diff options
Diffstat (limited to 'kernel')
98 files changed, 5378 insertions, 2592 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index ef0d95a190b4..25f9d83d1bbf 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -64,6 +64,7 @@ obj-$(CONFIG_CRASH_CORE) += crash_core.o obj-$(CONFIG_KEXEC_CORE) += kexec_core.o obj-$(CONFIG_KEXEC) += kexec.o obj-$(CONFIG_KEXEC_FILE) += kexec_file.o +obj-$(CONFIG_KEXEC_ELF) += kexec_elf.o obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o obj-$(CONFIG_COMPAT) += compat.o obj-$(CONFIG_CGROUPS) += cgroup/ @@ -126,7 +127,7 @@ $(obj)/config_data.gz: $(KCONFIG_CONFIG) FORCE $(obj)/kheaders.o: $(obj)/kheaders_data.tar.xz quiet_cmd_genikh = CHK $(obj)/kheaders_data.tar.xz -cmd_genikh = $(CONFIG_SHELL) $(srctree)/kernel/gen_kheaders.sh $@ + cmd_genikh = $(BASH) $(srctree)/kernel/gen_kheaders.sh $@ $(obj)/kheaders_data.tar.xz: FORCE $(call cmd,genikh) diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 29d781061cd5..e1d9adb212f9 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -22,3 +22,6 @@ obj-$(CONFIG_CGROUP_BPF) += cgroup.o ifeq ($(CONFIG_INET),y) obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o endif +ifeq ($(CONFIG_SYSFS),y) +obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o +endif diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 5fcc7a17eb5a..adb3adcebe3c 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -195,8 +195,8 @@ i < btf_type_vlen(struct_type); \ i++, member++) -static DEFINE_IDR(btf_idr); -static DEFINE_SPINLOCK(btf_idr_lock); +DEFINE_IDR(btf_idr); +DEFINE_SPINLOCK(btf_idr_lock); struct btf { void *data; @@ -3376,6 +3376,15 @@ void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, btf_type_ops(t)->seq_show(btf, t, type_id, obj, 0, m); } +#ifdef CONFIG_PROC_FS +static void bpf_btf_show_fdinfo(struct seq_file *m, struct file *filp) +{ + const struct btf *btf = filp->private_data; + + seq_printf(m, "btf_id:\t%u\n", btf->id); +} +#endif + static int btf_release(struct inode *inode, struct file *filp) { btf_put(filp->private_data); @@ -3383,6 +3392,9 @@ static int btf_release(struct inode *inode, struct file *filp) } const struct file_operations btf_fops = { +#ifdef CONFIG_PROC_FS + .show_fdinfo = bpf_btf_show_fdinfo, +#endif .release = btf_release, }; diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 0a00eaca6fae..ddd8addcdb5c 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -964,7 +964,6 @@ static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen) return -ENOMEM; ctx->optval_end = ctx->optval + max_optlen; - ctx->optlen = max_optlen; return 0; } @@ -984,7 +983,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, .level = *level, .optname = *optname, }; - int ret; + int ret, max_optlen; /* Opportunistic check to see whether we have any BPF program * attached to the hook so we don't waste time allocating @@ -994,10 +993,18 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_SETSOCKOPT)) return 0; - ret = sockopt_alloc_buf(&ctx, *optlen); + /* Allocate a bit more than the initial user buffer for + * BPF program. The canonical use case is overriding + * TCP_CONGESTION(nv) to TCP_CONGESTION(cubic). + */ + max_optlen = max_t(int, 16, *optlen); + + ret = sockopt_alloc_buf(&ctx, max_optlen); if (ret) return ret; + ctx.optlen = *optlen; + if (copy_from_user(ctx.optval, optval, *optlen) != 0) { ret = -EFAULT; goto out; @@ -1016,7 +1023,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, if (ctx.optlen == -1) { /* optlen set to -1, bypass kernel */ ret = 1; - } else if (ctx.optlen > *optlen || ctx.optlen < -1) { + } else if (ctx.optlen > max_optlen || ctx.optlen < -1) { /* optlen is out of bounds */ ret = -EFAULT; } else { @@ -1063,6 +1070,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, if (ret) return ret; + ctx.optlen = max_optlen; + if (!retval) { /* If kernel getsockopt finished successfully, * copy whatever was returned to the user back @@ -1325,6 +1334,7 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; + u32 read_size; switch (si->off) { case offsetof(struct bpf_sysctl, write): @@ -1356,7 +1366,9 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type, treg, si->dst_reg, offsetof(struct bpf_sysctl_kern, ppos)); *insn++ = BPF_STX_MEM( - BPF_SIZEOF(u32), treg, si->src_reg, 0); + BPF_SIZEOF(u32), treg, si->src_reg, + bpf_ctx_narrow_access_offset( + 0, sizeof(u32), sizeof(loff_t))); *insn++ = BPF_LDX_MEM( BPF_DW, treg, si->dst_reg, offsetof(struct bpf_sysctl_kern, tmp_reg)); @@ -1365,8 +1377,11 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type, BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos), si->dst_reg, si->src_reg, offsetof(struct bpf_sysctl_kern, ppos)); + read_size = bpf_size_to_bytes(BPF_SIZE(si->code)); *insn++ = BPF_LDX_MEM( - BPF_SIZE(si->code), si->dst_reg, si->dst_reg, 0); + BPF_SIZE(si->code), si->dst_reg, si->dst_reg, + bpf_ctx_narrow_access_offset( + 0, read_size, sizeof(loff_t))); } *target_size = sizeof(u32); break; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 8191a7db2777..66088a9e9b9e 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -890,7 +890,8 @@ int bpf_jit_get_func_addr(const struct bpf_prog *prog, static int bpf_jit_blind_insn(const struct bpf_insn *from, const struct bpf_insn *aux, - struct bpf_insn *to_buff) + struct bpf_insn *to_buff, + bool emit_zext) { struct bpf_insn *to = to_buff; u32 imm_rnd = get_random_int(); @@ -1005,6 +1006,8 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, case 0: /* Part 2 of BPF_LD | BPF_IMM | BPF_DW. */ *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[0].imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); + if (emit_zext) + *to++ = BPF_ZEXT_REG(BPF_REG_AX); *to++ = BPF_ALU64_REG(BPF_OR, aux[0].dst_reg, BPF_REG_AX); break; @@ -1088,7 +1091,8 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) insn[1].code == 0) memcpy(aux, insn, sizeof(aux)); - rewritten = bpf_jit_blind_insn(insn, aux, insn_buff); + rewritten = bpf_jit_blind_insn(insn, aux, insn_buff, + clone->aux->verifier_zext); if (!rewritten) continue; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index d83cf8ccc872..d27f3b60ff6d 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -37,6 +37,12 @@ * notifier hook walks the map we know that new dev references can not be * added by the user because core infrastructure ensures dev_get_by_index() * calls will fail at this point. + * + * The devmap_hash type is a map type which interprets keys as ifindexes and + * indexes these using a hashmap. This allows maps that use ifindex as key to be + * densely packed instead of having holes in the lookup array for unused + * ifindexes. The setup and packet enqueue/send code is shared between the two + * types of devmap; only the lookup and insertion is different. */ #include <linux/bpf.h> #include <net/xdp.h> @@ -59,10 +65,11 @@ struct xdp_bulk_queue { struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ + struct hlist_node index_hlist; struct bpf_dtab *dtab; - unsigned int bit; struct xdp_bulk_queue __percpu *bulkq; struct rcu_head rcu; + unsigned int idx; /* keep track of map index for tracepoint */ }; struct bpf_dtab { @@ -70,33 +77,45 @@ struct bpf_dtab { struct bpf_dtab_netdev **netdev_map; struct list_head __percpu *flush_list; struct list_head list; + + /* these are only used for DEVMAP_HASH type maps */ + struct hlist_head *dev_index_head; + spinlock_t index_lock; + unsigned int items; + u32 n_buckets; }; static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); -static struct bpf_map *dev_map_alloc(union bpf_attr *attr) +static struct hlist_head *dev_map_create_hash(unsigned int entries) +{ + int i; + struct hlist_head *hash; + + hash = kmalloc_array(entries, sizeof(*hash), GFP_KERNEL); + if (hash != NULL) + for (i = 0; i < entries; i++) + INIT_HLIST_HEAD(&hash[i]); + + return hash; +} + +static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) { - struct bpf_dtab *dtab; int err, cpu; 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 & ~DEV_CREATE_FLAG_MASK) - return ERR_PTR(-EINVAL); + return -EINVAL; /* Lookup returns a pointer straight to dev->ifindex, so make sure the * verifier prevents writes from the BPF side */ attr->map_flags |= BPF_F_RDONLY_PROG; - dtab = kzalloc(sizeof(*dtab), GFP_USER); - if (!dtab) - return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&dtab->map, attr); @@ -104,12 +123,18 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); cost += sizeof(struct list_head) * num_possible_cpus(); + if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); + + if (!dtab->n_buckets) /* Overflow check */ + return -EINVAL; + cost += sizeof(struct hlist_head) * dtab->n_buckets; + } + /* if map size is larger than memlock limit, reject it */ err = bpf_map_charge_init(&dtab->map.memory, cost); if (err) - goto free_dtab; - - err = -ENOMEM; + return -EINVAL; dtab->flush_list = alloc_percpu(struct list_head); if (!dtab->flush_list) @@ -124,19 +149,48 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) if (!dtab->netdev_map) goto free_percpu; - spin_lock(&dev_map_lock); - list_add_tail_rcu(&dtab->list, &dev_map_list); - spin_unlock(&dev_map_lock); + if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets); + if (!dtab->dev_index_head) + goto free_map_area; - return &dtab->map; + spin_lock_init(&dtab->index_lock); + } + return 0; + +free_map_area: + bpf_map_area_free(dtab->netdev_map); free_percpu: free_percpu(dtab->flush_list); free_charge: bpf_map_charge_finish(&dtab->map.memory); -free_dtab: - kfree(dtab); - return ERR_PTR(err); + return -ENOMEM; +} + +static struct bpf_map *dev_map_alloc(union bpf_attr *attr) +{ + struct bpf_dtab *dtab; + int err; + + if (!capable(CAP_NET_ADMIN)) + return ERR_PTR(-EPERM); + + dtab = kzalloc(sizeof(*dtab), GFP_USER); + if (!dtab) + return ERR_PTR(-ENOMEM); + + err = dev_map_init_map(dtab, attr); + if (err) { + kfree(dtab); + return ERR_PTR(err); + } + + spin_lock(&dev_map_lock); + list_add_tail_rcu(&dtab->list, &dev_map_list); + spin_unlock(&dev_map_lock); + + return &dtab->map; } static void dev_map_free(struct bpf_map *map) @@ -188,6 +242,7 @@ static void dev_map_free(struct bpf_map *map) free_percpu(dtab->flush_list); bpf_map_area_free(dtab->netdev_map); + kfree(dtab->dev_index_head); kfree(dtab); } @@ -208,6 +263,70 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } +static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, + int idx) +{ + return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)]; +} + +struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct hlist_head *head = dev_map_index_hash(dtab, key); + struct bpf_dtab_netdev *dev; + + hlist_for_each_entry_rcu(dev, head, index_hlist) + if (dev->idx == key) + return dev; + + return NULL; +} + +static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + u32 idx, *next = next_key; + struct bpf_dtab_netdev *dev, *next_dev; + struct hlist_head *head; + int i = 0; + + if (!key) + goto find_first; + + idx = *(u32 *)key; + + dev = __dev_map_hash_lookup_elem(map, idx); + if (!dev) + goto find_first; + + next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&dev->index_hlist)), + struct bpf_dtab_netdev, index_hlist); + + if (next_dev) { + *next = next_dev->idx; + return 0; + } + + i = idx & (dtab->n_buckets - 1); + i++; + + find_first: + for (; i < dtab->n_buckets; i++) { + head = dev_map_index_hash(dtab, i); + + next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), + struct bpf_dtab_netdev, + index_hlist); + if (next_dev) { + *next = next_dev->idx; + return 0; + } + } + + return -ENOENT; +} + static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags, bool in_napi_ctx) { @@ -235,7 +354,7 @@ static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags, out: bq->count = 0; - trace_xdp_devmap_xmit(&obj->dtab->map, obj->bit, + trace_xdp_devmap_xmit(&obj->dtab->map, obj->idx, sent, drops, bq->dev_rx, dev, err); bq->dev_rx = NULL; __list_del_clearprev(&bq->flush_node); @@ -363,6 +482,15 @@ static void *dev_map_lookup_elem(struct bpf_map *map, void *key) return dev ? &dev->ifindex : NULL; } +static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map, + *(u32 *)key); + struct net_device *dev = obj ? obj->dev : NULL; + + return dev ? &dev->ifindex : NULL; +} + static void dev_map_flush_old(struct bpf_dtab_netdev *dev) { if (dev->dev->netdev_ops->ndo_xdp_xmit) { @@ -412,17 +540,74 @@ static int dev_map_delete_elem(struct bpf_map *map, void *key) return 0; } -static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static int dev_map_hash_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); - struct net *net = current->nsproxy->net_ns; + struct bpf_dtab_netdev *old_dev; + int k = *(u32 *)key; + unsigned long flags; + int ret = -ENOENT; + + spin_lock_irqsave(&dtab->index_lock, flags); + + old_dev = __dev_map_hash_lookup_elem(map, k); + if (old_dev) { + dtab->items--; + hlist_del_init_rcu(&old_dev->index_hlist); + call_rcu(&old_dev->rcu, __dev_map_entry_free); + ret = 0; + } + spin_unlock_irqrestore(&dtab->index_lock, flags); + + return ret; +} + +static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, + struct bpf_dtab *dtab, + u32 ifindex, + unsigned int idx) +{ gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN; + struct bpf_dtab_netdev *dev; + struct xdp_bulk_queue *bq; + int cpu; + + dev = kmalloc_node(sizeof(*dev), gfp, dtab->map.numa_node); + if (!dev) + return ERR_PTR(-ENOMEM); + + dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq), + sizeof(void *), gfp); + if (!dev->bulkq) { + kfree(dev); + return ERR_PTR(-ENOMEM); + } + + for_each_possible_cpu(cpu) { + bq = per_cpu_ptr(dev->bulkq, cpu); + bq->obj = dev; + } + + dev->dev = dev_get_by_index(net, ifindex); + if (!dev->dev) { + free_percpu(dev->bulkq); + kfree(dev); + return ERR_PTR(-EINVAL); + } + + dev->idx = idx; + dev->dtab = dtab; + + return dev; +} + +static int __dev_map_update_elem(struct net *net, struct bpf_map *map, + void *key, void *value, u64 map_flags) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; u32 ifindex = *(u32 *)value; - struct xdp_bulk_queue *bq; u32 i = *(u32 *)key; - int cpu; if (unlikely(map_flags > BPF_EXIST)) return -EINVAL; @@ -434,31 +619,9 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, if (!ifindex) { dev = NULL; } else { - dev = kmalloc_node(sizeof(*dev), gfp, map->numa_node); - if (!dev) - return -ENOMEM; - - dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq), - sizeof(void *), gfp); - if (!dev->bulkq) { - kfree(dev); - return -ENOMEM; - } - - for_each_possible_cpu(cpu) { - bq = per_cpu_ptr(dev->bulkq, cpu); - bq->obj = dev; - } - - dev->dev = dev_get_by_index(net, ifindex); - if (!dev->dev) { - free_percpu(dev->bulkq); - kfree(dev); - return -EINVAL; - } - - dev->bit = i; - dev->dtab = dtab; + dev = __dev_map_alloc_node(net, dtab, ifindex, i); + if (IS_ERR(dev)) + return PTR_ERR(dev); } /* Use call_rcu() here to ensure rcu critical sections have completed @@ -472,6 +635,70 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, return 0; } +static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + return __dev_map_update_elem(current->nsproxy->net_ns, + map, key, value, map_flags); +} + +static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, + void *key, void *value, u64 map_flags) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_dtab_netdev *dev, *old_dev; + u32 ifindex = *(u32 *)value; + u32 idx = *(u32 *)key; + unsigned long flags; + int err = -EEXIST; + + if (unlikely(map_flags > BPF_EXIST || !ifindex)) + return -EINVAL; + + spin_lock_irqsave(&dtab->index_lock, flags); + + old_dev = __dev_map_hash_lookup_elem(map, idx); + if (old_dev && (map_flags & BPF_NOEXIST)) + goto out_err; + + dev = __dev_map_alloc_node(net, dtab, ifindex, idx); + if (IS_ERR(dev)) { + err = PTR_ERR(dev); + goto out_err; + } + + if (old_dev) { + hlist_del_rcu(&old_dev->index_hlist); + } else { + if (dtab->items >= dtab->map.max_entries) { + spin_unlock_irqrestore(&dtab->index_lock, flags); + call_rcu(&dev->rcu, __dev_map_entry_free); + return -E2BIG; + } + dtab->items++; + } + + hlist_add_head_rcu(&dev->index_hlist, + dev_map_index_hash(dtab, idx)); + spin_unlock_irqrestore(&dtab->index_lock, flags); + + if (old_dev) + call_rcu(&old_dev->rcu, __dev_map_entry_free); + + return 0; + +out_err: + spin_unlock_irqrestore(&dtab->index_lock, flags); + return err; +} + +static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + return __dev_map_hash_update_elem(current->nsproxy->net_ns, + map, key, value, map_flags); +} + const struct bpf_map_ops dev_map_ops = { .map_alloc = dev_map_alloc, .map_free = dev_map_free, @@ -482,6 +709,16 @@ const struct bpf_map_ops dev_map_ops = { .map_check_btf = map_check_no_btf, }; +const struct bpf_map_ops dev_map_hash_ops = { + .map_alloc = dev_map_alloc, + .map_free = dev_map_free, + .map_get_next_key = dev_map_hash_get_next_key, + .map_lookup_elem = dev_map_hash_lookup_elem, + .map_update_elem = dev_map_hash_update_elem, + .map_delete_elem = dev_map_hash_delete_elem, + .map_check_btf = map_check_no_btf, +}; + static int dev_map_notification(struct notifier_block *notifier, ulong event, void *ptr) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5d141f16f6fa..82eabd4e38ad 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -683,8 +683,8 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd) } /* map_idr_lock should have been held */ -static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map, - bool uref) +static struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, + bool uref) { int refold; @@ -704,6 +704,16 @@ static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map, return map; } +struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map, bool uref) +{ + spin_lock_bh(&map_idr_lock); + map = __bpf_map_inc_not_zero(map, uref); + spin_unlock_bh(&map_idr_lock); + + return map; +} +EXPORT_SYMBOL_GPL(bpf_map_inc_not_zero); + int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) { return -ENOTSUPP; @@ -1619,6 +1629,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | BPF_F_ANY_ALIGNMENT | + BPF_F_TEST_STATE_FREQ | BPF_F_TEST_RND_HI32)) return -EINVAL; @@ -1707,20 +1718,26 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) if (err) goto free_used_maps; - err = bpf_prog_new_fd(prog); - if (err < 0) { - /* failed to allocate fd. - * bpf_prog_put() is needed because the above - * bpf_prog_alloc_id() has published the prog - * to the userspace and the userspace may - * have refcnt-ed it through BPF_PROG_GET_FD_BY_ID. - */ - bpf_prog_put(prog); - return err; - } - + /* Upon success of bpf_prog_alloc_id(), the BPF prog is + * effectively publicly exposed. However, retrieving via + * bpf_prog_get_fd_by_id() will take another reference, + * therefore it cannot be gone underneath us. + * + * Only for the time /after/ successful bpf_prog_new_fd() + * and before returning to userspace, we might just hold + * one reference and any parallel close on that fd could + * rip everything out. Hence, below notifications must + * happen before bpf_prog_new_fd(). + * + * Also, any failure handling from this point onwards must + * be using bpf_prog_put() given the program is exposed. + */ bpf_prog_kallsyms_add(prog); perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0); + + err = bpf_prog_new_fd(prog); + if (err < 0) + bpf_prog_put(prog); return err; free_used_maps: @@ -2177,7 +2194,7 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr) spin_lock_bh(&map_idr_lock); map = idr_find(&map_idr, id); if (map) - map = bpf_map_inc_not_zero(map, true); + map = __bpf_map_inc_not_zero(map, true); else map = ERR_PTR(-ENOENT); spin_unlock_bh(&map_idr_lock); @@ -2874,6 +2891,10 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = bpf_obj_get_next_id(&attr, uattr, &map_idr, &map_idr_lock); break; + case BPF_BTF_GET_NEXT_ID: + err = bpf_obj_get_next_id(&attr, uattr, + &btf_idr, &btf_idr_lock); + break; case BPF_PROG_GET_FD_BY_ID: err = bpf_prog_get_fd_by_id(&attr); break; diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c new file mode 100644 index 000000000000..7ae5dddd1fe6 --- /dev/null +++ b/kernel/bpf/sysfs_btf.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Provide kernel BTF information for introspection and use by eBPF tools. + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/kobject.h> +#include <linux/init.h> +#include <linux/sysfs.h> + +/* See scripts/link-vmlinux.sh, gen_btf() func for details */ +extern char __weak _binary__btf_vmlinux_bin_start[]; +extern char __weak _binary__btf_vmlinux_bin_end[]; + +static ssize_t +btf_vmlinux_read(struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buf, loff_t off, size_t len) +{ + memcpy(buf, _binary__btf_vmlinux_bin_start + off, len); + return len; +} + +static struct bin_attribute bin_attr_btf_vmlinux __ro_after_init = { + .attr = { .name = "vmlinux", .mode = 0444, }, + .read = btf_vmlinux_read, +}; + +static struct kobject *btf_kobj; + +static int __init btf_vmlinux_init(void) +{ + if (!_binary__btf_vmlinux_bin_start) + return 0; + + btf_kobj = kobject_create_and_add("btf", kernel_kobj); + if (!btf_kobj) + return -ENOMEM; + + bin_attr_btf_vmlinux.size = _binary__btf_vmlinux_bin_end - + _binary__btf_vmlinux_bin_start; + + return sysfs_create_bin_file(btf_kobj, &bin_attr_btf_vmlinux); +} + +subsys_initcall(btf_vmlinux_init); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c84d83f86141..ffc3e53f5300 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -985,9 +985,6 @@ static void __mark_reg_unbounded(struct bpf_reg_state *reg) reg->smax_value = S64_MAX; reg->umin_value = 0; reg->umax_value = U64_MAX; - - /* constant backtracking is enabled for root only for now */ - reg->precise = capable(CAP_SYS_ADMIN) ? false : true; } /* Mark a register as having a completely unknown (scalar) value. */ @@ -1014,7 +1011,11 @@ static void mark_reg_unknown(struct bpf_verifier_env *env, __mark_reg_not_init(regs + regno); return; } - __mark_reg_unknown(regs + regno); + regs += regno; + __mark_reg_unknown(regs); + /* constant backtracking is enabled for root without bpf2bpf calls */ + regs->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ? + true : false; } static void __mark_reg_not_init(struct bpf_reg_state *reg) @@ -1771,16 +1772,21 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, bitmap_from_u64(mask, stack_mask); for_each_set_bit(i, mask, 64) { if (i >= func->allocated_stack / BPF_REG_SIZE) { - /* This can happen if backtracking - * is propagating stack precision where - * caller has larger stack frame - * than callee, but backtrack_insn() should - * have returned -ENOTSUPP. + /* the sequence of instructions: + * 2: (bf) r3 = r10 + * 3: (7b) *(u64 *)(r3 -8) = r0 + * 4: (79) r4 = *(u64 *)(r10 -8) + * doesn't contain jmps. It's backtracked + * as a single block. + * During backtracking insn 3 is not recognized as + * stack access, so at the end of backtracking + * stack slot fp-8 is still marked in stack_mask. + * However the parent state may not have accessed + * fp-8 and it's "unallocated" stack space. + * In such case fallback to conservative. */ - verbose(env, "BUG spi %d stack_size %d\n", - i, func->allocated_stack); - WARN_ONCE(1, "verifier backtracking bug"); - return -EFAULT; + mark_all_scalars_precise(env, st); + return 0; } if (func->stack[i].slot_type[0] != STACK_SPILL) { @@ -3457,6 +3463,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, goto error; break; case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: if (func_id != BPF_FUNC_redirect_map && func_id != BPF_FUNC_map_lookup_elem) goto error; @@ -3539,6 +3546,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, break; case BPF_FUNC_redirect_map: if (map->map_type != BPF_MAP_TYPE_DEVMAP && + map->map_type != BPF_MAP_TYPE_DEVMAP_HASH && map->map_type != BPF_MAP_TYPE_CPUMAP && map->map_type != BPF_MAP_TYPE_XSKMAP) goto error; @@ -7220,7 +7228,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) struct bpf_verifier_state_list *sl, **pprev; struct bpf_verifier_state *cur = env->cur_state, *new; int i, j, err, states_cnt = 0; - bool add_new_state = false; + bool add_new_state = env->test_state_freq ? true : false; cur->last_insn_idx = env->prev_insn_idx; if (!env->insn_aux_data[insn_idx].prune_point) @@ -8616,8 +8624,8 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } if (is_narrower_load && size < target_size) { - u8 shift = bpf_ctx_narrow_load_shift(off, size, - size_default); + u8 shift = bpf_ctx_narrow_access_offset( + off, size, size_default) * 8; if (ctx_field_size <= 4) { if (shift) insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH, @@ -9260,6 +9268,9 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, env->allow_ptr_leaks = is_priv; + if (is_priv) + env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; + ret = replace_map_fd_with_map_ptr(env); if (ret < 0) goto skip_full_check; diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c index 9bb96ace9fa1..942c662e2eed 100644 --- a/kernel/bpf/xskmap.c +++ b/kernel/bpf/xskmap.c @@ -13,8 +13,71 @@ struct xsk_map { struct bpf_map map; struct xdp_sock **xsk_map; struct list_head __percpu *flush_list; + spinlock_t lock; /* Synchronize map updates */ }; +int xsk_map_inc(struct xsk_map *map) +{ + struct bpf_map *m = &map->map; + + m = bpf_map_inc(m, false); + return PTR_ERR_OR_ZERO(m); +} + +void xsk_map_put(struct xsk_map *map) +{ + bpf_map_put(&map->map); +} + +static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map, + struct xdp_sock **map_entry) +{ + struct xsk_map_node *node; + int err; + + node = kzalloc(sizeof(*node), GFP_ATOMIC | __GFP_NOWARN); + if (!node) + return NULL; + + err = xsk_map_inc(map); + if (err) { + kfree(node); + return ERR_PTR(err); + } + + node->map = map; + node->map_entry = map_entry; + return node; +} + +static void xsk_map_node_free(struct xsk_map_node *node) +{ + xsk_map_put(node->map); + kfree(node); +} + +static void xsk_map_sock_add(struct xdp_sock *xs, struct xsk_map_node *node) +{ + spin_lock_bh(&xs->map_list_lock); + list_add_tail(&node->node, &xs->map_list); + spin_unlock_bh(&xs->map_list_lock); +} + +static void xsk_map_sock_delete(struct xdp_sock *xs, + struct xdp_sock **map_entry) +{ + struct xsk_map_node *n, *tmp; + + spin_lock_bh(&xs->map_list_lock); + list_for_each_entry_safe(n, tmp, &xs->map_list, node) { + if (map_entry == n->map_entry) { + list_del(&n->node); + xsk_map_node_free(n); + } + } + spin_unlock_bh(&xs->map_list_lock); +} + static struct bpf_map *xsk_map_alloc(union bpf_attr *attr) { struct xsk_map *m; @@ -34,6 +97,7 @@ static struct bpf_map *xsk_map_alloc(union bpf_attr *attr) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&m->map, attr); + spin_lock_init(&m->lock); cost = (u64)m->map.max_entries * sizeof(struct xdp_sock *); cost += sizeof(struct list_head) * num_possible_cpus(); @@ -71,21 +135,9 @@ free_m: static void xsk_map_free(struct bpf_map *map) { struct xsk_map *m = container_of(map, struct xsk_map, map); - int i; bpf_clear_redirect_map(map); synchronize_net(); - - for (i = 0; i < map->max_entries; i++) { - struct xdp_sock *xs; - - xs = m->xsk_map[i]; - if (!xs) - continue; - - sock_put((struct sock *)xs); - } - free_percpu(m->flush_list); bpf_map_area_free(m->xsk_map); kfree(m); @@ -164,8 +216,9 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct xsk_map *m = container_of(map, struct xsk_map, map); + struct xdp_sock *xs, *old_xs, **map_entry; u32 i = *(u32 *)key, fd = *(u32 *)value; - struct xdp_sock *xs, *old_xs; + struct xsk_map_node *node; struct socket *sock; int err; @@ -173,8 +226,6 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, return -EINVAL; if (unlikely(i >= m->map.max_entries)) return -E2BIG; - if (unlikely(map_flags == BPF_NOEXIST)) - return -EEXIST; sock = sockfd_lookup(fd, &err); if (!sock) @@ -192,32 +243,70 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, return -EOPNOTSUPP; } - sock_hold(sock->sk); + map_entry = &m->xsk_map[i]; + node = xsk_map_node_alloc(m, map_entry); + if (IS_ERR(node)) { + sockfd_put(sock); + return PTR_ERR(node); + } - old_xs = xchg(&m->xsk_map[i], xs); + spin_lock_bh(&m->lock); + old_xs = READ_ONCE(*map_entry); + if (old_xs == xs) { + err = 0; + goto out; + } else if (old_xs && map_flags == BPF_NOEXIST) { + err = -EEXIST; + goto out; + } else if (!old_xs && map_flags == BPF_EXIST) { + err = -ENOENT; + goto out; + } + xsk_map_sock_add(xs, node); + WRITE_ONCE(*map_entry, xs); if (old_xs) - sock_put((struct sock *)old_xs); - + xsk_map_sock_delete(old_xs, map_entry); + spin_unlock_bh(&m->lock); sockfd_put(sock); return 0; + +out: + spin_unlock_bh(&m->lock); + sockfd_put(sock); + xsk_map_node_free(node); + return err; } static int xsk_map_delete_elem(struct bpf_map *map, void *key) { struct xsk_map *m = container_of(map, struct xsk_map, map); - struct xdp_sock *old_xs; + struct xdp_sock *old_xs, **map_entry; int k = *(u32 *)key; if (k >= map->max_entries) return -EINVAL; - old_xs = xchg(&m->xsk_map[k], NULL); + spin_lock_bh(&m->lock); + map_entry = &m->xsk_map[k]; + old_xs = xchg(map_entry, NULL); if (old_xs) - sock_put((struct sock *)old_xs); + xsk_map_sock_delete(old_xs, map_entry); + spin_unlock_bh(&m->lock); return 0; } +void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, + struct xdp_sock **map_entry) +{ + spin_lock_bh(&map->lock); + if (READ_ONCE(*map_entry) == xs) { + WRITE_ONCE(*map_entry, NULL); + xsk_map_sock_delete(xs, map_entry); + } + spin_unlock_bh(&map->lock); +} + const struct bpf_map_ops xsk_map_ops = { .map_alloc = xsk_map_alloc, .map_free = xsk_map_free, diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 88006be40ea3..7f83f4121d8d 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -194,25 +194,6 @@ struct cgroup_pidlist { }; /* - * The following two functions "fix" the issue where there are more pids - * than kmalloc will give memory for; in such cases, we use vmalloc/vfree. - * TODO: replace with a kernel-wide solution to this problem - */ -#define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2)) -static void *pidlist_allocate(int count) -{ - if (PIDLIST_TOO_LARGE(count)) - return vmalloc(array_size(count, sizeof(pid_t))); - else - return kmalloc_array(count, sizeof(pid_t), GFP_KERNEL); -} - -static void pidlist_free(void *p) -{ - kvfree(p); -} - -/* * Used to destroy all pidlists lingering waiting for destroy timer. None * should be left afterwards. */ @@ -244,7 +225,7 @@ static void cgroup_pidlist_destroy_work_fn(struct work_struct *work) */ if (!delayed_work_pending(dwork)) { list_del(&l->links); - pidlist_free(l->list); + kvfree(l->list); put_pid_ns(l->key.ns); tofree = l; } @@ -365,7 +346,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, * show up until sometime later on. */ length = cgroup_task_count(cgrp); - array = pidlist_allocate(length); + array = kvmalloc_array(length, sizeof(pid_t), GFP_KERNEL); if (!array) return -ENOMEM; /* now, populate the array */ @@ -390,12 +371,12 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, l = cgroup_pidlist_find_create(cgrp, type); if (!l) { - pidlist_free(array); + kvfree(array); return -ENOMEM; } /* store array, freeing old if necessary */ - pidlist_free(l->list); + kvfree(l->list); l->list = array; l->length = length; *lp = l; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 753afbca549f..080561bb8a4b 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -488,7 +488,7 @@ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, rcu_read_lock(); css = cgroup_css(cgrp, ss); - if (!css || !css_tryget_online(css)) + if (css && !css_tryget_online(css)) css = NULL; rcu_read_unlock(); @@ -1891,7 +1891,7 @@ static int cgroup_reconfigure(struct fs_context *fc) */ static bool use_task_css_set_links __read_mostly; -static void cgroup_enable_task_cg_lists(void) +void cgroup_enable_task_cg_lists(void) { struct task_struct *p, *g; @@ -2894,7 +2894,7 @@ static void cgroup_print_ss_mask(struct seq_file *seq, u16 ss_mask) do_each_subsys_mask(ss, ssid, ss_mask) { if (printed) seq_putc(seq, ' '); - seq_printf(seq, "%s", ss->name); + seq_puts(seq, ss->name); printed = true; } while_each_subsys_mask(); if (printed) @@ -5255,8 +5255,16 @@ static struct cgroup *cgroup_create(struct cgroup *parent) * if the parent has to be frozen, the child has too. */ cgrp->freezer.e_freeze = parent->freezer.e_freeze; - if (cgrp->freezer.e_freeze) + if (cgrp->freezer.e_freeze) { + /* + * Set the CGRP_FREEZE flag, so when a process will be + * attached to the child cgroup, it will become frozen. + * At this point the new cgroup is unpopulated, so we can + * consider it frozen immediately. + */ + set_bit(CGRP_FREEZE, &cgrp->flags); set_bit(CGRP_FROZEN, &cgrp->flags); + } spin_lock_irq(&css_set_lock); for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 5aa37531ce76..c52bc91f882b 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -45,6 +45,7 @@ #include <linux/proc_fs.h> #include <linux/rcupdate.h> #include <linux/sched.h> +#include <linux/sched/deadline.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/seq_file.h> @@ -332,7 +333,18 @@ static struct cpuset top_cpuset = { * guidelines for accessing subsystem state in kernel/cgroup.c */ -static DEFINE_MUTEX(cpuset_mutex); +DEFINE_STATIC_PERCPU_RWSEM(cpuset_rwsem); + +void cpuset_read_lock(void) +{ + percpu_down_read(&cpuset_rwsem); +} + +void cpuset_read_unlock(void) +{ + percpu_up_read(&cpuset_rwsem); +} + static DEFINE_SPINLOCK(callback_lock); static struct workqueue_struct *cpuset_migrate_mm_wq; @@ -894,6 +906,67 @@ done: return ndoms; } +static void update_tasks_root_domain(struct cpuset *cs) +{ + struct css_task_iter it; + struct task_struct *task; + + css_task_iter_start(&cs->css, 0, &it); + + while ((task = css_task_iter_next(&it))) + dl_add_task_root_domain(task); + + css_task_iter_end(&it); +} + +static void rebuild_root_domains(void) +{ + struct cpuset *cs = NULL; + struct cgroup_subsys_state *pos_css; + + percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_cpus_held(); + lockdep_assert_held(&sched_domains_mutex); + + cgroup_enable_task_cg_lists(); + + rcu_read_lock(); + + /* + * Clear default root domain DL accounting, it will be computed again + * if a task belongs to it. + */ + dl_clear_root_domain(&def_root_domain); + + cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { + + if (cpumask_empty(cs->effective_cpus)) { + pos_css = css_rightmost_descendant(pos_css); + continue; + } + + css_get(&cs->css); + + rcu_read_unlock(); + + update_tasks_root_domain(cs); + + rcu_read_lock(); + css_put(&cs->css); + } + rcu_read_unlock(); +} + +static void +partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) +{ + mutex_lock(&sched_domains_mutex); + partition_sched_domains_locked(ndoms_new, doms_new, dattr_new); + rebuild_root_domains(); + mutex_unlock(&sched_domains_mutex); +} + /* * Rebuild scheduler domains. * @@ -911,8 +984,8 @@ static void rebuild_sched_domains_locked(void) cpumask_var_t *doms; int ndoms; - lockdep_assert_held(&cpuset_mutex); - get_online_cpus(); + lockdep_assert_cpus_held(); + percpu_rwsem_assert_held(&cpuset_rwsem); /* * We have raced with CPU hotplug. Don't do anything to avoid @@ -921,19 +994,17 @@ static void rebuild_sched_domains_locked(void) */ if (!top_cpuset.nr_subparts_cpus && !cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask)) - goto out; + return; if (top_cpuset.nr_subparts_cpus && !cpumask_subset(top_cpuset.effective_cpus, cpu_active_mask)) - goto out; + return; /* Generate domain masks and attrs */ ndoms = generate_sched_domains(&doms, &attr); /* Have scheduler rebuild the domains */ - partition_sched_domains(ndoms, doms, attr); -out: - put_online_cpus(); + partition_and_rebuild_sched_domains(ndoms, doms, attr); } #else /* !CONFIG_SMP */ static void rebuild_sched_domains_locked(void) @@ -943,9 +1014,11 @@ static void rebuild_sched_domains_locked(void) void rebuild_sched_domains(void) { - mutex_lock(&cpuset_mutex); + get_online_cpus(); + percpu_down_write(&cpuset_rwsem); rebuild_sched_domains_locked(); - mutex_unlock(&cpuset_mutex); + percpu_up_write(&cpuset_rwsem); + put_online_cpus(); } /** @@ -1051,7 +1124,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, int deleting; /* Moving cpus from subparts_cpus to effective_cpus */ bool part_error = false; /* Partition error? */ - lockdep_assert_held(&cpuset_mutex); + percpu_rwsem_assert_held(&cpuset_rwsem); /* * The parent must be a partition root. @@ -2039,7 +2112,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); cs = css_cs(css); - mutex_lock(&cpuset_mutex); + percpu_down_write(&cpuset_rwsem); /* allow moving tasks into an empty cpuset if on default hierarchy */ ret = -ENOSPC; @@ -2063,7 +2136,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) cs->attach_in_progress++; ret = 0; out_unlock: - mutex_unlock(&cpuset_mutex); + percpu_up_write(&cpuset_rwsem); return ret; } @@ -2073,9 +2146,9 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset) cgroup_taskset_first(tset, &css); - mutex_lock(&cpuset_mutex); + percpu_down_write(&cpuset_rwsem); css_cs(css)->attach_in_progress--; - mutex_unlock(&cpuset_mutex); + percpu_up_write(&cpuset_rwsem); } /* @@ -2098,7 +2171,7 @@ static void cpuset_attach(struct cgroup_taskset *tset) cgroup_taskset_first(tset, &css); cs = css_cs(css); - mutex_lock(&cpuset_mutex); + percpu_down_write(&cpuset_rwsem); /* prepare for attach */ if (cs == &top_cpuset) @@ -2152,7 +2225,7 @@ static void cpuset_attach(struct cgroup_taskset *tset) if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); - mutex_unlock(&cpuset_mutex); + percpu_up_write(&cpuset_rwsem); } /* The various types of files and directories in a cpuset file system */ @@ -2183,7 +2256,8 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, cpuset_filetype_t type = cft->private; int retval = 0; - mutex_lock(&cpuset_mutex); + get_online_cpus(); + percpu_down_write(&cpuset_rwsem); if (!is_cpuset_online(cs)) { retval = -ENODEV; goto out_unlock; @@ -2219,7 +2293,8 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, break; } out_unlock: - mutex_unlock(&cpuset_mutex); + percpu_up_write(&cpuset_rwsem); + put_online_cpus(); return retval; } @@ -2230,7 +2305,8 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, cpuset_filetype_t type = cft->private; int retval = -ENODEV; - mutex_lock(&cpuset_mutex); + get_online_cpus(); + percpu_down_write(&cpuset_rwsem); if (!is_cpuset_online(cs)) goto out_unlock; @@ -2243,7 +2319,8 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, break; } out_unlock: - mutex_unlock(&cpuset_mutex); + percpu_up_write(&cpuset_rwsem); + put_online_cpus(); return retval; } @@ -2282,7 +2359,8 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, kernfs_break_active_protection(of->kn); flush_work(&cpuset_hotplug_work); - mutex_lock(&cpuset_mutex); + get_online_cpus(); + percpu_down_write(&cpuset_rwsem); if (!is_cpuset_online(cs)) goto out_unlock; @@ -2306,7 +2384,8 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, free_cpuset(trialcs); out_unlock: - mutex_unlock(&cpuset_mutex); + percpu_up_write(&cpuset_rwsem); + put_online_cpus(); kernfs_unbreak_active_protection(of->kn); css_put(&cs->css); flush_workqueue(cpuset_migrate_mm_wq); @@ -2437,13 +2516,15 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf, return -EINVAL; css_get(&cs->css); - mutex_lock(&cpuset_mutex); + get_online_cpus(); + percpu_down_write(&cpuset_rwsem); if (!is_cpuset_online(cs)) goto out_unlock; retval = update_prstate(cs, val); out_unlock: - mutex_unlock(&cpuset_mutex); + percpu_up_write(&cpuset_rwsem); + put_online_cpus(); css_put(&cs->css); return retval ?: nbytes; } @@ -2649,7 +2730,8 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) if (!parent) return 0; - mutex_lock(&cpuset_mutex); + get_online_cpus(); + percpu_down_write(&cpuset_rwsem); set_bit(CS_ONLINE, &cs->flags); if (is_spread_page(parent)) @@ -2700,7 +2782,8 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) cpumask_copy(cs->effective_cpus, parent->cpus_allowed); spin_unlock_irq(&callback_lock); out_unlock: - mutex_unlock(&cpuset_mutex); + percpu_up_write(&cpuset_rwsem); + put_online_cpus(); return 0; } @@ -2719,7 +2802,8 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); - mutex_lock(&cpuset_mutex); + get_online_cpus(); + percpu_down_write(&cpuset_rwsem); if (is_partition_root(cs)) update_prstate(cs, 0); @@ -2738,7 +2822,8 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) cpuset_dec(); clear_bit(CS_ONLINE, &cs->flags); - mutex_unlock(&cpuset_mutex); + percpu_up_write(&cpuset_rwsem); + put_online_cpus(); } static void cpuset_css_free(struct cgroup_subsys_state *css) @@ -2750,7 +2835,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css) static void cpuset_bind(struct cgroup_subsys_state *root_css) { - mutex_lock(&cpuset_mutex); + percpu_down_write(&cpuset_rwsem); spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { @@ -2763,7 +2848,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css) } spin_unlock_irq(&callback_lock); - mutex_unlock(&cpuset_mutex); + percpu_up_write(&cpuset_rwsem); } /* @@ -2805,6 +2890,8 @@ struct cgroup_subsys cpuset_cgrp_subsys = { int __init cpuset_init(void) { + BUG_ON(percpu_init_rwsem(&cpuset_rwsem)); + BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&top_cpuset.subparts_cpus, GFP_KERNEL)); @@ -2876,7 +2963,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs, is_empty = cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed); - mutex_unlock(&cpuset_mutex); + percpu_up_write(&cpuset_rwsem); /* * Move tasks to the nearest ancestor with execution resources, @@ -2886,7 +2973,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs, if (is_empty) remove_tasks_in_empty_cpuset(cs); - mutex_lock(&cpuset_mutex); + percpu_down_write(&cpuset_rwsem); } static void @@ -2936,14 +3023,14 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) retry: wait_event(cpuset_attach_wq, cs->attach_in_progress == 0); - mutex_lock(&cpuset_mutex); + percpu_down_write(&cpuset_rwsem); /* * We have raced with task attaching. We wait until attaching * is finished, so we won't attach a task to an empty cpuset. */ if (cs->attach_in_progress) { - mutex_unlock(&cpuset_mutex); + percpu_up_write(&cpuset_rwsem); goto retry; } @@ -3011,7 +3098,7 @@ update_tasks: hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); - mutex_unlock(&cpuset_mutex); + percpu_up_write(&cpuset_rwsem); } /** @@ -3041,7 +3128,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work) if (on_dfl && !alloc_cpumasks(NULL, &tmp)) ptmp = &tmp; - mutex_lock(&cpuset_mutex); + percpu_down_write(&cpuset_rwsem); /* fetch the available cpus/mems and find out which changed how */ cpumask_copy(&new_cpus, cpu_active_mask); @@ -3091,7 +3178,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work) update_tasks_nodemask(&top_cpuset); } - mutex_unlock(&cpuset_mutex); + percpu_up_write(&cpuset_rwsem); /* if cpus or mems changed, we need to propagate to descendants */ if (cpus_updated || mems_updated) { diff --git a/kernel/cpu.c b/kernel/cpu.c index e84c0873559e..e1967e9eddc2 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -62,7 +62,6 @@ struct cpuhp_cpu_state { bool rollback; bool single; bool bringup; - bool booted_once; struct hlist_node *node; struct hlist_node *last; enum cpuhp_state cb_state; @@ -76,6 +75,10 @@ static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { .fail = CPUHP_INVALID, }; +#ifdef CONFIG_SMP +cpumask_t cpus_booted_once_mask; +#endif + #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) static struct lockdep_map cpuhp_state_up_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); @@ -433,7 +436,7 @@ static inline bool cpu_smt_allowed(unsigned int cpu) * CPU. Otherwise, a broadacasted MCE observing CR4.MCE=0b on any * core will shutdown the machine. */ - return !per_cpu(cpuhp_state, cpu).booted_once; + return !cpumask_test_cpu(cpu, &cpus_booted_once_mask); } #else static inline bool cpu_smt_allowed(unsigned int cpu) { return true; } @@ -1066,7 +1069,7 @@ void notify_cpu_starting(unsigned int cpu) int ret; rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ - st->booted_once = true; + cpumask_set_cpu(cpu, &cpus_booted_once_mask); while (st->state < target) { st->state++; ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); @@ -2295,6 +2298,9 @@ EXPORT_SYMBOL(__cpu_present_mask); struct cpumask __cpu_active_mask __read_mostly; EXPORT_SYMBOL(__cpu_active_mask); +atomic_t __num_online_cpus __read_mostly; +EXPORT_SYMBOL(__num_online_cpus); + void init_cpu_present(const struct cpumask *src) { cpumask_copy(&__cpu_present_mask, src); @@ -2310,6 +2316,27 @@ void init_cpu_online(const struct cpumask *src) cpumask_copy(&__cpu_online_mask, src); } +void set_cpu_online(unsigned int cpu, bool online) +{ + /* + * atomic_inc/dec() is required to handle the horrid abuse of this + * function by the reboot and kexec code which invoke it from + * IPI/NMI broadcasts when shutting down CPUs. Invocation from + * regular CPU hotplug is properly serialized. + * + * Note, that the fact that __num_online_cpus is of type atomic_t + * does not protect readers which are not serialized against + * concurrent hotplug operations. + */ + if (online) { + if (!cpumask_test_and_set_cpu(cpu, &__cpu_online_mask)) + atomic_inc(&__num_online_cpus); + } else { + if (cpumask_test_and_clear_cpu(cpu, &__cpu_online_mask)) + atomic_dec(&__num_online_cpus); + } +} + /* * Activate the first processor. */ @@ -2334,7 +2361,7 @@ void __init boot_cpu_init(void) void __init boot_cpu_hotplug_init(void) { #ifdef CONFIG_SMP - this_cpu_write(cpuhp_state.booted_once, true); + cpumask_set_cpu(smp_processor_id(), &cpus_booted_once_mask); #endif this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); } diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 5cc608de6883..10f1187b3907 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -787,11 +787,8 @@ out: } /* - * GDB places a breakpoint at this function to know dynamically - * loaded objects. It's not defined static so that only one instance with this - * name exists in the kernel. + * GDB places a breakpoint at this function to know dynamically loaded objects. */ - static int module_event(struct notifier_block *self, unsigned long val, void *data) { diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 9ecfa37c7fbf..4567fe998c30 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -830,7 +830,7 @@ static void parse_grep(const char *str) cp++; while (isspace(*cp)) cp++; - if (strncmp(cp, "grep ", 5)) { + if (!str_has_prefix(cp, "grep ")) { kdb_printf("invalid 'pipe', see grephelp\n"); return; } diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index 9decbba255fc..73c5c2b8e824 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -20,6 +20,15 @@ config ARCH_HAS_DMA_COHERENCE_H config ARCH_HAS_DMA_SET_MASK bool +# +# Select this option if the architecture needs special handling for +# DMA_ATTR_WRITE_COMBINE. Normally the "uncached" mapping should be what +# people thing of when saying write combine, so very few platforms should +# need to enable this. +# +config ARCH_HAS_DMA_WRITE_COMBINE + bool + config DMA_DECLARE_COHERENT bool @@ -45,9 +54,6 @@ config ARCH_HAS_DMA_PREP_COHERENT config ARCH_HAS_DMA_COHERENT_TO_PFN bool -config ARCH_HAS_DMA_MMAP_PGPROT - bool - config ARCH_HAS_FORCE_DMA_UNENCRYPTED bool diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c index 29fd6590dc1e..545e3869b0e3 100644 --- a/kernel/dma/coherent.c +++ b/kernel/dma/coherent.c @@ -122,18 +122,6 @@ int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, dma_release_coherent_memory(mem); return ret; } -EXPORT_SYMBOL(dma_declare_coherent_memory); - -void dma_release_declared_memory(struct device *dev) -{ - struct dma_coherent_mem *mem = dev->dma_mem; - - if (!mem) - return; - dma_release_coherent_memory(mem); - dev->dma_mem = NULL; -} -EXPORT_SYMBOL(dma_release_declared_memory); static void *__dma_alloc_from_coherent(struct dma_coherent_mem *mem, ssize_t size, dma_addr_t *dma_handle) @@ -288,7 +276,6 @@ int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma, return __dma_mmap_from_coherent(mem, vma, vaddr, size, ret); } -EXPORT_SYMBOL(dma_mmap_from_dev_coherent); int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *vaddr, size_t size, int *ret) diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 706113c6bebc..8402b29c280f 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -305,7 +305,7 @@ void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, dma_direct_sync_single_for_cpu(dev, addr, size, dir); if (unlikely(is_swiotlb_buffer(phys))) - swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); + swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs); } EXPORT_SYMBOL(dma_direct_unmap_page); diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index b0038ca3aa92..64a3d294f4b4 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -136,17 +136,29 @@ int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, return ret; } +/* + * The whole dma_get_sgtable() idea is fundamentally unsafe - it seems + * that the intention is to allow exporting memory allocated via the + * coherent DMA APIs through the dma_buf API, which only accepts a + * scattertable. This presents a couple of problems: + * 1. Not all memory allocated via the coherent DMA APIs is backed by + * a struct page + * 2. Passing coherent DMA memory into the streaming APIs is not allowed + * as we will try to flush the memory through a different alias to that + * actually being used (and the flushes are redundant.) + */ int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) { const struct dma_map_ops *ops = get_dma_ops(dev); - if (!dma_is_direct(ops) && ops->get_sgtable) - return ops->get_sgtable(dev, sgt, cpu_addr, dma_addr, size, - attrs); - return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr, size, - attrs); + if (dma_is_direct(ops)) + return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr, + size, attrs); + if (!ops->get_sgtable) + return -ENXIO; + return ops->get_sgtable(dev, sgt, cpu_addr, dma_addr, size, attrs); } EXPORT_SYMBOL(dma_get_sgtable_attrs); @@ -161,9 +173,11 @@ pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs) (IS_ENABLED(CONFIG_DMA_NONCOHERENT_CACHE_SYNC) && (attrs & DMA_ATTR_NON_CONSISTENT))) return prot; - if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_MMAP_PGPROT)) - return arch_dma_mmap_pgprot(dev, prot, attrs); - return pgprot_noncached(prot); +#ifdef CONFIG_ARCH_HAS_DMA_WRITE_COMBINE + if (attrs & DMA_ATTR_WRITE_COMBINE) + return pgprot_writecombine(prot); +#endif + return pgprot_dmacoherent(prot); } #endif /* CONFIG_MMU */ @@ -174,7 +188,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) { -#ifndef CONFIG_ARCH_NO_COHERENT_DMA_MMAP +#ifdef CONFIG_MMU unsigned long user_count = vma_pages(vma); unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; unsigned long off = vma->vm_pgoff; @@ -205,8 +219,29 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, user_count << PAGE_SHIFT, vma->vm_page_prot); #else return -ENXIO; -#endif /* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */ +#endif /* CONFIG_MMU */ +} + +/** + * dma_can_mmap - check if a given device supports dma_mmap_* + * @dev: device to check + * + * Returns %true if @dev supports dma_mmap_coherent() and dma_mmap_attrs() to + * map DMA allocations to userspace. + */ +bool dma_can_mmap(struct device *dev) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (dma_is_direct(ops)) { + return IS_ENABLED(CONFIG_MMU) && + (dev_is_dma_coherent(dev) || + IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN)); + } + + return ops->mmap != NULL; } +EXPORT_SYMBOL_GPL(dma_can_mmap); /** * dma_mmap_attrs - map a coherent DMA allocation into user space @@ -227,31 +262,15 @@ int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, { const struct dma_map_ops *ops = get_dma_ops(dev); - if (!dma_is_direct(ops) && ops->mmap) - return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs); - return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size, attrs); + if (dma_is_direct(ops)) + return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size, + attrs); + if (!ops->mmap) + return -ENXIO; + return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs); } EXPORT_SYMBOL(dma_mmap_attrs); -static u64 dma_default_get_required_mask(struct device *dev) -{ - u32 low_totalram = ((max_pfn - 1) << PAGE_SHIFT); - u32 high_totalram = ((max_pfn - 1) >> (32 - PAGE_SHIFT)); - u64 mask; - - if (!high_totalram) { - /* convert to mask just covering totalram */ - low_totalram = (1 << (fls(low_totalram) - 1)); - low_totalram += low_totalram - 1; - mask = low_totalram; - } else { - high_totalram = (1 << (fls(high_totalram) - 1)); - high_totalram += high_totalram - 1; - mask = (((u64)high_totalram) << 32) + 0xffffffff; - } - return mask; -} - u64 dma_get_required_mask(struct device *dev) { const struct dma_map_ops *ops = get_dma_ops(dev); @@ -260,7 +279,16 @@ u64 dma_get_required_mask(struct device *dev) return dma_direct_get_required_mask(dev); if (ops->get_required_mask) return ops->get_required_mask(dev); - return dma_default_get_required_mask(dev); + + /* + * We require every DMA ops implementation to at least support a 32-bit + * DMA mask (and use bounce buffering if that isn't supported in + * hardware). As the direct mapping code has its own routine to + * actually report an optimal mask we default to 32-bit here as that + * is the right thing for most IOMMUs, and at least not actively + * harmful in general. + */ + return DMA_BIT_MASK(32); } EXPORT_SYMBOL_GPL(dma_get_required_mask); @@ -405,3 +433,14 @@ size_t dma_max_mapping_size(struct device *dev) return size; } EXPORT_SYMBOL_GPL(dma_max_mapping_size); + +unsigned long dma_get_merge_boundary(struct device *dev) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (!ops || !ops->get_merge_boundary) + return 0; /* can't merge */ + + return ops->get_merge_boundary(dev); +} +EXPORT_SYMBOL_GPL(dma_get_merge_boundary); diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index ffe78f0b2fe4..ca4e5d44b571 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -11,13 +11,21 @@ #include <linux/slab.h> #include <linux/vmalloc.h> +struct page **dma_common_find_pages(void *cpu_addr) +{ + struct vm_struct *area = find_vm_area(cpu_addr); + + if (!area || area->flags != VM_DMA_COHERENT) + return NULL; + return area->pages; +} + static struct vm_struct *__dma_common_pages_remap(struct page **pages, - size_t size, unsigned long vm_flags, pgprot_t prot, - const void *caller) + size_t size, pgprot_t prot, const void *caller) { struct vm_struct *area; - area = get_vm_area_caller(size, vm_flags, caller); + area = get_vm_area_caller(size, VM_DMA_COHERENT, caller); if (!area) return NULL; @@ -34,12 +42,11 @@ static struct vm_struct *__dma_common_pages_remap(struct page **pages, * Cannot be used in non-sleeping contexts */ void *dma_common_pages_remap(struct page **pages, size_t size, - unsigned long vm_flags, pgprot_t prot, - const void *caller) + pgprot_t prot, const void *caller) { struct vm_struct *area; - area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller); + area = __dma_common_pages_remap(pages, size, prot, caller); if (!area) return NULL; @@ -53,7 +60,6 @@ void *dma_common_pages_remap(struct page **pages, size_t size, * Cannot be used in non-sleeping contexts */ void *dma_common_contiguous_remap(struct page *page, size_t size, - unsigned long vm_flags, pgprot_t prot, const void *caller) { int i; @@ -67,7 +73,7 @@ void *dma_common_contiguous_remap(struct page *page, size_t size, for (i = 0; i < (size >> PAGE_SHIFT); i++) pages[i] = nth_page(page, i); - area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller); + area = __dma_common_pages_remap(pages, size, prot, caller); kfree(pages); @@ -79,11 +85,11 @@ void *dma_common_contiguous_remap(struct page *page, size_t size, /* * Unmaps a range previously mapped by dma_common_*_remap */ -void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags) +void dma_common_free_remap(void *cpu_addr, size_t size) { - struct vm_struct *area = find_vm_area(cpu_addr); + struct page **pages = dma_common_find_pages(cpu_addr); - if (!area || (area->flags & vm_flags) != vm_flags) { + if (!pages) { WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr); return; } @@ -105,7 +111,16 @@ static int __init early_coherent_pool(char *p) } early_param("coherent_pool", early_coherent_pool); -int __init dma_atomic_pool_init(gfp_t gfp, pgprot_t prot) +static gfp_t dma_atomic_pool_gfp(void) +{ + if (IS_ENABLED(CONFIG_ZONE_DMA)) + return GFP_DMA; + if (IS_ENABLED(CONFIG_ZONE_DMA32)) + return GFP_DMA32; + return GFP_KERNEL; +} + +static int __init dma_atomic_pool_init(void) { unsigned int pool_size_order = get_order(atomic_pool_size); unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT; @@ -117,7 +132,7 @@ int __init dma_atomic_pool_init(gfp_t gfp, pgprot_t prot) page = dma_alloc_from_contiguous(NULL, nr_pages, pool_size_order, false); else - page = alloc_pages(gfp, pool_size_order); + page = alloc_pages(dma_atomic_pool_gfp(), pool_size_order); if (!page) goto out; @@ -127,8 +142,9 @@ int __init dma_atomic_pool_init(gfp_t gfp, pgprot_t prot) if (!atomic_pool) goto free_page; - addr = dma_common_contiguous_remap(page, atomic_pool_size, VM_USERMAP, - prot, __builtin_return_address(0)); + addr = dma_common_contiguous_remap(page, atomic_pool_size, + pgprot_dmacoherent(PAGE_KERNEL), + __builtin_return_address(0)); if (!addr) goto destroy_genpool; @@ -143,7 +159,7 @@ int __init dma_atomic_pool_init(gfp_t gfp, pgprot_t prot) return 0; remove_mapping: - dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP); + dma_common_free_remap(addr, atomic_pool_size); destroy_genpool: gen_pool_destroy(atomic_pool); atomic_pool = NULL; @@ -155,6 +171,7 @@ out: atomic_pool_size / 1024); return -ENOMEM; } +postcore_initcall(dma_atomic_pool_init); bool dma_in_atomic_pool(void *start, size_t size) { @@ -217,7 +234,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, arch_dma_prep_coherent(page, size); /* create a coherent mapping */ - ret = dma_common_contiguous_remap(page, size, VM_USERMAP, + ret = dma_common_contiguous_remap(page, size, dma_pgprot(dev, PAGE_KERNEL, attrs), __builtin_return_address(0)); if (!ret) { diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 9de232229063..796a44f8ef5a 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -444,7 +444,9 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr, phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr, - phys_addr_t orig_addr, size_t size, + phys_addr_t orig_addr, + size_t mapping_size, + size_t alloc_size, enum dma_data_direction dir, unsigned long attrs) { @@ -464,6 +466,12 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, pr_warn_once("%s is active and system is using DMA bounce buffers\n", sme_active() ? "SME" : "SEV"); + if (mapping_size > alloc_size) { + dev_warn_once(hwdev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)", + mapping_size, alloc_size); + return (phys_addr_t)DMA_MAPPING_ERROR; + } + mask = dma_get_seg_boundary(hwdev); tbl_dma_addr &= mask; @@ -471,8 +479,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, offset_slots = ALIGN(tbl_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; /* - * Carefully handle integer overflow which can occur when mask == ~0UL. - */ + * Carefully handle integer overflow which can occur when mask == ~0UL. + */ max_slots = mask + 1 ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT); @@ -481,8 +489,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, * For mappings greater than or equal to a page, we limit the stride * (and hence alignment) to a page size. */ - nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; - if (size >= PAGE_SIZE) + nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; + if (alloc_size >= PAGE_SIZE) stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT)); else stride = 1; @@ -547,7 +555,7 @@ not_found: spin_unlock_irqrestore(&io_tlb_lock, flags); if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n", - size, io_tlb_nslabs, tmp_io_tlb_used); + alloc_size, io_tlb_nslabs, tmp_io_tlb_used); return (phys_addr_t)DMA_MAPPING_ERROR; found: io_tlb_used += nslots; @@ -562,7 +570,7 @@ found: io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT); if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) - swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE); + swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_TO_DEVICE); return tlb_addr; } @@ -571,11 +579,11 @@ found: * tlb_addr is the physical address of the bounce buffer to unmap. */ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, - size_t size, enum dma_data_direction dir, - unsigned long attrs) + size_t mapping_size, size_t alloc_size, + enum dma_data_direction dir, unsigned long attrs) { unsigned long flags; - int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; + int i, count, nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT; phys_addr_t orig_addr = io_tlb_orig_addr[index]; @@ -585,7 +593,7 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, if (orig_addr != INVALID_PHYS_ADDR && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL))) - swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE); + swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_FROM_DEVICE); /* * Return the buffer to the free list by setting the corresponding @@ -665,14 +673,14 @@ bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr, /* Oh well, have to allocate and map a bounce buffer. */ *phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start), - *phys, size, dir, attrs); + *phys, size, size, dir, attrs); if (*phys == (phys_addr_t)DMA_MAPPING_ERROR) return false; /* Ensure that the address returned is DMA'ble */ *dma_addr = __phys_to_dma(dev, *phys); if (unlikely(!dma_capable(dev, *dma_addr, size))) { - swiotlb_tbl_unmap_single(dev, *phys, size, dir, + swiotlb_tbl_unmap_single(dev, *phys, size, size, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC); return false; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 0463c1151bae..4f08b17d6426 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1103,7 +1103,7 @@ static void __perf_mux_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu) cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * interval); raw_spin_lock_init(&cpuctx->hrtimer_lock); - hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); + hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD); timer->function = perf_mux_hrtimer_handler; } @@ -1121,7 +1121,7 @@ static int perf_mux_hrtimer_restart(struct perf_cpu_context *cpuctx) if (!cpuctx->hrtimer_active) { cpuctx->hrtimer_active = 1; hrtimer_forward_now(timer, cpuctx->hrtimer_interval); - hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED); + hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED_HARD); } raw_spin_unlock_irqrestore(&cpuctx->hrtimer_lock, flags); @@ -1887,6 +1887,89 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) ctx->generation++; } +static int +perf_aux_output_match(struct perf_event *event, struct perf_event *aux_event) +{ + if (!has_aux(aux_event)) + return 0; + + if (!event->pmu->aux_output_match) + return 0; + + return event->pmu->aux_output_match(aux_event); +} + +static void put_event(struct perf_event *event); +static void event_sched_out(struct perf_event *event, + struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx); + +static void perf_put_aux_event(struct perf_event *event) +{ + struct perf_event_context *ctx = event->ctx; + struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + struct perf_event *iter; + + /* + * If event uses aux_event tear down the link + */ + if (event->aux_event) { + iter = event->aux_event; + event->aux_event = NULL; + put_event(iter); + return; + } + + /* + * If the event is an aux_event, tear down all links to + * it from other events. + */ + for_each_sibling_event(iter, event->group_leader) { + if (iter->aux_event != event) + continue; + + iter->aux_event = NULL; + put_event(event); + + /* + * If it's ACTIVE, schedule it out and put it into ERROR + * state so that we don't try to schedule it again. Note + * that perf_event_enable() will clear the ERROR status. + */ + event_sched_out(iter, cpuctx, ctx); + perf_event_set_state(event, PERF_EVENT_STATE_ERROR); + } +} + +static int perf_get_aux_event(struct perf_event *event, + struct perf_event *group_leader) +{ + /* + * Our group leader must be an aux event if we want to be + * an aux_output. This way, the aux event will precede its + * aux_output events in the group, and therefore will always + * schedule first. + */ + if (!group_leader) + return 0; + + if (!perf_aux_output_match(event, group_leader)) + return 0; + + if (!atomic_long_inc_not_zero(&group_leader->refcount)) + return 0; + + /* + * Link aux_outputs to their aux event; this is undone in + * perf_group_detach() by perf_put_aux_event(). When the + * group in torn down, the aux_output events loose their + * link to the aux_event and can't schedule any more. + */ + event->aux_event = group_leader; + + return 1; +} + static void perf_group_detach(struct perf_event *event) { struct perf_event *sibling, *tmp; @@ -1902,6 +1985,8 @@ static void perf_group_detach(struct perf_event *event) event->attach_state &= ~PERF_ATTACH_GROUP; + perf_put_aux_event(event); + /* * If this is a sibling, remove it from its group. */ @@ -4089,10 +4174,8 @@ alloc_perf_context(struct pmu *pmu, struct task_struct *task) return NULL; __perf_event_init_context(ctx); - if (task) { - ctx->task = task; - get_task_struct(task); - } + if (task) + ctx->task = get_task_struct(task); ctx->pmu = pmu; return ctx; @@ -9491,7 +9574,7 @@ static void perf_swevent_start_hrtimer(struct perf_event *event) period = max_t(u64, 10000, hwc->sample_period); } hrtimer_start(&hwc->hrtimer, ns_to_ktime(period), - HRTIMER_MODE_REL_PINNED); + HRTIMER_MODE_REL_PINNED_HARD); } static void perf_swevent_cancel_hrtimer(struct perf_event *event) @@ -9513,7 +9596,7 @@ static void perf_swevent_init_hrtimer(struct perf_event *event) if (!is_sampling_event(event)) return; - hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); hwc->hrtimer.function = perf_swevent_hrtimer; /* @@ -10355,8 +10438,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, * and we cannot use the ctx information because we need the * pmu before we get a ctx. */ - get_task_struct(task); - event->hw.target = task; + event->hw.target = get_task_struct(task); } event->clock = &local_clock; @@ -10426,6 +10508,12 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, goto err_ns; } + if (event->attr.aux_output && + !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) { + err = -EOPNOTSUPP; + goto err_pmu; + } + err = exclusive_event_init(event); if (err) goto err_pmu; @@ -11082,6 +11170,8 @@ SYSCALL_DEFINE5(perf_event_open, } } + if (event->attr.aux_output && !perf_get_aux_event(event, group_leader)) + goto err_locked; /* * Must be under the same ctx::mutex as perf_install_in_context(), diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c index c5cd852fe86b..3cc8416ec844 100644 --- a/kernel/events/hw_breakpoint.c +++ b/kernel/events/hw_breakpoint.c @@ -413,7 +413,7 @@ static int hw_breakpoint_parse(struct perf_event *bp, int register_perf_hw_breakpoint(struct perf_event *bp) { - struct arch_hw_breakpoint hw; + struct arch_hw_breakpoint hw = { }; int err; err = reserve_bp_slot(bp); @@ -461,7 +461,7 @@ int modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *attr, bool check) { - struct arch_hw_breakpoint hw; + struct arch_hw_breakpoint hw = { }; int err; err = hw_breakpoint_parse(bp, attr, &hw); diff --git a/kernel/exit.c b/kernel/exit.c index 5b4a5dcce8f8..22ab6a4bdc51 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1554,6 +1554,23 @@ end: return retval; } +static struct pid *pidfd_get_pid(unsigned int fd) +{ + struct fd f; + struct pid *pid; + + f = fdget(fd); + if (!f.file) + return ERR_PTR(-EBADF); + + pid = pidfd_pid(f.file); + if (!IS_ERR(pid)) + get_pid(pid); + + fdput(f); + return pid; +} + static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop, int options, struct rusage *ru) { @@ -1576,19 +1593,32 @@ static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop, type = PIDTYPE_PID; if (upid <= 0) return -EINVAL; + + pid = find_get_pid(upid); break; case P_PGID: type = PIDTYPE_PGID; - if (upid <= 0) + if (upid < 0) + return -EINVAL; + + if (upid) + pid = find_get_pid(upid); + else + pid = get_task_pid(current, PIDTYPE_PGID); + break; + case P_PIDFD: + type = PIDTYPE_PID; + if (upid < 0) return -EINVAL; + + pid = pidfd_get_pid(upid); + if (IS_ERR(pid)) + return PTR_ERR(pid); break; default: return -EINVAL; } - if (type < PIDTYPE_MAX) - pid = find_get_pid(upid); - wo.wo_type = type; wo.wo_pid = pid; wo.wo_flags = options; diff --git a/kernel/fork.c b/kernel/fork.c index 2852d0e76ea3..53e780748fe3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -768,6 +768,7 @@ static void set_max_threads(unsigned int max_threads_suggested) int arch_task_struct_size __read_mostly; #endif +#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR static void task_struct_whitelist(unsigned long *offset, unsigned long *size) { /* Fetch thread_struct whitelist for the architecture. */ @@ -782,6 +783,7 @@ static void task_struct_whitelist(unsigned long *offset, unsigned long *size) else *offset += offsetof(struct task_struct, thread); } +#endif /* CONFIG_ARCH_TASK_STRUCT_ALLOCATOR */ void __init fork_init(void) { @@ -1517,28 +1519,17 @@ void __cleanup_sighand(struct sighand_struct *sighand) } } -#ifdef CONFIG_POSIX_TIMERS /* * Initialize POSIX timer handling for a thread group. */ static void posix_cpu_timers_init_group(struct signal_struct *sig) { + struct posix_cputimers *pct = &sig->posix_cputimers; unsigned long cpu_limit; cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); - if (cpu_limit != RLIM_INFINITY) { - sig->cputime_expires.prof_exp = cpu_limit * NSEC_PER_SEC; - sig->cputimer.running = true; - } - - /* The timer lists. */ - INIT_LIST_HEAD(&sig->cpu_timers[0]); - INIT_LIST_HEAD(&sig->cpu_timers[1]); - INIT_LIST_HEAD(&sig->cpu_timers[2]); + posix_cputimers_group_init(pct, cpu_limit); } -#else -static inline void posix_cpu_timers_init_group(struct signal_struct *sig) { } -#endif static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { @@ -1640,23 +1631,6 @@ static void rt_mutex_init_task(struct task_struct *p) #endif } -#ifdef CONFIG_POSIX_TIMERS -/* - * Initialize POSIX timer handling for a single task. - */ -static void posix_cpu_timers_init(struct task_struct *tsk) -{ - tsk->cputime_expires.prof_exp = 0; - tsk->cputime_expires.virt_exp = 0; - tsk->cputime_expires.sched_exp = 0; - INIT_LIST_HEAD(&tsk->cpu_timers[0]); - INIT_LIST_HEAD(&tsk->cpu_timers[1]); - INIT_LIST_HEAD(&tsk->cpu_timers[2]); -} -#else -static inline void posix_cpu_timers_init(struct task_struct *tsk) { } -#endif - static inline void init_task_pid_links(struct task_struct *task) { enum pid_type type; @@ -1690,6 +1664,14 @@ static inline void rcu_copy_process(struct task_struct *p) #endif /* #ifdef CONFIG_TASKS_RCU */ } +struct pid *pidfd_pid(const struct file *file) +{ + if (file->f_op == &pidfd_fops) + return file->private_data; + + return ERR_PTR(-EBADF); +} + static int pidfd_release(struct inode *inode, struct file *file) { struct pid *pid = file->private_data; @@ -1935,7 +1917,7 @@ static __latent_entropy struct task_struct *copy_process( task_io_accounting_init(&p->ioac); acct_clear_integrals(p); - posix_cpu_timers_init(p); + posix_cputimers_init(&p->posix_cputimers); p->io_context = NULL; audit_set_context(p, NULL); @@ -2338,6 +2320,8 @@ struct mm_struct *copy_init_mm(void) * * It copies the process, and if successful kick-starts * it and waits for it to finish using the VM if required. + * + * args->exit_signal is expected to be checked for sanity by the caller. */ long _do_fork(struct kernel_clone_args *args) { @@ -2562,6 +2546,14 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, if (copy_from_user(&args, uargs, size)) return -EFAULT; + /* + * Verify that higher 32bits of exit_signal are unset and that + * it is a valid signal + */ + if (unlikely((args.exit_signal & ~((u64)CSIGNAL)) || + !valid_signal(args.exit_signal))) + return -EINVAL; + *kargs = (struct kernel_clone_args){ .flags = args.flags, .pidfd = u64_to_user_ptr(args.pidfd), diff --git a/kernel/futex.c b/kernel/futex.c index 6d50728ef2e7..bd18f60e4c6c 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -487,11 +487,9 @@ futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, if (!time) return NULL; - hrtimer_init_on_stack(&timeout->timer, (flags & FLAGS_CLOCKRT) ? - CLOCK_REALTIME : CLOCK_MONOTONIC, - HRTIMER_MODE_ABS); - hrtimer_init_sleeper(timeout, current); - + hrtimer_init_sleeper_on_stack(timeout, (flags & FLAGS_CLOCKRT) ? + CLOCK_REALTIME : CLOCK_MONOTONIC, + HRTIMER_MODE_ABS); /* * If range_ns is 0, calling hrtimer_set_expires_range_ns() is * effectively the same as calling hrtimer_set_expires(). @@ -2613,7 +2611,7 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q, /* Arm the timer */ if (timeout) - hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS); + hrtimer_sleeper_start_expires(timeout, HRTIMER_MODE_ABS); /* * If we have been removed from the hash list, then another task @@ -2899,7 +2897,7 @@ retry_private: } if (unlikely(to)) - hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS); + hrtimer_sleeper_start_expires(to, HRTIMER_MODE_ABS); ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter); diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index 6fef48033f96..4d89ad4fae3b 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -7,6 +7,7 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/cpu.h> +#include <linux/sort.h> static void irq_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk, unsigned int cpus_per_vec) @@ -94,6 +95,155 @@ static int get_nodes_in_cpumask(cpumask_var_t *node_to_cpumask, return nodes; } +struct node_vectors { + unsigned id; + + union { + unsigned nvectors; + unsigned ncpus; + }; +}; + +static int ncpus_cmp_func(const void *l, const void *r) +{ + const struct node_vectors *ln = l; + const struct node_vectors *rn = r; + + return ln->ncpus - rn->ncpus; +} + +/* + * Allocate vector number for each node, so that for each node: + * + * 1) the allocated number is >= 1 + * + * 2) the allocated numbver is <= active CPU number of this node + * + * The actual allocated total vectors may be less than @numvecs when + * active total CPU number is less than @numvecs. + * + * Active CPUs means the CPUs in '@cpu_mask AND @node_to_cpumask[]' + * for each node. + */ +static void alloc_nodes_vectors(unsigned int numvecs, + cpumask_var_t *node_to_cpumask, + const struct cpumask *cpu_mask, + const nodemask_t nodemsk, + struct cpumask *nmsk, + struct node_vectors *node_vectors) +{ + unsigned n, remaining_ncpus = 0; + + for (n = 0; n < nr_node_ids; n++) { + node_vectors[n].id = n; + node_vectors[n].ncpus = UINT_MAX; + } + + for_each_node_mask(n, nodemsk) { + unsigned ncpus; + + cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]); + ncpus = cpumask_weight(nmsk); + + if (!ncpus) + continue; + remaining_ncpus += ncpus; + node_vectors[n].ncpus = ncpus; + } + + numvecs = min_t(unsigned, remaining_ncpus, numvecs); + + sort(node_vectors, nr_node_ids, sizeof(node_vectors[0]), + ncpus_cmp_func, NULL); + + /* + * Allocate vectors for each node according to the ratio of this + * node's nr_cpus to remaining un-assigned ncpus. 'numvecs' is + * bigger than number of active numa nodes. Always start the + * allocation from the node with minimized nr_cpus. + * + * This way guarantees that each active node gets allocated at + * least one vector, and the theory is simple: over-allocation + * is only done when this node is assigned by one vector, so + * other nodes will be allocated >= 1 vector, since 'numvecs' is + * bigger than number of numa nodes. + * + * One perfect invariant is that number of allocated vectors for + * each node is <= CPU count of this node: + * + * 1) suppose there are two nodes: A and B + * ncpu(X) is CPU count of node X + * vecs(X) is the vector count allocated to node X via this + * algorithm + * + * ncpu(A) <= ncpu(B) + * ncpu(A) + ncpu(B) = N + * vecs(A) + vecs(B) = V + * + * vecs(A) = max(1, round_down(V * ncpu(A) / N)) + * vecs(B) = V - vecs(A) + * + * both N and V are integer, and 2 <= V <= N, suppose + * V = N - delta, and 0 <= delta <= N - 2 + * + * 2) obviously vecs(A) <= ncpu(A) because: + * + * if vecs(A) is 1, then vecs(A) <= ncpu(A) given + * ncpu(A) >= 1 + * + * otherwise, + * vecs(A) <= V * ncpu(A) / N <= ncpu(A), given V <= N + * + * 3) prove how vecs(B) <= ncpu(B): + * + * if round_down(V * ncpu(A) / N) == 0, vecs(B) won't be + * over-allocated, so vecs(B) <= ncpu(B), + * + * otherwise: + * + * vecs(A) = + * round_down(V * ncpu(A) / N) = + * round_down((N - delta) * ncpu(A) / N) = + * round_down((N * ncpu(A) - delta * ncpu(A)) / N) >= + * round_down((N * ncpu(A) - delta * N) / N) = + * cpu(A) - delta + * + * then: + * + * vecs(A) - V >= ncpu(A) - delta - V + * => + * V - vecs(A) <= V + delta - ncpu(A) + * => + * vecs(B) <= N - ncpu(A) + * => + * vecs(B) <= cpu(B) + * + * For nodes >= 3, it can be thought as one node and another big + * node given that is exactly what this algorithm is implemented, + * and we always re-calculate 'remaining_ncpus' & 'numvecs', and + * finally for each node X: vecs(X) <= ncpu(X). + * + */ + for (n = 0; n < nr_node_ids; n++) { + unsigned nvectors, ncpus; + + if (node_vectors[n].ncpus == UINT_MAX) + continue; + + WARN_ON_ONCE(numvecs == 0); + + ncpus = node_vectors[n].ncpus; + nvectors = max_t(unsigned, 1, + numvecs * ncpus / remaining_ncpus); + WARN_ON_ONCE(nvectors > ncpus); + + node_vectors[n].nvectors = nvectors; + + remaining_ncpus -= ncpus; + numvecs -= nvectors; + } +} + static int __irq_build_affinity_masks(unsigned int startvec, unsigned int numvecs, unsigned int firstvec, @@ -102,10 +252,11 @@ static int __irq_build_affinity_masks(unsigned int startvec, struct cpumask *nmsk, struct irq_affinity_desc *masks) { - unsigned int n, nodes, cpus_per_vec, extra_vecs, done = 0; + unsigned int i, n, nodes, cpus_per_vec, extra_vecs, done = 0; unsigned int last_affv = firstvec + numvecs; unsigned int curvec = startvec; nodemask_t nodemsk = NODE_MASK_NONE; + struct node_vectors *node_vectors; if (!cpumask_weight(cpu_mask)) return 0; @@ -126,42 +277,56 @@ static int __irq_build_affinity_masks(unsigned int startvec, return numvecs; } - for_each_node_mask(n, nodemsk) { - unsigned int ncpus, v, vecs_to_assign, vecs_per_node; + node_vectors = kcalloc(nr_node_ids, + sizeof(struct node_vectors), + GFP_KERNEL); + if (!node_vectors) + return -ENOMEM; - /* Spread the vectors per node */ - vecs_per_node = (numvecs - (curvec - firstvec)) / nodes; + /* allocate vector number for each node */ + alloc_nodes_vectors(numvecs, node_to_cpumask, cpu_mask, + nodemsk, nmsk, node_vectors); - /* Get the cpus on this node which are in the mask */ - cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]); + for (i = 0; i < nr_node_ids; i++) { + unsigned int ncpus, v; + struct node_vectors *nv = &node_vectors[i]; + + if (nv->nvectors == UINT_MAX) + continue; - /* Calculate the number of cpus per vector */ + /* Get the cpus on this node which are in the mask */ + cpumask_and(nmsk, cpu_mask, node_to_cpumask[nv->id]); ncpus = cpumask_weight(nmsk); - vecs_to_assign = min(vecs_per_node, ncpus); + if (!ncpus) + continue; + + WARN_ON_ONCE(nv->nvectors > ncpus); /* Account for rounding errors */ - extra_vecs = ncpus - vecs_to_assign * (ncpus / vecs_to_assign); + extra_vecs = ncpus - nv->nvectors * (ncpus / nv->nvectors); - for (v = 0; curvec < last_affv && v < vecs_to_assign; - curvec++, v++) { - cpus_per_vec = ncpus / vecs_to_assign; + /* Spread allocated vectors on CPUs of the current node */ + for (v = 0; v < nv->nvectors; v++, curvec++) { + cpus_per_vec = ncpus / nv->nvectors; /* Account for extra vectors to compensate rounding errors */ if (extra_vecs) { cpus_per_vec++; --extra_vecs; } + + /* + * wrapping has to be considered given 'startvec' + * may start anywhere + */ + if (curvec >= last_affv) + curvec = firstvec; irq_spread_init_one(&masks[curvec].mask, nmsk, cpus_per_vec); } - - done += v; - if (done >= numvecs) - break; - if (curvec >= last_affv) - curvec = firstvec; - --nodes; + done += nv->nvectors; } + kfree(node_vectors); return done; } @@ -174,7 +339,7 @@ static int irq_build_affinity_masks(unsigned int startvec, unsigned int numvecs, unsigned int firstvec, struct irq_affinity_desc *masks) { - unsigned int curvec = startvec, nr_present, nr_others; + unsigned int curvec = startvec, nr_present = 0, nr_others = 0; cpumask_var_t *node_to_cpumask; cpumask_var_t nmsk, npresmsk; int ret = -ENOMEM; @@ -189,15 +354,17 @@ static int irq_build_affinity_masks(unsigned int startvec, unsigned int numvecs, if (!node_to_cpumask) goto fail_npresmsk; - ret = 0; /* Stabilize the cpumasks */ get_online_cpus(); build_node_to_cpumask(node_to_cpumask); /* Spread on present CPUs starting from affd->pre_vectors */ - nr_present = __irq_build_affinity_masks(curvec, numvecs, - firstvec, node_to_cpumask, - cpu_present_mask, nmsk, masks); + ret = __irq_build_affinity_masks(curvec, numvecs, firstvec, + node_to_cpumask, cpu_present_mask, + nmsk, masks); + if (ret < 0) + goto fail_build_affinity; + nr_present = ret; /* * Spread on non present CPUs starting from the next vector to be @@ -210,12 +377,16 @@ static int irq_build_affinity_masks(unsigned int startvec, unsigned int numvecs, else curvec = firstvec + nr_present; cpumask_andnot(npresmsk, cpu_possible_mask, cpu_present_mask); - nr_others = __irq_build_affinity_masks(curvec, numvecs, - firstvec, node_to_cpumask, - npresmsk, nmsk, masks); + ret = __irq_build_affinity_masks(curvec, numvecs, firstvec, + node_to_cpumask, npresmsk, nmsk, + masks); + if (ret >= 0) + nr_others = ret; + + fail_build_affinity: put_online_cpus(); - if (nr_present < numvecs) + if (ret >= 0) WARN_ON(nr_present + nr_others < numvecs); free_node_to_cpumask(node_to_cpumask); @@ -225,7 +396,7 @@ static int irq_build_affinity_masks(unsigned int startvec, unsigned int numvecs, fail_nmsk: free_cpumask_var(nmsk); - return ret; + return ret < 0 ? ret : 0; } static void default_calc_sets(struct irq_affinity *affd, unsigned int affvecs) diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 3078d0e48bba..132672b74e4b 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -31,7 +31,7 @@ struct irqchip_fwid { struct fwnode_handle fwnode; unsigned int type; char *name; - void *data; + phys_addr_t *pa; }; #ifdef CONFIG_GENERIC_IRQ_DEBUGFS @@ -62,7 +62,8 @@ EXPORT_SYMBOL_GPL(irqchip_fwnode_ops); * domain struct. */ struct fwnode_handle *__irq_domain_alloc_fwnode(unsigned int type, int id, - const char *name, void *data) + const char *name, + phys_addr_t *pa) { struct irqchip_fwid *fwid; char *n; @@ -77,7 +78,7 @@ struct fwnode_handle *__irq_domain_alloc_fwnode(unsigned int type, int id, n = kasprintf(GFP_KERNEL, "%s-%d", name, id); break; default: - n = kasprintf(GFP_KERNEL, "irqchip@%p", data); + n = kasprintf(GFP_KERNEL, "irqchip@%pa", pa); break; } @@ -89,7 +90,7 @@ struct fwnode_handle *__irq_domain_alloc_fwnode(unsigned int type, int id, fwid->type = type; fwid->name = n; - fwid->data = data; + fwid->pa = pa; fwid->fwnode.ops = &irqchip_fwnode_ops; return &fwid->fwnode; } @@ -148,6 +149,7 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, switch (fwid->type) { case IRQCHIP_FWNODE_NAMED: case IRQCHIP_FWNODE_NAMED_ID: + domain->fwnode = fwnode; domain->name = kstrdup(fwid->name, GFP_KERNEL); if (!domain->name) { kfree(domain); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index e8f7f179bf77..1753486b440c 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -23,7 +23,7 @@ #include "internals.h" -#ifdef CONFIG_IRQ_FORCED_THREADING +#if defined(CONFIG_IRQ_FORCED_THREADING) && !defined(CONFIG_PREEMPT_RT) __read_mostly bool force_irqthreads; EXPORT_SYMBOL_GPL(force_irqthreads); @@ -1255,8 +1255,7 @@ setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary) * the thread dies to avoid that the interrupt code * references an already freed task_struct. */ - get_task_struct(t); - new->thread = t; + new->thread = get_task_struct(t); /* * Tell the thread to set its affinity. This is * important for shared interrupt handlers as we do diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c index d6961d3c6f9e..8f557fa1f4fe 100644 --- a/kernel/irq/pm.c +++ b/kernel/irq/pm.c @@ -177,6 +177,26 @@ static void resume_irqs(bool want_early) } /** + * rearm_wake_irq - rearm a wakeup interrupt line after signaling wakeup + * @irq: Interrupt to rearm + */ +void rearm_wake_irq(unsigned int irq) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL); + + if (!desc || !(desc->istate & IRQS_SUSPENDED) || + !irqd_is_wakeup_set(&desc->irq_data)) + return; + + desc->istate &= ~IRQS_SUSPENDED; + irqd_set(&desc->irq_data, IRQD_WAKEUP_ARMED); + __enable_irq(desc); + + irq_put_desc_busunlock(desc, flags); +} + +/** * irq_pm_syscore_ops - enable interrupt lines early * * Enable all interrupt lines with %IRQF_EARLY_RESUME set. diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index da9addb8d655..cfc4f088a0e7 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -100,10 +100,6 @@ static int irq_affinity_hint_proc_show(struct seq_file *m, void *v) return 0; } -#ifndef is_affinity_mask_valid -#define is_affinity_mask_valid(val) 1 -#endif - int no_irq_affinity; static int irq_affinity_proc_show(struct seq_file *m, void *v) { @@ -136,11 +132,6 @@ static ssize_t write_irq_affinity(int type, struct file *file, if (err) goto free_cpumask; - if (!is_affinity_mask_valid(new_value)) { - err = -EINVAL; - goto free_cpumask; - } - /* * Do not allow disabling IRQs completely - it's a too easy * way to make the system unusable accidentally :-) At least @@ -232,11 +223,6 @@ static ssize_t default_affinity_write(struct file *file, if (err) goto out; - if (!is_affinity_mask_valid(new_value)) { - err = -EINVAL; - goto out; - } - /* * Do not allow disabling IRQs completely - it's a too easy * way to make the system unusable accidentally :-) At least diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c index 95414ad3506a..98c04ca5fa43 100644 --- a/kernel/irq/resend.c +++ b/kernel/irq/resend.c @@ -36,6 +36,8 @@ static void resend_irqs(unsigned long arg) irq = find_first_bit(irqs_resend, nr_irqs); clear_bit(irq, irqs_resend); desc = irq_to_desc(irq); + if (!desc) + continue; local_irq_disable(); desc->handle_irq(desc); local_irq_enable(); diff --git a/kernel/jump_label.c b/kernel/jump_label.c index df3008419a1d..cdb3ffab128b 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -407,7 +407,9 @@ static bool jump_label_can_update(struct jump_entry *entry, bool init) return false; if (!kernel_text_address(jump_entry_code(entry))) { - WARN_ONCE(1, "can't patch jump_label at %pS", (void *)jump_entry_code(entry)); + WARN_ONCE(!jump_entry_is_init(entry), + "can't patch jump_label at %pS", + (void *)jump_entry_code(entry)); return false; } diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 95a260f9214b..136ce049c4ad 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -263,8 +263,10 @@ int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, { char namebuf[KSYM_NAME_LEN]; - if (is_ksym_addr(addr)) - return !!get_symbol_pos(addr, symbolsize, offset); + if (is_ksym_addr(addr)) { + get_symbol_pos(addr, symbolsize, offset); + return 1; + } return !!module_address_lookup(addr, symbolsize, offset, NULL, namebuf) || !!__bpf_address_lookup(addr, symbolsize, offset, namebuf); } diff --git a/kernel/kexec_elf.c b/kernel/kexec_elf.c new file mode 100644 index 000000000000..d3689632e8b9 --- /dev/null +++ b/kernel/kexec_elf.c @@ -0,0 +1,430 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Load ELF vmlinux file for the kexec_file_load syscall. + * + * Copyright (C) 2004 Adam Litke (agl@us.ibm.com) + * Copyright (C) 2004 IBM Corp. + * Copyright (C) 2005 R Sharada (sharada@in.ibm.com) + * Copyright (C) 2006 Mohan Kumar M (mohan@in.ibm.com) + * Copyright (C) 2016 IBM Corporation + * + * Based on kexec-tools' kexec-elf-exec.c and kexec-elf-ppc64.c. + * Heavily modified for the kernel by + * Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>. + */ + +#define pr_fmt(fmt) "kexec_elf: " fmt + +#include <linux/elf.h> +#include <linux/kexec.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/types.h> + +static inline bool elf_is_elf_file(const struct elfhdr *ehdr) +{ + return memcmp(ehdr->e_ident, ELFMAG, SELFMAG) == 0; +} + +static uint64_t elf64_to_cpu(const struct elfhdr *ehdr, uint64_t value) +{ + if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB) + value = le64_to_cpu(value); + else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB) + value = be64_to_cpu(value); + + return value; +} + +static uint32_t elf32_to_cpu(const struct elfhdr *ehdr, uint32_t value) +{ + if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB) + value = le32_to_cpu(value); + else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB) + value = be32_to_cpu(value); + + return value; +} + +static uint16_t elf16_to_cpu(const struct elfhdr *ehdr, uint16_t value) +{ + if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB) + value = le16_to_cpu(value); + else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB) + value = be16_to_cpu(value); + + return value; +} + +/** + * elf_is_ehdr_sane - check that it is safe to use the ELF header + * @buf_len: size of the buffer in which the ELF file is loaded. + */ +static bool elf_is_ehdr_sane(const struct elfhdr *ehdr, size_t buf_len) +{ + if (ehdr->e_phnum > 0 && ehdr->e_phentsize != sizeof(struct elf_phdr)) { + pr_debug("Bad program header size.\n"); + return false; + } else if (ehdr->e_shnum > 0 && + ehdr->e_shentsize != sizeof(struct elf_shdr)) { + pr_debug("Bad section header size.\n"); + return false; + } else if (ehdr->e_ident[EI_VERSION] != EV_CURRENT || + ehdr->e_version != EV_CURRENT) { + pr_debug("Unknown ELF version.\n"); + return false; + } + + if (ehdr->e_phoff > 0 && ehdr->e_phnum > 0) { + size_t phdr_size; + + /* + * e_phnum is at most 65535 so calculating the size of the + * program header cannot overflow. + */ + phdr_size = sizeof(struct elf_phdr) * ehdr->e_phnum; + + /* Sanity check the program header table location. */ + if (ehdr->e_phoff + phdr_size < ehdr->e_phoff) { + pr_debug("Program headers at invalid location.\n"); + return false; + } else if (ehdr->e_phoff + phdr_size > buf_len) { + pr_debug("Program headers truncated.\n"); + return false; + } + } + + if (ehdr->e_shoff > 0 && ehdr->e_shnum > 0) { + size_t shdr_size; + + /* + * e_shnum is at most 65536 so calculating + * the size of the section header cannot overflow. + */ + shdr_size = sizeof(struct elf_shdr) * ehdr->e_shnum; + + /* Sanity check the section header table location. */ + if (ehdr->e_shoff + shdr_size < ehdr->e_shoff) { + pr_debug("Section headers at invalid location.\n"); + return false; + } else if (ehdr->e_shoff + shdr_size > buf_len) { + pr_debug("Section headers truncated.\n"); + return false; + } + } + + return true; +} + +static int elf_read_ehdr(const char *buf, size_t len, struct elfhdr *ehdr) +{ + struct elfhdr *buf_ehdr; + + if (len < sizeof(*buf_ehdr)) { + pr_debug("Buffer is too small to hold ELF header.\n"); + return -ENOEXEC; + } + + memset(ehdr, 0, sizeof(*ehdr)); + memcpy(ehdr->e_ident, buf, sizeof(ehdr->e_ident)); + if (!elf_is_elf_file(ehdr)) { + pr_debug("No ELF header magic.\n"); + return -ENOEXEC; + } + + if (ehdr->e_ident[EI_CLASS] != ELF_CLASS) { + pr_debug("Not a supported ELF class.\n"); + return -ENOEXEC; + } else if (ehdr->e_ident[EI_DATA] != ELFDATA2LSB && + ehdr->e_ident[EI_DATA] != ELFDATA2MSB) { + pr_debug("Not a supported ELF data format.\n"); + return -ENOEXEC; + } + + buf_ehdr = (struct elfhdr *) buf; + if (elf16_to_cpu(ehdr, buf_ehdr->e_ehsize) != sizeof(*buf_ehdr)) { + pr_debug("Bad ELF header size.\n"); + return -ENOEXEC; + } + + ehdr->e_type = elf16_to_cpu(ehdr, buf_ehdr->e_type); + ehdr->e_machine = elf16_to_cpu(ehdr, buf_ehdr->e_machine); + ehdr->e_version = elf32_to_cpu(ehdr, buf_ehdr->e_version); + ehdr->e_flags = elf32_to_cpu(ehdr, buf_ehdr->e_flags); + ehdr->e_phentsize = elf16_to_cpu(ehdr, buf_ehdr->e_phentsize); + ehdr->e_phnum = elf16_to_cpu(ehdr, buf_ehdr->e_phnum); + ehdr->e_shentsize = elf16_to_cpu(ehdr, buf_ehdr->e_shentsize); + ehdr->e_shnum = elf16_to_cpu(ehdr, buf_ehdr->e_shnum); + ehdr->e_shstrndx = elf16_to_cpu(ehdr, buf_ehdr->e_shstrndx); + + switch (ehdr->e_ident[EI_CLASS]) { + case ELFCLASS64: + ehdr->e_entry = elf64_to_cpu(ehdr, buf_ehdr->e_entry); + ehdr->e_phoff = elf64_to_cpu(ehdr, buf_ehdr->e_phoff); + ehdr->e_shoff = elf64_to_cpu(ehdr, buf_ehdr->e_shoff); + break; + + case ELFCLASS32: + ehdr->e_entry = elf32_to_cpu(ehdr, buf_ehdr->e_entry); + ehdr->e_phoff = elf32_to_cpu(ehdr, buf_ehdr->e_phoff); + ehdr->e_shoff = elf32_to_cpu(ehdr, buf_ehdr->e_shoff); + break; + + default: + pr_debug("Unknown ELF class.\n"); + return -EINVAL; + } + + return elf_is_ehdr_sane(ehdr, len) ? 0 : -ENOEXEC; +} + +/** + * elf_is_phdr_sane - check that it is safe to use the program header + * @buf_len: size of the buffer in which the ELF file is loaded. + */ +static bool elf_is_phdr_sane(const struct elf_phdr *phdr, size_t buf_len) +{ + + if (phdr->p_offset + phdr->p_filesz < phdr->p_offset) { + pr_debug("ELF segment location wraps around.\n"); + return false; + } else if (phdr->p_offset + phdr->p_filesz > buf_len) { + pr_debug("ELF segment not in file.\n"); + return false; + } else if (phdr->p_paddr + phdr->p_memsz < phdr->p_paddr) { + pr_debug("ELF segment address wraps around.\n"); + return false; + } + + return true; +} + +static int elf_read_phdr(const char *buf, size_t len, + struct kexec_elf_info *elf_info, + int idx) +{ + /* Override the const in proghdrs, we are the ones doing the loading. */ + struct elf_phdr *phdr = (struct elf_phdr *) &elf_info->proghdrs[idx]; + const struct elfhdr *ehdr = elf_info->ehdr; + const char *pbuf; + struct elf_phdr *buf_phdr; + + pbuf = buf + elf_info->ehdr->e_phoff + (idx * sizeof(*buf_phdr)); + buf_phdr = (struct elf_phdr *) pbuf; + + phdr->p_type = elf32_to_cpu(elf_info->ehdr, buf_phdr->p_type); + phdr->p_flags = elf32_to_cpu(elf_info->ehdr, buf_phdr->p_flags); + + switch (ehdr->e_ident[EI_CLASS]) { + case ELFCLASS64: + phdr->p_offset = elf64_to_cpu(ehdr, buf_phdr->p_offset); + phdr->p_paddr = elf64_to_cpu(ehdr, buf_phdr->p_paddr); + phdr->p_vaddr = elf64_to_cpu(ehdr, buf_phdr->p_vaddr); + phdr->p_filesz = elf64_to_cpu(ehdr, buf_phdr->p_filesz); + phdr->p_memsz = elf64_to_cpu(ehdr, buf_phdr->p_memsz); + phdr->p_align = elf64_to_cpu(ehdr, buf_phdr->p_align); + break; + + case ELFCLASS32: + phdr->p_offset = elf32_to_cpu(ehdr, buf_phdr->p_offset); + phdr->p_paddr = elf32_to_cpu(ehdr, buf_phdr->p_paddr); + phdr->p_vaddr = elf32_to_cpu(ehdr, buf_phdr->p_vaddr); + phdr->p_filesz = elf32_to_cpu(ehdr, buf_phdr->p_filesz); + phdr->p_memsz = elf32_to_cpu(ehdr, buf_phdr->p_memsz); + phdr->p_align = elf32_to_cpu(ehdr, buf_phdr->p_align); + break; + + default: + pr_debug("Unknown ELF class.\n"); + return -EINVAL; + } + + return elf_is_phdr_sane(phdr, len) ? 0 : -ENOEXEC; +} + +/** + * elf_read_phdrs - read the program headers from the buffer + * + * This function assumes that the program header table was checked for sanity. + * Use elf_is_ehdr_sane() if it wasn't. + */ +static int elf_read_phdrs(const char *buf, size_t len, + struct kexec_elf_info *elf_info) +{ + size_t phdr_size, i; + const struct elfhdr *ehdr = elf_info->ehdr; + + /* + * e_phnum is at most 65535 so calculating the size of the + * program header cannot overflow. + */ + phdr_size = sizeof(struct elf_phdr) * ehdr->e_phnum; + + elf_info->proghdrs = kzalloc(phdr_size, GFP_KERNEL); + if (!elf_info->proghdrs) + return -ENOMEM; + + for (i = 0; i < ehdr->e_phnum; i++) { + int ret; + + ret = elf_read_phdr(buf, len, elf_info, i); + if (ret) { + kfree(elf_info->proghdrs); + elf_info->proghdrs = NULL; + return ret; + } + } + + return 0; +} + +/** + * elf_read_from_buffer - read ELF file and sets up ELF header and ELF info + * @buf: Buffer to read ELF file from. + * @len: Size of @buf. + * @ehdr: Pointer to existing struct which will be populated. + * @elf_info: Pointer to existing struct which will be populated. + * + * This function allows reading ELF files with different byte order than + * the kernel, byte-swapping the fields as needed. + * + * Return: + * On success returns 0, and the caller should call + * kexec_free_elf_info(elf_info) to free the memory allocated for the section + * and program headers. + */ +static int elf_read_from_buffer(const char *buf, size_t len, + struct elfhdr *ehdr, + struct kexec_elf_info *elf_info) +{ + int ret; + + ret = elf_read_ehdr(buf, len, ehdr); + if (ret) + return ret; + + elf_info->buffer = buf; + elf_info->ehdr = ehdr; + if (ehdr->e_phoff > 0 && ehdr->e_phnum > 0) { + ret = elf_read_phdrs(buf, len, elf_info); + if (ret) + return ret; + } + return 0; +} + +/** + * kexec_free_elf_info - free memory allocated by elf_read_from_buffer + */ +void kexec_free_elf_info(struct kexec_elf_info *elf_info) +{ + kfree(elf_info->proghdrs); + memset(elf_info, 0, sizeof(*elf_info)); +} +/** + * kexec_build_elf_info - read ELF executable and check that we can use it + */ +int kexec_build_elf_info(const char *buf, size_t len, struct elfhdr *ehdr, + struct kexec_elf_info *elf_info) +{ + int i; + int ret; + + ret = elf_read_from_buffer(buf, len, ehdr, elf_info); + if (ret) + return ret; + + /* Big endian vmlinux has type ET_DYN. */ + if (ehdr->e_type != ET_EXEC && ehdr->e_type != ET_DYN) { + pr_err("Not an ELF executable.\n"); + goto error; + } else if (!elf_info->proghdrs) { + pr_err("No ELF program header.\n"); + goto error; + } + + for (i = 0; i < ehdr->e_phnum; i++) { + /* + * Kexec does not support loading interpreters. + * In addition this check keeps us from attempting + * to kexec ordinay executables. + */ + if (elf_info->proghdrs[i].p_type == PT_INTERP) { + pr_err("Requires an ELF interpreter.\n"); + goto error; + } + } + + return 0; +error: + kexec_free_elf_info(elf_info); + return -ENOEXEC; +} + + +int kexec_elf_probe(const char *buf, unsigned long len) +{ + struct elfhdr ehdr; + struct kexec_elf_info elf_info; + int ret; + + ret = kexec_build_elf_info(buf, len, &ehdr, &elf_info); + if (ret) + return ret; + + kexec_free_elf_info(&elf_info); + + return elf_check_arch(&ehdr) ? 0 : -ENOEXEC; +} + +/** + * kexec_elf_load - load ELF executable image + * @lowest_load_addr: On return, will be the address where the first PT_LOAD + * section will be loaded in memory. + * + * Return: + * 0 on success, negative value on failure. + */ +int kexec_elf_load(struct kimage *image, struct elfhdr *ehdr, + struct kexec_elf_info *elf_info, + struct kexec_buf *kbuf, + unsigned long *lowest_load_addr) +{ + unsigned long lowest_addr = UINT_MAX; + int ret; + size_t i; + + /* Read in the PT_LOAD segments. */ + for (i = 0; i < ehdr->e_phnum; i++) { + unsigned long load_addr; + size_t size; + const struct elf_phdr *phdr; + + phdr = &elf_info->proghdrs[i]; + if (phdr->p_type != PT_LOAD) + continue; + + size = phdr->p_filesz; + if (size > phdr->p_memsz) + size = phdr->p_memsz; + + kbuf->buffer = (void *) elf_info->buffer + phdr->p_offset; + kbuf->bufsz = size; + kbuf->memsz = phdr->p_memsz; + kbuf->buf_align = phdr->p_align; + kbuf->buf_min = phdr->p_paddr; + kbuf->mem = KEXEC_BUF_MEM_UNKNOWN; + ret = kexec_add_buffer(kbuf); + if (ret) + goto out; + load_addr = kbuf->mem; + + if (load_addr < lowest_addr) + lowest_addr = load_addr; + } + + *lowest_load_addr = lowest_addr; + ret = 0; + out: + return ret; +} diff --git a/kernel/kprobes.c b/kernel/kprobes.c index f57deec96ba1..53534aa258a6 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1538,7 +1538,8 @@ static int check_kprobe_address_safe(struct kprobe *p, /* Ensure it is not in reserved area nor out of text */ if (!kernel_text_address((unsigned long) p->addr) || within_kprobe_blacklist((unsigned long) p->addr) || - jump_label_text_reserved(p->addr, p->addr)) { + jump_label_text_reserved(p->addr, p->addr) || + find_bug((unsigned long)p->addr)) { ret = -EINVAL; goto out; } @@ -1930,7 +1931,7 @@ int register_kretprobe(struct kretprobe *rp) /* Pre-allocate memory for max kretprobe instances */ if (rp->maxactive <= 0) { -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION rp->maxactive = max_t(unsigned int, 10, 2*num_possible_cpus()); #else rp->maxactive = num_possible_cpus(); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 4861cf8e274b..233459c03b5a 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -449,33 +449,101 @@ static void print_lockdep_off(const char *bug_msg) unsigned long nr_stack_trace_entries; #ifdef CONFIG_PROVE_LOCKING +/** + * struct lock_trace - single stack backtrace + * @hash_entry: Entry in a stack_trace_hash[] list. + * @hash: jhash() of @entries. + * @nr_entries: Number of entries in @entries. + * @entries: Actual stack backtrace. + */ +struct lock_trace { + struct hlist_node hash_entry; + u32 hash; + u32 nr_entries; + unsigned long entries[0] __aligned(sizeof(unsigned long)); +}; +#define LOCK_TRACE_SIZE_IN_LONGS \ + (sizeof(struct lock_trace) / sizeof(unsigned long)) /* - * Stack-trace: tightly packed array of stack backtrace - * addresses. Protected by the graph_lock. + * Stack-trace: sequence of lock_trace structures. Protected by the graph_lock. */ static unsigned long stack_trace[MAX_STACK_TRACE_ENTRIES]; +static struct hlist_head stack_trace_hash[STACK_TRACE_HASH_SIZE]; + +static bool traces_identical(struct lock_trace *t1, struct lock_trace *t2) +{ + return t1->hash == t2->hash && t1->nr_entries == t2->nr_entries && + memcmp(t1->entries, t2->entries, + t1->nr_entries * sizeof(t1->entries[0])) == 0; +} -static int save_trace(struct lock_trace *trace) +static struct lock_trace *save_trace(void) { - unsigned long *entries = stack_trace + nr_stack_trace_entries; + struct lock_trace *trace, *t2; + struct hlist_head *hash_head; + u32 hash; unsigned int max_entries; - trace->offset = nr_stack_trace_entries; - max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries; - trace->nr_entries = stack_trace_save(entries, max_entries, 3); - nr_stack_trace_entries += trace->nr_entries; + BUILD_BUG_ON_NOT_POWER_OF_2(STACK_TRACE_HASH_SIZE); + BUILD_BUG_ON(LOCK_TRACE_SIZE_IN_LONGS >= MAX_STACK_TRACE_ENTRIES); + + trace = (struct lock_trace *)(stack_trace + nr_stack_trace_entries); + max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries - + LOCK_TRACE_SIZE_IN_LONGS; + trace->nr_entries = stack_trace_save(trace->entries, max_entries, 3); - if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES-1) { + if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES - + LOCK_TRACE_SIZE_IN_LONGS - 1) { if (!debug_locks_off_graph_unlock()) - return 0; + return NULL; print_lockdep_off("BUG: MAX_STACK_TRACE_ENTRIES too low!"); dump_stack(); - return 0; + return NULL; } - return 1; + hash = jhash(trace->entries, trace->nr_entries * + sizeof(trace->entries[0]), 0); + trace->hash = hash; + hash_head = stack_trace_hash + (hash & (STACK_TRACE_HASH_SIZE - 1)); + hlist_for_each_entry(t2, hash_head, hash_entry) { + if (traces_identical(trace, t2)) + return t2; + } + nr_stack_trace_entries += LOCK_TRACE_SIZE_IN_LONGS + trace->nr_entries; + hlist_add_head(&trace->hash_entry, hash_head); + + return trace; +} + +/* Return the number of stack traces in the stack_trace[] array. */ +u64 lockdep_stack_trace_count(void) +{ + struct lock_trace *trace; + u64 c = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(stack_trace_hash); i++) { + hlist_for_each_entry(trace, &stack_trace_hash[i], hash_entry) { + c++; + } + } + + return c; +} + +/* Return the number of stack hash chains that have at least one stack trace. */ +u64 lockdep_stack_hash_count(void) +{ + u64 c = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(stack_trace_hash); i++) + if (!hlist_empty(&stack_trace_hash[i])) + c++; + + return c; } #endif @@ -511,7 +579,7 @@ static const char *usage_str[] = }; #endif -const char * __get_key_name(struct lockdep_subclass_key *key, char *str) +const char *__get_key_name(const struct lockdep_subclass_key *key, char *str) { return kallsyms_lookup((unsigned long)key, NULL, NULL, NULL, str); } @@ -620,7 +688,7 @@ static void print_lock(struct held_lock *hlock) return; } - printk(KERN_CONT "%p", hlock->instance); + printk(KERN_CONT "%px", hlock->instance); print_lock_name(lock); printk(KERN_CONT ", at: %pS\n", (void *)hlock->acquire_ip); } @@ -1235,7 +1303,7 @@ static struct lock_list *alloc_list_entry(void) static int add_lock_to_list(struct lock_class *this, struct lock_class *links_to, struct list_head *head, unsigned long ip, int distance, - struct lock_trace *trace) + const struct lock_trace *trace) { struct lock_list *entry; /* @@ -1249,7 +1317,7 @@ static int add_lock_to_list(struct lock_class *this, entry->class = this; entry->links_to = links_to; entry->distance = distance; - entry->trace = *trace; + entry->trace = trace; /* * Both allocation and removal are done under the graph lock; but * iteration is under RCU-sched; see look_up_lock_class() and @@ -1470,11 +1538,10 @@ static inline int __bfs_backwards(struct lock_list *src_entry, } -static void print_lock_trace(struct lock_trace *trace, unsigned int spaces) +static void print_lock_trace(const struct lock_trace *trace, + unsigned int spaces) { - unsigned long *entries = stack_trace + trace->offset; - - stack_trace_print(entries, trace->nr_entries, spaces); + stack_trace_print(trace->entries, trace->nr_entries, spaces); } /* @@ -1489,7 +1556,7 @@ print_circular_bug_entry(struct lock_list *target, int depth) printk("\n-> #%u", depth); print_lock_name(target->class); printk(KERN_CONT ":\n"); - print_lock_trace(&target->trace, 6); + print_lock_trace(target->trace, 6); } static void @@ -1592,7 +1659,8 @@ static noinline void print_circular_bug(struct lock_list *this, if (!debug_locks_off_graph_unlock() || debug_locks_silent) return; - if (!save_trace(&this->trace)) + this->trace = save_trace(); + if (!this->trace) return; depth = get_lock_depth(target); @@ -1715,7 +1783,7 @@ check_path(struct lock_class *target, struct lock_list *src_entry, */ static noinline int check_noncircular(struct held_lock *src, struct held_lock *target, - struct lock_trace *trace) + struct lock_trace **const trace) { int ret; struct lock_list *uninitialized_var(target_entry); @@ -1729,13 +1797,13 @@ check_noncircular(struct held_lock *src, struct held_lock *target, ret = check_path(hlock_class(target), &src_entry, &target_entry); if (unlikely(!ret)) { - if (!trace->nr_entries) { + if (!*trace) { /* * If save_trace fails here, the printing might * trigger a WARN but because of the !nr_entries it * should not do bad things. */ - save_trace(trace); + *trace = save_trace(); } print_circular_bug(&src_entry, target_entry, src, target); @@ -1859,7 +1927,7 @@ static void print_lock_class_header(struct lock_class *class, int depth) len += printk("%*s %s", depth, "", usage_str[bit]); len += printk(KERN_CONT " at:\n"); - print_lock_trace(class->usage_traces + bit, len); + print_lock_trace(class->usage_traces[bit], len); } } printk("%*s }\n", depth, ""); @@ -1884,7 +1952,7 @@ print_shortest_lock_dependencies(struct lock_list *leaf, do { print_lock_class_header(entry->class, depth); printk("%*s ... acquired at:\n", depth, ""); - print_lock_trace(&entry->trace, 2); + print_lock_trace(entry->trace, 2); printk("\n"); if (depth == 0 && (entry != root)) { @@ -1995,14 +2063,14 @@ print_bad_irq_dependency(struct task_struct *curr, print_lock_name(backwards_entry->class); pr_warn("\n... which became %s-irq-safe at:\n", irqclass); - print_lock_trace(backwards_entry->class->usage_traces + bit1, 1); + print_lock_trace(backwards_entry->class->usage_traces[bit1], 1); pr_warn("\nto a %s-irq-unsafe lock:\n", irqclass); print_lock_name(forwards_entry->class); pr_warn("\n... which became %s-irq-unsafe at:\n", irqclass); pr_warn("..."); - print_lock_trace(forwards_entry->class->usage_traces + bit2, 1); + print_lock_trace(forwards_entry->class->usage_traces[bit2], 1); pr_warn("\nother info that might help us debug this:\n\n"); print_irq_lock_scenario(backwards_entry, forwards_entry, @@ -2011,13 +2079,15 @@ print_bad_irq_dependency(struct task_struct *curr, lockdep_print_held_locks(curr); pr_warn("\nthe dependencies between %s-irq-safe lock and the holding lock:\n", irqclass); - if (!save_trace(&prev_root->trace)) + prev_root->trace = save_trace(); + if (!prev_root->trace) return; print_shortest_lock_dependencies(backwards_entry, prev_root); pr_warn("\nthe dependencies between the lock to be acquired"); pr_warn(" and %s-irq-unsafe lock:\n", irqclass); - if (!save_trace(&next_root->trace)) + next_root->trace = save_trace(); + if (!next_root->trace) return; print_shortest_lock_dependencies(forwards_entry, next_root); @@ -2369,7 +2439,8 @@ check_deadlock(struct task_struct *curr, struct held_lock *next) */ static int check_prev_add(struct task_struct *curr, struct held_lock *prev, - struct held_lock *next, int distance, struct lock_trace *trace) + struct held_lock *next, int distance, + struct lock_trace **const trace) { struct lock_list *entry; int ret; @@ -2444,8 +2515,11 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, return ret; #endif - if (!trace->nr_entries && !save_trace(trace)) - return 0; + if (!*trace) { + *trace = save_trace(); + if (!*trace) + return 0; + } /* * Ok, all validations passed, add the new lock @@ -2453,14 +2527,14 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, */ ret = add_lock_to_list(hlock_class(next), hlock_class(prev), &hlock_class(prev)->locks_after, - next->acquire_ip, distance, trace); + next->acquire_ip, distance, *trace); if (!ret) return 0; ret = add_lock_to_list(hlock_class(prev), hlock_class(next), &hlock_class(next)->locks_before, - next->acquire_ip, distance, trace); + next->acquire_ip, distance, *trace); if (!ret) return 0; @@ -2476,7 +2550,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, static int check_prevs_add(struct task_struct *curr, struct held_lock *next) { - struct lock_trace trace = { .nr_entries = 0 }; + struct lock_trace *trace = NULL; int depth = curr->lockdep_depth; struct held_lock *hlock; @@ -3015,7 +3089,7 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this, print_lock(this); pr_warn("{%s} state was registered at:\n", usage_str[prev_bit]); - print_lock_trace(hlock_class(this)->usage_traces + prev_bit, 1); + print_lock_trace(hlock_class(this)->usage_traces[prev_bit], 1); print_irqtrace_events(curr); pr_warn("\nother info that might help us debug this:\n"); @@ -3096,7 +3170,8 @@ print_irq_inversion_bug(struct task_struct *curr, lockdep_print_held_locks(curr); pr_warn("\nthe shortest dependencies between 2nd lock and 1st lock:\n"); - if (!save_trace(&root->trace)) + root->trace = save_trace(); + if (!root->trace) return; print_shortest_lock_dependencies(other, root); @@ -3580,7 +3655,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, hlock_class(this)->usage_mask |= new_mask; - if (!save_trace(hlock_class(this)->usage_traces + new_bit)) + if (!(hlock_class(this)->usage_traces[new_bit] = save_trace())) return 0; switch (new_bit) { @@ -5157,6 +5232,12 @@ void __init lockdep_init(void) ) / 1024 ); +#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) + printk(" memory used for stack traces: %zu kB\n", + (sizeof(stack_trace) + sizeof(stack_trace_hash)) / 1024 + ); +#endif + printk(" per task-struct memory footprint: %zu bytes\n", sizeof(((struct task_struct *)NULL)->held_locks)); } diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index cc83568d5012..18d85aebbb57 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -92,6 +92,7 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ = #define MAX_LOCKDEP_ENTRIES 16384UL #define MAX_LOCKDEP_CHAINS_BITS 15 #define MAX_STACK_TRACE_ENTRIES 262144UL +#define STACK_TRACE_HASH_SIZE 8192 #else #define MAX_LOCKDEP_ENTRIES 32768UL @@ -102,6 +103,7 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ = * addresses. Protected by the hash_lock. */ #define MAX_STACK_TRACE_ENTRIES 524288UL +#define STACK_TRACE_HASH_SIZE 16384 #endif #define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS) @@ -116,7 +118,8 @@ extern struct lock_chain lock_chains[]; extern void get_usage_chars(struct lock_class *class, char usage[LOCK_USAGE_CHARS]); -extern const char * __get_key_name(struct lockdep_subclass_key *key, char *str); +extern const char *__get_key_name(const struct lockdep_subclass_key *key, + char *str); struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i); @@ -137,6 +140,10 @@ extern unsigned int max_bfs_queue_depth; #ifdef CONFIG_PROVE_LOCKING extern unsigned long lockdep_count_forward_deps(struct lock_class *); extern unsigned long lockdep_count_backward_deps(struct lock_class *); +#ifdef CONFIG_TRACE_IRQFLAGS +u64 lockdep_stack_trace_count(void); +u64 lockdep_stack_hash_count(void); +#endif #else static inline unsigned long lockdep_count_forward_deps(struct lock_class *class) diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index bda006f8a88b..dadb7b7fba37 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -285,6 +285,12 @@ static int lockdep_stats_show(struct seq_file *m, void *v) nr_process_chains); seq_printf(m, " stack-trace entries: %11lu [max: %lu]\n", nr_stack_trace_entries, MAX_STACK_TRACE_ENTRIES); +#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) + seq_printf(m, " number of stack traces: %llu\n", + lockdep_stack_trace_count()); + seq_printf(m, " number of stack hash chains: %llu\n", + lockdep_stack_hash_count()); +#endif seq_printf(m, " combined max dependencies: %11u\n", (nr_hardirq_chains + 1) * (nr_softirq_chains + 1) * @@ -399,7 +405,7 @@ static void seq_lock_time(struct seq_file *m, struct lock_time *lt) static void seq_stats(struct seq_file *m, struct lock_stat_data *data) { - struct lockdep_subclass_key *ckey; + const struct lockdep_subclass_key *ckey; struct lock_class_stats *stats; struct lock_class *class; const char *cname; diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 5e069734363c..468a9b8422e3 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -65,11 +65,37 @@ EXPORT_SYMBOL(__mutex_init); #define MUTEX_FLAGS 0x07 +/* + * Internal helper function; C doesn't allow us to hide it :/ + * + * DO NOT USE (outside of mutex code). + */ +static inline struct task_struct *__mutex_owner(struct mutex *lock) +{ + return (struct task_struct *)(atomic_long_read(&lock->owner) & ~MUTEX_FLAGS); +} + static inline struct task_struct *__owner_task(unsigned long owner) { return (struct task_struct *)(owner & ~MUTEX_FLAGS); } +bool mutex_is_locked(struct mutex *lock) +{ + return __mutex_owner(lock) != NULL; +} +EXPORT_SYMBOL(mutex_is_locked); + +__must_check enum mutex_trylock_recursive_enum +mutex_trylock_recursive(struct mutex *lock) +{ + if (unlikely(__mutex_owner(lock) == current)) + return MUTEX_TRYLOCK_RECURSIVE; + + return mutex_trylock(lock); +} +EXPORT_SYMBOL(mutex_trylock_recursive); + static inline unsigned long __owner_flags(unsigned long owner) { return owner & MUTEX_FLAGS; diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index fa83d36e30c6..2874bf556162 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -628,8 +628,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, } /* [10] Grab the next task, i.e. owner of @lock */ - task = rt_mutex_owner(lock); - get_task_struct(task); + task = get_task_struct(rt_mutex_owner(lock)); raw_spin_lock(&task->pi_lock); /* @@ -709,8 +708,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, } /* [10] Grab the next task, i.e. the owner of @lock */ - task = rt_mutex_owner(lock); - get_task_struct(task); + task = get_task_struct(rt_mutex_owner(lock)); raw_spin_lock(&task->pi_lock); /* [11] requeue the pi waiters if necessary */ diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index bd0f0d05724c..eef04551eae7 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -105,8 +105,9 @@ #ifdef CONFIG_DEBUG_RWSEMS # define DEBUG_RWSEMS_WARN_ON(c, sem) do { \ if (!debug_locks_silent && \ - WARN_ONCE(c, "DEBUG_RWSEMS_WARN_ON(%s): count = 0x%lx, owner = 0x%lx, curr 0x%lx, list %sempty\n",\ + WARN_ONCE(c, "DEBUG_RWSEMS_WARN_ON(%s): count = 0x%lx, magic = 0x%lx, owner = 0x%lx, curr 0x%lx, list %sempty\n",\ #c, atomic_long_read(&(sem)->count), \ + (unsigned long) sem->magic, \ atomic_long_read(&(sem)->owner), (long)current, \ list_empty(&(sem)->wait_list) ? "" : "not ")) \ debug_locks_off(); \ @@ -330,6 +331,9 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name, debug_check_no_locks_freed((void *)sem, sizeof(*sem)); lockdep_init_map(&sem->dep_map, name, key, 0); #endif +#ifdef CONFIG_DEBUG_RWSEMS + sem->magic = sem; +#endif atomic_long_set(&sem->count, RWSEM_UNLOCKED_VALUE); raw_spin_lock_init(&sem->wait_lock); INIT_LIST_HEAD(&sem->wait_list); @@ -724,11 +728,12 @@ rwsem_spin_on_owner(struct rw_semaphore *sem, unsigned long nonspinnable) rcu_read_lock(); for (;;) { - if (atomic_long_read(&sem->count) & RWSEM_FLAG_HANDOFF) { - state = OWNER_NONSPINNABLE; - break; - } - + /* + * When a waiting writer set the handoff flag, it may spin + * on the owner as well. Once that writer acquires the lock, + * we can spin on it. So we don't need to quit even when the + * handoff bit is set. + */ new = rwsem_owner_flags(sem, &new_flags); if ((new != owner) || (new_flags != flags)) { state = rwsem_owner_state(new, new_flags, nonspinnable); @@ -974,6 +979,13 @@ static inline bool rwsem_reader_phase_trylock(struct rw_semaphore *sem, { return false; } + +static inline int +rwsem_spin_on_owner(struct rw_semaphore *sem, unsigned long nonspinnable) +{ + return 0; +} +#define OWNER_NULL 1 #endif /* @@ -1206,6 +1218,18 @@ wait: raw_spin_unlock_irq(&sem->wait_lock); + /* + * After setting the handoff bit and failing to acquire + * the lock, attempt to spin on owner to accelerate lock + * transfer. If the previous owner is a on-cpu writer and it + * has just released the lock, OWNER_NULL will be returned. + * In this case, we attempt to acquire the lock again + * without sleeping. + */ + if ((wstate == WRITER_HANDOFF) && + (rwsem_spin_on_owner(sem, 0) == OWNER_NULL)) + goto trylock_again; + /* Block until there are no active lockers. */ for (;;) { if (signal_pending_state(state, current)) @@ -1240,7 +1264,7 @@ wait: break; } } - +trylock_again: raw_spin_lock_irq(&sem->wait_lock); } __set_current_state(TASK_RUNNING); @@ -1338,11 +1362,14 @@ static inline int __down_read_killable(struct rw_semaphore *sem) static inline int __down_read_trylock(struct rw_semaphore *sem) { + long tmp; + + DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem); + /* * Optimize for the case when the rwsem is not locked at all. */ - long tmp = RWSEM_UNLOCKED_VALUE; - + tmp = RWSEM_UNLOCKED_VALUE; do { if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp, tmp + RWSEM_READER_BIAS)) { @@ -1383,8 +1410,11 @@ static inline int __down_write_killable(struct rw_semaphore *sem) static inline int __down_write_trylock(struct rw_semaphore *sem) { - long tmp = RWSEM_UNLOCKED_VALUE; + long tmp; + DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem); + + tmp = RWSEM_UNLOCKED_VALUE; if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp, RWSEM_WRITER_LOCKED)) { rwsem_set_owner(sem); @@ -1400,7 +1430,9 @@ inline void __up_read(struct rw_semaphore *sem) { long tmp; + DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem); DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem); + rwsem_clear_reader_owned(sem); tmp = atomic_long_add_return_release(-RWSEM_READER_BIAS, &sem->count); DEBUG_RWSEMS_WARN_ON(tmp < 0, sem); @@ -1418,12 +1450,14 @@ static inline void __up_write(struct rw_semaphore *sem) { long tmp; + DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem); /* * sem->owner may differ from current if the ownership is transferred * to an anonymous writer by setting the RWSEM_NONSPINNABLE bits. */ DEBUG_RWSEMS_WARN_ON((rwsem_owner(sem) != current) && !rwsem_test_oflags(sem, RWSEM_NONSPINNABLE), sem); + rwsem_clear_owner(sem); tmp = atomic_long_fetch_add_release(-RWSEM_WRITER_LOCKED, &sem->count); if (unlikely(tmp & RWSEM_FLAG_WAITERS)) diff --git a/kernel/padata.c b/kernel/padata.c index 15a8ad63f4ff..c3fec1413295 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -46,18 +46,13 @@ static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index) return target_cpu; } -static int padata_cpu_hash(struct parallel_data *pd) +static int padata_cpu_hash(struct parallel_data *pd, unsigned int seq_nr) { - unsigned int seq_nr; - int cpu_index; - /* * Hash the sequence numbers to the cpus by taking * seq_nr mod. number of cpus in use. */ - - seq_nr = atomic_inc_return(&pd->seq_nr); - cpu_index = seq_nr % cpumask_weight(pd->cpumask.pcpu); + int cpu_index = seq_nr % cpumask_weight(pd->cpumask.pcpu); return padata_index_to_cpu(pd, cpu_index); } @@ -94,17 +89,19 @@ static void padata_parallel_worker(struct work_struct *parallel_work) * * @pinst: padata instance * @padata: object to be parallelized - * @cb_cpu: cpu the serialization callback function will run on, - * must be in the serial cpumask of padata(i.e. cpumask.cbcpu). + * @cb_cpu: pointer to the CPU that the serialization callback function should + * run on. If it's not in the serial cpumask of @pinst + * (i.e. cpumask.cbcpu), this function selects a fallback CPU and if + * none found, returns -EINVAL. * * The parallelization callback function will run with BHs off. * Note: Every object which is parallelized by padata_do_parallel * must be seen by padata_do_serial. */ int padata_do_parallel(struct padata_instance *pinst, - struct padata_priv *padata, int cb_cpu) + struct padata_priv *padata, int *cb_cpu) { - int target_cpu, err; + int i, cpu, cpu_index, target_cpu, err; struct padata_parallel_queue *queue; struct parallel_data *pd; @@ -116,8 +113,19 @@ int padata_do_parallel(struct padata_instance *pinst, if (!(pinst->flags & PADATA_INIT) || pinst->flags & PADATA_INVALID) goto out; - if (!cpumask_test_cpu(cb_cpu, pd->cpumask.cbcpu)) - goto out; + if (!cpumask_test_cpu(*cb_cpu, pd->cpumask.cbcpu)) { + if (!cpumask_weight(pd->cpumask.cbcpu)) + goto out; + + /* Select an alternate fallback CPU and notify the caller. */ + cpu_index = *cb_cpu % cpumask_weight(pd->cpumask.cbcpu); + + cpu = cpumask_first(pd->cpumask.cbcpu); + for (i = 0; i < cpu_index; i++) + cpu = cpumask_next(cpu, pd->cpumask.cbcpu); + + *cb_cpu = cpu; + } err = -EBUSY; if ((pinst->flags & PADATA_RESET)) @@ -129,9 +137,10 @@ int padata_do_parallel(struct padata_instance *pinst, err = 0; atomic_inc(&pd->refcnt); padata->pd = pd; - padata->cb_cpu = cb_cpu; + padata->cb_cpu = *cb_cpu; - target_cpu = padata_cpu_hash(pd); + padata->seq_nr = atomic_inc_return(&pd->seq_nr); + target_cpu = padata_cpu_hash(pd, padata->seq_nr); padata->cpu = target_cpu; queue = per_cpu_ptr(pd->pqueue, target_cpu); @@ -139,7 +148,7 @@ int padata_do_parallel(struct padata_instance *pinst, list_add_tail(&padata->list, &queue->parallel.list); spin_unlock(&queue->parallel.lock); - queue_work_on(target_cpu, pinst->wq, &queue->work); + queue_work(pinst->parallel_wq, &queue->work); out: rcu_read_unlock_bh(); @@ -149,63 +158,53 @@ out: EXPORT_SYMBOL(padata_do_parallel); /* - * padata_get_next - Get the next object that needs serialization. + * padata_find_next - Find the next object that needs serialization. * * Return values are: * * A pointer to the control struct of the next object that needs * serialization, if present in one of the percpu reorder queues. * - * -EINPROGRESS, if the next object that needs serialization will + * NULL, if the next object that needs serialization will * be parallel processed by another cpu and is not yet present in * the cpu's reorder queue. - * - * -ENODATA, if this cpu has to do the parallel processing for - * the next object. */ -static struct padata_priv *padata_get_next(struct parallel_data *pd) +static struct padata_priv *padata_find_next(struct parallel_data *pd, + bool remove_object) { - int cpu, num_cpus; - unsigned int next_nr, next_index; struct padata_parallel_queue *next_queue; struct padata_priv *padata; struct padata_list *reorder; + int cpu = pd->cpu; - num_cpus = cpumask_weight(pd->cpumask.pcpu); - - /* - * Calculate the percpu reorder queue and the sequence - * number of the next object. - */ - next_nr = pd->processed; - next_index = next_nr % num_cpus; - cpu = padata_index_to_cpu(pd, next_index); next_queue = per_cpu_ptr(pd->pqueue, cpu); - reorder = &next_queue->reorder; spin_lock(&reorder->lock); - if (!list_empty(&reorder->list)) { - padata = list_entry(reorder->list.next, - struct padata_priv, list); - - list_del_init(&padata->list); - atomic_dec(&pd->reorder_objects); + if (list_empty(&reorder->list)) { + spin_unlock(&reorder->lock); + return NULL; + } - pd->processed++; + padata = list_entry(reorder->list.next, struct padata_priv, list); + /* + * Checks the rare case where two or more parallel jobs have hashed to + * the same CPU and one of the later ones finishes first. + */ + if (padata->seq_nr != pd->processed) { spin_unlock(&reorder->lock); - goto out; + return NULL; } - spin_unlock(&reorder->lock); - if (__this_cpu_read(pd->pqueue->cpu_index) == next_queue->cpu_index) { - padata = ERR_PTR(-ENODATA); - goto out; + if (remove_object) { + list_del_init(&padata->list); + atomic_dec(&pd->reorder_objects); + ++pd->processed; + pd->cpu = cpumask_next_wrap(cpu, pd->cpumask.pcpu, -1, false); } - padata = ERR_PTR(-EINPROGRESS); -out: + spin_unlock(&reorder->lock); return padata; } @@ -215,6 +214,7 @@ static void padata_reorder(struct parallel_data *pd) struct padata_priv *padata; struct padata_serial_queue *squeue; struct padata_instance *pinst = pd->pinst; + struct padata_parallel_queue *next_queue; /* * We need to ensure that only one cpu can work on dequeueing of @@ -230,27 +230,16 @@ static void padata_reorder(struct parallel_data *pd) return; while (1) { - padata = padata_get_next(pd); + padata = padata_find_next(pd, true); /* * If the next object that needs serialization is parallel * processed by another cpu and is still on it's way to the * cpu's reorder queue, nothing to do for now. */ - if (PTR_ERR(padata) == -EINPROGRESS) + if (!padata) break; - /* - * This cpu has to do the parallel processing of the next - * object. It's waiting in the cpu's parallelization queue, - * so exit immediately. - */ - if (PTR_ERR(padata) == -ENODATA) { - del_timer(&pd->timer); - spin_unlock_bh(&pd->lock); - return; - } - cb_cpu = padata->cb_cpu; squeue = per_cpu_ptr(pd->squeue, cb_cpu); @@ -258,77 +247,37 @@ static void padata_reorder(struct parallel_data *pd) list_add_tail(&padata->list, &squeue->serial.list); spin_unlock(&squeue->serial.lock); - queue_work_on(cb_cpu, pinst->wq, &squeue->work); + queue_work_on(cb_cpu, pinst->serial_wq, &squeue->work); } spin_unlock_bh(&pd->lock); /* * The next object that needs serialization might have arrived to - * the reorder queues in the meantime, we will be called again - * from the timer function if no one else cares for it. + * the reorder queues in the meantime. * - * Ensure reorder_objects is read after pd->lock is dropped so we see - * an increment from another task in padata_do_serial. Pairs with + * Ensure reorder queue is read after pd->lock is dropped so we see + * new objects from another task in padata_do_serial. Pairs with * smp_mb__after_atomic in padata_do_serial. */ smp_mb(); - if (atomic_read(&pd->reorder_objects) - && !(pinst->flags & PADATA_RESET)) - mod_timer(&pd->timer, jiffies + HZ); - else - del_timer(&pd->timer); - return; + next_queue = per_cpu_ptr(pd->pqueue, pd->cpu); + if (!list_empty(&next_queue->reorder.list) && + padata_find_next(pd, false)) + queue_work(pinst->serial_wq, &pd->reorder_work); } static void invoke_padata_reorder(struct work_struct *work) { - struct padata_parallel_queue *pqueue; struct parallel_data *pd; local_bh_disable(); - pqueue = container_of(work, struct padata_parallel_queue, reorder_work); - pd = pqueue->pd; + pd = container_of(work, struct parallel_data, reorder_work); padata_reorder(pd); local_bh_enable(); } -static void padata_reorder_timer(struct timer_list *t) -{ - struct parallel_data *pd = from_timer(pd, t, timer); - unsigned int weight; - int target_cpu, cpu; - - cpu = get_cpu(); - - /* We don't lock pd here to not interfere with parallel processing - * padata_reorder() calls on other CPUs. We just need any CPU out of - * the cpumask.pcpu set. It would be nice if it's the right one but - * it doesn't matter if we're off to the next one by using an outdated - * pd->processed value. - */ - weight = cpumask_weight(pd->cpumask.pcpu); - target_cpu = padata_index_to_cpu(pd, pd->processed % weight); - - /* ensure to call the reorder callback on the correct CPU */ - if (cpu != target_cpu) { - struct padata_parallel_queue *pqueue; - struct padata_instance *pinst; - - /* The timer function is serialized wrt itself -- no locking - * needed. - */ - pinst = pd->pinst; - pqueue = per_cpu_ptr(pd->pqueue, target_cpu); - queue_work_on(target_cpu, pinst->wq, &pqueue->reorder_work); - } else { - padata_reorder(pd); - } - - put_cpu(); -} - static void padata_serial_worker(struct work_struct *serial_work) { struct padata_serial_queue *squeue; @@ -367,47 +316,28 @@ static void padata_serial_worker(struct work_struct *serial_work) */ void padata_do_serial(struct padata_priv *padata) { - int cpu; - struct padata_parallel_queue *pqueue; - struct parallel_data *pd; - int reorder_via_wq = 0; - - pd = padata->pd; - - cpu = get_cpu(); - - /* We need to run on the same CPU padata_do_parallel(.., padata, ..) - * was called on -- or, at least, enqueue the padata object into the - * correct per-cpu queue. - */ - if (cpu != padata->cpu) { - reorder_via_wq = 1; - cpu = padata->cpu; - } - - pqueue = per_cpu_ptr(pd->pqueue, cpu); + struct parallel_data *pd = padata->pd; + struct padata_parallel_queue *pqueue = per_cpu_ptr(pd->pqueue, + padata->cpu); + struct padata_priv *cur; spin_lock(&pqueue->reorder.lock); + /* Sort in ascending order of sequence number. */ + list_for_each_entry_reverse(cur, &pqueue->reorder.list, list) + if (cur->seq_nr < padata->seq_nr) + break; + list_add(&padata->list, &cur->list); atomic_inc(&pd->reorder_objects); - list_add_tail(&padata->list, &pqueue->reorder.list); spin_unlock(&pqueue->reorder.lock); /* - * Ensure the atomic_inc of reorder_objects above is ordered correctly + * Ensure the addition to the reorder list is ordered correctly * with the trylock of pd->lock in padata_reorder. Pairs with smp_mb * in padata_reorder. */ smp_mb__after_atomic(); - put_cpu(); - - /* If we're running on the wrong CPU, call padata_reorder() via a - * kernel worker. - */ - if (reorder_via_wq) - queue_work_on(cpu, pd->pinst->wq, &pqueue->reorder_work); - else - padata_reorder(pd); + padata_reorder(pd); } EXPORT_SYMBOL(padata_do_serial); @@ -415,17 +345,36 @@ static int padata_setup_cpumasks(struct parallel_data *pd, const struct cpumask *pcpumask, const struct cpumask *cbcpumask) { - if (!alloc_cpumask_var(&pd->cpumask.pcpu, GFP_KERNEL)) - return -ENOMEM; + struct workqueue_attrs *attrs; + int err = -ENOMEM; + if (!alloc_cpumask_var(&pd->cpumask.pcpu, GFP_KERNEL)) + goto out; cpumask_and(pd->cpumask.pcpu, pcpumask, cpu_online_mask); - if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL)) { - free_cpumask_var(pd->cpumask.pcpu); - return -ENOMEM; - } + if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL)) + goto free_pcpu_mask; cpumask_and(pd->cpumask.cbcpu, cbcpumask, cpu_online_mask); + + attrs = alloc_workqueue_attrs(); + if (!attrs) + goto free_cbcpu_mask; + + /* Restrict parallel_wq workers to pd->cpumask.pcpu. */ + cpumask_copy(attrs->cpumask, pd->cpumask.pcpu); + err = apply_workqueue_attrs(pd->pinst->parallel_wq, attrs); + free_workqueue_attrs(attrs); + if (err < 0) + goto free_cbcpu_mask; + return 0; + +free_cbcpu_mask: + free_cpumask_var(pd->cpumask.cbcpu); +free_pcpu_mask: + free_cpumask_var(pd->cpumask.pcpu); +out: + return err; } static void __padata_list_init(struct padata_list *pd_list) @@ -451,26 +400,15 @@ static void padata_init_squeues(struct parallel_data *pd) /* Initialize all percpu queues used by parallel workers */ static void padata_init_pqueues(struct parallel_data *pd) { - int cpu_index, cpu; + int cpu; struct padata_parallel_queue *pqueue; - cpu_index = 0; - for_each_possible_cpu(cpu) { + for_each_cpu(cpu, pd->cpumask.pcpu) { pqueue = per_cpu_ptr(pd->pqueue, cpu); - if (!cpumask_test_cpu(cpu, pd->cpumask.pcpu)) { - pqueue->cpu_index = -1; - continue; - } - - pqueue->pd = pd; - pqueue->cpu_index = cpu_index; - cpu_index++; - __padata_list_init(&pqueue->reorder); __padata_list_init(&pqueue->parallel); INIT_WORK(&pqueue->work, padata_parallel_worker); - INIT_WORK(&pqueue->reorder_work, invoke_padata_reorder); atomic_set(&pqueue->num_obj, 0); } } @@ -493,17 +431,19 @@ static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst, pd->squeue = alloc_percpu(struct padata_serial_queue); if (!pd->squeue) goto err_free_pqueue; + + pd->pinst = pinst; if (padata_setup_cpumasks(pd, pcpumask, cbcpumask) < 0) goto err_free_squeue; padata_init_pqueues(pd); padata_init_squeues(pd); - timer_setup(&pd->timer, padata_reorder_timer, 0); atomic_set(&pd->seq_nr, -1); atomic_set(&pd->reorder_objects, 0); atomic_set(&pd->refcnt, 0); - pd->pinst = pinst; spin_lock_init(&pd->lock); + pd->cpu = cpumask_first(pd->cpumask.pcpu); + INIT_WORK(&pd->reorder_work, invoke_padata_reorder); return pd; @@ -538,8 +478,6 @@ static void padata_flush_queues(struct parallel_data *pd) flush_work(&pqueue->work); } - del_timer_sync(&pd->timer); - if (atomic_read(&pd->reorder_objects)) padata_reorder(pd); @@ -883,6 +821,8 @@ static void __padata_free(struct padata_instance *pinst) padata_free_pd(pinst->pd); free_cpumask_var(pinst->cpumask.pcpu); free_cpumask_var(pinst->cpumask.cbcpu); + destroy_workqueue(pinst->serial_wq); + destroy_workqueue(pinst->parallel_wq); kfree(pinst); } @@ -1016,13 +956,11 @@ static struct kobj_type padata_attr_type = { * padata_alloc - allocate and initialize a padata instance and specify * cpumasks for serial and parallel workers. * - * @wq: workqueue to use for the allocated padata instance + * @name: used to identify the instance * @pcpumask: cpumask that will be used for padata parallelization * @cbcpumask: cpumask that will be used for padata serialization - * - * Must be called from a cpus_read_lock() protected region */ -static struct padata_instance *padata_alloc(struct workqueue_struct *wq, +static struct padata_instance *padata_alloc(const char *name, const struct cpumask *pcpumask, const struct cpumask *cbcpumask) { @@ -1033,11 +971,23 @@ static struct padata_instance *padata_alloc(struct workqueue_struct *wq, if (!pinst) goto err; - if (!alloc_cpumask_var(&pinst->cpumask.pcpu, GFP_KERNEL)) + pinst->parallel_wq = alloc_workqueue("%s_parallel", WQ_UNBOUND, 0, + name); + if (!pinst->parallel_wq) goto err_free_inst; + + get_online_cpus(); + + pinst->serial_wq = alloc_workqueue("%s_serial", WQ_MEM_RECLAIM | + WQ_CPU_INTENSIVE, 1, name); + if (!pinst->serial_wq) + goto err_put_cpus; + + if (!alloc_cpumask_var(&pinst->cpumask.pcpu, GFP_KERNEL)) + goto err_free_serial_wq; if (!alloc_cpumask_var(&pinst->cpumask.cbcpu, GFP_KERNEL)) { free_cpumask_var(pinst->cpumask.pcpu); - goto err_free_inst; + goto err_free_serial_wq; } if (!padata_validate_cpumask(pinst, pcpumask) || !padata_validate_cpumask(pinst, cbcpumask)) @@ -1049,8 +999,6 @@ static struct padata_instance *padata_alloc(struct workqueue_struct *wq, rcu_assign_pointer(pinst->pd, pd); - pinst->wq = wq; - cpumask_copy(pinst->cpumask.pcpu, pcpumask); cpumask_copy(pinst->cpumask.cbcpu, cbcpumask); @@ -1063,11 +1011,19 @@ static struct padata_instance *padata_alloc(struct workqueue_struct *wq, #ifdef CONFIG_HOTPLUG_CPU cpuhp_state_add_instance_nocalls_cpuslocked(hp_online, &pinst->node); #endif + + put_online_cpus(); + return pinst; err_free_masks: free_cpumask_var(pinst->cpumask.pcpu); free_cpumask_var(pinst->cpumask.cbcpu); +err_free_serial_wq: + destroy_workqueue(pinst->serial_wq); +err_put_cpus: + put_online_cpus(); + destroy_workqueue(pinst->parallel_wq); err_free_inst: kfree(pinst); err: @@ -1079,14 +1035,11 @@ err: * Use the cpu_possible_mask for serial and * parallel workers. * - * @wq: workqueue to use for the allocated padata instance - * - * Must be called from a cpus_read_lock() protected region + * @name: used to identify the instance */ -struct padata_instance *padata_alloc_possible(struct workqueue_struct *wq) +struct padata_instance *padata_alloc_possible(const char *name) { - lockdep_assert_cpus_held(); - return padata_alloc(wq, cpu_possible_mask, cpu_possible_mask); + return padata_alloc(name, cpu_possible_mask, cpu_possible_mask); } EXPORT_SYMBOL(padata_alloc_possible); diff --git a/kernel/power/autosleep.c b/kernel/power/autosleep.c index 41e83a779e19..9af5a50d3489 100644 --- a/kernel/power/autosleep.c +++ b/kernel/power/autosleep.c @@ -116,7 +116,7 @@ int pm_autosleep_set_state(suspend_state_t state) int __init pm_autosleep_init(void) { - autosleep_ws = wakeup_source_register("autosleep"); + autosleep_ws = wakeup_source_register(NULL, "autosleep"); if (!autosleep_ws) return -ENOMEM; diff --git a/kernel/power/main.c b/kernel/power/main.c index bdbd605c4215..e8710d179b35 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -254,7 +254,6 @@ static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr, power_attr(pm_test); #endif /* CONFIG_PM_SLEEP_DEBUG */ -#ifdef CONFIG_DEBUG_FS static char *suspend_step_name(enum suspend_stat_step step) { switch (step) { @@ -275,6 +274,92 @@ static char *suspend_step_name(enum suspend_stat_step step) } } +#define suspend_attr(_name) \ +static ssize_t _name##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, char *buf) \ +{ \ + return sprintf(buf, "%d\n", suspend_stats._name); \ +} \ +static struct kobj_attribute _name = __ATTR_RO(_name) + +suspend_attr(success); +suspend_attr(fail); +suspend_attr(failed_freeze); +suspend_attr(failed_prepare); +suspend_attr(failed_suspend); +suspend_attr(failed_suspend_late); +suspend_attr(failed_suspend_noirq); +suspend_attr(failed_resume); +suspend_attr(failed_resume_early); +suspend_attr(failed_resume_noirq); + +static ssize_t last_failed_dev_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + int index; + char *last_failed_dev = NULL; + + index = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1; + index %= REC_FAILED_NUM; + last_failed_dev = suspend_stats.failed_devs[index]; + + return sprintf(buf, "%s\n", last_failed_dev); +} +static struct kobj_attribute last_failed_dev = __ATTR_RO(last_failed_dev); + +static ssize_t last_failed_errno_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + int index; + int last_failed_errno; + + index = suspend_stats.last_failed_errno + REC_FAILED_NUM - 1; + index %= REC_FAILED_NUM; + last_failed_errno = suspend_stats.errno[index]; + + return sprintf(buf, "%d\n", last_failed_errno); +} +static struct kobj_attribute last_failed_errno = __ATTR_RO(last_failed_errno); + +static ssize_t last_failed_step_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + int index; + enum suspend_stat_step step; + char *last_failed_step = NULL; + + index = suspend_stats.last_failed_step + REC_FAILED_NUM - 1; + index %= REC_FAILED_NUM; + step = suspend_stats.failed_steps[index]; + last_failed_step = suspend_step_name(step); + + return sprintf(buf, "%s\n", last_failed_step); +} +static struct kobj_attribute last_failed_step = __ATTR_RO(last_failed_step); + +static struct attribute *suspend_attrs[] = { + &success.attr, + &fail.attr, + &failed_freeze.attr, + &failed_prepare.attr, + &failed_suspend.attr, + &failed_suspend_late.attr, + &failed_suspend_noirq.attr, + &failed_resume.attr, + &failed_resume_early.attr, + &failed_resume_noirq.attr, + &last_failed_dev.attr, + &last_failed_errno.attr, + &last_failed_step.attr, + NULL, +}; + +static struct attribute_group suspend_attr_group = { + .name = "suspend_stats", + .attrs = suspend_attrs, +}; + +#ifdef CONFIG_DEBUG_FS static int suspend_stats_show(struct seq_file *s, void *unused) { int i, index, last_dev, last_errno, last_step; @@ -495,7 +580,7 @@ static suspend_state_t decode_state(const char *buf, size_t n) len = p ? p - buf : n; /* Check hibernation first. */ - if (len == 4 && !strncmp(buf, "disk", len)) + if (len == 4 && str_has_prefix(buf, "disk")) return PM_SUSPEND_MAX; #ifdef CONFIG_SUSPEND @@ -794,6 +879,14 @@ static const struct attribute_group attr_group = { .attrs = g, }; +static const struct attribute_group *attr_groups[] = { + &attr_group, +#ifdef CONFIG_PM_SLEEP + &suspend_attr_group, +#endif + NULL, +}; + struct workqueue_struct *pm_wq; EXPORT_SYMBOL_GPL(pm_wq); @@ -815,7 +908,7 @@ static int __init pm_init(void) power_kobj = kobject_create_and_add("power", NULL); if (!power_kobj) return -ENOMEM; - error = sysfs_create_group(power_kobj, &attr_group); + error = sysfs_create_groups(power_kobj, attr_groups); if (error) return error; pm_print_times_init(); diff --git a/kernel/power/qos.c b/kernel/power/qos.c index 33e3febaba53..9568a2fe7c11 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -78,57 +78,9 @@ static struct pm_qos_object cpu_dma_pm_qos = { .name = "cpu_dma_latency", }; -static BLOCKING_NOTIFIER_HEAD(network_lat_notifier); -static struct pm_qos_constraints network_lat_constraints = { - .list = PLIST_HEAD_INIT(network_lat_constraints.list), - .target_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE, - .default_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE, - .no_constraint_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE, - .type = PM_QOS_MIN, - .notifiers = &network_lat_notifier, -}; -static struct pm_qos_object network_lat_pm_qos = { - .constraints = &network_lat_constraints, - .name = "network_latency", -}; - - -static BLOCKING_NOTIFIER_HEAD(network_throughput_notifier); -static struct pm_qos_constraints network_tput_constraints = { - .list = PLIST_HEAD_INIT(network_tput_constraints.list), - .target_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE, - .default_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE, - .no_constraint_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE, - .type = PM_QOS_MAX, - .notifiers = &network_throughput_notifier, -}; -static struct pm_qos_object network_throughput_pm_qos = { - .constraints = &network_tput_constraints, - .name = "network_throughput", -}; - - -static BLOCKING_NOTIFIER_HEAD(memory_bandwidth_notifier); -static struct pm_qos_constraints memory_bw_constraints = { - .list = PLIST_HEAD_INIT(memory_bw_constraints.list), - .target_value = PM_QOS_MEMORY_BANDWIDTH_DEFAULT_VALUE, - .default_value = PM_QOS_MEMORY_BANDWIDTH_DEFAULT_VALUE, - .no_constraint_value = PM_QOS_MEMORY_BANDWIDTH_DEFAULT_VALUE, - .type = PM_QOS_SUM, - .notifiers = &memory_bandwidth_notifier, -}; -static struct pm_qos_object memory_bandwidth_pm_qos = { - .constraints = &memory_bw_constraints, - .name = "memory_bandwidth", -}; - - static struct pm_qos_object *pm_qos_array[] = { &null_pm_qos, &cpu_dma_pm_qos, - &network_lat_pm_qos, - &network_throughput_pm_qos, - &memory_bandwidth_pm_qos, }; static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf, diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index c874a7026e24..f3b7239f1892 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -121,43 +121,25 @@ static void s2idle_loop(void) { pm_pr_dbg("suspend-to-idle\n"); + /* + * Suspend-to-idle equals: + * 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 try + * to avoid them upfront. + */ for (;;) { - int error; - - dpm_noirq_begin(); - - /* - * Suspend-to-idle equals - * 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; - - if (!error && s2idle_ops && s2idle_ops->wake) + if (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(); - if (pm_wakeup_pending()) break; pm_wakeup_clear(false); + + s2idle_enter(); } pm_pr_dbg("resume from suspend-to-idle\n"); @@ -271,14 +253,21 @@ static int platform_suspend_prepare_late(suspend_state_t state) static int platform_suspend_prepare_noirq(suspend_state_t state) { - return state != PM_SUSPEND_TO_IDLE && suspend_ops->prepare_late ? - suspend_ops->prepare_late() : 0; + if (state == PM_SUSPEND_TO_IDLE) + return s2idle_ops && s2idle_ops->prepare_late ? + s2idle_ops->prepare_late() : 0; + + return suspend_ops->prepare_late ? suspend_ops->prepare_late() : 0; } static void platform_resume_noirq(suspend_state_t state) { - if (state != PM_SUSPEND_TO_IDLE && suspend_ops->wake) + if (state == PM_SUSPEND_TO_IDLE) { + if (s2idle_ops && s2idle_ops->restore_early) + s2idle_ops->restore_early(); + } else if (suspend_ops->wake) { suspend_ops->wake(); + } } static void platform_resume_early(suspend_state_t state) @@ -415,11 +404,6 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) if (error) goto Devices_early_resume; - if (state == PM_SUSPEND_TO_IDLE && pm_test_level != TEST_PLATFORM) { - s2idle_loop(); - goto Platform_early_resume; - } - error = dpm_suspend_noirq(PMSG_SUSPEND); if (error) { pr_err("noirq suspend of devices failed\n"); @@ -432,6 +416,11 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) if (suspend_test(TEST_PLATFORM)) goto Platform_wake; + if (state == PM_SUSPEND_TO_IDLE) { + s2idle_loop(); + goto Platform_wake; + } + error = suspend_disable_secondary_cpus(); if (error || suspend_test(TEST_CPUS)) goto Enable_cpus; diff --git a/kernel/power/wakelock.c b/kernel/power/wakelock.c index 4210152e56f0..105df4dfc783 100644 --- a/kernel/power/wakelock.c +++ b/kernel/power/wakelock.c @@ -27,7 +27,7 @@ static DEFINE_MUTEX(wakelocks_lock); struct wakelock { char *name; struct rb_node node; - struct wakeup_source ws; + struct wakeup_source *ws; #ifdef CONFIG_PM_WAKELOCKS_GC struct list_head lru; #endif @@ -46,7 +46,7 @@ ssize_t pm_show_wakelocks(char *buf, bool show_active) for (node = rb_first(&wakelocks_tree); node; node = rb_next(node)) { wl = rb_entry(node, struct wakelock, node); - if (wl->ws.active == show_active) + if (wl->ws->active == show_active) str += scnprintf(str, end - str, "%s ", wl->name); } if (str > buf) @@ -112,16 +112,16 @@ static void __wakelocks_gc(struct work_struct *work) u64 idle_time_ns; bool active; - spin_lock_irq(&wl->ws.lock); - idle_time_ns = ktime_to_ns(ktime_sub(now, wl->ws.last_time)); - active = wl->ws.active; - spin_unlock_irq(&wl->ws.lock); + spin_lock_irq(&wl->ws->lock); + idle_time_ns = ktime_to_ns(ktime_sub(now, wl->ws->last_time)); + active = wl->ws->active; + spin_unlock_irq(&wl->ws->lock); if (idle_time_ns < ((u64)WL_GC_TIME_SEC * NSEC_PER_SEC)) break; if (!active) { - wakeup_source_remove(&wl->ws); + wakeup_source_unregister(wl->ws); rb_erase(&wl->node, &wakelocks_tree); list_del(&wl->lru); kfree(wl->name); @@ -187,9 +187,15 @@ static struct wakelock *wakelock_lookup_add(const char *name, size_t len, kfree(wl); return ERR_PTR(-ENOMEM); } - wl->ws.name = wl->name; - wl->ws.last_time = ktime_get(); - wakeup_source_add(&wl->ws); + + wl->ws = wakeup_source_register(NULL, wl->name); + if (!wl->ws) { + kfree(wl->name); + kfree(wl); + return ERR_PTR(-ENOMEM); + } + wl->ws->last_time = ktime_get(); + rb_link_node(&wl->node, parent, node); rb_insert_color(&wl->node, &wakelocks_tree); wakelocks_lru_add(wl); @@ -233,9 +239,9 @@ int pm_wake_lock(const char *buf) u64 timeout_ms = timeout_ns + NSEC_PER_MSEC - 1; do_div(timeout_ms, NSEC_PER_MSEC); - __pm_wakeup_event(&wl->ws, timeout_ms); + __pm_wakeup_event(wl->ws, timeout_ms); } else { - __pm_stay_awake(&wl->ws); + __pm_stay_awake(wl->ws); } wakelocks_lru_most_recent(wl); @@ -271,7 +277,7 @@ int pm_wake_unlock(const char *buf) ret = PTR_ERR(wl); goto out; } - __pm_relax(&wl->ws); + __pm_relax(wl->ws); wakelocks_lru_most_recent(wl); wakelocks_gc(); diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig index 480edf328b51..7644eda17d62 100644 --- a/kernel/rcu/Kconfig +++ b/kernel/rcu/Kconfig @@ -7,7 +7,7 @@ menu "RCU Subsystem" config TREE_RCU bool - default y if !PREEMPT && SMP + default y if !PREEMPTION && SMP help This option selects the RCU implementation that is designed for very large SMP system with hundreds or @@ -16,7 +16,7 @@ config TREE_RCU config PREEMPT_RCU bool - default y if PREEMPT + default y if PREEMPTION help This option selects the RCU implementation that is designed for very large SMP systems with hundreds or @@ -28,7 +28,7 @@ config PREEMPT_RCU config TINY_RCU bool - default y if !PREEMPT && !SMP + default y if !PREEMPTION && !SMP help This option selects the RCU implementation that is designed for UP systems from which real-time response @@ -70,7 +70,7 @@ config TREE_SRCU This option selects the full-fledged version of SRCU. config TASKS_RCU - def_bool PREEMPT + def_bool PREEMPTION select SRCU help This option enables a task-based RCU implementation that uses diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug index 5ec3ea4028e2..4aa02eee8f6c 100644 --- a/kernel/rcu/Kconfig.debug +++ b/kernel/rcu/Kconfig.debug @@ -8,6 +8,17 @@ menu "RCU Debugging" config PROVE_RCU def_bool PROVE_LOCKING +config PROVE_RCU_LIST + bool "RCU list lockdep debugging" + depends on PROVE_RCU && RCU_EXPERT + default n + help + Enable RCU lockdep checking for list usages. By default it is + turned off since there are several list RCU users that still + need to be converted to pass a lockdep expression. To prevent + false-positive splats, we keep it default disabled but once all + users are converted, we can remove this config option. + config TORTURE_TEST tristate default n diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 5290b01de534..8fd4f82c9b3d 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -227,6 +227,7 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head) #ifdef CONFIG_RCU_STALL_COMMON +extern int rcu_cpu_stall_ftrace_dump; extern int rcu_cpu_stall_suppress; extern int rcu_cpu_stall_timeout; int rcu_jiffies_till_stall_check(void); diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c index 9bd5f6023c21..495c58ce1640 100644 --- a/kernel/rcu/rcu_segcblist.c +++ b/kernel/rcu/rcu_segcblist.c @@ -24,6 +24,49 @@ void rcu_cblist_init(struct rcu_cblist *rclp) } /* + * Enqueue an rcu_head structure onto the specified callback list. + * This function assumes that the callback is non-lazy because it + * is intended for use by no-CBs CPUs, which do not distinguish + * between lazy and non-lazy RCU callbacks. + */ +void rcu_cblist_enqueue(struct rcu_cblist *rclp, struct rcu_head *rhp) +{ + *rclp->tail = rhp; + rclp->tail = &rhp->next; + WRITE_ONCE(rclp->len, rclp->len + 1); +} + +/* + * Flush the second rcu_cblist structure onto the first one, obliterating + * any contents of the first. If rhp is non-NULL, enqueue it as the sole + * element of the second rcu_cblist structure, but ensuring that the second + * rcu_cblist structure, if initially non-empty, always appears non-empty + * throughout the process. If rdp is NULL, the second rcu_cblist structure + * is instead initialized to empty. + */ +void rcu_cblist_flush_enqueue(struct rcu_cblist *drclp, + struct rcu_cblist *srclp, + struct rcu_head *rhp) +{ + drclp->head = srclp->head; + if (drclp->head) + drclp->tail = srclp->tail; + else + drclp->tail = &drclp->head; + drclp->len = srclp->len; + drclp->len_lazy = srclp->len_lazy; + if (!rhp) { + rcu_cblist_init(srclp); + } else { + rhp->next = NULL; + srclp->head = rhp; + srclp->tail = &rhp->next; + WRITE_ONCE(srclp->len, 1); + srclp->len_lazy = 0; + } +} + +/* * Dequeue the oldest rcu_head structure from the specified callback * list. This function assumes that the callback is non-lazy, but * the caller can later invoke rcu_cblist_dequeued_lazy() if it @@ -44,6 +87,67 @@ struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp) return rhp; } +/* Set the length of an rcu_segcblist structure. */ +void rcu_segcblist_set_len(struct rcu_segcblist *rsclp, long v) +{ +#ifdef CONFIG_RCU_NOCB_CPU + atomic_long_set(&rsclp->len, v); +#else + WRITE_ONCE(rsclp->len, v); +#endif +} + +/* + * Increase the numeric length of an rcu_segcblist structure by the + * specified amount, which can be negative. This can cause the ->len + * field to disagree with the actual number of callbacks on the structure. + * This increase is fully ordered with respect to the callers accesses + * both before and after. + */ +void rcu_segcblist_add_len(struct rcu_segcblist *rsclp, long v) +{ +#ifdef CONFIG_RCU_NOCB_CPU + smp_mb__before_atomic(); /* Up to the caller! */ + atomic_long_add(v, &rsclp->len); + smp_mb__after_atomic(); /* Up to the caller! */ +#else + smp_mb(); /* Up to the caller! */ + WRITE_ONCE(rsclp->len, rsclp->len + v); + smp_mb(); /* Up to the caller! */ +#endif +} + +/* + * Increase the numeric length of an rcu_segcblist structure by one. + * This can cause the ->len field to disagree with the actual number of + * callbacks on the structure. This increase is fully ordered with respect + * to the callers accesses both before and after. + */ +void rcu_segcblist_inc_len(struct rcu_segcblist *rsclp) +{ + rcu_segcblist_add_len(rsclp, 1); +} + +/* + * Exchange the numeric length of the specified rcu_segcblist structure + * with the specified value. This can cause the ->len field to disagree + * with the actual number of callbacks on the structure. This exchange is + * fully ordered with respect to the callers accesses both before and after. + */ +long rcu_segcblist_xchg_len(struct rcu_segcblist *rsclp, long v) +{ +#ifdef CONFIG_RCU_NOCB_CPU + return atomic_long_xchg(&rsclp->len, v); +#else + long ret = rsclp->len; + + smp_mb(); /* Up to the caller! */ + WRITE_ONCE(rsclp->len, v); + smp_mb(); /* Up to the caller! */ + return ret; +#endif +} + /* * Initialize an rcu_segcblist structure. */ @@ -56,8 +160,9 @@ void rcu_segcblist_init(struct rcu_segcblist *rsclp) rsclp->head = NULL; for (i = 0; i < RCU_CBLIST_NSEGS; i++) rsclp->tails[i] = &rsclp->head; - rsclp->len = 0; + rcu_segcblist_set_len(rsclp, 0); rsclp->len_lazy = 0; + rsclp->enabled = 1; } /* @@ -69,7 +174,16 @@ void rcu_segcblist_disable(struct rcu_segcblist *rsclp) WARN_ON_ONCE(!rcu_segcblist_empty(rsclp)); WARN_ON_ONCE(rcu_segcblist_n_cbs(rsclp)); WARN_ON_ONCE(rcu_segcblist_n_lazy_cbs(rsclp)); - rsclp->tails[RCU_NEXT_TAIL] = NULL; + rsclp->enabled = 0; +} + +/* + * Mark the specified rcu_segcblist structure as offloaded. This + * structure must be empty. + */ +void rcu_segcblist_offload(struct rcu_segcblist *rsclp) +{ + rsclp->offloaded = 1; } /* @@ -118,6 +232,18 @@ struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp) } /* + * Return false if there are no CBs awaiting grace periods, otherwise, + * return true and store the nearest waited-upon grace period into *lp. + */ +bool rcu_segcblist_nextgp(struct rcu_segcblist *rsclp, unsigned long *lp) +{ + if (!rcu_segcblist_pend_cbs(rsclp)) + return false; + *lp = rsclp->gp_seq[RCU_WAIT_TAIL]; + return true; +} + +/* * Enqueue the specified callback onto the specified rcu_segcblist * structure, updating accounting as needed. Note that the ->len * field may be accessed locklessly, hence the WRITE_ONCE(). @@ -129,13 +255,13 @@ struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp) void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp, struct rcu_head *rhp, bool lazy) { - WRITE_ONCE(rsclp->len, rsclp->len + 1); /* ->len sampled locklessly. */ + rcu_segcblist_inc_len(rsclp); if (lazy) rsclp->len_lazy++; smp_mb(); /* Ensure counts are updated before callback is enqueued. */ rhp->next = NULL; - *rsclp->tails[RCU_NEXT_TAIL] = rhp; - rsclp->tails[RCU_NEXT_TAIL] = &rhp->next; + WRITE_ONCE(*rsclp->tails[RCU_NEXT_TAIL], rhp); + WRITE_ONCE(rsclp->tails[RCU_NEXT_TAIL], &rhp->next); } /* @@ -155,7 +281,7 @@ bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp, if (rcu_segcblist_n_cbs(rsclp) == 0) return false; - WRITE_ONCE(rsclp->len, rsclp->len + 1); + rcu_segcblist_inc_len(rsclp); if (lazy) rsclp->len_lazy++; smp_mb(); /* Ensure counts are updated before callback is entrained. */ @@ -163,9 +289,9 @@ bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp, for (i = RCU_NEXT_TAIL; i > RCU_DONE_TAIL; i--) if (rsclp->tails[i] != rsclp->tails[i - 1]) break; - *rsclp->tails[i] = rhp; + WRITE_ONCE(*rsclp->tails[i], rhp); for (; i <= RCU_NEXT_TAIL; i++) - rsclp->tails[i] = &rhp->next; + WRITE_ONCE(rsclp->tails[i], &rhp->next); return true; } @@ -182,9 +308,8 @@ void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp, struct rcu_cblist *rclp) { rclp->len_lazy += rsclp->len_lazy; - rclp->len += rsclp->len; rsclp->len_lazy = 0; - WRITE_ONCE(rsclp->len, 0); /* ->len sampled locklessly. */ + rclp->len = rcu_segcblist_xchg_len(rsclp, 0); } /* @@ -200,12 +325,12 @@ void rcu_segcblist_extract_done_cbs(struct rcu_segcblist *rsclp, if (!rcu_segcblist_ready_cbs(rsclp)) return; /* Nothing to do. */ *rclp->tail = rsclp->head; - rsclp->head = *rsclp->tails[RCU_DONE_TAIL]; - *rsclp->tails[RCU_DONE_TAIL] = NULL; + WRITE_ONCE(rsclp->head, *rsclp->tails[RCU_DONE_TAIL]); + WRITE_ONCE(*rsclp->tails[RCU_DONE_TAIL], NULL); rclp->tail = rsclp->tails[RCU_DONE_TAIL]; for (i = RCU_CBLIST_NSEGS - 1; i >= RCU_DONE_TAIL; i--) if (rsclp->tails[i] == rsclp->tails[RCU_DONE_TAIL]) - rsclp->tails[i] = &rsclp->head; + WRITE_ONCE(rsclp->tails[i], &rsclp->head); } /* @@ -224,9 +349,9 @@ void rcu_segcblist_extract_pend_cbs(struct rcu_segcblist *rsclp, return; /* Nothing to do. */ *rclp->tail = *rsclp->tails[RCU_DONE_TAIL]; rclp->tail = rsclp->tails[RCU_NEXT_TAIL]; - *rsclp->tails[RCU_DONE_TAIL] = NULL; + WRITE_ONCE(*rsclp->tails[RCU_DONE_TAIL], NULL); for (i = RCU_DONE_TAIL + 1; i < RCU_CBLIST_NSEGS; i++) - rsclp->tails[i] = rsclp->tails[RCU_DONE_TAIL]; + WRITE_ONCE(rsclp->tails[i], rsclp->tails[RCU_DONE_TAIL]); } /* @@ -237,8 +362,7 @@ void rcu_segcblist_insert_count(struct rcu_segcblist *rsclp, struct rcu_cblist *rclp) { rsclp->len_lazy += rclp->len_lazy; - /* ->len sampled locklessly. */ - WRITE_ONCE(rsclp->len, rsclp->len + rclp->len); + rcu_segcblist_add_len(rsclp, rclp->len); rclp->len_lazy = 0; rclp->len = 0; } @@ -255,10 +379,10 @@ void rcu_segcblist_insert_done_cbs(struct rcu_segcblist *rsclp, if (!rclp->head) return; /* No callbacks to move. */ *rclp->tail = rsclp->head; - rsclp->head = rclp->head; + WRITE_ONCE(rsclp->head, rclp->head); for (i = RCU_DONE_TAIL; i < RCU_CBLIST_NSEGS; i++) if (&rsclp->head == rsclp->tails[i]) - rsclp->tails[i] = rclp->tail; + WRITE_ONCE(rsclp->tails[i], rclp->tail); else break; rclp->head = NULL; @@ -274,8 +398,8 @@ void rcu_segcblist_insert_pend_cbs(struct rcu_segcblist *rsclp, { if (!rclp->head) return; /* Nothing to do. */ - *rsclp->tails[RCU_NEXT_TAIL] = rclp->head; - rsclp->tails[RCU_NEXT_TAIL] = rclp->tail; + WRITE_ONCE(*rsclp->tails[RCU_NEXT_TAIL], rclp->head); + WRITE_ONCE(rsclp->tails[RCU_NEXT_TAIL], rclp->tail); rclp->head = NULL; rclp->tail = &rclp->head; } @@ -299,7 +423,7 @@ void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq) for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) { if (ULONG_CMP_LT(seq, rsclp->gp_seq[i])) break; - rsclp->tails[RCU_DONE_TAIL] = rsclp->tails[i]; + WRITE_ONCE(rsclp->tails[RCU_DONE_TAIL], rsclp->tails[i]); } /* If no callbacks moved, nothing more need be done. */ @@ -308,7 +432,7 @@ void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq) /* Clean up tail pointers that might have been misordered above. */ for (j = RCU_WAIT_TAIL; j < i; j++) - rsclp->tails[j] = rsclp->tails[RCU_DONE_TAIL]; + WRITE_ONCE(rsclp->tails[j], rsclp->tails[RCU_DONE_TAIL]); /* * Callbacks moved, so clean up the misordered ->tails[] pointers @@ -319,7 +443,7 @@ void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq) for (j = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++, j++) { if (rsclp->tails[j] == rsclp->tails[RCU_NEXT_TAIL]) break; /* No more callbacks. */ - rsclp->tails[j] = rsclp->tails[i]; + WRITE_ONCE(rsclp->tails[j], rsclp->tails[i]); rsclp->gp_seq[j] = rsclp->gp_seq[i]; } } @@ -384,7 +508,7 @@ bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq) * structure other than in the RCU_NEXT_TAIL segment. */ for (; i < RCU_NEXT_TAIL; i++) { - rsclp->tails[i] = rsclp->tails[RCU_NEXT_TAIL]; + WRITE_ONCE(rsclp->tails[i], rsclp->tails[RCU_NEXT_TAIL]); rsclp->gp_seq[i] = seq; } return true; diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h index 71b64648464e..815c2fdd3fcc 100644 --- a/kernel/rcu/rcu_segcblist.h +++ b/kernel/rcu/rcu_segcblist.h @@ -9,6 +9,12 @@ #include <linux/rcu_segcblist.h> +/* Return number of callbacks in the specified callback list. */ +static inline long rcu_cblist_n_cbs(struct rcu_cblist *rclp) +{ + return READ_ONCE(rclp->len); +} + /* * Account for the fact that a previously dequeued callback turned out * to be marked as lazy. @@ -19,6 +25,10 @@ static inline void rcu_cblist_dequeued_lazy(struct rcu_cblist *rclp) } void rcu_cblist_init(struct rcu_cblist *rclp); +void rcu_cblist_enqueue(struct rcu_cblist *rclp, struct rcu_head *rhp); +void rcu_cblist_flush_enqueue(struct rcu_cblist *drclp, + struct rcu_cblist *srclp, + struct rcu_head *rhp); struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp); /* @@ -36,13 +46,17 @@ struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp); */ static inline bool rcu_segcblist_empty(struct rcu_segcblist *rsclp) { - return !rsclp->head; + return !READ_ONCE(rsclp->head); } /* Return number of callbacks in segmented callback list. */ static inline long rcu_segcblist_n_cbs(struct rcu_segcblist *rsclp) { +#ifdef CONFIG_RCU_NOCB_CPU + return atomic_long_read(&rsclp->len); +#else return READ_ONCE(rsclp->len); +#endif } /* Return number of lazy callbacks in segmented callback list. */ @@ -54,16 +68,22 @@ static inline long rcu_segcblist_n_lazy_cbs(struct rcu_segcblist *rsclp) /* Return number of lazy callbacks in segmented callback list. */ static inline long rcu_segcblist_n_nonlazy_cbs(struct rcu_segcblist *rsclp) { - return rsclp->len - rsclp->len_lazy; + return rcu_segcblist_n_cbs(rsclp) - rsclp->len_lazy; } /* * Is the specified rcu_segcblist enabled, for example, not corresponding - * to an offline or callback-offloaded CPU? + * to an offline CPU? */ static inline bool rcu_segcblist_is_enabled(struct rcu_segcblist *rsclp) { - return !!rsclp->tails[RCU_NEXT_TAIL]; + return rsclp->enabled; +} + +/* Is the specified rcu_segcblist offloaded? */ +static inline bool rcu_segcblist_is_offloaded(struct rcu_segcblist *rsclp) +{ + return rsclp->offloaded; } /* @@ -73,36 +93,18 @@ static inline bool rcu_segcblist_is_enabled(struct rcu_segcblist *rsclp) */ static inline bool rcu_segcblist_restempty(struct rcu_segcblist *rsclp, int seg) { - return !*rsclp->tails[seg]; -} - -/* - * Interim function to return rcu_segcblist head pointer. Longer term, the - * rcu_segcblist will be used more pervasively, removing the need for this - * function. - */ -static inline struct rcu_head *rcu_segcblist_head(struct rcu_segcblist *rsclp) -{ - return rsclp->head; -} - -/* - * Interim function to return rcu_segcblist head pointer. Longer term, the - * rcu_segcblist will be used more pervasively, removing the need for this - * function. - */ -static inline struct rcu_head **rcu_segcblist_tail(struct rcu_segcblist *rsclp) -{ - WARN_ON_ONCE(rcu_segcblist_empty(rsclp)); - return rsclp->tails[RCU_NEXT_TAIL]; + return !READ_ONCE(*READ_ONCE(rsclp->tails[seg])); } +void rcu_segcblist_inc_len(struct rcu_segcblist *rsclp); void rcu_segcblist_init(struct rcu_segcblist *rsclp); void rcu_segcblist_disable(struct rcu_segcblist *rsclp); +void rcu_segcblist_offload(struct rcu_segcblist *rsclp); bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp); bool rcu_segcblist_pend_cbs(struct rcu_segcblist *rsclp); struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp); struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp); +bool rcu_segcblist_nextgp(struct rcu_segcblist *rsclp, unsigned long *lp); void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp, struct rcu_head *rhp, bool lazy); bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp, diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c index 7a6890b23c5f..5a879d073c1c 100644 --- a/kernel/rcu/rcuperf.c +++ b/kernel/rcu/rcuperf.c @@ -89,7 +89,7 @@ torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable static char *perf_type = "rcu"; module_param(perf_type, charp, 0444); -MODULE_PARM_DESC(perf_type, "Type of RCU to performance-test (rcu, rcu_bh, ...)"); +MODULE_PARM_DESC(perf_type, "Type of RCU to performance-test (rcu, srcu, ...)"); static int nrealreaders; static int nrealwriters; @@ -375,6 +375,14 @@ rcu_perf_writer(void *arg) if (holdoff) schedule_timeout_uninterruptible(holdoff * HZ); + /* + * Wait until rcu_end_inkernel_boot() is called for normal GP tests + * so that RCU is not always expedited for normal GP tests. + * The system_state test is approximate, but works well in practice. + */ + while (!gp_exp && system_state != SYSTEM_RUNNING) + schedule_timeout_uninterruptible(1); + t = ktime_get_mono_fast_ns(); if (atomic_inc_return(&n_rcu_perf_writer_started) >= nrealwriters) { t_rcu_perf_writer_started = t; diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index fce4e7e6f502..3c9feca1eab1 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -161,6 +161,7 @@ static atomic_long_t n_rcu_torture_timers; static long n_barrier_attempts; static long n_barrier_successes; /* did rcu_barrier test succeed? */ static struct list_head rcu_torture_removed; +static unsigned long shutdown_jiffies; static int rcu_torture_writer_state; #define RTWS_FIXED_DELAY 0 @@ -228,6 +229,15 @@ static u64 notrace rcu_trace_clock_local(void) } #endif /* #else #ifdef CONFIG_RCU_TRACE */ +/* + * Stop aggressive CPU-hog tests a bit before the end of the test in order + * to avoid interfering with test shutdown. + */ +static bool shutdown_time_arrived(void) +{ + return shutdown_secs && time_after(jiffies, shutdown_jiffies - 30 * HZ); +} + static unsigned long boost_starttime; /* jiffies of next boost test start. */ static DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */ /* and boost task create/destroy. */ @@ -1713,12 +1723,14 @@ static void rcu_torture_fwd_cb_cr(struct rcu_head *rhp) } // Give the scheduler a chance, even on nohz_full CPUs. -static void rcu_torture_fwd_prog_cond_resched(void) +static void rcu_torture_fwd_prog_cond_resched(unsigned long iter) { if (IS_ENABLED(CONFIG_PREEMPT) && IS_ENABLED(CONFIG_NO_HZ_FULL)) { - if (need_resched()) + // Real call_rcu() floods hit userspace, so emulate that. + if (need_resched() || (iter & 0xfff)) schedule(); } else { + // No userspace emulation: CB invocation throttles call_rcu() cond_resched(); } } @@ -1746,7 +1758,7 @@ static unsigned long rcu_torture_fwd_prog_cbfree(void) spin_unlock_irqrestore(&rcu_fwd_lock, flags); kfree(rfcp); freed++; - rcu_torture_fwd_prog_cond_resched(); + rcu_torture_fwd_prog_cond_resched(freed); } return freed; } @@ -1785,15 +1797,17 @@ static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries) WRITE_ONCE(rcu_fwd_startat, jiffies); stopat = rcu_fwd_startat + dur; while (time_before(jiffies, stopat) && + !shutdown_time_arrived() && !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) { idx = cur_ops->readlock(); udelay(10); cur_ops->readunlock(idx); if (!fwd_progress_need_resched || need_resched()) - rcu_torture_fwd_prog_cond_resched(); + rcu_torture_fwd_prog_cond_resched(1); } (*tested_tries)++; if (!time_before(jiffies, stopat) && + !shutdown_time_arrived() && !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) { (*tested)++; cver = READ_ONCE(rcu_torture_current_version) - cver; @@ -1852,6 +1866,7 @@ static void rcu_torture_fwd_prog_cr(void) gps = cur_ops->get_gp_seq(); rcu_launder_gp_seq_start = gps; while (time_before(jiffies, stopat) && + !shutdown_time_arrived() && !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) { rfcp = READ_ONCE(rcu_fwd_cb_head); rfcpn = NULL; @@ -1875,7 +1890,7 @@ static void rcu_torture_fwd_prog_cr(void) rfcp->rfc_gps = 0; } cur_ops->call(&rfcp->rh, rcu_torture_fwd_cb_cr); - rcu_torture_fwd_prog_cond_resched(); + rcu_torture_fwd_prog_cond_resched(n_launders + n_max_cbs); } stoppedat = jiffies; n_launders_cb_snap = READ_ONCE(n_launders_cb); @@ -1884,7 +1899,8 @@ static void rcu_torture_fwd_prog_cr(void) cur_ops->cb_barrier(); /* Wait for callbacks to be invoked. */ (void)rcu_torture_fwd_prog_cbfree(); - if (!torture_must_stop() && !READ_ONCE(rcu_fwd_emergency_stop)) { + if (!torture_must_stop() && !READ_ONCE(rcu_fwd_emergency_stop) && + !shutdown_time_arrived()) { WARN_ON(n_max_gps < MIN_FWD_CBS_LAUNDERED); pr_alert("%s Duration %lu barrier: %lu pending %ld n_launders: %ld n_launders_sa: %ld n_max_gps: %ld n_max_cbs: %ld cver %ld gps %ld\n", __func__, @@ -2160,6 +2176,7 @@ rcu_torture_cleanup(void) return; } + show_rcu_gp_kthreads(); rcu_torture_barrier_cleanup(); torture_stop_kthread(rcu_torture_fwd_prog, fwd_prog_task); torture_stop_kthread(rcu_torture_stall, stall_task); @@ -2465,6 +2482,7 @@ rcu_torture_init(void) goto unwind; rcutor_hp = firsterr; } + shutdown_jiffies = jiffies + shutdown_secs * HZ; firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup); if (firsterr) goto unwind; diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index cf0e886314f2..5dffade2d7cd 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -1279,8 +1279,9 @@ void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf) c0 = l0 - u0; c1 = l1 - u1; - pr_cont(" %d(%ld,%ld %1p)", - cpu, c0, c1, rcu_segcblist_head(&sdp->srcu_cblist)); + pr_cont(" %d(%ld,%ld %c)", + cpu, c0, c1, + "C."[rcu_segcblist_empty(&sdp->srcu_cblist)]); s0 += c0; s1 += c1; } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index a14e5fbbea46..81105141b6a8 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -56,6 +56,7 @@ #include <linux/smpboot.h> #include <linux/jiffies.h> #include <linux/sched/isolation.h> +#include <linux/sched/clock.h> #include "../time/tick-internal.h" #include "tree.h" @@ -210,9 +211,9 @@ static long rcu_get_n_cbs_cpu(int cpu) { struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); - if (rcu_segcblist_is_enabled(&rdp->cblist)) /* Online normal CPU? */ + if (rcu_segcblist_is_enabled(&rdp->cblist)) return rcu_segcblist_n_cbs(&rdp->cblist); - return rcu_get_n_cbs_nocb_cpu(rdp); /* Works for offline, too. */ + return 0; } void rcu_softirq_qs(void) @@ -416,6 +417,12 @@ module_param(qlowmark, long, 0444); static ulong jiffies_till_first_fqs = ULONG_MAX; static ulong jiffies_till_next_fqs = ULONG_MAX; static bool rcu_kick_kthreads; +static int rcu_divisor = 7; +module_param(rcu_divisor, int, 0644); + +/* Force an exit from rcu_do_batch() after 3 milliseconds. */ +static long rcu_resched_ns = 3 * NSEC_PER_MSEC; +module_param(rcu_resched_ns, long, 0644); /* * How long the grace period must be before we start recruiting @@ -1251,6 +1258,7 @@ static bool rcu_accelerate_cbs(struct rcu_node *rnp, struct rcu_data *rdp) unsigned long gp_seq_req; bool ret = false; + rcu_lockdep_assert_cblist_protected(rdp); raw_lockdep_assert_held_rcu_node(rnp); /* If no pending (not yet ready to invoke) callbacks, nothing to do. */ @@ -1292,7 +1300,7 @@ static void rcu_accelerate_cbs_unlocked(struct rcu_node *rnp, unsigned long c; bool needwake; - lockdep_assert_irqs_disabled(); + rcu_lockdep_assert_cblist_protected(rdp); c = rcu_seq_snap(&rcu_state.gp_seq); if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) { /* Old request still live, so mark recent callbacks. */ @@ -1318,6 +1326,7 @@ static void rcu_accelerate_cbs_unlocked(struct rcu_node *rnp, */ static bool rcu_advance_cbs(struct rcu_node *rnp, struct rcu_data *rdp) { + rcu_lockdep_assert_cblist_protected(rdp); raw_lockdep_assert_held_rcu_node(rnp); /* If no pending (not yet ready to invoke) callbacks, nothing to do. */ @@ -1335,6 +1344,21 @@ static bool rcu_advance_cbs(struct rcu_node *rnp, struct rcu_data *rdp) } /* + * Move and classify callbacks, but only if doing so won't require + * that the RCU grace-period kthread be awakened. + */ +static void __maybe_unused rcu_advance_cbs_nowake(struct rcu_node *rnp, + struct rcu_data *rdp) +{ + rcu_lockdep_assert_cblist_protected(rdp); + if (!rcu_seq_state(rcu_seq_current(&rnp->gp_seq)) || + !raw_spin_trylock_rcu_node(rnp)) + return; + WARN_ON_ONCE(rcu_advance_cbs(rnp, rdp)); + raw_spin_unlock_rcu_node(rnp); +} + +/* * Update CPU-local rcu_data state to record the beginnings and ends of * grace periods. The caller must hold the ->lock of the leaf rcu_node * structure corresponding to the current CPU, and must have irqs disabled. @@ -1342,8 +1366,10 @@ static bool rcu_advance_cbs(struct rcu_node *rnp, struct rcu_data *rdp) */ static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp) { - bool ret; + bool ret = false; bool need_gp; + const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) && + rcu_segcblist_is_offloaded(&rdp->cblist); raw_lockdep_assert_held_rcu_node(rnp); @@ -1353,10 +1379,12 @@ static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp) /* Handle the ends of any preceding grace periods first. */ if (rcu_seq_completed_gp(rdp->gp_seq, rnp->gp_seq) || unlikely(READ_ONCE(rdp->gpwrap))) { - ret = rcu_advance_cbs(rnp, rdp); /* Advance callbacks. */ + if (!offloaded) + ret = rcu_advance_cbs(rnp, rdp); /* Advance CBs. */ trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuend")); } else { - ret = rcu_accelerate_cbs(rnp, rdp); /* Recent callbacks. */ + if (!offloaded) + ret = rcu_accelerate_cbs(rnp, rdp); /* Recent CBs. */ } /* Now handle the beginnings of any new-to-this-CPU grace periods. */ @@ -1657,6 +1685,7 @@ static void rcu_gp_cleanup(void) unsigned long gp_duration; bool needgp = false; unsigned long new_gp_seq; + bool offloaded; struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(); struct swait_queue_head *sq; @@ -1722,7 +1751,9 @@ static void rcu_gp_cleanup(void) needgp = true; } /* Advance CBs to reduce false positives below. */ - if (!rcu_accelerate_cbs(rnp, rdp) && needgp) { + offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) && + rcu_segcblist_is_offloaded(&rdp->cblist); + if ((offloaded || !rcu_accelerate_cbs(rnp, rdp)) && needgp) { WRITE_ONCE(rcu_state.gp_flags, RCU_GP_FLAG_INIT); rcu_state.gp_req_activity = jiffies; trace_rcu_grace_period(rcu_state.name, @@ -1881,7 +1912,7 @@ rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags) struct rcu_node *rnp_p; raw_lockdep_assert_held_rcu_node(rnp); - if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT)) || + if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPTION)) || WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) || rnp->qsmask != 0) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); @@ -1916,7 +1947,9 @@ rcu_report_qs_rdp(int cpu, struct rcu_data *rdp) { unsigned long flags; unsigned long mask; - bool needwake; + bool needwake = false; + const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) && + rcu_segcblist_is_offloaded(&rdp->cblist); struct rcu_node *rnp; rnp = rdp->mynode; @@ -1943,7 +1976,8 @@ rcu_report_qs_rdp(int cpu, struct rcu_data *rdp) * This GP can't end until cpu checks in, so all of our * callbacks can be processed during the next GP. */ - needwake = rcu_accelerate_cbs(rnp, rdp); + if (!offloaded) + needwake = rcu_accelerate_cbs(rnp, rdp); rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags); /* ^^^ Released rnp->lock */ @@ -2077,9 +2111,12 @@ int rcutree_dead_cpu(unsigned int cpu) static void rcu_do_batch(struct rcu_data *rdp) { unsigned long flags; + const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) && + rcu_segcblist_is_offloaded(&rdp->cblist); struct rcu_head *rhp; struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl); long bl, count; + long pending, tlimit = 0; /* If no callbacks are ready, just return. */ if (!rcu_segcblist_ready_cbs(&rdp->cblist)) { @@ -2099,13 +2136,19 @@ static void rcu_do_batch(struct rcu_data *rdp) * callback counts, as rcu_barrier() needs to be conservative. */ local_irq_save(flags); + rcu_nocb_lock(rdp); WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); - bl = rdp->blimit; + pending = rcu_segcblist_n_cbs(&rdp->cblist); + bl = max(rdp->blimit, pending >> rcu_divisor); + if (unlikely(bl > 100)) + tlimit = local_clock() + rcu_resched_ns; trace_rcu_batch_start(rcu_state.name, rcu_segcblist_n_lazy_cbs(&rdp->cblist), rcu_segcblist_n_cbs(&rdp->cblist), bl); rcu_segcblist_extract_done_cbs(&rdp->cblist, &rcl); - local_irq_restore(flags); + if (offloaded) + rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist); + rcu_nocb_unlock_irqrestore(rdp, flags); /* Invoke callbacks. */ rhp = rcu_cblist_dequeue(&rcl); @@ -2117,13 +2160,29 @@ static void rcu_do_batch(struct rcu_data *rdp) * Stop only if limit reached and CPU has something to do. * Note: The rcl structure counts down from zero. */ - if (-rcl.len >= bl && + if (-rcl.len >= bl && !offloaded && (need_resched() || (!is_idle_task(current) && !rcu_is_callbacks_kthread()))) break; + if (unlikely(tlimit)) { + /* only call local_clock() every 32 callbacks */ + if (likely((-rcl.len & 31) || local_clock() < tlimit)) + continue; + /* Exceeded the time limit, so leave. */ + break; + } + if (offloaded) { + WARN_ON_ONCE(in_serving_softirq()); + local_bh_enable(); + lockdep_assert_irqs_enabled(); + cond_resched_tasks_rcu_qs(); + lockdep_assert_irqs_enabled(); + local_bh_disable(); + } } local_irq_save(flags); + rcu_nocb_lock(rdp); count = -rcl.len; trace_rcu_batch_end(rcu_state.name, count, !!rcl.head, need_resched(), is_idle_task(current), rcu_is_callbacks_kthread()); @@ -2149,12 +2208,14 @@ static void rcu_do_batch(struct rcu_data *rdp) * The following usually indicates a double call_rcu(). To track * this down, try building with CONFIG_DEBUG_OBJECTS_RCU_HEAD=y. */ - WARN_ON_ONCE(rcu_segcblist_empty(&rdp->cblist) != (count == 0)); + WARN_ON_ONCE(count == 0 && !rcu_segcblist_empty(&rdp->cblist)); + WARN_ON_ONCE(!IS_ENABLED(CONFIG_RCU_NOCB_CPU) && + count != 0 && rcu_segcblist_empty(&rdp->cblist)); - local_irq_restore(flags); + rcu_nocb_unlock_irqrestore(rdp, flags); /* Re-invoke RCU core processing if there are callbacks remaining. */ - if (rcu_segcblist_ready_cbs(&rdp->cblist)) + if (!offloaded && rcu_segcblist_ready_cbs(&rdp->cblist)) invoke_rcu_core(); } @@ -2205,7 +2266,7 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp)) mask = 0; raw_spin_lock_irqsave_rcu_node(rnp, flags); if (rnp->qsmask == 0) { - if (!IS_ENABLED(CONFIG_PREEMPT) || + if (!IS_ENABLED(CONFIG_PREEMPTION) || rcu_preempt_blocked_readers_cgp(rnp)) { /* * No point in scanning bits because they @@ -2280,6 +2341,8 @@ static __latent_entropy void rcu_core(void) unsigned long flags; struct rcu_data *rdp = raw_cpu_ptr(&rcu_data); struct rcu_node *rnp = rdp->mynode; + const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) && + rcu_segcblist_is_offloaded(&rdp->cblist); if (cpu_is_offline(smp_processor_id())) return; @@ -2299,7 +2362,7 @@ static __latent_entropy void rcu_core(void) /* No grace period and unregistered callbacks? */ if (!rcu_gp_in_progress() && - rcu_segcblist_is_enabled(&rdp->cblist)) { + rcu_segcblist_is_enabled(&rdp->cblist) && !offloaded) { local_irq_save(flags); if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) rcu_accelerate_cbs_unlocked(rnp, rdp); @@ -2309,7 +2372,7 @@ static __latent_entropy void rcu_core(void) rcu_check_gp_start_stall(rnp, rdp, rcu_jiffies_till_stall_check()); /* If there are callbacks ready, invoke them. */ - if (rcu_segcblist_ready_cbs(&rdp->cblist) && + if (!offloaded && rcu_segcblist_ready_cbs(&rdp->cblist) && likely(READ_ONCE(rcu_scheduler_fully_active))) rcu_do_batch(rdp); @@ -2489,10 +2552,11 @@ static void rcu_leak_callback(struct rcu_head *rhp) * is expected to specify a CPU. */ static void -__call_rcu(struct rcu_head *head, rcu_callback_t func, int cpu, bool lazy) +__call_rcu(struct rcu_head *head, rcu_callback_t func, bool lazy) { unsigned long flags; struct rcu_data *rdp; + bool was_alldone; /* Misaligned rcu_head! */ WARN_ON_ONCE((unsigned long)head & (sizeof(void *) - 1)); @@ -2514,28 +2578,18 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, int cpu, bool lazy) rdp = this_cpu_ptr(&rcu_data); /* Add the callback to our list. */ - if (unlikely(!rcu_segcblist_is_enabled(&rdp->cblist)) || cpu != -1) { - int offline; - - if (cpu != -1) - rdp = per_cpu_ptr(&rcu_data, cpu); - if (likely(rdp->mynode)) { - /* Post-boot, so this should be for a no-CBs CPU. */ - offline = !__call_rcu_nocb(rdp, head, lazy, flags); - WARN_ON_ONCE(offline); - /* Offline CPU, _call_rcu() illegal, leak callback. */ - local_irq_restore(flags); - return; - } - /* - * Very early boot, before rcu_init(). Initialize if needed - * and then drop through to queue the callback. - */ - WARN_ON_ONCE(cpu != -1); + if (unlikely(!rcu_segcblist_is_enabled(&rdp->cblist))) { + // This can trigger due to call_rcu() from offline CPU: + WARN_ON_ONCE(rcu_scheduler_active != RCU_SCHEDULER_INACTIVE); WARN_ON_ONCE(!rcu_is_watching()); + // Very early boot, before rcu_init(). Initialize if needed + // and then drop through to queue the callback. if (rcu_segcblist_empty(&rdp->cblist)) rcu_segcblist_init(&rdp->cblist); } + if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags)) + return; // Enqueued onto ->nocb_bypass, so just leave. + /* If we get here, rcu_nocb_try_bypass() acquired ->nocb_lock. */ rcu_segcblist_enqueue(&rdp->cblist, head, lazy); if (__is_kfree_rcu_offset((unsigned long)func)) trace_rcu_kfree_callback(rcu_state.name, head, @@ -2548,8 +2602,13 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, int cpu, bool lazy) rcu_segcblist_n_cbs(&rdp->cblist)); /* Go handle any RCU core processing required. */ - __call_rcu_core(rdp, head, flags); - local_irq_restore(flags); + if (IS_ENABLED(CONFIG_RCU_NOCB_CPU) && + unlikely(rcu_segcblist_is_offloaded(&rdp->cblist))) { + __call_rcu_nocb_wake(rdp, was_alldone, flags); /* unlocks */ + } else { + __call_rcu_core(rdp, head, flags); + local_irq_restore(flags); + } } /** @@ -2589,7 +2648,7 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, int cpu, bool lazy) */ void call_rcu(struct rcu_head *head, rcu_callback_t func) { - __call_rcu(head, func, -1, 0); + __call_rcu(head, func, 0); } EXPORT_SYMBOL_GPL(call_rcu); @@ -2602,7 +2661,7 @@ EXPORT_SYMBOL_GPL(call_rcu); */ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func) { - __call_rcu(head, func, -1, 1); + __call_rcu(head, func, 1); } EXPORT_SYMBOL_GPL(kfree_call_rcu); @@ -2622,7 +2681,7 @@ static int rcu_blocking_is_gp(void) { int ret; - if (IS_ENABLED(CONFIG_PREEMPT)) + if (IS_ENABLED(CONFIG_PREEMPTION)) return rcu_scheduler_active == RCU_SCHEDULER_INACTIVE; might_sleep(); /* Check for RCU read-side critical section. */ preempt_disable(); @@ -2735,6 +2794,10 @@ static int rcu_pending(void) /* Check for CPU stalls, if enabled. */ check_cpu_stall(rdp); + /* Does this CPU need a deferred NOCB wakeup? */ + if (rcu_nocb_need_deferred_wakeup(rdp)) + return 1; + /* Is this CPU a NO_HZ_FULL CPU that should ignore RCU? */ if (rcu_nohz_full_cpu()) return 0; @@ -2750,6 +2813,8 @@ static int rcu_pending(void) /* Has RCU gone idle with this CPU needing another grace period? */ if (!rcu_gp_in_progress() && rcu_segcblist_is_enabled(&rdp->cblist) && + (!IS_ENABLED(CONFIG_RCU_NOCB_CPU) || + !rcu_segcblist_is_offloaded(&rdp->cblist)) && !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) return 1; @@ -2758,10 +2823,6 @@ static int rcu_pending(void) unlikely(READ_ONCE(rdp->gpwrap))) /* outside lock */ return 1; - /* Does this CPU need a deferred NOCB wakeup? */ - if (rcu_nocb_need_deferred_wakeup(rdp)) - return 1; - /* nothing to do */ return 0; } @@ -2801,6 +2862,8 @@ static void rcu_barrier_func(void *unused) rcu_barrier_trace(TPS("IRQ"), -1, rcu_state.barrier_sequence); rdp->barrier_head.func = rcu_barrier_callback; debug_rcu_head_queue(&rdp->barrier_head); + rcu_nocb_lock(rdp); + WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies)); if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head, 0)) { atomic_inc(&rcu_state.barrier_cpu_count); } else { @@ -2808,6 +2871,7 @@ static void rcu_barrier_func(void *unused) rcu_barrier_trace(TPS("IRQNQ"), -1, rcu_state.barrier_sequence); } + rcu_nocb_unlock(rdp); } /** @@ -2858,22 +2922,11 @@ void rcu_barrier(void) * corresponding CPU's preceding callbacks have been invoked. */ for_each_possible_cpu(cpu) { - if (!cpu_online(cpu) && !rcu_is_nocb_cpu(cpu)) - continue; rdp = per_cpu_ptr(&rcu_data, cpu); - if (rcu_is_nocb_cpu(cpu)) { - if (!rcu_nocb_cpu_needs_barrier(cpu)) { - rcu_barrier_trace(TPS("OfflineNoCB"), cpu, - rcu_state.barrier_sequence); - } else { - rcu_barrier_trace(TPS("OnlineNoCB"), cpu, - rcu_state.barrier_sequence); - smp_mb__before_atomic(); - atomic_inc(&rcu_state.barrier_cpu_count); - __call_rcu(&rdp->barrier_head, - rcu_barrier_callback, cpu, 0); - } - } else if (rcu_segcblist_n_cbs(&rdp->cblist)) { + if (!cpu_online(cpu) && + !rcu_segcblist_is_offloaded(&rdp->cblist)) + continue; + if (rcu_segcblist_n_cbs(&rdp->cblist)) { rcu_barrier_trace(TPS("OnlineQ"), cpu, rcu_state.barrier_sequence); smp_call_function_single(cpu, rcu_barrier_func, NULL, 1); @@ -2958,7 +3011,8 @@ rcu_boot_init_percpu_data(int cpu) * Initializes a CPU's per-CPU RCU data. Note that only one online or * offline event can be happening at a given time. Note also that we can * accept some slop in the rsp->gp_seq access due to the fact that this - * CPU cannot possibly have any RCU callbacks in flight yet. + * CPU cannot possibly have any non-offloaded RCU callbacks in flight yet. + * And any offloaded callbacks are being numbered elsewhere. */ int rcutree_prepare_cpu(unsigned int cpu) { @@ -2972,7 +3026,7 @@ int rcutree_prepare_cpu(unsigned int cpu) rdp->n_force_qs_snap = rcu_state.n_force_qs; rdp->blimit = blimit; if (rcu_segcblist_empty(&rdp->cblist) && /* No early-boot CBs? */ - !init_nocb_callback_list(rdp)) + !rcu_segcblist_is_offloaded(&rdp->cblist)) rcu_segcblist_init(&rdp->cblist); /* Re-enable callbacks. */ rdp->dynticks_nesting = 1; /* CPU not up, no tearing. */ rcu_dynticks_eqs_online(); @@ -3151,29 +3205,38 @@ void rcutree_migrate_callbacks(int cpu) { unsigned long flags; struct rcu_data *my_rdp; + struct rcu_node *my_rnp; struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); - struct rcu_node *rnp_root = rcu_get_root(); bool needwake; - if (rcu_is_nocb_cpu(cpu) || rcu_segcblist_empty(&rdp->cblist)) + if (rcu_segcblist_is_offloaded(&rdp->cblist) || + rcu_segcblist_empty(&rdp->cblist)) return; /* No callbacks to migrate. */ local_irq_save(flags); my_rdp = this_cpu_ptr(&rcu_data); - if (rcu_nocb_adopt_orphan_cbs(my_rdp, rdp, flags)) { - local_irq_restore(flags); - return; - } - raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */ + my_rnp = my_rdp->mynode; + rcu_nocb_lock(my_rdp); /* irqs already disabled. */ + WARN_ON_ONCE(!rcu_nocb_flush_bypass(my_rdp, NULL, jiffies)); + raw_spin_lock_rcu_node(my_rnp); /* irqs already disabled. */ /* Leverage recent GPs and set GP for new callbacks. */ - needwake = rcu_advance_cbs(rnp_root, rdp) || - rcu_advance_cbs(rnp_root, my_rdp); + needwake = rcu_advance_cbs(my_rnp, rdp) || + rcu_advance_cbs(my_rnp, my_rdp); rcu_segcblist_merge(&my_rdp->cblist, &rdp->cblist); + needwake = needwake || rcu_advance_cbs(my_rnp, my_rdp); + rcu_segcblist_disable(&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 (rcu_segcblist_is_offloaded(&my_rdp->cblist)) { + raw_spin_unlock_rcu_node(my_rnp); /* irqs remain disabled. */ + __call_rcu_nocb_wake(my_rdp, true, flags); + } else { + rcu_nocb_unlock(my_rdp); /* irqs remain disabled. */ + raw_spin_unlock_irqrestore_rcu_node(my_rnp, flags); + } if (needwake) rcu_gp_kthread_wake(); + lockdep_assert_irqs_enabled(); 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", @@ -3234,13 +3297,13 @@ static int __init rcu_spawn_gp_kthread(void) t = kthread_create(rcu_gp_kthread, NULL, "%s", rcu_state.name); if (WARN_ONCE(IS_ERR(t), "%s: Could not start grace-period kthread, OOM is now expected behavior\n", __func__)) return 0; - rnp = rcu_get_root(); - raw_spin_lock_irqsave_rcu_node(rnp, flags); - rcu_state.gp_kthread = t; if (kthread_prio) { sp.sched_priority = kthread_prio; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); } + rnp = rcu_get_root(); + raw_spin_lock_irqsave_rcu_node(rnp, flags); + rcu_state.gp_kthread = t; raw_spin_unlock_irqrestore_rcu_node(rnp, flags); wake_up_process(t); rcu_spawn_nocb_kthreads(); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 7acaf3a62d39..c612f306fe89 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -194,29 +194,38 @@ struct rcu_data { /* 5) Callback offloading. */ #ifdef CONFIG_RCU_NOCB_CPU - struct rcu_head *nocb_head; /* CBs waiting for kthread. */ - struct rcu_head **nocb_tail; - atomic_long_t nocb_q_count; /* # CBs waiting for nocb */ - atomic_long_t nocb_q_count_lazy; /* invocation (all stages). */ - struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */ - struct rcu_head **nocb_follower_tail; - struct swait_queue_head nocb_wq; /* For nocb kthreads to sleep on. */ - struct task_struct *nocb_kthread; + struct swait_queue_head nocb_cb_wq; /* For nocb kthreads to sleep on. */ + struct task_struct *nocb_gp_kthread; raw_spinlock_t nocb_lock; /* Guard following pair of fields. */ + atomic_t nocb_lock_contended; /* Contention experienced. */ int nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */ struct timer_list nocb_timer; /* Enforce finite deferral. */ - - /* The following fields are used by the leader, hence own cacheline. */ - struct rcu_head *nocb_gp_head ____cacheline_internodealigned_in_smp; - /* CBs waiting for GP. */ - struct rcu_head **nocb_gp_tail; - bool nocb_leader_sleep; /* Is the nocb leader thread asleep? */ - struct rcu_data *nocb_next_follower; - /* Next follower in wakeup chain. */ - - /* The following fields are used by the follower, hence new cachline. */ - struct rcu_data *nocb_leader ____cacheline_internodealigned_in_smp; - /* Leader CPU takes GP-end wakeups. */ + unsigned long nocb_gp_adv_time; /* Last call_rcu() CB adv (jiffies). */ + + /* The following fields are used by call_rcu, hence own cacheline. */ + raw_spinlock_t nocb_bypass_lock ____cacheline_internodealigned_in_smp; + struct rcu_cblist nocb_bypass; /* Lock-contention-bypass CB list. */ + unsigned long nocb_bypass_first; /* Time (jiffies) of first enqueue. */ + unsigned long nocb_nobypass_last; /* Last ->cblist enqueue (jiffies). */ + int nocb_nobypass_count; /* # ->cblist enqueues at ^^^ time. */ + + /* The following fields are used by GP kthread, hence own cacheline. */ + raw_spinlock_t nocb_gp_lock ____cacheline_internodealigned_in_smp; + struct timer_list nocb_bypass_timer; /* Force nocb_bypass flush. */ + u8 nocb_gp_sleep; /* Is the nocb GP thread asleep? */ + u8 nocb_gp_bypass; /* Found a bypass on last scan? */ + u8 nocb_gp_gp; /* GP to wait for on last scan? */ + unsigned long nocb_gp_seq; /* If so, ->gp_seq to wait for. */ + unsigned long nocb_gp_loops; /* # passes through wait code. */ + struct swait_queue_head nocb_gp_wq; /* For nocb kthreads to sleep on. */ + bool nocb_cb_sleep; /* Is the nocb CB thread asleep? */ + struct task_struct *nocb_cb_kthread; + struct rcu_data *nocb_next_cb_rdp; + /* Next rcu_data in wakeup chain. */ + + /* The following fields are used by CB kthread, hence new cacheline. */ + struct rcu_data *nocb_gp_rdp ____cacheline_internodealigned_in_smp; + /* GP rdp takes GP-end wakeups. */ #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ /* 6) RCU priority boosting. */ @@ -419,25 +428,39 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp); static bool rcu_preempt_need_deferred_qs(struct task_struct *t); static void rcu_preempt_deferred_qs(struct task_struct *t); static void zero_cpu_stall_ticks(struct rcu_data *rdp); -static bool rcu_nocb_cpu_needs_barrier(int cpu); 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); -static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, - bool lazy, unsigned long flags); -static bool rcu_nocb_adopt_orphan_cbs(struct rcu_data *my_rdp, - struct rcu_data *rdp, - unsigned long flags); +static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp, + unsigned long j); +static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp, + bool *was_alldone, unsigned long flags); +static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty, + unsigned long flags); static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp); static void do_nocb_deferred_wakeup(struct rcu_data *rdp); static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp); static void rcu_spawn_cpu_nocb_kthread(int cpu); static void __init rcu_spawn_nocb_kthreads(void); +static void show_rcu_nocb_state(struct rcu_data *rdp); +static void rcu_nocb_lock(struct rcu_data *rdp); +static void rcu_nocb_unlock(struct rcu_data *rdp); +static void rcu_nocb_unlock_irqrestore(struct rcu_data *rdp, + unsigned long flags); +static void rcu_lockdep_assert_cblist_protected(struct rcu_data *rdp); #ifdef CONFIG_RCU_NOCB_CPU static void __init rcu_organize_nocb_kthreads(void); -#endif /* #ifdef CONFIG_RCU_NOCB_CPU */ -static bool init_nocb_callback_list(struct rcu_data *rdp); -static unsigned long rcu_get_n_cbs_nocb_cpu(struct rcu_data *rdp); +#define rcu_nocb_lock_irqsave(rdp, flags) \ +do { \ + if (!rcu_segcblist_is_offloaded(&(rdp)->cblist)) \ + local_irq_save(flags); \ + else \ + raw_spin_lock_irqsave(&(rdp)->nocb_lock, (flags)); \ +} while (0) +#else /* #ifdef CONFIG_RCU_NOCB_CPU */ +#define rcu_nocb_lock_irqsave(rdp, flags) local_irq_save(flags) +#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ + static void rcu_bind_gp_kthread(void); static bool rcu_nohz_full_cpu(void); static void rcu_dynticks_task_enter(void); diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index af7e7b9c86af..d632cd019597 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -781,7 +781,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) * other hand, if the CPU is not in an RCU read-side critical section, * the IPI handler reports the quiescent state immediately. * - * Although this is a greate improvement over previous expedited + * Although this is a great improvement over previous expedited * implementations, it is still unfriendly to real-time workloads, so is * thus not recommended for any sort of common-case code. In fact, if * you are using synchronize_rcu_expedited() in a loop, please restructure @@ -792,6 +792,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) */ void synchronize_rcu_expedited(void) { + bool boottime = (rcu_scheduler_active == RCU_SCHEDULER_INIT); struct rcu_exp_work rew; struct rcu_node *rnp; unsigned long s; @@ -817,7 +818,7 @@ void synchronize_rcu_expedited(void) return; /* Someone else did our work for us. */ /* Ensure that load happens before action based on it. */ - if (unlikely(rcu_scheduler_active == RCU_SCHEDULER_INIT)) { + if (unlikely(boottime)) { /* Direct call during scheduler init and early_initcalls(). */ rcu_exp_sel_wait_wake(s); } else { @@ -835,5 +836,8 @@ void synchronize_rcu_expedited(void) /* Let the next expedited grace period start. */ mutex_unlock(&rcu_state.exp_mutex); + + if (likely(!boottime)) + destroy_work_on_stack(&rew.rew_work); } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index acb225023ed1..2defc7fe74c3 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -288,7 +288,6 @@ void rcu_note_context_switch(bool preempt) struct rcu_data *rdp = this_cpu_ptr(&rcu_data); struct rcu_node *rnp; - barrier(); /* Avoid RCU read-side critical sections leaking down. */ trace_rcu_utilization(TPS("Start context switch")); lockdep_assert_irqs_disabled(); WARN_ON_ONCE(!preempt && t->rcu_read_lock_nesting > 0); @@ -314,15 +313,6 @@ void rcu_note_context_switch(bool preempt) ? rnp->gp_seq : rcu_seq_snap(&rnp->gp_seq)); rcu_preempt_ctxt_queue(rnp, rdp); - } else if (t->rcu_read_lock_nesting < 0 && - t->rcu_read_unlock_special.s) { - - /* - * Complete exit from RCU read-side critical section on - * behalf of preempted instance of __rcu_read_unlock(). - */ - rcu_read_unlock_special(t); - rcu_preempt_deferred_qs(t); } else { rcu_preempt_deferred_qs(t); } @@ -340,7 +330,6 @@ void rcu_note_context_switch(bool preempt) if (rdp->exp_deferred_qs) rcu_report_exp_rdp(rdp); trace_rcu_utilization(TPS("End context switch")); - barrier(); /* Avoid RCU read-side critical sections leaking up. */ } EXPORT_SYMBOL_GPL(rcu_note_context_switch); @@ -626,22 +615,18 @@ static void rcu_read_unlock_special(struct task_struct *t) (rdp->grpmask & rnp->expmask) || tick_nohz_full_cpu(rdp->cpu); // Need to defer quiescent state until everything is enabled. - if ((exp || in_irq()) && irqs_were_disabled && use_softirq && - (in_irq() || !t->rcu_read_unlock_special.b.deferred_qs)) { + if (irqs_were_disabled && use_softirq && + (in_interrupt() || + (exp && !t->rcu_read_unlock_special.b.deferred_qs))) { // Using softirq, safe to awaken, and we get // no help from enabling irqs, unlike bh/preempt. raise_softirq_irqoff(RCU_SOFTIRQ); - } else if (exp && irqs_were_disabled && !use_softirq && - !t->rcu_read_unlock_special.b.deferred_qs) { - // Safe to awaken and we get no help from enabling - // irqs, unlike bh/preempt. - invoke_rcu_core(); } else { // Enabling BH or preempt does reschedule, so... // Also if no expediting or NO_HZ_FULL, slow is OK. set_tsk_need_resched(current); set_preempt_need_resched(); - if (IS_ENABLED(CONFIG_IRQ_WORK) && + if (IS_ENABLED(CONFIG_IRQ_WORK) && irqs_were_disabled && !rdp->defer_qs_iw_pending && exp) { // Get scheduler to re-evaluate and call hooks. // If !IRQ_WORK, FQS scan will eventually IPI. @@ -828,11 +813,6 @@ static void rcu_qs(void) * dyntick-idle quiescent state visible to other CPUs, which will in * some cases serve for expedited as well as normal grace periods. * Either way, register a lightweight quiescent state. - * - * The barrier() calls are redundant in the common case when this is - * called externally, but just in case this is called from within this - * file. - * */ void rcu_all_qs(void) { @@ -847,14 +827,12 @@ void rcu_all_qs(void) return; } this_cpu_write(rcu_data.rcu_urgent_qs, false); - barrier(); /* Avoid RCU read-side critical sections leaking down. */ if (unlikely(raw_cpu_read(rcu_data.rcu_need_heavy_qs))) { local_irq_save(flags); rcu_momentary_dyntick_idle(); local_irq_restore(flags); } rcu_qs(); - barrier(); /* Avoid RCU read-side critical sections leaking up. */ preempt_enable(); } EXPORT_SYMBOL_GPL(rcu_all_qs); @@ -864,7 +842,6 @@ EXPORT_SYMBOL_GPL(rcu_all_qs); */ void rcu_note_context_switch(bool preempt) { - barrier(); /* Avoid RCU read-side critical sections leaking down. */ trace_rcu_utilization(TPS("Start context switch")); rcu_qs(); /* Load rcu_urgent_qs before other flags. */ @@ -877,7 +854,6 @@ void rcu_note_context_switch(bool preempt) rcu_tasks_qs(current); out: trace_rcu_utilization(TPS("End context switch")); - barrier(); /* Avoid RCU read-side critical sections leaking up. */ } EXPORT_SYMBOL_GPL(rcu_note_context_switch); @@ -1134,7 +1110,7 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) * already exist. We only create this kthread for preemptible RCU. * Returns zero if all is well, a negated errno otherwise. */ -static int rcu_spawn_one_boost_kthread(struct rcu_node *rnp) +static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp) { int rnp_index = rnp - rcu_get_root(); unsigned long flags; @@ -1142,25 +1118,27 @@ static int rcu_spawn_one_boost_kthread(struct rcu_node *rnp) struct task_struct *t; if (!IS_ENABLED(CONFIG_PREEMPT_RCU)) - return 0; + return; if (!rcu_scheduler_fully_active || rcu_rnp_online_cpus(rnp) == 0) - return 0; + return; rcu_state.boost = 1; + if (rnp->boost_kthread_task != NULL) - return 0; + return; + t = kthread_create(rcu_boost_kthread, (void *)rnp, "rcub/%d", rnp_index); - if (IS_ERR(t)) - return PTR_ERR(t); + if (WARN_ON_ONCE(IS_ERR(t))) + return; + raw_spin_lock_irqsave_rcu_node(rnp, flags); rnp->boost_kthread_task = t; raw_spin_unlock_irqrestore_rcu_node(rnp, flags); sp.sched_priority = kthread_prio; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */ - return 0; } /* @@ -1201,7 +1179,7 @@ static void __init rcu_spawn_boost_kthreads(void) struct rcu_node *rnp; rcu_for_each_leaf_node(rnp) - (void)rcu_spawn_one_boost_kthread(rnp); + rcu_spawn_one_boost_kthread(rnp); } static void rcu_prepare_kthreads(int cpu) @@ -1211,7 +1189,7 @@ static void rcu_prepare_kthreads(int cpu) /* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */ if (rcu_scheduler_fully_active) - (void)rcu_spawn_one_boost_kthread(rnp); + rcu_spawn_one_boost_kthread(rnp); } #else /* #ifdef CONFIG_RCU_BOOST */ @@ -1248,10 +1226,10 @@ static void rcu_prepare_kthreads(int cpu) #if !defined(CONFIG_RCU_FAST_NO_HZ) /* - * Check to see if any future RCU-related work will need to be done - * by the current CPU, even if none need be done immediately, returning - * 1 if so. This function is part of the RCU implementation; it is -not- - * an exported member of the RCU API. + * Check to see if any future non-offloaded RCU-related work will need + * to be done by the current CPU, even if none need be done immediately, + * returning 1 if so. This function is part of the RCU implementation; + * it is -not- an exported member of the RCU API. * * Because we not have RCU_FAST_NO_HZ, just check whether or not this * CPU has RCU callbacks queued. @@ -1259,7 +1237,8 @@ static void rcu_prepare_kthreads(int cpu) int rcu_needs_cpu(u64 basemono, u64 *nextevt) { *nextevt = KTIME_MAX; - return !rcu_segcblist_empty(&this_cpu_ptr(&rcu_data)->cblist); + return !rcu_segcblist_empty(&this_cpu_ptr(&rcu_data)->cblist) && + !rcu_segcblist_is_offloaded(&this_cpu_ptr(&rcu_data)->cblist); } /* @@ -1360,8 +1339,9 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt) lockdep_assert_irqs_disabled(); - /* If no callbacks, RCU doesn't need the CPU. */ - if (rcu_segcblist_empty(&rdp->cblist)) { + /* If no non-offloaded callbacks, RCU doesn't need the CPU. */ + if (rcu_segcblist_empty(&rdp->cblist) || + rcu_segcblist_is_offloaded(&this_cpu_ptr(&rcu_data)->cblist)) { *nextevt = KTIME_MAX; return 0; } @@ -1404,7 +1384,7 @@ static void rcu_prepare_for_idle(void) int tne; lockdep_assert_irqs_disabled(); - if (rcu_is_nocb_cpu(smp_processor_id())) + if (rcu_segcblist_is_offloaded(&rdp->cblist)) return; /* Handle nohz enablement switches conservatively. */ @@ -1453,8 +1433,10 @@ static void rcu_prepare_for_idle(void) */ static void rcu_cleanup_after_idle(void) { + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); + lockdep_assert_irqs_disabled(); - if (rcu_is_nocb_cpu(smp_processor_id())) + if (rcu_segcblist_is_offloaded(&rdp->cblist)) return; if (rcu_try_advance_all_cbs()) invoke_rcu_core(); @@ -1469,10 +1451,10 @@ static void rcu_cleanup_after_idle(void) * specified by rcu_nocb_mask. For the CPUs in the set, there are kthreads * created that pull the callbacks from the corresponding CPU, wait for * a grace period to elapse, and invoke the callbacks. These kthreads - * are organized into leaders, which manage incoming callbacks, wait for - * grace periods, and awaken followers, and the followers, which only - * invoke callbacks. Each leader is its own follower. The no-CBs CPUs - * do a wake_up() on their kthread when they insert a callback into any + * are organized into GP kthreads, which manage incoming callbacks, wait for + * grace periods, and awaken CB kthreads, and the CB kthreads, which only + * invoke callbacks. Each GP kthread invokes its own CBs. The no-CBs CPUs + * do a wake_up() on their GP kthread when they insert a callback into any * empty list, unless the rcu_nocb_poll boot parameter has been specified, * in which case each kthread actively polls its CPU. (Which isn't so great * for energy efficiency, but which does reduce RCU's overhead on that CPU.) @@ -1515,6 +1497,116 @@ static int __init parse_rcu_nocb_poll(char *arg) early_param("rcu_nocb_poll", parse_rcu_nocb_poll); /* + * Don't bother bypassing ->cblist if the call_rcu() rate is low. + * After all, the main point of bypassing is to avoid lock contention + * on ->nocb_lock, which only can happen at high call_rcu() rates. + */ +int nocb_nobypass_lim_per_jiffy = 16 * 1000 / HZ; +module_param(nocb_nobypass_lim_per_jiffy, int, 0); + +/* + * Acquire the specified rcu_data structure's ->nocb_bypass_lock. If the + * lock isn't immediately available, increment ->nocb_lock_contended to + * flag the contention. + */ +static void rcu_nocb_bypass_lock(struct rcu_data *rdp) +{ + lockdep_assert_irqs_disabled(); + if (raw_spin_trylock(&rdp->nocb_bypass_lock)) + return; + atomic_inc(&rdp->nocb_lock_contended); + WARN_ON_ONCE(smp_processor_id() != rdp->cpu); + smp_mb__after_atomic(); /* atomic_inc() before lock. */ + raw_spin_lock(&rdp->nocb_bypass_lock); + smp_mb__before_atomic(); /* atomic_dec() after lock. */ + atomic_dec(&rdp->nocb_lock_contended); +} + +/* + * Spinwait until the specified rcu_data structure's ->nocb_lock is + * not contended. Please note that this is extremely special-purpose, + * relying on the fact that at most two kthreads and one CPU contend for + * this lock, and also that the two kthreads are guaranteed to have frequent + * grace-period-duration time intervals between successive acquisitions + * of the lock. This allows us to use an extremely simple throttling + * mechanism, and further to apply it only to the CPU doing floods of + * call_rcu() invocations. Don't try this at home! + */ +static void rcu_nocb_wait_contended(struct rcu_data *rdp) +{ + WARN_ON_ONCE(smp_processor_id() != rdp->cpu); + while (WARN_ON_ONCE(atomic_read(&rdp->nocb_lock_contended))) + cpu_relax(); +} + +/* + * Conditionally acquire the specified rcu_data structure's + * ->nocb_bypass_lock. + */ +static bool rcu_nocb_bypass_trylock(struct rcu_data *rdp) +{ + lockdep_assert_irqs_disabled(); + return raw_spin_trylock(&rdp->nocb_bypass_lock); +} + +/* + * Release the specified rcu_data structure's ->nocb_bypass_lock. + */ +static void rcu_nocb_bypass_unlock(struct rcu_data *rdp) +{ + lockdep_assert_irqs_disabled(); + raw_spin_unlock(&rdp->nocb_bypass_lock); +} + +/* + * Acquire the specified rcu_data structure's ->nocb_lock, but only + * if it corresponds to a no-CBs CPU. + */ +static void rcu_nocb_lock(struct rcu_data *rdp) +{ + lockdep_assert_irqs_disabled(); + if (!rcu_segcblist_is_offloaded(&rdp->cblist)) + return; + raw_spin_lock(&rdp->nocb_lock); +} + +/* + * Release the specified rcu_data structure's ->nocb_lock, but only + * if it corresponds to a no-CBs CPU. + */ +static void rcu_nocb_unlock(struct rcu_data *rdp) +{ + if (rcu_segcblist_is_offloaded(&rdp->cblist)) { + lockdep_assert_irqs_disabled(); + raw_spin_unlock(&rdp->nocb_lock); + } +} + +/* + * Release the specified rcu_data structure's ->nocb_lock and restore + * interrupts, but only if it corresponds to a no-CBs CPU. + */ +static void rcu_nocb_unlock_irqrestore(struct rcu_data *rdp, + unsigned long flags) +{ + if (rcu_segcblist_is_offloaded(&rdp->cblist)) { + lockdep_assert_irqs_disabled(); + raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); + } else { + local_irq_restore(flags); + } +} + +/* Lockdep check that ->cblist may be safely accessed. */ +static void rcu_lockdep_assert_cblist_protected(struct rcu_data *rdp) +{ + lockdep_assert_irqs_disabled(); + if (rcu_segcblist_is_offloaded(&rdp->cblist) && + cpu_online(rdp->cpu)) + lockdep_assert_held(&rdp->nocb_lock); +} + +/* * Wake up any no-CBs CPUs' kthreads that were waiting on the just-ended * grace period. */ @@ -1543,440 +1635,514 @@ bool rcu_is_nocb_cpu(int cpu) } /* - * Kick the leader kthread for this NOCB group. Caller holds ->nocb_lock + * Kick the GP kthread for this NOCB group. Caller holds ->nocb_lock * and this function releases it. */ -static void __wake_nocb_leader(struct rcu_data *rdp, bool force, - unsigned long flags) +static void wake_nocb_gp(struct rcu_data *rdp, bool force, + unsigned long flags) __releases(rdp->nocb_lock) { - struct rcu_data *rdp_leader = rdp->nocb_leader; + bool needwake = false; + struct rcu_data *rdp_gp = rdp->nocb_gp_rdp; lockdep_assert_held(&rdp->nocb_lock); - if (!READ_ONCE(rdp_leader->nocb_kthread)) { - raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); + if (!READ_ONCE(rdp_gp->nocb_gp_kthread)) { + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, + TPS("AlreadyAwake")); + rcu_nocb_unlock_irqrestore(rdp, flags); return; } - if (rdp_leader->nocb_leader_sleep || force) { - /* Prior smp_mb__after_atomic() orders against prior enqueue. */ - WRITE_ONCE(rdp_leader->nocb_leader_sleep, false); - del_timer(&rdp->nocb_timer); - raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); - smp_mb(); /* ->nocb_leader_sleep before swake_up_one(). */ - swake_up_one(&rdp_leader->nocb_wq); - } else { - raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); + del_timer(&rdp->nocb_timer); + rcu_nocb_unlock_irqrestore(rdp, flags); + raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags); + if (force || READ_ONCE(rdp_gp->nocb_gp_sleep)) { + WRITE_ONCE(rdp_gp->nocb_gp_sleep, false); + needwake = true; + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("DoWake")); } + raw_spin_unlock_irqrestore(&rdp_gp->nocb_gp_lock, flags); + if (needwake) + wake_up_process(rdp_gp->nocb_gp_kthread); } /* - * Kick the leader kthread for this NOCB group, but caller has not - * acquired locks. + * Arrange to wake the GP kthread for this NOCB group at some future + * time when it is safe to do so. */ -static void wake_nocb_leader(struct rcu_data *rdp, bool force) +static void wake_nocb_gp_defer(struct rcu_data *rdp, int waketype, + const char *reason) { - unsigned long flags; + if (rdp->nocb_defer_wakeup == RCU_NOCB_WAKE_NOT) + mod_timer(&rdp->nocb_timer, jiffies + 1); + if (rdp->nocb_defer_wakeup < waketype) + WRITE_ONCE(rdp->nocb_defer_wakeup, waketype); + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, reason); +} + +/* + * Flush the ->nocb_bypass queue into ->cblist, enqueuing rhp if non-NULL. + * However, if there is a callback to be enqueued and if ->nocb_bypass + * proves to be initially empty, just return false because the no-CB GP + * kthread may need to be awakened in this case. + * + * Note that this function always returns true if rhp is NULL. + */ +static bool rcu_nocb_do_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp, + unsigned long j) +{ + struct rcu_cblist rcl; - raw_spin_lock_irqsave(&rdp->nocb_lock, flags); - __wake_nocb_leader(rdp, force, flags); + WARN_ON_ONCE(!rcu_segcblist_is_offloaded(&rdp->cblist)); + rcu_lockdep_assert_cblist_protected(rdp); + lockdep_assert_held(&rdp->nocb_bypass_lock); + if (rhp && !rcu_cblist_n_cbs(&rdp->nocb_bypass)) { + raw_spin_unlock(&rdp->nocb_bypass_lock); + return false; + } + /* Note: ->cblist.len already accounts for ->nocb_bypass contents. */ + if (rhp) + rcu_segcblist_inc_len(&rdp->cblist); /* Must precede enqueue. */ + rcu_cblist_flush_enqueue(&rcl, &rdp->nocb_bypass, rhp); + rcu_segcblist_insert_pend_cbs(&rdp->cblist, &rcl); + WRITE_ONCE(rdp->nocb_bypass_first, j); + rcu_nocb_bypass_unlock(rdp); + return true; } /* - * Arrange to wake the leader kthread for this NOCB group at some - * future time when it is safe to do so. + * Flush the ->nocb_bypass queue into ->cblist, enqueuing rhp if non-NULL. + * However, if there is a callback to be enqueued and if ->nocb_bypass + * proves to be initially empty, just return false because the no-CB GP + * kthread may need to be awakened in this case. + * + * Note that this function always returns true if rhp is NULL. */ -static void wake_nocb_leader_defer(struct rcu_data *rdp, int waketype, - const char *reason) +static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp, + unsigned long j) { - unsigned long flags; + if (!rcu_segcblist_is_offloaded(&rdp->cblist)) + return true; + rcu_lockdep_assert_cblist_protected(rdp); + rcu_nocb_bypass_lock(rdp); + return rcu_nocb_do_flush_bypass(rdp, rhp, j); +} - raw_spin_lock_irqsave(&rdp->nocb_lock, flags); - if (rdp->nocb_defer_wakeup == RCU_NOCB_WAKE_NOT) - mod_timer(&rdp->nocb_timer, jiffies + 1); - WRITE_ONCE(rdp->nocb_defer_wakeup, waketype); - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, reason); - raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); +/* + * If the ->nocb_bypass_lock is immediately available, flush the + * ->nocb_bypass queue into ->cblist. + */ +static void rcu_nocb_try_flush_bypass(struct rcu_data *rdp, unsigned long j) +{ + rcu_lockdep_assert_cblist_protected(rdp); + if (!rcu_segcblist_is_offloaded(&rdp->cblist) || + !rcu_nocb_bypass_trylock(rdp)) + return; + WARN_ON_ONCE(!rcu_nocb_do_flush_bypass(rdp, NULL, j)); } -/* Does rcu_barrier need to queue an RCU callback on the specified CPU? */ -static bool rcu_nocb_cpu_needs_barrier(int cpu) +/* + * See whether it is appropriate to use the ->nocb_bypass list in order + * to control contention on ->nocb_lock. A limited number of direct + * enqueues are permitted into ->cblist per jiffy. If ->nocb_bypass + * is non-empty, further callbacks must be placed into ->nocb_bypass, + * otherwise rcu_barrier() breaks. Use rcu_nocb_flush_bypass() to switch + * back to direct use of ->cblist. However, ->nocb_bypass should not be + * used if ->cblist is empty, because otherwise callbacks can be stranded + * on ->nocb_bypass because we cannot count on the current CPU ever again + * invoking call_rcu(). The general rule is that if ->nocb_bypass is + * non-empty, the corresponding no-CBs grace-period kthread must not be + * in an indefinite sleep state. + * + * Finally, it is not permitted to use the bypass during early boot, + * as doing so would confuse the auto-initialization code. Besides + * which, there is no point in worrying about lock contention while + * there is only one CPU in operation. + */ +static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp, + bool *was_alldone, unsigned long flags) { - struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); - unsigned long ret; -#ifdef CONFIG_PROVE_RCU - struct rcu_head *rhp; -#endif /* #ifdef CONFIG_PROVE_RCU */ + unsigned long c; + unsigned long cur_gp_seq; + unsigned long j = jiffies; + long ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass); - /* - * Check count of all no-CBs callbacks awaiting invocation. - * There needs to be a barrier before this function is called, - * but associated with a prior determination that no more - * callbacks would be posted. In the worst case, the first - * barrier in rcu_barrier() suffices (but the caller cannot - * necessarily rely on this, not a substitute for the caller - * getting the concurrency design right!). There must also be a - * barrier between the following load and posting of a callback - * (if a callback is in fact needed). This is associated with an - * atomic_inc() in the caller. - */ - ret = rcu_get_n_cbs_nocb_cpu(rdp); - -#ifdef CONFIG_PROVE_RCU - rhp = READ_ONCE(rdp->nocb_head); - if (!rhp) - rhp = READ_ONCE(rdp->nocb_gp_head); - if (!rhp) - rhp = READ_ONCE(rdp->nocb_follower_head); - - /* Having no rcuo kthread but CBs after scheduler starts is bad! */ - if (!READ_ONCE(rdp->nocb_kthread) && rhp && - rcu_scheduler_fully_active) { - /* RCU callback enqueued before CPU first came online??? */ - pr_err("RCU: Never-onlined no-CBs CPU %d has CB %p\n", - cpu, rhp->func); - WARN_ON_ONCE(1); + if (!rcu_segcblist_is_offloaded(&rdp->cblist)) { + *was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist); + return false; /* Not offloaded, no bypassing. */ + } + lockdep_assert_irqs_disabled(); + + // Don't use ->nocb_bypass during early boot. + if (rcu_scheduler_active != RCU_SCHEDULER_RUNNING) { + rcu_nocb_lock(rdp); + WARN_ON_ONCE(rcu_cblist_n_cbs(&rdp->nocb_bypass)); + *was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist); + return false; + } + + // If we have advanced to a new jiffy, reset counts to allow + // moving back from ->nocb_bypass to ->cblist. + if (j == rdp->nocb_nobypass_last) { + c = rdp->nocb_nobypass_count + 1; + } else { + WRITE_ONCE(rdp->nocb_nobypass_last, j); + c = rdp->nocb_nobypass_count - nocb_nobypass_lim_per_jiffy; + if (ULONG_CMP_LT(rdp->nocb_nobypass_count, + nocb_nobypass_lim_per_jiffy)) + c = 0; + else if (c > nocb_nobypass_lim_per_jiffy) + c = nocb_nobypass_lim_per_jiffy; + } + WRITE_ONCE(rdp->nocb_nobypass_count, c); + + // If there hasn't yet been all that many ->cblist enqueues + // this jiffy, tell the caller to enqueue onto ->cblist. But flush + // ->nocb_bypass first. + if (rdp->nocb_nobypass_count < nocb_nobypass_lim_per_jiffy) { + rcu_nocb_lock(rdp); + *was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist); + if (*was_alldone) + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, + TPS("FirstQ")); + WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, j)); + WARN_ON_ONCE(rcu_cblist_n_cbs(&rdp->nocb_bypass)); + return false; // Caller must enqueue the callback. + } + + // If ->nocb_bypass has been used too long or is too full, + // flush ->nocb_bypass to ->cblist. + if ((ncbs && j != READ_ONCE(rdp->nocb_bypass_first)) || + ncbs >= qhimark) { + rcu_nocb_lock(rdp); + if (!rcu_nocb_flush_bypass(rdp, rhp, j)) { + *was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist); + if (*was_alldone) + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, + TPS("FirstQ")); + WARN_ON_ONCE(rcu_cblist_n_cbs(&rdp->nocb_bypass)); + return false; // Caller must enqueue the callback. + } + if (j != rdp->nocb_gp_adv_time && + rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq) && + rcu_seq_done(&rdp->mynode->gp_seq, cur_gp_seq)) { + rcu_advance_cbs_nowake(rdp->mynode, rdp); + rdp->nocb_gp_adv_time = j; + } + rcu_nocb_unlock_irqrestore(rdp, flags); + return true; // Callback already enqueued. } -#endif /* #ifdef CONFIG_PROVE_RCU */ - return !!ret; + // We need to use the bypass. + rcu_nocb_wait_contended(rdp); + rcu_nocb_bypass_lock(rdp); + ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass); + rcu_segcblist_inc_len(&rdp->cblist); /* Must precede enqueue. */ + rcu_cblist_enqueue(&rdp->nocb_bypass, rhp); + if (!ncbs) { + WRITE_ONCE(rdp->nocb_bypass_first, j); + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("FirstBQ")); + } + rcu_nocb_bypass_unlock(rdp); + smp_mb(); /* Order enqueue before wake. */ + if (ncbs) { + local_irq_restore(flags); + } else { + // No-CBs GP kthread might be indefinitely asleep, if so, wake. + rcu_nocb_lock(rdp); // Rare during call_rcu() flood. + if (!rcu_segcblist_pend_cbs(&rdp->cblist)) { + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, + TPS("FirstBQwake")); + __call_rcu_nocb_wake(rdp, true, flags); + } else { + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, + TPS("FirstBQnoWake")); + rcu_nocb_unlock_irqrestore(rdp, flags); + } + } + return true; // Callback already enqueued. } /* - * Enqueue the specified string of rcu_head structures onto the specified - * CPU's no-CBs lists. The CPU is specified by rdp, the head of the - * string by rhp, and the tail of the string by rhtp. The non-lazy/lazy - * counts are supplied by rhcount and rhcount_lazy. + * Awaken the no-CBs grace-period kthead if needed, either due to it + * legitimately being asleep or due to overload conditions. * * If warranted, also wake up the kthread servicing this CPUs queues. */ -static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, - struct rcu_head *rhp, - struct rcu_head **rhtp, - int rhcount, int rhcount_lazy, - unsigned long flags) +static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone, + unsigned long flags) + __releases(rdp->nocb_lock) { - int len; - struct rcu_head **old_rhpp; + unsigned long cur_gp_seq; + unsigned long j; + long len; struct task_struct *t; - /* Enqueue the callback on the nocb list and update counts. */ - atomic_long_add(rhcount, &rdp->nocb_q_count); - /* rcu_barrier() relies on ->nocb_q_count add before xchg. */ - old_rhpp = xchg(&rdp->nocb_tail, rhtp); - WRITE_ONCE(*old_rhpp, rhp); - atomic_long_add(rhcount_lazy, &rdp->nocb_q_count_lazy); - smp_mb__after_atomic(); /* Store *old_rhpp before _wake test. */ - - /* If we are not being polled and there is a kthread, awaken it ... */ - t = READ_ONCE(rdp->nocb_kthread); + // If we are being polled or there is no kthread, just leave. + t = READ_ONCE(rdp->nocb_gp_kthread); if (rcu_nocb_poll || !t) { trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNotPoll")); + rcu_nocb_unlock_irqrestore(rdp, flags); return; } - len = rcu_get_n_cbs_nocb_cpu(rdp); - if (old_rhpp == &rdp->nocb_head) { + // Need to actually to a wakeup. + len = rcu_segcblist_n_cbs(&rdp->cblist); + if (was_alldone) { + rdp->qlen_last_fqs_check = len; if (!irqs_disabled_flags(flags)) { /* ... if queue was empty ... */ - wake_nocb_leader(rdp, false); + wake_nocb_gp(rdp, false, flags); trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeEmpty")); } else { - wake_nocb_leader_defer(rdp, RCU_NOCB_WAKE, - TPS("WakeEmptyIsDeferred")); + wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE, + TPS("WakeEmptyIsDeferred")); + rcu_nocb_unlock_irqrestore(rdp, flags); } - rdp->qlen_last_fqs_check = 0; } else if (len > rdp->qlen_last_fqs_check + qhimark) { /* ... or if many callbacks queued. */ - if (!irqs_disabled_flags(flags)) { - wake_nocb_leader(rdp, true); - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, - TPS("WakeOvf")); - } else { - wake_nocb_leader_defer(rdp, RCU_NOCB_WAKE_FORCE, - TPS("WakeOvfIsDeferred")); + rdp->qlen_last_fqs_check = len; + j = jiffies; + if (j != rdp->nocb_gp_adv_time && + rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq) && + rcu_seq_done(&rdp->mynode->gp_seq, cur_gp_seq)) { + rcu_advance_cbs_nowake(rdp->mynode, rdp); + rdp->nocb_gp_adv_time = j; } - rdp->qlen_last_fqs_check = LONG_MAX / 2; + smp_mb(); /* Enqueue before timer_pending(). */ + if ((rdp->nocb_cb_sleep || + !rcu_segcblist_ready_cbs(&rdp->cblist)) && + !timer_pending(&rdp->nocb_bypass_timer)) + wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE_FORCE, + TPS("WakeOvfIsDeferred")); + rcu_nocb_unlock_irqrestore(rdp, flags); } else { trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNot")); + rcu_nocb_unlock_irqrestore(rdp, flags); } return; } -/* - * This is a helper for __call_rcu(), which invokes this when the normal - * callback queue is inoperable. If this is not a no-CBs CPU, this - * function returns failure back to __call_rcu(), which can complain - * appropriately. - * - * Otherwise, this function queues the callback where the corresponding - * "rcuo" kthread can find it. - */ -static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, - bool lazy, unsigned long flags) +/* Wake up the no-CBs GP kthread to flush ->nocb_bypass. */ +static void do_nocb_bypass_wakeup_timer(struct timer_list *t) { + unsigned long flags; + struct rcu_data *rdp = from_timer(rdp, t, nocb_bypass_timer); - if (!rcu_is_nocb_cpu(rdp->cpu)) - return false; - __call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy, flags); - if (__is_kfree_rcu_offset((unsigned long)rhp->func)) - trace_rcu_kfree_callback(rcu_state.name, rhp, - (unsigned long)rhp->func, - -atomic_long_read(&rdp->nocb_q_count_lazy), - -rcu_get_n_cbs_nocb_cpu(rdp)); - else - trace_rcu_callback(rcu_state.name, rhp, - -atomic_long_read(&rdp->nocb_q_count_lazy), - -rcu_get_n_cbs_nocb_cpu(rdp)); - - /* - * If called from an extended quiescent state with interrupts - * disabled, invoke the RCU core in order to allow the idle-entry - * deferred-wakeup check to function. - */ - if (irqs_disabled_flags(flags) && - !rcu_is_watching() && - cpu_online(smp_processor_id())) - invoke_rcu_core(); - - return true; -} - -/* - * Adopt orphaned callbacks on a no-CBs CPU, or return 0 if this is - * not a no-CBs CPU. - */ -static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_data *my_rdp, - struct rcu_data *rdp, - unsigned long flags) -{ - lockdep_assert_irqs_disabled(); - if (!rcu_is_nocb_cpu(smp_processor_id())) - return false; /* Not NOCBs CPU, caller must migrate CBs. */ - __call_rcu_nocb_enqueue(my_rdp, rcu_segcblist_head(&rdp->cblist), - rcu_segcblist_tail(&rdp->cblist), - rcu_segcblist_n_cbs(&rdp->cblist), - rcu_segcblist_n_lazy_cbs(&rdp->cblist), flags); - rcu_segcblist_init(&rdp->cblist); - rcu_segcblist_disable(&rdp->cblist); - return true; + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("Timer")); + rcu_nocb_lock_irqsave(rdp, flags); + smp_mb__after_spinlock(); /* Timer expire before wakeup. */ + __call_rcu_nocb_wake(rdp, true, flags); } /* - * If necessary, kick off a new grace period, and either way wait - * for a subsequent grace period to complete. + * No-CBs GP kthreads come here to wait for additional callbacks to show up + * or for grace periods to end. */ -static void rcu_nocb_wait_gp(struct rcu_data *rdp) +static void nocb_gp_wait(struct rcu_data *my_rdp) { - unsigned long c; - bool d; + bool bypass = false; + long bypass_ncbs; + int __maybe_unused cpu = my_rdp->cpu; + unsigned long cur_gp_seq; unsigned long flags; + bool gotcbs; + unsigned long j = jiffies; + bool needwait_gp = false; // This prevents actual uninitialized use. bool needwake; - struct rcu_node *rnp = rdp->mynode; + bool needwake_gp; + struct rcu_data *rdp; + struct rcu_node *rnp; + unsigned long wait_gp_seq = 0; // Suppress "use uninitialized" warning. - local_irq_save(flags); - c = rcu_seq_snap(&rcu_state.gp_seq); - if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) { - local_irq_restore(flags); - } else { - raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ - needwake = rcu_start_this_gp(rnp, rdp, c); - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - if (needwake) + /* + * Each pass through the following loop checks for CBs and for the + * nearest grace period (if any) to wait for next. The CB kthreads + * and the global grace-period kthread are awakened if needed. + */ + for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_cb_rdp) { + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("Check")); + rcu_nocb_lock_irqsave(rdp, flags); + bypass_ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass); + if (bypass_ncbs && + (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + 1) || + bypass_ncbs > 2 * qhimark)) { + // Bypass full or old, so flush it. + (void)rcu_nocb_try_flush_bypass(rdp, j); + bypass_ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass); + } else if (!bypass_ncbs && rcu_segcblist_empty(&rdp->cblist)) { + rcu_nocb_unlock_irqrestore(rdp, flags); + continue; /* No callbacks here, try next. */ + } + if (bypass_ncbs) { + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, + TPS("Bypass")); + bypass = true; + } + rnp = rdp->mynode; + if (bypass) { // Avoid race with first bypass CB. + WRITE_ONCE(my_rdp->nocb_defer_wakeup, + RCU_NOCB_WAKE_NOT); + del_timer(&my_rdp->nocb_timer); + } + // Advance callbacks if helpful and low contention. + needwake_gp = false; + if (!rcu_segcblist_restempty(&rdp->cblist, + RCU_NEXT_READY_TAIL) || + (rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq) && + rcu_seq_done(&rnp->gp_seq, cur_gp_seq))) { + raw_spin_lock_rcu_node(rnp); /* irqs disabled. */ + needwake_gp = rcu_advance_cbs(rnp, rdp); + raw_spin_unlock_rcu_node(rnp); /* irqs disabled. */ + } + // Need to wait on some grace period? + WARN_ON_ONCE(!rcu_segcblist_restempty(&rdp->cblist, + RCU_NEXT_READY_TAIL)); + if (rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq)) { + if (!needwait_gp || + ULONG_CMP_LT(cur_gp_seq, wait_gp_seq)) + wait_gp_seq = cur_gp_seq; + needwait_gp = true; + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, + TPS("NeedWaitGP")); + } + if (rcu_segcblist_ready_cbs(&rdp->cblist)) { + needwake = rdp->nocb_cb_sleep; + WRITE_ONCE(rdp->nocb_cb_sleep, false); + smp_mb(); /* CB invocation -after- GP end. */ + } else { + needwake = false; + } + rcu_nocb_unlock_irqrestore(rdp, flags); + if (needwake) { + swake_up_one(&rdp->nocb_cb_wq); + gotcbs = true; + } + if (needwake_gp) rcu_gp_kthread_wake(); } - /* - * Wait for the grace period. Do so interruptibly to avoid messing - * up the load average. - */ - trace_rcu_this_gp(rnp, rdp, c, TPS("StartWait")); - for (;;) { + my_rdp->nocb_gp_bypass = bypass; + my_rdp->nocb_gp_gp = needwait_gp; + my_rdp->nocb_gp_seq = needwait_gp ? wait_gp_seq : 0; + if (bypass && !rcu_nocb_poll) { + // At least one child with non-empty ->nocb_bypass, so set + // timer in order to avoid stranding its callbacks. + raw_spin_lock_irqsave(&my_rdp->nocb_gp_lock, flags); + mod_timer(&my_rdp->nocb_bypass_timer, j + 2); + raw_spin_unlock_irqrestore(&my_rdp->nocb_gp_lock, flags); + } + if (rcu_nocb_poll) { + /* Polling, so trace if first poll in the series. */ + if (gotcbs) + trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Poll")); + schedule_timeout_interruptible(1); + } else if (!needwait_gp) { + /* Wait for callbacks to appear. */ + trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Sleep")); + swait_event_interruptible_exclusive(my_rdp->nocb_gp_wq, + !READ_ONCE(my_rdp->nocb_gp_sleep)); + trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("EndSleep")); + } else { + rnp = my_rdp->mynode; + trace_rcu_this_gp(rnp, my_rdp, wait_gp_seq, TPS("StartWait")); swait_event_interruptible_exclusive( - rnp->nocb_gp_wq[rcu_seq_ctr(c) & 0x1], - (d = rcu_seq_done(&rnp->gp_seq, c))); - if (likely(d)) - break; - WARN_ON(signal_pending(current)); - trace_rcu_this_gp(rnp, rdp, c, TPS("ResumeWait")); + rnp->nocb_gp_wq[rcu_seq_ctr(wait_gp_seq) & 0x1], + rcu_seq_done(&rnp->gp_seq, wait_gp_seq) || + !READ_ONCE(my_rdp->nocb_gp_sleep)); + trace_rcu_this_gp(rnp, my_rdp, wait_gp_seq, TPS("EndWait")); } - trace_rcu_this_gp(rnp, rdp, c, TPS("EndWait")); - smp_mb(); /* Ensure that CB invocation happens after GP end. */ + if (!rcu_nocb_poll) { + raw_spin_lock_irqsave(&my_rdp->nocb_gp_lock, flags); + if (bypass) + del_timer(&my_rdp->nocb_bypass_timer); + WRITE_ONCE(my_rdp->nocb_gp_sleep, true); + raw_spin_unlock_irqrestore(&my_rdp->nocb_gp_lock, flags); + } + my_rdp->nocb_gp_seq = -1; + WARN_ON(signal_pending(current)); } /* - * Leaders come here to wait for additional callbacks to show up. - * This function does not return until callbacks appear. + * No-CBs grace-period-wait kthread. There is one of these per group + * of CPUs, but only once at least one CPU in that group has come online + * at least once since boot. This kthread checks for newly posted + * callbacks from any of the CPUs it is responsible for, waits for a + * grace period, then awakens all of the rcu_nocb_cb_kthread() instances + * that then have callback-invocation work to do. */ -static void nocb_leader_wait(struct rcu_data *my_rdp) +static int rcu_nocb_gp_kthread(void *arg) { - bool firsttime = true; - unsigned long flags; - bool gotcbs; - struct rcu_data *rdp; - struct rcu_head **tail; - -wait_again: - - /* Wait for callbacks to appear. */ - if (!rcu_nocb_poll) { - trace_rcu_nocb_wake(rcu_state.name, my_rdp->cpu, TPS("Sleep")); - swait_event_interruptible_exclusive(my_rdp->nocb_wq, - !READ_ONCE(my_rdp->nocb_leader_sleep)); - raw_spin_lock_irqsave(&my_rdp->nocb_lock, flags); - my_rdp->nocb_leader_sleep = true; - WRITE_ONCE(my_rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT); - del_timer(&my_rdp->nocb_timer); - raw_spin_unlock_irqrestore(&my_rdp->nocb_lock, flags); - } else if (firsttime) { - firsttime = false; /* Don't drown trace log with "Poll"! */ - trace_rcu_nocb_wake(rcu_state.name, my_rdp->cpu, TPS("Poll")); - } - - /* - * Each pass through the following loop checks a follower for CBs. - * We are our own first follower. Any CBs found are moved to - * nocb_gp_head, where they await a grace period. - */ - gotcbs = false; - smp_mb(); /* wakeup and _sleep before ->nocb_head reads. */ - for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) { - rdp->nocb_gp_head = READ_ONCE(rdp->nocb_head); - if (!rdp->nocb_gp_head) - continue; /* No CBs here, try next follower. */ - - /* Move callbacks to wait-for-GP list, which is empty. */ - WRITE_ONCE(rdp->nocb_head, NULL); - rdp->nocb_gp_tail = xchg(&rdp->nocb_tail, &rdp->nocb_head); - gotcbs = true; - } - - /* No callbacks? Sleep a bit if polling, and go retry. */ - if (unlikely(!gotcbs)) { - WARN_ON(signal_pending(current)); - if (rcu_nocb_poll) { - schedule_timeout_interruptible(1); - } else { - trace_rcu_nocb_wake(rcu_state.name, my_rdp->cpu, - TPS("WokeEmpty")); - } - goto wait_again; - } + struct rcu_data *rdp = arg; - /* Wait for one grace period. */ - rcu_nocb_wait_gp(my_rdp); - - /* Each pass through the following loop wakes a follower, if needed. */ - for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) { - if (!rcu_nocb_poll && - READ_ONCE(rdp->nocb_head) && - READ_ONCE(my_rdp->nocb_leader_sleep)) { - raw_spin_lock_irqsave(&my_rdp->nocb_lock, flags); - my_rdp->nocb_leader_sleep = false;/* No need to sleep.*/ - raw_spin_unlock_irqrestore(&my_rdp->nocb_lock, flags); - } - if (!rdp->nocb_gp_head) - continue; /* No CBs, so no need to wake follower. */ - - /* Append callbacks to follower's "done" list. */ - raw_spin_lock_irqsave(&rdp->nocb_lock, flags); - tail = rdp->nocb_follower_tail; - rdp->nocb_follower_tail = rdp->nocb_gp_tail; - *tail = rdp->nocb_gp_head; - raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); - if (rdp != my_rdp && tail == &rdp->nocb_follower_head) { - /* List was empty, so wake up the follower. */ - swake_up_one(&rdp->nocb_wq); - } + for (;;) { + WRITE_ONCE(rdp->nocb_gp_loops, rdp->nocb_gp_loops + 1); + nocb_gp_wait(rdp); + cond_resched_tasks_rcu_qs(); } - - /* If we (the leader) don't have CBs, go wait some more. */ - if (!my_rdp->nocb_follower_head) - goto wait_again; + return 0; } /* - * Followers come here to wait for additional callbacks to show up. - * This function does not return until callbacks appear. + * Invoke any ready callbacks from the corresponding no-CBs CPU, + * then, if there are no more, wait for more to appear. */ -static void nocb_follower_wait(struct rcu_data *rdp) +static void nocb_cb_wait(struct rcu_data *rdp) { - for (;;) { - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("FollowerSleep")); - swait_event_interruptible_exclusive(rdp->nocb_wq, - READ_ONCE(rdp->nocb_follower_head)); - if (smp_load_acquire(&rdp->nocb_follower_head)) { - /* ^^^ Ensure CB invocation follows _head test. */ - return; - } - WARN_ON(signal_pending(current)); - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeEmpty")); + unsigned long cur_gp_seq; + unsigned long flags; + bool needwake_gp = false; + struct rcu_node *rnp = rdp->mynode; + + local_irq_save(flags); + rcu_momentary_dyntick_idle(); + local_irq_restore(flags); + local_bh_disable(); + rcu_do_batch(rdp); + local_bh_enable(); + lockdep_assert_irqs_enabled(); + rcu_nocb_lock_irqsave(rdp, flags); + if (rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq) && + rcu_seq_done(&rnp->gp_seq, cur_gp_seq) && + raw_spin_trylock_rcu_node(rnp)) { /* irqs already disabled. */ + needwake_gp = rcu_advance_cbs(rdp->mynode, rdp); + raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ + } + if (rcu_segcblist_ready_cbs(&rdp->cblist)) { + rcu_nocb_unlock_irqrestore(rdp, flags); + if (needwake_gp) + rcu_gp_kthread_wake(); + return; + } + + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("CBSleep")); + WRITE_ONCE(rdp->nocb_cb_sleep, true); + rcu_nocb_unlock_irqrestore(rdp, flags); + if (needwake_gp) + rcu_gp_kthread_wake(); + swait_event_interruptible_exclusive(rdp->nocb_cb_wq, + !READ_ONCE(rdp->nocb_cb_sleep)); + if (!smp_load_acquire(&rdp->nocb_cb_sleep)) { /* VVV */ + /* ^^^ Ensure CB invocation follows _sleep test. */ + return; } + WARN_ON(signal_pending(current)); + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeEmpty")); } /* - * Per-rcu_data kthread, but only for no-CBs CPUs. Each kthread invokes - * callbacks queued by the corresponding no-CBs CPU, however, there is - * an optional leader-follower relationship so that the grace-period - * kthreads don't have to do quite so many wakeups. + * Per-rcu_data kthread, but only for no-CBs CPUs. Repeatedly invoke + * nocb_cb_wait() to do the dirty work. */ -static int rcu_nocb_kthread(void *arg) +static int rcu_nocb_cb_kthread(void *arg) { - int c, cl; - unsigned long flags; - struct rcu_head *list; - struct rcu_head *next; - struct rcu_head **tail; struct rcu_data *rdp = arg; - /* Each pass through this loop invokes one batch of callbacks */ + // Each pass through this loop does one callback batch, and, + // if there are no more ready callbacks, waits for them. for (;;) { - /* Wait for callbacks. */ - if (rdp->nocb_leader == rdp) - nocb_leader_wait(rdp); - else - nocb_follower_wait(rdp); - - /* Pull the ready-to-invoke callbacks onto local list. */ - raw_spin_lock_irqsave(&rdp->nocb_lock, flags); - list = rdp->nocb_follower_head; - rdp->nocb_follower_head = NULL; - tail = rdp->nocb_follower_tail; - rdp->nocb_follower_tail = &rdp->nocb_follower_head; - raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); - if (WARN_ON_ONCE(!list)) - continue; - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeNonEmpty")); - - /* Each pass through the following loop invokes a callback. */ - trace_rcu_batch_start(rcu_state.name, - atomic_long_read(&rdp->nocb_q_count_lazy), - rcu_get_n_cbs_nocb_cpu(rdp), -1); - c = cl = 0; - while (list) { - next = list->next; - /* Wait for enqueuing to complete, if needed. */ - while (next == NULL && &list->next != tail) { - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, - TPS("WaitQueue")); - schedule_timeout_interruptible(1); - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, - TPS("WokeQueue")); - next = list->next; - } - debug_rcu_head_unqueue(list); - local_bh_disable(); - if (__rcu_reclaim(rcu_state.name, list)) - cl++; - c++; - local_bh_enable(); - cond_resched_tasks_rcu_qs(); - list = next; - } - trace_rcu_batch_end(rcu_state.name, c, !!list, 0, 0, 1); - smp_mb__before_atomic(); /* _add after CB invocation. */ - atomic_long_add(-c, &rdp->nocb_q_count); - atomic_long_add(-cl, &rdp->nocb_q_count_lazy); + nocb_cb_wait(rdp); + cond_resched_tasks_rcu_qs(); } return 0; } @@ -1993,14 +2159,14 @@ static void do_nocb_deferred_wakeup_common(struct rcu_data *rdp) unsigned long flags; int ndw; - raw_spin_lock_irqsave(&rdp->nocb_lock, flags); + rcu_nocb_lock_irqsave(rdp, flags); if (!rcu_nocb_need_deferred_wakeup(rdp)) { - raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); + rcu_nocb_unlock_irqrestore(rdp, flags); return; } ndw = READ_ONCE(rdp->nocb_defer_wakeup); WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT); - __wake_nocb_leader(rdp, ndw == RCU_NOCB_WAKE_FORCE, flags); + wake_nocb_gp(rdp, ndw == RCU_NOCB_WAKE_FORCE, flags); trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("DeferredWake")); } @@ -2027,6 +2193,7 @@ void __init rcu_init_nohz(void) { int cpu; bool need_rcu_nocb_mask = false; + struct rcu_data *rdp; #if defined(CONFIG_NO_HZ_FULL) if (tick_nohz_full_running && cpumask_weight(tick_nohz_full_mask)) @@ -2060,67 +2227,63 @@ void __init rcu_init_nohz(void) if (rcu_nocb_poll) pr_info("\tPoll for callbacks from no-CBs CPUs.\n"); - for_each_cpu(cpu, rcu_nocb_mask) - init_nocb_callback_list(per_cpu_ptr(&rcu_data, cpu)); + for_each_cpu(cpu, rcu_nocb_mask) { + rdp = per_cpu_ptr(&rcu_data, cpu); + if (rcu_segcblist_empty(&rdp->cblist)) + rcu_segcblist_init(&rdp->cblist); + rcu_segcblist_offload(&rdp->cblist); + } rcu_organize_nocb_kthreads(); } /* Initialize per-rcu_data variables for no-CBs CPUs. */ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) { - rdp->nocb_tail = &rdp->nocb_head; - init_swait_queue_head(&rdp->nocb_wq); - rdp->nocb_follower_tail = &rdp->nocb_follower_head; + init_swait_queue_head(&rdp->nocb_cb_wq); + init_swait_queue_head(&rdp->nocb_gp_wq); raw_spin_lock_init(&rdp->nocb_lock); + raw_spin_lock_init(&rdp->nocb_bypass_lock); + raw_spin_lock_init(&rdp->nocb_gp_lock); timer_setup(&rdp->nocb_timer, do_nocb_deferred_wakeup_timer, 0); + timer_setup(&rdp->nocb_bypass_timer, do_nocb_bypass_wakeup_timer, 0); + rcu_cblist_init(&rdp->nocb_bypass); } /* * If the specified CPU is a no-CBs CPU that does not already have its - * rcuo kthread, spawn it. If the CPUs are brought online out of order, - * this can require re-organizing the leader-follower relationships. + * rcuo CB kthread, spawn it. Additionally, if the rcuo GP kthread + * for this CPU's group has not yet been created, spawn it as well. */ static void rcu_spawn_one_nocb_kthread(int cpu) { - struct rcu_data *rdp; - struct rcu_data *rdp_last; - struct rcu_data *rdp_old_leader; - struct rcu_data *rdp_spawn = per_cpu_ptr(&rcu_data, cpu); + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + struct rcu_data *rdp_gp; struct task_struct *t; /* * If this isn't a no-CBs CPU or if it already has an rcuo kthread, * then nothing to do. */ - if (!rcu_is_nocb_cpu(cpu) || rdp_spawn->nocb_kthread) + if (!rcu_is_nocb_cpu(cpu) || rdp->nocb_cb_kthread) return; - /* If we didn't spawn the leader first, reorganize! */ - rdp_old_leader = rdp_spawn->nocb_leader; - if (rdp_old_leader != rdp_spawn && !rdp_old_leader->nocb_kthread) { - rdp_last = NULL; - rdp = rdp_old_leader; - do { - rdp->nocb_leader = rdp_spawn; - if (rdp_last && rdp != rdp_spawn) - rdp_last->nocb_next_follower = rdp; - if (rdp == rdp_spawn) { - rdp = rdp->nocb_next_follower; - } else { - rdp_last = rdp; - rdp = rdp->nocb_next_follower; - rdp_last->nocb_next_follower = NULL; - } - } while (rdp); - rdp_spawn->nocb_next_follower = rdp_old_leader; + /* If we didn't spawn the GP kthread first, reorganize! */ + rdp_gp = rdp->nocb_gp_rdp; + if (!rdp_gp->nocb_gp_kthread) { + t = kthread_run(rcu_nocb_gp_kthread, rdp_gp, + "rcuog/%d", rdp_gp->cpu); + if (WARN_ONCE(IS_ERR(t), "%s: Could not start rcuo GP kthread, OOM is now expected behavior\n", __func__)) + return; + WRITE_ONCE(rdp_gp->nocb_gp_kthread, t); } /* Spawn the kthread for this CPU. */ - t = kthread_run(rcu_nocb_kthread, rdp_spawn, + t = kthread_run(rcu_nocb_cb_kthread, rdp, "rcuo%c/%d", rcu_state.abbr, cpu); - if (WARN_ONCE(IS_ERR(t), "%s: Could not start rcuo kthread, OOM is now expected behavior\n", __func__)) + if (WARN_ONCE(IS_ERR(t), "%s: Could not start rcuo CB kthread, OOM is now expected behavior\n", __func__)) return; - WRITE_ONCE(rdp_spawn->nocb_kthread, t); + WRITE_ONCE(rdp->nocb_cb_kthread, t); + WRITE_ONCE(rdp->nocb_gp_kthread, rdp_gp->nocb_gp_kthread); } /* @@ -2147,27 +2310,28 @@ static void __init rcu_spawn_nocb_kthreads(void) rcu_spawn_cpu_nocb_kthread(cpu); } -/* How many follower CPU IDs per leader? Default of -1 for sqrt(nr_cpu_ids). */ -static int rcu_nocb_leader_stride = -1; -module_param(rcu_nocb_leader_stride, int, 0444); +/* How many CB CPU IDs per GP kthread? Default of -1 for sqrt(nr_cpu_ids). */ +static int rcu_nocb_gp_stride = -1; +module_param(rcu_nocb_gp_stride, int, 0444); /* - * Initialize leader-follower relationships for all no-CBs CPU. + * Initialize GP-CB relationships for all no-CBs CPU. */ static void __init rcu_organize_nocb_kthreads(void) { int cpu; - int ls = rcu_nocb_leader_stride; - int nl = 0; /* Next leader. */ + bool firsttime = true; + int ls = rcu_nocb_gp_stride; + int nl = 0; /* Next GP kthread. */ struct rcu_data *rdp; - struct rcu_data *rdp_leader = NULL; /* Suppress misguided gcc warn. */ + struct rcu_data *rdp_gp = NULL; /* Suppress misguided gcc warn. */ struct rcu_data *rdp_prev = NULL; if (!cpumask_available(rcu_nocb_mask)) return; if (ls == -1) { - ls = int_sqrt(nr_cpu_ids); - rcu_nocb_leader_stride = ls; + ls = nr_cpu_ids / int_sqrt(nr_cpu_ids); + rcu_nocb_gp_stride = ls; } /* @@ -2178,39 +2342,24 @@ static void __init rcu_organize_nocb_kthreads(void) for_each_cpu(cpu, rcu_nocb_mask) { rdp = per_cpu_ptr(&rcu_data, cpu); if (rdp->cpu >= nl) { - /* New leader, set up for followers & next leader. */ + /* New GP kthread, set up for CBs & next GP. */ nl = DIV_ROUND_UP(rdp->cpu + 1, ls) * ls; - rdp->nocb_leader = rdp; - rdp_leader = rdp; + rdp->nocb_gp_rdp = rdp; + rdp_gp = rdp; + if (!firsttime && dump_tree) + pr_cont("\n"); + firsttime = false; + pr_alert("%s: No-CB GP kthread CPU %d:", __func__, cpu); } else { - /* Another follower, link to previous leader. */ - rdp->nocb_leader = rdp_leader; - rdp_prev->nocb_next_follower = rdp; + /* Another CB kthread, link to previous GP kthread. */ + rdp->nocb_gp_rdp = rdp_gp; + rdp_prev->nocb_next_cb_rdp = rdp; + pr_alert(" %d", cpu); } rdp_prev = rdp; } } -/* Prevent __call_rcu() from enqueuing callbacks on no-CBs CPUs */ -static bool init_nocb_callback_list(struct rcu_data *rdp) -{ - if (!rcu_is_nocb_cpu(rdp->cpu)) - return false; - - /* If there are early-boot callbacks, move them to nocb lists. */ - if (!rcu_segcblist_empty(&rdp->cblist)) { - rdp->nocb_head = rcu_segcblist_head(&rdp->cblist); - rdp->nocb_tail = rcu_segcblist_tail(&rdp->cblist); - atomic_long_set(&rdp->nocb_q_count, - rcu_segcblist_n_cbs(&rdp->cblist)); - atomic_long_set(&rdp->nocb_q_count_lazy, - rcu_segcblist_n_lazy_cbs(&rdp->cblist)); - rcu_segcblist_init(&rdp->cblist); - } - rcu_segcblist_disable(&rdp->cblist); - return true; -} - /* * Bind the current task to the offloaded CPUs. If there are no offloaded * CPUs, leave the task unbound. Splat if the bind attempt fails. @@ -2223,20 +2372,101 @@ void rcu_bind_current_to_nocb(void) EXPORT_SYMBOL_GPL(rcu_bind_current_to_nocb); /* - * Return the number of RCU callbacks still queued from the specified - * CPU, which must be a nocbs CPU. + * Dump out nocb grace-period kthread state for the specified rcu_data + * structure. */ -static unsigned long rcu_get_n_cbs_nocb_cpu(struct rcu_data *rdp) +static void show_rcu_nocb_gp_state(struct rcu_data *rdp) { - return atomic_long_read(&rdp->nocb_q_count); + struct rcu_node *rnp = rdp->mynode; + + pr_info("nocb GP %d %c%c%c%c%c%c %c[%c%c] %c%c:%ld rnp %d:%d %lu\n", + rdp->cpu, + "kK"[!!rdp->nocb_gp_kthread], + "lL"[raw_spin_is_locked(&rdp->nocb_gp_lock)], + "dD"[!!rdp->nocb_defer_wakeup], + "tT"[timer_pending(&rdp->nocb_timer)], + "bB"[timer_pending(&rdp->nocb_bypass_timer)], + "sS"[!!rdp->nocb_gp_sleep], + ".W"[swait_active(&rdp->nocb_gp_wq)], + ".W"[swait_active(&rnp->nocb_gp_wq[0])], + ".W"[swait_active(&rnp->nocb_gp_wq[1])], + ".B"[!!rdp->nocb_gp_bypass], + ".G"[!!rdp->nocb_gp_gp], + (long)rdp->nocb_gp_seq, + rnp->grplo, rnp->grphi, READ_ONCE(rdp->nocb_gp_loops)); +} + +/* Dump out nocb kthread state for the specified rcu_data structure. */ +static void show_rcu_nocb_state(struct rcu_data *rdp) +{ + struct rcu_segcblist *rsclp = &rdp->cblist; + bool waslocked; + bool wastimer; + bool wassleep; + + if (rdp->nocb_gp_rdp == rdp) + show_rcu_nocb_gp_state(rdp); + + pr_info(" CB %d->%d %c%c%c%c%c%c F%ld L%ld C%d %c%c%c%c%c q%ld\n", + rdp->cpu, rdp->nocb_gp_rdp->cpu, + "kK"[!!rdp->nocb_cb_kthread], + "bB"[raw_spin_is_locked(&rdp->nocb_bypass_lock)], + "cC"[!!atomic_read(&rdp->nocb_lock_contended)], + "lL"[raw_spin_is_locked(&rdp->nocb_lock)], + "sS"[!!rdp->nocb_cb_sleep], + ".W"[swait_active(&rdp->nocb_cb_wq)], + jiffies - rdp->nocb_bypass_first, + jiffies - rdp->nocb_nobypass_last, + rdp->nocb_nobypass_count, + ".D"[rcu_segcblist_ready_cbs(rsclp)], + ".W"[!rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL)], + ".R"[!rcu_segcblist_restempty(rsclp, RCU_WAIT_TAIL)], + ".N"[!rcu_segcblist_restempty(rsclp, RCU_NEXT_READY_TAIL)], + ".B"[!!rcu_cblist_n_cbs(&rdp->nocb_bypass)], + rcu_segcblist_n_cbs(&rdp->cblist)); + + /* It is OK for GP kthreads to have GP state. */ + if (rdp->nocb_gp_rdp == rdp) + return; + + waslocked = raw_spin_is_locked(&rdp->nocb_gp_lock); + wastimer = timer_pending(&rdp->nocb_timer); + wassleep = swait_active(&rdp->nocb_gp_wq); + if (!rdp->nocb_defer_wakeup && !rdp->nocb_gp_sleep && + !waslocked && !wastimer && !wassleep) + return; /* Nothing untowards. */ + + pr_info(" !!! %c%c%c%c %c\n", + "lL"[waslocked], + "dD"[!!rdp->nocb_defer_wakeup], + "tT"[wastimer], + "sS"[!!rdp->nocb_gp_sleep], + ".W"[wassleep]); } #else /* #ifdef CONFIG_RCU_NOCB_CPU */ -static bool rcu_nocb_cpu_needs_barrier(int cpu) +/* No ->nocb_lock to acquire. */ +static void rcu_nocb_lock(struct rcu_data *rdp) +{ +} + +/* No ->nocb_lock to release. */ +static void rcu_nocb_unlock(struct rcu_data *rdp) { - WARN_ON_ONCE(1); /* Should be dead code. */ - return false; +} + +/* No ->nocb_lock to release. */ +static void rcu_nocb_unlock_irqrestore(struct rcu_data *rdp, + unsigned long flags) +{ + local_irq_restore(flags); +} + +/* Lockdep check that ->cblist may be safely accessed. */ +static void rcu_lockdep_assert_cblist_protected(struct rcu_data *rdp) +{ + lockdep_assert_irqs_disabled(); } static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) @@ -2252,19 +2482,24 @@ static void rcu_init_one_nocb(struct rcu_node *rnp) { } -static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, - bool lazy, unsigned long flags) +static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp, + unsigned long j) { - return false; + return true; } -static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_data *my_rdp, - struct rcu_data *rdp, - unsigned long flags) +static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp, + bool *was_alldone, unsigned long flags) { return false; } +static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty, + unsigned long flags) +{ + WARN_ON_ONCE(1); /* Should be dead code! */ +} + static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) { } @@ -2286,14 +2521,8 @@ static void __init rcu_spawn_nocb_kthreads(void) { } -static bool init_nocb_callback_list(struct rcu_data *rdp) -{ - return false; -} - -static unsigned long rcu_get_n_cbs_nocb_cpu(struct rcu_data *rdp) +static void show_rcu_nocb_state(struct rcu_data *rdp) { - return 0; } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 065183391f75..c0b8c458d8a6 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -163,7 +163,7 @@ static void rcu_iw_handler(struct irq_work *iwp) // // Printing RCU CPU stall warnings -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION /* * Dump detailed information for all tasks blocking the current RCU @@ -215,7 +215,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp) return ndetected; } -#else /* #ifdef CONFIG_PREEMPT */ +#else /* #ifdef CONFIG_PREEMPTION */ /* * Because preemptible RCU does not exist, we never have to check for @@ -233,7 +233,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp) { return 0; } -#endif /* #else #ifdef CONFIG_PREEMPT */ +#endif /* #else #ifdef CONFIG_PREEMPTION */ /* * Dump stacks of all tasks running on stalled CPUs. First try using @@ -527,6 +527,8 @@ static void check_cpu_stall(struct rcu_data *rdp) /* We haven't checked in, so go dump stack. */ print_cpu_stall(); + if (rcu_cpu_stall_ftrace_dump) + rcu_ftrace_dump(DUMP_ALL); } else if (rcu_gp_in_progress() && ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) && @@ -534,6 +536,8 @@ static void check_cpu_stall(struct rcu_data *rdp) /* They had a few time units to dump stack, so complain. */ print_other_cpu_stall(gs2); + if (rcu_cpu_stall_ftrace_dump) + rcu_ftrace_dump(DUMP_ALL); } } @@ -585,6 +589,11 @@ void show_rcu_gp_kthreads(void) cpu, (long)rdp->gp_seq_needed); } } + for_each_possible_cpu(cpu) { + rdp = per_cpu_ptr(&rcu_data, cpu); + if (rcu_segcblist_is_offloaded(&rdp->cblist)) + show_rcu_nocb_state(rdp); + } /* sched_show_task(rcu_state.gp_kthread); */ } EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 61df2bf08563..1861103662db 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -61,9 +61,15 @@ module_param(rcu_normal_after_boot, int, 0); #ifdef CONFIG_DEBUG_LOCK_ALLOC /** - * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section? + * rcu_read_lock_held_common() - might we be in RCU-sched read-side critical section? + * @ret: Best guess answer if lockdep cannot be relied on * - * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an + * Returns true if lockdep must be ignored, in which case *ret contains + * the best guess described below. Otherwise returns false, in which + * case *ret tells the caller nothing and the caller should instead + * consult lockdep. + * + * If CONFIG_DEBUG_LOCK_ALLOC is selected, set *ret to nonzero iff in an * RCU-sched read-side critical section. In absence of * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side * critical section unless it can prove otherwise. Note that disabling @@ -75,35 +81,45 @@ module_param(rcu_normal_after_boot, int, 0); * Check debug_lockdep_rcu_enabled() to prevent false positives during boot * and while lockdep is disabled. * - * Note that if the CPU is in the idle loop from an RCU point of - * view (ie: that we are in the section between rcu_idle_enter() and - * rcu_idle_exit()) then rcu_read_lock_held() returns false even if the CPU - * did an rcu_read_lock(). The reason for this is that RCU ignores CPUs - * that are in such a section, considering these as in extended quiescent - * state, so such a CPU is effectively never in an RCU read-side critical - * section regardless of what RCU primitives it invokes. This state of - * affairs is required --- we need to keep an RCU-free window in idle - * where the CPU may possibly enter into low power mode. This way we can - * notice an extended quiescent state to other CPUs that started a grace - * period. Otherwise we would delay any grace period as long as we run in - * the idle task. + * Note that if the CPU is in the idle loop from an RCU point of view (ie: + * that we are in the section between rcu_idle_enter() and rcu_idle_exit()) + * then rcu_read_lock_held() sets *ret to false even if the CPU did an + * rcu_read_lock(). The reason for this is that RCU ignores CPUs that are + * in such a section, considering these as in extended quiescent state, + * so such a CPU is effectively never in an RCU read-side critical section + * regardless of what RCU primitives it invokes. This state of affairs is + * required --- we need to keep an RCU-free window in idle where the CPU may + * possibly enter into low power mode. This way we can notice an extended + * quiescent state to other CPUs that started a grace period. Otherwise + * we would delay any grace period as long as we run in the idle task. * - * Similarly, we avoid claiming an SRCU read lock held if the current + * Similarly, we avoid claiming an RCU read lock held if the current * CPU is offline. */ +static bool rcu_read_lock_held_common(bool *ret) +{ + if (!debug_lockdep_rcu_enabled()) { + *ret = 1; + return true; + } + if (!rcu_is_watching()) { + *ret = 0; + return true; + } + if (!rcu_lockdep_current_cpu_online()) { + *ret = 0; + return true; + } + return false; +} + int rcu_read_lock_sched_held(void) { - int lockdep_opinion = 0; + bool ret; - if (!debug_lockdep_rcu_enabled()) - return 1; - if (!rcu_is_watching()) - return 0; - if (!rcu_lockdep_current_cpu_online()) - return 0; - if (debug_locks) - lockdep_opinion = lock_is_held(&rcu_sched_lock_map); - return lockdep_opinion || !preemptible(); + if (rcu_read_lock_held_common(&ret)) + return ret; + return lock_is_held(&rcu_sched_lock_map) || !preemptible(); } EXPORT_SYMBOL(rcu_read_lock_sched_held); #endif @@ -136,8 +152,7 @@ static atomic_t rcu_expedited_nesting = ATOMIC_INIT(1); */ bool rcu_gp_is_expedited(void) { - return rcu_expedited || atomic_read(&rcu_expedited_nesting) || - rcu_scheduler_active == RCU_SCHEDULER_INIT; + return rcu_expedited || atomic_read(&rcu_expedited_nesting); } EXPORT_SYMBOL_GPL(rcu_gp_is_expedited); @@ -261,12 +276,10 @@ NOKPROBE_SYMBOL(debug_lockdep_rcu_enabled); */ int rcu_read_lock_held(void) { - if (!debug_lockdep_rcu_enabled()) - return 1; - if (!rcu_is_watching()) - return 0; - if (!rcu_lockdep_current_cpu_online()) - return 0; + bool ret; + + if (rcu_read_lock_held_common(&ret)) + return ret; return lock_is_held(&rcu_lock_map); } EXPORT_SYMBOL_GPL(rcu_read_lock_held); @@ -288,16 +301,28 @@ EXPORT_SYMBOL_GPL(rcu_read_lock_held); */ int rcu_read_lock_bh_held(void) { - if (!debug_lockdep_rcu_enabled()) - return 1; - if (!rcu_is_watching()) - return 0; - if (!rcu_lockdep_current_cpu_online()) - return 0; + bool ret; + + if (rcu_read_lock_held_common(&ret)) + return ret; return in_softirq() || irqs_disabled(); } EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); +int rcu_read_lock_any_held(void) +{ + bool ret; + + if (rcu_read_lock_held_common(&ret)) + return ret; + if (lock_is_held(&rcu_lock_map) || + lock_is_held(&rcu_bh_lock_map) || + lock_is_held(&rcu_sched_lock_map)) + return 1; + return !preemptible(); +} +EXPORT_SYMBOL_GPL(rcu_read_lock_any_held); + #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /** @@ -437,6 +462,8 @@ EXPORT_SYMBOL_GPL(rcutorture_sched_setaffinity); #endif #ifdef CONFIG_RCU_STALL_COMMON +int rcu_cpu_stall_ftrace_dump __read_mostly; +module_param(rcu_cpu_stall_ftrace_dump, int, 0644); int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */ EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress); module_param(rcu_cpu_stall_suppress, int, 0644); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 010d578118d6..5e8387bdd09c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -255,7 +255,7 @@ static void __hrtick_restart(struct rq *rq) { struct hrtimer *timer = &rq->hrtick_timer; - hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED); + hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED_HARD); } /* @@ -314,7 +314,7 @@ void hrtick_start(struct rq *rq, u64 delay) */ delay = max_t(u64, delay, 10000LL); hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), - HRTIMER_MODE_REL_PINNED); + HRTIMER_MODE_REL_PINNED_HARD); } #endif /* CONFIG_SMP */ @@ -328,7 +328,7 @@ static void hrtick_rq_init(struct rq *rq) rq->hrtick_csd.info = rq; #endif - hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); rq->hrtick_timer.function = hrtick; } #else /* CONFIG_SCHED_HRTICK */ @@ -773,6 +773,18 @@ static void set_load_weight(struct task_struct *p, bool update_load) } #ifdef CONFIG_UCLAMP_TASK +/* + * Serializes updates of utilization clamp values + * + * The (slow-path) user-space triggers utilization clamp value updates which + * can require updates on (fast-path) scheduler's data structures used to + * support enqueue/dequeue operations. + * While the per-CPU rq lock protects fast-path update operations, user-space + * requests are serialized using a mutex to reduce the risk of conflicting + * updates or API abuses. + */ +static DEFINE_MUTEX(uclamp_mutex); + /* Max allowed minimum utilization */ unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE; @@ -798,7 +810,7 @@ static inline unsigned int uclamp_bucket_base_value(unsigned int clamp_value) return UCLAMP_BUCKET_DELTA * uclamp_bucket_id(clamp_value); } -static inline unsigned int uclamp_none(int clamp_id) +static inline enum uclamp_id uclamp_none(enum uclamp_id clamp_id) { if (clamp_id == UCLAMP_MIN) return 0; @@ -814,7 +826,7 @@ static inline void uclamp_se_set(struct uclamp_se *uc_se, } static inline unsigned int -uclamp_idle_value(struct rq *rq, unsigned int clamp_id, +uclamp_idle_value(struct rq *rq, enum uclamp_id clamp_id, unsigned int clamp_value) { /* @@ -830,7 +842,7 @@ uclamp_idle_value(struct rq *rq, unsigned int clamp_id, return uclamp_none(UCLAMP_MIN); } -static inline void uclamp_idle_reset(struct rq *rq, unsigned int clamp_id, +static inline void uclamp_idle_reset(struct rq *rq, enum uclamp_id clamp_id, unsigned int clamp_value) { /* Reset max-clamp retention only on idle exit */ @@ -841,8 +853,8 @@ static inline void uclamp_idle_reset(struct rq *rq, unsigned int clamp_id, } static inline -unsigned int uclamp_rq_max_value(struct rq *rq, unsigned int clamp_id, - unsigned int clamp_value) +enum uclamp_id uclamp_rq_max_value(struct rq *rq, enum uclamp_id clamp_id, + unsigned int clamp_value) { struct uclamp_bucket *bucket = rq->uclamp[clamp_id].bucket; int bucket_id = UCLAMP_BUCKETS - 1; @@ -861,16 +873,42 @@ unsigned int uclamp_rq_max_value(struct rq *rq, unsigned int clamp_id, return uclamp_idle_value(rq, clamp_id, clamp_value); } +static inline struct uclamp_se +uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id) +{ + struct uclamp_se uc_req = p->uclamp_req[clamp_id]; +#ifdef CONFIG_UCLAMP_TASK_GROUP + struct uclamp_se uc_max; + + /* + * Tasks in autogroups or root task group will be + * restricted by system defaults. + */ + if (task_group_is_autogroup(task_group(p))) + return uc_req; + if (task_group(p) == &root_task_group) + return uc_req; + + uc_max = task_group(p)->uclamp[clamp_id]; + if (uc_req.value > uc_max.value || !uc_req.user_defined) + return uc_max; +#endif + + return uc_req; +} + /* * The effective clamp bucket index of a task depends on, by increasing * priority: * - the task specific clamp value, when explicitly requested from userspace + * - the task group effective clamp value, for tasks not either in the root + * group or in an autogroup * - the system default clamp value, defined by the sysadmin */ static inline struct uclamp_se -uclamp_eff_get(struct task_struct *p, unsigned int clamp_id) +uclamp_eff_get(struct task_struct *p, enum uclamp_id clamp_id) { - struct uclamp_se uc_req = p->uclamp_req[clamp_id]; + struct uclamp_se uc_req = uclamp_tg_restrict(p, clamp_id); struct uclamp_se uc_max = uclamp_default[clamp_id]; /* System default restrictions always apply */ @@ -880,7 +918,7 @@ uclamp_eff_get(struct task_struct *p, unsigned int clamp_id) return uc_req; } -unsigned int uclamp_eff_value(struct task_struct *p, unsigned int clamp_id) +enum uclamp_id uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id) { struct uclamp_se uc_eff; @@ -904,7 +942,7 @@ unsigned int uclamp_eff_value(struct task_struct *p, unsigned int clamp_id) * for each bucket when all its RUNNABLE tasks require the same clamp. */ static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p, - unsigned int clamp_id) + enum uclamp_id clamp_id) { struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id]; struct uclamp_se *uc_se = &p->uclamp[clamp_id]; @@ -942,7 +980,7 @@ static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p, * enforce the expected state and warn. */ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p, - unsigned int clamp_id) + enum uclamp_id clamp_id) { struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id]; struct uclamp_se *uc_se = &p->uclamp[clamp_id]; @@ -981,7 +1019,7 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p, static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) { - unsigned int clamp_id; + enum uclamp_id clamp_id; if (unlikely(!p->sched_class->uclamp_enabled)) return; @@ -996,7 +1034,7 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) { - unsigned int clamp_id; + enum uclamp_id clamp_id; if (unlikely(!p->sched_class->uclamp_enabled)) return; @@ -1005,15 +1043,82 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) uclamp_rq_dec_id(rq, p, clamp_id); } +static inline void +uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id) +{ + struct rq_flags rf; + struct rq *rq; + + /* + * Lock the task and the rq where the task is (or was) queued. + * + * We might lock the (previous) rq of a !RUNNABLE task, but that's the + * price to pay to safely serialize util_{min,max} updates with + * enqueues, dequeues and migration operations. + * This is the same locking schema used by __set_cpus_allowed_ptr(). + */ + rq = task_rq_lock(p, &rf); + + /* + * Setting the clamp bucket is serialized by task_rq_lock(). + * If the task is not yet RUNNABLE and its task_struct is not + * affecting a valid clamp bucket, the next time it's enqueued, + * it will already see the updated clamp bucket value. + */ + if (!p->uclamp[clamp_id].active) { + uclamp_rq_dec_id(rq, p, clamp_id); + uclamp_rq_inc_id(rq, p, clamp_id); + } + + task_rq_unlock(rq, p, &rf); +} + +static inline void +uclamp_update_active_tasks(struct cgroup_subsys_state *css, + unsigned int clamps) +{ + enum uclamp_id clamp_id; + struct css_task_iter it; + struct task_struct *p; + + css_task_iter_start(css, 0, &it); + while ((p = css_task_iter_next(&it))) { + for_each_clamp_id(clamp_id) { + if ((0x1 << clamp_id) & clamps) + uclamp_update_active(p, clamp_id); + } + } + css_task_iter_end(&it); +} + +#ifdef CONFIG_UCLAMP_TASK_GROUP +static void cpu_util_update_eff(struct cgroup_subsys_state *css); +static void uclamp_update_root_tg(void) +{ + struct task_group *tg = &root_task_group; + + uclamp_se_set(&tg->uclamp_req[UCLAMP_MIN], + sysctl_sched_uclamp_util_min, false); + uclamp_se_set(&tg->uclamp_req[UCLAMP_MAX], + sysctl_sched_uclamp_util_max, false); + + rcu_read_lock(); + cpu_util_update_eff(&root_task_group.css); + rcu_read_unlock(); +} +#else +static void uclamp_update_root_tg(void) { } +#endif + int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + bool update_root_tg = false; int old_min, old_max; - static DEFINE_MUTEX(mutex); int result; - mutex_lock(&mutex); + mutex_lock(&uclamp_mutex); old_min = sysctl_sched_uclamp_util_min; old_max = sysctl_sched_uclamp_util_max; @@ -1032,23 +1137,30 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, if (old_min != sysctl_sched_uclamp_util_min) { uclamp_se_set(&uclamp_default[UCLAMP_MIN], sysctl_sched_uclamp_util_min, false); + update_root_tg = true; } if (old_max != sysctl_sched_uclamp_util_max) { uclamp_se_set(&uclamp_default[UCLAMP_MAX], sysctl_sched_uclamp_util_max, false); + update_root_tg = true; } + if (update_root_tg) + uclamp_update_root_tg(); + /* - * Updating all the RUNNABLE task is expensive, keep it simple and do - * just a lazy update at each next enqueue time. + * We update all RUNNABLE tasks only when task groups are in use. + * Otherwise, keep it simple and do just a lazy update at each next + * task enqueue time. */ + goto done; undo: sysctl_sched_uclamp_util_min = old_min; sysctl_sched_uclamp_util_max = old_max; done: - mutex_unlock(&mutex); + mutex_unlock(&uclamp_mutex); return result; } @@ -1075,7 +1187,7 @@ static int uclamp_validate(struct task_struct *p, static void __setscheduler_uclamp(struct task_struct *p, const struct sched_attr *attr) { - unsigned int clamp_id; + enum uclamp_id clamp_id; /* * On scheduling class change, reset to default clamps for tasks @@ -1112,7 +1224,7 @@ static void __setscheduler_uclamp(struct task_struct *p, static void uclamp_fork(struct task_struct *p) { - unsigned int clamp_id; + enum uclamp_id clamp_id; for_each_clamp_id(clamp_id) p->uclamp[clamp_id].active = false; @@ -1134,9 +1246,11 @@ static void uclamp_fork(struct task_struct *p) static void __init init_uclamp(void) { struct uclamp_se uc_max = {}; - unsigned int clamp_id; + enum uclamp_id clamp_id; int cpu; + mutex_init(&uclamp_mutex); + for_each_possible_cpu(cpu) { memset(&cpu_rq(cpu)->uclamp, 0, sizeof(struct uclamp_rq)); cpu_rq(cpu)->uclamp_flags = 0; @@ -1149,8 +1263,13 @@ static void __init init_uclamp(void) /* System defaults allow max clamp values for both indexes */ uclamp_se_set(&uc_max, uclamp_none(UCLAMP_MAX), false); - for_each_clamp_id(clamp_id) + for_each_clamp_id(clamp_id) { uclamp_default[clamp_id] = uc_max; +#ifdef CONFIG_UCLAMP_TASK_GROUP + root_task_group.uclamp_req[clamp_id] = uc_max; + root_task_group.uclamp[clamp_id] = uc_max; +#endif + } } #else /* CONFIG_UCLAMP_TASK */ @@ -1494,7 +1613,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) if (queued) enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK); if (running) - set_curr_task(rq, p); + set_next_task(rq, p); } /* @@ -3214,12 +3333,8 @@ static __always_inline struct rq * context_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next, struct rq_flags *rf) { - struct mm_struct *mm, *oldmm; - prepare_task_switch(rq, prev, next); - mm = next->mm; - oldmm = prev->active_mm; /* * For paravirt, this is coupled with an exit in switch_to to * combine the page table reload and the switch backend into @@ -3228,22 +3343,37 @@ context_switch(struct rq *rq, struct task_struct *prev, arch_start_context_switch(prev); /* - * If mm is non-NULL, we pass through switch_mm(). If mm is - * NULL, we will pass through mmdrop() in finish_task_switch(). - * Both of these contain the full memory barrier required by - * membarrier after storing to rq->curr, before returning to - * user-space. + * kernel -> kernel lazy + transfer active + * user -> kernel lazy + mmgrab() active + * + * kernel -> user switch + mmdrop() active + * user -> user switch */ - if (!mm) { - next->active_mm = oldmm; - mmgrab(oldmm); - enter_lazy_tlb(oldmm, next); - } else - switch_mm_irqs_off(oldmm, mm, next); + if (!next->mm) { // to kernel + enter_lazy_tlb(prev->active_mm, next); + + next->active_mm = prev->active_mm; + if (prev->mm) // from user + mmgrab(prev->active_mm); + else + prev->active_mm = NULL; + } else { // to user + /* + * sys_membarrier() requires an smp_mb() between setting + * rq->curr and returning to userspace. + * + * The below provides this either through switch_mm(), or in + * case 'prev->active_mm == next->mm' through + * finish_task_switch()'s mmdrop(). + */ - if (!prev->mm) { - prev->active_mm = NULL; - rq->prev_mm = oldmm; + switch_mm_irqs_off(prev->active_mm, next->mm, next); + + if (!prev->mm) { // from kernel + /* will mmdrop() in finish_task_switch(). */ + rq->prev_mm = prev->active_mm; + prev->active_mm = NULL; + } } rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); @@ -3486,8 +3616,36 @@ void scheduler_tick(void) struct tick_work { int cpu; + atomic_t state; struct delayed_work work; }; +/* Values for ->state, see diagram below. */ +#define TICK_SCHED_REMOTE_OFFLINE 0 +#define TICK_SCHED_REMOTE_OFFLINING 1 +#define TICK_SCHED_REMOTE_RUNNING 2 + +/* + * State diagram for ->state: + * + * + * TICK_SCHED_REMOTE_OFFLINE + * | ^ + * | | + * | | sched_tick_remote() + * | | + * | | + * +--TICK_SCHED_REMOTE_OFFLINING + * | ^ + * | | + * sched_tick_start() | | sched_tick_stop() + * | | + * V | + * TICK_SCHED_REMOTE_RUNNING + * + * + * Other transitions get WARN_ON_ONCE(), except that sched_tick_remote() + * and sched_tick_start() are happy to leave the state in RUNNING. + */ static struct tick_work __percpu *tick_work_cpu; @@ -3500,6 +3658,7 @@ static void sched_tick_remote(struct work_struct *work) struct task_struct *curr; struct rq_flags rf; u64 delta; + int os; /* * Handle the tick only if it appears the remote CPU is running in full @@ -3513,7 +3672,7 @@ static void sched_tick_remote(struct work_struct *work) rq_lock_irq(rq, &rf); curr = rq->curr; - if (is_idle_task(curr)) + if (is_idle_task(curr) || cpu_is_offline(cpu)) goto out_unlock; update_rq_clock(rq); @@ -3533,13 +3692,18 @@ out_requeue: /* * Run the remote tick once per second (1Hz). This arbitrary * frequency is large enough to avoid overload but short enough - * to keep scheduler internal stats reasonably up to date. + * to keep scheduler internal stats reasonably up to date. But + * first update state to reflect hotplug activity if required. */ - queue_delayed_work(system_unbound_wq, dwork, HZ); + os = atomic_fetch_add_unless(&twork->state, -1, TICK_SCHED_REMOTE_RUNNING); + WARN_ON_ONCE(os == TICK_SCHED_REMOTE_OFFLINE); + if (os == TICK_SCHED_REMOTE_RUNNING) + queue_delayed_work(system_unbound_wq, dwork, HZ); } static void sched_tick_start(int cpu) { + int os; struct tick_work *twork; if (housekeeping_cpu(cpu, HK_FLAG_TICK)) @@ -3548,15 +3712,20 @@ static void sched_tick_start(int cpu) WARN_ON_ONCE(!tick_work_cpu); twork = per_cpu_ptr(tick_work_cpu, cpu); - twork->cpu = cpu; - INIT_DELAYED_WORK(&twork->work, sched_tick_remote); - queue_delayed_work(system_unbound_wq, &twork->work, HZ); + os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_RUNNING); + WARN_ON_ONCE(os == TICK_SCHED_REMOTE_RUNNING); + if (os == TICK_SCHED_REMOTE_OFFLINE) { + twork->cpu = cpu; + INIT_DELAYED_WORK(&twork->work, sched_tick_remote); + queue_delayed_work(system_unbound_wq, &twork->work, HZ); + } } #ifdef CONFIG_HOTPLUG_CPU static void sched_tick_stop(int cpu) { struct tick_work *twork; + int os; if (housekeeping_cpu(cpu, HK_FLAG_TICK)) return; @@ -3564,7 +3733,10 @@ static void sched_tick_stop(int cpu) WARN_ON_ONCE(!tick_work_cpu); twork = per_cpu_ptr(tick_work_cpu, cpu); - cancel_delayed_work_sync(&twork->work); + /* There cannot be competing actions, but don't rely on stop-machine. */ + os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_OFFLINING); + WARN_ON_ONCE(os != TICK_SCHED_REMOTE_RUNNING); + /* Don't cancel, as this would mess up the state machine. */ } #endif /* CONFIG_HOTPLUG_CPU */ @@ -3572,7 +3744,6 @@ int __init sched_tick_offload_init(void) { tick_work_cpu = alloc_percpu(struct tick_work); BUG_ON(!tick_work_cpu); - return 0; } @@ -3581,7 +3752,7 @@ static inline void sched_tick_start(int cpu) { } static inline void sched_tick_stop(int cpu) { } #endif -#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ +#if defined(CONFIG_PREEMPTION) && (defined(CONFIG_DEBUG_PREEMPT) || \ defined(CONFIG_TRACE_PREEMPT_TOGGLE)) /* * If the value passed in is equal to the current preempt count @@ -3739,7 +3910,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) p = fair_sched_class.pick_next_task(rq, prev, rf); if (unlikely(p == RETRY_TASK)) - goto again; + goto restart; /* Assumes fair_sched_class->next == idle_sched_class */ if (unlikely(!p)) @@ -3748,14 +3919,19 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) return p; } -again: +restart: + /* + * Ensure that we put DL/RT tasks before the pick loop, such that they + * can PULL higher prio tasks when we lower the RQ 'priority'. + */ + prev->sched_class->put_prev_task(rq, prev, rf); + if (!rq->nr_running) + newidle_balance(rq, rf); + for_each_class(class) { - p = class->pick_next_task(rq, prev, rf); - if (p) { - if (unlikely(p == RETRY_TASK)) - goto again; + p = class->pick_next_task(rq, NULL, NULL); + if (p) return p; - } } /* The idle class should always have a runnable task: */ @@ -3782,7 +3958,7 @@ again: * task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets * called on the nearest possible occasion: * - * - If the kernel is preemptible (CONFIG_PREEMPT=y): + * - If the kernel is preemptible (CONFIG_PREEMPTION=y): * * - in syscall or exception context, at the next outmost * preempt_enable(). (this might be as soon as the wake_up()'s @@ -3791,7 +3967,7 @@ again: * - in IRQ context, return from interrupt-handler to * preemptible context * - * - If the kernel is not preemptible (CONFIG_PREEMPT is not set) + * - If the kernel is not preemptible (CONFIG_PREEMPTION is not set) * then at the next: * * - cond_resched() call @@ -4036,7 +4212,7 @@ static void __sched notrace preempt_schedule_common(void) } while (need_resched()); } -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION /* * this is the entry point to schedule() from in-kernel preemption * off of preempt_enable. Kernel preemptions off return from interrupt @@ -4108,7 +4284,7 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void) } EXPORT_SYMBOL_GPL(preempt_schedule_notrace); -#endif /* CONFIG_PREEMPT */ +#endif /* CONFIG_PREEMPTION */ /* * this is the entry point to schedule() from kernel preemption @@ -4276,7 +4452,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) if (queued) enqueue_task(rq, p, queue_flag); if (running) - set_curr_task(rq, p); + set_next_task(rq, p); check_class_changed(rq, p, prev_class, oldprio); out_unlock: @@ -4343,7 +4519,7 @@ void set_user_nice(struct task_struct *p, long nice) resched_curr(rq); } if (running) - set_curr_task(rq, p); + set_next_task(rq, p); out_unlock: task_rq_unlock(rq, p, &rf); } @@ -4660,6 +4836,9 @@ recheck: return retval; } + if (pi) + cpuset_read_lock(); + /* * Make sure no PI-waiters arrive (or leave) while we are * changing the priority of the task: @@ -4674,8 +4853,8 @@ recheck: * Changing the policy of the stop threads its a very bad idea: */ if (p == rq->stop) { - task_rq_unlock(rq, p, &rf); - return -EINVAL; + retval = -EINVAL; + goto unlock; } /* @@ -4693,8 +4872,8 @@ recheck: goto change; p->sched_reset_on_fork = reset_on_fork; - task_rq_unlock(rq, p, &rf); - return 0; + retval = 0; + goto unlock; } change: @@ -4707,8 +4886,8 @@ change: if (rt_bandwidth_enabled() && rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0 && !task_group_is_autogroup(task_group(p))) { - task_rq_unlock(rq, p, &rf); - return -EPERM; + retval = -EPERM; + goto unlock; } #endif #ifdef CONFIG_SMP @@ -4723,8 +4902,8 @@ change: */ if (!cpumask_subset(span, p->cpus_ptr) || rq->rd->dl_bw.bw == 0) { - task_rq_unlock(rq, p, &rf); - return -EPERM; + retval = -EPERM; + goto unlock; } } #endif @@ -4734,6 +4913,8 @@ change: if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { policy = oldpolicy = -1; task_rq_unlock(rq, p, &rf); + if (pi) + cpuset_read_unlock(); goto recheck; } @@ -4743,8 +4924,8 @@ change: * is available. */ if ((dl_policy(policy) || dl_task(p)) && sched_dl_overflow(p, policy, attr)) { - task_rq_unlock(rq, p, &rf); - return -EBUSY; + retval = -EBUSY; + goto unlock; } p->sched_reset_on_fork = reset_on_fork; @@ -4786,7 +4967,7 @@ change: enqueue_task(rq, p, queue_flags); } if (running) - set_curr_task(rq, p); + set_next_task(rq, p); check_class_changed(rq, p, prev_class, oldprio); @@ -4794,14 +4975,22 @@ change: preempt_disable(); task_rq_unlock(rq, p, &rf); - if (pi) + if (pi) { + cpuset_read_unlock(); rt_mutex_adjust_pi(p); + } /* Run balance callbacks after we've adjusted the PI chain: */ balance_callback(rq); preempt_enable(); return 0; + +unlock: + task_rq_unlock(rq, p, &rf); + if (pi) + cpuset_read_unlock(); + return retval; } static int _sched_setscheduler(struct task_struct *p, int policy, @@ -4885,10 +5074,15 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) rcu_read_lock(); retval = -ESRCH; p = find_process_by_pid(pid); - if (p != NULL) - retval = sched_setscheduler(p, policy, &lparam); + if (likely(p)) + get_task_struct(p); rcu_read_unlock(); + if (likely(p)) { + retval = sched_setscheduler(p, policy, &lparam); + put_task_struct(p); + } + return retval; } @@ -5105,37 +5299,40 @@ out_unlock: return retval; } -static int sched_read_attr(struct sched_attr __user *uattr, - struct sched_attr *attr, - unsigned int usize) +/* + * Copy the kernel size attribute structure (which might be larger + * than what user-space knows about) to user-space. + * + * Note that all cases are valid: user-space buffer can be larger or + * smaller than the kernel-space buffer. The usual case is that both + * have the same size. + */ +static int +sched_attr_copy_to_user(struct sched_attr __user *uattr, + struct sched_attr *kattr, + unsigned int usize) { - int ret; + unsigned int ksize = sizeof(*kattr); if (!access_ok(uattr, usize)) return -EFAULT; /* - * If we're handed a smaller struct than we know of, - * ensure all the unknown bits are 0 - i.e. old - * user-space does not get uncomplete information. + * sched_getattr() ABI forwards and backwards compatibility: + * + * If usize == ksize then we just copy everything to user-space and all is good. + * + * If usize < ksize then we only copy as much as user-space has space for, + * this keeps ABI compatibility as well. We skip the rest. + * + * If usize > ksize then user-space is using a newer version of the ABI, + * which part the kernel doesn't know about. Just ignore it - tooling can + * detect the kernel's knowledge of attributes from the attr->size value + * which is set to ksize in this case. */ - if (usize < sizeof(*attr)) { - unsigned char *addr; - unsigned char *end; - - addr = (void *)attr + usize; - end = (void *)attr + sizeof(*attr); - - for (; addr < end; addr++) { - if (*addr) - return -EFBIG; - } - - attr->size = usize; - } + kattr->size = min(usize, ksize); - ret = copy_to_user(uattr, attr, attr->size); - if (ret) + if (copy_to_user(uattr, kattr, kattr->size)) return -EFAULT; return 0; @@ -5145,20 +5342,18 @@ static int sched_read_attr(struct sched_attr __user *uattr, * sys_sched_getattr - similar to sched_getparam, but with sched_attr * @pid: the pid in question. * @uattr: structure containing the extended parameters. - * @size: sizeof(attr) for fwd/bwd comp. + * @usize: sizeof(attr) that user-space knows about, for forwards and backwards compatibility. * @flags: for future extension. */ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, - unsigned int, size, unsigned int, flags) + unsigned int, usize, unsigned int, flags) { - struct sched_attr attr = { - .size = sizeof(struct sched_attr), - }; + struct sched_attr kattr = { }; struct task_struct *p; int retval; - if (!uattr || pid < 0 || size > PAGE_SIZE || - size < SCHED_ATTR_SIZE_VER0 || flags) + if (!uattr || pid < 0 || usize > PAGE_SIZE || + usize < SCHED_ATTR_SIZE_VER0 || flags) return -EINVAL; rcu_read_lock(); @@ -5171,25 +5366,24 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, if (retval) goto out_unlock; - attr.sched_policy = p->policy; + kattr.sched_policy = p->policy; if (p->sched_reset_on_fork) - attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; + kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; if (task_has_dl_policy(p)) - __getparam_dl(p, &attr); + __getparam_dl(p, &kattr); else if (task_has_rt_policy(p)) - attr.sched_priority = p->rt_priority; + kattr.sched_priority = p->rt_priority; else - attr.sched_nice = task_nice(p); + kattr.sched_nice = task_nice(p); #ifdef CONFIG_UCLAMP_TASK - attr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value; - attr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value; + kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value; + kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value; #endif rcu_read_unlock(); - retval = sched_read_attr(uattr, &attr, size); - return retval; + return sched_attr_copy_to_user(uattr, &kattr, usize); out_unlock: rcu_read_unlock(); @@ -5419,7 +5613,7 @@ SYSCALL_DEFINE0(sched_yield) return 0; } -#ifndef CONFIG_PREEMPT +#ifndef CONFIG_PREEMPTION int __sched _cond_resched(void) { if (should_resched(0)) { @@ -5436,7 +5630,7 @@ EXPORT_SYMBOL(_cond_resched); * __cond_resched_lock() - if a reschedule is pending, drop the given lock, * call schedule, and on return reacquire the lock. * - * This works OK both with and without CONFIG_PREEMPT. We do strange low-level + * This works OK both with and without CONFIG_PREEMPTION. We do strange low-level * operations here to prevent schedule() from being called twice (once via * spin_unlock(), once by hand). */ @@ -5975,7 +6169,7 @@ void sched_setnuma(struct task_struct *p, int nid) if (queued) enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK); if (running) - set_curr_task(rq, p); + set_next_task(rq, p); task_rq_unlock(rq, p, &rf); } #endif /* CONFIG_NUMA_BALANCING */ @@ -6015,21 +6209,22 @@ static void calc_load_migrate(struct rq *rq) atomic_long_add(delta, &calc_load_tasks); } -static void put_prev_task_fake(struct rq *rq, struct task_struct *prev) +static struct task_struct *__pick_migrate_task(struct rq *rq) { -} + const struct sched_class *class; + struct task_struct *next; -static const struct sched_class fake_sched_class = { - .put_prev_task = put_prev_task_fake, -}; + for_each_class(class) { + next = class->pick_next_task(rq, NULL, NULL); + if (next) { + next->sched_class->put_prev_task(rq, next, NULL); + return next; + } + } -static struct task_struct fake_task = { - /* - * Avoid pull_{rt,dl}_task() - */ - .prio = MAX_PRIO + 1, - .sched_class = &fake_sched_class, -}; + /* The idle class should always have a runnable task */ + BUG(); +} /* * Migrate all tasks from the rq, sleeping tasks will be migrated by @@ -6072,12 +6267,7 @@ static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf) if (rq->nr_running == 1) break; - /* - * pick_next_task() assumes pinned rq->lock: - */ - next = pick_next_task(rq, &fake_task, rf); - BUG_ON(!next); - put_prev_task(rq, next); + next = __pick_migrate_task(rq); /* * Rules for changing task_struct::cpus_mask are holding @@ -6374,19 +6564,19 @@ DECLARE_PER_CPU(cpumask_var_t, select_idle_mask); void __init sched_init(void) { - unsigned long alloc_size = 0, ptr; + unsigned long ptr = 0; int i; wait_bit_init(); #ifdef CONFIG_FAIR_GROUP_SCHED - alloc_size += 2 * nr_cpu_ids * sizeof(void **); + ptr += 2 * nr_cpu_ids * sizeof(void **); #endif #ifdef CONFIG_RT_GROUP_SCHED - alloc_size += 2 * nr_cpu_ids * sizeof(void **); + ptr += 2 * nr_cpu_ids * sizeof(void **); #endif - if (alloc_size) { - ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT); + if (ptr) { + ptr = (unsigned long)kzalloc(ptr, GFP_NOWAIT); #ifdef CONFIG_FAIR_GROUP_SCHED root_task_group.se = (struct sched_entity **)ptr; @@ -6705,7 +6895,7 @@ struct task_struct *curr_task(int cpu) #ifdef CONFIG_IA64 /** - * set_curr_task - set the current task for a given CPU. + * ia64_set_curr_task - set the current task for a given CPU. * @cpu: the processor in question. * @p: the task pointer to set. * @@ -6730,6 +6920,20 @@ void ia64_set_curr_task(int cpu, struct task_struct *p) /* task_group_lock serializes the addition/removal of task groups */ static DEFINE_SPINLOCK(task_group_lock); +static inline void alloc_uclamp_sched_group(struct task_group *tg, + struct task_group *parent) +{ +#ifdef CONFIG_UCLAMP_TASK_GROUP + enum uclamp_id clamp_id; + + for_each_clamp_id(clamp_id) { + uclamp_se_set(&tg->uclamp_req[clamp_id], + uclamp_none(clamp_id), false); + tg->uclamp[clamp_id] = parent->uclamp[clamp_id]; + } +#endif +} + static void sched_free_group(struct task_group *tg) { free_fair_sched_group(tg); @@ -6753,6 +6957,8 @@ struct task_group *sched_create_group(struct task_group *parent) if (!alloc_rt_sched_group(tg, parent)) goto err; + alloc_uclamp_sched_group(tg, parent); + return tg; err: @@ -6856,7 +7062,7 @@ void sched_move_task(struct task_struct *tsk) if (queued) enqueue_task(rq, tsk, queue_flags); if (running) - set_curr_task(rq, tsk); + set_next_task(rq, tsk); task_rq_unlock(rq, tsk, &rf); } @@ -6939,10 +7145,6 @@ static int cpu_cgroup_can_attach(struct cgroup_taskset *tset) #ifdef CONFIG_RT_GROUP_SCHED if (!sched_rt_can_attach(css_tg(css), task)) return -EINVAL; -#else - /* We don't support RT-tasks being in separate groups */ - if (task->sched_class != &fair_sched_class) - return -EINVAL; #endif /* * Serialize against wake_up_new_task() such that if its @@ -6973,6 +7175,178 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset) sched_move_task(task); } +#ifdef CONFIG_UCLAMP_TASK_GROUP +static void cpu_util_update_eff(struct cgroup_subsys_state *css) +{ + struct cgroup_subsys_state *top_css = css; + struct uclamp_se *uc_parent = NULL; + struct uclamp_se *uc_se = NULL; + unsigned int eff[UCLAMP_CNT]; + enum uclamp_id clamp_id; + unsigned int clamps; + + css_for_each_descendant_pre(css, top_css) { + uc_parent = css_tg(css)->parent + ? css_tg(css)->parent->uclamp : NULL; + + for_each_clamp_id(clamp_id) { + /* Assume effective clamps matches requested clamps */ + eff[clamp_id] = css_tg(css)->uclamp_req[clamp_id].value; + /* Cap effective clamps with parent's effective clamps */ + if (uc_parent && + eff[clamp_id] > uc_parent[clamp_id].value) { + eff[clamp_id] = uc_parent[clamp_id].value; + } + } + /* Ensure protection is always capped by limit */ + eff[UCLAMP_MIN] = min(eff[UCLAMP_MIN], eff[UCLAMP_MAX]); + + /* Propagate most restrictive effective clamps */ + clamps = 0x0; + uc_se = css_tg(css)->uclamp; + for_each_clamp_id(clamp_id) { + if (eff[clamp_id] == uc_se[clamp_id].value) + continue; + uc_se[clamp_id].value = eff[clamp_id]; + uc_se[clamp_id].bucket_id = uclamp_bucket_id(eff[clamp_id]); + clamps |= (0x1 << clamp_id); + } + if (!clamps) { + css = css_rightmost_descendant(css); + continue; + } + + /* Immediately update descendants RUNNABLE tasks */ + uclamp_update_active_tasks(css, clamps); + } +} + +/* + * Integer 10^N with a given N exponent by casting to integer the literal "1eN" + * C expression. Since there is no way to convert a macro argument (N) into a + * character constant, use two levels of macros. + */ +#define _POW10(exp) ((unsigned int)1e##exp) +#define POW10(exp) _POW10(exp) + +struct uclamp_request { +#define UCLAMP_PERCENT_SHIFT 2 +#define UCLAMP_PERCENT_SCALE (100 * POW10(UCLAMP_PERCENT_SHIFT)) + s64 percent; + u64 util; + int ret; +}; + +static inline struct uclamp_request +capacity_from_percent(char *buf) +{ + struct uclamp_request req = { + .percent = UCLAMP_PERCENT_SCALE, + .util = SCHED_CAPACITY_SCALE, + .ret = 0, + }; + + buf = strim(buf); + if (strcmp(buf, "max")) { + req.ret = cgroup_parse_float(buf, UCLAMP_PERCENT_SHIFT, + &req.percent); + if (req.ret) + return req; + if (req.percent > UCLAMP_PERCENT_SCALE) { + req.ret = -ERANGE; + return req; + } + + req.util = req.percent << SCHED_CAPACITY_SHIFT; + req.util = DIV_ROUND_CLOSEST_ULL(req.util, UCLAMP_PERCENT_SCALE); + } + + return req; +} + +static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off, + enum uclamp_id clamp_id) +{ + struct uclamp_request req; + struct task_group *tg; + + req = capacity_from_percent(buf); + if (req.ret) + return req.ret; + + mutex_lock(&uclamp_mutex); + rcu_read_lock(); + + tg = css_tg(of_css(of)); + if (tg->uclamp_req[clamp_id].value != req.util) + uclamp_se_set(&tg->uclamp_req[clamp_id], req.util, false); + + /* + * Because of not recoverable conversion rounding we keep track of the + * exact requested value + */ + tg->uclamp_pct[clamp_id] = req.percent; + + /* Update effective clamps to track the most restrictive value */ + cpu_util_update_eff(of_css(of)); + + rcu_read_unlock(); + mutex_unlock(&uclamp_mutex); + + return nbytes; +} + +static ssize_t cpu_uclamp_min_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + return cpu_uclamp_write(of, buf, nbytes, off, UCLAMP_MIN); +} + +static ssize_t cpu_uclamp_max_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + return cpu_uclamp_write(of, buf, nbytes, off, UCLAMP_MAX); +} + +static inline void cpu_uclamp_print(struct seq_file *sf, + enum uclamp_id clamp_id) +{ + struct task_group *tg; + u64 util_clamp; + u64 percent; + u32 rem; + + rcu_read_lock(); + tg = css_tg(seq_css(sf)); + util_clamp = tg->uclamp_req[clamp_id].value; + rcu_read_unlock(); + + if (util_clamp == SCHED_CAPACITY_SCALE) { + seq_puts(sf, "max\n"); + return; + } + + percent = tg->uclamp_pct[clamp_id]; + percent = div_u64_rem(percent, POW10(UCLAMP_PERCENT_SHIFT), &rem); + seq_printf(sf, "%llu.%0*u\n", percent, UCLAMP_PERCENT_SHIFT, rem); +} + +static int cpu_uclamp_min_show(struct seq_file *sf, void *v) +{ + cpu_uclamp_print(sf, UCLAMP_MIN); + return 0; +} + +static int cpu_uclamp_max_show(struct seq_file *sf, void *v) +{ + cpu_uclamp_print(sf, UCLAMP_MAX); + return 0; +} +#endif /* CONFIG_UCLAMP_TASK_GROUP */ + #ifdef CONFIG_FAIR_GROUP_SCHED static int cpu_shares_write_u64(struct cgroup_subsys_state *css, struct cftype *cftype, u64 shareval) @@ -7318,6 +7692,20 @@ static struct cftype cpu_legacy_files[] = { .write_u64 = cpu_rt_period_write_uint, }, #endif +#ifdef CONFIG_UCLAMP_TASK_GROUP + { + .name = "uclamp.min", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cpu_uclamp_min_show, + .write = cpu_uclamp_min_write, + }, + { + .name = "uclamp.max", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cpu_uclamp_max_show, + .write = cpu_uclamp_max_write, + }, +#endif { } /* Terminate */ }; @@ -7485,6 +7873,20 @@ static struct cftype cpu_files[] = { .write = cpu_max_write, }, #endif +#ifdef CONFIG_UCLAMP_TASK_GROUP + { + .name = "uclamp.min", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cpu_uclamp_min_show, + .write = cpu_uclamp_min_write, + }, + { + .name = "uclamp.max", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cpu_uclamp_max_show, + .write = cpu_uclamp_max_write, + }, +#endif { } /* terminate */ }; diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 867b4bb6d4be..86800b4d5453 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -117,6 +117,7 @@ static void sugov_fast_switch(struct sugov_policy *sg_policy, u64 time, unsigned int next_freq) { struct cpufreq_policy *policy = sg_policy->policy; + int cpu; if (!sugov_update_next_freq(sg_policy, time, next_freq)) return; @@ -126,7 +127,11 @@ static void sugov_fast_switch(struct sugov_policy *sg_policy, u64 time, return; policy->cur = next_freq; - trace_cpu_frequency(next_freq, smp_processor_id()); + + if (trace_cpu_frequency_enabled()) { + for_each_cpu(cpu, policy->cpus) + trace_cpu_frequency(next_freq, cpu); + } } static void sugov_deferred_update(struct sugov_policy *sg_policy, u64 time, @@ -263,9 +268,9 @@ unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs, * irq metric. Because IRQ/steal time is hidden from the task clock we * need to scale the task numbers: * - * 1 - irq - * U' = irq + ------- * U - * max + * max - irq + * U' = irq + --------- * U + * max */ util = scale_irq_capacity(util, irq, max); util += irq; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 46122edd8552..2dc48720f189 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -287,7 +287,7 @@ static void task_non_contending(struct task_struct *p) dl_se->dl_non_contending = 1; get_task_struct(p); - hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL); + hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL_HARD); } static void task_contending(struct sched_dl_entity *dl_se, int flags) @@ -529,6 +529,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq); static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p) { struct rq *later_rq = NULL; + struct dl_bw *dl_b; later_rq = find_lock_later_rq(p, rq); if (!later_rq) { @@ -557,6 +558,38 @@ static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p double_lock_balance(rq, later_rq); } + if (p->dl.dl_non_contending || p->dl.dl_throttled) { + /* + * Inactive timer is armed (or callback is running, but + * waiting for us to release rq locks). In any case, when it + * will fire (or continue), it will see running_bw of this + * task migrated to later_rq (and correctly handle it). + */ + sub_running_bw(&p->dl, &rq->dl); + sub_rq_bw(&p->dl, &rq->dl); + + add_rq_bw(&p->dl, &later_rq->dl); + add_running_bw(&p->dl, &later_rq->dl); + } else { + sub_rq_bw(&p->dl, &rq->dl); + add_rq_bw(&p->dl, &later_rq->dl); + } + + /* + * And we finally need to fixup root_domain(s) bandwidth accounting, + * since p is still hanging out in the old (now moved to default) root + * domain. + */ + dl_b = &rq->rd->dl_bw; + raw_spin_lock(&dl_b->lock); + __dl_sub(dl_b, p->dl.dl_bw, cpumask_weight(rq->rd->span)); + raw_spin_unlock(&dl_b->lock); + + dl_b = &later_rq->rd->dl_bw; + raw_spin_lock(&dl_b->lock); + __dl_add(dl_b, p->dl.dl_bw, cpumask_weight(later_rq->rd->span)); + raw_spin_unlock(&dl_b->lock); + set_task_cpu(p, later_rq->cpu); double_unlock_balance(later_rq, rq); @@ -923,7 +956,7 @@ static int start_dl_timer(struct task_struct *p) */ if (!hrtimer_is_queued(timer)) { get_task_struct(p); - hrtimer_start(timer, act, HRTIMER_MODE_ABS); + hrtimer_start(timer, act, HRTIMER_MODE_ABS_HARD); } return 1; @@ -1053,7 +1086,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se) { struct hrtimer *timer = &dl_se->dl_timer; - hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); timer->function = dl_task_timer; } @@ -1292,7 +1325,7 @@ void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se) { struct hrtimer *timer = &dl_se->inactive_timer; - hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); timer->function = inactive_task_timer; } @@ -1694,12 +1727,20 @@ static void start_hrtick_dl(struct rq *rq, struct task_struct *p) } #endif -static inline void set_next_task(struct rq *rq, struct task_struct *p) +static void set_next_task_dl(struct rq *rq, struct task_struct *p) { p->se.exec_start = rq_clock_task(rq); /* You can't push away the running task */ dequeue_pushable_dl_task(rq, p); + + if (hrtick_enabled(rq)) + start_hrtick_dl(rq, p); + + if (rq->curr->sched_class != &dl_sched_class) + update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0); + + deadline_queue_push_tasks(rq); } static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq, @@ -1720,64 +1761,42 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) struct task_struct *p; struct dl_rq *dl_rq; - dl_rq = &rq->dl; + WARN_ON_ONCE(prev || rf); - if (need_pull_dl_task(rq, prev)) { - /* - * This is OK, because current is on_cpu, which avoids it being - * picked for load-balance and preemption/IRQs are still - * disabled avoiding further scheduler activity on it and we're - * being very careful to re-start the picking loop. - */ - rq_unpin_lock(rq, rf); - pull_dl_task(rq); - rq_repin_lock(rq, rf); - /* - * pull_dl_task() can drop (and re-acquire) rq->lock; this - * means a stop task can slip in, in which case we need to - * re-start task selection. - */ - if (rq->stop && task_on_rq_queued(rq->stop)) - return RETRY_TASK; - } - - /* - * When prev is DL, we may throttle it in put_prev_task(). - * So, we update time before we check for dl_nr_running. - */ - if (prev->sched_class == &dl_sched_class) - update_curr_dl(rq); + dl_rq = &rq->dl; if (unlikely(!dl_rq->dl_nr_running)) return NULL; - put_prev_task(rq, prev); - dl_se = pick_next_dl_entity(rq, dl_rq); BUG_ON(!dl_se); p = dl_task_of(dl_se); - set_next_task(rq, p); - - if (hrtick_enabled(rq)) - start_hrtick_dl(rq, p); - - deadline_queue_push_tasks(rq); - - if (rq->curr->sched_class != &dl_sched_class) - update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0); + set_next_task_dl(rq, p); return p; } -static void put_prev_task_dl(struct rq *rq, struct task_struct *p) +static void put_prev_task_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf) { update_curr_dl(rq); update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1); if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); + + if (rf && !on_dl_rq(&p->dl) && need_pull_dl_task(rq, p)) { + /* + * This is OK, because current is on_cpu, which avoids it being + * picked for load-balance and preemption/IRQs are still + * disabled avoiding further scheduler activity on it and we've + * not yet started the picking loop. + */ + rq_unpin_lock(rq, rf); + pull_dl_task(rq); + rq_repin_lock(rq, rf); + } } /* @@ -1811,11 +1830,6 @@ static void task_fork_dl(struct task_struct *p) */ } -static void set_curr_task_dl(struct rq *rq) -{ - set_next_task(rq, rq->curr); -} - #ifdef CONFIG_SMP /* Only try algorithms three times */ @@ -2275,6 +2289,36 @@ void __init init_sched_dl_class(void) GFP_KERNEL, cpu_to_node(i)); } +void dl_add_task_root_domain(struct task_struct *p) +{ + struct rq_flags rf; + struct rq *rq; + struct dl_bw *dl_b; + + rq = task_rq_lock(p, &rf); + if (!dl_task(p)) + goto unlock; + + dl_b = &rq->rd->dl_bw; + raw_spin_lock(&dl_b->lock); + + __dl_add(dl_b, p->dl.dl_bw, cpumask_weight(rq->rd->span)); + + raw_spin_unlock(&dl_b->lock); + +unlock: + task_rq_unlock(rq, p, &rf); +} + +void dl_clear_root_domain(struct root_domain *rd) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&rd->dl_bw.lock, flags); + rd->dl_bw.total_bw = 0; + raw_spin_unlock_irqrestore(&rd->dl_bw.lock, flags); +} + #endif /* CONFIG_SMP */ static void switched_from_dl(struct rq *rq, struct task_struct *p) @@ -2395,6 +2439,7 @@ const struct sched_class dl_sched_class = { .pick_next_task = pick_next_task_dl, .put_prev_task = put_prev_task_dl, + .set_next_task = set_next_task_dl, #ifdef CONFIG_SMP .select_task_rq = select_task_rq_dl, @@ -2405,7 +2450,6 @@ const struct sched_class dl_sched_class = { .task_woken = task_woken_dl, #endif - .set_curr_task = set_curr_task_dl, .task_tick = task_tick_dl, .task_fork = task_fork_dl, diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index bc9cfeaac8bd..d4bbf68c3161 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -96,12 +96,12 @@ int __weak arch_asym_cpu_priority(int cpu) } /* - * The margin used when comparing utilization with CPU capacity: - * util * margin < capacity * 1024 + * The margin used when comparing utilization with CPU capacity. * * (default: ~20%) */ -static unsigned int capacity_margin = 1280; +#define fits_capacity(cap, max) ((cap) * 1280 < (max) * 1024) + #endif #ifdef CONFIG_CFS_BANDWIDTH @@ -1188,47 +1188,6 @@ 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; - RCU_INIT_POINTER(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 = NUMA_NO_NODE; - 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 != NUMA_NO_NODE); @@ -2523,7 +2482,7 @@ static void reset_ptenuma_scan(struct task_struct *p) * The expensive part of numa migration is done from task_work context. * Triggered from task_tick_numa(). */ -void task_numa_work(struct callback_head *work) +static void task_numa_work(struct callback_head *work) { unsigned long migrate, next_scan, now = jiffies; struct task_struct *p = current; @@ -2536,7 +2495,7 @@ void task_numa_work(struct callback_head *work) SCHED_WARN_ON(p != container_of(work, struct task_struct, numa_work)); - work->next = work; /* protect against double add */ + work->next = work; /* * Who cares about NUMA placement when they're dying. * @@ -2665,6 +2624,50 @@ out: } } +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; + /* Protect against double add, see task_tick_numa and task_numa_work */ + p->numa_work.next = &p->numa_work; + p->numa_faults = NULL; + RCU_INIT_POINTER(p->numa_group, NULL); + p->last_task_numa_placement = 0; + p->last_sum_exec_runtime = 0; + + init_task_work(&p->numa_work, task_numa_work); + + /* New address space, reset the preferred nid */ + if (!(clone_flags & CLONE_VM)) { + p->numa_preferred_nid = NUMA_NO_NODE; + 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; + } +} + /* * Drive the periodic memory faults.. */ @@ -2693,10 +2696,8 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr) curr->numa_scan_period = task_scan_start(curr); curr->node_stamp += period; - if (!time_before(jiffies, curr->mm->numa_next_scan)) { - init_task_work(work, task_numa_work); /* TODO: move this into sched_fork() */ + if (!time_before(jiffies, curr->mm->numa_next_scan)) task_work_add(curr, work, true); - } } } @@ -3689,8 +3690,6 @@ static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq) return cfs_rq->avg.load_avg; } -static int idle_balance(struct rq *this_rq, struct rq_flags *rf); - static inline unsigned long task_util(struct task_struct *p) { return READ_ONCE(p->se.avg.util_avg); @@ -3807,7 +3806,7 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) static inline int task_fits_capacity(struct task_struct *p, long capacity) { - return capacity * 1024 > task_util_est(p) * capacity_margin; + return fits_capacity(task_util_est(p), capacity); } static inline void update_misfit_status(struct task_struct *p, struct rq *rq) @@ -4370,8 +4369,6 @@ void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b) now = sched_clock_cpu(smp_processor_id()); cfs_b->runtime = cfs_b->quota; - cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period); - cfs_b->expires_seq++; } static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) @@ -4393,8 +4390,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) { struct task_group *tg = cfs_rq->tg; struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg); - u64 amount = 0, min_amount, expires; - int expires_seq; + u64 amount = 0, min_amount; /* note: this is a positive sum as runtime_remaining <= 0 */ min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining; @@ -4411,65 +4407,23 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) cfs_b->idle = 0; } } - expires_seq = cfs_b->expires_seq; - expires = cfs_b->runtime_expires; raw_spin_unlock(&cfs_b->lock); cfs_rq->runtime_remaining += amount; - /* - * we may have advanced our local expiration to account for allowed - * spread between our sched_clock and the one on which runtime was - * issued. - */ - if (cfs_rq->expires_seq != expires_seq) { - cfs_rq->expires_seq = expires_seq; - cfs_rq->runtime_expires = expires; - } return cfs_rq->runtime_remaining > 0; } -/* - * Note: This depends on the synchronization provided by sched_clock and the - * fact that rq->clock snapshots this value. - */ -static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq) -{ - struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); - - /* if the deadline is ahead of our clock, nothing to do */ - if (likely((s64)(rq_clock(rq_of(cfs_rq)) - cfs_rq->runtime_expires) < 0)) - return; - - if (cfs_rq->runtime_remaining < 0) - return; - - /* - * If the local deadline has passed we have to consider the - * possibility that our sched_clock is 'fast' and the global deadline - * has not truly expired. - * - * Fortunately we can check determine whether this the case by checking - * whether the global deadline(cfs_b->expires_seq) has advanced. - */ - if (cfs_rq->expires_seq == cfs_b->expires_seq) { - /* extend local deadline, drift is bounded above by 2 ticks */ - cfs_rq->runtime_expires += TICK_NSEC; - } else { - /* global deadline is ahead, expiration has passed */ - cfs_rq->runtime_remaining = 0; - } -} - static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) { /* dock delta_exec before expiring quota (as it could span periods) */ cfs_rq->runtime_remaining -= delta_exec; - expire_cfs_rq_runtime(cfs_rq); if (likely(cfs_rq->runtime_remaining > 0)) return; + if (cfs_rq->throttled) + return; /* * if we're unable to extend our runtime we resched so that the active * hierarchy can be throttled @@ -4554,7 +4508,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) struct rq *rq = rq_of(cfs_rq); struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); struct sched_entity *se; - long task_delta, dequeue = 1; + long task_delta, idle_task_delta, dequeue = 1; bool empty; se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))]; @@ -4565,6 +4519,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) rcu_read_unlock(); task_delta = cfs_rq->h_nr_running; + idle_task_delta = cfs_rq->idle_h_nr_running; for_each_sched_entity(se) { struct cfs_rq *qcfs_rq = cfs_rq_of(se); /* throttled entity or throttle-on-deactivate */ @@ -4574,6 +4529,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) if (dequeue) dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP); qcfs_rq->h_nr_running -= task_delta; + qcfs_rq->idle_h_nr_running -= idle_task_delta; if (qcfs_rq->load.weight) dequeue = 0; @@ -4613,7 +4569,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); struct sched_entity *se; int enqueue = 1; - long task_delta; + long task_delta, idle_task_delta; se = cfs_rq->tg->se[cpu_of(rq)]; @@ -4633,6 +4589,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) return; task_delta = cfs_rq->h_nr_running; + idle_task_delta = cfs_rq->idle_h_nr_running; for_each_sched_entity(se) { if (se->on_rq) enqueue = 0; @@ -4641,6 +4598,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) if (enqueue) enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP); cfs_rq->h_nr_running += task_delta; + cfs_rq->idle_h_nr_running += idle_task_delta; if (cfs_rq_throttled(cfs_rq)) break; @@ -4656,8 +4614,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) resched_curr(rq); } -static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, - u64 remaining, u64 expires) +static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining) { struct cfs_rq *cfs_rq; u64 runtime; @@ -4673,13 +4630,15 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, if (!cfs_rq_throttled(cfs_rq)) goto next; + /* By the above check, this should never be true */ + SCHED_WARN_ON(cfs_rq->runtime_remaining > 0); + runtime = -cfs_rq->runtime_remaining + 1; if (runtime > remaining) runtime = remaining; remaining -= runtime; cfs_rq->runtime_remaining += runtime; - cfs_rq->runtime_expires = expires; /* we check whether we're throttled above */ if (cfs_rq->runtime_remaining > 0) @@ -4704,7 +4663,7 @@ next: */ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, unsigned long flags) { - u64 runtime, runtime_expires; + u64 runtime; int throttled; /* no need to continue the timer with no bandwidth constraint */ @@ -4732,8 +4691,6 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u /* account preceding periods in which throttling occurred */ cfs_b->nr_throttled += overrun; - runtime_expires = cfs_b->runtime_expires; - /* * This check is repeated as we are holding onto the new bandwidth while * we unthrottle. This can potentially race with an unthrottled group @@ -4746,8 +4703,7 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u cfs_b->distribute_running = 1; raw_spin_unlock_irqrestore(&cfs_b->lock, flags); /* we can't nest cfs_b->lock while distributing bandwidth */ - runtime = distribute_cfs_runtime(cfs_b, runtime, - runtime_expires); + runtime = distribute_cfs_runtime(cfs_b, runtime); raw_spin_lock_irqsave(&cfs_b->lock, flags); cfs_b->distribute_running = 0; @@ -4829,8 +4785,7 @@ static void __return_cfs_rq_runtime(struct cfs_rq *cfs_rq) return; raw_spin_lock(&cfs_b->lock); - if (cfs_b->quota != RUNTIME_INF && - cfs_rq->runtime_expires == cfs_b->runtime_expires) { + if (cfs_b->quota != RUNTIME_INF) { cfs_b->runtime += slack_runtime; /* we are under rq->lock, defer unthrottling using a timer */ @@ -4863,7 +4818,6 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) { u64 runtime = 0, slice = sched_cfs_bandwidth_slice(); unsigned long flags; - u64 expires; /* confirm we're still not at a refresh boundary */ raw_spin_lock_irqsave(&cfs_b->lock, flags); @@ -4881,7 +4835,6 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) runtime = cfs_b->runtime; - expires = cfs_b->runtime_expires; if (runtime) cfs_b->distribute_running = 1; @@ -4890,11 +4843,10 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) if (!runtime) return; - runtime = distribute_cfs_runtime(cfs_b, runtime, expires); + runtime = distribute_cfs_runtime(cfs_b, runtime); raw_spin_lock_irqsave(&cfs_b->lock, flags); - if (expires == cfs_b->runtime_expires) - lsub_positive(&cfs_b->runtime, runtime); + lsub_positive(&cfs_b->runtime, runtime); cfs_b->distribute_running = 0; raw_spin_unlock_irqrestore(&cfs_b->lock, flags); } @@ -5051,8 +5003,6 @@ void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b) cfs_b->period_active = 1; overrun = hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period); - cfs_b->runtime_expires += (overrun + 1) * ktime_to_ns(cfs_b->period); - cfs_b->expires_seq++; hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED); } @@ -5230,7 +5180,7 @@ static inline unsigned long cpu_util(int cpu); static inline bool cpu_overutilized(int cpu) { - return (capacity_of(cpu) * 1024) < (cpu_util(cpu) * capacity_margin); + return !fits_capacity(cpu_util(cpu), capacity_of(cpu)); } static inline void update_overutilized_status(struct rq *rq) @@ -5254,6 +5204,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) { struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; + int idle_h_nr_running = task_has_idle_policy(p); /* * The code below (indirectly) updates schedutil which looks at @@ -5286,6 +5237,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (cfs_rq_throttled(cfs_rq)) break; cfs_rq->h_nr_running++; + cfs_rq->idle_h_nr_running += idle_h_nr_running; flags = ENQUEUE_WAKEUP; } @@ -5293,6 +5245,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); cfs_rq->h_nr_running++; + cfs_rq->idle_h_nr_running += idle_h_nr_running; if (cfs_rq_throttled(cfs_rq)) break; @@ -5354,6 +5307,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; int task_sleep = flags & DEQUEUE_SLEEP; + int idle_h_nr_running = task_has_idle_policy(p); for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); @@ -5368,6 +5322,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (cfs_rq_throttled(cfs_rq)) break; cfs_rq->h_nr_running--; + cfs_rq->idle_h_nr_running -= idle_h_nr_running; /* Don't dequeue parent if it has other entities besides us */ if (cfs_rq->load.weight) { @@ -5387,6 +5342,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); cfs_rq->h_nr_running--; + cfs_rq->idle_h_nr_running -= idle_h_nr_running; if (cfs_rq_throttled(cfs_rq)) break; @@ -5420,6 +5376,15 @@ static struct { #endif /* CONFIG_NO_HZ_COMMON */ +/* CPU only has SCHED_IDLE tasks enqueued */ +static int sched_idle_cpu(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + return unlikely(rq->nr_running == rq->cfs.idle_h_nr_running && + rq->nr_running); +} + static unsigned long cpu_runnable_load(struct rq *rq) { return cfs_rq_runnable_load_avg(&rq->cfs); @@ -5742,7 +5707,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this unsigned int min_exit_latency = UINT_MAX; u64 latest_idle_timestamp = 0; int least_loaded_cpu = this_cpu; - int shallowest_idle_cpu = -1; + int shallowest_idle_cpu = -1, si_cpu = -1; int i; /* Check if we have any choice: */ @@ -5773,7 +5738,12 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this latest_idle_timestamp = rq->idle_stamp; shallowest_idle_cpu = i; } - } else if (shallowest_idle_cpu == -1) { + } else if (shallowest_idle_cpu == -1 && si_cpu == -1) { + if (sched_idle_cpu(i)) { + si_cpu = i; + continue; + } + load = cpu_runnable_load(cpu_rq(i)); if (load < min_load) { min_load = load; @@ -5782,7 +5752,11 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this } } - return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu; + if (shallowest_idle_cpu != -1) + return shallowest_idle_cpu; + if (si_cpu != -1) + return si_cpu; + return least_loaded_cpu; } static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p, @@ -5935,7 +5909,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int */ static int select_idle_smt(struct task_struct *p, int target) { - int cpu; + int cpu, si_cpu = -1; if (!static_branch_likely(&sched_smt_present)) return -1; @@ -5945,9 +5919,11 @@ static int select_idle_smt(struct task_struct *p, int target) continue; if (available_idle_cpu(cpu)) return cpu; + if (si_cpu == -1 && sched_idle_cpu(cpu)) + si_cpu = cpu; } - return -1; + return si_cpu; } #else /* CONFIG_SCHED_SMT */ @@ -5975,8 +5951,8 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t u64 avg_cost, avg_idle; u64 time, cost; s64 delta; - int cpu, nr = INT_MAX; int this = smp_processor_id(); + int cpu, nr = INT_MAX, si_cpu = -1; this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc)); if (!this_sd) @@ -6004,11 +5980,13 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t for_each_cpu_wrap(cpu, sched_domain_span(sd), target) { if (!--nr) - return -1; + return si_cpu; if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; if (available_idle_cpu(cpu)) break; + if (si_cpu == -1 && sched_idle_cpu(cpu)) + si_cpu = cpu; } time = cpu_clock(this) - time; @@ -6027,13 +6005,14 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) struct sched_domain *sd; int i, recent_used_cpu; - if (available_idle_cpu(target)) + if (available_idle_cpu(target) || sched_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) && available_idle_cpu(prev)) + if (prev != target && cpus_share_cache(prev, target) && + (available_idle_cpu(prev) || sched_idle_cpu(prev))) return prev; /* Check a recently used CPU as a potential idle candidate: */ @@ -6041,7 +6020,7 @@ 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) && - available_idle_cpu(recent_used_cpu) && + (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) && cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) { /* * Replace recent_used_cpu with prev as it is a potential @@ -6277,69 +6256,55 @@ static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu) } /* - * compute_energy(): Estimates the energy that would be consumed if @p was + * compute_energy(): Estimates the energy that @pd would consume if @p was * migrated to @dst_cpu. compute_energy() predicts what will be the utilization - * landscape of the * CPUs after the task migration, and uses the Energy Model + * landscape of @pd's CPUs after the task migration, and uses the Energy Model * to compute what would be the energy if we decided to actually migrate that * task. */ static long compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) { - unsigned int max_util, util_cfs, cpu_util, cpu_cap; - unsigned long sum_util, energy = 0; - struct task_struct *tsk; + struct cpumask *pd_mask = perf_domain_span(pd); + unsigned long cpu_cap = arch_scale_cpu_capacity(cpumask_first(pd_mask)); + unsigned long max_util = 0, sum_util = 0; int cpu; - for (; pd; pd = pd->next) { - struct cpumask *pd_mask = perf_domain_span(pd); + /* + * The capacity state of CPUs of the current rd can be driven by CPUs + * of another rd if they belong to the same pd. So, account for the + * utilization of these CPUs too by masking pd with cpu_online_mask + * instead of the rd span. + * + * If an entire pd is outside of the current rd, it will not appear in + * its pd list and will not be accounted by compute_energy(). + */ + for_each_cpu_and(cpu, pd_mask, cpu_online_mask) { + unsigned long cpu_util, util_cfs = cpu_util_next(cpu, p, dst_cpu); + struct task_struct *tsk = cpu == dst_cpu ? p : NULL; /* - * The energy model mandates all the CPUs of a performance - * domain have the same capacity. + * Busy time computation: utilization clamping is not + * required since the ratio (sum_util / cpu_capacity) + * is already enough to scale the EM reported power + * consumption at the (eventually clamped) cpu_capacity. */ - cpu_cap = arch_scale_cpu_capacity(cpumask_first(pd_mask)); - max_util = sum_util = 0; + sum_util += schedutil_cpu_util(cpu, util_cfs, cpu_cap, + ENERGY_UTIL, NULL); /* - * The capacity state of CPUs of the current rd can be driven by - * CPUs of another rd if they belong to the same performance - * domain. So, account for the utilization of these CPUs too - * by masking pd with cpu_online_mask instead of the rd span. - * - * If an entire performance domain is outside of the current rd, - * it will not appear in its pd list and will not be accounted - * by compute_energy(). + * Performance domain frequency: utilization clamping + * must be considered since it affects the selection + * of the performance domain frequency. + * NOTE: in case RT tasks are running, by default the + * FREQUENCY_UTIL's utilization can be max OPP. */ - for_each_cpu_and(cpu, pd_mask, cpu_online_mask) { - util_cfs = cpu_util_next(cpu, p, dst_cpu); - - /* - * Busy time computation: utilization clamping is not - * required since the ratio (sum_util / cpu_capacity) - * is already enough to scale the EM reported power - * consumption at the (eventually clamped) cpu_capacity. - */ - sum_util += schedutil_cpu_util(cpu, util_cfs, cpu_cap, - ENERGY_UTIL, NULL); - - /* - * Performance domain frequency: utilization clamping - * must be considered since it affects the selection - * of the performance domain frequency. - * NOTE: in case RT tasks are running, by default the - * FREQUENCY_UTIL's utilization can be max OPP. - */ - tsk = cpu == dst_cpu ? p : NULL; - cpu_util = schedutil_cpu_util(cpu, util_cfs, cpu_cap, - FREQUENCY_UTIL, tsk); - max_util = max(max_util, cpu_util); - } - - energy += em_pd_energy(pd->em_pd, max_util, sum_util); + cpu_util = schedutil_cpu_util(cpu, util_cfs, cpu_cap, + FREQUENCY_UTIL, tsk); + max_util = max(max_util, cpu_util); } - return energy; + return em_pd_energy(pd->em_pd, max_util, sum_util); } /* @@ -6381,21 +6346,19 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) * other use-cases too. So, until someone finds a better way to solve this, * let's keep things simple by re-using the existing slow path. */ - static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) { - unsigned long prev_energy = ULONG_MAX, best_energy = ULONG_MAX; + unsigned long prev_delta = ULONG_MAX, best_delta = ULONG_MAX; struct root_domain *rd = cpu_rq(smp_processor_id())->rd; + unsigned long cpu_cap, util, base_energy = 0; int cpu, best_energy_cpu = prev_cpu; - struct perf_domain *head, *pd; - unsigned long cpu_cap, util; struct sched_domain *sd; + struct perf_domain *pd; rcu_read_lock(); pd = rcu_dereference(rd->pd); if (!pd || READ_ONCE(rd->overutilized)) goto fail; - head = pd; /* * Energy-aware wake-up happens on the lowest sched_domain starting @@ -6412,9 +6375,14 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) goto unlock; for (; pd; pd = pd->next) { - unsigned long cur_energy, spare_cap, max_spare_cap = 0; + unsigned long cur_delta, spare_cap, max_spare_cap = 0; + unsigned long base_energy_pd; int max_spare_cap_cpu = -1; + /* Compute the 'base' energy of the pd, without @p */ + base_energy_pd = compute_energy(p, -1, pd); + base_energy += base_energy_pd; + for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) { if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; @@ -6422,14 +6390,14 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) /* Skip CPUs that will be overutilized. */ util = cpu_util_next(cpu, p, cpu); cpu_cap = capacity_of(cpu); - if (cpu_cap * 1024 < util * capacity_margin) + if (!fits_capacity(util, cpu_cap)) continue; /* Always use prev_cpu as a candidate. */ if (cpu == prev_cpu) { - prev_energy = compute_energy(p, prev_cpu, head); - best_energy = min(best_energy, prev_energy); - continue; + prev_delta = compute_energy(p, prev_cpu, pd); + prev_delta -= base_energy_pd; + best_delta = min(best_delta, prev_delta); } /* @@ -6445,9 +6413,10 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) /* Evaluate the energy impact of using this CPU. */ if (max_spare_cap_cpu >= 0) { - cur_energy = compute_energy(p, max_spare_cap_cpu, head); - if (cur_energy < best_energy) { - best_energy = cur_energy; + cur_delta = compute_energy(p, max_spare_cap_cpu, pd); + cur_delta -= base_energy_pd; + if (cur_delta < best_delta) { + best_delta = cur_delta; best_energy_cpu = max_spare_cap_cpu; } } @@ -6459,10 +6428,10 @@ unlock: * Pick the best CPU if prev_cpu cannot be used, or if it saves at * least 6% of the energy used by prev_cpu. */ - if (prev_energy == ULONG_MAX) + if (prev_delta == ULONG_MAX) return best_energy_cpu; - if ((prev_energy - best_energy) > (prev_energy >> 4)) + if ((prev_delta - best_delta) > ((prev_delta + base_energy) >> 4)) return best_energy_cpu; return prev_cpu; @@ -6796,7 +6765,7 @@ again: goto idle; #ifdef CONFIG_FAIR_GROUP_SCHED - if (prev->sched_class != &fair_sched_class) + if (!prev || prev->sched_class != &fair_sched_class) goto simple; /* @@ -6873,8 +6842,8 @@ again: goto done; simple: #endif - - put_prev_task(rq, prev); + if (prev) + put_prev_task(rq, prev); do { se = pick_next_entity(cfs_rq, NULL); @@ -6902,11 +6871,13 @@ done: __maybe_unused; return p; idle: - update_misfit_status(NULL, rq); - new_tasks = idle_balance(rq, rf); + if (!rf) + return NULL; + + new_tasks = newidle_balance(rq, rf); /* - * Because idle_balance() releases (and re-acquires) rq->lock, it is + * Because newidle_balance() releases (and re-acquires) rq->lock, it is * possible for any higher priority task to appear. In that case we * must re-start the pick_next_entity() loop. */ @@ -6928,7 +6899,7 @@ idle: /* * Account for a descheduled task: */ -static void put_prev_task_fair(struct rq *rq, struct task_struct *prev) +static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { struct sched_entity *se = &prev->se; struct cfs_rq *cfs_rq; @@ -7430,7 +7401,7 @@ static int detach_tasks(struct lb_env *env) detached++; env->imbalance -= load; -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION /* * NEWIDLE balancing is a source of latency, so preemptible * kernels will stop after the first task is detached to minimize @@ -7977,8 +7948,7 @@ group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs) static inline bool group_smaller_min_cpu_capacity(struct sched_group *sg, struct sched_group *ref) { - return sg->sgc->min_capacity * capacity_margin < - ref->sgc->min_capacity * 1024; + return fits_capacity(sg->sgc->min_capacity, ref->sgc->min_capacity); } /* @@ -7988,8 +7958,7 @@ group_smaller_min_cpu_capacity(struct sched_group *sg, struct sched_group *ref) static inline bool group_smaller_max_cpu_capacity(struct sched_group *sg, struct sched_group *ref) { - return sg->sgc->max_capacity * capacity_margin < - ref->sgc->max_capacity * 1024; + return fits_capacity(sg->sgc->max_capacity, ref->sgc->max_capacity); } static inline enum @@ -9047,9 +9016,10 @@ more_balance: out_balanced: /* * We reach balance although we may have faced some affinity - * constraints. Clear the imbalance flag if it was set. + * constraints. Clear the imbalance flag only if other tasks got + * a chance to move and fix the imbalance. */ - if (sd_parent) { + if (sd_parent && !(env.flags & LBF_ALL_PINNED)) { int *group_imbalance = &sd_parent->groups->sgc->imbalance; if (*group_imbalance) @@ -9070,10 +9040,10 @@ out_one_pinned: ld_moved = 0; /* - * idle_balance() disregards balance intervals, so we could repeatedly - * reach this code, which would lead to balance_interval skyrocketting - * in a short amount of time. Skip the balance_interval increase logic - * to avoid that. + * newidle_balance() disregards balance intervals, so we could + * repeatedly reach this code, which would lead to balance_interval + * skyrocketting in a short amount of time. Skip the balance_interval + * increase logic to avoid that. */ if (env.idle == CPU_NEWLY_IDLE) goto out; @@ -9783,7 +9753,7 @@ static inline void nohz_newidle_balance(struct rq *this_rq) { } * idle_balance is called by schedule() if this_cpu is about to become * idle. Attempts to pull tasks from other CPUs. */ -static int idle_balance(struct rq *this_rq, struct rq_flags *rf) +int newidle_balance(struct rq *this_rq, struct rq_flags *rf) { unsigned long next_balance = jiffies + HZ; int this_cpu = this_rq->cpu; @@ -9791,6 +9761,7 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf) int pulled_task = 0; u64 curr_cost = 0; + update_misfit_status(NULL, this_rq); /* * We must set idle_stamp _before_ calling idle_balance(), such that we * measure the duration of idle_balance() as idle time. @@ -10175,9 +10146,19 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p) * This routine is mostly called to set cfs_rq->curr field when a task * migrates between groups/classes. */ -static void set_curr_task_fair(struct rq *rq) +static void set_next_task_fair(struct rq *rq, struct task_struct *p) { - struct sched_entity *se = &rq->curr->se; + struct sched_entity *se = &p->se; + +#ifdef CONFIG_SMP + if (task_on_rq_queued(p)) { + /* + * Move the next running task to the front of the list, so our + * cfs_tasks list becomes MRU one. + */ + list_move(&se->group_node, &rq->cfs_tasks); + } +#endif for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); @@ -10295,18 +10276,18 @@ err: void online_fair_sched_group(struct task_group *tg) { struct sched_entity *se; + struct rq_flags rf; struct rq *rq; int i; for_each_possible_cpu(i) { rq = cpu_rq(i); se = tg->se[i]; - - raw_spin_lock_irq(&rq->lock); + rq_lock_irq(rq, &rf); update_rq_clock(rq); attach_entity_cfs_rq(se); sync_throttle(tg, i); - raw_spin_unlock_irq(&rq->lock); + rq_unlock_irq(rq, &rf); } } @@ -10448,7 +10429,9 @@ const struct sched_class fair_sched_class = { .check_preempt_curr = check_preempt_wakeup, .pick_next_task = pick_next_task_fair, + .put_prev_task = put_prev_task_fair, + .set_next_task = set_next_task_fair, #ifdef CONFIG_SMP .select_task_rq = select_task_rq_fair, @@ -10461,7 +10444,6 @@ const struct sched_class fair_sched_class = { .set_cpus_allowed = set_cpus_allowed_common, #endif - .set_curr_task = set_curr_task_fair, .task_tick = task_tick_fair, .task_fork = task_fork_fair, diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 80940939b733..c892c6280c9f 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -241,13 +241,14 @@ static void do_idle(void) check_pgt_cache(); rmb(); + local_irq_disable(); + if (cpu_is_offline(cpu)) { - tick_nohz_idle_stop_tick_protected(); + tick_nohz_idle_stop_tick(); cpuhp_report_idle_dead(); arch_cpu_idle_dead(); } - local_irq_disable(); arch_cpu_idle_enter(); /* @@ -311,7 +312,7 @@ static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer) return HRTIMER_NORESTART; } -void play_idle(unsigned long duration_ms) +void play_idle(unsigned long duration_us) { struct idle_timer it; @@ -323,7 +324,7 @@ void play_idle(unsigned long duration_ms) WARN_ON_ONCE(current->nr_cpus_allowed != 1); WARN_ON_ONCE(!(current->flags & PF_KTHREAD)); WARN_ON_ONCE(!(current->flags & PF_NO_SETAFFINITY)); - WARN_ON_ONCE(!duration_ms); + WARN_ON_ONCE(!duration_us); rcu_sleep_check(); preempt_disable(); @@ -333,7 +334,8 @@ void play_idle(unsigned long duration_ms) it.done = 0; hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); it.timer.function = idle_inject_timer_fn; - hrtimer_start(&it.timer, ms_to_ktime(duration_ms), HRTIMER_MODE_REL_PINNED); + hrtimer_start(&it.timer, ns_to_ktime(duration_us * NSEC_PER_USEC), + HRTIMER_MODE_REL_PINNED); while (!READ_ONCE(it.done)) do_idle(); @@ -374,14 +376,27 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl resched_curr(rq); } -static struct task_struct * -pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +{ +} + +static void set_next_task_idle(struct rq *rq, struct task_struct *next) { - put_prev_task(rq, prev); update_idle_core(rq); schedstat_inc(rq->sched_goidle); +} + +static struct task_struct * +pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +{ + struct task_struct *next = rq->idle; - return rq->idle; + if (prev) + put_prev_task(rq, prev); + + set_next_task_idle(rq, next); + + return next; } /* @@ -397,10 +412,6 @@ dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags) raw_spin_lock_irq(&rq->lock); } -static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) -{ -} - /* * scheduler tick hitting a task of our scheduling class. * @@ -413,10 +424,6 @@ static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued) { } -static void set_curr_task_idle(struct rq *rq) -{ -} - static void switched_to_idle(struct rq *rq, struct task_struct *p) { BUG(); @@ -451,13 +458,13 @@ const struct sched_class idle_sched_class = { .pick_next_task = pick_next_task_idle, .put_prev_task = put_prev_task_idle, + .set_next_task = set_next_task_idle, #ifdef CONFIG_SMP .select_task_rq = select_task_rq_idle, .set_cpus_allowed = set_cpus_allowed_common, #endif - .set_curr_task = set_curr_task_idle, .task_tick = task_tick_idle, .get_rr_interval = get_rr_interval_idle, diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index ccb28085b114..9fcb2a695a41 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -22,9 +22,17 @@ EXPORT_SYMBOL_GPL(housekeeping_enabled); int housekeeping_any_cpu(enum hk_flags flags) { - if (static_branch_unlikely(&housekeeping_overridden)) - if (housekeeping_flags & flags) + int cpu; + + if (static_branch_unlikely(&housekeeping_overridden)) { + if (housekeeping_flags & flags) { + cpu = sched_numa_find_closest(housekeeping_mask, smp_processor_id()); + if (cpu < nr_cpu_ids) + return cpu; + return cpumask_any_and(housekeeping_mask, cpu_online_mask); + } + } return smp_processor_id(); } EXPORT_SYMBOL_GPL(housekeeping_any_cpu); diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 6e52b67b420e..517e3719027e 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1198,7 +1198,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, if (static_branch_likely(&psi_disabled)) return -EOPNOTSUPP; - buf_size = min(nbytes, (sizeof(buf) - 1)); + buf_size = min(nbytes, sizeof(buf)); if (copy_from_user(buf, user_buf, buf_size)) return -EFAULT; diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index a532558a5176..ebaa4e619684 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -45,8 +45,8 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) raw_spin_lock_init(&rt_b->rt_runtime_lock); - hrtimer_init(&rt_b->rt_period_timer, - CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&rt_b->rt_period_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_HARD); rt_b->rt_period_timer.function = sched_rt_period_timer; } @@ -67,7 +67,8 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) * to update the period. */ hrtimer_forward_now(&rt_b->rt_period_timer, ns_to_ktime(0)); - hrtimer_start_expires(&rt_b->rt_period_timer, HRTIMER_MODE_ABS_PINNED); + hrtimer_start_expires(&rt_b->rt_period_timer, + HRTIMER_MODE_ABS_PINNED_HARD); } raw_spin_unlock(&rt_b->rt_runtime_lock); } @@ -1498,12 +1499,22 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag #endif } -static inline void set_next_task(struct rq *rq, struct task_struct *p) +static inline void set_next_task_rt(struct rq *rq, struct task_struct *p) { p->se.exec_start = rq_clock_task(rq); /* The running task is never eligible for pushing */ dequeue_pushable_task(rq, p); + + /* + * If prev task was rt, put_prev_task() has already updated the + * utilization. We only care of the case where we start to schedule a + * rt task + */ + if (rq->curr->sched_class != &rt_sched_class) + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0); + + rt_queue_push_tasks(rq); } static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq, @@ -1543,56 +1554,19 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) struct task_struct *p; struct rt_rq *rt_rq = &rq->rt; - if (need_pull_rt_task(rq, prev)) { - /* - * This is OK, because current is on_cpu, which avoids it being - * picked for load-balance and preemption/IRQs are still - * disabled avoiding further scheduler activity on it and we're - * being very careful to re-start the picking loop. - */ - rq_unpin_lock(rq, rf); - pull_rt_task(rq); - rq_repin_lock(rq, rf); - /* - * pull_rt_task() can drop (and re-acquire) rq->lock; this - * means a dl or stop task can slip in, in which case we need - * to re-start task selection. - */ - if (unlikely((rq->stop && task_on_rq_queued(rq->stop)) || - rq->dl.dl_nr_running)) - return RETRY_TASK; - } - - /* - * We may dequeue prev's rt_rq in put_prev_task(). - * So, we update time before rt_queued check. - */ - if (prev->sched_class == &rt_sched_class) - update_curr_rt(rq); + WARN_ON_ONCE(prev || rf); if (!rt_rq->rt_queued) return NULL; - put_prev_task(rq, prev); - p = _pick_next_task_rt(rq); - set_next_task(rq, p); - - rt_queue_push_tasks(rq); - - /* - * If prev task was rt, put_prev_task() has already updated the - * utilization. We only care of the case where we start to schedule a - * rt task - */ - if (rq->curr->sched_class != &rt_sched_class) - update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0); + set_next_task_rt(rq, p); return p; } -static void put_prev_task_rt(struct rq *rq, struct task_struct *p) +static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf) { update_curr_rt(rq); @@ -1604,6 +1578,18 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) */ if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); + + if (rf && !on_rt_rq(&p->rt) && need_pull_rt_task(rq, p)) { + /* + * This is OK, because current is on_cpu, which avoids it being + * picked for load-balance and preemption/IRQs are still + * disabled avoiding further scheduler activity on it and we've + * not yet started the picking loop. + */ + rq_unpin_lock(rq, rf); + pull_rt_task(rq); + rq_repin_lock(rq, rf); + } } #ifdef CONFIG_SMP @@ -2304,8 +2290,10 @@ static void watchdog(struct rq *rq, struct task_struct *p) } next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ); - if (p->rt.timeout > next) - p->cputime_expires.sched_exp = p->se.sum_exec_runtime; + if (p->rt.timeout > next) { + posix_cputimers_rt_watchdog(&p->posix_cputimers, + p->se.sum_exec_runtime); + } } } #else @@ -2354,11 +2342,6 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) } } -static void set_curr_task_rt(struct rq *rq) -{ - set_next_task(rq, rq->curr); -} - static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task) { /* @@ -2380,6 +2363,7 @@ const struct sched_class rt_sched_class = { .pick_next_task = pick_next_task_rt, .put_prev_task = put_prev_task_rt, + .set_next_task = set_next_task_rt, #ifdef CONFIG_SMP .select_task_rq = select_task_rq_rt, @@ -2391,7 +2375,6 @@ const struct sched_class rt_sched_class = { .switched_from = switched_from_rt, #endif - .set_curr_task = set_curr_task_rt, .task_tick = task_tick_rt, .get_rr_interval = get_rr_interval_rt, diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 802b1f3405f2..b3cb895d14a2 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -335,8 +335,6 @@ struct cfs_bandwidth { u64 quota; u64 runtime; s64 hierarchical_quota; - u64 runtime_expires; - int expires_seq; u8 idle; u8 period_active; @@ -393,6 +391,16 @@ struct task_group { #endif struct cfs_bandwidth cfs_bandwidth; + +#ifdef CONFIG_UCLAMP_TASK_GROUP + /* The two decimal precision [%] value requested from user-space */ + unsigned int uclamp_pct[UCLAMP_CNT]; + /* Clamp values requested for a task group */ + struct uclamp_se uclamp_req[UCLAMP_CNT]; + /* Effective clamp values used for a task group */ + struct uclamp_se uclamp[UCLAMP_CNT]; +#endif + }; #ifdef CONFIG_FAIR_GROUP_SCHED @@ -483,7 +491,8 @@ struct cfs_rq { struct load_weight load; unsigned long runnable_weight; unsigned int nr_running; - unsigned int h_nr_running; + unsigned int h_nr_running; /* SCHED_{NORMAL,BATCH,IDLE} */ + unsigned int idle_h_nr_running; /* SCHED_IDLE */ u64 exec_clock; u64 min_vruntime; @@ -556,8 +565,6 @@ struct cfs_rq { #ifdef CONFIG_CFS_BANDWIDTH int runtime_enabled; - int expires_seq; - u64 runtime_expires; s64 runtime_remaining; u64 throttled_clock; @@ -777,9 +784,6 @@ struct root_domain { struct perf_domain __rcu *pd; }; -extern struct root_domain def_root_domain; -extern struct mutex sched_domains_mutex; - extern void init_defrootdomain(void); extern int sched_init_domains(const struct cpumask *cpu_map); extern void rq_attach_root(struct rq *rq, struct root_domain *rd); @@ -1261,16 +1265,18 @@ enum numa_topology_type { extern enum numa_topology_type sched_numa_topology_type; extern int sched_max_numa_distance; extern bool find_numa_distance(int distance); -#endif - -#ifdef CONFIG_NUMA extern void sched_init_numa(void); extern void sched_domains_numa_masks_set(unsigned int cpu); extern void sched_domains_numa_masks_clear(unsigned int cpu); +extern int sched_numa_find_closest(const struct cpumask *cpus, int cpu); #else static inline void sched_init_numa(void) { } static inline void sched_domains_numa_masks_set(unsigned int cpu) { } static inline void sched_domains_numa_masks_clear(unsigned int cpu) { } +static inline int sched_numa_find_closest(const struct cpumask *cpus, int cpu) +{ + return nr_cpu_ids; +} #endif #ifdef CONFIG_NUMA_BALANCING @@ -1449,10 +1455,14 @@ static inline void unregister_sched_domain_sysctl(void) } #endif +extern int newidle_balance(struct rq *this_rq, struct rq_flags *rf); + #else static inline void sched_ttwu_pending(void) { } +static inline int newidle_balance(struct rq *this_rq, struct rq_flags *rf) { return 0; } + #endif /* CONFIG_SMP */ #include "stats.h" @@ -1700,17 +1710,21 @@ struct sched_class { void (*check_preempt_curr)(struct rq *rq, struct task_struct *p, int flags); /* - * It is the responsibility of the pick_next_task() method that will - * return the next task to call put_prev_task() on the @prev task or - * something equivalent. + * Both @prev and @rf are optional and may be NULL, in which case the + * caller must already have invoked put_prev_task(rq, prev, rf). + * + * Otherwise it is the responsibility of the pick_next_task() to call + * put_prev_task() on the @prev task or something equivalent, IFF it + * returns a next task. * - * May return RETRY_TASK when it finds a higher prio class has runnable - * tasks. + * In that case (@rf != NULL) it may return RETRY_TASK when it finds a + * higher prio class has runnable tasks. */ struct task_struct * (*pick_next_task)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf); - void (*put_prev_task)(struct rq *rq, struct task_struct *p); + void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct rq_flags *rf); + void (*set_next_task)(struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags); @@ -1725,7 +1739,6 @@ struct sched_class { void (*rq_offline)(struct rq *rq); #endif - void (*set_curr_task)(struct rq *rq); void (*task_tick)(struct rq *rq, struct task_struct *p, int queued); void (*task_fork)(struct task_struct *p); void (*task_dead)(struct task_struct *p); @@ -1755,12 +1768,14 @@ struct sched_class { static inline void put_prev_task(struct rq *rq, struct task_struct *prev) { - prev->sched_class->put_prev_task(rq, prev); + WARN_ON_ONCE(rq->curr != prev); + prev->sched_class->put_prev_task(rq, prev, NULL); } -static inline void set_curr_task(struct rq *rq, struct task_struct *curr) +static inline void set_next_task(struct rq *rq, struct task_struct *next) { - curr->sched_class->set_curr_task(rq); + WARN_ON_ONCE(rq->curr != next); + next->sched_class->set_next_task(rq, next); } #ifdef CONFIG_SMP @@ -1943,7 +1958,7 @@ unsigned long arch_scale_freq_capacity(int cpu) #endif #ifdef CONFIG_SMP -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION static inline void double_rq_lock(struct rq *rq1, struct rq *rq2); @@ -1995,7 +2010,7 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest) return ret; } -#endif /* CONFIG_PREEMPT */ +#endif /* CONFIG_PREEMPTION */ /* * double_lock_balance - lock the busiest runqueue, this_rq is locked already. @@ -2266,7 +2281,7 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {} #endif /* CONFIG_CPU_FREQ */ #ifdef CONFIG_UCLAMP_TASK -unsigned int uclamp_eff_value(struct task_struct *p, unsigned int clamp_id); +enum uclamp_id uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id); static __always_inline unsigned int uclamp_util_with(struct rq *rq, unsigned int util, diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index aa0de240fb41..ba683fe81a6e 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -157,9 +157,10 @@ static inline void sched_info_dequeued(struct rq *rq, struct task_struct *t) { unsigned long long now = rq_clock(rq), delta = 0; - if (unlikely(sched_info_on())) + if (sched_info_on()) { if (t->sched_info.last_queued) delta = now - t->sched_info.last_queued; + } sched_info_reset_dequeued(t); t->sched_info.run_delay += delta; @@ -192,7 +193,7 @@ static void sched_info_arrive(struct rq *rq, struct task_struct *t) */ static inline void sched_info_queued(struct rq *rq, struct task_struct *t) { - if (unlikely(sched_info_on())) { + if (sched_info_on()) { if (!t->sched_info.last_queued) t->sched_info.last_queued = rq_clock(rq); } @@ -239,7 +240,7 @@ __sched_info_switch(struct rq *rq, struct task_struct *prev, struct task_struct static inline void sched_info_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next) { - if (unlikely(sched_info_on())) + if (sched_info_on()) __sched_info_switch(rq, prev, next); } diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index c183b790ca54..7e1cee4e65b2 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -23,17 +23,22 @@ check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags) /* we're never preempted */ } +static void set_next_task_stop(struct rq *rq, struct task_struct *stop) +{ + stop->se.exec_start = rq_clock_task(rq); +} + static struct task_struct * pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { struct task_struct *stop = rq->stop; + WARN_ON_ONCE(prev || rf); + if (!stop || !task_on_rq_queued(stop)) return NULL; - put_prev_task(rq, prev); - - stop->se.exec_start = rq_clock_task(rq); + set_next_task_stop(rq, stop); return stop; } @@ -55,7 +60,7 @@ static void yield_task_stop(struct rq *rq) BUG(); /* the stop task should never yield, its pointless. */ } -static void put_prev_task_stop(struct rq *rq, struct task_struct *prev) +static void put_prev_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { struct task_struct *curr = rq->curr; u64 delta_exec; @@ -86,13 +91,6 @@ static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued) { } -static void set_curr_task_stop(struct rq *rq) -{ - struct task_struct *stop = rq->stop; - - stop->se.exec_start = rq_clock_task(rq); -} - static void switched_to_stop(struct rq *rq, struct task_struct *p) { BUG(); /* its impossible to change to this class */ @@ -128,13 +126,13 @@ const struct sched_class stop_sched_class = { .pick_next_task = pick_next_task_stop, .put_prev_task = put_prev_task_stop, + .set_next_task = set_next_task_stop, #ifdef CONFIG_SMP .select_task_rq = select_task_rq_stop, .set_cpus_allowed = set_cpus_allowed_common, #endif - .set_curr_task = set_curr_task_stop, .task_tick = task_tick_stop, .get_rr_interval = get_rr_interval_stop, diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index f751ce0b783e..b5667a273bf6 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1284,6 +1284,7 @@ static int sched_domains_curr_level; int sched_max_numa_distance; static int *sched_domains_numa_distance; static struct cpumask ***sched_domains_numa_masks; +int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE; #endif /* @@ -1402,7 +1403,7 @@ sd_init(struct sched_domain_topology_level *tl, sd->flags &= ~SD_PREFER_SIBLING; sd->flags |= SD_SERIALIZE; - if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) { + if (sched_domains_numa_distance[tl->numa_level] > node_reclaim_distance) { sd->flags &= ~(SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE); @@ -1724,6 +1725,26 @@ void sched_domains_numa_masks_clear(unsigned int cpu) } } +/* + * sched_numa_find_closest() - given the NUMA topology, find the cpu + * closest to @cpu from @cpumask. + * cpumask: cpumask to find a cpu from + * cpu: cpu to be close to + * + * returns: cpu, or nr_cpu_ids when nothing found. + */ +int sched_numa_find_closest(const struct cpumask *cpus, int cpu) +{ + int i, j = cpu_to_node(cpu); + + for (i = 0; i < sched_domains_numa_levels; i++) { + cpu = cpumask_any_and(cpus, sched_domains_numa_masks[i][j]); + if (cpu < nr_cpu_ids) + return cpu; + } + return nr_cpu_ids; +} + #endif /* CONFIG_NUMA */ static int __sdt_alloc(const struct cpumask *cpu_map) @@ -2149,16 +2170,16 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, * ndoms_new == 0 is a special case for destroying existing domains, * and it will not create the default domain. * - * Call with hotplug lock held + * Call with hotplug lock and sched_domains_mutex held */ -void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], - struct sched_domain_attr *dattr_new) +void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) { bool __maybe_unused has_eas = false; int i, j, n; int new_topology; - mutex_lock(&sched_domains_mutex); + lockdep_assert_held(&sched_domains_mutex); /* Always unregister in case we don't destroy any domains: */ unregister_sched_domain_sysctl(); @@ -2183,8 +2204,19 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], for (i = 0; i < ndoms_cur; i++) { for (j = 0; j < n && !new_topology; j++) { if (cpumask_equal(doms_cur[i], doms_new[j]) && - dattrs_equal(dattr_cur, i, dattr_new, j)) + dattrs_equal(dattr_cur, i, dattr_new, j)) { + struct root_domain *rd; + + /* + * This domain won't be destroyed and as such + * its dl_bw->total_bw needs to be cleared. It + * will be recomputed in function + * update_tasks_root_domain(). + */ + rd = cpu_rq(cpumask_any(doms_cur[i]))->rd; + dl_clear_root_domain(rd); goto match1; + } } /* No match - a current sched domain not in new doms_new[] */ detach_destroy_domains(doms_cur[i]); @@ -2241,6 +2273,15 @@ match3: ndoms_cur = ndoms_new; register_sched_domain_sysctl(); +} +/* + * Call with hotplug lock held + */ +void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) +{ + mutex_lock(&sched_domains_mutex); + partition_sched_domains_locked(ndoms_new, doms_new, dattr_new); mutex_unlock(&sched_domains_mutex); } diff --git a/kernel/signal.c b/kernel/signal.c index 534fec266a33..c4da1ef56fdf 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3678,8 +3678,11 @@ static int copy_siginfo_from_user_any(kernel_siginfo_t *kinfo, siginfo_t *info) static struct pid *pidfd_to_pid(const struct file *file) { - if (file->f_op == &pidfd_fops) - return file->private_data; + struct pid *pid; + + pid = pidfd_pid(file); + if (!IS_ERR(pid)) + return pid; return tgid_pidfd_to_pid(file); } diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c index f5440abb7532..6d1f68b7e528 100644 --- a/kernel/stacktrace.c +++ b/kernel/stacktrace.c @@ -20,7 +20,7 @@ * @nr_entries: Number of entries in the storage array * @spaces: Number of leading spaces to print */ -void stack_trace_print(unsigned long *entries, unsigned int nr_entries, +void stack_trace_print(const unsigned long *entries, unsigned int nr_entries, int spaces) { unsigned int i; @@ -43,7 +43,7 @@ EXPORT_SYMBOL_GPL(stack_trace_print); * * Return: Number of bytes printed. */ -int stack_trace_snprint(char *buf, size_t size, unsigned long *entries, +int stack_trace_snprint(char *buf, size_t size, const unsigned long *entries, unsigned int nr_entries, int spaces) { unsigned int generated, i, total = 0; diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index b4f83f7bdf86..c7031a22aa7b 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -383,6 +383,7 @@ static bool queue_stop_cpus_work(const struct cpumask *cpumask, */ preempt_disable(); stop_cpus_in_progress = true; + barrier(); for_each_cpu(cpu, cpumask) { work = &per_cpu(cpu_stopper.stop_work, cpu); work->fn = fn; @@ -391,6 +392,7 @@ static bool queue_stop_cpus_work(const struct cpumask *cpumask, if (cpu_stop_queue_work(cpu, work)) queued = true; } + barrier(); stop_cpus_in_progress = false; preempt_enable(); diff --git a/kernel/sys.c b/kernel/sys.c index 2969304c29fe..a611d1d58c7d 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -103,12 +103,6 @@ #ifndef SET_TSC_CTL # define SET_TSC_CTL(a) (-EINVAL) #endif -#ifndef MPX_ENABLE_MANAGEMENT -# define MPX_ENABLE_MANAGEMENT() (-EINVAL) -#endif -#ifndef MPX_DISABLE_MANAGEMENT -# define MPX_DISABLE_MANAGEMENT() (-EINVAL) -#endif #ifndef GET_FP_MODE # define GET_FP_MODE(a) (-EINVAL) #endif @@ -124,6 +118,12 @@ #ifndef PAC_RESET_KEYS # define PAC_RESET_KEYS(a, b) (-EINVAL) #endif +#ifndef SET_TAGGED_ADDR_CTRL +# define SET_TAGGED_ADDR_CTRL(a) (-EINVAL) +#endif +#ifndef GET_TAGGED_ADDR_CTRL +# define GET_TAGGED_ADDR_CTRL() (-EINVAL) +#endif /* * this is where the system-wide overflow UID and GID are defined, for @@ -1557,15 +1557,6 @@ int do_prlimit(struct task_struct *tsk, unsigned int resource, retval = -EPERM; if (!retval) retval = security_task_setrlimit(tsk, resource, new_rlim); - if (resource == RLIMIT_CPU && new_rlim->rlim_cur == 0) { - /* - * The caller is asking for an immediate RLIMIT_CPU - * expiry. But we use the zero value to mean "it was - * never set". So let's cheat and make it one second - * instead - */ - new_rlim->rlim_cur = 1; - } } if (!retval) { if (old_rlim) @@ -1576,10 +1567,9 @@ int do_prlimit(struct task_struct *tsk, unsigned int resource, task_unlock(tsk->group_leader); /* - * RLIMIT_CPU handling. Note that the kernel fails to return an error - * code if it rejected the user's attempt to set RLIMIT_CPU. This is a - * very long-standing error, and fixing it now risks breakage of - * applications, so we live with it + * RLIMIT_CPU handling. Arm the posix CPU timer if the limit is not + * infite. In case of RLIM_INFINITY the posix CPU timer code + * ignores the rlimit. */ if (!retval && new_rlim && resource == RLIMIT_CPU && new_rlim->rlim_cur != RLIM_INFINITY && @@ -2456,15 +2446,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, up_write(&me->mm->mmap_sem); break; case PR_MPX_ENABLE_MANAGEMENT: - if (arg2 || arg3 || arg4 || arg5) - return -EINVAL; - error = MPX_ENABLE_MANAGEMENT(); - break; case PR_MPX_DISABLE_MANAGEMENT: - if (arg2 || arg3 || arg4 || arg5) - return -EINVAL; - error = MPX_DISABLE_MANAGEMENT(); - break; + /* No longer implemented: */ + return -EINVAL; case PR_SET_FP_MODE: error = SET_FP_MODE(me, arg2); break; @@ -2492,6 +2476,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, return -EINVAL; error = PAC_RESET_KEYS(me, arg2); break; + case PR_SET_TAGGED_ADDR_CTRL: + if (arg3 || arg4 || arg5) + return -EINVAL; + error = SET_TAGGED_ADDR_CTRL(arg2); + break; + case PR_GET_TAGGED_ADDR_CTRL: + if (arg2 || arg3 || arg4 || arg5) + return -EINVAL; + error = GET_TAGGED_ADDR_CTRL(); + break; default: error = -EINVAL; break; diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 57518efc3810..451f9d05ccfe 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -97,7 +97,7 @@ static int alarmtimer_rtc_add_device(struct device *dev, if (!device_may_wakeup(rtc->dev.parent)) return -1; - __ws = wakeup_source_register("alarmtimer"); + __ws = wakeup_source_register(dev, "alarmtimer"); spin_lock_irqsave(&rtcdev_lock, flags); if (!rtcdev) { @@ -432,7 +432,7 @@ int alarm_cancel(struct alarm *alarm) int ret = alarm_try_to_cancel(alarm); if (ret >= 0) return ret; - cpu_relax(); + hrtimer_cancel_wait_running(&alarm->timer); } } EXPORT_SYMBOL_GPL(alarm_cancel); @@ -606,6 +606,19 @@ static int alarm_timer_try_to_cancel(struct k_itimer *timr) } /** + * alarm_timer_wait_running - Posix timer callback to wait for a timer + * @timr: Pointer to the posixtimer data struct + * + * Called from the core code when timer cancel detected that the callback + * is running. @timr is unlocked and rcu read lock is held to prevent it + * from being freed. + */ +static void alarm_timer_wait_running(struct k_itimer *timr) +{ + hrtimer_cancel_wait_running(&timr->it.alarm.alarmtimer.timer); +} + +/** * alarm_timer_arm - Posix timer callback to arm a timer * @timr: Pointer to the posixtimer data struct * @expires: The new expiry time @@ -672,7 +685,7 @@ static int alarm_timer_create(struct k_itimer *new_timer) enum alarmtimer_type type; if (!alarmtimer_get_rtcdev()) - return -ENOTSUPP; + return -EOPNOTSUPP; if (!capable(CAP_WAKE_ALARM)) return -EPERM; @@ -790,7 +803,7 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, int ret = 0; if (!alarmtimer_get_rtcdev()) - return -ENOTSUPP; + return -EOPNOTSUPP; if (flags & ~TIMER_ABSTIME) return -EINVAL; @@ -834,6 +847,7 @@ const struct k_clock alarm_clock = { .timer_forward = alarm_timer_forward, .timer_remaining = alarm_timer_remaining, .timer_try_to_cancel = alarm_timer_try_to_cancel, + .timer_wait_running = alarm_timer_wait_running, .nsleep = alarm_timer_nsleep, }; #endif /* CONFIG_POSIX_TIMERS */ diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 5ee77f1a8a92..0d4dc241c0fb 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -140,6 +140,11 @@ static struct hrtimer_cpu_base migration_cpu_base = { #define migration_base migration_cpu_base.clock_base[0] +static inline bool is_migration_base(struct hrtimer_clock_base *base) +{ + return base == &migration_base; +} + /* * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock * means that all timers which are tied to this base via timer->base are @@ -264,6 +269,11 @@ again: #else /* CONFIG_SMP */ +static inline bool is_migration_base(struct hrtimer_clock_base *base) +{ + return false; +} + static inline struct hrtimer_clock_base * lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) { @@ -427,6 +437,17 @@ void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t clock_id, } EXPORT_SYMBOL_GPL(hrtimer_init_on_stack); +static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, + clockid_t clock_id, enum hrtimer_mode mode); + +void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, + clockid_t clock_id, enum hrtimer_mode mode) +{ + debug_object_init_on_stack(&sl->timer, &hrtimer_debug_descr); + __hrtimer_init_sleeper(sl, clock_id, mode); +} +EXPORT_SYMBOL_GPL(hrtimer_init_sleeper_on_stack); + void destroy_hrtimer_on_stack(struct hrtimer *timer) { debug_object_free(timer, &hrtimer_debug_descr); @@ -1096,9 +1117,13 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, /* * Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft - * match. + * match on CONFIG_PREEMPT_RT = n. With PREEMPT_RT check the hard + * expiry mode because unmarked timers are moved to softirq expiry. */ - WARN_ON_ONCE(!(mode & HRTIMER_MODE_SOFT) ^ !timer->is_soft); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + WARN_ON_ONCE(!(mode & HRTIMER_MODE_SOFT) ^ !timer->is_soft); + else + WARN_ON_ONCE(!(mode & HRTIMER_MODE_HARD) ^ !timer->is_hard); base = lock_hrtimer_base(timer, &flags); @@ -1147,6 +1172,93 @@ int hrtimer_try_to_cancel(struct hrtimer *timer) } EXPORT_SYMBOL_GPL(hrtimer_try_to_cancel); +#ifdef CONFIG_PREEMPT_RT +static void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) +{ + spin_lock_init(&base->softirq_expiry_lock); +} + +static void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) +{ + spin_lock(&base->softirq_expiry_lock); +} + +static void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) +{ + spin_unlock(&base->softirq_expiry_lock); +} + +/* + * The counterpart to hrtimer_cancel_wait_running(). + * + * If there is a waiter for cpu_base->expiry_lock, then it was waiting for + * the timer callback to finish. Drop expiry_lock and reaquire it. That + * allows the waiter to acquire the lock and make progress. + */ +static void hrtimer_sync_wait_running(struct hrtimer_cpu_base *cpu_base, + unsigned long flags) +{ + if (atomic_read(&cpu_base->timer_waiters)) { + raw_spin_unlock_irqrestore(&cpu_base->lock, flags); + spin_unlock(&cpu_base->softirq_expiry_lock); + spin_lock(&cpu_base->softirq_expiry_lock); + raw_spin_lock_irq(&cpu_base->lock); + } +} + +/* + * This function is called on PREEMPT_RT kernels when the fast path + * deletion of a timer failed because the timer callback function was + * running. + * + * This prevents priority inversion: if the soft irq thread is preempted + * in the middle of a timer callback, then calling del_timer_sync() can + * lead to two issues: + * + * - If the caller is on a remote CPU then it has to spin wait for the timer + * handler to complete. This can result in unbound priority inversion. + * + * - If the caller originates from the task which preempted the timer + * handler on the same CPU, then spin waiting for the timer handler to + * complete is never going to end. + */ +void hrtimer_cancel_wait_running(const struct hrtimer *timer) +{ + /* Lockless read. Prevent the compiler from reloading it below */ + struct hrtimer_clock_base *base = READ_ONCE(timer->base); + + /* + * Just relax if the timer expires in hard interrupt context or if + * it is currently on the migration base. + */ + if (!timer->is_soft || is_migration_base(base)) { + cpu_relax(); + return; + } + + /* + * Mark the base as contended and grab the expiry lock, which is + * held by the softirq across the timer callback. Drop the lock + * immediately so the softirq can expire the next timer. In theory + * the timer could already be running again, but that's more than + * unlikely and just causes another wait loop. + */ + atomic_inc(&base->cpu_base->timer_waiters); + spin_lock_bh(&base->cpu_base->softirq_expiry_lock); + atomic_dec(&base->cpu_base->timer_waiters); + spin_unlock_bh(&base->cpu_base->softirq_expiry_lock); +} +#else +static inline void +hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) { } +static inline void +hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) { } +static inline void +hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) { } +static inline void hrtimer_sync_wait_running(struct hrtimer_cpu_base *base, + unsigned long flags) { } +#endif + /** * hrtimer_cancel - cancel a timer and wait for the handler to finish. * @timer: the timer to be cancelled @@ -1157,13 +1269,15 @@ EXPORT_SYMBOL_GPL(hrtimer_try_to_cancel); */ int hrtimer_cancel(struct hrtimer *timer) { - for (;;) { - int ret = hrtimer_try_to_cancel(timer); + int ret; - if (ret >= 0) - return ret; - cpu_relax(); - } + do { + ret = hrtimer_try_to_cancel(timer); + + if (ret < 0) + hrtimer_cancel_wait_running(timer); + } while (ret < 0); + return ret; } EXPORT_SYMBOL_GPL(hrtimer_cancel); @@ -1260,8 +1374,17 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { bool softtimer = !!(mode & HRTIMER_MODE_SOFT); - int base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0; struct hrtimer_cpu_base *cpu_base; + int base; + + /* + * On PREEMPT_RT enabled kernels hrtimers which are not explicitely + * marked for hard interrupt expiry mode are moved into soft + * interrupt context for latency reasons and because the callbacks + * can invoke functions which might sleep on RT, e.g. spin_lock(). + */ + if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(mode & HRTIMER_MODE_HARD)) + softtimer = true; memset(timer, 0, sizeof(struct hrtimer)); @@ -1275,8 +1398,10 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, if (clock_id == CLOCK_REALTIME && mode & HRTIMER_MODE_REL) clock_id = CLOCK_MONOTONIC; + base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0; base += hrtimer_clockid_to_base(clock_id); timer->is_soft = softtimer; + timer->is_hard = !softtimer; timer->base = &cpu_base->clock_base[base]; timerqueue_init(&timer->node); } @@ -1449,6 +1574,8 @@ static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now, break; __run_hrtimer(cpu_base, base, timer, &basenow, flags); + if (active_mask == HRTIMER_ACTIVE_SOFT) + hrtimer_sync_wait_running(cpu_base, flags); } } } @@ -1459,6 +1586,7 @@ static __latent_entropy void hrtimer_run_softirq(struct softirq_action *h) unsigned long flags; ktime_t now; + hrtimer_cpu_base_lock_expiry(cpu_base); raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); @@ -1468,6 +1596,7 @@ static __latent_entropy void hrtimer_run_softirq(struct softirq_action *h) hrtimer_update_softirq_timer(cpu_base, true); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); + hrtimer_cpu_base_unlock_expiry(cpu_base); } #ifdef CONFIG_HIGH_RES_TIMERS @@ -1639,10 +1768,75 @@ static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer) return HRTIMER_NORESTART; } -void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task) +/** + * hrtimer_sleeper_start_expires - Start a hrtimer sleeper timer + * @sl: sleeper to be started + * @mode: timer mode abs/rel + * + * Wrapper around hrtimer_start_expires() for hrtimer_sleeper based timers + * to allow PREEMPT_RT to tweak the delivery mode (soft/hardirq context) + */ +void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl, + enum hrtimer_mode mode) +{ + /* + * Make the enqueue delivery mode check work on RT. If the sleeper + * was initialized for hard interrupt delivery, force the mode bit. + * This is a special case for hrtimer_sleepers because + * hrtimer_init_sleeper() determines the delivery mode on RT so the + * fiddling with this decision is avoided at the call sites. + */ + if (IS_ENABLED(CONFIG_PREEMPT_RT) && sl->timer.is_hard) + mode |= HRTIMER_MODE_HARD; + + hrtimer_start_expires(&sl->timer, mode); +} +EXPORT_SYMBOL_GPL(hrtimer_sleeper_start_expires); + +static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, + clockid_t clock_id, enum hrtimer_mode mode) { + /* + * On PREEMPT_RT enabled kernels hrtimers which are not explicitely + * marked for hard interrupt expiry mode are moved into soft + * interrupt context either for latency reasons or because the + * hrtimer callback takes regular spinlocks or invokes other + * functions which are not suitable for hard interrupt context on + * PREEMPT_RT. + * + * The hrtimer_sleeper callback is RT compatible in hard interrupt + * context, but there is a latency concern: Untrusted userspace can + * spawn many threads which arm timers for the same expiry time on + * the same CPU. That causes a latency spike due to the wakeup of + * a gazillion threads. + * + * OTOH, priviledged real-time user space applications rely on the + * low latency of hard interrupt wakeups. If the current task is in + * a real-time scheduling class, mark the mode for hard interrupt + * expiry. + */ + if (IS_ENABLED(CONFIG_PREEMPT_RT)) { + if (task_is_realtime(current) && !(mode & HRTIMER_MODE_SOFT)) + mode |= HRTIMER_MODE_HARD; + } + + __hrtimer_init(&sl->timer, clock_id, mode); sl->timer.function = hrtimer_wakeup; - sl->task = task; + sl->task = current; +} + +/** + * hrtimer_init_sleeper - initialize sleeper to the given clock + * @sl: sleeper to be initialized + * @clock_id: the clock to be used + * @mode: timer mode abs/rel + */ +void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, + enum hrtimer_mode mode) +{ + debug_init(&sl->timer, clock_id, mode); + __hrtimer_init_sleeper(sl, clock_id, mode); + } EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); @@ -1669,11 +1863,9 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod { struct restart_block *restart; - hrtimer_init_sleeper(t, current); - do { set_current_state(TASK_INTERRUPTIBLE); - hrtimer_start_expires(&t->timer, mode); + hrtimer_sleeper_start_expires(t, mode); if (likely(t->task)) freezable_schedule(); @@ -1707,10 +1899,9 @@ static long __sched hrtimer_nanosleep_restart(struct restart_block *restart) struct hrtimer_sleeper t; int ret; - hrtimer_init_on_stack(&t.timer, restart->nanosleep.clockid, - HRTIMER_MODE_ABS); + hrtimer_init_sleeper_on_stack(&t, restart->nanosleep.clockid, + HRTIMER_MODE_ABS); hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); - ret = do_nanosleep(&t, HRTIMER_MODE_ABS); destroy_hrtimer_on_stack(&t.timer); return ret; @@ -1728,7 +1919,7 @@ long hrtimer_nanosleep(const struct timespec64 *rqtp, if (dl_task(current) || rt_task(current)) slack = 0; - hrtimer_init_on_stack(&t.timer, clockid, mode); + hrtimer_init_sleeper_on_stack(&t, clockid, mode); hrtimer_set_expires_range_ns(&t.timer, timespec64_to_ktime(*rqtp), slack); ret = do_nanosleep(&t, mode); if (ret != -ERESTART_RESTARTBLOCK) @@ -1809,6 +2000,7 @@ int hrtimers_prepare_cpu(unsigned int cpu) cpu_base->softirq_next_timer = NULL; cpu_base->expires_next = KTIME_MAX; cpu_base->softirq_expires_next = KTIME_MAX; + hrtimer_cpu_base_init_expiry_lock(cpu_base); return 0; } @@ -1927,12 +2119,9 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, return -EINTR; } - hrtimer_init_on_stack(&t.timer, clock_id, mode); + hrtimer_init_sleeper_on_stack(&t, clock_id, mode); hrtimer_set_expires_range_ns(&t.timer, *expires, delta); - - hrtimer_init_sleeper(&t, current); - - hrtimer_start_expires(&t.timer, mode); + hrtimer_sleeper_start_expires(&t, mode); if (likely(t.task)) schedule(); diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c index 02068b2d5862..77f1e5635cc1 100644 --- a/kernel/time/itimer.c +++ b/kernel/time/itimer.c @@ -55,15 +55,10 @@ static void get_cpu_itimer(struct task_struct *tsk, unsigned int clock_id, val = it->expires; interval = it->incr; if (val) { - struct task_cputime cputime; - u64 t; + u64 t, samples[CPUCLOCK_MAX]; - thread_group_cputimer(tsk, &cputime); - if (clock_id == CPUCLOCK_PROF) - t = cputime.utime + cputime.stime; - else - /* CPUCLOCK_VIRT */ - t = cputime.utime; + thread_group_sample_cputime(tsk, samples); + t = samples[clock_id]; if (val < t) /* about to fire */ @@ -213,6 +208,7 @@ again: /* We are sharing ->siglock with it_real_fn() */ if (hrtimer_try_to_cancel(timer) < 0) { spin_unlock_irq(&tsk->sighand->siglock); + hrtimer_cancel_wait_running(timer); goto again; } expires = timeval_to_ktime(value->it_value); diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 0a426f4e3125..92a431981b1c 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -20,11 +20,20 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer); +void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit) +{ + posix_cputimers_init(pct); + if (cpu_limit != RLIM_INFINITY) { + pct->bases[CPUCLOCK_PROF].nextevt = cpu_limit * NSEC_PER_SEC; + pct->timers_active = true; + } +} + /* * Called after updating RLIMIT_CPU to run cpu timer and update - * tsk->signal->cputime_expires expiration cache if necessary. Needs - * siglock protection since other code may update expiration cache as - * well. + * tsk->signal->posix_cputimers.bases[clock].nextevt expiration cache if + * necessary. Needs siglock protection since other code may update the + * expiration cache as well. */ void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new) { @@ -35,46 +44,97 @@ void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new) spin_unlock_irq(&task->sighand->siglock); } -static int check_clock(const clockid_t which_clock) +/* + * Functions for validating access to tasks. + */ +static struct task_struct *lookup_task(const pid_t pid, bool thread, + bool gettime) { - int error = 0; struct task_struct *p; - const pid_t pid = CPUCLOCK_PID(which_clock); - - if (CPUCLOCK_WHICH(which_clock) >= CPUCLOCK_MAX) - return -EINVAL; - if (pid == 0) - return 0; + /* + * If the encoded PID is 0, then the timer is targeted at current + * or the process to which current belongs. + */ + if (!pid) + return thread ? current : current->group_leader; - rcu_read_lock(); p = find_task_by_vpid(pid); - if (!p || !(CPUCLOCK_PERTHREAD(which_clock) ? - same_thread_group(p, current) : has_group_leader_pid(p))) { - error = -EINVAL; + if (!p) + return p; + + if (thread) + return same_thread_group(p, current) ? p : NULL; + + if (gettime) { + /* + * For clock_gettime(PROCESS) the task does not need to be + * the actual group leader. tsk->sighand gives + * access to the group's clock. + * + * Timers need the group leader because they take a + * reference on it and store the task pointer until the + * timer is destroyed. + */ + return (p == current || thread_group_leader(p)) ? p : NULL; } + + /* + * For processes require that p is group leader. + */ + return has_group_leader_pid(p) ? p : NULL; +} + +static struct task_struct *__get_task_for_clock(const clockid_t clock, + bool getref, bool gettime) +{ + const bool thread = !!CPUCLOCK_PERTHREAD(clock); + const pid_t pid = CPUCLOCK_PID(clock); + struct task_struct *p; + + if (CPUCLOCK_WHICH(clock) >= CPUCLOCK_MAX) + return NULL; + + rcu_read_lock(); + p = lookup_task(pid, thread, gettime); + if (p && getref) + get_task_struct(p); rcu_read_unlock(); + return p; +} - return error; +static inline struct task_struct *get_task_for_clock(const clockid_t clock) +{ + return __get_task_for_clock(clock, true, false); +} + +static inline struct task_struct *get_task_for_clock_get(const clockid_t clock) +{ + return __get_task_for_clock(clock, true, true); +} + +static inline int validate_clock_permissions(const clockid_t clock) +{ + return __get_task_for_clock(clock, false, false) ? 0 : -EINVAL; } /* * Update expiry time from increment, and increase overrun count, * given the current clock sample. */ -static void bump_cpu_timer(struct k_itimer *timer, u64 now) +static u64 bump_cpu_timer(struct k_itimer *timer, u64 now) { + u64 delta, incr, expires = timer->it.cpu.node.expires; int i; - u64 delta, incr; if (!timer->it_interval) - return; + return expires; - if (now < timer->it.cpu.expires) - return; + if (now < expires) + return expires; incr = timer->it_interval; - delta = now + incr - timer->it.cpu.expires; + delta = now + incr - expires; /* Don't use (incr*2 < delta), incr*2 might overflow. */ for (i = 0; incr < delta - incr; i++) @@ -84,48 +144,26 @@ static void bump_cpu_timer(struct k_itimer *timer, u64 now) if (delta < incr) continue; - timer->it.cpu.expires += incr; + timer->it.cpu.node.expires += incr; timer->it_overrun += 1LL << i; delta -= incr; } + return timer->it.cpu.node.expires; } -/** - * task_cputime_zero - Check a task_cputime struct for all zero fields. - * - * @cputime: The struct to compare. - * - * Checks @cputime to see if all fields are zero. Returns true if all fields - * are zero, false if any field is nonzero. - */ -static inline int task_cputime_zero(const struct task_cputime *cputime) +/* Check whether all cache entries contain U64_MAX, i.e. eternal expiry time */ +static inline bool expiry_cache_is_inactive(const struct posix_cputimers *pct) { - if (!cputime->utime && !cputime->stime && !cputime->sum_exec_runtime) - return 1; - return 0; -} - -static inline u64 prof_ticks(struct task_struct *p) -{ - u64 utime, stime; - - task_cputime(p, &utime, &stime); - - return utime + stime; -} -static inline u64 virt_ticks(struct task_struct *p) -{ - u64 utime, stime; - - task_cputime(p, &utime, &stime); - - return utime; + return !(~pct->bases[CPUCLOCK_PROF].nextevt | + ~pct->bases[CPUCLOCK_VIRT].nextevt | + ~pct->bases[CPUCLOCK_SCHED].nextevt); } static int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec64 *tp) { - int error = check_clock(which_clock); + int error = validate_clock_permissions(which_clock); + if (!error) { tp->tv_sec = 0; tp->tv_nsec = ((NSEC_PER_SEC + HZ - 1) / HZ); @@ -142,42 +180,66 @@ posix_cpu_clock_getres(const clockid_t which_clock, struct timespec64 *tp) } static int -posix_cpu_clock_set(const clockid_t which_clock, const struct timespec64 *tp) +posix_cpu_clock_set(const clockid_t clock, const struct timespec64 *tp) { + int error = validate_clock_permissions(clock); + /* * You can never reset a CPU clock, but we check for other errors * in the call before failing with EPERM. */ - int error = check_clock(which_clock); - if (error == 0) { - error = -EPERM; - } - return error; + return error ? : -EPERM; } - /* - * Sample a per-thread clock for the given task. + * Sample a per-thread clock for the given task. clkid is validated. */ -static int cpu_clock_sample(const clockid_t which_clock, - struct task_struct *p, u64 *sample) +static u64 cpu_clock_sample(const clockid_t clkid, struct task_struct *p) { - switch (CPUCLOCK_WHICH(which_clock)) { - default: - return -EINVAL; + u64 utime, stime; + + if (clkid == CPUCLOCK_SCHED) + return task_sched_runtime(p); + + task_cputime(p, &utime, &stime); + + switch (clkid) { case CPUCLOCK_PROF: - *sample = prof_ticks(p); - break; + return utime + stime; case CPUCLOCK_VIRT: - *sample = virt_ticks(p); - break; - case CPUCLOCK_SCHED: - *sample = task_sched_runtime(p); - break; + return utime; + default: + WARN_ON_ONCE(1); } return 0; } +static inline void store_samples(u64 *samples, u64 stime, u64 utime, u64 rtime) +{ + samples[CPUCLOCK_PROF] = stime + utime; + samples[CPUCLOCK_VIRT] = utime; + samples[CPUCLOCK_SCHED] = rtime; +} + +static void task_sample_cputime(struct task_struct *p, u64 *samples) +{ + u64 stime, utime; + + task_cputime(p, &utime, &stime); + store_samples(samples, stime, utime, p->se.sum_exec_runtime); +} + +static void proc_sample_cputime_atomic(struct task_cputime_atomic *at, + u64 *samples) +{ + u64 stime, utime, rtime; + + utime = atomic64_read(&at->utime); + stime = atomic64_read(&at->stime); + rtime = atomic64_read(&at->sum_exec_runtime); + store_samples(samples, stime, utime, rtime); +} + /* * Set cputime to sum_cputime if sum_cputime > cputime. Use cmpxchg * to avoid race conditions with concurrent updates to cputime. @@ -193,29 +255,56 @@ retry: } } -static void update_gt_cputime(struct task_cputime_atomic *cputime_atomic, struct task_cputime *sum) +static void update_gt_cputime(struct task_cputime_atomic *cputime_atomic, + struct task_cputime *sum) { __update_gt_cputime(&cputime_atomic->utime, sum->utime); __update_gt_cputime(&cputime_atomic->stime, sum->stime); __update_gt_cputime(&cputime_atomic->sum_exec_runtime, sum->sum_exec_runtime); } -/* Sample task_cputime_atomic values in "atomic_timers", store results in "times". */ -static inline void sample_cputime_atomic(struct task_cputime *times, - struct task_cputime_atomic *atomic_times) +/** + * thread_group_sample_cputime - Sample cputime for a given task + * @tsk: Task for which cputime needs to be started + * @iimes: Storage for time samples + * + * Called from sys_getitimer() to calculate the expiry time of an active + * timer. That means group cputime accounting is already active. Called + * with task sighand lock held. + * + * Updates @times with an uptodate sample of the thread group cputimes. + */ +void thread_group_sample_cputime(struct task_struct *tsk, u64 *samples) { - times->utime = atomic64_read(&atomic_times->utime); - times->stime = atomic64_read(&atomic_times->stime); - times->sum_exec_runtime = atomic64_read(&atomic_times->sum_exec_runtime); + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + struct posix_cputimers *pct = &tsk->signal->posix_cputimers; + + WARN_ON_ONCE(!pct->timers_active); + + proc_sample_cputime_atomic(&cputimer->cputime_atomic, samples); } -void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times) +/** + * thread_group_start_cputime - Start cputime and return a sample + * @tsk: Task for which cputime needs to be started + * @samples: Storage for time samples + * + * The thread group cputime accouting is avoided when there are no posix + * CPU timers armed. Before starting a timer it's required to check whether + * the time accounting is active. If not, a full update of the atomic + * accounting store needs to be done and the accounting enabled. + * + * Updates @times with an uptodate sample of the thread group cputimes. + */ +static void thread_group_start_cputime(struct task_struct *tsk, u64 *samples) { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; - struct task_cputime sum; + struct posix_cputimers *pct = &tsk->signal->posix_cputimers; /* Check if cputimer isn't running. This is accessed without locking. */ - if (!READ_ONCE(cputimer->running)) { + if (!READ_ONCE(pct->timers_active)) { + struct task_cputime sum; + /* * The POSIX timer interface allows for absolute time expiry * values through the TIMER_ABSTIME flag, therefore we have @@ -225,94 +314,69 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times) update_gt_cputime(&cputimer->cputime_atomic, &sum); /* - * We're setting cputimer->running without a lock. Ensure - * this only gets written to in one operation. We set - * running after update_gt_cputime() as a small optimization, - * but barriers are not required because update_gt_cputime() + * We're setting timers_active without a lock. Ensure this + * only gets written to in one operation. We set it after + * update_gt_cputime() as a small optimization, but + * barriers are not required because update_gt_cputime() * can handle concurrent updates. */ - WRITE_ONCE(cputimer->running, true); + WRITE_ONCE(pct->timers_active, true); } - sample_cputime_atomic(times, &cputimer->cputime_atomic); + proc_sample_cputime_atomic(&cputimer->cputime_atomic, samples); } -/* - * Sample a process (thread group) clock for the given group_leader task. - * Must be called with task sighand lock held for safe while_each_thread() - * traversal. - */ -static int cpu_clock_sample_group(const clockid_t which_clock, - struct task_struct *p, - u64 *sample) +static void __thread_group_cputime(struct task_struct *tsk, u64 *samples) { - struct task_cputime cputime; + struct task_cputime ct; - switch (CPUCLOCK_WHICH(which_clock)) { - default: - return -EINVAL; - case CPUCLOCK_PROF: - thread_group_cputime(p, &cputime); - *sample = cputime.utime + cputime.stime; - break; - case CPUCLOCK_VIRT: - thread_group_cputime(p, &cputime); - *sample = cputime.utime; - break; - case CPUCLOCK_SCHED: - thread_group_cputime(p, &cputime); - *sample = cputime.sum_exec_runtime; - break; - } - return 0; + thread_group_cputime(tsk, &ct); + store_samples(samples, ct.stime, ct.utime, ct.sum_exec_runtime); } -static int posix_cpu_clock_get_task(struct task_struct *tsk, - const clockid_t which_clock, - struct timespec64 *tp) +/* + * Sample a process (thread group) clock for the given task clkid. If the + * group's cputime accounting is already enabled, read the atomic + * store. Otherwise a full update is required. Task's sighand lock must be + * held to protect the task traversal on a full update. clkid is already + * validated. + */ +static u64 cpu_clock_sample_group(const clockid_t clkid, struct task_struct *p, + bool start) { - int err = -EINVAL; - u64 rtn; + struct thread_group_cputimer *cputimer = &p->signal->cputimer; + struct posix_cputimers *pct = &p->signal->posix_cputimers; + u64 samples[CPUCLOCK_MAX]; - if (CPUCLOCK_PERTHREAD(which_clock)) { - if (same_thread_group(tsk, current)) - err = cpu_clock_sample(which_clock, tsk, &rtn); + if (!READ_ONCE(pct->timers_active)) { + if (start) + thread_group_start_cputime(p, samples); + else + __thread_group_cputime(p, samples); } else { - if (tsk == current || thread_group_leader(tsk)) - err = cpu_clock_sample_group(which_clock, tsk, &rtn); + proc_sample_cputime_atomic(&cputimer->cputime_atomic, samples); } - if (!err) - *tp = ns_to_timespec64(rtn); - - return err; + return samples[clkid]; } - -static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec64 *tp) +static int posix_cpu_clock_get(const clockid_t clock, struct timespec64 *tp) { - const pid_t pid = CPUCLOCK_PID(which_clock); - int err = -EINVAL; + const clockid_t clkid = CPUCLOCK_WHICH(clock); + struct task_struct *tsk; + u64 t; - if (pid == 0) { - /* - * Special case constant value for our own clocks. - * We don't have to do any lookup to find ourselves. - */ - err = posix_cpu_clock_get_task(current, which_clock, tp); - } else { - /* - * Find the given PID, and validate that the caller - * should be able to see it. - */ - struct task_struct *p; - rcu_read_lock(); - p = find_task_by_vpid(pid); - if (p) - err = posix_cpu_clock_get_task(p, which_clock, tp); - rcu_read_unlock(); - } + tsk = get_task_for_clock_get(clock); + if (!tsk) + return -EINVAL; - return err; + if (CPUCLOCK_PERTHREAD(clock)) + t = cpu_clock_sample(clkid, tsk); + else + t = cpu_clock_sample_group(clkid, tsk, false); + put_task_struct(tsk); + + *tp = ns_to_timespec64(t); + return 0; } /* @@ -322,44 +386,15 @@ static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec64 *t */ static int posix_cpu_timer_create(struct k_itimer *new_timer) { - int ret = 0; - const pid_t pid = CPUCLOCK_PID(new_timer->it_clock); - struct task_struct *p; + struct task_struct *p = get_task_for_clock(new_timer->it_clock); - if (CPUCLOCK_WHICH(new_timer->it_clock) >= CPUCLOCK_MAX) + if (!p) return -EINVAL; new_timer->kclock = &clock_posix_cpu; - - INIT_LIST_HEAD(&new_timer->it.cpu.entry); - - rcu_read_lock(); - if (CPUCLOCK_PERTHREAD(new_timer->it_clock)) { - if (pid == 0) { - p = current; - } else { - p = find_task_by_vpid(pid); - if (p && !same_thread_group(p, current)) - p = NULL; - } - } else { - if (pid == 0) { - p = current->group_leader; - } else { - p = find_task_by_vpid(pid); - if (p && !has_group_leader_pid(p)) - p = NULL; - } - } + timerqueue_init(&new_timer->it.cpu.node); new_timer->it.cpu.task = p; - if (p) { - get_task_struct(p); - } else { - ret = -EINVAL; - } - rcu_read_unlock(); - - return ret; + return 0; } /* @@ -370,12 +405,14 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer) */ static int posix_cpu_timer_del(struct k_itimer *timer) { - int ret = 0; - unsigned long flags; + struct cpu_timer *ctmr = &timer->it.cpu; + struct task_struct *p = ctmr->task; struct sighand_struct *sighand; - struct task_struct *p = timer->it.cpu.task; + unsigned long flags; + int ret = 0; - WARN_ON_ONCE(p == NULL); + if (WARN_ON_ONCE(!p)) + return -EINVAL; /* * Protect against sighand release/switch in exit/exec and process/ @@ -384,15 +421,15 @@ static int posix_cpu_timer_del(struct k_itimer *timer) sighand = lock_task_sighand(p, &flags); if (unlikely(sighand == NULL)) { /* - * We raced with the reaping of the task. - * The deletion should have cleared us off the list. + * This raced with the reaping of the task. The exit cleanup + * should have removed this timer from the timer queue. */ - WARN_ON_ONCE(!list_empty(&timer->it.cpu.entry)); + WARN_ON_ONCE(ctmr->head || timerqueue_node_queued(&ctmr->node)); } else { if (timer->it.cpu.firing) ret = TIMER_RETRY; else - list_del(&timer->it.cpu.entry); + cpu_timer_dequeue(ctmr); unlock_task_sighand(p, &flags); } @@ -403,25 +440,30 @@ static int posix_cpu_timer_del(struct k_itimer *timer) return ret; } -static void cleanup_timers_list(struct list_head *head) +static void cleanup_timerqueue(struct timerqueue_head *head) { - struct cpu_timer_list *timer, *next; + struct timerqueue_node *node; + struct cpu_timer *ctmr; - list_for_each_entry_safe(timer, next, head, entry) - list_del_init(&timer->entry); + while ((node = timerqueue_getnext(head))) { + timerqueue_del(head, node); + ctmr = container_of(node, struct cpu_timer, node); + ctmr->head = NULL; + } } /* - * Clean out CPU timers still ticking when a thread exited. The task - * pointer is cleared, and the expiry time is replaced with the residual - * time for later timer_gettime calls to return. + * Clean out CPU timers which are still armed when a thread exits. The + * timers are only removed from the list. No other updates are done. The + * corresponding posix timers are still accessible, but cannot be rearmed. + * * This must be called with the siglock held. */ -static void cleanup_timers(struct list_head *head) +static void cleanup_timers(struct posix_cputimers *pct) { - cleanup_timers_list(head); - cleanup_timers_list(++head); - cleanup_timers_list(++head); + cleanup_timerqueue(&pct->bases[CPUCLOCK_PROF].tqhead); + cleanup_timerqueue(&pct->bases[CPUCLOCK_VIRT].tqhead); + cleanup_timerqueue(&pct->bases[CPUCLOCK_SCHED].tqhead); } /* @@ -431,16 +473,11 @@ static void cleanup_timers(struct list_head *head) */ void posix_cpu_timers_exit(struct task_struct *tsk) { - cleanup_timers(tsk->cpu_timers); + cleanup_timers(&tsk->posix_cputimers); } void posix_cpu_timers_exit_group(struct task_struct *tsk) { - cleanup_timers(tsk->signal->cpu_timers); -} - -static inline int expires_gt(u64 expires, u64 new_exp) -{ - return expires == 0 || expires > new_exp; + cleanup_timers(&tsk->signal->posix_cputimers); } /* @@ -449,58 +486,33 @@ static inline int expires_gt(u64 expires, u64 new_exp) */ static void arm_timer(struct k_itimer *timer) { - struct task_struct *p = timer->it.cpu.task; - struct list_head *head, *listpos; - struct task_cputime *cputime_expires; - struct cpu_timer_list *const nt = &timer->it.cpu; - struct cpu_timer_list *next; - - if (CPUCLOCK_PERTHREAD(timer->it_clock)) { - head = p->cpu_timers; - cputime_expires = &p->cputime_expires; - } else { - head = p->signal->cpu_timers; - cputime_expires = &p->signal->cputime_expires; - } - head += CPUCLOCK_WHICH(timer->it_clock); - - listpos = head; - list_for_each_entry(next, head, entry) { - if (nt->expires < next->expires) - break; - listpos = &next->entry; - } - list_add(&nt->entry, listpos); - - if (listpos == head) { - u64 exp = nt->expires; + int clkidx = CPUCLOCK_WHICH(timer->it_clock); + struct cpu_timer *ctmr = &timer->it.cpu; + u64 newexp = cpu_timer_getexpires(ctmr); + struct task_struct *p = ctmr->task; + struct posix_cputimer_base *base; + + if (CPUCLOCK_PERTHREAD(timer->it_clock)) + base = p->posix_cputimers.bases + clkidx; + else + base = p->signal->posix_cputimers.bases + clkidx; + + if (!cpu_timer_enqueue(&base->tqhead, ctmr)) + return; - /* - * We are the new earliest-expiring POSIX 1.b timer, hence - * need to update expiration cache. Take into account that - * for process timers we share expiration cache with itimers - * and RLIMIT_CPU and for thread timers with RLIMIT_RTTIME. - */ + /* + * We are the new earliest-expiring POSIX 1.b timer, hence + * need to update expiration cache. Take into account that + * for process timers we share expiration cache with itimers + * and RLIMIT_CPU and for thread timers with RLIMIT_RTTIME. + */ + if (newexp < base->nextevt) + base->nextevt = newexp; - switch (CPUCLOCK_WHICH(timer->it_clock)) { - case CPUCLOCK_PROF: - if (expires_gt(cputime_expires->prof_exp, exp)) - cputime_expires->prof_exp = exp; - break; - case CPUCLOCK_VIRT: - if (expires_gt(cputime_expires->virt_exp, exp)) - cputime_expires->virt_exp = exp; - break; - case CPUCLOCK_SCHED: - if (expires_gt(cputime_expires->sched_exp, exp)) - cputime_expires->sched_exp = exp; - break; - } - if (CPUCLOCK_PERTHREAD(timer->it_clock)) - tick_dep_set_task(p, TICK_DEP_BIT_POSIX_TIMER); - else - tick_dep_set_signal(p->signal, TICK_DEP_BIT_POSIX_TIMER); - } + if (CPUCLOCK_PERTHREAD(timer->it_clock)) + tick_dep_set_task(p, TICK_DEP_BIT_POSIX_TIMER); + else + tick_dep_set_signal(p->signal, TICK_DEP_BIT_POSIX_TIMER); } /* @@ -508,24 +520,26 @@ static void arm_timer(struct k_itimer *timer) */ static void cpu_timer_fire(struct k_itimer *timer) { + struct cpu_timer *ctmr = &timer->it.cpu; + if ((timer->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) { /* * User don't want any signal. */ - timer->it.cpu.expires = 0; + cpu_timer_setexpires(ctmr, 0); } else if (unlikely(timer->sigq == NULL)) { /* * This a special case for clock_nanosleep, * not a normal timer from sys_timer_create. */ wake_up_process(timer->it_process); - timer->it.cpu.expires = 0; + cpu_timer_setexpires(ctmr, 0); } else if (!timer->it_interval) { /* * One-shot timer. Clear it as soon as it's fired. */ posix_timer_event(timer, 0); - timer->it.cpu.expires = 0; + cpu_timer_setexpires(ctmr, 0); } else if (posix_timer_event(timer, ++timer->it_requeue_pending)) { /* * The signal did not get queued because the signal @@ -539,33 +553,6 @@ static void cpu_timer_fire(struct k_itimer *timer) } /* - * Sample a process (thread group) timer for the given group_leader task. - * Must be called with task sighand lock held for safe while_each_thread() - * traversal. - */ -static int cpu_timer_sample_group(const clockid_t which_clock, - struct task_struct *p, u64 *sample) -{ - struct task_cputime cputime; - - thread_group_cputimer(p, &cputime); - switch (CPUCLOCK_WHICH(which_clock)) { - default: - return -EINVAL; - case CPUCLOCK_PROF: - *sample = cputime.utime + cputime.stime; - break; - case CPUCLOCK_VIRT: - *sample = cputime.utime; - break; - case CPUCLOCK_SCHED: - *sample = cputime.sum_exec_runtime; - break; - } - return 0; -} - -/* * Guts of sys_timer_settime for CPU timers. * This is called with the timer locked and interrupts disabled. * If we return TIMER_RETRY, it's necessary to release the timer's lock @@ -574,13 +561,16 @@ static int cpu_timer_sample_group(const clockid_t which_clock, static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, struct itimerspec64 *new, struct itimerspec64 *old) { - unsigned long flags; - struct sighand_struct *sighand; - struct task_struct *p = timer->it.cpu.task; + clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); u64 old_expires, new_expires, old_incr, val; - int ret; + struct cpu_timer *ctmr = &timer->it.cpu; + struct task_struct *p = ctmr->task; + struct sighand_struct *sighand; + unsigned long flags; + int ret = 0; - WARN_ON_ONCE(p == NULL); + if (WARN_ON_ONCE(!p)) + return -EINVAL; /* * Use the to_ktime conversion because that clamps the maximum @@ -597,22 +587,21 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, * If p has just been reaped, we can no * longer get any information about it at all. */ - if (unlikely(sighand == NULL)) { + if (unlikely(sighand == NULL)) return -ESRCH; - } /* * Disarm any old timer after extracting its expiry time. */ - - ret = 0; old_incr = timer->it_interval; - old_expires = timer->it.cpu.expires; + old_expires = cpu_timer_getexpires(ctmr); + if (unlikely(timer->it.cpu.firing)) { timer->it.cpu.firing = -1; ret = TIMER_RETRY; - } else - list_del_init(&timer->it.cpu.entry); + } else { + cpu_timer_dequeue(ctmr); + } /* * We need to sample the current value to convert the new @@ -622,11 +611,10 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, * times (in arm_timer). With an absolute time, we must * check if it's already passed. In short, we need a sample. */ - if (CPUCLOCK_PERTHREAD(timer->it_clock)) { - cpu_clock_sample(timer->it_clock, p, &val); - } else { - cpu_timer_sample_group(timer->it_clock, p, &val); - } + if (CPUCLOCK_PERTHREAD(timer->it_clock)) + val = cpu_clock_sample(clkid, p); + else + val = cpu_clock_sample_group(clkid, p, true); if (old) { if (old_expires == 0) { @@ -634,18 +622,16 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, old->it_value.tv_nsec = 0; } else { /* - * Update the timer in case it has - * overrun already. If it has, - * we'll report it as having overrun - * and with the next reloaded timer - * already ticking, though we are - * swallowing that pending - * notification here to install the - * new setting. + * Update the timer in case it has overrun already. + * If it has, we'll report it as having overrun and + * with the next reloaded timer already ticking, + * though we are swallowing that pending + * notification here to install the new setting. */ - bump_cpu_timer(timer, val); - if (val < timer->it.cpu.expires) { - old_expires = timer->it.cpu.expires - val; + u64 exp = bump_cpu_timer(timer, val); + + if (val < exp) { + old_expires = exp - val; old->it_value = ns_to_timespec64(old_expires); } else { old->it_value.tv_nsec = 1; @@ -674,7 +660,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, * For a timer with no notification action, we don't actually * arm the timer (we'll just fake it for timer_gettime). */ - timer->it.cpu.expires = new_expires; + cpu_timer_setexpires(ctmr, new_expires); if (new_expires != 0 && val < new_expires) { arm_timer(timer); } @@ -715,24 +701,27 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp) { - u64 now; - struct task_struct *p = timer->it.cpu.task; + clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); + struct cpu_timer *ctmr = &timer->it.cpu; + u64 now, expires = cpu_timer_getexpires(ctmr); + struct task_struct *p = ctmr->task; - WARN_ON_ONCE(p == NULL); + if (WARN_ON_ONCE(!p)) + return; /* * Easy part: convert the reload time. */ itp->it_interval = ktime_to_timespec64(timer->it_interval); - if (!timer->it.cpu.expires) + if (!expires) return; /* * Sample the clock to take the difference with the expiry time. */ if (CPUCLOCK_PERTHREAD(timer->it_clock)) { - cpu_clock_sample(timer->it_clock, p, &now); + now = cpu_clock_sample(clkid, p); } else { struct sighand_struct *sighand; unsigned long flags; @@ -747,18 +736,18 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp /* * The process has been reaped. * We can't even collect a sample any more. - * Call the timer disarmed, nothing else to do. + * Disarm the timer, nothing else to do. */ - timer->it.cpu.expires = 0; + cpu_timer_setexpires(ctmr, 0); return; } else { - cpu_timer_sample_group(timer->it_clock, p, &now); + now = cpu_clock_sample_group(clkid, p, false); unlock_task_sighand(p, &flags); } } - if (now < timer->it.cpu.expires) { - itp->it_value = ns_to_timespec64(timer->it.cpu.expires - now); + if (now < expires) { + itp->it_value = ns_to_timespec64(expires - now); } else { /* * The timer should have expired already, but the firing @@ -769,26 +758,42 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp } } -static unsigned long long -check_timers_list(struct list_head *timers, - struct list_head *firing, - unsigned long long curr) -{ - int maxfire = 20; +#define MAX_COLLECTED 20 - while (!list_empty(timers)) { - struct cpu_timer_list *t; +static u64 collect_timerqueue(struct timerqueue_head *head, + struct list_head *firing, u64 now) +{ + struct timerqueue_node *next; + int i = 0; + + while ((next = timerqueue_getnext(head))) { + struct cpu_timer *ctmr; + u64 expires; + + ctmr = container_of(next, struct cpu_timer, node); + expires = cpu_timer_getexpires(ctmr); + /* Limit the number of timers to expire at once */ + if (++i == MAX_COLLECTED || now < expires) + return expires; + + ctmr->firing = 1; + cpu_timer_dequeue(ctmr); + list_add_tail(&ctmr->elist, firing); + } - t = list_first_entry(timers, struct cpu_timer_list, entry); + return U64_MAX; +} - if (!--maxfire || curr < t->expires) - return t->expires; +static void collect_posix_cputimers(struct posix_cputimers *pct, u64 *samples, + struct list_head *firing) +{ + struct posix_cputimer_base *base = pct->bases; + int i; - t->firing = 1; - list_move_tail(&t->entry, firing); + for (i = 0; i < CPUCLOCK_MAX; i++, base++) { + base->nextevt = collect_timerqueue(&base->tqhead, firing, + samples[i]); } - - return 0; } static inline void check_dl_overrun(struct task_struct *tsk) @@ -799,6 +804,20 @@ static inline void check_dl_overrun(struct task_struct *tsk) } } +static bool check_rlimit(u64 time, u64 limit, int signo, bool rt, bool hard) +{ + if (time < limit) + return false; + + if (print_fatal_signals) { + pr_info("%s Watchdog Timeout (%s): %s[%d]\n", + rt ? "RT" : "CPU", hard ? "hard" : "soft", + current->comm, task_pid_nr(current)); + } + __group_send_sig_info(signo, SEND_SIG_PRIV, current); + return true; +} + /* * Check for any per-thread CPU timers that have fired and move them off * the tsk->cpu_timers[N] list onto the firing list. Here we update the @@ -807,76 +826,50 @@ static inline void check_dl_overrun(struct task_struct *tsk) static void check_thread_timers(struct task_struct *tsk, struct list_head *firing) { - struct list_head *timers = tsk->cpu_timers; - struct task_cputime *tsk_expires = &tsk->cputime_expires; - u64 expires; + struct posix_cputimers *pct = &tsk->posix_cputimers; + u64 samples[CPUCLOCK_MAX]; unsigned long soft; if (dl_task(tsk)) check_dl_overrun(tsk); - /* - * If cputime_expires is zero, then there are no active - * per thread CPU timers. - */ - if (task_cputime_zero(&tsk->cputime_expires)) + if (expiry_cache_is_inactive(pct)) return; - expires = check_timers_list(timers, firing, prof_ticks(tsk)); - tsk_expires->prof_exp = expires; - - expires = check_timers_list(++timers, firing, virt_ticks(tsk)); - tsk_expires->virt_exp = expires; - - tsk_expires->sched_exp = check_timers_list(++timers, firing, - tsk->se.sum_exec_runtime); + task_sample_cputime(tsk, samples); + collect_posix_cputimers(pct, samples, firing); /* * Check for the special case thread timers. */ soft = task_rlimit(tsk, RLIMIT_RTTIME); if (soft != RLIM_INFINITY) { + /* Task RT timeout is accounted in jiffies. RTTIME is usec */ + unsigned long rttime = tsk->rt.timeout * (USEC_PER_SEC / HZ); unsigned long hard = task_rlimit_max(tsk, RLIMIT_RTTIME); + /* At the hard limit, send SIGKILL. No further action. */ if (hard != RLIM_INFINITY && - tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) { - /* - * At the hard limit, we just die. - * No need to calculate anything else now. - */ - if (print_fatal_signals) { - pr_info("CPU Watchdog Timeout (hard): %s[%d]\n", - tsk->comm, task_pid_nr(tsk)); - } - __group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk); + check_rlimit(rttime, hard, SIGKILL, true, true)) return; - } - if (tsk->rt.timeout > DIV_ROUND_UP(soft, USEC_PER_SEC/HZ)) { - /* - * At the soft limit, send a SIGXCPU every second. - */ - if (soft < hard) { - soft += USEC_PER_SEC; - tsk->signal->rlim[RLIMIT_RTTIME].rlim_cur = - soft; - } - if (print_fatal_signals) { - pr_info("RT Watchdog Timeout (soft): %s[%d]\n", - tsk->comm, task_pid_nr(tsk)); - } - __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk); + + /* At the soft limit, send a SIGXCPU every second */ + if (check_rlimit(rttime, soft, SIGXCPU, true, false)) { + soft += USEC_PER_SEC; + tsk->signal->rlim[RLIMIT_RTTIME].rlim_cur = soft; } } - if (task_cputime_zero(tsk_expires)) + + if (expiry_cache_is_inactive(pct)) tick_dep_clear_task(tsk, TICK_DEP_BIT_POSIX_TIMER); } static inline void stop_process_timers(struct signal_struct *sig) { - struct thread_group_cputimer *cputimer = &sig->cputimer; + struct posix_cputimers *pct = &sig->posix_cputimers; - /* Turn off cputimer->running. This is done without locking. */ - WRITE_ONCE(cputimer->running, false); + /* Turn off the active flag. This is done without locking. */ + WRITE_ONCE(pct->timers_active, false); tick_dep_clear_signal(sig, TICK_DEP_BIT_POSIX_TIMER); } @@ -898,7 +891,7 @@ static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it, __group_send_sig_info(signo, SEND_SIG_PRIV, tsk); } - if (it->expires && (!*expires || it->expires < *expires)) + if (it->expires && it->expires < *expires) *expires = it->expires; } @@ -911,87 +904,69 @@ static void check_process_timers(struct task_struct *tsk, struct list_head *firing) { struct signal_struct *const sig = tsk->signal; - u64 utime, ptime, virt_expires, prof_expires; - u64 sum_sched_runtime, sched_expires; - struct list_head *timers = sig->cpu_timers; - struct task_cputime cputime; + struct posix_cputimers *pct = &sig->posix_cputimers; + u64 samples[CPUCLOCK_MAX]; unsigned long soft; /* - * If cputimer is not running, then there are no active - * process wide timers (POSIX 1.b, itimers, RLIMIT_CPU). + * If there are no active process wide timers (POSIX 1.b, itimers, + * RLIMIT_CPU) nothing to check. Also skip the process wide timer + * processing when there is already another task handling them. */ - if (!READ_ONCE(tsk->signal->cputimer.running)) + if (!READ_ONCE(pct->timers_active) || pct->expiry_active) return; - /* + /* * Signify that a thread is checking for process timers. * Write access to this field is protected by the sighand lock. */ - sig->cputimer.checking_timer = true; + pct->expiry_active = true; /* - * Collect the current process totals. + * Collect the current process totals. Group accounting is active + * so the sample can be taken directly. */ - thread_group_cputimer(tsk, &cputime); - utime = cputime.utime; - ptime = utime + cputime.stime; - sum_sched_runtime = cputime.sum_exec_runtime; - - prof_expires = check_timers_list(timers, firing, ptime); - virt_expires = check_timers_list(++timers, firing, utime); - sched_expires = check_timers_list(++timers, firing, sum_sched_runtime); + proc_sample_cputime_atomic(&sig->cputimer.cputime_atomic, samples); + collect_posix_cputimers(pct, samples, firing); /* * Check for the special case process timers. */ - check_cpu_itimer(tsk, &sig->it[CPUCLOCK_PROF], &prof_expires, ptime, - SIGPROF); - check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime, - SIGVTALRM); + check_cpu_itimer(tsk, &sig->it[CPUCLOCK_PROF], + &pct->bases[CPUCLOCK_PROF].nextevt, + samples[CPUCLOCK_PROF], SIGPROF); + check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], + &pct->bases[CPUCLOCK_VIRT].nextevt, + samples[CPUCLOCK_VIRT], SIGVTALRM); + soft = task_rlimit(tsk, RLIMIT_CPU); if (soft != RLIM_INFINITY) { - unsigned long psecs = div_u64(ptime, NSEC_PER_SEC); + /* RLIMIT_CPU is in seconds. Samples are nanoseconds */ unsigned long hard = task_rlimit_max(tsk, RLIMIT_CPU); - u64 x; - if (psecs >= hard) { - /* - * At the hard limit, we just die. - * No need to calculate anything else now. - */ - if (print_fatal_signals) { - pr_info("RT Watchdog Timeout (hard): %s[%d]\n", - tsk->comm, task_pid_nr(tsk)); - } - __group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk); + u64 ptime = samples[CPUCLOCK_PROF]; + u64 softns = (u64)soft * NSEC_PER_SEC; + u64 hardns = (u64)hard * NSEC_PER_SEC; + + /* At the hard limit, send SIGKILL. No further action. */ + if (hard != RLIM_INFINITY && + check_rlimit(ptime, hardns, SIGKILL, false, true)) return; + + /* At the soft limit, send a SIGXCPU every second */ + if (check_rlimit(ptime, softns, SIGXCPU, false, false)) { + sig->rlim[RLIMIT_CPU].rlim_cur = soft + 1; + softns += NSEC_PER_SEC; } - if (psecs >= soft) { - /* - * At the soft limit, send a SIGXCPU every second. - */ - if (print_fatal_signals) { - pr_info("CPU Watchdog Timeout (soft): %s[%d]\n", - tsk->comm, task_pid_nr(tsk)); - } - __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk); - if (soft < hard) { - soft++; - sig->rlim[RLIMIT_CPU].rlim_cur = soft; - } - } - x = soft * NSEC_PER_SEC; - if (!prof_expires || x < prof_expires) - prof_expires = x; + + /* Update the expiry cache */ + if (softns < pct->bases[CPUCLOCK_PROF].nextevt) + pct->bases[CPUCLOCK_PROF].nextevt = softns; } - sig->cputime_expires.prof_exp = prof_expires; - sig->cputime_expires.virt_exp = virt_expires; - sig->cputime_expires.sched_exp = sched_expires; - if (task_cputime_zero(&sig->cputime_expires)) + if (expiry_cache_is_inactive(pct)) stop_process_timers(sig); - sig->cputimer.checking_timer = false; + pct->expiry_active = false; } /* @@ -1000,18 +975,21 @@ static void check_process_timers(struct task_struct *tsk, */ static void posix_cpu_timer_rearm(struct k_itimer *timer) { + clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); + struct cpu_timer *ctmr = &timer->it.cpu; + struct task_struct *p = ctmr->task; struct sighand_struct *sighand; unsigned long flags; - struct task_struct *p = timer->it.cpu.task; u64 now; - WARN_ON_ONCE(p == NULL); + if (WARN_ON_ONCE(!p)) + return; /* * Fetch the current sample and update the timer's expiry time. */ if (CPUCLOCK_PERTHREAD(timer->it_clock)) { - cpu_clock_sample(timer->it_clock, p, &now); + now = cpu_clock_sample(clkid, p); bump_cpu_timer(timer, now); if (unlikely(p->exit_state)) return; @@ -1031,13 +1009,13 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer) * The process has been reaped. * We can't even collect a sample any more. */ - timer->it.cpu.expires = 0; + cpu_timer_setexpires(ctmr, 0); return; } else if (unlikely(p->exit_state) && thread_group_empty(p)) { /* If the process is dying, no need to rearm */ goto unlock; } - cpu_timer_sample_group(timer->it_clock, p, &now); + now = cpu_clock_sample_group(clkid, p, true); bump_cpu_timer(timer, now); /* Leave the sighand locked for the call below. */ } @@ -1051,26 +1029,24 @@ unlock: } /** - * task_cputime_expired - Compare two task_cputime entities. + * task_cputimers_expired - Check whether posix CPU timers are expired * - * @sample: The task_cputime structure to be checked for expiration. - * @expires: Expiration times, against which @sample will be checked. + * @samples: Array of current samples for the CPUCLOCK clocks + * @pct: Pointer to a posix_cputimers container * - * Checks @sample against @expires to see if any field of @sample has expired. - * Returns true if any field of the former is greater than the corresponding - * field of the latter if the latter field is set. Otherwise returns false. + * Returns true if any member of @samples is greater than the corresponding + * member of @pct->bases[CLK].nextevt. False otherwise */ -static inline int task_cputime_expired(const struct task_cputime *sample, - const struct task_cputime *expires) +static inline bool +task_cputimers_expired(const u64 *sample, struct posix_cputimers *pct) { - if (expires->utime && sample->utime >= expires->utime) - return 1; - if (expires->stime && sample->utime + sample->stime >= expires->stime) - return 1; - if (expires->sum_exec_runtime != 0 && - sample->sum_exec_runtime >= expires->sum_exec_runtime) - return 1; - return 0; + int i; + + for (i = 0; i < CPUCLOCK_MAX; i++) { + if (sample[i] >= pct->bases[i].nextevt) + return true; + } + return false; } /** @@ -1083,48 +1059,50 @@ static inline int task_cputime_expired(const struct task_cputime *sample, * timers and compare them with the corresponding expiration times. Return * true if a timer has expired, else return false. */ -static inline int fastpath_timer_check(struct task_struct *tsk) +static inline bool fastpath_timer_check(struct task_struct *tsk) { + struct posix_cputimers *pct = &tsk->posix_cputimers; struct signal_struct *sig; - if (!task_cputime_zero(&tsk->cputime_expires)) { - struct task_cputime task_sample; + if (!expiry_cache_is_inactive(pct)) { + u64 samples[CPUCLOCK_MAX]; - task_cputime(tsk, &task_sample.utime, &task_sample.stime); - task_sample.sum_exec_runtime = tsk->se.sum_exec_runtime; - if (task_cputime_expired(&task_sample, &tsk->cputime_expires)) - return 1; + task_sample_cputime(tsk, samples); + if (task_cputimers_expired(samples, pct)) + return true; } sig = tsk->signal; + pct = &sig->posix_cputimers; /* - * Check if thread group timers expired when the cputimer is - * running and no other thread in the group is already checking - * for thread group cputimers. These fields are read without the - * sighand lock. However, this is fine because this is meant to - * be a fastpath heuristic to determine whether we should try to - * acquire the sighand lock to check/handle timers. + * Check if thread group timers expired when timers are active and + * no other thread in the group is already handling expiry for + * thread group cputimers. These fields are read without the + * sighand lock. However, this is fine because this is meant to be + * a fastpath heuristic to determine whether we should try to + * acquire the sighand lock to handle timer expiry. * - * In the worst case scenario, if 'running' or 'checking_timer' gets - * set but the current thread doesn't see the change yet, we'll wait - * until the next thread in the group gets a scheduler interrupt to - * handle the timer. This isn't an issue in practice because these - * types of delays with signals actually getting sent are expected. + * In the worst case scenario, if concurrently timers_active is set + * or expiry_active is cleared, but the current thread doesn't see + * the change yet, the timer checks are delayed until the next + * thread in the group gets a scheduler interrupt to handle the + * timer. This isn't an issue in practice because these types of + * delays with signals actually getting sent are expected. */ - if (READ_ONCE(sig->cputimer.running) && - !READ_ONCE(sig->cputimer.checking_timer)) { - struct task_cputime group_sample; + if (READ_ONCE(pct->timers_active) && !READ_ONCE(pct->expiry_active)) { + u64 samples[CPUCLOCK_MAX]; - sample_cputime_atomic(&group_sample, &sig->cputimer.cputime_atomic); + proc_sample_cputime_atomic(&sig->cputimer.cputime_atomic, + samples); - if (task_cputime_expired(&group_sample, &sig->cputime_expires)) - return 1; + if (task_cputimers_expired(samples, pct)) + return true; } if (dl_task(tsk) && tsk->dl.dl_overrun) - return 1; + return true; - return 0; + return false; } /* @@ -1132,11 +1110,12 @@ static inline int fastpath_timer_check(struct task_struct *tsk) * already updated our counts. We need to check if any timers fire now. * Interrupts are disabled. */ -void run_posix_cpu_timers(struct task_struct *tsk) +void run_posix_cpu_timers(void) { - LIST_HEAD(firing); + struct task_struct *tsk = current; struct k_itimer *timer, *next; unsigned long flags; + LIST_HEAD(firing); lockdep_assert_irqs_disabled(); @@ -1174,11 +1153,11 @@ void run_posix_cpu_timers(struct task_struct *tsk) * each timer's lock before clearing its firing flag, so no * timer call will interfere. */ - list_for_each_entry_safe(timer, next, &firing, it.cpu.entry) { + list_for_each_entry_safe(timer, next, &firing, it.cpu.elist) { int cpu_firing; spin_lock(&timer->it_lock); - list_del_init(&timer->it.cpu.entry); + list_del_init(&timer->it.cpu.elist); cpu_firing = timer->it.cpu.firing; timer->it.cpu.firing = 0; /* @@ -1196,16 +1175,18 @@ void run_posix_cpu_timers(struct task_struct *tsk) * Set one of the process-wide special case CPU timers or RLIMIT_CPU. * The tsk->sighand->siglock must be held by the caller. */ -void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, +void set_process_cpu_timer(struct task_struct *tsk, unsigned int clkid, u64 *newval, u64 *oldval) { - u64 now; - int ret; + u64 now, *nextevt; + + if (WARN_ON_ONCE(clkid >= CPUCLOCK_SCHED)) + return; - WARN_ON_ONCE(clock_idx == CPUCLOCK_SCHED); - ret = cpu_timer_sample_group(clock_idx, tsk, &now); + nextevt = &tsk->signal->posix_cputimers.bases[clkid].nextevt; + now = cpu_clock_sample_group(clkid, tsk, true); - if (oldval && ret != -EINVAL) { + if (oldval) { /* * We are setting itimer. The *oldval is absolute and we update * it to be relative, *newval argument is relative and we update @@ -1226,19 +1207,11 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, } /* - * Update expiration cache if we are the earliest timer, or eventually - * RLIMIT_CPU limit is earlier than prof_exp cpu timer expire. + * Update expiration cache if this is the earliest timer. CPUCLOCK_PROF + * expiry cache is also used by RLIMIT_CPU!. */ - switch (clock_idx) { - case CPUCLOCK_PROF: - if (expires_gt(tsk->signal->cputime_expires.prof_exp, *newval)) - tsk->signal->cputime_expires.prof_exp = *newval; - break; - case CPUCLOCK_VIRT: - if (expires_gt(tsk->signal->cputime_expires.virt_exp, *newval)) - tsk->signal->cputime_expires.virt_exp = *newval; - break; - } + if (*newval < *nextevt) + *nextevt = *newval; tick_dep_set_signal(tsk->signal, TICK_DEP_BIT_POSIX_TIMER); } @@ -1260,6 +1233,7 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, timer.it_overrun = -1; error = posix_cpu_timer_create(&timer); timer.it_process = current; + if (!error) { static struct itimerspec64 zero_it; struct restart_block *restart; @@ -1275,7 +1249,7 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, } while (!signal_pending(current)) { - if (timer.it.cpu.expires == 0) { + if (!cpu_timer_getexpires(&timer.it.cpu)) { /* * Our timer fired and was reset, below * deletion can not fail. @@ -1297,7 +1271,7 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, /* * We were interrupted by a signal. */ - expires = timer.it.cpu.expires; + expires = cpu_timer_getexpires(&timer.it.cpu); error = posix_cpu_timer_set(&timer, 0, &zero_it, &it); if (!error) { /* diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index d7f2d91acdac..0ec5b7a1d769 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -442,7 +442,7 @@ static struct k_itimer * alloc_posix_timer(void) static void k_itimer_rcu_free(struct rcu_head *head) { - struct k_itimer *tmr = container_of(head, struct k_itimer, it.rcu); + struct k_itimer *tmr = container_of(head, struct k_itimer, rcu); kmem_cache_free(posix_timers_cache, tmr); } @@ -459,7 +459,7 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set) } put_pid(tmr->it_pid); sigqueue_free(tmr->sigq); - call_rcu(&tmr->it.rcu, k_itimer_rcu_free); + call_rcu(&tmr->rcu, k_itimer_rcu_free); } static int common_timer_create(struct k_itimer *new_timer) @@ -805,6 +805,35 @@ static int common_hrtimer_try_to_cancel(struct k_itimer *timr) return hrtimer_try_to_cancel(&timr->it.real.timer); } +static void common_timer_wait_running(struct k_itimer *timer) +{ + hrtimer_cancel_wait_running(&timer->it.real.timer); +} + +/* + * On PREEMPT_RT this prevent priority inversion against softirq kthread in + * case it gets preempted while executing a timer callback. See comments in + * hrtimer_cancel_wait_running. For PREEMPT_RT=n this just results in a + * cpu_relax(). + */ +static struct k_itimer *timer_wait_running(struct k_itimer *timer, + unsigned long *flags) +{ + const struct k_clock *kc = READ_ONCE(timer->kclock); + timer_t timer_id = READ_ONCE(timer->it_id); + + /* Prevent kfree(timer) after dropping the lock */ + rcu_read_lock(); + unlock_timer(timer, *flags); + + if (!WARN_ON_ONCE(!kc->timer_wait_running)) + kc->timer_wait_running(timer); + + rcu_read_unlock(); + /* Relock the timer. It might be not longer hashed. */ + return lock_timer(timer_id, flags); +} + /* Set a POSIX.1b interval timer. */ int common_timer_set(struct k_itimer *timr, int flags, struct itimerspec64 *new_setting, @@ -844,13 +873,13 @@ int common_timer_set(struct k_itimer *timr, int flags, return 0; } -static int do_timer_settime(timer_t timer_id, int flags, +static int do_timer_settime(timer_t timer_id, int tmr_flags, struct itimerspec64 *new_spec64, struct itimerspec64 *old_spec64) { const struct k_clock *kc; struct k_itimer *timr; - unsigned long flag; + unsigned long flags; int error = 0; if (!timespec64_valid(&new_spec64->it_interval) || @@ -859,8 +888,9 @@ static int do_timer_settime(timer_t timer_id, int flags, if (old_spec64) memset(old_spec64, 0, sizeof(*old_spec64)); + + timr = lock_timer(timer_id, &flags); retry: - timr = lock_timer(timer_id, &flag); if (!timr) return -EINVAL; @@ -868,13 +898,16 @@ retry: if (WARN_ON_ONCE(!kc || !kc->timer_set)) error = -EINVAL; else - error = kc->timer_set(timr, flags, new_spec64, old_spec64); + error = kc->timer_set(timr, tmr_flags, new_spec64, old_spec64); - unlock_timer(timr, flag); if (error == TIMER_RETRY) { - old_spec64 = NULL; // We already got the old time... + // We already got the old time... + old_spec64 = NULL; + /* Unlocks and relocks the timer if it still exists */ + timr = timer_wait_running(timr, &flags); goto retry; } + unlock_timer(timr, flags); return error; } @@ -951,13 +984,15 @@ SYSCALL_DEFINE1(timer_delete, timer_t, timer_id) struct k_itimer *timer; unsigned long flags; -retry_delete: timer = lock_timer(timer_id, &flags); + +retry_delete: if (!timer) return -EINVAL; - if (timer_delete_hook(timer) == TIMER_RETRY) { - unlock_timer(timer, flags); + if (unlikely(timer_delete_hook(timer) == TIMER_RETRY)) { + /* Unlocks and relocks the timer if it still exists */ + timer = timer_wait_running(timer, &flags); goto retry_delete; } @@ -1238,6 +1273,7 @@ static const struct k_clock clock_realtime = { .timer_forward = common_hrtimer_forward, .timer_remaining = common_hrtimer_remaining, .timer_try_to_cancel = common_hrtimer_try_to_cancel, + .timer_wait_running = common_timer_wait_running, .timer_arm = common_hrtimer_arm, }; @@ -1253,6 +1289,7 @@ static const struct k_clock clock_monotonic = { .timer_forward = common_hrtimer_forward, .timer_remaining = common_hrtimer_remaining, .timer_try_to_cancel = common_hrtimer_try_to_cancel, + .timer_wait_running = common_timer_wait_running, .timer_arm = common_hrtimer_arm, }; @@ -1283,6 +1320,7 @@ static const struct k_clock clock_tai = { .timer_forward = common_hrtimer_forward, .timer_remaining = common_hrtimer_remaining, .timer_try_to_cancel = common_hrtimer_try_to_cancel, + .timer_wait_running = common_timer_wait_running, .timer_arm = common_hrtimer_arm, }; @@ -1298,6 +1336,7 @@ static const struct k_clock clock_boottime = { .timer_forward = common_hrtimer_forward, .timer_remaining = common_hrtimer_remaining, .timer_try_to_cancel = common_hrtimer_try_to_cancel, + .timer_wait_running = common_timer_wait_running, .timer_arm = common_hrtimer_arm, }; diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h index de5daa6d975a..897c29e162b9 100644 --- a/kernel/time/posix-timers.h +++ b/kernel/time/posix-timers.h @@ -24,6 +24,7 @@ struct k_clock { int (*timer_try_to_cancel)(struct k_itimer *timr); void (*timer_arm)(struct k_itimer *timr, ktime_t expires, bool absolute, bool sigev_none); + void (*timer_wait_running)(struct k_itimer *timr); }; extern const struct k_clock clock_posix_cpu; diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c index 5be6154e2fd2..c1f5bb590b5e 100644 --- a/kernel/time/tick-broadcast-hrtimer.c +++ b/kernel/time/tick-broadcast-hrtimer.c @@ -59,11 +59,16 @@ static int bc_set_next(ktime_t expires, struct clock_event_device *bc) * hrtimer_{start/cancel} functions call into tracing, * calls to these functions must be bound within RCU_NONIDLE. */ - RCU_NONIDLE({ + RCU_NONIDLE( + { bc_moved = hrtimer_try_to_cancel(&bctimer) >= 0; - if (bc_moved) + if (bc_moved) { hrtimer_start(&bctimer, expires, - HRTIMER_MODE_ABS_PINNED);}); + HRTIMER_MODE_ABS_PINNED_HARD); + } + } + ); + if (bc_moved) { /* Bind the "device" to the cpu */ bc->bound_on = smp_processor_id(); @@ -104,7 +109,7 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t) void tick_setup_hrtimer_broadcast(void) { - hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); bctimer.function = bc_handler; clockevents_register_device(&ce_broadcast_hrtimer); } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index be9707f68024..955851748dc3 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -634,10 +634,12 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) /* Forward the time to expire in the future */ hrtimer_forward(&ts->sched_timer, now, tick_period); - if (ts->nohz_mode == NOHZ_MODE_HIGHRES) - hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED); - else + if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { + hrtimer_start_expires(&ts->sched_timer, + HRTIMER_MODE_ABS_PINNED_HARD); + } else { tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); + } /* * Reset to make sure next tick stop doesn't get fooled by past @@ -802,7 +804,8 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) } if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { - hrtimer_start(&ts->sched_timer, tick, HRTIMER_MODE_ABS_PINNED); + hrtimer_start(&ts->sched_timer, tick, + HRTIMER_MODE_ABS_PINNED_HARD); } else { hrtimer_set_expires(&ts->sched_timer, tick); tick_program_event(tick, 1); @@ -1230,7 +1233,7 @@ static void tick_nohz_switch_to_nohz(void) * Recycle the hrtimer in ts, so we can share the * hrtimer_forward with the highres code. */ - hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); /* Get the next period */ next = tick_init_jiffy_update(); @@ -1327,7 +1330,7 @@ void tick_setup_sched_timer(void) /* * Emulate tick processing via per-CPU hrtimers: */ - hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); ts->sched_timer.function = tick_sched_timer; /* Get the next period (per-CPU) */ @@ -1342,7 +1345,7 @@ void tick_setup_sched_timer(void) } hrtimer_forward(&ts->sched_timer, now, tick_period); - hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED); + hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD); tick_nohz_activate(ts, NOHZ_MODE_HIGHRES); } #endif /* HIGH_RES_TIMERS */ diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 343c7ba33b1c..0e315a2e77ae 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -196,6 +196,10 @@ EXPORT_SYMBOL(jiffies_64); struct timer_base { raw_spinlock_t lock; struct timer_list *running_timer; +#ifdef CONFIG_PREEMPT_RT + spinlock_t expiry_lock; + atomic_t timer_waiters; +#endif unsigned long clk; unsigned long next_expiry; unsigned int cpu; @@ -1227,7 +1231,78 @@ int try_to_del_timer_sync(struct timer_list *timer) } EXPORT_SYMBOL(try_to_del_timer_sync); -#ifdef CONFIG_SMP +#ifdef CONFIG_PREEMPT_RT +static __init void timer_base_init_expiry_lock(struct timer_base *base) +{ + spin_lock_init(&base->expiry_lock); +} + +static inline void timer_base_lock_expiry(struct timer_base *base) +{ + spin_lock(&base->expiry_lock); +} + +static inline void timer_base_unlock_expiry(struct timer_base *base) +{ + spin_unlock(&base->expiry_lock); +} + +/* + * The counterpart to del_timer_wait_running(). + * + * If there is a waiter for base->expiry_lock, then it was waiting for the + * timer callback to finish. Drop expiry_lock and reaquire it. That allows + * the waiter to acquire the lock and make progress. + */ +static void timer_sync_wait_running(struct timer_base *base) +{ + if (atomic_read(&base->timer_waiters)) { + spin_unlock(&base->expiry_lock); + spin_lock(&base->expiry_lock); + } +} + +/* + * This function is called on PREEMPT_RT kernels when the fast path + * deletion of a timer failed because the timer callback function was + * running. + * + * This prevents priority inversion, if the softirq thread on a remote CPU + * got preempted, and it prevents a life lock when the task which tries to + * delete a timer preempted the softirq thread running the timer callback + * function. + */ +static void del_timer_wait_running(struct timer_list *timer) +{ + u32 tf; + + tf = READ_ONCE(timer->flags); + if (!(tf & TIMER_MIGRATING)) { + struct timer_base *base = get_timer_base(tf); + + /* + * Mark the base as contended and grab the expiry lock, + * which is held by the softirq across the timer + * callback. Drop the lock immediately so the softirq can + * expire the next timer. In theory the timer could already + * be running again, but that's more than unlikely and just + * causes another wait loop. + */ + atomic_inc(&base->timer_waiters); + spin_lock_bh(&base->expiry_lock); + atomic_dec(&base->timer_waiters); + spin_unlock_bh(&base->expiry_lock); + } +} +#else +static inline void timer_base_init_expiry_lock(struct timer_base *base) { } +static inline void timer_base_lock_expiry(struct timer_base *base) { } +static inline void timer_base_unlock_expiry(struct timer_base *base) { } +static inline void timer_sync_wait_running(struct timer_base *base) { } +static inline void del_timer_wait_running(struct timer_list *timer) { } +#endif + +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) /** * del_timer_sync - deactivate a timer and wait for the handler to finish. * @timer: the timer to be deactivated @@ -1266,6 +1341,8 @@ EXPORT_SYMBOL(try_to_del_timer_sync); */ int del_timer_sync(struct timer_list *timer) { + int ret; + #ifdef CONFIG_LOCKDEP unsigned long flags; @@ -1283,12 +1360,17 @@ int del_timer_sync(struct timer_list *timer) * could lead to deadlock. */ WARN_ON(in_irq() && !(timer->flags & TIMER_IRQSAFE)); - for (;;) { - int ret = try_to_del_timer_sync(timer); - if (ret >= 0) - return ret; - cpu_relax(); - } + + do { + ret = try_to_del_timer_sync(timer); + + if (unlikely(ret < 0)) { + del_timer_wait_running(timer); + cpu_relax(); + } + } while (ret < 0); + + return ret; } EXPORT_SYMBOL(del_timer_sync); #endif @@ -1360,10 +1442,13 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head) if (timer->flags & TIMER_IRQSAFE) { raw_spin_unlock(&base->lock); call_timer_fn(timer, fn, baseclk); + base->running_timer = NULL; raw_spin_lock(&base->lock); } else { raw_spin_unlock_irq(&base->lock); call_timer_fn(timer, fn, baseclk); + base->running_timer = NULL; + timer_sync_wait_running(base); raw_spin_lock_irq(&base->lock); } } @@ -1643,7 +1728,7 @@ void update_process_times(int user_tick) #endif scheduler_tick(); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) - run_posix_cpu_timers(p); + run_posix_cpu_timers(); } /** @@ -1658,6 +1743,7 @@ static inline void __run_timers(struct timer_base *base) if (!time_after_eq(jiffies, base->clk)) return; + timer_base_lock_expiry(base); raw_spin_lock_irq(&base->lock); /* @@ -1684,8 +1770,8 @@ static inline void __run_timers(struct timer_base *base) while (levels--) expire_timers(base, heads + levels); } - base->running_timer = NULL; raw_spin_unlock_irq(&base->lock); + timer_base_unlock_expiry(base); } /* @@ -1930,6 +2016,7 @@ static void __init init_timer_cpu(int cpu) base->cpu = cpu; raw_spin_lock_init(&base->lock); base->clk = jiffies; + timer_base_init_expiry_lock(base); } } diff --git a/kernel/torture.c b/kernel/torture.c index a8d9bdfba7c3..7c13f5558b71 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -263,7 +263,6 @@ static void torture_onoff_cleanup(void) onoff_task = NULL; #endif /* #ifdef CONFIG_HOTPLUG_CPU */ } -EXPORT_SYMBOL_GPL(torture_onoff_cleanup); /* * Print online/offline testing statistics. @@ -449,7 +448,6 @@ static void torture_shuffle_cleanup(void) } shuffler_task = NULL; } -EXPORT_SYMBOL_GPL(torture_shuffle_cleanup); /* * Variables for auto-shutdown. This allows "lights out" torture runs diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 98da8998c25c..e08527f50d2a 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -146,7 +146,7 @@ config FUNCTION_TRACER select GENERIC_TRACER select CONTEXT_SWITCH_TRACER select GLOB - select TASKS_RCU if PREEMPT + select TASKS_RCU if PREEMPTION help Enable the kernel to trace every kernel function. This is done by using a compiler feature to insert a small, 5-byte No-Operation @@ -179,7 +179,7 @@ config TRACE_PREEMPT_TOGGLE config PREEMPTIRQ_EVENTS bool "Enable trace events for preempt and irq disable/enable" select TRACE_IRQFLAGS - select TRACE_PREEMPT_TOGGLE if PREEMPT + select TRACE_PREEMPT_TOGGLE if PREEMPTION select GENERIC_TRACER default n help @@ -214,7 +214,7 @@ config PREEMPT_TRACER bool "Preemption-off Latency Tracer" default n depends on !ARCH_USES_GETTIMEOFFSET - depends on PREEMPT + depends on PREEMPTION select GENERIC_TRACER select TRACER_MAX_TRACE select RING_BUFFER_ALLOW_SWAP @@ -520,7 +520,8 @@ config BPF_EVENTS bool default y help - This allows the user to attach BPF programs to kprobe events. + This allows the user to attach BPF programs to kprobe, uprobe, and + tracepoint events. config DYNAMIC_EVENTS def_bool n diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index c4cc048eb594..62a50bf399d6 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2814,7 +2814,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command) * synchornize_rcu_tasks() will wait for those tasks to * execute and either schedule voluntarily or enter user space. */ - if (IS_ENABLED(CONFIG_PREEMPT)) + if (IS_ENABLED(CONFIG_PREEMPTION)) synchronize_rcu_tasks(); free_ops: diff --git a/kernel/trace/ftrace_internal.h b/kernel/trace/ftrace_internal.h index 0515a2096f90..0456e0a3dab1 100644 --- a/kernel/trace/ftrace_internal.h +++ b/kernel/trace/ftrace_internal.h @@ -6,22 +6,22 @@ /* * Traverse the ftrace_global_list, invoking all entries. The reason that we - * can use rcu_dereference_raw_notrace() is that elements removed from this list + * can use rcu_dereference_raw_check() is that elements removed from this list * are simply leaked, so there is no need to interact with a grace-period - * mechanism. The rcu_dereference_raw_notrace() calls are needed to handle + * mechanism. The rcu_dereference_raw_check() calls are needed to handle * concurrent insertions into the ftrace_global_list. * * Silly Alpha and silly pointer-speculation compiler optimizations! */ #define do_for_each_ftrace_op(op, list) \ - op = rcu_dereference_raw_notrace(list); \ + op = rcu_dereference_raw_check(list); \ do /* * Optimized for just a single item in the list (as that is the normal case). */ #define while_for_each_ftrace_op(op) \ - while (likely(op = rcu_dereference_raw_notrace((op)->next)) && \ + while (likely(op = rcu_dereference_raw_check((op)->next)) && \ unlikely((op) != &ftrace_list_end)) extern struct ftrace_ops __rcu *ftrace_ops_list; diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index 0564f6db0561..09b0b49f346e 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -267,7 +267,7 @@ static void ring_buffer_producer(void) if (consumer && !(cnt % wakeup_interval)) wake_up_process(consumer); -#ifndef CONFIG_PREEMPT +#ifndef CONFIG_PREEMPTION /* * If we are a non preempt kernel, the 10 second run will * stop everything while it runs. Instead, we will call diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index e917aa783675..252f79c435f8 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2642,10 +2642,10 @@ static void ftrace_exports(struct ring_buffer_event *event) preempt_disable_notrace(); - export = rcu_dereference_raw_notrace(ftrace_exports_list); + export = rcu_dereference_raw_check(ftrace_exports_list); while (export) { trace_process_export(export, event); - export = rcu_dereference_raw_notrace(export->next); + export = rcu_dereference_raw_check(export->next); } preempt_enable_notrace(); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 648930823b57..b89cdfe20bc1 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -255,12 +255,12 @@ void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer, local_save_flags(fbuffer->flags); fbuffer->pc = preempt_count(); /* - * If CONFIG_PREEMPT is enabled, then the tracepoint itself disables + * If CONFIG_PREEMPTION is enabled, then the tracepoint itself disables * preemption (adding one to the preempt_count). Since we are * interested in the preempt_count at the time the tracepoint was * hit, we need to subtract one to offset the increment. */ - if (IS_ENABLED(CONFIG_PREEMPT)) + if (IS_ENABLED(CONFIG_PREEMPTION)) fbuffer->pc--; fbuffer->trace_file = trace_file; diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 743b2b520d34..5e43b9664eca 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -579,8 +579,7 @@ probe_wakeup(void *ignore, struct task_struct *p) else tracing_dl = 0; - wakeup_task = p; - get_task_struct(wakeup_task); + wakeup_task = get_task_struct(p); local_save_flags(flags); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 7f9e7b9306fe..f41334ef0971 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -490,10 +490,10 @@ static void watchdog_enable(unsigned int cpu) * 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_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); hrtimer->function = watchdog_timer_fn; hrtimer_start(hrtimer, ns_to_ktime(sample_period), - HRTIMER_MODE_REL_PINNED); + HRTIMER_MODE_REL_PINNED_HARD); /* Initialize timestamp */ __touch_watchdog(); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 601d61150b65..bc2e09a8ea61 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3329,7 +3329,7 @@ EXPORT_SYMBOL_GPL(execute_in_process_context); * * Undo alloc_workqueue_attrs(). */ -static void free_workqueue_attrs(struct workqueue_attrs *attrs) +void free_workqueue_attrs(struct workqueue_attrs *attrs) { if (attrs) { free_cpumask_var(attrs->cpumask); @@ -3345,7 +3345,7 @@ static void free_workqueue_attrs(struct workqueue_attrs *attrs) * * Return: The allocated new workqueue_attr on success. %NULL on failure. */ -static struct workqueue_attrs *alloc_workqueue_attrs(void) +struct workqueue_attrs *alloc_workqueue_attrs(void) { struct workqueue_attrs *attrs; @@ -4030,16 +4030,20 @@ static int apply_workqueue_attrs_locked(struct workqueue_struct *wq, * * Performs GFP_KERNEL allocations. * + * Assumes caller has CPU hotplug read exclusion, i.e. get_online_cpus(). + * * Return: 0 on success and -errno on failure. */ -static int apply_workqueue_attrs(struct workqueue_struct *wq, +int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { int ret; - apply_wqattrs_lock(); + lockdep_assert_cpus_held(); + + mutex_lock(&wq_pool_mutex); ret = apply_workqueue_attrs_locked(wq, attrs); - apply_wqattrs_unlock(); + mutex_unlock(&wq_pool_mutex); return ret; } @@ -4152,16 +4156,21 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq) mutex_unlock(&wq->mutex); } return 0; - } else if (wq->flags & __WQ_ORDERED) { + } + + get_online_cpus(); + if (wq->flags & __WQ_ORDERED) { ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]); /* there should only be single pwq for ordering guarantee */ WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node || wq->pwqs.prev != &wq->dfl_pwq->pwqs_node), "ordering guarantee broken for workqueue %s\n", wq->name); - return ret; } else { - return apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]); + ret = apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]); } + put_online_cpus(); + + return ret; } static int wq_clamp_max_active(int max_active, unsigned int flags, |