diff options
Diffstat (limited to 'include')
125 files changed, 3143 insertions, 1191 deletions
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index aa4096126553..8c4768c44a01 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -83,6 +83,10 @@ struct device; * bitmap_to_arr64(buf, src, nbits) Copy nbits from buf to u64[] dst * bitmap_get_value8(map, start) Get 8bit value from map at start * bitmap_set_value8(map, value, start) Set 8bit value to map at start + * bitmap_read(map, start, nbits) Read an nbits-sized value from + * map at start + * bitmap_write(map, value, start, nbits) Write an nbits-sized value to + * map at start * * Note, bitmap_zero() and bitmap_fill() operate over the region of * unsigned longs, that is, bits behind bitmap till the unsigned long @@ -222,9 +226,11 @@ void bitmap_fold(unsigned long *dst, const unsigned long *orig, #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) +#define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE) + static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = 0; @@ -234,7 +240,7 @@ static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = ~0UL; @@ -245,7 +251,7 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = *src; @@ -722,38 +728,83 @@ static inline void bitmap_from_u64(unsigned long *dst, u64 mask) } /** - * bitmap_get_value8 - get an 8-bit value within a memory region + * bitmap_read - read a value of n-bits from the memory region * @map: address to the bitmap memory region - * @start: bit offset of the 8-bit value; must be a multiple of 8 + * @start: bit offset of the n-bit value + * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG * - * Returns the 8-bit value located at the @start bit offset within the @src - * memory region. + * Returns: value of @nbits bits located at the @start bit offset within the + * @map memory region. For @nbits = 0 and @nbits > BITS_PER_LONG the return + * value is undefined. */ -static inline unsigned long bitmap_get_value8(const unsigned long *map, - unsigned long start) +static inline unsigned long bitmap_read(const unsigned long *map, + unsigned long start, + unsigned long nbits) { - const size_t index = BIT_WORD(start); - const unsigned long offset = start % BITS_PER_LONG; + size_t index = BIT_WORD(start); + unsigned long offset = start % BITS_PER_LONG; + unsigned long space = BITS_PER_LONG - offset; + unsigned long value_low, value_high; + + if (unlikely(!nbits || nbits > BITS_PER_LONG)) + return 0; + + if (space >= nbits) + return (map[index] >> offset) & BITMAP_LAST_WORD_MASK(nbits); - return (map[index] >> offset) & 0xFF; + value_low = map[index] & BITMAP_FIRST_WORD_MASK(start); + value_high = map[index + 1] & BITMAP_LAST_WORD_MASK(start + nbits); + return (value_low >> offset) | (value_high << space); } /** - * bitmap_set_value8 - set an 8-bit value within a memory region + * bitmap_write - write n-bit value within a memory region * @map: address to the bitmap memory region - * @value: the 8-bit value; values wider than 8 bits may clobber bitmap - * @start: bit offset of the 8-bit value; must be a multiple of 8 + * @value: value to write, clamped to nbits + * @start: bit offset of the n-bit value + * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG. + * + * bitmap_write() behaves as-if implemented as @nbits calls of __assign_bit(), + * i.e. bits beyond @nbits are ignored: + * + * for (bit = 0; bit < nbits; bit++) + * __assign_bit(start + bit, bitmap, val & BIT(bit)); + * + * For @nbits == 0 and @nbits > BITS_PER_LONG no writes are performed. */ -static inline void bitmap_set_value8(unsigned long *map, unsigned long value, - unsigned long start) -{ - const size_t index = BIT_WORD(start); - const unsigned long offset = start % BITS_PER_LONG; - - map[index] &= ~(0xFFUL << offset); +static inline void bitmap_write(unsigned long *map, unsigned long value, + unsigned long start, unsigned long nbits) +{ + size_t index; + unsigned long offset; + unsigned long space; + unsigned long mask; + bool fit; + + if (unlikely(!nbits || nbits > BITS_PER_LONG)) + return; + + mask = BITMAP_LAST_WORD_MASK(nbits); + value &= mask; + offset = start % BITS_PER_LONG; + space = BITS_PER_LONG - offset; + fit = space >= nbits; + index = BIT_WORD(start); + + map[index] &= (fit ? (~(mask << offset)) : ~BITMAP_FIRST_WORD_MASK(start)); map[index] |= value << offset; + if (fit) + return; + + map[index + 1] &= BITMAP_FIRST_WORD_MASK(start + nbits); + map[index + 1] |= (value >> space); } +#define bitmap_get_value8(map, start) \ + bitmap_read(map, start, BITS_PER_BYTE) +#define bitmap_set_value8(map, value, start) \ + bitmap_write(map, value, start, BITS_PER_BYTE) + #endif /* __ASSEMBLY__ */ #endif /* __LINUX_BITMAP_H */ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 2ba557e067fe..b25dc8742124 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -21,6 +21,8 @@ #define BITS_TO_U32(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u32)) #define BITS_TO_BYTES(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(char)) +#define BYTES_TO_BITS(nb) ((nb) * BITS_PER_BYTE) + extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); extern unsigned int __sw_hweight32(unsigned int w); @@ -80,6 +82,7 @@ __check_bitop_pr(__test_and_set_bit); __check_bitop_pr(__test_and_clear_bit); __check_bitop_pr(__test_and_change_bit); __check_bitop_pr(test_bit); +__check_bitop_pr(test_bit_acquire); #undef __check_bitop_pr @@ -272,23 +275,11 @@ static inline unsigned long fns(unsigned long word, unsigned int n) * @addr: the address to start counting from * @value: the value to assign */ -static __always_inline void assign_bit(long nr, volatile unsigned long *addr, - bool value) -{ - if (value) - set_bit(nr, addr); - else - clear_bit(nr, addr); -} +#define assign_bit(nr, addr, value) \ + ((value) ? set_bit((nr), (addr)) : clear_bit((nr), (addr))) -static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, - bool value) -{ - if (value) - __set_bit(nr, addr); - else - __clear_bit(nr, addr); -} +#define __assign_bit(nr, addr, value) \ + ((value) ? __set_bit((nr), (addr)) : __clear_bit((nr), (addr))) /** * __ptr_set_bit - Set bit in a pointer's value diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 890e152d553e..90094400cc63 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -184,8 +184,8 @@ struct bpf_map_ops { }; enum { - /* Support at most 10 fields in a BTF type */ - BTF_FIELDS_MAX = 10, + /* Support at most 11 fields in a BTF type */ + BTF_FIELDS_MAX = 11, }; enum btf_field_type { @@ -202,6 +202,7 @@ enum btf_field_type { BPF_GRAPH_NODE = BPF_RB_NODE | BPF_LIST_NODE, BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD, BPF_REFCOUNT = (1 << 9), + BPF_WORKQUEUE = (1 << 10), }; typedef void (*btf_dtor_kfunc_t)(void *); @@ -238,6 +239,7 @@ struct btf_record { u32 field_mask; int spin_lock_off; int timer_off; + int wq_off; int refcount_off; struct btf_field fields[]; }; @@ -312,6 +314,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type) return "bpf_spin_lock"; case BPF_TIMER: return "bpf_timer"; + case BPF_WORKQUEUE: + return "bpf_wq"; case BPF_KPTR_UNREF: case BPF_KPTR_REF: return "kptr"; @@ -340,6 +344,8 @@ static inline u32 btf_field_type_size(enum btf_field_type type) return sizeof(struct bpf_spin_lock); case BPF_TIMER: return sizeof(struct bpf_timer); + case BPF_WORKQUEUE: + return sizeof(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: @@ -367,6 +373,8 @@ static inline u32 btf_field_type_align(enum btf_field_type type) return __alignof__(struct bpf_spin_lock); case BPF_TIMER: return __alignof__(struct bpf_timer); + case BPF_WORKQUEUE: + return __alignof__(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: @@ -406,6 +414,7 @@ static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) /* RB_ROOT_CACHED 0-inits, no need to do anything after memset */ case BPF_SPIN_LOCK: case BPF_TIMER: + case BPF_WORKQUEUE: case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: @@ -525,6 +534,7 @@ static inline void zero_map_value(struct bpf_map *map, void *dst) void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); void bpf_timer_cancel_and_free(void *timer); +void bpf_wq_cancel_and_free(void *timer); void bpf_list_head_free(const struct btf_field *field, void *list_head, struct bpf_spin_lock *spin_lock); void bpf_rb_root_free(const struct btf_field *field, void *rb_root, @@ -1116,8 +1126,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i 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 __must_check arch_protect_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); @@ -1266,6 +1275,7 @@ 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); +bool __bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr); #ifdef CONFIG_BPF_JIT int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); @@ -1622,6 +1632,12 @@ struct bpf_tracing_link { struct bpf_prog *tgt_prog; }; +struct bpf_raw_tp_link { + struct bpf_link link; + struct bpf_raw_event_map *btp; + u64 cookie; +}; + struct bpf_link_primer { struct bpf_link *link; struct file *file; @@ -2204,6 +2220,7 @@ void bpf_map_free_record(struct bpf_map *map); struct btf_record *btf_record_dup(const struct btf_record *rec); bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b); void bpf_obj_free_timer(const struct btf_record *rec, void *obj); +void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj); void bpf_obj_free_fields(const struct btf_record *rec, void *obj); void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu); @@ -3005,6 +3022,7 @@ int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); +int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog); void sock_map_unhash(struct sock *sk); void sock_map_destroy(struct sock *sk); @@ -3103,6 +3121,11 @@ static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, { return -EINVAL; } + +static inline int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ diff --git a/include/linux/bpf_crypto.h b/include/linux/bpf_crypto.h new file mode 100644 index 000000000000..a41e71d4e2d9 --- /dev/null +++ b/include/linux/bpf_crypto.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#ifndef _BPF_CRYPTO_H +#define _BPF_CRYPTO_H + +struct bpf_crypto_type { + void *(*alloc_tfm)(const char *algo); + void (*free_tfm)(void *tfm); + int (*has_algo)(const char *algo); + int (*setkey)(void *tfm, const u8 *key, unsigned int keylen); + int (*setauthsize)(void *tfm, unsigned int authsize); + int (*encrypt)(void *tfm, const u8 *src, u8 *dst, unsigned int len, u8 *iv); + int (*decrypt)(void *tfm, const u8 *src, u8 *dst, unsigned int len, u8 *iv); + unsigned int (*ivsize)(void *tfm); + unsigned int (*statesize)(void *tfm); + u32 (*get_flags)(void *tfm); + struct module *owner; + char name[14]; +}; + +int bpf_crypto_register_type(const struct bpf_crypto_type *type); +int bpf_crypto_unregister_type(const struct bpf_crypto_type *type); + +#endif /* _BPF_CRYPTO_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7cb1b75eee38..50aa87f8d77f 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -421,11 +421,13 @@ struct bpf_verifier_state { struct bpf_active_lock active_lock; bool speculative; bool active_rcu_lock; + u32 active_preempt_lock; /* If this state was ever pointed-to by other state's loop_entry field * this flag would be set to true. Used to avoid freeing such states * while they are still in use. */ bool used_as_loop_entry; + bool in_sleepable; /* first and last insn idx of this verifier state */ u32 first_insn_idx; @@ -502,6 +504,13 @@ struct bpf_loop_inline_state { u32 callback_subprogno; /* valid when fit_for_inline is true */ }; +/* pointer and state for maps */ +struct bpf_map_ptr_state { + struct bpf_map *map_ptr; + bool poison; + bool unpriv; +}; + /* Possible states for alu_state member. */ #define BPF_ALU_SANITIZE_SRC (1U << 0) #define BPF_ALU_SANITIZE_DST (1U << 1) @@ -514,7 +523,7 @@ struct bpf_loop_inline_state { struct bpf_insn_aux_data { union { enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ - unsigned long map_ptr_state; /* pointer/poison value for maps */ + struct bpf_map_ptr_state map_ptr_state; s32 call_imm; /* saved imm field of call insn */ u32 alu_limit; /* limit for add/sub register with pointer */ struct { diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index e24aabfe8ecc..c0e3e1426a82 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -3,6 +3,8 @@ #ifndef _LINUX_BTF_IDS_H #define _LINUX_BTF_IDS_H +#include <linux/types.h> /* for u32 */ + struct btf_id_set { u32 cnt; u32 ids[]; diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 774c2570fe51..d1a9dbb8e1a7 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -300,6 +300,17 @@ struct ftrace_likely_data { #define __no_sanitize_or_inline __always_inline #endif +/* + * Apply __counted_by() when the Endianness matches to increase test coverage. + */ +#ifdef __LITTLE_ENDIAN +#define __counted_by_le(member) __counted_by(member) +#define __counted_by_be(member) +#else +#define __counted_by_le(member) +#define __counted_by_be(member) __counted_by(member) +#endif + /* Do not trap wrapping arithmetic within an annotated function. */ #ifdef CONFIG_UBSAN_SIGNED_WRAP # define __signed_wrap __attribute__((no_sanitize("signed-integer-overflow"))) diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index ac9f3109c984..e8c412ee6400 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -893,7 +893,7 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp) */ static inline unsigned int cpumask_size(void) { - return BITS_TO_LONGS(large_cpumask_bits) * sizeof(long); + return bitmap_size(large_cpumask_bits); } /* diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h index 5693a4be0d9a..281298e77a15 100644 --- a/include/linux/dynamic_queue_limits.h +++ b/include/linux/dynamic_queue_limits.h @@ -50,6 +50,9 @@ struct dql { unsigned int adj_limit; /* limit + num_completed */ unsigned int last_obj_cnt; /* Count at last queuing */ + /* Stall threshold (in jiffies), defined by user */ + unsigned short stall_thrs; + unsigned long history_head; /* top 58 bits of jiffies */ /* stall entries, a bit per entry */ unsigned long history[DQL_HIST_LEN]; @@ -71,8 +74,6 @@ struct dql { unsigned int min_limit; /* Minimum limit */ unsigned int slack_hold_time; /* Time to measure slack */ - /* Stall threshold (in jiffies), defined by user */ - unsigned short stall_thrs; /* Longest stall detected, reported to user */ unsigned short stall_max; unsigned long last_reap; /* Last reap (in jiffies) */ @@ -83,27 +84,11 @@ struct dql { #define DQL_MAX_OBJECT (UINT_MAX / 16) #define DQL_MAX_LIMIT ((UINT_MAX / 2) - DQL_MAX_OBJECT) -/* - * Record number of objects queued. Assumes that caller has already checked - * availability in the queue with dql_avail. - */ -static inline void dql_queued(struct dql *dql, unsigned int count) +/* Populate the bitmap to be processed later in dql_check_stall() */ +static inline void dql_queue_stall(struct dql *dql) { unsigned long map, now, now_hi, i; - BUG_ON(count > DQL_MAX_OBJECT); - - dql->last_obj_cnt = count; - - /* We want to force a write first, so that cpu do not attempt - * to get cache line containing last_obj_cnt, num_queued, adj_limit - * in Shared state, but directly does a Request For Ownership - * It is only a hint, we use barrier() only. - */ - barrier(); - - dql->num_queued += count; - now = jiffies; now_hi = now / BITS_PER_LONG; @@ -133,6 +118,31 @@ static inline void dql_queued(struct dql *dql, unsigned int count) WRITE_ONCE(DQL_HIST_ENT(dql, now_hi), map | BIT_MASK(now)); } +/* + * Record number of objects queued. Assumes that caller has already checked + * availability in the queue with dql_avail. + */ +static inline void dql_queued(struct dql *dql, unsigned int count) +{ + if (WARN_ON_ONCE(count > DQL_MAX_OBJECT)) + return; + + dql->last_obj_cnt = count; + + /* We want to force a write first, so that cpu do not attempt + * to get cache line containing last_obj_cnt, num_queued, adj_limit + * in Shared state, but directly does a Request For Ownership + * It is only a hint, we use barrier() only. + */ + barrier(); + + dql->num_queued += count; + + /* Only populate stall information if the threshold is set */ + if (READ_ONCE(dql->stall_thrs)) + dql_queue_stall(dql); +} + /* Returns how many objects can be queued, < 0 indicates over limit. */ static inline int dql_avail(const struct dql *dql) { diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 297231854ada..2ad1ffa4ccb9 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -71,6 +71,12 @@ static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }; #define eth_stp_addr eth_reserved_addr_base +static const u8 eth_ipv4_mcast_addr_base[ETH_ALEN] __aligned(2) = +{ 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 }; + +static const u8 eth_ipv6_mcast_addr_base[ETH_ALEN] __aligned(2) = +{ 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 }; + /** * is_link_local_ether_addr - Determine if given Ethernet address is link-local * @addr: Pointer to a six-byte array containing the Ethernet address @@ -430,18 +436,16 @@ static inline bool ether_addr_equal_masked(const u8 *addr1, const u8 *addr2, static inline bool ether_addr_is_ipv4_mcast(const u8 *addr) { - u8 base[ETH_ALEN] = { 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 }; u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0x80, 0x00, 0x00 }; - return ether_addr_equal_masked(addr, base, mask); + return ether_addr_equal_masked(addr, eth_ipv4_mcast_addr_base, mask); } static inline bool ether_addr_is_ipv6_mcast(const u8 *addr) { - u8 base[ETH_ALEN] = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 }; u8 mask[ETH_ALEN] = { 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 }; - return ether_addr_equal_masked(addr, base, mask); + return ether_addr_equal_masked(addr, eth_ipv6_mcast_addr_base, mask); } static inline bool ether_addr_is_ip_mcast(const u8 *addr) diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 9901e563f706..6fd9107d3cc0 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -480,6 +480,26 @@ struct ethtool_rmon_stats { ); }; +/** + * struct ethtool_ts_stats - HW timestamping statistics + * @pkts: Number of packets successfully timestamped by the hardware. + * @lost: Number of hardware timestamping requests where the timestamping + * information from the hardware never arrived for submission with + * the skb. + * @err: Number of arbitrary timestamp generation error events that the + * hardware encountered, exclusive of @lost statistics. Cases such + * as resource exhaustion, unavailability, firmware errors, and + * detected illogical timestamp values not submitted with the skb + * are inclusive to this counter. + */ +struct ethtool_ts_stats { + struct_group(tx_stats, + u64 pkts; + u64 lost; + u64 err; + ); +}; + #define ETH_MODULE_EEPROM_PAGE_LEN 128 #define ETH_MODULE_MAX_I2C_ADDRESS 0x7f @@ -755,7 +775,10 @@ struct ethtool_rxfh_param { * @get_ts_info: Get the time stamping and PTP hardware clock capabilities. * It may be called with RCU, or rtnl or reference on the device. * Drivers supporting transmit time stamps in software should set this to - * ethtool_op_get_ts_info(). + * ethtool_op_get_ts_info(). Drivers must not zero statistics which they + * don't report. The stats structure is initialized to ETHTOOL_STAT_NOT_SET + * indicating driver does not report statistics. + * @get_ts_stats: Query the device hardware timestamping statistics. * @get_module_info: Get the size and type of the eeprom contained within * a plug-in module. * @get_module_eeprom: Get the eeprom information from the plug-in module @@ -898,6 +921,8 @@ struct ethtool_ops { struct ethtool_dump *, void *); int (*set_dump)(struct net_device *, struct ethtool_dump *); int (*get_ts_info)(struct net_device *, struct ethtool_ts_info *); + void (*get_ts_stats)(struct net_device *dev, + struct ethtool_ts_stats *ts_stats); int (*get_module_info)(struct net_device *, struct ethtool_modinfo *); int (*get_module_eeprom)(struct net_device *, diff --git a/include/linux/filter.h b/include/linux/filter.h index 219ee7a76874..0f12cf01070e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -75,6 +75,9 @@ struct ctl_table_header; /* unused opcode to mark special load instruction. Same as BPF_MSH */ #define BPF_PROBE_MEM32 0xa0 +/* unused opcode to mark special atomic instruction */ +#define BPF_PROBE_ATOMIC 0xe0 + /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 @@ -178,6 +181,25 @@ struct ctl_table_header; .off = 0, \ .imm = 0 }) +/* Special (internal-only) form of mov, used to resolve per-CPU addrs: + * dst_reg = src_reg + <percpu_base_off> + * BPF_ADDR_PERCPU is used as a special insn->off value. + */ +#define BPF_ADDR_PERCPU (-1) + +#define BPF_MOV64_PERCPU_REG(DST, SRC) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = BPF_ADDR_PERCPU, \ + .imm = 0 }) + +static inline bool insn_is_mov_percpu_addr(const struct bpf_insn *insn) +{ + return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->off == BPF_ADDR_PERCPU; +} + /* Short form of mov, dst_reg = imm32 */ #define BPF_MOV64_IMM(DST, IMM) \ @@ -228,6 +250,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) return insn->code == (BPF_ALU | BPF_MOV | BPF_X) && insn->imm == 1; } +/* addr_space_cast from as(0) to as(1) is for converting bpf arena pointers + * to pointers in user vma. + */ +static inline bool insn_is_cast_user(const struct bpf_insn *insn) +{ + return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && + insn->off == BPF_ADDR_SPACE_CAST && + insn->imm == 1U << 16; +} + /* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */ #define BPF_LD_IMM64(DST, IMM) \ BPF_LD_IMM64_RAW(DST, 0, IMM) @@ -644,14 +676,16 @@ static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog, cant_migrate(); if (static_branch_unlikely(&bpf_stats_enabled_key)) { struct bpf_prog_stats *stats; - u64 start = sched_clock(); + u64 duration, start = sched_clock(); unsigned long flags; ret = dfunc(ctx, prog->insnsi, prog->bpf_func); + + duration = sched_clock() - start; stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->cnt); - u64_stats_add(&stats->nsecs, sched_clock() - start); + u64_stats_add(&stats->nsecs, duration); u64_stats_update_end_irqrestore(&stats->syncp, flags); } else { ret = dfunc(ctx, prog->insnsi, prog->bpf_func); @@ -887,20 +921,22 @@ bpf_ctx_narrow_access_offset(u32 off, u32 size, u32 size_default) #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) -static inline void bpf_prog_lock_ro(struct bpf_prog *fp) +static inline int __must_check bpf_prog_lock_ro(struct bpf_prog *fp) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON if (!fp->jited) { set_vm_flush_reset_perms(fp); - set_memory_ro((unsigned long)fp, fp->pages); + return set_memory_ro((unsigned long)fp, fp->pages); } #endif + return 0; } -static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) +static inline int __must_check +bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { set_vm_flush_reset_perms(hdr); - set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT); + return set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT); } int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); @@ -957,12 +993,15 @@ u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); bool bpf_jit_needs_zext(void); +bool bpf_jit_inlines_helper_call(s32 imm); bool bpf_jit_supports_subprog_tailcalls(void); +bool bpf_jit_supports_percpu_insn(void); bool bpf_jit_supports_kfunc_call(void); bool bpf_jit_supports_far_kfunc_call(void); bool bpf_jit_supports_exceptions(void); bool bpf_jit_supports_ptr_xchg(void); bool bpf_jit_supports_arena(void); +bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena); u64 bpf_arch_uaddress_limit(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); bool bpf_helper_changes_pkt_data(void *func); diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h deleted file mode 100644 index c285968e437a..000000000000 --- a/include/linux/genetlink.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_GENERIC_NETLINK_H -#define __LINUX_GENERIC_NETLINK_H - -#include <uapi/linux/genetlink.h> - - -/* All generic netlink requests are serialized by a global lock. */ -extern void genl_lock(void); -extern void genl_unlock(void); - -/* for synchronisation between af_netlink and genetlink */ -extern atomic_t genl_sk_destructing_cnt; -extern wait_queue_head_t genl_sk_destructing_waitq; - -#define MODULE_ALIAS_GENL_FAMILY(family)\ - MODULE_ALIAS_NET_PF_PROTO_NAME(PF_NETLINK, NETLINK_GENERIC, "-family-" family) - -#endif /* __LINUX_GENERIC_NETLINK_H */ diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h index a419d93789ff..621b87a87d74 100644 --- a/include/linux/genl_magic_struct.h +++ b/include/linux/genl_magic_struct.h @@ -15,8 +15,8 @@ #endif #include <linux/args.h> -#include <linux/genetlink.h> #include <linux/types.h> +#include <net/genetlink.h> extern int CONCATENATE(GENL_MAGIC_FAMILY, _genl_register)(void); extern void CONCATENATE(GENL_MAGIC_FAMILY, _genl_unregister)(void); diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 3385a2cc5b09..de2dce743ee2 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1287,6 +1287,24 @@ struct ieee80211_ttlm_elem { u8 optional[]; } __packed; +/** + * struct ieee80211_bss_load_elem - BSS Load elemen + * + * Defined in section 9.4.2.26 in IEEE 802.11-REVme D4.1 + * + * @sta_count: total number of STAs currently associated with the AP. + * @channel_util: Percentage of time that the access point sensed the channel + * was busy. This value is in range [0, 255], the highest value means + * 100% busy. + * @avail_admission_capa: remaining amount of medium time used for admission + * control. + */ +struct ieee80211_bss_load_elem { + __le16 sta_count; + u8 channel_util; + __le16 avail_admission_capa; +} __packed; + struct ieee80211_mgmt { __le16 frame_control; __le16 duration; @@ -2742,9 +2760,11 @@ static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len) #define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x40000000 #define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x80000000 -#define IEEE80211_6GHZ_CTRL_REG_LPI_AP 0 -#define IEEE80211_6GHZ_CTRL_REG_SP_AP 1 -#define IEEE80211_6GHZ_CTRL_REG_VLP_AP 2 +#define IEEE80211_6GHZ_CTRL_REG_LPI_AP 0 +#define IEEE80211_6GHZ_CTRL_REG_SP_AP 1 +#define IEEE80211_6GHZ_CTRL_REG_VLP_AP 2 +#define IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP 3 +#define IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP 4 /** * struct ieee80211_he_6ghz_oper - HE 6 GHz operation Information field @@ -5166,7 +5186,7 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) bool check_common_len = false; u16 control; - if (len < fixed) + if (!data || len < fixed) return false; control = le16_to_cpu(mle->control); @@ -5302,7 +5322,7 @@ static inline bool ieee80211_mle_basic_sta_prof_size_ok(const u8 *data, info_len += 1; return prof->sta_info_len >= info_len && - fixed + prof->sta_info_len <= len; + fixed + prof->sta_info_len - 1 <= len; } /** diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index 287f590ed56b..d94bfd9ac8cc 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -43,29 +43,10 @@ static inline int linkmode_andnot(unsigned long *dst, const unsigned long *src1, return bitmap_andnot(dst, src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static inline void linkmode_set_bit(int nr, volatile unsigned long *addr) -{ - __set_bit(nr, addr); -} - -static inline void linkmode_clear_bit(int nr, volatile unsigned long *addr) -{ - __clear_bit(nr, addr); -} - -static inline void linkmode_mod_bit(int nr, volatile unsigned long *addr, - int set) -{ - if (set) - linkmode_set_bit(nr, addr); - else - linkmode_clear_bit(nr, addr); -} - -static inline int linkmode_test_bit(int nr, const volatile unsigned long *addr) -{ - return test_bit(nr, addr); -} +#define linkmode_test_bit test_bit +#define linkmode_set_bit __set_bit +#define linkmode_clear_bit __clear_bit +#define linkmode_mod_bit __assign_bit static inline void linkmode_set_bit_array(const int *array, int array_size, unsigned long *addr) diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index 693eba9869e4..b1fbe4118414 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -7,6 +7,7 @@ /* Known PHY IDs */ #define MARVELL_PHY_ID_88E1101 0x01410c60 +#define MARVELL_PHY_ID_88E3082 0x01410c80 #define MARVELL_PHY_ID_88E1112 0x01410c90 #define MARVELL_PHY_ID_88E1111 0x01410cc0 #define MARVELL_PHY_ID_88E1118 0x01410e10 @@ -31,6 +32,8 @@ /* Marvel 88E1111 in Finisar SFP module with modified PHY ID */ #define MARVELL_PHY_ID_88E1111_FINISAR 0x01ff0cc0 +/* ID from 88E6020, assumed to be the same for the whole 6250 family */ +#define MARVELL_PHY_ID_88E6250_FAMILY 0x01410db0 /* These Ethernet switch families contain embedded PHYs, but they do * not have a model ID. So the switch driver traps reads to the ID2 * register and returns the switch family ID diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 77b8c0a26674..cde01e133a1b 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -630,13 +630,29 @@ int mhi_async_power_up(struct mhi_controller *mhi_cntrl); int mhi_sync_power_up(struct mhi_controller *mhi_cntrl); /** - * mhi_power_down - Start MHI power down sequence + * mhi_power_down - Power down the MHI device and also destroy the + * 'struct device' for the channels associated with it. + * See also mhi_power_down_keep_dev() which is a variant + * of this API that keeps the 'struct device' for channels + * (useful during suspend/hibernation). * @mhi_cntrl: MHI controller * @graceful: Link is still accessible, so do a graceful shutdown process */ void mhi_power_down(struct mhi_controller *mhi_cntrl, bool graceful); /** + * mhi_power_down_keep_dev - Power down the MHI device but keep the 'struct + * device' for the channels associated with it. + * This is a variant of 'mhi_power_down()' and + * useful in scenarios such as suspend/hibernation + * where destroying of the 'struct device' is not + * needed. + * @mhi_cntrl: MHI controller + * @graceful: Link is still accessible, so do a graceful shutdown process + */ +void mhi_power_down_keep_dev(struct mhi_controller *mhi_cntrl, bool graceful); + +/** * mhi_unprepare_after_power_down - Free any allocated memory after power down * @mhi_cntrl: MHI controller */ diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index cb15308b5cb0..991526039ccb 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -95,9 +95,10 @@ enum { }; enum { - MLX5_CQ_MODIFY_PERIOD = 1 << 0, - MLX5_CQ_MODIFY_COUNT = 1 << 1, - MLX5_CQ_MODIFY_OVERRUN = 1 << 2, + MLX5_CQ_MODIFY_PERIOD = BIT(0), + MLX5_CQ_MODIFY_COUNT = BIT(1), + MLX5_CQ_MODIFY_OVERRUN = BIT(2), + MLX5_CQ_MODIFY_PERIOD_MODE = BIT(4), }; enum { diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 01275c6e8468..d7bb31d9a446 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -68,7 +68,7 @@ #define MLX5_UN_SZ_BYTES(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 8) #define MLX5_UN_SZ_DW(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 32) #define MLX5_BYTE_OFF(typ, fld) (__mlx5_bit_off(typ, fld) / 8) -#define MLX5_ADDR_OF(typ, p, fld) ((void *)((uint8_t *)(p) + MLX5_BYTE_OFF(typ, fld))) +#define MLX5_ADDR_OF(typ, p, fld) ((void *)((u8 *)(p) + MLX5_BYTE_OFF(typ, fld))) /* insert a value to a struct */ #define MLX5_SET(typ, p, fld, v) do { \ @@ -1336,6 +1336,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_ESW_FT_FIELD_SUPPORT_2(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE(mdev, ft_field_support_2_esw_fdb.cap) +#define MLX5_CAP_NIC_RX_FT_FIELD_SUPPORT_2(mdev, cap) \ + MLX5_CAP_FLOWTABLE(mdev, ft_field_support_2_nic_receive.cap) + #define MLX5_CAP_ESW(mdev, cap) \ MLX5_GET(e_switch_cap, \ mdev->caps.hca[MLX5_CAP_ESWITCH]->cur, cap) @@ -1359,6 +1362,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) \ MLX5_CAP_PORT_SELECTION(mdev, flow_table_properties_port_selection.cap) +#define MLX5_CAP_PORT_SELECTION_FT_FIELD_SUPPORT_2(mdev, cap) \ + MLX5_CAP_PORT_SELECTION(mdev, ft_field_support_2_port_selection.cap) + #define MLX5_CAP_ODP(mdev, cap)\ MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index bf9324a31ae9..779cfdf2e9d6 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -85,7 +85,7 @@ enum mlx5_sqp_t { }; enum { - MLX5_MAX_PORTS = 4, + MLX5_MAX_PORTS = 8, }; enum { @@ -862,6 +862,7 @@ struct mlx5_cmd_work_ent { void *context; int idx; struct completion handling; + struct completion slotted; struct completion done; struct mlx5_cmd *cmd; struct work_struct work; @@ -1374,11 +1375,4 @@ static inline bool mlx5_is_macsec_roce_supported(struct mlx5_core_dev *mdev) enum { MLX5_OCTWORD = 16, }; - -struct msi_map mlx5_msix_alloc(struct mlx5_core_dev *dev, - irqreturn_t (*handler)(int, void *), - const struct irq_affinity_desc *affdesc, - const char *name); -void mlx5_msix_free(struct mlx5_core_dev *dev, struct msi_map map); - #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c940b329a475..f468763478ae 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -416,7 +416,10 @@ struct mlx5_ifc_flow_table_fields_supported_bits { /* Table 2170 - Flow Table Fields Supported 2 Format */ struct mlx5_ifc_flow_table_fields_supported_2_bits { - u8 reserved_at_0[0xe]; + u8 reserved_at_0[0x2]; + u8 inner_l4_type[0x1]; + u8 outer_l4_type[0x1]; + u8 reserved_at_4[0xa]; u8 bth_opcode[0x1]; u8 reserved_at_f[0x1]; u8 tunnel_header_0_1[0x1]; @@ -525,6 +528,12 @@ union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits { u8 reserved_at_0[0x80]; }; +enum { + MLX5_PACKET_L4_TYPE_NONE, + MLX5_PACKET_L4_TYPE_TCP, + MLX5_PACKET_L4_TYPE_UDP, +}; + struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 smac_47_16[0x20]; @@ -550,7 +559,8 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 tcp_sport[0x10]; u8 tcp_dport[0x10]; - u8 reserved_at_c0[0x10]; + u8 l4_type[0x2]; + u8 reserved_at_c2[0xe]; u8 ipv4_ihl[0x4]; u8 reserved_at_c4[0x4]; @@ -846,7 +856,11 @@ struct mlx5_ifc_flow_table_nic_cap_bits { struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit_sniffer; - u8 reserved_at_e00[0x700]; + u8 reserved_at_e00[0x600]; + + struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_nic_receive; + + u8 reserved_at_1480[0x80]; struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_nic_receive_rdma; @@ -876,7 +890,9 @@ struct mlx5_ifc_port_selection_cap_bits { struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_port_selection; - u8 reserved_at_400[0x7c00]; + struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_port_selection; + + u8 reserved_at_480[0x7b80]; }; enum { @@ -1469,7 +1485,9 @@ enum { }; struct mlx5_ifc_cmd_hca_cap_bits { - u8 reserved_at_0[0x10]; + u8 reserved_at_0[0x6]; + u8 page_request_disable[0x1]; + u8 reserved_at_7[0x9]; u8 shared_object_to_user_object_allowed[0x1]; u8 reserved_at_13[0xe]; u8 vhca_resource_manager[0x1]; @@ -1668,7 +1686,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 cq_oi[0x1]; u8 cq_resize[0x1]; u8 cq_moderation[0x1]; - u8 reserved_at_223[0x3]; + u8 cq_period_mode_modify[0x1]; + u8 reserved_at_224[0x2]; u8 cq_eq_remap[0x1]; u8 pg[0x1]; u8 block_lb_mc[0x1]; @@ -2004,7 +2023,13 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_3a0[0x10]; u8 max_rqt_vhca_id[0x10]; - u8 reserved_at_3c0[0x440]; + u8 reserved_at_3c0[0x20]; + + u8 reserved_at_3e0[0x10]; + u8 pcc_ifa2[0x1]; + u8 reserved_at_3f1[0xf]; + + u8 reserved_at_400[0x400]; }; enum mlx5_ifc_flow_destination_type { @@ -4361,10 +4386,10 @@ enum { MLX5_CQC_ST_FIRED = 0xa, }; -enum { +enum mlx5_cq_period_mode { MLX5_CQ_PERIOD_MODE_START_FROM_EQE = 0x0, MLX5_CQ_PERIOD_MODE_START_FROM_CQE = 0x1, - MLX5_CQ_PERIOD_NUM_MODES + MLX5_CQ_PERIOD_NUM_MODES, }; struct mlx5_ifc_cqc_bits { @@ -9793,7 +9818,21 @@ struct mlx5_ifc_pplm_reg_bits { u8 fec_override_admin_100g_2x[0x10]; u8 fec_override_admin_50g_1x[0x10]; - u8 reserved_at_140[0x140]; + u8 fec_override_cap_800g_8x[0x10]; + u8 fec_override_cap_400g_4x[0x10]; + + u8 fec_override_cap_200g_2x[0x10]; + u8 fec_override_cap_100g_1x[0x10]; + + u8 reserved_at_180[0xa0]; + + u8 fec_override_admin_800g_8x[0x10]; + u8 fec_override_admin_400g_4x[0x10]; + + u8 fec_override_admin_200g_2x[0x10]; + u8 fec_override_admin_100g_1x[0x10]; + + u8 reserved_at_260[0x20]; }; struct mlx5_ifc_ppcnt_reg_bits { @@ -10165,7 +10204,9 @@ struct mlx5_ifc_mtutc_reg_bits { }; struct mlx5_ifc_pcam_enhanced_features_bits { - u8 reserved_at_0[0x68]; + u8 reserved_at_0[0x48]; + u8 fec_100G_per_lane_in_pplm[0x1]; + u8 reserved_at_49[0x1f]; u8 fec_50G_per_lane_in_pplm[0x1]; u8 reserved_at_69[0x4]; u8 rx_icrc_encapsulated_counter[0x1]; diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 7fada7a714fe..7cddfdac2f57 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -124,6 +124,7 @@ #define SDIO_DEVICE_ID_REALTEK_RTW8723DS_2ANT 0xd723 #define SDIO_DEVICE_ID_REALTEK_RTW8723DS_1ANT 0xd724 #define SDIO_DEVICE_ID_REALTEK_RTW8821DS 0xd821 +#define SDIO_DEVICE_ID_REALTEK_RTW8723CS 0xb703 #define SDIO_VENDOR_ID_SIANO 0x039a #define SDIO_DEVICE_ID_SIANO_NOVA_B0 0x0201 diff --git a/include/linux/net/intel/libie/rx.h b/include/linux/net/intel/libie/rx.h new file mode 100644 index 000000000000..8e97775f1d66 --- /dev/null +++ b/include/linux/net/intel/libie/rx.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2024 Intel Corporation */ + +#ifndef __LIBIE_RX_H +#define __LIBIE_RX_H + +#include <net/libeth/rx.h> + +/* Rx buffer management */ + +/* The largest size for a single descriptor as per HW */ +#define LIBIE_MAX_RX_BUF_LEN 9728U +/* "True" HW-writeable space: minimum from SW and HW values */ +#define LIBIE_RX_BUF_LEN(hr) min_t(u32, LIBETH_RX_PAGE_LEN(hr), \ + LIBIE_MAX_RX_BUF_LEN) + +/* The maximum frame size as per HW (S/G) */ +#define __LIBIE_MAX_RX_FRM_LEN 16382U +/* ATST, HW can chain up to 5 Rx descriptors */ +#define LIBIE_MAX_RX_FRM_LEN(hr) \ + min_t(u32, __LIBIE_MAX_RX_FRM_LEN, LIBIE_RX_BUF_LEN(hr) * 5) +/* Maximum frame size minus LL overhead */ +#define LIBIE_MAX_MTU \ + (LIBIE_MAX_RX_FRM_LEN(LIBETH_MAX_HEADROOM) - LIBETH_RX_LL_LEN) + +/* O(1) converting i40e/ice/iavf's 8/10-bit hardware packet type to a parsed + * bitfield struct. + */ + +#define LIBIE_RX_PT_NUM 154 + +extern const struct libeth_rx_pt libie_rx_pt_lut[LIBIE_RX_PT_NUM]; + +/** + * libie_rx_pt_parse - convert HW packet type to software bitfield structure + * @pt: 10-bit hardware packet type value from the descriptor + * + * ```libie_rx_pt_lut``` must be accessed only using this wrapper. + * + * Return: parsed bitfield struct corresponding to the provided ptype. + */ +static inline struct libeth_rx_pt libie_rx_pt_parse(u32 pt) +{ + if (unlikely(pt >= LIBIE_RX_PT_NUM)) + pt = 0; + + return libie_rx_pt_lut[pt]; +} + +#endif /* __LIBIE_RX_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cb37817d6382..d20c6c99eb88 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -59,7 +59,7 @@ struct ethtool_ops; struct kernel_hwtstamp_config; struct phy_device; struct dsa_port; -struct ip_tunnel_parm; +struct ip_tunnel_parm_kern; struct macsec_context; struct macsec_ops; struct netdev_name_node; @@ -1327,7 +1327,7 @@ struct netdev_net_notifier { * queue id bound to an AF_XDP socket. The flags field specifies if * only RX, only Tx, or both should be woken up using the flags * XDP_WAKEUP_RX and XDP_WAKEUP_TX. - * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p, + * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm_kern *p, * int cmd); * Add, change, delete or get information on an IPv4 tunnel. * struct net_device *(*ndo_get_peer_dev)(struct net_device *dev); @@ -1583,7 +1583,8 @@ struct net_device_ops { int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); int (*ndo_tunnel_ctl)(struct net_device *dev, - struct ip_tunnel_parm *p, int cmd); + struct ip_tunnel_parm_kern *p, + int cmd); struct net_device * (*ndo_get_peer_dev)(struct net_device *dev); int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path); @@ -1956,6 +1957,7 @@ enum netdev_reg_state { * @sysfs_rx_queue_group: Space for optional per-rx queue attributes * @rtnl_link_ops: Rtnl_link_ops * @stat_ops: Optional ops for queue-aware statistics + * @queue_mgmt_ops: Optional ops for queue management * * @gso_max_size: Maximum size of generic segmentation offload * @tso_max_size: Device (as in HW) limit on the max TSO request size @@ -2338,6 +2340,8 @@ struct net_device { const struct netdev_stat_ops *stat_ops; + const struct netdev_queue_mgmt_ops *queue_mgmt_ops; + /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SEGS 65535u #define GSO_LEGACY_MAX_SIZE 65536u @@ -2367,8 +2371,8 @@ struct net_device { struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; bool proto_down; + bool threaded; unsigned wol_enabled:1; - unsigned threaded:1; struct list_head net_notifier_list; @@ -3133,6 +3137,7 @@ struct net_device *netdev_get_by_name(struct net *net, const char *name, netdevice_tracker *tracker, gfp_t gfp); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); struct net_device *dev_get_by_napi_id(unsigned int napi_id); +void netdev_copy_name(struct net_device *dev, char *name); static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, @@ -3203,6 +3208,7 @@ struct softnet_data { struct softnet_data *rps_ipi_list; #endif + unsigned int received_rps; bool in_net_rx_action; bool in_napi_threaded_poll; @@ -3235,11 +3241,11 @@ struct softnet_data { unsigned int cpu; unsigned int input_queue_tail; #endif - unsigned int received_rps; - unsigned int dropped; struct sk_buff_head input_pkt_queue; struct napi_struct backlog; + atomic_t dropped ____cacheline_aligned_in_smp; + /* Another possibly contended cache line */ spinlock_t defer_lock ____cacheline_aligned_in_smp; int defer_count; @@ -3248,21 +3254,6 @@ struct softnet_data { call_single_data_t defer_csd; }; -static inline void input_queue_head_incr(struct softnet_data *sd) -{ -#ifdef CONFIG_RPS - sd->input_queue_head++; -#endif -} - -static inline void input_queue_tail_incr_save(struct softnet_data *sd, - unsigned int *qtail) -{ -#ifdef CONFIG_RPS - *qtail = ++sd->input_queue_tail; -#endif -} - DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); static inline int dev_recursion_level(void) @@ -3270,23 +3261,6 @@ static inline int dev_recursion_level(void) return this_cpu_read(softnet_data.xmit.recursion); } -#define XMIT_RECURSION_LIMIT 8 -static inline bool dev_xmit_recursion(void) -{ - return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > - XMIT_RECURSION_LIMIT); -} - -static inline void dev_xmit_recursion_inc(void) -{ - __this_cpu_inc(softnet_data.xmit.recursion); -} - -static inline void dev_xmit_recursion_dec(void) -{ - __this_cpu_dec(softnet_data.xmit.recursion); -} - void __netif_schedule(struct Qdisc *q); void netif_schedule_queue(struct netdev_queue *txq); @@ -4127,6 +4101,8 @@ static inline void dev_put(struct net_device *dev) netdev_put(dev, NULL); } +DEFINE_FREE(dev_put, struct net_device *, if (_T) dev_put(_T)) + static inline void netdev_ref_replace(struct net_device *odev, struct net_device *ndev, netdevice_tracker *tracker, @@ -4545,6 +4521,9 @@ static inline void netif_addr_unlock_bh(struct net_device *dev) void ether_setup(struct net_device *dev); +/* Allocate dummy net_device */ +struct net_device *alloc_netdev_dummy(int sizeof_priv); + /* Support for loadable net-drivers */ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, diff --git a/include/linux/phy.h b/include/linux/phy.h index 3f68b8239bb1..e6e83304558e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -778,6 +778,7 @@ struct phy_device { /* Generic phy_device::dev_flags */ #define PHY_F_NO_IRQ 0x80000000 +#define PHY_F_RXC_ALWAYS_ON 0x40000000 static inline struct phy_device *to_phy_device(const struct device *dev) { diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 9a57deefcb07..5ea6b2ad2396 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -138,6 +138,9 @@ enum phylink_op_type { * @poll_fixed_state: if true, starts link_poll, * if MAC link is at %MLO_AN_FIXED mode. * @mac_managed_pm: if true, indicate the MAC driver is responsible for PHY PM. + * @mac_requires_rxc: if true, the MAC always requires a receive clock from PHY. + * The PHY driver should start the clock signal as soon as + * possible and avoid stopping it during suspend events. * @ovr_an_inband: if true, override PCS to MLO_AN_INBAND * @get_fixed_state: callback to execute to determine the fixed link state, * if MAC link is at %MLO_AN_FIXED mode. @@ -150,6 +153,7 @@ struct phylink_config { enum phylink_op_type type; bool poll_fixed_state; bool mac_managed_pm; + bool mac_requires_rxc; bool ovr_an_inband; void (*get_fixed_state)(struct phylink_config *config, struct phylink_link_state *state); @@ -392,6 +396,10 @@ struct phylink_pcs_ops; * @phylink: pointer to &struct phylink_config * @neg_mode: provide PCS neg mode via "mode" argument * @poll: poll the PCS for link changes + * @rxc_always_on: The MAC driver requires the reference clock + * to always be on. Standalone PCS drivers which + * do not have access to a PHY device can check + * this instead of PHY_F_RXC_ALWAYS_ON. * * This structure is designed to be embedded within the PCS private data, * and will be passed between phylink and the PCS. @@ -404,6 +412,7 @@ struct phylink_pcs { struct phylink *phylink; bool neg_mode; bool poll; + bool rxc_always_on; }; /** @@ -418,6 +427,8 @@ struct phylink_pcs { * @pcs_an_restart: restart 802.3z BaseX autonegotiation. * @pcs_link_up: program the PCS for the resolved link configuration * (where necessary). + * @pcs_pre_init: configure PCS components necessary for MAC hardware + * initialization e.g. RX clock for stmmac. */ struct phylink_pcs_ops { int (*pcs_validate)(struct phylink_pcs *pcs, unsigned long *supported, @@ -437,6 +448,7 @@ struct phylink_pcs_ops { void (*pcs_an_restart)(struct phylink_pcs *pcs); void (*pcs_link_up)(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, int speed, int duplex); + int (*pcs_pre_init)(struct phylink_pcs *pcs); }; #if 0 /* For kernel-doc purposes only. */ @@ -542,6 +554,34 @@ void pcs_an_restart(struct phylink_pcs *pcs); */ void pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, int speed, int duplex); + +/** + * pcs_pre_init() - Configure PCS components necessary for MAC initialization + * @pcs: a pointer to a &struct phylink_pcs. + * + * This function can be called by MAC drivers through the + * phylink_pcs_pre_init() wrapper, before their hardware is initialized. It + * should not be called after the link is brought up, as reconfiguring the PCS + * at this point could break the link. + * + * Some MAC devices require specific hardware initialization to be performed by + * their associated PCS device before they can properly initialize their own + * hardware. An example of this is the initialization of stmmac controllers, + * which requires an active REF_CLK signal to be provided by the PHY/PCS. + * + * By calling phylink_pcs_pre_init(), MAC drivers can ensure that the PCS is + * setup in a way that allows for successful hardware initialization. + * + * The specific configuration performed by pcs_pre_init() is dependent on the + * model of PCS and the requirements of the MAC device attached to it. PCS + * driver authors should consider whether their target device is to be used in + * conjunction with a MAC device whose driver calls phylink_pcs_pre_init(). MAC + * driver authors should document their requirements for the PCS + * pre-initialization. + * + */ +int pcs_pre_init(struct phylink_pcs *pcs); + #endif struct phylink *phylink_create(struct phylink_config *, @@ -561,6 +601,8 @@ void phylink_disconnect_phy(struct phylink *); void phylink_mac_change(struct phylink *, bool up); void phylink_pcs_change(struct phylink_pcs *, bool up); +int phylink_pcs_pre_init(struct phylink *pl, struct phylink_pcs *pcs); + void phylink_start(struct phylink *); void phylink_stop(struct phylink *); diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h index fb724c65c77b..6d07c95dabb9 100644 --- a/include/linux/pse-pd/pse.h +++ b/include/linux/pse-pd/pse.h @@ -15,11 +15,14 @@ struct pse_controller_dev; /** * struct pse_control_config - PSE control/channel configuration. * - * @admin_cotrol: set PoDL PSE admin control as described in + * @podl_admin_control: set PoDL PSE admin control as described in * IEEE 802.3-2018 30.15.1.2.1 acPoDLPSEAdminControl + * @c33_admin_control: set PSE admin control as described in + * IEEE 802.3-2022 30.9.1.2.1 acPSEAdminControl */ struct pse_control_config { - enum ethtool_podl_pse_admin_state admin_cotrol; + enum ethtool_podl_pse_admin_state podl_admin_control; + enum ethtool_c33_pse_admin_state c33_admin_control; }; /** @@ -29,25 +32,36 @@ struct pse_control_config { * functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState * @podl_pw_status: power detection status of the PoDL PSE. * IEEE 802.3-2018 30.15.1.1.3 aPoDLPSEPowerDetectionStatus: + * @c33_admin_state: operational state of the PSE + * functions. IEEE 802.3-2022 30.9.1.1.2 aPSEAdminState + * @c33_pw_status: power detection status of the PSE. + * IEEE 802.3-2022 30.9.1.1.5 aPSEPowerDetectionStatus: */ struct pse_control_status { enum ethtool_podl_pse_admin_state podl_admin_state; enum ethtool_podl_pse_pw_d_status podl_pw_status; + enum ethtool_c33_pse_admin_state c33_admin_state; + enum ethtool_c33_pse_pw_d_status c33_pw_status; }; /** * struct pse_controller_ops - PSE controller driver callbacks * * @ethtool_get_status: get PSE control status for ethtool interface - * @ethtool_set_config: set PSE control configuration over ethtool interface + * @setup_pi_matrix: setup PI matrix of the PSE controller + * @pi_is_enabled: Return 1 if the PSE PI is enabled, 0 if not. + * May also return negative errno. + * @pi_enable: Configure the PSE PI as enabled. + * @pi_disable: Configure the PSE PI as disabled. */ struct pse_controller_ops { int (*ethtool_get_status)(struct pse_controller_dev *pcdev, unsigned long id, struct netlink_ext_ack *extack, struct pse_control_status *status); - int (*ethtool_set_config)(struct pse_controller_dev *pcdev, - unsigned long id, struct netlink_ext_ack *extack, - const struct pse_control_config *config); + int (*setup_pi_matrix)(struct pse_controller_dev *pcdev); + int (*pi_is_enabled)(struct pse_controller_dev *pcdev, int id); + int (*pi_enable)(struct pse_controller_dev *pcdev, int id); + int (*pi_disable)(struct pse_controller_dev *pcdev, int id); }; struct module; @@ -55,6 +69,40 @@ struct device_node; struct of_phandle_args; struct pse_control; +/* PSE PI pairset pinout can either be Alternative A or Alternative B */ +enum pse_pi_pairset_pinout { + ALTERNATIVE_A, + ALTERNATIVE_B, +}; + +/** + * struct pse_pi_pairset - PSE PI pairset entity describing the pinout + * alternative ant its phandle + * + * @pinout: description of the pinout alternative + * @np: device node pointer describing the pairset phandle + */ +struct pse_pi_pairset { + enum pse_pi_pairset_pinout pinout; + struct device_node *np; +}; + +/** + * struct pse_pi - PSE PI (Power Interface) entity as described in + * IEEE 802.3-2022 145.2.4 + * + * @pairset: table of the PSE PI pinout alternative for the two pairset + * @np: device node pointer of the PSE PI node + * @rdev: regulator represented by the PSE PI + * @admin_state_enabled: PI enabled state + */ +struct pse_pi { + struct pse_pi_pairset pairset[2]; + struct device_node *np; + struct regulator_dev *rdev; + bool admin_state_enabled; +}; + /** * struct pse_controller_dev - PSE controller entity that might * provide multiple PSE controls @@ -64,10 +112,11 @@ struct pse_control; * @pse_control_head: head of internal list of requested PSE controls * @dev: corresponding driver model device struct * @of_pse_n_cells: number of cells in PSE line specifiers - * @of_xlate: translation function to translate from specifier as found in the - * device tree to id as given to the PSE control ops * @nr_lines: number of PSE controls in this controller device * @lock: Mutex for serialization access to the PSE controller + * @types: types of the PSE controller + * @pi: table of PSE PIs described in this controller device + * @no_of_pse_pi: flag set if the pse_pis devicetree node is not used */ struct pse_controller_dev { const struct pse_controller_ops *ops; @@ -76,10 +125,11 @@ struct pse_controller_dev { struct list_head pse_control_head; struct device *dev; int of_pse_n_cells; - int (*of_xlate)(struct pse_controller_dev *pcdev, - const struct of_phandle_args *pse_spec); unsigned int nr_lines; struct mutex lock; + enum ethtool_pse_types types; + struct pse_pi *pi; + bool no_of_pse_pi; }; #if IS_ENABLED(CONFIG_PSE_CONTROLLER) @@ -99,6 +149,9 @@ int pse_ethtool_set_config(struct pse_control *psec, struct netlink_ext_ack *extack, const struct pse_control_config *config); +bool pse_has_podl(struct pse_control *psec); +bool pse_has_c33(struct pse_control *psec); + #else static inline struct pse_control *of_pse_control_get(struct device_node *node) @@ -124,6 +177,16 @@ static inline int pse_ethtool_set_config(struct pse_control *psec, return -ENOTSUPP; } +static inline bool pse_has_podl(struct pse_control *psec) +{ + return false; +} + +static inline bool pse_has_c33(struct pse_control *psec) +{ + return false; +} + #endif #endif diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 5b5357c0bd8c..8463a128e2f4 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -633,7 +633,7 @@ restart: * @params: hash table parameters * * Computes the hash value for the key and traverses the bucket chain looking - * for a entry with an identical key. The first matching entry is returned. + * for an entry with an identical key. The first matching entry is returned. * * This must only be called under the RCU read lock. * @@ -655,7 +655,7 @@ static inline void *rhashtable_lookup( * @params: hash table parameters * * Computes the hash value for the key and traverses the bucket chain looking - * for a entry with an identical key. The first matching entry is returned. + * for an entry with an identical key. The first matching entry is returned. * * Only use this function when you have other mechanisms guaranteeing * that the object won't go away after the RCU read lock is released. @@ -682,7 +682,7 @@ static inline void *rhashtable_lookup_fast( * @params: hash table parameters * * Computes the hash value for the key and traverses the bucket chain looking - * for a entry with an identical key. All matching entries are returned + * for an entry with an identical key. All matching entries are returned * in a list. * * This must only be called under the RCU read lock. @@ -699,7 +699,7 @@ static inline struct rhlist_head *rhltable_lookup( } /* Internal function, please use rhashtable_insert_fast() instead. This - * function returns the existing element already in hashes in there is a clash, + * function returns the existing element already in hashes if there is a clash, * otherwise it returns an error via ERR_PTR(). */ static inline void *__rhashtable_insert_fast( @@ -1130,7 +1130,7 @@ static inline int rhashtable_remove_fast( * * Since the hash chain is single linked, the removal operation needs to * walk the bucket chain upon removal. The removal operation is thus - * considerable slow if the hash table is not correctly sized. + * considerably slower if the hash table is not correctly sized. * * Will automatically shrink the table if permitted when residency drops * below 30% diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index cdfc897f1e3c..a7da7dfc06a2 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -7,6 +7,7 @@ #include <linux/netdevice.h> #include <linux/wait.h> #include <linux/refcount.h> +#include <linux/cleanup.h> #include <uapi/linux/rtnetlink.h> extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo); @@ -46,6 +47,8 @@ extern int rtnl_is_locked(void); extern int rtnl_lock_killable(void); extern bool refcount_dec_and_rtnl_lock(refcount_t *r); +DEFINE_LOCK_GUARD_0(rtnl, rtnl_lock(), rtnl_unlock()) + extern wait_queue_head_t netdev_unregistering_wq; extern atomic_t dev_unreg_count; extern struct rw_semaphore pernet_ops_rwsem; diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 9346cd44814d..a45da7eef9a2 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -554,7 +554,7 @@ bool sfp_may_have_phy(struct sfp_bus *bus, const struct sfp_eeprom_id *id); void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, unsigned long *support, unsigned long *interfaces); phy_interface_t sfp_select_interface(struct sfp_bus *bus, - unsigned long *link_modes); + const unsigned long *link_modes); int sfp_get_module_info(struct sfp_bus *bus, struct ethtool_modinfo *modinfo); int sfp_get_module_eeprom(struct sfp_bus *bus, struct ethtool_eeprom *ee, @@ -592,7 +592,7 @@ static inline void sfp_parse_support(struct sfp_bus *bus, } static inline phy_interface_t sfp_select_interface(struct sfp_bus *bus, - unsigned long *link_modes) + const unsigned long *link_modes) { return PHY_INTERFACE_MODE_NA; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1cc72c370190..c0b97c93a6de 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -353,8 +353,6 @@ struct sk_buff; #define MAX_SKB_FRAGS CONFIG_MAX_SKB_FRAGS -extern int sysctl_max_skb_frags; - /* Set skb_shinfo(skb)->gso_size to this in case you want skb_segment to * segment using its current segmentation instead. */ @@ -998,7 +996,7 @@ struct sk_buff { #ifdef CONFIG_NETFILTER_SKIP_EGRESS __u8 nf_skip_egress:1; #endif -#ifdef CONFIG_TLS_DEVICE +#ifdef CONFIG_SKB_DECRYPTED __u8 decrypted:1; #endif __u8 slow_gro:1; @@ -1180,15 +1178,6 @@ static inline bool skb_dst_is_noref(const struct sk_buff *skb) return (skb->_skb_refdst & SKB_DST_NOREF) && skb_dst(skb); } -/** - * skb_rtable - Returns the skb &rtable - * @skb: buffer - */ -static inline struct rtable *skb_rtable(const struct sk_buff *skb) -{ - return (struct rtable *)skb_dst(skb); -} - /* For mangling skb->pkt_type from user space side from applications * such as nft, tc, etc, we only allow a conservative subset of * possible pkt_types to be set. @@ -1621,17 +1610,26 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) static inline int skb_cmp_decrypted(const struct sk_buff *skb1, const struct sk_buff *skb2) { -#ifdef CONFIG_TLS_DEVICE +#ifdef CONFIG_SKB_DECRYPTED return skb2->decrypted - skb1->decrypted; #else return 0; #endif } +static inline bool skb_is_decrypted(const struct sk_buff *skb) +{ +#ifdef CONFIG_SKB_DECRYPTED + return skb->decrypted; +#else + return false; +#endif +} + static inline void skb_copy_decrypted(struct sk_buff *to, const struct sk_buff *from) { -#ifdef CONFIG_TLS_DEVICE +#ifdef CONFIG_SKB_DECRYPTED to->decrypted = from->decrypted; #endif } @@ -3370,13 +3368,7 @@ static inline void *napi_alloc_frag_align(unsigned int fragsz, return __napi_alloc_frag_align(fragsz, -align); } -struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, - unsigned int length, gfp_t gfp_mask); -static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi, - unsigned int length) -{ - return __napi_alloc_skb(napi, length, GFP_ATOMIC); -} +struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int length); void napi_consume_skb(struct sk_buff *skb, int budget); void napi_skb_free_stolen_head(struct sk_buff *skb); @@ -3509,85 +3501,10 @@ static inline struct page *skb_frag_page(const skb_frag_t *frag) return netmem_to_page(frag->netmem); } -/** - * __skb_frag_ref - take an addition reference on a paged fragment. - * @frag: the paged fragment - * - * Takes an additional reference on the paged fragment @frag. - */ -static inline void __skb_frag_ref(skb_frag_t *frag) -{ - get_page(skb_frag_page(frag)); -} - -/** - * skb_frag_ref - take an addition reference on a paged fragment of an skb. - * @skb: the buffer - * @f: the fragment offset. - * - * Takes an additional reference on the @f'th paged fragment of @skb. - */ -static inline void skb_frag_ref(struct sk_buff *skb, int f) -{ - __skb_frag_ref(&skb_shinfo(skb)->frags[f]); -} - int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, struct bpf_prog *prog); -bool napi_pp_put_page(struct page *page, bool napi_safe); - -static inline void -skb_page_unref(const struct sk_buff *skb, struct page *page, bool napi_safe) -{ -#ifdef CONFIG_PAGE_POOL - if (skb->pp_recycle && napi_pp_put_page(page, napi_safe)) - return; -#endif - put_page(page); -} - -static inline void -napi_frag_unref(skb_frag_t *frag, bool recycle, bool napi_safe) -{ - struct page *page = skb_frag_page(frag); - -#ifdef CONFIG_PAGE_POOL - if (recycle && napi_pp_put_page(page, napi_safe)) - return; -#endif - put_page(page); -} - -/** - * __skb_frag_unref - release a reference on a paged fragment. - * @frag: the paged fragment - * @recycle: recycle the page if allocated via page_pool - * - * Releases a reference on the paged fragment @frag - * or recycles the page via the page_pool API. - */ -static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) -{ - napi_frag_unref(frag, recycle, false); -} - -/** - * skb_frag_unref - release a reference on a paged fragment of an skb. - * @skb: the buffer - * @f: the fragment offset - * - * Releases a reference on the @f'th paged fragment of @skb. - */ -static inline void skb_frag_unref(struct sk_buff *skb, int f) -{ - struct skb_shared_info *shinfo = skb_shinfo(skb); - - if (!skb_zcopy_managed(skb)) - __skb_frag_unref(&shinfo->frags[f], skb->pp_recycle); -} - /** * skb_frag_address - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer @@ -4078,12 +3995,6 @@ int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, struct iov_iter *from, int len); int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm); void skb_free_datagram(struct sock *sk, struct sk_buff *skb); -void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len); -static inline void skb_free_datagram_locked(struct sock *sk, - struct sk_buff *skb) -{ - __skb_free_datagram_locked(sk, skb, 0); -} int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); diff --git a/include/linux/skbuff_ref.h b/include/linux/skbuff_ref.h new file mode 100644 index 000000000000..11f0a4063403 --- /dev/null +++ b/include/linux/skbuff_ref.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Skb ref helpers. + * + */ + +#ifndef _LINUX_SKBUFF_REF_H +#define _LINUX_SKBUFF_REF_H + +#include <linux/skbuff.h> + +/** + * __skb_frag_ref - take an addition reference on a paged fragment. + * @frag: the paged fragment + * + * Takes an additional reference on the paged fragment @frag. + */ +static inline void __skb_frag_ref(skb_frag_t *frag) +{ + get_page(skb_frag_page(frag)); +} + +/** + * skb_frag_ref - take an addition reference on a paged fragment of an skb. + * @skb: the buffer + * @f: the fragment offset. + * + * Takes an additional reference on the @f'th paged fragment of @skb. + */ +static inline void skb_frag_ref(struct sk_buff *skb, int f) +{ + __skb_frag_ref(&skb_shinfo(skb)->frags[f]); +} + +bool napi_pp_put_page(struct page *page); + +static inline void +skb_page_unref(struct page *page, bool recycle) +{ +#ifdef CONFIG_PAGE_POOL + if (recycle && napi_pp_put_page(page)) + return; +#endif + put_page(page); +} + +/** + * __skb_frag_unref - release a reference on a paged fragment. + * @frag: the paged fragment + * @recycle: recycle the page if allocated via page_pool + * + * Releases a reference on the paged fragment @frag + * or recycles the page via the page_pool API. + */ +static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) +{ + skb_page_unref(skb_frag_page(frag), recycle); +} + +/** + * skb_frag_unref - release a reference on a paged fragment of an skb. + * @skb: the buffer + * @f: the fragment offset + * + * Releases a reference on the @f'th paged fragment of @skb. + */ +static inline void skb_frag_unref(struct sk_buff *skb, int f) +{ + struct skb_shared_info *shinfo = skb_shinfo(skb); + + if (!skb_zcopy_managed(skb)) + __skb_frag_unref(&shinfo->frags[f], skb->pp_recycle); +} + +#endif /* _LINUX_SKBUFF_REF_H */ diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index a509caf823d6..3f3246a6a6fb 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -58,6 +58,10 @@ struct sk_psock_progs { struct bpf_prog *stream_parser; struct bpf_prog *stream_verdict; struct bpf_prog *skb_verdict; + struct bpf_link *msg_parser_link; + struct bpf_link *stream_parser_link; + struct bpf_link *stream_verdict_link; + struct bpf_link *skb_verdict_link; }; enum sk_psock_state_bits { diff --git a/include/linux/slab.h b/include/linux/slab.h index 739b21262507..ebc20173cd4e 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -774,14 +774,27 @@ static inline __alloc_size(1) void *kvzalloc(size_t size, gfp_t flags) return kvmalloc(size, flags | __GFP_ZERO); } -static inline __alloc_size(1, 2) void *kvmalloc_array(size_t n, size_t size, gfp_t flags) +static inline __alloc_size(1, 2) void * +kvmalloc_array_node(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; - return kvmalloc(bytes, flags); + return kvmalloc_node(bytes, flags, node); +} + +static inline __alloc_size(1, 2) void * +kvmalloc_array(size_t n, size_t size, gfp_t flags) +{ + return kvmalloc_array_node(n, size, flags, NUMA_NO_NODE); +} + +static inline __alloc_size(1, 2) void * +kvcalloc_node(size_t n, size_t size, gfp_t flags, int node) +{ + return kvmalloc_array_node(n, size, flags | __GFP_ZERO, node); } static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t flags) diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 1f326da289d3..a2257380c3f1 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -621,14 +621,6 @@ extern u32 ssb_dma_translation(struct ssb_device *dev); #define SSB_DMA_TRANSLATION_MASK 0xC0000000 #define SSB_DMA_TRANSLATION_SHIFT 30 -static inline void __cold __ssb_dma_not_implemented(struct ssb_device *dev) -{ -#ifdef CONFIG_SSB_DEBUG - printk(KERN_ERR "SSB: BUG! Calling DMA API for " - "unsupported bustype %d\n", dev->bus->bustype); -#endif /* DEBUG */ -} - #ifdef CONFIG_SSB_PCIHOST /* PCI-host wrapper driver */ extern int ssb_pcihost_register(struct pci_driver *driver); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index dfa1828cd756..f92c195c76ed 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -115,21 +115,6 @@ struct stmmac_axi { bool axi_rb; }; -#define EST_GCL 1024 -struct stmmac_est { - struct mutex lock; - int enable; - u32 btr_reserve[2]; - u32 btr_offset[2]; - u32 btr[2]; - u32 ctr[2]; - u32 ter; - u32 gcl_unaligned[EST_GCL]; - u32 gcl[EST_GCL]; - u32 gcl_size; - u32 max_sdu[MTL_MAX_TX_QUEUES]; -}; - struct stmmac_rxq_cfg { u8 mode_to_use; u32 chan; @@ -246,7 +231,6 @@ struct plat_stmmacenet_data { struct fwnode_handle *port_node; struct device_node *mdio_node; struct stmmac_dma_cfg *dma_cfg; - struct stmmac_est *est; struct stmmac_fpe_cfg *fpe_cfg; struct stmmac_safety_feature_cfg *safety_feat_cfg; int clk_csr; @@ -285,6 +269,8 @@ struct plat_stmmacenet_data { int (*crosststamp)(ktime_t *device, struct system_counterval_t *system, void *ctx); void (*dump_debug_regs)(void *priv); + int (*pcs_init)(struct stmmac_priv *priv); + void (*pcs_exit)(struct stmmac_priv *priv); void *bsp_priv; struct clk *stmmac_clk; struct clk *pclk; diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index ee7d33b89e9e..9413241df962 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -182,7 +182,7 @@ struct ctl_table_header { struct rcu_head rcu; }; struct completion *unregistering; - struct ctl_table *ctl_table_arg; + const struct ctl_table *ctl_table_arg; struct ctl_table_root *root; struct ctl_table_set *set; struct ctl_dir *parent; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 55399ee2a57e..6a5e08b937b3 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -244,6 +244,7 @@ struct tcp_sock { /* 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 */ + u8 recvmsg_inq : 1;/* Indicate # of bytes in queue upon recvmsg */ __cacheline_group_end(tcp_sock_read_rx); /* TX read-write hotpath cache lines */ @@ -266,8 +267,6 @@ struct tcp_sock { u32 mdev_us; /* medium deviation */ u32 rtt_seq; /* sequence number to update rttvar */ 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 */ 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 @@ -284,6 +283,8 @@ struct tcp_sock { * 0x5?10 << 16 + snd_wnd in net byte order */ __be32 pred_flags; + u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ + u64 tcp_mstamp; /* most recent packet received/sent */ 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 */ @@ -370,7 +371,6 @@ struct tcp_sock { tlp_retrans:1, /* TLP is a retransmission */ unused:5; 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 */ fastopen_client_fail:2, /* reason why fastopen failed */ diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 6f9bdfb09d1d..9df3e2973626 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -765,8 +765,11 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx); int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie); void perf_event_detach_bpf_prog(struct perf_event *event); int perf_event_query_prog_array(struct perf_event *event, void __user *info); -int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog); -int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog); + +struct bpf_raw_tp_link; +int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link); +int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link); + struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name); void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp); int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, @@ -794,11 +797,12 @@ perf_event_query_prog_array(struct perf_event *event, void __user *info) { return -EOPNOTSUPP; } -static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *p) +struct bpf_raw_tp_link; +static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { return -EOPNOTSUPP; } -static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *p) +static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { return -EOPNOTSUPP; } @@ -909,31 +913,31 @@ void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp); int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie); void perf_event_free_bpf_prog(struct perf_event *event); -void bpf_trace_run1(struct bpf_prog *prog, u64 arg1); -void bpf_trace_run2(struct bpf_prog *prog, u64 arg1, u64 arg2); -void bpf_trace_run3(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run1(struct bpf_raw_tp_link *link, u64 arg1); +void bpf_trace_run2(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2); +void bpf_trace_run3(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3); -void bpf_trace_run4(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run4(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4); -void bpf_trace_run5(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run5(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5); -void bpf_trace_run6(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run6(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6); -void bpf_trace_run7(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run7(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7); -void bpf_trace_run8(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run8(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8); -void bpf_trace_run9(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run9(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9); -void bpf_trace_run10(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run10(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10); -void bpf_trace_run11(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run11(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10, u64 arg11); -void bpf_trace_run12(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run12(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10, u64 arg11, u64 arg12); void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx, diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 26c4325aa373..96fea920873b 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -126,6 +126,8 @@ struct virtio_admin_cmd { * @vqs: the list of virtqueues for this device. * @features: the features supported by both driver and device. * @priv: private pointer for the driver's use. + * @debugfs_dir: debugfs directory entry. + * @debugfs_filter_features: features to be filtered set by debugfs. */ struct virtio_device { int index; @@ -141,6 +143,10 @@ struct virtio_device { struct list_head vqs; u64 features; void *priv; +#ifdef CONFIG_VIRTIO_DEBUG + struct dentry *debugfs_dir; + u64 debugfs_filter_features; +#endif }; #define dev_to_virtio(_dev) container_of_const(_dev, struct virtio_device, dev) @@ -237,4 +243,33 @@ void virtqueue_dma_sync_single_range_for_cpu(struct virtqueue *_vq, dma_addr_t a void virtqueue_dma_sync_single_range_for_device(struct virtqueue *_vq, dma_addr_t addr, unsigned long offset, size_t size, enum dma_data_direction dir); + +#ifdef CONFIG_VIRTIO_DEBUG +void virtio_debug_device_init(struct virtio_device *dev); +void virtio_debug_device_exit(struct virtio_device *dev); +void virtio_debug_device_filter_features(struct virtio_device *dev); +void virtio_debug_init(void); +void virtio_debug_exit(void); +#else +static inline void virtio_debug_device_init(struct virtio_device *dev) +{ +} + +static inline void virtio_debug_device_exit(struct virtio_device *dev) +{ +} + +static inline void virtio_debug_device_filter_features(struct virtio_device *dev) +{ +} + +static inline void virtio_debug_init(void) +{ +} + +static inline void virtio_debug_exit(void) +{ +} +#endif + #endif /* _LINUX_VIRTIO_H */ diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 3dee0b2721aa..b6eedf7650da 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -17,14 +17,31 @@ static inline struct unix_sock *unix_get_socket(struct file *filp) } #endif -extern spinlock_t unix_gc_lock; extern unsigned int unix_tot_inflight; - -void unix_inflight(struct user_struct *user, struct file *fp); -void unix_notinflight(struct user_struct *user, struct file *fp); +void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver); +void unix_del_edges(struct scm_fp_list *fpl); +void unix_update_edges(struct unix_sock *receiver); +int unix_prepare_fpl(struct scm_fp_list *fpl); +void unix_destroy_fpl(struct scm_fp_list *fpl); void unix_gc(void); void wait_for_unix_gc(struct scm_fp_list *fpl); +struct unix_vertex { + struct list_head edges; + struct list_head entry; + struct list_head scc_entry; + unsigned long out_degree; + unsigned long index; + unsigned long scc_index; +}; + +struct unix_edge { + struct unix_sock *predecessor; + struct unix_sock *successor; + struct list_head vertex_entry; + struct list_head stack_entry; +}; + struct sock *unix_peer_get(struct sock *sk); #define UNIX_HASH_MOD (256 - 1) @@ -50,6 +67,7 @@ struct unix_skb_parms { struct scm_stat { atomic_t nr_fds; + unsigned long nr_unix_fds; }; #define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) @@ -62,12 +80,9 @@ struct unix_sock { struct path path; struct mutex iolock, bindlock; struct sock *peer; - struct list_head link; - unsigned long inflight; + struct sock *listener; + struct unix_vertex *vertex; spinlock_t lock; - unsigned long gc_flags; -#define UNIX_GC_CANDIDATE 0 -#define UNIX_GC_MAYBE_CYCLE 1 struct socket_wq peer_wq; wait_queue_entry_t peer_wake; struct scm_stat scm_stat; diff --git a/include/net/ax25.h b/include/net/ax25.h index 0d939e5aee4e..cb622d84cd0c 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -139,7 +139,9 @@ enum { AX25_VALUES_N2, /* Default N2 value */ AX25_VALUES_PACLEN, /* AX.25 MTU */ AX25_VALUES_PROTOCOL, /* Std AX.25, DAMA Slave, DAMA Master */ +#ifdef CONFIG_AX25_DAMA_SLAVE AX25_VALUES_DS_TIMEOUT, /* DAMA Slave timeout */ +#endif AX25_MAX_VALUES /* THIS MUST REMAIN THE LAST ENTRY OF THIS LIST */ }; @@ -216,7 +218,7 @@ typedef struct { struct ctl_table; typedef struct ax25_dev { - struct ax25_dev *next; + struct list_head list; struct net_device *dev; netdevice_tracker dev_tracker; @@ -330,7 +332,6 @@ int ax25_addr_size(const ax25_digi *); void ax25_digi_invert(const ax25_digi *, ax25_digi *); /* ax25_dev.c */ -extern ax25_dev *ax25_dev_list; extern spinlock_t ax25_dev_lock; #if IS_ENABLED(CONFIG_AX25) diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index eaec5d6caa29..b3228bd6cd6b 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -285,7 +285,7 @@ void bt_err_ratelimited(const char *fmt, ...); bt_err_ratelimited("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) /* Connection and socket states */ -enum { +enum bt_sock_state { BT_CONNECTED = 1, /* Equal to TCP_ESTABLISHED to make net code happy */ BT_OPEN, BT_BOUND, diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 5c12761cbc0e..fe932ca3bc8c 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -33,9 +33,6 @@ #define HCI_MAX_FRAME_SIZE (HCI_MAX_ACL_SIZE + 4) #define HCI_LINK_KEY_SIZE 16 -#define HCI_AMP_LINK_KEY_SIZE (2 * HCI_LINK_KEY_SIZE) - -#define HCI_MAX_AMP_ASSOC_SIZE 672 #define HCI_MAX_CPB_DATA_SIZE 252 @@ -71,26 +68,6 @@ #define HCI_SMD 9 #define HCI_VIRTIO 10 -/* HCI controller types */ -#define HCI_PRIMARY 0x00 -#define HCI_AMP 0x01 - -/* First BR/EDR Controller shall have ID = 0 */ -#define AMP_ID_BREDR 0x00 - -/* AMP controller types */ -#define AMP_TYPE_BREDR 0x00 -#define AMP_TYPE_80211 0x01 - -/* AMP controller status */ -#define AMP_STATUS_POWERED_DOWN 0x00 -#define AMP_STATUS_BLUETOOTH_ONLY 0x01 -#define AMP_STATUS_NO_CAPACITY 0x02 -#define AMP_STATUS_LOW_CAPACITY 0x03 -#define AMP_STATUS_MEDIUM_CAPACITY 0x04 -#define AMP_STATUS_HIGH_CAPACITY 0x05 -#define AMP_STATUS_FULL_CAPACITY 0x06 - /* HCI device quirks */ enum { /* When this quirk is set, the HCI Reset command is send when @@ -456,7 +433,6 @@ enum { #define HCI_AUTO_OFF_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */ #define HCI_ACL_CONN_TIMEOUT msecs_to_jiffies(20000) /* 20 seconds */ #define HCI_LE_CONN_TIMEOUT msecs_to_jiffies(20000) /* 20 seconds */ -#define HCI_LE_AUTOCONN_TIMEOUT msecs_to_jiffies(4000) /* 4 seconds */ /* HCI data types */ #define HCI_COMMAND_PKT 0x01 @@ -528,7 +504,6 @@ enum { #define ESCO_LINK 0x02 /* Low Energy links do not have defined link type. Use invented one */ #define LE_LINK 0x80 -#define AMP_LINK 0x81 #define ISO_LINK 0x82 #define INVALID_LINK 0xff @@ -944,56 +919,6 @@ struct hci_cp_io_capability_neg_reply { __u8 reason; } __packed; -#define HCI_OP_CREATE_PHY_LINK 0x0435 -struct hci_cp_create_phy_link { - __u8 phy_handle; - __u8 key_len; - __u8 key_type; - __u8 key[HCI_AMP_LINK_KEY_SIZE]; -} __packed; - -#define HCI_OP_ACCEPT_PHY_LINK 0x0436 -struct hci_cp_accept_phy_link { - __u8 phy_handle; - __u8 key_len; - __u8 key_type; - __u8 key[HCI_AMP_LINK_KEY_SIZE]; -} __packed; - -#define HCI_OP_DISCONN_PHY_LINK 0x0437 -struct hci_cp_disconn_phy_link { - __u8 phy_handle; - __u8 reason; -} __packed; - -struct ext_flow_spec { - __u8 id; - __u8 stype; - __le16 msdu; - __le32 sdu_itime; - __le32 acc_lat; - __le32 flush_to; -} __packed; - -#define HCI_OP_CREATE_LOGICAL_LINK 0x0438 -#define HCI_OP_ACCEPT_LOGICAL_LINK 0x0439 -struct hci_cp_create_accept_logical_link { - __u8 phy_handle; - struct ext_flow_spec tx_flow_spec; - struct ext_flow_spec rx_flow_spec; -} __packed; - -#define HCI_OP_DISCONN_LOGICAL_LINK 0x043a -struct hci_cp_disconn_logical_link { - __le16 log_handle; -} __packed; - -#define HCI_OP_LOGICAL_LINK_CANCEL 0x043b -struct hci_cp_logical_link_cancel { - __u8 phy_handle; - __u8 flow_spec_id; -} __packed; - #define HCI_OP_ENHANCED_SETUP_SYNC_CONN 0x043d struct hci_coding_format { __u8 id; @@ -1615,46 +1540,6 @@ struct hci_rp_read_enc_key_size { __u8 key_size; } __packed; -#define HCI_OP_READ_LOCAL_AMP_INFO 0x1409 -struct hci_rp_read_local_amp_info { - __u8 status; - __u8 amp_status; - __le32 total_bw; - __le32 max_bw; - __le32 min_latency; - __le32 max_pdu; - __u8 amp_type; - __le16 pal_cap; - __le16 max_assoc_size; - __le32 max_flush_to; - __le32 be_flush_to; -} __packed; - -#define HCI_OP_READ_LOCAL_AMP_ASSOC 0x140a -struct hci_cp_read_local_amp_assoc { - __u8 phy_handle; - __le16 len_so_far; - __le16 max_len; -} __packed; -struct hci_rp_read_local_amp_assoc { - __u8 status; - __u8 phy_handle; - __le16 rem_len; - __u8 frag[]; -} __packed; - -#define HCI_OP_WRITE_REMOTE_AMP_ASSOC 0x140b -struct hci_cp_write_remote_amp_assoc { - __u8 phy_handle; - __le16 len_so_far; - __le16 rem_len; - __u8 frag[]; -} __packed; -struct hci_rp_write_remote_amp_assoc { - __u8 status; - __u8 phy_handle; -} __packed; - #define HCI_OP_GET_MWS_TRANSPORT_CONFIG 0x140c #define HCI_OP_ENABLE_DUT_MODE 0x1803 @@ -1666,6 +1551,15 @@ struct hci_cp_le_set_event_mask { __u8 mask[8]; } __packed; +/* BLUETOOTH CORE SPECIFICATION Version 5.4 | Vol 4, Part E + * 7.8.2 LE Read Buffer Size command + * MAX_LE_MTU is 0xffff. + * 0 is also valid. It means that no dedicated LE Buffer exists. + * It should use the HCI_Read_Buffer_Size command and mtu is shared + * between BR/EDR and LE. + */ +#define HCI_MIN_LE_MTU 0x001b + #define HCI_OP_LE_READ_BUFFER_SIZE 0x2002 struct hci_rp_le_read_buffer_size { __u8 status; @@ -2026,7 +1920,7 @@ struct hci_cp_le_set_ext_adv_data { __u8 operation; __u8 frag_pref; __u8 length; - __u8 data[]; + __u8 data[] __counted_by(length); } __packed; #define HCI_OP_LE_SET_EXT_SCAN_RSP_DATA 0x2038 @@ -2035,7 +1929,7 @@ struct hci_cp_le_set_ext_scan_rsp_data { __u8 operation; __u8 frag_pref; __u8 length; - __u8 data[]; + __u8 data[] __counted_by(length); } __packed; #define HCI_OP_LE_SET_EXT_ADV_ENABLE 0x2039 @@ -2061,7 +1955,7 @@ struct hci_cp_le_set_per_adv_data { __u8 handle; __u8 operation; __u8 length; - __u8 data[]; + __u8 data[] __counted_by(length); } __packed; #define HCI_OP_LE_SET_PER_ADV_ENABLE 0x2040 @@ -2144,7 +2038,7 @@ struct hci_cp_le_set_cig_params { __le16 c_latency; __le16 p_latency; __u8 num_cis; - struct hci_cis_params cis[]; + struct hci_cis_params cis[] __counted_by(num_cis); } __packed; struct hci_rp_le_set_cig_params { @@ -2162,7 +2056,7 @@ struct hci_cis { struct hci_cp_le_create_cis { __u8 num_cis; - struct hci_cis cis[]; + struct hci_cis cis[] __counted_by(num_cis); } __packed; #define HCI_OP_LE_REMOVE_CIG 0x2065 @@ -2216,7 +2110,7 @@ struct hci_cp_le_big_create_sync { __u8 mse; __le16 timeout; __u8 num_bis; - __u8 bis[]; + __u8 bis[] __counted_by(num_bis); } __packed; #define HCI_OP_LE_BIG_TERM_SYNC 0x206c diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index e8f581f3f3ce..9231396fe96f 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -126,7 +126,6 @@ enum suspended_state { struct hci_conn_hash { struct list_head list; unsigned int acl_num; - unsigned int amp_num; unsigned int sco_num; unsigned int iso_num; unsigned int le_num; @@ -247,6 +246,7 @@ struct adv_info { bool periodic; __u8 mesh; __u8 instance; + __u8 handle; __u32 flags; __u16 timeout; __u16 remaining_time; @@ -341,14 +341,6 @@ struct adv_monitor { /* Default authenticated payload timeout 30s */ #define DEFAULT_AUTH_PAYLOAD_TIMEOUT 0x0bb8 -struct amp_assoc { - __u16 len; - __u16 offset; - __u16 rem_len; - __u16 len_so_far; - __u8 data[HCI_MAX_AMP_ASSOC_SIZE]; -}; - #define HCI_MAX_PAGES 3 struct hci_dev { @@ -361,7 +353,6 @@ struct hci_dev { unsigned long flags; __u16 id; __u8 bus; - __u8 dev_type; bdaddr_t bdaddr; bdaddr_t setup_addr; bdaddr_t public_addr; @@ -467,21 +458,6 @@ struct hci_dev { __u16 sniff_min_interval; __u16 sniff_max_interval; - __u8 amp_status; - __u32 amp_total_bw; - __u32 amp_max_bw; - __u32 amp_min_latency; - __u32 amp_max_pdu; - __u8 amp_type; - __u16 amp_pal_cap; - __u16 amp_assoc_size; - __u32 amp_max_flush_to; - __u32 amp_be_flush_to; - - struct amp_assoc loc_assoc; - - __u8 flow_ctl_mode; - unsigned int auto_accept_delay; unsigned long quirks; @@ -501,11 +477,6 @@ struct hci_dev { unsigned int le_pkts; unsigned int iso_pkts; - __u16 block_len; - __u16 block_mtu; - __u16 num_blocks; - __u16 block_cnt; - unsigned long acl_last_tx; unsigned long sco_last_tx; unsigned long le_last_tx; @@ -706,6 +677,7 @@ struct hci_conn { __u16 handle; __u16 sync_handle; __u16 state; + __u16 mtu; __u8 mode; __u8 type; __u8 role; @@ -777,7 +749,6 @@ struct hci_conn { void *l2cap_data; void *sco_data; void *iso_data; - struct amp_mgr *amp_mgr; struct list_head link_list; struct hci_conn *parent; @@ -804,7 +775,6 @@ struct hci_chan { struct sk_buff_head data_q; unsigned int sent; __u8 state; - bool amp; }; struct hci_conn_params { @@ -1013,9 +983,6 @@ static inline void hci_conn_hash_add(struct hci_dev *hdev, struct hci_conn *c) case ACL_LINK: h->acl_num++; break; - case AMP_LINK: - h->amp_num++; - break; case LE_LINK: h->le_num++; if (c->role == HCI_ROLE_SLAVE) @@ -1042,9 +1009,6 @@ static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c) case ACL_LINK: h->acl_num--; break; - case AMP_LINK: - h->amp_num--; - break; case LE_LINK: h->le_num--; if (c->role == HCI_ROLE_SLAVE) @@ -1066,8 +1030,6 @@ static inline unsigned int hci_conn_num(struct hci_dev *hdev, __u8 type) switch (type) { case ACL_LINK: return h->acl_num; - case AMP_LINK: - return h->amp_num; case LE_LINK: return h->le_num; case SCO_LINK: @@ -1084,7 +1046,7 @@ static inline unsigned int hci_conn_count(struct hci_dev *hdev) { struct hci_conn_hash *c = &hdev->conn_hash; - return c->acl_num + c->amp_num + c->sco_num + c->le_num + c->iso_num; + return c->acl_num + c->sco_num + c->le_num + c->iso_num; } static inline bool hci_conn_valid(struct hci_dev *hdev, struct hci_conn *conn) @@ -1373,8 +1335,7 @@ hci_conn_hash_lookup_pa_sync_handle(struct hci_dev *hdev, __u16 sync_handle) rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { - if (c->type != ISO_LINK || - !test_bit(HCI_CONN_PA_SYNC, &c->flags)) + if (c->type != ISO_LINK) continue; if (c->sync_handle == sync_handle) { @@ -1610,10 +1571,6 @@ static inline void hci_conn_drop(struct hci_conn *conn) } break; - case AMP_LINK: - timeo = conn->disc_timeout; - break; - default: timeo = 0; break; @@ -2235,8 +2192,22 @@ void hci_mgmt_chan_unregister(struct hci_mgmt_chan *c); /* These LE scan and inquiry parameters were chosen according to LE General * Discovery Procedure specification. */ -#define DISCOV_LE_SCAN_WIN 0x12 -#define DISCOV_LE_SCAN_INT 0x12 +#define DISCOV_LE_SCAN_WIN 0x0012 /* 11.25 msec */ +#define DISCOV_LE_SCAN_INT 0x0012 /* 11.25 msec */ +#define DISCOV_LE_SCAN_INT_FAST 0x0060 /* 60 msec */ +#define DISCOV_LE_SCAN_WIN_FAST 0x0030 /* 30 msec */ +#define DISCOV_LE_SCAN_INT_CONN 0x0060 /* 60 msec */ +#define DISCOV_LE_SCAN_WIN_CONN 0x0060 /* 60 msec */ +#define DISCOV_LE_SCAN_INT_SLOW1 0x0800 /* 1.28 sec */ +#define DISCOV_LE_SCAN_WIN_SLOW1 0x0012 /* 11.25 msec */ +#define DISCOV_LE_SCAN_INT_SLOW2 0x1000 /* 2.56 sec */ +#define DISCOV_LE_SCAN_WIN_SLOW2 0x0024 /* 22.5 msec */ +#define DISCOV_CODED_SCAN_INT_FAST 0x0120 /* 180 msec */ +#define DISCOV_CODED_SCAN_WIN_FAST 0x0090 /* 90 msec */ +#define DISCOV_CODED_SCAN_INT_SLOW1 0x1800 /* 3.84 sec */ +#define DISCOV_CODED_SCAN_WIN_SLOW1 0x0036 /* 33.75 msec */ +#define DISCOV_CODED_SCAN_INT_SLOW2 0x3000 /* 7.68 sec */ +#define DISCOV_CODED_SCAN_WIN_SLOW2 0x006c /* 67.5 msec */ #define DISCOV_LE_TIMEOUT 10240 /* msec */ #define DISCOV_INTERLEAVED_TIMEOUT 5120 /* msec */ #define DISCOV_INTERLEAVED_INQUIRY_LEN 0x04 diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index a4278aa618ab..5cfdc813491a 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -463,18 +463,24 @@ struct l2cap_le_credits { #define L2CAP_ECRED_MAX_CID 5 struct l2cap_ecred_conn_req { - __le16 psm; - __le16 mtu; - __le16 mps; - __le16 credits; + /* New members must be added within the struct_group() macro below. */ + __struct_group(l2cap_ecred_conn_req_hdr, hdr, __packed, + __le16 psm; + __le16 mtu; + __le16 mps; + __le16 credits; + ); __le16 scid[]; } __packed; struct l2cap_ecred_conn_rsp { - __le16 mtu; - __le16 mps; - __le16 credits; - __le16 result; + /* New members must be added within the struct_group() macro below. */ + struct_group_tagged(l2cap_ecred_conn_rsp_hdr, hdr, + __le16 mtu; + __le16 mps; + __le16 credits; + __le16 result; + ); __le16 dcid[]; }; @@ -548,6 +554,9 @@ struct l2cap_chan { __u16 tx_credits; __u16 rx_credits; + /* estimated available receive buffer space or -1 if unknown */ + ssize_t rx_avail; + __u8 tx_state; __u8 rx_state; @@ -682,10 +691,15 @@ struct l2cap_user { /* ----- L2CAP socket info ----- */ #define l2cap_pi(sk) ((struct l2cap_pinfo *) sk) +struct l2cap_rx_busy { + struct list_head list; + struct sk_buff *skb; +}; + struct l2cap_pinfo { struct bt_sock bt; struct l2cap_chan *chan; - struct sk_buff *rx_busy_skb; + struct list_head rx_busy; }; enum { @@ -943,6 +957,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, int l2cap_chan_reconfigure(struct l2cap_chan *chan, __u16 mtu); int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len); void l2cap_chan_busy(struct l2cap_chan *chan, int busy); +void l2cap_chan_rx_avail(struct l2cap_chan *chan, ssize_t rx_avail); int l2cap_chan_check_security(struct l2cap_chan *chan, bool initiator); void l2cap_chan_set_defaults(struct l2cap_chan *chan); int l2cap_ertm_init(struct l2cap_chan *chan); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 1e09329acc42..cbf1664dc569 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1149,6 +1149,8 @@ ieee80211_chandef_max_power(struct cfg80211_chan_def *chandef) * @band_mask: which bands to check on * @prohibited_flags: which channels to not consider usable, * %IEEE80211_CHAN_DISABLED is always taken into account + * + * Return: %true if usable channels found, %false otherwise */ bool cfg80211_any_usable_channels(struct wiphy *wiphy, unsigned long band_mask, @@ -1575,6 +1577,8 @@ struct cfg80211_csa_settings { * @beacon_next: beacon data to be used after the color change * @count: number of beacons until the color change * @color: the color used after the change + * @link_id: defines the link on which color change is expected during MLO. + * 0 in case of non-MLO. */ struct cfg80211_color_change_settings { struct cfg80211_beacon_data beacon_color_change; @@ -1583,6 +1587,7 @@ struct cfg80211_color_change_settings { struct cfg80211_beacon_data beacon_next; u8 count; u8 color; + u8 link_id; }; /** @@ -1833,9 +1838,11 @@ enum cfg80211_station_type { * * Utility function for the @change_station driver method. Call this function * with the appropriate station type looking up the station (and checking that - * it exists). It will verify whether the station change is acceptable, and if - * not will return an error code. Note that it may modify the parameters for - * backward compatibility reasons, so don't use them before calling this. + * it exists). It will verify whether the station change is acceptable. + * + * Return: 0 if the change is acceptable, otherwise an error code. Note that + * it may modify the parameters for backward compatibility reasons, so don't + * use them before calling this. */ int cfg80211_check_station_change(struct wiphy *wiphy, struct station_parameters *params, @@ -2229,7 +2236,7 @@ struct cfg80211_sar_capa { * @mac_addr: the mac address of the station of interest * @sinfo: pointer to the structure to fill with the information * - * Returns 0 on success and sinfo is filled with the available information + * Return: 0 on success and sinfo is filled with the available information * otherwise returns a negative error code and the content of sinfo has to be * considered undefined. */ @@ -5334,6 +5341,8 @@ struct wiphy_iftype_ext_capab { * cfg80211_get_iftype_ext_capa - lookup interface type extended capability * @wiphy: the wiphy to look up from * @type: the interface type to look up + * + * Return: The extended capability for the given interface @type, may be %NULL */ const struct wiphy_iftype_ext_capab * cfg80211_get_iftype_ext_capa(struct wiphy *wiphy, enum nl80211_iftype type); @@ -5904,6 +5913,10 @@ int wiphy_register(struct wiphy *wiphy); /** * get_wiphy_regdom - get custom regdomain for the given wiphy * @wiphy: the wiphy to get the regdomain from + * + * Context: Requires any of RTNL, wiphy mutex or RCU protection. + * + * Return: pointer to the regulatory domain associated with the wiphy */ const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy); @@ -6421,6 +6434,8 @@ ieee80211_get_channel(struct wiphy *wiphy, int freq) * * The Preferred Scanning Channels (PSC) are defined in * Draft IEEE P802.11ax/D5.0, 26.17.2.3.3 + * + * Return: %true if channel is a PSC, %false otherwise */ static inline bool cfg80211_channel_is_psc(struct ieee80211_channel *chan) { @@ -6450,8 +6465,8 @@ ieee80211_get_response_rate(struct ieee80211_supported_band *sband, * ieee80211_mandatory_rates - get mandatory rates for a given band * @sband: the band to look for rates in * - * This function returns a bitmap of the mandatory rates for the given - * band, bits are set according to the rate position in the bitrates array. + * Return: a bitmap of the mandatory rates for the given band, bits + * are set according to the rate position in the bitrates array. */ u32 ieee80211_mandatory_rates(struct ieee80211_supported_band *sband); @@ -6665,6 +6680,8 @@ bool ieee80211_get_8023_tunnel_proto(const void *hdr, __be16 *proto); * header to the ethernet header (if present). * * @skb: The 802.3 frame with embedded mesh header + * + * Return: 0 on success. Non-zero on error. */ int ieee80211_strip_8023_mesh_hdr(struct sk_buff *skb); @@ -7043,6 +7060,8 @@ const struct ieee80211_reg_rule *freq_reg_info(struct wiphy *wiphy, * * You can use this to map the regulatory request initiator enum to a * proper string representation. + * + * Return: pointer to string representation of the initiator */ const char *reg_initiator_name(enum nl80211_reg_initiator initiator); @@ -7051,6 +7070,8 @@ const char *reg_initiator_name(enum nl80211_reg_initiator initiator); * @wiphy: wiphy for which pre-CAC capability is checked. * * Pre-CAC is allowed only in some regdomains (notable ETSI). + * + * Return: %true if allowed, %false otherwise */ bool regulatory_pre_cac_allowed(struct wiphy *wiphy); @@ -7185,6 +7206,8 @@ static inline void cfg80211_gen_new_bssid(const u8 *bssid, u8 max_bssid, * cfg80211_is_element_inherited - returns if element ID should be inherited * @element: element to check * @non_inherit_element: non inheritance element + * + * Return: %true if should be inherited, %false otherwise */ bool cfg80211_is_element_inherited(const struct element *element, const struct element *non_inherit_element); @@ -7197,6 +7220,8 @@ bool cfg80211_is_element_inherited(const struct element *element, * @sub_elem: current MBSSID subelement (profile) * @merged_ie: location of the merged profile * @max_copy_len: max merged profile length + * + * Return: the number of bytes merged */ size_t cfg80211_merge_profile(const u8 *ie, size_t ielen, const struct element *mbssid_elem, @@ -7224,7 +7249,7 @@ enum cfg80211_bss_frame_type { * @ielen: length of IEs * @band: enum nl80211_band of the channel * - * Returns the channel number, or -1 if none could be determined. + * Return: the channel number, or -1 if none could be determined. */ int cfg80211_get_ies_channel_number(const u8 *ie, size_t ielen, enum nl80211_band band); @@ -7302,6 +7327,8 @@ cfg80211_inform_bss(struct wiphy *wiphy, * @bss_type: type of BSS, see &enum ieee80211_bss_type * @privacy: privacy filter, see &enum ieee80211_privacy * @use_for: indicates which use is intended + * + * Return: Reference-counted BSS on success. %NULL on error. */ struct cfg80211_bss *__cfg80211_get_bss(struct wiphy *wiphy, struct ieee80211_channel *channel, @@ -7322,6 +7349,8 @@ struct cfg80211_bss *__cfg80211_get_bss(struct wiphy *wiphy, * @privacy: privacy filter, see &enum ieee80211_privacy * * This version implies regular usage, %NL80211_BSS_USE_FOR_NORMAL. + * + * Return: Reference-counted BSS on success. %NULL on error. */ static inline struct cfg80211_bss * cfg80211_get_bss(struct wiphy *wiphy, struct ieee80211_channel *channel, @@ -7706,8 +7735,9 @@ int cfg80211_vendor_cmd_reply(struct sk_buff *skb); * cfg80211_vendor_cmd_get_sender - get the current sender netlink ID * @wiphy: the wiphy * - * Return the current netlink port ID in a vendor command handler. - * Valid to call only there. + * Return: the current netlink port ID in a vendor command handler. + * + * Context: May only be called from a vendor command handler */ unsigned int cfg80211_vendor_cmd_get_sender(struct wiphy *wiphy); @@ -8260,6 +8290,8 @@ void cfg80211_tx_mgmt_expired(struct wireless_dev *wdev, u64 cookie, * * @sinfo: the station information * @gfp: allocation flags + * + * Return: 0 on success. Non-zero on error. */ int cfg80211_sinfo_alloc_tid_stats(struct station_info *sinfo, gfp_t gfp); @@ -8777,13 +8809,13 @@ bool cfg80211_reg_can_beacon(struct wiphy *wiphy, * also checks if IR-relaxation conditions apply, to allow beaconing under * more permissive conditions. * - * Requires the wiphy mutex to be held. + * Context: Requires the wiphy mutex to be held. */ bool cfg80211_reg_can_beacon_relax(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, enum nl80211_iftype iftype); -/* +/** * cfg80211_ch_switch_notify - update wdev channel and notify userspace * @dev: the device which switched channels * @chandef: the new channel definition @@ -8796,7 +8828,7 @@ void cfg80211_ch_switch_notify(struct net_device *dev, struct cfg80211_chan_def *chandef, unsigned int link_id); -/* +/** * cfg80211_ch_switch_started_notify - notify channel switch start * @dev: the device on which the channel switch started * @chandef: the future channel definition @@ -8819,7 +8851,7 @@ void cfg80211_ch_switch_started_notify(struct net_device *dev, * @operating_class: the operating class to convert * @band: band pointer to fill * - * Returns %true if the conversion was successful, %false otherwise. + * Return: %true if the conversion was successful, %false otherwise. */ bool ieee80211_operating_class_to_band(u8 operating_class, enum nl80211_band *band); @@ -8831,7 +8863,7 @@ bool ieee80211_operating_class_to_band(u8 operating_class, * @chan: the ieee80211_channel to convert * @chandef: a pointer to the resulting chandef * - * Returns %true if the conversion was successful, %false otherwise. + * Return: %true if the conversion was successful, %false otherwise. */ bool ieee80211_operating_class_to_chandef(u8 operating_class, struct ieee80211_channel *chan, @@ -8843,7 +8875,7 @@ bool ieee80211_operating_class_to_chandef(u8 operating_class, * @chandef: the chandef to convert * @op_class: a pointer to the resulting operating class * - * Returns %true if the conversion was successful, %false otherwise. + * Return: %true if the conversion was successful, %false otherwise. */ bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, u8 *op_class); @@ -8853,7 +8885,7 @@ bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, * * @chandef: the chandef to convert * - * Returns the center frequency of chandef (1st segment) in KHz. + * Return: the center frequency of chandef (1st segment) in KHz. */ static inline u32 ieee80211_chandef_to_khz(const struct cfg80211_chan_def *chandef) @@ -8861,7 +8893,7 @@ ieee80211_chandef_to_khz(const struct cfg80211_chan_def *chandef) return MHZ_TO_KHZ(chandef->center_freq1) + chandef->freq1_offset; } -/* +/** * cfg80211_tdls_oper_request - request userspace to perform TDLS operation * @dev: the device on which the operation is requested * @peer: the MAC address of the peer device @@ -8880,11 +8912,11 @@ void cfg80211_tdls_oper_request(struct net_device *dev, const u8 *peer, enum nl80211_tdls_operation oper, u16 reason_code, gfp_t gfp); -/* +/** * cfg80211_calculate_bitrate - calculate actual bitrate (in 100Kbps units) * @rate: given rate_info to calculate bitrate from * - * return 0 if MCS index >= 32 + * Return: calculated bitrate */ u32 cfg80211_calculate_bitrate(struct rate_info *rate); @@ -8898,7 +8930,7 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate); * when the driver wishes to unregister the wdev, e.g. when the hardware device * is unbound from the driver. * - * Requires the RTNL and wiphy mutex to be held. + * Context: Requires the RTNL and wiphy mutex to be held. */ void cfg80211_unregister_wdev(struct wireless_dev *wdev); @@ -8911,7 +8943,9 @@ void cfg80211_unregister_wdev(struct wireless_dev *wdev); * held. Otherwise, both register_netdevice() and register_netdev() are usable * instead as well. * - * Requires the RTNL and wiphy mutex to be held. + * Context: Requires the RTNL and wiphy mutex to be held. + * + * Return: 0 on success. Non-zero on error. */ int cfg80211_register_netdevice(struct net_device *dev); @@ -8924,7 +8958,7 @@ int cfg80211_register_netdevice(struct net_device *dev); * is held. Otherwise, both unregister_netdevice() and unregister_netdev() are * usable instead as well. * - * Requires the RTNL and wiphy mutex to be held. + * Context: Requires the RTNL and wiphy mutex to be held. */ static inline void cfg80211_unregister_netdevice(struct net_device *dev) { @@ -9000,9 +9034,9 @@ int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len, * correctly, if not the result of using this function will not * be ordered correctly either, i.e. it does no reordering. * - * The function returns the offset where the next part of the - * buffer starts, which may be @ielen if the entire (remainder) - * of the buffer should be used. + * Return: The offset where the next part of the buffer starts, which + * may be @ielen if the entire (remainder) of the buffer should be + * used. */ size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen, const u8 *ids, int n_ids, @@ -9030,9 +9064,9 @@ size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen, * correctly, if not the result of using this function will not * be ordered correctly either, i.e. it does no reordering. * - * The function returns the offset where the next part of the - * buffer starts, which may be @ielen if the entire (remainder) - * of the buffer should be used. + * Return: The offset where the next part of the buffer starts, which + * may be @ielen if the entire (remainder) of the buffer should be + * used. */ static inline size_t ieee80211_ie_split(const u8 *ies, size_t ielen, const u8 *ids, int n_ids, size_t offset) @@ -9096,6 +9130,8 @@ unsigned int ieee80211_get_num_supported_channels(struct wiphy *wiphy); * This function can be called by the driver to check whether a * combination of interfaces and their types are allowed according to * the interface combinations. + * + * Return: 0 if combinations are allowed. Non-zero on error. */ int cfg80211_check_combinations(struct wiphy *wiphy, struct iface_combination_params *params); @@ -9111,6 +9147,8 @@ int cfg80211_check_combinations(struct wiphy *wiphy, * This function can be called by the driver to check what possible * combinations it fits in at a given moment, e.g. for channel switching * purposes. + * + * Return: 0 on success. Non-zero on error. */ int cfg80211_iter_combinations(struct wiphy *wiphy, struct iface_combination_params *params, @@ -9118,7 +9156,7 @@ int cfg80211_iter_combinations(struct wiphy *wiphy, void *data), void *data); -/* +/** * cfg80211_stop_iface - trigger interface disconnection * * @wiphy: the wiphy @@ -9173,6 +9211,8 @@ static inline void wiphy_ext_feature_set(struct wiphy *wiphy, * * The extended features are flagged in multiple bytes (see * &struct wiphy.@ext_features) + * + * Return: %true if extended feature flag is set, %false otherwise */ static inline bool wiphy_ext_feature_isset(struct wiphy *wiphy, @@ -9294,6 +9334,8 @@ void cfg80211_pmsr_complete(struct wireless_dev *wdev, * Check whether the interface is allowed to operate; additionally, this API * can be used to check iftype against the software interfaces when * check_swif is '1'. + * + * Return: %true if allowed, %false otherwise */ bool cfg80211_iftype_allowed(struct wiphy *wiphy, enum nl80211_iftype iftype, bool is_4addr, u8 check_swif); @@ -9386,60 +9428,78 @@ void cfg80211_bss_flush(struct wiphy *wiphy); * @cmd: the actual event we want to notify * @count: the number of TBTTs until the color change happens * @color_bitmap: representations of the colors that the local BSS is aware of + * @link_id: valid link_id in case of MLO or 0 for non-MLO. + * + * Return: 0 on success. Non-zero on error. */ int cfg80211_bss_color_notify(struct net_device *dev, enum nl80211_commands cmd, u8 count, - u64 color_bitmap); + u64 color_bitmap, u8 link_id); /** * cfg80211_obss_color_collision_notify - notify about bss color collision * @dev: network device * @color_bitmap: representations of the colors that the local BSS is aware of + * @link_id: valid link_id in case of MLO or 0 for non-MLO. + * + * Return: 0 on success. Non-zero on error. */ static inline int cfg80211_obss_color_collision_notify(struct net_device *dev, - u64 color_bitmap) + u64 color_bitmap, + u8 link_id) { return cfg80211_bss_color_notify(dev, NL80211_CMD_OBSS_COLOR_COLLISION, - 0, color_bitmap); + 0, color_bitmap, link_id); } /** * cfg80211_color_change_started_notify - notify color change start * @dev: the device on which the color is switched * @count: the number of TBTTs until the color change happens + * @link_id: valid link_id in case of MLO or 0 for non-MLO. * * Inform the userspace about the color change that has started. + * + * Return: 0 on success. Non-zero on error. */ static inline int cfg80211_color_change_started_notify(struct net_device *dev, - u8 count) + u8 count, u8 link_id) { return cfg80211_bss_color_notify(dev, NL80211_CMD_COLOR_CHANGE_STARTED, - count, 0); + count, 0, link_id); } /** * cfg80211_color_change_aborted_notify - notify color change abort * @dev: the device on which the color is switched + * @link_id: valid link_id in case of MLO or 0 for non-MLO. * * Inform the userspace about the color change that has aborted. + * + * Return: 0 on success. Non-zero on error. */ -static inline int cfg80211_color_change_aborted_notify(struct net_device *dev) +static inline int cfg80211_color_change_aborted_notify(struct net_device *dev, + u8 link_id) { return cfg80211_bss_color_notify(dev, NL80211_CMD_COLOR_CHANGE_ABORTED, - 0, 0); + 0, 0, link_id); } /** * cfg80211_color_change_notify - notify color change completion * @dev: the device on which the color was switched + * @link_id: valid link_id in case of MLO or 0 for non-MLO. * * Inform the userspace about the color change that has completed. + * + * Return: 0 on success. Non-zero on error. */ -static inline int cfg80211_color_change_notify(struct net_device *dev) +static inline int cfg80211_color_change_notify(struct net_device *dev, + u8 link_id) { return cfg80211_bss_color_notify(dev, NL80211_CMD_COLOR_CHANGE_COMPLETED, - 0, 0); + 0, 0, link_id); } /** @@ -9477,6 +9537,8 @@ void cfg80211_schedule_channels_check(struct wireless_dev *wdev); * @ppos: read position * @handler: the read handler to call (under wiphy lock) * @data: additional data to pass to the read handler + * + * Return: the number of characters read, or a negative errno */ ssize_t wiphy_locked_debugfs_read(struct wiphy *wiphy, struct file *file, char *buf, size_t bufsize, @@ -9499,6 +9561,8 @@ ssize_t wiphy_locked_debugfs_read(struct wiphy *wiphy, struct file *file, * @count: read count * @handler: the write handler to call (under wiphy lock) * @data: additional data to pass to the write handler + * + * Return: the number of characters written, or a negative errno */ ssize_t wiphy_locked_debugfs_write(struct wiphy *wiphy, struct file *file, char *buf, size_t bufsize, diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h index 53dd7d988a2d..c9111bb2f59b 100644 --- a/include/net/cipso_ipv4.h +++ b/include/net/cipso_ipv4.h @@ -183,7 +183,8 @@ int cipso_v4_getattr(const unsigned char *cipso, struct netlbl_lsm_secattr *secattr); int cipso_v4_sock_setattr(struct sock *sk, const struct cipso_v4_doi *doi_def, - const struct netlbl_lsm_secattr *secattr); + const struct netlbl_lsm_secattr *secattr, + bool sk_locked); void cipso_v4_sock_delattr(struct sock *sk); int cipso_v4_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr); int cipso_v4_req_setattr(struct request_sock *req, @@ -214,7 +215,8 @@ static inline int cipso_v4_getattr(const unsigned char *cipso, static inline int cipso_v4_sock_setattr(struct sock *sk, const struct cipso_v4_doi *doi_def, - const struct netlbl_lsm_secattr *secattr) + const struct netlbl_lsm_secattr *secattr, + bool sk_locked) { return -ENOSYS; } diff --git a/include/net/devlink.h b/include/net/devlink.h index 9ac394bdfbe4..35eb0f884386 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -483,7 +483,8 @@ struct devlink_param { int (*get)(struct devlink *devlink, u32 id, struct devlink_param_gset_ctx *ctx); int (*set)(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx); + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack); int (*validate)(struct devlink *devlink, u32 id, union devlink_param_value val, struct netlink_ext_ack *extack); @@ -599,12 +600,14 @@ enum devlink_param_generic_id { .validate = _validate, \ } -/* Part number, identifier of board design */ +/* Identifier of board design */ #define DEVLINK_INFO_VERSION_GENERIC_BOARD_ID "board.id" /* Revision of board design */ #define DEVLINK_INFO_VERSION_GENERIC_BOARD_REV "board.rev" /* Maker of the board */ #define DEVLINK_INFO_VERSION_GENERIC_BOARD_MANUFACTURE "board.manufacture" +/* Part number of the board and its components */ +#define DEVLINK_INFO_VERSION_GENERIC_BOARD_PART_NUMBER "board.part_number" /* Part number, identifier of asic design */ #define DEVLINK_INFO_VERSION_GENERIC_ASIC_ID "asic.id" @@ -1602,6 +1605,14 @@ void devlink_free(struct devlink *devlink); * capability. Should be used by device drivers to * enable/disable ipsec_packet capability of a * function managed by the devlink port. + * @port_fn_max_io_eqs_get: Callback used to get port function's maximum number + * of event queues. Should be used by device drivers to + * report the maximum event queues of a function + * managed by the devlink port. + * @port_fn_max_io_eqs_set: Callback used to set port function's maximum number + * of event queues. Should be used by device drivers to + * configure maximum number of event queues + * of a function managed by the devlink port. * * Note: Driver should return -EOPNOTSUPP if it doesn't support * port function (@port_fn_*) handling for a particular port. @@ -1651,6 +1662,12 @@ struct devlink_port_ops { int (*port_fn_ipsec_packet_set)(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack); + int (*port_fn_max_io_eqs_get)(struct devlink_port *devlink_port, + u32 *max_eqs, + struct netlink_ext_ack *extack); + int (*port_fn_max_io_eqs_set)(struct devlink_port *devlink_port, + u32 max_eqs, + struct netlink_ext_ack *extack); }; void devlink_port_init(struct devlink *devlink, diff --git a/include/net/dsa.h b/include/net/dsa.h index 7c0da9effe4e..b60e7e410aba 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -24,9 +24,6 @@ struct dsa_8021q_context; struct tc_action; -struct phy_device; -struct fixed_phy_status; -struct phylink_link_state; #define DSA_TAG_PROTO_NONE_VALUE 0 #define DSA_TAG_PROTO_BRCM_VALUE 1 @@ -327,6 +324,12 @@ struct dsa_port { }; }; +static inline struct dsa_port * +dsa_phylink_to_port(struct phylink_config *config) +{ + return container_of(config, struct dsa_port, pl_config); +} + /* TODO: ideally DSA ports would have a single dp->link_dp member, * and no dst->rtable nor this struct dsa_link would be needed, * but this would require some more complex tree walking, @@ -430,6 +433,11 @@ struct dsa_switch { */ u32 fdb_isolation:1; + /* Drivers that have global DSCP mapping settings must set this to + * true to automatically apply the settings to all ports. + */ + u32 dscp_prio_mapping_is_global:1; + /* Listener for switch fabric events */ struct notifier_block nb; @@ -452,6 +460,11 @@ struct dsa_switch { const struct dsa_switch_ops *ops; /* + * Allow a DSA switch driver to override the phylink MAC ops + */ + const struct phylink_mac_ops *phylink_mac_ops; + + /* * User mii_bus and devices for the individual ports. */ u32 phys_mii_mask; @@ -578,6 +591,10 @@ static inline bool dsa_is_user_port(struct dsa_switch *ds, int p) dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_user((_dp))) +#define dsa_switch_for_each_user_port_continue_reverse(_dp, _ds) \ + dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ + if (dsa_port_is_user((_dp))) + #define dsa_switch_for_each_cpu_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) @@ -858,14 +875,6 @@ struct dsa_switch_ops { int regnum, u16 val); /* - * Link state adjustment (called from libphy) - */ - void (*adjust_link)(struct dsa_switch *ds, int port, - struct phy_device *phydev); - void (*fixed_link_update)(struct dsa_switch *ds, int port, - struct fixed_phy_status *st); - - /* * PHYLINK integration */ void (*phylink_get_caps)(struct dsa_switch *ds, int port, @@ -955,6 +964,10 @@ struct dsa_switch_ops { u8 prio); int (*port_del_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); + int (*port_set_apptrust)(struct dsa_switch *ds, int port, + const u8 *sel, int nsel); + int (*port_get_apptrust)(struct dsa_switch *ds, int port, u8 *sel, + int *nsel); /* * Suspend and resume @@ -1247,7 +1260,8 @@ struct dsa_switch_ops { int dsa_devlink_param_get(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx); int dsa_devlink_param_set(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx); + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack); int dsa_devlink_params_register(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); diff --git a/include/net/dscp.h b/include/net/dscp.h new file mode 100644 index 000000000000..ba40540868c9 --- /dev/null +++ b/include/net/dscp.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Pengutronix, Oleksij Rempel <kernel@pengutronix.de> */ + +#ifndef __DSCP_H__ +#define __DSCP_H__ + +/* + * DSCP Pools and Codepoint Space Division: + * + * The Differentiated Services (Diffserv) architecture defines a method for + * classifying and managing network traffic using the DS field in IPv4 and IPv6 + * packet headers. This field can carry one of 64 distinct DSCP (Differentiated + * Services Code Point) values, which are divided into three pools based on + * their Least Significant Bits (LSB) patterns and intended usage. Each pool has + * a specific registration procedure for assigning DSCP values: + * + * Pool 1 (Standards Action Pool): + * - Codepoint Space: xxxxx0 + * This pool includes DSCP values ending in '0' (binary), allocated via + * Standards Action. It is intended for globally recognized traffic classes, + * ensuring interoperability across the internet. This pool encompasses + * well-known DSCP values such as CS0-CS7, AFxx, EF, and VOICE-ADMIT. + * + * Pool 2 (Experimental/Local Use Pool): + * - Codepoint Space: xxxx11 + * Reserved for DSCP values ending in '11' (binary), this pool is designated + * for Experimental or Local Use. It allows for private or temporary traffic + * marking schemes not intended for standardized global use, facilitating + * testing and network-specific configurations without impacting + * interoperability. + * + * Pool 3 (Preferential Standardization Pool): + * - Codepoint Space: xxxx01 + * Initially reserved for experimental or local use, this pool now serves as + * a secondary standardization resource should Pool 1 become exhausted. DSCP + * values ending in '01' (binary) are assigned via Standards Action, with a + * focus on adopting new, standardized traffic classes as the need arises. + * + * For pool updates see: + * https://www.iana.org/assignments/dscp-registry/dscp-registry.xhtml + */ + +/* Pool 1: Standardized DSCP values as per [RFC8126] */ +#define DSCP_CS0 0 /* 000000, [RFC2474] */ +/* CS0 is some times called default (DF) */ +#define DSCP_DF 0 /* 000000, [RFC2474] */ +#define DSCP_CS1 8 /* 001000, [RFC2474] */ +#define DSCP_CS2 16 /* 010000, [RFC2474] */ +#define DSCP_CS3 24 /* 011000, [RFC2474] */ +#define DSCP_CS4 32 /* 100000, [RFC2474] */ +#define DSCP_CS5 40 /* 101000, [RFC2474] */ +#define DSCP_CS6 48 /* 110000, [RFC2474] */ +#define DSCP_CS7 56 /* 111000, [RFC2474] */ +#define DSCP_AF11 10 /* 001010, [RFC2597] */ +#define DSCP_AF12 12 /* 001100, [RFC2597] */ +#define DSCP_AF13 14 /* 001110, [RFC2597] */ +#define DSCP_AF21 18 /* 010010, [RFC2597] */ +#define DSCP_AF22 20 /* 010100, [RFC2597] */ +#define DSCP_AF23 22 /* 010110, [RFC2597] */ +#define DSCP_AF31 26 /* 011010, [RFC2597] */ +#define DSCP_AF32 28 /* 011100, [RFC2597] */ +#define DSCP_AF33 30 /* 011110, [RFC2597] */ +#define DSCP_AF41 34 /* 100010, [RFC2597] */ +#define DSCP_AF42 36 /* 100100, [RFC2597] */ +#define DSCP_AF43 38 /* 100110, [RFC2597] */ +#define DSCP_EF 46 /* 101110, [RFC3246] */ +#define DSCP_VOICE_ADMIT 44 /* 101100, [RFC5865] */ + +/* Pool 3: Standardized assignments, previously available for experimental/local + * use + */ +#define DSCP_LE 1 /* 000001, [RFC8622] */ + +#define DSCP_MAX 64 + +#endif /* __DSCP_H__ */ diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h index df6622a5fe98..b4a55d2d5e71 100644 --- a/include/net/dst_cache.h +++ b/include/net/dst_cache.h @@ -76,7 +76,7 @@ struct dst_entry *dst_cache_get_ip6(struct dst_cache *dst_cache, */ static inline void dst_cache_reset(struct dst_cache *dst_cache) { - dst_cache->reset_ts = jiffies; + WRITE_ONCE(dst_cache->reset_ts, jiffies); } /** diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 1b7fae4c6b24..4160731dcb6e 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -198,7 +198,7 @@ static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr, __be32 daddr, __u8 tos, __u8 ttl, __be16 tp_dst, - __be16 flags, + const unsigned long *flags, __be64 tunnel_id, int md_size) { @@ -215,7 +215,7 @@ static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr, } static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, - __be16 flags, + const unsigned long *flags, __be64 tunnel_id, int md_size) { @@ -230,7 +230,7 @@ static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *sad __u8 tos, __u8 ttl, __be16 tp_dst, __be32 label, - __be16 flags, + const unsigned long *flags, __be64 tunnel_id, int md_size) { @@ -243,7 +243,7 @@ static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *sad info = &tun_dst->u.tun_info; info->mode = IP_TUNNEL_INFO_IPV6; - info->key.tun_flags = flags; + ip_tunnel_flags_copy(info->key.tun_flags, flags); info->key.tun_id = tunnel_id; info->key.tp_src = 0; info->key.tp_dst = tp_dst; @@ -259,7 +259,7 @@ static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *sad } static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb, - __be16 flags, + const unsigned long *flags, __be64 tunnel_id, int md_size) { diff --git a/include/net/espintcp.h b/include/net/espintcp.h index 0335bbd76552..c70efd704b6d 100644 --- a/include/net/espintcp.h +++ b/include/net/espintcp.h @@ -32,7 +32,7 @@ struct espintcp_ctx { static inline struct espintcp_ctx *espintcp_getctx(const struct sock *sk) { - struct inet_connection_sock *icsk = inet_csk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); /* RCU is only needed for diag */ return (__force void *)icsk->icsk_ulp_data; diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 1a7131d6cb0e..9ab376d1a677 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -97,7 +97,7 @@ struct flow_dissector_key_enc_opts { * here but seems difficult to #include */ u8 len; - __be16 dst_opt_type; + u32 dst_opt_type; }; struct flow_dissector_key_keyid { diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 314087a5e181..ec9f80509f60 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -345,7 +345,7 @@ static inline bool flow_action_has_entries(const struct flow_action *action) * flow_offload_has_one_action() - check if exactly one action is present * @action: tc filter flow offload action * - * Returns true if exactly one action is present. + * Return: true if exactly one action is present. */ static inline bool flow_offload_has_one_action(const struct flow_action *action) { @@ -449,6 +449,61 @@ static inline bool flow_rule_match_key(const struct flow_rule *rule, return dissector_uses_key(rule->match.dissector, key); } +/** + * flow_rule_is_supp_control_flags() - check for supported control flags + * @supp_flags: control flags supported by driver + * @ctrl_flags: control flags present in rule + * @extack: The netlink extended ACK for reporting errors. + * + * Return: true if only supported control flags are set, false otherwise. + */ +static inline bool flow_rule_is_supp_control_flags(const u32 supp_flags, + const u32 ctrl_flags, + struct netlink_ext_ack *extack) +{ + if (likely((ctrl_flags & ~supp_flags) == 0)) + return true; + + NL_SET_ERR_MSG_FMT_MOD(extack, + "Unsupported match on control.flags %#x", + ctrl_flags); + + return false; +} + +/** + * flow_rule_has_control_flags() - check for presence of any control flags + * @ctrl_flags: control flags present in rule + * @extack: The netlink extended ACK for reporting errors. + * + * Return: true if control flags are set, false otherwise. + */ +static inline bool flow_rule_has_control_flags(const u32 ctrl_flags, + struct netlink_ext_ack *extack) +{ + return !flow_rule_is_supp_control_flags(0, ctrl_flags, extack); +} + +/** + * flow_rule_match_has_control_flags() - match and check for any control flags + * @rule: The flow_rule under evaluation. + * @extack: The netlink extended ACK for reporting errors. + * + * Return: true if control flags are set, false otherwise. + */ +static inline bool flow_rule_match_has_control_flags(struct flow_rule *rule, + struct netlink_ext_ack *extack) +{ + struct flow_match_control match; + + if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) + return false; + + flow_rule_match_control(rule, &match); + + return flow_rule_has_control_flags(match.mask->flags, extack); +} + struct flow_stats { u64 pkts; u64 bytes; diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 9ece6e5a3ea8..9ab49bfeae78 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -2,12 +2,20 @@ #ifndef __NET_GENERIC_NETLINK_H #define __NET_GENERIC_NETLINK_H -#include <linux/genetlink.h> +#include <linux/net.h> #include <net/netlink.h> #include <net/net_namespace.h> +#include <uapi/linux/genetlink.h> #define GENLMSG_DEFAULT_SIZE (NLMSG_DEFAULT_SIZE - GENL_HDRLEN) +/* Non-parallel generic netlink requests are serialized by a global lock. */ +void genl_lock(void); +void genl_unlock(void); + +#define MODULE_ALIAS_GENL_FAMILY(family) \ + MODULE_ALIAS_NET_PF_PROTO_NAME(PF_NETLINK, NETLINK_GENERIC, "-family-" family) + /* Binding to multicast group requires %CAP_NET_ADMIN */ #define GENL_MCAST_CAP_NET_ADMIN BIT(0) /* Binding to multicast group requires %CAP_SYS_ADMIN */ diff --git a/include/net/gre.h b/include/net/gre.h index 4e209708b754..ccd293203284 100644 --- a/include/net/gre.h +++ b/include/net/gre.h @@ -49,67 +49,61 @@ static inline bool netif_is_ip6gretap(const struct net_device *dev) !strcmp(dev->rtnl_link_ops->kind, "ip6gretap"); } -static inline int gre_calc_hlen(__be16 o_flags) +static inline int gre_calc_hlen(const unsigned long *o_flags) { int addend = 4; - if (o_flags & TUNNEL_CSUM) + if (test_bit(IP_TUNNEL_CSUM_BIT, o_flags)) addend += 4; - if (o_flags & TUNNEL_KEY) + if (test_bit(IP_TUNNEL_KEY_BIT, o_flags)) addend += 4; - if (o_flags & TUNNEL_SEQ) + if (test_bit(IP_TUNNEL_SEQ_BIT, o_flags)) addend += 4; return addend; } -static inline __be16 gre_flags_to_tnl_flags(__be16 flags) +static inline void gre_flags_to_tnl_flags(unsigned long *dst, __be16 flags) { - __be16 tflags = 0; - - if (flags & GRE_CSUM) - tflags |= TUNNEL_CSUM; - if (flags & GRE_ROUTING) - tflags |= TUNNEL_ROUTING; - if (flags & GRE_KEY) - tflags |= TUNNEL_KEY; - if (flags & GRE_SEQ) - tflags |= TUNNEL_SEQ; - if (flags & GRE_STRICT) - tflags |= TUNNEL_STRICT; - if (flags & GRE_REC) - tflags |= TUNNEL_REC; - if (flags & GRE_VERSION) - tflags |= TUNNEL_VERSION; - - return tflags; + IP_TUNNEL_DECLARE_FLAGS(res) = { }; + + __assign_bit(IP_TUNNEL_CSUM_BIT, res, flags & GRE_CSUM); + __assign_bit(IP_TUNNEL_ROUTING_BIT, res, flags & GRE_ROUTING); + __assign_bit(IP_TUNNEL_KEY_BIT, res, flags & GRE_KEY); + __assign_bit(IP_TUNNEL_SEQ_BIT, res, flags & GRE_SEQ); + __assign_bit(IP_TUNNEL_STRICT_BIT, res, flags & GRE_STRICT); + __assign_bit(IP_TUNNEL_REC_BIT, res, flags & GRE_REC); + __assign_bit(IP_TUNNEL_VERSION_BIT, res, flags & GRE_VERSION); + + ip_tunnel_flags_copy(dst, res); } -static inline __be16 gre_tnl_flags_to_gre_flags(__be16 tflags) +static inline __be16 gre_tnl_flags_to_gre_flags(const unsigned long *tflags) { __be16 flags = 0; - if (tflags & TUNNEL_CSUM) + if (test_bit(IP_TUNNEL_CSUM_BIT, tflags)) flags |= GRE_CSUM; - if (tflags & TUNNEL_ROUTING) + if (test_bit(IP_TUNNEL_ROUTING_BIT, tflags)) flags |= GRE_ROUTING; - if (tflags & TUNNEL_KEY) + if (test_bit(IP_TUNNEL_KEY_BIT, tflags)) flags |= GRE_KEY; - if (tflags & TUNNEL_SEQ) + if (test_bit(IP_TUNNEL_SEQ_BIT, tflags)) flags |= GRE_SEQ; - if (tflags & TUNNEL_STRICT) + if (test_bit(IP_TUNNEL_STRICT_BIT, tflags)) flags |= GRE_STRICT; - if (tflags & TUNNEL_REC) + if (test_bit(IP_TUNNEL_REC_BIT, tflags)) flags |= GRE_REC; - if (tflags & TUNNEL_VERSION) + if (test_bit(IP_TUNNEL_VERSION_BIT, tflags)) flags |= GRE_VERSION; return flags; } static inline void gre_build_header(struct sk_buff *skb, int hdr_len, - __be16 flags, __be16 proto, + const unsigned long *flags, __be16 proto, __be32 key, __be32 seq) { + IP_TUNNEL_DECLARE_FLAGS(cond) = { }; struct gre_base_hdr *greh; skb_push(skb, hdr_len); @@ -120,18 +114,22 @@ static inline void gre_build_header(struct sk_buff *skb, int hdr_len, greh->flags = gre_tnl_flags_to_gre_flags(flags); greh->protocol = proto; - if (flags & (TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_SEQ)) { + __set_bit(IP_TUNNEL_KEY_BIT, cond); + __set_bit(IP_TUNNEL_CSUM_BIT, cond); + __set_bit(IP_TUNNEL_SEQ_BIT, cond); + + if (ip_tunnel_flags_intersect(flags, cond)) { __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4); - if (flags & TUNNEL_SEQ) { + if (test_bit(IP_TUNNEL_SEQ_BIT, flags)) { *ptr = seq; ptr--; } - if (flags & TUNNEL_KEY) { + if (test_bit(IP_TUNNEL_KEY_BIT, flags)) { *ptr = key; ptr--; } - if (flags & TUNNEL_CSUM && + if (test_bit(IP_TUNNEL_CSUM_BIT, flags) && !(skb_shinfo(skb)->gso_type & (SKB_GSO_GRE | SKB_GSO_GRE_CSUM))) { *ptr = 0; diff --git a/include/net/gro.h b/include/net/gro.h index c1d4ca0463a1..b9b58c1f8d19 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -36,15 +36,14 @@ struct napi_gro_cb { /* This is non-zero if the packet cannot be merged with the new skb. */ u16 flush; - /* Save the IP ID here and check when we get to the transport layer */ - u16 flush_id; - /* Number of segments aggregated. */ u16 count; /* Used in ipv6_gro_receive() and foo-over-udp and esp-in-udp */ u16 proto; + u16 pad; + /* Used in napi_gro_cb::free */ #define NAPI_GRO_FREE 1 #define NAPI_GRO_FREE_STOLEN_HEAD 2 @@ -75,8 +74,8 @@ struct napi_gro_cb { /* Used in GRE, set in fou/gue_gro_receive */ u8 is_fou:1; - /* Used to determine if flush_id can be ignored */ - u8 is_atomic:1; + /* Used to determine if ipid_offset can be ignored */ + u8 ip_fixedid:1; /* Number of gro_receive callbacks this packet already went through */ u8 recursion_counter:4; @@ -181,12 +180,17 @@ static inline void *skb_gro_header(struct sk_buff *skb, unsigned int hlen, return ptr; } +static inline int skb_gro_receive_network_offset(const struct sk_buff *skb) +{ + return NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark]; +} + static inline void *skb_gro_network_header(const struct sk_buff *skb) { if (skb_gro_may_pull(skb, skb_gro_offset(skb))) - return skb_gro_header_fast(skb, skb_network_offset(skb)); + return skb_gro_header_fast(skb, skb_gro_receive_network_offset(skb)); - return skb_network_header(skb); + return skb->data + skb_gro_receive_network_offset(skb); } static inline __wsum inet_gro_compute_pseudo(const struct sk_buff *skb, @@ -437,7 +441,71 @@ static inline __wsum ip6_gro_compute_pseudo(const struct sk_buff *skb, skb_gro_len(skb), proto, 0)); } +static inline int inet_gro_flush(const struct iphdr *iph, const struct iphdr *iph2, + struct sk_buff *p, bool outer) +{ + const u32 id = ntohl(*(__be32 *)&iph->id); + const u32 id2 = ntohl(*(__be32 *)&iph2->id); + const u16 ipid_offset = (id >> 16) - (id2 >> 16); + const u16 count = NAPI_GRO_CB(p)->count; + const u32 df = id & IP_DF; + int flush; + + /* All fields must match except length and checksum. */ + flush = (iph->ttl ^ iph2->ttl) | (iph->tos ^ iph2->tos) | (df ^ (id2 & IP_DF)); + + if (flush | (outer && df)) + return flush; + + /* When we receive our second frame we can make a decision on if we + * continue this flow as an atomic flow with a fixed ID or if we use + * an incrementing ID. + */ + if (count == 1 && df && !ipid_offset) + NAPI_GRO_CB(p)->ip_fixedid = true; + + return ipid_offset ^ (count * !NAPI_GRO_CB(p)->ip_fixedid); +} + +static inline int ipv6_gro_flush(const struct ipv6hdr *iph, const struct ipv6hdr *iph2) +{ + /* <Version:4><Traffic_Class:8><Flow_Label:20> */ + __be32 first_word = *(__be32 *)iph ^ *(__be32 *)iph2; + + /* Flush if Traffic Class fields are different. */ + return !!((first_word & htonl(0x0FF00000)) | + (__force __be32)(iph->hop_limit ^ iph2->hop_limit)); +} + +static inline int __gro_receive_network_flush(const void *th, const void *th2, + struct sk_buff *p, const u16 diff, + bool outer) +{ + const void *nh = th - diff; + const void *nh2 = th2 - diff; + + if (((struct iphdr *)nh)->version == 6) + return ipv6_gro_flush(nh, nh2); + else + return inet_gro_flush(nh, nh2, p, outer); +} + +static inline int gro_receive_network_flush(const void *th, const void *th2, + struct sk_buff *p) +{ + const bool encap_mark = NAPI_GRO_CB(p)->encap_mark; + int off = skb_transport_offset(p); + int flush; + + flush = __gro_receive_network_flush(th, th2, p, off - NAPI_GRO_CB(p)->network_offset, encap_mark); + if (encap_mark) + flush |= __gro_receive_network_flush(th, th2, p, off - NAPI_GRO_CB(p)->inner_network_offset, false); + + return flush; +} + int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); +int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb); /* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ static inline void gro_normal_list(struct napi_struct *napi) diff --git a/include/net/gtp.h b/include/net/gtp.h index 2a503f035d18..c0253c8702d0 100644 --- a/include/net/gtp.h +++ b/include/net/gtp.h @@ -78,4 +78,9 @@ static inline bool netif_is_gtp(const struct net_device *dev) #define GTP1_F_EXTHDR 0x04 #define GTP1_F_MASK 0x07 +struct gtp_ext_hdr { + __u8 len; + __u8 data[]; +}; + #endif diff --git a/include/net/hotdata.h b/include/net/hotdata.h index 003667a1efd6..30e9570beb2a 100644 --- a/include/net/hotdata.h +++ b/include/net/hotdata.h @@ -38,6 +38,9 @@ struct net_hotdata { int max_backlog; int dev_tx_weight; int dev_rx_weight; + int sysctl_max_skb_frags; + int sysctl_skb_defer_max; + int sysctl_mem_pcpu_rsv; }; #define inet_ehash_secret net_hotdata.tcp_protocol.secret diff --git a/include/net/ieee8021q.h b/include/net/ieee8021q.h new file mode 100644 index 000000000000..8bfe903dd3d0 --- /dev/null +++ b/include/net/ieee8021q.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Pengutronix, Oleksij Rempel <kernel@pengutronix.de> */ + +#ifndef _NET_IEEE8021Q_H +#define _NET_IEEE8021Q_H + +#include <linux/errno.h> + +/** + * enum ieee8021q_traffic_type - 802.1Q traffic type priority values (802.1Q-2022) + * + * @IEEE8021Q_TT_BK: Background + * @IEEE8021Q_TT_BE: Best Effort (default). According to 802.1Q-2022, BE is 0 + * but has higher priority than BK which is 1. + * @IEEE8021Q_TT_EE: Excellent Effort + * @IEEE8021Q_TT_CA: Critical Applications + * @IEEE8021Q_TT_VI: Video, < 100 ms latency and jitter + * @IEEE8021Q_TT_VO: Voice, < 10 ms latency and jitter + * @IEEE8021Q_TT_IC: Internetwork Control + * @IEEE8021Q_TT_NC: Network Control + */ +enum ieee8021q_traffic_type { + IEEE8021Q_TT_BK = 0, + IEEE8021Q_TT_BE = 1, + IEEE8021Q_TT_EE = 2, + IEEE8021Q_TT_CA = 3, + IEEE8021Q_TT_VI = 4, + IEEE8021Q_TT_VO = 5, + IEEE8021Q_TT_IC = 6, + IEEE8021Q_TT_NC = 7, + + /* private: */ + IEEE8021Q_TT_MAX, +}; + +#define SIMPLE_IETF_DSCP_TO_IEEE8021Q_TT(dscp) ((dscp >> 3) & 0x7) + +#if IS_ENABLED(CONFIG_NET_IEEE8021Q_HELPERS) + +int ietf_dscp_to_ieee8021q_tt(u8 dscp); +int ieee8021q_tt_to_tc(enum ieee8021q_traffic_type tt, unsigned int num_queues); + +#else + +static inline int ietf_dscp_to_ieee8021q_tt(u8 dscp) +{ + return -EOPNOTSUPP; +} + +static inline int ieee8021q_tt_to_tc(enum ieee8021q_traffic_type tt, + unsigned int num_queues) +{ + return -EOPNOTSUPP; +} + +#endif +#endif /* _NET_IEEE8021Q_H */ diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index ccf171f7eb60..20e7b0c0b3d1 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -147,10 +147,7 @@ struct inet_connection_sock { #define ICSK_TIME_LOSS_PROBE 5 /* Tail loss probe timer */ #define ICSK_TIME_REO_TIMEOUT 6 /* Reordering timer */ -static inline struct inet_connection_sock *inet_csk(const struct sock *sk) -{ - return (struct inet_connection_sock *)sk; -} +#define inet_csk(ptr) container_of_const(ptr, struct inet_connection_sock, icsk_inet.sk) static inline void *inet_csk_ca(const struct sock *sk) { @@ -284,7 +281,7 @@ static inline int inet_csk_reqsk_queue_len(const struct sock *sk) static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) { - return inet_csk_reqsk_queue_len(sk) >= sk->sk_max_ack_backlog; + return inet_csk_reqsk_queue_len(sk) >= READ_ONCE(sk->sk_max_ack_backlog); } bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index f28da08a37b4..2a536eea9424 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -111,7 +111,7 @@ static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo void inet_twsk_deschedule_put(struct inet_timewait_sock *tw); -void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family); +void inet_twsk_purge(struct inet_hashinfo *hashinfo); static inline struct net *twsk_net(const struct inet_timewait_sock *twsk) diff --git a/include/net/ip.h b/include/net/ip.h index 25cb688bdc62..6d735e00d3f3 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -423,7 +423,7 @@ int ip_decrease_ttl(struct iphdr *iph) static inline int ip_mtu_locked(const struct dst_entry *dst) { - const struct rtable *rt = (const struct rtable *)dst; + const struct rtable *rt = dst_rtable(dst); return rt->rt_mtu_locked || dst_metric_locked(dst, RTAX_MTU); } @@ -461,7 +461,7 @@ static inline bool ip_sk_ignore_df(const struct sock *sk) static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, bool forwarding) { - const struct rtable *rt = container_of(dst, struct rtable, dst); + const struct rtable *rt = dst_rtable(dst); struct net *net = dev_net(dst->dev); unsigned int mtu; diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 323c94f1845b..6cb867ce4878 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -234,9 +234,11 @@ struct fib6_result { for (rt = (w)->leaf; rt; \ rt = rcu_dereference_protected(rt->fib6_next, 1)) -static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) +#define dst_rt6_info(_ptr) container_of_const(_ptr, struct rt6_info, dst) + +static inline struct inet6_dev *ip6_dst_idev(const struct dst_entry *dst) { - return ((struct rt6_info *)dst)->rt6i_idev; + return dst_rt6_info(dst)->rt6i_idev; } static inline bool fib6_requires_src(const struct fib6_info *rt) @@ -338,7 +340,7 @@ static inline void fib6_info_release(struct fib6_info *f6i) { if (f6i && refcount_dec_and_test(&f6i->fib6_ref)) { DEBUG_NET_WARN_ON_ONCE(!hlist_unhashed(&f6i->gc_link)); - call_rcu(&f6i->rcu, fib6_info_destroy_rcu); + call_rcu_hurry(&f6i->rcu, fib6_info_destroy_rcu); } } diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index a30c6aa9e5cf..a18ed24fed94 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -210,12 +210,11 @@ void rt6_uncached_list_del(struct rt6_info *rt); static inline const struct rt6_info *skb_rt6_info(const struct sk_buff *skb) { const struct dst_entry *dst = skb_dst(skb); - const struct rt6_info *rt6 = NULL; if (dst) - rt6 = container_of(dst, struct rt6_info, dst); + return dst_rt6_info(dst); - return rt6; + return NULL; } /* @@ -227,7 +226,7 @@ static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, { struct ipv6_pinfo *np = inet6_sk(sk); - np->dst_cookie = rt6_get_cookie((struct rt6_info *)dst); + np->dst_cookie = rt6_get_cookie(dst_rt6_info(dst)); sk_setup_caps(sk, dst); np->daddr_cache = daddr; #ifdef CONFIG_IPV6_SUBTREES @@ -240,7 +239,7 @@ void ip6_sk_dst_store_flow(struct sock *sk, struct dst_entry *dst, static inline bool ipv6_unicast_destination(const struct sk_buff *skb) { - struct rt6_info *rt = (struct rt6_info *) skb_dst(skb); + const struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); return rt->rt6i_flags & RTF_LOCAL; } @@ -248,7 +247,7 @@ static inline bool ipv6_unicast_destination(const struct sk_buff *skb) static inline bool ipv6_anycast_destination(const struct dst_entry *dst, const struct in6_addr *daddr) { - struct rt6_info *rt = (struct rt6_info *)dst; + const struct rt6_info *rt = dst_rt6_info(dst); return rt->rt6i_flags & RTF_ANYCAST || (rt->rt6i_dst.plen < 127 && diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 74b369bddf49..399592405c72 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -30,8 +30,8 @@ struct __ip6_tnl_parm { struct in6_addr laddr; /* local tunnel end-point address */ struct in6_addr raddr; /* remote tunnel end-point address */ - __be16 i_flags; - __be16 o_flags; + IP_TUNNEL_DECLARE_FLAGS(i_flags); + IP_TUNNEL_DECLARE_FLAGS(o_flags); __be32 i_key; __be32 o_key; diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index c286cc2e766e..9a6a08ec7713 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -36,6 +36,24 @@ (sizeof_field(struct ip_tunnel_key, u) - \ sizeof_field(struct ip_tunnel_key, u.ipv4)) +#define __ipt_flag_op(op, ...) \ + op(__VA_ARGS__, __IP_TUNNEL_FLAG_NUM) + +#define IP_TUNNEL_DECLARE_FLAGS(...) \ + __ipt_flag_op(DECLARE_BITMAP, __VA_ARGS__) + +#define ip_tunnel_flags_zero(...) __ipt_flag_op(bitmap_zero, __VA_ARGS__) +#define ip_tunnel_flags_copy(...) __ipt_flag_op(bitmap_copy, __VA_ARGS__) +#define ip_tunnel_flags_and(...) __ipt_flag_op(bitmap_and, __VA_ARGS__) +#define ip_tunnel_flags_or(...) __ipt_flag_op(bitmap_or, __VA_ARGS__) + +#define ip_tunnel_flags_empty(...) \ + __ipt_flag_op(bitmap_empty, __VA_ARGS__) +#define ip_tunnel_flags_intersect(...) \ + __ipt_flag_op(bitmap_intersects, __VA_ARGS__) +#define ip_tunnel_flags_subset(...) \ + __ipt_flag_op(bitmap_subset, __VA_ARGS__) + struct ip_tunnel_key { __be64 tun_id; union { @@ -48,11 +66,11 @@ struct ip_tunnel_key { struct in6_addr dst; } ipv6; } u; - __be16 tun_flags; - u8 tos; /* TOS for IPv4, TC for IPv6 */ - u8 ttl; /* TTL for IPv4, HL for IPv6 */ + IP_TUNNEL_DECLARE_FLAGS(tun_flags); __be32 label; /* Flow Label for IPv6 */ u32 nhid; + u8 tos; /* TOS for IPv4, TC for IPv6 */ + u8 ttl; /* TTL for IPv4, HL for IPv6 */ __be16 tp_src; __be16 tp_dst; __u8 flow_flags; @@ -110,6 +128,17 @@ struct ip_tunnel_prl_entry { struct metadata_dst; +/* Kernel-side variant of ip_tunnel_parm */ +struct ip_tunnel_parm_kern { + char name[IFNAMSIZ]; + IP_TUNNEL_DECLARE_FLAGS(i_flags); + IP_TUNNEL_DECLARE_FLAGS(o_flags); + __be32 i_key; + __be32 o_key; + int link; + struct iphdr iph; +}; + struct ip_tunnel { struct ip_tunnel __rcu *next; struct hlist_node hash_node; @@ -136,7 +165,7 @@ struct ip_tunnel { struct dst_cache dst_cache; - struct ip_tunnel_parm parms; + struct ip_tunnel_parm_kern parms; int mlink; int encap_hlen; /* Encap header length (FOU,GUE) */ @@ -157,7 +186,7 @@ struct ip_tunnel { }; struct tnl_ptk_info { - __be16 flags; + IP_TUNNEL_DECLARE_FLAGS(flags); __be16 proto; __be32 key; __be32 seq; @@ -179,11 +208,80 @@ struct ip_tunnel_net { int type; }; +static inline void ip_tunnel_set_options_present(unsigned long *flags) +{ + IP_TUNNEL_DECLARE_FLAGS(present) = { }; + + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, present); + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_GTP_OPT_BIT, present); + __set_bit(IP_TUNNEL_PFCP_OPT_BIT, present); + + ip_tunnel_flags_or(flags, flags, present); +} + +static inline void ip_tunnel_clear_options_present(unsigned long *flags) +{ + IP_TUNNEL_DECLARE_FLAGS(present) = { }; + + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, present); + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_GTP_OPT_BIT, present); + __set_bit(IP_TUNNEL_PFCP_OPT_BIT, present); + + __ipt_flag_op(bitmap_andnot, flags, flags, present); +} + +static inline bool ip_tunnel_is_options_present(const unsigned long *flags) +{ + IP_TUNNEL_DECLARE_FLAGS(present) = { }; + + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, present); + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_GTP_OPT_BIT, present); + __set_bit(IP_TUNNEL_PFCP_OPT_BIT, present); + + return ip_tunnel_flags_intersect(flags, present); +} + +static inline bool ip_tunnel_flags_is_be16_compat(const unsigned long *flags) +{ + IP_TUNNEL_DECLARE_FLAGS(supp) = { }; + + bitmap_set(supp, 0, BITS_PER_TYPE(__be16)); + __set_bit(IP_TUNNEL_VTI_BIT, supp); + + return ip_tunnel_flags_subset(flags, supp); +} + +static inline void ip_tunnel_flags_from_be16(unsigned long *dst, __be16 flags) +{ + ip_tunnel_flags_zero(dst); + + bitmap_write(dst, be16_to_cpu(flags), 0, BITS_PER_TYPE(__be16)); + __assign_bit(IP_TUNNEL_VTI_BIT, dst, flags & VTI_ISVTI); +} + +static inline __be16 ip_tunnel_flags_to_be16(const unsigned long *flags) +{ + __be16 ret; + + ret = cpu_to_be16(bitmap_read(flags, 0, BITS_PER_TYPE(__be16))); + if (test_bit(IP_TUNNEL_VTI_BIT, flags)) + ret |= VTI_ISVTI; + + return ret; +} + static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, __be32 saddr, __be32 daddr, u8 tos, u8 ttl, __be32 label, __be16 tp_src, __be16 tp_dst, - __be64 tun_id, __be16 tun_flags) + __be64 tun_id, + const unsigned long *tun_flags) { key->tun_id = tun_id; key->u.ipv4.src = saddr; @@ -193,7 +291,7 @@ static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, key->tos = tos; key->ttl = ttl; key->label = label; - key->tun_flags = tun_flags; + ip_tunnel_flags_copy(key->tun_flags, tun_flags); /* For the tunnel types on the top of IPsec, the tp_src and tp_dst of * the upper tunnel are used. @@ -214,12 +312,8 @@ ip_tunnel_dst_cache_usable(const struct sk_buff *skb, { if (skb->mark) return false; - if (!info) - return true; - if (info->key.tun_flags & TUNNEL_NOCACHE) - return false; - return true; + return !info || !test_bit(IP_TUNNEL_NOCACHE_BIT, info->key.tun_flags); } static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info @@ -291,14 +385,18 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, const u8 protocol); void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const u8 proto, int tunnel_hlen); -int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); +int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, + int cmd); +bool ip_tunnel_parm_from_user(struct ip_tunnel_parm_kern *kp, + const void __user *data); +bool ip_tunnel_parm_to_user(void __user *data, struct ip_tunnel_parm_kern *kp); int ip_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu); struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, - int link, __be16 flags, + int link, const unsigned long *flags, __be32 remote, __be32 local, __be32 key); @@ -307,16 +405,16 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, bool log_ecn_error); int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], - struct ip_tunnel_parm *p, __u32 fwmark); + struct ip_tunnel_parm_kern *p, __u32 fwmark); int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], - struct ip_tunnel_parm *p, __u32 fwmark); + struct ip_tunnel_parm_kern *p, __u32 fwmark); void ip_tunnel_setup(struct net_device *dev, unsigned int net_id); bool ip_tunnel_netlink_encap_parms(struct nlattr *data[], struct ip_tunnel_encap *encap); void ip_tunnel_netlink_parms(struct nlattr *data[], - struct ip_tunnel_parm *parms); + struct ip_tunnel_parm_kern *parms); extern const struct header_ops ip_tunnel_header_ops; __be16 ip_tunnel_parse_protocol(const struct sk_buff *skb); @@ -547,12 +645,13 @@ static inline void ip_tunnel_info_opts_get(void *to, static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, const void *from, int len, - __be16 flags) + const unsigned long *flags) { info->options_len = len; if (len > 0) { memcpy(ip_tunnel_info_opts(info), from, len); - info->key.tun_flags |= flags; + ip_tunnel_flags_or(info->key.tun_flags, info->key.tun_flags, + flags); } } @@ -596,7 +695,7 @@ static inline void ip_tunnel_info_opts_get(void *to, static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, const void *from, int len, - __be16 flags) + const unsigned long *flags) { info->options_len = 0; } diff --git a/include/net/libeth/rx.h b/include/net/libeth/rx.h new file mode 100644 index 000000000000..f29ea3e34c6c --- /dev/null +++ b/include/net/libeth/rx.h @@ -0,0 +1,242 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2024 Intel Corporation */ + +#ifndef __LIBETH_RX_H +#define __LIBETH_RX_H + +#include <linux/if_vlan.h> + +#include <net/page_pool/helpers.h> +#include <net/xdp.h> + +/* Rx buffer management */ + +/* Space reserved in front of each frame */ +#define LIBETH_SKB_HEADROOM (NET_SKB_PAD + NET_IP_ALIGN) +/* Maximum headroom for worst-case calculations */ +#define LIBETH_MAX_HEADROOM LIBETH_SKB_HEADROOM +/* Link layer / L2 overhead: Ethernet, 2 VLAN tags (C + S), FCS */ +#define LIBETH_RX_LL_LEN (ETH_HLEN + 2 * VLAN_HLEN + ETH_FCS_LEN) + +/* Always use order-0 pages */ +#define LIBETH_RX_PAGE_ORDER 0 +/* Pick a sane buffer stride and align to a cacheline boundary */ +#define LIBETH_RX_BUF_STRIDE SKB_DATA_ALIGN(128) +/* HW-writeable space in one buffer: truesize - headroom/tailroom, aligned */ +#define LIBETH_RX_PAGE_LEN(hr) \ + ALIGN_DOWN(SKB_MAX_ORDER(hr, LIBETH_RX_PAGE_ORDER), \ + LIBETH_RX_BUF_STRIDE) + +/** + * struct libeth_fqe - structure representing an Rx buffer (fill queue element) + * @page: page holding the buffer + * @offset: offset from the page start (to the headroom) + * @truesize: total space occupied by the buffer (w/ headroom and tailroom) + * + * Depending on the MTU, API switches between one-page-per-frame and shared + * page model (to conserve memory on bigger-page platforms). In case of the + * former, @offset is always 0 and @truesize is always ```PAGE_SIZE```. + */ +struct libeth_fqe { + struct page *page; + u32 offset; + u32 truesize; +} __aligned_largest; + +/** + * struct libeth_fq - structure representing a buffer (fill) queue + * @fp: hotpath part of the structure + * @pp: &page_pool for buffer management + * @fqes: array of Rx buffers + * @truesize: size to allocate per buffer, w/overhead + * @count: number of descriptors/buffers the queue has + * @buf_len: HW-writeable length per each buffer + * @nid: ID of the closest NUMA node with memory + */ +struct libeth_fq { + struct_group_tagged(libeth_fq_fp, fp, + struct page_pool *pp; + struct libeth_fqe *fqes; + + u32 truesize; + u32 count; + ); + + /* Cold fields */ + u32 buf_len; + int nid; +}; + +int libeth_rx_fq_create(struct libeth_fq *fq, struct napi_struct *napi); +void libeth_rx_fq_destroy(struct libeth_fq *fq); + +/** + * libeth_rx_alloc - allocate a new Rx buffer + * @fq: fill queue to allocate for + * @i: index of the buffer within the queue + * + * Return: DMA address to be passed to HW for Rx on successful allocation, + * ```DMA_MAPPING_ERROR``` otherwise. + */ +static inline dma_addr_t libeth_rx_alloc(const struct libeth_fq_fp *fq, u32 i) +{ + struct libeth_fqe *buf = &fq->fqes[i]; + + buf->truesize = fq->truesize; + buf->page = page_pool_dev_alloc(fq->pp, &buf->offset, &buf->truesize); + if (unlikely(!buf->page)) + return DMA_MAPPING_ERROR; + + return page_pool_get_dma_addr(buf->page) + buf->offset + + fq->pp->p.offset; +} + +void libeth_rx_recycle_slow(struct page *page); + +/** + * libeth_rx_sync_for_cpu - synchronize or recycle buffer post DMA + * @fqe: buffer to process + * @len: frame length from the descriptor + * + * Process the buffer after it's written by HW. The regular path is to + * synchronize DMA for CPU, but in case of no data it will be immediately + * recycled back to its PP. + * + * Return: true when there's data to process, false otherwise. + */ +static inline bool libeth_rx_sync_for_cpu(const struct libeth_fqe *fqe, + u32 len) +{ + struct page *page = fqe->page; + + /* Very rare, but possible case. The most common reason: + * the last fragment contained FCS only, which was then + * stripped by the HW. + */ + if (unlikely(!len)) { + libeth_rx_recycle_slow(page); + return false; + } + + page_pool_dma_sync_for_cpu(page->pp, page, fqe->offset, len); + + return true; +} + +/* Converting abstract packet type numbers into a software structure with + * the packet parameters to do O(1) lookup on Rx. + */ + +enum { + LIBETH_RX_PT_OUTER_L2 = 0U, + LIBETH_RX_PT_OUTER_IPV4, + LIBETH_RX_PT_OUTER_IPV6, +}; + +enum { + LIBETH_RX_PT_NOT_FRAG = 0U, + LIBETH_RX_PT_FRAG, +}; + +enum { + LIBETH_RX_PT_TUNNEL_IP_NONE = 0U, + LIBETH_RX_PT_TUNNEL_IP_IP, + LIBETH_RX_PT_TUNNEL_IP_GRENAT, + LIBETH_RX_PT_TUNNEL_IP_GRENAT_MAC, + LIBETH_RX_PT_TUNNEL_IP_GRENAT_MAC_VLAN, +}; + +enum { + LIBETH_RX_PT_TUNNEL_END_NONE = 0U, + LIBETH_RX_PT_TUNNEL_END_IPV4, + LIBETH_RX_PT_TUNNEL_END_IPV6, +}; + +enum { + LIBETH_RX_PT_INNER_NONE = 0U, + LIBETH_RX_PT_INNER_UDP, + LIBETH_RX_PT_INNER_TCP, + LIBETH_RX_PT_INNER_SCTP, + LIBETH_RX_PT_INNER_ICMP, + LIBETH_RX_PT_INNER_TIMESYNC, +}; + +#define LIBETH_RX_PT_PAYLOAD_NONE PKT_HASH_TYPE_NONE +#define LIBETH_RX_PT_PAYLOAD_L2 PKT_HASH_TYPE_L2 +#define LIBETH_RX_PT_PAYLOAD_L3 PKT_HASH_TYPE_L3 +#define LIBETH_RX_PT_PAYLOAD_L4 PKT_HASH_TYPE_L4 + +struct libeth_rx_pt { + u32 outer_ip:2; + u32 outer_frag:1; + u32 tunnel_type:3; + u32 tunnel_end_prot:2; + u32 tunnel_end_frag:1; + u32 inner_prot:3; + enum pkt_hash_types payload_layer:2; + + u32 pad:2; + enum xdp_rss_hash_type hash_type:16; +}; + +void libeth_rx_pt_gen_hash_type(struct libeth_rx_pt *pt); + +/** + * libeth_rx_pt_get_ip_ver - get IP version from a packet type structure + * @pt: packet type params + * + * Wrapper to compile out the IPv6 code from the drivers when not supported + * by the kernel. + * + * Return: @pt.outer_ip or stub for IPv6 when not compiled-in. + */ +static inline u32 libeth_rx_pt_get_ip_ver(struct libeth_rx_pt pt) +{ +#if !IS_ENABLED(CONFIG_IPV6) + switch (pt.outer_ip) { + case LIBETH_RX_PT_OUTER_IPV4: + return LIBETH_RX_PT_OUTER_IPV4; + default: + return LIBETH_RX_PT_OUTER_L2; + } +#else + return pt.outer_ip; +#endif +} + +/* libeth_has_*() can be used to quickly check whether the HW metadata is + * available to avoid further expensive processing such as descriptor reads. + * They already check for the corresponding netdev feature to be enabled, + * thus can be used as drop-in replacements. + */ + +static inline bool libeth_rx_pt_has_checksum(const struct net_device *dev, + struct libeth_rx_pt pt) +{ + /* Non-zero _INNER* is only possible when _OUTER_IPV* is set, + * it is enough to check only for the L4 type. + */ + return likely(pt.inner_prot > LIBETH_RX_PT_INNER_NONE && + (dev->features & NETIF_F_RXCSUM)); +} + +static inline bool libeth_rx_pt_has_hash(const struct net_device *dev, + struct libeth_rx_pt pt) +{ + return likely(pt.payload_layer > LIBETH_RX_PT_PAYLOAD_NONE && + (dev->features & NETIF_F_RXHASH)); +} + +/** + * libeth_rx_pt_set_hash - fill in skb hash value basing on the PT + * @skb: skb to fill the hash in + * @hash: 32-bit hash value from the descriptor + * @pt: packet type + */ +static inline void libeth_rx_pt_set_hash(struct sk_buff *skb, u32 hash, + struct libeth_rx_pt pt) +{ + skb_set_hash(skb, hash, pt.payload_layer); +} + +#endif /* __LIBETH_RX_H */ diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 2d7f87bc5324..cafc664ee531 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -361,7 +361,7 @@ struct ieee80211_vif_chanctx_switch { * @BSS_CHANGED_UNSOL_BCAST_PROBE_RESP: Unsolicited broadcast probe response * status changed. * @BSS_CHANGED_MLD_VALID_LINKS: MLD valid links status changed. - * @BSS_CHANGED_MLD_TTLM: TID to link mapping was changed + * @BSS_CHANGED_MLD_TTLM: negotiated TID to link mapping was changed */ enum ieee80211_bss_change { BSS_CHANGED_ASSOC = 1<<0, @@ -1924,10 +1924,12 @@ enum ieee80211_neg_ttlm_res { * @active_links: The bitmap of active links, or 0 for non-MLO. * The driver shouldn't change this directly, but use the * API calls meant for that purpose. - * @dormant_links: bitmap of valid but disabled links, or 0 for non-MLO. - * Must be a subset of valid_links. + * @dormant_links: subset of the valid links that are disabled/suspended + * due to advertised or negotiated TTLM respectively. + * 0 for non-MLO. * @suspended_links: subset of dormant_links representing links that are - * suspended. + * suspended due to negotiated TTLM, and could be activated in the + * future by tearing down the TTLM negotiation. * 0 for non-MLO. * @neg_ttlm: negotiated TID to link mapping info. * see &struct ieee80211_neg_ttlm. @@ -2052,7 +2054,7 @@ static inline bool ieee80211_vif_is_mesh(struct ieee80211_vif *vif) * This can be used by mac80211 drivers with direct cfg80211 APIs * (like the vendor commands) that get a wdev. * - * Note that this function may return %NULL if the given wdev isn't + * Return: pointer to the wdev, or %NULL if the given wdev isn't * associated with a vif that the driver knows about (e.g. monitor * or AP_VLAN interfaces.) */ @@ -2065,6 +2067,8 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev); * This can be used by mac80211 drivers with direct cfg80211 APIs * (like the vendor commands) that needs to get the wdev for a vif. * This can also be useful to get the netdev associated to a vif. + * + * Return: pointer to the wdev */ struct wireless_dev *ieee80211_vif_to_wdev(struct ieee80211_vif *vif); @@ -2123,8 +2127,8 @@ static inline bool lockdep_vif_wiphy_mutex_held(struct ieee80211_vif *vif) * @IEEE80211_KEY_FLAG_GENERATE_MMIC on the same key. * @IEEE80211_KEY_FLAG_NO_AUTO_TX: Key needs explicit Tx activation. * @IEEE80211_KEY_FLAG_GENERATE_MMIE: This flag should be set by the driver - * for a AES_CMAC key to indicate that it requires sequence number - * generation only + * for a AES_CMAC or a AES_GMAC key to indicate that it requires sequence + * number generation only * @IEEE80211_KEY_FLAG_SPP_AMSDU: SPP A-MSDUs can be used with this key * (set by mac80211 from the sta->spp_amsdu flag) */ @@ -2780,6 +2784,8 @@ struct ieee80211_txq { * * @IEEE80211_HW_DISALLOW_PUNCTURING: HW requires disabling puncturing in EHT * and connecting with a lower bandwidth instead + * @IEEE80211_HW_DISALLOW_PUNCTURING_5GHZ: HW requires disabling puncturing in + * EHT in 5 GHz and connecting with a lower bandwidth instead * * @IEEE80211_HW_HANDLES_QUIET_CSA: HW/driver handles quieting for CSA, so * no need to stop queues. This really should be set by a driver that @@ -2844,6 +2850,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_DETECTS_COLOR_COLLISION, IEEE80211_HW_MLO_MCAST_MULTI_LINK_TX, IEEE80211_HW_DISALLOW_PUNCTURING, + IEEE80211_HW_DISALLOW_PUNCTURING_5GHZ, IEEE80211_HW_HANDLES_QUIET_CSA, /* keep last, obviously */ @@ -5600,7 +5607,7 @@ void ieee80211_csa_finish(struct ieee80211_vif *vif, unsigned int link_id); * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @link_id: valid link_id during MLO or 0 for non-MLO * - * This function returns whether the countdown reached zero. + * Return: %true if the countdown reached 1, %false otherwise */ bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif, unsigned int link_id); @@ -5608,12 +5615,13 @@ bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif, /** * ieee80211_color_change_finish - notify mac80211 about color change * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * @link_id: valid link_id during MLO or 0 for non-MLO * * After a color change announcement was scheduled and the counter in this * announcement hits 1, this function must be called by the driver to * notify mac80211 that the color can be changed */ -void ieee80211_color_change_finish(struct ieee80211_vif *vif); +void ieee80211_color_change_finish(struct ieee80211_vif *vif, u8 link_id); /** * ieee80211_proberesp_get - retrieve a Probe Response template @@ -5945,8 +5953,8 @@ void ieee80211_remove_key(struct ieee80211_key_conf *keyconf); * key(s) will be available. These will be needed by mac80211 for proper * RX processing, so this function allows setting them. * - * The function returns the newly allocated key structure, which will - * have similar contents to the passed key configuration but point to + * Return: the newly allocated key structure, which will have + * similar contents to the passed key configuration but point to * mac80211-owned memory. In case of errors, the function returns an * ERR_PTR(), use IS_ERR() etc. * @@ -6345,6 +6353,8 @@ struct ieee80211_sta *ieee80211_find_sta_by_ifaddr(struct ieee80211_hw *hw, * may be %NULL if the link ID is not needed * * Obtain the STA by link address, must use RCU protection. + * + * Return: pointer to STA if found, otherwise %NULL. */ struct ieee80211_sta * ieee80211_find_sta_by_link_addrs(struct ieee80211_hw *hw, @@ -6474,8 +6484,8 @@ void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid, * @hw: pointer obtained from ieee80211_alloc_hw() * @txq: pointer obtained from station or virtual interface * - * Return true if the AQL's airtime limit has not been reached and the txq can - * continue to send more packets to the device. Otherwise return false. + * Return: %true if the AQL's airtime limit has not been reached and the txq can + * continue to send more packets to the device. Otherwise return %false. */ bool ieee80211_txq_airtime_check(struct ieee80211_hw *hw, struct ieee80211_txq *txq); @@ -6978,6 +6988,8 @@ bool rate_usable_index_exists(struct ieee80211_supported_band *sband, * @hw: pointer as obtained from ieee80211_alloc_hw() * @pubsta: &struct ieee80211_sta pointer to the target destination. * @rates: new tx rate set to be used for this station. + * + * Return: 0 on success. An error code otherwise. */ int rate_control_set_rates(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, @@ -7138,6 +7150,8 @@ void ieee80211_report_wowlan_wakeup(struct ieee80211_vif *vif, * @band: the band to transmit on * @sta: optional pointer to get the station to send the frame to * + * Return: %true if the skb was prepared, %false otherwise + * * Note: must be called under RCU lock */ bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw, @@ -7154,6 +7168,8 @@ bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw, * * @skb: packet injected by userspace * @dev: the &struct device of this 802.11 device + * + * Return: %true if the radiotap header was parsed, %false otherwise */ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, struct net_device *dev); @@ -7263,7 +7279,7 @@ void ieee80211_unreserve_tid(struct ieee80211_sta *sta, u8 tid); * @txq: pointer obtained from station or virtual interface, or from * ieee80211_next_txq() * - * Returns the skb if successful, %NULL if no frame was available. + * Return: the skb if successful, %NULL if no frame was available. * * Note that this must be called in an rcu_read_lock() critical section, * which can only be released after the SKB was handled. Some pointers in @@ -7289,6 +7305,8 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, * @hw: pointer as obtained from ieee80211_alloc_hw() * @txq: pointer obtained from station or virtual interface, or from * ieee80211_next_txq() + * + * Return: the skb if successful, %NULL if no frame was available. */ static inline struct sk_buff *ieee80211_tx_dequeue_ni(struct ieee80211_hw *hw, struct ieee80211_txq *txq) @@ -7320,7 +7338,7 @@ void ieee80211_handle_wake_tx_queue(struct ieee80211_hw *hw, * @hw: pointer as obtained from ieee80211_alloc_hw() * @ac: AC number to return packets from. * - * Returns the next txq if successful, %NULL if no queue is eligible. If a txq + * Return: the next txq if successful, %NULL if no queue is eligible. If a txq * is returned, it should be returned with ieee80211_return_txq() after the * driver has finished scheduling it. */ @@ -7403,6 +7421,8 @@ ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq, * * @hw: pointer as obtained from ieee80211_alloc_hw() * @txq: pointer obtained from station or virtual interface + * + * Return: %true if transmission is allowed, %false otherwise */ bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw, struct ieee80211_txq *txq); @@ -7463,6 +7483,8 @@ void ieee80211_nan_func_match(struct ieee80211_vif *vif, * @status: &struct ieee80211_rx_status containing the transmission rate * information. * @len: frame length in bytes + * + * Return: the airtime estimate */ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, struct ieee80211_rx_status *status, @@ -7477,23 +7499,13 @@ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, * @hw: pointer as obtained from ieee80211_alloc_hw() * @info: &struct ieee80211_tx_info of the frame. * @len: frame length in bytes + * + * Return: the airtime estimate */ u32 ieee80211_calc_tx_airtime(struct ieee80211_hw *hw, struct ieee80211_tx_info *info, int len); /** - * ieee80211_set_hw_80211_encap - enable hardware encapsulation offloading. - * - * This function is used to notify mac80211 that a vif can be passed raw 802.3 - * frames. The driver needs to then handle the 802.11 encapsulation inside the - * hardware or firmware. - * - * @vif: &struct ieee80211_vif pointer from the add_interface callback. - * @enable: indicate if the feature should be turned on or off - */ -bool ieee80211_set_hw_80211_encap(struct ieee80211_vif *vif, bool enable); - -/** * ieee80211_get_fils_discovery_tmpl - Get FILS discovery template. * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. @@ -7522,6 +7534,7 @@ ieee80211_get_unsol_bcast_probe_resp_tmpl(struct ieee80211_hw *hw, /** * ieee80211_obss_color_collision_notify - notify userland about a BSS color * collision. + * @link_id: valid link_id during MLO or 0 for non-MLO * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @color_bitmap: a 64 bit bitmap representing the colors that the local BSS is @@ -7529,7 +7542,7 @@ ieee80211_get_unsol_bcast_probe_resp_tmpl(struct ieee80211_hw *hw, */ void ieee80211_obss_color_collision_notify(struct ieee80211_vif *vif, - u64 color_bitmap); + u64 color_bitmap, u8 link_id); /** * ieee80211_is_tx_data - check if frame is a data frame @@ -7538,6 +7551,8 @@ ieee80211_obss_color_collision_notify(struct ieee80211_vif *vif, * hardware encapsulation enabled are data frames. * * @skb: the frame to be transmitted. + * + * Return: %true if @skb is a data frame, %false otherwise */ static inline bool ieee80211_is_tx_data(struct sk_buff *skb) { @@ -7573,6 +7588,8 @@ static inline bool ieee80211_is_tx_data(struct sk_buff *skb) * - change_sta_links(0x10) for each affected STA (the AP) * - assign_vif_chanctx(link_id=4) * - change_vif_links(0x10) + * + * Return: 0 on success. An error code otherwise. */ int ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links); @@ -7589,6 +7606,15 @@ int ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links); void ieee80211_set_active_links_async(struct ieee80211_vif *vif, u16 active_links); +/** + * ieee80211_send_teardown_neg_ttlm - tear down a negotiated TTLM request + * @vif: the interface on which the tear down request should be sent. + * + * This function can be used to tear down a previously accepted negotiated + * TTLM request. + */ +void ieee80211_send_teardown_neg_ttlm(struct ieee80211_vif *vif); + /* for older drivers - let's not document these ... */ int ieee80211_emulate_add_chanctx(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx); diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 4eeedf14711b..561f6719fb4e 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -670,6 +670,7 @@ struct mana_cfg_rx_steer_req_v2 { u8 hashkey[MANA_HASH_KEY_SIZE]; u8 cqe_coalescing_enable; u8 reserved2[7]; + mana_handle_t indir_tab[] __counted_by(num_indir_entries); }; /* HW DATA */ struct mana_cfg_rx_steer_resp { diff --git a/include/net/mptcp.h b/include/net/mptcp.h index fb996124b3d5..0bc4ab03f487 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -97,6 +97,9 @@ struct mptcp_out_options { }; #define MPTCP_SCHED_NAME_MAX 16 +#define MPTCP_SCHED_MAX 128 +#define MPTCP_SCHED_BUF_MAX (MPTCP_SCHED_NAME_MAX * MPTCP_SCHED_MAX) + #define MPTCP_SUBFLOWS_MAX 8 struct mptcp_sched_data { diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h index 1ec408585373..a8a7e48dfa6c 100644 --- a/include/net/netdev_queues.h +++ b/include/net/netdev_queues.h @@ -9,11 +9,41 @@ struct netdev_queue_stats_rx { u64 bytes; u64 packets; u64 alloc_fail; + + u64 hw_drops; + u64 hw_drop_overruns; + + u64 csum_unnecessary; + u64 csum_none; + u64 csum_bad; + + u64 hw_gro_packets; + u64 hw_gro_bytes; + u64 hw_gro_wire_packets; + u64 hw_gro_wire_bytes; + + u64 hw_drop_ratelimits; }; struct netdev_queue_stats_tx { u64 bytes; u64 packets; + + u64 hw_drops; + u64 hw_drop_errors; + + u64 csum_none; + u64 needs_csum; + + u64 hw_gso_packets; + u64 hw_gso_bytes; + u64 hw_gso_wire_packets; + u64 hw_gso_wire_bytes; + + u64 hw_drop_ratelimits; + + u64 stop; + u64 wake; }; /** @@ -61,6 +91,37 @@ struct netdev_stat_ops { }; /** + * struct netdev_queue_mgmt_ops - netdev ops for queue management + * + * @ndo_queue_mem_size: Size of the struct that describes a queue's memory. + * + * @ndo_queue_mem_alloc: Allocate memory for an RX queue at the specified index. + * The new memory is written at the specified address. + * + * @ndo_queue_mem_free: Free memory from an RX queue. + * + * @ndo_queue_start: Start an RX queue with the specified memory and at the + * specified index. + * + * @ndo_queue_stop: Stop the RX queue at the specified index. The stopped + * queue's memory is written at the specified address. + */ +struct netdev_queue_mgmt_ops { + size_t ndo_queue_mem_size; + int (*ndo_queue_mem_alloc)(struct net_device *dev, + void *per_queue_mem, + int idx); + void (*ndo_queue_mem_free)(struct net_device *dev, + void *per_queue_mem); + int (*ndo_queue_start)(struct net_device *dev, + void *per_queue_mem, + int idx); + int (*ndo_queue_stop)(struct net_device *dev, + void *per_queue_mem, + int idx); +}; + +/** * DOC: Lockless queue stopping / waking helpers. * * The netif_txq_maybe_stop() and __netif_txq_completed_wake() diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 3f1ed467f951..2796153b03da 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -416,7 +416,7 @@ struct nft_expr_info; int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla, struct nft_expr_info *info); -int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src); +int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src, gfp_t gfp); void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr); int nft_expr_dump(struct sk_buff *skb, unsigned int attr, const struct nft_expr *expr, bool reset); @@ -935,7 +935,7 @@ struct nft_expr_ops { struct nft_regs *regs, const struct nft_pktinfo *pkt); int (*clone)(struct nft_expr *dst, - const struct nft_expr *src); + const struct nft_expr *src, gfp_t gfp); unsigned int size; int (*init)(const struct nft_ctx *ctx, diff --git a/include/net/netlabel.h b/include/net/netlabel.h index f3ab0b8a4b18..2133ad723fc1 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -470,7 +470,8 @@ void netlbl_bitmap_setbit(unsigned char *bitmap, u32 bit, u8 state); int netlbl_enabled(void); int netlbl_sock_setattr(struct sock *sk, u16 family, - const struct netlbl_lsm_secattr *secattr); + const struct netlbl_lsm_secattr *secattr, + bool sk_locked); void netlbl_sock_delattr(struct sock *sk); int netlbl_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr); @@ -487,6 +488,7 @@ int netlbl_skbuff_getattr(const struct sk_buff *skb, u16 family, struct netlbl_lsm_secattr *secattr); void netlbl_skbuff_err(struct sk_buff *skb, u16 family, int error, int gateway); +bool netlbl_sk_lock_check(struct sock *sk); /* * LSM label mapping cache operations @@ -614,7 +616,8 @@ static inline int netlbl_enabled(void) } static inline int netlbl_sock_setattr(struct sock *sk, u16 family, - const struct netlbl_lsm_secattr *secattr) + const struct netlbl_lsm_secattr *secattr, + bool sk_locked) { return -ENOSYS; } @@ -673,6 +676,11 @@ static inline struct audit_buffer *netlbl_audit_start(int type, { return NULL; } + +static inline bool netlbl_sk_lock_check(struct sock *sk) +{ + return true; +} #endif /* CONFIG_NETLABEL */ const struct netlbl_calipso_ops * diff --git a/include/net/netlink.h b/include/net/netlink.h index c19ff921b661..61cef3bd2d31 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -41,7 +41,8 @@ * nlmsg_get_pos() return current position in message * nlmsg_trim() trim part of message * nlmsg_cancel() cancel message construction - * nlmsg_free() free a netlink message + * nlmsg_consume() free a netlink message (expected) + * nlmsg_free() free a netlink message (drop) * * Message Sending: * nlmsg_multicast() multicast message to several groups @@ -157,7 +158,11 @@ * nla_parse() parse and validate stream of attrs * nla_parse_nested() parse nested attributes * nla_for_each_attr() loop over all attributes + * nla_for_each_attr_type() loop over all attributes with the + * given type * nla_for_each_nested() loop over the nested attributes + * nla_for_each_nested_type() loop over the nested attributes with + * the given type *========================================================================= */ @@ -1078,7 +1083,7 @@ static inline void nlmsg_cancel(struct sk_buff *skb, struct nlmsghdr *nlh) } /** - * nlmsg_free - free a netlink message + * nlmsg_free - drop a netlink message * @skb: socket buffer of netlink message */ static inline void nlmsg_free(struct sk_buff *skb) @@ -1087,6 +1092,15 @@ static inline void nlmsg_free(struct sk_buff *skb) } /** + * nlmsg_consume - free a netlink message + * @skb: socket buffer of netlink message + */ +static inline void nlmsg_consume(struct sk_buff *skb) +{ + consume_skb(skb); +} + +/** * nlmsg_multicast_filtered - multicast a netlink message with filter function * @sk: netlink socket to spread messages to * @skb: netlink message as socket buffer @@ -2071,6 +2085,18 @@ static inline int nla_total_size_64bit(int payload) pos = nla_next(pos, &(rem))) /** + * nla_for_each_attr_type - iterate over a stream of attributes + * @pos: loop counter, set to current attribute + * @type: required attribute type for @pos + * @head: head of attribute stream + * @len: length of attribute stream + * @rem: initialized to len, holds bytes currently remaining in stream + */ +#define nla_for_each_attr_type(pos, type, head, len, rem) \ + nla_for_each_attr(pos, head, len, rem) \ + if (nla_type(pos) == type) + +/** * nla_for_each_nested - iterate over nested attributes * @pos: loop counter, set to current attribute * @nla: attribute containing the nested attributes @@ -2080,6 +2106,17 @@ static inline int nla_total_size_64bit(int payload) nla_for_each_attr(pos, nla_data(nla), nla_len(nla), rem) /** + * nla_for_each_nested_type - iterate over nested attributes + * @pos: loop counter, set to current attribute + * @type: required attribute type for @pos + * @nla: attribute containing the nested attributes + * @rem: initialized to len, holds bytes currently remaining in stream + */ +#define nla_for_each_nested_type(pos, type, nla, rem) \ + nla_for_each_nested(pos, nla, rem) \ + if (nla_type(pos) == type) + +/** * nla_is_last - Test if attribute is last in stream * @nla: attribute to test * @rem: bytes remaining in stream diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 7ca315ad500e..68463aebcc05 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -267,7 +267,7 @@ static inline bool nexthop_get(struct nexthop *nh) static inline void nexthop_put(struct nexthop *nh) { if (refcount_dec_and_test(&nh->refcnt)) - call_rcu(&nh->rcu, nexthop_free_rcu); + call_rcu_hurry(&nh->rcu, nexthop_free_rcu); } static inline bool nexthop_cmp(const struct nexthop *nh1, diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 1d397c1a0043..873631c79ab1 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -52,13 +52,15 @@ #ifndef _NET_PAGE_POOL_HELPERS_H #define _NET_PAGE_POOL_HELPERS_H +#include <linux/dma-mapping.h> + #include <net/page_pool/types.h> #ifdef CONFIG_PAGE_POOL_STATS /* Deprecated driver-facing API, use netlink instead */ int page_pool_ethtool_stats_get_count(void); u8 *page_pool_ethtool_stats_get_strings(u8 *data); -u64 *page_pool_ethtool_stats_get(u64 *data, void *stats); +u64 *page_pool_ethtool_stats_get(u64 *data, const void *stats); bool page_pool_get_stats(const struct page_pool *pool, struct page_pool_stats *stats); @@ -73,7 +75,7 @@ static inline u8 *page_pool_ethtool_stats_get_strings(u8 *data) return data; } -static inline u64 *page_pool_ethtool_stats_get(u64 *data, void *stats) +static inline u64 *page_pool_ethtool_stats_get(u64 *data, const void *stats) { return data; } @@ -204,8 +206,8 @@ static inline void *page_pool_dev_alloc_va(struct page_pool *pool, * Get the stored dma direction. A driver might decide to store this locally * and avoid the extra cache line from page_pool to determine the direction. */ -static -inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool) +static inline enum dma_data_direction +page_pool_get_dma_dir(const struct page_pool *pool) { return pool->p.dma_dir; } @@ -370,7 +372,7 @@ static inline void page_pool_free_va(struct page_pool *pool, void *va, * Fetch the DMA address of the page. The page pool to which the page belongs * must had been created with PP_FLAG_DMA_MAP. */ -static inline dma_addr_t page_pool_get_dma_addr(struct page *page) +static inline dma_addr_t page_pool_get_dma_addr(const struct page *page) { dma_addr_t ret = page->dma_addr; @@ -395,6 +397,28 @@ static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr) return false; } +/** + * page_pool_dma_sync_for_cpu - sync Rx page for CPU after it's written by HW + * @pool: &page_pool the @page belongs to + * @page: page to sync + * @offset: offset from page start to "hard" start if using PP frags + * @dma_sync_size: size of the data written to the page + * + * Can be used as a shorthand to sync Rx pages before accessing them in the + * driver. Caller must ensure the pool was created with ``PP_FLAG_DMA_MAP``. + * Note that this version performs DMA sync unconditionally, even if the + * associated PP doesn't perform sync-for-device. + */ +static inline void page_pool_dma_sync_for_cpu(const struct page_pool *pool, + const struct page *page, + u32 offset, u32 dma_sync_size) +{ + dma_sync_single_range_for_cpu(pool->p.dev, + page_pool_get_dma_addr(page), + offset + pool->p.offset, dma_sync_size, + page_pool_get_dma_dir(pool)); +} + static inline bool page_pool_put(struct page_pool *pool) { return refcount_dec_and_test(&pool->user_cnt); diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 5e43a08d3231..a6ebed002216 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -213,7 +213,7 @@ struct xdp_mem_info; #ifdef CONFIG_PAGE_POOL void page_pool_destroy(struct page_pool *pool); void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), - struct xdp_mem_info *mem); + const struct xdp_mem_info *mem); void page_pool_put_page_bulk(struct page_pool *pool, void **data, int count); #else @@ -223,7 +223,7 @@ static inline void page_pool_destroy(struct page_pool *pool) static inline void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), - struct xdp_mem_info *mem) + const struct xdp_mem_info *mem) { } diff --git a/include/net/pfcp.h b/include/net/pfcp.h new file mode 100644 index 000000000000..af14f970b80e --- /dev/null +++ b/include/net/pfcp.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _PFCP_H_ +#define _PFCP_H_ + +#include <uapi/linux/if_ether.h> +#include <net/dst_metadata.h> +#include <linux/netdevice.h> +#include <uapi/linux/ipv6.h> +#include <net/udp_tunnel.h> +#include <uapi/linux/udp.h> +#include <uapi/linux/ip.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/bits.h> + +#define PFCP_PORT 8805 + +/* PFCP protocol header */ +struct pfcphdr { + u8 flags; + u8 message_type; + __be16 message_length; +}; + +/* PFCP header flags */ +#define PFCP_SEID_FLAG BIT(0) +#define PFCP_MP_FLAG BIT(1) + +#define PFCP_VERSION_MASK GENMASK(4, 0) + +#define PFCP_HLEN (sizeof(struct udphdr) + sizeof(struct pfcphdr)) + +/* PFCP node related messages */ +struct pfcphdr_node { + u8 seq_number[3]; + u8 reserved; +}; + +/* PFCP session related messages */ +struct pfcphdr_session { + __be64 seid; + u8 seq_number[3]; +#ifdef __LITTLE_ENDIAN_BITFIELD + u8 message_priority:4, + reserved:4; +#elif defined(__BIG_ENDIAN_BITFIELD) + u8 reserved:4, + message_priprity:4; +#else +#error "Please fix <asm/byteorder>" +#endif +}; + +struct pfcp_metadata { + u8 type; + __be64 seid; +} __packed; + +enum { + PFCP_TYPE_NODE = 0, + PFCP_TYPE_SESSION = 1, +}; + +#define PFCP_HEADROOM (sizeof(struct iphdr) + sizeof(struct udphdr) + \ + sizeof(struct pfcphdr) + sizeof(struct ethhdr)) +#define PFCP6_HEADROOM (sizeof(struct ipv6hdr) + sizeof(struct udphdr) + \ + sizeof(struct pfcphdr) + sizeof(struct ethhdr)) + +static inline struct pfcphdr *pfcp_hdr(struct sk_buff *skb) +{ + return (struct pfcphdr *)(udp_hdr(skb) + 1); +} + +static inline struct pfcphdr_node *pfcp_hdr_node(struct sk_buff *skb) +{ + return (struct pfcphdr_node *)(pfcp_hdr(skb) + 1); +} + +static inline struct pfcphdr_session *pfcp_hdr_session(struct sk_buff *skb) +{ + return (struct pfcphdr_session *)(pfcp_hdr(skb) + 1); +} + +static inline bool netif_is_pfcp(const struct net_device *dev) +{ + return dev->rtnl_link_ops && + !strcmp(dev->rtnl_link_ops->kind, "pfcp"); +} + +#endif diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index a4ee43f493bb..41297bd38dff 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -74,6 +74,15 @@ static inline bool tcf_block_non_null_shared(struct tcf_block *block) return block && block->index; } +#ifdef CONFIG_NET_CLS_ACT +DECLARE_STATIC_KEY_FALSE(tcf_bypass_check_needed_key); + +static inline bool tcf_block_bypass_sw(struct tcf_block *block) +{ + return block && block->bypass_wanted; +} +#endif + static inline struct Qdisc *tcf_block_q(struct tcf_block *block) { WARN_ON(tcf_block_shared(block)); diff --git a/include/net/proto_memory.h b/include/net/proto_memory.h new file mode 100644 index 000000000000..a6ab2f4f5e28 --- /dev/null +++ b/include/net/proto_memory.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _PROTO_MEMORY_H +#define _PROTO_MEMORY_H + +#include <net/sock.h> +#include <net/hotdata.h> + +/* 1 MB per cpu, in page units */ +#define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT)) + +static inline bool sk_has_memory_pressure(const struct sock *sk) +{ + return sk->sk_prot->memory_pressure != NULL; +} + +static inline bool +proto_memory_pressure(const struct proto *prot) +{ + if (!prot->memory_pressure) + return false; + return !!READ_ONCE(*prot->memory_pressure); +} + +static inline bool sk_under_global_memory_pressure(const struct sock *sk) +{ + return proto_memory_pressure(sk->sk_prot); +} + +static inline bool sk_under_memory_pressure(const struct sock *sk) +{ + if (!sk->sk_prot->memory_pressure) + return false; + + if (mem_cgroup_sockets_enabled && sk->sk_memcg && + mem_cgroup_under_socket_pressure(sk->sk_memcg)) + return true; + + return !!READ_ONCE(*sk->sk_prot->memory_pressure); +} + +static inline long +proto_memory_allocated(const struct proto *prot) +{ + return max(0L, atomic_long_read(prot->memory_allocated)); +} + +static inline long +sk_memory_allocated(const struct sock *sk) +{ + return proto_memory_allocated(sk->sk_prot); +} + +static inline void proto_memory_pcpu_drain(struct proto *proto) +{ + int val = this_cpu_xchg(*proto->per_cpu_fw_alloc, 0); + + if (val) + atomic_long_add(val, proto->memory_allocated); +} + +static inline void +sk_memory_allocated_add(const struct sock *sk, int val) +{ + struct proto *proto = sk->sk_prot; + + val = this_cpu_add_return(*proto->per_cpu_fw_alloc, val); + + if (unlikely(val >= READ_ONCE(net_hotdata.sysctl_mem_pcpu_rsv))) + proto_memory_pcpu_drain(proto); +} + +static inline void +sk_memory_allocated_sub(const struct sock *sk, int val) +{ + struct proto *proto = sk->sk_prot; + + val = this_cpu_sub_return(*proto->per_cpu_fw_alloc, val); + + if (unlikely(val <= -READ_ONCE(net_hotdata.sysctl_mem_pcpu_rsv))) + proto_memory_pcpu_drain(proto); +} + +#endif /* _PROTO_MEMORY_H */ diff --git a/include/net/red.h b/include/net/red.h index 425364de0df7..802287d52c9e 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -233,10 +233,10 @@ static inline void red_set_parms(struct red_parms *p, int delta = qth_max - qth_min; u32 max_p_delta; - p->qth_min = qth_min << Wlog; - p->qth_max = qth_max << Wlog; - p->Wlog = Wlog; - p->Plog = Plog; + WRITE_ONCE(p->qth_min, qth_min << Wlog); + WRITE_ONCE(p->qth_max, qth_max << Wlog); + WRITE_ONCE(p->Wlog, Wlog); + WRITE_ONCE(p->Plog, Plog); if (delta <= 0) delta = 1; p->qth_delta = delta; @@ -244,7 +244,7 @@ static inline void red_set_parms(struct red_parms *p, max_P = red_maxp(Plog); max_P *= delta; /* max_P = (qth_max - qth_min)/2^Plog */ } - p->max_P = max_P; + WRITE_ONCE(p->max_P, max_P); max_p_delta = max_P / delta; max_p_delta = max(max_p_delta, 1U); p->max_P_reciprocal = reciprocal_value(max_p_delta); @@ -257,7 +257,7 @@ static inline void red_set_parms(struct red_parms *p, p->target_min = qth_min + 2*delta; p->target_max = qth_min + 3*delta; - p->Scell_log = Scell_log; + WRITE_ONCE(p->Scell_log, Scell_log); p->Scell_max = (255 << Scell_log); if (stab) diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 004e651e6067..bdc737832da6 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -18,6 +18,7 @@ #include <linux/refcount.h> #include <net/sock.h> +#include <net/rstreason.h> struct request_sock; struct sk_buff; @@ -34,7 +35,8 @@ struct request_sock_ops { void (*send_ack)(const struct sock *sk, struct sk_buff *skb, struct request_sock *req); void (*send_reset)(const struct sock *sk, - struct sk_buff *skb); + struct sk_buff *skb, + enum sk_rst_reason reason); void (*destructor)(struct request_sock *req); void (*syn_ack_timeout)(const struct request_sock *req); }; diff --git a/include/net/route.h b/include/net/route.h index d4a0147942f1..93833cfe9c96 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -35,8 +35,6 @@ #include <linux/cache.h> #include <linux/security.h> -#define RTO_ONLINK 0x01 - static inline __u8 ip_sock_rt_scope(const struct sock *sk) { if (sock_flag(sk, SOCK_LOCALROUTE)) @@ -77,6 +75,17 @@ struct rtable { rt_pmtu:31; }; +#define dst_rtable(_ptr) container_of_const(_ptr, struct rtable, dst) + +/** + * skb_rtable - Returns the skb &rtable + * @skb: buffer + */ +static inline struct rtable *skb_rtable(const struct sk_buff *skb) +{ + return dst_rtable(skb_dst(skb)); +} + static inline bool rt_is_input_route(const struct rtable *rt) { return rt->rt_is_input != 0; @@ -141,15 +150,22 @@ static inline struct rtable *ip_route_output_key(struct net *net, struct flowi4 return ip_route_output_flow(net, flp, NULL); } +/* Simplistic IPv4 route lookup function. + * This is only suitable for some particular use cases: since the flowi4 + * structure is only partially set, it may bypass some fib-rules. + */ static inline struct rtable *ip_route_output(struct net *net, __be32 daddr, - __be32 saddr, u8 tos, int oif) + __be32 saddr, u8 tos, int oif, + __u8 scope) { struct flowi4 fl4 = { .flowi4_oif = oif, .flowi4_tos = tos, + .flowi4_scope = scope, .daddr = daddr, .saddr = saddr, }; + return ip_route_output_key(net, &fl4); } diff --git a/include/net/rps.h b/include/net/rps.h index 7660243e905b..a93401d23d66 100644 --- a/include/net/rps.h +++ b/include/net/rps.h @@ -122,4 +122,32 @@ static inline void sock_rps_record_flow(const struct sock *sk) #endif } +static inline u32 rps_input_queue_tail_incr(struct softnet_data *sd) +{ +#ifdef CONFIG_RPS + return ++sd->input_queue_tail; +#else + return 0; +#endif +} + +static inline void rps_input_queue_tail_save(u32 *dest, u32 tail) +{ +#ifdef CONFIG_RPS + WRITE_ONCE(*dest, tail); +#endif +} + +static inline void rps_input_queue_head_add(struct softnet_data *sd, int val) +{ +#ifdef CONFIG_RPS + WRITE_ONCE(sd->input_queue_head, sd->input_queue_head + val); +#endif +} + +static inline void rps_input_queue_head_incr(struct softnet_data *sd) +{ + rps_input_queue_head_add(sd, 1); +} + #endif /* _NET_RPS_H */ diff --git a/include/net/rstreason.h b/include/net/rstreason.h new file mode 100644 index 000000000000..2575c85d7f7a --- /dev/null +++ b/include/net/rstreason.h @@ -0,0 +1,182 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef _LINUX_RSTREASON_H +#define _LINUX_RSTREASON_H +#include <net/dropreason-core.h> +#include <uapi/linux/mptcp.h> + +#define DEFINE_RST_REASON(FN, FNe) \ + FN(NOT_SPECIFIED) \ + FN(NO_SOCKET) \ + FN(TCP_INVALID_ACK_SEQUENCE) \ + FN(TCP_RFC7323_PAWS) \ + FN(TCP_TOO_OLD_ACK) \ + FN(TCP_ACK_UNSENT_DATA) \ + FN(TCP_FLAGS) \ + FN(TCP_OLD_ACK) \ + FN(TCP_ABORT_ON_DATA) \ + FN(TCP_TIMEWAIT_SOCKET) \ + FN(INVALID_SYN) \ + FN(MPTCP_RST_EUNSPEC) \ + FN(MPTCP_RST_EMPTCP) \ + FN(MPTCP_RST_ERESOURCE) \ + FN(MPTCP_RST_EPROHIBIT) \ + FN(MPTCP_RST_EWQ2BIG) \ + FN(MPTCP_RST_EBADPERF) \ + FN(MPTCP_RST_EMIDDLEBOX) \ + FN(ERROR) \ + FNe(MAX) + +/** + * enum sk_rst_reason - the reasons of socket reset + * + * The reasons of sk reset, which are used in DCCP/TCP/MPTCP protocols. + * + * There are three parts in order: + * 1) skb drop reasons: relying on drop reasons for such as passive reset + * 2) independent reset reasons: such as active reset reasons + * 3) reset reasons in MPTCP: only for MPTCP use + */ +enum sk_rst_reason { + /* Refer to include/net/dropreason-core.h + * Rely on skb drop reasons because it indicates exactly why RST + * could happen. + */ + /** @SK_RST_REASON_NOT_SPECIFIED: reset reason is not specified */ + SK_RST_REASON_NOT_SPECIFIED, + /** @SK_RST_REASON_NO_SOCKET: no valid socket that can be used */ + SK_RST_REASON_NO_SOCKET, + /** + * @SK_RST_REASON_TCP_INVALID_ACK_SEQUENCE: Not acceptable ACK SEQ + * field because ack sequence is not in the window between snd_una + * and snd_nxt + */ + SK_RST_REASON_TCP_INVALID_ACK_SEQUENCE, + /** + * @SK_RST_REASON_TCP_RFC7323_PAWS: PAWS check, corresponding to + * LINUX_MIB_PAWSESTABREJECTED, LINUX_MIB_PAWSACTIVEREJECTED + */ + SK_RST_REASON_TCP_RFC7323_PAWS, + /** @SK_RST_REASON_TCP_TOO_OLD_ACK: TCP ACK is too old */ + SK_RST_REASON_TCP_TOO_OLD_ACK, + /** + * @SK_RST_REASON_TCP_ACK_UNSENT_DATA: TCP ACK for data we haven't + * sent yet + */ + SK_RST_REASON_TCP_ACK_UNSENT_DATA, + /** @SK_RST_REASON_TCP_FLAGS: TCP flags invalid */ + SK_RST_REASON_TCP_FLAGS, + /** @SK_RST_REASON_TCP_OLD_ACK: TCP ACK is old, but in window */ + SK_RST_REASON_TCP_OLD_ACK, + /** + * @SK_RST_REASON_TCP_ABORT_ON_DATA: abort on data + * corresponding to LINUX_MIB_TCPABORTONDATA + */ + SK_RST_REASON_TCP_ABORT_ON_DATA, + + /* Here start with the independent reasons */ + /** @SK_RST_REASON_TCP_TIMEWAIT_SOCKET: happen on the timewait socket */ + SK_RST_REASON_TCP_TIMEWAIT_SOCKET, + /** + * @SK_RST_REASON_INVALID_SYN: receive bad syn packet + * RFC 793 says if the state is not CLOSED/LISTEN/SYN-SENT then + * "fourth, check the SYN bit,...If the SYN is in the window it is + * an error, send a reset" + */ + SK_RST_REASON_INVALID_SYN, + + /* Copy from include/uapi/linux/mptcp.h. + * These reset fields will not be changed since they adhere to + * RFC 8684. So do not touch them. I'm going to list each definition + * of them respectively. + */ + /** + * @SK_RST_REASON_MPTCP_RST_EUNSPEC: Unspecified error. + * This is the default error; it implies that the subflow is no + * longer available. The presence of this option shows that the + * RST was generated by an MPTCP-aware device. + */ + SK_RST_REASON_MPTCP_RST_EUNSPEC, + /** + * @SK_RST_REASON_MPTCP_RST_EMPTCP: MPTCP-specific error. + * An error has been detected in the processing of MPTCP options. + * This is the usual reason code to return in the cases where a RST + * is being sent to close a subflow because of an invalid response. + */ + SK_RST_REASON_MPTCP_RST_EMPTCP, + /** + * @SK_RST_REASON_MPTCP_RST_ERESOURCE: Lack of resources. + * This code indicates that the sending host does not have enough + * resources to support the terminated subflow. + */ + SK_RST_REASON_MPTCP_RST_ERESOURCE, + /** + * @SK_RST_REASON_MPTCP_RST_EPROHIBIT: Administratively prohibited. + * This code indicates that the requested subflow is prohibited by + * the policies of the sending host. + */ + SK_RST_REASON_MPTCP_RST_EPROHIBIT, + /** + * @SK_RST_REASON_MPTCP_RST_EWQ2BIG: Too much outstanding data. + * This code indicates that there is an excessive amount of data + * that needs to be transmitted over the terminated subflow while + * having already been acknowledged over one or more other subflows. + * This may occur if a path has been unavailable for a short period + * and it is more efficient to reset and start again than it is to + * retransmit the queued data. + */ + SK_RST_REASON_MPTCP_RST_EWQ2BIG, + /** + * @SK_RST_REASON_MPTCP_RST_EBADPERF: Unacceptable performance. + * This code indicates that the performance of this subflow was + * too low compared to the other subflows of this Multipath TCP + * connection. + */ + SK_RST_REASON_MPTCP_RST_EBADPERF, + /** + * @SK_RST_REASON_MPTCP_RST_EMIDDLEBOX: Middlebox interference. + * Middlebox interference has been detected over this subflow, + * making MPTCP signaling invalid. For example, this may be sent + * if the checksum does not validate. + */ + SK_RST_REASON_MPTCP_RST_EMIDDLEBOX, + + /** @SK_RST_REASON_ERROR: unexpected error happens */ + SK_RST_REASON_ERROR, + + /** + * @SK_RST_REASON_MAX: Maximum of socket reset reasons. + * It shouldn't be used as a real 'reason'. + */ + SK_RST_REASON_MAX, +}; + +/* Convert skb drop reasons to enum sk_rst_reason type */ +static inline enum sk_rst_reason +sk_rst_convert_drop_reason(enum skb_drop_reason reason) +{ + switch (reason) { + case SKB_DROP_REASON_NOT_SPECIFIED: + return SK_RST_REASON_NOT_SPECIFIED; + case SKB_DROP_REASON_NO_SOCKET: + return SK_RST_REASON_NO_SOCKET; + case SKB_DROP_REASON_TCP_INVALID_ACK_SEQUENCE: + return SK_RST_REASON_TCP_INVALID_ACK_SEQUENCE; + case SKB_DROP_REASON_TCP_RFC7323_PAWS: + return SK_RST_REASON_TCP_RFC7323_PAWS; + case SKB_DROP_REASON_TCP_TOO_OLD_ACK: + return SK_RST_REASON_TCP_TOO_OLD_ACK; + case SKB_DROP_REASON_TCP_ACK_UNSENT_DATA: + return SK_RST_REASON_TCP_ACK_UNSENT_DATA; + case SKB_DROP_REASON_TCP_FLAGS: + return SK_RST_REASON_TCP_FLAGS; + case SKB_DROP_REASON_TCP_OLD_ACK: + return SK_RST_REASON_TCP_OLD_ACK; + case SKB_DROP_REASON_TCP_ABORT_ON_DATA: + return SK_RST_REASON_TCP_ABORT_ON_DATA; + default: + /* If we don't have our own corresponding reason */ + return SK_RST_REASON_NOT_SPECIFIED; + } +} +#endif diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 41ca14e81d55..79edd5b5e3c9 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -128,6 +128,7 @@ struct Qdisc { struct rcu_head rcu; netdevice_tracker dev_tracker; + struct lock_class_key root_lock_key; /* private data */ long privdata[] ____cacheline_aligned; }; @@ -423,6 +424,7 @@ struct tcf_proto { */ spinlock_t lock; bool deleting; + bool counted; refcount_t refcnt; struct rcu_head rcu; struct hlist_node destroy_ht_node; @@ -472,6 +474,9 @@ struct tcf_block { struct flow_block flow_block; struct list_head owner_list; bool keep_dst; + bool bypass_wanted; + atomic_t filtercnt; /* Number of filters */ + atomic_t skipswcnt; /* Number of skip_sw filters */ atomic_t offloadcnt; /* Number of oddloaded filters */ unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */ unsigned int lockeddevcnt; /* Number of devs that require rtnl lock. */ diff --git a/include/net/scm.h b/include/net/scm.h index 92276a2c5543..0d35c7c77a74 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -23,10 +23,20 @@ struct scm_creds { kgid_t gid; }; +#ifdef CONFIG_UNIX +struct unix_edge; +#endif + struct scm_fp_list { short count; short count_unix; short max; +#ifdef CONFIG_UNIX + bool inflight; + bool dead; + struct list_head vertices; + struct unix_edge *edges; +#endif struct user_struct *user; struct file *fp[SCM_MAX_FD]; }; diff --git a/include/net/smc.h b/include/net/smc.h index c9dcb30e3fd9..db84e4e35080 100644 --- a/include/net/smc.h +++ b/include/net/smc.h @@ -26,9 +26,6 @@ struct smc_hashinfo { struct hlist_head ht; }; -int smc_hash_sk(struct sock *sk); -void smc_unhash_sk(struct sock *sk); - /* SMCD/ISM device driver interface */ struct smcd_dmb { u64 dmb_tok; @@ -50,7 +47,6 @@ struct smcd_dmb { #define ISM_ERROR 0xFFFF struct smcd_dev; -struct ism_client; struct smcd_gid { u64 gid; @@ -61,14 +57,8 @@ struct smcd_ops { int (*query_remote_gid)(struct smcd_dev *dev, struct smcd_gid *rgid, u32 vid_valid, u32 vid); int (*register_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb, - struct ism_client *client); + void *client); int (*unregister_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb); - int (*add_vlan_id)(struct smcd_dev *dev, u64 vlan_id); - int (*del_vlan_id)(struct smcd_dev *dev, u64 vlan_id); - int (*set_vlan_required)(struct smcd_dev *dev); - int (*reset_vlan_required)(struct smcd_dev *dev); - int (*signal_event)(struct smcd_dev *dev, struct smcd_gid *rgid, - u32 trigger_irq, u32 event_code, u64 info); int (*move_data)(struct smcd_dev *dev, u64 dmb_tok, unsigned int idx, bool sf, unsigned int offset, void *data, unsigned int size); @@ -76,11 +66,23 @@ struct smcd_ops { void (*get_local_gid)(struct smcd_dev *dev, struct smcd_gid *gid); u16 (*get_chid)(struct smcd_dev *dev); struct device* (*get_dev)(struct smcd_dev *dev); + + /* optional operations */ + int (*add_vlan_id)(struct smcd_dev *dev, u64 vlan_id); + int (*del_vlan_id)(struct smcd_dev *dev, u64 vlan_id); + int (*set_vlan_required)(struct smcd_dev *dev); + int (*reset_vlan_required)(struct smcd_dev *dev); + int (*signal_event)(struct smcd_dev *dev, struct smcd_gid *rgid, + u32 trigger_irq, u32 event_code, u64 info); + int (*support_dmb_nocopy)(struct smcd_dev *dev); + int (*attach_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb); + int (*detach_dmb)(struct smcd_dev *dev, u64 token); }; struct smcd_dev { const struct smcd_ops *ops; void *priv; + void *client; struct list_head list; spinlock_t lock; struct smc_connection **conn; diff --git a/include/net/sock.h b/include/net/sock.h index b4b553df7870..0450494a1766 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1371,75 +1371,6 @@ static inline int sk_under_cgroup_hierarchy(struct sock *sk, #endif } -static inline bool sk_has_memory_pressure(const struct sock *sk) -{ - return sk->sk_prot->memory_pressure != NULL; -} - -static inline bool sk_under_global_memory_pressure(const struct sock *sk) -{ - return sk->sk_prot->memory_pressure && - !!READ_ONCE(*sk->sk_prot->memory_pressure); -} - -static inline bool sk_under_memory_pressure(const struct sock *sk) -{ - if (!sk->sk_prot->memory_pressure) - return false; - - if (mem_cgroup_sockets_enabled && sk->sk_memcg && - mem_cgroup_under_socket_pressure(sk->sk_memcg)) - return true; - - return !!READ_ONCE(*sk->sk_prot->memory_pressure); -} - -static inline long -proto_memory_allocated(const struct proto *prot) -{ - return max(0L, atomic_long_read(prot->memory_allocated)); -} - -static inline long -sk_memory_allocated(const struct sock *sk) -{ - return proto_memory_allocated(sk->sk_prot); -} - -/* 1 MB per cpu, in page units */ -#define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT)) -extern int sysctl_mem_pcpu_rsv; - -static inline void proto_memory_pcpu_drain(struct proto *proto) -{ - int val = this_cpu_xchg(*proto->per_cpu_fw_alloc, 0); - - if (val) - atomic_long_add(val, proto->memory_allocated); -} - -static inline void -sk_memory_allocated_add(const struct sock *sk, int val) -{ - struct proto *proto = sk->sk_prot; - - val = this_cpu_add_return(*proto->per_cpu_fw_alloc, val); - - if (unlikely(val >= READ_ONCE(sysctl_mem_pcpu_rsv))) - proto_memory_pcpu_drain(proto); -} - -static inline void -sk_memory_allocated_sub(const struct sock *sk, int val) -{ - struct proto *proto = sk->sk_prot; - - val = this_cpu_sub_return(*proto->per_cpu_fw_alloc, val); - - if (unlikely(val <= -READ_ONCE(sysctl_mem_pcpu_rsv))) - proto_memory_pcpu_drain(proto); -} - #define SK_ALLOC_PERCPU_COUNTER_BATCH 16 static inline void sk_sockets_allocated_dec(struct sock *sk) @@ -1466,15 +1397,6 @@ proto_sockets_allocated_sum_positive(struct proto *prot) return percpu_counter_sum_positive(prot->sockets_allocated); } -static inline bool -proto_memory_pressure(struct proto *prot) -{ - if (!prot->memory_pressure) - return false; - return !!READ_ONCE(*prot->memory_pressure); -} - - #ifdef CONFIG_PROC_FS #define PROTO_INUSE_NR 64 /* should be enough for the first time */ struct prot_inuse { @@ -2515,6 +2437,12 @@ static inline void sk_wake_async(const struct sock *sk, int how, int band) } } +static inline void sk_wake_async_rcu(const struct sock *sk, int how, int band) +{ + if (unlikely(sock_flag(sk, SOCK_FASYNC))) + sock_wake_async(rcu_dereference(sk->sk_wq), how, band); +} + /* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might * need sizeof(sk_buff) + MTU + padding, unless net driver perform copybreak. * Note: for send buffers, TCP works better if we can build two skbs at @@ -2831,12 +2759,10 @@ static inline struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb, if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb) { skb = sk->sk_validate_xmit_skb(sk, dev, skb); -#ifdef CONFIG_TLS_DEVICE - } else if (unlikely(skb->decrypted)) { + } else if (unlikely(skb_is_decrypted(skb))) { pr_warn_ratelimited("unencrypted skb with no associated socket - dropping\n"); kfree_skb(skb); skb = NULL; -#endif } #endif diff --git a/include/net/tcp.h b/include/net/tcp.h index 6ae35199d3b3..060e95b331a2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -52,6 +52,8 @@ extern struct inet_hashinfo tcp_hashinfo; DECLARE_PER_CPU(unsigned int, tcp_orphan_count); int tcp_orphan_count_sum(void); +DECLARE_PER_CPU(u32, tcp_tw_isn); + void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_HEADER L1_CACHE_ALIGN(128 + MAX_HEADER) @@ -294,14 +296,6 @@ static inline bool between(__u32 seq1, __u32 seq2, __u32 seq3) return seq3 - seq2 >= seq1 - seq2; } -static inline bool tcp_out_of_memory(struct sock *sk) -{ - if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && - sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2)) - return true; - return false; -} - static inline void tcp_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { sk_wmem_queued_add(sk, -skb->truesize); @@ -314,7 +308,7 @@ static inline void tcp_wmem_free_skb(struct sock *sk, struct sk_buff *skb) void sk_forced_mem_schedule(struct sock *sk, int size); -bool tcp_check_oom(struct sock *sk, int shift); +bool tcp_check_oom(const struct sock *sk, int shift); extern struct proto tcp_prot; @@ -353,7 +347,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb); void tcp_rcv_space_adjust(struct sock *sk); int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp); void tcp_twsk_destructor(struct sock *sk); -void tcp_twsk_purge(struct list_head *net_exit_list, int family); +void tcp_twsk_purge(struct list_head *net_exit_list); ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); @@ -392,7 +386,8 @@ enum tcp_tw_status { enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, - const struct tcphdr *th); + const struct tcphdr *th, + u32 *tw_isn); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, bool fastopen, bool *lost_race); @@ -667,7 +662,8 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, void tcp_send_probe0(struct sock *); int tcp_write_wakeup(struct sock *, int mib); void tcp_send_fin(struct sock *sk); -void tcp_send_active_reset(struct sock *sk, gfp_t priority); +void tcp_send_active_reset(struct sock *sk, gfp_t priority, + enum sk_rst_reason reason); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); void __tcp_send_ack(struct sock *sk, u32 rcv_nxt); @@ -742,7 +738,7 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu); int tcp_mss_to_mtu(struct sock *sk, int mss); void tcp_mtup_init(struct sock *sk); -static inline void tcp_bound_rto(const struct sock *sk) +static inline void tcp_bound_rto(struct sock *sk) { if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX) inet_csk(sk)->icsk_rto = TCP_RTO_MAX; @@ -925,6 +921,19 @@ static inline u32 tcp_rsk_tsval(const struct tcp_request_sock *treq) #define TCPHDR_SYN_ECN (TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR) +/* State flags for sacked in struct tcp_skb_cb */ +enum tcp_skb_cb_sacked_flags { + TCPCB_SACKED_ACKED = (1 << 0), /* SKB ACK'd by a SACK block */ + TCPCB_SACKED_RETRANS = (1 << 1), /* SKB retransmitted */ + TCPCB_LOST = (1 << 2), /* SKB is lost */ + TCPCB_TAGBITS = (TCPCB_SACKED_ACKED | TCPCB_SACKED_RETRANS | + TCPCB_LOST), /* All tag bits */ + TCPCB_REPAIRED = (1 << 4), /* SKB repaired (no skb_mstamp_ns) */ + TCPCB_EVER_RETRANS = (1 << 7), /* Ever retransmitted frame */ + TCPCB_RETRANS = (TCPCB_SACKED_RETRANS | TCPCB_EVER_RETRANS | + TCPCB_REPAIRED), +}; + /* This is what the send packet queuing engine uses to pass * TCP per-packet control information to the transmission code. * We also store the host-order sequence numbers in here too. @@ -935,13 +944,10 @@ struct tcp_skb_cb { __u32 seq; /* Starting sequence number */ __u32 end_seq; /* SEQ + FIN + SYN + datalen */ union { - /* Note : tcp_tw_isn is used in input path only - * (isn chosen by tcp_timewait_state_process()) - * + /* Note : * tcp_gso_segs/size are used in write queue only, * cf tcp_skb_pcount()/tcp_skb_mss() */ - __u32 tcp_tw_isn; struct { u16 tcp_gso_segs; u16 tcp_gso_size; @@ -950,15 +956,6 @@ struct tcp_skb_cb { __u8 tcp_flags; /* TCP header flags. (tcp[13]) */ __u8 sacked; /* State flags for SACK. */ -#define TCPCB_SACKED_ACKED 0x01 /* SKB ACK'd by a SACK block */ -#define TCPCB_SACKED_RETRANS 0x02 /* SKB retransmitted */ -#define TCPCB_LOST 0x04 /* SKB is lost */ -#define TCPCB_TAGBITS 0x07 /* All tag bits */ -#define TCPCB_REPAIRED 0x10 /* SKB repaired (no skb_mstamp_ns) */ -#define TCPCB_EVER_RETRANS 0x80 /* Ever retransmitted frame */ -#define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \ - TCPCB_REPAIRED) - __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */ __u8 txstamp_ack:1, /* Record TX timestamp for ack? */ eor:1, /* Is skb MSG_EOR marked? */ @@ -1167,7 +1164,7 @@ struct tcp_congestion_ops { /* call when packets are delivered to update cwnd and pacing rate, * after all the ca_state processing. (optional) */ - void (*cong_control)(struct sock *sk, const struct rate_sample *rs); + void (*cong_control)(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs); /* new value of cwnd after loss (required) */ @@ -1539,11 +1536,10 @@ static inline int tcp_space_from_win(const struct sock *sk, int win) return __tcp_space_from_win(tcp_sk(sk)->scaling_ratio, win); } -/* Assume a conservative default of 1200 bytes of payload per 4K page. +/* Assume a 50% default for skb->len/skb->truesize ratio. * This may be adjusted later in tcp_measure_rcv_mss(). */ -#define TCP_DEFAULT_SCALING_RATIO ((1200 << TCP_RMEM_TO_WIN_SCALE) / \ - SKB_TRUESIZE(4096)) +#define TCP_DEFAULT_SCALING_RATIO (1 << (TCP_RMEM_TO_WIN_SCALE - 1)) static inline void tcp_scaling_ratio_init(struct sock *sk) { @@ -2195,7 +2191,10 @@ void tcp_v4_destroy_sock(struct sock *sk); struct sk_buff *tcp_gso_segment(struct sk_buff *skb, netdev_features_t features); -struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb); +struct tcphdr *tcp_gro_pull_header(struct sk_buff *skb); +struct sk_buff *tcp_gro_lookup(struct list_head *head, struct tcphdr *th); +struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, + struct tcphdr *th); INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *skb, int thoff)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *skb, int thoff)); @@ -2284,7 +2283,8 @@ struct tcp_request_sock_ops { struct dst_entry *(*route_req)(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, - struct request_sock *req); + struct request_sock *req, + u32 tw_isn); u32 (*init_seq)(const struct sk_buff *skb); u32 (*init_ts_off)(const struct net *net, const struct sk_buff *skb); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, @@ -2706,10 +2706,10 @@ static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1); } -static inline void tcp_bpf_rtt(struct sock *sk) +static inline void tcp_bpf_rtt(struct sock *sk, long mrtt, u32 srtt) { if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_RTT_CB_FLAG)) - tcp_call_bpf(sk, BPF_SOCK_OPS_RTT_CB, 0, NULL); + tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_RTT_CB, mrtt, srtt); } #if IS_ENABLED(CONFIG_SMC) diff --git a/include/net/timewait_sock.h b/include/net/timewait_sock.h index 74d2b463cc95..62b3e9f2aed4 100644 --- a/include/net/timewait_sock.h +++ b/include/net/timewait_sock.h @@ -15,18 +15,9 @@ struct timewait_sock_ops { struct kmem_cache *twsk_slab; char *twsk_slab_name; unsigned int twsk_obj_size; - int (*twsk_unique)(struct sock *sk, - struct sock *sktw, void *twp); void (*twsk_destructor)(struct sock *sk); }; -static inline int twsk_unique(struct sock *sk, struct sock *sktw, void *twp) -{ - if (sk->sk_prot->twsk_prot->twsk_unique != NULL) - return sk->sk_prot->twsk_prot->twsk_unique(sk, sktw, twp); - return 0; -} - static inline void twsk_destructor(struct sock *sk) { if (sk->sk_prot->twsk_prot->twsk_destructor != NULL) diff --git a/include/net/tls.h b/include/net/tls.h index 33f657d3c051..3a33924db2bc 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -362,7 +362,7 @@ static inline bool tls_is_skb_tx_device_offloaded(const struct sk_buff *skb) static inline struct tls_context *tls_get_ctx(const struct sock *sk) { - struct inet_connection_sock *icsk = inet_csk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); /* Use RCU on icsk_ulp_data only for sock diag code, * TLS data path doesn't need rcu_dereference(). diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index d716214fe03d..a93dc51f6323 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -179,8 +179,8 @@ struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb, struct dst_cache *dst_cache); struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, - __be16 flags, __be64 tunnel_id, - int md_size); + const unsigned long *flags, + __be64 tunnel_id, int md_size); #ifdef CONFIG_INET static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index cb4841a9fffd..77ebf5bcf0b9 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -291,6 +291,7 @@ struct xfrm_state { /* Private data of this transformer, format is opaque, * interpreted by xfrm_type methods. */ void *data; + u8 dir; }; static inline struct net *xs_net(struct xfrm_state *x) diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h index e609cd7da47e..a2ea11cc912e 100644 --- a/include/trace/bpf_probe.h +++ b/include/trace/bpf_probe.h @@ -46,8 +46,7 @@ static notrace void \ __bpf_trace_##call(void *__data, proto) \ { \ - struct bpf_prog *prog = __data; \ - CONCATENATE(bpf_trace_run, COUNT_ARGS(args))(prog, CAST_TO_U64(args)); \ + CONCATENATE(bpf_trace_run, COUNT_ARGS(args))(__data, CAST_TO_U64(args)); \ } #undef DECLARE_EVENT_CLASS diff --git a/include/trace/events/bpf_test_run.h b/include/trace/events/bpf_test_run.h index 265447e3f71a..0c924d39b7cb 100644 --- a/include/trace/events/bpf_test_run.h +++ b/include/trace/events/bpf_test_run.h @@ -7,6 +7,23 @@ #include <linux/tracepoint.h> +TRACE_EVENT(bpf_trigger_tp, + + TP_PROTO(int nonce), + + TP_ARGS(nonce), + + TP_STRUCT__entry( + __field(int, nonce) + ), + + TP_fast_assign( + __entry->nonce = nonce; + ), + + TP_printk("nonce %d", __entry->nonce) +); + DECLARE_EVENT_CLASS(bpf_test_finish, TP_PROTO(int *err), diff --git a/include/trace/events/icmp.h b/include/trace/events/icmp.h new file mode 100644 index 000000000000..31559796949a --- /dev/null +++ b/include/trace/events/icmp.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM icmp + +#if !defined(_TRACE_ICMP_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_ICMP_H + +#include <linux/icmp.h> +#include <linux/tracepoint.h> + +TRACE_EVENT(icmp_send, + + TP_PROTO(const struct sk_buff *skb, int type, int code), + + TP_ARGS(skb, type, code), + + TP_STRUCT__entry( + __field(const void *, skbaddr) + __field(int, type) + __field(int, code) + __array(__u8, saddr, 4) + __array(__u8, daddr, 4) + __field(__u16, sport) + __field(__u16, dport) + __field(unsigned short, ulen) + ), + + TP_fast_assign( + struct iphdr *iph = ip_hdr(skb); + struct udphdr *uh = udp_hdr(skb); + int proto_4 = iph->protocol; + __be32 *p32; + + __entry->skbaddr = skb; + __entry->type = type; + __entry->code = code; + + if (proto_4 != IPPROTO_UDP || (u8 *)uh < skb->head || + (u8 *)uh + sizeof(struct udphdr) + > skb_tail_pointer(skb)) { + __entry->sport = 0; + __entry->dport = 0; + __entry->ulen = 0; + } else { + __entry->sport = ntohs(uh->source); + __entry->dport = ntohs(uh->dest); + __entry->ulen = ntohs(uh->len); + } + + p32 = (__be32 *) __entry->saddr; + *p32 = iph->saddr; + + p32 = (__be32 *) __entry->daddr; + *p32 = iph->daddr; + ), + + TP_printk("icmp_send: type=%d, code=%d. From %pI4:%u to %pI4:%u ulen=%d skbaddr=%p", + __entry->type, __entry->code, + __entry->saddr, __entry->sport, __entry->daddr, + __entry->dport, __entry->ulen, __entry->skbaddr) +); + +#endif /* _TRACE_ICMP_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> + diff --git a/include/trace/events/mdio.h b/include/trace/events/mdio.h index 0f241cbe00ab..285b3e4f83ba 100644 --- a/include/trace/events/mdio.h +++ b/include/trace/events/mdio.h @@ -25,7 +25,7 @@ TRACE_EVENT_CONDITION(mdio_access, ), TP_fast_assign( - strncpy(__entry->busid, bus->id, MII_BUS_ID_SIZE); + strscpy(__entry->busid, bus->id, MII_BUS_ID_SIZE); __entry->read = read; __entry->addr = addr; __entry->regnum = regnum; diff --git a/include/trace/events/net_probe_common.h b/include/trace/events/net_probe_common.h index 3930119cab08..976a58364bff 100644 --- a/include/trace/events/net_probe_common.h +++ b/include/trace/events/net_probe_common.h @@ -41,4 +41,75 @@ #endif +#define TP_STORE_V4MAPPED(__entry, saddr, daddr) \ + do { \ + struct in6_addr *pin6; \ + \ + pin6 = (struct in6_addr *)__entry->saddr_v6; \ + ipv6_addr_set_v4mapped(saddr, pin6); \ + pin6 = (struct in6_addr *)__entry->daddr_v6; \ + ipv6_addr_set_v4mapped(daddr, pin6); \ + } while (0) + +#if IS_ENABLED(CONFIG_IPV6) +#define TP_STORE_ADDRS(__entry, saddr, daddr, saddr6, daddr6) \ + do { \ + if (sk->sk_family == AF_INET6) { \ + struct in6_addr *pin6; \ + \ + pin6 = (struct in6_addr *)__entry->saddr_v6; \ + *pin6 = saddr6; \ + pin6 = (struct in6_addr *)__entry->daddr_v6; \ + *pin6 = daddr6; \ + } else { \ + TP_STORE_V4MAPPED(__entry, saddr, daddr); \ + } \ + } while (0) +#else +#define TP_STORE_ADDRS(__entry, saddr, daddr, saddr6, daddr6) \ + TP_STORE_V4MAPPED(__entry, saddr, daddr) +#endif + +#define TP_STORE_ADDR_PORTS_SKB_V4(skb, protoh, entry_saddr, entry_daddr) \ + do { \ + struct sockaddr_in *v4 = (void *)entry_saddr; \ + \ + v4->sin_family = AF_INET; \ + v4->sin_port = protoh->source; \ + v4->sin_addr.s_addr = ip_hdr(skb)->saddr; \ + v4 = (void *)entry_daddr; \ + v4->sin_family = AF_INET; \ + v4->sin_port = protoh->dest; \ + v4->sin_addr.s_addr = ip_hdr(skb)->daddr; \ + } while (0) + +#if IS_ENABLED(CONFIG_IPV6) + +#define TP_STORE_ADDR_PORTS_SKB(skb, protoh, entry_saddr, entry_daddr) \ + do { \ + const struct iphdr *iph = ip_hdr(skb); \ + \ + if (iph->version == 6) { \ + struct sockaddr_in6 *v6 = (void *)entry_saddr; \ + \ + v6->sin6_family = AF_INET6; \ + v6->sin6_port = protoh->source; \ + v6->sin6_addr = ipv6_hdr(skb)->saddr; \ + v6 = (void *)entry_daddr; \ + v6->sin6_family = AF_INET6; \ + v6->sin6_port = protoh->dest; \ + v6->sin6_addr = ipv6_hdr(skb)->daddr; \ + } else \ + TP_STORE_ADDR_PORTS_SKB_V4(skb, protoh, \ + entry_saddr, \ + entry_daddr); \ + } while (0) + +#else + +#define TP_STORE_ADDR_PORTS_SKB(skb, protoh, entry_saddr, entry_daddr) \ + TP_STORE_ADDR_PORTS_SKB_V4(skb, protoh, entry_saddr, entry_daddr) + +#endif + #endif diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h index fd206a6ab5b8..3836de435d9d 100644 --- a/include/trace/events/sock.h +++ b/include/trace/events/sock.h @@ -10,6 +10,7 @@ #include <linux/tracepoint.h> #include <linux/ipv6.h> #include <linux/tcp.h> +#include <trace/events/net_probe_common.h> #define family_names \ EM(AF_INET) \ @@ -109,7 +110,7 @@ TRACE_EVENT(sock_exceed_buf_limit, ), TP_fast_assign( - strncpy(__entry->name, prot->name, 32); + strscpy(__entry->name, prot->name, 32); __entry->sysctl_mem[0] = READ_ONCE(prot->sysctl_mem[0]); __entry->sysctl_mem[1] = READ_ONCE(prot->sysctl_mem[1]); __entry->sysctl_mem[2] = READ_ONCE(prot->sysctl_mem[2]); @@ -159,7 +160,6 @@ TRACE_EVENT(inet_sock_set_state, TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); - struct in6_addr *pin6; __be32 *p32; __entry->skaddr = sk; @@ -177,20 +177,8 @@ TRACE_EVENT(inet_sock_set_state, p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) { - pin6 = (struct in6_addr *)__entry->saddr_v6; - *pin6 = sk->sk_v6_rcv_saddr; - pin6 = (struct in6_addr *)__entry->daddr_v6; - *pin6 = sk->sk_v6_daddr; - } else -#endif - { - pin6 = (struct in6_addr *)__entry->saddr_v6; - ipv6_addr_set_v4mapped(inet->inet_saddr, pin6); - pin6 = (struct in6_addr *)__entry->daddr_v6; - ipv6_addr_set_v4mapped(inet->inet_daddr, pin6); - } + TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, + sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), TP_printk("family=%s protocol=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c oldstate=%s newstate=%s", @@ -223,7 +211,6 @@ TRACE_EVENT(inet_sk_error_report, TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); - struct in6_addr *pin6; __be32 *p32; __entry->error = sk->sk_err; @@ -238,20 +225,8 @@ TRACE_EVENT(inet_sk_error_report, p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) { - pin6 = (struct in6_addr *)__entry->saddr_v6; - *pin6 = sk->sk_v6_rcv_saddr; - pin6 = (struct in6_addr *)__entry->daddr_v6; - *pin6 = sk->sk_v6_daddr; - } else -#endif - { - pin6 = (struct in6_addr *)__entry->saddr_v6; - ipv6_addr_set_v4mapped(inet->inet_saddr, pin6); - pin6 = (struct in6_addr *)__entry->daddr_v6; - ipv6_addr_set_v4mapped(inet->inet_daddr, pin6); - } + TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, + sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), TP_printk("family=%s protocol=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c error=%d", diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 699dafd204ea..49b5ee091cf6 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -11,35 +11,7 @@ #include <net/ipv6.h> #include <net/tcp.h> #include <linux/sock_diag.h> - -#define TP_STORE_V4MAPPED(__entry, saddr, daddr) \ - do { \ - struct in6_addr *pin6; \ - \ - pin6 = (struct in6_addr *)__entry->saddr_v6; \ - ipv6_addr_set_v4mapped(saddr, pin6); \ - pin6 = (struct in6_addr *)__entry->daddr_v6; \ - ipv6_addr_set_v4mapped(daddr, pin6); \ - } while (0) - -#if IS_ENABLED(CONFIG_IPV6) -#define TP_STORE_ADDRS(__entry, saddr, daddr, saddr6, daddr6) \ - do { \ - if (sk->sk_family == AF_INET6) { \ - struct in6_addr *pin6; \ - \ - pin6 = (struct in6_addr *)__entry->saddr_v6; \ - *pin6 = saddr6; \ - pin6 = (struct in6_addr *)__entry->daddr_v6; \ - *pin6 = daddr6; \ - } else { \ - TP_STORE_V4MAPPED(__entry, saddr, daddr); \ - } \ - } while (0) -#else -#define TP_STORE_ADDRS(__entry, saddr, daddr, saddr6, daddr6) \ - TP_STORE_V4MAPPED(__entry, saddr, daddr) -#endif +#include <net/rstreason.h> /* * tcp event with arguments sk and skb @@ -103,17 +75,70 @@ DEFINE_EVENT(tcp_event_sk_skb, tcp_retransmit_skb, TP_ARGS(sk, skb) ); +#undef FN +#define FN(reason) TRACE_DEFINE_ENUM(SK_RST_REASON_##reason); +DEFINE_RST_REASON(FN, FN) + +#undef FN +#undef FNe +#define FN(reason) { SK_RST_REASON_##reason, #reason }, +#define FNe(reason) { SK_RST_REASON_##reason, #reason } + /* * skb of trace_tcp_send_reset is the skb that caused RST. In case of * active reset, skb should be NULL */ -DEFINE_EVENT(tcp_event_sk_skb, tcp_send_reset, +TRACE_EVENT(tcp_send_reset, - TP_PROTO(const struct sock *sk, const struct sk_buff *skb), + TP_PROTO(const struct sock *sk, + const struct sk_buff *skb, + const enum sk_rst_reason reason), - TP_ARGS(sk, skb) + TP_ARGS(sk, skb, reason), + + TP_STRUCT__entry( + __field(const void *, skbaddr) + __field(const void *, skaddr) + __field(int, state) + __field(enum sk_rst_reason, reason) + __array(__u8, saddr, sizeof(struct sockaddr_in6)) + __array(__u8, daddr, sizeof(struct sockaddr_in6)) + ), + + TP_fast_assign( + __entry->skbaddr = skb; + __entry->skaddr = sk; + /* Zero means unknown state. */ + __entry->state = sk ? sk->sk_state : 0; + + memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); + memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); + + if (sk && sk_fullsock(sk)) { + const struct inet_sock *inet = inet_sk(sk); + + TP_STORE_ADDR_PORTS(__entry, inet, sk); + } else if (skb) { + const struct tcphdr *th = (const struct tcphdr *)skb->data; + /* + * We should reverse the 4-tuple of skb, so later + * it can print the right flow direction of rst. + */ + TP_STORE_ADDR_PORTS_SKB(skb, th, entry->daddr, entry->saddr); + } + __entry->reason = reason; + ), + + TP_printk("skbaddr=%p skaddr=%p src=%pISpc dest=%pISpc state=%s reason=%s", + __entry->skbaddr, __entry->skaddr, + __entry->saddr, __entry->daddr, + __entry->state ? show_tcp_state_name(__entry->state) : "UNKNOWN", + __print_symbolic(__entry->reason, DEFINE_RST_REASON(FN, FNe))) ); +#undef FN +#undef FNe + /* * tcp event with arguments sk * @@ -302,48 +327,6 @@ TRACE_EVENT(tcp_probe, __entry->skbaddr, __entry->skaddr) ); -#define TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb) \ - do { \ - const struct tcphdr *th = (const struct tcphdr *)skb->data; \ - struct sockaddr_in *v4 = (void *)__entry->saddr; \ - \ - v4->sin_family = AF_INET; \ - v4->sin_port = th->source; \ - v4->sin_addr.s_addr = ip_hdr(skb)->saddr; \ - v4 = (void *)__entry->daddr; \ - v4->sin_family = AF_INET; \ - v4->sin_port = th->dest; \ - v4->sin_addr.s_addr = ip_hdr(skb)->daddr; \ - } while (0) - -#if IS_ENABLED(CONFIG_IPV6) - -#define TP_STORE_ADDR_PORTS_SKB(__entry, skb) \ - do { \ - const struct iphdr *iph = ip_hdr(skb); \ - \ - if (iph->version == 6) { \ - const struct tcphdr *th = (const struct tcphdr *)skb->data; \ - struct sockaddr_in6 *v6 = (void *)__entry->saddr; \ - \ - v6->sin6_family = AF_INET6; \ - v6->sin6_port = th->source; \ - v6->sin6_addr = ipv6_hdr(skb)->saddr; \ - v6 = (void *)__entry->daddr; \ - v6->sin6_family = AF_INET6; \ - v6->sin6_port = th->dest; \ - v6->sin6_addr = ipv6_hdr(skb)->daddr; \ - } else \ - TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb); \ - } while (0) - -#else - -#define TP_STORE_ADDR_PORTS_SKB(__entry, skb) \ - TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb) - -#endif - /* * tcp event with only skb */ @@ -360,12 +343,13 @@ DECLARE_EVENT_CLASS(tcp_event_skb, ), TP_fast_assign( + const struct tcphdr *th = (const struct tcphdr *)skb->data; __entry->skbaddr = skb; memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); - TP_STORE_ADDR_PORTS_SKB(__entry, skb); + TP_STORE_ADDR_PORTS_SKB(skb, th, __entry->saddr, __entry->daddr); ), TP_printk("skbaddr=%p src=%pISpc dest=%pISpc", diff --git a/include/trace/events/udp.h b/include/trace/events/udp.h index 336fe272889f..6142be4068e2 100644 --- a/include/trace/events/udp.h +++ b/include/trace/events/udp.h @@ -7,24 +7,43 @@ #include <linux/udp.h> #include <linux/tracepoint.h> +#include <trace/events/net_probe_common.h> TRACE_EVENT(udp_fail_queue_rcv_skb, - TP_PROTO(int rc, struct sock *sk), + TP_PROTO(int rc, struct sock *sk, struct sk_buff *skb), - TP_ARGS(rc, sk), + TP_ARGS(rc, sk, skb), TP_STRUCT__entry( __field(int, rc) - __field(__u16, lport) + + __field(__u16, sport) + __field(__u16, dport) + __field(__u16, family) + __array(__u8, saddr, sizeof(struct sockaddr_in6)) + __array(__u8, daddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( + const struct udphdr *uh = (const struct udphdr *)udp_hdr(skb); + __entry->rc = rc; - __entry->lport = inet_sk(sk)->inet_num; + + /* for filtering use */ + __entry->sport = ntohs(uh->source); + __entry->dport = ntohs(uh->dest); + __entry->family = sk->sk_family; + + memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); + memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); + + TP_STORE_ADDR_PORTS_SKB(skb, uh, __entry->saddr, __entry->daddr); ), - TP_printk("rc=%d port=%hu", __entry->rc, __entry->lport) + TP_printk("rc=%d family=%s src=%pISpc dest=%pISpc", __entry->rc, + show_family_name(__entry->family), + __entry->saddr, __entry->daddr) ); #endif /* _TRACE_UDP_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3c42b9f1bada..90706a47f6ff 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1115,6 +1115,7 @@ enum bpf_attach_type { BPF_CGROUP_UNIX_GETSOCKNAME, BPF_NETKIT_PRIMARY, BPF_NETKIT_PEER, + BPF_TRACE_KPROBE_SESSION, __MAX_BPF_ATTACH_TYPE }; @@ -1135,6 +1136,7 @@ enum bpf_link_type { BPF_LINK_TYPE_TCX = 11, BPF_LINK_TYPE_UPROBE_MULTI = 12, BPF_LINK_TYPE_NETKIT = 13, + BPF_LINK_TYPE_SOCKMAP = 14, __MAX_BPF_LINK_TYPE, }; @@ -1662,8 +1664,10 @@ union bpf_attr { } query; struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ - __u64 name; - __u32 prog_fd; + __u64 name; + __u32 prog_fd; + __u32 :32; + __aligned_u64 cookie; } raw_tracepoint; struct { /* anonymous struct for BPF_BTF_LOAD */ @@ -3392,6 +3396,10 @@ union bpf_attr { * for the nexthop. If the src addr cannot be derived, * **BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this * case, *params*->dmac and *params*->smac are not set either. + * **BPF_FIB_LOOKUP_MARK** + * Use the mark present in *params*->mark for the fib lookup. + * This option should not be used with BPF_FIB_LOOKUP_DIRECT, + * as it only has meaning for full lookups. * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -5020,7 +5028,7 @@ union bpf_attr { * bytes will be copied to *dst* * Return * The **hash_algo** is returned on success, - * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if + * **-EOPNOTSUPP** if IMA is disabled or **-EINVAL** if * invalid arguments are passed. * * struct socket *bpf_sock_from_file(struct file *file) @@ -5506,7 +5514,7 @@ union bpf_attr { * bytes will be copied to *dst* * Return * The **hash_algo** is returned on success, - * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if + * **-EOPNOTSUPP** if the hash calculation failed or **-EINVAL** if * invalid arguments are passed. * * void *bpf_kptr_xchg(void *map_value, void *ptr) @@ -6718,6 +6726,10 @@ struct bpf_link_info { __u32 ifindex; __u32 attach_type; } netkit; + struct { + __u32 map_id; + __u32 attach_type; + } sockmap; }; } __attribute__((aligned(8))); @@ -6936,6 +6948,8 @@ enum { * socket transition to LISTEN state. */ BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. + * Arg1: measured RTT input (mrtt) + * Arg2: updated srtt */ BPF_SOCK_OPS_PARSE_HDR_OPT_CB, /* Parse the header option. * It will be called to handle @@ -7118,6 +7132,7 @@ enum { BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), BPF_FIB_LOOKUP_TBID = (1U << 3), BPF_FIB_LOOKUP_SRC = (1U << 4), + BPF_FIB_LOOKUP_MARK = (1U << 5), }; enum { @@ -7150,7 +7165,7 @@ struct bpf_fib_lookup { /* output: MTU value */ __u16 mtu_result; - }; + } __attribute__((packed, aligned(2))); /* input: L3 device index for lookup * output: device index from FIB lookup */ @@ -7195,8 +7210,19 @@ struct bpf_fib_lookup { __u32 tbid; }; - __u8 smac[6]; /* ETH_ALEN */ - __u8 dmac[6]; /* ETH_ALEN */ + union { + /* input */ + struct { + __u32 mark; /* policy routing */ + /* 2 4-byte holes for input */ + }; + + /* output: source and dest mac */ + struct { + __u8 smac[6]; /* ETH_ALEN */ + __u8 dmac[6]; /* ETH_ALEN */ + }; + }; }; struct bpf_redir_neigh { @@ -7283,6 +7309,10 @@ struct bpf_timer { __u64 __opaque[2]; } __attribute__((aligned(8))); +struct bpf_wq { + __u64 __opaque[2]; +} __attribute__((aligned(8))); + struct bpf_dynptr { __u64 __opaque[2]; } __attribute__((aligned(8))); diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 2da0c7eb6710..9401aa343673 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -686,6 +686,7 @@ enum devlink_port_function_attr { DEVLINK_PORT_FN_ATTR_OPSTATE, /* u8 */ DEVLINK_PORT_FN_ATTR_CAPS, /* bitfield32 */ DEVLINK_PORT_FN_ATTR_DEVLINK, /* nested */ + DEVLINK_PORT_FN_ATTR_MAX_IO_EQS, /* u32 */ __DEVLINK_PORT_FUNCTION_ATTR_MAX, DEVLINK_PORT_FUNCTION_ATTR_MAX = __DEVLINK_PORT_FUNCTION_ATTR_MAX - 1 diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 11fc18988bc2..8733a3117902 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -753,6 +753,61 @@ enum ethtool_module_power_mode { }; /** + * enum ethtool_pse_types - Types of PSE controller. + * @ETHTOOL_PSE_UNKNOWN: Type of PSE controller is unknown + * @ETHTOOL_PSE_PODL: PSE controller which support PoDL + * @ETHTOOL_PSE_C33: PSE controller which support Clause 33 (PoE) + */ +enum ethtool_pse_types { + ETHTOOL_PSE_UNKNOWN = 1 << 0, + ETHTOOL_PSE_PODL = 1 << 1, + ETHTOOL_PSE_C33 = 1 << 2, +}; + +/** + * enum ethtool_c33_pse_admin_state - operational state of the PoDL PSE + * functions. IEEE 802.3-2022 30.9.1.1.2 aPSEAdminState + * @ETHTOOL_C33_PSE_ADMIN_STATE_UNKNOWN: state of PSE functions is unknown + * @ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED: PSE functions are disabled + * @ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED: PSE functions are enabled + */ +enum ethtool_c33_pse_admin_state { + ETHTOOL_C33_PSE_ADMIN_STATE_UNKNOWN = 1, + ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED, + ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED, +}; + +/** + * enum ethtool_c33_pse_pw_d_status - power detection status of the PSE. + * IEEE 802.3-2022 30.9.1.1.3 aPoDLPSEPowerDetectionStatus: + * @ETHTOOL_C33_PSE_PW_D_STATUS_UNKNOWN: PSE status is unknown + * @ETHTOOL_C33_PSE_PW_D_STATUS_DISABLED: The enumeration "disabled" + * indicates that the PSE State diagram is in the state DISABLED. + * @ETHTOOL_C33_PSE_PW_D_STATUS_SEARCHING: The enumeration "searching" + * indicates the PSE State diagram is in a state other than those + * listed. + * @ETHTOOL_C33_PSE_PW_D_STATUS_DELIVERING: The enumeration + * "deliveringPower" indicates that the PSE State diagram is in the + * state POWER_ON. + * @ETHTOOL_C33_PSE_PW_D_STATUS_TEST: The enumeration "test" indicates that + * the PSE State diagram is in the state TEST_MODE. + * @ETHTOOL_C33_PSE_PW_D_STATUS_FAULT: The enumeration "fault" indicates that + * the PSE State diagram is in the state TEST_ERROR. + * @ETHTOOL_C33_PSE_PW_D_STATUS_OTHERFAULT: The enumeration "otherFault" + * indicates that the PSE State diagram is in the state IDLE due to + * the variable error_condition = true. + */ +enum ethtool_c33_pse_pw_d_status { + ETHTOOL_C33_PSE_PW_D_STATUS_UNKNOWN = 1, + ETHTOOL_C33_PSE_PW_D_STATUS_DISABLED, + ETHTOOL_C33_PSE_PW_D_STATUS_SEARCHING, + ETHTOOL_C33_PSE_PW_D_STATUS_DELIVERING, + ETHTOOL_C33_PSE_PW_D_STATUS_TEST, + ETHTOOL_C33_PSE_PW_D_STATUS_FAULT, + ETHTOOL_C33_PSE_PW_D_STATUS_OTHERFAULT, +}; + +/** * enum ethtool_podl_pse_admin_state - operational state of the PoDL PSE * functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState * @ETHTOOL_PODL_PSE_ADMIN_STATE_UNKNOWN: state of PoDL PSE functions are diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 3f89074aa06c..b49b804b9495 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -117,12 +117,11 @@ enum { /* request header */ -/* use compact bitsets in reply */ -#define ETHTOOL_FLAG_COMPACT_BITSETS (1 << 0) -/* provide optional reply for SET or ACT requests */ -#define ETHTOOL_FLAG_OMIT_REPLY (1 << 1) -/* request statistics, if supported by the driver */ -#define ETHTOOL_FLAG_STATS (1 << 2) +enum ethtool_header_flags { + ETHTOOL_FLAG_COMPACT_BITSETS = 1 << 0, /* use compact bitsets in reply */ + ETHTOOL_FLAG_OMIT_REPLY = 1 << 1, /* provide optional reply for SET or ACT requests */ + ETHTOOL_FLAG_STATS = 1 << 2, /* request statistics, if supported by the driver */ +}; #define ETHTOOL_FLAG_ALL (ETHTOOL_FLAG_COMPACT_BITSETS | \ ETHTOOL_FLAG_OMIT_REPLY | \ @@ -478,12 +477,26 @@ enum { ETHTOOL_A_TSINFO_TX_TYPES, /* bitset */ ETHTOOL_A_TSINFO_RX_FILTERS, /* bitset */ ETHTOOL_A_TSINFO_PHC_INDEX, /* u32 */ + ETHTOOL_A_TSINFO_STATS, /* nest - _A_TSINFO_STAT */ /* add new constants above here */ __ETHTOOL_A_TSINFO_CNT, ETHTOOL_A_TSINFO_MAX = (__ETHTOOL_A_TSINFO_CNT - 1) }; +enum { + ETHTOOL_A_TS_STAT_UNSPEC, + + ETHTOOL_A_TS_STAT_TX_PKTS, /* uint */ + ETHTOOL_A_TS_STAT_TX_LOST, /* uint */ + ETHTOOL_A_TS_STAT_TX_ERR, /* uint */ + + /* add new constants above here */ + __ETHTOOL_A_TS_STAT_CNT, + ETHTOOL_A_TS_STAT_MAX = (__ETHTOOL_A_TS_STAT_CNT - 1) + +}; + /* PHC VCLOCKS */ enum { @@ -515,6 +528,10 @@ enum { ETHTOOL_A_CABLE_RESULT_CODE_OPEN, ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT, ETHTOOL_A_CABLE_RESULT_CODE_CROSS_SHORT, + /* detected reflection caused by the impedance discontinuity between + * a regular 100 Ohm cable and a part with the abnormal impedance value + */ + ETHTOOL_A_CABLE_RESULT_CODE_IMPEDANCE_MISMATCH, }; enum { @@ -895,6 +912,9 @@ enum { ETHTOOL_A_PODL_PSE_ADMIN_STATE, /* u32 */ ETHTOOL_A_PODL_PSE_ADMIN_CONTROL, /* u32 */ ETHTOOL_A_PODL_PSE_PW_D_STATUS, /* u32 */ + ETHTOOL_A_C33_PSE_ADMIN_STATE, /* u32 */ + ETHTOOL_A_C33_PSE_ADMIN_CONTROL, /* u32 */ + ETHTOOL_A_C33_PSE_PW_D_STATUS, /* u32 */ /* add new constants above here */ __ETHTOOL_A_PSE_CNT, diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h index 3dcdb9e33cba..40f5388d6de0 100644 --- a/include/uapi/linux/gtp.h +++ b/include/uapi/linux/gtp.h @@ -31,6 +31,9 @@ enum gtp_attrs { GTPA_I_TEI, /* for GTPv1 only */ GTPA_O_TEI, /* for GTPv1 only */ GTPA_PAD, + GTPA_PEER_ADDR6, + GTPA_MS_ADDR6, + GTPA_FAMILY, __GTPA_MAX, }; #define GTPA_MAX (__GTPA_MAX - 1) diff --git a/include/uapi/linux/icmpv6.h b/include/uapi/linux/icmpv6.h index ecaece3af38d..4eaab89e2856 100644 --- a/include/uapi/linux/icmpv6.h +++ b/include/uapi/linux/icmpv6.h @@ -112,6 +112,7 @@ struct icmp6hdr { #define ICMPV6_MOBILE_PREFIX_ADV 147 #define ICMPV6_MRDISC_ADV 151 +#define ICMPV6_MRDISC_SOL 152 #define ICMPV6_MSG_MAX 255 diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index ffa637b38c93..6dc258993b17 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1466,6 +1466,8 @@ enum { IFLA_GTP_ROLE, IFLA_GTP_CREATE_SOCKETS, IFLA_GTP_RESTART_COUNT, + IFLA_GTP_LOCAL, + IFLA_GTP_LOCAL6, __IFLA_GTP_MAX, }; #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) @@ -1771,6 +1773,7 @@ enum { IFLA_HSR_PROTOCOL, /* Indicate different protocol than * HSR. For example PRP. */ + IFLA_HSR_INTERLINK, /* HSR interlink network device */ __IFLA_HSR_MAX, }; diff --git a/include/uapi/linux/if_team.h b/include/uapi/linux/if_team.h index 13c61fecb78b..a5c06243a435 100644 --- a/include/uapi/linux/if_team.h +++ b/include/uapi/linux/if_team.h @@ -1,108 +1,78 @@ -/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ -/* - * include/linux/if_team.h - Network team device driver header - * Copyright (c) 2011 Jiri Pirko <jpirko@redhat.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/team.yaml */ +/* YNL-GEN uapi header */ -#ifndef _UAPI_LINUX_IF_TEAM_H_ -#define _UAPI_LINUX_IF_TEAM_H_ +#ifndef _UAPI_LINUX_IF_TEAM_H +#define _UAPI_LINUX_IF_TEAM_H +#define TEAM_GENL_NAME "team" +#define TEAM_GENL_VERSION 1 -#define TEAM_STRING_MAX_LEN 32 - -/********************************** - * NETLINK_GENERIC netlink family. - **********************************/ - -enum { - TEAM_CMD_NOOP, - TEAM_CMD_OPTIONS_SET, - TEAM_CMD_OPTIONS_GET, - TEAM_CMD_PORT_LIST_GET, - - __TEAM_CMD_MAX, - TEAM_CMD_MAX = (__TEAM_CMD_MAX - 1), -}; +#define TEAM_STRING_MAX_LEN 32 +#define TEAM_GENL_CHANGE_EVENT_MC_GRP_NAME "change_event" enum { TEAM_ATTR_UNSPEC, - TEAM_ATTR_TEAM_IFINDEX, /* u32 */ - TEAM_ATTR_LIST_OPTION, /* nest */ - TEAM_ATTR_LIST_PORT, /* nest */ + TEAM_ATTR_TEAM_IFINDEX, + TEAM_ATTR_LIST_OPTION, + TEAM_ATTR_LIST_PORT, __TEAM_ATTR_MAX, - TEAM_ATTR_MAX = __TEAM_ATTR_MAX - 1, + TEAM_ATTR_MAX = (__TEAM_ATTR_MAX - 1) }; -/* Nested layout of get/set msg: - * - * [TEAM_ATTR_LIST_OPTION] - * [TEAM_ATTR_ITEM_OPTION] - * [TEAM_ATTR_OPTION_*], ... - * [TEAM_ATTR_ITEM_OPTION] - * [TEAM_ATTR_OPTION_*], ... - * ... - * [TEAM_ATTR_LIST_PORT] - * [TEAM_ATTR_ITEM_PORT] - * [TEAM_ATTR_PORT_*], ... - * [TEAM_ATTR_ITEM_PORT] - * [TEAM_ATTR_PORT_*], ... - * ... - */ - enum { TEAM_ATTR_ITEM_OPTION_UNSPEC, - TEAM_ATTR_ITEM_OPTION, /* nest */ + TEAM_ATTR_ITEM_OPTION, __TEAM_ATTR_ITEM_OPTION_MAX, - TEAM_ATTR_ITEM_OPTION_MAX = __TEAM_ATTR_ITEM_OPTION_MAX - 1, + TEAM_ATTR_ITEM_OPTION_MAX = (__TEAM_ATTR_ITEM_OPTION_MAX - 1) }; enum { TEAM_ATTR_OPTION_UNSPEC, - TEAM_ATTR_OPTION_NAME, /* string */ - TEAM_ATTR_OPTION_CHANGED, /* flag */ - TEAM_ATTR_OPTION_TYPE, /* u8 */ - TEAM_ATTR_OPTION_DATA, /* dynamic */ - TEAM_ATTR_OPTION_REMOVED, /* flag */ - TEAM_ATTR_OPTION_PORT_IFINDEX, /* u32 */ /* for per-port options */ - TEAM_ATTR_OPTION_ARRAY_INDEX, /* u32 */ /* for array options */ + TEAM_ATTR_OPTION_NAME, + TEAM_ATTR_OPTION_CHANGED, + TEAM_ATTR_OPTION_TYPE, + TEAM_ATTR_OPTION_DATA, + TEAM_ATTR_OPTION_REMOVED, + TEAM_ATTR_OPTION_PORT_IFINDEX, + TEAM_ATTR_OPTION_ARRAY_INDEX, __TEAM_ATTR_OPTION_MAX, - TEAM_ATTR_OPTION_MAX = __TEAM_ATTR_OPTION_MAX - 1, + TEAM_ATTR_OPTION_MAX = (__TEAM_ATTR_OPTION_MAX - 1) }; enum { TEAM_ATTR_ITEM_PORT_UNSPEC, - TEAM_ATTR_ITEM_PORT, /* nest */ + TEAM_ATTR_ITEM_PORT, __TEAM_ATTR_ITEM_PORT_MAX, - TEAM_ATTR_ITEM_PORT_MAX = __TEAM_ATTR_ITEM_PORT_MAX - 1, + TEAM_ATTR_ITEM_PORT_MAX = (__TEAM_ATTR_ITEM_PORT_MAX - 1) }; enum { TEAM_ATTR_PORT_UNSPEC, - TEAM_ATTR_PORT_IFINDEX, /* u32 */ - TEAM_ATTR_PORT_CHANGED, /* flag */ - TEAM_ATTR_PORT_LINKUP, /* flag */ - TEAM_ATTR_PORT_SPEED, /* u32 */ - TEAM_ATTR_PORT_DUPLEX, /* u8 */ - TEAM_ATTR_PORT_REMOVED, /* flag */ + TEAM_ATTR_PORT_IFINDEX, + TEAM_ATTR_PORT_CHANGED, + TEAM_ATTR_PORT_LINKUP, + TEAM_ATTR_PORT_SPEED, + TEAM_ATTR_PORT_DUPLEX, + TEAM_ATTR_PORT_REMOVED, __TEAM_ATTR_PORT_MAX, - TEAM_ATTR_PORT_MAX = __TEAM_ATTR_PORT_MAX - 1, + TEAM_ATTR_PORT_MAX = (__TEAM_ATTR_PORT_MAX - 1) }; -/* - * NETLINK_GENERIC related info - */ -#define TEAM_GENL_NAME "team" -#define TEAM_GENL_VERSION 0x1 -#define TEAM_GENL_CHANGE_EVENT_MC_GRP_NAME "change_event" +enum { + TEAM_CMD_NOOP, + TEAM_CMD_OPTIONS_SET, + TEAM_CMD_OPTIONS_GET, + TEAM_CMD_PORT_LIST_GET, + + __TEAM_CMD_MAX, + TEAM_CMD_MAX = (__TEAM_CMD_MAX - 1) +}; -#endif /* _UAPI_LINUX_IF_TEAM_H_ */ +#endif /* _UAPI_LINUX_IF_TEAM_H */ diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 102119628ff5..e1a246dd8c62 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -161,6 +161,14 @@ enum { #define IFLA_VTI_MAX (__IFLA_VTI_MAX - 1) +#ifndef __KERNEL__ +/* Historically, tunnel flags have been defined as __be16 and now there are + * no free bits left. It is strongly advised to switch the already existing + * userspace code to the new *_BIT definitions from down below, as __be16 + * can't be simply cast to a wider type on LE systems. All new flags and + * code must use *_BIT only. + */ + #define TUNNEL_CSUM __cpu_to_be16(0x01) #define TUNNEL_ROUTING __cpu_to_be16(0x02) #define TUNNEL_KEY __cpu_to_be16(0x04) @@ -181,5 +189,33 @@ enum { #define TUNNEL_OPTIONS_PRESENT \ (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT | TUNNEL_ERSPAN_OPT | \ TUNNEL_GTP_OPT) +#endif + +enum { + IP_TUNNEL_CSUM_BIT = 0U, + IP_TUNNEL_ROUTING_BIT, + IP_TUNNEL_KEY_BIT, + IP_TUNNEL_SEQ_BIT, + IP_TUNNEL_STRICT_BIT, + IP_TUNNEL_REC_BIT, + IP_TUNNEL_VERSION_BIT, + IP_TUNNEL_NO_KEY_BIT, + IP_TUNNEL_DONT_FRAGMENT_BIT, + IP_TUNNEL_OAM_BIT, + IP_TUNNEL_CRIT_OPT_BIT, + IP_TUNNEL_GENEVE_OPT_BIT, /* OPTIONS_PRESENT */ + IP_TUNNEL_VXLAN_OPT_BIT, /* OPTIONS_PRESENT */ + IP_TUNNEL_NOCACHE_BIT, + IP_TUNNEL_ERSPAN_OPT_BIT, /* OPTIONS_PRESENT */ + IP_TUNNEL_GTP_OPT_BIT, /* OPTIONS_PRESENT */ + + IP_TUNNEL_VTI_BIT, + IP_TUNNEL_SIT_ISATAP_BIT = IP_TUNNEL_VTI_BIT, + + /* Flags starting from here are not available via the old UAPI */ + IP_TUNNEL_PFCP_OPT_BIT, /* OPTIONS_PRESENT */ + + __IP_TUNNEL_FLAG_NUM, +}; #endif /* _UAPI_IF_TUNNEL_H_ */ diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 74cfe496891e..67d015df8893 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -58,6 +58,10 @@ struct mptcp_info { __u64 mptcpi_bytes_received; __u64 mptcpi_bytes_acked; __u8 mptcpi_subflows_total; + __u8 reserved[3]; + __u32 mptcpi_last_data_sent; + __u32 mptcpi_last_data_recv; + __u32 mptcpi_last_ack_recv; }; /* MPTCP Reset reason codes, rfc8684 */ diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index bb65ee840cda..a8188202413e 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -146,6 +146,27 @@ enum { NETDEV_A_QSTATS_TX_PACKETS, NETDEV_A_QSTATS_TX_BYTES, NETDEV_A_QSTATS_RX_ALLOC_FAIL, + NETDEV_A_QSTATS_RX_HW_DROPS, + NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS, + NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY, + NETDEV_A_QSTATS_RX_CSUM_NONE, + NETDEV_A_QSTATS_RX_CSUM_BAD, + NETDEV_A_QSTATS_RX_HW_GRO_PACKETS, + NETDEV_A_QSTATS_RX_HW_GRO_BYTES, + NETDEV_A_QSTATS_RX_HW_GRO_WIRE_PACKETS, + NETDEV_A_QSTATS_RX_HW_GRO_WIRE_BYTES, + NETDEV_A_QSTATS_RX_HW_DROP_RATELIMITS, + NETDEV_A_QSTATS_TX_HW_DROPS, + NETDEV_A_QSTATS_TX_HW_DROP_ERRORS, + NETDEV_A_QSTATS_TX_CSUM_NONE, + NETDEV_A_QSTATS_TX_NEEDS_CSUM, + NETDEV_A_QSTATS_TX_HW_GSO_PACKETS, + NETDEV_A_QSTATS_TX_HW_GSO_BYTES, + NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS, + NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES, + NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS, + NETDEV_A_QSTATS_TX_STOP, + NETDEV_A_QSTATS_TX_WAKE, __NETDEV_A_QSTATS_MAX, NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index f23ecbdd84a2..f917bc6c9b6f 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -413,8 +413,8 @@ * are like for %NL80211_CMD_SET_BEACON, and additionally parameters that * do not change are used, these include %NL80211_ATTR_BEACON_INTERVAL, * %NL80211_ATTR_DTIM_PERIOD, %NL80211_ATTR_SSID, - * %NL80211_ATTR_HIDDEN_SSID, %NL80211_ATTR_CIPHERS_PAIRWISE, - * %NL80211_ATTR_CIPHER_GROUP, %NL80211_ATTR_WPA_VERSIONS, + * %NL80211_ATTR_HIDDEN_SSID, %NL80211_ATTR_CIPHER_SUITES_PAIRWISE, + * %NL80211_ATTR_CIPHER_SUITE_GROUP, %NL80211_ATTR_WPA_VERSIONS, * %NL80211_ATTR_AKM_SUITES, %NL80211_ATTR_PRIVACY, * %NL80211_ATTR_AUTH_TYPE, %NL80211_ATTR_INACTIVITY_TIMEOUT, * %NL80211_ATTR_ACL_POLICY and %NL80211_ATTR_MAC_ADDRS. @@ -442,20 +442,15 @@ * stations connected and using at least that link as one of its links. * * @NL80211_CMD_GET_MPATH: Get mesh path attributes for mesh path to - * destination %NL80211_ATTR_MAC on the interface identified by - * %NL80211_ATTR_IFINDEX. + * destination %NL80211_ATTR_MAC on the interface identified by + * %NL80211_ATTR_IFINDEX. * @NL80211_CMD_SET_MPATH: Set mesh path attributes for mesh path to - * destination %NL80211_ATTR_MAC on the interface identified by - * %NL80211_ATTR_IFINDEX. + * destination %NL80211_ATTR_MAC on the interface identified by + * %NL80211_ATTR_IFINDEX. * @NL80211_CMD_NEW_MPATH: Create a new mesh path for the destination given by * %NL80211_ATTR_MAC via %NL80211_ATTR_MPATH_NEXT_HOP. * @NL80211_CMD_DEL_MPATH: Delete a mesh path to the destination given by * %NL80211_ATTR_MAC. - * @NL80211_CMD_NEW_PATH: Add a mesh path with given attributes to the - * interface identified by %NL80211_ATTR_IFINDEX. - * @NL80211_CMD_DEL_PATH: Remove a mesh path identified by %NL80211_ATTR_MAC - * or, if no MAC address given, all mesh paths, on the interface identified - * by %NL80211_ATTR_IFINDEX. * @NL80211_CMD_SET_BSS: Set BSS attributes for BSS identified by * %NL80211_ATTR_IFINDEX. * @@ -476,15 +471,15 @@ * after being queried by the kernel. CRDA replies by sending a regulatory * domain structure which consists of %NL80211_ATTR_REG_ALPHA set to our * current alpha2 if it found a match. It also provides - * NL80211_ATTR_REG_RULE_FLAGS, and a set of regulatory rules. Each - * regulatory rule is a nested set of attributes given by - * %NL80211_ATTR_REG_RULE_FREQ_[START|END] and - * %NL80211_ATTR_FREQ_RANGE_MAX_BW with an attached power rule given by - * %NL80211_ATTR_REG_RULE_POWER_MAX_ANT_GAIN and - * %NL80211_ATTR_REG_RULE_POWER_MAX_EIRP. + * NL80211_ATTR_REG_RULE_FLAGS, and a set of regulatory rules. Each + * regulatory rule is a nested set of attributes given by + * %NL80211_ATTR_REG_RULE_FREQ_[START|END] and + * %NL80211_ATTR_FREQ_RANGE_MAX_BW with an attached power rule given by + * %NL80211_ATTR_REG_RULE_POWER_MAX_ANT_GAIN and + * %NL80211_ATTR_REG_RULE_POWER_MAX_EIRP. * @NL80211_CMD_REQ_SET_REG: ask the wireless core to set the regulatory domain - * to the specified ISO/IEC 3166-1 alpha2 country code. The core will - * store this as a valid request and then query userspace for it. + * to the specified ISO/IEC 3166-1 alpha2 country code. The core will + * store this as a valid request and then query userspace for it. * * @NL80211_CMD_GET_MESH_CONFIG: Get mesh networking properties for the * interface identified by %NL80211_ATTR_IFINDEX @@ -574,31 +569,31 @@ * @NL80211_CMD_FLUSH_PMKSA: Flush all PMKSA cache entries. * * @NL80211_CMD_REG_CHANGE: indicates to userspace the regulatory domain - * has been changed and provides details of the request information - * that caused the change such as who initiated the regulatory request - * (%NL80211_ATTR_REG_INITIATOR), the wiphy_idx - * (%NL80211_ATTR_REG_ALPHA2) on which the request was made from if - * the initiator was %NL80211_REGDOM_SET_BY_COUNTRY_IE or - * %NL80211_REGDOM_SET_BY_DRIVER, the type of regulatory domain - * set (%NL80211_ATTR_REG_TYPE), if the type of regulatory domain is - * %NL80211_REG_TYPE_COUNTRY the alpha2 to which we have moved on - * to (%NL80211_ATTR_REG_ALPHA2). + * has been changed and provides details of the request information + * that caused the change such as who initiated the regulatory request + * (%NL80211_ATTR_REG_INITIATOR), the wiphy_idx + * (%NL80211_ATTR_REG_ALPHA2) on which the request was made from if + * the initiator was %NL80211_REGDOM_SET_BY_COUNTRY_IE or + * %NL80211_REGDOM_SET_BY_DRIVER, the type of regulatory domain + * set (%NL80211_ATTR_REG_TYPE), if the type of regulatory domain is + * %NL80211_REG_TYPE_COUNTRY the alpha2 to which we have moved on + * to (%NL80211_ATTR_REG_ALPHA2). * @NL80211_CMD_REG_BEACON_HINT: indicates to userspace that an AP beacon - * has been found while world roaming thus enabling active scan or - * any mode of operation that initiates TX (beacons) on a channel - * where we would not have been able to do either before. As an example - * if you are world roaming (regulatory domain set to world or if your - * driver is using a custom world roaming regulatory domain) and while - * doing a passive scan on the 5 GHz band you find an AP there (if not - * on a DFS channel) you will now be able to actively scan for that AP - * or use AP mode on your card on that same channel. Note that this will - * never be used for channels 1-11 on the 2 GHz band as they are always - * enabled world wide. This beacon hint is only sent if your device had - * either disabled active scanning or beaconing on a channel. We send to - * userspace the wiphy on which we removed a restriction from - * (%NL80211_ATTR_WIPHY) and the channel on which this occurred - * before (%NL80211_ATTR_FREQ_BEFORE) and after (%NL80211_ATTR_FREQ_AFTER) - * the beacon hint was processed. + * has been found while world roaming thus enabling active scan or + * any mode of operation that initiates TX (beacons) on a channel + * where we would not have been able to do either before. As an example + * if you are world roaming (regulatory domain set to world or if your + * driver is using a custom world roaming regulatory domain) and while + * doing a passive scan on the 5 GHz band you find an AP there (if not + * on a DFS channel) you will now be able to actively scan for that AP + * or use AP mode on your card on that same channel. Note that this will + * never be used for channels 1-11 on the 2 GHz band as they are always + * enabled world wide. This beacon hint is only sent if your device had + * either disabled active scanning or beaconing on a channel. We send to + * userspace the wiphy on which we removed a restriction from + * (%NL80211_ATTR_WIPHY) and the channel on which this occurred + * before (%NL80211_ATTR_FREQ_BEFORE) and after (%NL80211_ATTR_FREQ_AFTER) + * the beacon hint was processed. * * @NL80211_CMD_AUTHENTICATE: authentication request and notification. * This command is used both as a command (request to authenticate) and @@ -1120,7 +1115,7 @@ * current configuration is not changed. If it is present but * set to zero, the configuration is changed to don't-care * (i.e. the device can decide what to do). - * @NL80211_CMD_NAN_FUNC_MATCH: Notification sent when a match is reported. + * @NL80211_CMD_NAN_MATCH: Notification sent when a match is reported. * This will contain a %NL80211_ATTR_NAN_MATCH nested attribute and * %NL80211_ATTR_COOKIE. * @@ -1715,21 +1710,21 @@ enum nl80211_commands { * (see &enum nl80211_plink_action). * @NL80211_ATTR_MPATH_NEXT_HOP: MAC address of the next hop for a mesh path. * @NL80211_ATTR_MPATH_INFO: information about a mesh_path, part of mesh path - * info given for %NL80211_CMD_GET_MPATH, nested attribute described at + * info given for %NL80211_CMD_GET_MPATH, nested attribute described at * &enum nl80211_mpath_info. * * @NL80211_ATTR_MNTR_FLAGS: flags, nested element with NLA_FLAG attributes of * &enum nl80211_mntr_flags. * * @NL80211_ATTR_REG_ALPHA2: an ISO-3166-alpha2 country code for which the - * current regulatory domain should be set to or is already set to. - * For example, 'CR', for Costa Rica. This attribute is used by the kernel - * to query the CRDA to retrieve one regulatory domain. This attribute can - * also be used by userspace to query the kernel for the currently set - * regulatory domain. We chose an alpha2 as that is also used by the - * IEEE-802.11 country information element to identify a country. - * Users can also simply ask the wireless core to set regulatory domain - * to a specific alpha2. + * current regulatory domain should be set to or is already set to. + * For example, 'CR', for Costa Rica. This attribute is used by the kernel + * to query the CRDA to retrieve one regulatory domain. This attribute can + * also be used by userspace to query the kernel for the currently set + * regulatory domain. We chose an alpha2 as that is also used by the + * IEEE-802.11 country information element to identify a country. + * Users can also simply ask the wireless core to set regulatory domain + * to a specific alpha2. * @NL80211_ATTR_REG_RULES: a nested array of regulatory domain regulatory * rules. * @@ -1772,9 +1767,9 @@ enum nl80211_commands { * @NL80211_ATTR_BSS: scan result BSS * * @NL80211_ATTR_REG_INITIATOR: indicates who requested the regulatory domain - * currently in effect. This could be any of the %NL80211_REGDOM_SET_BY_* + * currently in effect. This could be any of the %NL80211_REGDOM_SET_BY_* * @NL80211_ATTR_REG_TYPE: indicates the type of the regulatory domain currently - * set. This can be one of the nl80211_reg_type (%NL80211_REGDOM_TYPE_*) + * set. This can be one of the nl80211_reg_type (%NL80211_REGDOM_TYPE_*) * * @NL80211_ATTR_SUPPORTED_COMMANDS: wiphy attribute that specifies * an array of command numbers (i.e. a mapping index to command number) @@ -1793,15 +1788,15 @@ enum nl80211_commands { * a u32 * * @NL80211_ATTR_FREQ_BEFORE: A channel which has suffered a regulatory change - * due to considerations from a beacon hint. This attribute reflects - * the state of the channel _before_ the beacon hint processing. This - * attributes consists of a nested attribute containing - * NL80211_FREQUENCY_ATTR_* + * due to considerations from a beacon hint. This attribute reflects + * the state of the channel _before_ the beacon hint processing. This + * attributes consists of a nested attribute containing + * NL80211_FREQUENCY_ATTR_* * @NL80211_ATTR_FREQ_AFTER: A channel which has suffered a regulatory change - * due to considerations from a beacon hint. This attribute reflects - * the state of the channel _after_ the beacon hint processing. This - * attributes consists of a nested attribute containing - * NL80211_FREQUENCY_ATTR_* + * due to considerations from a beacon hint. This attribute reflects + * the state of the channel _after_ the beacon hint processing. This + * attributes consists of a nested attribute containing + * NL80211_FREQUENCY_ATTR_* * * @NL80211_ATTR_CIPHER_SUITES: a set of u32 values indicating the supported * cipher suites @@ -1862,12 +1857,6 @@ enum nl80211_commands { * that protected APs should be used. This is also used with NEW_BEACON to * indicate that the BSS is to use protection. * - * @NL80211_ATTR_CIPHERS_PAIRWISE: Used with CONNECT, ASSOCIATE, and NEW_BEACON - * to indicate which unicast key ciphers will be used with the connection - * (an array of u32). - * @NL80211_ATTR_CIPHER_GROUP: Used with CONNECT, ASSOCIATE, and NEW_BEACON to - * indicate which group key cipher will be used with the connection (a - * u32). * @NL80211_ATTR_WPA_VERSIONS: Used with CONNECT, ASSOCIATE, and NEW_BEACON to * indicate which WPA version(s) the AP we want to associate with is using * (a u32 with flags from &enum nl80211_wpa_versions). @@ -1898,6 +1887,7 @@ enum nl80211_commands { * with %NL80211_KEY_* sub-attributes * * @NL80211_ATTR_PID: Process ID of a network namespace. + * @NL80211_ATTR_NETNS_FD: File descriptor of a network namespace. * * @NL80211_ATTR_GENERATION: Used to indicate consistent snapshots for * dumps. This number increases whenever the object list being @@ -1952,6 +1942,7 @@ enum nl80211_commands { * * @NL80211_ATTR_ACK: Flag attribute indicating that the frame was * acknowledged by the recipient. + * @NL80211_ATTR_ACK_SIGNAL: Station's ack signal strength (s32) * * @NL80211_ATTR_PS_STATE: powersave state, using &enum nl80211_ps_state values. * @@ -2149,6 +2140,9 @@ enum nl80211_commands { * @NL80211_ATTR_DISABLE_HE: Force HE capable interfaces to disable * this feature during association. This is a flag attribute. * Currently only supported in mac80211 drivers. + * @NL80211_ATTR_DISABLE_EHT: Force EHT capable interfaces to disable + * this feature during association. This is a flag attribute. + * Currently only supported in mac80211 drivers. * @NL80211_ATTR_HT_CAPABILITY_MASK: Specify which bits of the * ATTR_HT_CAPABILITY to which attention should be paid. * Currently, only mac80211 NICs support this feature. @@ -2158,6 +2152,12 @@ enum nl80211_commands { * All values are treated as suggestions and may be ignored * by the driver as required. The actual values may be seen in * the station debugfs ht_caps file. + * @NL80211_ATTR_VHT_CAPABILITY_MASK: Specify which bits of the + * ATTR_VHT_CAPABILITY to which attention should be paid. + * Currently, only mac80211 NICs support this feature. + * All values are treated as suggestions and may be ignored + * by the driver as required. The actual values may be seen in + * the station debugfs vht_caps file. * * @NL80211_ATTR_DFS_REGION: region for regulatory rules which this country * abides to when initiating radiation on DFS channels. A country maps @@ -2416,7 +2416,7 @@ enum nl80211_commands { * scheduled scan is started. Or the delay before a WoWLAN * net-detect scan is started, counting from the moment the * system is suspended. This value is a u32, in seconds. - + * * @NL80211_ATTR_REG_INDOOR: flag attribute, if set indicates that the device * is operating in an indoor environment. * @@ -3565,7 +3565,7 @@ enum nl80211_sta_flags { * enum nl80211_sta_p2p_ps_status - station support of P2P PS * * @NL80211_P2P_PS_UNSUPPORTED: station doesn't support P2P PS mechanism - * @@NL80211_P2P_PS_SUPPORTED: station supports P2P PS mechanism + * @NL80211_P2P_PS_SUPPORTED: station supports P2P PS mechanism * @NUM_NL80211_P2P_PS_STATUS: number of values */ enum nl80211_sta_p2p_ps_status { @@ -3603,9 +3603,9 @@ enum nl80211_he_gi { /** * enum nl80211_he_ltf - HE long training field - * @NL80211_RATE_INFO_HE_1xLTF: 3.2 usec - * @NL80211_RATE_INFO_HE_2xLTF: 6.4 usec - * @NL80211_RATE_INFO_HE_4xLTF: 12.8 usec + * @NL80211_RATE_INFO_HE_1XLTF: 3.2 usec + * @NL80211_RATE_INFO_HE_2XLTF: 6.4 usec + * @NL80211_RATE_INFO_HE_4XLTF: 12.8 usec */ enum nl80211_he_ltf { NL80211_RATE_INFO_HE_1XLTF, @@ -3720,7 +3720,7 @@ enum nl80211_eht_ru_alloc { * @NL80211_RATE_INFO_HE_GI: HE guard interval identifier * (u8, see &enum nl80211_he_gi) * @NL80211_RATE_INFO_HE_DCM: HE DCM value (u8, 0/1) - * @NL80211_RATE_INFO_RU_ALLOC: HE RU allocation, if not present then + * @NL80211_RATE_INFO_HE_RU_ALLOC: HE RU allocation, if not present then * non-OFDMA was used (u8, see &enum nl80211_he_ru_alloc) * @NL80211_RATE_INFO_320_MHZ_WIDTH: 320 MHz bitrate * @NL80211_RATE_INFO_EHT_MCS: EHT MCS index (u8, 0-15) @@ -3823,7 +3823,7 @@ enum nl80211_sta_bss_param { * (u64, to this station) * @NL80211_STA_INFO_SIGNAL: signal strength of last received PPDU (u8, dBm) * @NL80211_STA_INFO_TX_BITRATE: current unicast tx rate, nested attribute - * containing info as possible, see &enum nl80211_rate_info + * containing info as possible, see &enum nl80211_rate_info * @NL80211_STA_INFO_RX_PACKETS: total received packet (MSDUs and MMPDUs) * (u32, from this station) * @NL80211_STA_INFO_TX_PACKETS: total transmitted packets (MSDUs and MMPDUs) @@ -3852,8 +3852,8 @@ enum nl80211_sta_bss_param { * Contains a nested array of signal strength attributes (u8, dBm) * @NL80211_STA_INFO_CHAIN_SIGNAL_AVG: per-chain signal strength average * Same format as NL80211_STA_INFO_CHAIN_SIGNAL. - * @NL80211_STA_EXPECTED_THROUGHPUT: expected throughput considering also the - * 802.11 header (u32, kbps) + * @NL80211_STA_INFO_EXPECTED_THROUGHPUT: expected throughput considering also + * the 802.11 header (u32, kbps) * @NL80211_STA_INFO_RX_DROP_MISC: RX packets dropped for unspecified reasons * (u64) * @NL80211_STA_INFO_BEACON_RX: number of beacons received from this peer (u64) @@ -4039,7 +4039,7 @@ enum nl80211_mpath_flags { * @NL80211_MPATH_INFO_METRIC: metric (cost) of this mesh path * @NL80211_MPATH_INFO_EXPTIME: expiration time for the path, in msec from now * @NL80211_MPATH_INFO_FLAGS: mesh path flags, enumerated in - * &enum nl80211_mpath_flags; + * &enum nl80211_mpath_flags; * @NL80211_MPATH_INFO_DISCOVERY_TIMEOUT: total path discovery timeout, in msec * @NL80211_MPATH_INFO_DISCOVERY_RETRIES: mesh path discovery retries * @NL80211_MPATH_INFO_HOP_COUNT: hop count to destination @@ -4179,7 +4179,7 @@ enum nl80211_band_attr { * @NL80211_WMMR_CW_MAX: Maximum contention window slot. * @NL80211_WMMR_AIFSN: Arbitration Inter Frame Space. * @NL80211_WMMR_TXOP: Maximum allowed tx operation time. - * @nl80211_WMMR_MAX: highest possible wmm rule. + * @NL80211_WMMR_MAX: highest possible wmm rule. * @__NL80211_WMMR_LAST: Internal use. */ enum nl80211_wmm_rule { @@ -4201,8 +4201,9 @@ enum nl80211_wmm_rule { * @NL80211_FREQUENCY_ATTR_DISABLED: Channel is disabled in current * regulatory domain. * @NL80211_FREQUENCY_ATTR_NO_IR: no mechanisms that initiate radiation - * are permitted on this channel, this includes sending probe - * requests, or modes of operation that require beaconing. + * are permitted on this channel, this includes sending probe + * requests, or modes of operation that require beaconing. + * @__NL80211_FREQUENCY_ATTR_NO_IBSS: obsolete, same as _NO_IR * @NL80211_FREQUENCY_ATTR_RADAR: Radar detection is mandatory * on this channel in current regulatory domain. * @NL80211_FREQUENCY_ATTR_MAX_TX_POWER: Maximum transmission power in mBm @@ -4357,16 +4358,16 @@ enum nl80211_bitrate_attr { }; /** - * enum nl80211_initiator - Indicates the initiator of a reg domain request + * enum nl80211_reg_initiator - Indicates the initiator of a reg domain request * @NL80211_REGDOM_SET_BY_CORE: Core queried CRDA for a dynamic world - * regulatory domain. + * regulatory domain. * @NL80211_REGDOM_SET_BY_USER: User asked the wireless core to set the - * regulatory domain. + * regulatory domain. * @NL80211_REGDOM_SET_BY_DRIVER: a wireless drivers has hinted to the - * wireless core it thinks its knows the regulatory domain we should be in. + * wireless core it thinks its knows the regulatory domain we should be in. * @NL80211_REGDOM_SET_BY_COUNTRY_IE: the wireless core has received an - * 802.11 country information element with regulatory information it - * thinks we should consider. cfg80211 only processes the country + * 802.11 country information element with regulatory information it + * thinks we should consider. cfg80211 only processes the country * code from the IE, and relies on the regulatory domain information * structure passed by userspace (CRDA) from our wireless-regdb. * If a channel is enabled but the country code indicates it should @@ -4385,11 +4386,11 @@ enum nl80211_reg_initiator { * to a specific country. When this is set you can count on the * ISO / IEC 3166 alpha2 country code being valid. * @NL80211_REGDOM_TYPE_WORLD: the regulatory set domain is the world regulatory - * domain. + * domain. * @NL80211_REGDOM_TYPE_CUSTOM_WORLD: the regulatory domain set is a custom - * driver specific world regulatory domain. These do not apply system-wide - * and are only applicable to the individual devices which have requested - * them to be applied. + * driver specific world regulatory domain. These do not apply system-wide + * and are only applicable to the individual devices which have requested + * them to be applied. * @NL80211_REGDOM_TYPE_INTERSECTION: the regulatory domain set is the product * of an intersection between two regulatory domains -- the previously * set regulatory domain on the system and the last accepted regulatory @@ -4406,21 +4407,21 @@ enum nl80211_reg_type { * enum nl80211_reg_rule_attr - regulatory rule attributes * @__NL80211_REG_RULE_ATTR_INVALID: attribute number 0 is reserved * @NL80211_ATTR_REG_RULE_FLAGS: a set of flags which specify additional - * considerations for a given frequency range. These are the - * &enum nl80211_reg_rule_flags. + * considerations for a given frequency range. These are the + * &enum nl80211_reg_rule_flags. * @NL80211_ATTR_FREQ_RANGE_START: starting frequencry for the regulatory - * rule in KHz. This is not a center of frequency but an actual regulatory - * band edge. + * rule in KHz. This is not a center of frequency but an actual regulatory + * band edge. * @NL80211_ATTR_FREQ_RANGE_END: ending frequency for the regulatory rule - * in KHz. This is not a center a frequency but an actual regulatory - * band edge. + * in KHz. This is not a center a frequency but an actual regulatory + * band edge. * @NL80211_ATTR_FREQ_RANGE_MAX_BW: maximum allowed bandwidth for this * frequency range, in KHz. * @NL80211_ATTR_POWER_RULE_MAX_ANT_GAIN: the maximum allowed antenna gain - * for a given frequency range. The value is in mBi (100 * dBi). - * If you don't have one then don't send this. + * for a given frequency range. The value is in mBi (100 * dBi). + * If you don't have one then don't send this. * @NL80211_ATTR_POWER_RULE_MAX_EIRP: the maximum allowed EIRP for - * a given frequency range. The value is in mBm (100 * dBm). + * a given frequency range. The value is in mBm (100 * dBm). * @NL80211_ATTR_DFS_CAC_TIME: DFS CAC time in milliseconds. * If not present or 0 default CAC time will be used. * @NL80211_ATTR_POWER_RULE_PSD: power spectral density (in dBm). @@ -4507,8 +4508,9 @@ enum nl80211_sched_scan_match_attr { * @NL80211_RRF_PTP_ONLY: this is only for Point To Point links * @NL80211_RRF_PTMP_ONLY: this is only for Point To Multi Point links * @NL80211_RRF_NO_IR: no mechanisms that initiate radiation are allowed, - * this includes probe requests or modes of operation that require - * beaconing. + * this includes probe requests or modes of operation that require + * beaconing. + * @__NL80211_RRF_NO_IBSS: obsolete, same as NO_IR * @NL80211_RRF_AUTO_BW: maximum available bandwidth should be calculated * base on contiguous rules and wider channels will be allowed to cross * multiple contiguous/overlapping frequency ranges. @@ -4522,9 +4524,9 @@ enum nl80211_sched_scan_match_attr { * @NL80211_RRF_NO_EHT: EHT operation not allowed * @NL80211_RRF_PSD: Ruleset has power spectral density value * @NL80211_RRF_DFS_CONCURRENT: Operation on this channel is allowed for - peer-to-peer or adhoc communication under the control of a DFS master - which operates on the same channel (FCC-594280 D01 Section B.3). - Should be used together with %NL80211_RRF_DFS only. + * peer-to-peer or adhoc communication under the control of a DFS master + * which operates on the same channel (FCC-594280 D01 Section B.3). + * Should be used together with %NL80211_RRF_DFS only. * @NL80211_RRF_NO_6GHZ_VLP_CLIENT: Client connection to VLP AP not allowed * @NL80211_RRF_NO_6GHZ_AFC_CLIENT: Client connection to AFC AP not allowed */ @@ -4707,8 +4709,8 @@ enum nl80211_mntr_flags { * alternate between Active and Doze states, but may not wake up * for neighbor's beacons. * - * @__NL80211_MESH_POWER_AFTER_LAST - internal use - * @NL80211_MESH_POWER_MAX - highest possible power save level + * @__NL80211_MESH_POWER_AFTER_LAST: internal use + * @NL80211_MESH_POWER_MAX: highest possible power save level */ enum nl80211_mesh_power_mode { @@ -5728,7 +5730,7 @@ struct nl80211_pattern_support { * "TCP connection wakeup" for more details. This is a nested attribute * containing the exact information for establishing and keeping alive * the TCP connection. - * @NL80211_WOWLAN_TRIG_TCP_WAKEUP_MATCH: For wakeup reporting only, the + * @NL80211_WOWLAN_TRIG_WAKEUP_TCP_MATCH: For wakeup reporting only, the * wakeup packet was received on the TCP connection * @NL80211_WOWLAN_TRIG_WAKEUP_TCP_CONNLOST: For wakeup reporting only, the * TCP connection was lost or failed to be established @@ -6077,7 +6079,7 @@ enum nl80211_plink_state { * @NL80211_PLINK_ACTION_BLOCK: block traffic from this mesh peer * @NUM_NL80211_PLINK_ACTIONS: number of possible actions */ -enum plink_actions { +enum nl80211_plink_action { NL80211_PLINK_ACTION_NO_ACTION, NL80211_PLINK_ACTION_OPEN, NL80211_PLINK_ACTION_BLOCK, @@ -6404,6 +6406,7 @@ enum nl80211_feature_flags { * receiving control port frames over nl80211 instead of the netdevice. * @NL80211_EXT_FEATURE_ACK_SIGNAL_SUPPORT: This driver/device supports * (average) ACK signal strength reporting. + * @NL80211_EXT_FEATURE_DATA_ACK_SIGNAL_SUPPORT: Backward-compatible ID * @NL80211_EXT_FEATURE_TXQS: Driver supports FQ-CoDel-enabled intermediate * TXQs. * @NL80211_EXT_FEATURE_SCAN_RANDOM_SN: Driver/device supports randomizing the @@ -6787,6 +6790,8 @@ enum nl80211_acl_policy { * @NL80211_SMPS_STATIC: static SMPS (use a single antenna) * @NL80211_SMPS_DYNAMIC: dynamic smps (start with a single antenna and * turn on other antennas after CTS/RTS). + * @__NL80211_SMPS_AFTER_LAST: internal + * @NL80211_SMPS_MAX: highest used enumeration */ enum nl80211_smps_mode { NL80211_SMPS_OFF, @@ -7008,6 +7013,8 @@ enum nl80211_bss_select_attr { * @NL80211_NAN_FUNC_PUBLISH: function is publish * @NL80211_NAN_FUNC_SUBSCRIBE: function is subscribe * @NL80211_NAN_FUNC_FOLLOW_UP: function is follow-up + * @__NL80211_NAN_FUNC_TYPE_AFTER_LAST: internal use + * @NL80211_NAN_FUNC_MAX_TYPE: internal use */ enum nl80211_nan_function_type { NL80211_NAN_FUNC_PUBLISH, @@ -7168,7 +7175,7 @@ enum nl80211_nan_match_attributes { }; /** - * nl80211_external_auth_action - Action to perform with external + * enum nl80211_external_auth_action - Action to perform with external * authentication request. Used by NL80211_ATTR_EXTERNAL_AUTH_ACTION. * @NL80211_EXTERNAL_AUTH_START: Start the authentication. * @NL80211_EXTERNAL_AUTH_ABORT: Abort the ongoing authentication. @@ -7186,7 +7193,7 @@ enum nl80211_external_auth_action { * @NL80211_FTM_RESP_ATTR_LCI: The content of Measurement Report Element * (9.4.2.22 in 802.11-2016) with type 8 - LCI (9.4.2.22.10), * i.e. starting with the measurement token - * @NL80211_FTM_RESP_ATTR_CIVIC: The content of Measurement Report Element + * @NL80211_FTM_RESP_ATTR_CIVICLOC: The content of Measurement Report Element * (9.4.2.22 in 802.11-2016) with type 11 - Civic (Section 9.4.2.22.13), * i.e. starting with the measurement token * @__NL80211_FTM_RESP_ATTR_LAST: Internal @@ -7829,6 +7836,7 @@ enum nl80211_sae_pwe_mechanism { * * @NL80211_SAR_TYPE_POWER: power limitation specified in 0.25dBm unit * + * @NUM_NL80211_SAR_TYPE: internal */ enum nl80211_sar_type { NL80211_SAR_TYPE_POWER, @@ -7842,6 +7850,8 @@ enum nl80211_sar_type { /** * enum nl80211_sar_attrs - Attributes for SAR spec * + * @__NL80211_SAR_ATTR_INVALID: Invalid + * * @NL80211_SAR_ATTR_TYPE: the SAR type as defined in &enum nl80211_sar_type. * * @NL80211_SAR_ATTR_SPECS: Nested array of SAR power @@ -7873,6 +7883,8 @@ enum nl80211_sar_attrs { /** * enum nl80211_sar_specs_attrs - Attributes for SAR power limit specs * + * @__NL80211_SAR_ATTR_SPECS_INVALID: Invalid + * * @NL80211_SAR_ATTR_SPECS_POWER: Required (s32)value to specify the actual * power limit value in units of 0.25 dBm if type is * NL80211_SAR_TYPE_POWER. (i.e., a value of 44 represents 11 dBm). diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index ea277039f89d..229fc925ec3a 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -587,6 +587,10 @@ enum { * TCA_FLOWER_KEY_ENC_OPT_GTP_ * attributes */ + TCA_FLOWER_KEY_ENC_OPTS_PFCP, /* Nested + * TCA_FLOWER_KEY_ENC_IPT_PFCP + * attributes + */ __TCA_FLOWER_KEY_ENC_OPTS_MAX, }; @@ -637,6 +641,16 @@ enum { (__TCA_FLOWER_KEY_ENC_OPT_GTP_MAX - 1) enum { + TCA_FLOWER_KEY_ENC_OPT_PFCP_UNSPEC, + TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE, /* u8 */ + TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID, /* be64 */ + __TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX, +}; + +#define TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX \ + (__TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX - 1) + +enum { TCA_FLOWER_KEY_MPLS_OPTS_UNSPEC, TCA_FLOWER_KEY_MPLS_OPTS_LSE, __TCA_FLOWER_KEY_MPLS_OPTS_MAX, diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index a0819c6a5988..adf5fd78dd50 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -337,6 +337,8 @@ enum LINUX_MIB_XFRMFWDHDRERROR, /* XfrmFwdHdrError*/ LINUX_MIB_XFRMOUTSTATEINVALID, /* XfrmOutStateInvalid */ LINUX_MIB_XFRMACQUIREERROR, /* XfrmAcquireError */ + LINUX_MIB_XFRMOUTSTATEDIRERROR, /* XfrmOutStateDirError */ + LINUX_MIB_XFRMINSTATEDIRERROR, /* XfrmInStateDirError */ __LINUX_MIB_XFRMMAX }; diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index c07e9f90c084..dbf896f3146c 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -135,6 +135,8 @@ enum { #define TCP_AO_GET_KEYS 41 /* List MKT(s) */ #define TCP_AO_REPAIR 42 /* Get/Set SNEs and ISNs */ +#define TCP_IS_MPTCP 43 /* Is MPTCP being used? */ + #define TCP_REPAIR_ON 1 #define TCP_REPAIR_OFF 0 #define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */ diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h index 4828794efcf8..1a0fe8b151fb 100644 --- a/include/uapi/linux/udp.h +++ b/include/uapi/linux/udp.h @@ -36,7 +36,7 @@ struct udphdr { #define UDP_GRO 104 /* This socket can receive UDP GRO packets */ /* UDP encapsulation types */ -#define UDP_ENCAP_ESPINUDP_NON_IKE 1 /* draft-ietf-ipsec-nat-t-ike-00/01 */ +#define UDP_ENCAP_ESPINUDP_NON_IKE 1 /* unused draft-ietf-ipsec-nat-t-ike-00/01 */ #define UDP_ENCAP_ESPINUDP 2 /* draft-ietf-ipsec-udp-encaps-06 */ #define UDP_ENCAP_L2TPINUDP 3 /* rfc2661 */ #define UDP_ENCAP_GTP0 4 /* GSM TS 09.60 */ diff --git a/include/uapi/linux/virtio_bt.h b/include/uapi/linux/virtio_bt.h index af798f4c9680..3cc7d633456b 100644 --- a/include/uapi/linux/virtio_bt.h +++ b/include/uapi/linux/virtio_bt.h @@ -13,7 +13,6 @@ enum virtio_bt_config_type { VIRTIO_BT_CONFIG_TYPE_PRIMARY = 0, - VIRTIO_BT_CONFIG_TYPE_AMP = 1, }; enum virtio_bt_config_vendor { diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index cc65ef0f3c3e..ac9174717ef1 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -56,6 +56,7 @@ #define VIRTIO_NET_F_MQ 22 /* Device supports Receive Flow * Steering */ #define VIRTIO_NET_F_CTRL_MAC_ADDR 23 /* Set MAC address */ +#define VIRTIO_NET_F_DEVICE_STATS 50 /* Device can provide device-level statistics. */ #define VIRTIO_NET_F_VQ_NOTF_COAL 52 /* Device supports virtqueue notification coalescing */ #define VIRTIO_NET_F_NOTF_COAL 53 /* Device supports notifications coalescing */ #define VIRTIO_NET_F_GUEST_USO4 54 /* Guest can handle USOv4 in. */ @@ -406,4 +407,146 @@ struct virtio_net_ctrl_coal_vq { struct virtio_net_ctrl_coal coal; }; +/* + * Device Statistics + */ +#define VIRTIO_NET_CTRL_STATS 8 +#define VIRTIO_NET_CTRL_STATS_QUERY 0 +#define VIRTIO_NET_CTRL_STATS_GET 1 + +struct virtio_net_stats_capabilities { + +#define VIRTIO_NET_STATS_TYPE_CVQ (1ULL << 32) + +#define VIRTIO_NET_STATS_TYPE_RX_BASIC (1ULL << 0) +#define VIRTIO_NET_STATS_TYPE_RX_CSUM (1ULL << 1) +#define VIRTIO_NET_STATS_TYPE_RX_GSO (1ULL << 2) +#define VIRTIO_NET_STATS_TYPE_RX_SPEED (1ULL << 3) + +#define VIRTIO_NET_STATS_TYPE_TX_BASIC (1ULL << 16) +#define VIRTIO_NET_STATS_TYPE_TX_CSUM (1ULL << 17) +#define VIRTIO_NET_STATS_TYPE_TX_GSO (1ULL << 18) +#define VIRTIO_NET_STATS_TYPE_TX_SPEED (1ULL << 19) + + __le64 supported_stats_types[1]; +}; + +struct virtio_net_ctrl_queue_stats { + struct { + __le16 vq_index; + __le16 reserved[3]; + __le64 types_bitmap[1]; + } stats[1]; +}; + +struct virtio_net_stats_reply_hdr { +#define VIRTIO_NET_STATS_TYPE_REPLY_CVQ 32 + +#define VIRTIO_NET_STATS_TYPE_REPLY_RX_BASIC 0 +#define VIRTIO_NET_STATS_TYPE_REPLY_RX_CSUM 1 +#define VIRTIO_NET_STATS_TYPE_REPLY_RX_GSO 2 +#define VIRTIO_NET_STATS_TYPE_REPLY_RX_SPEED 3 + +#define VIRTIO_NET_STATS_TYPE_REPLY_TX_BASIC 16 +#define VIRTIO_NET_STATS_TYPE_REPLY_TX_CSUM 17 +#define VIRTIO_NET_STATS_TYPE_REPLY_TX_GSO 18 +#define VIRTIO_NET_STATS_TYPE_REPLY_TX_SPEED 19 + __u8 type; + __u8 reserved; + __le16 vq_index; + __le16 reserved1; + __le16 size; +}; + +struct virtio_net_stats_cvq { + struct virtio_net_stats_reply_hdr hdr; + + __le64 command_num; + __le64 ok_num; +}; + +struct virtio_net_stats_rx_basic { + struct virtio_net_stats_reply_hdr hdr; + + __le64 rx_notifications; + + __le64 rx_packets; + __le64 rx_bytes; + + __le64 rx_interrupts; + + __le64 rx_drops; + __le64 rx_drop_overruns; +}; + +struct virtio_net_stats_tx_basic { + struct virtio_net_stats_reply_hdr hdr; + + __le64 tx_notifications; + + __le64 tx_packets; + __le64 tx_bytes; + + __le64 tx_interrupts; + + __le64 tx_drops; + __le64 tx_drop_malformed; +}; + +struct virtio_net_stats_rx_csum { + struct virtio_net_stats_reply_hdr hdr; + + __le64 rx_csum_valid; + __le64 rx_needs_csum; + __le64 rx_csum_none; + __le64 rx_csum_bad; +}; + +struct virtio_net_stats_tx_csum { + struct virtio_net_stats_reply_hdr hdr; + + __le64 tx_csum_none; + __le64 tx_needs_csum; +}; + +struct virtio_net_stats_rx_gso { + struct virtio_net_stats_reply_hdr hdr; + + __le64 rx_gso_packets; + __le64 rx_gso_bytes; + __le64 rx_gso_packets_coalesced; + __le64 rx_gso_bytes_coalesced; +}; + +struct virtio_net_stats_tx_gso { + struct virtio_net_stats_reply_hdr hdr; + + __le64 tx_gso_packets; + __le64 tx_gso_bytes; + __le64 tx_gso_segments; + __le64 tx_gso_segments_bytes; + __le64 tx_gso_packets_noseg; + __le64 tx_gso_bytes_noseg; +}; + +struct virtio_net_stats_rx_speed { + struct virtio_net_stats_reply_hdr hdr; + + /* rx_{packets,bytes}_allowance_exceeded are too long. So rename to + * short name. + */ + __le64 rx_ratelimit_packets; + __le64 rx_ratelimit_bytes; +}; + +struct virtio_net_stats_tx_speed { + struct virtio_net_stats_reply_hdr hdr; + + /* tx_{packets,bytes}_allowance_exceeded are too long. So rename to + * short name. + */ + __le64 tx_ratelimit_packets; + __le64 tx_ratelimit_bytes; +}; + #endif /* _UAPI_LINUX_VIRTIO_NET_H */ diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 594b66e16395..d950d02ab791 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -141,6 +141,11 @@ enum { XFRM_POLICY_MAX = 3 }; +enum xfrm_sa_dir { + XFRM_SA_DIR_IN = 1, + XFRM_SA_DIR_OUT = 2 +}; + enum { XFRM_SHARE_ANY, /* No limitations */ XFRM_SHARE_SESSION, /* For this session only */ @@ -315,6 +320,7 @@ enum xfrm_attr_type_t { XFRMA_SET_MARK_MASK, /* __u32 */ XFRMA_IF_ID, /* __u32 */ XFRMA_MTIMER_THRESH, /* __u32 in seconds for input SA */ + XFRMA_SA_DIR, /* __u8 */ __XFRMA_MAX #define XFRMA_OUTPUT_MARK XFRMA_SET_MARK /* Compatibility */ |