diff options
Diffstat (limited to 'kernel')
35 files changed, 777 insertions, 792 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 98c0f00c3f5e..e2636737b69b 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -98,7 +98,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) array_size += (u64) attr->max_entries * elem_size * num_possible_cpus(); if (array_size >= U32_MAX - PAGE_SIZE || - elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) { + bpf_array_alloc_percpu(array)) { bpf_map_area_free(array); return ERR_PTR(-ENOMEM); } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 917cc04a0a94..7b62df86be1d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1022,7 +1022,7 @@ select_insn: struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2; struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_prog *prog; - u64 index = BPF_R3; + u32 index = BPF_R3; if (unlikely(index >= array->map.max_entries)) goto out; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index e093d9a2c4dd..e745d6a88224 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -69,7 +69,7 @@ static LIST_HEAD(dev_map_list); static u64 dev_map_bitmap_size(const union bpf_attr *attr) { - return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long); + return BITS_TO_LONGS((u64) attr->max_entries) * sizeof(unsigned long); } static struct bpf_map *dev_map_alloc(union bpf_attr *attr) @@ -78,6 +78,9 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) int err = -EINVAL; u64 cost; + if (!capable(CAP_NET_ADMIN)) + return ERR_PTR(-EPERM); + /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) @@ -111,8 +114,9 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) err = -ENOMEM; /* A per cpu bitfield with a bit per possible net device */ - dtab->flush_needed = __alloc_percpu(dev_map_bitmap_size(attr), - __alignof__(unsigned long)); + dtab->flush_needed = __alloc_percpu_gfp(dev_map_bitmap_size(attr), + __alignof__(unsigned long), + GFP_KERNEL | __GFP_NOWARN); if (!dtab->flush_needed) goto free_dtab; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 431126f31ea3..6533f08d1238 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -317,10 +317,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) */ goto free_htab; - if (percpu && round_up(htab->map.value_size, 8) > PCPU_MIN_UNIT_SIZE) - /* make sure the size for pcpu_alloc() is reasonable */ - goto free_htab; - htab->elem_size = sizeof(struct htab_elem) + round_up(htab->map.key_size, 8); if (percpu) diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index e833ed914358..be1dde967208 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -363,6 +363,7 @@ out: putname(pname); return ret; } +EXPORT_SYMBOL_GPL(bpf_obj_get_user); static void bpf_evict_inode(struct inode *inode) { diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 6424ce0e4969..66f00a2b27f4 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -39,6 +39,7 @@ #include <linux/workqueue.h> #include <linux/list.h> #include <net/strparser.h> +#include <net/tcp.h> struct bpf_stab { struct bpf_map map; @@ -92,6 +93,14 @@ static inline struct smap_psock *smap_psock_sk(const struct sock *sk) return rcu_dereference_sk_user_data(sk); } +/* compute the linear packet data range [data, data_end) for skb when + * sk_skb type programs are in use. + */ +static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb) +{ + TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb); +} + static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) { struct bpf_prog *prog = READ_ONCE(psock->bpf_verdict); @@ -101,12 +110,20 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) return SK_DROP; skb_orphan(skb); + /* We need to ensure that BPF metadata for maps is also cleared + * when we orphan the skb so that we don't have the possibility + * to reference a stale map. + */ + TCP_SKB_CB(skb)->bpf.map = NULL; skb->sk = psock->sock; - bpf_compute_data_end(skb); + bpf_compute_data_end_sk_skb(skb); + preempt_disable(); rc = (*prog->bpf_func)(skb, prog->insnsi); + preempt_enable(); skb->sk = NULL; - return rc; + return rc == SK_PASS ? + (TCP_SKB_CB(skb)->bpf.map ? SK_REDIRECT : SK_PASS) : SK_DROP; } static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) @@ -114,17 +131,10 @@ static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) struct sock *sk; int rc; - /* Because we use per cpu values to feed input from sock redirect - * in BPF program to do_sk_redirect_map() call we need to ensure we - * are not preempted. RCU read lock is not sufficient in this case - * with CONFIG_PREEMPT_RCU enabled so we must be explicit here. - */ - preempt_disable(); rc = smap_verdict_func(psock, skb); switch (rc) { case SK_REDIRECT: - sk = do_sk_redirect_map(); - preempt_enable(); + sk = do_sk_redirect_map(skb); if (likely(sk)) { struct smap_psock *peer = smap_psock_sk(sk); @@ -141,8 +151,6 @@ static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) /* Fall through and free skb otherwise */ case SK_DROP: default: - if (rc != SK_REDIRECT) - preempt_enable(); kfree_skb(skb); } } @@ -369,7 +377,7 @@ static int smap_parse_func_strparser(struct strparser *strp, * any socket yet. */ skb->sk = psock->sock; - bpf_compute_data_end(skb); + bpf_compute_data_end_sk_skb(skb); rc = (*prog->bpf_func)(skb, prog->insnsi); skb->sk = NULL; rcu_read_unlock(); @@ -487,6 +495,9 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) int err = -EINVAL; u64 cost; + if (!capable(CAP_NET_ADMIN)) + return ERR_PTR(-EPERM); + /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) @@ -840,6 +851,12 @@ static int sock_map_update_elem(struct bpf_map *map, return -EINVAL; } + if (skops.sk->sk_type != SOCK_STREAM || + skops.sk->sk_protocol != IPPROTO_TCP) { + fput(socket->file); + return -EOPNOTSUPP; + } + err = sock_map_ctx_update_elem(&skops, map, key, flags); fput(socket->file); return err; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b914fbe1383e..c48ca2a34b5e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -653,6 +653,10 @@ static void mark_reg_read(const struct bpf_verifier_state *state, u32 regno) { struct bpf_verifier_state *parent = state->parent; + if (regno == BPF_REG_FP) + /* We don't need to worry about FP liveness because it's read-only */ + return; + while (parent) { /* if read wasn't screened by an earlier write ... */ if (state->regs[regno].live & REG_LIVE_WRITTEN) @@ -1112,7 +1116,12 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn /* ctx accesses must be at a fixed offset, so that we can * determine what type of data were returned. */ - if (!tnum_is_const(reg->var_off)) { + if (reg->off) { + verbose("dereference of modified ctx ptr R%d off=%d+%d, ctx+const is allowed, ctx+const+const is not\n", + regno, reg->off, off - reg->off); + return -EACCES; + } + if (!tnum_is_const(reg->var_off) || reg->var_off.value) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); @@ -1120,7 +1129,6 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn tn_buf, off, size); return -EACCES; } - off += reg->var_off.value; err = check_ctx_access(env, insn_idx, off, size, t, ®_type); if (!err && t == BPF_READ && value_regno >= 0) { /* ctx access returns either a scalar, or a @@ -2345,6 +2353,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) * copy register state to dest reg */ regs[insn->dst_reg] = regs[insn->src_reg]; + regs[insn->dst_reg].live |= REG_LIVE_WRITTEN; } else { /* R1 = (u32) R2 */ if (is_pointer_value(env, insn->src_reg)) { @@ -2421,12 +2430,15 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } static void find_good_pkt_pointers(struct bpf_verifier_state *state, - struct bpf_reg_state *dst_reg) + struct bpf_reg_state *dst_reg, + bool range_right_open) { struct bpf_reg_state *regs = state->regs, *reg; + u16 new_range; int i; - if (dst_reg->off < 0) + if (dst_reg->off < 0 || + (dst_reg->off == 0 && range_right_open)) /* This doesn't give us any range */ return; @@ -2437,9 +2449,13 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, */ return; - /* LLVM can generate four kind of checks: + new_range = dst_reg->off; + if (range_right_open) + new_range--; + + /* Examples for register markings: * - * Type 1/2: + * pkt_data in dst register: * * r2 = r3; * r2 += 8; @@ -2456,7 +2472,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, * r2=pkt(id=n,off=8,r=0) * r3=pkt(id=n,off=0,r=0) * - * Type 3/4: + * pkt_data in src register: * * r2 = r3; * r2 += 8; @@ -2474,7 +2490,9 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, * r3=pkt(id=n,off=0,r=0) * * Find register r3 and mark its range as r3=pkt(id=n,off=0,r=8) - * so that range of bytes [r3, r3 + 8) is safe to access. + * or r3=pkt(id=n,off=0,r=8-1), so that range of bytes [r3, r3 + 8) + * and [r3, r3 + 8-1) respectively is safe to access depending on + * the check. */ /* If our ids match, then we must have the same max_value. And we @@ -2485,14 +2503,14 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, for (i = 0; i < MAX_BPF_REG; i++) if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id) /* keep the maximum range already checked */ - regs[i].range = max_t(u16, regs[i].range, dst_reg->off); + regs[i].range = max(regs[i].range, new_range); for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] != STACK_SPILL) continue; reg = &state->spilled_regs[i / BPF_REG_SIZE]; if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id) - reg->range = max_t(u16, reg->range, dst_reg->off); + reg->range = max(reg->range, new_range); } } @@ -2856,19 +2874,43 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && dst_reg->type == PTR_TO_PACKET && regs[insn->src_reg].type == PTR_TO_PACKET_END) { - find_good_pkt_pointers(this_branch, dst_reg); + /* pkt_data' > pkt_end */ + find_good_pkt_pointers(this_branch, dst_reg, false); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && + dst_reg->type == PTR_TO_PACKET_END && + regs[insn->src_reg].type == PTR_TO_PACKET) { + /* pkt_end > pkt_data' */ + find_good_pkt_pointers(other_branch, ®s[insn->src_reg], true); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && dst_reg->type == PTR_TO_PACKET && regs[insn->src_reg].type == PTR_TO_PACKET_END) { - find_good_pkt_pointers(other_branch, dst_reg); + /* pkt_data' < pkt_end */ + find_good_pkt_pointers(other_branch, dst_reg, true); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && + dst_reg->type == PTR_TO_PACKET_END && + regs[insn->src_reg].type == PTR_TO_PACKET) { + /* pkt_end < pkt_data' */ + find_good_pkt_pointers(this_branch, ®s[insn->src_reg], false); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && + dst_reg->type == PTR_TO_PACKET && + regs[insn->src_reg].type == PTR_TO_PACKET_END) { + /* pkt_data' >= pkt_end */ + find_good_pkt_pointers(this_branch, dst_reg, true); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && dst_reg->type == PTR_TO_PACKET_END && regs[insn->src_reg].type == PTR_TO_PACKET) { - find_good_pkt_pointers(other_branch, ®s[insn->src_reg]); + /* pkt_end >= pkt_data' */ + find_good_pkt_pointers(other_branch, ®s[insn->src_reg], false); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && + dst_reg->type == PTR_TO_PACKET && + regs[insn->src_reg].type == PTR_TO_PACKET_END) { + /* pkt_data' <= pkt_end */ + find_good_pkt_pointers(other_branch, dst_reg, false); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && dst_reg->type == PTR_TO_PACKET_END && regs[insn->src_reg].type == PTR_TO_PACKET) { - find_good_pkt_pointers(this_branch, ®s[insn->src_reg]); + /* pkt_end <= pkt_data' */ + find_good_pkt_pointers(this_branch, ®s[insn->src_reg], true); } else if (is_pointer_value(env, insn->dst_reg)) { verbose("R%d pointer comparison prohibited\n", insn->dst_reg); return -EACCES; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d6551cd45238..44857278eb8a 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2311,6 +2311,14 @@ out_release_tset: list_del_init(&cset->mg_node); } spin_unlock_irq(&css_set_lock); + + /* + * Re-initialize the cgroup_taskset structure in case it is reused + * again in another cgroup_migrate_add_task()/cgroup_migrate_execute() + * iteration. + */ + tset->nr_tasks = 0; + tset->csets = &tset->src_csets; return ret; } diff --git a/kernel/cpu.c b/kernel/cpu.c index 8de11a29e495..04892a82f6ac 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -24,6 +24,7 @@ #include <linux/lockdep.h> #include <linux/tick.h> #include <linux/irq.h> +#include <linux/nmi.h> #include <linux/smpboot.h> #include <linux/relay.h> #include <linux/slab.h> @@ -631,6 +632,11 @@ cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, __cpuhp_kick_ap(st); } + /* + * Clean up the leftovers so the next hotplug operation wont use stale + * data. + */ + st->node = st->last = NULL; return ret; } @@ -897,6 +903,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, out: cpus_write_unlock(); + /* + * Do post unplug cleanup. This is still protected against + * concurrent CPU hotplug via cpu_add_remove_lock. + */ + lockup_detector_cleanup(); return ret; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 6bc21e202ae4..9d93db81fa36 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -662,7 +662,7 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) /* * Do not update time when cgroup is not active */ - if (cgrp == event->cgrp) + if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) __update_cgrp_time(event->cgrp); } @@ -8955,6 +8955,14 @@ static struct perf_cpu_context __percpu *find_pmu_context(int ctxn) static void free_pmu_context(struct pmu *pmu) { + /* + * Static contexts such as perf_sw_context have a global lifetime + * and may be shared between different PMUs. Avoid freeing them + * when a single PMU is going away. + */ + if (pmu->task_ctx_nr > perf_invalid_context) + return; + mutex_lock(&pmus_lock); free_percpu(pmu->pmu_cpu_context); mutex_unlock(&pmus_lock); diff --git a/kernel/exit.c b/kernel/exit.c index f2cd53e92147..f6cad39f35df 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1610,6 +1610,9 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, if (!infop) return err; + if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop))) + return -EFAULT; + user_access_begin(); unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); @@ -1735,6 +1738,9 @@ COMPAT_SYSCALL_DEFINE5(waitid, if (!infop) return err; + if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop))) + return -EFAULT; + user_access_begin(); unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); diff --git a/kernel/fork.c b/kernel/fork.c index 10646182440f..07cc743698d3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -215,6 +215,10 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) if (!s) continue; +#ifdef CONFIG_DEBUG_KMEMLEAK + /* Clear stale pointers from reused stack. */ + memset(s->addr, 0, THREAD_SIZE); +#endif tsk->stack_vm_area = s; return s->addr; } @@ -946,6 +950,24 @@ void mmput(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(mmput); +#ifdef CONFIG_MMU +static void mmput_async_fn(struct work_struct *work) +{ + struct mm_struct *mm = container_of(work, struct mm_struct, + async_put_work); + + __mmput(mm); +} + +void mmput_async(struct mm_struct *mm) +{ + if (atomic_dec_and_test(&mm->mm_users)) { + INIT_WORK(&mm->async_put_work, mmput_async_fn); + schedule_work(&mm->async_put_work); + } +} +#endif + /** * set_mm_exe_file - change a reference to the mm's executable file * diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 6fc89fd93824..5a2ef92c2782 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -265,8 +265,8 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force) irq_setup_affinity(desc); break; case IRQ_STARTUP_MANAGED: + irq_do_set_affinity(d, aff, false); ret = __irq_startup(desc); - irq_set_affinity_locked(d, aff, false); break; case IRQ_STARTUP_ABORT: return 0; diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c index 638eb9c83d9f..9eb09aef0313 100644 --- a/kernel/irq/cpuhotplug.c +++ b/kernel/irq/cpuhotplug.c @@ -18,8 +18,34 @@ static inline bool irq_needs_fixup(struct irq_data *d) { const struct cpumask *m = irq_data_get_effective_affinity_mask(d); + unsigned int cpu = smp_processor_id(); - return cpumask_test_cpu(smp_processor_id(), m); +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + /* + * The cpumask_empty() check is a workaround for interrupt chips, + * which do not implement effective affinity, but the architecture has + * enabled the config switch. Use the general affinity mask instead. + */ + if (cpumask_empty(m)) + m = irq_data_get_affinity_mask(d); + + /* + * Sanity check. If the mask is not empty when excluding the outgoing + * CPU then it must contain at least one online CPU. The outgoing CPU + * has been removed from the online mask already. + */ + if (cpumask_any_but(m, cpu) < nr_cpu_ids && + cpumask_any_and(m, cpu_online_mask) >= nr_cpu_ids) { + /* + * If this happens then there was a missed IRQ fixup at some + * point. Warn about it and enforce fixup. + */ + pr_warn("Eff. affinity %*pbl of IRQ %u contains only offline CPUs after offlining CPU %u\n", + cpumask_pr_args(m), d->irq, cpu); + return true; + } +#endif + return cpumask_test_cpu(cpu, m); } static bool migrate_one_irq(struct irq_desc *desc) diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index 5270a54b9fa4..c26c5bb6b491 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -135,17 +135,26 @@ void irq_gc_ack_clr_bit(struct irq_data *d) } /** - * irq_gc_mask_disable_reg_and_ack - Mask and ack pending interrupt + * irq_gc_mask_disable_and_ack_set - Mask and ack pending interrupt * @d: irq_data + * + * This generic implementation of the irq_mask_ack method is for chips + * with separate enable/disable registers instead of a single mask + * register and where a pending interrupt is acknowledged by setting a + * bit. + * + * Note: This is the only permutation currently used. Similar generic + * functions should be added here if other permutations are required. */ -void irq_gc_mask_disable_reg_and_ack(struct irq_data *d) +void irq_gc_mask_disable_and_ack_set(struct irq_data *d) { struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); struct irq_chip_type *ct = irq_data_get_chip_type(d); u32 mask = d->mask; irq_gc_lock(gc); - irq_reg_writel(gc, mask, ct->regs.mask); + irq_reg_writel(gc, mask, ct->regs.disable); + *ct->mask_cache &= ~mask; irq_reg_writel(gc, mask, ct->regs.ack); irq_gc_unlock(gc); } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index d00132b5c325..4bff6a10ae8e 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -168,6 +168,19 @@ void irq_set_thread_affinity(struct irq_desc *desc) set_bit(IRQTF_AFFINITY, &action->thread_flags); } +static void irq_validate_effective_affinity(struct irq_data *data) +{ +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + const struct cpumask *m = irq_data_get_effective_affinity_mask(data); + struct irq_chip *chip = irq_data_get_irq_chip(data); + + if (!cpumask_empty(m)) + return; + pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n", + chip->name, data->irq); +#endif +} + int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -175,12 +188,16 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, struct irq_chip *chip = irq_data_get_irq_chip(data); int ret; + if (!chip || !chip->irq_set_affinity) + return -EINVAL; + ret = chip->irq_set_affinity(data, mask, force); switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: cpumask_copy(desc->irq_common_data.affinity, mask); case IRQ_SET_MASK_OK_NOCOPY: + irq_validate_effective_affinity(data); irq_set_thread_affinity(desc); ret = 0; } diff --git a/kernel/kcmp.c b/kernel/kcmp.c index ea34ed8bb952..055bb2962a0b 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -131,7 +131,7 @@ static int kcmp_epoll_target(struct task_struct *task1, if (filp_epoll) { filp_tgt = get_epoll_tfile_raw_ptr(filp_epoll, slot.tfd, slot.toff); fput(filp_epoll); - } else + } if (IS_ERR(filp_tgt)) return PTR_ERR(filp_tgt); diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index b9628e43c78f..bf8c8fd72589 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -830,6 +830,41 @@ int klp_register_patch(struct klp_patch *patch) } EXPORT_SYMBOL_GPL(klp_register_patch); +/* + * Remove parts of patches that touch a given kernel module. The list of + * patches processed might be limited. When limit is NULL, all patches + * will be handled. + */ +static void klp_cleanup_module_patches_limited(struct module *mod, + struct klp_patch *limit) +{ + struct klp_patch *patch; + struct klp_object *obj; + + list_for_each_entry(patch, &klp_patches, list) { + if (patch == limit) + break; + + klp_for_each_object(patch, obj) { + if (!klp_is_module(obj) || strcmp(obj->name, mod->name)) + continue; + + /* + * Only unpatch the module if the patch is enabled or + * is in transition. + */ + if (patch->enabled || patch == klp_transition_patch) { + pr_notice("reverting patch '%s' on unloading module '%s'\n", + patch->mod->name, obj->mod->name); + klp_unpatch_object(obj); + } + + klp_free_object_loaded(obj); + break; + } + } +} + int klp_module_coming(struct module *mod) { int ret; @@ -894,7 +929,7 @@ err: pr_warn("patch '%s' failed for module '%s', refusing to load module '%s'\n", patch->mod->name, obj->mod->name, obj->mod->name); mod->klp_alive = false; - klp_free_object_loaded(obj); + klp_cleanup_module_patches_limited(mod, patch); mutex_unlock(&klp_mutex); return ret; @@ -902,9 +937,6 @@ err: void klp_module_going(struct module *mod) { - struct klp_patch *patch; - struct klp_object *obj; - if (WARN_ON(mod->state != MODULE_STATE_GOING && mod->state != MODULE_STATE_COMING)) return; @@ -917,25 +949,7 @@ void klp_module_going(struct module *mod) */ mod->klp_alive = false; - list_for_each_entry(patch, &klp_patches, list) { - klp_for_each_object(patch, obj) { - if (!klp_is_module(obj) || strcmp(obj->name, mod->name)) - continue; - - /* - * Only unpatch the module if the patch is enabled or - * is in transition. - */ - if (patch->enabled || patch == klp_transition_patch) { - pr_notice("reverting patch '%s' on unloading module '%s'\n", - patch->mod->name, obj->mod->name); - klp_unpatch_object(obj); - } - - klp_free_object_loaded(obj); - break; - } - } + klp_cleanup_module_patches_limited(mod, NULL); mutex_unlock(&klp_mutex); } diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 44c8d0d17170..e36e652d996f 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -1873,10 +1873,10 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, struct held_lock *next, int distance, struct stack_trace *trace, int (*save)(struct stack_trace *trace)) { + struct lock_list *uninitialized_var(target_entry); struct lock_list *entry; - int ret; struct lock_list this; - struct lock_list *uninitialized_var(target_entry); + int ret; /* * Prove that the new <prev> -> <next> dependency would not @@ -1890,8 +1890,17 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, this.class = hlock_class(next); this.parent = NULL; ret = check_noncircular(&this, hlock_class(prev), &target_entry); - if (unlikely(!ret)) + if (unlikely(!ret)) { + if (!trace->entries) { + /* + * If @save fails here, the printing might trigger + * a WARN but because of the !nr_entries it should + * not do bad things. + */ + save(trace); + } return print_circular_bug(&this, target_entry, next, prev, trace); + } else if (unlikely(ret < 0)) return print_bfs_bug(ret); @@ -1938,7 +1947,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, return print_bfs_bug(ret); - if (save && !save(trace)) + if (!trace->entries && !save(trace)) return 0; /* @@ -1958,20 +1967,6 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, if (!ret) return 0; - /* - * Debugging printouts: - */ - if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) { - graph_unlock(); - printk("\n new dependency: "); - print_lock_name(hlock_class(prev)); - printk(KERN_CONT " => "); - print_lock_name(hlock_class(next)); - printk(KERN_CONT "\n"); - dump_stack(); - if (!graph_lock()) - return 0; - } return 2; } @@ -1986,8 +1981,12 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next) { int depth = curr->lockdep_depth; struct held_lock *hlock; - struct stack_trace trace; - int (*save)(struct stack_trace *trace) = save_trace; + struct stack_trace trace = { + .nr_entries = 0, + .max_entries = 0, + .entries = NULL, + .skip = 0, + }; /* * Debugging checks. @@ -2018,18 +2017,11 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next) */ if (hlock->read != 2 && hlock->check) { int ret = check_prev_add(curr, hlock, next, - distance, &trace, save); + distance, &trace, save_trace); if (!ret) return 0; /* - * Stop saving stack_trace if save_trace() was - * called at least once: - */ - if (save && ret == 2) - save = NULL; - - /* * Stop after the first non-trylock entry, * as non-trylock entries have added their * own direct dependencies already, so this diff --git a/kernel/memremap.c b/kernel/memremap.c index 6bcbfbf1a8fd..403ab9cdb949 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -350,7 +350,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, pgprot_t pgprot = PAGE_KERNEL; struct dev_pagemap *pgmap; struct page_map *page_map; - int error, nid, is_ram; + int error, nid, is_ram, i = 0; align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) @@ -448,6 +448,8 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, list_del(&page->lru); page->pgmap = pgmap; percpu_ref_get(ref); + if (!(++i % 1024)) + cond_resched(); } devres_add(dev, page_map); return __va(res->start); diff --git a/kernel/params.c b/kernel/params.c index 60b2d8101355..cc9108c2a1fd 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -224,7 +224,7 @@ char *parse_args(const char *doing, } \ int param_get_##name(char *buffer, const struct kernel_param *kp) \ { \ - return scnprintf(buffer, PAGE_SIZE, format, \ + return scnprintf(buffer, PAGE_SIZE, format "\n", \ *((type *)kp->arg)); \ } \ const struct kernel_param_ops param_ops_##name = { \ @@ -236,14 +236,14 @@ char *parse_args(const char *doing, EXPORT_SYMBOL(param_ops_##name) -STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", kstrtou8); -STANDARD_PARAM_DEF(short, short, "%hi", kstrtos16); -STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", kstrtou16); -STANDARD_PARAM_DEF(int, int, "%i", kstrtoint); -STANDARD_PARAM_DEF(uint, unsigned int, "%u", kstrtouint); -STANDARD_PARAM_DEF(long, long, "%li", kstrtol); -STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul); -STANDARD_PARAM_DEF(ullong, unsigned long long, "%llu", kstrtoull); +STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", kstrtou8); +STANDARD_PARAM_DEF(short, short, "%hi", kstrtos16); +STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", kstrtou16); +STANDARD_PARAM_DEF(int, int, "%i", kstrtoint); +STANDARD_PARAM_DEF(uint, unsigned int, "%u", kstrtouint); +STANDARD_PARAM_DEF(long, long, "%li", kstrtol); +STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul); +STANDARD_PARAM_DEF(ullong, unsigned long long, "%llu", kstrtoull); int param_set_charp(const char *val, const struct kernel_param *kp) { @@ -270,7 +270,7 @@ EXPORT_SYMBOL(param_set_charp); int param_get_charp(char *buffer, const struct kernel_param *kp) { - return scnprintf(buffer, PAGE_SIZE, "%s", *((char **)kp->arg)); + return scnprintf(buffer, PAGE_SIZE, "%s\n", *((char **)kp->arg)); } EXPORT_SYMBOL(param_get_charp); @@ -301,7 +301,7 @@ EXPORT_SYMBOL(param_set_bool); int param_get_bool(char *buffer, const struct kernel_param *kp) { /* Y and N chosen as being relatively non-coder friendly */ - return sprintf(buffer, "%c", *(bool *)kp->arg ? 'Y' : 'N'); + return sprintf(buffer, "%c\n", *(bool *)kp->arg ? 'Y' : 'N'); } EXPORT_SYMBOL(param_get_bool); @@ -360,7 +360,7 @@ EXPORT_SYMBOL(param_set_invbool); int param_get_invbool(char *buffer, const struct kernel_param *kp) { - return sprintf(buffer, "%c", (*(bool *)kp->arg) ? 'N' : 'Y'); + return sprintf(buffer, "%c\n", (*(bool *)kp->arg) ? 'N' : 'Y'); } EXPORT_SYMBOL(param_get_invbool); @@ -460,8 +460,9 @@ static int param_array_get(char *buffer, const struct kernel_param *kp) struct kernel_param p = *kp; for (i = off = 0; i < (arr->num ? *arr->num : arr->max); i++) { + /* Replace \n with comma */ if (i) - buffer[off++] = ','; + buffer[off - 1] = ','; p.arg = arr->elem + arr->elemsize * i; check_kparam_locked(p.mod); ret = arr->ops->get(buffer + off, &p); @@ -507,7 +508,7 @@ EXPORT_SYMBOL(param_set_copystring); int param_get_string(char *buffer, const struct kernel_param *kp) { const struct kparam_string *kps = kp->str; - return strlcpy(buffer, kps->string, kps->maxlen); + return scnprintf(buffer, PAGE_SIZE, "%s\n", kps->string); } EXPORT_SYMBOL(param_get_string); @@ -549,10 +550,6 @@ static ssize_t param_attr_show(struct module_attribute *mattr, kernel_param_lock(mk->mod); count = attribute->param->ops->get(buf, attribute->param); kernel_param_unlock(mk->mod); - if (count > 0) { - strcat(buf, "\n"); - ++count; - } return count; } @@ -600,7 +597,7 @@ EXPORT_SYMBOL(kernel_param_unlock); /* * add_sysfs_param - add a parameter to sysfs * @mk: struct module_kobject - * @kparam: the actual parameter definition to add to sysfs + * @kp: the actual parameter definition to add to sysfs * @name: name of parameter * * Create a kobject if for a (per-module) parameter if mp NULL, and diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 3e2b4f519009..ccd2d20e6b06 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -120,22 +120,26 @@ static void s2idle_loop(void) * frozen processes + suspended devices + idle processors. * Thus s2idle_enter() should be called right after * all devices have been suspended. + * + * Wakeups during the noirq suspend of devices may be spurious, + * so prevent them from terminating the loop right away. */ error = dpm_noirq_suspend_devices(PMSG_SUSPEND); if (!error) s2idle_enter(); + else if (error == -EBUSY && pm_wakeup_pending()) + error = 0; - dpm_noirq_resume_devices(PMSG_RESUME); - if (error && (error != -EBUSY || !pm_wakeup_pending())) { - dpm_noirq_end(); - break; - } - - if (s2idle_ops && s2idle_ops->wake) + if (!error && s2idle_ops && s2idle_ops->wake) s2idle_ops->wake(); + dpm_noirq_resume_devices(PMSG_RESUME); + dpm_noirq_end(); + if (error) + break; + if (s2idle_ops && s2idle_ops->sync) s2idle_ops->sync(); diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 729a8706751d..6d5880089ff6 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -854,7 +854,7 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp, /** * call_srcu() - Queue a callback for invocation after an SRCU grace period * @sp: srcu_struct in queue the callback - * @head: structure to be used for queueing the SRCU callback. + * @rhp: structure to be used for queueing the SRCU callback. * @func: function to be invoked after the SRCU grace period * * The callback function will be invoked some time after a full SRCU diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c index 50d1861f7759..3f943efcf61c 100644 --- a/kernel/rcu/sync.c +++ b/kernel/rcu/sync.c @@ -85,6 +85,9 @@ void rcu_sync_init(struct rcu_sync *rsp, enum rcu_sync_type type) } /** + * rcu_sync_enter_start - Force readers onto slow path for multiple updates + * @rsp: Pointer to rcu_sync structure to use for synchronization + * * Must be called after rcu_sync_init() and before first use. * * Ensures rcu_sync_is_idle() returns false and rcu_sync_{enter,exit}() @@ -142,7 +145,7 @@ void rcu_sync_enter(struct rcu_sync *rsp) /** * rcu_sync_func() - Callback function managing reader access to fastpath - * @rsp: Pointer to rcu_sync structure to use for synchronization + * @rhp: Pointer to rcu_head in rcu_sync structure to use for synchronization * * This function is passed to one of the call_rcu() functions by * rcu_sync_exit(), so that it is invoked after a grace period following the @@ -158,9 +161,9 @@ void rcu_sync_enter(struct rcu_sync *rsp) * rcu_sync_exit(). Otherwise, set all state back to idle so that readers * can again use their fastpaths. */ -static void rcu_sync_func(struct rcu_head *rcu) +static void rcu_sync_func(struct rcu_head *rhp) { - struct rcu_sync *rsp = container_of(rcu, struct rcu_sync, cb_head); + struct rcu_sync *rsp = container_of(rhp, struct rcu_sync, cb_head); unsigned long flags; BUG_ON(rsp->gp_state != GP_PASSED); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 0c44c7b42e6d..3e3650e94ae6 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -884,7 +884,7 @@ void rcu_irq_exit(void) rdtp = this_cpu_ptr(&rcu_dynticks); /* Page faults can happen in NMI handlers, so check... */ - if (READ_ONCE(rdtp->dynticks_nmi_nesting)) + if (rdtp->dynticks_nmi_nesting) return; WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && @@ -1022,7 +1022,7 @@ void rcu_irq_enter(void) rdtp = this_cpu_ptr(&rcu_dynticks); /* Page faults can happen in NMI handlers, so check... */ - if (READ_ONCE(rdtp->dynticks_nmi_nesting)) + if (rdtp->dynticks_nmi_nesting) return; oldval = rdtp->dynticks_nesting; @@ -3097,9 +3097,10 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, * read-side critical sections have completed. call_rcu_sched() assumes * that the read-side critical sections end on enabling of preemption * or on voluntary preemption. - * RCU read-side critical sections are delimited by : - * - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR - * - anything that disables preemption. + * RCU read-side critical sections are delimited by: + * + * - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR + * - anything that disables preemption. * * These may be nested. * @@ -3124,11 +3125,12 @@ EXPORT_SYMBOL_GPL(call_rcu_sched); * handler. This means that read-side critical sections in process * context must not be interrupted by softirqs. This interface is to be * used when most of the read-side critical sections are in softirq context. - * RCU read-side critical sections are delimited by : - * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context. - * OR - * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. - * These may be nested. + * RCU read-side critical sections are delimited by: + * + * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context, OR + * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. + * + * These may be nested. * * See the description of call_rcu() for more detailed information on * memory ordering guarantees. diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 70ba32e08a23..d3f3094856fe 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5356,91 +5356,62 @@ static int wake_wide(struct task_struct *p) return 1; } -struct llc_stats { - unsigned long nr_running; - unsigned long load; - unsigned long capacity; - int has_capacity; -}; +/* + * The purpose of wake_affine() is to quickly determine on which CPU we can run + * soonest. For the purpose of speed we only consider the waking and previous + * CPU. + * + * wake_affine_idle() - only considers 'now', it check if the waking CPU is (or + * will be) idle. + * + * wake_affine_weight() - considers the weight to reflect the average + * scheduling latency of the CPUs. This seems to work + * for the overloaded case. + */ -static bool get_llc_stats(struct llc_stats *stats, int cpu) +static bool +wake_affine_idle(struct sched_domain *sd, struct task_struct *p, + int this_cpu, int prev_cpu, int sync) { - struct sched_domain_shared *sds = rcu_dereference(per_cpu(sd_llc_shared, cpu)); - - if (!sds) - return false; + if (idle_cpu(this_cpu)) + return true; - stats->nr_running = READ_ONCE(sds->nr_running); - stats->load = READ_ONCE(sds->load); - stats->capacity = READ_ONCE(sds->capacity); - stats->has_capacity = stats->nr_running < per_cpu(sd_llc_size, cpu); + if (sync && cpu_rq(this_cpu)->nr_running == 1) + return true; - return true; + return false; } -/* - * Can a task be moved from prev_cpu to this_cpu without causing a load - * imbalance that would trigger the load balancer? - * - * Since we're running on 'stale' values, we might in fact create an imbalance - * but recomputing these values is expensive, as that'd mean iteration 2 cache - * domains worth of CPUs. - */ static bool -wake_affine_llc(struct sched_domain *sd, struct task_struct *p, - int this_cpu, int prev_cpu, int sync) +wake_affine_weight(struct sched_domain *sd, struct task_struct *p, + int this_cpu, int prev_cpu, int sync) { - struct llc_stats prev_stats, this_stats; s64 this_eff_load, prev_eff_load; unsigned long task_load; - if (!get_llc_stats(&prev_stats, prev_cpu) || - !get_llc_stats(&this_stats, this_cpu)) - return false; + this_eff_load = target_load(this_cpu, sd->wake_idx); + prev_eff_load = source_load(prev_cpu, sd->wake_idx); - /* - * If sync wakeup then subtract the (maximum possible) - * effect of the currently running task from the load - * of the current LLC. - */ if (sync) { unsigned long current_load = task_h_load(current); - /* in this case load hits 0 and this LLC is considered 'idle' */ - if (current_load > this_stats.load) + if (current_load > this_eff_load) return true; - this_stats.load -= current_load; + this_eff_load -= current_load; } - /* - * The has_capacity stuff is not SMT aware, but by trying to balance - * the nr_running on both ends we try and fill the domain at equal - * rates, thereby first consuming cores before siblings. - */ - - /* if the old cache has capacity, stay there */ - if (prev_stats.has_capacity && prev_stats.nr_running < this_stats.nr_running+1) - return false; - - /* if this cache has capacity, come here */ - if (this_stats.has_capacity && this_stats.nr_running+1 < prev_stats.nr_running) - return true; - - /* - * Check to see if we can move the load without causing too much - * imbalance. - */ task_load = task_h_load(p); - this_eff_load = 100; - this_eff_load *= prev_stats.capacity; - - prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2; - prev_eff_load *= this_stats.capacity; + this_eff_load += task_load; + if (sched_feat(WA_BIAS)) + this_eff_load *= 100; + this_eff_load *= capacity_of(prev_cpu); - this_eff_load *= this_stats.load + task_load; - prev_eff_load *= prev_stats.load - task_load; + prev_eff_load -= task_load; + if (sched_feat(WA_BIAS)) + prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2; + prev_eff_load *= capacity_of(this_cpu); return this_eff_load <= prev_eff_load; } @@ -5449,22 +5420,13 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int prev_cpu, int sync) { int this_cpu = smp_processor_id(); - bool affine; + bool affine = false; - /* - * Default to no affine wakeups; wake_affine() should not effect a task - * placement the load-balancer feels inclined to undo. The conservative - * option is therefore to not move tasks when they wake up. - */ - affine = false; + if (sched_feat(WA_IDLE) && !affine) + affine = wake_affine_idle(sd, p, this_cpu, prev_cpu, sync); - /* - * If the wakeup is across cache domains, try to evaluate if movement - * makes sense, otherwise rely on select_idle_siblings() to do - * placement inside the cache domain. - */ - if (!cpus_share_cache(prev_cpu, this_cpu)) - affine = wake_affine_llc(sd, p, this_cpu, prev_cpu, sync); + if (sched_feat(WA_WEIGHT) && !affine) + affine = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync); schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts); if (affine) { @@ -7600,7 +7562,6 @@ static inline enum fbq_type fbq_classify_rq(struct rq *rq) */ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds) { - struct sched_domain_shared *shared = env->sd->shared; struct sched_domain *child = env->sd->child; struct sched_group *sg = env->sd->groups; struct sg_lb_stats *local = &sds->local_stat; @@ -7672,22 +7633,6 @@ next_group: if (env->dst_rq->rd->overload != overload) env->dst_rq->rd->overload = overload; } - - if (!shared) - return; - - /* - * Since these are sums over groups they can contain some CPUs - * multiple times for the NUMA domains. - * - * Currently only wake_affine_llc() and find_busiest_group() - * uses these numbers, only the last is affected by this problem. - * - * XXX fix that. - */ - WRITE_ONCE(shared->nr_running, sds->total_running); - WRITE_ONCE(shared->load, sds->total_load); - WRITE_ONCE(shared->capacity, sds->total_capacity); } /** @@ -8098,6 +8043,13 @@ static int should_we_balance(struct lb_env *env) int cpu, balance_cpu = -1; /* + * Ensure the balancing environment is consistent; can happen + * when the softirq triggers 'during' hotplug. + */ + if (!cpumask_test_cpu(env->dst_cpu, env->cpus)) + return 0; + + /* * In the newly idle case, we will allow all the cpu's * to do the newly idle load balance. */ diff --git a/kernel/sched/features.h b/kernel/sched/features.h index d3fb15555291..319ed0e8a347 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -81,3 +81,6 @@ SCHED_FEAT(RT_RUNTIME_SHARE, true) SCHED_FEAT(LB_MIN, false) SCHED_FEAT(ATTACH_AGE_LOAD, true) +SCHED_FEAT(WA_IDLE, true) +SCHED_FEAT(WA_WEIGHT, true) +SCHED_FEAT(WA_BIAS, true) diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index a92fddc22747..dd7908743dab 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -18,6 +18,7 @@ #include <linux/membarrier.h> #include <linux/tick.h> #include <linux/cpumask.h> +#include <linux/atomic.h> #include "sched.h" /* for cpu_rq(). */ @@ -26,21 +27,26 @@ * except MEMBARRIER_CMD_QUERY. */ #define MEMBARRIER_CMD_BITMASK \ - (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED) + (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED \ + | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED) static void ipi_mb(void *info) { smp_mb(); /* IPIs should be serializing but paranoid. */ } -static void membarrier_private_expedited(void) +static int membarrier_private_expedited(void) { int cpu; bool fallback = false; cpumask_var_t tmpmask; + if (!(atomic_read(¤t->mm->membarrier_state) + & MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY)) + return -EPERM; + if (num_online_cpus() == 1) - return; + return 0; /* * Matches memory barriers around rq->curr modification in @@ -94,6 +100,24 @@ static void membarrier_private_expedited(void) * rq->curr modification in scheduler. */ smp_mb(); /* exit from system call is not a mb */ + return 0; +} + +static void membarrier_register_private_expedited(void) +{ + struct task_struct *p = current; + struct mm_struct *mm = p->mm; + + /* + * We need to consider threads belonging to different thread + * groups, which use the same mm. (CLONE_VM but not + * CLONE_THREAD). + */ + if (atomic_read(&mm->membarrier_state) + & MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY) + return; + atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY, + &mm->membarrier_state); } /** @@ -144,7 +168,9 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags) synchronize_sched(); return 0; case MEMBARRIER_CMD_PRIVATE_EXPEDITED: - membarrier_private_expedited(); + return membarrier_private_expedited(); + case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED: + membarrier_register_private_expedited(); return 0; default: return -EINVAL; diff --git a/kernel/seccomp.c b/kernel/seccomp.c index bb3a38005b9c..0ae832e13b97 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -473,7 +473,7 @@ static long seccomp_attach_filter(unsigned int flags, return 0; } -void __get_seccomp_filter(struct seccomp_filter *filter) +static void __get_seccomp_filter(struct seccomp_filter *filter) { /* Reference count is bounded by the number of total processes. */ refcount_inc(&filter->usage); diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 1d71c051a951..5043e7433f4b 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -344,39 +344,30 @@ EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); * by the client, but only by calling this function. * This function can only be called on a registered smp_hotplug_thread. */ -int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *new) +void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, + const struct cpumask *new) { struct cpumask *old = plug_thread->cpumask; - cpumask_var_t tmp; + static struct cpumask tmp; unsigned int cpu; - if (!alloc_cpumask_var(&tmp, GFP_KERNEL)) - return -ENOMEM; - - get_online_cpus(); + lockdep_assert_cpus_held(); mutex_lock(&smpboot_threads_lock); /* Park threads that were exclusively enabled on the old mask. */ - cpumask_andnot(tmp, old, new); - for_each_cpu_and(cpu, tmp, cpu_online_mask) + cpumask_andnot(&tmp, old, new); + for_each_cpu_and(cpu, &tmp, cpu_online_mask) smpboot_park_thread(plug_thread, cpu); /* Unpark threads that are exclusively enabled on the new mask. */ - cpumask_andnot(tmp, new, old); - for_each_cpu_and(cpu, tmp, cpu_online_mask) + cpumask_andnot(&tmp, new, old); + for_each_cpu_and(cpu, &tmp, cpu_online_mask) smpboot_unpark_thread(plug_thread, cpu); cpumask_copy(old, new); mutex_unlock(&smpboot_threads_lock); - put_online_cpus(); - - free_cpumask_var(tmp); - - return 0; } -EXPORT_SYMBOL_GPL(smpboot_update_cpumask_percpu_thread); static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 423554ad3610..d9c31bc2eaea 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -872,9 +872,9 @@ static struct ctl_table kern_table[] = { #if defined(CONFIG_LOCKUP_DETECTOR) { .procname = "watchdog", - .data = &watchdog_user_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = proc_watchdog, .extra1 = &zero, .extra2 = &one, @@ -890,16 +890,12 @@ static struct ctl_table kern_table[] = { }, { .procname = "nmi_watchdog", - .data = &nmi_watchdog_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &nmi_watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = NMI_WATCHDOG_SYSCTL_PERM, .proc_handler = proc_nmi_watchdog, .extra1 = &zero, -#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) .extra2 = &one, -#else - .extra2 = &zero, -#endif }, { .procname = "watchdog_cpumask", @@ -911,9 +907,9 @@ static struct ctl_table kern_table[] = { #ifdef CONFIG_SOFTLOCKUP_DETECTOR { .procname = "soft_watchdog", - .data = &soft_watchdog_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &soft_watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = proc_soft_watchdog, .extra1 = &zero, .extra2 = &one, @@ -2188,8 +2184,6 @@ static int do_proc_douintvec_conv(unsigned long *lvalp, if (write) { if (*lvalp > UINT_MAX) return -EINVAL; - if (*lvalp > UINT_MAX) - return -EINVAL; *valp = *lvalp; } else { unsigned int val = *valp; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6abfafd7f173..8319e09e15b9 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4954,9 +4954,6 @@ static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata; static char ftrace_graph_notrace_buf[FTRACE_FILTER_SIZE] __initdata; static int ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer); -static unsigned long save_global_trampoline; -static unsigned long save_global_flags; - static int __init set_graph_function(char *str) { strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE); @@ -6808,17 +6805,6 @@ void unregister_ftrace_graph(void) unregister_pm_notifier(&ftrace_suspend_notifier); unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); -#ifdef CONFIG_DYNAMIC_FTRACE - /* - * Function graph does not allocate the trampoline, but - * other global_ops do. We need to reset the ALLOC_TRAMP flag - * if one was used. - */ - global_ops.trampoline = save_global_trampoline; - if (save_global_flags & FTRACE_OPS_FL_ALLOC_TRAMP) - global_ops.flags |= FTRACE_OPS_FL_ALLOC_TRAMP; -#endif - out: mutex_unlock(&ftrace_lock); } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index f5d52024f6b7..6bcb854909c0 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -29,20 +29,29 @@ #include <linux/kvm_para.h> #include <linux/kthread.h> -/* Watchdog configuration */ -static DEFINE_MUTEX(watchdog_proc_mutex); - -int __read_mostly nmi_watchdog_enabled; +static DEFINE_MUTEX(watchdog_mutex); #if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG) -unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED | - NMI_WATCHDOG_ENABLED; +# define WATCHDOG_DEFAULT (SOFT_WATCHDOG_ENABLED | NMI_WATCHDOG_ENABLED) +# define NMI_WATCHDOG_DEFAULT 1 #else -unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED; +# define WATCHDOG_DEFAULT (SOFT_WATCHDOG_ENABLED) +# define NMI_WATCHDOG_DEFAULT 0 #endif +unsigned long __read_mostly watchdog_enabled; +int __read_mostly watchdog_user_enabled = 1; +int __read_mostly nmi_watchdog_user_enabled = NMI_WATCHDOG_DEFAULT; +int __read_mostly soft_watchdog_user_enabled = 1; +int __read_mostly watchdog_thresh = 10; +int __read_mostly nmi_watchdog_available; + +struct cpumask watchdog_allowed_mask __read_mostly; + +struct cpumask watchdog_cpumask __read_mostly; +unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); + #ifdef CONFIG_HARDLOCKUP_DETECTOR -/* boot commands */ /* * Should we panic when a soft-lockup or hard-lockup occurs: */ @@ -56,9 +65,9 @@ unsigned int __read_mostly hardlockup_panic = * kernel command line parameters are parsed, because otherwise it is not * possible to override this in hardlockup_panic_setup(). */ -void hardlockup_detector_disable(void) +void __init hardlockup_detector_disable(void) { - watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + nmi_watchdog_user_enabled = 0; } static int __init hardlockup_panic_setup(char *str) @@ -68,48 +77,24 @@ static int __init hardlockup_panic_setup(char *str) else if (!strncmp(str, "nopanic", 7)) hardlockup_panic = 0; else if (!strncmp(str, "0", 1)) - watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + nmi_watchdog_user_enabled = 0; else if (!strncmp(str, "1", 1)) - watchdog_enabled |= NMI_WATCHDOG_ENABLED; + nmi_watchdog_user_enabled = 1; return 1; } __setup("nmi_watchdog=", hardlockup_panic_setup); -#endif - -#ifdef CONFIG_SOFTLOCKUP_DETECTOR -int __read_mostly soft_watchdog_enabled; -#endif - -int __read_mostly watchdog_user_enabled; -int __read_mostly watchdog_thresh = 10; - -#ifdef CONFIG_SMP -int __read_mostly sysctl_softlockup_all_cpu_backtrace; +# ifdef CONFIG_SMP int __read_mostly sysctl_hardlockup_all_cpu_backtrace; -#endif -struct cpumask watchdog_cpumask __read_mostly; -unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); -/* - * The 'watchdog_running' variable is set to 1 when the watchdog threads - * are registered/started and is set to 0 when the watchdog threads are - * unregistered/stopped, so it is an indicator whether the threads exist. - */ -static int __read_mostly watchdog_running; -/* - * If a subsystem has a need to deactivate the watchdog temporarily, it - * can use the suspend/resume interface to achieve this. The content of - * the 'watchdog_suspended' variable reflects this state. Existing threads - * are parked/unparked by the lockup_detector_{suspend|resume} functions - * (see comment blocks pertaining to those functions for further details). - * - * 'watchdog_suspended' also prevents threads from being registered/started - * or unregistered/stopped via parameters in /proc/sys/kernel, so the state - * of 'watchdog_running' cannot change while the watchdog is deactivated - * temporarily (see related code in 'proc' handlers). - */ -int __read_mostly watchdog_suspended; +static int __init hardlockup_all_cpu_backtrace_setup(char *str) +{ + sysctl_hardlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0); + return 1; +} +__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); +# endif /* CONFIG_SMP */ +#endif /* CONFIG_HARDLOCKUP_DETECTOR */ /* * These functions can be overridden if an architecture implements its @@ -121,36 +106,68 @@ int __read_mostly watchdog_suspended; */ int __weak watchdog_nmi_enable(unsigned int cpu) { + hardlockup_detector_perf_enable(); return 0; } + void __weak watchdog_nmi_disable(unsigned int cpu) { + hardlockup_detector_perf_disable(); } -/* - * watchdog_nmi_reconfigure can be implemented to be notified after any - * watchdog configuration change. The arch hardlockup watchdog should - * respond to the following variables: - * - nmi_watchdog_enabled +/* Return 0, if a NMI watchdog is available. Error code otherwise */ +int __weak __init watchdog_nmi_probe(void) +{ + return hardlockup_detector_perf_init(); +} + +/** + * watchdog_nmi_stop - Stop the watchdog for reconfiguration + * + * The reconfiguration steps are: + * watchdog_nmi_stop(); + * update_variables(); + * watchdog_nmi_start(); + */ +void __weak watchdog_nmi_stop(void) { } + +/** + * watchdog_nmi_start - Start the watchdog after reconfiguration + * + * Counterpart to watchdog_nmi_stop(). + * + * The following variables have been updated in update_variables() and + * contain the currently valid configuration: + * - watchdog_enabled * - watchdog_thresh * - watchdog_cpumask - * - sysctl_hardlockup_all_cpu_backtrace - * - hardlockup_panic - * - watchdog_suspended */ -void __weak watchdog_nmi_reconfigure(void) +void __weak watchdog_nmi_start(void) { } + +/** + * lockup_detector_update_enable - Update the sysctl enable bit + * + * Caller needs to make sure that the NMI/perf watchdogs are off, so this + * can't race with watchdog_nmi_disable(). + */ +static void lockup_detector_update_enable(void) { + watchdog_enabled = 0; + if (!watchdog_user_enabled) + return; + if (nmi_watchdog_available && nmi_watchdog_user_enabled) + watchdog_enabled |= NMI_WATCHDOG_ENABLED; + if (soft_watchdog_user_enabled) + watchdog_enabled |= SOFT_WATCHDOG_ENABLED; } - #ifdef CONFIG_SOFTLOCKUP_DETECTOR -/* Helper for online, unparked cpus. */ -#define for_each_watchdog_cpu(cpu) \ - for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask) - -atomic_t watchdog_park_in_progress = ATOMIC_INIT(0); +/* Global variables, exported for sysctl */ +unsigned int __read_mostly softlockup_panic = + CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; +static bool softlockup_threads_initialized __read_mostly; static u64 __read_mostly sample_period; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); @@ -164,50 +181,40 @@ static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); static unsigned long soft_lockup_nmi_warn; -unsigned int __read_mostly softlockup_panic = - CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; - static int __init softlockup_panic_setup(char *str) { softlockup_panic = simple_strtoul(str, NULL, 0); - return 1; } __setup("softlockup_panic=", softlockup_panic_setup); static int __init nowatchdog_setup(char *str) { - watchdog_enabled = 0; + watchdog_user_enabled = 0; return 1; } __setup("nowatchdog", nowatchdog_setup); static int __init nosoftlockup_setup(char *str) { - watchdog_enabled &= ~SOFT_WATCHDOG_ENABLED; + soft_watchdog_user_enabled = 0; return 1; } __setup("nosoftlockup", nosoftlockup_setup); #ifdef CONFIG_SMP +int __read_mostly sysctl_softlockup_all_cpu_backtrace; + static int __init softlockup_all_cpu_backtrace_setup(char *str) { - sysctl_softlockup_all_cpu_backtrace = - !!simple_strtol(str, NULL, 0); + sysctl_softlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0); return 1; } __setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup); -#ifdef CONFIG_HARDLOCKUP_DETECTOR -static int __init hardlockup_all_cpu_backtrace_setup(char *str) -{ - sysctl_hardlockup_all_cpu_backtrace = - !!simple_strtol(str, NULL, 0); - return 1; -} -__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); -#endif #endif +static void __lockup_detector_cleanup(void); + /* * Hard-lockup warnings should be triggered after just a few seconds. Soft- * lockups can have false positives under extreme conditions. So we generally @@ -278,11 +285,15 @@ void touch_all_softlockup_watchdogs(void) int cpu; /* - * this is done lockless - * do we care if a 0 races with a timestamp? - * all it means is the softlock check starts one cycle later + * watchdog_mutex cannpt be taken here, as this might be called + * from (soft)interrupt context, so the access to + * watchdog_allowed_cpumask might race with a concurrent update. + * + * The watchdog time stamp can race against a concurrent real + * update as well, the only side effect might be a cycle delay for + * the softlockup check. */ - for_each_watchdog_cpu(cpu) + for_each_cpu(cpu, &watchdog_allowed_mask) per_cpu(watchdog_touch_ts, cpu) = 0; wq_watchdog_touch(-1); } @@ -322,9 +333,6 @@ static void watchdog_interrupt_count(void) __this_cpu_inc(hrtimer_interrupts); } -static int watchdog_enable_all_cpus(void); -static void watchdog_disable_all_cpus(void); - /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { @@ -333,7 +341,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; - if (atomic_read(&watchdog_park_in_progress) != 0) + if (!watchdog_enabled) return HRTIMER_NORESTART; /* kick the hardlockup detector */ @@ -447,32 +455,38 @@ static void watchdog_set_prio(unsigned int policy, unsigned int prio) static void watchdog_enable(unsigned int cpu) { - struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); - /* kick off the timer for the hardlockup detector */ + /* + * Start the timer first to prevent the NMI watchdog triggering + * before the timer has a chance to fire. + */ hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer->function = watchdog_timer_fn; - - /* Enable the perf event */ - watchdog_nmi_enable(cpu); - - /* done here because hrtimer_start can only pin to smp_processor_id() */ hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL_PINNED); - /* initialize timestamp */ - watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); + /* Initialize timestamp */ __touch_watchdog(); + /* Enable the perf event */ + if (watchdog_enabled & NMI_WATCHDOG_ENABLED) + watchdog_nmi_enable(cpu); + + watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); } static void watchdog_disable(unsigned int cpu) { - struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); watchdog_set_prio(SCHED_NORMAL, 0); - hrtimer_cancel(hrtimer); - /* disable the perf event */ + /* + * Disable the perf event first. That prevents that a large delay + * between disabling the timer and disabling the perf event causes + * the perf NMI to detect a false positive. + */ watchdog_nmi_disable(cpu); + hrtimer_cancel(hrtimer); } static void watchdog_cleanup(unsigned int cpu, bool online) @@ -499,21 +513,6 @@ static void watchdog(unsigned int cpu) __this_cpu_write(soft_lockup_hrtimer_cnt, __this_cpu_read(hrtimer_interrupts)); __touch_watchdog(); - - /* - * watchdog_nmi_enable() clears the NMI_WATCHDOG_ENABLED bit in the - * failure path. Check for failures that can occur asynchronously - - * for example, when CPUs are on-lined - and shut down the hardware - * perf event on each CPU accordingly. - * - * The only non-obvious place this bit can be cleared is through - * watchdog_nmi_enable(), so a pr_info() is placed there. Placing a - * pr_info here would be too noisy as it would result in a message - * every few seconds if the hardlockup was disabled but the softlockup - * enabled. - */ - if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) - watchdog_nmi_disable(cpu); } static struct smp_hotplug_thread watchdog_threads = { @@ -527,295 +526,174 @@ static struct smp_hotplug_thread watchdog_threads = { .unpark = watchdog_enable, }; -/* - * park all watchdog threads that are specified in 'watchdog_cpumask' - * - * This function returns an error if kthread_park() of a watchdog thread - * fails. In this situation, the watchdog threads of some CPUs can already - * be parked and the watchdog threads of other CPUs can still be runnable. - * Callers are expected to handle this special condition as appropriate in - * their context. - * - * This function may only be called in a context that is protected against - * races with CPU hotplug - for example, via get_online_cpus(). - */ -static int watchdog_park_threads(void) +static void softlockup_update_smpboot_threads(void) { - int cpu, ret = 0; + lockdep_assert_held(&watchdog_mutex); - atomic_set(&watchdog_park_in_progress, 1); + if (!softlockup_threads_initialized) + return; - for_each_watchdog_cpu(cpu) { - ret = kthread_park(per_cpu(softlockup_watchdog, cpu)); - if (ret) - break; - } - - atomic_set(&watchdog_park_in_progress, 0); - - return ret; + smpboot_update_cpumask_percpu_thread(&watchdog_threads, + &watchdog_allowed_mask); } -/* - * unpark all watchdog threads that are specified in 'watchdog_cpumask' - * - * This function may only be called in a context that is protected against - * races with CPU hotplug - for example, via get_online_cpus(). - */ -static void watchdog_unpark_threads(void) +/* Temporarily park all watchdog threads */ +static void softlockup_park_all_threads(void) { - int cpu; - - for_each_watchdog_cpu(cpu) - kthread_unpark(per_cpu(softlockup_watchdog, cpu)); + cpumask_clear(&watchdog_allowed_mask); + softlockup_update_smpboot_threads(); } -static int update_watchdog_all_cpus(void) +/* Unpark enabled threads */ +static void softlockup_unpark_threads(void) { - int ret; - - ret = watchdog_park_threads(); - if (ret) - return ret; - - watchdog_unpark_threads(); - - return 0; + cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); + softlockup_update_smpboot_threads(); } -static int watchdog_enable_all_cpus(void) +static void lockup_detector_reconfigure(void) { - int err = 0; - - if (!watchdog_running) { - err = smpboot_register_percpu_thread_cpumask(&watchdog_threads, - &watchdog_cpumask); - if (err) - pr_err("Failed to create watchdog threads, disabled\n"); - else - watchdog_running = 1; - } else { - /* - * Enable/disable the lockup detectors or - * change the sample period 'on the fly'. - */ - err = update_watchdog_all_cpus(); - - if (err) { - watchdog_disable_all_cpus(); - pr_err("Failed to update lockup detectors, disabled\n"); - } - } - - if (err) - watchdog_enabled = 0; - - return err; + cpus_read_lock(); + watchdog_nmi_stop(); + softlockup_park_all_threads(); + set_sample_period(); + lockup_detector_update_enable(); + if (watchdog_enabled && watchdog_thresh) + softlockup_unpark_threads(); + watchdog_nmi_start(); + cpus_read_unlock(); + /* + * Must be called outside the cpus locked section to prevent + * recursive locking in the perf code. + */ + __lockup_detector_cleanup(); } -static void watchdog_disable_all_cpus(void) +/* + * Create the watchdog thread infrastructure and configure the detector(s). + * + * The threads are not unparked as watchdog_allowed_mask is empty. When + * the threads are sucessfully initialized, take the proper locks and + * unpark the threads in the watchdog_cpumask if the watchdog is enabled. + */ +static __init void lockup_detector_setup(void) { - if (watchdog_running) { - watchdog_running = 0; - smpboot_unregister_percpu_thread(&watchdog_threads); - } -} + int ret; -#ifdef CONFIG_SYSCTL -static int watchdog_update_cpus(void) -{ - return smpboot_update_cpumask_percpu_thread( - &watchdog_threads, &watchdog_cpumask); -} -#endif + /* + * If sysctl is off and watchdog got disabled on the command line, + * nothing to do here. + */ + lockup_detector_update_enable(); -#else /* SOFTLOCKUP */ -static int watchdog_park_threads(void) -{ - return 0; -} + if (!IS_ENABLED(CONFIG_SYSCTL) && + !(watchdog_enabled && watchdog_thresh)) + return; -static void watchdog_unpark_threads(void) -{ -} + ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads, + &watchdog_allowed_mask); + if (ret) { + pr_err("Failed to initialize soft lockup detector threads\n"); + return; + } -static int watchdog_enable_all_cpus(void) -{ - return 0; + mutex_lock(&watchdog_mutex); + softlockup_threads_initialized = true; + lockup_detector_reconfigure(); + mutex_unlock(&watchdog_mutex); } -static void watchdog_disable_all_cpus(void) +#else /* CONFIG_SOFTLOCKUP_DETECTOR */ +static inline int watchdog_park_threads(void) { return 0; } +static inline void watchdog_unpark_threads(void) { } +static inline int watchdog_enable_all_cpus(void) { return 0; } +static inline void watchdog_disable_all_cpus(void) { } +static void lockup_detector_reconfigure(void) { + cpus_read_lock(); + watchdog_nmi_stop(); + lockup_detector_update_enable(); + watchdog_nmi_start(); + cpus_read_unlock(); } - -#ifdef CONFIG_SYSCTL -static int watchdog_update_cpus(void) +static inline void lockup_detector_setup(void) { - return 0; + lockup_detector_reconfigure(); } -#endif +#endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ -static void set_sample_period(void) +static void __lockup_detector_cleanup(void) { + lockdep_assert_held(&watchdog_mutex); + hardlockup_detector_perf_cleanup(); } -#endif /* SOFTLOCKUP */ -/* - * Suspend the hard and soft lockup detector by parking the watchdog threads. +/** + * lockup_detector_cleanup - Cleanup after cpu hotplug or sysctl changes + * + * Caller must not hold the cpu hotplug rwsem. */ -int lockup_detector_suspend(void) +void lockup_detector_cleanup(void) { - int ret = 0; - - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); - /* - * Multiple suspend requests can be active in parallel (counted by - * the 'watchdog_suspended' variable). If the watchdog threads are - * running, the first caller takes care that they will be parked. - * The state of 'watchdog_running' cannot change while a suspend - * request is active (see related code in 'proc' handlers). - */ - if (watchdog_running && !watchdog_suspended) - ret = watchdog_park_threads(); - - if (ret == 0) - watchdog_suspended++; - else { - watchdog_disable_all_cpus(); - pr_err("Failed to suspend lockup detectors, disabled\n"); - watchdog_enabled = 0; - } - - watchdog_nmi_reconfigure(); - - mutex_unlock(&watchdog_proc_mutex); - - return ret; + mutex_lock(&watchdog_mutex); + __lockup_detector_cleanup(); + mutex_unlock(&watchdog_mutex); } -/* - * Resume the hard and soft lockup detector by unparking the watchdog threads. +/** + * lockup_detector_soft_poweroff - Interface to stop lockup detector(s) + * + * Special interface for parisc. It prevents lockup detector warnings from + * the default pm_poweroff() function which busy loops forever. */ -void lockup_detector_resume(void) +void lockup_detector_soft_poweroff(void) { - mutex_lock(&watchdog_proc_mutex); - - watchdog_suspended--; - /* - * The watchdog threads are unparked if they were previously running - * and if there is no more active suspend request. - */ - if (watchdog_running && !watchdog_suspended) - watchdog_unpark_threads(); - - watchdog_nmi_reconfigure(); - - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + watchdog_enabled = 0; } #ifdef CONFIG_SYSCTL -/* - * Update the run state of the lockup detectors. - */ -static int proc_watchdog_update(void) +/* Propagate any changes to the watchdog threads */ +static void proc_watchdog_update(void) { - int err = 0; - - /* - * Watchdog threads won't be started if they are already active. - * The 'watchdog_running' variable in watchdog_*_all_cpus() takes - * care of this. If those threads are already active, the sample - * period will be updated and the lockup detectors will be enabled - * or disabled 'on the fly'. - */ - if (watchdog_enabled && watchdog_thresh) - err = watchdog_enable_all_cpus(); - else - watchdog_disable_all_cpus(); - - watchdog_nmi_reconfigure(); - - return err; - + /* Remove impossible cpus to keep sysctl output clean. */ + cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); + lockup_detector_reconfigure(); } /* * common function for watchdog, nmi_watchdog and soft_watchdog parameter * - * caller | table->data points to | 'which' contains the flag(s) - * -------------------|-----------------------|----------------------------- - * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED or'ed - * | | with SOFT_WATCHDOG_ENABLED - * -------------------|-----------------------|----------------------------- - * proc_nmi_watchdog | nmi_watchdog_enabled | NMI_WATCHDOG_ENABLED - * -------------------|-----------------------|----------------------------- - * proc_soft_watchdog | soft_watchdog_enabled | SOFT_WATCHDOG_ENABLED + * caller | table->data points to | 'which' + * -------------------|----------------------------|-------------------------- + * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED | + * | | SOFT_WATCHDOG_ENABLED + * -------------------|----------------------------|-------------------------- + * proc_nmi_watchdog | nmi_watchdog_user_enabled | NMI_WATCHDOG_ENABLED + * -------------------|----------------------------|-------------------------- + * proc_soft_watchdog | soft_watchdog_user_enabled | SOFT_WATCHDOG_ENABLED */ static int proc_watchdog_common(int which, struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int err, old, new; - int *watchdog_param = (int *)table->data; + int err, old, *param = table->data; - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); + mutex_lock(&watchdog_mutex); - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } - - /* - * If the parameter is being read return the state of the corresponding - * bit(s) in 'watchdog_enabled', else update 'watchdog_enabled' and the - * run state of the lockup detectors. - */ if (!write) { - *watchdog_param = (watchdog_enabled & which) != 0; + /* + * On read synchronize the userspace interface. This is a + * racy snapshot. + */ + *param = (watchdog_enabled & which) != 0; err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); } else { + old = READ_ONCE(*param); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (err) - goto out; - - /* - * There is a race window between fetching the current value - * from 'watchdog_enabled' and storing the new value. During - * this race window, watchdog_nmi_enable() can sneak in and - * clear the NMI_WATCHDOG_ENABLED bit in 'watchdog_enabled'. - * The 'cmpxchg' detects this race and the loop retries. - */ - do { - old = watchdog_enabled; - /* - * If the parameter value is not zero set the - * corresponding bit(s), else clear it(them). - */ - if (*watchdog_param) - new = old | which; - else - new = old & ~which; - } while (cmpxchg(&watchdog_enabled, old, new) != old); - - /* - * Update the run state of the lockup detectors. There is _no_ - * need to check the value returned by proc_watchdog_update() - * and to restore the previous value of 'watchdog_enabled' as - * both lockup detectors are disabled if proc_watchdog_update() - * returns an error. - */ - if (old == new) - goto out; - - err = proc_watchdog_update(); + if (!err && old != READ_ONCE(*param)) + proc_watchdog_update(); } -out: - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + mutex_unlock(&watchdog_mutex); return err; } @@ -835,6 +713,8 @@ int proc_watchdog(struct ctl_table *table, int write, int proc_nmi_watchdog(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + if (!nmi_watchdog_available && write) + return -ENOTSUPP; return proc_watchdog_common(NMI_WATCHDOG_ENABLED, table, write, buffer, lenp, ppos); } @@ -855,39 +735,17 @@ int proc_soft_watchdog(struct ctl_table *table, int write, int proc_watchdog_thresh(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int err, old, new; - - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); + int err, old; - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } + mutex_lock(&watchdog_mutex); - old = ACCESS_ONCE(watchdog_thresh); + old = READ_ONCE(watchdog_thresh); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (err || !write) - goto out; - - /* - * Update the sample period. Restore on failure. - */ - new = ACCESS_ONCE(watchdog_thresh); - if (old == new) - goto out; + if (!err && write && old != READ_ONCE(watchdog_thresh)) + proc_watchdog_update(); - set_sample_period(); - err = proc_watchdog_update(); - if (err) { - watchdog_thresh = old; - set_sample_period(); - } -out: - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + mutex_unlock(&watchdog_mutex); return err; } @@ -902,45 +760,19 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, { int err; - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); - - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } + mutex_lock(&watchdog_mutex); err = proc_do_large_bitmap(table, write, buffer, lenp, ppos); - if (!err && write) { - /* Remove impossible cpus to keep sysctl output cleaner. */ - cpumask_and(&watchdog_cpumask, &watchdog_cpumask, - cpu_possible_mask); - - if (watchdog_running) { - /* - * Failure would be due to being unable to allocate - * a temporary cpumask, so we are likely not in a - * position to do much else to make things better. - */ - if (watchdog_update_cpus() != 0) - pr_err("cpumask update failed\n"); - } + if (!err && write) + proc_watchdog_update(); - watchdog_nmi_reconfigure(); - } -out: - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + mutex_unlock(&watchdog_mutex); return err; } - #endif /* CONFIG_SYSCTL */ void __init lockup_detector_init(void) { - set_sample_period(); - #ifdef CONFIG_NO_HZ_FULL if (tick_nohz_full_enabled()) { pr_info("Disabling watchdog on nohz_full cores by default\n"); @@ -951,6 +783,7 @@ void __init lockup_detector_init(void) cpumask_copy(&watchdog_cpumask, cpu_possible_mask); #endif - if (watchdog_enabled) - watchdog_enable_all_cpus(); + if (!watchdog_nmi_probe()) + nmi_watchdog_available = true; + lockup_detector_setup(); } diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 3a09ea1b1d3d..71a62ceacdc8 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -21,8 +21,10 @@ static DEFINE_PER_CPU(bool, hard_watchdog_warn); static DEFINE_PER_CPU(bool, watchdog_nmi_touch); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); +static struct cpumask dead_events_mask; static unsigned long hardlockup_allcpu_dumped; +static unsigned int watchdog_cpus; void arch_touch_nmi_watchdog(void) { @@ -103,15 +105,12 @@ static struct perf_event_attr wd_hw_attr = { /* Callback function for perf event subsystem */ static void watchdog_overflow_callback(struct perf_event *event, - struct perf_sample_data *data, - struct pt_regs *regs) + struct perf_sample_data *data, + struct pt_regs *regs) { /* Ensure the watchdog never gets throttled */ event->hw.interrupts = 0; - if (atomic_read(&watchdog_park_in_progress) != 0) - return; - if (__this_cpu_read(watchdog_nmi_touch) == true) { __this_cpu_write(watchdog_nmi_touch, false); return; @@ -160,104 +159,131 @@ static void watchdog_overflow_callback(struct perf_event *event, return; } -/* - * People like the simple clean cpu node info on boot. - * Reduce the watchdog noise by only printing messages - * that are different from what cpu0 displayed. - */ -static unsigned long firstcpu_err; -static atomic_t watchdog_cpus; - -int watchdog_nmi_enable(unsigned int cpu) +static int hardlockup_detector_event_create(void) { + unsigned int cpu = smp_processor_id(); struct perf_event_attr *wd_attr; - struct perf_event *event = per_cpu(watchdog_ev, cpu); - int firstcpu = 0; - - /* nothing to do if the hard lockup detector is disabled */ - if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) - goto out; - - /* is it already setup and enabled? */ - if (event && event->state > PERF_EVENT_STATE_OFF) - goto out; - - /* it is setup but not enabled */ - if (event != NULL) - goto out_enable; - - if (atomic_inc_return(&watchdog_cpus) == 1) - firstcpu = 1; + struct perf_event *evt; wd_attr = &wd_hw_attr; wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh); /* Try to register using hardware perf events */ - event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); + evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL, + watchdog_overflow_callback, NULL); + if (IS_ERR(evt)) { + pr_info("Perf event create on CPU %d failed with %ld\n", cpu, + PTR_ERR(evt)); + return PTR_ERR(evt); + } + this_cpu_write(watchdog_ev, evt); + return 0; +} - /* save the first cpu's error for future comparision */ - if (firstcpu && IS_ERR(event)) - firstcpu_err = PTR_ERR(event); +/** + * hardlockup_detector_perf_enable - Enable the local event + */ +void hardlockup_detector_perf_enable(void) +{ + if (hardlockup_detector_event_create()) + return; - if (!IS_ERR(event)) { - /* only print for the first cpu initialized */ - if (firstcpu || firstcpu_err) - pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n"); - goto out_save; - } + if (!watchdog_cpus++) + pr_info("Enabled. Permanently consumes one hw-PMU counter.\n"); - /* - * Disable the hard lockup detector if _any_ CPU fails to set up - * set up the hardware perf event. The watchdog() function checks - * the NMI_WATCHDOG_ENABLED bit periodically. - * - * The barriers are for syncing up watchdog_enabled across all the - * cpus, as clear_bit() does not use barriers. - */ - smp_mb__before_atomic(); - clear_bit(NMI_WATCHDOG_ENABLED_BIT, &watchdog_enabled); - smp_mb__after_atomic(); - - /* skip displaying the same error again */ - if (!firstcpu && (PTR_ERR(event) == firstcpu_err)) - return PTR_ERR(event); - - /* vary the KERN level based on the returned errno */ - if (PTR_ERR(event) == -EOPNOTSUPP) - pr_info("disabled (cpu%i): not supported (no LAPIC?)\n", cpu); - else if (PTR_ERR(event) == -ENOENT) - pr_warn("disabled (cpu%i): hardware events not enabled\n", - cpu); - else - pr_err("disabled (cpu%i): unable to create perf event: %ld\n", - cpu, PTR_ERR(event)); - - pr_info("Shutting down hard lockup detector on all cpus\n"); - - return PTR_ERR(event); - - /* success path */ -out_save: - per_cpu(watchdog_ev, cpu) = event; -out_enable: - perf_event_enable(per_cpu(watchdog_ev, cpu)); -out: - return 0; + perf_event_enable(this_cpu_read(watchdog_ev)); } -void watchdog_nmi_disable(unsigned int cpu) +/** + * hardlockup_detector_perf_disable - Disable the local event + */ +void hardlockup_detector_perf_disable(void) { - struct perf_event *event = per_cpu(watchdog_ev, cpu); + struct perf_event *event = this_cpu_read(watchdog_ev); if (event) { perf_event_disable(event); + cpumask_set_cpu(smp_processor_id(), &dead_events_mask); + watchdog_cpus--; + } +} + +/** + * hardlockup_detector_perf_cleanup - Cleanup disabled events and destroy them + * + * Called from lockup_detector_cleanup(). Serialized by the caller. + */ +void hardlockup_detector_perf_cleanup(void) +{ + int cpu; + + for_each_cpu(cpu, &dead_events_mask) { + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + /* + * Required because for_each_cpu() reports unconditionally + * CPU0 as set on UP kernels. Sigh. + */ + if (event) + perf_event_release_kernel(event); per_cpu(watchdog_ev, cpu) = NULL; + } + cpumask_clear(&dead_events_mask); +} + +/** + * hardlockup_detector_perf_stop - Globally stop watchdog events + * + * Special interface for x86 to handle the perf HT bug. + */ +void __init hardlockup_detector_perf_stop(void) +{ + int cpu; + + lockdep_assert_cpus_held(); + + for_each_online_cpu(cpu) { + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + if (event) + perf_event_disable(event); + } +} - /* should be in cleanup, but blocks oprofile */ - perf_event_release_kernel(event); +/** + * hardlockup_detector_perf_restart - Globally restart watchdog events + * + * Special interface for x86 to handle the perf HT bug. + */ +void __init hardlockup_detector_perf_restart(void) +{ + int cpu; + + lockdep_assert_cpus_held(); + + if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) + return; + + for_each_online_cpu(cpu) { + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + if (event) + perf_event_enable(event); + } +} + +/** + * hardlockup_detector_perf_init - Probe whether NMI event is available at all + */ +int __init hardlockup_detector_perf_init(void) +{ + int ret = hardlockup_detector_event_create(); - /* watchdog_nmi_enable() expects this to be zero initially. */ - if (atomic_dec_and_test(&watchdog_cpus)) - firstcpu_err = 0; + if (ret) { + pr_info("Perf NMI watchdog permanently disabled\n"); + } else { + perf_event_release_kernel(this_cpu_read(watchdog_ev)); + this_cpu_write(watchdog_ev, NULL); } + return ret; } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 64d0edf428f8..a2dccfe1acec 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -68,6 +68,7 @@ enum { * attach_mutex to avoid changing binding state while * worker_attach_to_pool() is in progress. */ + POOL_MANAGER_ACTIVE = 1 << 0, /* being managed */ POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ /* worker flags */ @@ -165,7 +166,6 @@ struct worker_pool { /* L: hash of busy workers */ /* see manage_workers() for details on the two manager mutexes */ - struct mutex manager_arb; /* manager arbitration */ struct worker *manager; /* L: purely informational */ struct mutex attach_mutex; /* attach/detach exclusion */ struct list_head workers; /* A: attached workers */ @@ -299,6 +299,7 @@ static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf; static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */ static DEFINE_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ +static DECLARE_WAIT_QUEUE_HEAD(wq_manager_wait); /* wait for manager to go away */ static LIST_HEAD(workqueues); /* PR: list of all workqueues */ static bool workqueue_freezing; /* PL: have wqs started freezing? */ @@ -801,7 +802,7 @@ static bool need_to_create_worker(struct worker_pool *pool) /* Do we have too many workers and should some go away? */ static bool too_many_workers(struct worker_pool *pool) { - bool managing = mutex_is_locked(&pool->manager_arb); + bool managing = pool->flags & POOL_MANAGER_ACTIVE; int nr_idle = pool->nr_idle + managing; /* manager is considered idle */ int nr_busy = pool->nr_workers - nr_idle; @@ -1980,24 +1981,17 @@ static bool manage_workers(struct worker *worker) { struct worker_pool *pool = worker->pool; - /* - * Anyone who successfully grabs manager_arb wins the arbitration - * and becomes the manager. mutex_trylock() on pool->manager_arb - * failure while holding pool->lock reliably indicates that someone - * else is managing the pool and the worker which failed trylock - * can proceed to executing work items. This means that anyone - * grabbing manager_arb is responsible for actually performing - * manager duties. If manager_arb is grabbed and released without - * actual management, the pool may stall indefinitely. - */ - if (!mutex_trylock(&pool->manager_arb)) + if (pool->flags & POOL_MANAGER_ACTIVE) return false; + + pool->flags |= POOL_MANAGER_ACTIVE; pool->manager = worker; maybe_create_worker(pool); pool->manager = NULL; - mutex_unlock(&pool->manager_arb); + pool->flags &= ~POOL_MANAGER_ACTIVE; + wake_up(&wq_manager_wait); return true; } @@ -3248,7 +3242,6 @@ static int init_worker_pool(struct worker_pool *pool) setup_timer(&pool->mayday_timer, pool_mayday_timeout, (unsigned long)pool); - mutex_init(&pool->manager_arb); mutex_init(&pool->attach_mutex); INIT_LIST_HEAD(&pool->workers); @@ -3318,13 +3311,15 @@ static void put_unbound_pool(struct worker_pool *pool) hash_del(&pool->hash_node); /* - * Become the manager and destroy all workers. Grabbing - * manager_arb prevents @pool's workers from blocking on - * attach_mutex. + * Become the manager and destroy all workers. This prevents + * @pool's workers from blocking on attach_mutex. We're the last + * manager and @pool gets freed with the flag set. */ - mutex_lock(&pool->manager_arb); - spin_lock_irq(&pool->lock); + wait_event_lock_irq(wq_manager_wait, + !(pool->flags & POOL_MANAGER_ACTIVE), pool->lock); + pool->flags |= POOL_MANAGER_ACTIVE; + while ((worker = first_idle_worker(pool))) destroy_worker(worker); WARN_ON(pool->nr_workers || pool->nr_idle); @@ -3338,8 +3333,6 @@ static void put_unbound_pool(struct worker_pool *pool) if (pool->detach_completion) wait_for_completion(pool->detach_completion); - mutex_unlock(&pool->manager_arb); - /* shut down the timers */ del_timer_sync(&pool->idle_timer); del_timer_sync(&pool->mayday_timer); |