diff options
Diffstat (limited to 'kernel')
58 files changed, 1183 insertions, 1337 deletions
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index ba03ec39efb3..6ef6746a7871 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -218,47 +218,84 @@ int bpf_prog_calc_tag(struct bpf_prog *fp) return 0; } -static void bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta) +static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, u32 delta, + u32 curr, const bool probe_pass) { + const s64 imm_min = S32_MIN, imm_max = S32_MAX; + s64 imm = insn->imm; + + if (curr < pos && curr + imm + 1 > pos) + imm += delta; + else if (curr > pos + delta && curr + imm + 1 <= pos + delta) + imm -= delta; + if (imm < imm_min || imm > imm_max) + return -ERANGE; + if (!probe_pass) + insn->imm = imm; + return 0; +} + +static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, u32 delta, + u32 curr, const bool probe_pass) +{ + const s32 off_min = S16_MIN, off_max = S16_MAX; + s32 off = insn->off; + + if (curr < pos && curr + off + 1 > pos) + off += delta; + else if (curr > pos + delta && curr + off + 1 <= pos + delta) + off -= delta; + if (off < off_min || off > off_max) + return -ERANGE; + if (!probe_pass) + insn->off = off; + return 0; +} + +static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta, + const bool probe_pass) +{ + u32 i, insn_cnt = prog->len + (probe_pass ? delta : 0); struct bpf_insn *insn = prog->insnsi; - u32 i, insn_cnt = prog->len; - bool pseudo_call; - u8 code; - int off; + int ret = 0; for (i = 0; i < insn_cnt; i++, insn++) { + u8 code; + + /* In the probing pass we still operate on the original, + * unpatched image in order to check overflows before we + * do any other adjustments. Therefore skip the patchlet. + */ + if (probe_pass && i == pos) { + i += delta + 1; + insn++; + } code = insn->code; - if (BPF_CLASS(code) != BPF_JMP) - continue; - if (BPF_OP(code) == BPF_EXIT) + if (BPF_CLASS(code) != BPF_JMP || + BPF_OP(code) == BPF_EXIT) continue; + /* Adjust offset of jmps if we cross patch boundaries. */ if (BPF_OP(code) == BPF_CALL) { - if (insn->src_reg == BPF_PSEUDO_CALL) - pseudo_call = true; - else + if (insn->src_reg != BPF_PSEUDO_CALL) continue; + ret = bpf_adj_delta_to_imm(insn, pos, delta, i, + probe_pass); } else { - pseudo_call = false; + ret = bpf_adj_delta_to_off(insn, pos, delta, i, + probe_pass); } - off = pseudo_call ? insn->imm : insn->off; - - /* Adjust offset of jmps if we cross boundaries. */ - if (i < pos && i + off + 1 > pos) - off += delta; - else if (i > pos + delta && i + off + 1 <= pos + delta) - off -= delta; - - if (pseudo_call) - insn->imm = off; - else - insn->off = off; + if (ret) + break; } + + return ret; } struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len) { u32 insn_adj_cnt, insn_rest, insn_delta = len - 1; + const u32 cnt_max = S16_MAX; struct bpf_prog *prog_adj; /* Since our patchlet doesn't expand the image, we're done. */ @@ -269,6 +306,15 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, insn_adj_cnt = prog->len + insn_delta; + /* Reject anything that would potentially let the insn->off + * target overflow when we have excessive program expansions. + * We need to probe here before we do any reallocation where + * we afterwards may not fail anymore. + */ + if (insn_adj_cnt > cnt_max && + bpf_adj_branches(prog, off, insn_delta, true)) + return NULL; + /* Several new instructions need to be inserted. Make room * for them. Likely, there's no need for a new allocation as * last page could have large enough tailroom. @@ -294,7 +340,11 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, sizeof(*patch) * insn_rest); memcpy(prog_adj->insnsi + off, patch, sizeof(*patch) * len); - bpf_adj_branches(prog_adj, off, insn_delta); + /* We are guaranteed to not fail at this point, otherwise + * the ship has sailed to reverse to the original state. An + * overflow cannot happen at this point. + */ + BUG_ON(bpf_adj_branches(prog_adj, off, insn_delta, false)); return prog_adj; } diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 098eca568c2b..95a84b2f10ce 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -1703,11 +1703,11 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, * we increment the refcnt. If this is the case abort with an * error. */ - verdict = bpf_prog_inc_not_zero(stab->bpf_verdict); + verdict = bpf_prog_inc_not_zero(verdict); if (IS_ERR(verdict)) return PTR_ERR(verdict); - parse = bpf_prog_inc_not_zero(stab->bpf_parse); + parse = bpf_prog_inc_not_zero(parse); if (IS_ERR(parse)) { bpf_prog_put(verdict); return PTR_ERR(parse); @@ -1715,12 +1715,12 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, } if (tx_msg) { - tx_msg = bpf_prog_inc_not_zero(stab->bpf_tx_msg); + tx_msg = bpf_prog_inc_not_zero(tx_msg); if (IS_ERR(tx_msg)) { - if (verdict) - bpf_prog_put(verdict); - if (parse) + if (parse && verdict) { bpf_prog_put(parse); + bpf_prog_put(verdict); + } return PTR_ERR(tx_msg); } } @@ -1805,10 +1805,10 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, out_free: smap_release_sock(psock, sock); out_progs: - if (verdict) - bpf_prog_put(verdict); - if (parse) + if (parse && verdict) { bpf_prog_put(parse); + bpf_prog_put(verdict); + } if (tx_msg) bpf_prog_put(tx_msg); write_unlock_bh(&sock->sk_callback_lock); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5dd1dcb902bf..1904e814f282 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -156,7 +156,29 @@ struct bpf_verifier_stack_elem { #define BPF_COMPLEXITY_LIMIT_INSNS 131072 #define BPF_COMPLEXITY_LIMIT_STACK 1024 -#define BPF_MAP_PTR_POISON ((void *)0xeB9F + POISON_POINTER_DELTA) +#define BPF_MAP_PTR_UNPRIV 1UL +#define BPF_MAP_PTR_POISON ((void *)((0xeB9FUL << 1) + \ + POISON_POINTER_DELTA)) +#define BPF_MAP_PTR(X) ((struct bpf_map *)((X) & ~BPF_MAP_PTR_UNPRIV)) + +static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux) +{ + return BPF_MAP_PTR(aux->map_state) == BPF_MAP_PTR_POISON; +} + +static bool bpf_map_ptr_unpriv(const struct bpf_insn_aux_data *aux) +{ + return aux->map_state & BPF_MAP_PTR_UNPRIV; +} + +static void bpf_map_ptr_store(struct bpf_insn_aux_data *aux, + const struct bpf_map *map, bool unpriv) +{ + BUILD_BUG_ON((unsigned long)BPF_MAP_PTR_POISON & BPF_MAP_PTR_UNPRIV); + unpriv |= bpf_map_ptr_unpriv(aux); + aux->map_state = (unsigned long)map | + (unpriv ? BPF_MAP_PTR_UNPRIV : 0UL); +} struct bpf_call_arg_meta { struct bpf_map *map_ptr; @@ -978,7 +1000,7 @@ static bool register_is_null(struct bpf_reg_state *reg) */ static int check_stack_write(struct bpf_verifier_env *env, struct bpf_func_state *state, /* func where register points to */ - int off, int size, int value_regno) + int off, int size, int value_regno, int insn_idx) { struct bpf_func_state *cur; /* state of the current function */ int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err; @@ -1017,8 +1039,33 @@ static int check_stack_write(struct bpf_verifier_env *env, state->stack[spi].spilled_ptr = cur->regs[value_regno]; state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; - for (i = 0; i < BPF_REG_SIZE; i++) + for (i = 0; i < BPF_REG_SIZE; i++) { + if (state->stack[spi].slot_type[i] == STACK_MISC && + !env->allow_ptr_leaks) { + int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off; + int soff = (-spi - 1) * BPF_REG_SIZE; + + /* detected reuse of integer stack slot with a pointer + * which means either llvm is reusing stack slot or + * an attacker is trying to exploit CVE-2018-3639 + * (speculative store bypass) + * Have to sanitize that slot with preemptive + * store of zero. + */ + if (*poff && *poff != soff) { + /* disallow programs where single insn stores + * into two different stack slots, since verifier + * cannot sanitize them + */ + verbose(env, + "insn %d cannot access two stack slots fp%d and fp%d", + insn_idx, *poff, soff); + return -EINVAL; + } + *poff = soff; + } state->stack[spi].slot_type[i] = STACK_SPILL; + } } else { u8 type = STACK_MISC; @@ -1694,7 +1741,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (t == BPF_WRITE) err = check_stack_write(env, state, off, size, - value_regno); + value_regno, insn_idx); else err = check_stack_read(env, state, off, size, value_regno); @@ -2333,6 +2380,29 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) return 0; } +static int +record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, + int func_id, int insn_idx) +{ + struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; + + if (func_id != BPF_FUNC_tail_call && + func_id != BPF_FUNC_map_lookup_elem) + return 0; + if (meta->map_ptr == NULL) { + verbose(env, "kernel subsystem misconfigured verifier\n"); + return -EINVAL; + } + + if (!BPF_MAP_PTR(aux->map_state)) + bpf_map_ptr_store(aux, meta->map_ptr, + meta->map_ptr->unpriv_array); + else if (BPF_MAP_PTR(aux->map_state) != meta->map_ptr) + bpf_map_ptr_store(aux, BPF_MAP_PTR_POISON, + meta->map_ptr->unpriv_array); + return 0; +} + static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx) { const struct bpf_func_proto *fn = NULL; @@ -2387,13 +2457,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta); if (err) return err; - if (func_id == BPF_FUNC_tail_call) { - if (meta.map_ptr == NULL) { - verbose(env, "verifier bug\n"); - return -EINVAL; - } - env->insn_aux_data[insn_idx].map_ptr = meta.map_ptr; - } err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta); if (err) return err; @@ -2404,6 +2467,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn if (err) return err; + err = record_func_map(env, &meta, func_id, insn_idx); + if (err) + return err; + /* Mark slots with STACK_MISC in case of raw mode, stack offset * is inferred from register state. */ @@ -2428,8 +2495,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn } else if (fn->ret_type == RET_VOID) { regs[BPF_REG_0].type = NOT_INIT; } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) { - struct bpf_insn_aux_data *insn_aux; - regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; /* There is no offset yet applied, variable or fixed */ mark_reg_known_zero(env, regs, BPF_REG_0); @@ -2445,11 +2510,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn } regs[BPF_REG_0].map_ptr = meta.map_ptr; regs[BPF_REG_0].id = ++env->id_gen; - insn_aux = &env->insn_aux_data[insn_idx]; - if (!insn_aux->map_ptr) - insn_aux->map_ptr = meta.map_ptr; - else if (insn_aux->map_ptr != meta.map_ptr) - insn_aux->map_ptr = BPF_MAP_PTR_POISON; } else { verbose(env, "unknown return type %d of func %s#%d\n", fn->ret_type, func_id_name(func_id), func_id); @@ -5169,6 +5229,34 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) else continue; + if (type == BPF_WRITE && + env->insn_aux_data[i + delta].sanitize_stack_off) { + struct bpf_insn patch[] = { + /* Sanitize suspicious stack slot with zero. + * There are no memory dependencies for this store, + * since it's only using frame pointer and immediate + * constant of zero + */ + BPF_ST_MEM(BPF_DW, BPF_REG_FP, + env->insn_aux_data[i + delta].sanitize_stack_off, + 0), + /* the original STX instruction will immediately + * overwrite the same stack slot with appropriate value + */ + *insn, + }; + + cnt = ARRAY_SIZE(patch); + new_prog = bpf_patch_insn_data(env, i + delta, patch, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX) continue; @@ -5417,6 +5505,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) struct bpf_insn *insn = prog->insnsi; const struct bpf_func_proto *fn; const int insn_cnt = prog->len; + struct bpf_insn_aux_data *aux; struct bpf_insn insn_buf[16]; struct bpf_prog *new_prog; struct bpf_map *map_ptr; @@ -5491,19 +5580,22 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) insn->imm = 0; insn->code = BPF_JMP | BPF_TAIL_CALL; + aux = &env->insn_aux_data[i + delta]; + if (!bpf_map_ptr_unpriv(aux)) + continue; + /* instead of changing every JIT dealing with tail_call * emit two extra insns: * if (index >= max_entries) goto out; * index &= array->index_mask; * to avoid out-of-bounds cpu speculation */ - map_ptr = env->insn_aux_data[i + delta].map_ptr; - if (map_ptr == BPF_MAP_PTR_POISON) { + if (bpf_map_ptr_poisoned(aux)) { verbose(env, "tail_call abusing map_ptr\n"); return -EINVAL; } - if (!map_ptr->unpriv_array) - continue; + + map_ptr = BPF_MAP_PTR(aux->map_state); insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3, map_ptr->max_entries, 2); insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3, @@ -5527,9 +5619,12 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) */ if (prog->jit_requested && BITS_PER_LONG == 64 && insn->imm == BPF_FUNC_map_lookup_elem) { - map_ptr = env->insn_aux_data[i + delta].map_ptr; - if (map_ptr == BPF_MAP_PTR_POISON || - !map_ptr->ops->map_gen_lookup) + aux = &env->insn_aux_data[i + delta]; + if (bpf_map_ptr_poisoned(aux)) + goto patch_call_imm; + + map_ptr = BPF_MAP_PTR(aux->map_state); + if (!map_ptr->ops->map_gen_lookup) goto patch_call_imm; cnt = map_ptr->ops->map_gen_lookup(map_ptr, insn_buf); diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index b928b27050c6..0808a33d16d3 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -218,9 +218,9 @@ extern const struct proc_ns_operations cgroupns_operations; * cgroup-v1.c */ extern struct cftype cgroup1_base_files[]; -extern const struct file_operations proc_cgroupstats_operations; extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops; +int proc_cgroupstats_show(struct seq_file *m, void *v); bool cgroup1_ssid_disabled(int ssid); void cgroup1_pidlist_destroy_all(struct cgroup *cgrp); void cgroup1_release_agent(struct work_struct *work); diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index a2c05d2476ac..e06c97f3ed1a 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -682,7 +682,7 @@ struct cftype cgroup1_base_files[] = { }; /* Display information about each subsystem and each hierarchy */ -static int proc_cgroupstats_show(struct seq_file *m, void *v) +int proc_cgroupstats_show(struct seq_file *m, void *v) { struct cgroup_subsys *ss; int i; @@ -705,18 +705,6 @@ static int proc_cgroupstats_show(struct seq_file *m, void *v) return 0; } -static int cgroupstats_open(struct inode *inode, struct file *file) -{ - return single_open(file, proc_cgroupstats_show, NULL); -} - -const struct file_operations proc_cgroupstats_operations = { - .open = cgroupstats_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - /** * cgroupstats_build - build and fill cgroupstats * @stats: cgroupstats to fill information into diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index a662bfcbea0e..12883656e63e 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5335,7 +5335,7 @@ int __init cgroup_init(void) WARN_ON(sysfs_create_mount_point(fs_kobj, "cgroup")); WARN_ON(register_filesystem(&cgroup_fs_type)); WARN_ON(register_filesystem(&cgroup2_fs_type)); - WARN_ON(!proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations)); + WARN_ON(!proc_create_single("cgroups", 0, NULL, proc_cgroupstats_show)); return 0; } diff --git a/kernel/delayacct.c b/kernel/delayacct.c index e2764d767f18..ca8ac2824f0b 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -44,23 +44,24 @@ void __delayacct_tsk_init(struct task_struct *tsk) { tsk->delays = kmem_cache_zalloc(delayacct_cache, GFP_KERNEL); if (tsk->delays) - spin_lock_init(&tsk->delays->lock); + raw_spin_lock_init(&tsk->delays->lock); } /* * Finish delay accounting for a statistic using its timestamps (@start), * accumalator (@total) and @count */ -static void delayacct_end(spinlock_t *lock, u64 *start, u64 *total, u32 *count) +static void delayacct_end(raw_spinlock_t *lock, u64 *start, u64 *total, + u32 *count) { s64 ns = ktime_get_ns() - *start; unsigned long flags; if (ns > 0) { - spin_lock_irqsave(lock, flags); + raw_spin_lock_irqsave(lock, flags); *total += ns; (*count)++; - spin_unlock_irqrestore(lock, flags); + raw_spin_unlock_irqrestore(lock, flags); } } @@ -127,7 +128,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) /* zero XXX_total, non-zero XXX_count implies XXX stat overflowed */ - spin_lock_irqsave(&tsk->delays->lock, flags); + raw_spin_lock_irqsave(&tsk->delays->lock, flags); tmp = d->blkio_delay_total + tsk->delays->blkio_delay; d->blkio_delay_total = (tmp < d->blkio_delay_total) ? 0 : tmp; tmp = d->swapin_delay_total + tsk->delays->swapin_delay; @@ -137,7 +138,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) d->blkio_count += tsk->delays->blkio_count; d->swapin_count += tsk->delays->swapin_count; d->freepages_count += tsk->delays->freepages_count; - spin_unlock_irqrestore(&tsk->delays->lock, flags); + raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return 0; } @@ -147,10 +148,10 @@ __u64 __delayacct_blkio_ticks(struct task_struct *tsk) __u64 ret; unsigned long flags; - spin_lock_irqsave(&tsk->delays->lock, flags); + raw_spin_lock_irqsave(&tsk->delays->lock, flags); ret = nsec_to_clock_t(tsk->delays->blkio_delay + tsk->delays->swapin_delay); - spin_unlock_irqrestore(&tsk->delays->lock, flags); + raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return ret; } diff --git a/kernel/dma.c b/kernel/dma.c index 3506fc34a712..40f152936316 100644 --- a/kernel/dma.c +++ b/kernel/dma.c @@ -135,21 +135,9 @@ static int proc_dma_show(struct seq_file *m, void *v) } #endif /* MAX_DMA_CHANNELS */ -static int proc_dma_open(struct inode *inode, struct file *file) -{ - return single_open(file, proc_dma_show, NULL); -} - -static const struct file_operations proc_dma_operations = { - .open = proc_dma_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static int __init proc_dma_init(void) { - proc_create("dma", 0, NULL, &proc_dma_operations); + proc_create_single("dma", 0, NULL, proc_dma_show); return 0; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 67612ce359ad..08f5e1b42b43 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5120,6 +5120,8 @@ static long perf_compat_ioctl(struct file *file, unsigned int cmd, switch (_IOC_NR(cmd)) { case _IOC_NR(PERF_EVENT_IOC_SET_FILTER): case _IOC_NR(PERF_EVENT_IOC_ID): + case _IOC_NR(PERF_EVENT_IOC_QUERY_BPF): + case _IOC_NR(PERF_EVENT_IOC_MODIFY_ATTRIBUTES): /* Fix up pointer size (usually 4 -> 8 in 32-on-64-bit case */ if (_IOC_SIZE(cmd) == sizeof(compat_uptr_t)) { cmd &= ~IOCSIZE_MASK; @@ -6668,7 +6670,7 @@ static void perf_event_addr_filters_exec(struct perf_event *event, void *data) raw_spin_lock_irqsave(&ifh->lock, flags); list_for_each_entry(filter, &ifh->list, entry) { - if (filter->inode) { + if (filter->path.dentry) { event->addr_filters_offs[count] = 0; restart++; } @@ -7333,7 +7335,7 @@ static bool perf_addr_filter_match(struct perf_addr_filter *filter, struct file *file, unsigned long offset, unsigned long size) { - if (filter->inode != file_inode(file)) + if (d_inode(filter->path.dentry) != file_inode(file)) return false; if (filter->offset > offset + size) @@ -8686,8 +8688,7 @@ static void free_filters_list(struct list_head *filters) struct perf_addr_filter *filter, *iter; list_for_each_entry_safe(filter, iter, filters, entry) { - if (filter->inode) - iput(filter->inode); + path_put(&filter->path); list_del(&filter->entry); kfree(filter); } @@ -8784,7 +8785,7 @@ static void perf_event_addr_filters_apply(struct perf_event *event) * Adjust base offset if the filter is associated to a binary * that needs to be mapped: */ - if (filter->inode) + if (filter->path.dentry) event->addr_filters_offs[count] = perf_addr_filter_apply(filter, mm); @@ -8858,7 +8859,6 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, { struct perf_addr_filter *filter = NULL; char *start, *orig, *filename = NULL; - struct path path; substring_t args[MAX_OPT_ARGS]; int state = IF_STATE_ACTION, token; unsigned int kernel = 0; @@ -8971,19 +8971,18 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, goto fail_free_name; /* look up the path and grab its inode */ - ret = kern_path(filename, LOOKUP_FOLLOW, &path); + ret = kern_path(filename, LOOKUP_FOLLOW, + &filter->path); if (ret) goto fail_free_name; - filter->inode = igrab(d_inode(path.dentry)); - path_put(&path); kfree(filename); filename = NULL; ret = -EINVAL; - if (!filter->inode || - !S_ISREG(filter->inode->i_mode)) - /* free_filters_list() will iput() */ + if (!filter->path.dentry || + !S_ISREG(d_inode(filter->path.dentry) + ->i_mode)) goto fail; event->addr_filters.nr_file_filters++; @@ -10521,19 +10520,20 @@ SYSCALL_DEFINE5(perf_event_open, if (pmu->task_ctx_nr == perf_sw_context) event->event_caps |= PERF_EV_CAP_SOFTWARE; - if (group_leader && - (is_software_event(event) != is_software_event(group_leader))) { - if (is_software_event(event)) { + if (group_leader) { + if (is_software_event(event) && + !in_software_context(group_leader)) { /* - * If event and group_leader are not both a software - * event, and event is, then group leader is not. + * If the event is a sw event, but the group_leader + * is on hw context. * - * Allow the addition of software events to !software - * groups, this is safe because software events never - * fail to schedule. + * Allow the addition of software events to hw + * groups, this is safe because software events + * never fail to schedule. */ - pmu = group_leader->pmu; - } else if (is_software_event(group_leader) && + pmu = group_leader->ctx->pmu; + } else if (!is_software_event(event) && + is_software_event(group_leader) && (group_leader->group_caps & PERF_EV_CAP_SOFTWARE)) { /* * In case the group is a pure software group, and we diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c index a5697119290e..33f07c5f2515 100644 --- a/kernel/exec_domain.c +++ b/kernel/exec_domain.c @@ -27,21 +27,9 @@ static int execdomains_proc_show(struct seq_file *m, void *v) return 0; } -static int execdomains_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, execdomains_proc_show, NULL); -} - -static const struct file_operations execdomains_proc_fops = { - .open = execdomains_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static int __init proc_execdomains_init(void) { - proc_create("execdomains", 0, NULL, &execdomains_proc_fops); + proc_create_single("execdomains", 0, NULL, execdomains_proc_show); return 0; } module_init(proc_execdomains_init); diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 7cb091d81d91..37eda10f5c36 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -185,11 +185,6 @@ static int irq_affinity_list_proc_open(struct inode *inode, struct file *file) return single_open(file, irq_affinity_list_proc_show, PDE_DATA(inode)); } -static int irq_affinity_hint_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, irq_affinity_hint_proc_show, PDE_DATA(inode)); -} - static const struct file_operations irq_affinity_proc_fops = { .open = irq_affinity_proc_open, .read = seq_read, @@ -198,13 +193,6 @@ static const struct file_operations irq_affinity_proc_fops = { .write = irq_affinity_proc_write, }; -static const struct file_operations irq_affinity_hint_proc_fops = { - .open = irq_affinity_hint_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static const struct file_operations irq_affinity_list_proc_fops = { .open = irq_affinity_list_proc_open, .read = seq_read, @@ -223,32 +211,6 @@ static int irq_effective_aff_list_proc_show(struct seq_file *m, void *v) { return show_irq_affinity(EFFECTIVE_LIST, m); } - -static int irq_effective_aff_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, irq_effective_aff_proc_show, PDE_DATA(inode)); -} - -static int irq_effective_aff_list_proc_open(struct inode *inode, - struct file *file) -{ - return single_open(file, irq_effective_aff_list_proc_show, - PDE_DATA(inode)); -} - -static const struct file_operations irq_effective_aff_proc_fops = { - .open = irq_effective_aff_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static const struct file_operations irq_effective_aff_list_proc_fops = { - .open = irq_effective_aff_list_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; #endif static int default_affinity_show(struct seq_file *m, void *v) @@ -313,18 +275,6 @@ static int irq_node_proc_show(struct seq_file *m, void *v) seq_printf(m, "%d\n", irq_desc_get_node(desc)); return 0; } - -static int irq_node_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, irq_node_proc_show, PDE_DATA(inode)); -} - -static const struct file_operations irq_node_proc_fops = { - .open = irq_node_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; #endif static int irq_spurious_proc_show(struct seq_file *m, void *v) @@ -337,18 +287,6 @@ static int irq_spurious_proc_show(struct seq_file *m, void *v) return 0; } -static int irq_spurious_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, irq_spurious_proc_show, PDE_DATA(inode)); -} - -static const struct file_operations irq_spurious_proc_fops = { - .open = irq_spurious_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - #define MAX_NAMELEN 128 static int name_unique(unsigned int irq, struct irqaction *new_action) @@ -421,24 +359,24 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc) &irq_affinity_proc_fops, irqp); /* create /proc/irq/<irq>/affinity_hint */ - proc_create_data("affinity_hint", 0444, desc->dir, - &irq_affinity_hint_proc_fops, irqp); + proc_create_single_data("affinity_hint", 0444, desc->dir, + irq_affinity_hint_proc_show, irqp); /* create /proc/irq/<irq>/smp_affinity_list */ proc_create_data("smp_affinity_list", 0644, desc->dir, &irq_affinity_list_proc_fops, irqp); - proc_create_data("node", 0444, desc->dir, - &irq_node_proc_fops, irqp); + proc_create_single_data("node", 0444, desc->dir, irq_node_proc_show, + irqp); # ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK - proc_create_data("effective_affinity", 0444, desc->dir, - &irq_effective_aff_proc_fops, irqp); - proc_create_data("effective_affinity_list", 0444, desc->dir, - &irq_effective_aff_list_proc_fops, irqp); + proc_create_single_data("effective_affinity", 0444, desc->dir, + irq_effective_aff_proc_show, irqp); + proc_create_single_data("effective_affinity_list", 0444, desc->dir, + irq_effective_aff_list_proc_show, irqp); # endif #endif - proc_create_data("spurious", 0444, desc->dir, - &irq_spurious_proc_fops, (void *)(long)irq); + proc_create_single_data("spurious", 0444, desc->dir, + irq_spurious_proc_show, (void *)(long)irq); out_unlock: mutex_unlock(®ister_lock); diff --git a/kernel/kthread.c b/kernel/kthread.c index 2017a39ab490..481951bf091d 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -193,7 +193,7 @@ EXPORT_SYMBOL_GPL(kthread_parkme); void kthread_park_complete(struct task_struct *k) { - complete(&to_kthread(k)->parked); + complete_all(&to_kthread(k)->parked); } static int kthread(void *_create) @@ -459,6 +459,7 @@ void kthread_unpark(struct task_struct *k) if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags)) __kthread_bind(k, kthread->cpu, TASK_PARKED); + reinit_completion(&kthread->parked); clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); wake_up_state(k, TASK_PARKED); } @@ -483,9 +484,6 @@ int kthread_park(struct task_struct *k) if (WARN_ON(k->flags & PF_EXITING)) return -ENOSYS; - if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags))) - return -EBUSY; - set_bit(KTHREAD_SHOULD_PARK, &kthread->flags); if (k != current) { wake_up_process(k); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 023386338269..edcac5de7ebc 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -561,20 +561,24 @@ static void print_lock(struct held_lock *hlock) printk(KERN_CONT ", at: %pS\n", (void *)hlock->acquire_ip); } -static void lockdep_print_held_locks(struct task_struct *curr) +static void lockdep_print_held_locks(struct task_struct *p) { - int i, depth = curr->lockdep_depth; + int i, depth = READ_ONCE(p->lockdep_depth); - if (!depth) { - printk("no locks held by %s/%d.\n", curr->comm, task_pid_nr(curr)); + if (!depth) + printk("no locks held by %s/%d.\n", p->comm, task_pid_nr(p)); + else + printk("%d lock%s held by %s/%d:\n", depth, + depth > 1 ? "s" : "", p->comm, task_pid_nr(p)); + /* + * It's not reliable to print a task's held locks if it's not sleeping + * and it's not the current task. + */ + if (p->state == TASK_RUNNING && p != current) return; - } - printk("%d lock%s held by %s/%d:\n", - depth, depth > 1 ? "s" : "", curr->comm, task_pid_nr(curr)); - for (i = 0; i < depth; i++) { printk(" #%d: ", i); - print_lock(curr->held_locks + i); + print_lock(p->held_locks + i); } } @@ -4451,8 +4455,6 @@ EXPORT_SYMBOL_GPL(debug_check_no_locks_held); void debug_show_all_locks(void) { struct task_struct *g, *p; - int count = 10; - int unlock = 1; if (unlikely(!debug_locks)) { pr_warn("INFO: lockdep is turned off.\n"); @@ -4460,50 +4462,18 @@ void debug_show_all_locks(void) } pr_warn("\nShowing all locks held in the system:\n"); - /* - * Here we try to get the tasklist_lock as hard as possible, - * if not successful after 2 seconds we ignore it (but keep - * trying). This is to enable a debug printout even if a - * tasklist_lock-holding task deadlocks or crashes. - */ -retry: - if (!read_trylock(&tasklist_lock)) { - if (count == 10) - pr_warn("hm, tasklist_lock locked, retrying... "); - if (count) { - count--; - pr_cont(" #%d", 10-count); - mdelay(200); - goto retry; - } - pr_cont(" ignoring it.\n"); - unlock = 0; - } else { - if (count != 10) - pr_cont(" locked it.\n"); - } - - do_each_thread(g, p) { - /* - * It's not reliable to print a task's held locks - * if it's not sleeping (or if it's not the current - * task): - */ - if (p->state == TASK_RUNNING && p != current) + rcu_read_lock(); + for_each_process_thread(g, p) { + if (!p->lockdep_depth) continue; - if (p->lockdep_depth) - lockdep_print_held_locks(p); - if (!unlock) - if (read_trylock(&tasklist_lock)) - unlock = 1; + lockdep_print_held_locks(p); touch_nmi_watchdog(); - } while_each_thread(g, p); + touch_all_softlockup_watchdogs(); + } + rcu_read_unlock(); pr_warn("\n"); pr_warn("=============================================\n\n"); - - if (unlock) - read_unlock(&tasklist_lock); } EXPORT_SYMBOL_GPL(debug_show_all_locks); #endif diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index ad69bbc9bd28..3dd980dfba2d 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -101,18 +101,6 @@ static const struct seq_operations lockdep_ops = { .show = l_show, }; -static int lockdep_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &lockdep_ops); -} - -static const struct file_operations proc_lockdep_operations = { - .open = lockdep_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - #ifdef CONFIG_PROVE_LOCKING static void *lc_start(struct seq_file *m, loff_t *pos) { @@ -170,18 +158,6 @@ static const struct seq_operations lockdep_chains_ops = { .stop = lc_stop, .show = lc_show, }; - -static int lockdep_chains_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &lockdep_chains_ops); -} - -static const struct file_operations proc_lockdep_chains_operations = { - .open = lockdep_chains_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; #endif /* CONFIG_PROVE_LOCKING */ static void lockdep_stats_debug_show(struct seq_file *m) @@ -355,18 +331,6 @@ static int lockdep_stats_show(struct seq_file *m, void *v) return 0; } -static int lockdep_stats_open(struct inode *inode, struct file *file) -{ - return single_open(file, lockdep_stats_show, NULL); -} - -static const struct file_operations proc_lockdep_stats_operations = { - .open = lockdep_stats_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - #ifdef CONFIG_LOCK_STAT struct lock_stat_data { @@ -682,14 +646,11 @@ static const struct file_operations proc_lock_stat_operations = { static int __init lockdep_proc_init(void) { - proc_create("lockdep", S_IRUSR, NULL, &proc_lockdep_operations); + proc_create_seq("lockdep", S_IRUSR, NULL, &lockdep_ops); #ifdef CONFIG_PROVE_LOCKING - proc_create("lockdep_chains", S_IRUSR, NULL, - &proc_lockdep_chains_operations); + proc_create_seq("lockdep_chains", S_IRUSR, NULL, &lockdep_chains_ops); #endif - proc_create("lockdep_stats", S_IRUSR, NULL, - &proc_lockdep_stats_operations); - + proc_create_single("lockdep_stats", S_IRUSR, NULL, lockdep_stats_show); #ifdef CONFIG_LOCK_STAT proc_create("lock_stat", S_IRUSR | S_IWUSR, NULL, &proc_lock_stat_operations); diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h index f046b7ce9dd6..5e10153b4d3c 100644 --- a/kernel/locking/mcs_spinlock.h +++ b/kernel/locking/mcs_spinlock.h @@ -23,13 +23,15 @@ struct mcs_spinlock { #ifndef arch_mcs_spin_lock_contended /* - * Using smp_load_acquire() provides a memory barrier that ensures - * subsequent operations happen after the lock is acquired. + * Using smp_cond_load_acquire() provides the acquire semantics + * required so that subsequent operations happen after the + * lock is acquired. Additionally, some architectures such as + * ARM64 would like to do spin-waiting instead of purely + * spinning, and smp_cond_load_acquire() provides that behavior. */ #define arch_mcs_spin_lock_contended(l) \ do { \ - while (!(smp_load_acquire(l))) \ - cpu_relax(); \ + smp_cond_load_acquire(l, VAL); \ } while (0) #endif diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 2048359f33d2..f44f658ae629 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -139,8 +139,9 @@ static inline bool __mutex_trylock(struct mutex *lock) static __always_inline bool __mutex_trylock_fast(struct mutex *lock) { unsigned long curr = (unsigned long)current; + unsigned long zero = 0UL; - if (!atomic_long_cmpxchg_acquire(&lock->owner, 0UL, curr)) + if (atomic_long_try_cmpxchg_acquire(&lock->owner, &zero, curr)) return true; return false; diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index d880296245c5..bfaeb05123ff 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -12,11 +12,11 @@ * GNU General Public License for more details. * * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P. - * (C) Copyright 2013-2014 Red Hat, Inc. + * (C) Copyright 2013-2014,2018 Red Hat, Inc. * (C) Copyright 2015 Intel Corp. * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP * - * Authors: Waiman Long <waiman.long@hpe.com> + * Authors: Waiman Long <longman@redhat.com> * Peter Zijlstra <peterz@infradead.org> */ @@ -33,6 +33,11 @@ #include <asm/qspinlock.h> /* + * Include queued spinlock statistics code + */ +#include "qspinlock_stat.h" + +/* * The basic principle of a queue-based spinlock can best be understood * by studying a classic queue-based spinlock implementation called the * MCS lock. The paper below provides a good description for this kind @@ -77,6 +82,18 @@ #endif /* + * The pending bit spinning loop count. + * This heuristic is used to limit the number of lockword accesses + * made by atomic_cond_read_relaxed when waiting for the lock to + * transition out of the "== _Q_PENDING_VAL" state. We don't spin + * indefinitely because there's no guarantee that we'll make forward + * progress. + */ +#ifndef _Q_PENDING_LOOPS +#define _Q_PENDING_LOOPS 1 +#endif + +/* * Per-CPU queue node structures; we can never have more than 4 nested * contexts: task, softirq, hardirq, nmi. * @@ -114,41 +131,18 @@ static inline __pure struct mcs_spinlock *decode_tail(u32 tail) #define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK) -/* - * By using the whole 2nd least significant byte for the pending bit, we - * can allow better optimization of the lock acquisition for the pending - * bit holder. +#if _Q_PENDING_BITS == 8 +/** + * clear_pending - clear the pending bit. + * @lock: Pointer to queued spinlock structure * - * This internal structure is also used by the set_locked function which - * is not restricted to _Q_PENDING_BITS == 8. + * *,1,* -> *,0,* */ -struct __qspinlock { - union { - atomic_t val; -#ifdef __LITTLE_ENDIAN - struct { - u8 locked; - u8 pending; - }; - struct { - u16 locked_pending; - u16 tail; - }; -#else - struct { - u16 tail; - u16 locked_pending; - }; - struct { - u8 reserved[2]; - u8 pending; - u8 locked; - }; -#endif - }; -}; +static __always_inline void clear_pending(struct qspinlock *lock) +{ + WRITE_ONCE(lock->pending, 0); +} -#if _Q_PENDING_BITS == 8 /** * clear_pending_set_locked - take ownership and clear the pending bit. * @lock: Pointer to queued spinlock structure @@ -159,9 +153,7 @@ struct __qspinlock { */ static __always_inline void clear_pending_set_locked(struct qspinlock *lock) { - struct __qspinlock *l = (void *)lock; - - WRITE_ONCE(l->locked_pending, _Q_LOCKED_VAL); + WRITE_ONCE(lock->locked_pending, _Q_LOCKED_VAL); } /* @@ -176,19 +168,28 @@ static __always_inline void clear_pending_set_locked(struct qspinlock *lock) */ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail) { - struct __qspinlock *l = (void *)lock; - /* - * Use release semantics to make sure that the MCS node is properly - * initialized before changing the tail code. + * We can use relaxed semantics since the caller ensures that the + * MCS node is properly initialized before updating the tail. */ - return (u32)xchg_release(&l->tail, + return (u32)xchg_relaxed(&lock->tail, tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET; } #else /* _Q_PENDING_BITS == 8 */ /** + * clear_pending - clear the pending bit. + * @lock: Pointer to queued spinlock structure + * + * *,1,* -> *,0,* + */ +static __always_inline void clear_pending(struct qspinlock *lock) +{ + atomic_andnot(_Q_PENDING_VAL, &lock->val); +} + +/** * clear_pending_set_locked - take ownership and clear the pending bit. * @lock: Pointer to queued spinlock structure * @@ -216,10 +217,11 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail) for (;;) { new = (val & _Q_LOCKED_PENDING_MASK) | tail; /* - * Use release semantics to make sure that the MCS node is - * properly initialized before changing the tail code. + * We can use relaxed semantics since the caller ensures that + * the MCS node is properly initialized before updating the + * tail. */ - old = atomic_cmpxchg_release(&lock->val, val, new); + old = atomic_cmpxchg_relaxed(&lock->val, val, new); if (old == val) break; @@ -237,9 +239,7 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail) */ static __always_inline void set_locked(struct qspinlock *lock) { - struct __qspinlock *l = (void *)lock; - - WRITE_ONCE(l->locked, _Q_LOCKED_VAL); + WRITE_ONCE(lock->locked, _Q_LOCKED_VAL); } @@ -294,86 +294,83 @@ static __always_inline u32 __pv_wait_head_or_lock(struct qspinlock *lock, void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) { struct mcs_spinlock *prev, *next, *node; - u32 new, old, tail; + u32 old, tail; int idx; BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS)); if (pv_enabled()) - goto queue; + goto pv_queue; if (virt_spin_lock(lock)) return; /* - * wait for in-progress pending->locked hand-overs + * Wait for in-progress pending->locked hand-overs with a bounded + * number of spins so that we guarantee forward progress. * * 0,1,0 -> 0,0,1 */ if (val == _Q_PENDING_VAL) { - while ((val = atomic_read(&lock->val)) == _Q_PENDING_VAL) - cpu_relax(); + int cnt = _Q_PENDING_LOOPS; + val = atomic_cond_read_relaxed(&lock->val, + (VAL != _Q_PENDING_VAL) || !cnt--); } /* + * If we observe any contention; queue. + */ + if (val & ~_Q_LOCKED_MASK) + goto queue; + + /* * trylock || pending * * 0,0,0 -> 0,0,1 ; trylock * 0,0,1 -> 0,1,1 ; pending */ - for (;;) { + val = atomic_fetch_or_acquire(_Q_PENDING_VAL, &lock->val); + if (!(val & ~_Q_LOCKED_MASK)) { /* - * If we observe any contention; queue. + * We're pending, wait for the owner to go away. + * + * *,1,1 -> *,1,0 + * + * this wait loop must be a load-acquire such that we match the + * store-release that clears the locked bit and create lock + * sequentiality; this is because not all + * clear_pending_set_locked() implementations imply full + * barriers. */ - if (val & ~_Q_LOCKED_MASK) - goto queue; - - new = _Q_LOCKED_VAL; - if (val == new) - new |= _Q_PENDING_VAL; + if (val & _Q_LOCKED_MASK) { + atomic_cond_read_acquire(&lock->val, + !(VAL & _Q_LOCKED_MASK)); + } /* - * Acquire semantic is required here as the function may - * return immediately if the lock was free. + * take ownership and clear the pending bit. + * + * *,1,0 -> *,0,1 */ - old = atomic_cmpxchg_acquire(&lock->val, val, new); - if (old == val) - break; - - val = old; - } - - /* - * we won the trylock - */ - if (new == _Q_LOCKED_VAL) + clear_pending_set_locked(lock); + qstat_inc(qstat_lock_pending, true); return; + } /* - * we're pending, wait for the owner to go away. - * - * *,1,1 -> *,1,0 - * - * this wait loop must be a load-acquire such that we match the - * store-release that clears the locked bit and create lock - * sequentiality; this is because not all clear_pending_set_locked() - * implementations imply full barriers. - */ - smp_cond_load_acquire(&lock->val.counter, !(VAL & _Q_LOCKED_MASK)); - - /* - * take ownership and clear the pending bit. - * - * *,1,0 -> *,0,1 + * If pending was clear but there are waiters in the queue, then + * we need to undo our setting of pending before we queue ourselves. */ - clear_pending_set_locked(lock); - return; + if (!(val & _Q_PENDING_MASK)) + clear_pending(lock); /* * End of pending bit optimistic spinning and beginning of MCS * queuing. */ queue: + qstat_inc(qstat_lock_slowpath, true); +pv_queue: node = this_cpu_ptr(&mcs_nodes[0]); idx = node->count++; tail = encode_tail(smp_processor_id(), idx); @@ -400,12 +397,18 @@ queue: goto release; /* + * Ensure that the initialisation of @node is complete before we + * publish the updated tail via xchg_tail() and potentially link + * @node into the waitqueue via WRITE_ONCE(prev->next, node) below. + */ + smp_wmb(); + + /* + * Publish the updated tail. * We have already touched the queueing cacheline; don't bother with * pending stuff. * * p,*,* -> n,*,* - * - * RELEASE, such that the stores to @node must be complete. */ old = xchg_tail(lock, tail); next = NULL; @@ -417,14 +420,8 @@ queue: if (old & _Q_TAIL_MASK) { prev = decode_tail(old); - /* - * We must ensure that the stores to @node are observed before - * the write to prev->next. The address dependency from - * xchg_tail is not sufficient to ensure this because the read - * component of xchg_tail is unordered with respect to the - * initialisation of @node. - */ - smp_store_release(&prev->next, node); + /* Link @node into the waitqueue. */ + WRITE_ONCE(prev->next, node); pv_wait_node(node, prev); arch_mcs_spin_lock_contended(&node->locked); @@ -453,8 +450,8 @@ queue: * * The PV pv_wait_head_or_lock function, if active, will acquire * the lock and return a non-zero value. So we have to skip the - * smp_cond_load_acquire() call. As the next PV queue head hasn't been - * designated yet, there is no way for the locked value to become + * atomic_cond_read_acquire() call. As the next PV queue head hasn't + * been designated yet, there is no way for the locked value to become * _Q_SLOW_VAL. So both the set_locked() and the * atomic_cmpxchg_relaxed() calls will be safe. * @@ -464,44 +461,38 @@ queue: if ((val = pv_wait_head_or_lock(lock, node))) goto locked; - val = smp_cond_load_acquire(&lock->val.counter, !(VAL & _Q_LOCKED_PENDING_MASK)); + val = atomic_cond_read_acquire(&lock->val, !(VAL & _Q_LOCKED_PENDING_MASK)); locked: /* * claim the lock: * * n,0,0 -> 0,0,1 : lock, uncontended - * *,0,0 -> *,0,1 : lock, contended + * *,*,0 -> *,*,1 : lock, contended * - * If the queue head is the only one in the queue (lock value == tail), - * clear the tail code and grab the lock. Otherwise, we only need - * to grab the lock. + * If the queue head is the only one in the queue (lock value == tail) + * and nobody is pending, clear the tail code and grab the lock. + * Otherwise, we only need to grab the lock. */ - for (;;) { - /* In the PV case we might already have _Q_LOCKED_VAL set */ - if ((val & _Q_TAIL_MASK) != tail) { - set_locked(lock); - break; - } - /* - * The smp_cond_load_acquire() call above has provided the - * necessary acquire semantics required for locking. At most - * two iterations of this loop may be ran. - */ - old = atomic_cmpxchg_relaxed(&lock->val, val, _Q_LOCKED_VAL); - if (old == val) - goto release; /* No contention */ - val = old; - } + /* + * In the PV case we might already have _Q_LOCKED_VAL set. + * + * The atomic_cond_read_acquire() call above has provided the + * necessary acquire semantics required for locking. + */ + if (((val & _Q_TAIL_MASK) == tail) && + atomic_try_cmpxchg_relaxed(&lock->val, &val, _Q_LOCKED_VAL)) + goto release; /* No contention */ + + /* Either somebody is queued behind us or _Q_PENDING_VAL is set */ + set_locked(lock); /* * contended path; wait for next if not observed yet, release. */ - if (!next) { - while (!(next = READ_ONCE(node->next))) - cpu_relax(); - } + if (!next) + next = smp_cond_load_relaxed(&node->next, (VAL)); arch_mcs_spin_unlock_contended(&next->locked); pv_kick_node(lock, next); diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index 6ee477765e6c..5a0cf5f9008c 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -56,11 +56,6 @@ struct pv_node { }; /* - * Include queued spinlock statistics code - */ -#include "qspinlock_stat.h" - -/* * Hybrid PV queued/unfair lock * * By replacing the regular queued_spin_trylock() with the function below, @@ -87,8 +82,6 @@ struct pv_node { #define queued_spin_trylock(l) pv_hybrid_queued_unfair_trylock(l) static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock) { - struct __qspinlock *l = (void *)lock; - /* * Stay in unfair lock mode as long as queued mode waiters are * present in the MCS wait queue but the pending bit isn't set. @@ -97,7 +90,7 @@ static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock) int val = atomic_read(&lock->val); if (!(val & _Q_LOCKED_PENDING_MASK) && - (cmpxchg_acquire(&l->locked, 0, _Q_LOCKED_VAL) == 0)) { + (cmpxchg_acquire(&lock->locked, 0, _Q_LOCKED_VAL) == 0)) { qstat_inc(qstat_pv_lock_stealing, true); return true; } @@ -117,16 +110,7 @@ static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock) #if _Q_PENDING_BITS == 8 static __always_inline void set_pending(struct qspinlock *lock) { - struct __qspinlock *l = (void *)lock; - - WRITE_ONCE(l->pending, 1); -} - -static __always_inline void clear_pending(struct qspinlock *lock) -{ - struct __qspinlock *l = (void *)lock; - - WRITE_ONCE(l->pending, 0); + WRITE_ONCE(lock->pending, 1); } /* @@ -136,10 +120,8 @@ static __always_inline void clear_pending(struct qspinlock *lock) */ static __always_inline int trylock_clear_pending(struct qspinlock *lock) { - struct __qspinlock *l = (void *)lock; - - return !READ_ONCE(l->locked) && - (cmpxchg_acquire(&l->locked_pending, _Q_PENDING_VAL, + return !READ_ONCE(lock->locked) && + (cmpxchg_acquire(&lock->locked_pending, _Q_PENDING_VAL, _Q_LOCKED_VAL) == _Q_PENDING_VAL); } #else /* _Q_PENDING_BITS == 8 */ @@ -148,11 +130,6 @@ static __always_inline void set_pending(struct qspinlock *lock) atomic_or(_Q_PENDING_VAL, &lock->val); } -static __always_inline void clear_pending(struct qspinlock *lock) -{ - atomic_andnot(_Q_PENDING_VAL, &lock->val); -} - static __always_inline int trylock_clear_pending(struct qspinlock *lock) { int val = atomic_read(&lock->val); @@ -384,7 +361,6 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev) static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node) { struct pv_node *pn = (struct pv_node *)node; - struct __qspinlock *l = (void *)lock; /* * If the vCPU is indeed halted, advance its state to match that of @@ -413,7 +389,7 @@ static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node) * the hash table later on at unlock time, no atomic instruction is * needed. */ - WRITE_ONCE(l->locked, _Q_SLOW_VAL); + WRITE_ONCE(lock->locked, _Q_SLOW_VAL); (void)pv_hash(lock, pn); } @@ -428,7 +404,6 @@ static u32 pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node) { struct pv_node *pn = (struct pv_node *)node; - struct __qspinlock *l = (void *)lock; struct qspinlock **lp = NULL; int waitcnt = 0; int loop; @@ -443,7 +418,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node) /* * Tracking # of slowpath locking operations */ - qstat_inc(qstat_pv_lock_slowpath, true); + qstat_inc(qstat_lock_slowpath, true); for (;; waitcnt++) { /* @@ -479,13 +454,13 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node) * * Matches the smp_rmb() in __pv_queued_spin_unlock(). */ - if (xchg(&l->locked, _Q_SLOW_VAL) == 0) { + if (xchg(&lock->locked, _Q_SLOW_VAL) == 0) { /* * The lock was free and now we own the lock. * Change the lock value back to _Q_LOCKED_VAL * and unhash the table. */ - WRITE_ONCE(l->locked, _Q_LOCKED_VAL); + WRITE_ONCE(lock->locked, _Q_LOCKED_VAL); WRITE_ONCE(*lp, NULL); goto gotlock; } @@ -493,7 +468,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node) WRITE_ONCE(pn->state, vcpu_hashed); qstat_inc(qstat_pv_wait_head, true); qstat_inc(qstat_pv_wait_again, waitcnt); - pv_wait(&l->locked, _Q_SLOW_VAL); + pv_wait(&lock->locked, _Q_SLOW_VAL); /* * Because of lock stealing, the queue head vCPU may not be @@ -518,7 +493,6 @@ gotlock: __visible void __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked) { - struct __qspinlock *l = (void *)lock; struct pv_node *node; if (unlikely(locked != _Q_SLOW_VAL)) { @@ -547,7 +521,7 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked) * Now that we have a reference to the (likely) blocked pv_node, * release the lock. */ - smp_store_release(&l->locked, 0); + smp_store_release(&lock->locked, 0); /* * At this point the memory pointed at by lock can be freed/reused, @@ -573,7 +547,6 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked) #ifndef __pv_queued_spin_unlock __visible void __pv_queued_spin_unlock(struct qspinlock *lock) { - struct __qspinlock *l = (void *)lock; u8 locked; /* @@ -581,7 +554,7 @@ __visible void __pv_queued_spin_unlock(struct qspinlock *lock) * unhash. Otherwise it would be possible to have multiple @lock * entries, which would be BAD. */ - locked = cmpxchg_release(&l->locked, _Q_LOCKED_VAL, 0); + locked = cmpxchg_release(&lock->locked, _Q_LOCKED_VAL, 0); if (likely(locked == _Q_LOCKED_VAL)) return; diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h index 4a30ef63c607..6bd78c0740fc 100644 --- a/kernel/locking/qspinlock_stat.h +++ b/kernel/locking/qspinlock_stat.h @@ -22,13 +22,14 @@ * pv_kick_wake - # of vCPU kicks used for computing pv_latency_wake * pv_latency_kick - average latency (ns) of vCPU kick operation * pv_latency_wake - average latency (ns) from vCPU kick to wakeup - * pv_lock_slowpath - # of locking operations via the slowpath * pv_lock_stealing - # of lock stealing operations * pv_spurious_wakeup - # of spurious wakeups in non-head vCPUs * pv_wait_again - # of wait's after a queue head vCPU kick * pv_wait_early - # of early vCPU wait's * pv_wait_head - # of vCPU wait's at the queue head * pv_wait_node - # of vCPU wait's at a non-head queue node + * lock_pending - # of locking operations via pending code + * lock_slowpath - # of locking operations via MCS lock queue * * Writing to the "reset_counters" file will reset all the above counter * values. @@ -46,13 +47,14 @@ enum qlock_stats { qstat_pv_kick_wake, qstat_pv_latency_kick, qstat_pv_latency_wake, - qstat_pv_lock_slowpath, qstat_pv_lock_stealing, qstat_pv_spurious_wakeup, qstat_pv_wait_again, qstat_pv_wait_early, qstat_pv_wait_head, qstat_pv_wait_node, + qstat_lock_pending, + qstat_lock_slowpath, qstat_num, /* Total number of statistical counters */ qstat_reset_cnts = qstat_num, }; @@ -73,12 +75,13 @@ static const char * const qstat_names[qstat_num + 1] = { [qstat_pv_spurious_wakeup] = "pv_spurious_wakeup", [qstat_pv_latency_kick] = "pv_latency_kick", [qstat_pv_latency_wake] = "pv_latency_wake", - [qstat_pv_lock_slowpath] = "pv_lock_slowpath", [qstat_pv_lock_stealing] = "pv_lock_stealing", [qstat_pv_wait_again] = "pv_wait_again", [qstat_pv_wait_early] = "pv_wait_early", [qstat_pv_wait_head] = "pv_wait_head", [qstat_pv_wait_node] = "pv_wait_node", + [qstat_lock_pending] = "lock_pending", + [qstat_lock_slowpath] = "lock_slowpath", [qstat_reset_cnts] = "reset_counters", }; diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index e795908f3607..3064c50e181e 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -347,30 +347,31 @@ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem) } } +static inline bool owner_on_cpu(struct task_struct *owner) +{ + /* + * As lock holder preemption issue, we both skip spinning if + * task is not on cpu or its cpu is preempted + */ + return owner->on_cpu && !vcpu_is_preempted(task_cpu(owner)); +} + static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem) { struct task_struct *owner; bool ret = true; + BUILD_BUG_ON(!rwsem_has_anonymous_owner(RWSEM_OWNER_UNKNOWN)); + if (need_resched()) return false; rcu_read_lock(); owner = READ_ONCE(sem->owner); - if (!rwsem_owner_is_writer(owner)) { - /* - * Don't spin if the rwsem is readers owned. - */ - ret = !rwsem_owner_is_reader(owner); - goto done; + if (owner) { + ret = is_rwsem_owner_spinnable(owner) && + owner_on_cpu(owner); } - - /* - * As lock holder preemption issue, we both skip spinning if task is not - * on cpu or its cpu is preempted - */ - ret = owner->on_cpu && !vcpu_is_preempted(task_cpu(owner)); -done: rcu_read_unlock(); return ret; } @@ -382,11 +383,11 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem) { struct task_struct *owner = READ_ONCE(sem->owner); - if (!rwsem_owner_is_writer(owner)) - goto out; + if (!is_rwsem_owner_spinnable(owner)) + return false; rcu_read_lock(); - while (sem->owner == owner) { + while (owner && (READ_ONCE(sem->owner) == owner)) { /* * Ensure we emit the owner->on_cpu, dereference _after_ * checking sem->owner still matches owner, if that fails, @@ -399,8 +400,7 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem) * abort spinning when need_resched or owner is not running or * owner's cpu is preempted. */ - if (!owner->on_cpu || need_resched() || - vcpu_is_preempted(task_cpu(owner))) { + if (need_resched() || !owner_on_cpu(owner)) { rcu_read_unlock(); return false; } @@ -408,12 +408,12 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem) cpu_relax(); } rcu_read_unlock(); -out: + /* * If there is a new owner or the owner is not set, we continue * spinning. */ - return !rwsem_owner_is_reader(READ_ONCE(sem->owner)); + return is_rwsem_owner_spinnable(READ_ONCE(sem->owner)); } static bool rwsem_optimistic_spin(struct rw_semaphore *sem) diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 30465a2f2b6c..bc1e507be9ff 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -221,5 +221,3 @@ void up_read_non_owner(struct rw_semaphore *sem) EXPORT_SYMBOL(up_read_non_owner); #endif - - diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h index a17cba8d94bb..b9d0e72aa80f 100644 --- a/kernel/locking/rwsem.h +++ b/kernel/locking/rwsem.h @@ -1,20 +1,24 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * The owner field of the rw_semaphore structure will be set to - * RWSEM_READ_OWNED when a reader grabs the lock. A writer will clear + * RWSEM_READER_OWNED when a reader grabs the lock. A writer will clear * the owner field when it unlocks. A reader, on the other hand, will * not touch the owner field when it unlocks. * - * In essence, the owner field now has the following 3 states: + * In essence, the owner field now has the following 4 states: * 1) 0 * - lock is free or the owner hasn't set the field yet * 2) RWSEM_READER_OWNED * - lock is currently or previously owned by readers (lock is free * or not set by owner yet) - * 3) Other non-zero value - * - a writer owns the lock + * 3) RWSEM_ANONYMOUSLY_OWNED bit set with some other bits set as well + * - lock is owned by an anonymous writer, so spinning on the lock + * owner should be disabled. + * 4) Other non-zero value + * - a writer owns the lock and other writers can spin on the lock owner. */ -#define RWSEM_READER_OWNED ((struct task_struct *)1UL) +#define RWSEM_ANONYMOUSLY_OWNED (1UL << 0) +#define RWSEM_READER_OWNED ((struct task_struct *)RWSEM_ANONYMOUSLY_OWNED) #ifdef CONFIG_DEBUG_RWSEMS # define DEBUG_RWSEMS_WARN_ON(c) DEBUG_LOCKS_WARN_ON(c) @@ -51,14 +55,22 @@ static inline void rwsem_set_reader_owned(struct rw_semaphore *sem) WRITE_ONCE(sem->owner, RWSEM_READER_OWNED); } -static inline bool rwsem_owner_is_writer(struct task_struct *owner) +/* + * Return true if the a rwsem waiter can spin on the rwsem's owner + * and steal the lock, i.e. the lock is not anonymously owned. + * N.B. !owner is considered spinnable. + */ +static inline bool is_rwsem_owner_spinnable(struct task_struct *owner) { - return owner && owner != RWSEM_READER_OWNED; + return !((unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED); } -static inline bool rwsem_owner_is_reader(struct task_struct *owner) +/* + * Return true if rwsem is owned by an anonymous writer or readers. + */ +static inline bool rwsem_has_anonymous_owner(struct task_struct *owner) { - return owner == RWSEM_READER_OWNED; + return (unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED; } #else static inline void rwsem_set_owner(struct rw_semaphore *sem) diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 11b4282c2d20..1efcb5b0c3ed 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -269,7 +269,7 @@ static int hib_submit_io(int op, int op_flags, pgoff_t page_off, void *addr, struct bio *bio; int error = 0; - bio = bio_alloc(__GFP_RECLAIM | __GFP_HIGH, 1); + bio = bio_alloc(GFP_NOIO | __GFP_HIGH, 1); bio->bi_iter.bi_sector = page_off * (PAGE_SIZE >> 9); bio_set_dev(bio, hib_resume_bdev); bio_set_op_attrs(bio, op, op_flags); @@ -376,7 +376,7 @@ static int write_page(void *buf, sector_t offset, struct hib_bio_batch *hb) return -ENOSPC; if (hb) { - src = (void *)__get_free_page(__GFP_RECLAIM | __GFP_NOWARN | + src = (void *)__get_free_page(GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY); if (src) { copy_page(src, buf); @@ -384,7 +384,7 @@ static int write_page(void *buf, sector_t offset, struct hib_bio_batch *hb) ret = hib_wait_io(hb); /* Free pages */ if (ret) return ret; - src = (void *)__get_free_page(__GFP_RECLAIM | + src = (void *)__get_free_page(GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY); if (src) { @@ -691,7 +691,7 @@ static int save_image_lzo(struct swap_map_handle *handle, nr_threads = num_online_cpus() - 1; nr_threads = clamp_val(nr_threads, 1, LZO_THREADS); - page = (void *)__get_free_page(__GFP_RECLAIM | __GFP_HIGH); + page = (void *)__get_free_page(GFP_NOIO | __GFP_HIGH); if (!page) { pr_err("Failed to allocate LZO page\n"); ret = -ENOMEM; @@ -989,7 +989,7 @@ static int get_swap_reader(struct swap_map_handle *handle, last = tmp; tmp->map = (struct swap_map_page *) - __get_free_page(__GFP_RECLAIM | __GFP_HIGH); + __get_free_page(GFP_NOIO | __GFP_HIGH); if (!tmp->map) { release_swap_reader(handle); return -ENOMEM; @@ -1261,8 +1261,8 @@ static int load_image_lzo(struct swap_map_handle *handle, for (i = 0; i < read_pages; i++) { page[i] = (void *)__get_free_page(i < LZO_CMP_PAGES ? - __GFP_RECLAIM | __GFP_HIGH : - __GFP_RECLAIM | __GFP_NOWARN | + GFP_NOIO | __GFP_HIGH : + GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY); if (!page[i]) { diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 7a693e31184a..40cea6735c2d 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -270,6 +270,12 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt) } } +/* Returns first leaf rcu_node of the specified RCU flavor. */ +#define rcu_first_leaf_node(rsp) ((rsp)->level[rcu_num_lvls - 1]) + +/* Is this rcu_node a leaf? */ +#define rcu_is_leaf_node(rnp) ((rnp)->level == rcu_num_lvls - 1) + /* * Do a full breadth-first scan of the rcu_node structures for the * specified rcu_state structure. @@ -284,8 +290,7 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt) * rcu_node tree with but one rcu_node structure, this loop is a no-op. */ #define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \ - for ((rnp) = &(rsp)->node[0]; \ - (rnp) < (rsp)->level[rcu_num_lvls - 1]; (rnp)++) + for ((rnp) = &(rsp)->node[0]; !rcu_is_leaf_node(rsp, rnp); (rnp)++) /* * Scan the leaves of the rcu_node hierarchy for the specified rcu_state @@ -294,7 +299,7 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt) * It is still a leaf node, even if it is also the root node. */ #define rcu_for_each_leaf_node(rsp, rnp) \ - for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \ + for ((rnp) = rcu_first_leaf_node(rsp); \ (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++) /* @@ -486,6 +491,7 @@ void rcu_force_quiescent_state(void); void rcu_bh_force_quiescent_state(void); void rcu_sched_force_quiescent_state(void); extern struct workqueue_struct *rcu_gp_wq; +extern struct workqueue_struct *rcu_par_gp_wq; #endif /* #else #ifdef CONFIG_TINY_RCU */ #ifdef CONFIG_RCU_NOCB_CPU diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c index 88cba7c2956c..5aff271adf1e 100644 --- a/kernel/rcu/rcu_segcblist.c +++ b/kernel/rcu/rcu_segcblist.c @@ -404,24 +404,6 @@ bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq) } /* - * Scan the specified rcu_segcblist structure for callbacks that need - * a grace period later than the one specified by "seq". We don't look - * at the RCU_DONE_TAIL or RCU_NEXT_TAIL segments because they don't - * have a grace-period sequence number. - */ -bool rcu_segcblist_future_gp_needed(struct rcu_segcblist *rsclp, - unsigned long seq) -{ - int i; - - for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) - if (rsclp->tails[i - 1] != rsclp->tails[i] && - ULONG_CMP_LT(seq, rsclp->gp_seq[i])) - return true; - return false; -} - -/* * Merge the source rcu_segcblist structure into the destination * rcu_segcblist structure, then initialize the source. Any pending * callbacks from the source get to start over. It is best to diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h index 581c12b63544..948470cef385 100644 --- a/kernel/rcu/rcu_segcblist.h +++ b/kernel/rcu/rcu_segcblist.h @@ -134,7 +134,5 @@ void rcu_segcblist_insert_pend_cbs(struct rcu_segcblist *rsclp, struct rcu_cblist *rclp); void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq); bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq); -bool rcu_segcblist_future_gp_needed(struct rcu_segcblist *rsclp, - unsigned long seq); void rcu_segcblist_merge(struct rcu_segcblist *dst_rsclp, struct rcu_segcblist *src_rsclp); diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c index 777e7a6a0292..e232846516b3 100644 --- a/kernel/rcu/rcuperf.c +++ b/kernel/rcu/rcuperf.c @@ -369,7 +369,7 @@ static bool __maybe_unused torturing_tasks(void) */ static void rcu_perf_wait_shutdown(void) { - cond_resched_rcu_qs(); + cond_resched_tasks_rcu_qs(); if (atomic_read(&n_rcu_perf_writer_finished) < nrealwriters) return; while (!torture_must_stop()) diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 680c96d8c00f..e628fcfd1bde 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -593,7 +593,12 @@ static void srcu_torture_init(void) static void srcu_torture_cleanup(void) { - cleanup_srcu_struct(&srcu_ctld); + static DEFINE_TORTURE_RANDOM(rand); + + if (torture_random(&rand) & 0x800) + cleanup_srcu_struct(&srcu_ctld); + else + cleanup_srcu_struct_quiesced(&srcu_ctld); srcu_ctlp = &srcu_ctl; /* In case of a later rcutorture run. */ } @@ -1609,6 +1614,9 @@ static enum cpuhp_state rcutor_hp; static void rcu_torture_cleanup(void) { + int flags = 0; + unsigned long gpnum = 0; + unsigned long completed = 0; int i; rcutorture_record_test_transition(); @@ -1639,6 +1647,11 @@ rcu_torture_cleanup(void) fakewriter_tasks = NULL; } + rcutorture_get_gp_data(cur_ops->ttype, &flags, &gpnum, &completed); + srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, + &flags, &gpnum, &completed); + pr_alert("%s: End-test grace-period state: g%lu c%lu f%#x\n", + cur_ops->name, gpnum, completed, flags); torture_stop_kthread(rcu_torture_stats, stats_task); torture_stop_kthread(rcu_torture_fqs, fqs_task); for (i = 0; i < ncbflooders; i++) diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c index 76ac5f50b2c7..622792abe41a 100644 --- a/kernel/rcu/srcutiny.c +++ b/kernel/rcu/srcutiny.c @@ -86,16 +86,19 @@ EXPORT_SYMBOL_GPL(init_srcu_struct); * Must invoke this after you are finished using a given srcu_struct that * was initialized via init_srcu_struct(), else you leak memory. */ -void cleanup_srcu_struct(struct srcu_struct *sp) +void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced) { WARN_ON(sp->srcu_lock_nesting[0] || sp->srcu_lock_nesting[1]); - flush_work(&sp->srcu_work); + if (quiesced) + WARN_ON(work_pending(&sp->srcu_work)); + else + flush_work(&sp->srcu_work); WARN_ON(sp->srcu_gp_running); WARN_ON(sp->srcu_gp_waiting); WARN_ON(sp->srcu_cb_head); WARN_ON(&sp->srcu_cb_head != sp->srcu_cb_tail); } -EXPORT_SYMBOL_GPL(cleanup_srcu_struct); +EXPORT_SYMBOL_GPL(_cleanup_srcu_struct); /* * Removes the count for the old reader from the appropriate element of diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index fb560fca9ef4..b4123d7a2cec 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -366,24 +366,28 @@ static unsigned long srcu_get_delay(struct srcu_struct *sp) return SRCU_INTERVAL; } -/** - * cleanup_srcu_struct - deconstruct a sleep-RCU structure - * @sp: structure to clean up. - * - * Must invoke this after you are finished using a given srcu_struct that - * was initialized via init_srcu_struct(), else you leak memory. - */ -void cleanup_srcu_struct(struct srcu_struct *sp) +/* Helper for cleanup_srcu_struct() and cleanup_srcu_struct_quiesced(). */ +void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced) { int cpu; if (WARN_ON(!srcu_get_delay(sp))) - return; /* Leakage unless caller handles error. */ + return; /* Just leak it! */ if (WARN_ON(srcu_readers_active(sp))) - return; /* Leakage unless caller handles error. */ - flush_delayed_work(&sp->work); + return; /* Just leak it! */ + if (quiesced) { + if (WARN_ON(delayed_work_pending(&sp->work))) + return; /* Just leak it! */ + } else { + flush_delayed_work(&sp->work); + } for_each_possible_cpu(cpu) - flush_delayed_work(&per_cpu_ptr(sp->sda, cpu)->work); + if (quiesced) { + if (WARN_ON(delayed_work_pending(&per_cpu_ptr(sp->sda, cpu)->work))) + return; /* Just leak it! */ + } else { + flush_delayed_work(&per_cpu_ptr(sp->sda, cpu)->work); + } if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) || WARN_ON(srcu_readers_active(sp))) { pr_info("%s: Active srcu_struct %p state: %d\n", __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq))); @@ -392,7 +396,7 @@ void cleanup_srcu_struct(struct srcu_struct *sp) free_percpu(sp->sda); sp->sda = NULL; } -EXPORT_SYMBOL_GPL(cleanup_srcu_struct); +EXPORT_SYMBOL_GPL(_cleanup_srcu_struct); /* * Counts the new reader in the appropriate per-CPU element of the diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 2a734692a581..aa7cade1b9f3 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -524,8 +524,6 @@ module_param(rcu_kick_kthreads, bool, 0644); static ulong jiffies_till_sched_qs = HZ / 10; module_param(jiffies_till_sched_qs, ulong, 0444); -static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, - struct rcu_data *rdp); static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)); static void force_quiescent_state(struct rcu_state *rsp); static int rcu_pending(void); @@ -711,44 +709,6 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp) } /* - * Is there any need for future grace periods? - * Interrupts must be disabled. If the caller does not hold the root - * rnp_node structure's ->lock, the results are advisory only. - */ -static int rcu_future_needs_gp(struct rcu_state *rsp) -{ - struct rcu_node *rnp = rcu_get_root(rsp); - int idx = (READ_ONCE(rnp->completed) + 1) & 0x1; - int *fp = &rnp->need_future_gp[idx]; - - lockdep_assert_irqs_disabled(); - return READ_ONCE(*fp); -} - -/* - * Does the current CPU require a not-yet-started grace period? - * The caller must have disabled interrupts to prevent races with - * normal callback registry. - */ -static bool -cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp) -{ - lockdep_assert_irqs_disabled(); - if (rcu_gp_in_progress(rsp)) - return false; /* No, a grace period is already in progress. */ - if (rcu_future_needs_gp(rsp)) - return true; /* Yes, a no-CBs CPU needs one. */ - if (!rcu_segcblist_is_enabled(&rdp->cblist)) - return false; /* No, this is a no-CBs (or offline) CPU. */ - if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) - return true; /* Yes, CPU has newly registered callbacks. */ - if (rcu_segcblist_future_gp_needed(&rdp->cblist, - READ_ONCE(rsp->completed))) - return true; /* Yes, CBs for future grace period. */ - return false; /* No grace period needed. */ -} - -/* * Enter an RCU extended quiescent state, which can be either the * idle loop or adaptive-tickless usermode execution. * @@ -1234,10 +1194,10 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) } /* - * Has this CPU encountered a cond_resched_rcu_qs() since the - * beginning of the grace period? For this to be the case, - * the CPU has to have noticed the current grace period. This - * might not be the case for nohz_full CPUs looping in the kernel. + * Has this CPU encountered a cond_resched() since the beginning + * of the grace period? For this to be the case, the CPU has to + * have noticed the current grace period. This might not be the + * case for nohz_full CPUs looping in the kernel. */ jtsq = jiffies_till_sched_qs; ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu); @@ -1642,18 +1602,30 @@ static unsigned long rcu_cbs_completed(struct rcu_state *rsp, return rnp->completed + 1; /* + * If the current rcu_node structure believes that RCU is + * idle, and if the rcu_state structure does not yet reflect + * the start of a new grace period, then the next grace period + * will suffice. The memory barrier is needed to accurately + * sample the rsp->gpnum, and pairs with the second lock + * acquisition in rcu_gp_init(), which is augmented with + * smp_mb__after_unlock_lock() for this purpose. + */ + if (rnp->gpnum == rnp->completed) { + smp_mb(); /* See above block comment. */ + if (READ_ONCE(rsp->gpnum) == rnp->completed) + return rnp->completed + 1; + } + + /* * Otherwise, wait for a possible partial grace period and * then the subsequent full grace period. */ return rnp->completed + 2; } -/* - * Trace-event helper function for rcu_start_future_gp() and - * rcu_nocb_wait_gp(). - */ -static void trace_rcu_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, - unsigned long c, const char *s) +/* Trace-event wrapper function for trace_rcu_future_grace_period. */ +static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, + unsigned long c, const char *s) { trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum, rnp->completed, c, rnp->level, @@ -1661,96 +1633,67 @@ static void trace_rcu_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, } /* - * Start some future grace period, as needed to handle newly arrived + * Start the specified grace period, as needed to handle newly arrived * callbacks. The required future grace periods are recorded in each - * rcu_node structure's ->need_future_gp field. Returns true if there + * rcu_node structure's ->need_future_gp[] field. Returns true if there * is reason to awaken the grace-period kthread. * - * The caller must hold the specified rcu_node structure's ->lock. + * The caller must hold the specified rcu_node structure's ->lock, which + * is why the caller is responsible for waking the grace-period kthread. */ -static bool __maybe_unused -rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, - unsigned long *c_out) +static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, + unsigned long c) { - unsigned long c; bool ret = false; - struct rcu_node *rnp_root = rcu_get_root(rdp->rsp); - - raw_lockdep_assert_held_rcu_node(rnp); - - /* - * Pick up grace-period number for new callbacks. If this - * grace period is already marked as needed, return to the caller. - */ - c = rcu_cbs_completed(rdp->rsp, rnp); - trace_rcu_future_gp(rnp, rdp, c, TPS("Startleaf")); - if (rnp->need_future_gp[c & 0x1]) { - trace_rcu_future_gp(rnp, rdp, c, TPS("Prestartleaf")); - goto out; - } + struct rcu_state *rsp = rdp->rsp; + struct rcu_node *rnp_root; /* - * If either this rcu_node structure or the root rcu_node structure - * believe that a grace period is in progress, then we must wait - * for the one following, which is in "c". Because our request - * will be noticed at the end of the current grace period, we don't - * need to explicitly start one. We only do the lockless check - * of rnp_root's fields if the current rcu_node structure thinks - * there is no grace period in flight, and because we hold rnp->lock, - * the only possible change is when rnp_root's two fields are - * equal, in which case rnp_root->gpnum might be concurrently - * incremented. But that is OK, as it will just result in our - * doing some extra useless work. + * Use funnel locking to either acquire the root rcu_node + * structure's lock or bail out if the need for this grace period + * has already been recorded -- or has already started. If there + * is already a grace period in progress in a non-leaf node, no + * recording is needed because the end of the grace period will + * scan the leaf rcu_node structures. Note that rnp->lock must + * not be released. */ - if (rnp->gpnum != rnp->completed || - READ_ONCE(rnp_root->gpnum) != READ_ONCE(rnp_root->completed)) { - rnp->need_future_gp[c & 0x1]++; - trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleaf")); - goto out; + raw_lockdep_assert_held_rcu_node(rnp); + trace_rcu_this_gp(rnp, rdp, c, TPS("Startleaf")); + for (rnp_root = rnp; 1; rnp_root = rnp_root->parent) { + if (rnp_root != rnp) + raw_spin_lock_rcu_node(rnp_root); + WARN_ON_ONCE(ULONG_CMP_LT(rnp_root->gpnum + + need_future_gp_mask(), c)); + if (need_future_gp_element(rnp_root, c) || + ULONG_CMP_GE(rnp_root->gpnum, c) || + (rnp != rnp_root && + rnp_root->gpnum != rnp_root->completed)) { + trace_rcu_this_gp(rnp_root, rdp, c, TPS("Prestarted")); + goto unlock_out; + } + need_future_gp_element(rnp_root, c) = true; + if (rnp_root != rnp && rnp_root->parent != NULL) + raw_spin_unlock_rcu_node(rnp_root); + if (!rnp_root->parent) + break; /* At root, and perhaps also leaf. */ } - /* - * There might be no grace period in progress. If we don't already - * hold it, acquire the root rcu_node structure's lock in order to - * start one (if needed). - */ - if (rnp != rnp_root) - raw_spin_lock_rcu_node(rnp_root); - - /* - * Get a new grace-period number. If there really is no grace - * period in progress, it will be smaller than the one we obtained - * earlier. Adjust callbacks as needed. - */ - c = rcu_cbs_completed(rdp->rsp, rnp_root); - if (!rcu_is_nocb_cpu(rdp->cpu)) - (void)rcu_segcblist_accelerate(&rdp->cblist, c); - - /* - * If the needed for the required grace period is already - * recorded, trace and leave. - */ - if (rnp_root->need_future_gp[c & 0x1]) { - trace_rcu_future_gp(rnp, rdp, c, TPS("Prestartedroot")); + /* If GP already in progress, just leave, otherwise start one. */ + if (rnp_root->gpnum != rnp_root->completed) { + trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedleafroot")); goto unlock_out; } - - /* Record the need for the future grace period. */ - rnp_root->need_future_gp[c & 0x1]++; - - /* If a grace period is not already in progress, start one. */ - if (rnp_root->gpnum != rnp_root->completed) { - trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleafroot")); - } else { - trace_rcu_future_gp(rnp, rdp, c, TPS("Startedroot")); - ret = rcu_start_gp_advanced(rdp->rsp, rnp_root, rdp); + trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedroot")); + WRITE_ONCE(rsp->gp_flags, rsp->gp_flags | RCU_GP_FLAG_INIT); + if (!rsp->gp_kthread) { + trace_rcu_this_gp(rnp_root, rdp, c, TPS("NoGPkthread")); + goto unlock_out; } + trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("newreq")); + ret = true; /* Caller must wake GP kthread. */ unlock_out: if (rnp != rnp_root) raw_spin_unlock_rcu_node(rnp_root); -out: - if (c_out != NULL) - *c_out = c; return ret; } @@ -1758,16 +1701,16 @@ out: * Clean up any old requests for the just-ended grace period. Also return * whether any additional grace periods have been requested. */ -static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) +static bool rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) { - int c = rnp->completed; - int needmore; + unsigned long c = rnp->completed; + bool needmore; struct rcu_data *rdp = this_cpu_ptr(rsp->rda); - rnp->need_future_gp[c & 0x1] = 0; - needmore = rnp->need_future_gp[(c + 1) & 0x1]; - trace_rcu_future_gp(rnp, rdp, c, - needmore ? TPS("CleanupMore") : TPS("Cleanup")); + need_future_gp_element(rnp, c) = false; + needmore = need_any_future_gp(rnp); + trace_rcu_this_gp(rnp, rdp, c, + needmore ? TPS("CleanupMore") : TPS("Cleanup")); return needmore; } @@ -1802,6 +1745,7 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp) static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { + unsigned long c; bool ret = false; raw_lockdep_assert_held_rcu_node(rnp); @@ -1820,8 +1764,9 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, * accelerating callback invocation to an earlier grace-period * number. */ - if (rcu_segcblist_accelerate(&rdp->cblist, rcu_cbs_completed(rsp, rnp))) - ret = rcu_start_future_gp(rnp, rdp, NULL); + c = rcu_cbs_completed(rsp, rnp); + if (rcu_segcblist_accelerate(&rdp->cblist, c)) + ret = rcu_start_this_gp(rnp, rdp, c); /* Trace depending on how much we were able to accelerate. */ if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL)) @@ -2049,7 +1994,7 @@ static bool rcu_gp_init(struct rcu_state *rsp) rnp->level, rnp->grplo, rnp->grphi, rnp->qsmask); raw_spin_unlock_irq_rcu_node(rnp); - cond_resched_rcu_qs(); + cond_resched_tasks_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); } @@ -2108,7 +2053,6 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) { unsigned long gp_duration; bool needgp = false; - int nocb = 0; struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); struct swait_queue_head *sq; @@ -2147,31 +2091,35 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) if (rnp == rdp->mynode) needgp = __note_gp_changes(rsp, rnp, rdp) || needgp; /* smp_mb() provided by prior unlock-lock pair. */ - nocb += rcu_future_gp_cleanup(rsp, rnp); + needgp = rcu_future_gp_cleanup(rsp, rnp) || needgp; sq = rcu_nocb_gp_get(rnp); raw_spin_unlock_irq_rcu_node(rnp); rcu_nocb_gp_cleanup(sq); - cond_resched_rcu_qs(); + cond_resched_tasks_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); rcu_gp_slow(rsp, gp_cleanup_delay); } rnp = rcu_get_root(rsp); raw_spin_lock_irq_rcu_node(rnp); /* Order GP before ->completed update. */ - rcu_nocb_gp_set(rnp, nocb); /* Declare grace period done. */ WRITE_ONCE(rsp->completed, rsp->gpnum); trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end")); rsp->gp_state = RCU_GP_IDLE; + /* Check for GP requests since above loop. */ rdp = this_cpu_ptr(rsp->rda); + if (need_any_future_gp(rnp)) { + trace_rcu_this_gp(rnp, rdp, rsp->completed - 1, + TPS("CleanupMore")); + needgp = true; + } /* Advance CBs to reduce false positives below. */ - needgp = rcu_advance_cbs(rsp, rnp, rdp) || needgp; - if (needgp || cpu_needs_another_gp(rsp, rdp)) { + if (!rcu_accelerate_cbs(rsp, rnp, rdp) && needgp) { WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT); - trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("newreq")); } + WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT); raw_spin_unlock_irq_rcu_node(rnp); } @@ -2202,7 +2150,7 @@ static int __noreturn rcu_gp_kthread(void *arg) /* Locking provides needed memory barrier. */ if (rcu_gp_init(rsp)) break; - cond_resched_rcu_qs(); + cond_resched_tasks_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, @@ -2247,7 +2195,7 @@ static int __noreturn rcu_gp_kthread(void *arg) trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("fqsend")); - cond_resched_rcu_qs(); + cond_resched_tasks_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); ret = 0; /* Force full wait till next FQS. */ j = jiffies_till_next_fqs; @@ -2260,7 +2208,7 @@ static int __noreturn rcu_gp_kthread(void *arg) } } else { /* Deal with stray signal. */ - cond_resched_rcu_qs(); + cond_resched_tasks_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, @@ -2283,71 +2231,6 @@ static int __noreturn rcu_gp_kthread(void *arg) } /* - * Start a new RCU grace period if warranted, re-initializing the hierarchy - * in preparation for detecting the next grace period. The caller must hold - * the root node's ->lock and hard irqs must be disabled. - * - * Note that it is legal for a dying CPU (which is marked as offline) to - * invoke this function. This can happen when the dying CPU reports its - * quiescent state. - * - * Returns true if the grace-period kthread must be awakened. - */ -static bool -rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, - struct rcu_data *rdp) -{ - raw_lockdep_assert_held_rcu_node(rnp); - if (!rsp->gp_kthread || !cpu_needs_another_gp(rsp, rdp)) { - /* - * Either we have not yet spawned the grace-period - * task, this CPU does not need another grace period, - * or a grace period is already in progress. - * Either way, don't start a new grace period. - */ - return false; - } - WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT); - trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), - TPS("newreq")); - - /* - * We can't do wakeups while holding the rnp->lock, as that - * could cause possible deadlocks with the rq->lock. Defer - * the wakeup to our caller. - */ - return true; -} - -/* - * Similar to rcu_start_gp_advanced(), but also advance the calling CPU's - * callbacks. Note that rcu_start_gp_advanced() cannot do this because it - * is invoked indirectly from rcu_advance_cbs(), which would result in - * endless recursion -- or would do so if it wasn't for the self-deadlock - * that is encountered beforehand. - * - * Returns true if the grace-period kthread needs to be awakened. - */ -static bool rcu_start_gp(struct rcu_state *rsp) -{ - struct rcu_data *rdp = this_cpu_ptr(rsp->rda); - struct rcu_node *rnp = rcu_get_root(rsp); - bool ret = false; - - /* - * If there is no grace period in progress right now, any - * callbacks we have up to this point will be satisfied by the - * next grace period. Also, advancing the callbacks reduces the - * probability of false positives from cpu_needs_another_gp() - * resulting in pointless grace periods. So, advance callbacks - * then start the grace period! - */ - ret = rcu_advance_cbs(rsp, rnp, rdp) || ret; - ret = rcu_start_gp_advanced(rsp, rnp, rdp) || ret; - return ret; -} - -/* * Report a full set of quiescent states to the specified rcu_state data * structure. Invoke rcu_gp_kthread_wake() to awaken the grace-period * kthread if another grace period is required. Whether we wake @@ -2398,7 +2281,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, return; } WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */ - WARN_ON_ONCE(rnp->level != rcu_num_lvls - 1 && + WARN_ON_ONCE(!rcu_is_leaf_node(rnp) && rcu_preempt_blocked_readers_cgp(rnp)); rnp->qsmask &= ~mask; trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum, @@ -2782,7 +2665,7 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)) struct rcu_node *rnp; rcu_for_each_leaf_node(rsp, rnp) { - cond_resched_rcu_qs(); + cond_resched_tasks_rcu_qs(); mask = 0; raw_spin_lock_irqsave_rcu_node(rnp, flags); if (rnp->qsmask == 0) { @@ -2874,22 +2757,27 @@ __rcu_process_callbacks(struct rcu_state *rsp) unsigned long flags; bool needwake; struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); + struct rcu_node *rnp; WARN_ON_ONCE(!rdp->beenonline); /* Update RCU state based on any recent quiescent states. */ rcu_check_quiescent_state(rsp, rdp); - /* Does this CPU require a not-yet-started grace period? */ - local_irq_save(flags); - if (cpu_needs_another_gp(rsp, rdp)) { - raw_spin_lock_rcu_node(rcu_get_root(rsp)); /* irqs disabled. */ - needwake = rcu_start_gp(rsp); - raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags); - if (needwake) - rcu_gp_kthread_wake(rsp); - } else { - local_irq_restore(flags); + /* No grace period and unregistered callbacks? */ + if (!rcu_gp_in_progress(rsp) && + rcu_segcblist_is_enabled(&rdp->cblist)) { + local_irq_save(flags); + if (rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) { + local_irq_restore(flags); + } else { + rnp = rdp->mynode; + raw_spin_lock_rcu_node(rnp); /* irqs disabled. */ + needwake = rcu_accelerate_cbs(rsp, rnp, rdp); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + if (needwake) + rcu_gp_kthread_wake(rsp); + } } /* If there are callbacks ready, invoke them. */ @@ -2973,11 +2861,11 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, /* Start a new grace period if one not already started. */ if (!rcu_gp_in_progress(rsp)) { - struct rcu_node *rnp_root = rcu_get_root(rsp); + struct rcu_node *rnp = rdp->mynode; - raw_spin_lock_rcu_node(rnp_root); - needwake = rcu_start_gp(rsp); - raw_spin_unlock_rcu_node(rnp_root); + raw_spin_lock_rcu_node(rnp); + needwake = rcu_accelerate_cbs(rsp, rnp, rdp); + raw_spin_unlock_rcu_node(rnp); if (needwake) rcu_gp_kthread_wake(rsp); } else { @@ -3368,7 +3256,9 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) return 1; /* Has RCU gone idle with this CPU needing another grace period? */ - if (cpu_needs_another_gp(rsp, rdp)) + if (!rcu_gp_in_progress(rsp) && + rcu_segcblist_is_enabled(&rdp->cblist) && + !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) return 1; /* Has another RCU grace period completed? */ @@ -3775,6 +3665,8 @@ int rcutree_dead_cpu(unsigned int cpu) return 0; } +static DEFINE_PER_CPU(int, rcu_cpu_started); + /* * Mark the specified CPU as being online so that subsequent grace periods * (both expedited and normal) will wait on it. Note that this means that @@ -3796,6 +3688,11 @@ void rcu_cpu_starting(unsigned int cpu) struct rcu_node *rnp; struct rcu_state *rsp; + if (per_cpu(rcu_cpu_started, cpu)) + return; + + per_cpu(rcu_cpu_started, cpu) = 1; + for_each_rcu_flavor(rsp) { rdp = per_cpu_ptr(rsp->rda, cpu); rnp = rdp->mynode; @@ -3852,6 +3749,8 @@ void rcu_report_dead(unsigned int cpu) preempt_enable(); for_each_rcu_flavor(rsp) rcu_cleanup_dying_idle_cpu(cpu, rsp); + + per_cpu(rcu_cpu_started, cpu) = 0; } /* Migrate the dead CPU's callbacks to the current CPU. */ @@ -3861,6 +3760,7 @@ static void rcu_migrate_callbacks(int cpu, struct rcu_state *rsp) struct rcu_data *my_rdp; struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp_root = rcu_get_root(rdp->rsp); + bool needwake; if (rcu_is_nocb_cpu(cpu) || rcu_segcblist_empty(&rdp->cblist)) return; /* No callbacks to migrate. */ @@ -3872,12 +3772,15 @@ static void rcu_migrate_callbacks(int cpu, struct rcu_state *rsp) return; } raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */ - rcu_advance_cbs(rsp, rnp_root, rdp); /* Leverage recent GPs. */ - rcu_advance_cbs(rsp, rnp_root, my_rdp); /* Assign GP to pending CBs. */ + /* Leverage recent GPs and set GP for new callbacks. */ + needwake = rcu_advance_cbs(rsp, rnp_root, rdp) || + rcu_advance_cbs(rsp, rnp_root, my_rdp); rcu_segcblist_merge(&my_rdp->cblist, &rdp->cblist); WARN_ON_ONCE(rcu_segcblist_empty(&my_rdp->cblist) != !rcu_segcblist_n_cbs(&my_rdp->cblist)); raw_spin_unlock_irqrestore_rcu_node(rnp_root, flags); + if (needwake) + rcu_gp_kthread_wake(rsp); WARN_ONCE(rcu_segcblist_n_cbs(&rdp->cblist) != 0 || !rcu_segcblist_empty(&rdp->cblist), "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, 1stCB=%p\n", @@ -4056,7 +3959,7 @@ static void __init rcu_init_one(struct rcu_state *rsp) init_swait_queue_head(&rsp->gp_wq); init_swait_queue_head(&rsp->expedited_wq); - rnp = rsp->level[rcu_num_lvls - 1]; + rnp = rcu_first_leaf_node(rsp); for_each_possible_cpu(i) { while (i > rnp->grphi) rnp++; @@ -4168,6 +4071,7 @@ static void __init rcu_dump_rcu_node_tree(struct rcu_state *rsp) } struct workqueue_struct *rcu_gp_wq; +struct workqueue_struct *rcu_par_gp_wq; void __init rcu_init(void) { @@ -4199,6 +4103,8 @@ void __init rcu_init(void) /* Create workqueue for expedited GPs and for Tree SRCU. */ rcu_gp_wq = alloc_workqueue("rcu_gp", WQ_MEM_RECLAIM, 0); WARN_ON(!rcu_gp_wq); + rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0); + WARN_ON(!rcu_par_gp_wq); } #include "tree_exp.h" diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index f491ab4f2e8e..78e051dffc5b 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -58,6 +58,14 @@ struct rcu_dynticks { #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ }; +/* Communicate arguments to a workqueue handler. */ +struct rcu_exp_work { + smp_call_func_t rew_func; + struct rcu_state *rew_rsp; + unsigned long rew_s; + struct work_struct rew_work; +}; + /* RCU's kthread states for tracing. */ #define RCU_KTHREAD_STOPPED 0 #define RCU_KTHREAD_RUNNING 1 @@ -150,15 +158,32 @@ struct rcu_node { struct swait_queue_head nocb_gp_wq[2]; /* Place for rcu_nocb_kthread() to wait GP. */ #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ - int need_future_gp[2]; - /* Counts of upcoming no-CB GP requests. */ + u8 need_future_gp[4]; /* Counts of upcoming GP requests. */ raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp; spinlock_t exp_lock ____cacheline_internodealigned_in_smp; unsigned long exp_seq_rq; wait_queue_head_t exp_wq[4]; + struct rcu_exp_work rew; + bool exp_need_flush; /* Need to flush workitem? */ } ____cacheline_internodealigned_in_smp; +/* Accessors for ->need_future_gp[] array. */ +#define need_future_gp_mask() \ + (ARRAY_SIZE(((struct rcu_node *)NULL)->need_future_gp) - 1) +#define need_future_gp_element(rnp, c) \ + ((rnp)->need_future_gp[(c) & need_future_gp_mask()]) +#define need_any_future_gp(rnp) \ +({ \ + int __i; \ + bool __nonzero = false; \ + \ + for (__i = 0; __i < ARRAY_SIZE((rnp)->need_future_gp); __i++) \ + __nonzero = __nonzero || \ + READ_ONCE((rnp)->need_future_gp[__i]); \ + __nonzero; \ +}) + /* * Bitmasks in an rcu_node cover the interval [grplo, grphi] of CPU IDs, and * are indexed relative to this interval rather than the global CPU ID space. @@ -224,10 +249,6 @@ struct rcu_data { #ifdef CONFIG_RCU_FAST_NO_HZ struct rcu_head oom_head; #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ - atomic_long_t exp_workdone0; /* # done by workqueue. */ - atomic_long_t exp_workdone1; /* # done by others #1. */ - atomic_long_t exp_workdone2; /* # done by others #2. */ - atomic_long_t exp_workdone3; /* # done by others #3. */ int exp_dynticks_snap; /* Double-check need for IPI. */ /* 6) Callback offloading. */ @@ -408,7 +429,6 @@ extern struct rcu_state rcu_preempt_state; #endif /* #ifdef CONFIG_PREEMPT_RCU */ int rcu_dynticks_snap(struct rcu_dynticks *rdtp); -bool rcu_eqs_special_set(int cpu); #ifdef CONFIG_RCU_BOOST DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status); @@ -438,7 +458,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); static void invoke_rcu_callbacks_kthread(void); static bool rcu_is_callbacks_kthread(void); #ifdef CONFIG_RCU_BOOST -static void rcu_preempt_do_callbacks(void); static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, struct rcu_node *rnp); #endif /* #ifdef CONFIG_RCU_BOOST */ @@ -454,7 +473,6 @@ static void print_cpu_stall_info_end(void); static void zero_cpu_stall_ticks(struct rcu_data *rdp); static void increment_cpu_stall_ticks(void); static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu); -static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq); static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp); static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq); static void rcu_init_one_nocb(struct rcu_node *rnp); diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index f72eefab8543..d40708e8c5d6 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -20,6 +20,8 @@ * Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> */ +#include <linux/lockdep.h> + /* * Record the start of an expedited grace period. */ @@ -154,15 +156,35 @@ static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp) * for the current expedited grace period. Works only for preemptible * RCU -- other RCU implementation use other means. * - * Caller must hold the rcu_state's exp_mutex. + * Caller must hold the specificed rcu_node structure's ->lock */ static bool sync_rcu_preempt_exp_done(struct rcu_node *rnp) { + raw_lockdep_assert_held_rcu_node(rnp); + return rnp->exp_tasks == NULL && READ_ONCE(rnp->expmask) == 0; } /* + * Like sync_rcu_preempt_exp_done(), but this function assumes the caller + * doesn't hold the rcu_node's ->lock, and will acquire and release the lock + * itself + */ +static bool sync_rcu_preempt_exp_done_unlocked(struct rcu_node *rnp) +{ + unsigned long flags; + bool ret; + + raw_spin_lock_irqsave_rcu_node(rnp, flags); + ret = sync_rcu_preempt_exp_done(rnp); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + + return ret; +} + + +/* * Report the exit from RCU read-side critical section for the last task * that queued itself during or before the current expedited preemptible-RCU * grace period. This event is reported either to the rcu_node structure on @@ -170,8 +192,7 @@ static bool sync_rcu_preempt_exp_done(struct rcu_node *rnp) * recursively up the tree. (Calm down, calm down, we do the recursion * iteratively!) * - * Caller must hold the rcu_state's exp_mutex and the specified rcu_node - * structure's ->lock. + * Caller must hold the specified rcu_node structure's ->lock. */ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, bool wake, unsigned long flags) @@ -207,8 +228,6 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, /* * Report expedited quiescent state for specified node. This is a * lock-acquisition wrapper function for __rcu_report_exp_rnp(). - * - * Caller must hold the rcu_state's exp_mutex. */ static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, bool wake) @@ -221,8 +240,7 @@ static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp, /* * Report expedited quiescent state for multiple CPUs, all covered by the - * specified leaf rcu_node structure. Caller must hold the rcu_state's - * exp_mutex. + * specified leaf rcu_node structure. */ static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp, unsigned long mask, bool wake) @@ -248,14 +266,12 @@ static void rcu_report_exp_rdp(struct rcu_state *rsp, struct rcu_data *rdp, } /* Common code for synchronize_{rcu,sched}_expedited() work-done checking. */ -static bool sync_exp_work_done(struct rcu_state *rsp, atomic_long_t *stat, - unsigned long s) +static bool sync_exp_work_done(struct rcu_state *rsp, unsigned long s) { if (rcu_exp_gp_seq_done(rsp, s)) { trace_rcu_exp_grace_period(rsp->name, s, TPS("done")); /* Ensure test happens before caller kfree(). */ smp_mb__before_atomic(); /* ^^^ */ - atomic_long_inc(stat); return true; } return false; @@ -289,7 +305,7 @@ static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s) * promoting locality and is not strictly needed for correctness. */ for (; rnp != NULL; rnp = rnp->parent) { - if (sync_exp_work_done(rsp, &rdp->exp_workdone1, s)) + if (sync_exp_work_done(rsp, s)) return true; /* Work not done, either wait here or go up. */ @@ -302,8 +318,7 @@ static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s) rnp->grplo, rnp->grphi, TPS("wait")); wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3], - sync_exp_work_done(rsp, - &rdp->exp_workdone2, s)); + sync_exp_work_done(rsp, s)); return true; } rnp->exp_seq_rq = s; /* Followers can wait on us. */ @@ -313,7 +328,7 @@ static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s) } mutex_lock(&rsp->exp_mutex); fastpath: - if (sync_exp_work_done(rsp, &rdp->exp_workdone3, s)) { + if (sync_exp_work_done(rsp, s)) { mutex_unlock(&rsp->exp_mutex); return true; } @@ -362,93 +377,129 @@ static void sync_sched_exp_online_cleanup(int cpu) } /* - * Select the nodes that the upcoming expedited grace period needs - * to wait for. + * Select the CPUs within the specified rcu_node that the upcoming + * expedited grace period needs to wait for. */ -static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, - smp_call_func_t func) +static void sync_rcu_exp_select_node_cpus(struct work_struct *wp) { int cpu; unsigned long flags; + smp_call_func_t func; unsigned long mask_ofl_test; unsigned long mask_ofl_ipi; int ret; - struct rcu_node *rnp; - - trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset")); - sync_exp_reset_tree(rsp); - trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("select")); - rcu_for_each_leaf_node(rsp, rnp) { - raw_spin_lock_irqsave_rcu_node(rnp, flags); + struct rcu_exp_work *rewp = + container_of(wp, struct rcu_exp_work, rew_work); + struct rcu_node *rnp = container_of(rewp, struct rcu_node, rew); + struct rcu_state *rsp = rewp->rew_rsp; - /* Each pass checks a CPU for identity, offline, and idle. */ - mask_ofl_test = 0; - for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) { - unsigned long mask = leaf_node_cpu_bit(rnp, cpu); - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); - struct rcu_dynticks *rdtp = per_cpu_ptr(&rcu_dynticks, cpu); - int snap; + func = rewp->rew_func; + raw_spin_lock_irqsave_rcu_node(rnp, flags); - if (raw_smp_processor_id() == cpu || - !(rnp->qsmaskinitnext & mask)) { + /* Each pass checks a CPU for identity, offline, and idle. */ + mask_ofl_test = 0; + for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) { + unsigned long mask = leaf_node_cpu_bit(rnp, cpu); + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_dynticks *rdtp = per_cpu_ptr(&rcu_dynticks, cpu); + int snap; + + if (raw_smp_processor_id() == cpu || + !(rnp->qsmaskinitnext & mask)) { + mask_ofl_test |= mask; + } else { + snap = rcu_dynticks_snap(rdtp); + if (rcu_dynticks_in_eqs(snap)) mask_ofl_test |= mask; - } else { - snap = rcu_dynticks_snap(rdtp); - if (rcu_dynticks_in_eqs(snap)) - mask_ofl_test |= mask; - else - rdp->exp_dynticks_snap = snap; - } + else + rdp->exp_dynticks_snap = snap; } - mask_ofl_ipi = rnp->expmask & ~mask_ofl_test; - - /* - * Need to wait for any blocked tasks as well. Note that - * additional blocking tasks will also block the expedited - * GP until such time as the ->expmask bits are cleared. - */ - if (rcu_preempt_has_tasks(rnp)) - rnp->exp_tasks = rnp->blkd_tasks.next; - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + } + mask_ofl_ipi = rnp->expmask & ~mask_ofl_test; - /* IPI the remaining CPUs for expedited quiescent state. */ - for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) { - unsigned long mask = leaf_node_cpu_bit(rnp, cpu); - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + /* + * Need to wait for any blocked tasks as well. Note that + * additional blocking tasks will also block the expedited GP + * until such time as the ->expmask bits are cleared. + */ + if (rcu_preempt_has_tasks(rnp)) + rnp->exp_tasks = rnp->blkd_tasks.next; + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - if (!(mask_ofl_ipi & mask)) - continue; + /* IPI the remaining CPUs for expedited quiescent state. */ + for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) { + unsigned long mask = leaf_node_cpu_bit(rnp, cpu); + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + + if (!(mask_ofl_ipi & mask)) + continue; retry_ipi: - if (rcu_dynticks_in_eqs_since(rdp->dynticks, - rdp->exp_dynticks_snap)) { - mask_ofl_test |= mask; - continue; - } - ret = smp_call_function_single(cpu, func, rsp, 0); - if (!ret) { - mask_ofl_ipi &= ~mask; - continue; - } - /* Failed, raced with CPU hotplug operation. */ - raw_spin_lock_irqsave_rcu_node(rnp, flags); - if ((rnp->qsmaskinitnext & mask) && - (rnp->expmask & mask)) { - /* Online, so delay for a bit and try again. */ - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("selectofl")); - schedule_timeout_uninterruptible(1); - goto retry_ipi; - } - /* CPU really is offline, so we can ignore it. */ - if (!(rnp->expmask & mask)) - mask_ofl_ipi &= ~mask; + if (rcu_dynticks_in_eqs_since(rdp->dynticks, + rdp->exp_dynticks_snap)) { + mask_ofl_test |= mask; + continue; + } + ret = smp_call_function_single(cpu, func, rsp, 0); + if (!ret) { + mask_ofl_ipi &= ~mask; + continue; + } + /* Failed, raced with CPU hotplug operation. */ + raw_spin_lock_irqsave_rcu_node(rnp, flags); + if ((rnp->qsmaskinitnext & mask) && + (rnp->expmask & mask)) { + /* Online, so delay for a bit and try again. */ raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("selectofl")); + schedule_timeout_uninterruptible(1); + goto retry_ipi; + } + /* CPU really is offline, so we can ignore it. */ + if (!(rnp->expmask & mask)) + mask_ofl_ipi &= ~mask; + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + } + /* Report quiescent states for those that went offline. */ + mask_ofl_test |= mask_ofl_ipi; + if (mask_ofl_test) + rcu_report_exp_cpu_mult(rsp, rnp, mask_ofl_test, false); +} + +/* + * Select the nodes that the upcoming expedited grace period needs + * to wait for. + */ +static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, + smp_call_func_t func) +{ + struct rcu_node *rnp; + + trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset")); + sync_exp_reset_tree(rsp); + trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("select")); + + /* Schedule work for each leaf rcu_node structure. */ + rcu_for_each_leaf_node(rsp, rnp) { + rnp->exp_need_flush = false; + if (!READ_ONCE(rnp->expmask)) + continue; /* Avoid early boot non-existent wq. */ + rnp->rew.rew_func = func; + rnp->rew.rew_rsp = rsp; + if (!READ_ONCE(rcu_par_gp_wq) || + rcu_scheduler_active != RCU_SCHEDULER_RUNNING) { + /* No workqueues yet. */ + sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work); + continue; } - /* Report quiescent states for those that went offline. */ - mask_ofl_test |= mask_ofl_ipi; - if (mask_ofl_test) - rcu_report_exp_cpu_mult(rsp, rnp, mask_ofl_test, false); + INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus); + queue_work_on(rnp->grplo, rcu_par_gp_wq, &rnp->rew.rew_work); + rnp->exp_need_flush = true; } + + /* Wait for workqueue jobs (if any) to complete. */ + rcu_for_each_leaf_node(rsp, rnp) + if (rnp->exp_need_flush) + flush_work(&rnp->rew.rew_work); } static void synchronize_sched_expedited_wait(struct rcu_state *rsp) @@ -469,9 +520,9 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) for (;;) { ret = swait_event_timeout( rsp->expedited_wq, - sync_rcu_preempt_exp_done(rnp_root), + sync_rcu_preempt_exp_done_unlocked(rnp_root), jiffies_stall); - if (ret > 0 || sync_rcu_preempt_exp_done(rnp_root)) + if (ret > 0 || sync_rcu_preempt_exp_done_unlocked(rnp_root)) return; WARN_ON(ret < 0); /* workqueues should not be signaled. */ if (rcu_cpu_stall_suppress) @@ -504,7 +555,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) rcu_for_each_node_breadth_first(rsp, rnp) { if (rnp == rnp_root) continue; /* printed unconditionally */ - if (sync_rcu_preempt_exp_done(rnp)) + if (sync_rcu_preempt_exp_done_unlocked(rnp)) continue; pr_cont(" l=%u:%d-%d:%#lx/%c", rnp->level, rnp->grplo, rnp->grphi, @@ -560,14 +611,6 @@ static void rcu_exp_wait_wake(struct rcu_state *rsp, unsigned long s) mutex_unlock(&rsp->exp_wake_mutex); } -/* Let the workqueue handler know what it is supposed to do. */ -struct rcu_exp_work { - smp_call_func_t rew_func; - struct rcu_state *rew_rsp; - unsigned long rew_s; - struct work_struct rew_work; -}; - /* * Common code to drive an expedited grace period forward, used by * workqueues and mid-boot-time tasks. @@ -633,7 +676,7 @@ static void _synchronize_rcu_expedited(struct rcu_state *rsp, rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id()); rnp = rcu_get_root(rsp); wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3], - sync_exp_work_done(rsp, &rdp->exp_workdone0, s)); + sync_exp_work_done(rsp, s)); smp_mb(); /* Workqueue actions happen before return. */ /* Let the next expedited grace period start. */ diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 84fbee4686d3..7fd12039e512 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -182,7 +182,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) raw_lockdep_assert_held_rcu_node(rnp); WARN_ON_ONCE(rdp->mynode != rnp); - WARN_ON_ONCE(rnp->level != rcu_num_lvls - 1); + WARN_ON_ONCE(!rcu_is_leaf_node(rnp)); /* * Decide where to queue the newly blocked task. In theory, @@ -384,6 +384,50 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) } /* + * Preemptible RCU implementation for rcu_read_lock(). + * Just increment ->rcu_read_lock_nesting, shared state will be updated + * if we block. + */ +void __rcu_read_lock(void) +{ + current->rcu_read_lock_nesting++; + barrier(); /* critical section after entry code. */ +} +EXPORT_SYMBOL_GPL(__rcu_read_lock); + +/* + * Preemptible RCU implementation for rcu_read_unlock(). + * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost + * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then + * invoke rcu_read_unlock_special() to clean up after a context switch + * in an RCU read-side critical section and other special cases. + */ +void __rcu_read_unlock(void) +{ + struct task_struct *t = current; + + if (t->rcu_read_lock_nesting != 1) { + --t->rcu_read_lock_nesting; + } else { + barrier(); /* critical section before exit code. */ + t->rcu_read_lock_nesting = INT_MIN; + barrier(); /* assign before ->rcu_read_unlock_special load */ + if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s))) + rcu_read_unlock_special(t); + barrier(); /* ->rcu_read_unlock_special load before assign */ + t->rcu_read_lock_nesting = 0; + } +#ifdef CONFIG_PROVE_LOCKING + { + int rrln = READ_ONCE(t->rcu_read_lock_nesting); + + WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); + } +#endif /* #ifdef CONFIG_PROVE_LOCKING */ +} +EXPORT_SYMBOL_GPL(__rcu_read_unlock); + +/* * Advance a ->blkd_tasks-list pointer to the next entry, instead * returning NULL if at the end of the list. */ @@ -489,7 +533,7 @@ void rcu_read_unlock_special(struct task_struct *t) rnp = t->rcu_blocked_node; raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ WARN_ON_ONCE(rnp != t->rcu_blocked_node); - WARN_ON_ONCE(rnp->level != rcu_num_lvls - 1); + WARN_ON_ONCE(!rcu_is_leaf_node(rnp)); empty_norm = !rcu_preempt_blocked_readers_cgp(rnp); empty_exp = sync_rcu_preempt_exp_done(rnp); smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */ @@ -685,15 +729,6 @@ static void rcu_preempt_check_callbacks(void) t->rcu_read_unlock_special.b.need_qs = true; } -#ifdef CONFIG_RCU_BOOST - -static void rcu_preempt_do_callbacks(void) -{ - rcu_do_batch(rcu_state_p, this_cpu_ptr(rcu_data_p)); -} - -#endif /* #ifdef CONFIG_RCU_BOOST */ - /** * call_rcu() - Queue an RCU callback for invocation after a grace period. * @head: structure to be used for queueing the RCU updates. @@ -1140,7 +1175,7 @@ static void rcu_kthread_do_work(void) { rcu_do_batch(&rcu_sched_state, this_cpu_ptr(&rcu_sched_data)); rcu_do_batch(&rcu_bh_state, this_cpu_ptr(&rcu_bh_data)); - rcu_preempt_do_callbacks(); + rcu_do_batch(&rcu_preempt_state, this_cpu_ptr(&rcu_preempt_data)); } static void rcu_cpu_kthread_setup(unsigned int cpu) @@ -1607,7 +1642,7 @@ static int rcu_oom_notify(struct notifier_block *self, for_each_online_cpu(cpu) { smp_call_function_single(cpu, rcu_oom_notify_cpu, NULL, 1); - cond_resched_rcu_qs(); + cond_resched_tasks_rcu_qs(); } /* Unconditionally decrement: no need to wake ourselves up. */ @@ -1780,19 +1815,6 @@ static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) swake_up_all(sq); } -/* - * Set the root rcu_node structure's ->need_future_gp field - * based on the sum of those of all rcu_node structures. This does - * double-count the root rcu_node structure's requests, but this - * is necessary to handle the possibility of a rcu_nocb_kthread() - * having awakened during the time that the rcu_node structures - * were being updated for the end of the previous grace period. - */ -static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq) -{ - rnp->need_future_gp[(rnp->completed + 1) & 0x1] += nrq; -} - static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp) { return &rnp->nocb_gp_wq[rnp->completed & 0x1]; @@ -1966,7 +1988,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeOvf")); } else { - wake_nocb_leader_defer(rdp, RCU_NOCB_WAKE, + wake_nocb_leader_defer(rdp, RCU_NOCB_WAKE_FORCE, TPS("WakeOvfIsDeferred")); } rdp->qlen_last_fqs_check = LONG_MAX / 2; @@ -2048,7 +2070,8 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) struct rcu_node *rnp = rdp->mynode; raw_spin_lock_irqsave_rcu_node(rnp, flags); - needwake = rcu_start_future_gp(rnp, rdp, &c); + c = rcu_cbs_completed(rdp->rsp, rnp); + needwake = rcu_start_this_gp(rnp, rdp, c); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); if (needwake) rcu_gp_kthread_wake(rdp->rsp); @@ -2057,7 +2080,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) * Wait for the grace period. Do so interruptibly to avoid messing * up the load average. */ - trace_rcu_future_gp(rnp, rdp, c, TPS("StartWait")); + trace_rcu_this_gp(rnp, rdp, c, TPS("StartWait")); for (;;) { swait_event_interruptible( rnp->nocb_gp_wq[c & 0x1], @@ -2065,9 +2088,9 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) if (likely(d)) break; WARN_ON(signal_pending(current)); - trace_rcu_future_gp(rnp, rdp, c, TPS("ResumeWait")); + trace_rcu_this_gp(rnp, rdp, c, TPS("ResumeWait")); } - trace_rcu_future_gp(rnp, rdp, c, TPS("EndWait")); + trace_rcu_this_gp(rnp, rdp, c, TPS("EndWait")); smp_mb(); /* Ensure that CB invocation happens after GP end. */ } @@ -2236,7 +2259,7 @@ static int rcu_nocb_kthread(void *arg) cl++; c++; local_bh_enable(); - cond_resched_rcu_qs(); + cond_resched_tasks_rcu_qs(); list = next; } trace_rcu_batch_end(rdp->rsp->name, c, !!list, 0, 0, 1); @@ -2292,7 +2315,7 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp) void __init rcu_init_nohz(void) { int cpu; - bool need_rcu_nocb_mask = true; + bool need_rcu_nocb_mask = false; struct rcu_state *rsp; #if defined(CONFIG_NO_HZ_FULL) @@ -2315,7 +2338,7 @@ void __init rcu_init_nohz(void) #endif /* #if defined(CONFIG_NO_HZ_FULL) */ if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) { - pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n"); + pr_info("\tNote: kernel parameter 'rcu_nocbs=', 'nohz_full', or 'isolcpus=' contains nonexistent CPUs.\n"); cpumask_and(rcu_nocb_mask, cpu_possible_mask, rcu_nocb_mask); } @@ -2495,10 +2518,6 @@ static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) { } -static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq) -{ -} - static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp) { return NULL; @@ -2587,8 +2606,7 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp) } /* - * Bind the grace-period kthread for the sysidle flavor of RCU to the - * timekeeping CPU. + * Bind the RCU grace-period kthreads to the housekeeping CPU. */ static void rcu_bind_gp_kthread(void) { diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 68fa19a5e7bd..4c230a60ece4 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -226,54 +226,6 @@ core_initcall(rcu_set_runtime_mode); #endif /* #if !defined(CONFIG_TINY_RCU) || defined(CONFIG_SRCU) */ -#ifdef CONFIG_PREEMPT_RCU - -/* - * Preemptible RCU implementation for rcu_read_lock(). - * Just increment ->rcu_read_lock_nesting, shared state will be updated - * if we block. - */ -void __rcu_read_lock(void) -{ - current->rcu_read_lock_nesting++; - barrier(); /* critical section after entry code. */ -} -EXPORT_SYMBOL_GPL(__rcu_read_lock); - -/* - * Preemptible RCU implementation for rcu_read_unlock(). - * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost - * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then - * invoke rcu_read_unlock_special() to clean up after a context switch - * in an RCU read-side critical section and other special cases. - */ -void __rcu_read_unlock(void) -{ - struct task_struct *t = current; - - if (t->rcu_read_lock_nesting != 1) { - --t->rcu_read_lock_nesting; - } else { - barrier(); /* critical section before exit code. */ - t->rcu_read_lock_nesting = INT_MIN; - barrier(); /* assign before ->rcu_read_unlock_special load */ - if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s))) - rcu_read_unlock_special(t); - barrier(); /* ->rcu_read_unlock_special load before assign */ - t->rcu_read_lock_nesting = 0; - } -#ifdef CONFIG_PROVE_LOCKING - { - int rrln = READ_ONCE(t->rcu_read_lock_nesting); - - WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); - } -#endif /* #ifdef CONFIG_PROVE_LOCKING */ -} -EXPORT_SYMBOL_GPL(__rcu_read_unlock); - -#endif /* #ifdef CONFIG_PREEMPT_RCU */ - #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key rcu_lock_key; struct lockdep_map rcu_lock_map = @@ -624,7 +576,7 @@ EXPORT_SYMBOL_GPL(call_rcu_tasks); * grace period has elapsed, in other words after all currently * executing rcu-tasks read-side critical sections have elapsed. These * read-side critical sections are delimited by calls to schedule(), - * cond_resched_rcu_qs(), idle execution, userspace execution, calls + * cond_resched_tasks_rcu_qs(), idle execution, userspace execution, calls * to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched(). * * This is a very specialized primitive, intended only for a few uses in diff --git a/kernel/resource.c b/kernel/resource.c index 2af6c03858b9..b589dda910b3 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -87,7 +87,7 @@ enum { MAX_IORES_LEVEL = 5 }; static void *r_start(struct seq_file *m, loff_t *pos) __acquires(resource_lock) { - struct resource *p = m->private; + struct resource *p = PDE_DATA(file_inode(m->file)); loff_t l = 0; read_lock(&resource_lock); for (p = p->child; p && l < *pos; p = r_next(m, p, &l)) @@ -103,7 +103,7 @@ static void r_stop(struct seq_file *m, void *v) static int r_show(struct seq_file *m, void *v) { - struct resource *root = m->private; + struct resource *root = PDE_DATA(file_inode(m->file)); struct resource *r = v, *p; unsigned long long start, end; int width = root->end < 0x10000 ? 4 : 8; @@ -135,44 +135,11 @@ static const struct seq_operations resource_op = { .show = r_show, }; -static int ioports_open(struct inode *inode, struct file *file) -{ - int res = seq_open(file, &resource_op); - if (!res) { - struct seq_file *m = file->private_data; - m->private = &ioport_resource; - } - return res; -} - -static int iomem_open(struct inode *inode, struct file *file) -{ - int res = seq_open(file, &resource_op); - if (!res) { - struct seq_file *m = file->private_data; - m->private = &iomem_resource; - } - return res; -} - -static const struct file_operations proc_ioports_operations = { - .open = ioports_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static const struct file_operations proc_iomem_operations = { - .open = iomem_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - static int __init ioresources_init(void) { - proc_create("ioports", 0, NULL, &proc_ioports_operations); - proc_create("iomem", 0, NULL, &proc_iomem_operations); + proc_create_seq_data("ioports", 0, NULL, &resource_op, + &ioport_resource); + proc_create_seq_data("iomem", 0, NULL, &resource_op, &iomem_resource); return 0; } __initcall(ioresources_init); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 092f7c4de903..e9866f86f304 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -881,6 +881,33 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) } #ifdef CONFIG_SMP + +static inline bool is_per_cpu_kthread(struct task_struct *p) +{ + if (!(p->flags & PF_KTHREAD)) + return false; + + if (p->nr_cpus_allowed != 1) + return false; + + return true; +} + +/* + * Per-CPU kthreads are allowed to run on !actie && online CPUs, see + * __set_cpus_allowed_ptr() and select_fallback_rq(). + */ +static inline bool is_cpu_allowed(struct task_struct *p, int cpu) +{ + if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) + return false; + + if (is_per_cpu_kthread(p)) + return cpu_online(cpu); + + return cpu_active(cpu); +} + /* * This is how migration works: * @@ -938,16 +965,8 @@ struct migration_arg { static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf, struct task_struct *p, int dest_cpu) { - if (p->flags & PF_KTHREAD) { - if (unlikely(!cpu_online(dest_cpu))) - return rq; - } else { - if (unlikely(!cpu_active(dest_cpu))) - return rq; - } - /* Affinity changed (again). */ - if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) + if (!is_cpu_allowed(p, dest_cpu)) return rq; update_rq_clock(rq); @@ -1476,10 +1495,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p) for (;;) { /* Any allowed, online CPU? */ for_each_cpu(dest_cpu, &p->cpus_allowed) { - if (!(p->flags & PF_KTHREAD) && !cpu_active(dest_cpu)) - continue; - if (!cpu_online(dest_cpu)) + if (!is_cpu_allowed(p, dest_cpu)) continue; + goto out; } @@ -1542,8 +1560,7 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) * [ this allows ->select_task() to simply return task_cpu(p) and * not worry about this generic constraint ] */ - if (unlikely(!cpumask_test_cpu(cpu, &p->cpus_allowed) || - !cpu_online(cpu))) + if (unlikely(!is_cpu_allowed(p, cpu))) cpu = select_fallback_rq(task_cpu(p), p); return cpu; @@ -2177,27 +2194,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) INIT_HLIST_HEAD(&p->preempt_notifiers); #endif -#ifdef CONFIG_NUMA_BALANCING - if (p->mm && atomic_read(&p->mm->mm_users) == 1) { - p->mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay); - p->mm->numa_scan_seq = 0; - } - - if (clone_flags & CLONE_VM) - p->numa_preferred_nid = current->numa_preferred_nid; - else - p->numa_preferred_nid = -1; - - p->node_stamp = 0ULL; - p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0; - p->numa_scan_period = sysctl_numa_balancing_scan_delay; - p->numa_work.next = &p->numa_work; - p->numa_faults = NULL; - p->last_task_numa_placement = 0; - p->last_sum_exec_runtime = 0; - - p->numa_group = NULL; -#endif /* CONFIG_NUMA_BALANCING */ + init_numa_balancing(clone_flags, p); } DEFINE_STATIC_KEY_FALSE(sched_numa_balancing); @@ -4033,6 +4030,23 @@ int idle_cpu(int cpu) } /** + * available_idle_cpu - is a given CPU idle for enqueuing work. + * @cpu: the CPU in question. + * + * Return: 1 if the CPU is currently idle. 0 otherwise. + */ +int available_idle_cpu(int cpu) +{ + if (!idle_cpu(cpu)) + return 0; + + if (vcpu_is_preempted(cpu)) + return 0; + + return 1; +} + +/** * idle_task - return the idle task for a given CPU. * @cpu: the processor in question. * @@ -5008,20 +5022,6 @@ int __cond_resched_lock(spinlock_t *lock) } EXPORT_SYMBOL(__cond_resched_lock); -int __sched __cond_resched_softirq(void) -{ - BUG_ON(!in_softirq()); - - if (should_resched(SOFTIRQ_DISABLE_OFFSET)) { - local_bh_enable(); - preempt_schedule_common(); - local_bh_disable(); - return 1; - } - return 0; -} -EXPORT_SYMBOL(__cond_resched_softirq); - /** * yield - yield the current processor to other threads. * diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index e13df951aca7..28592b62b1d5 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -183,22 +183,21 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu) static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu) { struct rq *rq = cpu_rq(sg_cpu->cpu); - unsigned long util; - if (rq->rt.rt_nr_running) { - util = sg_cpu->max; - } else { - util = sg_cpu->util_dl; - if (rq->cfs.h_nr_running) - util += sg_cpu->util_cfs; - } + if (rq->rt.rt_nr_running) + return sg_cpu->max; /* + * Utilization required by DEADLINE must always be granted while, for + * FAIR, we use blocked utilization of IDLE CPUs as a mechanism to + * gracefully reduce the frequency when no tasks show up for longer + * periods of time. + * * Ideally we would like to set util_dl as min/guaranteed freq and * util_cfs + util_dl as requested freq. However, cpufreq is not yet * ready for such an interface. So, we only do the latter for now. */ - return min(util, sg_cpu->max); + return min(sg_cpu->max, (sg_cpu->util_dl + sg_cpu->util_cfs)); } static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, u64 time, unsigned int flags) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index e7b3008b85bb..fbfc3f1d368a 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1117,7 +1117,7 @@ extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq); * should be larger than 2^(64 - 20 - 8), which is more than 64 seconds. * So, overflow is not an issue here. */ -u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se) +static u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se) { u64 u_inact = rq->dl.this_bw - rq->dl.running_bw; /* Utot - Uact */ u64 u_act; @@ -1259,6 +1259,9 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer) rq = task_rq_lock(p, &rf); + sched_clock_tick(); + update_rq_clock(rq); + if (!dl_task(p) || p->state == TASK_DEAD) { struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); @@ -1278,9 +1281,6 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer) if (dl_se->dl_non_contending == 0) goto unlock; - sched_clock_tick(); - update_rq_clock(rq); - sub_running_bw(dl_se, &rq->dl); dl_se->dl_non_contending = 0; unlock: @@ -2731,8 +2731,6 @@ bool dl_cpu_busy(unsigned int cpu) #endif #ifdef CONFIG_SCHED_DEBUG -extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq); - void print_dl_stats(struct seq_file *m, int cpu) { print_dl_rq(m, cpu, &cpu_rq(cpu)->dl); diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 15b10e210a6b..e593b4118578 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -823,35 +823,9 @@ static const struct seq_operations sched_debug_sops = { .show = sched_debug_show, }; -static int sched_debug_release(struct inode *inode, struct file *file) -{ - seq_release(inode, file); - - return 0; -} - -static int sched_debug_open(struct inode *inode, struct file *filp) -{ - int ret = 0; - - ret = seq_open(filp, &sched_debug_sops); - - return ret; -} - -static const struct file_operations sched_debug_fops = { - .open = sched_debug_open, - .read = seq_read, - .llseek = seq_lseek, - .release = sched_debug_release, -}; - static int __init init_sched_debug_procfs(void) { - struct proc_dir_entry *pe; - - pe = proc_create("sched_debug", 0444, NULL, &sched_debug_fops); - if (!pe) + if (!proc_create_seq("sched_debug", 0444, NULL, &sched_debug_sops)) return -ENOMEM; return 0; } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 79f574dba096..e497c05aab7f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1139,6 +1139,47 @@ static unsigned int task_scan_max(struct task_struct *p) return max(smin, smax); } +void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) +{ + int mm_users = 0; + struct mm_struct *mm = p->mm; + + if (mm) { + mm_users = atomic_read(&mm->mm_users); + if (mm_users == 1) { + mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay); + mm->numa_scan_seq = 0; + } + } + p->node_stamp = 0; + p->numa_scan_seq = mm ? mm->numa_scan_seq : 0; + p->numa_scan_period = sysctl_numa_balancing_scan_delay; + p->numa_work.next = &p->numa_work; + p->numa_faults = NULL; + p->numa_group = NULL; + p->last_task_numa_placement = 0; + p->last_sum_exec_runtime = 0; + + /* New address space, reset the preferred nid */ + if (!(clone_flags & CLONE_VM)) { + p->numa_preferred_nid = -1; + return; + } + + /* + * New thread, keep existing numa_preferred_nid which should be copied + * already by arch_dup_task_struct but stagger when scans start. + */ + if (mm) { + unsigned int delay; + + delay = min_t(unsigned int, task_scan_max(current), + current->numa_scan_period * mm_users * NSEC_PER_MSEC); + delay += 2 * TICK_NSEC; + p->node_stamp = delay; + } +} + static void account_numa_enqueue(struct rq *rq, struct task_struct *p) { rq->nr_numa_running += (p->numa_preferred_nid != -1); @@ -5345,6 +5386,14 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) struct sched_entity *se = &p->se; /* + * The code below (indirectly) updates schedutil which looks at + * the cfs_rq utilization to select a frequency. + * Let's add the task's estimated utilization to the cfs_rq's + * estimated utilization, before we update schedutil. + */ + util_est_enqueue(&rq->cfs, p); + + /* * If in_iowait is set, the code below may not trigger any cpufreq * utilization updates, so do it here explicitly with the IOWAIT flag * passed. @@ -5385,7 +5434,6 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (!se) add_nr_running(rq, 1); - util_est_enqueue(&rq->cfs, p); hrtick_update(rq); } @@ -5858,8 +5906,8 @@ wake_affine_idle(int this_cpu, int prev_cpu, int sync) * a cpufreq perspective, it's better to have higher utilisation * on one CPU. */ - if (idle_cpu(this_cpu) && cpus_share_cache(this_cpu, prev_cpu)) - return idle_cpu(prev_cpu) ? prev_cpu : this_cpu; + if (available_idle_cpu(this_cpu) && cpus_share_cache(this_cpu, prev_cpu)) + return available_idle_cpu(prev_cpu) ? prev_cpu : this_cpu; if (sync && cpu_rq(this_cpu)->nr_running == 1) return this_cpu; @@ -6102,7 +6150,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this /* Traverse only the allowed CPUs */ for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) { - if (idle_cpu(i)) { + if (available_idle_cpu(i)) { struct rq *rq = cpu_rq(i); struct cpuidle_state *idle = idle_get_state(rq); if (idle && idle->exit_latency < min_exit_latency) { @@ -6144,6 +6192,13 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p if (!cpumask_intersects(sched_domain_span(sd), &p->cpus_allowed)) return prev_cpu; + /* + * We need task's util for capacity_spare_wake, sync it up to prev_cpu's + * last_update_time. + */ + if (!(sd_flag & SD_BALANCE_FORK)) + sync_entity_load_avg(&p->se); + while (sd) { struct sched_group *group; struct sched_domain *tmp; @@ -6224,7 +6279,7 @@ void __update_idle_core(struct rq *rq) if (cpu == core) continue; - if (!idle_cpu(cpu)) + if (!available_idle_cpu(cpu)) goto unlock; } @@ -6256,7 +6311,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int for_each_cpu(cpu, cpu_smt_mask(core)) { cpumask_clear_cpu(cpu, cpus); - if (!idle_cpu(cpu)) + if (!available_idle_cpu(cpu)) idle = false; } @@ -6285,7 +6340,7 @@ static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int t for_each_cpu(cpu, cpu_smt_mask(target)) { if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) continue; - if (idle_cpu(cpu)) + if (available_idle_cpu(cpu)) return cpu; } @@ -6348,7 +6403,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t return -1; if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) continue; - if (idle_cpu(cpu)) + if (available_idle_cpu(cpu)) break; } @@ -6368,13 +6423,13 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) struct sched_domain *sd; int i, recent_used_cpu; - if (idle_cpu(target)) + if (available_idle_cpu(target)) return target; /* * If the previous CPU is cache affine and idle, don't be stupid: */ - if (prev != target && cpus_share_cache(prev, target) && idle_cpu(prev)) + if (prev != target && cpus_share_cache(prev, target) && available_idle_cpu(prev)) return prev; /* Check a recently used CPU as a potential idle candidate: */ @@ -6382,7 +6437,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) if (recent_used_cpu != prev && recent_used_cpu != target && cpus_share_cache(recent_used_cpu, target) && - idle_cpu(recent_used_cpu) && + available_idle_cpu(recent_used_cpu) && cpumask_test_cpu(p->recent_used_cpu, &p->cpus_allowed)) { /* * Replace recent_used_cpu with prev as it is a potential @@ -6558,7 +6613,7 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu) static int select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags) { - struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL; + struct sched_domain *tmp, *sd = NULL; int cpu = smp_processor_id(); int new_cpu = prev_cpu; int want_affine = 0; @@ -6581,7 +6636,10 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f */ if (want_affine && (tmp->flags & SD_WAKE_AFFINE) && cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) { - affine_sd = tmp; + if (cpu != prev_cpu) + new_cpu = wake_affine(tmp, p, cpu, prev_cpu, sync); + + sd = NULL; /* Prefer wake_affine over balance flags */ break; } @@ -6591,33 +6649,16 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f break; } - if (affine_sd) { - sd = NULL; /* Prefer wake_affine over balance flags */ - if (cpu == prev_cpu) - goto pick_cpu; - - new_cpu = wake_affine(affine_sd, p, cpu, prev_cpu, sync); - } - - if (sd && !(sd_flag & SD_BALANCE_FORK)) { - /* - * We're going to need the task's util for capacity_spare_wake - * in find_idlest_group. Sync it up to prev_cpu's - * last_update_time. - */ - sync_entity_load_avg(&p->se); - } + if (unlikely(sd)) { + /* Slow path */ + new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag); + } else if (sd_flag & SD_BALANCE_WAKE) { /* XXX always ? */ + /* Fast path */ - if (!sd) { -pick_cpu: - if (sd_flag & SD_BALANCE_WAKE) { /* XXX always ? */ - new_cpu = select_idle_sibling(p, prev_cpu, new_cpu); + new_cpu = select_idle_sibling(p, prev_cpu, new_cpu); - if (want_affine) - current->recent_used_cpu = cpu; - } - } else { - new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag); + if (want_affine) + current->recent_used_cpu = cpu; } rcu_read_unlock(); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 7aef6b4e885a..ef3c4e6f5345 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -2701,8 +2701,6 @@ int sched_rr_handler(struct ctl_table *table, int write, } #ifdef CONFIG_SCHED_DEBUG -extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq); - void print_rt_stats(struct seq_file *m, int cpu) { rt_rq_iter_t iter; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 15750c222ca2..6601baf2361c 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -983,7 +983,7 @@ static inline void rq_clock_skip_update(struct rq *rq) } /* - * See rt task throttoling, which is the only time a skip + * See rt task throttling, which is the only time a skip * request is cancelled. */ static inline void rq_clock_cancel_skipupdate(struct rq *rq) @@ -1069,6 +1069,12 @@ enum numa_faults_stats { extern void sched_setnuma(struct task_struct *p, int node); extern int migrate_task_to(struct task_struct *p, int cpu); extern int migrate_swap(struct task_struct *, struct task_struct *); +extern void init_numa_balancing(unsigned long clone_flags, struct task_struct *p); +#else +static inline void +init_numa_balancing(unsigned long clone_flags, struct task_struct *p) +{ +} #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_SMP @@ -2025,8 +2031,9 @@ extern bool sched_debug_enabled; extern void print_cfs_stats(struct seq_file *m, int cpu); extern void print_rt_stats(struct seq_file *m, int cpu); extern void print_dl_stats(struct seq_file *m, int cpu); -extern void -print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq); +extern void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq); +extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq); +extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq); #ifdef CONFIG_NUMA_BALANCING extern void show_numa_stats(struct task_struct *p, struct seq_file *m); diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c index ab112cbfd7c8..750fb3c67eed 100644 --- a/kernel/sched/stats.c +++ b/kernel/sched/stats.c @@ -120,22 +120,9 @@ static const struct seq_operations schedstat_sops = { .show = show_schedstat, }; -static int schedstat_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &schedstat_sops); -} - -static const struct file_operations proc_schedstat_operations = { - .open = schedstat_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - static int __init proc_schedstat_init(void) { - proc_create("schedstat", 0, NULL, &proc_schedstat_operations); - + proc_create_seq("schedstat", 0, NULL, &schedstat_sops); return 0; } subsys_initcall(proc_schedstat_init); diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 64cc564f5255..61a1125c1ae4 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1708,7 +1708,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att rcu_read_unlock(); if (rq && sched_debug_enabled) { - pr_info("span: %*pbl (max cpu_capacity = %lu)\n", + pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n", cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity); } diff --git a/kernel/seccomp.c b/kernel/seccomp.c index dc77548167ef..e691d9a6c58d 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -19,6 +19,8 @@ #include <linux/compat.h> #include <linux/coredump.h> #include <linux/kmemleak.h> +#include <linux/nospec.h> +#include <linux/prctl.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <linux/seccomp.h> @@ -227,8 +229,11 @@ static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode) return true; } +void __weak arch_seccomp_spec_mitigate(struct task_struct *task) { } + static inline void seccomp_assign_mode(struct task_struct *task, - unsigned long seccomp_mode) + unsigned long seccomp_mode, + unsigned long flags) { assert_spin_locked(&task->sighand->siglock); @@ -238,6 +243,9 @@ static inline void seccomp_assign_mode(struct task_struct *task, * filter) is set. */ smp_mb__before_atomic(); + /* Assume default seccomp processes want spec flaw mitigation. */ + if ((flags & SECCOMP_FILTER_FLAG_SPEC_ALLOW) == 0) + arch_seccomp_spec_mitigate(task); set_tsk_thread_flag(task, TIF_SECCOMP); } @@ -305,7 +313,7 @@ static inline pid_t seccomp_can_sync_threads(void) * without dropping the locks. * */ -static inline void seccomp_sync_threads(void) +static inline void seccomp_sync_threads(unsigned long flags) { struct task_struct *thread, *caller; @@ -346,7 +354,8 @@ static inline void seccomp_sync_threads(void) * allow one thread to transition the other. */ if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) - seccomp_assign_mode(thread, SECCOMP_MODE_FILTER); + seccomp_assign_mode(thread, SECCOMP_MODE_FILTER, + flags); } } @@ -469,7 +478,7 @@ static long seccomp_attach_filter(unsigned int flags, /* Now that the new filter is in place, synchronize to all threads. */ if (flags & SECCOMP_FILTER_FLAG_TSYNC) - seccomp_sync_threads(); + seccomp_sync_threads(flags); return 0; } @@ -818,7 +827,7 @@ static long seccomp_set_mode_strict(void) #ifdef TIF_NOTSC disable_TSC(); #endif - seccomp_assign_mode(current, seccomp_mode); + seccomp_assign_mode(current, seccomp_mode, 0); ret = 0; out: @@ -876,7 +885,7 @@ static long seccomp_set_mode_filter(unsigned int flags, /* Do not free the successfully attached filter. */ prepared = NULL; - seccomp_assign_mode(current, seccomp_mode); + seccomp_assign_mode(current, seccomp_mode, flags); out: spin_unlock_irq(¤t->sighand->siglock); if (flags & SECCOMP_FILTER_FLAG_TSYNC) diff --git a/kernel/signal.c b/kernel/signal.c index 9c33163a6165..0f865d67415d 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1539,7 +1539,6 @@ int send_sig_fault(int sig, int code, void __user *addr return send_sig_info(info.si_signo, &info, t); } -#if defined(BUS_MCEERR_AO) && defined(BUS_MCEERR_AR) int force_sig_mceerr(int code, void __user *addr, short lsb, struct task_struct *t) { struct siginfo info; @@ -1568,9 +1567,7 @@ int send_sig_mceerr(int code, void __user *addr, short lsb, struct task_struct * return send_sig_info(info.si_signo, &info, t); } EXPORT_SYMBOL(send_sig_mceerr); -#endif -#ifdef SEGV_BNDERR int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper) { struct siginfo info; @@ -1584,7 +1581,6 @@ int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper) info.si_upper = upper; return force_sig_info(info.si_signo, &info, current); } -#endif #ifdef SEGV_PKUERR int force_sig_pkuerr(void __user *addr, u32 pkey) @@ -2837,8 +2833,19 @@ enum siginfo_layout siginfo_layout(int sig, int si_code) [SIGPOLL] = { NSIGPOLL, SIL_POLL }, [SIGSYS] = { NSIGSYS, SIL_SYS }, }; - if ((sig < ARRAY_SIZE(filter)) && (si_code <= filter[sig].limit)) + if ((sig < ARRAY_SIZE(filter)) && (si_code <= filter[sig].limit)) { layout = filter[sig].layout; + /* Handle the exceptions */ + if ((sig == SIGBUS) && + (si_code >= BUS_MCEERR_AR) && (si_code <= BUS_MCEERR_AO)) + layout = SIL_FAULT_MCEERR; + else if ((sig == SIGSEGV) && (si_code == SEGV_BNDERR)) + layout = SIL_FAULT_BNDERR; +#ifdef SEGV_PKUERR + else if ((sig == SIGSEGV) && (si_code == SEGV_PKUERR)) + layout = SIL_FAULT_PKUERR; +#endif + } else if (si_code <= NSIGPOLL) layout = SIL_POLL; } else { @@ -2848,104 +2855,15 @@ enum siginfo_layout siginfo_layout(int sig, int si_code) layout = SIL_POLL; else if (si_code < 0) layout = SIL_RT; - /* Tests to support buggy kernel ABIs */ -#ifdef TRAP_FIXME - if ((sig == SIGTRAP) && (si_code == TRAP_FIXME)) - layout = SIL_FAULT; -#endif -#ifdef FPE_FIXME - if ((sig == SIGFPE) && (si_code == FPE_FIXME)) - layout = SIL_FAULT; -#endif } return layout; } int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from) { - int err; - - if (!access_ok (VERIFY_WRITE, to, sizeof(siginfo_t))) + if (copy_to_user(to, from , sizeof(struct siginfo))) return -EFAULT; - if (from->si_code < 0) - return __copy_to_user(to, from, sizeof(siginfo_t)) - ? -EFAULT : 0; - /* - * If you change siginfo_t structure, please be sure - * this code is fixed accordingly. - * Please remember to update the signalfd_copyinfo() function - * inside fs/signalfd.c too, in case siginfo_t changes. - * It should never copy any pad contained in the structure - * to avoid security leaks, but must copy the generic - * 3 ints plus the relevant union member. - */ - err = __put_user(from->si_signo, &to->si_signo); - err |= __put_user(from->si_errno, &to->si_errno); - err |= __put_user(from->si_code, &to->si_code); - switch (siginfo_layout(from->si_signo, from->si_code)) { - case SIL_KILL: - err |= __put_user(from->si_pid, &to->si_pid); - err |= __put_user(from->si_uid, &to->si_uid); - break; - case SIL_TIMER: - /* Unreached SI_TIMER is negative */ - break; - case SIL_POLL: - err |= __put_user(from->si_band, &to->si_band); - err |= __put_user(from->si_fd, &to->si_fd); - break; - case SIL_FAULT: - err |= __put_user(from->si_addr, &to->si_addr); -#ifdef __ARCH_SI_TRAPNO - err |= __put_user(from->si_trapno, &to->si_trapno); -#endif -#ifdef __ia64__ - err |= __put_user(from->si_imm, &to->si_imm); - err |= __put_user(from->si_flags, &to->si_flags); - err |= __put_user(from->si_isr, &to->si_isr); -#endif - /* - * Other callers might not initialize the si_lsb field, - * so check explicitly for the right codes here. - */ -#ifdef BUS_MCEERR_AR - if (from->si_signo == SIGBUS && from->si_code == BUS_MCEERR_AR) - err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb); -#endif -#ifdef BUS_MCEERR_AO - if (from->si_signo == SIGBUS && from->si_code == BUS_MCEERR_AO) - err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb); -#endif -#ifdef SEGV_BNDERR - if (from->si_signo == SIGSEGV && from->si_code == SEGV_BNDERR) { - err |= __put_user(from->si_lower, &to->si_lower); - err |= __put_user(from->si_upper, &to->si_upper); - } -#endif -#ifdef SEGV_PKUERR - if (from->si_signo == SIGSEGV && from->si_code == SEGV_PKUERR) - err |= __put_user(from->si_pkey, &to->si_pkey); -#endif - break; - case SIL_CHLD: - err |= __put_user(from->si_pid, &to->si_pid); - err |= __put_user(from->si_uid, &to->si_uid); - err |= __put_user(from->si_status, &to->si_status); - err |= __put_user(from->si_utime, &to->si_utime); - err |= __put_user(from->si_stime, &to->si_stime); - break; - case SIL_RT: - err |= __put_user(from->si_pid, &to->si_pid); - err |= __put_user(from->si_uid, &to->si_uid); - err |= __put_user(from->si_ptr, &to->si_ptr); - break; - case SIL_SYS: - err |= __put_user(from->si_call_addr, &to->si_call_addr); - err |= __put_user(from->si_syscall, &to->si_syscall); - err |= __put_user(from->si_arch, &to->si_arch); - break; - } - return err; + return 0; } #ifdef CONFIG_COMPAT @@ -2984,27 +2902,28 @@ int __copy_siginfo_to_user32(struct compat_siginfo __user *to, #ifdef __ARCH_SI_TRAPNO new.si_trapno = from->si_trapno; #endif -#ifdef BUS_MCEERR_AR - if ((from->si_signo == SIGBUS) && (from->si_code == BUS_MCEERR_AR)) - new.si_addr_lsb = from->si_addr_lsb; -#endif -#ifdef BUS_MCEERR_AO - if ((from->si_signo == SIGBUS) && (from->si_code == BUS_MCEERR_AO)) - new.si_addr_lsb = from->si_addr_lsb; + break; + case SIL_FAULT_MCEERR: + new.si_addr = ptr_to_compat(from->si_addr); +#ifdef __ARCH_SI_TRAPNO + new.si_trapno = from->si_trapno; #endif -#ifdef SEGV_BNDERR - if ((from->si_signo == SIGSEGV) && - (from->si_code == SEGV_BNDERR)) { - new.si_lower = ptr_to_compat(from->si_lower); - new.si_upper = ptr_to_compat(from->si_upper); - } + new.si_addr_lsb = from->si_addr_lsb; + break; + case SIL_FAULT_BNDERR: + new.si_addr = ptr_to_compat(from->si_addr); +#ifdef __ARCH_SI_TRAPNO + new.si_trapno = from->si_trapno; #endif -#ifdef SEGV_PKUERR - if ((from->si_signo == SIGSEGV) && - (from->si_code == SEGV_PKUERR)) - new.si_pkey = from->si_pkey; + new.si_lower = ptr_to_compat(from->si_lower); + new.si_upper = ptr_to_compat(from->si_upper); + break; + case SIL_FAULT_PKUERR: + new.si_addr = ptr_to_compat(from->si_addr); +#ifdef __ARCH_SI_TRAPNO + new.si_trapno = from->si_trapno; #endif - + new.si_pkey = from->si_pkey; break; case SIL_CHLD: new.si_pid = from->si_pid; @@ -3070,24 +2989,28 @@ int copy_siginfo_from_user32(struct siginfo *to, #ifdef __ARCH_SI_TRAPNO to->si_trapno = from.si_trapno; #endif -#ifdef BUS_MCEERR_AR - if ((from.si_signo == SIGBUS) && (from.si_code == BUS_MCEERR_AR)) - to->si_addr_lsb = from.si_addr_lsb; -#endif -#ifdef BUS_MCEER_AO - if ((from.si_signo == SIGBUS) && (from.si_code == BUS_MCEERR_AO)) - to->si_addr_lsb = from.si_addr_lsb; + break; + case SIL_FAULT_MCEERR: + to->si_addr = compat_ptr(from.si_addr); +#ifdef __ARCH_SI_TRAPNO + to->si_trapno = from.si_trapno; #endif -#ifdef SEGV_BNDERR - if ((from.si_signo == SIGSEGV) && (from.si_code == SEGV_BNDERR)) { - to->si_lower = compat_ptr(from.si_lower); - to->si_upper = compat_ptr(from.si_upper); - } + to->si_addr_lsb = from.si_addr_lsb; + break; + case SIL_FAULT_BNDERR: + to->si_addr = compat_ptr(from.si_addr); +#ifdef __ARCH_SI_TRAPNO + to->si_trapno = from.si_trapno; #endif -#ifdef SEGV_PKUERR - if ((from.si_signo == SIGSEGV) && (from.si_code == SEGV_PKUERR)) - to->si_pkey = from.si_pkey; + to->si_lower = compat_ptr(from.si_lower); + to->si_upper = compat_ptr(from.si_upper); + break; + case SIL_FAULT_PKUERR: + to->si_addr = compat_ptr(from.si_addr); +#ifdef __ARCH_SI_TRAPNO + to->si_trapno = from.si_trapno; #endif + to->si_pkey = from.si_pkey; break; case SIL_CHLD: to->si_pid = from.si_pid; diff --git a/kernel/softirq.c b/kernel/softirq.c index c5fafd792df1..de2f57fddc04 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -145,8 +145,7 @@ static void __local_bh_enable(unsigned int cnt) } /* - * Special-case - softirqs can safely be enabled in - * cond_resched_softirq(), or by __do_softirq(), + * Special-case - softirqs can safely be enabled by __do_softirq(), * without processing still-pending softirqs: */ void _local_bh_enable(void) diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 64c0291b579c..f89014a2c238 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -37,7 +37,7 @@ struct cpu_stop_done { struct cpu_stopper { struct task_struct *thread; - spinlock_t lock; + raw_spinlock_t lock; bool enabled; /* is this stopper enabled? */ struct list_head works; /* list of pending works */ @@ -81,13 +81,13 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) unsigned long flags; bool enabled; - spin_lock_irqsave(&stopper->lock, flags); + raw_spin_lock_irqsave(&stopper->lock, flags); enabled = stopper->enabled; if (enabled) __cpu_stop_queue_work(stopper, work, &wakeq); else if (work->done) cpu_stop_signal_done(work->done); - spin_unlock_irqrestore(&stopper->lock, flags); + raw_spin_unlock_irqrestore(&stopper->lock, flags); wake_up_q(&wakeq); @@ -237,8 +237,8 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1, DEFINE_WAKE_Q(wakeq); int err; retry: - spin_lock_irq(&stopper1->lock); - spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING); + raw_spin_lock_irq(&stopper1->lock); + raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING); err = -ENOENT; if (!stopper1->enabled || !stopper2->enabled) @@ -261,8 +261,8 @@ retry: __cpu_stop_queue_work(stopper1, work1, &wakeq); __cpu_stop_queue_work(stopper2, work2, &wakeq); unlock: - spin_unlock(&stopper2->lock); - spin_unlock_irq(&stopper1->lock); + raw_spin_unlock(&stopper2->lock); + raw_spin_unlock_irq(&stopper1->lock); if (unlikely(err == -EDEADLK)) { while (stop_cpus_in_progress) @@ -457,9 +457,9 @@ static int cpu_stop_should_run(unsigned int cpu) unsigned long flags; int run; - spin_lock_irqsave(&stopper->lock, flags); + raw_spin_lock_irqsave(&stopper->lock, flags); run = !list_empty(&stopper->works); - spin_unlock_irqrestore(&stopper->lock, flags); + raw_spin_unlock_irqrestore(&stopper->lock, flags); return run; } @@ -470,13 +470,13 @@ static void cpu_stopper_thread(unsigned int cpu) repeat: work = NULL; - spin_lock_irq(&stopper->lock); + raw_spin_lock_irq(&stopper->lock); if (!list_empty(&stopper->works)) { work = list_first_entry(&stopper->works, struct cpu_stop_work, list); list_del_init(&work->list); } - spin_unlock_irq(&stopper->lock); + raw_spin_unlock_irq(&stopper->lock); if (work) { cpu_stop_fn_t fn = work->fn; @@ -550,7 +550,7 @@ static int __init cpu_stop_init(void) for_each_possible_cpu(cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); - spin_lock_init(&stopper->lock); + raw_spin_lock_init(&stopper->lock); INIT_LIST_HEAD(&stopper->works); } diff --git a/kernel/sys.c b/kernel/sys.c index ad692183dfe9..d1b2b8d934bb 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -61,6 +61,8 @@ #include <linux/uidgid.h> #include <linux/cred.h> +#include <linux/nospec.h> + #include <linux/kmsg_dump.h> /* Move somewhere else to avoid recompiling? */ #include <generated/utsrelease.h> @@ -69,6 +71,9 @@ #include <asm/io.h> #include <asm/unistd.h> +/* Hardening for Spectre-v1 */ +#include <linux/nospec.h> + #include "uid16.h" #ifndef SET_UNALIGN_CTL @@ -1451,6 +1456,7 @@ SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, if (resource >= RLIM_NLIMITS) return -EINVAL; + resource = array_index_nospec(resource, RLIM_NLIMITS); task_lock(current->group_leader); x = current->signal->rlim[resource]; task_unlock(current->group_leader); @@ -1470,6 +1476,7 @@ COMPAT_SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, if (resource >= RLIM_NLIMITS) return -EINVAL; + resource = array_index_nospec(resource, RLIM_NLIMITS); task_lock(current->group_leader); r = current->signal->rlim[resource]; task_unlock(current->group_leader); @@ -2242,6 +2249,17 @@ static int propagate_has_child_subreaper(struct task_struct *p, void *data) return 1; } +int __weak arch_prctl_spec_ctrl_get(struct task_struct *t, unsigned long which) +{ + return -EINVAL; +} + +int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which, + unsigned long ctrl) +{ + return -EINVAL; +} + SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { @@ -2450,6 +2468,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_SVE_GET_VL: error = SVE_GET_VL(); break; + case PR_GET_SPECULATION_CTRL: + if (arg3 || arg4 || arg5) + return -EINVAL; + error = arch_prctl_spec_ctrl_get(me, arg2); + break; + case PR_SET_SPECULATION_CTRL: + if (arg4 || arg5) + return -EINVAL; + error = arch_prctl_spec_ctrl_set(me, arg2, arg3); + break; default: error = -EINVAL; break; diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 9791364925dc..183169c2a75b 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -43,7 +43,9 @@ COND_SYSCALL(io_submit); COND_SYSCALL_COMPAT(io_submit); COND_SYSCALL(io_cancel); COND_SYSCALL(io_getevents); +COND_SYSCALL(io_pgetevents); COND_SYSCALL_COMPAT(io_getevents); +COND_SYSCALL_COMPAT(io_pgetevents); /* fs/xattr.c */ diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index b398c2ea69b2..aa2094d5dd27 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -612,6 +612,14 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev) now = ktime_get(); /* Find all expired events */ for_each_cpu(cpu, tick_broadcast_oneshot_mask) { + /* + * Required for !SMP because for_each_cpu() reports + * unconditionally CPU0 as set on UP kernels. + */ + if (!IS_ENABLED(CONFIG_SMP) && + cpumask_empty(tick_broadcast_oneshot_mask)) + break; + td = &per_cpu(tick_cpu_device, cpu); if (td->evtdev->next_event <= now) { cpumask_set_cpu(cpu, tmpmask); diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index 0ed768b56c60..675c4e9563a9 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -372,24 +372,12 @@ static const struct seq_operations timer_list_sops = { .show = timer_list_show, }; -static int timer_list_open(struct inode *inode, struct file *filp) -{ - return seq_open_private(filp, &timer_list_sops, - sizeof(struct timer_list_iter)); -} - -static const struct file_operations timer_list_fops = { - .open = timer_list_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_private, -}; - static int __init init_timer_list_procfs(void) { struct proc_dir_entry *pe; - pe = proc_create("timer_list", 0400, NULL, &timer_list_fops); + pe = proc_create_seq_private("timer_list", 0400, NULL, &timer_list_sops, + sizeof(struct timer_list_iter), NULL); if (!pe) return -ENOMEM; return 0; diff --git a/kernel/torture.c b/kernel/torture.c index 37b94012a3f8..3de1efbecd6a 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -574,7 +574,7 @@ void stutter_wait(const char *title) { int spt; - cond_resched_rcu_qs(); + cond_resched_tasks_rcu_qs(); spt = READ_ONCE(stutter_pause_test); for (; spt; spt = READ_ONCE(stutter_pause_test)) { if (spt == 1) { diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 414d7210b2ec..bcd93031d042 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -893,7 +893,7 @@ int __trace_bputs(unsigned long ip, const char *str) EXPORT_SYMBOL_GPL(__trace_bputs); #ifdef CONFIG_TRACER_SNAPSHOT -static void tracing_snapshot_instance(struct trace_array *tr) +void tracing_snapshot_instance(struct trace_array *tr) { struct tracer *tracer = tr->current_trace; unsigned long flags; @@ -949,7 +949,7 @@ static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf, struct trace_buffer *size_buf, int cpu_id); static void set_buffer_entries(struct trace_buffer *buf, unsigned long val); -static int alloc_snapshot(struct trace_array *tr) +int tracing_alloc_snapshot_instance(struct trace_array *tr) { int ret; @@ -995,7 +995,7 @@ int tracing_alloc_snapshot(void) struct trace_array *tr = &global_trace; int ret; - ret = alloc_snapshot(tr); + ret = tracing_alloc_snapshot_instance(tr); WARN_ON(ret < 0); return ret; @@ -5408,7 +5408,7 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf) #ifdef CONFIG_TRACER_MAX_TRACE if (t->use_max_tr && !had_max_tr) { - ret = alloc_snapshot(tr); + ret = tracing_alloc_snapshot_instance(tr); if (ret < 0) goto out; } @@ -6451,7 +6451,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, } #endif if (!tr->allocated_snapshot) { - ret = alloc_snapshot(tr); + ret = tracing_alloc_snapshot_instance(tr); if (ret < 0) break; } @@ -7179,7 +7179,7 @@ ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash, return ret; out_reg: - ret = alloc_snapshot(tr); + ret = tracing_alloc_snapshot_instance(tr); if (ret < 0) goto out; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 6fb46a06c9dc..507954b4e058 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1817,6 +1817,17 @@ static inline void __init trace_event_init(void) { } static inline void trace_event_eval_update(struct trace_eval_map **map, int len) { } #endif +#ifdef CONFIG_TRACER_SNAPSHOT +void tracing_snapshot_instance(struct trace_array *tr); +int tracing_alloc_snapshot_instance(struct trace_array *tr); +#else +static inline void tracing_snapshot_instance(struct trace_array *tr) { } +static inline int tracing_alloc_snapshot_instance(struct trace_array *tr) +{ + return 0; +} +#endif + extern struct trace_iterator *tracepoint_print_iter; #endif /* _LINUX_KERNEL_TRACE_H */ diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c index 22fee766081b..80e0b2aca703 100644 --- a/kernel/trace/trace_benchmark.c +++ b/kernel/trace/trace_benchmark.c @@ -159,13 +159,13 @@ static int benchmark_event_kthread(void *arg) * wants to run, schedule in, but if the CPU is idle, * we'll keep burning cycles. * - * Note the _rcu_qs() version of cond_resched() will + * Note the tasks_rcu_qs() version of cond_resched() will * notify synchronize_rcu_tasks() that this thread has * passed a quiescent state for rcu_tasks. Otherwise * this thread will never voluntarily schedule which would * block synchronize_rcu_tasks() indefinitely. */ - cond_resched(); + cond_resched_tasks_rcu_qs(); } return 0; diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index d251cabcf69a..8b5bdcf64871 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -483,9 +483,10 @@ clear_event_triggers(struct trace_array *tr) struct trace_event_file *file; list_for_each_entry(file, &tr->events, list) { - struct event_trigger_data *data; - list_for_each_entry_rcu(data, &file->triggers, list) { + struct event_trigger_data *data, *n; + list_for_each_entry_safe(data, n, &file->triggers, list) { trace_event_trigger_enable_disable(file, 0); + list_del_rcu(&data->list); if (data->ops->free) data->ops->free(data->ops, data); } @@ -642,6 +643,7 @@ event_trigger_callback(struct event_command *cmd_ops, trigger_data->count = -1; trigger_data->ops = trigger_ops; trigger_data->cmd_ops = cmd_ops; + trigger_data->private_data = file; INIT_LIST_HEAD(&trigger_data->list); INIT_LIST_HEAD(&trigger_data->named_list); @@ -1053,7 +1055,12 @@ static void snapshot_trigger(struct event_trigger_data *data, void *rec, struct ring_buffer_event *event) { - tracing_snapshot(); + struct trace_event_file *file = data->private_data; + + if (file) + tracing_snapshot_instance(file->tr); + else + tracing_snapshot(); } static void @@ -1076,7 +1083,7 @@ register_snapshot_trigger(char *glob, struct event_trigger_ops *ops, { int ret = register_trigger(glob, ops, data, file); - if (ret > 0 && tracing_alloc_snapshot() != 0) { + if (ret > 0 && tracing_alloc_snapshot_instance(file->tr) != 0) { unregister_trigger(glob, ops, data, file); ret = 0; } |