diff options
Diffstat (limited to 'include/linux')
74 files changed, 1633 insertions, 638 deletions
diff --git a/include/linux/arm-smccc-rsi.h b/include/linux/arm-smccc-rsi.h index fddb77986f70..cca881ddfdba 100644 --- a/include/linux/arm-smccc-rsi.h +++ b/include/linux/arm-smccc-rsi.h @@ -128,7 +128,7 @@ struct realm_config { union { struct { unsigned long ipa_bits; /* Width of IPA in bits */ - unsigned long hash_algo; /* Hash algorithm */ + u8 hash_algo; /* Hash algorithm */ }; u8 pad[0x200]; }; diff --git a/include/linux/bio.h b/include/linux/bio.h index 75f8086351c0..7a794ce723b8 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -80,7 +80,8 @@ static inline bool bio_no_advance_iter(const struct bio *bio) { return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE || - bio_op(bio) == REQ_OP_WRITE_ZEROES; + bio_op(bio) == REQ_OP_WRITE_ZEROES || + op_is_dmabuf(bio->bi_opf); } static inline void *bio_data(struct bio *bio) @@ -113,11 +114,13 @@ static inline void bio_advance_iter(const struct bio *bio, { iter->bi_sector += bytes >> 9; - if (bio_no_advance_iter(bio)) + if (bio_no_advance_iter(bio)) { iter->bi_size -= bytes; - else + iter->bi_offset += bytes; + } else { bvec_iter_advance(bio->bi_io_vec, iter, bytes); /* TODO: It is reasonable to complete bio with error here. */ + } } /* @bytes should be less or equal to bvec[i->bi_idx].bv_len */ @@ -127,10 +130,12 @@ static inline void bio_advance_iter_single(const struct bio *bio, { iter->bi_sector += bytes >> 9; - if (bio_no_advance_iter(bio)) + if (bio_no_advance_iter(bio)) { iter->bi_size -= bytes; - else + iter->bi_offset += bytes; + } else { bvec_iter_advance_single(bio->bi_io_vec, iter, bytes); + } } void __bio_advance(struct bio *, unsigned bytes); @@ -256,12 +261,6 @@ static inline struct folio *bio_first_folio_all(struct bio *bio) return page_folio(bio_first_page_all(bio)); } -static inline struct bio_vec *bio_last_bvec_all(struct bio *bio) -{ - WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); - return &bio->bi_io_vec[bio->bi_vcnt - 1]; -} - /** * struct folio_iter - State for iterating all folios in a bio. * @folio: The current folio we're iterating. NULL after the last folio. @@ -440,12 +439,12 @@ static inline void bio_wouldblock_error(struct bio *bio) /* * Calculate number of bvec segments that should be allocated to fit data - * pointed by @iter. If @iter is backed by bvec it's going to be reused - * instead of allocating a new one. + * pointed by @iter. If @iter is backed by a bvec or a dmabuf, the bvec array / + * the dma map are going to be reused, and so no extra allocation is required. */ static inline int bio_iov_vecs_to_alloc(struct iov_iter *iter, int max_segs) { - if (iov_iter_is_bvec(iter)) + if (iov_iter_is_bvec(iter) || iov_iter_is_dmabuf_map(iter)) return 0; return iov_iter_npages(iter, max_segs); } diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index af878597afb8..7c7504c84e09 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -1017,6 +1017,13 @@ static inline void *blk_mq_rq_to_pdu(struct request *rq) return rq + 1; } +static inline bool blk_mq_rq_is_dmabuf(struct request *rq) +{ + if (!IS_ENABLED(CONFIG_DMA_SHARED_BUFFER)) + return false; + return rq->bio && op_is_dmabuf(rq->bio->bi_opf); +} + static inline struct blk_mq_hw_ctx *queue_hctx(struct request_queue *q, int id) { struct blk_mq_hw_ctx *hctx; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 98e21b4cbf32..0cc09b975d8f 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -233,7 +233,12 @@ struct bio { atomic_t __bi_remaining; /* The actual vec list, preserved by bio_reset() */ - struct bio_vec *bi_io_vec; + union { + struct bio_vec *bi_io_vec; + /* Driver specific dma map, valid IFF REQ_DMABUF is set */ + struct dma_buf_io_map *bi_dmabuf_map; + }; + struct bvec_iter bi_iter; union { @@ -402,6 +407,7 @@ enum req_flag_bits { __REQ_DRV, /* for driver use */ __REQ_FS_PRIVATE, /* for file system (submitter) use */ __REQ_ATOMIC, /* for atomic write operations */ + __REQ_DMABUF, /* Using premmaped dma buffers */ /* * Command specific flags, keep last: */ @@ -434,6 +440,7 @@ enum req_flag_bits { #define REQ_DRV (__force blk_opf_t)(1ULL << __REQ_DRV) #define REQ_FS_PRIVATE (__force blk_opf_t)(1ULL << __REQ_FS_PRIVATE) #define REQ_ATOMIC (__force blk_opf_t)(1ULL << __REQ_ATOMIC) +#define REQ_DMABUF (__force blk_opf_t)(1ULL << __REQ_DMABUF) #define REQ_NOUNMAP (__force blk_opf_t)(1ULL << __REQ_NOUNMAP) @@ -487,6 +494,11 @@ static inline bool op_is_discard(blk_opf_t op) return (op & REQ_OP_MASK) == REQ_OP_DISCARD; } +static inline bool op_is_dmabuf(blk_opf_t op) +{ + return op & REQ_DMABUF; +} + /* * Check if a bio or request operation is a zone management operation. */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d003a9d2d1f6..2d5c30823aab 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1599,6 +1599,8 @@ struct block_device_operations { /* returns the length of the identifier or a negative errno: */ int (*get_unique_id)(struct gendisk *disk, u8 id[16], enum blk_unique_id id_type); + int (*init_dma_buf_io_ctx)(struct block_device *, + struct dma_buf_io_ctx *); struct module *owner; const struct pr_ops *pr_ops; diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index fdc15b6f4d1b..260a6f46042e 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -27,6 +27,10 @@ bool __init cmdline_has_extra_options(void); #define BOOTCONFIG_ALIGN (1 << BOOTCONFIG_ALIGN_SHIFT) #define BOOTCONFIG_ALIGN_MASK (BOOTCONFIG_ALIGN - 1) +/* Bootconfig footer is [size][csum][BOOTCONFIG_MAGIC]. */ +#define BOOTCONFIG_FOOTER_SIZE \ + (sizeof(uint32_t) * 2 + BOOTCONFIG_MAGIC_LEN) + /** * xbc_calc_checksum() - Calculate checksum of bootconfig * @data: Bootconfig data. @@ -266,7 +270,15 @@ int __init xbc_node_compose_key_after(struct xbc_node *root, struct xbc_node *node, char *buf, size_t size); /* Render key/value pairs under @root as a flat cmdline string */ -int __init xbc_snprint_cmdline(char *buf, size_t size, struct xbc_node *root); +typedef bool (*xbc_cmdline_filter_fn)(struct xbc_node *node, const char *key, void *data); + +int __init xbc_snprint_cmdline_filter(char *buf, size_t size, struct xbc_node *root, + xbc_cmdline_filter_fn filter, void *data); + +static inline int __init xbc_snprint_cmdline(char *buf, size_t size, struct xbc_node *root) +{ + return xbc_snprint_cmdline_filter(buf, size, root, NULL, NULL); +} /** * xbc_node_compose_key() - Compose full key string of the XBC node diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 8a75a6cd7309..02ef7f899b3d 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -345,27 +345,19 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, * calling bpf_setsockopt on listener-sk will not make sense anyway, * so passing 'sock_ops->sk == req_sk' to the bpf prog is appropriate here. */ -#define BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(sock_ops, sk) \ -({ \ - int __ret = 0; \ - if (cgroup_bpf_enabled(CGROUP_SOCK_OPS)) \ - __ret = __cgroup_bpf_run_filter_sock_ops(sk, \ - sock_ops, \ - CGROUP_SOCK_OPS); \ - __ret; \ -}) - -#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ -({ \ - int __ret = 0; \ - if (cgroup_bpf_enabled(CGROUP_SOCK_OPS) && (sock_ops)->sk) { \ - typeof(sk) __sk = sk_to_full_sk((sock_ops)->sk); \ - if (__sk && sk_fullsock(__sk)) \ - __ret = __cgroup_bpf_run_filter_sock_ops(__sk, \ - sock_ops, \ - CGROUP_SOCK_OPS); \ - } \ - __ret; \ +#define __BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(sock_ops, sk) \ + __cgroup_bpf_run_filter_sock_ops(sk, sock_ops, \ + CGROUP_SOCK_OPS) + +#define __BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ +({ \ + int __ret = 0; \ + typeof(sk) __sk = sk_to_full_sk((sock_ops)->sk); \ + if (__sk && sk_fullsock(__sk)) \ + __ret = __cgroup_bpf_run_filter_sock_ops(__sk, \ + sock_ops, \ + CGROUP_SOCK_OPS); \ + __ret; \ }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) \ @@ -529,7 +521,7 @@ static inline int cgroup_bpf_struct_ops_attach(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) +#define __BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c51083c761cf..791398e14962 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -9,6 +9,20 @@ #include <linux/filter.h> /* for MAX_BPF_STACK */ #include <linux/tnum.h> #include <linux/cnum.h> +#include <linux/math64.h> /* for div_s64_rem() */ + +/* + * Mathematical modulo, the residue of 'v' modulo 'step', normalized to [0, step). + * This differs from C's '%' operator, which truncates the quotient toward zero + * and so returns a remainder with the sign of the dividend (e.g. -1 % 3 == -1, not 2). + */ +static inline u16 imod(s64 v, u16 step) +{ + s32 rem; + + div_s64_rem(v, step, &rem); + return rem < 0 ? rem + step : rem; +} /* Maximum variable offset umax_value permitted when resolving memory accesses. * In practice this is far bigger than any realistic pointer offset; this limit @@ -125,6 +139,13 @@ struct bpf_reg_state { */ struct cnum64 r64; /* 64-bit range as circular number */ struct cnum32 r32; /* 32-bit range as circular number */ + /* + * The value described by this register, interpreted as s64, lies on + * a line described by a linear equation base + step * k. + * Invariant: base < step. + */ + u16 base; + u16 step; /* For PTR_TO_PACKET, used to find other pointers with the same variable * offset, so they can share range knowledge. * For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we @@ -163,9 +184,9 @@ struct bpf_reg_state { * other registers. Kept outside the metadata union for ID remapping * during state comparisons. */ - u32 map_uid; + u32 map_uid:31; /* if (!precise && SCALAR_VALUE) min/max/tnum don't affect safety */ - bool precise; + u32 precise:1; }; static inline s64 reg_smin(const struct bpf_reg_state *reg) @@ -307,6 +328,25 @@ struct bpf_retval_range { bool return_32bit; }; +/* SCEV/widening register space: r0..r10 plus every stack slot of a frame. */ +#define BPF_SCEV_REGS_NUM (MAX_BPF_REG + MAX_BPF_STACK_SLOTS) + +struct bpf_loop_iters { + u32 min_header_count; /* min number of times header is executed */ + u32 max_header_count; /* max number of times header is executed */ + unsigned long precise_regs[BITS_TO_LONGS(BPF_SCEV_REGS_NUM)]; +}; + +struct loop_stack_entry { + struct bpf_verifier_state *entry_state; + u32 min_header_count; + u32 max_header_count; + u32 loop_id:31; + u32 terminates:1; +}; + +#define LOOP_STACK_SIZE 16 + /* state of the program: * type of all registers and stack info */ @@ -352,6 +392,11 @@ struct bpf_func_state { u32 callback_depth; /* Instructions processed in this frame and callees on the current path. */ u32 insns_subtotal; + /* + * Control-flow loop nesting at the current insn within this frame's + * subprogram (loops never cross subprogram boundaries). + */ + u32 loop_stack_cnt; /* The following fields should be last. See copy_func_state() */ /* The state of the stack. Each element of the array describes BPF_REG_SIZE @@ -369,6 +414,7 @@ struct bpf_func_state { u16 out_stack_arg_cnt; /* Number of outgoing on-stack argument slots */ struct bpf_reg_state *stack_arg_regs; /* Outgoing on-stack arguments */ + struct loop_stack_entry *loop_stack; }; #define MAX_CALL_FRAMES 16 @@ -415,6 +461,7 @@ static_assert(MAX_BPF_STACK_SLOTS <= (1 << 12)); #define MAX_STACK_ARG_SLOTS (MAX_BPF_FUNC_ARGS - MAX_BPF_FUNC_REG_ARGS) #define BPF_ID_MAP_SIZE ((MAX_BPF_REG + MAX_BPF_STACK_SLOTS + MAX_STACK_ARG_SLOTS) * \ MAX_CALL_FRAMES) + struct bpf_verifier_state { /* call stack tracking */ struct bpf_func_state *frame[MAX_CALL_FRAMES]; @@ -481,7 +528,10 @@ struct bpf_verifier_state { bool speculative; bool in_sleepable; - /* first and last insn idx of this verifier state */ + /* + * First and last insn idx of this verifier state. + * last_insn_idx is -1 if no instructions have been executed yet. + */ u32 first_insn_idx; u32 last_insn_idx; /* if this state is a backedge state then equal_state @@ -508,7 +558,7 @@ static inline u32 bpf_stack_nr_slots(const struct bpf_func_state *frame) /* * Stack slot @spi of @frame, covering bytes [fp - (spi + 1) * 8, fp - spi * 8). - * The caller must ensure spi < bpf_stack_nr_slots(frame), see grow_stack_state(). + * The caller must ensure spi < bpf_stack_nr_slots(frame), see bpf_grow_stack_state(). */ static inline struct bpf_stack_state *bpf_stack_slot(const struct bpf_func_state *frame, u32 spi) { @@ -629,6 +679,52 @@ struct bpf_iarray { u32 items[]; }; +#define iarray_for_each(item, arr) \ + for (int ___idx = 0; \ + ___idx < (arr)->cnt && ({ item = (arr)->items[___idx]; 1; }); \ + ___idx++) + +#define MAX_BACKEDGES 16 +#define MAX_LOOP_EXITS 256 + +/* Number of exit conditions dominating a backedge. */ +#define MAX_LATCHES 4 + +struct bpf_backedge { + int from; + /* + * Conditional jumps within the loop that dominate 'from' and have + * a successor outside the loop, nearest first. latches[0] is the + * latch; the remaining entries are additional exit conditions. + * Each usable condition gives an upper bound on the iteration count, + * so keeping only a subset is sound. + */ + int latches[MAX_LATCHES]; + u8 latches_cnt; +}; + +struct bpf_loop_exit { + int from; /* instruction inside the loop */ + int to; /* instruction outside the loop */ +}; + +struct bpf_loop { + struct bpf_backedge backedges[MAX_BACKEDGES]; + /* edges exiting from this loop, includes edges from nested loops */ + struct bpf_loop_exit *exits; + int backedges_cnt; + int exits_cnt; + bool irreducible; + bool backedges_overflow; + bool exits_overflow; + /* + * Loop-entry registers used to compute stack addresses for loads, + * stores and calls requiring fixed stack offsets, in this and nested + * loops. + */ + unsigned long store_base_regs[BITS_TO_LONGS(BPF_SCEV_REGS_NUM)]; +}; + struct bpf_insn_aux_data { union { enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ @@ -662,6 +758,13 @@ struct bpf_insn_aux_data { }; struct btf_struct_meta *kptr_struct_meta; u64 map_key_state; /* constant (32 bit) key tracking for maps */ + /* + * Per-instruction summary of stack slots in the current frame + * that this instruction may write to. + */ + DECLARE_BITMAP(may_write_mask, MAX_BPF_STACK_SLOTS); + DECLARE_BITMAP(live_stack_before, MAX_BPF_STACK_SLOTS); + u16 stack_ptrs; /* bitmask of regs that may hold a frame pointer here (arg_track) */ int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ u32 seen; /* this insn was processed by the verifier at env->pass_cnt */ bool nospec; /* do not execute this instruction speculatively */ @@ -673,6 +776,8 @@ struct bpf_insn_aux_data { bool is_iter_next; /* bpf_iter_<type>_next() kfunc call */ bool call_with_percpu_alloc_ptr; /* {this,per}_cpu_ptr() with prog percpu alloc */ bool arena_scalar; /* ldx/stx/st/atomic through a number, it's an address in arena */ + bool bb_end; /* last instruction of a basic block */ + bool need_scev; u8 alu_state; /* used in combination with alu_limit */ /* true if STX or LDX instruction is a part of a spill/fill * pattern for a bpf_fastcall call. @@ -719,6 +824,13 @@ struct bpf_insn_aux_data { u16 const_reg_map_mask; u16 const_reg_subprog_mask; u32 const_reg_vals[10]; + /* + * Header index of the innermost loop containing this instruction, -1 if none. + * For a loop header, identifies the parent loop instead. + */ + s32 loop_header; + /* additional information about the loop if this instruction is a loop header */ + struct bpf_loop *loop; }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ @@ -921,6 +1033,7 @@ struct bpf_scc_info { }; struct bpf_liveness; +struct scev; struct bpf_fd_array { union { @@ -1008,6 +1121,7 @@ struct bpf_verifier_env { * see bpf_subprog_info->postorder_start. */ int *insn_postorder; + int *postorder_nums; int cur_stack; /* current position in the insn_postorder vector */ int cur_postorder; @@ -1083,6 +1197,8 @@ struct bpf_verifier_env { u32 scc_cnt; struct bpf_iarray *succ; struct bpf_iarray *gotox_tmp_buf; + int *idoms; + struct scev *scev; }; static inline struct bpf_func_info_aux *subprog_aux(struct bpf_verifier_env *env, int subprog) @@ -1144,6 +1260,7 @@ int bpf_vlog_finalize(struct bpf_verifier_log *log, u32 *log_size_actual); __printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env, u32 insn_off, const char *prefix_fmt, ...); +void bpf_verbose_snum(struct bpf_verifier_env *env, s64 num); #define verifier_bug_if(cond, env, fmt, args...) \ ({ \ @@ -1261,6 +1378,7 @@ void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab); int mark_chain_precision(struct bpf_verifier_env *env, int regno); int bpf_is_state_visited(struct bpf_verifier_env *env, int insn_idx); +int bpf_split_cur_state(struct bpf_verifier_env *env); int bpf_update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st); void bpf_clear_jmp_history(struct bpf_verifier_state *state); @@ -1275,7 +1393,9 @@ int bpf_push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state void bpf_bt_sync_linked_regs(struct backtrack_state *bt, struct bpf_jmp_history_entry *hist); void bpf_mark_reg_not_init(const struct bpf_verifier_env *env, struct bpf_reg_state *reg); +void bpf_mark_reg_known_scalar(struct bpf_reg_state *reg, u64 imm); void bpf_mark_reg_unknown_imprecise(struct bpf_reg_state *reg); +int bpf_grow_stack_state(struct bpf_verifier_env *env, struct bpf_func_state *state, int size); void bpf_mark_all_scalars_precise(struct bpf_verifier_env *env, struct bpf_verifier_state *st); void bpf_clear_singular_ids(struct bpf_verifier_env *env, struct bpf_verifier_state *st); @@ -1339,6 +1459,15 @@ static inline bool bpf_is_spilled_reg(const struct bpf_stack_state *stack) return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL; } +static inline int bpf_spill_size(const struct bpf_stack_state *stack) +{ + int i, spill_size = 0; + + for (i = BPF_REG_SIZE - 1; i >= 0 && stack->slot_type[i] == STACK_SPILL; i--) + spill_size++; + return spill_size; +} + static inline bool bpf_is_spilled_scalar_reg(const struct bpf_stack_state *stack) { return bpf_is_spilled_reg(stack) && stack->spilled_ptr.type == SCALAR_VALUE; @@ -1723,17 +1852,37 @@ bool bpf_is_may_goto_insn(struct bpf_insn *insn); void bpf_verbose_insn(struct bpf_verifier_env *env, struct bpf_insn *insn); bool bpf_get_call_summary(struct bpf_verifier_env *env, struct bpf_insn *call, struct bpf_call_summary *cs); -s64 bpf_helper_stack_access_bytes(struct bpf_verifier_env *env, - struct bpf_insn *insn, int arg, - int insn_idx); -s64 bpf_kfunc_stack_access_bytes(struct bpf_verifier_env *env, - struct bpf_insn *insn, int arg, - int insn_idx); +/* Stack effects used for state pruning; must_write implies may_write. */ +struct arg_access_info { + u32 size; /* Maximum extent; U32_MAX if unknown. */ + u8 may_read:1; /* Incoming contents or initialization may be needed. */ + u8 may_write:1; + u8 must_write:1; /* Prior verifier state is destroyed throughout size. */ +}; + +struct arg_access_info +bpf_helper_stack_access_bytes(struct bpf_verifier_env *env, + struct bpf_insn *insn, int arg, int insn_idx); +struct arg_access_info +bpf_kfunc_stack_access_bytes(struct bpf_verifier_env *env, + struct bpf_insn *insn, int arg, int insn_idx); +struct arg_access_info +bpf_global_subprog_stack_access_bytes(struct bpf_verifier_env *env, + struct bpf_insn *insn, int arg, int insn_idx); int bpf_compute_subprog_arg_access(struct bpf_verifier_env *env); +bool bpf_same_memory_origin(const struct bpf_reg_state *reg_a, + const struct bpf_reg_state *reg_b); +int bpf_set_reg_range(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + struct cnum64 range, u16 base, u16 step); +bool bpf_reg_union_compatible(const struct bpf_reg_state *a, const struct bpf_reg_state *b); +int bpf_reg_union(struct bpf_verifier_env *env, struct bpf_reg_state *acc, + const struct bpf_reg_state *src); int bpf_stack_liveness_init(struct bpf_verifier_env *env); void bpf_stack_liveness_free(struct bpf_verifier_env *env); int bpf_live_stack_query_init(struct bpf_verifier_env *env, struct bpf_verifier_state *st); +const unsigned long *bpf_may_write_mask(struct bpf_verifier_env *env, u32 insn_idx); +bool bpf_needs_fixed_stack_off(struct bpf_verifier_env *env, int insn_idx); bool bpf_stack_slot_alive(struct bpf_verifier_env *env, u32 frameno, u32 spi); int bpf_compute_live_registers(struct bpf_verifier_env *env); @@ -1830,6 +1979,7 @@ int bpf_check_attach_btf_id_multi(struct btf *btf, struct bpf_prog *prog, u32 bt struct bpf_attach_target_info *tgt_info); /* Functions in fixups.c, called from bpf_check() */ +void bpf_clear_insn_aux_data(struct bpf_verifier_env *env, int start, int len); int bpf_remove_fastcall_spills_fills(struct bpf_verifier_env *env); int bpf_optimize_bpf_loop(struct bpf_verifier_env *env); void bpf_opt_hard_wire_dead_code_branches(struct bpf_verifier_env *env); @@ -1842,4 +1992,23 @@ int bpf_fixup_call_args(struct bpf_verifier_env *env); int bpf_do_misc_fixups(struct bpf_verifier_env *env); int bpf_insn_def32(struct bpf_prog *prog, struct bpf_insn *insn); +int bpf_flip_opcode(u32 opcode); +u8 bpf_rev_opcode(u8 opcode); + +int bpf_compute_idoms(struct bpf_verifier_env *env); +int bpf_compute_loops(struct bpf_verifier_env *env); +int bpf_loop_at_index(struct bpf_verifier_env *env, u32 idx); +bool bpf_is_nested_loop(struct bpf_verifier_env *env, int inner_header, int outer_header); + +int bpf_init_scev(struct bpf_verifier_env *env); +void bpf_free_scev(struct bpf_verifier_env *env); +int bpf_compute_scev(struct bpf_verifier_env *env); + +int bpf_compute_loop_iters(struct bpf_verifier_env *env, struct bpf_verifier_state *st, + struct bpf_loop_iters *iters); +int bpf_widen_scev_regs(struct bpf_verifier_env *env, struct bpf_verifier_state *st, + struct bpf_verifier_state *loop_entry, struct bpf_loop_iters *iters); +int bpf_clamp_scev_regs(struct bpf_verifier_env *env, struct bpf_func_state *st, u32 insn_idx, + struct bpf_verifier_state *entry_state, u32 max_header_count); + #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index 14fa93268630..a697246feeac 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -66,7 +66,8 @@ void bsg_job_done(struct bsg_job *job, int result, unsigned int reply_payload_rcv_len); struct request_queue *bsg_setup_queue(struct device *dev, const char *name, struct queue_limits *lim, bsg_job_fn *job_fn, - bsg_timeout_fn *timeout, int dd_job_size); + bsg_timeout_fn *timeout, int dd_job_size, + unsigned int reply_len); void bsg_remove_queue(struct request_queue *q); void bsg_job_put(struct bsg_job *job); int __must_check bsg_job_get(struct bsg_job *job); diff --git a/include/linux/btf.h b/include/linux/btf.h index 4b63bb91550a..b66e20a18c54 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -5,6 +5,7 @@ #define _LINUX_BTF_H 1 #include <linux/types.h> +#include <linux/module.h> #include <linux/bpfptr.h> #include <linux/bsearch.h> #include <linux/btf_ids.h> @@ -118,6 +119,19 @@ struct btf_show; struct btf_id_set; struct bpf_prog; +#define BTF_LINK_SHA256_LEN 32 + +/* + * A .BTF.link or .BTF.inline.link section identifies the module which + * carries a vmlinux BTF section. The module name is NUL terminated and the + * field is padded to __MODULE_NAME_LEN. + */ +struct btf_link { + char module_name[__MODULE_NAME_LEN]; + u8 sha256[BTF_LINK_SHA256_LEN]; + u32 btf_size; +} __packed; + typedef int (*btf_kfunc_filter_t)(const struct bpf_prog *prog, u32 kfunc_id); struct btf_kfunc_id_set { @@ -594,7 +608,8 @@ struct btf_field_iter { #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); void btf_set_base_btf(struct btf *btf, const struct btf *base_btf); -int btf_relocate(struct btf *btf, const struct btf *base_btf, __u32 **map_ids); +int btf_relocate(struct btf *btf, const struct btf *base_btf, __u32 **map_ids, + __u32 **map_strs); int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, enum btf_field_iter_kind iter_kind); __u32 *btf_field_iter_next(struct btf_field_iter *it); @@ -624,6 +639,29 @@ bool btf_types_are_same(const struct btf *btf1, u32 id1, const struct btf *btf2, u32 id2); int btf_check_iter_arg(struct btf *btf, const struct btf_type *func, int arg_idx); +#if IS_ENABLED(CONFIG_SYSFS) +struct bin_attribute *sysfs_btf_add(const char *name, void *data, size_t data_size, + bool mmap, const char *lazy_module_name); +bool sysfs_btf_update(struct bin_attribute *attr, void *data); +void sysfs_btf_remove(struct bin_attribute *attr); +#else +static inline struct bin_attribute * +sysfs_btf_add(const char *name, void *data, size_t data_size, bool mmap, + const char *lazy_module_name) +{ + return NULL; +} + +static inline bool sysfs_btf_update(struct bin_attribute *attr, void *data) +{ + return false; +} + +static inline void sysfs_btf_remove(struct bin_attribute *attr) +{ +} +#endif + static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t) { if (!btf_type_is_ptr(t)) @@ -645,7 +683,7 @@ static inline void btf_set_base_btf(struct btf *btf, const struct btf *base_btf) } static inline int btf_relocate(void *log, struct btf *btf, const struct btf *base_btf, - __u32 **map_ids) + __u32 **map_ids, __u32 **map_strs) { return -EOPNOTSUPP; } diff --git a/include/linux/bvec.h b/include/linux/bvec.h index df9ce860e787..8decff9484c4 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -108,7 +108,8 @@ struct bvec_iter { unsigned int bi_idx; /* - * Current offset in the bvec entry pointed to by `bi_idx`. + * Current offset in the bvec entry pointed to by `bi_idx` or into + * a dma-buf map. */ unsigned int bi_offset; } __packed __aligned(4); diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index b179b1813278..61c4abf19995 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -265,6 +265,12 @@ int omap2_clk_disable_autoidle_all(void); int omap2_clk_enable_autoidle_all(void); int omap2_clk_allow_idle(struct clk *clk); int omap2_clk_deny_idle(struct clk *clk); +unsigned long omap2_dpllcore_recalc(struct clk_hw *hw, + unsigned long parent_rate); +int omap2_reprogram_dpllcore(struct clk_hw *clk, unsigned long rate, + unsigned long parent_rate); +void omap2xxx_clkt_dpllcore_init(struct clk_hw *hw); +void omap2xxx_clkt_vps_init(void); unsigned long omap2_get_dpll_rate(struct clk_hw_omap *clk); void ti_dt_clk_init_retry_clks(void); @@ -316,6 +322,8 @@ void omap3_noncore_dpll_restore_context(struct clk_hw *hw); int omap3_core_dpll_save_context(struct clk_hw *hw); void omap3_core_dpll_restore_context(struct clk_hw *hw); +extern const struct clk_hw_omap_ops clkhwops_omap2xxx_dpll; + #ifdef CONFIG_ATAGS int omap3430_clk_legacy_init(void); int omap3430es1_clk_legacy_init(void); diff --git a/include/linux/cnum.h b/include/linux/cnum.h index 49b7d0c7645d..49160318adf9 100644 --- a/include/linux/cnum.h +++ b/include/linux/cnum.h @@ -39,6 +39,7 @@ u32 cnum32_umin(struct cnum32 cnum); u32 cnum32_umax(struct cnum32 cnum); s32 cnum32_smin(struct cnum32 cnum); s32 cnum32_smax(struct cnum32 cnum); +struct cnum32 cnum32_union(struct cnum32 a, struct cnum32 b); struct cnum32 cnum32_intersect(struct cnum32 a, struct cnum32 b); void cnum32_intersect_with(struct cnum32 *dst, struct cnum32 src); void cnum32_intersect_with_urange(struct cnum32 *dst, u32 min, u32 max); @@ -65,6 +66,7 @@ u64 cnum64_umin(struct cnum64 cnum); u64 cnum64_umax(struct cnum64 cnum); s64 cnum64_smin(struct cnum64 cnum); s64 cnum64_smax(struct cnum64 cnum); +struct cnum64 cnum64_union(struct cnum64 a, struct cnum64 b); struct cnum64 cnum64_intersect(struct cnum64 a, struct cnum64 b); void cnum64_intersect_with(struct cnum64 *dst, struct cnum64 src); void cnum64_intersect_with_urange(struct cnum64 *dst, u64 min, u64 max); @@ -78,5 +80,6 @@ bool cnum64_is_subset(struct cnum64 outer, struct cnum64 inner); struct cnum32 cnum32_from_cnum64(struct cnum64 cnum); struct cnum64 cnum64_cnum32_intersect(struct cnum64 a, struct cnum32 b); +struct cnum64 cnum64_intersect_linear(struct cnum64 in, u16 base, u16 step); #endif /* _LINUX_CNUM_H */ diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 476c4c560d17..625e95e684c7 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -323,6 +323,18 @@ #define __pure __attribute__((__pure__)) /* + * Optional: not supported by gcc + * Optional: only supported since clang >= 20.0 + * + * clang: https://clang.llvm.org/docs/AttributeReference.html#require-explicit-initialization + */ +#if __has_attribute(__require_explicit_initialization__) +# define __require_explicit_initialization __attribute__((__require_explicit_initialization__)) +#else +# define __require_explicit_initialization +#endif + +/* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-section-function-attribute * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-section-variable-attribute * clang: https://clang.llvm.org/docs/AttributeReference.html#section-declspec-allocate diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 74af57b9406b..8e857770dd21 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -5,6 +5,7 @@ #include <linux/types.h> #include <linux/mm.h> #include <linux/fs.h> +#include <linux/pid_types.h> #include <linux/sched/coredump.h> #include <uapi/linux/coredump.h> #include <asm/siginfo.h> @@ -51,7 +52,8 @@ struct coredump_params { int vma_count; size_t vma_data_size; struct core_vma_metadata *vma_meta; - struct pid *pid; + /* Dumping thread and its thread-group leader by pid type. */ + DECLARE_PIDS(pid, PIDTYPE_TGID); }; extern unsigned int core_file_note_size_limit; diff --git a/include/linux/dcache.h b/include/linux/dcache.h index adf239f8205f..d5ce9ecb28f3 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -239,7 +239,8 @@ enum dentry_flags { DCACHE_DENTRY_CURSOR = BIT(25), DCACHE_NORCU = BIT(26), /* No RCU delay for freeing */ DCACHE_PERSISTENT = BIT(27), -/* 28, 29, 30 free */ + DCACHE_UNCOVERED = BIT(28), /* lost its mounts on its way out */ +/* 29, 30 free */ DCACHE_PRIVATE = BIT(31) /* fs-specific flag */ }; diff --git a/include/linux/dma-buf-io.h b/include/linux/dma-buf-io.h new file mode 100644 index 000000000000..b9bbeca1744f --- /dev/null +++ b/include/linux/dma-buf-io.h @@ -0,0 +1,125 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __DMA_BUF_IO_H__ +#define __DMA_BUF_IO_H__ + +#include <linux/dma-buf.h> + +struct dma_buf_io_ctx; +struct dma_buf_io_map; + +struct dma_buf_io_ops { + /* + * Create a new map for the given ctx. Called with the reservation + * lock held. + */ + struct dma_buf_io_map *(*map)(struct dma_buf_io_ctx *ctx); + + /* + * Clean up device specific parts of the @map. Called with the + * reservation lock held. + */ + void (*unmap)(struct dma_buf_io_ctx *ctx, struct dma_buf_io_map *map); + + /* + * The user tries to destroy the ctx. Release all device specific + * parts of the token. + */ + void (*release)(struct dma_buf_io_ctx *); +}; + +struct dma_buf_io_map { + /* + * Counts attached requests and other users. Device specific unmapping + * is deferred until all refs are dropped. + */ + struct percpu_ref refs; + /* + * Shift for the minimum segment size of the mapping. + */ + unsigned min_seg_shift; + + struct dma_buf_io_ctx *ctx; + struct completion drained; +}; + +struct dma_buf_io_ctx { + struct dma_buf_io_map __rcu *map; + struct dma_buf *dmabuf; + enum dma_data_direction dir; + bool is_dead; + + void *dev_priv; + const struct dma_buf_io_ops *dev_ops; +}; + +int dma_buf_io_ctx_create(struct file *file, + struct dma_buf *dmabuf, + enum dma_data_direction dir, + struct dma_buf_io_ctx **ctx); +void dma_buf_io_ctx_release(struct dma_buf_io_ctx *ctx); + +struct dma_buf_io_map *dma_buf_io_create_map(struct dma_buf_io_ctx *ctx); + +static inline struct dma_buf_io_map * +__dma_buf_io_get_map(struct dma_buf_io_ctx *ctx) +{ + struct dma_buf_io_map *map; + + guard(rcu)(); + + map = rcu_dereference(ctx->map); + if (unlikely(!map || !percpu_ref_tryget_live_rcu(&map->refs))) + return NULL; + + return map; +} + +/** + * dma_buf_io_get_map - Create a new or reference an existing map. + * @ctx: [in] dma-buf I/O context + * @nowait: [in] specifies whether it's allowed to block + * + * Create a new or acquire an existing map. When succeeds, it returns + * a referenced map, which should eventually be put down with + * dma_buf_io_map_drop(). If @nowait is set and the function would block, + * it return -EAGAIN, and the caller is expected to retry from a context + * where blocking is allowed. + * + * Returns a map on success, or ERR_PTR encoded errno otherwise. + */ +static inline struct dma_buf_io_map * +dma_buf_io_get_map(struct dma_buf_io_ctx *ctx, bool nowait) +{ + struct dma_buf_io_map *map; + + map = __dma_buf_io_get_map(ctx); + if (likely(map)) + return map; + + if (nowait) + return ERR_PTR(-EAGAIN); + return dma_buf_io_create_map(ctx); +} + +/** + * dma_buf_io_map_drop - Drop the map. + * @map: [in] dma-buf I/O map + * + * Put down a reference for the @map acquired via dma_buf_io_get_map(). + * Should be called as soon as I/O is completed. + */ +static inline void dma_buf_io_map_drop(struct dma_buf_io_map *map) +{ + percpu_ref_put(&map->refs); +} + +/* + * Device API + */ + +void dma_buf_io_invalidate_mappings(struct dma_buf_io_ctx *ctx); +int dma_buf_io_init_map(struct dma_buf_io_ctx *ctx, struct dma_buf_io_map *map, + struct sg_table *sgt); +void dma_buf_io_detach(struct dma_buf_io_ctx *ctx); + +#endif diff --git a/include/linux/firewire.h b/include/linux/firewire.h index dbb5c825a1cc..9c563fbdbbf0 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -92,17 +92,17 @@ struct fw_card { u64 reset_jiffies; struct { - int current_tlabel; - u64 tlabel_mask; - struct list_head list; + int current_tlabel __guarded_by(&lock); + u64 tlabel_mask __guarded_by(&lock); + struct list_head list __guarded_by(&lock); spinlock_t lock; } transactions; struct { - u32 hi; - u32 lo; - unsigned int cycles; - unsigned int jiffies; + u32 hi __guarded_by(&lock); + u32 lo __guarded_by(&lock); + unsigned int cycles __guarded_by(&lock); + unsigned int jiffies __guarded_by(&lock); spinlock_t lock; } split_timeout; @@ -139,7 +139,7 @@ struct fw_card { u32 broadcast_channel; struct { - __be32 buffer[(CSR_TOPOLOGY_MAP_END - CSR_TOPOLOGY_MAP) / 4]; + __be32 buffer[(CSR_TOPOLOGY_MAP_END - CSR_TOPOLOGY_MAP) / 4] __guarded_by(&lock); spinlock_t lock; } topology_map; @@ -286,20 +286,69 @@ struct fw_request; typedef void (*fw_packet_callback_t)(struct fw_packet *packet, struct fw_card *card, int status); + +/** + * typedef fw_transaction_callback_t - Function to handle the result of outgoing transaction. + * @card: the interface to send the request at + * @rcode: the response code + * @data: the data for the response subaction + * @length: the length of data + * @callback_data: the data registered with this callback + * + * This callback is called from a workqueue in process context after the outgoing transaction is + * completed successfully or unsuccessfully. + * + * Among its parameters is the response code which is either one of the rcodes per IEEE 1394 or, in + * case of internal errors, the firewire-core specific %RCODE_SEND_ERROR. The other firewire-core + * specific rcodes (%RCODE_CANCELLED, %RCODE_BUSY, %RCODE_GENERATION, %RCODE_NO_ACK) denote + * transaction timeout, busy responder, stale request generation, or missing ACK respectively. + * + * Context: Process context. + */ typedef void (*fw_transaction_callback_t)(struct fw_card *card, int rcode, void *data, size_t length, void *callback_data); + +/** + * typedef fw_transaction_callback_with_tstamp_t - Function to handle the result of outgoing + * transaction with hardware time stamps. + * @card: the interface to send the request at + * @rcode: the response code + * @request_tstamp: the time stamp at which the request subaction finished + * @response_tstamp: the time stamp at which the response subaction finished + * @data: the data for the response subaction + * @length: the length of data + * @callback_data: the data registered with this callback + * + * This callback is called from a workqueue in process context after the outgoing transaction is + * completed successfully or unsuccessfully. + * + * Among its parameters is the response code which is either one of the rcodes per IEEE 1394 or, in + * case of internal errors, the firewire-core specific %RCODE_SEND_ERROR. The other firewire-core + * specific rcodes (%RCODE_CANCELLED, %RCODE_BUSY, %RCODE_GENERATION, %RCODE_NO_ACK) denote + * transaction timeout, busy responder, stale request generation, or missing ACK respectively. + * + * The timestamp consists of the low order 3 bits of second field and the full 13 bits of count + * field of isochronous cycle time register. + * + * Context: Process context. + */ typedef void (*fw_transaction_callback_with_tstamp_t)(struct fw_card *card, int rcode, u32 request_tstamp, u32 response_tstamp, void *data, size_t length, void *callback_data); +/** + * union fw_transaction_callback - A union to store the outgoing transaction callback. + * @without_tstamp: Callback without hardware timestamps. + * @with_tstamp: Callback with hardware timestamps. + */ union fw_transaction_callback { fw_transaction_callback_t without_tstamp; fw_transaction_callback_with_tstamp_t with_tstamp; }; /** - * typedef fw_address_callback_t - Function to handle the request of the asynchronous transaction. + * typedef fw_address_callback_t - Function to handle the request of the incoming transaction. * @card: the card instance which receives the request * @request: the request instance. * @tcode: the transaction code @@ -313,8 +362,9 @@ union fw_transaction_callback { * * This callback handles an inbound request subaction. * - * The callback is responsible that fw_send_response() is called on the @request, except for FCP - * registers for which the core takes care of that. + * The contents of @request are opaque to the callback. The callback is responsible for calling + * fw_send_response() for @request, except for FCP registers, for which the core handles the + * response. * * Context: Process context. */ @@ -352,7 +402,15 @@ struct fw_packet { void *driver_data; }; +/** + * struct fw_transaction - A structure to hold outgoing transaction state. + * + * All structure members are for internal use only. Once passed to __fw_send_request(), this + * structure holds the state of an outgoing transaction. It must not be freed until the callback + * reports the transaction result. + */ struct fw_transaction { + /* private: */ int node_id; /* The generation is implied; it is always the current. */ int tlabel; struct list_head link; @@ -377,18 +435,37 @@ struct fw_transaction { u32 response_timestamp; }; +/** + * struct fw_address_handler - A handler for incoming transaction requests to a registered address + * region. + * @offset: The registered offset, available after successful registration. + * @length: The length of the address region in bytes, a multiple of a quadlet. + * @address_callback: Callback invoked when a transaction request is received for the registered + * address region. + * @callback_data: Data passed to @address_callback. + * + * This structure represents a handler registered to receive incoming asynchronous requests to a + * specific region of the address space on the local node. + */ struct fw_address_handler { u64 offset; u64 length; fw_address_callback_t address_callback; void *callback_data; - // Only for core functions. + /* private: */ struct list_head link; struct kref kref; struct completion done; }; +/** + * struct fw_address_region - An address range. + * @start: The starting offset in bytes, a multiple of a quadlet. + * @end: The ending offset in bytes, a multiple of a quadlet. + * + * Represents a range of addresses in the local node's address space. + */ struct fw_address_region { u64 start; u64 end; @@ -429,6 +506,8 @@ void __fw_send_request(struct fw_card *card, struct fw_transaction *t, int tcode * * After the transaction is completed successfully or unsuccessfully, the @callback will be called * in process context. + * + * Context: Any context. */ static inline void fw_send_request(struct fw_card *card, struct fw_transaction *t, int tcode, int destination_id, int generation, int speed, @@ -461,6 +540,8 @@ static inline void fw_send_request(struct fw_card *card, struct fw_transaction * * * After the transaction is completed successfully or unsuccessfully, the @callback will be called * in process context. + * + * Context: Any context. */ static inline void fw_send_request_with_tstamp(struct fw_card *card, struct fw_transaction *t, int tcode, int destination_id, int generation, int speed, unsigned long long offset, diff --git a/include/linux/firmware/intel/stratix10-smc.h b/include/linux/firmware/intel/stratix10-smc.h index 366309260121..6a6fa51ad39e 100644 --- a/include/linux/firmware/intel/stratix10-smc.h +++ b/include/linux/firmware/intel/stratix10-smc.h @@ -725,6 +725,27 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) INTEL_SIP_SMC_ASYNC_VAL(INTEL_SIP_SMC_ASYNC_FUNC_ID_POLL) /** + * Request INTEL_SIP_SMC_ASYNC_POLL_ON_IRQ + * Async call used by service driver at EL1 to retrieve the transaction IDs + * of available responses from the SDM mailbox (typically after an IRQ). + * + * Call register usage: + * a0 INTEL_SIP_SMC_ASYNC_POLL_ON_IRQ + * a1-a17 not used + * + * Return status + * a0 INTEL_SIP_SMC_STATUS_OK + * a1-a4 contain a bitmap of pending transaction IDs (set bit positions) + * a5-a17 not used + * Or + * a0 INTEL_SIP_SMC_STATUS_NO_RESPONSE + * a1-a17 not used + */ +#define INTEL_SIP_SMC_ASYNC_FUNC_ID_IRQ_POLL (0xC9) +#define INTEL_SIP_SMC_ASYNC_POLL_ON_IRQ \ + INTEL_SIP_SMC_ASYNC_VAL(INTEL_SIP_SMC_ASYNC_FUNC_ID_IRQ_POLL) + +/** * Request INTEL_SIP_SMC_ASYNC_HWMON_READTEMP * Async call to request temperature * @@ -813,4 +834,27 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) #define INTEL_SIP_SMC_ASYNC_FUNC_ID_RSU_NOTIFY (0xEC) #define INTEL_SIP_SMC_ASYNC_RSU_NOTIFY \ INTEL_SIP_SMC_ASYNC_VAL(INTEL_SIP_SMC_ASYNC_FUNC_ID_RSU_NOTIFY) + +/** + * Request INTEL_SIP_SMC_SDM_REMAPPER_CONFIG + * + * Sync call to configure the SDM address remapper. On Agilex5, the remapper + * must be bypassed when the SMMU is active to avoid conflicts with IOMMU + * address translation. + * + * Call register usage: + * a0: INTEL_SIP_SMC_SDM_REMAPPER_CONFIG + * a1: INTEL_SIP_SMC_SDM_REMAPPER_ENABLE or INTEL_SIP_SMC_SDM_REMAPPER_BYPASS + * a2-7: not used + * + * Return status: + * a0: INTEL_SIP_SMC_STATUS_OK + * a1-3: not used + */ +#define INTEL_SIP_SMC_FUNCID_SDM_REMAPPER_CONFIG 513 +#define INTEL_SIP_SMC_SDM_REMAPPER_CONFIG \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_SDM_REMAPPER_CONFIG) +#define INTEL_SIP_SMC_SDM_REMAPPER_ENABLE 0 +#define INTEL_SIP_SMC_SDM_REMAPPER_BYPASS 1 + #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index 83d41d9f1130..f387c961e0a0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1914,6 +1914,7 @@ struct dir_context { #define COPY_FILE_SPLICE (1 << 0) struct io_uring_cmd; +struct dma_buf_io_ctx; struct offset_ctx; struct file_operations { @@ -1960,6 +1961,7 @@ struct file_operations { int (*uring_cmd_iopoll)(struct io_uring_cmd *, struct io_comp_batch *, unsigned int poll_flags); int (*mmap_prepare)(struct vm_area_desc *); + int (*init_dma_buf_io_ctx)(struct file *, struct dma_buf_io_ctx *); } __randomize_layout; /* Supports async buffered reads */ diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index c920aba5177c..d1727dffecc5 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -150,10 +150,10 @@ extern int vfs_parse_fs_param_source(struct fs_context *fc, struct fs_parameter *param); extern void fc_drop_locked(struct fs_context *fc); -extern int get_tree_super(struct fs_context *fc, - int (*test)(struct super_block *, struct fs_context *), - int (*fill_super)(struct super_block *sb, - struct fs_context *fc)); +int get_tree_super(struct fs_context *fc, + int (*test)(struct super_block *, struct fs_context *), + int (*fill_super)(struct super_block *sb, + struct fs_context *fc)); extern int get_tree_nodev(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)); diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 618eed4d6d72..a6d5c1a89cff 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -566,6 +566,7 @@ struct fsnotify_mark_connector { unsigned char prio; /* Highest priority group */ #define FSNOTIFY_CONN_FLAG_IS_WATCHED 0x01 #define FSNOTIFY_CONN_FLAG_HAS_IREF 0x02 +#define FSNOTIFY_CONN_FLAG_DESTROYING 0x04 unsigned short flags; /* flags [lock] */ union { /* Object pointer [lock] */ diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index bd76a16a63af..b041d9142d2b 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -416,6 +416,7 @@ void free_ftrace_hash(struct ftrace_hash *hash); struct ftrace_func_entry *add_ftrace_hash_entry_direct(struct ftrace_hash *hash, unsigned long ip, unsigned long direct); void add_ftrace_hash_entry(struct ftrace_hash *hash, struct ftrace_func_entry *entry); +struct ftrace_func_entry *ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip); void ftrace_hash_remove(struct ftrace_hash *hash); /* The hash used to know what functions callbacks trace */ diff --git a/include/linux/futex.h b/include/linux/futex.h index 18ed18d5cbc1..a895d8c69d66 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -23,28 +23,32 @@ struct task_struct; * 01 : Shared futex (PTHREAD_PROCESS_SHARED) * mapped on a file (reference on the underlying inode) * 10 : Shared futex (PTHREAD_PROCESS_SHARED) - * (but private mapping on an mm, and reference taken on it) + * (but private mapping on an mm) */ -#define FUT_OFF_INODE 1 /* We set bit 0 if key has a reference on inode */ -#define FUT_OFF_MMSHARED 2 /* We set bit 1 if key has a reference on mm */ +#define FUT_OFF_INODE 1 /* We set bit 0 if shared key identifies an inode */ +#define FUT_OFF_MMSHARED 2 /* We set bit 1 if shared key identifies an mm */ union futex_key { + /* For FUT_OFF_INODE */ struct { u64 i_seq; unsigned long pgoff; unsigned int offset; /* unsigned int node; */ } shared; + + /* For FUT_OFF_MMSHARED or private */ struct { union { - struct mm_struct *mm; - u64 __tmp; + struct mm_struct *mm; /* for private */ + u64 mm_seq; /* for FUT_OFF_MMSHARED */ }; unsigned long address; unsigned int offset; /* unsigned int node; */ } private; + struct { u64 ptr; unsigned long word; @@ -152,11 +156,10 @@ static inline void futex_set_vdso_cs_range(struct futex_mm_data *fd, unsigned in static inline void futex_fixup_robust_unlock(struct pt_regs *regs) { } #endif /* !CONFIG_FUTEX_ROBUST_UNLOCK */ - -#if defined(CONFIG_FUTEX_PRIVATE_HASH) || defined(CONFIG_FUTEX_ROBUST_UNLOCK) +#ifdef CONFIG_FUTEX void futex_mm_init(struct mm_struct *mm); #else static inline void futex_mm_init(struct mm_struct *mm) { } -#endif +#endif /* !CONFIG_FUTEX */ #endif /* _LINUX_FUTEX_H */ diff --git a/include/linux/futex_types.h b/include/linux/futex_types.h index d320c0571f0c..34b16f2828e7 100644 --- a/include/linux/futex_types.h +++ b/include/linux/futex_types.h @@ -85,10 +85,12 @@ struct futex_unlock_cs_ranges { }; * struct futex_mm_data - Futex related per MM data * @phash: Futex private hash related data * @unlock: Futex unlock VDSO critical sections + * @unique_id: Unique ID of the MM, for FUT_OFF_MMSHARED futexes */ struct futex_mm_data { struct futex_mm_phash phash; struct futex_unlock_cs_ranges unlock; + atomic64_t unique_id; }; #else /* CONFIG_FUTEX */ struct futex_sched_data { }; diff --git a/include/linux/gpio/legacy.h b/include/linux/gpio/legacy.h index 557ef635935e..4001208d5d63 100644 --- a/include/linux/gpio/legacy.h +++ b/include/linux/gpio/legacy.h @@ -63,10 +63,6 @@ static inline int gpio_get_value_cansleep(unsigned gpio) { return gpiod_get_raw_value_cansleep(gpio_to_desc(gpio)); } -static inline void gpio_set_value_cansleep(unsigned gpio, int value) -{ - gpiod_set_raw_value_cansleep(gpio_to_desc(gpio), value); -} static inline int gpio_get_value(unsigned gpio) { @@ -148,12 +144,6 @@ static inline int gpio_get_value_cansleep(unsigned gpio) return 0; } -static inline void gpio_set_value_cansleep(unsigned gpio, int value) -{ - /* GPIO can never have been requested or set as output */ - WARN_ON(1); -} - static inline int gpio_to_irq(unsigned gpio) { /* GPIO can never have been requested or set as input */ diff --git a/include/linux/greybus/bundle.h b/include/linux/greybus/bundle.h index df8d88424cb7..361a94d3499b 100644 --- a/include/linux/greybus/bundle.h +++ b/include/linux/greybus/bundle.h @@ -59,14 +59,9 @@ static inline int gb_pm_runtime_get_sync(struct gb_bundle *bundle) return 0; } -static inline int gb_pm_runtime_put_autosuspend(struct gb_bundle *bundle) +static inline void gb_pm_runtime_put_autosuspend(struct gb_bundle *bundle) { - int retval; - - pm_runtime_mark_last_busy(&bundle->dev); - retval = pm_runtime_put_autosuspend(&bundle->dev); - - return retval; + pm_runtime_put_autosuspend(&bundle->dev); } static inline void gb_pm_runtime_get_noresume(struct gb_bundle *bundle) @@ -82,8 +77,7 @@ static inline void gb_pm_runtime_put_noidle(struct gb_bundle *bundle) #else static inline int gb_pm_runtime_get_sync(struct gb_bundle *bundle) { return 0; } -static inline int gb_pm_runtime_put_autosuspend(struct gb_bundle *bundle) -{ return 0; } +static inline void gb_pm_runtime_put_autosuspend(struct gb_bundle *bundle) {} static inline void gb_pm_runtime_get_noresume(struct gb_bundle *bundle) {} static inline void gb_pm_runtime_put_noidle(struct gb_bundle *bundle) {} diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 73b48dd9f135..2648c49cd8f6 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -108,7 +108,7 @@ DECLARE_PER_CPU(unsigned int, nmi_nesting); #define __preempt_count_nmi_enter() \ do { \ __preempt_count_add(HARDIRQ_OFFSET); \ - /* Maximum NMI nesting is 15. */ \ + /* NMI nesting is represented in 4 bits. */ \ BUG_ON(__this_cpu_read(nmi_nesting) >= 15); \ __this_cpu_inc(nmi_nesting); \ preempt_count_set(preempt_count() | NMI_MASK); \ diff --git a/include/linux/hazptr.h b/include/linux/hazptr.h deleted file mode 100644 index d1670121947a..000000000000 --- a/include/linux/hazptr.h +++ /dev/null @@ -1,325 +0,0 @@ -// SPDX-License-Identifier: LGPL-2.1-or-later -// -// SPDX-FileCopyrightText: 2024 Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - -#ifndef _LINUX_HAZPTR_H -#define _LINUX_HAZPTR_H - -/* - * hazptr: Hazard Pointers - * - * This API provides existence guarantees of objects through hazard - * pointers. - * - * Its main benefit over RCU is that it allows fast reclaim of - * HP-protected pointers without needing to wait for a grace period. - * - * References: - * - * [1]: M. M. Michael, "Hazard pointers: safe memory reclamation for - * lock-free objects," in IEEE Transactions on Parallel and - * Distributed Systems, vol. 15, no. 6, pp. 491-504, June 2004 - */ - -#include <linux/percpu.h> -#include <linux/types.h> -#include <linux/cleanup.h> -#include <linux/sched.h> - -/* 4 slots (each sizeof(hazptr_slot_item)) fit in a single 64-byte cache line. */ -#define NR_HAZPTR_PERCPU_SLOTS 4 - -/* The current hazard pointer wildcard. */ -extern void *hazptr_wildcard; - -/* - * Hazard pointer slot. - */ -struct hazptr_slot { - void *addr; -}; - -struct hazptr_overflow_list; - -struct hazptr_backup_slot { - struct hlist_node overflow_node; - struct hazptr_slot slot; - /* Overflow list where the backup slot is added. */ - struct hazptr_overflow_list *overflow_list; -}; - -struct hazptr_ctx { - struct hazptr_slot *slot; - /* Backup slot in case all per-CPU slots are used. */ - struct hazptr_backup_slot backup_slot; - struct hlist_node preempt_node; -#ifdef CONFIG_HAZPTR_DEBUG - bool detach_task, detach_cpu; /* Whether the ctx has been detached from task/cpu. */ - int acquire_pid, acquire_cpu; /* Note the task and cpu number at acquire. */ - unsigned long acquire_caller; /* Acquire instruction pointer. */ -#endif -}; - -struct hazptr_slot_ctx { - struct hazptr_ctx *ctx; -}; - -struct hazptr_slot_item { - struct hazptr_slot slot; - struct hazptr_slot_ctx ctx; -}; - -struct hazptr_percpu_slots { - struct hazptr_slot_item items[NR_HAZPTR_PERCPU_SLOTS]; -} ____cacheline_aligned; - -DECLARE_PER_CPU(struct hazptr_percpu_slots, hazptr_percpu_slots); - -void *__hazptr_acquire(struct hazptr_ctx *ctx, void * const *addr_p); - -/** - * hazptr_synchronize: Wait for release from hazard-pointer protection - * - * @addr: The address to be released from hazard-pointer protection - * - * Wait for the specified @addr to be released from protection from all - * hazard pointers. The caller should make @addr inaccessible to all - * hazard-pointer readers before invoking this function. - * - * Must be called from preemptible context. - */ -void hazptr_synchronize(void *addr); - -/* - * hazptr_chain_backup_slot: Chain backup slot into overflow list. - * - * Set backup slot address to @addr, and chain it into the overflow - * list. - */ -struct hazptr_slot *hazptr_chain_backup_slot(struct hazptr_ctx *ctx); - -/* - * hazptr_unchain_backup_slot: Unchain backup slot from overflow list. - */ -void hazptr_unchain_backup_slot(struct hazptr_ctx *ctx); - -static inline -bool hazptr_slot_is_backup(struct hazptr_ctx *ctx, struct hazptr_slot *slot) -{ - return slot == &ctx->backup_slot.slot; -} - -/* Internal helper. */ -static inline -void hazptr_promote_to_backup_slot(struct hazptr_ctx *ctx, struct hazptr_slot *slot) -{ - struct hazptr_slot *backup_slot; - - backup_slot = hazptr_chain_backup_slot(ctx); - /* - * Move hazard pointer from the per-CPU slot to the - * backup slot. This requires hazard pointer - * synchronize to iterate on per-CPU slots with - * load-acquire before iterating on the overflow list. - */ - WRITE_ONCE(backup_slot->addr, slot->addr); - /* - * store-release orders store to backup slot addr before - * store to per-CPU slot addr. - */ - smp_store_release(&slot->addr, NULL); - /* Use the backup slot for context. */ - ctx->slot = backup_slot; -} - -/** - * hazptr_detach - Allow a hazard pointer to be released in some other context - * - * @ctx: The hazard-pointer context to be detached. - * - * By default, a given hazptr_acquire() and the corresponding - * hazptr_release() must run in a single execution context, for example, - * the context of a single task or a single interrupt handler. When you - * have acquired a hazard pointer in one context and need to release it - * in another, you must invoke hazptr_detach() on that hazard pointer's - * context. It is permissible to invoke hazptr_detach() multiple times - * on the same @ctx while it is protecting the same pointer, however, - * the first invocation absolutely must be in the same context that did - * the hazptr_acquire(), and must take place after the return from that - * hazptr_acquire(). - * - * For example, if a hazard pointer is acquired by a task and released - * by a timer handler, that task would need to pass the hazard pointer's - * context to hazptr_detach() after return from the hazptr_acquire() and - * before arming the timer (or at least before the handler had a chance - * to access that hazard-pointer context). - */ -static inline -void hazptr_detach(struct hazptr_ctx *ctx) -{ - struct hazptr_slot *slot; - - guard(preempt)(); - slot = ctx->slot; - if (!slot->addr) - return; -#ifdef CONFIG_HAZPTR_DEBUG - ctx->detach_task = ctx->detach_cpu = true; -#endif - if (unlikely(hazptr_slot_is_backup(ctx, slot))) - return; - hazptr_promote_to_backup_slot(ctx, slot); -} - -static inline -void hazptr_note_context_switch(void) -{ - struct hazptr_percpu_slots *percpu_slots = this_cpu_ptr(&hazptr_percpu_slots); - unsigned int idx; - - for (idx = 0; idx < NR_HAZPTR_PERCPU_SLOTS; idx++) { - struct hazptr_slot_item *item = &percpu_slots->items[idx]; - struct hazptr_slot *slot = &item->slot; - - if (!slot->addr) - continue; -#ifdef CONFIG_HAZPTR_DEBUG - item->ctx.ctx->detach_cpu = true; -#endif - hazptr_promote_to_backup_slot(item->ctx.ctx, slot); - } -} - -/** - * hazptr_acquire - Load pointer at address and protect with hazard pointer. - * - * @ctx: The hazard-pointer context to be passed to hazptr_release(). - * @addr_p: Pointer to the pointer that is to be hazard-pointer protected. - * - * Load @addr_p, and protect the loaded pointer with hazard pointer. - * This protection is roughly similar to (but way faster than) that of a - * reference counter, and ends with a later call to hazptr_release(). - * - * This protection is unconditional, and has limitations similar to - * that of unconditional reference-counter acquisition. In particular, - * although holding a hazard pointer prevents a hazard-pointer-protected - * object from being freed, it does not prevent that object from being - * removed from a linked data structure, and does not prevent other - * hazard-pointer-protected objects referenced by this object from being - * both removed and freed. At which point, invoking hazptr_acquire() - * on these dangling pointers would be a bug. On the other hand, use of - * hazptr_acquire() is safe for immortal pointers to objects that do not - * themselves contain pointers to hazard-pointer-protected objects. - * Other (more complex) use cases are also possible. - * - * By default, the call to hazptr_release() must be running in the same - * execution context as the corresponding hazptr_acquire(), for example, - * within the same task or interrupt handler. When it is necessary to - * instead call hazptr_release() from some other context, pass @ctx to - * hazptr_detach() in the original context after invoking hazptr_acquire() - * but before making the hazard pointer available to that other context. - * - * It is not permissible to invoke hazptr_acquire() twice on the same @ctx - * without an intervening hazptr_release(). - * - * Returns a non-NULL protected address if the loaded pointer is non-NULL. - * Returns NULL if the loaded pointer is NULL. - * - * On success the protected hazptr slot is stored in @ctx->slot. - */ -static inline -void *hazptr_acquire(struct hazptr_ctx *ctx, void * const *addr_p) -{ - struct hazptr_percpu_slots *percpu_slots; - struct hazptr_slot_item *slot_item; - struct hazptr_slot *slot; - void *addr; - - guard(preempt)(); - percpu_slots = this_cpu_ptr(&hazptr_percpu_slots); - slot_item = &percpu_slots->items[0]; - slot = &slot_item->slot; -#ifdef CONFIG_HAZPTR_DEBUG - ctx->detach_cpu = ctx->detach_task = false; - ctx->acquire_pid = current->pid; - ctx->acquire_cpu = smp_processor_id(); - ctx->acquire_caller = _THIS_IP_; -#endif - if (unlikely(slot->addr)) - return __hazptr_acquire(ctx, addr_p); - WRITE_ONCE(slot->addr, READ_ONCE(hazptr_wildcard)); /* Store B */ - - /* Memory ordering: Store B before Load A. */ - smp_mb(); - - /* - * Load @addr_p after storing wildcard to the hazard pointer slot. - */ - addr = READ_ONCE(*addr_p); /* Load A */ - - /* - * We don't care about ordering of Store C. It will simply - * replace the wildcard by a more specific address. If addr is - * NULL, we simply store NULL into the slot. - */ - WRITE_ONCE(slot->addr, addr); /* Store C */ - slot_item->ctx.ctx = ctx; - ctx->slot = slot; - return addr; -} - -#ifdef CONFIG_HAZPTR_DEBUG -/* Called with preemption disabled. */ -static inline -void hazptr_release_debug(struct hazptr_ctx *ctx, void *addr) -{ - int pid = current->pid, cpu = smp_processor_id(); - bool warn_remote_cpu = !ctx->detach_cpu && ctx->acquire_cpu != cpu, - warn_remote_task = !ctx->detach_task && ctx->acquire_pid != pid; - - WARN_ONCE(warn_remote_cpu || warn_remote_task, - "Hazard Pointer (addr=%p) released on remote %s without %s. Acquire: caller=%pS, pid=%d, cpu=%d. Release: pid=%d, cpu=%d.", - addr, - warn_remote_task ? "task" : "cpu", - warn_remote_task ? "being detached from task" : "context switch", - (void *) ctx->acquire_caller, ctx->acquire_pid, ctx->acquire_cpu, pid, cpu); -} -#else -static inline void hazptr_release_debug(struct hazptr_ctx *ctx, void *addr) { } -#endif - -/** - * hazptr_release - Release the specified hazard pointer - * - * @ctx: The hazard-pointer context that was passed to hazptr_acquire(). - * @addr_p: The pointer that is to be hazard-pointer unprotected. - * - * Release the protected hazard pointer recorded in @ctx. - * - * By default, hazptr_release() must execute in the same execution context - * that invoked the corresponding hazptr_acquire(), for example, within the - * same task or the same interrupt handler. However, if this restriction - * is problematic for your use case, please see hazptr_detach(). - * - * It is permissible (though unwise from a maintainability viewpoint) - * to invoke hazptr_release() twice on the same @ctx without an intervening - * hazptr_acquire(). - */ -static inline -void hazptr_release(struct hazptr_ctx *ctx, void *addr) -{ - struct hazptr_slot *slot; - - if (!addr) - return; - guard(preempt)(); - hazptr_release_debug(ctx, addr); - slot = ctx->slot; - smp_store_release(&slot->addr, NULL); - if (unlikely(hazptr_slot_is_backup(ctx, slot))) - hazptr_unchain_backup_slot(ctx); -} - -void hazptr_init(void); - -#endif /* _LINUX_HAZPTR_H */ diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 8ca0fa3be2ac..c745f7ad2298 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -510,6 +510,8 @@ change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, int hugepage_madvise(struct vm_area_struct *vma, vm_flags_t *vm_flags, int advice); +int madvise_collapse(struct vm_area_struct *vma, unsigned long start, + unsigned long end, bool *lock_dropped); void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct vm_area_struct *next); spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma); @@ -713,6 +715,13 @@ static inline int hugepage_madvise(struct vm_area_struct *vma, return -EINVAL; } +static inline int madvise_collapse(struct vm_area_struct *vma, + unsigned long start, + unsigned long end, bool *lock_dropped) +{ + return -EINVAL; +} + static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, diff --git a/include/linux/interrupt_rc.h b/include/linux/interrupt_rc.h index a9ed937a80e7..d385ab05a2b6 100644 --- a/include/linux/interrupt_rc.h +++ b/include/linux/interrupt_rc.h @@ -11,6 +11,7 @@ * make it easier to include without hitting circular header dependencies. */ +#include <linux/debug_locks.h> #include <linux/irqflags.h> #include <linux/preempt.h> #include <linux/processor.h> @@ -65,6 +66,13 @@ static inline void local_interrupt_disable(void) local_irq_save(flags); new_count = hardirq_disable_enter(); + /* Is hardirq disable count overflow soon? */ + if (IS_ENABLED(CONFIG_DEBUG_PREEMPT) && + DEBUG_LOCKS_WARN_ON(((new_count & HARDIRQ_DISABLE_MASK) + + (10 << HARDIRQ_DISABLE_SHIFT)) >= + HARDIRQ_DISABLE_MASK)) + return; + if ((new_count & HARDIRQ_DISABLE_MASK) == HARDIRQ_DISABLE_OFFSET) _local_interrupt_save_state(flags); } @@ -73,6 +81,11 @@ static inline void local_interrupt_enable(void) { int new_count; + /* Unpaired local_interrupt_enable()? Warn and abort. */ + if (IS_ENABLED(CONFIG_DEBUG_PREEMPT) && + DEBUG_LOCKS_WARN_ON((preempt_count() & HARDIRQ_DISABLE_MASK) == 0)) + return; + new_count = hardirq_disable_exit(); if ((new_count & HARDIRQ_DISABLE_MASK) == 0) diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 53941c6a6875..50970b382a9a 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -11,6 +11,7 @@ struct iou_loop_params; struct io_uring_bpf_ops; +struct dma_buf_io_map; enum { /* @@ -612,6 +613,7 @@ enum { REQ_F_IMPORT_BUFFER_BIT, REQ_F_SQE_COPIED_BIT, REQ_F_IOPOLL_BIT, + REQ_F_DMABUF_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -707,6 +709,8 @@ enum { REQ_F_SQE_COPIED = IO_REQ_FLAG(REQ_F_SQE_COPIED_BIT), /* request must be iopolled to completion (set in ->issue()) */ REQ_F_IOPOLL = IO_REQ_FLAG(REQ_F_IOPOLL_BIT), + /* there is a dma map attached to request that needs to be dropped */ + REQ_F_DMABUF = IO_REQ_FLAG(REQ_F_DMABUF_BIT), }; struct io_tw_req { @@ -829,6 +833,7 @@ struct io_kiocb { /* custom credentials, valid IFF REQ_F_CREDS is set */ const struct cred *creds; struct io_wq_work work; + struct dma_buf_io_map *dmabuf_map; struct io_big_cqe { u64 extra1; diff --git a/include/linux/iov_iter.h b/include/linux/iov_iter.h index 39ffd5878f50..e88930af7f36 100644 --- a/include/linux/iov_iter.h +++ b/include/linux/iov_iter.h @@ -319,6 +319,8 @@ size_t iterate_and_advance2(struct iov_iter *iter, size_t len, void *priv, return iterate_bvecq(iter, len, priv, priv2, step); if (iov_iter_is_xarray(iter)) return iterate_xarray(iter, len, priv, priv2, step); + if (WARN_ON_ONCE(iov_iter_is_dmabuf_map(iter))) + return 0; return iterate_discard(iter, len, priv, priv2, step); } diff --git a/include/linux/irq-entry-common.h b/include/linux/irq-entry-common.h index 2be273bb68f0..d5a66f54d70b 100644 --- a/include/linux/irq-entry-common.h +++ b/include/linux/irq-entry-common.h @@ -453,6 +453,25 @@ static inline void irqentry_exit_to_kernel_mode_preempt(struct pt_regs *regs, irqentry_exit_cond_resched(); } +/* + * The deferred hrtimer rearm is the tail of the timer interrupt, moved to the + * interrupt return path so that it runs after a possible reschedule. By now + * irq_exit_rcu() has left lockdep's hardirq context. Re-enter it for the + * rearm, so that the hrtimer base lock and the timekeeping sequence count are + * not chained onto the locks held by the interrupted context, which would add + * new lock chains for every lock stack an interrupt hits. + * + * The rearm on return to user mode needs no such annotation: no locks are + * held there, so it uses the same lock chains as the rearm in hardirq + * context. + */ +static __always_inline void irqentry_hrtimer_rearm_deferred(void) +{ + lockdep_hardirq_enter(); + hrtimer_rearm_deferred(); + lockdep_hardirq_exit(); +} + /** * irqentry_exit_to_kernel_mode_after_preempt - Establish trace, lockdep and RCU state * @regs: Pointer to current's pt_regs @@ -476,7 +495,7 @@ irqentry_exit_to_kernel_mode_after_preempt(struct pt_regs *regs, irqentry_state_ */ if (state.exit_rcu) { instrumentation_begin(); - hrtimer_rearm_deferred(); + irqentry_hrtimer_rearm_deferred(); /* Tell the tracer that IRET will enable interrupts */ trace_hardirqs_on_prepare(); lockdep_hardirqs_on_prepare(); @@ -487,7 +506,7 @@ irqentry_exit_to_kernel_mode_after_preempt(struct pt_regs *regs, irqentry_state_ } instrumentation_begin(); - hrtimer_rearm_deferred(); + irqentry_hrtimer_rearm_deferred(); /* Covers both tracing and lockdep */ trace_hardirqs_on(); instrumentation_end(); diff --git a/include/linux/key.h b/include/linux/key.h index bd10fe45819d..dd386c56278c 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -441,6 +441,8 @@ extern int keyring_restrict(key_ref_t keyring, const char *type, const char *restriction); extern void key_register_bpf_keyring(struct key *keyring); +extern void key_register_dm_verity_keyring(struct key *keyring); +extern void key_register_fs_verity_keyring(struct key *keyring); extern struct key *key_lookup(key_serial_t id); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f6e6a6c7b18c..4d4e76a50d77 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -45,6 +45,10 @@ #include <asm/kvm_host.h> #include <linux/kvm_dirty_ring.h> +#define __KVM_DEV_STRING(name, x) __stringify(name ## _ ## x) +#define _KVM_DEV_STRING(name, x) __KVM_DEV_STRING(name, x) +#define KVM_DEV_STRING(x) _KVM_DEV_STRING(KVM_DEV_NAME, x) + #ifndef KVM_MAX_VCPU_IDS #define KVM_MAX_VCPU_IDS KVM_MAX_VCPUS #endif @@ -725,7 +729,11 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) #ifndef kvm_arch_has_readonly_mem static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm) { - return IS_ENABLED(CONFIG_HAVE_KVM_READONLY_MEM); +#ifdef __KVM_HAVE_READONLY_MEM + return true; +#else + return false; +#endif } #endif @@ -817,7 +825,7 @@ struct kvm { struct kvm_vm_stat stat; struct kvm_arch arch; refcount_t users_count; -#ifdef CONFIG_KVM_MMIO +#ifndef __KVM_NO_MMIO struct kvm_coalesced_mmio_ring *coalesced_mmio_ring; spinlock_t ring_lock; struct list_head coalesced_zones; @@ -2462,7 +2470,7 @@ void kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd, struct kvm_kernel_irq_routing_entry *new); #endif /* CONFIG_HAVE_KVM_IRQ_BYPASS */ -#ifdef CONFIG_HAVE_KVM_INVALID_WAKEUPS +#ifdef __KVM_HAVE_INVALID_WAKEUPS /* If we wakeup during the poll time, was it a sucessful poll? */ static inline bool vcpu_valid_wakeup(struct kvm_vcpu *vcpu) { @@ -2474,9 +2482,9 @@ static inline bool vcpu_valid_wakeup(struct kvm_vcpu *vcpu) { return true; } -#endif /* CONFIG_HAVE_KVM_INVALID_WAKEUPS */ +#endif /* __KVM_HAVE_INVALID_WAKEUPS */ -#ifdef CONFIG_HAVE_KVM_NO_POLL +#ifdef __KVM_HAVE_NO_POLL /* Callback that tells if we must not poll */ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu); #else @@ -2484,18 +2492,18 @@ static inline bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) { return false; } -#endif /* CONFIG_HAVE_KVM_NO_POLL */ +#endif /* __KVM_HAVE_NO_POLL */ void kvm_arch_guest_memory_reclaimed(struct kvm *kvm); -#ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE +#ifdef __KVM_HAVE_VCPU_RUN_PID_CHANGE int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu); #else static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) { return 0; } -#endif /* CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE */ +#endif /* __KVM_HAVE_VCPU_RUN_PID_CHANGE */ #ifdef CONFIG_VIRT_XFER_TO_GUEST_WORK static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu) diff --git a/include/linux/landlock.h b/include/linux/landlock.h index 004cbd0b9298..0ee4880988ba 100644 --- a/include/linux/landlock.h +++ b/include/linux/landlock.h @@ -13,14 +13,16 @@ #include <uapi/linux/landlock.h> /* - * Access-right and scope names, shared between the audit records (get_blocker() - * in security/landlock/audit.c) and the trace events + * Access-right, scope, and permission names, shared between the audit records + * (get_blocker() in security/landlock/audit.c) and the trace events * (include/trace/events/landlock.h). A consumer defines * _LANDLOCK_NAME_ENTRY(mask, name) before expanding a list and undefines it * afterwards: audit maps each entry to a "[bit] = name" slot for O(1) lookup, * the trace events map it to a __print_flags() { mask, name } pair. The bit * value lives only in the LANDLOCK_* UAPI constant each entry references. - * Names are unprefixed; audit prepends the "fs."/"net."/"scope." category. + * Access-right and scope names are unprefixed; audit prepends the + * "fs."/"net."/"scope." category. Permission entries carry an action and a + * domain for the qualified and bare views below. */ #define _LANDLOCK_ACCESS_FS_NAMES \ _LANDLOCK_NAME_ENTRY(LANDLOCK_ACCESS_FS_EXECUTE, "execute"), \ @@ -53,4 +55,25 @@ "abstract_unix_socket"), \ _LANDLOCK_NAME_ENTRY(LANDLOCK_SCOPE_SIGNAL, "signal") +#define _LANDLOCK_PERMISSION_NAMESPACE_NAME "namespace" +#define _LANDLOCK_PERMISSION_CAPABILITY_NAME "capability" + +#define _LANDLOCK_PERMISSION_LIST(entry) \ + entry(LANDLOCK_PERMISSION_NAMESPACE_USE, "use", \ + _LANDLOCK_PERMISSION_NAMESPACE_NAME), \ + entry(LANDLOCK_PERMISSION_CAPABILITY_USE, "use", \ + _LANDLOCK_PERMISSION_CAPABILITY_NAME) + +#define _LANDLOCK_PERMISSION_QUALIFIED_ENTRY(mask, action, domain) \ + _LANDLOCK_NAME_ENTRY(mask, domain "." action) + +#define _LANDLOCK_PERMISSION_BARE_ENTRY(mask, action, ...) \ + _LANDLOCK_NAME_ENTRY(mask, action) + +#define _LANDLOCK_PERMISSION_NAMES \ + _LANDLOCK_PERMISSION_LIST(_LANDLOCK_PERMISSION_QUALIFIED_ENTRY) + +#define _LANDLOCK_PERMISSION_BLOCKER_NAMES \ + _LANDLOCK_PERMISSION_LIST(_LANDLOCK_PERMISSION_BARE_ENTRY) + #endif /* _LINUX_LANDLOCK_H */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index ea288cf21400..40e6e0aa2f8d 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -412,9 +412,6 @@ static __always_inline phys_addr_t memblock_phys_alloc(phys_addr_t size, MEMBLOCK_ALLOC_ACCESSIBLE); } -void *memblock_alloc_exact_nid_raw(phys_addr_t size, phys_addr_t align, - phys_addr_t min_addr, phys_addr_t max_addr, - int nid); void *memblock_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid); diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index f6383a57a872..852f331f03fd 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -304,4 +304,20 @@ bool mhi_ep_queue_is_empty(struct mhi_ep_device *mhi_dev, enum dma_data_directio */ int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb); +/** + * mhi_ep_queue_buf - Transfer buffer contents to host over MHI Endpoint + * @mhi_dev: Device associated with the DL channel + * @buf: Buffer to be queued. On success, ownership passes to the MHI stack; + * the caller must not free @buf until the DL transfer callback fires + * with result->buf_addr equal to @buf. On failure, the caller retains + * ownership and must free @buf. + * Note: if @len spans multiple host DL TREs, the DL transfer callback + * fires once per TRE, each time with result->buf_addr equal to @buf. + * @len: Size of the buffer + * + * Return: 0 if the buffer contents have been transferred successfully, a + * negative error code otherwise. + */ +int mhi_ep_queue_buf(struct mhi_ep_device *mhi_dev, void *buf, size_t len); + #endif diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 8247cb0f8dfd..697fc9387b73 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -929,7 +929,7 @@ struct mlx5_ifc_flow_table_nic_cap_bits { struct mlx5_ifc_port_selection_cap_bits { u8 reserved_at_0[0x10]; u8 port_select_flow_table[0x1]; - u8 reserved_at_11[0x1]; + u8 port_select_eswitch[0x1]; u8 port_select_flow_table_bypass[0x1]; u8 reserved_at_13[0xd]; @@ -1070,7 +1070,9 @@ struct mlx5_ifc_e_switch_cap_bits { u8 root_ft_on_other_esw[0x1]; u8 reserved_at_a[0x1]; u8 esw_vport_state_max_tx_speed[0x1]; - u8 reserved_at_c[0xd]; + u8 esw_vport_state_cap_tx_speed[0x1]; + u8 esw_vport_state_effective_tx_speed[0x1]; + u8 reserved_at_e[0xb]; u8 esw_functions_changed[0x1]; u8 reserved_at_1a[0x1]; u8 ecpf_vport_exists[0x1]; @@ -2008,7 +2010,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_3b0[0x2]; u8 qp_latency_sensitive_disable[0x1]; u8 log_max_stride_sz_sq[0x5]; - u8 reserved_at_3b8[0x3]; + u8 reserved_at_3b8[0x1]; + u8 multi_uplink_eswitch[0x1]; + u8 reserved_at_3ba[0x1]; u8 log_min_stride_sz_sq[0x5]; u8 hairpin[0x1]; @@ -5492,6 +5496,9 @@ struct mlx5_ifc_query_vport_state_out_bits { u8 reserved_at_70[0x8]; u8 admin_state[0x4]; u8 state[0x4]; + + u8 cap_tx_speed[0x10]; + u8 effective_tx_speed[0x10]; }; struct mlx5_ifc_array1024_auto_bits { @@ -7948,6 +7955,9 @@ struct mlx5_ifc_modify_vport_state_in_bits { u8 reserved_at_74[0x4]; u8 admin_state[0x4]; u8 reserved_at_7c[0x4]; + + u8 cap_tx_speed[0x10]; + u8 effective_tx_speed[0x10]; }; struct mlx5_ifc_modify_tis_out_bits { diff --git a/include/linux/mm.h b/include/linux/mm.h index 26979c5f8f2e..ba755a438fa0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1695,57 +1695,22 @@ static inline bool vma_is_fixed_mapping(const struct vm_area_struct *vma) } /** - * vma_flags_can_merge() - Do the specified VMA flags permit the VMA to be - * merged with another? - * @flags: The VMA flags to test. - * Returns: true if the flags permit merging, false otherwise. - */ -static inline bool vma_flags_can_merge(const vma_flags_t *flags) -{ - /* - * VMA merging assumes that a VMA's flags and fields completely describe - * its state. - * - * However, mappings which are not mm-managed may have established state - * upon mapping not embodied in any attribute of the VMA. - * - * Additionally, private (CoW) PFN maps encode the source PFN of the - * range in vma->vm_pgoff, which may otherwise cause spurious merges. - */ - if (!vma_flags_is_mm_managed(flags)) - return false; - /* VMA explicitly marked as being unmergeable. */ - if (vma_flags_is_fixed_mapping(flags)) - return false; - - return true; -} - -/** - * vma_can_merge() - Do @vma's flags permit it to be merged with another VMA? - * @vma: The VMA to test. - * Returns: true if the flags permit merging, otherwise false. - */ -static inline bool vma_can_merge(const struct vm_area_struct *vma) -{ - return vma_flags_can_merge(&vma->flags); -} - -/** * vma_flags_is_mm_backed() - Do the specified VMA flags imply the mapping is * backed by core mm? * @flags: The VMA flags to test. * * An mm-backed mapping is one managed by core mm (see - * vma_flags_is_mm_managed()) for which two further things are true: + * vma_flags_is_mm_managed()) whose contents are established by core mm's own + * fault path rather than a custom ->fault handler. * - * 1. Everything mapped was placed there by core mm's fault path (no custom - * ->fault). - * 2. What is mapped stays there until it is zapped or unmapped by the user. + * Mappings not managed by core mm are populated by their owner, and fixed + * mappings may be mm-managed but have their contents established by a custom + * ->fault handler, so neither are mm-backed. hugetlb mappings are fixed, but + * core mm owns them entirely, so they are. * - * These mappings are the only ones which can be sensibly locked, merged, dumped - * or be subject to uffd faulting, as all of these assume core mm and core mm - * alone manages these, and that the mappings will remain there. + * These are the only mappings which can sensibly be merged, locked, dumped or + * be subject to uffd faulting, as all of these assume core mm and core mm + * alone manages their contents. * * Returns: true if the flags imply an mm-backed mapping, otherwise false. */ @@ -1761,11 +1726,7 @@ static inline bool vma_flags_is_mm_backed(const vma_flags_t *flags) * by a custom ->fault handler, so core mm cannot assume ordinary fault * semantics over them. */ - if (!vma_flags_is_mm_managed(flags) || - vma_flags_is_fixed_mapping(flags)) - return false; - /* Core mm may discard droppable memory at any time. */ - return !vma_flags_test_single_mask(flags, VMA_DROPPABLE); + return vma_flags_is_mm_managed(flags) && !vma_flags_is_fixed_mapping(flags); } /** @@ -1782,6 +1743,43 @@ static inline bool vma_is_mm_backed(const struct vm_area_struct *vma) } /** + * vma_flags_can_merge() - Do the specified VMA flags permit the VMA to be + * merged with another? + * @flags: The VMA flags to test. + * Returns: true if the flags permit merging, false otherwise. + */ +static inline bool vma_flags_can_merge(const vma_flags_t *flags) +{ + /* + * VMA merging assumes that a VMA's flags and fields completely describe + * its state, which is only the case for mm-backed mappings. + * + * Mappings which are not mm-managed may have established state upon + * mapping not embodied in any attribute of the VMA. + * + * Additionally, private (CoW) PFN maps encode the source PFN of the + * range in vma->vm_pgoff, which may otherwise cause spurious merges. + */ + if (!vma_flags_is_mm_backed(flags)) + return false; + /* + * hugetlb mappings contain per-VMA state, so their flags and fields do + * not completely describe them. + */ + return !vma_flags_is_hugetlb(flags); +} + +/** + * vma_can_merge() - Do @vma's flags permit it to be merged with another VMA? + * @vma: The VMA to test. + * Returns: true if the flags permit merging, otherwise false. + */ +static inline bool vma_can_merge(const struct vm_area_struct *vma) +{ + return vma_flags_can_merge(&vma->flags); +} + +/** * vma_kernel_pagesize - Default page size granularity for this VMA. * @vma: The user mapping. * @@ -3969,23 +3967,6 @@ static inline void pagetable_free_kernel(struct ptdesc *pt) __pagetable_free(pt); } #endif -/** - * pagetable_free - Free pagetables - * @pt: The page table descriptor - * - * pagetable_free frees the memory of all page tables described by a page - * table descriptor and the memory for the descriptor itself. - */ -static inline void pagetable_free(struct ptdesc *pt) -{ - if (ptdesc_test_kernel(pt)) { - ptdesc_clear_kernel(pt); - pagetable_free_kernel(pt); - } else { - __pagetable_free(pt); - } -} - #if defined(CONFIG_SPLIT_PTE_PTLOCKS) #if ALLOC_SPLIT_PTLOCKS void __init ptlock_cache_init(void); @@ -4078,6 +4059,26 @@ static inline void pagetable_dtor(struct ptdesc *ptdesc) lruvec_stat_sub_folio(folio, NR_PAGETABLE); } +/** + * pagetable_free - Free pagetables + * @pt: The page table descriptor + * + * pagetable_free frees the memory of all page tables described by a page + * table descriptor and the memory for the descriptor itself. + */ +static inline void pagetable_free(struct ptdesc *pt) +{ + if (PageTable(ptdesc_page(pt))) + pagetable_dtor(pt); + + if (ptdesc_test_kernel(pt)) { + ptdesc_clear_kernel(pt); + pagetable_free_kernel(pt); + } else { + __pagetable_free(pt); + } +} + static inline void pagetable_dtor_free(struct ptdesc *ptdesc) { pagetable_dtor(ptdesc); @@ -4834,28 +4835,26 @@ discontig_kernel_map_abort(struct discontig_kernel_page_state *state) static inline void discontig_kernel_map_page(struct discontig_kernel_page_state *state, - struct page *page) + struct page *page) { struct folio *folio = page_folio(page); + unsigned long nr_pages = 1; if (folio_test_large(folio)) { VM_WARN_ON_ONCE(page != folio_page(folio, 0)); - state->action = DISCONTIG_KERNEL_PAGE_MAP_COMPOUND_PAGE; - state->__folio = folio; - state->__nr_pages = min(state->nr_pages_remain, - folio_nr_pages(folio)); - } else { - state->action = DISCONTIG_KERNEL_PAGE_MAP_PAGE; - state->__page = page; - state->__nr_pages = 1; + nr_pages = folio_nr_pages(folio); } + + state->action = DISCONTIG_KERNEL_PAGE_MAP_CONTIG_PAGES; + state->__page = page; + state->__nr_pages = min(nr_pages, state->nr_pages_remain); } static inline void -discontig_kernel_map_page_range(struct discontig_kernel_page_state *state, - struct page **page_arr, unsigned long nr_pages) +discontig_kernel_map_pages(struct discontig_kernel_page_state *state, + struct page **page_arr, unsigned long nr_pages) { - state->action = DISCONTIG_KERNEL_PAGE_MAP_PAGE_RANGE; + state->action = DISCONTIG_KERNEL_PAGE_MAP_PAGES; state->__page_arr = page_arr; state->__nr_pages = min(nr_pages, state->nr_pages_remain); } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6141160ec652..0dead656d3e3 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -825,9 +825,8 @@ enum mmap_action_type { enum discontig_kernel_page_action { DISCONTIG_KERNEL_PAGE_ABORT, - DISCONTIG_KERNEL_PAGE_MAP_PAGE, - DISCONTIG_KERNEL_PAGE_MAP_COMPOUND_PAGE, - DISCONTIG_KERNEL_PAGE_MAP_PAGE_RANGE, + DISCONTIG_KERNEL_PAGE_MAP_PAGES, /* Array of individual pages. */ + DISCONTIG_KERNEL_PAGE_MAP_CONTIG_PAGES, /* 1..N contiguous pages. */ }; struct discontig_kernel_page_state { @@ -847,7 +846,6 @@ struct discontig_kernel_page_state { enum discontig_kernel_page_action action; union { struct page *__page; - struct folio *__folio; struct page **__page_arr; }; unsigned long __nr_pages; diff --git a/include/linux/module.h b/include/linux/module.h index 2c5a02621c19..76f4f3596477 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -503,6 +503,10 @@ struct module { void *btf_data; void *btf_base_data; #endif +#if IS_ENABLED(CONFIG_DEBUG_INFO_BTF_INLINE) + unsigned int btf_inline_data_size; + void *btf_inline_data; +#endif #ifdef CONFIG_JUMP_LABEL struct jump_entry *jump_entries; unsigned int num_jump_entries; diff --git a/include/linux/mtd/nand-qpic-common.h b/include/linux/mtd/nand-qpic-common.h index 0f40964eefe7..f31fd18d837f 100644 --- a/include/linux/mtd/nand-qpic-common.h +++ b/include/linux/mtd/nand-qpic-common.h @@ -457,6 +457,12 @@ struct qcom_nandc_props { bool use_codeword_fixup; }; +struct qcom_nandc_read_stats { + __le32 flash; + __le32 buffer; + __le32 erased_cw; +}; + void qcom_free_bam_transaction(struct qcom_nand_controller *nandc); struct bam_transaction *qcom_alloc_bam_transaction(struct qcom_nand_controller *nandc); void qcom_clear_bam_transaction(struct qcom_nand_controller *nandc); @@ -482,5 +488,16 @@ int qcom_submit_descs(struct qcom_nand_controller *nandc); void qcom_clear_read_regs(struct qcom_nand_controller *nandc); void qcom_nandc_unalloc(struct qcom_nand_controller *nandc); int qcom_nandc_alloc(struct qcom_nand_controller *nandc); +int qcom_nandc_check_flash_errors(struct qcom_nand_controller *nandc, + int cw_cnt); +void qcom_nandc_config_page_read(struct qcom_nand_controller *nandc); +void qcom_nandc_config_page_write(struct qcom_nand_controller *nandc); +void qcom_nandc_config_cw_write(struct qcom_nand_controller *nandc); +void qcom_nandc_set_read_loc_first(struct qcom_nand_controller *nandc, + int reg_base, u32 cw_offset, + u32 read_size, u32 is_last_read_loc); +void qcom_nandc_set_read_loc_last(struct qcom_nand_controller *nandc, + int reg_base, u32 cw_offset, + u32 read_size, u32 is_last_read_loc); #endif diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5b4b92e76b67..8fbe3a5d8169 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -5500,7 +5500,14 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev, netdev_features_t passthru_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features); -netdev_features_t netif_skb_features(struct sk_buff *skb); +netdev_features_t __netif_skb_features(struct sk_buff *skb, + bool check_gso_limits); + +static inline netdev_features_t netif_skb_features(struct sk_buff *skb) +{ + return __netif_skb_features(skb, true); +} + void skb_warn_bad_offload(const struct sk_buff *skb); static inline bool net_gso_ok(netdev_features_t features, int gso_type) @@ -5566,15 +5573,6 @@ netif_get_gro_max_size(const struct net_device *dev, const struct sk_buff *skb) READ_ONCE(dev->gro_ipv4_max_size); } -static inline unsigned int -netif_get_gso_max_size(const struct net_device *dev, const struct sk_buff *skb) -{ - /* pairs with WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */ - return skb->protocol == htons(ETH_P_IPV6) ? - READ_ONCE(dev->gso_max_size) : - READ_ONCE(dev->gso_ipv4_max_size); -} - static inline bool netif_is_macsec(const struct net_device *dev) { return dev->priv_flags & IFF_MACSEC; diff --git a/include/linux/nfs_common.h b/include/linux/nfs_common.h index a541c3a02887..88dccd8564cf 100644 --- a/include/linux/nfs_common.h +++ b/include/linux/nfs_common.h @@ -6,11 +6,11 @@ #define _LINUX_NFS_COMMON_H #include <linux/errno.h> -#include <uapi/linux/nfs.h> +#include <linux/types.h> /* Mapping from NFS error code to "errno" error code. */ -int nfs_stat_to_errno(enum nfs_stat status); +int nfs_stat_to_errno(int status); int nfs4_stat_to_errno(int stat); __u32 nfs_localio_errno_to_nfs4_stat(int errno); diff --git a/include/linux/overflow.h b/include/linux/overflow.h index a8cb6319b4fb..d0f04436343e 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -418,7 +418,7 @@ static __always_inline size_t __must_check size_sub(size_t minuend, size_t subtr #define flex_array_size(p, member, count) \ __builtin_choose_expr(__is_constexpr(count), \ (count) * sizeof(*(p)->member) + __must_be_array((p)->member), \ - size_mul(count, sizeof(*(p)->member) + __must_be_array((p)->member))) + size_mul(count, sizeof(*(p)->member)) + __must_be_array((p)->member)) /** * struct_size() - Calculate size of structure with trailing flexible array. diff --git a/include/linux/pci.h b/include/linux/pci.h index d1dad3a3b1d0..6482549a8417 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -468,6 +468,7 @@ struct pci_dev { unsigned int is_busmaster:1; /* Is busmaster */ unsigned int no_msi:1; /* May not use MSI */ + unsigned int no_aer_anfe:1; /* Do not unmask ANFE */ unsigned int block_cfg_access:1; /* Config space access blocked */ unsigned int broken_parity_status:1; /* Generates false positive parity */ unsigned int irq_reroute_variant:2; /* Needs IRQ rerouting variant */ @@ -615,7 +616,10 @@ static inline struct pci_dev *pci_physfn(struct pci_dev *dev) struct pci_dev *pci_alloc_dev(struct pci_bus *bus); -#define to_pci_dev(n) container_of(n, struct pci_dev, dev) +static inline struct pci_dev *to_pci_dev(const struct device *dev) +{ + return container_of(dev, struct pci_dev, dev); +} #define for_each_pci_dev(d) while ((d = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, d)) != NULL) #define for_each_pci_dev_reverse(d) \ while ((d = pci_get_device_reverse(PCI_ANY_ID, PCI_ANY_ID, d)) != NULL) @@ -1484,7 +1488,7 @@ int pcie_set_mps(struct pci_dev *dev, int mps); u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev, enum pci_bus_speed *speed, enum pcie_link_width *width); -int pcie_link_speed_mbps(struct pci_dev *pdev); +int pcie_link_bandwidth_mbps(struct pci_dev *pdev); void pcie_print_link_status(struct pci_dev *dev); int pcie_reset_flr(struct pci_dev *dev, bool probe); int pcie_flr(struct pci_dev *dev); @@ -1960,10 +1964,9 @@ int pci_disable_link_state(struct pci_dev *pdev, int state); int pci_disable_link_state_locked(struct pci_dev *pdev, int state); int pci_enable_link_state(struct pci_dev *pdev, int state); int pci_enable_link_state_locked(struct pci_dev *pdev, int state); -int pci_force_enable_link_state(struct pci_dev *pdev, int state); void pcie_no_aspm(void); bool pcie_aspm_support_enabled(void); -u32 pcie_aspm_enabled(struct pci_dev *pdev); +bool pcie_aspm_enabled(struct pci_dev *pdev); #else static inline int pci_disable_link_state(struct pci_dev *pdev, int state) { return 0; } @@ -1973,11 +1976,9 @@ static inline int pci_enable_link_state(struct pci_dev *pdev, int state) { return 0; } static inline int pci_enable_link_state_locked(struct pci_dev *pdev, int state) { return 0; } -static inline int pci_force_enable_link_state(struct pci_dev *pdev, int state) -{ return 0; } static inline void pcie_no_aspm(void) { } static inline bool pcie_aspm_support_enabled(void) { return false; } -static inline u32 pcie_aspm_enabled(struct pci_dev *pdev) { return 0; } +static inline bool pcie_aspm_enabled(struct pci_dev *pdev) { return false; } #endif #ifdef CONFIG_HOTPLUG_PCI diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 0693e4532a68..030c86dd6d67 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -889,6 +889,7 @@ #define PCI_DEVICE_ID_TI_XX12 0x8039 #define PCI_DEVICE_ID_TI_XX12_FM 0x803b #define PCI_DEVICE_ID_TI_XIO2000A 0x8231 +#define PCI_DEVICE_ID_TI_TUSB73X0 0x8241 #define PCI_DEVICE_ID_TI_1130 0xac12 #define PCI_DEVICE_ID_TI_1031 0xac13 #define PCI_DEVICE_ID_TI_1131 0xac15 diff --git a/include/linux/pid.h b/include/linux/pid.h index ddaef0bbc8ba..185bf0cde2d1 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -2,6 +2,9 @@ #ifndef _LINUX_PID_H #define _LINUX_PID_H +#include <linux/array_size.h> +#include <linux/build_bug.h> +#include <linux/minmax.h> #include <linux/pid_types.h> #include <linux/rculist.h> #include <linux/rcupdate.h> @@ -92,6 +95,56 @@ static inline struct pid *get_pid(struct pid *pid) } extern void put_pid(struct pid *pid); + +/* + * Helpers for arrays of struct pid indexed by pid type declared with + * DECLARE_PIDS(). The array covers PIDTYPE_PID up to the pid type it + * was declared with and the helpers take that bound from the array. + */ +static inline void __get_pids(struct pid **dst, struct pid *const *src, + enum pid_type last) +{ + for (enum pid_type type = PIDTYPE_PID; type <= last; type++) + dst[type] = get_pid(src[type]); +} + +static inline void __put_pids(struct pid **pids, enum pid_type last) +{ + for (enum pid_type type = PIDTYPE_PID; type <= last; type++) { + put_pid(pids[type]); + pids[type] = NULL; + } +} + +static inline void __swap_pids(struct pid **a, struct pid **b, + enum pid_type last) +{ + for (enum pid_type type = PIDTYPE_PID; type <= last; type++) + swap(a[type], b[type]); +} + +static inline bool __pids_equal(struct pid *const *a, struct pid *const *b, + enum pid_type last) +{ + for (enum pid_type type = PIDTYPE_PID; type <= last; type++) + if (a[type] != b[type]) + return false; + return true; +} + +/* The last pid type an array declared with DECLARE_PIDS() covers. */ +#define pids_last(pids) \ + ((enum pid_type)(ARRAY_SIZE(pids) - 1 + \ + BUILD_BUG_ON_ZERO(ARRAY_SIZE(pids) > PIDTYPE_MAX))) + +#define __pids_last2(a, b) \ + (pids_last(a) + BUILD_BUG_ON_ZERO(ARRAY_SIZE(a) != ARRAY_SIZE(b))) + +#define get_pids(dst, src) __get_pids(dst, src, __pids_last2(dst, src)) +#define put_pids(pids) __put_pids(pids, pids_last(pids)) +#define swap_pids(a, b) __swap_pids(a, b, __pids_last2(a, b)) +#define pids_equal(a, b) __pids_equal(a, b, __pids_last2(a, b)) + extern struct task_struct *pid_task(struct pid *pid, enum pid_type); static inline bool pid_has_task(struct pid *pid, enum pid_type type) { @@ -187,6 +240,15 @@ static inline pid_t pid_nr(struct pid *pid) pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns); pid_t pid_vnr(struct pid *pid); +/* + * Needs tasklist_lock if type > PIDTYPE_TGID. A lockless reader can: + * + * - race with a change_pid() that moves the task to another hlist, + * and continue to scan the wrong list. + * + * - race with a copy_process() that adds a new task to the start of hlist, + * and miss the new child. + */ #define do_each_pid_task(pid, type, task) \ do { \ if ((pid) != NULL) \ @@ -264,7 +326,7 @@ static inline pid_t task_tgid_nr(struct task_struct *tsk) */ static inline int pid_alive(const struct task_struct *p) { - return p->thread_pid != NULL; + return READ_ONCE(p->thread_pid) != NULL; } static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) diff --git a/include/linux/pid_types.h b/include/linux/pid_types.h index c2aee1d91dcf..3302690a2a28 100644 --- a/include/linux/pid_types.h +++ b/include/linux/pid_types.h @@ -2,6 +2,8 @@ #ifndef _LINUX_PID_TYPES_H #define _LINUX_PID_TYPES_H +#include <linux/build_bug.h> + enum pid_type { PIDTYPE_PID, PIDTYPE_TGID, @@ -10,6 +12,12 @@ enum pid_type { PIDTYPE_MAX, }; +struct pid; + +/* An array of struct pid indexed by pid type, PIDTYPE_PID up to @last. */ +#define DECLARE_PIDS(name, last) \ + struct pid *name[(last) + 1 + BUILD_BUG_ON_ZERO((last) >= PIDTYPE_MAX)] + struct pid_namespace; extern struct pid_namespace init_pid_ns; diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h index 0abf7da9ab23..3c1e82f1a369 100644 --- a/include/linux/pidfs.h +++ b/include/linux/pidfs.h @@ -3,6 +3,7 @@ #define _LINUX_PID_FS_H #include <linux/gfp_types.h> +#include <linux/pid.h> struct coredump_params; @@ -32,5 +33,9 @@ static inline int pidfs_register_pid(struct pid *pid) } void pidfs_free_pid(struct pid *pid); +int __pidfs_register_pids(struct pid *const *pids, enum pid_type last); + +/* Register the pids of an array declared with DECLARE_PIDS(). */ +#define pidfs_register_pids(pids) __pidfs_register_pids(pids, pids_last(pids)) #endif /* _LINUX_PID_FS_H */ diff --git a/include/linux/platform_data/dmtimer-omap.h b/include/linux/platform_data/dmtimer-omap.h index 726d89143842..b78ee4676b98 100644 --- a/include/linux/platform_data/dmtimer-omap.h +++ b/include/linux/platform_data/dmtimer-omap.h @@ -57,6 +57,8 @@ struct dmtimer_platform_data { u32 timer_errata; int (*get_context_loss_count)(struct device *); const struct omap_dm_timer_ops *timer_ops; + /* always-on timers can be used for clocksource/clockevent */ + bool system_timer_capable; }; #endif /* __PLATFORM_DATA_DMTIMER_OMAP_H__ */ diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index d2fa1c41bfd2..b9fc1be86ae3 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -15,6 +15,8 @@ #include <linux/compiler.h> #include <linux/rbtree.h> #include <linux/rcupdate.h> +#include <linux/args.h> +#include <linux/minmax.h> /* * Please note - only struct rb_augment_callbacks and the prototypes for @@ -28,6 +30,7 @@ struct rb_augment_callbacks { void (*propagate)(struct rb_node *node, struct rb_node *stop); void (*copy)(struct rb_node *old, struct rb_node *new); void (*rotate)(struct rb_node *old, struct rb_node *new); + void (*merge)(struct rb_node *node, struct rb_node *new); }; extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root, @@ -60,6 +63,12 @@ rb_insert_augmented_cached(struct rb_node *node, rb_insert_augmented(node, &root->rb_root, augment); } +/* + * Insert @node into the leftmost cached augmented tree @tree. + * + * The augmented data of @node must already describe @node alone; it is + * merged into every ancestor on the way down through augment->merge(). + */ static __always_inline struct rb_node * rb_add_augmented_cached(struct rb_node *node, struct rb_root_cached *tree, bool (*less)(struct rb_node *, const struct rb_node *), @@ -71,6 +80,7 @@ rb_add_augmented_cached(struct rb_node *node, struct rb_root_cached *tree, while (*link) { parent = *link; + augment->merge(parent, node); if (less(node, parent)) { link = &parent->rb_left; } else { @@ -80,12 +90,108 @@ rb_add_augmented_cached(struct rb_node *node, struct rb_root_cached *tree, } rb_link_node(node, parent, link); - augment->propagate(parent, NULL); /* suboptimal */ rb_insert_augmented_cached(node, tree, leftmost, augment); return leftmost ? node : NULL; } +#define RB_FOR_EACH_1(what, RBNAME, RBSTRUCT, RBFIELD, x) \ + what(1, RBNAME, RBSTRUCT, RBFIELD, x) + +#define RB_FOR_EACH_2(what, RBNAME, RBSTRUCT, RBFIELD, x, ...) \ + what(2, RBNAME, RBSTRUCT, RBFIELD, x) \ + RB_FOR_EACH_1(what, RBNAME, RBSTRUCT, RBFIELD, __VA_ARGS__) + +#define RB_FOR_EACH_3(what, RBNAME, RBSTRUCT, RBFIELD, x, ...) \ + what(3, RBNAME, RBSTRUCT, RBFIELD, x) \ + RB_FOR_EACH_2(what, RBNAME, RBSTRUCT, RBFIELD, __VA_ARGS__) + +#define RB_FOR_EACH_4(what, RBNAME, RBSTRUCT, RBFIELD, x, ...) \ + what(4, RBNAME, RBSTRUCT, RBFIELD, x) \ + RB_FOR_EACH_3(what, RBNAME, RBSTRUCT, RBFIELD, __VA_ARGS__) + +#define RB_FOR_EACH_5(what, RBNAME, RBSTRUCT, RBFIELD, x, ...) \ + what(5, RBNAME, RBSTRUCT, RBFIELD, x) \ + RB_FOR_EACH_4(what, RBNAME, RBSTRUCT, RBFIELD, __VA_ARGS__) + +#define RB_FOR_EACH_6(what, RBNAME, RBSTRUCT, RBFIELD, x, ...) \ + what(6, RBNAME, RBSTRUCT, RBFIELD, x) \ + RB_FOR_EACH_5(what, RBNAME, RBSTRUCT, RBFIELD, __VA_ARGS__) + +#define RB_FOR_EACH_7(what, RBNAME, RBSTRUCT, RBFIELD, x, ...) \ + what(7, RBNAME, RBSTRUCT, RBFIELD, x) \ + RB_FOR_EACH_6(what, RBNAME, RBSTRUCT, RBFIELD, __VA_ARGS__) + +#define RB_FOR_EACH_8(what, RBNAME, RBSTRUCT, RBFIELD, x, ...) \ + what(8, RBNAME, RBSTRUCT, RBFIELD, x) \ + RB_FOR_EACH_7(what, RBNAME, RBSTRUCT, RBFIELD, __VA_ARGS__) + +#define RB_FOR_EACH(action, RBNAME, RBSTRUCT, RBFIELD, ...) \ + CONCATENATE(RB_FOR_EACH_, COUNT_ARGS(__VA_ARGS__)) \ + (action, RBNAME, RBSTRUCT, RBFIELD, __VA_ARGS__) + +/* + * One augmented field: @val is the node's own contribution (a member for + * RB_AUG(), a function of the node for RB_AUG_FUNC()), @aug the member + * holding the aggregate over the subtree, and @fold(a, b) combines two + * aggregates: min, max, a sum, ... It must be commutative and associative. + */ +#define RB_AUG_FUNC(val, aug, fold) (val(s), aug, fold) +#define RB_AUG(val, aug, fold) (s->val, aug, fold) +#define RB_UNPACK(...) __VA_ARGS__ + +#define __RB_INST(n, RBNAME, RBSTRUCT, RBFIELD, val, aug, fold) \ +static inline void \ +RBNAME ## _copy_ ## n(RBSTRUCT *old, RBSTRUCT *new) \ +{ \ + new->aug = old->aug; \ +} \ +static inline bool \ +RBNAME ## _compute_ ## n(RBSTRUCT *s, bool exit) \ +{ \ + TYPEOF_UNQUAL(s->aug) _old_aug = s->aug; \ + TYPEOF_UNQUAL(s->aug) _val = val; \ + struct rb_node *_node = &s->RBFIELD; \ + if (_node->rb_right) { \ + RBSTRUCT *_c = container_of(_node->rb_right, typeof(*s), RBFIELD); \ + _val = fold(_val, _c->aug); \ + } \ + if (_node->rb_left) { \ + RBSTRUCT *_c = container_of(_node->rb_left, typeof(*s), RBFIELD); \ + _val = fold(_val, _c->aug); \ + } \ + if (exit && _old_aug == _val) \ + return true; \ + s->aug = _val; \ + return false; \ +} +#define _RB_INST(n, RBNAME, RBSTRUCT, RBFIELD, args) \ + __RB_INST(n, RBNAME, RBSTRUCT, RBFIELD, args) +#define RB_INST(n, RBNAME, RBSTRUCT, RBFIELD, x) \ + _RB_INST(n, RBNAME, RBSTRUCT, RBFIELD, RB_UNPACK x) + +#define __RB_COPY(n, RBNAME, RBSTRUCT, RBFIELD, val, aug, fold) \ + RBNAME ## _copy_ ## n(old, new); +#define _RB_COPY(n, RBNAME, RBSTRUCT, RBFIELD, args) \ + __RB_COPY(n, RBNAME, RBSTRUCT, RBFIELD, args) +#define RB_COPY(n, RBNAME, RBSTRUCT, RBFIELD, x) \ + _RB_COPY(n, RBNAME, RBSTRUCT, RBFIELD, RB_UNPACK x) + +#define __RB_COMPUTE(n, RBNAME, RBSTRUCT, RBFIELD, val, aug, fold) \ + ret &= RBNAME ## _compute_ ## n(node, exit); +#define _RB_COMPUTE(n, RBNAME, RBSTRUCT, RBFIELD, args) \ + __RB_COMPUTE(n, RBNAME, RBSTRUCT, RBFIELD, args) +#define RB_COMPUTE(n, RBNAME, RBSTRUCT, RBFIELD, x) \ + _RB_COMPUTE(n, RBNAME, RBSTRUCT, RBFIELD, RB_UNPACK x) + +/* fold @new, about to become a descendant of @node, into @node */ +#define __RB_MERGE(n, RBNAME, RBSTRUCT, RBFIELD, val, aug, fold) \ + node->aug = fold(node->aug, new->aug); +#define _RB_MERGE(n, RBNAME, RBSTRUCT, RBFIELD, args) \ + __RB_MERGE(n, RBNAME, RBSTRUCT, RBFIELD, args) +#define RB_MERGE(n, RBNAME, RBSTRUCT, RBFIELD, x) \ + _RB_MERGE(n, RBNAME, RBSTRUCT, RBFIELD, RB_UNPACK x) + /* * Template for declaring augmented rbtree callbacks (generic multi fields) * @@ -93,18 +199,29 @@ rb_add_augmented_cached(struct rb_node *node, struct rb_root_cached *tree, * RBNAME: name of the rb_augment_callbacks structure * RBSTRUCT: struct type of the tree nodes * RBFIELD: name of struct rb_node field within RBSTRUCT - * RBCOPY: name of function that copies the RBAUGMENTED datas - * RBCOMPUTE: name of function that recomputes the RBAUGMENTED datas + * RBAUG...: list of RB_AUG() describing the augmented data */ - -#define RB_DECLARE_CALLBACKS_MULTI(RBSTATIC, RBNAME, \ - RBSTRUCT, RBFIELD, RBCOPY, RBCOMPUTE) \ +#define RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ + RBSTRUCT, RBFIELD, RBAUG...) \ +RB_FOR_EACH(RB_INST, RBNAME, RBSTRUCT, RBFIELD, RBAUG) \ +static inline void \ +RBNAME ## __copy(RBSTRUCT *old, RBSTRUCT *new) \ +{ \ + RB_FOR_EACH(RB_COPY, RBNAME, RBSTRUCT, RBFIELD, RBAUG); \ +} \ +static inline bool \ +RBNAME ## __compute(RBSTRUCT *node, bool exit) \ +{ \ + bool ret = true; \ + RB_FOR_EACH(RB_COMPUTE, RBNAME, RBSTRUCT, RBFIELD, RBAUG); \ + return ret; \ +} \ static inline void \ RBNAME ## _propagate(struct rb_node *rb, struct rb_node *stop) \ { \ while (rb != stop) { \ RBSTRUCT *node = rb_entry(rb, RBSTRUCT, RBFIELD); \ - if (RBCOMPUTE(node, true)) \ + if (RBNAME ## __compute(node, true)) \ break; \ rb = rb_parent(&node->RBFIELD); \ } \ @@ -114,44 +231,31 @@ RBNAME ## _copy(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ - RBCOPY(new, old); \ + RBNAME ## __copy(old, new); \ } \ static void \ RBNAME ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ - RBCOPY(new, old); \ - RBCOMPUTE(old, false); \ + RBNAME ## __copy(old, new); \ + RBNAME ## __compute(old, false); \ +} \ +static inline void \ +RBNAME ## _merge(struct rb_node *rb, struct rb_node *rb_new) \ +{ \ + RBSTRUCT *node = rb_entry(rb, RBSTRUCT, RBFIELD); \ + RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ + RB_FOR_EACH(RB_MERGE, RBNAME, RBSTRUCT, RBFIELD, RBAUG); \ } \ RBSTATIC const struct rb_augment_callbacks RBNAME = { \ .propagate = RBNAME ## _propagate, \ .copy = RBNAME ## _copy, \ - .rotate = RBNAME ## _rotate \ + .rotate = RBNAME ## _rotate, \ + .merge = RBNAME ## _merge \ }; /* - * Template for declaring augmented rbtree callbacks (generic single field) - * - * RBSTATIC: 'static' or empty - * RBNAME: name of the rb_augment_callbacks structure - * RBSTRUCT: struct type of the tree nodes - * RBFIELD: name of struct rb_node field within RBSTRUCT - * RBAUGMENTED: name of field within RBSTRUCT holding data for subtree - * RBCOMPUTE: name of function that recomputes the RBAUGMENTED data - */ - -#define RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ - RBSTRUCT, RBFIELD, RBAUGMENTED, RBCOMPUTE) \ -static inline void \ -RBNAME ## _copy_single(RBSTRUCT *new, RBSTRUCT *old) \ -{ \ - new->RBAUGMENTED = old->RBAUGMENTED; \ -} \ -RB_DECLARE_CALLBACKS_MULTI(RBSTATIC, RBNAME, \ - RBSTRUCT, RBFIELD, RBNAME ## _copy_single, RBCOMPUTE) - -/* * Template for declaring augmented rbtree callbacks, * computing RBAUGMENTED scalar as max(RBCOMPUTE(node)) for all subtree nodes. * @@ -159,34 +263,15 @@ RB_DECLARE_CALLBACKS_MULTI(RBSTATIC, RBNAME, \ * RBNAME: name of the rb_augment_callbacks structure * RBSTRUCT: struct type of the tree nodes * RBFIELD: name of struct rb_node field within RBSTRUCT - * RBTYPE: type of the RBAUGMENTED field - * RBAUGMENTED: name of RBTYPE field within RBSTRUCT holding data for subtree - * RBCOMPUTE: name of function that returns the per-node RBTYPE scalar + * RBTYPE: type of the RBAUGMENTED field -- unused, assumed typeof(RBAUGMENTED) + * RBAUGMENTED: name of field within RBSTRUCT holding data for subtree + * RBVALUE: name of function that returns the per-node RBTYPE scalar */ -#define RB_DECLARE_CALLBACKS_MAX(RBSTATIC, RBNAME, RBSTRUCT, RBFIELD, \ - RBTYPE, RBAUGMENTED, RBCOMPUTE) \ -static inline bool RBNAME ## _compute_max(RBSTRUCT *node, bool exit) \ -{ \ - RBSTRUCT *child; \ - RBTYPE max = RBCOMPUTE(node); \ - if (node->RBFIELD.rb_left) { \ - child = rb_entry(node->RBFIELD.rb_left, RBSTRUCT, RBFIELD); \ - if (child->RBAUGMENTED > max) \ - max = child->RBAUGMENTED; \ - } \ - if (node->RBFIELD.rb_right) { \ - child = rb_entry(node->RBFIELD.rb_right, RBSTRUCT, RBFIELD); \ - if (child->RBAUGMENTED > max) \ - max = child->RBAUGMENTED; \ - } \ - if (exit && node->RBAUGMENTED == max) \ - return true; \ - node->RBAUGMENTED = max; \ - return false; \ -} \ -RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ - RBSTRUCT, RBFIELD, RBAUGMENTED, RBNAME ## _compute_max) +#define RB_DECLARE_CALLBACKS_MAX(RBSTATIC, RBNAME, RBSTRUCT, RBFIELD, \ + RBTYPE, RBAUGMENTED, RBVALUE) \ +RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, RBSTRUCT, RBFIELD, \ + RB_AUG_FUNC(RBVALUE, RBAUGMENTED, max)) #define RB_RED 0 diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 16a04202888b..e6ad4f2a475c 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -116,7 +116,7 @@ int rcutree_offline_cpu(unsigned int cpu); void rcutree_migrate_callbacks(int cpu); -/* Called from hotplug and also arm64 early secondary boot failure */ +/* Called from hotplug */ void rcutree_report_cpu_dead(void); #endif /* __LINUX_RCUTREE_H */ diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index ff0ad1e12c01..00019b1895e6 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -233,7 +233,7 @@ enum rproc_features { * @subdevs: list of subdevices, to following the running state * @notifyids: idr for dynamically assigning rproc-wide unique notify ids * @index: index of this rproc device - * @attach_work: workqueue for attaching rproc + * @boot_work: workqueue for booting rproc * @crash_handler: workqueue for handling a crash * @crash_handler_lock: serializes crash handler queueing and deletion * @deleting: remoteproc deletion has begun @@ -280,7 +280,7 @@ struct rproc { struct list_head subdevs; struct idr notifyids; int index; - struct work_struct attach_work; + struct work_struct boot_work; struct work_struct crash_handler; spinlock_t crash_handler_lock; bool deleting; diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index d9419dc902f6..0adb51ab1542 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -131,8 +131,8 @@ struct signal_struct { * process will inherit a flag if they should look for a * child_subreaper process at exit. */ - unsigned int is_child_subreaper:1; - unsigned int has_child_subreaper:1; + bool is_child_subreaper; + bool has_child_subreaper; unsigned int autoreap:1; #ifdef CONFIG_POSIX_TIMERS @@ -697,6 +697,24 @@ struct pid *task_pid_type(struct task_struct *task, enum pid_type type) return pid; } +/* Fill @pids with the pid types of @task up to @last, without references. */ +static inline void __task_pids(struct pid **pids, enum pid_type last, + struct task_struct *task) +{ + for (enum pid_type type = PIDTYPE_PID; type <= last; type++) + pids[type] = task_pid_type(task, type); +} + +static inline void __get_task_pids(struct pid **pids, enum pid_type last, + struct task_struct *task) +{ + for (enum pid_type type = PIDTYPE_PID; type <= last; type++) + pids[type] = get_pid(task_pid_type(task, type)); +} + +#define task_pids(pids, task) __task_pids(pids, pids_last(pids), task) +#define get_task_pids(pids, task) __get_task_pids(pids, pids_last(pids), task) + static inline struct pid *task_tgid(struct task_struct *task) { return task->signal->pids[PIDTYPE_TGID]; diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h index 9f2839e73f8a..f006f2654e4c 100644 --- a/include/linux/seq_buf.h +++ b/include/linux/seq_buf.h @@ -5,6 +5,7 @@ #include <linux/bug.h> #include <linux/minmax.h> #include <linux/seq_file.h> +#include <linux/string.h> #include <linux/types.h> /* @@ -30,6 +31,10 @@ struct seq_buf { .size = SIZE, \ } +/** + * seq_buf_clear - reset the seq_buf to be read / appended from the beginning + * @s: the seq_buf handle + */ static inline void seq_buf_clear(struct seq_buf *s) { s->len = 0; @@ -37,6 +42,14 @@ static inline void seq_buf_clear(struct seq_buf *s) s->buffer[0] = '\0'; } +/** + * seq_buf_init - initialize a seq_buf + * @s: the seq_buf handle + * @buf: pointer to the buffer + * @size: total size of @buf + * + * The contents of the buffer are ignored. + */ static inline void seq_buf_init(struct seq_buf *s, char *buf, unsigned int size) { @@ -55,12 +68,46 @@ seq_buf_has_overflowed(struct seq_buf *s) return s->len > s->size; } +/* + * Mark @s as overflowed, which discards the length of what it holds. The + * bytes up to its last one are the string from then on, as that is where + * seq_buf_str() terminates it, so clear whatever was not written: a writer + * sets len to how much it filled, and anything past that was never adopted. + */ static inline void seq_buf_set_overflow(struct seq_buf *s) { + if (s->len < s->size) + memset(s->buffer + s->len, 0, s->size - s->len); + s->len = s->size + 1; } +/** + * seq_buf_init_append - initialize a seq_buf over a buffer that may + * already hold NUL-terminated content + * @s: the seq_buf handle + * @buf: pointer to the (possibly non-empty) buffer + * @size: total size of @buf + * + * Unlike seq_buf_init(), which always starts @buf at len=0, this + * preserves whatever NUL-terminated content @buf already holds and + * positions @s to append after it. Useful for converting code that used + * to append to an existing buffer with strlcat()/scnprintf() and friends. + * + * If @buf holds no NUL within @size, @s starts out overflowed, as + * strlcat() treats such a buffer as already truncated. + */ +static inline void +seq_buf_init_append(struct seq_buf *s, char *buf, unsigned int size) +{ + s->buffer = buf; + s->size = size; + s->len = strnlen(buf, size); + if (s->len == size) + seq_buf_set_overflow(s); +} + /* * How much buffer is left on the seq_buf? */ @@ -79,6 +126,27 @@ static inline unsigned int seq_buf_used(struct seq_buf *s) return min(s->len, s->size); } +/* + * NUL-terminate the buffer in @s: directly after the data when there is + * room for it, otherwise in the last byte of the buffer. @s->size must not + * be zero. + * + * Returns: the offset of the NUL. + */ +static inline size_t __seq_buf_terminate(struct seq_buf *s) +{ + size_t end; + + if (seq_buf_buffer_left(s)) + end = s->len; + else + end = s->size - 1; + + s->buffer[end] = 0; + + return end; +} + /** * seq_buf_str - get NUL-terminated C string from seq_buf * @s: the seq_buf handle @@ -88,7 +156,14 @@ static inline unsigned int seq_buf_used(struct seq_buf *s) * * Note, if this is called when the buffer has overflowed, then * the last byte of the buffer is zeroed, and the len will still - * point passed it. + * point passed it. The same happens when the buffer is exactly + * full: the NUL takes the place of the last byte written, which is + * lost, though seq_buf_used() still counts it. + * + * A zero-sized seq_buf has nowhere to put a NUL, so the empty string + * is returned instead of writing to @s->buffer. Any other seq_buf + * returns @s->buffer, even when it holds an empty string, so callers + * always get their own buffer back. * * After this function is called, s->buffer is safe to use * in string operations. @@ -97,18 +172,68 @@ static inline unsigned int seq_buf_used(struct seq_buf *s) */ static inline const char *seq_buf_str(struct seq_buf *s) { - if (WARN_ON(s->size == 0)) + if (s->size == 0) return ""; - if (seq_buf_buffer_left(s)) - s->buffer[s->len] = 0; - else - s->buffer[s->size - 1] = 0; + __seq_buf_terminate(s); return s->buffer; } /** + * seq_buf_strlen - get the length of the NUL-terminated C string in seq_buf + * @s: the seq_buf handle + * + * This makes sure that the buffer in @s is NUL-terminated, exactly as + * seq_buf_str() does, and returns the length of the resulting string + * without walking it. Unlike seq_buf_used(), this does not count the byte + * given up to the NUL when the buffer is full or has overflowed. When the + * buffer is exactly full, that byte is the last one written, and calling + * either function loses it. + * + * A zero-sized seq_buf holds no string, so 0 is returned without writing + * to @s->buffer, matching what seq_buf_str() returns for one. + * + * After this function is called, s->buffer is safe to use + * in string operations. + * + * Returns: the offset of the NUL that terminates @s->buffer. That is the + * length of the string unless an earlier NUL is in the way, either one the + * data written to @s carried itself, or one seq_buf_set_overflow() left + * behind when it cleared what no writer had claimed. + */ +static inline size_t seq_buf_strlen(struct seq_buf *s) +{ + if (s->size == 0) + return 0; + + return __seq_buf_terminate(s); +} + +/** + * seq_buf_terminate - NUL-terminate the string in a seq_buf + * @s: the seq_buf handle + * + * Terminate @s->buffer exactly as seq_buf_str() and seq_buf_strlen() do, + * for callers that want neither the pointer nor the length and only need + * the buffer to be safe to read as a C string. A zero-sized seq_buf has + * nowhere to put a NUL and is left untouched. + * + * Nothing is returned on purpose: a caller that wants the length should + * use seq_buf_strlen(), which says so. + * + * After this function is called, s->buffer is safe to use + * in string operations. + */ +static inline void seq_buf_terminate(struct seq_buf *s) +{ + if (s->size == 0) + return; + + __seq_buf_terminate(s); +} + +/** * seq_buf_get_buf - get buffer to write arbitrary data to * @s: the seq_buf handle * @bufp: the beginning of the buffer is stored here @@ -155,11 +280,11 @@ static inline void seq_buf_commit(struct seq_buf *s, int num) * * Removes the last written character to the seq_buf @s. * - * Returns the last character or -1 if it is empty. + * Returns the last character, or -1 if @s is empty or has overflowed. */ static inline int seq_buf_pop(struct seq_buf *s) { - if (!s->len) + if (!s->len || seq_buf_has_overflowed(s)) return -1; s->len--; diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index dc0e8c62d9e0..f0e7e52a0905 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -28,11 +28,16 @@ struct seq_file { void *private; }; +/* All four are called without checking for NULL. */ struct seq_operations { - void * (*start) (struct seq_file *m, loff_t *pos); - void (*stop) (struct seq_file *m, void *v); - void * (*next) (struct seq_file *m, void *v, loff_t *pos); - int (*show) (struct seq_file *m, void *v); + void *(*start)(struct seq_file *m, loff_t *pos) + __require_explicit_initialization; + void (*stop)(struct seq_file *m, void *v) + __require_explicit_initialization; + void *(*next)(struct seq_file *m, void *v, loff_t *pos) + __require_explicit_initialization; + int (*show)(struct seq_file *m, void *v) + __require_explicit_initialization; }; #define SEQ_SKIP 1 diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index eeb868e93e15..d91c0477be9d 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -186,10 +186,10 @@ static inline struct uart_8250_port *up_to_u8250p(struct uart_port *up) return container_of(up, struct uart_8250_port, port); } -int serial8250_register_8250_port(const struct uart_8250_port *); -void serial8250_unregister_port(int line); -void serial8250_suspend_port(int line); -void serial8250_resume_port(int line); +struct uart_8250_port *serial8250_register_8250_port(const struct uart_8250_port *); +void serial8250_unregister_port(struct uart_8250_port *); +void serial8250_suspend_port(struct uart_8250_port *); +void serial8250_resume_port(struct uart_8250_port *); int early_serial_setup(struct uart_port *port); int early_serial8250_setup(struct earlycon_device *device, const char *options); diff --git a/include/linux/socket.h b/include/linux/socket.h index 5a5eb1250103..b17fdb7d38a7 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -189,10 +189,11 @@ static inline size_t msg_data_left(const struct msghdr *msg) /* "Socket"-level control message types: */ -#define SCM_RIGHTS 0x01 /* rw: access rights (array of int) */ -#define SCM_CREDENTIALS 0x02 /* rw: struct ucred */ -#define SCM_SECURITY 0x03 /* rw: security label */ -#define SCM_PIDFD 0x04 /* ro: pidfd (int) */ +#define SCM_RIGHTS 0x01 /* rw: access rights (array of int) */ +#define SCM_CREDENTIALS 0x02 /* rw: struct ucred */ +#define SCM_SECURITY 0x03 /* rw: security label */ +#define SCM_PIDFD 0x04 /* ro: pidfd (int) */ +#define SCM_PIDFD_THREAD 0x05 /* ro: thread pidfd (int) */ struct ucred { __u32 pid; diff --git a/include/linux/spinlock_types_raw.h b/include/linux/spinlock_types_raw.h index e5644ab2161f..942c229c90bb 100644 --- a/include/linux/spinlock_types_raw.h +++ b/include/linux/spinlock_types_raw.h @@ -11,6 +11,10 @@ #include <linux/lockdep_types.h> +/* + * Keep in sync with rust/kernel/sync/lock/spinlock.rs + */ + context_lock_struct(raw_spinlock) { arch_spinlock_t raw_lock; #ifdef CONFIG_DEBUG_SPINLOCK diff --git a/include/linux/spmi.h b/include/linux/spmi.h index 4eb9564a7fb3..4daebc980501 100644 --- a/include/linux/spmi.h +++ b/include/linux/spmi.h @@ -70,6 +70,22 @@ int spmi_device_add(struct spmi_device *sdev); void spmi_device_remove(struct spmi_device *sdev); /** + * struct spmi_subdevice - Basic representation of an SPMI sub-device + * @sdev: Sub-device representation of an SPMI device + * @devid: Platform Device ID of an SPMI sub-device + */ +struct spmi_subdevice { + struct spmi_device sdev; + unsigned int devid; +}; + +struct spmi_subdevice *spmi_subdevice_alloc_and_add(struct spmi_device *sparent); +void spmi_subdevice_remove(struct spmi_subdevice *sdev); + +struct spmi_subdevice *devm_spmi_subdevice_alloc_and_add(struct device *dev, + struct spmi_device *sparent); + +/** * struct spmi_controller - interface to the SPMI master controller * @dev: Driver model representation of the device. * @nr: board-specific number identifier for this controller/bus @@ -173,6 +189,7 @@ static inline void spmi_driver_unregister(struct spmi_driver *sdrv) struct device_node; struct spmi_device *spmi_find_device_by_of_node(struct device_node *np); +struct spmi_device *spmi_get_parent_spmi_device(struct device *dev); int spmi_register_read(struct spmi_device *sdev, u8 addr, u8 *buf); int spmi_ext_register_read(struct spmi_device *sdev, u8 addr, u8 *buf, size_t len); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 24698856eb40..cfb5ab17dabd 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -87,6 +87,8 @@ struct svc_serv { char * sv_name; /* service name */ bool sv_is_pooled; /* is this a pooled service? */ + /* Caller registers with rpcbind itself. Set before svc_bind(). */ + bool sv_no_rpcbind; struct svc_pool * sv_pools; /* array of thread pools */ int (*sv_threadfn)(void *data); diff --git a/include/linux/sunrpc/xdrgen/nfs2.h b/include/linux/sunrpc/xdrgen/nfs2.h new file mode 100644 index 000000000000..1d26de39ac69 --- /dev/null +++ b/include/linux/sunrpc/xdrgen/nfs2.h @@ -0,0 +1,298 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Generated by xdrgen. Manual edits will be lost. */ +/* XDR specification file: ../../Documentation/sunrpc/xdr/nfs2.x */ +/* XDR specification modification time: Tue Sep 8 11:26:28 2026 */ + +#ifndef _LINUX_XDRGEN_NFS2_DEF_H +#define _LINUX_XDRGEN_NFS2_DEF_H + +#include <linux/types.h> +#include <linux/sunrpc/xdrgen/_defs.h> + +enum { NFS_MAXDATA = 8192 }; + +enum { NFS_MAXPATHLEN = 1024 }; + +enum { NFS_MAXNAMLEN = 255 }; + +enum { NFS_COOKIESIZE = 4 }; + +enum { NFS_FHSIZE = 32 }; + +enum nfsstat { + NFS_OK = 0, + NFSERR_PERM = 1, + NFSERR_NOENT = 2, + NFSERR_IO = 5, + NFSERR_NXIO = 6, + NFSERR_ACCES = 13, + NFSERR_EXIST = 17, + NFSERR_NODEV = 19, + NFSERR_NOTDIR = 20, + NFSERR_ISDIR = 21, + NFSERR_FBIG = 27, + NFSERR_NOSPC = 28, + NFSERR_ROFS = 30, + NFSERR_NAMETOOLONG = 63, + NFSERR_NOTEMPTY = 66, + NFSERR_DQUOT = 69, + NFSERR_STALE = 70, + NFSERR_WFLUSH = 99, +}; + +typedef __be32 nfsstat; + +enum ftype { + NFNON = 0, + NFREG = 1, + NFDIR = 2, + NFBLK = 3, + NFCHR = 4, + NFLNK = 5, +}; + +typedef enum ftype ftype; + +typedef u8 fhandle[NFS_FHSIZE]; + +typedef u8 nfscookie[NFS_COOKIESIZE]; + +struct timeval { + u32 seconds; + u32 useconds; +}; + +struct fattr { + ftype type; + u32 mode; + u32 nlink; + u32 uid; + u32 gid; + u32 size; + u32 blocksize; + u32 rdev; + u32 blocks; + u32 fsid; + u32 fileid; + struct timeval atime; + struct timeval mtime; + struct timeval ctime; +}; + +struct sattr { + u32 mode; + u32 uid; + u32 gid; + u32 size; + struct timeval atime; + struct timeval mtime; +}; + +typedef string filename; + +typedef string path; + +struct attrstat { + nfsstat status; + union { + struct fattr attributes; + } u; +}; + +struct diropargs { + fhandle dir; + filename name; +}; + +struct diropok { + fhandle file; + struct fattr attributes; +}; + +struct diropres { + nfsstat status; + union { + struct diropok diropok; + } u; +}; + +struct sattrargs { + fhandle file; + struct sattr attributes; +}; + +struct readlinkres { + nfsstat status; + union { + path data; + } u; +}; + +struct readargs { + fhandle file; + u32 offset; + u32 count; + u32 totalcount; +}; + +struct readresok { + struct fattr attributes; + opaque data; +}; + +struct readres { + nfsstat status; + union { + struct readresok readresok; + } u; +}; + +struct writeargs { + fhandle file; + u32 beginoffset; + u32 offset; + u32 totalcount; + struct xdr_buf data; +}; + +struct createargs { + struct diropargs where; + struct sattr attributes; +}; + +struct renameargs { + struct diropargs from; + struct diropargs to; +}; + +struct linkargs { + fhandle from; + struct diropargs to; +}; + +struct symlinkargs { + struct diropargs from; + struct xdr_buf to; + struct sattr attributes; +}; + +struct readdirargs { + fhandle dir; + nfscookie cookie; + u32 count; +}; + +struct entry { + u32 fileid; + filename name; + nfscookie cookie; +}; + +struct readdirok { + struct entry *entries; + bool eof; +}; + +struct readdirres { + nfsstat status; + union { + struct readdirok readdirok; + } u; +}; + +struct info { + u32 tsize; + u32 bsize; + u32 blocks; + u32 bfree; + u32 bavail; +}; + +struct statfsres { + nfsstat status; + union { + struct info info; + } u; +}; + +enum { + NFSPROC_NULL = 0, + NFSPROC_GETATTR = 1, + NFSPROC_SETATTR = 2, + NFSPROC_ROOT = 3, + NFSPROC_LOOKUP = 4, + NFSPROC_READLINK = 5, + NFSPROC_READ = 6, + NFSPROC_WRITECACHE = 7, + NFSPROC_WRITE = 8, + NFSPROC_CREATE = 9, + NFSPROC_REMOVE = 10, + NFSPROC_RENAME = 11, + NFSPROC_LINK = 12, + NFSPROC_SYMLINK = 13, + NFSPROC_MKDIR = 14, + NFSPROC_RMDIR = 15, + NFSPROC_READDIR = 16, + NFSPROC_STATFS = 17, +}; + +#ifndef NFS_PROGRAM +#define NFS_PROGRAM (100003) +#endif + +#define NFS2_nfsstat_sz (XDR_int) +#define NFS2_ftype_sz (XDR_int) +#define NFS2_fhandle_sz (XDR_QUADLEN(NFS_FHSIZE)) +#define NFS2_nfscookie_sz (XDR_QUADLEN(NFS_COOKIESIZE)) +#define NFS2_timeval_sz \ + (XDR_unsigned_int + XDR_unsigned_int) +#define NFS2_fattr_sz \ + (NFS2_ftype_sz + XDR_unsigned_int + XDR_unsigned_int + XDR_unsigned_int + XDR_unsigned_int + XDR_unsigned_int + XDR_unsigned_int + XDR_unsigned_int + XDR_unsigned_int + XDR_unsigned_int + XDR_unsigned_int + NFS2_timeval_sz + NFS2_timeval_sz + NFS2_timeval_sz) +#define NFS2_sattr_sz \ + (XDR_unsigned_int + XDR_unsigned_int + XDR_unsigned_int + XDR_unsigned_int + NFS2_timeval_sz + NFS2_timeval_sz) +#define NFS2_filename_sz (XDR_unsigned_int + XDR_QUADLEN(NFS_MAXNAMLEN)) +#define NFS2_path_sz (XDR_unsigned_int + XDR_QUADLEN(NFS_MAXPATHLEN)) +#define NFS2_attrstat_sz \ + (NFS2_nfsstat_sz + NFS2_fattr_sz) +#define NFS2_diropargs_sz \ + (NFS2_fhandle_sz + NFS2_filename_sz) +#define NFS2_diropok_sz \ + (NFS2_fhandle_sz + NFS2_fattr_sz) +#define NFS2_diropres_sz \ + (NFS2_nfsstat_sz + NFS2_diropok_sz) +#define NFS2_sattrargs_sz \ + (NFS2_fhandle_sz + NFS2_sattr_sz) +#define NFS2_readlinkres_sz \ + (NFS2_nfsstat_sz + NFS2_path_sz) +#define NFS2_readargs_sz \ + (NFS2_fhandle_sz + XDR_unsigned_int + XDR_unsigned_int + XDR_unsigned_int) +#define NFS2_readresok_sz \ + (NFS2_fattr_sz + XDR_unsigned_int + XDR_QUADLEN(NFS_MAXDATA)) +#define NFS2_readres_sz \ + (NFS2_nfsstat_sz + NFS2_readresok_sz) +#define NFS2_writeargs_sz \ + (NFS2_fhandle_sz + XDR_unsigned_int + XDR_unsigned_int + XDR_unsigned_int + XDR_unsigned_int + XDR_QUADLEN(NFS_MAXDATA)) +#define NFS2_createargs_sz \ + (NFS2_diropargs_sz + NFS2_sattr_sz) +#define NFS2_renameargs_sz \ + (NFS2_diropargs_sz + NFS2_diropargs_sz) +#define NFS2_linkargs_sz \ + (NFS2_fhandle_sz + NFS2_diropargs_sz) +#define NFS2_symlinkargs_sz \ + (NFS2_diropargs_sz + NFS2_path_sz + NFS2_sattr_sz) +#define NFS2_readdirargs_sz \ + (NFS2_fhandle_sz + NFS2_nfscookie_sz + XDR_unsigned_int) +#define NFS2_entry_sz \ + (XDR_bool + XDR_unsigned_int + NFS2_filename_sz + NFS2_nfscookie_sz) +#define NFS2_readdirok_sz \ + (XDR_bool + XDR_bool) +#define NFS2_readdirres_sz \ + (NFS2_nfsstat_sz + NFS2_readdirok_sz) +#define NFS2_info_sz \ + (XDR_unsigned_int + XDR_unsigned_int + XDR_unsigned_int + XDR_unsigned_int + XDR_unsigned_int) +#define NFS2_statfsres_sz \ + (NFS2_nfsstat_sz + NFS2_info_sz) +#define NFS2_MAX_ARGS_SZ \ + (NFS2_writeargs_sz) + +#endif /* _LINUX_XDRGEN_NFS2_DEF_H */ diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index a82045804d34..005730623f3b 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -145,6 +145,7 @@ struct xprtsec_parms { enum xprtsec_policies policy; /* authentication material */ + key_serial_t keyring_serial; key_serial_t cert_serial; key_serial_t privkey_serial; }; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index e4d1720f49f0..d18f7bc1e5d0 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -233,6 +233,13 @@ struct tcp_sock { is_sack_reneg:1, /* in recovery from loss with SACK reneg? */ is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */ recvmsg_inq : 1;/* Indicate # of bytes in queue upon recvmsg */ +#ifdef CONFIG_BPF + u32 bpf_tcp_ops_flags; +#define BPF_TCP_OPS_TEST_FLAG(TP, ARG) \ + (READ_ONCE((TP)->bpf_tcp_ops_flags) & BPF_TCP_OPS_FLAG_ ## ARG) +#else +#define BPF_TCP_OPS_TEST_FLAG(TP, ARG) (0) +#endif __cacheline_group_end(tcp_sock_read_txrx); /* RX read-mostly hotpath cache lines */ diff --git a/include/linux/tnum.h b/include/linux/tnum.h index ca2cfec8de08..16682248f963 100644 --- a/include/linux/tnum.h +++ b/include/linux/tnum.h @@ -134,4 +134,6 @@ static inline bool tnum_subreg_is_const(struct tnum a) /* Returns the smallest member of t larger than z */ u64 tnum_step(struct tnum t, u64 z); +u32 tnum_alignment(struct tnum a); + #endif /* _LINUX_TNUM_H */ diff --git a/include/linux/torture.h b/include/linux/torture.h index 1b6d5be641f8..c9b47d138302 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -98,7 +98,6 @@ void torture_shutdown_absorb(const char *title); int torture_shutdown_init(int ssecs, void (*cleanup)(void)); /* Task stuttering, which forces load/no-load transitions. */ -bool stutter_will_wait(void); bool stutter_wait(const char *title); int torture_stutter_init(int s, int sgap); @@ -132,11 +131,8 @@ void _torture_stop_kthread(char *m, struct task_struct **tp); #endif void torture_sched_set_normal(struct task_struct *t, int nice); -#if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_ENABLED(CONFIG_LOCK_TORTURE_TEST) || IS_ENABLED(CONFIG_HAZPTR_TORTURE_TEST) +#if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_MODULE(CONFIG_RCU_TORTURE_TEST) || IS_ENABLED(CONFIG_LOCK_TORTURE_TEST) || IS_MODULE(CONFIG_LOCK_TORTURE_TEST) long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask, bool dowarn); #endif -/* Atomic per-CPU counters. */ -s64 torture_sum_pcpu_atomic_long(atomic_long_t __percpu *pcp); - #endif /* __LINUX_TORTURE_H */ diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h index 697d619aafdc..7174ebf3f015 100644 --- a/include/linux/trace_seq.h +++ b/include/linux/trace_seq.h @@ -86,7 +86,10 @@ static inline bool trace_seq_has_overflowed(struct trace_seq *s) * * Removes the last written character to the trace_seq @s. * - * Returns the last character or -1 if it is empty. + * Returns the last character, or -1 if the underlying seq_buf is empty or + * has overflowed. Note that only that buffer is consulted: a @s marked + * full by a write that did not fit, which trace_seq_has_overflowed() + * reports as overflowed, still pops the last character written. */ static inline int trace_seq_pop(struct trace_seq *s) { diff --git a/include/linux/uio.h b/include/linux/uio.h index 8d82a8258ef1..3fc98542922e 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -11,6 +11,7 @@ #include <uapi/linux/uio.h> struct page; +struct dma_buf_io_map; typedef unsigned int __bitwise iov_iter_extraction_t; @@ -28,6 +29,7 @@ enum iter_type { ITER_BVECQ, ITER_XARRAY, ITER_DISCARD, + ITER_DMABUF_MAP, }; #define ITER_SOURCE 1 // == WRITE @@ -70,6 +72,7 @@ struct iov_iter { const struct bvecq *bvecq; struct xarray *xarray; void __user *ubuf; + struct dma_buf_io_map *dmabuf_map; }; size_t count; }; @@ -154,6 +157,11 @@ static inline bool iov_iter_is_xarray(const struct iov_iter *i) return iov_iter_type(i) == ITER_XARRAY; } +static inline bool iov_iter_is_dmabuf_map(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_DMABUF_MAP; +} + static inline unsigned char iov_iter_rw(const struct iov_iter *i) { return i->data_source ? WRITE : READ; @@ -299,6 +307,9 @@ void iov_iter_bvec_queue(struct iov_iter *i, unsigned int direction, unsigned int first_slot, unsigned int offset, size_t count); void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray, loff_t start, size_t count); +void iov_iter_dmabuf_map(struct iov_iter *i, unsigned int direction, + struct dma_buf_io_map *map, + loff_t off, size_t count); ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages, diff --git a/include/linux/unicode.h b/include/linux/unicode.h index 64fa44fe180c..3a8cb603eb93 100644 --- a/include/linux/unicode.h +++ b/include/linux/unicode.h @@ -53,6 +53,7 @@ struct unicode_map { unsigned int version; const struct utf8data *ntab[UTF8_NMAX]; const struct utf8data_table *tables; + struct rcu_head rcu; }; int utf8_validate(const struct unicode_map *um, const struct qstr *str); diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index ab0a32a90629..5866f19d3c7b 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -305,9 +305,17 @@ struct usb_serial_driver { void (*write_bulk_callback)(struct urb *urb); /* Called by the generic read bulk callback */ void (*process_read_urb)(struct urb *urb); + /* + * Called with port->lock held before preparing another write URB. + * Drivers returning false must restart the generic write path when + * writes may proceed again. + */ + bool (*write_ready)(struct usb_serial_port *port); /* Called by the generic write implementation */ int (*prepare_write_buffer)(struct usb_serial_port *port, void *dest, size_t size); + /* Called with port->lock held to roll back a failed write submission */ + void (*write_rollback)(struct usb_serial_port *port, int count); }; #define to_usb_serial_driver(d) \ container_of(d, struct usb_serial_driver, driver) diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 9a1674c152aa..2f3fa2787737 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -8,6 +8,7 @@ * Author: Tom Lyon, pugs@cisco.com */ +#include <linux/device.h> #include <linux/mutex.h> #include <linux/pci.h> #include <linux/vfio.h> @@ -16,6 +17,7 @@ #include <linux/types.h> #include <linux/uuid.h> #include <linux/notifier.h> +#include <linux/pm.h> #ifndef VFIO_PCI_CORE_H #define VFIO_PCI_CORE_H @@ -168,7 +170,6 @@ int vfio_pci_core_init_dev(struct vfio_device *core_vdev); void vfio_pci_core_release_dev(struct vfio_device *core_vdev); int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev); void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev); -extern const struct pci_error_handlers vfio_pci_core_err_handlers; int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev, int nr_virtfn); long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd, @@ -193,8 +194,6 @@ int vfio_pci_core_match_token_uuid(struct vfio_device *core_vdev, int vfio_pci_core_enable(struct vfio_pci_core_device *vdev); void vfio_pci_core_disable(struct vfio_pci_core_device *vdev); void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev); -pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev, - pci_channel_state_t state); ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, void __iomem *io, char __user *buf, loff_t off, size_t count, size_t x_start, @@ -260,4 +259,40 @@ vfio_pci_core_get_iomap(struct vfio_pci_core_device *vdev, unsigned int bar) int vfio_pci_dma_buf_iommufd_map(struct dma_buf_attachment *attachment, struct phys_vec *phys); +int vfio_pci_core_runtime_suspend(struct vfio_pci_core_device *vdev); +int vfio_pci_core_runtime_resume(struct vfio_pci_core_device *vdev); +pci_ers_result_t vfio_pci_core_aer_err_detected(struct vfio_pci_core_device *vdev); + +/* + * Per-driver PM/AER trampolines. driver_data points to the driver's private + * structure, which embeds a struct vfio_pci_core_device. + * + * @name: prefix for <name>_pm_ops and <name>_aer_err_detected + * @drv_type: type of the driver's private structure, including struct + * @member: member containing the struct vfio_pci_core_device + */ +#define VFIO_PCI_CORE_DEFINE_CALLBACKS(name, drv_type, member) \ +static int __maybe_unused name##_pm_suspend(struct device *dev) \ +{ \ + drv_type *drvdata = dev_get_drvdata(dev); \ + \ + return vfio_pci_core_runtime_suspend(&drvdata->member); \ +} \ +static int __maybe_unused name##_pm_resume(struct device *dev) \ +{ \ + drv_type *drvdata = dev_get_drvdata(dev); \ + \ + return vfio_pci_core_runtime_resume(&drvdata->member); \ +} \ +static const struct dev_pm_ops name##_pm_ops = { \ + SET_RUNTIME_PM_OPS(name##_pm_suspend, name##_pm_resume, NULL) \ +}; \ +static pci_ers_result_t name##_aer_err_detected(struct pci_dev *pdev, \ + pci_channel_state_t state) \ +{ \ + drv_type *drvdata = pci_get_drvdata(pdev); \ + \ + return vfio_pci_core_aer_err_detected(&drvdata->member); \ +} + #endif /* VFIO_PCI_CORE_H */ |