIO device (0-31) */ int addr; int flags; + int reset_state; struct gpio_desc *reset_gpio; struct reset_control *reset_ctrl; unsigned int reset_assert_delay; diff --git a/include/linux/mii_timestamper.h b/include/linux/mii_timestamper.h index fa940bbaf8ae..26b04f73f214 100644 --- a/include/linux/mii_timestamper.h +++ b/include/linux/mii_timestamper.h @@ -9,6 +9,7 @@ #include <linux/device.h> #include <linux/ethtool.h> #include <linux/skbuff.h> +#include <linux/net_tstamp.h> struct phy_device; @@ -51,7 +52,8 @@ struct mii_timestamper { struct sk_buff *skb, int type); int (*hwtstamp)(struct mii_timestamper *mii_ts, - struct ifreq *ifreq); + struct kernel_hwtstamp_config *kernel_config, + struct netlink_ext_ack *extack); void (*link_state)(struct mii_timestamper *mii_ts, struct phy_device *phydev); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 820bca965fb6..01275c6e8468 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -918,7 +918,7 @@ static inline u8 get_cqe_tls_offload(struct mlx5_cqe64 *cqe) return (cqe->tls_outer_l3_tunneled >> 3) & 0x3; } -static inline bool cqe_has_vlan(struct mlx5_cqe64 *cqe) +static inline bool cqe_has_vlan(const struct mlx5_cqe64 *cqe) { return cqe->l4_l3_hdr_type & 0x1; } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d2b8d4a74a30..7ee5b79ff3d6 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -150,6 +150,7 @@ enum { MLX5_REG_MTPPSE = 0x9054, MLX5_REG_MTUTC = 0x9055, MLX5_REG_MPEGC = 0x9056, + MLX5_REG_MPIR = 0x9059, MLX5_REG_MCQS = 0x9060, MLX5_REG_MCQI = 0x9061, MLX5_REG_MCC = 0x9062, @@ -678,6 +679,8 @@ struct mlx5e_resources { struct mlx5_td td; u32 mkey; struct mlx5_sq_bfreg bfreg; +#define MLX5_MAX_NUM_TC 8 + u32 tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC]; } hw_objs; struct net_device *uplink_netdev; struct mutex uplink_netdev_lock; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3f7b664d625b..fee20fc010c2 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -435,7 +435,7 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 flow_table_modify[0x1]; u8 reformat[0x1]; u8 decap[0x1]; - u8 reserved_at_9[0x1]; + u8 reset_root_to_default[0x1]; u8 pop_vlan[0x1]; u8 push_vlan[0x1]; u8 reserved_at_c[0x1]; @@ -1801,7 +1801,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 disable_local_lb_uc[0x1]; u8 disable_local_lb_mc[0x1]; u8 log_min_hairpin_wq_data_sz[0x5]; - u8 reserved_at_3e8[0x2]; + u8 reserved_at_3e8[0x1]; + u8 silent_mode[0x1]; u8 vhca_state[0x1]; u8 log_max_vlan_list[0x5]; u8 reserved_at_3f0[0x3]; @@ -1818,7 +1819,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_460[0x1]; u8 ats[0x1]; - u8 reserved_at_462[0x1]; + u8 cross_vhca_rqt[0x1]; u8 log_max_uctx[0x5]; u8 reserved_at_468[0x1]; u8 crypto[0x1]; @@ -1943,6 +1944,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { enum { MLX5_CROSS_VHCA_OBJ_TO_OBJ_SUPPORTED_LOCAL_FLOW_TABLE_TO_REMOTE_FLOW_TABLE_MISS = 0x80000, + MLX5_CROSS_VHCA_OBJ_TO_OBJ_SUPPORTED_LOCAL_FLOW_TABLE_ROOT_TO_REMOTE_FLOW_TABLE = (1ULL << 20), }; enum { @@ -1992,7 +1994,11 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_260[0x120]; u8 reserved_at_380[0x10]; u8 ec_vf_vport_base[0x10]; - u8 reserved_at_3a0[0x460]; + + u8 reserved_at_3a0[0x10]; + u8 max_rqt_vhca_id[0x10]; + + u8 reserved_at_3c0[0x440]; }; enum mlx5_ifc_flow_destination_type { @@ -2151,6 +2157,13 @@ struct mlx5_ifc_rq_num_bits { u8 rq_num[0x18]; }; +struct mlx5_ifc_rq_vhca_bits { + u8 reserved_at_0[0x8]; + u8 rq_num[0x18]; + u8 reserved_at_20[0x10]; + u8 rq_vhca_id[0x10]; +}; + struct mlx5_ifc_mac_address_layout_bits { u8 reserved_at_0[0x10]; u8 mac_addr_47_32[0x10]; @@ -3901,7 +3914,10 @@ struct mlx5_ifc_rqtc_bits { u8 reserved_at_e0[0x6a0]; - struct mlx5_ifc_rq_num_bits rq_num[]; + union { + DECLARE_FLEX_ARRAY(struct mlx5_ifc_rq_num_bits, rq_num); + DECLARE_FLEX_ARRAY(struct mlx5_ifc_rq_vhca_bits, rq_vhca); + }; }; enum { @@ -4744,7 +4760,10 @@ struct mlx5_ifc_set_l2_table_entry_in_bits { u8 reserved_at_c0[0x20]; - u8 reserved_at_e0[0x13]; + u8 reserved_at_e0[0x10]; + u8 silent_mode_valid[0x1]; + u8 silent_mode[0x1]; + u8 reserved_at_f2[0x1]; u8 vlan_valid[0x1]; u8 vlan[0xc]; @@ -10089,6 +10108,20 @@ struct mlx5_ifc_mpegc_reg_bits { u8 reserved_at_60[0x100]; }; +struct mlx5_ifc_mpir_reg_bits { + u8 sdm[0x1]; + u8 reserved_at_1[0x1b]; + u8 host_buses[0x4]; + + u8 reserved_at_20[0x20]; + + u8 local_port[0x8]; + u8 reserved_at_28[0x15]; + u8 sd_group[0x3]; + + u8 reserved_at_60[0x20]; +}; + enum { MLX5_MTUTC_FREQ_ADJ_UNITS_PPB = 0x0, MLX5_MTUTC_FREQ_ADJ_UNITS_SCALED_PPM = 0x1, @@ -10103,7 +10136,10 @@ enum { struct mlx5_ifc_mtutc_reg_bits { u8 reserved_at_0[0x5]; u8 freq_adj_units[0x3]; - u8 reserved_at_8[0x14]; + u8 reserved_at_8[0x3]; + u8 log_max_freq_adjustment[0x5]; + + u8 reserved_at_10[0xc]; u8 operation[0x4]; u8 freq_adjustment[0x20]; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 957ce38768b2..64e4572ef06d 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -125,7 +125,7 @@ struct page { struct page_pool *pp; unsigned long _pp_mapping_pad; unsigned long dma_addr; - atomic_long_t pp_frag_count; + atomic_long_t pp_ref_count; }; struct { /* Tail pages of compound page */ unsigned long compound_head; /* Bit zero is set */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2564e209465e..75c7725e5e4f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -382,6 +382,7 @@ struct napi_struct { /* control-path-only fields follow */ struct list_head dev_list; struct hlist_node napi_hash_node; + int irq; }; enum { @@ -665,6 +666,10 @@ struct netdev_queue { #ifdef CONFIG_XDP_SOCKETS struct xsk_buff_pool *pool; #endif + /* NAPI instance for the queue + * Readers and writers must hold RTNL + */ + struct napi_struct *napi; /* * write-mostly part */ @@ -1324,6 +1329,9 @@ struct netdev_net_notifier { * int (*ndo_mdb_del)(struct net_device *dev, struct nlattr *tb[], * struct netlink_ext_ack *extack); * Deletes the MDB entry from dev. + * int (*ndo_mdb_del_bulk)(struct net_device *dev, struct nlattr *tb[], + * struct netlink_ext_ack *extack); + * Bulk deletes MDB entries from dev. * int (*ndo_mdb_dump)(struct net_device *dev, struct sk_buff *skb, * struct netlink_callback *cb); * Dumps MDB entries from dev. The first argument (marker) in the netlink @@ -1606,6 +1614,9 @@ struct net_device_ops { int (*ndo_mdb_del)(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack); + int (*ndo_mdb_del_bulk)(struct net_device *dev, + struct nlattr *tb[], + struct netlink_ext_ack *extack); int (*ndo_mdb_dump)(struct net_device *dev, struct sk_buff *skb, struct netlink_callback *cb); @@ -1865,6 +1876,7 @@ enum netdev_stat_type { * @netdev_ops: Includes several pointers to callbacks, * if one wants to override the ndo_*() functions * @xdp_metadata_ops: Includes pointers to XDP metadata callbacks. + * @xsk_tx_metadata_ops: Includes pointers to AF_XDP TX metadata callbacks. * @ethtool_ops: Management operations * @l3mdev_ops: Layer 3 master device operations * @ndisc_ops: Includes callbacks for different IPv6 neighbour @@ -2091,6 +2103,70 @@ enum netdev_stat_type { */ struct net_device { + /* Cacheline organization can be found documented in + * Documentation/networking/net_cachelines/net_device.rst. + * Please update the document when adding new fields. + */ + + /* TX read-mostly hotpath */ + __cacheline_group_begin(net_device_read_tx); + unsigned long long priv_flags; + const struct net_device_ops *netdev_ops; + const struct header_ops *header_ops; + struct netdev_queue *_tx; + unsigned int real_num_tx_queues; + unsigned int gso_max_size; + unsigned int gso_ipv4_max_size; + u16 gso_max_segs; + s16 num_tc; + /* Note : dev->mtu is often read without holding a lock. + * Writers usually hold RTNL. + * It is recommended to use READ_ONCE() to annotate the reads, + * and to use WRITE_ONCE() to annotate the writes. + */ + unsigned int mtu; + unsigned short needed_headroom; + struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; +#ifdef CONFIG_XPS + struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX]; +#endif +#ifdef CONFIG_NETFILTER_EGRESS + struct nf_hook_entries __rcu *nf_hooks_egress; +#endif +#ifdef CONFIG_NET_XGRESS + struct bpf_mprog_entry __rcu *tcx_egress; +#endif + __cacheline_group_end(net_device_read_tx); + + /* TXRX read-mostly hotpath */ + __cacheline_group_begin(net_device_read_txrx); + unsigned int flags; + unsigned short hard_header_len; + netdev_features_t features; + struct inet6_dev __rcu *ip6_ptr; + __cacheline_group_end(net_device_read_txrx); + + /* RX read-mostly hotpath */ + __cacheline_group_begin(net_device_read_rx); + struct list_head ptype_specific; + int ifindex; + unsigned int real_num_rx_queues; + struct netdev_rx_queue *_rx; + unsigned long gro_flush_timeout; + int napi_defer_hard_irqs; + unsigned int gro_max_size; + unsigned int gro_ipv4_max_size; + rx_handler_func_t __rcu *rx_handler; + void __rcu *rx_handler_data; + possible_net_t nd_net; +#ifdef CONFIG_NETPOLL + struct netpoll_info __rcu *npinfo; +#endif +#ifdef CONFIG_NET_XGRESS + struct bpf_mprog_entry __rcu *tcx_ingress; +#endif + __cacheline_group_end(net_device_read_rx); + char name[IFNAMSIZ]; struct netdev_name_node *name_node; struct dev_ifalias __rcu *ifalias; @@ -2115,7 +2191,6 @@ struct net_device { struct list_head unreg_list; struct list_head close_list; struct list_head ptype_all; - struct list_head ptype_specific; struct { struct list_head upper; @@ -2123,25 +2198,13 @@ struct net_device { } adj_list; /* Read-mostly cache-line for fast-path access */ - unsigned int flags; xdp_features_t xdp_features; - unsigned long long priv_flags; - const struct net_device_ops *netdev_ops; const struct xdp_metadata_ops *xdp_metadata_ops; - int ifindex; + const struct xsk_tx_metadata_ops *xsk_tx_metadata_ops; unsigned short gflags; - unsigned short hard_header_len; - /* Note : dev->mtu is often read without holding a lock. - * Writers usually hold RTNL. - * It is recommended to use READ_ONCE() to annotate the reads, - * and to use WRITE_ONCE() to annotate the writes. - */ - unsigned int mtu; - unsigned short needed_headroom; unsigned short needed_tailroom; - netdev_features_t features; netdev_features_t hw_features; netdev_features_t wanted_features; netdev_features_t vlan_features; @@ -2185,8 +2248,6 @@ struct net_device { const struct tlsdev_ops *tlsdev_ops; #endif - const struct header_ops *header_ops; - unsigned char operstate; unsigned char link_mode; @@ -2227,9 +2288,7 @@ struct net_device { /* Protocol-specific pointers */ - struct in_device __rcu *ip_ptr; - struct inet6_dev __rcu *ip6_ptr; #if IS_ENABLED(CONFIG_VLAN_8021Q) struct vlan_info __rcu *vlan_info; #endif @@ -2264,26 +2323,14 @@ struct net_device { /* Interface address info used in eth_type_trans() */ const unsigned char *dev_addr; - struct netdev_rx_queue *_rx; unsigned int num_rx_queues; - unsigned int real_num_rx_queues; - struct bpf_prog __rcu *xdp_prog; - unsigned long gro_flush_timeout; - int napi_defer_hard_irqs; #define GRO_LEGACY_MAX_SIZE 65536u /* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE), * and shinfo->gso_segs is a 16bit field. */ #define GRO_MAX_SIZE (8 * 65535u) - unsigned int gro_max_size; - unsigned int gro_ipv4_max_size; unsigned int xdp_zc_max_segs; - rx_handler_func_t __rcu *rx_handler; - void __rcu *rx_handler_data; -#ifdef CONFIG_NET_XGRESS - struct bpf_mprog_entry __rcu *tcx_ingress; -#endif struct netdev_queue __rcu *ingress_queue; #ifdef CONFIG_NETFILTER_INGRESS struct nf_hook_entries __rcu *nf_hooks_ingress; @@ -2298,25 +2345,13 @@ struct net_device { /* * Cache lines mostly used on transmit path */ - struct netdev_queue *_tx ____cacheline_aligned_in_smp; unsigned int num_tx_queues; - unsigned int real_num_tx_queues; struct Qdisc __rcu *qdisc; unsigned int tx_queue_len; spinlock_t tx_global_lock; struct xdp_dev_bulk_queue __percpu *xdp_bulkq; -#ifdef CONFIG_XPS - struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX]; -#endif -#ifdef CONFIG_NET_XGRESS - struct bpf_mprog_entry __rcu *tcx_egress; -#endif -#ifdef CONFIG_NETFILTER_EGRESS - struct nf_hook_entries __rcu *nf_hooks_egress; -#endif - #ifdef CONFIG_NET_SCHED DECLARE_HASHTABLE (qdisc_hash, 4); #endif @@ -2355,12 +2390,6 @@ struct net_device { bool needs_free_netdev; void (*priv_destructor)(struct net_device *dev); -#ifdef CONFIG_NETPOLL - struct netpoll_info __rcu *npinfo; -#endif - - possible_net_t nd_net; - /* mid-layer private */ void *ml_priv; enum netdev_ml_priv_type ml_priv_type; @@ -2395,20 +2424,15 @@ struct net_device { */ #define GSO_MAX_SIZE (8 * GSO_MAX_SEGS) - unsigned int gso_max_size; #define TSO_LEGACY_MAX_SIZE 65536 #define TSO_MAX_SIZE UINT_MAX unsigned int tso_max_size; - u16 gso_max_segs; #define TSO_MAX_SEGS U16_MAX u16 tso_max_segs; - unsigned int gso_ipv4_max_size; #ifdef CONFIG_DCB const struct dcbnl_rtnl_ops *dcbnl_ops; #endif - s16 num_tc; - struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; u8 prio_tc_map[TC_BITMASK + 1]; #if IS_ENABLED(CONFIG_FCOE) @@ -2447,6 +2471,10 @@ struct net_device { #if IS_ENABLED(CONFIG_DPLL) struct dpll_pin *dpll_pin; #endif +#if IS_ENABLED(CONFIG_PAGE_POOL) + /** @page_pools: page pools created for this netdevice */ + struct hlist_head page_pools; +#endif }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -2651,6 +2679,15 @@ static inline void *netdev_priv(const struct net_device *dev) */ #define SET_NETDEV_DEVTYPE(net, devtype) ((net)->dev.type = (devtype)) +void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index, + enum netdev_queue_type type, + struct napi_struct *napi); + +static inline void netif_napi_set_irq(struct napi_struct *napi, int irq) +{ + napi->irq = irq; +} + /* Default NAPI poll() weight * Device drivers are strongly advised to not use bigger value */ @@ -3964,6 +4001,9 @@ int generic_hwtstamp_get_lower(struct net_device *dev, int generic_hwtstamp_set_lower(struct net_device *dev, struct kernel_hwtstamp_config *kernel_cfg, struct netlink_ext_ack *extack); +int dev_set_hwtstamp_phylib(struct net_device *dev, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack); int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata); unsigned int dev_get_flags(const struct net_device *); int __dev_change_flags(struct net_device *dev, unsigned int flags, @@ -4196,6 +4236,15 @@ static inline void netdev_ref_replace(struct net_device *odev, void linkwatch_fire_event(struct net_device *dev); /** + * linkwatch_sync_dev - sync linkwatch for the given device + * @dev: network device to sync linkwatch for + * + * Sync linkwatch for the given device, removing it from the + * pending work list (if queued). + */ +void linkwatch_sync_dev(struct net_device *dev); + +/** * netif_carrier_ok - test if carrier present * @dev: network device * diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 7834c0be2831..61aa48f46dd7 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -51,7 +51,7 @@ struct nf_ipv6_ops { u32 (*cookie_init_sequence)(const struct ipv6hdr *iph, const struct tcphdr *th, u16 *mssp); int (*cookie_v6_check)(const struct ipv6hdr *iph, - const struct tcphdr *th, __u32 cookie); + const struct tcphdr *th); #endif void (*route_input)(struct sk_buff *skb); int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, @@ -179,16 +179,16 @@ static inline u32 nf_ipv6_cookie_init_sequence(const struct ipv6hdr *iph, } static inline int nf_cookie_v6_check(const struct ipv6hdr *iph, - const struct tcphdr *th, __u32 cookie) + const struct tcphdr *th) { #if IS_ENABLED(CONFIG_SYN_COOKIES) #if IS_MODULE(CONFIG_IPV6) const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); if (v6_ops) - return v6_ops->cookie_v6_check(iph, th, cookie); + return v6_ops->cookie_v6_check(iph, th); #elif IS_BUILTIN(CONFIG_IPV6) - return __cookie_v6_check(iph, th, cookie); + return __cookie_v6_check(iph, th); #endif #endif return 0; diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 75d7de34c908..1a4445bf2ab9 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -228,10 +228,12 @@ bool netlink_strict_get_check(struct sk_buff *skb); int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock); int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation); + +typedef int (*netlink_filter_fn)(struct sock *dsk, struct sk_buff *skb, void *data); + int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation, - int (*filter)(struct sock *dsk, - struct sk_buff *skb, void *data), + netlink_filter_fn filter, void *filter_data); int netlink_set_err(struct sock *ssk, __u32 portid, __u32 group, int code); int netlink_register_notifier(struct notifier_block *nb); @@ -351,5 +353,6 @@ bool netlink_ns_capable(const struct sk_buff *skb, struct user_namespace *ns, int cap); bool netlink_capable(const struct sk_buff *skb, int cap); bool netlink_net_capable(const struct sk_buff *skb, int cap); +struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast); #endif /* __LINUX_NETLINK_H */ diff --git a/include/linux/phy.h b/include/linux/phy.h index 3cc52826f18e..e9e85d347587 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -327,7 +327,8 @@ struct mdio_bus_stats { /** * struct phy_package_shared - Shared information in PHY packages - * @addr: Common PHY address used to combine PHYs in one package + * @base_addr: Base PHY address of PHY package used to combine PHYs + * in one package and for offset calculation of phy_package_read/write * @refcnt: Number of PHYs connected to this shared data * @flags: Initialization of PHY package * @priv_size: Size of the shared private data @priv @@ -338,7 +339,7 @@ struct mdio_bus_stats { * phy_package_leave(). */ struct phy_package_shared { - int addr; + u8 base_addr; refcount_t refcnt; unsigned long flags; size_t priv_size; @@ -605,6 +606,8 @@ struct macsec_ops; * @irq_rerun: Flag indicating interrupts occurred while PHY was suspended, * requiring a rerun of the interrupt handler after resume * @interface: enum phy_interface_t value + * @possible_interfaces: bitmap if interface modes that the attached PHY + * will switch between depending on media speed. * @skb: Netlink message for cable diagnostics * @nest: Netlink nest used for cable diagnostics * @ehdr: nNtlink header for cable diagnostics @@ -674,6 +677,7 @@ struct phy_device { u32 dev_flags; phy_interface_t interface; + DECLARE_PHY_INTERFACE_MASK(possible_interfaces); /* * forced speed & duplex (no autoneg) @@ -1560,9 +1564,11 @@ static inline bool phy_has_txtstamp(struct phy_device *phydev) return phydev && phydev->mii_ts && phydev->mii_ts->txtstamp; } -static inline int phy_hwtstamp(struct phy_device *phydev, struct ifreq *ifr) +static inline int phy_hwtstamp(struct phy_device *phydev, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack) { - return phydev->mii_ts->hwtstamp(phydev->mii_ts, ifr); + return phydev->mii_ts->hwtstamp(phydev->mii_ts, cfg, extack); } static inline bool phy_rxtstamp(struct phy_device *phydev, struct sk_buff *skb, @@ -1861,6 +1867,7 @@ int genphy_c45_an_config_aneg(struct phy_device *phydev); int genphy_c45_an_disable_aneg(struct phy_device *phydev); int genphy_c45_read_mdix(struct phy_device *phydev); int genphy_c45_pma_read_abilities(struct phy_device *phydev); +int genphy_c45_pma_read_ext_abilities(struct phy_device *phydev); int genphy_c45_pma_baset1_read_abilities(struct phy_device *phydev); int genphy_c45_read_eee_abilities(struct phy_device *phydev); int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev); @@ -1970,10 +1977,10 @@ int phy_ethtool_get_link_ksettings(struct net_device *ndev, int phy_ethtool_set_link_ksettings(struct net_device *ndev, const struct ethtool_link_ksettings *cmd); int phy_ethtool_nway_reset(struct net_device *ndev); -int phy_package_join(struct phy_device *phydev, int addr, size_t priv_size); +int phy_package_join(struct phy_device *phydev, int base_addr, size_t priv_size); void phy_package_leave(struct phy_device *phydev); int devm_phy_package_join(struct device *dev, struct phy_device *phydev, - int addr, size_t priv_size); + int base_addr, size_t priv_size); int __init mdio_bus_init(void); void mdio_bus_exit(void); @@ -1996,48 +2003,83 @@ int __phy_hwtstamp_set(struct phy_device *phydev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack); -static inline int phy_package_read(struct phy_device *phydev, u32 regnum) +static inline int phy_package_address(struct phy_device *phydev, + unsigned int addr_offset) { struct phy_package_shared *shared = phydev->shared; + u8 base_addr = shared->base_addr; - if (!shared) + if (addr_offset >= PHY_MAX_ADDR - base_addr) return -EIO; - return mdiobus_read(phydev->mdio.bus, shared->addr, regnum); + /* we know that addr will be in the range 0..31 and thus the + * implicit cast to a signed int is not a problem. + */ + return base_addr + addr_offset; } -static inline int __phy_package_read(struct phy_device *phydev, u32 regnum) +static inline int phy_package_read(struct phy_device *phydev, + unsigned int addr_offset, u32 regnum) { - struct phy_package_shared *shared = phydev->shared; + int addr = phy_package_address(phydev, addr_offset); - if (!shared) - return -EIO; + if (addr < 0) + return addr; + + return mdiobus_read(phydev->mdio.bus, addr, regnum); +} + +static inline int __phy_package_read(struct phy_device *phydev, + unsigned int addr_offset, u32 regnum) +{ + int addr = phy_package_address(phydev, addr_offset); + + if (addr < 0) + return addr; - return __mdiobus_read(phydev->mdio.bus, shared->addr, regnum); + return __mdiobus_read(phydev->mdio.bus, addr, regnum); } static inline int phy_package_write(struct phy_device *phydev, - u32 regnum, u16 val) + unsigned int addr_offset, u32 regnum, + u16 val) { - struct phy_package_shared *shared = phydev->shared; + int addr = phy_package_address(phydev, addr_offset); - if (!shared) - return -EIO; + if (addr < 0) + return addr; - return mdiobus_write(phydev->mdio.bus, shared->addr, regnum, val); + return mdiobus_write(phydev->mdio.bus, addr, regnum, val); } static inline int __phy_package_write(struct phy_device *phydev, - u32 regnum, u16 val) + unsigned int addr_offset, u32 regnum, + u16 val) { - struct phy_package_shared *shared = phydev->shared; + int addr = phy_package_address(phydev, addr_offset); - if (!shared) - return -EIO; + if (addr < 0) + return addr; - return __mdiobus_write(phydev->mdio.bus, shared->addr, regnum, val); + return __mdiobus_write(phydev->mdio.bus, addr, regnum, val); } +int __phy_package_read_mmd(struct phy_device *phydev, + unsigned int addr_offset, int devad, + u32 regnum); + +int phy_package_read_mmd(struct phy_device *phydev, + unsigned int addr_offset, int devad, + u32 regnum); + +int __phy_package_write_mmd(struct phy_device *phydev, + unsigned int addr_offset, int devad, + u32 regnum, u16 val); + +int phy_package_write_mmd(struct phy_device *phydev, + unsigned int addr_offset, int devad, + u32 regnum, u16 val); + static inline bool __phy_package_set_once(struct phy_device *phydev, unsigned int b) { diff --git a/include/linux/platform_data/microchip-ksz.h b/include/linux/platform_data/microchip-ksz.h index ea1cc6d829e9..f177416635a2 100644 --- a/include/linux/platform_data/microchip-ksz.h +++ b/include/linux/platform_data/microchip-ksz.h @@ -20,10 +20,31 @@ #define __MICROCHIP_KSZ_H #include <linux/types.h> +#include <linux/platform_data/dsa.h> + +enum ksz_chip_id { + KSZ8563_CHIP_ID = 0x8563, + KSZ8795_CHIP_ID = 0x8795, + KSZ8794_CHIP_ID = 0x8794, + KSZ8765_CHIP_ID = 0x8765, + KSZ8830_CHIP_ID = 0x8830, + KSZ9477_CHIP_ID = 0x00947700, + KSZ9896_CHIP_ID = 0x00989600, + KSZ9897_CHIP_ID = 0x00989700, + KSZ9893_CHIP_ID = 0x00989300, + KSZ9563_CHIP_ID = 0x00956300, + KSZ9567_CHIP_ID = 0x00956700, + LAN9370_CHIP_ID = 0x00937000, + LAN9371_CHIP_ID = 0x00937100, + LAN9372_CHIP_ID = 0x00937200, + LAN9373_CHIP_ID = 0x00937300, + LAN9374_CHIP_ID = 0x00937400, +}; struct ksz_platform_data { + /* Must be first such that dsa_register_switch() can access it */ + struct dsa_chip_data cd; u32 chip_id; - u16 enabled_ports; }; #endif diff --git a/include/linux/poison.h b/include/linux/poison.h index 851a855d3868..27a7dad17eef 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -83,6 +83,8 @@ /********** net/core/skbuff.c **********/ #define SKB_LIST_POISON_NEXT ((void *)(0x800 + POISON_POINTER_DELTA)) +/********** net/ **********/ +#define NET_PTR_POISON ((void *)(0x801 + POISON_POINTER_DELTA)) /********** kernel/bpf/ **********/ #define BPF_PTR_POISON ((void *)(0xeB9FUL + POISON_POINTER_DELTA)) diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 3d6cf306cd55..410529fca18b 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -10,6 +10,13 @@ #include <uapi/linux/rtnetlink.h> extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo); + +static inline int rtnetlink_maybe_send(struct sk_buff *skb, struct net *net, + u32 pid, u32 group, int echo) +{ + return !skb ? 0 : rtnetlink_send(skb, net, pid, group, echo); +} + extern int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid); extern void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group, const struct nlmsghdr *nlh, gfp_t flags); @@ -72,6 +79,18 @@ static inline bool lockdep_rtnl_is_held(void) #define rtnl_dereference(p) \ rcu_dereference_protected(p, lockdep_rtnl_is_held()) +/** + * rcu_replace_pointer_rtnl - replace an RCU pointer under rtnl_lock, returning + * its old value + * @rp: RCU pointer, whose value is returned + * @p: regular pointer + * + * Perform a replacement under rtnl_lock, where @rp is an RCU-annotated + * pointer. The old value of @rp is returned, and @rp is set to @p + */ +#define rcu_replace_pointer_rtnl(rp, p) \ + rcu_replace_pointer(rp, p, lockdep_rtnl_is_held()) + static inline struct netdev_queue *dev_ingress_queue(struct net_device *dev) { return rtnl_dereference(dev->ingress_queue); @@ -130,4 +149,26 @@ extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, extern void rtnl_offload_xstats_notify(struct net_device *dev); +static inline int rtnl_has_listeners(const struct net *net, u32 group) +{ + struct sock *rtnl = net->rtnl; + + return netlink_has_listeners(rtnl, group); +} + +/** + * rtnl_notify_needed - check if notification is needed + * @net: Pointer to the net namespace + * @nlflags: netlink ingress message flags + * @group: rtnl group + * + * Based on the ingress message flags and rtnl group, returns true + * if a notification is needed, false otherwise. + */ +static inline bool +rtnl_notify_needed(const struct net *net, u16 nlflags, u32 group) +{ + return (nlflags & NLM_F_ECHO) || rtnl_has_listeners(net, group); +} + #endif /* __LINUX_RTNETLINK_H */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 27998f73183e..ea5c8ab3ed00 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -566,6 +566,15 @@ struct ubuf_info_msgzc { int mm_account_pinned_pages(struct mmpin *mmp, size_t size); void mm_unaccount_pinned_pages(struct mmpin *mmp); +/* Preserve some data across TX submission and completion. + * + * Note, this state is stored in the driver. Extending the layout + * might need some special care. + */ +struct xsk_tx_metadata_compl { + __u64 *tx_timestamp; +}; + /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ @@ -578,7 +587,10 @@ struct skb_shared_info { /* Warning: this field is not always filled in (UFO)! */ unsigned short gso_segs; struct sk_buff *frag_list; - struct skb_shared_hwtstamps hwtstamps; + union { + struct skb_shared_hwtstamps hwtstamps; + struct xsk_tx_metadata_compl xsk_meta; + }; unsigned int gso_type; u32 tskey; @@ -1057,7 +1069,7 @@ struct sk_buff { refcount_t users; #ifdef CONFIG_SKB_EXTENSIONS - /* only useable after checking ->active_extensions != 0 */ + /* only usable after checking ->active_extensions != 0 */ struct skb_ext *extensions; #endif }; @@ -3299,7 +3311,7 @@ static inline struct page *__dev_alloc_pages(gfp_t gfp_mask, unsigned int order) { /* This piece of code contains several assumptions. - * 1. This is for device Rx, therefor a cold page is preferred. + * 1. This is for device Rx, therefore a cold page is preferred. * 2. The expectation is the user wants a compound page. * 3. If requesting a order 0 page it will not be compound * due to the check to see if order has a value in prep_new_page @@ -4235,10 +4247,13 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, { 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; + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || + BITS_PER_LONG != 64) + goto slow; + + /* Using more efficient variant than plain call to memcmp(). */ 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)) @@ -4258,11 +4273,11 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, fallthrough; case 4: diffs |= __it_diff(a, b, 32); break; + default: +slow: + return memcmp(a - meta_len, b - meta_len, meta_len); } 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, diff --git a/include/linux/tcp.h b/include/linux/tcp.h index b646b574b060..89b290d8c8dc 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -190,23 +190,121 @@ static inline bool tcp_rsk_used_ao(const struct request_sock *req) #define TCP_RMEM_TO_WIN_SCALE 8 struct tcp_sock { + /* Cacheline organization can be found documented in + * Documentation/networking/net_cachelines/tcp_sock.rst. + * Please update the document when adding new fields. + */ + /* inet_connection_sock has to be the first member of tcp_sock */ struct inet_connection_sock inet_conn; - u16 tcp_header_len; /* Bytes of tcp header to send */ + + /* TX read-mostly hotpath cache lines */ + __cacheline_group_begin(tcp_sock_read_tx); + /* timestamp of last sent data packet (for restart window) */ + u32 max_window; /* Maximal window ever seen from peer */ + u32 rcv_ssthresh; /* Current window clamp */ + u32 reordering; /* Packet reordering metric. */ + u32 notsent_lowat; /* TCP_NOTSENT_LOWAT */ u16 gso_segs; /* Max number of segs per GSO packet */ + /* from STCP, retrans queue hinting */ + struct sk_buff *lost_skb_hint; + struct sk_buff *retransmit_skb_hint; + __cacheline_group_end(tcp_sock_read_tx); + + /* TXRX read-mostly hotpath cache lines */ + __cacheline_group_begin(tcp_sock_read_txrx); + u32 tsoffset; /* timestamp offset */ + u32 snd_wnd; /* The window we expect to receive */ + u32 mss_cache; /* Cached effective mss, not including SACKS */ + u32 snd_cwnd; /* Sending congestion window */ + u32 prr_out; /* Total number of pkts sent during Recovery. */ + u32 lost_out; /* Lost packets */ + u32 sacked_out; /* SACK'd packets */ + u16 tcp_header_len; /* Bytes of tcp header to send */ + u8 chrono_type : 2, /* current chronograph type */ + repair : 1, + is_sack_reneg:1, /* in recovery from loss with SACK reneg? */ + is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */ + __cacheline_group_end(tcp_sock_read_txrx); + + /* RX read-mostly hotpath cache lines */ + __cacheline_group_begin(tcp_sock_read_rx); + u32 copied_seq; /* Head of yet unread data */ + u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ + u32 snd_wl1; /* Sequence for window update */ + u32 tlp_high_seq; /* snd_nxt at the time of TLP */ + u32 rttvar_us; /* smoothed mdev_max */ + u32 retrans_out; /* Retransmitted packets out */ + u16 advmss; /* Advertised MSS */ + u16 urg_data; /* Saved octet of OOB data and control flags */ + u32 lost; /* Total data packets lost incl. rexmits */ + struct minmax rtt_min; + /* OOO segments go in this rbtree. Socket lock must be held. */ + struct rb_root out_of_order_queue; + u32 snd_ssthresh; /* Slow start size threshold */ + __cacheline_group_end(tcp_sock_read_rx); + /* TX read-write hotpath cache lines */ + __cacheline_group_begin(tcp_sock_write_tx) ____cacheline_aligned; + u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut + * The total number of segments sent. + */ + u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut + * total number of data segments sent. + */ + u64 bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut + * total number of data bytes sent. + */ + u32 snd_sml; /* Last byte of the most recently transmitted small packet */ + u32 chrono_start; /* Start time in jiffies of a TCP chrono */ + u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ + u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ + u32 pushed_seq; /* Last pushed seq, required to talk to windows */ + u32 lsndtime; + u32 mdev_us; /* medium deviation */ + u64 tcp_wstamp_ns; /* departure time for next sent data packet */ + u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ + u64 tcp_mstamp; /* most recent packet received/sent */ + u32 rtt_seq; /* sequence number to update rttvar */ + struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */ + struct sk_buff *highest_sack; /* skb just after the highest + * skb with SACKed bit set + * (validity guaranteed only if + * sacked_out > 0) + */ + u8 ecn_flags; /* ECN status bits. */ + __cacheline_group_end(tcp_sock_write_tx); + + /* TXRX read-write hotpath cache lines */ + __cacheline_group_begin(tcp_sock_write_txrx); /* * Header prediction flags * 0x5?10 << 16 + snd_wnd in net byte order */ __be32 pred_flags; - + u32 rcv_nxt; /* What we want to receive next */ + u32 snd_nxt; /* Next sequence we send */ + u32 snd_una; /* First byte we want an ack for */ + u32 window_clamp; /* Maximal window to advertise */ + u32 srtt_us; /* smoothed round trip time << 3 in usecs */ + u32 packets_out; /* Packets which are "in flight" */ + u32 snd_up; /* Urgent pointer */ + u32 delivered; /* Total data packets delivered incl. rexmits */ + u32 delivered_ce; /* Like the above but only ECE marked packets */ + u32 app_limited; /* limited until "delivered" reaches this val */ + u32 rcv_wnd; /* Current receiver window */ /* - * RFC793 variables by their proper names. This means you can - * read the code and the spec side by side (and laugh ...) - * See RFC793 and RFC1122. The RFC writes these in capitals. + * Options received (usually on last packet, some only on SYN packets). */ - u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived + struct tcp_options_received rx_opt; + u8 nonagle : 4,/* Disable Nagle algorithm? */ + rate_app_limited:1; /* rate_{delivered,interval_us} limited? */ + __cacheline_group_end(tcp_sock_write_txrx); + + /* RX read-write hotpath cache lines */ + __cacheline_group_begin(tcp_sock_write_rx); + u64 bytes_received; + /* RFC4898 tcpEStatsAppHCThruOctetsReceived * sum(delta(rcv_nxt)), or how many bytes * were acked. */ @@ -216,45 +314,44 @@ struct tcp_sock { u32 data_segs_in; /* RFC4898 tcpEStatsPerfDataSegsIn * total number of data segments in. */ - u32 rcv_nxt; /* What we want to receive next */ - u32 copied_seq; /* Head of yet unread data */ u32 rcv_wup; /* rcv_nxt on last window update sent */ - u32 snd_nxt; /* Next sequence we send */ - u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut - * The total number of segments sent. - */ - u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut - * total number of data segments sent. - */ - u64 bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut - * total number of data bytes sent. - */ + u32 max_packets_out; /* max packets_out in last window */ + u32 cwnd_usage_seq; /* right edge of cwnd usage tracking flight */ + u32 rate_delivered; /* saved rate sample: packets delivered */ + u32 rate_interval_us; /* saved rate sample: time elapsed */ + u32 rcv_rtt_last_tsecr; + u64 first_tx_mstamp; /* start of window send phase */ + u64 delivered_mstamp; /* time we reached "delivered" */ u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked * sum(delta(snd_una)), or how many bytes * were acked. */ + struct { + u32 rtt_us; + u32 seq; + u64 time; + } rcv_rtt_est; +/* Receiver queue space */ + struct { + u32 space; + u32 seq; + u64 time; + } rcvq_space; + __cacheline_group_end(tcp_sock_write_rx); + /* End of Hot Path */ + +/* + * RFC793 variables by their proper names. This means you can + * read the code and the spec side by side (and laugh ...) + * See RFC793 and RFC1122. The RFC writes these in capitals. + */ u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups * total number of DSACK blocks received */ - u32 snd_una; /* First byte we want an ack for */ - u32 snd_sml; /* Last byte of the most recently transmitted small packet */ - u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ - u32 lsndtime; /* timestamp of last sent data packet (for restart window) */ u32 last_oow_ack_time; /* timestamp of last out-of-window ACK */ u32 compressed_ack_rcv_nxt; - - 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 */ - u32 max_window; /* Maximal window ever seen from peer */ - u32 mss_cache; /* Cached effective mss, not including SACKS */ - u32 window_clamp; /* Maximal window to advertise */ - u32 rcv_ssthresh; /* Current window clamp */ u8 scaling_ratio; /* see tcp_win_from_space() */ /* Information of the most recently (s)acked skb */ struct tcp_rack { @@ -268,24 +365,16 @@ struct tcp_sock { dsack_seen:1, /* Whether DSACK seen after last adj */ advanced:1; /* mstamp advanced since last lost marking */ } rack; - u16 advmss; /* Advertised MSS */ u8 compressed_ack; u8 dup_ack_counter:2, tlp_retrans:1, /* TLP is a retransmission */ tcp_usec_ts:1, /* TSval values in usec */ unused:4; - u32 chrono_start; /* Start time in jiffies of a TCP chrono */ - u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ - u8 chrono_type:2, /* current chronograph type */ - rate_app_limited:1, /* rate_{delivered,interval_us} limited? */ + u8 thin_lto : 1,/* Use linear timeouts for thin streams */ + recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */ fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */ fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */ - is_sack_reneg:1, /* in recovery from loss with SACK reneg? */ - fastopen_client_fail:2; /* reason why fastopen failed */ - u8 nonagle : 4,/* Disable Nagle algorithm? */ - thin_lto : 1,/* Use linear timeouts for thin streams */ - recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */ - repair : 1, + fastopen_client_fail:2, /* reason why fastopen failed */ frto : 1;/* F-RTO (RFC5682) activated in CA_Loss */ u8 repair_queue; u8 save_syn:2, /* Save headers of SYN packet */ @@ -293,45 +382,19 @@ struct tcp_sock { syn_fastopen:1, /* SYN includes Fast Open option */ syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */ syn_fastopen_ch:1, /* Active TFO re-enabling probe */ - syn_data_acked:1,/* data in SYN is acked by SYN-ACK */ - is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */ - u32 tlp_high_seq; /* snd_nxt at the time of TLP */ + syn_data_acked:1;/* data in SYN is acked by SYN-ACK */ u32 tcp_tx_delay; /* delay (in usec) added to TX packets */ - u64 tcp_wstamp_ns; /* departure time for next sent data packet */ - u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ /* RTT measurement */ - u64 tcp_mstamp; /* most recent packet received/sent */ - u32 srtt_us; /* smoothed round trip time << 3 in usecs */ - u32 mdev_us; /* medium deviation */ u32 mdev_max_us; /* maximal mdev for the last rtt period */ - u32 rttvar_us; /* smoothed mdev_max */ - u32 rtt_seq; /* sequence number to update rttvar */ - struct minmax rtt_min; - u32 packets_out; /* Packets which are "in flight" */ - u32 retrans_out; /* Retransmitted packets out */ - u32 max_packets_out; /* max packets_out in last window */ - u32 cwnd_usage_seq; /* right edge of cwnd usage tracking flight */ - - u16 urg_data; /* Saved octet of OOB data and control flags */ - u8 ecn_flags; /* ECN status bits. */ u8 keepalive_probes; /* num of allowed keep alive probes */ - u32 reordering; /* Packet reordering metric. */ u32 reord_seen; /* number of data packet reordering events */ - u32 snd_up; /* Urgent pointer */ - -/* - * Options received (usually on last packet, some only on SYN packets). - */ - struct tcp_options_received rx_opt; /* * Slow start and congestion control (see also Nagle, and Karn & Partridge) */ - u32 snd_ssthresh; /* Slow start size threshold */ - u32 snd_cwnd; /* Sending congestion window */ u32 snd_cwnd_cnt; /* Linear increase counter */ u32 snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */ u32 snd_cwnd_used; @@ -339,32 +402,10 @@ struct tcp_sock { u32 prior_cwnd; /* cwnd right before starting loss recovery */ u32 prr_delivered; /* Number of newly delivered packets to * receiver in Recovery. */ - u32 prr_out; /* Total number of pkts sent during Recovery. */ - u32 delivered; /* Total data packets delivered incl. rexmits */ - u32 delivered_ce; /* Like the above but only ECE marked packets */ - u32 lost; /* Total data packets lost incl. rexmits */ - u32 app_limited; /* limited until "delivered" reaches this val */ - u64 first_tx_mstamp; /* start of window send phase */ - u64 delivered_mstamp; /* time we reached "delivered" */ - u32 rate_delivered; /* saved rate sample: packets delivered */ - u32 rate_interval_us; /* saved rate sample: time elapsed */ - - u32 rcv_wnd; /* Current receiver window */ - u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ - u32 notsent_lowat; /* TCP_NOTSENT_LOWAT */ - u32 pushed_seq; /* Last pushed seq, required to talk to windows */ - u32 lost_out; /* Lost packets */ - u32 sacked_out; /* SACK'd packets */ struct hrtimer pacing_timer; struct hrtimer compressed_ack_timer; - /* from STCP, retrans queue hinting */ - struct sk_buff* lost_skb_hint; - struct sk_buff *retransmit_skb_hint; - - /* OOO segments go in this rbtree. Socket lock must be held. */ - struct rb_root out_of_order_queue; struct sk_buff *ooo_last_skb; /* cache rb_last(out_of_order_queue) */ /* SACKs data, these 2 need to be together (see tcp_options_write) */ @@ -373,12 +414,6 @@ struct tcp_sock { struct tcp_sack_block recv_sack_cache[4]; - struct sk_buff *highest_sack; /* skb just after the highest - * skb with SACKed bit set - * (validity guaranteed only if - * sacked_out > 0) - */ - int lost_cnt_hint; u32 prior_ssthresh; /* ssthresh saved at recovery start */ @@ -429,21 +464,6 @@ struct tcp_sock { u32 rcv_ooopack; /* Received out-of-order packets, for tcpinfo */ -/* Receiver side RTT estimation */ - u32 rcv_rtt_last_tsecr; - struct { - u32 rtt_us; - u32 seq; - u64 time; - } rcv_rtt_est; - -/* Receiver queue space */ - struct { - u32 space; - u32 seq; - u64 time; - } rcvq_space; - /* TCP-specific MTU probe information. */ struct { u32 probe_seq_start; diff --git a/include/linux/tnum.h b/include/linux/tnum.h index 1c3948a1d6ad..3c13240077b8 100644 --- a/include/linux/tnum.h +++ b/include/linux/tnum.h @@ -106,6 +106,10 @@ int tnum_sbin(char *str, size_t size, struct tnum a); struct tnum tnum_subreg(struct tnum a); /* Returns the tnum with the lower 32-bit subreg cleared */ struct tnum tnum_clear_subreg(struct tnum a); +/* Returns the tnum with the lower 32-bit subreg in *reg* set to the lower + * 32-bit subreg in *subreg* + */ +struct tnum tnum_with_subreg(struct tnum reg, struct tnum subreg); /* Returns the tnum with the lower 32-bit subreg set to value */ struct tnum tnum_const_subreg(struct tnum a, u32 value); /* Returns true if 32-bit subreg @a is a known constant*/ diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index ebb3ce63d64d..c82089dee0c8 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -256,4 +256,5 @@ void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit); void virtio_transport_deliver_tap_pkt(struct sk_buff *skb); int virtio_transport_purge_skbs(void *vsk, struct sk_buff_head *list); int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t read_actor); +int virtio_transport_notify_set_rcvlowat(struct vsock_sock *vsk, int val); #endif /* _LINUX_VIRTIO_VSOCK_H */ |