diff options
Diffstat (limited to 'kernel')
97 files changed, 5548 insertions, 2097 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 6785982013dc..1e1a31673577 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -3,7 +3,7 @@ # Makefile for the linux kernel. # -obj-y = fork.o exec_domain.o panic.o \ +obj-y = fork.o exec_domain.o exec_state.o panic.o \ cpu.o exit.o softirq.o resource.o \ sysctl.o capability.o ptrace.o user.o \ signal.o sys.o umh.o workqueue.o pid.o task_work.o \ diff --git a/kernel/acct.c b/kernel/acct.c index cbbf79d718cf..c440d43479ca 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -249,7 +249,7 @@ static int acct_on(const char __user *name) return -EINVAL; /* Exclude procfs and sysfs. */ - if (file_inode(file)->i_sb->s_iflags & SB_I_USERNS_VISIBLE) + if (file_inode(file)->i_sb->s_type->fs_flags & FS_USERNS_MOUNT_RESTRICTED) return -EINVAL; if (!(file->f_mode & FMODE_CAN_WRITE)) diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 25c06a011825..c3f79b5a2f8c 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -21,6 +21,9 @@ #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <linux/kstrtox.h> +#include <linux/xattr.h> +#include <linux/security.h> + #include "preload/bpf_preload.h" enum bpf_type { @@ -30,6 +33,23 @@ enum bpf_type { BPF_TYPE_LINK, }; +struct bpf_fs_inode { + struct list_head xattrs; + struct simple_xattr_limits xlimits; + struct inode vfs_inode; +}; + +static inline struct bpf_fs_inode *BPF_FS_I(struct inode *inode) +{ + return container_of(inode, struct bpf_fs_inode, vfs_inode); +} + +static struct kmem_cache *bpf_fs_inode_cachep __ro_after_init; + +static int bpf_fs_initxattrs(struct inode *inode, + const struct xattr *xattr_array, void *fs_info); +static ssize_t bpf_fs_listxattr(struct dentry *dentry, char *buf, size_t size); + static void *bpf_any_get(void *raw, enum bpf_type type) { switch (type) { @@ -94,10 +114,17 @@ static void *bpf_fd_probe_obj(u32 ufd, enum bpf_type *type) } static const struct inode_operations bpf_dir_iops; +static const struct inode_operations bpf_symlink_iops; -static const struct inode_operations bpf_prog_iops = { }; -static const struct inode_operations bpf_map_iops = { }; -static const struct inode_operations bpf_link_iops = { }; +static const struct inode_operations bpf_prog_iops = { + .listxattr = bpf_fs_listxattr, +}; +static const struct inode_operations bpf_map_iops = { + .listxattr = bpf_fs_listxattr, +}; +static const struct inode_operations bpf_link_iops = { + .listxattr = bpf_fs_listxattr, +}; struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir, @@ -153,11 +180,19 @@ static struct dentry *bpf_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; + int ret; inode = bpf_get_inode(dir->i_sb, dir, mode | S_IFDIR); if (IS_ERR(inode)) return ERR_CAST(inode); + ret = security_inode_init_security(inode, dir, &dentry->d_name, + bpf_fs_initxattrs, NULL); + if (ret && ret != -EOPNOTSUPP) { + iput(inode); + return ERR_PTR(ret); + } + inode->i_op = &bpf_dir_iops; inode->i_fop = &simple_dir_operations; @@ -330,10 +365,20 @@ static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw, const struct file_operations *fops) { struct inode *dir = dentry->d_parent->d_inode; - struct inode *inode = bpf_get_inode(dir->i_sb, dir, mode); + struct inode *inode; + int ret; + + inode = bpf_get_inode(dir->i_sb, dir, mode); if (IS_ERR(inode)) return PTR_ERR(inode); + ret = security_inode_init_security(inode, dir, &dentry->d_name, + bpf_fs_initxattrs, NULL); + if (ret && ret != -EOPNOTSUPP) { + iput(inode); + return ret; + } + inode->i_op = iops; inode->i_fop = fops; inode->i_private = raw; @@ -382,9 +427,11 @@ bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags) static int bpf_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *target) { - char *link = kstrdup(target, GFP_USER | __GFP_NOWARN); struct inode *inode; + char *link; + int ret; + link = kstrdup(target, GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!link) return -ENOMEM; @@ -394,13 +441,25 @@ static int bpf_symlink(struct mnt_idmap *idmap, struct inode *dir, return PTR_ERR(inode); } - inode->i_op = &simple_symlink_inode_operations; + inode->i_op = &bpf_symlink_iops; inode->i_link = link; + ret = security_inode_init_security(inode, dir, &dentry->d_name, + bpf_fs_initxattrs, NULL); + if (ret && ret != -EOPNOTSUPP) { + iput(inode); + return ret; + } + bpf_dentry_finalize(dentry, inode, dir); return 0; } +static const struct inode_operations bpf_symlink_iops = { + .get_link = simple_get_link, + .listxattr = bpf_fs_listxattr, +}; + static const struct inode_operations bpf_dir_iops = { .lookup = bpf_lookup, .mkdir = bpf_mkdir, @@ -409,6 +468,7 @@ static const struct inode_operations bpf_dir_iops = { .rename = simple_rename, .link = simple_link, .unlink = simple_unlink, + .listxattr = bpf_fs_listxattr, }; /* pin iterator link into bpffs */ @@ -762,22 +822,147 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) return 0; } +static struct inode *bpf_fs_alloc_inode(struct super_block *sb) +{ + struct bpf_fs_inode *bi; + + bi = alloc_inode_sb(sb, bpf_fs_inode_cachep, GFP_KERNEL); + if (!bi) + return NULL; + INIT_LIST_HEAD_RCU(&bi->xattrs); + simple_xattr_limits_init(&bi->xlimits); + return &bi->vfs_inode; +} + static void bpf_destroy_inode(struct inode *inode) { + struct bpf_mount_opts *opts = inode->i_sb->s_fs_info; + struct bpf_fs_inode *bi = BPF_FS_I(inode); enum bpf_type type; - if (S_ISLNK(inode->i_mode)) - kfree(inode->i_link); if (!bpf_inode_type(inode, &type)) bpf_any_put(inode->i_private, type); - free_inode_nonrcu(inode); + simple_xattrs_free(&opts->xa_cache, &bi->xattrs, NULL); +} + +static void bpf_free_inode(struct inode *inode) +{ + if (S_ISLNK(inode->i_mode)) + kfree(inode->i_link); + kmem_cache_free(bpf_fs_inode_cachep, BPF_FS_I(inode)); +} + +static int bpf_fs_xattr_get(const struct xattr_handler *handler, + struct dentry *unused, struct inode *inode, + const char *name, void *value, size_t size) +{ + struct bpf_mount_opts *opts = inode->i_sb->s_fs_info; + struct bpf_fs_inode *bi = BPF_FS_I(inode); + + name = xattr_full_name(handler, name); + return simple_xattr_get(&opts->xa_cache, &bi->xattrs, name, value, size); +} + +enum { + BPF_FS_XATTR_UNSPEC, + BPF_FS_XATTR_SECURITY, + BPF_FS_XATTR_TRUSTED, +}; + +static int bpf_fs_xattr_set(const struct xattr_handler *handler, + struct mnt_idmap *idmap, struct dentry *unused, + struct inode *inode, const char *name, + const void *value, size_t size, int flags) +{ + struct bpf_mount_opts *opts = inode->i_sb->s_fs_info; + struct bpf_fs_inode *bi = BPF_FS_I(inode); + struct simple_xattr *old; + int err = -EINVAL; + + name = xattr_full_name(handler, name); + switch (handler->flags) { + case BPF_FS_XATTR_SECURITY: + err = simple_xattr_set_limited(&opts->xa_cache, &bi->xattrs, + &bi->xlimits, name, value, size, + flags); + break; + case BPF_FS_XATTR_TRUSTED: + old = simple_xattr_set(&opts->xa_cache, &bi->xattrs, name, + value, size, flags); + err = IS_ERR(old) ? PTR_ERR(old) : 0; + if (!err) + simple_xattr_free_rcu(old); + break; + } + if (err) + return err; + inode_set_ctime_current(inode); + return 0; +} + +static const struct xattr_handler bpf_fs_trusted_xattr_handler = { + .prefix = XATTR_TRUSTED_PREFIX, + .flags = BPF_FS_XATTR_TRUSTED, + .get = bpf_fs_xattr_get, + .set = bpf_fs_xattr_set, +}; + +static const struct xattr_handler bpf_fs_security_xattr_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .flags = BPF_FS_XATTR_SECURITY, + .get = bpf_fs_xattr_get, + .set = bpf_fs_xattr_set, +}; + +static const struct xattr_handler * const bpf_fs_xattr_handlers[] = { + &bpf_fs_trusted_xattr_handler, + &bpf_fs_security_xattr_handler, + NULL, +}; + +static ssize_t bpf_fs_listxattr(struct dentry *dentry, char *buf, size_t size) +{ + struct inode *inode = d_inode(dentry); + + return simple_xattr_list(inode, &BPF_FS_I(inode)->xattrs, buf, size); +} + +static int bpf_fs_initxattrs(struct inode *inode, + const struct xattr *xattr_array, void *fs_info) +{ + struct bpf_mount_opts *opts = inode->i_sb->s_fs_info; + struct bpf_fs_inode *bi = BPF_FS_I(inode); + const struct xattr *xattr; + int err; + + for (xattr = xattr_array; xattr->name != NULL; xattr++) { + CLASS(simple_xattr, new_xattr)(xattr->value, xattr->value_len); + if (IS_ERR(new_xattr)) + return PTR_ERR(new_xattr); + + new_xattr->name = kasprintf(GFP_KERNEL_ACCOUNT, + XATTR_SECURITY_PREFIX "%s", + xattr->name); + if (!new_xattr->name) + return -ENOMEM; + + err = simple_xattr_add_limited(&opts->xa_cache, &bi->xattrs, + &bi->xlimits, new_xattr); + if (err) + return err; + + retain_and_null_ptr(new_xattr); + } + return 0; } const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = inode_just_drop, .show_options = bpf_show_options, + .alloc_inode = bpf_fs_alloc_inode, .destroy_inode = bpf_destroy_inode, + .free_inode = bpf_free_inode, }; enum { @@ -996,25 +1181,38 @@ out: static int bpf_fill_super(struct super_block *sb, struct fs_context *fc) { - static const struct tree_descr bpf_rfiles[] = { { "" } }; struct bpf_mount_opts *opts = sb->s_fs_info; struct inode *inode; - int ret; /* Mounting an instance of BPF FS requires privileges */ if (fc->user_ns != &init_user_ns && !capable(CAP_SYS_ADMIN)) return -EPERM; - ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles); - if (ret) - return ret; - + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; + sb->s_magic = BPF_FS_MAGIC; sb->s_op = &bpf_super_ops; + sb->s_xattr = bpf_fs_xattr_handlers; + sb->s_iflags |= SB_I_NOEXEC; + sb->s_iflags |= SB_I_NODEV; + sb->s_time_gran = 1; + + inode = bpf_get_inode(sb, NULL, S_IFDIR | 0777); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + inode->i_ino = 1; + inode->i_op = &bpf_dir_iops; + inode->i_fop = &simple_dir_operations; + set_nlink(inode, 2); + + sb->s_root = d_make_root(inode); + if (!sb->s_root) + return -ENOMEM; - inode = sb->s_root->d_inode; + inode = d_inode(sb->s_root); inode->i_uid = opts->uid; inode->i_gid = opts->gid; - inode->i_op = &bpf_dir_iops; inode->i_mode &= ~S_IALLUGO; populate_bpffs(sb->s_root); inode->i_mode |= S_ISVTX | opts->mode; @@ -1068,6 +1266,7 @@ static void bpf_kill_super(struct super_block *sb) struct bpf_mount_opts *opts = sb->s_fs_info; kill_anon_super(sb); + simple_xattr_cache_cleanup(&opts->xa_cache); kfree(opts); } @@ -1080,18 +1279,37 @@ static struct file_system_type bpf_fs_type = { .fs_flags = FS_USERNS_MOUNT, }; +static void bpf_fs_inode_init_once(void *foo) +{ + struct bpf_fs_inode *bi = foo; + + inode_init_once(&bi->vfs_inode); +} + static int __init bpf_init(void) { int ret; + bpf_fs_inode_cachep = kmem_cache_create("bpf_fs_inode_cache", + sizeof(struct bpf_fs_inode), + 0, SLAB_ACCOUNT, + bpf_fs_inode_init_once); + if (!bpf_fs_inode_cachep) + return -ENOMEM; + ret = sysfs_create_mount_point(fs_kobj, "bpf"); if (ret) - return ret; + goto out_cache; ret = register_filesystem(&bpf_fs_type); - if (ret) + if (ret) { sysfs_remove_mount_point(fs_kobj, "bpf"); + goto out_cache; + } + return 0; +out_cache: + kmem_cache_destroy(bpf_fs_inode_cachep); return ret; } fs_initcall(bpf_init); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 5c33ab20cc20..c9e14fda3d6f 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1811,9 +1811,9 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, * Compute add/delete mask to/from effective_cpus * * For valid partition: - * addmask = exclusive_cpus & ~newmask + * addmask = effective_xcpus & ~newmask * & parent->effective_xcpus - * delmask = newmask & ~exclusive_cpus + * delmask = newmask & ~effective_xcpus * & parent->effective_xcpus * * For invalid partition: @@ -1825,11 +1825,11 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, deleting = cpumask_and(tmp->delmask, newmask, parent->effective_xcpus); } else { - cpumask_andnot(tmp->addmask, xcpus, newmask); + cpumask_andnot(tmp->addmask, cs->effective_xcpus, newmask); adding = cpumask_and(tmp->addmask, tmp->addmask, parent->effective_xcpus); - cpumask_andnot(tmp->delmask, newmask, xcpus); + cpumask_andnot(tmp->delmask, newmask, cs->effective_xcpus); deleting = cpumask_and(tmp->delmask, tmp->delmask, parent->effective_xcpus); } @@ -1868,7 +1868,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, part_error = PERR_NOCPUS; deleting = false; adding = cpumask_and(tmp->addmask, - xcpus, parent->effective_xcpus); + cs->effective_xcpus, parent->effective_xcpus); } } else { /* @@ -1890,7 +1890,8 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, part_error = PERR_NOCPUS; if (is_partition_valid(cs)) adding = cpumask_and(tmp->addmask, - xcpus, parent->effective_xcpus); + cs->effective_xcpus, + parent->effective_xcpus); } else if (is_partition_invalid(cs) && !cpumask_empty(xcpus) && cpumask_subset(xcpus, parent->effective_xcpus)) { struct cgroup_subsys_state *css; diff --git a/kernel/configs/hardening.config b/kernel/configs/hardening.config index 7c3924614e01..26831a2a5739 100644 --- a/kernel/configs/hardening.config +++ b/kernel/configs/hardening.config @@ -22,7 +22,7 @@ CONFIG_SLAB_FREELIST_RANDOM=y CONFIG_SLAB_FREELIST_HARDENED=y CONFIG_SLAB_BUCKETS=y CONFIG_SHUFFLE_PAGE_ALLOCATOR=y -CONFIG_RANDOM_KMALLOC_CACHES=y +CONFIG_KMALLOC_PARTITION_CACHES=y # Sanity check userspace page table mappings. CONFIG_PAGE_TABLE_CHECK=y diff --git a/kernel/cpu.c b/kernel/cpu.c index bc4f7a9ba64e..f975bb34915b 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2639,7 +2639,7 @@ static void cpuhp_offline_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); - dev->offline = true; + dev_set_offline(dev); /* Tell user space about the state change */ kobject_uevent(&dev->kobj, KOBJ_OFFLINE); } @@ -2648,7 +2648,7 @@ static void cpuhp_online_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); - dev->offline = false; + dev_clear_offline(dev); /* Tell user space about the state change */ kobject_uevent(&dev->kobj, KOBJ_ONLINE); } diff --git a/kernel/cred.c b/kernel/cred.c index 12a7b1ce5131..3df4e15bd67f 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -384,8 +384,9 @@ int commit_creds(struct cred *new) !uid_eq(old->fsuid, new->fsuid) || !gid_eq(old->fsgid, new->fsgid) || !cred_cap_issubset(old, new)) { + /* mm-less tasks share init_task's exec_state */ if (task->mm) - set_dumpable(task->mm, suid_dumpable); + task_exec_state_set_dumpable(suid_dumpable); task->pdeath_signal = 0; /* * If a task drops privileges and becomes nondumpable, diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 3248f8b4d096..2c0e2cd89b5e 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -1556,7 +1556,7 @@ void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, struct dma_debug_entry ref = { .type = dma_debug_sg, .dev = dev, - .paddr = sg_phys(sg), + .paddr = sg_phys(s), .dev_addr = sg_dma_address(s), .size = sg_dma_len(s), .direction = direction, diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 583c5922bca2..4391b797d4db 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -476,7 +476,7 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, * must be mapped with CPU physical address and not PCI * bus addresses. */ - break; + fallthrough; case PCI_P2PDMA_MAP_NONE: need_sync = true; sg->dma_address = dma_direct_map_phys(dev, sg_phys(sg), diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index e6b07f160d20..4eedb1a6273a 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -126,11 +126,9 @@ static bool dma_go_direct(struct device *dev, dma_addr_t mask, if (likely(!ops)) return true; -#ifdef CONFIG_DMA_OPS_BYPASS - if (dev->dma_ops_bypass) + if (IS_ENABLED(CONFIG_DMA_OPS_BYPASS) && dev_dma_ops_bypass(dev)) return min_not_zero(mask, dev->bus_dma_limit) >= dma_direct_get_required_mask(dev); -#endif return false; } @@ -472,7 +470,7 @@ bool dma_need_unmap(struct device *dev) { if (!dma_map_direct(dev, get_dma_ops(dev))) return true; - if (!dev->dma_skip_sync) + if (!dev_dma_skip_sync(dev)) return true; return IS_ENABLED(CONFIG_DMA_API_DEBUG); } @@ -488,16 +486,16 @@ static void dma_setup_need_sync(struct device *dev) * mapping, if any. During the device initialization, it's * enough to check only for the DMA coherence. */ - dev->dma_skip_sync = dev_is_dma_coherent(dev); + dev_assign_dma_skip_sync(dev, dev_is_dma_coherent(dev)); else if (!ops->sync_single_for_device && !ops->sync_single_for_cpu && !ops->sync_sg_for_device && !ops->sync_sg_for_cpu) /* * Synchronization is not possible when none of DMA sync ops * is set. */ - dev->dma_skip_sync = true; + dev_set_dma_skip_sync(dev); else - dev->dma_skip_sync = false; + dev_clear_dma_skip_sync(dev); } #else /* !CONFIG_DMA_NEED_SYNC */ static inline void dma_setup_need_sync(struct device *dev) { } diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 19d2244a9fef..e3d381fd3d25 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -1,11 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/irq-entry-common.h> -#include <linux/resume_user_mode.h> +#include <linux/futex.h> #include <linux/highmem.h> +#include <linux/irq-entry-common.h> #include <linux/jump_label.h> #include <linux/kmsan.h> #include <linux/livepatch.h> +#include <linux/resume_user_mode.h> #include <linux/tick.h> /* Workaround to allow gradual conversion of architecture code */ @@ -60,8 +61,10 @@ static __always_inline unsigned long __exit_to_user_mode_loop(struct pt_regs *re if (ti_work & _TIF_PATCH_PENDING) klp_update_patch_state(current); - if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) + if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) { + futex_fixup_robust_unlock(regs); arch_do_signal_or_restart(regs); + } if (ti_work & _TIF_NOTIFY_RESUME) resume_user_mode_work(regs); diff --git a/kernel/events/core.c b/kernel/events/core.c index 7935d5663944..95d806bba654 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -58,6 +58,7 @@ #include <linux/percpu-rwsem.h> #include <linux/unwind_deferred.h> #include <linux/kvm_types.h> +#include <linux/seq_file.h> #include "internal.h" @@ -7546,6 +7547,33 @@ static int perf_fasync(int fd, struct file *filp, int on) return 0; } +static void perf_show_fdinfo(struct seq_file *m, struct file *f) +{ + struct perf_event *event = f->private_data; + struct perf_event_context *ctx; + struct mutex *child_mutex; + + ctx = perf_event_ctx_lock(event); + child_mutex = event->parent ? &event->parent->child_mutex : &event->child_mutex; + mutex_lock(child_mutex); + + seq_printf(m, "perf_event_attr.type:\t%u\n", event->orig_type); + if (event->pmu) + seq_printf(m, "pmu_type:\t%u\n", event->pmu->type); + seq_printf(m, "perf_event_attr.config:\t0x%llx\n", (unsigned long long)event->attr.config); + seq_printf(m, "perf_event_attr.config1:\t0x%llx\n", + (unsigned long long)event->attr.config1); + seq_printf(m, "perf_event_attr.config2:\t0x%llx\n", + (unsigned long long)event->attr.config2); + seq_printf(m, "perf_event_attr.config3:\t0x%llx\n", + (unsigned long long)event->attr.config3); + seq_printf(m, "perf_event_attr.config4:\t0x%llx\n", + (unsigned long long)event->attr.config4); + + mutex_unlock(child_mutex); + perf_event_ctx_unlock(event, ctx); +} + static const struct file_operations perf_fops = { .release = perf_release, .read = perf_read, @@ -7554,6 +7582,7 @@ static const struct file_operations perf_fops = { .compat_ioctl = perf_compat_ioctl, .mmap = perf_mmap, .fasync = perf_fasync, + .show_fdinfo = perf_show_fdinfo, }; /* diff --git a/kernel/exec_state.c b/kernel/exec_state.c new file mode 100644 index 000000000000..6034f4b4808f --- /dev/null +++ b/kernel/exec_state.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2026 Christian Brauner <brauner@kernel.org> */ +#include <linux/init.h> +#include <linux/rcupdate.h> +#include <linux/refcount.h> +#include <linux/sched.h> +#include <linux/sched/coredump.h> +#include <linux/sched/exec_state.h> +#include <linux/sched/signal.h> +#include <linux/slab.h> +#include <linux/user_namespace.h> + +static struct kmem_cache *task_exec_state_cachep; + +static void __free_task_exec_state(struct rcu_head *rcu) +{ + struct task_exec_state *exec_state = container_of(rcu, struct task_exec_state, rcu); + + put_user_ns(exec_state->user_ns); + kmem_cache_free(task_exec_state_cachep, exec_state); +} + +void put_task_exec_state(struct task_exec_state *exec_state) +{ + if (exec_state && refcount_dec_and_test(&exec_state->count)) + call_rcu(&exec_state->rcu, __free_task_exec_state); +} + +struct task_exec_state *alloc_task_exec_state(struct user_namespace *user_ns) +{ + struct task_exec_state *exec_state; + + exec_state = kmem_cache_alloc(task_exec_state_cachep, GFP_KERNEL); + if (!exec_state) + return NULL; + refcount_set(&exec_state->count, 1); + exec_state->dumpable = TASK_DUMPABLE_OFF; + exec_state->user_ns = get_user_ns(user_ns); + return exec_state; +} + +struct task_exec_state *task_exec_state_rcu(const struct task_struct *tsk) +{ + struct task_exec_state *exec_state; + + exec_state = rcu_dereference_check(tsk->exec_state, + lockdep_is_held(&tsk->alloc_lock)); + WARN_ON_ONCE(!exec_state); + return exec_state; +} + +struct task_exec_state *task_exec_state_replace(struct task_struct *tsk, + struct task_exec_state *exec_state) +{ + /* + * Updates must hold both locks so callers needing a consistent + * snapshot of mm + dumpability are covered. + */ + lockdep_assert_held(&tsk->alloc_lock); + lockdep_assert_held_write(&tsk->signal->exec_update_lock); + + return rcu_replace_pointer(tsk->exec_state, exec_state, true); +} + +/* + * The non-CLONE_VM clone path: allocate a fresh exec_state and + * inherit the parent's dumpable mode and user_ns reference. CLONE_VM + * siblings refcount-share via copy_exec_state() in fork.c; only this + * path and execve() ever allocate. + */ +int task_exec_state_copy(struct task_struct *tsk) +{ + struct task_exec_state *src, *dst; + + src = rcu_dereference_protected(current->exec_state, true); + dst = alloc_task_exec_state(src->user_ns); + if (!dst) + return -ENOMEM; + dst->dumpable = READ_ONCE(src->dumpable); + rcu_assign_pointer(tsk->exec_state, dst); + return 0; +} + +/* + * Store TASK_DUMPABLE_* on current->exec_state. All callers + * (commit_creds, begin_new_exec, prctl(PR_SET_DUMPABLE)) act on the + * running task, which guarantees ->exec_state is allocated and cannot + * be replaced under us. + */ +void task_exec_state_set_dumpable(enum task_dumpable value) +{ + struct task_exec_state *exec_state; + + if (WARN_ON_ONCE(value > TASK_DUMPABLE_ROOT)) + value = TASK_DUMPABLE_OFF; + + exec_state = rcu_dereference_protected(current->exec_state, true); + /* mm-less tasks share init_task's exec_state; never mutate it */ + if (WARN_ON_ONCE(exec_state == &init_task_exec_state)) + return; + WRITE_ONCE(exec_state->dumpable, value); +} + +enum task_dumpable task_exec_state_get_dumpable(struct task_struct *task) +{ + struct task_exec_state *exec_state; + + guard(rcu)(); + exec_state = rcu_dereference(task->exec_state); + return READ_ONCE(exec_state->dumpable); +} + +void __init exec_state_init(void) +{ + task_exec_state_cachep = kmem_cache_create("task_exec_state", + sizeof(struct task_exec_state), 0, + SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, + NULL); +} diff --git a/kernel/exit.c b/kernel/exit.c index f50d73c272d6..1056422bc101 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -543,6 +543,32 @@ void mm_update_next_owner(struct mm_struct *mm) } #endif /* CONFIG_MEMCG */ +#if defined(CONFIG_SCHED_CACHE) && defined(CONFIG_NUMA_BALANCING) +/* + * Subtract the memory footprint of the current task from + * mm. + */ +static void exit_mm_sched_cache(struct mm_struct *mm) +{ + unsigned long fp, sub; + + if (!current->total_numa_faults) + return; + /* + * No lock protection due to performance considerations. + * Make sure mm->sc_stat.footprint does not become + * negative. + */ + fp = READ_ONCE(mm->sc_stat.footprint); + sub = min(fp, current->total_numa_faults); + WRITE_ONCE(mm->sc_stat.footprint, fp - sub); +} +#else +static inline void exit_mm_sched_cache(struct mm_struct *mm) +{ +} +#endif /* CONFIG_SCHED_CACHE CONFIG_NUMA_BALANCING */ + /* * Turn us into a lazy TLB process if we * aren't already.. @@ -554,6 +580,9 @@ static void exit_mm(void) exit_mm_release(current, mm); if (!mm) return; + + exit_mm_sched_cache(mm); + mmap_read_lock(mm); mmgrab_lazy_tlb(mm); BUG_ON(mm != current->active_mm); @@ -571,7 +600,6 @@ static void exit_mm(void) */ smp_mb__after_spinlock(); local_irq_disable(); - current->user_dumpable = (get_dumpable(mm) == SUID_DUMP_USER); current->mm = NULL; membarrier_update_current_mm(NULL); enter_lazy_tlb(mm, current); @@ -989,8 +1017,8 @@ void __noreturn do_exit(long code) proc_exit_connector(tsk); mpol_put_task_policy(tsk); #ifdef CONFIG_FUTEX - if (unlikely(current->pi_state_cache)) - kfree(current->pi_state_cache); + if (unlikely(current->futex.pi_state_cache)) + kfree(current->futex.pi_state_cache); #endif /* * Make sure we are holding no locks: diff --git a/kernel/fork.c b/kernel/fork.c index 5f3fdfdb14c7..addc555a1077 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -23,6 +23,7 @@ #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/sched/ext.h> +#include <linux/sched/exec_state.h> #include <linux/seq_file.h> #include <linux/rtmutex.h> #include <linux/init.h> @@ -555,6 +556,7 @@ void free_task(struct task_struct *tsk) if (tsk->flags & PF_KTHREAD) free_kthread_struct(tsk); bpf_task_storage_free(tsk); + put_task_exec_state(rcu_access_pointer(tsk->exec_state)); free_task_struct(tsk); } EXPORT_SYMBOL(free_task); @@ -726,12 +728,12 @@ void __mmdrop(struct mm_struct *mm) cleanup_lazy_tlbs(mm); WARN_ON_ONCE(mm == current->active_mm); + mm_destroy_sched(mm); mm_free_pgd(mm); mm_free_id(mm); destroy_context(mm); mmu_notifier_subscriptions_destroy(mm); check_mm(mm); - put_user_ns(mm->user_ns); mm_pasid_drop(mm); mm_destroy_cid(mm); percpu_counter_destroy_many(mm->rss_stat, NR_MM_COUNTERS); @@ -946,6 +948,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->seccomp.filter = NULL; #endif + RCU_INIT_POINTER(tsk->exec_state, NULL); + setup_thread_stack(tsk, orig); clear_user_return_notifier(tsk); clear_tsk_need_resched(tsk); @@ -1072,8 +1076,7 @@ static void mmap_init_lock(struct mm_struct *mm) #endif } -static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, - struct user_namespace *user_ns) +static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) { mt_init_flags(&mm->mm_mt, MM_MT_FLAGS); mt_set_external_lock(&mm->mm_mt, &mm->mmap_lock); @@ -1101,6 +1104,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, #endif mm_init_uprobes_state(mm); hugetlb_count_init(mm); + futex_mm_init(mm); mm_flags_clear_all(mm); if (current->mm) { @@ -1113,11 +1117,8 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm->def_flags = 0; } - if (futex_mm_init(mm)) - goto fail_mm_init; - if (mm_alloc_pgd(mm)) - goto fail_nopgd; + goto fail_mm_init; if (mm_alloc_id(mm)) goto fail_noid; @@ -1128,15 +1129,19 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, if (mm_alloc_cid(mm, p)) goto fail_cid; + if (mm_alloc_sched(mm)) + goto fail_sched; + if (percpu_counter_init_many(mm->rss_stat, 0, GFP_KERNEL_ACCOUNT, NR_MM_COUNTERS)) goto fail_pcpu; - mm->user_ns = get_user_ns(user_ns); lru_gen_init_mm(mm); return mm; fail_pcpu: + mm_destroy_sched(mm); +fail_sched: mm_destroy_cid(mm); fail_cid: destroy_context(mm); @@ -1144,8 +1149,6 @@ fail_nocontext: mm_free_id(mm); fail_noid: mm_free_pgd(mm); -fail_nopgd: - futex_hash_free(mm); fail_mm_init: free_mm(mm); return NULL; @@ -1163,7 +1166,7 @@ struct mm_struct *mm_alloc(void) return NULL; memset(mm, 0, sizeof(*mm)); - return mm_init(mm, current, current_user_ns()); + return mm_init(mm, current); } EXPORT_SYMBOL_IF_KUNIT(mm_alloc); @@ -1527,7 +1530,7 @@ static struct mm_struct *dup_mm(struct task_struct *tsk, memcpy(mm, oldmm, sizeof(*mm)); - if (!mm_init(mm, tsk, mm->user_ns)) + if (!mm_init(mm, tsk)) goto fail_nomem; uprobe_start_dup_mmap(); @@ -1593,6 +1596,22 @@ static int copy_mm(u64 clone_flags, struct task_struct *tsk) return 0; } +static int copy_exec_state(u64 clone_flags, struct task_struct *tsk) +{ + struct task_exec_state *exec_state; + + /* CLONE_VM siblings refcount-share the parent's exec_state. */ + if (clone_flags & CLONE_VM) { + exec_state = rcu_dereference_protected(current->exec_state, true); + refcount_inc(&exec_state->count); + rcu_assign_pointer(tsk->exec_state, exec_state); + return 0; + } + + /* Everyone else inherits a fresh copy. */ + return task_exec_state_copy(tsk); +} + static int copy_fs(u64 clone_flags, struct task_struct *tsk) { struct fs_struct *fs = current->fs; @@ -2090,6 +2109,9 @@ __latent_entropy struct task_struct *copy_process( p = dup_task_struct(current, node); if (!p) goto fork_out; + retval = copy_exec_state(clone_flags, p); + if (retval) + goto bad_fork_free; p->flags &= ~PF_KTHREAD; if (args->kthread) p->flags |= PF_KTHREAD; @@ -2218,6 +2240,7 @@ __latent_entropy struct task_struct *copy_process( lockdep_init_task(p); p->blocked_on = NULL; /* not blocked yet */ + p->blocked_donor = NULL; /* nobody is boosting p yet */ #ifdef CONFIG_BCACHE p->sequential_io = 0; @@ -2664,8 +2687,6 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) * * 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. */ pid_t kernel_clone(struct kernel_clone_args *args) { @@ -2700,6 +2721,9 @@ pid_t kernel_clone(struct kernel_clone_args *args) (args->pidfd == args->parent_tid)) return -EINVAL; + if (!valid_signal(args->exit_signal)) + return -EINVAL; + /* * Determine whether and which event to report to ptracer. When * called from kernel_thread or CLONE_UNTRACED is explicitly @@ -2898,11 +2922,9 @@ static noinline int copy_clone_args_from_user(struct kernel_clone_args *kargs, return -EINVAL; /* - * Verify that higher 32bits of exit_signal are unset and that - * it is a valid signal + * Verify that higher 32bits of exit_signal are unset */ - if (unlikely((args.exit_signal & ~((u64)CSIGNAL)) || - !valid_signal(args.exit_signal))) + if (unlikely(args.exit_signal & ~((u64)CSIGNAL))) return -EINVAL; if ((args.flags & CLONE_INTO_CGROUP) && @@ -3098,6 +3120,7 @@ void __init proc_caches_init(void) sizeof(struct signal_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); + exec_state_init(); files_cachep = kmem_cache_create("files_cache", sizeof(struct files_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, diff --git a/kernel/futex/core.c b/kernel/futex/core.c index ff2a4fb2993f..179b26e9c934 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -32,18 +32,21 @@ * "But they come in a choice of three flavours!" */ #include <linux/compat.h> -#include <linux/jhash.h> -#include <linux/pagemap.h> #include <linux/debugfs.h> -#include <linux/plist.h> +#include <linux/fault-inject.h> #include <linux/gfp.h> -#include <linux/vmalloc.h> +#include <linux/jhash.h> #include <linux/memblock.h> -#include <linux/fault-inject.h> -#include <linux/slab.h> -#include <linux/prctl.h> #include <linux/mempolicy.h> #include <linux/mmap_lock.h> +#include <linux/pagemap.h> +#include <linux/plist.h> +#include <linux/prctl.h> +#include <linux/rseq.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> + +#include <vdso/futex.h> #include "futex.h" #include "../locking/rtmutex_common.h" @@ -124,7 +127,7 @@ late_initcall(fail_futex_debugfs); #endif /* CONFIG_FAIL_FUTEX */ static struct futex_hash_bucket * -__futex_hash(union futex_key *key, struct futex_private_hash *fph); +__futex_hash(union futex_key *key, struct futex_private_hash *fph, struct futex_private_hash **fph_p); #ifdef CONFIG_FUTEX_PRIVATE_HASH static bool futex_ref_get(struct futex_private_hash *fph); @@ -133,15 +136,6 @@ static bool futex_ref_is_dead(struct futex_private_hash *fph); enum { FR_PERCPU = 0, FR_ATOMIC }; -static inline bool futex_key_is_private(union futex_key *key) -{ - /* - * Relies on get_futex_key() to set either bit for shared - * futexes -- see comment with union futex_key. - */ - return !(key->both.offset & (FUT_OFF_INODE | FUT_OFF_MMSHARED)); -} - static bool futex_private_hash_get(struct futex_private_hash *fph) { return futex_ref_get(fph); @@ -149,51 +143,18 @@ static bool futex_private_hash_get(struct futex_private_hash *fph) void futex_private_hash_put(struct futex_private_hash *fph) { - if (futex_ref_put(fph)) + if (fph && futex_ref_put(fph)) wake_up_var(fph->mm); } -/** - * futex_hash_get - Get an additional reference for the local hash. - * @hb: ptr to the private local hash. - * - * Obtain an additional reference for the already obtained hash bucket. The - * caller must already own an reference. - */ -void futex_hash_get(struct futex_hash_bucket *hb) -{ - struct futex_private_hash *fph = hb->priv; - - if (!fph) - return; - WARN_ON_ONCE(!futex_private_hash_get(fph)); -} - -void futex_hash_put(struct futex_hash_bucket *hb) -{ - struct futex_private_hash *fph = hb->priv; - - if (!fph) - return; - futex_private_hash_put(fph); -} - static struct futex_hash_bucket * __futex_hash_private(union futex_key *key, struct futex_private_hash *fph) { u32 hash; - if (!futex_key_is_private(key)) - return NULL; - - if (!fph) - fph = rcu_dereference(key->private.mm->futex_phash); - if (!fph || !fph->hash_mask) - return NULL; - - hash = jhash2((void *)&key->private.address, - sizeof(key->private.address) / 4, + hash = jhash2((void *)&key->private.address, sizeof(key->private.address) / 4, key->both.offset); + return &fph->queues[hash & fph->hash_mask]; } @@ -211,13 +172,12 @@ static void futex_rehash_private(struct futex_private_hash *old, spin_lock(&hb_old->lock); plist_for_each_entry_safe(this, tmp, &hb_old->chain, list) { - plist_del(&this->list, &hb_old->chain); futex_hb_waiters_dec(hb_old); WARN_ON_ONCE(this->lock_ptr != &hb_old->lock); - hb_new = __futex_hash(&this->key, new); + hb_new = __futex_hash(&this->key, new, NULL); futex_hb_waiters_inc(hb_new); /* * The new pointer isn't published yet but an already @@ -232,18 +192,17 @@ static void futex_rehash_private(struct futex_private_hash *old, } } -static bool __futex_pivot_hash(struct mm_struct *mm, - struct futex_private_hash *new) +static bool __futex_pivot_hash(struct mm_struct *mm, struct futex_private_hash *new) { + struct futex_mm_phash *mmph = &mm->futex.phash; struct futex_private_hash *fph; - WARN_ON_ONCE(mm->futex_phash_new); + WARN_ON_ONCE(mmph->hash_new); - fph = rcu_dereference_protected(mm->futex_phash, - lockdep_is_held(&mm->futex_hash_lock)); + fph = rcu_dereference_protected(mmph->hash, lockdep_is_held(&mmph->lock)); if (fph) { if (!futex_ref_is_dead(fph)) { - mm->futex_phash_new = new; + mmph->hash_new = new; return false; } @@ -251,8 +210,8 @@ static bool __futex_pivot_hash(struct mm_struct *mm, } new->state = FR_PERCPU; scoped_guard(rcu) { - mm->futex_batches = get_state_synchronize_rcu(); - rcu_assign_pointer(mm->futex_phash, new); + mmph->batches = get_state_synchronize_rcu(); + rcu_assign_pointer(mmph->hash, new); } kvfree_rcu(fph, rcu); return true; @@ -260,20 +219,19 @@ static bool __futex_pivot_hash(struct mm_struct *mm, static void futex_pivot_hash(struct mm_struct *mm) { - scoped_guard(mutex, &mm->futex_hash_lock) { + scoped_guard(mutex, &mm->futex.phash.lock) { struct futex_private_hash *fph; - fph = mm->futex_phash_new; + fph = mm->futex.phash.hash_new; if (fph) { - mm->futex_phash_new = NULL; + mm->futex.phash.hash_new = NULL; __futex_pivot_hash(mm, fph); } } } -struct futex_private_hash *futex_private_hash(void) +struct futex_private_hash *futex_private_hash(struct mm_struct *mm) { - struct mm_struct *mm = current->mm; /* * Ideally we don't loop. If there is a replacement in progress * then a new private hash is already prepared and a reference can't be @@ -288,7 +246,7 @@ again: scoped_guard(rcu) { struct futex_private_hash *fph; - fph = rcu_dereference(mm->futex_phash); + fph = rcu_dereference(mm->futex.phash.hash); if (!fph) return NULL; @@ -299,18 +257,17 @@ again: goto again; } -struct futex_hash_bucket *futex_hash(union futex_key *key) +struct futex_bucket_ref futex_hash(union futex_key *key) { - struct futex_private_hash *fph; - struct futex_hash_bucket *hb; - again: scoped_guard(rcu) { - hb = __futex_hash(key, NULL); - fph = hb->priv; + struct futex_private_hash *fph = NULL; + struct futex_hash_bucket *hb; + + hb = __futex_hash(key, NULL, &fph); if (!fph || futex_private_hash_get(fph)) - return hb; + return (struct futex_bucket_ref){ .hb = hb, .fph = fph }; } futex_pivot_hash(key->private.mm); goto again; @@ -318,15 +275,9 @@ again: #else /* !CONFIG_FUTEX_PRIVATE_HASH */ -static struct futex_hash_bucket * -__futex_hash_private(union futex_key *key, struct futex_private_hash *fph) +struct futex_bucket_ref futex_hash(union futex_key *key) { - return NULL; -} - -struct futex_hash_bucket *futex_hash(union futex_key *key) -{ - return __futex_hash(key, NULL); + return (struct futex_bucket_ref){ .hb = __futex_hash(key, NULL, NULL), .fph = NULL }; } #endif /* CONFIG_FUTEX_PRIVATE_HASH */ @@ -404,6 +355,8 @@ static int futex_mpol(struct mm_struct *mm, unsigned long addr) * __futex_hash - Return the hash bucket * @key: Pointer to the futex key for which the hash is calculated * @fph: Pointer to private hash if known + * @fph_p: Pointer to a private hash pointer; output for the private hash + * used when set. * * We hash on the keys returned from get_futex_key (see below) and return the * corresponding hash bucket. @@ -412,21 +365,24 @@ static int futex_mpol(struct mm_struct *mm, unsigned long addr) * global hash is returned. */ static struct futex_hash_bucket * -__futex_hash(union futex_key *key, struct futex_private_hash *fph) +__futex_hash(union futex_key *key, struct futex_private_hash *fph, struct futex_private_hash **fph_p) { int node = key->both.node; u32 hash; - if (node == FUTEX_NO_NODE) { - struct futex_hash_bucket *hb; - - hb = __futex_hash_private(key, fph); - if (hb) - return hb; +#ifdef CONFIG_FUTEX_PRIVATE_HASH + if (node == FUTEX_NO_NODE && futex_key_is_private(key)) { + if (!fph) + fph = rcu_dereference(key->private.mm->futex.phash.hash); + if (fph && fph->hash_mask) { + if (fph_p) + *fph_p = fph; + return __futex_hash_private(key, fph); + } } +#endif - hash = jhash2((u32 *)key, - offsetof(typeof(*key), both.offset) / sizeof(u32), + hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / sizeof(u32), key->both.offset); if (node == FUTEX_NO_NODE) { @@ -441,8 +397,7 @@ __futex_hash(union futex_key *key, struct futex_private_hash *fph) */ node = (hash >> futex_hashshift) % nr_node_ids; if (!node_possible(node)) { - node = find_next_bit_wrap(node_possible_map.bits, - nr_node_ids, node); + node = find_next_bit_wrap(node_possible_map.bits, nr_node_ids, node); } } @@ -459,9 +414,8 @@ __futex_hash(union futex_key *key, struct futex_private_hash *fph) * Return: Initialized hrtimer_sleeper structure or NULL if no timeout * value given */ -struct hrtimer_sleeper * -futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, - int flags, u64 range_ns) +struct hrtimer_sleeper *futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, + int flags, u64 range_ns) { if (!time) return NULL; @@ -829,7 +783,7 @@ void wait_for_owner_exiting(int ret, struct task_struct *exiting) if (WARN_ON_ONCE(ret == -EBUSY && !exiting)) return; - mutex_lock(&exiting->futex_exit_mutex); + mutex_lock(&exiting->futex.exit_mutex); /* * No point in doing state checking here. If the waiter got here * while the task was in exec()->exec_futex_release() then it can @@ -838,7 +792,7 @@ void wait_for_owner_exiting(int ret, struct task_struct *exiting) * already. Highly unlikely and not a problem. Just one more round * through the futex maze. */ - mutex_unlock(&exiting->futex_exit_mutex); + mutex_unlock(&exiting->futex.exit_mutex); put_task_struct(exiting); } @@ -1012,8 +966,9 @@ void futex_unqueue_pi(struct futex_q *q) * dying task, and do notification if so: */ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, - bool pi, bool pending_op) + unsigned int mod, bool pending_op) { + bool pi = !!(mod & FUTEX_ROBUST_MOD_PI); u32 uval, nval, mval; pid_t owner; int err; @@ -1047,7 +1002,7 @@ retry: * * In both cases the following conditions are met: * - * 1) task->robust_list->list_op_pending != NULL + * 1) task->futex.robust_list->list_op_pending != NULL * @pending_op == true * 2) The owner part of user space futex value == 0 * 3) Regular futex: @pi == false @@ -1065,7 +1020,7 @@ retry: owner = uval & FUTEX_TID_MASK; if (pending_op && !pi && !owner) { - futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, + futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, NULL, 1, FUTEX_BITSET_MATCH_ANY); return 0; } @@ -1119,7 +1074,7 @@ retry: * PI futexes happens in exit_pi_state(): */ if (!pi && (uval & FUTEX_WAITERS)) { - futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, + futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, NULL, 1, FUTEX_BITSET_MATCH_ANY); } @@ -1131,31 +1086,30 @@ retry: */ static inline int fetch_robust_entry(struct robust_list __user **entry, struct robust_list __user * __user *head, - unsigned int *pi) + unsigned int *mod) { unsigned long uentry; if (get_user(uentry, (unsigned long __user *)head)) return -EFAULT; - *entry = (void __user *)(uentry & ~1UL); - *pi = uentry & 1; + *entry = (void __user *)(uentry & ~FUTEX_ROBUST_MOD_MASK); + *mod = uentry & FUTEX_ROBUST_MOD_MASK; return 0; } /* - * Walk curr->robust_list (very carefully, it's a userspace list!) + * Walk curr->futex.robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. * * We silently return on any sign of list-walking problem. */ static void exit_robust_list(struct task_struct *curr) { - struct robust_list_head __user *head = curr->robust_list; + struct robust_list_head __user *head = curr->futex.robust_list; + unsigned int limit = ROBUST_LIST_LIMIT, cur_mod, next_mod, pend_mod; struct robust_list __user *entry, *next_entry, *pending; - unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; - unsigned int next_pi; unsigned long futex_offset; int rc; @@ -1163,7 +1117,7 @@ static void exit_robust_list(struct task_struct *curr) * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): */ - if (fetch_robust_entry(&entry, &head->list.next, &pi)) + if (fetch_robust_entry(&entry, &head->list.next, &cur_mod)) return; /* * Fetch the relative futex offset: @@ -1174,7 +1128,7 @@ static void exit_robust_list(struct task_struct *curr) * Fetch any possibly pending lock-add first, and handle it * if it exists: */ - if (fetch_robust_entry(&pending, &head->list_op_pending, &pip)) + if (fetch_robust_entry(&pending, &head->list_op_pending, &pend_mod)) return; next_entry = NULL; /* avoid warning with gcc */ @@ -1183,20 +1137,20 @@ static void exit_robust_list(struct task_struct *curr) * Fetch the next entry in the list before calling * handle_futex_death: */ - rc = fetch_robust_entry(&next_entry, &entry->next, &next_pi); + rc = fetch_robust_entry(&next_entry, &entry->next, &next_mod); /* * A pending lock might already be on the list, so * don't process it twice: */ if (entry != pending) { if (handle_futex_death((void __user *)entry + futex_offset, - curr, pi, HANDLE_DEATH_LIST)) + curr, cur_mod, HANDLE_DEATH_LIST)) return; } if (rc) return; entry = next_entry; - pi = next_pi; + cur_mod = next_mod; /* * Avoid excessively long or circular lists: */ @@ -1208,10 +1162,31 @@ static void exit_robust_list(struct task_struct *curr) if (pending) { handle_futex_death((void __user *)pending + futex_offset, - curr, pip, HANDLE_DEATH_PENDING); + curr, pend_mod, HANDLE_DEATH_PENDING); } } +static bool robust_list_clear_pending(unsigned long __user *pop) +{ + struct robust_list_head __user *head = current->futex.robust_list; + + if (!put_user(0UL, pop)) + return true; + + /* + * Just give up. The robust list head is usually part of TLS, so the + * chance that this gets resolved is close to zero. + * + * If @pop_addr is the robust_list_head::list_op_pending pointer then + * clear the robust list head pointer to prevent further damage when the + * task exits. Better a few stale futexes than corrupted memory. But + * that's mostly an academic exercise. + */ + if (pop == (unsigned long __user *)&head->list_op_pending) + current->futex.robust_list = NULL; + return false; +} + #ifdef CONFIG_COMPAT static void __user *futex_uaddr(struct robust_list __user *entry, compat_long_t futex_offset) @@ -1227,29 +1202,28 @@ static void __user *futex_uaddr(struct robust_list __user *entry, */ static inline int compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry, - compat_uptr_t __user *head, unsigned int *pi) + compat_uptr_t __user *head, unsigned int *pflags) { if (get_user(*uentry, head)) return -EFAULT; - *entry = compat_ptr((*uentry) & ~1); - *pi = (unsigned int)(*uentry) & 1; + *entry = compat_ptr((*uentry) & ~FUTEX_ROBUST_MOD_MASK); + *pflags = (unsigned int)(*uentry) & FUTEX_ROBUST_MOD_MASK; return 0; } /* - * Walk curr->robust_list (very carefully, it's a userspace list!) + * Walk curr->futex.robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. * * We silently return on any sign of list-walking problem. */ static void compat_exit_robust_list(struct task_struct *curr) { - struct compat_robust_list_head __user *head = curr->compat_robust_list; + struct compat_robust_list_head __user *head = current->futex.compat_robust_list; + unsigned int limit = ROBUST_LIST_LIMIT, cur_mod, next_mod, pend_mod; struct robust_list __user *entry, *next_entry, *pending; - unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; - unsigned int next_pi; compat_uptr_t uentry, next_uentry, upending; compat_long_t futex_offset; int rc; @@ -1258,7 +1232,7 @@ static void compat_exit_robust_list(struct task_struct *curr) * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): */ - if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &pi)) + if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &cur_mod)) return; /* * Fetch the relative futex offset: @@ -1269,8 +1243,7 @@ static void compat_exit_robust_list(struct task_struct *curr) * Fetch any possibly pending lock-add first, and handle it * if it exists: */ - if (compat_fetch_robust_entry(&upending, &pending, - &head->list_op_pending, &pip)) + if (compat_fetch_robust_entry(&upending, &pending, &head->list_op_pending, &pend_mod)) return; next_entry = NULL; /* avoid warning with gcc */ @@ -1280,7 +1253,7 @@ static void compat_exit_robust_list(struct task_struct *curr) * handle_futex_death: */ rc = compat_fetch_robust_entry(&next_uentry, &next_entry, - (compat_uptr_t __user *)&entry->next, &next_pi); + (compat_uptr_t __user *)&entry->next, &next_mod); /* * A pending lock might already be on the list, so * dont process it twice: @@ -1288,15 +1261,14 @@ static void compat_exit_robust_list(struct task_struct *curr) if (entry != pending) { void __user *uaddr = futex_uaddr(entry, futex_offset); - if (handle_futex_death(uaddr, curr, pi, - HANDLE_DEATH_LIST)) + if (handle_futex_death(uaddr, curr, cur_mod, HANDLE_DEATH_LIST)) return; } if (rc) return; uentry = next_uentry; entry = next_entry; - pi = next_pi; + cur_mod = next_mod; /* * Avoid excessively long or circular lists: */ @@ -1308,9 +1280,24 @@ static void compat_exit_robust_list(struct task_struct *curr) if (pending) { void __user *uaddr = futex_uaddr(pending, futex_offset); - handle_futex_death(uaddr, curr, pip, HANDLE_DEATH_PENDING); + handle_futex_death(uaddr, curr, pend_mod, HANDLE_DEATH_PENDING); } } + +static bool compat_robust_list_clear_pending(u32 __user *pop) +{ + struct compat_robust_list_head __user *head = current->futex.compat_robust_list; + + if (!put_user(0U, pop)) + return true; + + /* See comment in robust_list_clear_pending(). */ + if (pop == &head->list_op_pending) + current->futex.compat_robust_list = NULL; + return false; +} +#else +static bool compat_robust_list_clear_pending(u32 __user *pop_addr) { return false; } #endif #ifdef CONFIG_FUTEX_PI @@ -1322,7 +1309,7 @@ static void compat_exit_robust_list(struct task_struct *curr) */ static void exit_pi_state_list(struct task_struct *curr) { - struct list_head *next, *head = &curr->pi_state_list; + struct list_head *next, *head = &curr->futex.pi_state_list; struct futex_pi_state *pi_state; union futex_key key = FUTEX_KEY_INIT; @@ -1336,7 +1323,7 @@ static void exit_pi_state_list(struct task_struct *curr) * on the mutex. */ WARN_ON(curr != current); - guard(private_hash)(); + guard(private_hash)(current->mm); /* * We are a ZOMBIE and nobody can enqueue itself on * pi_state_list anymore, but we have to be careful @@ -1348,7 +1335,8 @@ static void exit_pi_state_list(struct task_struct *curr) pi_state = list_entry(next, struct futex_pi_state, list); key = pi_state->key; if (1) { - CLASS(hb, hb)(&key); + CLASS(hbr, hbr)(&key); + auto hb = hbr.hb; /* * We can race against put_pi_state() removing itself from the @@ -1404,21 +1392,50 @@ static void exit_pi_state_list(struct task_struct *curr) static inline void exit_pi_state_list(struct task_struct *curr) { } #endif +bool futex_robust_list_clear_pending(void __user *pop, unsigned int flags) +{ + bool size32bit = !!(flags & FLAGS_ROBUST_LIST32); + + if (!IS_ENABLED(CONFIG_64BIT) && !size32bit) + return false; + + if (IS_ENABLED(CONFIG_64BIT) && size32bit) + return compat_robust_list_clear_pending(pop); + + return robust_list_clear_pending(pop); +} + +#ifdef CONFIG_FUTEX_ROBUST_UNLOCK +void __futex_fixup_robust_unlock(struct pt_regs *regs, struct futex_unlock_cs_range *csr) +{ + /* + * arch_futex_robust_unlock_get_pop() returns the list pending op pointer from + * @regs if the try_cmpxchg() succeeded. + */ + void __user *pop = arch_futex_robust_unlock_get_pop(regs); + + if (!pop) + return; + + futex_robust_list_clear_pending(pop, csr->pop_size32 ? FLAGS_ROBUST_LIST32 : 0); +} +#endif /* CONFIG_FUTEX_ROBUST_UNLOCK */ + static void futex_cleanup(struct task_struct *tsk) { - if (unlikely(tsk->robust_list)) { + if (unlikely(tsk->futex.robust_list)) { exit_robust_list(tsk); - tsk->robust_list = NULL; + tsk->futex.robust_list = NULL; } #ifdef CONFIG_COMPAT - if (unlikely(tsk->compat_robust_list)) { + if (unlikely(tsk->futex.compat_robust_list)) { compat_exit_robust_list(tsk); - tsk->compat_robust_list = NULL; + tsk->futex.compat_robust_list = NULL; } #endif - if (unlikely(!list_empty(&tsk->pi_state_list))) + if (unlikely(!list_empty(&tsk->futex.pi_state_list))) exit_pi_state_list(tsk); } @@ -1442,23 +1459,23 @@ static void futex_cleanup(struct task_struct *tsk) void futex_exit_recursive(struct task_struct *tsk) { /* If the state is FUTEX_STATE_EXITING then futex_exit_mutex is held */ - if (tsk->futex_state == FUTEX_STATE_EXITING) { - __assume_ctx_lock(&tsk->futex_exit_mutex); - mutex_unlock(&tsk->futex_exit_mutex); + if (tsk->futex.state == FUTEX_STATE_EXITING) { + __assume_ctx_lock(&tsk->futex.exit_mutex); + mutex_unlock(&tsk->futex.exit_mutex); } - tsk->futex_state = FUTEX_STATE_DEAD; + tsk->futex.state = FUTEX_STATE_DEAD; } static void futex_cleanup_begin(struct task_struct *tsk) - __acquires(&tsk->futex_exit_mutex) + __acquires(&tsk->futex.exit_mutex) { /* * Prevent various race issues against a concurrent incoming waiter * including live locks by forcing the waiter to block on - * tsk->futex_exit_mutex when it observes FUTEX_STATE_EXITING in + * tsk->futex.exit_mutex when it observes FUTEX_STATE_EXITING in * attach_to_pi_owner(). */ - mutex_lock(&tsk->futex_exit_mutex); + mutex_lock(&tsk->futex.exit_mutex); /* * Switch the state to FUTEX_STATE_EXITING under tsk->pi_lock. @@ -1472,23 +1489,23 @@ static void futex_cleanup_begin(struct task_struct *tsk) * be observed in exit_pi_state_list(). */ raw_spin_lock_irq(&tsk->pi_lock); - tsk->futex_state = FUTEX_STATE_EXITING; + tsk->futex.state = FUTEX_STATE_EXITING; raw_spin_unlock_irq(&tsk->pi_lock); } static void futex_cleanup_end(struct task_struct *tsk, int state) - __releases(&tsk->futex_exit_mutex) + __releases(&tsk->futex.exit_mutex) { /* * Lockless store. The only side effect is that an observer might * take another loop until it becomes visible. */ - tsk->futex_state = state; + tsk->futex.state = state; /* * Drop the exit protection. This unblocks waiters which observed * FUTEX_STATE_EXITING to reevaluate the state. */ - mutex_unlock(&tsk->futex_exit_mutex); + mutex_unlock(&tsk->futex.exit_mutex); } void futex_exec_release(struct task_struct *tsk) @@ -1516,12 +1533,8 @@ void futex_exit_release(struct task_struct *tsk) futex_cleanup_end(tsk, FUTEX_STATE_DEAD); } -static void futex_hash_bucket_init(struct futex_hash_bucket *fhb, - struct futex_private_hash *fph) +static void futex_hash_bucket_init(struct futex_hash_bucket *fhb) { -#ifdef CONFIG_FUTEX_PRIVATE_HASH - fhb->priv = fph; -#endif atomic_set(&fhb->waiters, 0); plist_head_init(&fhb->chain); spin_lock_init(&fhb->lock); @@ -1553,17 +1566,17 @@ static void __futex_ref_atomic_begin(struct futex_private_hash *fph) * otherwise it would be impossible for it to have reported success * from futex_ref_is_dead(). */ - WARN_ON_ONCE(atomic_long_read(&mm->futex_atomic) != 0); + WARN_ON_ONCE(atomic_long_read(&mm->futex.phash.atomic) != 0); /* * Set the atomic to the bias value such that futex_ref_{get,put}() * will never observe 0. Will be fixed up in __futex_ref_atomic_end() * when folding in the percpu count. */ - atomic_long_set(&mm->futex_atomic, LONG_MAX); + atomic_long_set(&mm->futex.phash.atomic, LONG_MAX); smp_store_release(&fph->state, FR_ATOMIC); - call_rcu_hurry(&mm->futex_rcu, futex_ref_rcu); + call_rcu_hurry(&mm->futex.phash.rcu, futex_ref_rcu); } static void __futex_ref_atomic_end(struct futex_private_hash *fph) @@ -1584,7 +1597,7 @@ static void __futex_ref_atomic_end(struct futex_private_hash *fph) * Therefore the per-cpu counter is now stable, sum and reset. */ for_each_possible_cpu(cpu) { - unsigned int *ptr = per_cpu_ptr(mm->futex_ref, cpu); + unsigned int *ptr = per_cpu_ptr(mm->futex.phash.ref, cpu); count += *ptr; *ptr = 0; } @@ -1592,7 +1605,7 @@ static void __futex_ref_atomic_end(struct futex_private_hash *fph) /* * Re-init for the next cycle. */ - this_cpu_inc(*mm->futex_ref); /* 0 -> 1 */ + this_cpu_inc(*mm->futex.phash.ref); /* 0 -> 1 */ /* * Add actual count, subtract bias and initial refcount. @@ -1600,7 +1613,7 @@ static void __futex_ref_atomic_end(struct futex_private_hash *fph) * The moment this atomic operation happens, futex_ref_is_dead() can * become true. */ - ret = atomic_long_add_return(count - LONG_MAX - 1, &mm->futex_atomic); + ret = atomic_long_add_return(count - LONG_MAX - 1, &mm->futex.phash.atomic); if (!ret) wake_up_var(mm); @@ -1610,8 +1623,8 @@ static void __futex_ref_atomic_end(struct futex_private_hash *fph) static void futex_ref_rcu(struct rcu_head *head) { - struct mm_struct *mm = container_of(head, struct mm_struct, futex_rcu); - struct futex_private_hash *fph = rcu_dereference_raw(mm->futex_phash); + struct mm_struct *mm = container_of(head, struct mm_struct, futex.phash.rcu); + struct futex_private_hash *fph = rcu_dereference_raw(mm->futex.phash.hash); if (fph->state == FR_PERCPU) { /* @@ -1640,7 +1653,7 @@ static void futex_ref_drop(struct futex_private_hash *fph) /* * Can only transition the current fph; */ - WARN_ON_ONCE(rcu_dereference_raw(mm->futex_phash) != fph); + WARN_ON_ONCE(rcu_dereference_raw(mm->futex.phash.hash) != fph); /* * We enqueue at least one RCU callback. Ensure mm stays if the task * exits before the transition is completed. @@ -1651,9 +1664,9 @@ static void futex_ref_drop(struct futex_private_hash *fph) * In order to avoid the following scenario: * * futex_hash() __futex_pivot_hash() - * guard(rcu); guard(mm->futex_hash_lock); - * fph = mm->futex_phash; - * rcu_assign_pointer(&mm->futex_phash, new); + * guard(rcu); guard(mm->futex.phash.lock); + * fph = mm->futex.phash.hash; + * rcu_assign_pointer(&mm->futex.phash.hash, new); * futex_hash_allocate() * futex_ref_drop() * fph->state = FR_ATOMIC; @@ -1668,7 +1681,7 @@ static void futex_ref_drop(struct futex_private_hash *fph) * There must be at least one full grace-period between publishing a * new fph and trying to replace it. */ - if (poll_state_synchronize_rcu(mm->futex_batches)) { + if (poll_state_synchronize_rcu(mm->futex.phash.batches)) { /* * There was a grace-period, we can begin now. */ @@ -1676,7 +1689,7 @@ static void futex_ref_drop(struct futex_private_hash *fph) return; } - call_rcu_hurry(&mm->futex_rcu, futex_ref_rcu); + call_rcu_hurry(&mm->futex.phash.rcu, futex_ref_rcu); } static bool futex_ref_get(struct futex_private_hash *fph) @@ -1686,11 +1699,11 @@ static bool futex_ref_get(struct futex_private_hash *fph) guard(preempt)(); if (READ_ONCE(fph->state) == FR_PERCPU) { - __this_cpu_inc(*mm->futex_ref); + __this_cpu_inc(*mm->futex.phash.ref); return true; } - return atomic_long_inc_not_zero(&mm->futex_atomic); + return atomic_long_inc_not_zero(&mm->futex.phash.atomic); } static bool futex_ref_put(struct futex_private_hash *fph) @@ -1700,11 +1713,11 @@ static bool futex_ref_put(struct futex_private_hash *fph) guard(preempt)(); if (READ_ONCE(fph->state) == FR_PERCPU) { - __this_cpu_dec(*mm->futex_ref); + __this_cpu_dec(*mm->futex.phash.ref); return false; } - return atomic_long_dec_and_test(&mm->futex_atomic); + return atomic_long_dec_and_test(&mm->futex.phash.atomic); } static bool futex_ref_is_dead(struct futex_private_hash *fph) @@ -1716,28 +1729,23 @@ static bool futex_ref_is_dead(struct futex_private_hash *fph) if (smp_load_acquire(&fph->state) == FR_PERCPU) return false; - return atomic_long_read(&mm->futex_atomic) == 0; + return atomic_long_read(&mm->futex.phash.atomic) == 0; } -int futex_mm_init(struct mm_struct *mm) +static void futex_hash_init_mm(struct futex_mm_data *fd) { - mutex_init(&mm->futex_hash_lock); - RCU_INIT_POINTER(mm->futex_phash, NULL); - mm->futex_phash_new = NULL; - /* futex-ref */ - mm->futex_ref = NULL; - atomic_long_set(&mm->futex_atomic, 0); - mm->futex_batches = get_state_synchronize_rcu(); - return 0; + memset(&fd->phash, 0, sizeof(fd->phash)); + mutex_init(&fd->phash.lock); + fd->phash.batches = get_state_synchronize_rcu(); } void futex_hash_free(struct mm_struct *mm) { struct futex_private_hash *fph; - free_percpu(mm->futex_ref); - kvfree(mm->futex_phash_new); - fph = rcu_dereference_raw(mm->futex_phash); + free_percpu(mm->futex.phash.ref); + kvfree(mm->futex.phash.hash_new); + fph = rcu_dereference_raw(mm->futex.phash.hash); if (fph) kvfree(fph); } @@ -1748,10 +1756,10 @@ static bool futex_pivot_pending(struct mm_struct *mm) guard(rcu)(); - if (!mm->futex_phash_new) + if (!mm->futex.phash.hash_new) return true; - fph = rcu_dereference(mm->futex_phash); + fph = rcu_dereference(mm->futex.phash.hash); return futex_ref_is_dead(fph); } @@ -1793,7 +1801,7 @@ static int futex_hash_allocate(unsigned int hash_slots, unsigned int flags) * Once we've disabled the global hash there is no way back. */ scoped_guard(rcu) { - fph = rcu_dereference(mm->futex_phash); + fph = rcu_dereference(mm->futex.phash.hash); if (fph && !fph->hash_mask) { if (custom) return -EBUSY; @@ -1801,15 +1809,15 @@ static int futex_hash_allocate(unsigned int hash_slots, unsigned int flags) } } - if (!mm->futex_ref) { + if (!mm->futex.phash.ref) { /* * This will always be allocated by the first thread and * therefore requires no locking. */ - mm->futex_ref = alloc_percpu(unsigned int); - if (!mm->futex_ref) + mm->futex.phash.ref = alloc_percpu(unsigned int); + if (!mm->futex.phash.ref) return -ENOMEM; - this_cpu_inc(*mm->futex_ref); /* 0 -> 1 */ + this_cpu_inc(*mm->futex.phash.ref); /* 0 -> 1 */ } fph = kvzalloc(struct_size(fph, queues, hash_slots), @@ -1822,7 +1830,7 @@ static int futex_hash_allocate(unsigned int hash_slots, unsigned int flags) fph->mm = mm; for (i = 0; i < hash_slots; i++) - futex_hash_bucket_init(&fph->queues[i], fph); + futex_hash_bucket_init(&fph->queues[i]); if (custom) { /* @@ -1832,14 +1840,14 @@ again: wait_var_event(mm, futex_pivot_pending(mm)); } - scoped_guard(mutex, &mm->futex_hash_lock) { + scoped_guard(mutex, &mm->futex.phash.lock) { struct futex_private_hash *free __free(kvfree) = NULL; struct futex_private_hash *cur, *new; - cur = rcu_dereference_protected(mm->futex_phash, - lockdep_is_held(&mm->futex_hash_lock)); - new = mm->futex_phash_new; - mm->futex_phash_new = NULL; + cur = rcu_dereference_protected(mm->futex.phash.hash, + lockdep_is_held(&mm->futex.phash.lock)); + new = mm->futex.phash.hash_new; + mm->futex.phash.hash_new = NULL; if (fph) { if (cur && !cur->hash_mask) { @@ -1849,7 +1857,7 @@ again: * the second one returns here. */ free = fph; - mm->futex_phash_new = new; + mm->futex.phash.hash_new = new; return -EBUSY; } if (cur && !new) { @@ -1879,7 +1887,7 @@ again: if (new) { /* - * Will set mm->futex_phash_new on failure; + * Will set mm->futex.phash.new_hash on failure; * futex_private_hash_get() will try again. */ if (!__futex_pivot_hash(mm, new) && custom) @@ -1898,11 +1906,9 @@ int futex_hash_allocate_default(void) return 0; scoped_guard(rcu) { - threads = min_t(unsigned int, - get_nr_threads(current), - num_online_cpus()); + threads = min_t(unsigned int, get_nr_threads(current), num_online_cpus()); - fph = rcu_dereference(current->mm->futex_phash); + fph = rcu_dereference(current->mm->futex.phash.hash); if (fph) { if (fph->custom) return 0; @@ -1929,24 +1935,52 @@ static int futex_hash_get_slots(void) struct futex_private_hash *fph; guard(rcu)(); - fph = rcu_dereference(current->mm->futex_phash); + fph = rcu_dereference(current->mm->futex.phash.hash); if (fph && fph->hash_mask) return fph->hash_mask + 1; return 0; } +#else /* CONFIG_FUTEX_PRIVATE_HASH */ +static inline int futex_hash_allocate(unsigned int hslots, unsigned int flags) { return -EINVAL; } +static inline int futex_hash_get_slots(void) { return 0; } +static inline void futex_hash_init_mm(struct futex_mm_data *fd) { } +#endif /* !CONFIG_FUTEX_PRIVATE_HASH */ -#else +#ifdef CONFIG_FUTEX_ROBUST_UNLOCK +static void futex_invalidate_cs_ranges(struct futex_mm_data *fd) +{ + /* + * Invalidate start_ip so that the quick check fails for ip >= start_ip + * if VDSO is not mapped or the second slot is not available for compat + * tasks as they use VDSO32 which does not provide the 64-bit pointer + * variant. + */ + for (int i = 0; i < FUTEX_ROBUST_MAX_CS_RANGES; i++) + fd->unlock.cs_ranges[i].start_ip = ~0UL; +} -static int futex_hash_allocate(unsigned int hash_slots, unsigned int flags) +void futex_reset_cs_ranges(struct futex_mm_data *fd) { - return -EINVAL; + memset(fd->unlock.cs_ranges, 0, sizeof(fd->unlock.cs_ranges)); + futex_invalidate_cs_ranges(fd); } -static int futex_hash_get_slots(void) +static void futex_robust_unlock_init_mm(struct futex_mm_data *fd) { - return 0; + /* mm_dup() preserves the range, mm_alloc() clears it */ + if (!fd->unlock.cs_ranges[0].start_ip) + futex_invalidate_cs_ranges(fd); } +#else /* CONFIG_FUTEX_ROBUST_UNLOCK */ +static inline void futex_robust_unlock_init_mm(struct futex_mm_data *fd) { } +#endif /* !CONFIG_FUTEX_ROBUST_UNLOCK */ +#if defined(CONFIG_FUTEX_PRIVATE_HASH) || defined(CONFIG_FUTEX_ROBUST_UNLOCK) +void futex_mm_init(struct mm_struct *mm) +{ + futex_hash_init_mm(&mm->futex); + futex_robust_unlock_init_mm(&mm->futex); +} #endif int futex_hash_prctl(unsigned long arg2, unsigned long arg3, unsigned long arg4) @@ -2001,7 +2035,7 @@ static int __init futex_init(void) BUG_ON(!table); for (i = 0; i < hashsize; i++) - futex_hash_bucket_init(&table[i], NULL); + futex_hash_bucket_init(&table[i]); futex_queues[n] = table; } diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h index 9f6bf6f585fc..f00f0863ed44 100644 --- a/kernel/futex/futex.h +++ b/kernel/futex/futex.h @@ -40,6 +40,8 @@ #define FLAGS_NUMA 0x0080 #define FLAGS_STRICT 0x0100 #define FLAGS_MPOL 0x0200 +#define FLAGS_ROBUST_UNLOCK 0x0400 +#define FLAGS_ROBUST_LIST32 0x0800 /* FUTEX_ to FLAGS_ */ static inline unsigned int futex_to_flags(unsigned int op) @@ -52,6 +54,12 @@ static inline unsigned int futex_to_flags(unsigned int op) if (op & FUTEX_CLOCK_REALTIME) flags |= FLAGS_CLOCKRT; + if (op & FUTEX_ROBUST_UNLOCK) + flags |= FLAGS_ROBUST_UNLOCK; + + if (op & FUTEX_ROBUST_LIST32) + flags |= FLAGS_ROBUST_LIST32; + return flags; } @@ -126,6 +134,15 @@ static inline bool should_fail_futex(bool fshared) } #endif +static inline bool futex_key_is_private(union futex_key *key) +{ + /* + * Relies on get_futex_key() to set either bit for shared + * futexes -- see comment with union futex_key. + */ + return !(key->both.offset & (FUT_OFF_INODE | FUT_OFF_MMSHARED)); +} + /* * Hash buckets are shared by all the futex_keys that hash to the same * location. Each key may have multiple futex_q structures, one for each task @@ -135,7 +152,6 @@ struct futex_hash_bucket { atomic_t waiters; spinlock_t lock; struct plist_head chain; - struct futex_private_hash *priv; } ____cacheline_aligned_in_smp; /* @@ -175,7 +191,7 @@ typedef void (futex_wake_fn)(struct wake_q_head *wake_q, struct futex_q *q); * @requeue_pi_key: the requeue_pi target futex key * @bitset: bitset for the optional bitmasked wakeup * @requeue_state: State field for futex_requeue_pi() - * @drop_hb_ref: Waiter should drop the extra hash bucket reference if true + * @drop_fph: Waiter should drop the extra private hash reference when set * @requeue_wait: RCU wait for futex_requeue_pi() (RT only) * * We use this hashed waitqueue, instead of a normal wait_queue_entry_t, so @@ -202,7 +218,7 @@ struct futex_q { union futex_key *requeue_pi_key; u32 bitset; atomic_t requeue_state; - bool drop_hb_ref; + struct futex_private_hash *drop_fph; #ifdef CONFIG_PREEMPT_RT struct rcuwait requeue_wait; #endif @@ -222,28 +238,29 @@ extern struct hrtimer_sleeper * futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, int flags, u64 range_ns); -extern struct futex_hash_bucket *futex_hash(union futex_key *key); -#ifdef CONFIG_FUTEX_PRIVATE_HASH -extern void futex_hash_get(struct futex_hash_bucket *hb); -extern void futex_hash_put(struct futex_hash_bucket *hb); +struct futex_bucket_ref { + struct futex_hash_bucket *hb; + struct futex_private_hash *fph; +}; -extern struct futex_private_hash *futex_private_hash(void); +#ifdef CONFIG_FUTEX_PRIVATE_HASH +extern struct futex_private_hash *futex_private_hash(struct mm_struct *mm); extern void futex_private_hash_put(struct futex_private_hash *fph); #else /* !CONFIG_FUTEX_PRIVATE_HASH */ -static inline void futex_hash_get(struct futex_hash_bucket *hb) { } -static inline void futex_hash_put(struct futex_hash_bucket *hb) { } -static inline struct futex_private_hash *futex_private_hash(void) { return NULL; } +static inline struct futex_private_hash *futex_private_hash(struct mm_struct *mm) { return NULL; } static inline void futex_private_hash_put(struct futex_private_hash *fph) { } #endif -DEFINE_CLASS(hb, struct futex_hash_bucket *, - if (_T) futex_hash_put(_T), +extern struct futex_bucket_ref futex_hash(union futex_key *key); + +DEFINE_CLASS(hbr, struct futex_bucket_ref, + if (_T.fph) futex_private_hash_put(_T.fph), futex_hash(key), union futex_key *key); DEFINE_CLASS(private_hash, struct futex_private_hash *, if (_T) futex_private_hash_put(_T), - futex_private_hash(), void); + futex_private_hash(mm), struct mm_struct *mm); /** * futex_match - Check whether two futex keys are equal @@ -449,13 +466,16 @@ extern int futex_unqueue_multiple(struct futex_vector *v, int count); extern int futex_wait_multiple(struct futex_vector *vs, unsigned int count, struct hrtimer_sleeper *to); -extern int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset); +extern int futex_wake(u32 __user *uaddr, unsigned int flags, void __user *pop, + int nr_wake, u32 bitset); extern int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, int nr_wake, int nr_wake2, int op); -extern int futex_unlock_pi(u32 __user *uaddr, unsigned int flags); +extern int futex_unlock_pi(u32 __user *uaddr, unsigned int flags, void __user *pop); extern int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock); +bool futex_robust_list_clear_pending(void __user *pop, unsigned int flags); + #endif /* _FUTEX_H */ diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c index 643199fdbe62..795011ea1202 100644 --- a/kernel/futex/pi.c +++ b/kernel/futex/pi.c @@ -14,7 +14,7 @@ int refill_pi_state_cache(void) { struct futex_pi_state *pi_state; - if (likely(current->pi_state_cache)) + if (likely(current->futex.pi_state_cache)) return 0; pi_state = kzalloc_obj(*pi_state); @@ -28,17 +28,17 @@ int refill_pi_state_cache(void) refcount_set(&pi_state->refcount, 1); pi_state->key = FUTEX_KEY_INIT; - current->pi_state_cache = pi_state; + current->futex.pi_state_cache = pi_state; return 0; } static struct futex_pi_state *alloc_pi_state(void) { - struct futex_pi_state *pi_state = current->pi_state_cache; + struct futex_pi_state *pi_state = current->futex.pi_state_cache; WARN_ON(!pi_state); - current->pi_state_cache = NULL; + current->futex.pi_state_cache = NULL; return pi_state; } @@ -60,7 +60,7 @@ static void pi_state_update_owner(struct futex_pi_state *pi_state, if (new_owner) { raw_spin_lock(&new_owner->pi_lock); WARN_ON(!list_empty(&pi_state->list)); - list_add(&pi_state->list, &new_owner->pi_state_list); + list_add(&pi_state->list, &new_owner->futex.pi_state_list); pi_state->owner = new_owner; raw_spin_unlock(&new_owner->pi_lock); } @@ -96,7 +96,7 @@ void put_pi_state(struct futex_pi_state *pi_state) raw_spin_unlock_irqrestore(&pi_state->pi_mutex.wait_lock, flags); } - if (current->pi_state_cache) { + if (current->futex.pi_state_cache) { kfree(pi_state); } else { /* @@ -106,7 +106,7 @@ void put_pi_state(struct futex_pi_state *pi_state) */ pi_state->owner = NULL; refcount_set(&pi_state->refcount, 1); - current->pi_state_cache = pi_state; + current->futex.pi_state_cache = pi_state; } } @@ -179,7 +179,7 @@ void put_pi_state(struct futex_pi_state *pi_state) * * p->pi_lock: * - * p->pi_state_list -> pi_state->list, relation + * p->futex.pi_state_list -> pi_state->list, relation * pi_mutex->owner -> pi_state->owner, relation * * pi_state->refcount: @@ -327,7 +327,7 @@ static int handle_exit_race(u32 __user *uaddr, u32 uval, * If the futex exit state is not yet FUTEX_STATE_DEAD, tell the * caller that the alleged owner is busy. */ - if (tsk && tsk->futex_state != FUTEX_STATE_DEAD) + if (tsk && tsk->futex.state != FUTEX_STATE_DEAD) return -EBUSY; /* @@ -346,8 +346,8 @@ static int handle_exit_race(u32 __user *uaddr, u32 uval, * *uaddr = 0xC0000000; tsk = get_task(PID); * } if (!tsk->flags & PF_EXITING) { * ... attach(); - * tsk->futex_state = } else { - * FUTEX_STATE_DEAD; if (tsk->futex_state != + * tsk->futex.state = } else { + * FUTEX_STATE_DEAD; if (tsk->futex.state != * FUTEX_STATE_DEAD) * return -EAGAIN; * return -ESRCH; <--- FAIL @@ -396,7 +396,7 @@ static void __attach_to_pi_owner(struct task_struct *p, union futex_key *key, pi_state->key = *key; WARN_ON(!list_empty(&pi_state->list)); - list_add(&pi_state->list, &p->pi_state_list); + list_add(&pi_state->list, &p->futex.pi_state_list); /* * Assignment without holding pi_state->pi_mutex.wait_lock is safe * because there is no concurrency as the object is not published yet. @@ -440,7 +440,7 @@ static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key, * in futex_exit_release(), we do this protected by p->pi_lock: */ raw_spin_lock_irq(&p->pi_lock); - if (unlikely(p->futex_state != FUTEX_STATE_OK)) { + if (unlikely(p->futex.state != FUTEX_STATE_OK)) { /* * The task is on the way out. When the futex state is * FUTEX_STATE_DEAD, we know that the task has finished @@ -945,7 +945,8 @@ retry: retry_private: if (1) { - CLASS(hb, hb)(&q.key); + CLASS(hbr, hbr)(&q.key); + auto hb = hbr.hb; futex_q_lock(&q, hb); @@ -1009,7 +1010,7 @@ retry_private: * the thread, performing resize, will block on hb->lock during * the requeue. */ - futex_hash_put(no_free_ptr(hb)); + futex_private_hash_put(no_free_ptr(hbr.fph)); /* * Must be done before we enqueue the waiter, here is unfortunately * under the hb lock, but that *should* work because it does nothing. @@ -1100,11 +1101,9 @@ no_block: __release(&hb->lock); futex_unqueue_pi(&q); spin_unlock(q.lock_ptr); - if (q.drop_hb_ref) { - CLASS(hb, hb)(&q.key); - /* Additional reference from futex_unlock_pi() */ - futex_hash_put(hb); - } + + /* Additional reference from futex_unlock_pi() */ + futex_private_hash_put(q.drop_fph); goto out; out_unlock_put_key: @@ -1139,7 +1138,7 @@ out: * This is the in-kernel slowpath: we look up the PI state (if any), * and do the rt-mutex unlock. */ -int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) +static int __futex_unlock_pi(u32 __user *uaddr, unsigned int flags) { u32 curval, uval, vpid = task_pid_vnr(current); union futex_key key = FUTEX_KEY_INIT; @@ -1148,7 +1147,6 @@ int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) if (!IS_ENABLED(CONFIG_FUTEX_PI)) return -ENOSYS; - retry: if (get_user(uval, uaddr)) return -EFAULT; @@ -1162,7 +1160,8 @@ retry: if (ret) return ret; - CLASS(hb, hb)(&key); + CLASS(hbr, hbr)(&key); + auto hb = hbr.hb; spin_lock(&hb->lock); retry_hb: @@ -1219,8 +1218,9 @@ retry_hb: * Acquire a reference for the leaving waiter to ensure * valid futex_q::lock_ptr. */ - futex_hash_get(hb); - top_waiter->drop_hb_ref = true; + if (futex_key_is_private(&key)) + top_waiter->drop_fph = futex_private_hash(key.private.mm); + __futex_unqueue(top_waiter); raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); goto retry_hb; @@ -1302,3 +1302,15 @@ pi_faulted: return ret; } +int futex_unlock_pi(u32 __user *uaddr, unsigned int flags, void __user *pop) +{ + int ret = __futex_unlock_pi(uaddr, flags); + + if (ret || !(flags & FLAGS_ROBUST_UNLOCK)) + return ret; + + if (!futex_robust_list_clear_pending(pop, flags)) + return -EFAULT; + + return 0; +} diff --git a/kernel/futex/requeue.c b/kernel/futex/requeue.c index b597cb3d17fc..7384672916fb 100644 --- a/kernel/futex/requeue.c +++ b/kernel/futex/requeue.c @@ -241,8 +241,8 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key, * Acquire a reference for the waiter to ensure valid * futex_q::lock_ptr. */ - futex_hash_get(hb); - q->drop_hb_ref = true; + if (futex_key_is_private(key)) + q->drop_fph = futex_private_hash(key->private.mm); q->lock_ptr = &hb->lock; task = READ_ONCE(q->task); @@ -459,8 +459,10 @@ retry: retry_private: if (1) { - CLASS(hb, hb1)(&key1); - CLASS(hb, hb2)(&key2); + CLASS(hbr, hbr1)(&key1); + CLASS(hbr, hbr2)(&key2); + auto hb1 = hbr1.hb; + auto hb2 = hbr2.hb; futex_hb_waiters_inc(hb2); double_lock_hb(hb1, hb2); @@ -643,6 +645,12 @@ retry_private: continue; } + /* Self-deadlock: non-top waiter already owns the PI futex. */ + if (rt_mutex_owner(&pi_state->pi_mutex) == this->task) { + ret = -EDEADLK; + break; + } + ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex, this->rt_waiter, this->task); @@ -832,7 +840,8 @@ int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, switch (futex_requeue_pi_wakeup_sync(&q)) { case Q_REQUEUE_PI_IGNORE: { - CLASS(hb, hb)(&q.key); + CLASS(hbr, hbr)(&q.key); + auto hb = hbr.hb; /* The waiter is still on uaddr1 */ spin_lock(&hb->lock); ret = handle_early_requeue_pi_wakeup(hb, &q, to); @@ -902,11 +911,8 @@ int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, default: BUG(); } - if (q.drop_hb_ref) { - CLASS(hb, hb)(&q.key); - /* Additional reference from requeue_pi_wake_futex() */ - futex_hash_put(hb); - } + /* Additional reference from requeue_pi_wake_futex() */ + futex_private_hash_put(q.drop_fph); out: if (to) { diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c index 77ad9691f6a6..2fa19d9d008d 100644 --- a/kernel/futex/syscalls.c +++ b/kernel/futex/syscalls.c @@ -25,17 +25,13 @@ * @head: pointer to the list-head * @len: length of the list-head, as userspace expects */ -SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head, - size_t, len) +SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head, size_t, len) { - /* - * The kernel knows only one size for now: - */ + /* The kernel knows only one size for now. */ if (unlikely(len != sizeof(*head))) return -EINVAL; - current->robust_list = head; - + current->futex.robust_list = head; return 0; } @@ -43,9 +39,9 @@ static inline void __user *futex_task_robust_list(struct task_struct *p, bool co { #ifdef CONFIG_COMPAT if (compat) - return p->compat_robust_list; + return p->futex.compat_robust_list; #endif - return p->robust_list; + return p->futex.robust_list; } static void __user *futex_get_robust_list_common(int pid, bool compat) @@ -122,6 +118,13 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, return -ENOSYS; } + if (flags & FLAGS_ROBUST_UNLOCK) { + if (cmd != FUTEX_WAKE && + cmd != FUTEX_WAKE_BITSET && + cmd != FUTEX_UNLOCK_PI) + return -ENOSYS; + } + switch (cmd) { case FUTEX_WAIT: val3 = FUTEX_BITSET_MATCH_ANY; @@ -132,7 +135,7 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, val3 = FUTEX_BITSET_MATCH_ANY; fallthrough; case FUTEX_WAKE_BITSET: - return futex_wake(uaddr, flags, val, val3); + return futex_wake(uaddr, flags, uaddr2, val, val3); case FUTEX_REQUEUE: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, NULL, 0); case FUTEX_CMP_REQUEUE: @@ -145,7 +148,7 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, case FUTEX_LOCK_PI2: return futex_lock_pi(uaddr, flags, timeout, 0); case FUTEX_UNLOCK_PI: - return futex_unlock_pi(uaddr, flags); + return futex_unlock_pi(uaddr, flags, uaddr2); case FUTEX_TRYLOCK_PI: return futex_lock_pi(uaddr, flags, NULL, 1); case FUTEX_WAIT_REQUEUE_PI: @@ -379,7 +382,7 @@ SYSCALL_DEFINE4(futex_wake, if (!futex_validate_input(flags, mask)) return -EINVAL; - return futex_wake(uaddr, FLAGS_STRICT | flags, nr, mask); + return futex_wake(uaddr, FLAGS_STRICT | flags, NULL, nr, mask); } /* @@ -475,15 +478,13 @@ SYSCALL_DEFINE4(futex_requeue, } #ifdef CONFIG_COMPAT -COMPAT_SYSCALL_DEFINE2(set_robust_list, - struct compat_robust_list_head __user *, head, - compat_size_t, len) +COMPAT_SYSCALL_DEFINE2(set_robust_list, struct compat_robust_list_head __user *, head, + compat_size_t, len) { if (unlikely(len != sizeof(*head))) return -EINVAL; - current->compat_robust_list = head; - + current->futex.compat_robust_list = head; return 0; } @@ -523,4 +524,3 @@ SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val, return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); } #endif /* CONFIG_COMPAT_32BIT_TIME */ - diff --git a/kernel/futex/waitwake.c b/kernel/futex/waitwake.c index ceed9d879059..d4483d15d30a 100644 --- a/kernel/futex/waitwake.c +++ b/kernel/futex/waitwake.c @@ -150,12 +150,35 @@ void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q) } /* + * If requested, clear the robust list pending op and unlock the futex + */ +static bool futex_robust_unlock(u32 __user *uaddr, unsigned int flags, void __user *pop) +{ + if (!(flags & FLAGS_ROBUST_UNLOCK)) + return true; + + /* First unlock the futex, which requires release semantics. */ + scoped_user_write_access(uaddr, efault) + unsafe_atomic_store_release_user(0, uaddr, efault); + + /* + * Clear the pending list op now. If that fails, then the task is in + * deeper trouble as the robust list head is usually part of the TLS. + * The chance of survival is close to zero. + */ + return futex_robust_list_clear_pending(pop, flags); + +efault: + return false; +} + +/* * Wake up waiters matching bitset queued on this futex (uaddr). */ -int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) +int futex_wake(u32 __user *uaddr, unsigned int flags, void __user *pop, int nr_wake, u32 bitset) { - struct futex_q *this, *next; union futex_key key = FUTEX_KEY_INIT; + struct futex_q *this, *next; DEFINE_WAKE_Q(wake_q); int ret; @@ -166,10 +189,14 @@ int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) if (unlikely(ret != 0)) return ret; + if (!futex_robust_unlock(uaddr, flags, pop)) + return -EFAULT; + if ((flags & FLAGS_STRICT) && !nr_wake) return 0; - CLASS(hb, hb)(&key); + CLASS(hbr, hbr)(&key); + auto hb = hbr.hb; /* Make sure we really have tasks to wakeup */ if (!futex_hb_waiters_pending(hb)) @@ -266,8 +293,10 @@ retry: retry_private: if (1) { - CLASS(hb, hb1)(&key1); - CLASS(hb, hb2)(&key2); + CLASS(hbr, hbr1)(&key1); + CLASS(hbr, hbr2)(&key2); + auto hb1 = hbr1.hb; + auto hb2 = hbr2.hb; double_lock_hb(hb1, hb2); op_ret = futex_atomic_op_inuser(op, uaddr2); @@ -409,7 +438,7 @@ int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken) * Make sure to have a reference on the private_hash such that we * don't block on rehash after changing the task state below. */ - guard(private_hash)(); + guard(private_hash)(current->mm); /* * Enqueuing multiple futexes is tricky, because we need to enqueue @@ -446,7 +475,8 @@ retry: u32 val = vs[i].w.val; if (1) { - CLASS(hb, hb)(&q->key); + CLASS(hbr, hbr)(&q->key); + auto hb = hbr.hb; futex_q_lock(q, hb); ret = futex_get_value_locked(&uval, uaddr); @@ -621,7 +651,8 @@ retry: retry_private: if (1) { - CLASS(hb, hb)(&q->key); + CLASS(hbr, hbr)(&q->key); + auto hb = hbr.hb; futex_q_lock(q, hb); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index b635e3c5d5b6..de754db414d1 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -48,9 +48,11 @@ int irq_set_chip(unsigned int irq, const struct irq_chip *chip) scoped_irqdesc->irq_data.chip = (struct irq_chip *)(chip ?: &no_irq_chip); ret = 0; } - /* For !CONFIG_SPARSE_IRQ make the irq show up in allocated_irqs. */ - if (!ret) + if (!ret) { + /* For !CONFIG_SPARSE_IRQ make the irq show up in allocated_irqs. */ irq_mark_irq(irq); + irq_proc_update_chip(chip); + } return ret; } EXPORT_SYMBOL(irq_set_chip); @@ -1012,6 +1014,7 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, WARN_ON(irq_chip_pm_get(irq_desc_get_irq_data(desc))); irq_activate_and_startup(desc, IRQ_RESEND); } + irq_proc_update_valid(desc); } void __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, @@ -1072,6 +1075,7 @@ void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set) trigger = tmp; irqd_set(&desc->irq_data, trigger); + irq_proc_update_valid(desc); } } EXPORT_SYMBOL_GPL(irq_modify_status); diff --git a/kernel/irq/debugfs.h b/kernel/irq/debugfs.h new file mode 100644 index 000000000000..8a9360d5fefb --- /dev/null +++ b/kernel/irq/debugfs.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _KERNEL_IRQ_DEBUGFS_H +#define _KERNEL_IRQ_DEBUGFS_H + +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS +#include <linux/debugfs.h> + +struct irq_bit_descr { + unsigned int mask; + char *name; +}; + +#define BIT_MASK_DESCR(m) { .mask = m, .name = #m } + +void irq_debug_show_bits(struct seq_file *m, int ind, unsigned int state, + const struct irq_bit_descr *sd, int size); + +void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc); +static inline void irq_remove_debugfs_entry(struct irq_desc *desc) +{ + debugfs_remove(desc->debugfs_file); + kfree(desc->dev_name); +} +void irq_debugfs_copy_devname(int irq, struct device *dev); +# ifdef CONFIG_IRQ_DOMAIN +void irq_domain_debugfs_init(struct dentry *root); +# else +static inline void irq_domain_debugfs_init(struct dentry *root) +{ +} +# endif +#else /* CONFIG_GENERIC_IRQ_DEBUGFS */ +static inline void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *d) +{ +} +static inline void irq_remove_debugfs_entry(struct irq_desc *d) +{ +} +static inline void irq_debugfs_copy_devname(int irq, struct device *dev) +{ +} +#endif /* CONFIG_GENERIC_IRQ_DEBUGFS */ + +#endif diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 9412e57056f5..0ce21dd45404 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -9,8 +9,12 @@ #include <linux/irqdesc.h> #include <linux/kernel_stat.h> #include <linux/pm_runtime.h> +#include <linux/rcuref.h> #include <linux/sched/clock.h> +#include "debugfs.h" +#include "proc.h" + #ifdef CONFIG_SPARSE_IRQ # define MAX_SPARSE_IRQS INT_MAX #else @@ -21,6 +25,7 @@ extern bool noirqdebug; extern int irq_poll_cpu; +extern unsigned int total_nr_irqs; extern struct irqaction chained_action; @@ -100,9 +105,23 @@ extern void unmask_irq(struct irq_desc *desc); extern void unmask_threaded_irq(struct irq_desc *desc); #ifdef CONFIG_SPARSE_IRQ -static inline void irq_mark_irq(unsigned int irq) { } +static __always_inline void irq_mark_irq(unsigned int irq) { } +void irq_desc_free_rcu(struct irq_desc *desc); + +static __always_inline bool irq_desc_get_ref(struct irq_desc *desc) +{ + return rcuref_get(&desc->refcnt); +} + +static __always_inline void irq_desc_put_ref(struct irq_desc *desc) +{ + if (rcuref_put(&desc->refcnt)) + irq_desc_free_rcu(desc); +} #else extern void irq_mark_irq(unsigned int irq); +static __always_inline bool irq_desc_get_ref(struct irq_desc *desc) { return true; } +static __always_inline void irq_desc_put_ref(struct irq_desc *desc) { } #endif irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc); @@ -122,6 +141,7 @@ extern void register_irq_proc(unsigned int irq, struct irq_desc *desc); extern void unregister_irq_proc(unsigned int irq, struct irq_desc *desc); extern void register_handler_proc(unsigned int irq, struct irqaction *action); extern void unregister_handler_proc(unsigned int irq, struct irqaction *action); +void irq_proc_update_valid(struct irq_desc *desc); #else static inline void register_irq_proc(unsigned int irq, struct irq_desc *desc) { } static inline void unregister_irq_proc(unsigned int irq, struct irq_desc *desc) { } @@ -129,8 +149,11 @@ static inline void register_handler_proc(unsigned int irq, struct irqaction *action) { } static inline void unregister_handler_proc(unsigned int irq, struct irqaction *action) { } +static inline void irq_proc_update_valid(struct irq_desc *desc) { } #endif +struct irq_desc *irq_find_desc_at_or_after(unsigned int offset); + extern bool irq_can_set_affinity_usr(unsigned int irq); extern int irq_do_set_affinity(struct irq_data *data, @@ -171,7 +194,7 @@ void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus) __DEFINE_CLASS_IS_CONDITIONAL(irqdesc_lock, true); __DEFINE_UNLOCK_GUARD(irqdesc_lock, struct irq_desc, - __irq_put_desc_unlock(_T->lock, _T->flags, _T->bus), + if (_T->lock) __irq_put_desc_unlock(_T->lock, _T->flags, _T->bus), unsigned long flags; bool bus); static inline class_irqdesc_lock_t class_irqdesc_lock_constructor(unsigned int irq, bool bus, @@ -372,42 +395,3 @@ static inline struct irq_data *irqd_get_parent_data(struct irq_data *irqd) return NULL; #endif } - -#ifdef CONFIG_GENERIC_IRQ_DEBUGFS -#include <linux/debugfs.h> - -struct irq_bit_descr { - unsigned int mask; - char *name; -}; - -#define BIT_MASK_DESCR(m) { .mask = m, .name = #m } - -void irq_debug_show_bits(struct seq_file *m, int ind, unsigned int state, - const struct irq_bit_descr *sd, int size); - -void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc); -static inline void irq_remove_debugfs_entry(struct irq_desc *desc) -{ - debugfs_remove(desc->debugfs_file); - kfree(desc->dev_name); -} -void irq_debugfs_copy_devname(int irq, struct device *dev); -# ifdef CONFIG_IRQ_DOMAIN -void irq_domain_debugfs_init(struct dentry *root); -# else -static inline void irq_domain_debugfs_init(struct dentry *root) -{ -} -# endif -#else /* CONFIG_GENERIC_IRQ_DEBUGFS */ -static inline void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *d) -{ -} -static inline void irq_remove_debugfs_entry(struct irq_desc *d) -{ -} -static inline void irq_debugfs_copy_devname(int irq, struct device *dev) -{ -} -#endif /* CONFIG_GENERIC_IRQ_DEBUGFS */ diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 7173b8b634f2..80ef4e27dcf4 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -137,17 +137,18 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node, desc->tot_count = 0; desc->name = NULL; desc->owner = owner; + rcuref_init(&desc->refcnt, 1); desc_smp_init(desc, node, affinity); } -static unsigned int nr_irqs = NR_IRQS; +unsigned int total_nr_irqs __read_mostly = NR_IRQS; /** * irq_get_nr_irqs() - Number of interrupts supported by the system. */ unsigned int irq_get_nr_irqs(void) { - return nr_irqs; + return total_nr_irqs; } EXPORT_SYMBOL_GPL(irq_get_nr_irqs); @@ -157,13 +158,12 @@ EXPORT_SYMBOL_GPL(irq_get_nr_irqs); * * Return: @nr. */ -unsigned int irq_set_nr_irqs(unsigned int nr) +unsigned int __init irq_set_nr_irqs(unsigned int nr) { - nr_irqs = nr; - + total_nr_irqs = nr; + irq_proc_calc_prec(); return nr; } -EXPORT_SYMBOL_GPL(irq_set_nr_irqs); static DEFINE_MUTEX(sparse_irq_lock); static struct maple_tree sparse_irqs = MTREE_INIT_EXT(sparse_irqs, @@ -181,15 +181,12 @@ static int irq_find_free_area(unsigned int from, unsigned int cnt) return mas.index; } -static unsigned int irq_find_at_or_after(unsigned int offset) +struct irq_desc *irq_find_desc_at_or_after(unsigned int offset) { unsigned long index = offset; - struct irq_desc *desc; - - guard(rcu)(); - desc = mt_find(&sparse_irqs, &index, nr_irqs); - return desc ? irq_desc_get_irq(desc) : nr_irqs; + lockdep_assert_in_rcu_read_lock(); + return mt_find(&sparse_irqs, &index, total_nr_irqs); } static void irq_insert_desc(unsigned int irq, struct irq_desc *desc) @@ -466,6 +463,17 @@ static void delayed_free_desc(struct rcu_head *rhp) kobject_put(&desc->kobj); } +void irq_desc_free_rcu(struct irq_desc *desc) +{ + /* + * We free the descriptor, masks and stat fields via RCU. That + * allows demultiplex interrupts to do rcu based management of + * the child interrupts. + * This also allows us to use rcu in kstat_irqs_usr(). + */ + call_rcu(&desc->rcu, delayed_free_desc); +} + static void free_desc(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); @@ -484,14 +492,7 @@ static void free_desc(unsigned int irq) */ irq_sysfs_del(desc); delete_irq_desc(irq); - - /* - * We free the descriptor, masks and stat fields via RCU. That - * allows demultiplex interrupts to do rcu based management of - * the child interrupts. - * This also allows us to use rcu in kstat_irqs_usr(). - */ - call_rcu(&desc->rcu, delayed_free_desc); + irq_desc_put_ref(desc); } static int alloc_descs(unsigned int start, unsigned int cnt, int node, @@ -543,7 +544,8 @@ static bool irq_expand_nr_irqs(unsigned int nr) { if (nr > MAX_SPARSE_IRQS) return false; - nr_irqs = nr; + total_nr_irqs = nr; + irq_proc_calc_prec(); return true; } @@ -557,21 +559,22 @@ int __init early_irq_init(void) /* Let arch update nr_irqs and return the nr of preallocated irqs */ initcnt = arch_probe_nr_irqs(); printk(KERN_INFO "NR_IRQS: %d, nr_irqs: %d, preallocated irqs: %d\n", - NR_IRQS, nr_irqs, initcnt); + NR_IRQS, total_nr_irqs, initcnt); - if (WARN_ON(nr_irqs > MAX_SPARSE_IRQS)) - nr_irqs = MAX_SPARSE_IRQS; + if (WARN_ON(total_nr_irqs > MAX_SPARSE_IRQS)) + total_nr_irqs = MAX_SPARSE_IRQS; if (WARN_ON(initcnt > MAX_SPARSE_IRQS)) initcnt = MAX_SPARSE_IRQS; - if (initcnt > nr_irqs) - nr_irqs = initcnt; + if (initcnt > total_nr_irqs) + total_nr_irqs = initcnt; for (i = 0; i < initcnt; i++) { desc = alloc_desc(i, node, 0, NULL, NULL); irq_insert_desc(i, desc); } + irq_proc_calc_prec(); return arch_early_irq_init(); } @@ -592,7 +595,7 @@ int __init early_irq_init(void) init_irq_default_affinity(); - printk(KERN_INFO "NR_IRQS: %d\n", NR_IRQS); + pr_info("NR_IRQS: %d\n", NR_IRQS); count = ARRAY_SIZE(irq_desc); @@ -602,6 +605,7 @@ int __init early_irq_init(void) goto __free_desc_res; } + irq_proc_calc_prec(); return arch_early_irq_init(); __free_desc_res: @@ -862,7 +866,7 @@ void irq_free_descs(unsigned int from, unsigned int cnt) { int i; - if (from >= nr_irqs || (from + cnt) > nr_irqs) + if (from >= total_nr_irqs || (from + cnt) > total_nr_irqs) return; guard(mutex)(&sparse_irq_lock); @@ -911,7 +915,7 @@ int __ref __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int no if (irq >=0 && start != irq) return -EEXIST; - if (start + cnt > nr_irqs) { + if (start + cnt > total_nr_irqs) { if (!irq_expand_nr_irqs(start + cnt)) return -ENOMEM; } @@ -923,11 +927,15 @@ EXPORT_SYMBOL_GPL(__irq_alloc_descs); * irq_get_next_irq - get next allocated irq number * @offset: where to start the search * - * Returns next irq number after offset or nr_irqs if none is found. + * Returns next irq number after offset or total_nr_irqs if none is found. */ unsigned int irq_get_next_irq(unsigned int offset) { - return irq_find_at_or_after(offset); + struct irq_desc *desc; + + guard(rcu)(); + desc = irq_find_desc_at_or_after(offset); + return desc ? irq_desc_get_irq(desc) : total_nr_irqs; } struct irq_desc *__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus, diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index cc93abf009e8..f15c9f1223bb 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -20,6 +20,8 @@ #include <linux/smp.h> #include <linux/fs.h> +#include "proc.h" + static LIST_HEAD(irq_domain_list); static DEFINE_MUTEX(irq_domain_mutex); @@ -1532,6 +1534,7 @@ int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq, irq_data->chip = (struct irq_chip *)(chip ? chip : &no_irq_chip); irq_data->chip_data = chip_data; + irq_proc_update_chip(chip); return 0; } EXPORT_SYMBOL_GPL(irq_domain_set_hwirq_and_chip); @@ -2081,7 +2084,7 @@ static void irq_domain_free_one_irq(struct irq_domain *domain, unsigned int virq #endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ #ifdef CONFIG_GENERIC_IRQ_DEBUGFS -#include "internals.h" +#include "debugfs.h" static struct dentry *domain_dir; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 2e8072437826..7eb07e3bdb4c 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1802,6 +1802,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) __enable_irq(desc); } + irq_proc_update_valid(desc); raw_spin_unlock_irqrestore(&desc->lock, flags); chip_bus_sync_unlock(desc); mutex_unlock(&desc->request_mutex); @@ -1906,6 +1907,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) desc->affinity_hint = NULL; #endif + irq_proc_update_valid(desc); raw_spin_unlock_irqrestore(&desc->lock, flags); /* * Drop bus_lock here so the changes which were done in the chip @@ -2026,24 +2028,32 @@ const void *free_irq(unsigned int irq, void *dev_id) } EXPORT_SYMBOL(free_irq); -/* This function must be called with desc->lock held */ static const void *__cleanup_nmi(unsigned int irq, struct irq_desc *desc) { + struct irqaction *action = NULL; const char *devname = NULL; - desc->istate &= ~IRQS_NMI; + scoped_guard(raw_spinlock_irqsave, &desc->lock) { + irq_nmi_teardown(desc); - if (!WARN_ON(desc->action == NULL)) { - irq_pm_remove_action(desc, desc->action); - devname = desc->action->name; - unregister_handler_proc(irq, desc->action); + desc->istate &= ~IRQS_NMI; - kfree(desc->action); + if (!WARN_ON(desc->action == NULL)) { + action = desc->action; + irq_pm_remove_action(desc, action); + devname = action->name; + } desc->action = NULL; + + irq_settings_clr_disable_unlazy(desc); + irq_shutdown_and_deactivate(desc); } - irq_settings_clr_disable_unlazy(desc); - irq_shutdown_and_deactivate(desc); + irq_proc_update_valid(desc); + + if (action) + unregister_handler_proc(irq, action); + kfree(action); irq_release_resources(desc); @@ -2067,8 +2077,6 @@ const void *free_nmi(unsigned int irq, void *dev_id) if (WARN_ON(desc->depth == 0)) disable_nmi_nosync(irq); - guard(raw_spinlock_irqsave)(&desc->lock); - irq_nmi_teardown(desc); return __cleanup_nmi(irq, desc); } @@ -2318,13 +2326,14 @@ int request_nmi(unsigned int irq, irq_handler_t handler, /* Setup NMI state */ desc->istate |= IRQS_NMI; retval = irq_nmi_setup(desc); - if (retval) { - __cleanup_nmi(irq, desc); - return -EINVAL; - } - return 0; } + if (retval) { + __cleanup_nmi(irq, desc); + return -EINVAL; + } + return 0; + err_irq_setup: irq_chip_pm_put(&desc->irq_data); err_out: @@ -2428,8 +2437,10 @@ static struct irqaction *__free_percpu_irq(unsigned int irq, void __percpu *dev_ *action_ptr = action->next; /* Demote from NMI if we killed the last action */ - if (!desc->action) + if (!desc->action) { desc->istate &= ~IRQS_NMI; + irq_proc_update_valid(desc); + } } unregister_handler_proc(irq, action); diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index b0999a4f1f68..1b835725f7b1 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -10,6 +10,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/interrupt.h> +#include <linux/kernel.h> #include <linux/kernel_stat.h> #include <linux/mutex.h> #include <linux/string.h> @@ -326,7 +327,7 @@ void register_handler_proc(unsigned int irq, struct irqaction *action) #undef MAX_NAMELEN -#define MAX_NAMELEN 10 +#define MAX_NAMELEN 11 void register_irq_proc(unsigned int irq, struct irq_desc *desc) { @@ -348,7 +349,7 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc) return; /* create /proc/irq/1234 */ - sprintf(name, "%u", irq); + snprintf(name, MAX_NAMELEN, "%u", irq); desc->dir = proc_mkdir(name, root_irq_dir); if (!desc->dir) return; @@ -401,7 +402,7 @@ void unregister_irq_proc(unsigned int irq, struct irq_desc *desc) #endif remove_proc_entry("spurious", desc->dir); - sprintf(name, "%u", irq); + snprintf(name, MAX_NAMELEN, "%u", irq); remove_proc_entry(name, root_irq_dir); } @@ -439,77 +440,159 @@ void init_irq_proc(void) register_irq_proc(irq, desc); } +void irq_proc_update_valid(struct irq_desc *desc) +{ + u32 set = _IRQ_PROC_VALID; + + if (irq_settings_is_hidden(desc) || irq_desc_is_chained(desc) || !desc->action) + set = 0; + + irq_settings_update_proc_valid(desc, set); +} + #ifdef CONFIG_GENERIC_IRQ_SHOW +#define ARCH_PROC_IRQDESC ((void *)0x00001111) + int __weak arch_show_interrupts(struct seq_file *p, int prec) { return 0; } +static DEFINE_RAW_SPINLOCK(irq_proc_constraints_lock); + +static struct irq_proc_constraints { + bool print_header; + unsigned int num_prec; + unsigned int chip_width; +} irq_proc_constraints __read_mostly = { + .num_prec = 4, + .chip_width = 8, +}; + #ifndef ACTUAL_NR_IRQS -# define ACTUAL_NR_IRQS irq_get_nr_irqs() +# define ACTUAL_NR_IRQS total_nr_irqs #endif -int show_interrupts(struct seq_file *p, void *v) +void irq_proc_calc_prec(void) { - const unsigned int nr_irqs = irq_get_nr_irqs(); - static int prec; + unsigned int prec, n; - int i = *(loff_t *) v, j; - struct irqaction *action; - struct irq_desc *desc; + for (prec = 4, n = 10000; prec < 10 && n <= total_nr_irqs; ++prec) + n *= 10; + + guard(raw_spinlock_irqsave)(&irq_proc_constraints_lock); + if (prec > irq_proc_constraints.num_prec) + WRITE_ONCE(irq_proc_constraints.num_prec, prec); +} + +void irq_proc_update_chip(const struct irq_chip *chip) +{ + unsigned int len = chip && chip->name ? strlen(chip->name) : 0; + + if (!len || len <= READ_ONCE(irq_proc_constraints.chip_width)) + return; + + /* Can be invoked from interrupt disabled contexts */ + guard(raw_spinlock_irqsave)(&irq_proc_constraints_lock); + if (len > irq_proc_constraints.chip_width) + WRITE_ONCE(irq_proc_constraints.chip_width, len); +} + +/* Same as seq_put_decimal_ull_width(p, " ", cnt, 10) */ +#define ZSTR1 " 0" +#define ZSTR1_LEN (sizeof(ZSTR1) - 1) +#define ZSTR16 ZSTR1 ZSTR1 ZSTR1 ZSTR1 ZSTR1 ZSTR1 ZSTR1 ZSTR1 \ + ZSTR1 ZSTR1 ZSTR1 ZSTR1 ZSTR1 ZSTR1 ZSTR1 ZSTR1 +#define ZSTR256 ZSTR16 ZSTR16 ZSTR16 ZSTR16 ZSTR16 ZSTR16 ZSTR16 ZSTR16 \ + ZSTR16 ZSTR16 ZSTR16 ZSTR16 ZSTR16 ZSTR16 ZSTR16 ZSTR16 + +static inline void irq_proc_emit_zero_counts(struct seq_file *p, unsigned int zeros) +{ + if (!zeros) + return; + + for (unsigned int n = min(zeros, 256); n; zeros -= n, n = min(zeros, 256)) + seq_write(p, ZSTR256, n * ZSTR1_LEN); +} + +static inline unsigned int irq_proc_emit_count(struct seq_file *p, unsigned int cnt, + unsigned int zeros) +{ + if (!cnt) + return zeros + 1; - if (i > ACTUAL_NR_IRQS) - return 0; + irq_proc_emit_zero_counts(p, zeros); + seq_put_decimal_ull_width(p, " ", cnt, 10); + return 0; +} - if (i == ACTUAL_NR_IRQS) - return arch_show_interrupts(p, prec); +void irq_proc_emit_counts(struct seq_file *p, unsigned int __percpu *cnts) +{ + unsigned int cpu, zeros = 0; - /* print header and calculate the width of the first column */ - if (i == 0) { - for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec) - j *= 10; + for_each_online_cpu(cpu) + zeros = irq_proc_emit_count(p, per_cpu(*cnts, cpu), zeros); + irq_proc_emit_zero_counts(p, zeros); +} - seq_printf(p, "%*s", prec + 8, ""); - for_each_online_cpu(j) - seq_printf(p, "CPU%-8d", j); +static int irq_seq_show(struct seq_file *p, void *v) +{ + struct irq_proc_constraints *constr = p->private; + struct irq_desc *desc = v; + struct irqaction *action; + + /* Print header for the first interrupt? */ + if (constr->print_header) { + unsigned int cpu; + + seq_printf(p, "%*s", constr->num_prec + 8, ""); + for_each_online_cpu(cpu) + seq_printf(p, "CPU%-8d", cpu); seq_putc(p, '\n'); + constr->print_header = false; } - guard(rcu)(); - desc = irq_to_desc(i); - if (!desc || irq_settings_is_hidden(desc)) - return 0; + if (desc == ARCH_PROC_IRQDESC) + return arch_show_interrupts(p, constr->num_prec); - if (!desc->action || irq_desc_is_chained(desc) || !desc->kstat_irqs) - return 0; + seq_put_decimal_ull_width(p, "", irq_desc_get_irq(desc), constr->num_prec); + seq_putc(p, ':'); - seq_printf(p, "%*d:", prec, i); - for_each_online_cpu(j) { - unsigned int cnt = desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, j) : 0; + /* + * Always output per CPU interrupts. Output device interrupts only when + * desc::tot_count is not zero. + */ + if (irq_settings_is_per_cpu(desc) || irq_settings_is_per_cpu_devid(desc) || + data_race(desc->tot_count)) + irq_proc_emit_counts(p, &desc->kstat_irqs->cnt); + else + irq_proc_emit_zero_counts(p, num_online_cpus()); - seq_put_decimal_ull_width(p, " ", cnt, 10); - } - seq_putc(p, ' '); + /* Enforce a visual gap */ + seq_write(p, " ", 2); guard(raw_spinlock_irq)(&desc->lock); if (desc->irq_data.chip) { if (desc->irq_data.chip->irq_print_chip) desc->irq_data.chip->irq_print_chip(&desc->irq_data, p); else if (desc->irq_data.chip->name) - seq_printf(p, "%8s", desc->irq_data.chip->name); + seq_printf(p, "%-*s", constr->chip_width, desc->irq_data.chip->name); else - seq_printf(p, "%8s", "-"); + seq_printf(p, "%-*s", constr->chip_width, "-"); } else { - seq_printf(p, "%8s", "None"); + seq_printf(p, "%-*s", constr->chip_width, "None"); } + + seq_putc(p, ' '); if (desc->irq_data.domain) - seq_printf(p, " %*lu", prec, desc->irq_data.hwirq); + seq_put_decimal_ull_width(p, "", desc->irq_data.hwirq, constr->num_prec); else - seq_printf(p, " %*s", prec, ""); -#ifdef CONFIG_GENERIC_IRQ_SHOW_LEVEL - seq_printf(p, " %-8s", irqd_is_level_type(&desc->irq_data) ? "Level" : "Edge"); -#endif + seq_printf(p, " %*s", constr->num_prec, ""); + + if (IS_ENABLED(CONFIG_GENERIC_IRQ_SHOW_LEVEL)) + seq_printf(p, " %-8s", irqd_is_level_type(&desc->irq_data) ? "Level" : "Edge"); + if (desc->name) seq_printf(p, "-%-8s", desc->name); @@ -523,4 +606,73 @@ int show_interrupts(struct seq_file *p, void *v) seq_putc(p, '\n'); return 0; } + +static void *irq_seq_next_desc(loff_t *pos) +{ + if (*pos > total_nr_irqs) + return NULL; + + guard(rcu)(); + for (;;) { + struct irq_desc *desc = irq_find_desc_at_or_after((unsigned int) *pos); + + if (desc) { + *pos = irq_desc_get_irq(desc); + /* + * If valid for output then try to acquire a reference + * count on the descriptor so that it can't be freed + * after dropping RCU read lock on return. + */ + if (irq_settings_proc_valid(desc) && irq_desc_get_ref(desc)) + return desc; + (*pos)++; + } else { + *pos = total_nr_irqs; + return ARCH_PROC_IRQDESC; + } + } +} + +static void *irq_seq_start(struct seq_file *f, loff_t *pos) +{ + if (!*pos) { + struct irq_proc_constraints *constr = f->private; + + constr->num_prec = READ_ONCE(irq_proc_constraints.num_prec); + constr->chip_width = READ_ONCE(irq_proc_constraints.chip_width); + constr->print_header = true; + } + return irq_seq_next_desc(pos); +} + +static void *irq_seq_next(struct seq_file *f, void *v, loff_t *pos) +{ + if (v && v != ARCH_PROC_IRQDESC) + irq_desc_put_ref(v); + + (*pos)++; + return irq_seq_next_desc(pos); +} + +static void irq_seq_stop(struct seq_file *f, void *v) +{ + if (v && v != ARCH_PROC_IRQDESC) + irq_desc_put_ref(v); +} + +static const struct seq_operations irq_seq_ops = { + .start = irq_seq_start, + .next = irq_seq_next, + .stop = irq_seq_stop, + .show = irq_seq_show, +}; + +static int __init irq_proc_init(void) +{ + proc_create_seq_private("interrupts", 0, NULL, &irq_seq_ops, + sizeof(irq_proc_constraints), NULL); + return 0; +} +fs_initcall(irq_proc_init); + #endif diff --git a/kernel/irq/proc.h b/kernel/irq/proc.h new file mode 100644 index 000000000000..0631d57fbfb7 --- /dev/null +++ b/kernel/irq/proc.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _KERNEL_IRQ_PROC_H +#define _KERNEL_IRQ_PROC_H + +#if defined(CONFIG_PROC_FS) && defined(CONFIG_GENERIC_IRQ_SHOW) +void irq_proc_calc_prec(void); +void irq_proc_update_chip(const struct irq_chip *chip); +#else +static inline void irq_proc_calc_prec(void) { } +static inline void irq_proc_update_chip(const struct irq_chip *chip) { } +#endif + +#endif diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h index 00b3bd127692..0a0c027a5d34 100644 --- a/kernel/irq/settings.h +++ b/kernel/irq/settings.h @@ -18,6 +18,7 @@ enum { _IRQ_DISABLE_UNLAZY = IRQ_DISABLE_UNLAZY, _IRQ_HIDDEN = IRQ_HIDDEN, _IRQ_NO_DEBUG = IRQ_NO_DEBUG, + _IRQ_PROC_VALID = IRQ_RESERVED, _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK, }; @@ -34,6 +35,7 @@ enum { #define IRQ_DISABLE_UNLAZY GOT_YOU_MORON #define IRQ_HIDDEN GOT_YOU_MORON #define IRQ_NO_DEBUG GOT_YOU_MORON +#define IRQ_RESERVED GOT_YOU_MORON #undef IRQF_MODIFY_MASK #define IRQF_MODIFY_MASK GOT_YOU_MORON @@ -180,3 +182,14 @@ static inline bool irq_settings_no_debug(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_NO_DEBUG; } + +static inline bool irq_settings_proc_valid(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_PROC_VALID; +} + +static inline void irq_settings_update_proc_valid(struct irq_desc *desc, u32 set) +{ + desc->status_use_accessors &= ~_IRQ_PROC_VALID; + desc->status_use_accessors |= (set & _IRQ_PROC_VALID); +} diff --git a/kernel/kthread.c b/kernel/kthread.c index 791210daf8b4..63beb59b7a3d 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -1619,7 +1619,6 @@ void kthread_use_mm(struct mm_struct *mm) WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD)); WARN_ON_ONCE(tsk->mm); - WARN_ON_ONCE(!mm->user_ns); /* * It is possible for mm to be the same as tsk->active_mm, but diff --git a/kernel/liveupdate/kexec_handover.c b/kernel/liveupdate/kexec_handover.c index 2592f7ca16e2..1b592d86dc48 100644 --- a/kernel/liveupdate/kexec_handover.c +++ b/kernel/liveupdate/kexec_handover.c @@ -357,20 +357,6 @@ int kho_radix_walk_tree(struct kho_radix_tree *tree, } EXPORT_SYMBOL_GPL(kho_radix_walk_tree); -static void __kho_unpreserve(struct kho_radix_tree *tree, - unsigned long pfn, unsigned long end_pfn) -{ - unsigned int order; - - while (pfn < end_pfn) { - order = min(count_trailing_zeros(pfn), ilog2(end_pfn - pfn)); - - kho_radix_del_page(tree, pfn, order); - - pfn += 1 << order; - } -} - /* For physically contiguous 0-order pages. */ static void kho_init_pages(struct page *page, unsigned long nr_pages) { @@ -860,6 +846,37 @@ void kho_unpreserve_folio(struct folio *folio) } EXPORT_SYMBOL_GPL(kho_unpreserve_folio); +static unsigned int __kho_preserve_pages_order(unsigned long start_pfn, + unsigned long end_pfn) +{ + unsigned int order = min(count_trailing_zeros(start_pfn), + ilog2(end_pfn - start_pfn)); + + /* + * Make sure all the pages in a single preservation are in the same NUMA + * node. The restore machinery can not cope with a preservation spanning + * multiple NUMA nodes. + */ + while (pfn_to_nid(start_pfn) != pfn_to_nid(start_pfn + (1UL << order) - 1)) + order--; + + return order; +} + +static void __kho_unpreserve(struct kho_radix_tree *tree, + unsigned long pfn, unsigned long end_pfn) +{ + unsigned int order; + + while (pfn < end_pfn) { + order = __kho_preserve_pages_order(pfn, end_pfn); + + kho_radix_del_page(tree, pfn, order); + + pfn += 1 << order; + } +} + /** * kho_preserve_pages - preserve contiguous pages across kexec * @page: first page in the list. @@ -885,16 +902,7 @@ int kho_preserve_pages(struct page *page, unsigned long nr_pages) } while (pfn < end_pfn) { - unsigned int order = - min(count_trailing_zeros(pfn), ilog2(end_pfn - pfn)); - - /* - * Make sure all the pages in a single preservation are in the - * same NUMA node. The restore machinery can not cope with a - * preservation spanning multiple NUMA nodes. - */ - while (pfn_to_nid(pfn) != pfn_to_nid(pfn + (1UL << order) - 1)) - order--; + unsigned int order = __kho_preserve_pages_order(pfn, end_pfn); err = kho_radix_add_page(tree, pfn, order); if (err) { diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 09534628dc01..8a85912d7ee6 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -763,6 +763,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas raw_spin_lock_irqsave(&lock->wait_lock, flags); raw_spin_lock(¤t->blocked_lock); __set_task_blocked_on(current, lock); + set_current_state(state); if (opt_acquired) break; @@ -980,9 +981,8 @@ EXPORT_SYMBOL_GPL(ww_mutex_lock_interruptible); static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip) __releases(lock) { - struct task_struct *next = NULL; + struct task_struct *donor, *next = NULL; struct mutex_waiter *waiter; - DEFINE_WAKE_Q(wake_q); unsigned long owner; unsigned long flags; @@ -990,6 +990,14 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne __release(lock); /* + * Ensures the proxy donor stack is stable across unlock and handoff. + * Specifically, it avoids the case where current->blocked_donor is + * NULL when it is inspected while doing the unlock, but a preemption + * before taking the wake_lock would make it set and a hand-off is + * missed. + */ + guard(preempt)(); + /* * Release the lock before (potentially) taking the spinlock such that * other contenders can get on with things ASAP. * @@ -1001,6 +1009,12 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne MUTEX_WARN_ON(__owner_task(owner) != current); MUTEX_WARN_ON(owner & MUTEX_FLAG_PICKUP); + if (sched_proxy_exec() && current->blocked_donor) { + /* force handoff if we have a blocked_donor */ + owner = MUTEX_FLAG_HANDOFF; + break; + } + if (owner & MUTEX_FLAG_HANDOFF) break; @@ -1013,20 +1027,56 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne } raw_spin_lock_irqsave(&lock->wait_lock, flags); + raw_spin_lock(¤t->blocked_lock); debug_mutex_unlock(lock); + + if (sched_proxy_exec()) { + /* + * If we have a task boosting current, and that task was boosting + * current through this lock, hand the lock to that task, as that + * is the highest waiter, as selected by the scheduling function. + */ + donor = current->blocked_donor; + if (donor) { + struct mutex *next_lock; + + raw_spin_lock_nested(&donor->blocked_lock, SINGLE_DEPTH_NESTING); + next_lock = __get_task_blocked_on(donor); + if (next_lock == lock) { + next = get_task_struct(donor); + __clear_task_blocked_on(next, lock); + current->blocked_donor = NULL; + } + raw_spin_unlock(&donor->blocked_lock); + } + } + + /* + * Failing that, pick first on the wait list. + */ waiter = lock->first_waiter; - if (waiter) { - next = waiter->task; + if (!next && waiter) { + next = get_task_struct(waiter->task); + raw_spin_lock_nested(&next->blocked_lock, SINGLE_DEPTH_NESTING); debug_mutex_wake_waiter(lock, waiter); - set_task_blocked_on_waking(next, lock); - wake_q_add(&wake_q, next); + __clear_task_blocked_on(next, lock); + raw_spin_unlock(&next->blocked_lock); + } + if (trace_contended_release_enabled() && waiter) + trace_call__contended_release(lock); + if (owner & MUTEX_FLAG_HANDOFF) __mutex_handoff(lock, next); - raw_spin_unlock_irqrestore_wake(&lock->wait_lock, flags, &wake_q); + raw_spin_unlock(¤t->blocked_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + if (next) { + wake_up_process(next); + put_task_struct(next); + } } #ifndef CONFIG_DEBUG_LOCK_ALLOC @@ -1220,6 +1270,7 @@ EXPORT_SYMBOL(ww_mutex_lock_interruptible); EXPORT_TRACEPOINT_SYMBOL_GPL(contention_begin); EXPORT_TRACEPOINT_SYMBOL_GPL(contention_end); +EXPORT_TRACEPOINT_SYMBOL_GPL(contended_release); /** * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0 diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index ef234469baac..f7e152c40d6d 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -263,6 +263,9 @@ void percpu_up_write(struct percpu_rw_semaphore *sem) { rwsem_release(&sem->dep_map, _RET_IP_); + if (trace_contended_release_enabled() && wq_has_sleeper(&sem->waiters)) + trace_call__contended_release(sem); + /* * Signal the writer is done, no fast path yet. * @@ -288,3 +291,29 @@ void percpu_up_write(struct percpu_rw_semaphore *sem) rcu_sync_exit(&sem->rss); } EXPORT_SYMBOL_GPL(percpu_up_write); + +void __percpu_up_read(struct percpu_rw_semaphore *sem) +{ + lockdep_assert_preemption_disabled(); + /* + * After percpu_up_write() completes, rcu_sync_is_idle() can still + * return false during the grace period, forcing readers into this + * slowpath. Only trace when a writer is actually waiting for + * readers to drain. + */ + if (trace_contended_release_enabled() && rcuwait_active(&sem->writer)) + trace_call__contended_release(sem); + /* + * slowpath; reader will only ever wake a single blocked + * writer. + */ + smp_mb(); /* B matches C */ + /* + * In other words, if they see our decrement (presumably to + * aggregate zero, as that is the only time it matters) they + * will also see our critical section. + */ + this_cpu_dec(*sem->read_count); + rcuwait_wake_up(&sem->writer); +} +EXPORT_SYMBOL_GPL(__percpu_up_read); diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 4f386ea6c792..4728631ae719 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -484,6 +484,7 @@ static __always_inline bool __waiter_less(struct rb_node *a, const struct rb_nod static __always_inline void rt_mutex_enqueue(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter) + __must_hold(&lock->wait_lock) { lockdep_assert_held(&lock->wait_lock); @@ -492,6 +493,7 @@ rt_mutex_enqueue(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter) static __always_inline void rt_mutex_dequeue(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter) + __must_hold(&lock->wait_lock) { lockdep_assert_held(&lock->wait_lock); @@ -1092,6 +1094,7 @@ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task, static int __sched try_to_take_rt_mutex(struct rt_mutex_base *lock, struct task_struct *task, struct rt_mutex_waiter *waiter) + __must_hold(&lock->wait_lock) { lockdep_assert_held(&lock->wait_lock); @@ -1319,6 +1322,7 @@ static int __sched task_blocks_on_rt_mutex(struct rt_mutex_base *lock, */ static void __sched mark_wakeup_next_waiter(struct rt_wake_q_head *wqh, struct rt_mutex_base *lock) + __must_hold(&lock->wait_lock) { struct rt_mutex_waiter *waiter; @@ -1466,6 +1470,7 @@ static void __sched rt_mutex_slowunlock(struct rt_mutex_base *lock) raw_spin_lock_irqsave(&lock->wait_lock, flags); } + trace_contended_release(lock); /* * The wakeup next waiter path does not suffer from the above * race. See the comments there. @@ -1558,6 +1563,9 @@ static void __sched remove_waiter(struct rt_mutex_base *lock, lockdep_assert_held(&lock->wait_lock); + if (!waiter_task) /* never enqueued */ + return; + scoped_guard(raw_spinlock, &waiter_task->pi_lock) { rt_mutex_dequeue(lock, waiter); waiter_task->pi_blocked_on = NULL; diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c index 124219aea46e..5d48d64725b1 100644 --- a/kernel/locking/rtmutex_api.c +++ b/kernel/locking/rtmutex_api.c @@ -41,6 +41,7 @@ static __always_inline int __rt_mutex_lock_common(struct rt_mutex *lock, unsigned int state, struct lockdep_map *nest_lock, unsigned int subclass) + __cond_acquires(0, lock) { int ret; @@ -67,13 +68,27 @@ EXPORT_SYMBOL(rt_mutex_base_init); */ void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass) { - __rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, NULL, subclass); + if (__rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, NULL, subclass) == 0) + return; + /* + * The code below is never reached because __rt_mutex_lock_common() only + * returns an error code if interrupted by a signal or upon a timeout. + */ + WARN_ON_ONCE(true); + __acquire(lock); } EXPORT_SYMBOL_GPL(rt_mutex_lock_nested); void __sched _rt_mutex_lock_nest_lock(struct rt_mutex *lock, struct lockdep_map *nest_lock) { - __rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, nest_lock, 0); + if (__rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, nest_lock, 0) == 0) + return; + /* + * The code below is never reached because __rt_mutex_lock_common() only + * returns an error code if interrupted by a signal or upon a timeout. + */ + WARN_ON_ONCE(true); + __acquire(lock); } EXPORT_SYMBOL_GPL(_rt_mutex_lock_nest_lock); @@ -86,7 +101,14 @@ EXPORT_SYMBOL_GPL(_rt_mutex_lock_nest_lock); */ void __sched rt_mutex_lock(struct rt_mutex *lock) { - __rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, NULL, 0); + if (__rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, NULL, 0) == 0) + return; + /* + * The code below is never reached because __rt_mutex_lock_common() only + * returns an error code if interrupted by a signal or upon a timeout. + */ + WARN_ON_ONCE(true); + __acquire(lock); } EXPORT_SYMBOL_GPL(rt_mutex_lock); #endif @@ -157,6 +179,7 @@ void __sched rt_mutex_unlock(struct rt_mutex *lock) { mutex_release(&lock->dep_map, _RET_IP_); __rt_mutex_unlock(&lock->rtmutex); + __release(lock); } EXPORT_SYMBOL_GPL(rt_mutex_unlock); @@ -182,6 +205,7 @@ int __sched __rt_mutex_futex_trylock(struct rt_mutex_base *lock) */ bool __sched __rt_mutex_futex_unlock(struct rt_mutex_base *lock, struct rt_wake_q_head *wqh) + __must_hold(&lock->wait_lock) { lockdep_assert_held(&lock->wait_lock); @@ -312,6 +336,7 @@ int __sched __rt_mutex_start_proxy_lock(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter, struct task_struct *task, struct wake_q_head *wake_q) + __must_hold(&lock->wait_lock) { int ret; @@ -365,7 +390,7 @@ int __sched rt_mutex_start_proxy_lock(struct rt_mutex_base *lock, raw_spin_lock_irq(&lock->wait_lock); ret = __rt_mutex_start_proxy_lock(lock, waiter, task, &wake_q); - if (unlikely(ret)) + if (unlikely(ret < 0)) remove_waiter(lock, waiter); preempt_disable(); raw_spin_unlock_irq(&lock->wait_lock); diff --git a/kernel/locking/rwbase_rt.c b/kernel/locking/rwbase_rt.c index 82e078c0665a..2835c9ef9b3f 100644 --- a/kernel/locking/rwbase_rt.c +++ b/kernel/locking/rwbase_rt.c @@ -174,6 +174,8 @@ static void __sched __rwbase_read_unlock(struct rwbase_rt *rwb, static __always_inline void rwbase_read_unlock(struct rwbase_rt *rwb, unsigned int state) { + if (trace_contended_release_enabled() && rt_mutex_owner(&rwb->rtmutex)) + trace_call__contended_release(rwb); /* * rwb->readers can only hit 0 when a writer is waiting for the * active readers to leave the critical section. @@ -205,6 +207,8 @@ static inline void rwbase_write_unlock(struct rwbase_rt *rwb) unsigned long flags; raw_spin_lock_irqsave(&rtm->wait_lock, flags); + if (trace_contended_release_enabled() && rt_mutex_has_waiters(rtm)) + trace_call__contended_release(rwb); __rwbase_write_unlock(rwb, WRITER_BIAS, flags); } @@ -214,6 +218,8 @@ static inline void rwbase_write_downgrade(struct rwbase_rt *rwb) unsigned long flags; raw_spin_lock_irqsave(&rtm->wait_lock, flags); + if (trace_contended_release_enabled() && rt_mutex_has_waiters(rtm)) + trace_call__contended_release(rwb); /* Release it and account current as reader */ __rwbase_write_unlock(rwb, WRITER_BIAS - 1, flags); } diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index bf647097369c..b9c180ac1eee 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -1387,6 +1387,8 @@ static inline void __up_read(struct rw_semaphore *sem) rwsem_clear_reader_owned(sem); tmp = atomic_long_add_return_release(-RWSEM_READER_BIAS, &sem->count); DEBUG_RWSEMS_WARN_ON(tmp < 0, sem); + if (trace_contended_release_enabled() && (tmp & RWSEM_FLAG_WAITERS)) + trace_call__contended_release(sem); if (unlikely((tmp & (RWSEM_LOCK_MASK|RWSEM_FLAG_WAITERS)) == RWSEM_FLAG_WAITERS)) { clear_nonspinnable(sem); @@ -1413,8 +1415,10 @@ static inline void __up_write(struct rw_semaphore *sem) preempt_disable(); rwsem_clear_owner(sem); tmp = atomic_long_fetch_add_release(-RWSEM_WRITER_LOCKED, &sem->count); - if (unlikely(tmp & RWSEM_FLAG_WAITERS)) + if (unlikely(tmp & RWSEM_FLAG_WAITERS)) { + trace_contended_release(sem); rwsem_wake(sem); + } preempt_enable(); } @@ -1437,8 +1441,10 @@ static inline void __downgrade_write(struct rw_semaphore *sem) tmp = atomic_long_fetch_add_release( -RWSEM_WRITER_LOCKED+RWSEM_READER_BIAS, &sem->count); rwsem_set_reader_owned(sem); - if (tmp & RWSEM_FLAG_WAITERS) + if (tmp & RWSEM_FLAG_WAITERS) { + trace_contended_release(sem); rwsem_downgrade_wake(sem); + } preempt_enable(); } diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c index 74d41433ba13..233730c25933 100644 --- a/kernel/locking/semaphore.c +++ b/kernel/locking/semaphore.c @@ -230,6 +230,10 @@ void __sched up(struct semaphore *sem) sem->count++; else __up(sem, &wake_q); + + if (trace_contended_release_enabled() && !wake_q_empty(&wake_q)) + trace_call__contended_release(sem); + raw_spin_unlock_irqrestore(&sem->lock, flags); if (!wake_q_empty(&wake_q)) wake_up_q(&wake_q); diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h index 6c12452097e1..d62b49b53ec3 100644 --- a/kernel/locking/ww_mutex.h +++ b/kernel/locking/ww_mutex.h @@ -324,7 +324,7 @@ __ww_mutex_die(struct MUTEX *lock, struct MUTEX_WAITER *waiter, * blocked_on to PROXY_WAKING. Otherwise we can see * circular blocked_on relationships that can't resolve. */ - set_task_blocked_on_waking(waiter->task, lock); + clear_task_blocked_on(waiter->task, lock); wake_q_add(wake_q, waiter->task); } @@ -383,7 +383,7 @@ static bool __ww_mutex_wound(struct MUTEX *lock, * are waking the mutex owner, who may be currently * blocked on a different mutex. */ - set_task_blocked_on_waking(owner, NULL); + clear_task_blocked_on(owner, NULL); wake_q_add(wake_q, owner); } return true; diff --git a/kernel/panic.c b/kernel/panic.c index 20feada5319d..213725b612aa 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -39,6 +39,7 @@ #include <linux/sys_info.h> #include <trace/events/error_report.h> #include <asm/sections.h> +#include <kunit/test-bug.h> #define PANIC_TIMER_STEP 100 #define PANIC_BLINK_SPD 18 @@ -1124,6 +1125,11 @@ void warn_slowpath_fmt(const char *file, int line, unsigned taint, bool rcu = warn_rcu_enter(); struct warn_args args; + if (kunit_is_suppressed_warning(true)) { + warn_rcu_exit(rcu); + return; + } + pr_warn(CUT_HERE); if (!fmt) { @@ -1146,6 +1152,11 @@ void __warn_printk(const char *fmt, ...) bool rcu = warn_rcu_enter(); va_list args; + if (kunit_is_suppressed_warning(false)) { + warn_rcu_exit(rcu); + return; + } + pr_warn(CUT_HERE); va_start(args, fmt); diff --git a/kernel/params.c b/kernel/params.c index 74d620bc2521..a668863a4bb6 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -942,9 +942,9 @@ const struct kobj_type module_ktype = { /* * param_sysfs_init - create "module" kset * - * This must be done before the initramfs is unpacked and - * request_module() thus becomes possible, because otherwise the - * module load would fail in mod_sysfs_init. + * This must be done before any driver registration so that when a driver comes + * from a built-in module, the driver core can add the module under /sys/module + * and create the associated driver symlinks. */ static int __init param_sysfs_init(void) { @@ -957,7 +957,7 @@ static int __init param_sysfs_init(void) return 0; } -subsys_initcall(param_sysfs_init); +pure_initcall(param_sysfs_init); /* * param_sysfs_builtin_init - add sysfs version and parameter diff --git a/kernel/pid.c b/kernel/pid.c index fd5c2d4aa349..f55189a3d07d 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -885,10 +885,12 @@ static struct file *__pidfd_fget(struct task_struct *task, int fd) if (ret) return ERR_PTR(ret); - if (ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS)) - file = fget_task(task, fd); - else + if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS)) file = ERR_PTR(-EPERM); + else if (task->flags & PF_EXITING) + file = ERR_PTR(-ESRCH); + else + file = fget_task(task, fd); up_read(&task->signal->exec_update_lock); diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 05337f437cca..530c897311d4 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -42,6 +42,7 @@ config HIBERNATION select CRC32 select CRYPTO select CRYPTO_LZO + select CRYPTO_LZ4 help Enable the suspend to disk (STD) functionality, which is usually called "hibernation" in user interfaces. STD checkpoints the diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index af8d07bafe02..d2479c69d71a 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -392,23 +392,6 @@ static int create_image(int platform_mode) return error; } -static void shrink_shmem_memory(void) -{ - struct sysinfo info; - unsigned long nr_shmem_pages, nr_freed_pages; - - si_meminfo(&info); - nr_shmem_pages = info.sharedram; /* current page count used for shmem */ - /* - * The intent is to reclaim all shmem pages. Though shrink_all_memory() can - * only reclaim about half of them, it's enough for creating the hibernation - * image. - */ - nr_freed_pages = shrink_all_memory(nr_shmem_pages); - pr_debug("requested to reclaim %lu shmem pages, actually freed %lu pages\n", - nr_shmem_pages, nr_freed_pages); -} - /** * hibernation_snapshot - Quiesce devices and create a hibernation image. * @platform_mode: If set, use platform driver to prepare for the transition. @@ -425,14 +408,9 @@ int hibernation_snapshot(int platform_mode) if (error) goto Close; - /* Preallocate image memory before shutting down devices. */ - error = hibernate_preallocate_memory(); - if (error) - goto Close; - error = freeze_kernel_threads(); if (error) - goto Cleanup; + goto Close; if (hibernation_test(TEST_FREEZER)) { @@ -445,19 +423,13 @@ int hibernation_snapshot(int platform_mode) } error = dpm_prepare(PMSG_FREEZE); - if (error) { - dpm_complete(PMSG_RECOVER); - goto Thaw; - } + if (error) + goto Complete; - /* - * Device drivers may move lots of data to shmem in dpm_prepare(). The shmem - * pages will use lots of system memory, causing hibernation image creation - * fail due to insufficient free memory. - * This call is to force flush the shmem pages to swap disk and reclaim - * the system memory so that image creation can succeed. - */ - shrink_shmem_memory(); + /* Preallocate image memory before shutting down devices. */ + error = hibernate_preallocate_memory(); + if (error) + goto Complete; console_suspend_all(); pm_restrict_gfp_mask(); @@ -492,10 +464,10 @@ int hibernation_snapshot(int platform_mode) platform_end(platform_mode); return error; + Complete: + dpm_complete(PMSG_RECOVER); Thaw: thaw_kernel_threads(); - Cleanup: - swsusp_free(); goto Close; } diff --git a/kernel/power/qos.c b/kernel/power/qos.c index 398b994b73aa..1944dbeb0d4c 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -519,18 +519,23 @@ static int __init cpu_latency_qos_init(void) int ret; ret = misc_register(&cpu_latency_qos_miscdev); - if (ret < 0) + if (ret < 0) { pr_err("%s: %s setup failed\n", __func__, cpu_latency_qos_miscdev.name); + return ret; + } #ifdef CONFIG_PM_QOS_CPU_SYSTEM_WAKEUP ret = misc_register(&cpu_wakeup_latency_qos_miscdev); - if (ret < 0) + if (ret < 0) { pr_err("%s: %s setup failed\n", __func__, cpu_wakeup_latency_qos_miscdev.name); + misc_deregister(&cpu_latency_qos_miscdev); + return ret; + } #endif - return ret; + return 0; } late_initcall(cpu_latency_qos_init); #endif /* CONFIG_CPU_IDLE */ diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 2e64869bb5a0..b28233b8d00e 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -570,29 +570,23 @@ struct crc_data { wait_queue_head_t done; /* crc update done */ u32 *crc32; /* points to handle's crc32 */ size_t **unc_len; /* uncompressed lengths */ - unsigned char **unc; /* uncompressed data */ + unsigned char *unc[]; /* uncompressed data */ }; static struct crc_data *alloc_crc_data(int nr_threads) { struct crc_data *crc; - crc = kzalloc_obj(*crc); + crc = kzalloc_flex(*crc, unc, nr_threads); if (!crc) return NULL; - crc->unc = kcalloc(nr_threads, sizeof(*crc->unc), GFP_KERNEL); - if (!crc->unc) - goto err_free_crc; - crc->unc_len = kzalloc_objs(*crc->unc_len, nr_threads); if (!crc->unc_len) - goto err_free_unc; + goto err_free_crc; return crc; -err_free_unc: - kfree(crc->unc); err_free_crc: kfree(crc); return NULL; @@ -607,7 +601,6 @@ static void free_crc_data(struct crc_data *crc) kthread_stop(crc->thr); kfree(crc->unc_len); - kfree(crc->unc); kfree(crc); } diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 130043bfc209..d041645d9d17 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -13,6 +13,7 @@ #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> +#include <linux/sched/exec_state.h> #include <linux/sched/task.h> #include <linux/errno.h> #include <linux/mm.h> @@ -36,6 +37,30 @@ #include <asm/syscall.h> /* for syscall_get_* */ +/** + * ptracer_access_allowed - may current peek/poke @tsk's address space? + * @tsk: tracee + * + * Per-access check used by ptrace_access_vm() and architecture-specific + * tag/register accessors. Returns true iff current is the registered + * ptracer of @tsk and either @tsk is owner-dumpable or current holds + * CAP_SYS_PTRACE in @tsk's exec namespace. Lighter than + * __ptrace_may_access(): it re-validates only dumpability and + * capability on every access, without re-running LSM hooks or + * cred_cap_issubset() checks performed at attach time. + */ +bool ptracer_access_allowed(struct task_struct *tsk) +{ + const struct task_exec_state *es; + + guard(rcu)(); + if (ptrace_parent(tsk) != current) + return false; + es = task_exec_state_rcu(tsk); + return READ_ONCE(es->dumpable) == TASK_DUMPABLE_OWNER || + ptracer_capable(tsk, es->user_ns); +} + /* * Access another process' address space via ptrace. * Source/target buffer must be kernel space, @@ -45,21 +70,14 @@ int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct mm_struct *mm; - int ret; + int ret = 0; mm = get_task_mm(tsk); if (!mm) return 0; - if (!tsk->ptrace || - (current != tsk->parent) || - ((get_dumpable(mm) != SUID_DUMP_USER) && - !ptracer_capable(tsk, mm->user_ns))) { - mmput(mm); - return 0; - } - - ret = access_remote_vm(mm, addr, buf, len, gup_flags); + if (ptracer_access_allowed(tsk)) + ret = access_remote_vm(mm, addr, buf, len, gup_flags); mmput(mm); return ret; @@ -274,16 +292,13 @@ static bool ptrace_has_cap(struct user_namespace *ns, unsigned int mode) static bool task_still_dumpable(struct task_struct *task, unsigned int mode) { - struct mm_struct *mm = task->mm; - if (mm) { - if (get_dumpable(mm) == SUID_DUMP_USER) - return true; - return ptrace_has_cap(mm->user_ns, mode); - } + const struct task_exec_state *exec_state; - if (task->user_dumpable) + guard(rcu)(); + exec_state = task_exec_state_rcu(task); + if (READ_ONCE(exec_state->dumpable) == TASK_DUMPABLE_OWNER) return true; - return ptrace_has_cap(&init_user_ns, mode); + return ptrace_has_cap(exec_state->user_ns, mode); } /* Returns 0 on success, -errno on denial. */ diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 5f2848b828dc..882a158ada7b 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -572,7 +572,7 @@ static unsigned long rcu_no_completed(void) static void rcu_torture_deferred_free(struct rcu_torture *p) { - call_rcu_hurry(&p->rtort_rcu, rcu_torture_cb); + call_rcu(&p->rtort_rcu, rcu_torture_cb); } static void rcu_sync_torture_init(void) @@ -619,7 +619,7 @@ static struct rcu_torture_ops rcu_ops = { .poll_gp_state_exp = poll_state_synchronize_rcu, .cond_sync_exp = cond_synchronize_rcu_expedited, .cond_sync_exp_full = cond_synchronize_rcu_expedited_full, - .call = call_rcu_hurry, + .call = call_rcu, .cb_barrier = rcu_barrier, .fqs = rcu_force_quiescent_state, .gp_kthread_dbg = show_rcu_gp_kthreads, @@ -1145,7 +1145,7 @@ static void rcu_tasks_torture_deferred_free(struct rcu_torture *p) static void synchronize_rcu_mult_test(void) { - synchronize_rcu_mult(call_rcu_tasks, call_rcu_hurry); + synchronize_rcu_mult(call_rcu_tasks, call_rcu); } static struct rcu_torture_ops tasks_ops = { @@ -1632,6 +1632,17 @@ static void do_rtws_sync(struct torture_random_state *trsp, void (*sync)(void)) } /* + * Do an rcu_barrier() to motivate lazy callbacks during a stutter + * pause. Without this, we can get false-positives rtort_pipe_count + * splats. + */ +static void rcu_torture_writer_work(struct work_struct *work) +{ + if (cur_ops->cb_barrier) + cur_ops->cb_barrier(); +} + +/* * RCU torture writer kthread. Repeatedly substitutes a new structure * for that pointed to by rcu_torture_current, freeing the old structure * after a series of grace periods (the "pipeline"). @@ -1651,6 +1662,7 @@ rcu_torture_writer(void *arg) int i; int idx; unsigned long j; + struct work_struct lazy_work; int oldnice = task_nice(current); struct rcu_gp_oldstate *rgo = NULL; int rgo_size = 0; @@ -1703,6 +1715,9 @@ rcu_torture_writer(void *arg) pr_alert("%s" TORTURE_FLAG " Waited %lu jiffies for boot to complete.\n", torture_type, jiffies - j); + if (IS_ENABLED(CONFIG_RCU_LAZY)) + INIT_WORK_ONSTACK(&lazy_work, rcu_torture_writer_work); + do { rcu_torture_writer_state = RTWS_FIXED_DELAY; torture_hrtimeout_us(500, 1000, &rand); @@ -1895,6 +1910,8 @@ rcu_torture_writer(void *arg) !rcu_gp_is_normal(); } rcu_torture_writer_state = RTWS_STUTTER; + if (IS_ENABLED(CONFIG_RCU_LAZY)) + queue_work(system_percpu_wq, &lazy_work); stutter_waited = stutter_wait("rcu_torture_writer"); if (stutter_waited && !atomic_read(&rcu_fwd_cb_nodelay) && @@ -1925,6 +1942,12 @@ rcu_torture_writer(void *arg) pr_alert("%s" TORTURE_FLAG " Dynamic grace-period expediting was disabled.\n", torture_type); + + if (IS_ENABLED(CONFIG_RCU_LAZY)) { + cancel_work_sync(&lazy_work); + destroy_work_on_stack(&lazy_work); + } + kfree(ulo); kfree(rgo); rcu_torture_writer_state = RTWS_STOPPING; diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 48f0d803c8e2..f4da5fad70f5 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -373,7 +373,8 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func, // Queuing callbacks before initialization not yet supported. if (WARN_ON_ONCE(!rcu_segcblist_is_enabled(&rtpcp->cblist))) rcu_segcblist_init(&rtpcp->cblist); - needwake = (func == wakeme_after_rcu) || + needwake = (!havekthread && rcu_segcblist_empty(&rtpcp->cblist)) || + (func == wakeme_after_rcu) || (rcu_segcblist_n_cbs(&rtpcp->cblist) == rcu_task_lazy_lim); if (havekthread && !needwake && !timer_pending(&rtpcp->lazy_timer)) { if (rtp->lazy_jiffies) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 55df6d37145e..03a43d3d2616 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -492,7 +492,7 @@ static int param_set_next_fqs_jiffies(const char *val, const struct kernel_param int ret = kstrtoul(val, 0, &j); if (!ret) { - WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : (j ?: 1)); + WRITE_ONCE(*(ulong *)kp->arg, clamp_val(j, 1, HZ)); adjust_jiffies_till_sched_qs(); } return ret; @@ -969,14 +969,11 @@ static int rcu_watching_snap_recheck(struct rcu_data *rdp) if (rcu_cpu_stall_cputime && rdp->snap_record.gp_seq != rdp->gp_seq) { int cpu = rdp->cpu; struct rcu_snap_record *rsrp; - struct kernel_cpustat *kcsp; - - kcsp = &kcpustat_cpu(cpu); rsrp = &rdp->snap_record; - rsrp->cputime_irq = kcpustat_field(kcsp, CPUTIME_IRQ, cpu); - rsrp->cputime_softirq = kcpustat_field(kcsp, CPUTIME_SOFTIRQ, cpu); - rsrp->cputime_system = kcpustat_field(kcsp, CPUTIME_SYSTEM, cpu); + rsrp->cputime_irq = kcpustat_field(CPUTIME_IRQ, cpu); + rsrp->cputime_softirq = kcpustat_field(CPUTIME_SOFTIRQ, cpu); + rsrp->cputime_system = kcpustat_field(CPUTIME_SYSTEM, cpu); rsrp->nr_hardirqs = kstat_cpu_irqs_sum(cpu) + arch_irq_stat_cpu(cpu); rsrp->nr_softirqs = kstat_cpu_softirqs_sum(cpu); rsrp->nr_csw = nr_context_switches_cpu(cpu); @@ -1632,17 +1629,21 @@ static void rcu_sr_put_wait_head(struct llist_node *node) atomic_set_release(&sr_wn->inuse, 0); } -/* Enable rcu_normal_wake_from_gp automatically on small systems. */ -#define WAKE_FROM_GP_CPU_THRESHOLD 16 - -static int rcu_normal_wake_from_gp = -1; +static int rcu_normal_wake_from_gp = 1; module_param(rcu_normal_wake_from_gp, int, 0644); static struct workqueue_struct *sync_wq; +#define RCU_SR_NORMAL_LATCH_THR 64 + +/* Number of in-flight synchronize_rcu() calls queued on srs_next. */ +static atomic_long_t rcu_sr_normal_count; +static int rcu_sr_normal_latched; /* 0/1 */ + static void rcu_sr_normal_complete(struct llist_node *node) { struct rcu_synchronize *rs = container_of( (struct rcu_head *) node, struct rcu_synchronize, head); + long nr; WARN_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && !poll_state_synchronize_rcu_full(&rs->oldstate), @@ -1650,6 +1651,15 @@ static void rcu_sr_normal_complete(struct llist_node *node) /* Finally. */ complete(&rs->completion); + nr = atomic_long_dec_return(&rcu_sr_normal_count); + WARN_ON_ONCE(nr < 0); + + /* + * Unlatch: switch back to normal path when fully + * drained and if it has been latched. + */ + if (nr == 0) + (void)cmpxchg_relaxed(&rcu_sr_normal_latched, 1, 0); } static void rcu_sr_normal_gp_cleanup_work(struct work_struct *work) @@ -1795,6 +1805,24 @@ static bool rcu_sr_normal_gp_init(void) static void rcu_sr_normal_add_req(struct rcu_synchronize *rs) { + /* + * Increment before publish to avoid a complete + * vs enqueue race on latch. + */ + long nr = atomic_long_inc_return(&rcu_sr_normal_count); + + /* + * Latch when threshold is reached. Checking for an exact match + * restricts cmpxchg() to a single context. + * + * This latch is intentionally relaxed and best-effort. Concurrent + * set/clear can race and temporarily lose the latch, which is OK + * because it only selects between the fast and fallback paths. + */ + if (nr == RCU_SR_NORMAL_LATCH_THR) + (void)cmpxchg_relaxed(&rcu_sr_normal_latched, 0, 1); + + /* Publish for the GP kthread/worker. */ llist_add((struct llist_node *) &rs->head, &rcu_state.srs_next); } @@ -2584,7 +2612,7 @@ static void rcu_do_batch(struct rcu_data *rdp) const long npj = NSEC_PER_SEC / HZ; long rrn = READ_ONCE(rcu_resched_ns); - rrn = rrn < NSEC_PER_MSEC ? NSEC_PER_MSEC : rrn > NSEC_PER_SEC ? NSEC_PER_SEC : rrn; + rrn = clamp(rrn, NSEC_PER_MSEC, NSEC_PER_SEC); tlimit = local_clock() + rrn; jlimit = jiffies + (rrn + npj + 1) / npj; jlimit_check = true; @@ -3278,14 +3306,15 @@ static void synchronize_rcu_normal(void) { struct rcu_synchronize rs; + init_rcu_head_on_stack(&rs.head); trace_rcu_sr_normal(rcu_state.name, &rs.head, TPS("request")); - if (READ_ONCE(rcu_normal_wake_from_gp) < 1) { + if (READ_ONCE(rcu_normal_wake_from_gp) < 1 || + READ_ONCE(rcu_sr_normal_latched)) { wait_rcu_gp(call_rcu_hurry); goto trace_complete_out; } - init_rcu_head_on_stack(&rs.head); init_completion(&rs.completion); /* @@ -3302,10 +3331,10 @@ static void synchronize_rcu_normal(void) /* Now we can wait. */ wait_for_completion(&rs.completion); - destroy_rcu_head_on_stack(&rs.head); trace_complete_out: trace_rcu_sr_normal(rcu_state.name, &rs.head, TPS("complete")); + destroy_rcu_head_on_stack(&rs.head); } /** @@ -4904,12 +4933,6 @@ void __init rcu_init(void) sync_wq = alloc_workqueue("sync_wq", WQ_MEM_RECLAIM | WQ_UNBOUND, 0); WARN_ON(!sync_wq); - /* Respect if explicitly disabled via a boot parameter. */ - if (rcu_normal_wake_from_gp < 0) { - if (num_possible_cpus() <= WAKE_FROM_GP_CPU_THRESHOLD) - rcu_normal_wake_from_gp = 1; - } - /* Fill in default value for rcutree.qovld boot parameter. */ /* -After- the rcu_node ->lock fields are initialized! */ if (qovld < 0) diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index 1047b30cd46b..373b877cf171 100644 --- a/kernel/rcu/tree_nocb.h +++ b/kernel/rcu/tree_nocb.h @@ -655,7 +655,7 @@ static void nocb_gp_sleep(struct rcu_data *my_rdp, int cpu) * No-CBs GP kthreads come here to wait for additional callbacks to show up * or for grace periods to end. */ -static void nocb_gp_wait(struct rcu_data *my_rdp) +static noinline_for_stack void nocb_gp_wait(struct rcu_data *my_rdp) { bool bypass = false; int __maybe_unused cpu = my_rdp->cpu; diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index b67532cb8770..cf7ae51cba40 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -479,7 +479,6 @@ static void print_cpu_stat_info(int cpu) { struct rcu_snap_record rsr, *rsrp; struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); - struct kernel_cpustat *kcsp = &kcpustat_cpu(cpu); if (!rcu_cpu_stall_cputime) return; @@ -488,9 +487,9 @@ static void print_cpu_stat_info(int cpu) if (rsrp->gp_seq != rdp->gp_seq) return; - rsr.cputime_irq = kcpustat_field(kcsp, CPUTIME_IRQ, cpu); - rsr.cputime_softirq = kcpustat_field(kcsp, CPUTIME_SOFTIRQ, cpu); - rsr.cputime_system = kcpustat_field(kcsp, CPUTIME_SYSTEM, cpu); + rsr.cputime_irq = kcpustat_field(CPUTIME_IRQ, cpu); + rsr.cputime_softirq = kcpustat_field(CPUTIME_SOFTIRQ, cpu); + rsr.cputime_system = kcpustat_field(CPUTIME_SYSTEM, cpu); pr_err("\t hardirqs softirqs csw/system\n"); pr_err("\t number: %8lld %10d %12lld\n", diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b8871449d3c6..8b791e9e9f67 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -537,13 +537,22 @@ sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { } /* need a wrapper since we may need to trace from modules */ EXPORT_TRACEPOINT_SYMBOL(sched_set_state_tp); -/* Call via the helper macro trace_set_current_state. */ +/* + * Call via the helper macro trace_set_current_state. + * Calls to this function MUST be guarded by a + * tracepoint_enabled(sched_set_state_tp) + */ void __trace_set_current_state(int state_value) { - trace_sched_set_state_tp(current, state_value); + trace_call__sched_set_state_tp(current, state_value); } EXPORT_SYMBOL(__trace_set_current_state); +int task_llc(const struct task_struct *p) +{ + return per_cpu(sd_llc_id, task_cpu(p)); +} + /* * Serialization rules: * @@ -615,6 +624,12 @@ EXPORT_SYMBOL(__trace_set_current_state); * [ The astute reader will observe that it is possible for two tasks on one * CPU to have ->on_cpu = 1 at the same time. ] * + * p->is_blocked <- { 0, 1 }: + * + * is set by try_to_block_task() and cleared by ttwu_do_wakeup() and tracks + * if the task is blocked. Traditionally this would mirror p->on_rq, however + * due things like DELAY_DEQUEUE and PROXY_EXEC, this can diverge. + * * task_cpu(p): is changed by set_task_cpu(), the rules are: * * - Don't call set_task_cpu() on a blocked task: @@ -1203,9 +1218,13 @@ static void __resched_curr(struct rq *rq, int tif) } } +/* + * Calls to this function MUST be guarded by a + * tracepoint_enabled(sched_set_need_resched_tp) + */ void __trace_set_need_resched(struct task_struct *curr, int tif) { - trace_sched_set_need_resched_tp(curr, smp_processor_id(), tif); + trace_call__sched_set_need_resched_tp(curr, smp_processor_id(), tif); } EXPORT_SYMBOL_GPL(__trace_set_need_resched); @@ -2223,8 +2242,29 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags) dequeue_task(rq, p, flags); } -static void block_task(struct rq *rq, struct task_struct *p, int flags) +static void block_task(struct rq *rq, struct task_struct *p, unsigned long task_state) { + int flags = DEQUEUE_NOCLOCK; + + p->sched_contributes_to_load = + (task_state & TASK_UNINTERRUPTIBLE) && + !(task_state & TASK_NOLOAD) && + !(task_state & TASK_FROZEN); + + if (unlikely(is_special_task_state(task_state))) + flags |= DEQUEUE_SPECIAL; + + /* + * __schedule() ttwu() + * prev_state = prev->state; if (p->on_rq && ...) + * if (prev_state) goto out; + * p->on_rq = 0; smp_acquire__after_ctrl_dep(); + * p->state = TASK_WAKING + * + * Where __schedule() and ttwu() have matching control dependencies. + * + * After this, schedule() must not care about p->state any more. + */ if (dequeue_task(rq, p, DEQUEUE_SLEEP | flags)) __block_task(rq, p); } @@ -3685,6 +3725,7 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags) */ static inline void ttwu_do_wakeup(struct task_struct *p) { + p->is_blocked = 0; WRITE_ONCE(p->__state, TASK_RUNNING); trace_sched_wakeup(p); } @@ -3701,6 +3742,65 @@ void update_rq_avg_idle(struct rq *rq) rq->idle_stamp = 0; } +#ifdef CONFIG_SCHED_PROXY_EXEC +static void zap_balance_callbacks(struct rq *rq); + +static inline void proxy_reset_donor(struct rq *rq) +{ + WARN_ON_ONCE(rq->donor == rq->curr); + + put_prev_set_next_task(rq, rq->donor, rq->curr); + rq_set_donor(rq, rq->curr); + zap_balance_callbacks(rq); + resched_curr(rq); +} + +/* + * Checks to see if task p has been proxy-migrated to another rq + * and needs to be returned. If so, we deactivate the task here + * so that it can be properly woken up on the p->wake_cpu + * (or whichever cpu select_task_rq() picks at the bottom of + * try_to_wake_up() + */ +static inline bool proxy_needs_return(struct rq *rq, struct task_struct *p) +{ + /* + * Typically per __set_task_cpu(), task_cpu(p) == p->wake_cpu. + * + * However, proxy_set_task_cpu() is such that it preserves the + * original cpu in p->wake_cpu while migrating p for proxy reasons + * (possibly outside of the allowed p->cpus_ptr). + * + * Furthermore, migration_cpu_stop() / __migrate_swap_task(), will + * only set p->wake_cpu when !p->on_rq, and since here p->on_rq, this + * will not apply. But if it did, this check is the safe way around + * and would migrate. + */ + if (task_cpu(p) == p->wake_cpu) + return false; + + scoped_guard(raw_spinlock, &p->blocked_lock) { + /* Task is waking up; clear any blocked_on relationship */ + __clear_task_blocked_on(p, NULL); + + /* If already current, don't need to return migrate */ + if (task_current(rq, p)) + return false; + + /* If we're return migrating the rq->donor, switch it out for idle */ + if (task_current_donor(rq, p)) + proxy_reset_donor(rq); + } + block_task(rq, p, TASK_WAKING); + return true; +} +#else /* !CONFIG_SCHED_PROXY_EXEC */ +static inline bool proxy_needs_return(struct rq *rq, struct task_struct *p) +{ + return false; +} +#endif /* CONFIG_SCHED_PROXY_EXEC */ + static void ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, struct rq_flags *rf) @@ -3716,8 +3816,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, en_flags |= ENQUEUE_RQ_SELECTED; if (wake_flags & WF_MIGRATED) en_flags |= ENQUEUE_MIGRATED; - else - if (p->in_iowait) { + else if (p->in_iowait) { delayacct_blkio_end(p); atomic_dec(&task_rq(p)->nr_iowait); } @@ -3765,28 +3864,28 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, */ static int ttwu_runnable(struct task_struct *p, int wake_flags) { - struct rq_flags rf; - struct rq *rq; - int ret = 0; + ACQUIRE(__task_rq_lock, guard)(p); + struct rq *rq = guard.rq; - rq = __task_rq_lock(p, &rf); - if (task_on_rq_queued(p)) { - update_rq_clock(rq); + if (!task_on_rq_queued(p)) + return 0; + + update_rq_clock(rq); + if (p->is_blocked) { if (p->se.sched_delayed) enqueue_task(rq, p, ENQUEUE_NOCLOCK | ENQUEUE_DELAYED); - if (!task_on_cpu(rq, p)) { - /* - * When on_rq && !on_cpu the task is preempted, see if - * it should preempt the task that is current now. - */ - wakeup_preempt(rq, p, wake_flags); - } - ttwu_do_wakeup(p); - ret = 1; + if (proxy_needs_return(rq, p)) + return 0; } - __task_rq_unlock(rq, p, &rf); - - return ret; + if (!task_on_cpu(rq, p)) { + /* + * When on_rq && !on_cpu the task is preempted, see if + * it should preempt the task that is current now. + */ + wakeup_preempt(rq, p, wake_flags); + } + ttwu_do_wakeup(p); + return 1; } void sched_ttwu_pending(void *arg) @@ -4173,6 +4272,9 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * it disabling IRQs (this allows not taking ->pi_lock). */ WARN_ON_ONCE(p->se.sched_delayed); + WARN_ON_ONCE(p->is_blocked); + /* If p is current, we know we can run here, so clear blocked_on */ + clear_task_blocked_on(p, NULL); if (!ttwu_state_match(p, state, &success)) goto out; @@ -4189,6 +4291,7 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) */ scoped_guard (raw_spinlock_irqsave, &p->pi_lock) { smp_mb__after_spinlock(); + if (!ttwu_state_match(p, state, &success)) break; @@ -4297,6 +4400,16 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) wake_flags |= WF_MIGRATED; psi_ttwu_dequeue(p); set_task_cpu(p, cpu); + } else if (cpu != p->wake_cpu) { + /* + * If we were proxy-migrated to cpu, then + * select_task_rq() picks cpu instead of wake_cpu + * to return to, we won't call set_task_cpu(), + * leaving a stale wake_cpu pointing to where we + * proxy-migrated from. So just fixup wake_cpu here + * if its not correct + */ + p->wake_cpu = cpu; } ttwu_queue(p, cpu, wake_flags); @@ -4463,6 +4576,7 @@ static void __sched_fork(u64 clone_flags, struct task_struct *p) /* A delayed task cannot be in clone(). */ WARN_ON_ONCE(p->se.sched_delayed); + WARN_ON_ONCE(p->is_blocked); #ifdef CONFIG_FAIR_GROUP_SCHED p->se.cfs_rq = NULL; @@ -4498,6 +4612,7 @@ static void __sched_fork(u64 clone_flags, struct task_struct *p) init_numa_balancing(clone_flags, p); p->wake_entry.u_flags = CSD_TYPE_TTWU; p->migration_pending = NULL; + init_sched_mm(p); } DEFINE_STATIC_KEY_FALSE(sched_numa_balancing); @@ -4710,6 +4825,7 @@ int sched_fork(u64 clone_flags, struct task_struct *p) p->policy = SCHED_NORMAL; p->static_prio = NICE_TO_PRIO(0); p->rt_priority = 0; + p->timer_slack_ns = p->default_timer_slack_ns; } else if (PRIO_TO_NICE(p->static_prio) < 0) p->static_prio = NICE_TO_PRIO(0); @@ -5518,7 +5634,11 @@ void sched_exec(void) } DEFINE_PER_CPU(struct kernel_stat, kstat); -DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat); +DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat) = { +#ifdef CONFIG_NO_HZ_COMMON + .idle_sleeptime_seq = SEQCNT_ZERO(kernel_cpustat.idle_sleeptime_seq) +#endif +}; EXPORT_PER_CPU_SYMBOL(kstat); EXPORT_PER_CPU_SYMBOL(kernel_cpustat); @@ -5972,10 +6092,9 @@ static inline void schedule_debug(struct task_struct *prev, bool preempt) schedstat_inc(this_rq()->sched_count); } -static void prev_balance(struct rq *rq, struct task_struct *prev, - struct rq_flags *rf) +static void prev_balance(struct rq *rq, struct rq_flags *rf) { - const struct sched_class *start_class = prev->sched_class; + const struct sched_class *start_class = rq->donor->sched_class; const struct sched_class *class; /* @@ -5987,7 +6106,7 @@ static void prev_balance(struct rq *rq, struct task_struct *prev, * a runnable task of @class priority or higher. */ for_active_class_range(class, start_class, &idle_sched_class) { - if (class->balance && class->balance(rq, prev, rf)) + if (class->balance && class->balance(rq, rf)) break; } } @@ -5996,7 +6115,7 @@ static void prev_balance(struct rq *rq, struct task_struct *prev, * Pick up the highest-prio task: */ static inline struct task_struct * -__pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +__pick_next_task(struct rq *rq, struct rq_flags *rf) __must_hold(__rq_lockp(rq)) { const struct sched_class *class; @@ -6013,40 +6132,31 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) * higher scheduling class, because otherwise those lose the * opportunity to pull in more work from other CPUs. */ - if (likely(!sched_class_above(prev->sched_class, &fair_sched_class) && + if (likely(!sched_class_above(rq->donor->sched_class, &fair_sched_class) && rq->nr_running == rq->cfs.h_nr_queued)) { - p = pick_next_task_fair(rq, prev, rf); + p = pick_task_fair(rq, rf); if (unlikely(p == RETRY_TASK)) goto restart; /* Assume the next prioritized class is idle_sched_class */ - if (!p) { + if (!p) p = pick_task_idle(rq, rf); - put_prev_set_next_task(rq, prev, p); - } + put_prev_set_next_task(rq, rq->donor, p); return p; } restart: - prev_balance(rq, prev, rf); + prev_balance(rq, rf); for_each_active_class(class) { - if (class->pick_next_task) { - p = class->pick_next_task(rq, prev, rf); - if (unlikely(p == RETRY_TASK)) - goto restart; - if (p) - return p; - } else { - p = class->pick_task(rq, rf); - if (unlikely(p == RETRY_TASK)) - goto restart; - if (p) { - put_prev_set_next_task(rq, prev, p); - return p; - } + p = class->pick_task(rq, rf); + if (unlikely(p == RETRY_TASK)) + goto restart; + if (p) { + put_prev_set_next_task(rq, rq->donor, p); + return p; } } @@ -6097,7 +6207,7 @@ extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_f static void queue_core_balance(struct rq *rq); static struct task_struct * -pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +pick_next_task(struct rq *rq, struct rq_flags *rf) __must_hold(__rq_lockp(rq)) { struct task_struct *next, *p, *max; @@ -6110,7 +6220,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) bool need_sync; if (!sched_core_enabled(rq)) - return __pick_next_task(rq, prev, rf); + return __pick_next_task(rq, rf); cpu = cpu_of(rq); @@ -6123,7 +6233,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) */ rq->core_pick = NULL; rq->core_dl_server = NULL; - return __pick_next_task(rq, prev, rf); + return __pick_next_task(rq, rf); } /* @@ -6147,7 +6257,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) goto out_set_next; } - prev_balance(rq, prev, rf); + prev_balance(rq, rf); smt_mask = cpu_smt_mask(cpu); need_sync = !!rq->core->core_cookie; @@ -6329,7 +6439,7 @@ restart_multi: } out_set_next: - put_prev_set_next_task(rq, prev, next); + put_prev_set_next_task(rq, rq->donor, next); if (rq->core->core_forceidle_count && next == rq->idle) queue_core_balance(rq); @@ -6552,10 +6662,10 @@ static inline void sched_core_cpu_deactivate(unsigned int cpu) {} static inline void sched_core_cpu_dying(unsigned int cpu) {} static struct task_struct * -pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +pick_next_task(struct rq *rq, struct rq_flags *rf) __must_hold(__rq_lockp(rq)) { - return __pick_next_task(rq, prev, rf); + return __pick_next_task(rq, rf); } #endif /* !CONFIG_SCHED_CORE */ @@ -6583,16 +6693,19 @@ static bool try_to_block_task(struct rq *rq, struct task_struct *p, unsigned long *task_state_p, bool should_block) { unsigned long task_state = *task_state_p; - int flags = DEQUEUE_NOCLOCK; + + WARN_ON_ONCE(p->is_blocked); if (signal_pending_state(task_state, p)) { WRITE_ONCE(p->__state, TASK_RUNNING); *task_state_p = TASK_RUNNING; - set_task_blocked_on_waking(p, NULL); + clear_task_blocked_on(p, NULL); return false; } + p->is_blocked = 1; + /* * We check should_block after signal_pending because we * will want to wake the task in that case. But if @@ -6603,26 +6716,7 @@ static bool try_to_block_task(struct rq *rq, struct task_struct *p, if (!should_block) return false; - p->sched_contributes_to_load = - (task_state & TASK_UNINTERRUPTIBLE) && - !(task_state & TASK_NOLOAD) && - !(task_state & TASK_FROZEN); - - if (unlikely(is_special_task_state(task_state))) - flags |= DEQUEUE_SPECIAL; - - /* - * __schedule() ttwu() - * prev_state = prev->state; if (p->on_rq && ...) - * if (prev_state) goto out; - * p->on_rq = 0; smp_acquire__after_ctrl_dep(); - * p->state = TASK_WAKING - * - * Where __schedule() and ttwu() have matching control dependencies. - * - * After this, schedule() must not care about p->state any more. - */ - block_task(rq, p, flags); + block_task(rq, p, task_state); return true; } @@ -6645,18 +6739,18 @@ static inline void proxy_set_task_cpu(struct task_struct *p, int cpu) static inline struct task_struct *proxy_resched_idle(struct rq *rq) { put_prev_set_next_task(rq, rq->donor, rq->idle); + rq->next_class = &idle_sched_class; rq_set_donor(rq, rq->idle); set_tsk_need_resched(rq->idle); return rq->idle; } -static bool proxy_deactivate(struct rq *rq, struct task_struct *donor) +static void proxy_deactivate(struct rq *rq, struct task_struct *donor) { unsigned long state = READ_ONCE(donor->__state); - /* Don't deactivate if the state has been changed to TASK_RUNNING */ - if (state == TASK_RUNNING) - return false; + WARN_ON_ONCE(state == TASK_RUNNING); + WARN_ON_ONCE(donor->blocked_on); /* * Because we got donor from pick_next_task(), it is *crucial* * that we call proxy_resched_idle() before we deactivate it. @@ -6667,7 +6761,7 @@ static bool proxy_deactivate(struct rq *rq, struct task_struct *donor) * need to be changed from next *before* we deactivate. */ proxy_resched_idle(rq); - return try_to_block_task(rq, donor, &state, true); + block_task(rq, donor, state); } static inline void proxy_release_rq_lock(struct rq *rq, struct rq_flags *rf) @@ -6741,76 +6835,21 @@ static void proxy_migrate_task(struct rq *rq, struct rq_flags *rf, proxy_reacquire_rq_lock(rq, rf); } -static void proxy_force_return(struct rq *rq, struct rq_flags *rf, - struct task_struct *p) - __must_hold(__rq_lockp(rq)) -{ - struct rq *task_rq, *target_rq = NULL; - int cpu, wake_flag = WF_TTWU; - - lockdep_assert_rq_held(rq); - WARN_ON(p == rq->curr); - - if (p == rq->donor) - proxy_resched_idle(rq); - - proxy_release_rq_lock(rq, rf); - /* - * We drop the rq lock, and re-grab task_rq_lock to get - * the pi_lock (needed for select_task_rq) as well. - */ - scoped_guard (task_rq_lock, p) { - task_rq = scope.rq; - - /* - * Since we let go of the rq lock, the task may have been - * woken or migrated to another rq before we got the - * task_rq_lock. So re-check we're on the same RQ. If - * not, the task has already been migrated and that CPU - * will handle any futher migrations. - */ - if (task_rq != rq) - break; - - /* - * Similarly, if we've been dequeued, someone else will - * wake us - */ - if (!task_on_rq_queued(p)) - break; - - /* - * Since we should only be calling here from __schedule() - * -> find_proxy_task(), no one else should have - * assigned current out from under us. But check and warn - * if we see this, then bail. - */ - if (task_current(task_rq, p) || task_on_cpu(task_rq, p)) { - WARN_ONCE(1, "%s rq: %i current/on_cpu task %s %d on_cpu: %i\n", - __func__, cpu_of(task_rq), - p->comm, p->pid, p->on_cpu); - break; - } - - update_rq_clock(task_rq); - deactivate_task(task_rq, p, DEQUEUE_NOCLOCK); - cpu = select_task_rq(p, p->wake_cpu, &wake_flag); - set_task_cpu(p, cpu); - target_rq = cpu_rq(cpu); - clear_task_blocked_on(p, NULL); - } - - if (target_rq) - attach_one_task(target_rq, p); - - proxy_reacquire_rq_lock(rq, rf); -} - /* * Find runnable lock owner to proxy for mutex blocked donor * * Follow the blocked-on relation: - * task->blocked_on -> mutex->owner -> task... + * + * ,-> task + * | | blocked-on + * | v + * blocked_donor | mutex + * | | owner + * | v + * `-- task + * + * and set the blocked_donor relation, this latter is used by the mutex + * code to find which (blocked) task to hand-off to. * * Lock order: * @@ -6830,18 +6869,19 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf) bool curr_in_chain = false; int this_cpu = cpu_of(rq); struct task_struct *p; - struct mutex *mutex; int owner_cpu; /* Follow blocked_on chain. */ - for (p = donor; (mutex = p->blocked_on); p = owner) { + for (p = donor; p->is_blocked; p = owner) { /* if its PROXY_WAKING, do return migration or run if current */ - if (mutex == PROXY_WAKING) { + struct mutex *mutex = p->blocked_on; + if (!mutex) { + clear_task_blocked_on(p, mutex); if (task_current(rq, p)) { - clear_task_blocked_on(p, PROXY_WAKING); + p->is_blocked = 0; return p; } - goto force_return; + goto deactivate; } /* @@ -6872,17 +6912,19 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf) * and return p (if it is current and safe to * just run on this rq), or return-migrate the task. */ + __clear_task_blocked_on(p, NULL); if (task_current(rq, p)) { - __clear_task_blocked_on(p, NULL); + p->is_blocked = 0; return p; } - goto force_return; + goto deactivate; } if (!READ_ONCE(owner->on_rq) || owner->se.sched_delayed) { /* XXX Don't handle blocked owners/delayed dequeue yet */ if (curr_in_chain) return proxy_resched_idle(rq); + __clear_task_blocked_on(p, NULL); goto deactivate; } @@ -6950,17 +6992,13 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf) * rq, therefore holding @rq->lock is sufficient to * guarantee its existence, as per ttwu_remote(). */ + owner->blocked_donor = p; } WARN_ON_ONCE(owner && !owner->on_rq); return owner; deactivate: - if (proxy_deactivate(rq, donor)) - return NULL; - /* If deactivate fails, force return */ - p = donor; -force_return: - proxy_force_return(rq, rf, p); + proxy_deactivate(rq, p); return NULL; migrate_task: proxy_migrate_task(rq, rf, p, owner_cpu); @@ -7102,13 +7140,14 @@ static void __sched notrace __schedule(int sched_mode) pick_again: assert_balance_callbacks_empty(rq); - next = pick_next_task(rq, rq->donor, &rf); + next = pick_next_task(rq, &rf); rq->next_class = next->sched_class; if (sched_proxy_exec()) { struct task_struct *prev_donor = rq->donor; rq_set_donor(rq, next); - if (unlikely(next->blocked_on)) { + next->blocked_donor = NULL; + if (unlikely(next->is_blocked)) { next = find_proxy_task(rq, next, &rf); if (!next) { zap_balance_callbacks(rq); @@ -7964,7 +8003,7 @@ static void __sched_dynamic_update(int mode) break; } - preempt_dynamic_mode = mode; + WRITE_ONCE(preempt_dynamic_mode, mode); } void sched_dynamic_update(int mode) @@ -8005,12 +8044,13 @@ static void __init preempt_dynamic_init(void) } } -# define PREEMPT_MODEL_ACCESSOR(mode) \ - bool preempt_model_##mode(void) \ - { \ - WARN_ON_ONCE(preempt_dynamic_mode == preempt_dynamic_undefined); \ - return preempt_dynamic_mode == preempt_dynamic_##mode; \ - } \ +# define PREEMPT_MODEL_ACCESSOR(mode) \ + bool preempt_model_##mode(void) \ + { \ + int mode = READ_ONCE(preempt_dynamic_mode); \ + WARN_ON_ONCE(mode == preempt_dynamic_undefined); \ + return mode == preempt_dynamic_##mode; \ + } \ EXPORT_SYMBOL_GPL(preempt_model_##mode) PREEMPT_MODEL_ACCESSOR(none); @@ -8604,18 +8644,14 @@ static void cpuset_cpu_inactive(unsigned int cpu) static inline void sched_smt_present_inc(int cpu) { -#ifdef CONFIG_SCHED_SMT if (cpumask_weight(cpu_smt_mask(cpu)) == 2) static_branch_inc_cpuslocked(&sched_smt_present); -#endif } static inline void sched_smt_present_dec(int cpu) { -#ifdef CONFIG_SCHED_SMT if (cpumask_weight(cpu_smt_mask(cpu)) == 2) static_branch_dec_cpuslocked(&sched_smt_present); -#endif } int sched_cpu_activate(unsigned int cpu) @@ -8670,7 +8706,8 @@ int sched_cpu_deactivate(unsigned int cpu) * Remove CPU from nohz.idle_cpus_mask to prevent participating in * load balancing when not active */ - nohz_balance_exit_idle(rq); + scoped_guard (rcu) + nohz_balance_exit_idle(rq); set_cpu_active(cpu, false); @@ -8694,6 +8731,8 @@ int sched_cpu_deactivate(unsigned int cpu) */ synchronize_rcu(); + sched_domains_free_llc_id(cpu); + sched_set_rq_offline(rq, cpu); scx_rq_deactivate(rq); @@ -8703,9 +8742,7 @@ int sched_cpu_deactivate(unsigned int cpu) */ sched_smt_present_dec(cpu); -#ifdef CONFIG_SCHED_SMT sched_core_cpu_deactivate(cpu); -#endif if (!sched_smp_initialized) return 0; @@ -8873,7 +8910,7 @@ static struct kmem_cache *task_group_cache __ro_after_init; void __init sched_init(void) { - unsigned long ptr = 0; + unsigned long __maybe_unused ptr = 0; int i; /* Make sure the linker didn't screw up */ @@ -8889,36 +8926,24 @@ void __init sched_init(void) wait_bit_init(); #ifdef CONFIG_FAIR_GROUP_SCHED - ptr += 2 * nr_cpu_ids * sizeof(void **); -#endif -#ifdef CONFIG_RT_GROUP_SCHED - ptr += 2 * nr_cpu_ids * sizeof(void **); -#endif - if (ptr) { - ptr = (unsigned long)kzalloc(ptr, GFP_NOWAIT); - -#ifdef CONFIG_FAIR_GROUP_SCHED - root_task_group.se = (struct sched_entity **)ptr; - ptr += nr_cpu_ids * sizeof(void **); + root_task_group.cfs_rq = &runqueues.cfs; - root_task_group.cfs_rq = (struct cfs_rq **)ptr; - ptr += nr_cpu_ids * sizeof(void **); - - root_task_group.shares = ROOT_TASK_GROUP_LOAD; - init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL); + root_task_group.shares = ROOT_TASK_GROUP_LOAD; + init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL); #endif /* CONFIG_FAIR_GROUP_SCHED */ #ifdef CONFIG_EXT_GROUP_SCHED - scx_tg_init(&root_task_group); + scx_tg_init(&root_task_group); #endif /* CONFIG_EXT_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED - root_task_group.rt_se = (struct sched_rt_entity **)ptr; - ptr += nr_cpu_ids * sizeof(void **); + ptr += 2 * nr_cpu_ids * sizeof(void **); + ptr = (unsigned long)kzalloc(ptr, GFP_NOWAIT); + root_task_group.rt_se = (struct sched_rt_entity **)ptr; + ptr += nr_cpu_ids * sizeof(void **); - root_task_group.rt_rq = (struct rt_rq **)ptr; - ptr += nr_cpu_ids * sizeof(void **); + root_task_group.rt_rq = (struct rt_rq **)ptr; + ptr += nr_cpu_ids * sizeof(void **); #endif /* CONFIG_RT_GROUP_SCHED */ - } init_defrootdomain(); @@ -9027,6 +9052,11 @@ void __init sched_init(void) rq->core_cookie = 0UL; #endif +#ifdef CONFIG_SCHED_CACHE + raw_spin_lock_init(&rq->cpu_epoch_lock); + rq->cpu_epoch_next = jiffies; +#endif + zalloc_cpumask_var_node(&rq->scratch_mask, GFP_KERNEL, cpu_to_node(i)); } @@ -9828,15 +9858,18 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, } for_each_online_cpu(i) { - struct cfs_rq *cfs_rq = tg->cfs_rq[i]; + struct cfs_rq *cfs_rq = tg_cfs_rq(tg, i); struct rq *rq = cfs_rq->rq; guard(rq_lock_irq)(rq); + cfs_rq->runtime_enabled = runtime_enabled; cfs_rq->runtime_remaining = 1; - if (cfs_rq->throttled) + if (cfs_rq->throttled) { + update_rq_clock(rq); unthrottle_cfs_rq(cfs_rq); + } } if (runtime_was_enabled && !runtime_enabled) @@ -9977,7 +10010,7 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v) int i; for_each_possible_cpu(i) { - stats = __schedstats_from_se(tg->se[i]); + stats = __schedstats_from_se(tg_se(tg, i)); ws += schedstat_val(stats->wait_sum); } @@ -9996,7 +10029,7 @@ static u64 throttled_time_self(struct task_group *tg) u64 total = 0; for_each_possible_cpu(i) { - total += READ_ONCE(tg->cfs_rq[i]->throttled_clock_self_time); + total += READ_ONCE(tg_cfs_rq(tg, i)->throttled_clock_self_time); } return total; diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c index 73b6b2426911..43e0bde3038e 100644 --- a/kernel/sched/core_sched.c +++ b/kernel/sched/core_sched.c @@ -136,7 +136,7 @@ int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type, struct pid *grp; int err = 0; - if (!static_branch_likely(&sched_smt_present)) + if (!sched_smt_active()) return -ENODEV; BUILD_BUG_ON(PR_SCHED_CORE_SCOPE_THREAD != PIDTYPE_PID); diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index fbf31db0d2f3..679ac65be6b0 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -2,6 +2,7 @@ /* * Simple CPU accounting cgroup controller */ +#include <linux/sched/clock.h> #include <linux/sched/cputime.h> #include <linux/tsacct_kern.h> #include "sched.h" @@ -46,7 +47,8 @@ static void irqtime_account_delta(struct irqtime *irqtime, u64 delta, u64_stats_update_begin(&irqtime->sync); cpustat[idx] += delta; irqtime->total += delta; - irqtime->tick_delta += delta; + if (!kcpustat_idle_dyntick()) + irqtime->tick_delta += delta; u64_stats_update_end(&irqtime->sync); } @@ -414,16 +416,219 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick, } } -static void irqtime_account_idle_ticks(int ticks) -{ - irqtime_account_process_tick(current, 0, ticks); -} #else /* !CONFIG_IRQ_TIME_ACCOUNTING: */ -static inline void irqtime_account_idle_ticks(int ticks) { } static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick, int nr_ticks) { } #endif /* !CONFIG_IRQ_TIME_ACCOUNTING */ +#ifdef CONFIG_NO_HZ_COMMON +static void kcpustat_idle_stop(struct kernel_cpustat *kc, u64 now) +{ + u64 *cpustat = kc->cpustat; + u64 delta, steal, steal_delta; + int iowait; + + if (!kc->idle_elapse) + return; + + iowait = nr_iowait_cpu(smp_processor_id()) > 0; + delta = now - kc->idle_entrytime; + steal = steal_account_process_time(delta); + + /* + * Record the idle time after substracting the steal time from + * previous update sequence. Don't substract the steal time from + * the current update sequence to avoid readers moving backward. + */ + write_seqcount_begin(&kc->idle_sleeptime_seq); + steal_delta = min_t(u64, kc->idle_stealtime[iowait], delta); + delta -= steal_delta; + kc->idle_stealtime[iowait] -= steal_delta; + + if (iowait) + cpustat[CPUTIME_IOWAIT] += delta; + else + cpustat[CPUTIME_IDLE] += delta; + + kc->idle_stealtime[iowait] += steal; + kc->idle_entrytime = now; + kc->idle_elapse = false; + write_seqcount_end(&kc->idle_sleeptime_seq); +} + +static void kcpustat_idle_start(struct kernel_cpustat *kc, u64 now) +{ + /* Irqtime accounting might have been enabled in the middle of the IRQ */ + if (kc->idle_elapse) + return; + + write_seqcount_begin(&kc->idle_sleeptime_seq); + kc->idle_entrytime = now; + kc->idle_elapse = true; + write_seqcount_end(&kc->idle_sleeptime_seq); +} + +void kcpustat_dyntick_stop(u64 now) +{ + struct kernel_cpustat *kc = kcpustat_this_cpu; + + if (!vtime_generic_enabled_this_cpu()) { + WARN_ON_ONCE(!kc->idle_dyntick); + kcpustat_idle_stop(kc, now); + kc->idle_dyntick = false; + vtime_dyntick_stop(); + } +} + +void kcpustat_dyntick_start(u64 now) +{ + struct kernel_cpustat *kc = kcpustat_this_cpu; + + if (!vtime_generic_enabled_this_cpu()) { + vtime_dyntick_start(); + kc->idle_dyntick = true; + kcpustat_idle_start(kc, now); + } +} + +void kcpustat_irq_enter(u64 now) +{ + struct kernel_cpustat *kc = kcpustat_this_cpu; + + if (!vtime_generic_enabled_this_cpu() && + (irqtime_enabled() || vtime_accounting_enabled_this_cpu())) + kcpustat_idle_stop(kc, now); +} + +void kcpustat_irq_exit(u64 now) +{ + struct kernel_cpustat *kc = kcpustat_this_cpu; + + /* + * Generic vtime already does its own idle accounting. + * But irqtime accounting or arch vtime which also accounts IRQs + * need to pause nohz accounting. Resume nohz accounting as long + * as the irqtime config is enabled to handle case where irqtime + * accounting got runtime disabled in the middle of an IRQ. + */ + if (!vtime_generic_enabled_this_cpu() && + (IS_ENABLED(CONFIG_IRQ_TIME_ACCOUNTING) || vtime_accounting_enabled_this_cpu())) + kcpustat_idle_start(kc, now); +} + +static u64 kcpustat_field_dyntick(int cpu, enum cpu_usage_stat idx, + bool compute_delta, u64 now) +{ + struct kernel_cpustat *kc = &kcpustat_cpu(cpu); + int iowait = idx == CPUTIME_IOWAIT; + u64 *cpustat = kc->cpustat; + unsigned int seq; + u64 idle; + + do { + seq = read_seqcount_begin(&kc->idle_sleeptime_seq); + + idle = cpustat[idx]; + + if (kc->idle_elapse && compute_delta && now > kc->idle_entrytime) { + u64 delta = now - kc->idle_entrytime; + + delta -= min_t(u64, kc->idle_stealtime[iowait], delta); + idle += delta; + } + } while (read_seqcount_retry(&kc->idle_sleeptime_seq, seq)); + + return idle; +} + +u64 kcpustat_field_idle(int cpu) +{ + return kcpustat_field_dyntick(cpu, CPUTIME_IDLE, + !nr_iowait_cpu(cpu), ktime_get()); +} +EXPORT_SYMBOL_GPL(kcpustat_field_idle); + +u64 kcpustat_field_iowait(int cpu) +{ + return kcpustat_field_dyntick(cpu, CPUTIME_IOWAIT, + nr_iowait_cpu(cpu), ktime_get()); +} +EXPORT_SYMBOL_GPL(kcpustat_field_iowait); +#else +static u64 kcpustat_field_dyntick(int cpu, enum cpu_usage_stat idx, + bool compute_delta, ktime_t now) +{ + return kcpustat_cpu(cpu).cpustat[idx]; +} +#endif /* CONFIG_NO_HZ_COMMON */ + +static u64 get_cpu_sleep_time_us(int cpu, enum cpu_usage_stat idx, + bool compute_delta, u64 *last_update_time) +{ + ktime_t now = ktime_get(); + u64 res; + + if (vtime_generic_enabled_cpu(cpu)) + res = kcpustat_field(idx, cpu); + else + res = kcpustat_field_dyntick(cpu, idx, compute_delta, now); + + do_div(res, NSEC_PER_USEC); + + if (last_update_time) + *last_update_time = ktime_to_us(now); + + return res; +} + +/** + * get_cpu_idle_time_us - get the total idle time of a CPU + * @cpu: CPU number to query + * @last_update_time: variable to store update time in. Do not update + * counters if NULL. + * + * Return the cumulative idle time (since boot) for a given + * CPU, in microseconds. Note that this is partially broken due to + * the counter of iowait tasks that can be remotely updated without + * any synchronization. Therefore it is possible to observe backward + * values within two consecutive reads. + * + * This time is measured via accounting rather than sampling, + * and is as accurate as ktime_get() is. + * + * Return: total idle time of the @cpu + */ +u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time) +{ + return get_cpu_sleep_time_us(cpu, CPUTIME_IDLE, + !nr_iowait_cpu(cpu), last_update_time); +} +EXPORT_SYMBOL_GPL(get_cpu_idle_time_us); + +/** + * get_cpu_iowait_time_us - get the total iowait time of a CPU + * @cpu: CPU number to query + * @last_update_time: variable to store update time in. Do not update + * counters if NULL. + * + * Return the cumulative iowait time (since boot) for a given + * CPU, in microseconds. Note this is partially broken due to + * the counter of iowait tasks that can be remotely updated without + * any synchronization. Therefore it is possible to observe backward + * values within two consecutive reads. + * + * This time is measured via accounting rather than sampling, + * and is as accurate as ktime_get() is. + * + * Return: total iowait time of @cpu + */ +u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) +{ + return get_cpu_sleep_time_us(cpu, CPUTIME_IOWAIT, + nr_iowait_cpu(cpu), last_update_time); +} +EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us); + /* * Use precise platform statistics if available: */ @@ -437,11 +642,15 @@ void vtime_account_irq(struct task_struct *tsk, unsigned int offset) vtime_account_hardirq(tsk); } else if (pc & SOFTIRQ_OFFSET) { vtime_account_softirq(tsk); - } else if (!IS_ENABLED(CONFIG_HAVE_VIRT_CPU_ACCOUNTING_IDLE) && - is_idle_task(tsk)) { - vtime_account_idle(tsk); + } else if (!kcpustat_idle_dyntick()) { + if (!IS_ENABLED(CONFIG_HAVE_VIRT_CPU_ACCOUNTING_IDLE) && + is_idle_task(tsk)) { + vtime_account_idle(tsk); + } else { + vtime_account_kernel(tsk); + } } else { - vtime_account_kernel(tsk); + vtime_reset(); } } @@ -483,6 +692,9 @@ void account_process_tick(struct task_struct *p, int user_tick) if (vtime_accounting_enabled_this_cpu()) return; + if (kcpustat_idle_dyntick()) + return; + if (irqtime_enabled()) { irqtime_account_process_tick(p, user_tick, 1); return; @@ -505,29 +717,6 @@ void account_process_tick(struct task_struct *p, int user_tick) } /* - * Account multiple ticks of idle time. - * @ticks: number of stolen ticks - */ -void account_idle_ticks(unsigned long ticks) -{ - u64 cputime, steal; - - if (irqtime_enabled()) { - irqtime_account_idle_ticks(ticks); - return; - } - - cputime = ticks * TICK_NSEC; - steal = steal_account_process_time(ULONG_MAX); - - if (steal >= cputime) - return; - - cputime -= steal; - account_idle_time(cputime); -} - -/* * Adjust tick based cputime random precision against scheduler runtime * accounting. * @@ -587,12 +776,6 @@ void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev, } stime = mul_u64_u64_div_u64(stime, rtime, stime + utime); - /* - * Because mul_u64_u64_div_u64() can approximate on some - * achitectures; enforce the constraint that: a*b/(b+c) <= a. - */ - if (unlikely(stime > rtime)) - stime = rtime; update: /* @@ -773,9 +956,9 @@ void vtime_guest_exit(struct task_struct *tsk) } EXPORT_SYMBOL_GPL(vtime_guest_exit); -void vtime_account_idle(struct task_struct *tsk) +static void __vtime_account_idle(struct vtime *vtime) { - account_idle_time(get_vtime_delta(&tsk->vtime)); + account_idle_time(get_vtime_delta(vtime)); } void vtime_task_switch_generic(struct task_struct *prev) @@ -784,7 +967,7 @@ void vtime_task_switch_generic(struct task_struct *prev) write_seqcount_begin(&vtime->seqcount); if (vtime->state == VTIME_IDLE) - vtime_account_idle(prev); + __vtime_account_idle(vtime); else __vtime_account_kernel(prev, vtime); vtime->state = VTIME_INACTIVE; @@ -926,6 +1109,7 @@ static int kcpustat_field_vtime(u64 *cpustat, int cpu, u64 *val) { struct vtime *vtime = &tsk->vtime; + struct rq *rq = cpu_rq(cpu); unsigned int seq; do { @@ -967,6 +1151,14 @@ static int kcpustat_field_vtime(u64 *cpustat, if (state == VTIME_GUEST && task_nice(tsk) > 0) *val += vtime->gtime + vtime_delta(vtime); break; + case CPUTIME_IDLE: + if (state == VTIME_IDLE && !atomic_read(&rq->nr_iowait)) + *val += vtime_delta(vtime); + break; + case CPUTIME_IOWAIT: + if (state == VTIME_IDLE && atomic_read(&rq->nr_iowait) > 0) + *val += vtime_delta(vtime); + break; default: break; } @@ -975,16 +1167,15 @@ static int kcpustat_field_vtime(u64 *cpustat, return 0; } -u64 kcpustat_field(struct kernel_cpustat *kcpustat, - enum cpu_usage_stat usage, int cpu) +u64 kcpustat_field(enum cpu_usage_stat usage, int cpu) { - u64 *cpustat = kcpustat->cpustat; + u64 *cpustat = kcpustat_cpu(cpu).cpustat; u64 val = cpustat[usage]; struct rq *rq; int err; - if (!vtime_accounting_enabled_cpu(cpu)) - return val; + if (!vtime_generic_enabled_cpu(cpu)) + return kcpustat_field_default(usage, cpu); rq = cpu_rq(cpu); @@ -1030,8 +1221,8 @@ static int kcpustat_cpu_fetch_vtime(struct kernel_cpustat *dst, *dst = *src; cpustat = dst->cpustat; - /* Task is sleeping, dead or idle, nothing to add */ - if (state < VTIME_SYS) + /* Task is sleeping or dead, nothing to add */ + if (state < VTIME_IDLE) continue; delta = vtime_delta(vtime); @@ -1040,15 +1231,17 @@ static int kcpustat_cpu_fetch_vtime(struct kernel_cpustat *dst, * Task runs either in user (including guest) or kernel space, * add pending nohz time to the right place. */ - if (state == VTIME_SYS) { + switch (state) { + case VTIME_SYS: cpustat[CPUTIME_SYSTEM] += vtime->stime + delta; - } else if (state == VTIME_USER) { + break; + case VTIME_USER: if (task_nice(tsk) > 0) cpustat[CPUTIME_NICE] += vtime->utime + delta; else cpustat[CPUTIME_USER] += vtime->utime + delta; - } else { - WARN_ON_ONCE(state != VTIME_GUEST); + break; + case VTIME_GUEST: if (task_nice(tsk) > 0) { cpustat[CPUTIME_GUEST_NICE] += vtime->gtime + delta; cpustat[CPUTIME_NICE] += vtime->gtime + delta; @@ -1056,6 +1249,15 @@ static int kcpustat_cpu_fetch_vtime(struct kernel_cpustat *dst, cpustat[CPUTIME_GUEST] += vtime->gtime + delta; cpustat[CPUTIME_USER] += vtime->gtime + delta; } + break; + case VTIME_IDLE: + if (atomic_read(&cpu_rq(cpu)->nr_iowait) > 0) + cpustat[CPUTIME_IOWAIT] += delta; + else + cpustat[CPUTIME_IDLE] += delta; + break; + default: + WARN_ON_ONCE(1); } } while (read_seqcount_retry(&vtime->seqcount, seq)); @@ -1068,8 +1270,8 @@ void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu) struct rq *rq; int err; - if (!vtime_accounting_enabled_cpu(cpu)) { - *dst = *src; + if (!vtime_generic_enabled_cpu(cpu)) { + kcpustat_cpu_fetch_default(dst, cpu); return; } @@ -1082,7 +1284,7 @@ void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu) curr = rcu_dereference(rq->curr); if (WARN_ON_ONCE(!curr)) { rcu_read_unlock(); - *dst = *src; + kcpustat_cpu_fetch_default(dst, cpu); return; } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 7db4c87df83b..0f858b98c9aa 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1515,8 +1515,12 @@ throttle: if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(dl_se))) { if (dl_server(dl_se)) { - replenish_dl_new_period(dl_se, rq); - start_dl_timer(dl_se); + if (dl_se->dl_defer) { + replenish_dl_new_period(dl_se, rq); + start_dl_timer(dl_se); + } else { + enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH); + } } else { enqueue_task_dl(rq, dl_task_of(dl_se), ENQUEUE_REPLENISH); } @@ -1793,7 +1797,8 @@ void dl_server_start(struct sched_dl_entity *dl_se) struct rq *rq = dl_se->rq; dl_se->dl_defer_idle = 0; - if (!dl_server(dl_se) || dl_se->dl_server_active || !dl_se->dl_runtime) + if (!dl_server(dl_se) || dl_se->dl_server_active || !dl_se->dl_runtime || + !dl_se->dl_bw_attached) return; /* @@ -1868,6 +1873,13 @@ void sched_init_dl_servers(void) dl_se->dl_server = 1; dl_se->dl_defer = 1; setup_new_dl_entity(dl_se); + + /* + * No BPF scheduler is loaded at boot, so the ext_server has no + * tasks to protect. Detach its bandwidth reservation, it will + * be attached when a BPF scheduler is loaded. + */ + dl_server_detach_bw(dl_se); #endif } } @@ -1878,6 +1890,9 @@ void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq) int cpu = cpu_of(rq); struct dl_bw *dl_b; + if (!dl_se->dl_bw_attached) + return; + dl_b = dl_bw_of(cpu_of(rq)); guard(raw_spinlock)(&dl_b->lock); @@ -1889,7 +1904,8 @@ void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq) int dl_server_apply_params(struct sched_dl_entity *dl_se, u64 runtime, u64 period, bool init) { - u64 old_bw = init ? 0 : to_ratio(dl_se->dl_period, dl_se->dl_runtime); + u64 old_bw = (init || !dl_se->dl_bw_attached) ? 0 : + to_ratio(dl_se->dl_period, dl_se->dl_runtime); u64 new_bw = to_ratio(period, runtime); struct rq *rq = dl_se->rq; int cpu = cpu_of(rq); @@ -1909,7 +1925,8 @@ int dl_server_apply_params(struct sched_dl_entity *dl_se, u64 runtime, u64 perio if (init) { __add_rq_bw(new_bw, &rq->dl); __dl_add(dl_b, new_bw, cpus); - } else { + dl_se->dl_bw_attached = 1; + } else if (dl_se->dl_bw_attached) { __dl_sub(dl_b, dl_se->dl_bw, cpus); __dl_add(dl_b, new_bw, cpus); @@ -1930,6 +1947,181 @@ int dl_server_apply_params(struct sched_dl_entity *dl_se, u64 runtime, u64 perio } /* + * Add @dl_se's bw to the root-domain accounting. + * + * Return -EBUSY if attaching would overflow root domain capacity. + */ +static int __dl_server_attach_bw_locked(struct sched_dl_entity *dl_se, + struct dl_bw *dl_b, int cpus) +{ + struct rq *rq = dl_se->rq; + unsigned long cap; + + /* + * Always update @rq->dl.this_bw, but only update @dl_b->total_bw + * (and run the overflow check it gates) while this CPU is active. + * + * This mirrors dl_server_add_bw() during root-domain rebuilds, which + * only publishes bandwidth from active CPUs into @dl_b. + */ + if (cpu_active(cpu_of(rq))) { + cap = dl_bw_capacity(cpu_of(rq)); + if (__dl_overflow(dl_b, cap, 0, dl_se->dl_bw)) + return -EBUSY; + __dl_add(dl_b, dl_se->dl_bw, cpus); + } + __add_rq_bw(dl_se->dl_bw, &rq->dl); + dl_se->dl_bw_attached = 1; + + return 0; +} + +/* + * Drain @dl_se and remove its bw from the root-domain accounting. + */ +static void __dl_server_detach_bw_locked(struct sched_dl_entity *dl_se, + struct dl_bw *dl_b, int cpus) +{ + struct rq *rq = dl_se->rq; + + /* + * If the server is still active (on_rq), dequeue it via + * dl_server_stop(); task_non_contending() will either subtract + * @dl_bw from running_bw immediately (0-lag passed) or set + * dl_non_contending and arm the inactive_timer. + */ + if (dl_se->dl_server_active) + dl_server_stop(dl_se); + + /* + * Drop @dl_se's contribution from this rq's bandwidth accounting, + * mirroring the __add_rq_bw() done at attach time. + */ + dl_rq_change_utilization(rq, dl_se, 0); + + /* + * Update @dl_b only while this CPU is active, matching + * dl_server_add_bw() during root-domain rebuilds. + * + * If this CPU is inactive, its bandwidth is not currently accounted in + * @dl_b->total_bw: either attach skipped adding it, or a rebuild + * already dropped it while re-publishing active CPUs only. + * + * In that case there is nothing to subtract from @dl_b. Just clear + * @dl_se->dl_bw_attached; if the CPU becomes active again, the next + * rebuild will re-publish its bandwidth. + */ + if (cpu_active(cpu_of(rq))) + __dl_sub(dl_b, dl_se->dl_bw, cpus); + dl_se->dl_bw_attached = 0; +} + +/* + * Attach @dl_se's bandwidth to the root domain's total_bw accounting. + * + * Use to dynamically register a dl_server's bandwidth reservation while + * preserving its configured @dl_runtime / @dl_period. No-op if @dl_se is + * already attached. + * + * Returns -EBUSY if attaching would overflow the root domain capacity. + */ +int dl_server_attach_bw(struct sched_dl_entity *dl_se) +{ + struct rq *rq = dl_se->rq; + int cpu = cpu_of(rq); + struct dl_bw *dl_b; + int cpus, ret; + + if (dl_se->dl_bw_attached) + return 0; + + scoped_guard (raw_spinlock, &dl_bw_of(cpu)->lock) { + dl_b = dl_bw_of(cpu); + cpus = dl_bw_cpus(cpu); + ret = __dl_server_attach_bw_locked(dl_se, dl_b, cpus); + } + if (ret) + return ret; + + /* + * The natural 0->nr_running transition that triggers dl_server_start() + * may have happened while @dl_se was still detached (e.g., between + * scx_bypass(false) and the scx_enable() re-balance loop), so kick a + * start here. + * + * dl_server_start() bails out cleanly if there's nothing to schedule or + * it's already active. Skip if @cpu is offline; the server will be + * started naturally on the first enqueue once @cpu comes back. + */ + if (cpu_online(cpu)) + dl_server_start(dl_se); + + return 0; +} + +/* + * Detach @dl_se's bandwidth from the root domain's total_bw accounting. + * + * Use to dynamically unregister a dl_server's bandwidth reservation while + * preserving its configured @dl_runtime / @dl_period. No-op if @dl_se is + * not currently attached. + */ +void dl_server_detach_bw(struct sched_dl_entity *dl_se) +{ + int cpu = cpu_of(dl_se->rq); + struct dl_bw *dl_b; + int cpus; + + if (!dl_se->dl_bw_attached) + return; + + dl_b = dl_bw_of(cpu); + guard(raw_spinlock)(&dl_b->lock); + cpus = dl_bw_cpus(cpu); + __dl_server_detach_bw_locked(dl_se, dl_b, cpus); +} + +/* + * Atomically detach @detach_se and attach @attach_se on the same rq, holding + * @dl_b->lock across both operations so a concurrent sched_setattr() cannot + * steal the bandwidth freed by the detach before the attach can claim it. + * + * Both entities must live on the same rq (same root domain). Returns the + * result of the attach: -EBUSY if attaching @attach_se would overflow root + * domain capacity (in which case both servers end up detached). + */ +int dl_server_swap_bw(struct sched_dl_entity *detach_se, + struct sched_dl_entity *attach_se) +{ + struct rq *rq = detach_se->rq; + int cpu = cpu_of(rq); + struct dl_bw *dl_b; + int cpus, ret; + + WARN_ON_ONCE(attach_se->rq != rq); + + scoped_guard (raw_spinlock, &dl_bw_of(cpu)->lock) { + dl_b = dl_bw_of(cpu); + cpus = dl_bw_cpus(cpu); + + if (detach_se->dl_bw_attached) + __dl_server_detach_bw_locked(detach_se, dl_b, cpus); + + if (attach_se->dl_bw_attached) + ret = 0; + else + ret = __dl_server_attach_bw_locked(attach_se, dl_b, cpus); + } + if (ret) + return ret; + + if (cpu_online(cpu)) + dl_server_start(attach_se); + + return 0; +} + +/* * Update the current task's runtime statistics (provided it is still * a -deadline task and has not been removed from the dl_rq). */ @@ -2292,7 +2484,10 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se, int flags) static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) { - if (is_dl_boosted(&p->dl)) { + struct sched_dl_entity *dl_se = &p->dl; + struct dl_rq *dl_rq = &rq->dl; + + if (is_dl_boosted(dl_se)) { /* * Because of delays in the detection of the overrun of a * thread's runtime, it might be the case that a thread @@ -2305,14 +2500,14 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) * * In this case, the boost overrides the throttle. */ - if (p->dl.dl_throttled) { + if (dl_se->dl_throttled) { /* * The replenish timer needs to be canceled. No * problem if it fires concurrently: boosted threads * are ignored in dl_task_timer(). */ - cancel_replenish_timer(&p->dl); - p->dl.dl_throttled = 0; + cancel_replenish_timer(dl_se); + dl_se->dl_throttled = 0; } } else if (!dl_prio(p->normal_prio)) { /* @@ -2324,7 +2519,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) * being boosted again with no means to replenish the runtime and clear * the throttle. */ - p->dl.dl_throttled = 0; + dl_se->dl_throttled = 0; if (!(flags & ENQUEUE_REPLENISH)) printk_deferred_once("sched: DL de-boosted task PID %d: REPLENISH flag missing\n", task_pid_nr(p)); @@ -2333,20 +2528,23 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) } check_schedstat_required(); - update_stats_wait_start_dl(dl_rq_of_se(&p->dl), &p->dl); + update_stats_wait_start_dl(dl_rq, dl_se); - if (p->on_rq == TASK_ON_RQ_MIGRATING) + if (task_on_rq_migrating(p)) flags |= ENQUEUE_MIGRATING; - enqueue_dl_entity(&p->dl, flags); + enqueue_dl_entity(dl_se, flags); - if (dl_server(&p->dl)) + if (dl_server(dl_se)) return; if (task_is_blocked(p)) return; - if (!task_current(rq, p) && !p->dl.dl_throttled && p->nr_cpus_allowed > 1) + if (dl_rq->curr == dl_se) + return; + + if (!task_current(rq, p) && !dl_se->dl_throttled && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); } @@ -2354,7 +2552,7 @@ static bool dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) { update_curr_dl(rq); - if (p->on_rq == TASK_ON_RQ_MIGRATING) + if (task_on_rq_migrating(p)) flags |= DEQUEUE_MIGRATING; dequeue_dl_entity(&p->dl, flags); @@ -2506,8 +2704,14 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p) resched_curr(rq); } -static int balance_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf) +static int balance_dl(struct rq *rq, struct rq_flags *rf) { + /* + * Note, rq->donor may change during rq lock drops, + * so don't re-use prev across lock drops + */ + struct task_struct *p = rq->donor; + if (!on_dl_rq(&p->dl) && need_pull_dl_task(rq, p)) { /* * This is OK, because current is on_cpu, which avoids it being @@ -2562,6 +2766,10 @@ static void start_hrtick_dl(struct rq *rq, struct sched_dl_entity *dl_se) } #endif /* !CONFIG_SCHED_HRTICK */ +/* + * DL keeps current in tree, because ->deadline is not typically changed while + * a task is runnable. + */ static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first) { struct sched_dl_entity *dl_se = &p->dl; @@ -2574,6 +2782,9 @@ static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first) /* You can't push away the running task */ dequeue_pushable_dl_task(rq, p); + WARN_ON_ONCE(dl_rq->curr); + dl_rq->curr = dl_se; + if (!first) return; @@ -2637,17 +2848,20 @@ static void put_prev_task_dl(struct rq *rq, struct task_struct *p, struct task_s struct sched_dl_entity *dl_se = &p->dl; struct dl_rq *dl_rq = &rq->dl; - if (on_dl_rq(&p->dl)) + if (on_dl_rq(dl_se)) update_stats_wait_start_dl(dl_rq, dl_se); update_curr_dl(rq); update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1); + WARN_ON_ONCE(dl_rq->curr != dl_se); + dl_rq->curr = NULL; + if (task_is_blocked(p)) return; - if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1) + if (on_dl_rq(dl_se) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); } @@ -3236,12 +3450,12 @@ static void dl_server_add_bw(struct root_domain *rd, int cpu) struct sched_dl_entity *dl_se; dl_se = &cpu_rq(cpu)->fair_server; - if (dl_server(dl_se) && cpu_active(cpu)) + if (dl_server(dl_se) && dl_se->dl_bw_attached && cpu_active(cpu)) __dl_add(&rd->dl_bw, dl_se->dl_bw, dl_bw_cpus(cpu)); #ifdef CONFIG_SCHED_CLASS_EXT dl_se = &cpu_rq(cpu)->ext_server; - if (dl_server(dl_se) && cpu_active(cpu)) + if (dl_server(dl_se) && dl_se->dl_bw_attached && cpu_active(cpu)) __dl_add(&rd->dl_bw, dl_se->dl_bw, dl_bw_cpus(cpu)); #endif } @@ -3250,11 +3464,13 @@ static u64 dl_server_read_bw(int cpu) { u64 dl_bw = 0; - if (cpu_rq(cpu)->fair_server.dl_server) + if (cpu_rq(cpu)->fair_server.dl_server && + cpu_rq(cpu)->fair_server.dl_bw_attached) dl_bw += cpu_rq(cpu)->fair_server.dl_bw; #ifdef CONFIG_SCHED_CLASS_EXT - if (cpu_rq(cpu)->ext_server.dl_server) + if (cpu_rq(cpu)->ext_server.dl_server && + cpu_rq(cpu)->ext_server.dl_bw_attached) dl_bw += cpu_rq(cpu)->ext_server.dl_bw; #endif diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 74c1617cf652..40584b27ea0c 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -136,7 +136,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf, if (cnt > 63) cnt = 63; - if (copy_from_user(&buf, ubuf, cnt)) + if (copy_from_user(buf, ubuf, cnt)) return -EFAULT; buf[cnt] = 0; @@ -210,6 +210,48 @@ static const struct file_operations sched_scaling_fops = { .release = single_release, }; +#ifdef CONFIG_SCHED_CACHE +static ssize_t +sched_cache_enable_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + bool val; + int ret; + + ret = kstrtobool_from_user(ubuf, cnt, &val); + if (ret) + return ret; + + sysctl_sched_cache_user = val; + + sched_cache_active_set(); + + *ppos += cnt; + + return cnt; +} + +static int sched_cache_enable_show(struct seq_file *m, void *v) +{ + seq_printf(m, "%d\n", sysctl_sched_cache_user); + return 0; +} + +static int sched_cache_enable_open(struct inode *inode, + struct file *filp) +{ + return single_open(filp, sched_cache_enable_show, NULL); +} + +static const struct file_operations sched_cache_enable_fops = { + .open = sched_cache_enable_open, + .write = sched_cache_enable_write, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; +#endif + #ifdef CONFIG_PREEMPT_DYNAMIC static ssize_t sched_dynamic_write(struct file *filp, const char __user *ubuf, @@ -221,7 +263,7 @@ static ssize_t sched_dynamic_write(struct file *filp, const char __user *ubuf, if (cnt > 15) cnt = 15; - if (copy_from_user(&buf, ubuf, cnt)) + if (copy_from_user(buf, ubuf, cnt)) return -EFAULT; buf[cnt] = 0; @@ -239,6 +281,7 @@ static ssize_t sched_dynamic_write(struct file *filp, const char __user *ubuf, static int sched_dynamic_show(struct seq_file *m, void *v) { int i = (IS_ENABLED(CONFIG_PREEMPT_RT) || IS_ENABLED(CONFIG_ARCH_HAS_PREEMPT_LAZY)) * 2; + int mode = READ_ONCE(preempt_dynamic_mode); int j; /* Count entries in NULL terminated preempt_modes */ @@ -247,10 +290,10 @@ static int sched_dynamic_show(struct seq_file *m, void *v) j -= !IS_ENABLED(CONFIG_ARCH_HAS_PREEMPT_LAZY); for (; i < j; i++) { - if (preempt_dynamic_mode == i) + if (mode == i) seq_puts(m, "("); seq_puts(m, preempt_modes[i]); - if (preempt_dynamic_mode == i) + if (mode == i) seq_puts(m, ")"); seq_puts(m, " "); @@ -373,6 +416,9 @@ static ssize_t sched_server_write_common(struct file *filp, const char __user *u return -EINVAL; } + if (!cpu_online(cpu_of(rq))) + return -EBUSY; + update_rq_clock(rq); dl_server_stop(dl_se); retval = dl_server_apply_params(dl_se, runtime, period, 0); @@ -445,6 +491,8 @@ static const struct file_operations fair_server_runtime_fops = { .release = single_release, }; +static struct dentry *debugfs_sched; + #ifdef CONFIG_SCHED_CLASS_EXT static ssize_t sched_ext_server_runtime_write(struct file *filp, const char __user *ubuf, @@ -477,75 +525,92 @@ static const struct file_operations ext_server_runtime_fops = { .llseek = seq_lseek, .release = single_release, }; -#endif /* CONFIG_SCHED_CLASS_EXT */ static ssize_t -sched_fair_server_period_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) +sched_ext_server_period_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) { long cpu = (long) ((struct seq_file *) filp->private_data)->private; struct rq *rq = cpu_rq(cpu); return sched_server_write_common(filp, ubuf, cnt, ppos, DL_PERIOD, - &rq->fair_server); + &rq->ext_server); } -static int sched_fair_server_period_show(struct seq_file *m, void *v) +static int sched_ext_server_period_show(struct seq_file *m, void *v) { unsigned long cpu = (unsigned long) m->private; struct rq *rq = cpu_rq(cpu); - return sched_server_show_common(m, v, DL_PERIOD, &rq->fair_server); + return sched_server_show_common(m, v, DL_PERIOD, &rq->ext_server); } -static int sched_fair_server_period_open(struct inode *inode, struct file *filp) +static int sched_ext_server_period_open(struct inode *inode, struct file *filp) { - return single_open(filp, sched_fair_server_period_show, inode->i_private); + return single_open(filp, sched_ext_server_period_show, inode->i_private); } -static const struct file_operations fair_server_period_fops = { - .open = sched_fair_server_period_open, - .write = sched_fair_server_period_write, +static const struct file_operations ext_server_period_fops = { + .open = sched_ext_server_period_open, + .write = sched_ext_server_period_write, .read = seq_read, .llseek = seq_lseek, .release = single_release, }; -#ifdef CONFIG_SCHED_CLASS_EXT +static void debugfs_ext_server_init(void) +{ + struct dentry *d_ext; + unsigned long cpu; + + d_ext = debugfs_create_dir("ext_server", debugfs_sched); + if (!d_ext) + return; + + for_each_possible_cpu(cpu) { + struct dentry *d_cpu; + char buf[32]; + + snprintf(buf, sizeof(buf), "cpu%lu", cpu); + d_cpu = debugfs_create_dir(buf, d_ext); + + debugfs_create_file("runtime", 0644, d_cpu, (void *) cpu, &ext_server_runtime_fops); + debugfs_create_file("period", 0644, d_cpu, (void *) cpu, &ext_server_period_fops); + } +} +#endif /* CONFIG_SCHED_CLASS_EXT */ + static ssize_t -sched_ext_server_period_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) +sched_fair_server_period_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) { long cpu = (long) ((struct seq_file *) filp->private_data)->private; struct rq *rq = cpu_rq(cpu); return sched_server_write_common(filp, ubuf, cnt, ppos, DL_PERIOD, - &rq->ext_server); + &rq->fair_server); } -static int sched_ext_server_period_show(struct seq_file *m, void *v) +static int sched_fair_server_period_show(struct seq_file *m, void *v) { unsigned long cpu = (unsigned long) m->private; struct rq *rq = cpu_rq(cpu); - return sched_server_show_common(m, v, DL_PERIOD, &rq->ext_server); + return sched_server_show_common(m, v, DL_PERIOD, &rq->fair_server); } -static int sched_ext_server_period_open(struct inode *inode, struct file *filp) +static int sched_fair_server_period_open(struct inode *inode, struct file *filp) { - return single_open(filp, sched_ext_server_period_show, inode->i_private); + return single_open(filp, sched_fair_server_period_show, inode->i_private); } -static const struct file_operations ext_server_period_fops = { - .open = sched_ext_server_period_open, - .write = sched_ext_server_period_write, +static const struct file_operations fair_server_period_fops = { + .open = sched_fair_server_period_open, + .write = sched_fair_server_period_write, .read = seq_read, .llseek = seq_lseek, .release = single_release, }; -#endif /* CONFIG_SCHED_CLASS_EXT */ - -static struct dentry *debugfs_sched; static void debugfs_fair_server_init(void) { @@ -568,32 +633,9 @@ static void debugfs_fair_server_init(void) } } -#ifdef CONFIG_SCHED_CLASS_EXT -static void debugfs_ext_server_init(void) -{ - struct dentry *d_ext; - unsigned long cpu; - - d_ext = debugfs_create_dir("ext_server", debugfs_sched); - if (!d_ext) - return; - - for_each_possible_cpu(cpu) { - struct dentry *d_cpu; - char buf[32]; - - snprintf(buf, sizeof(buf), "cpu%lu", cpu); - d_cpu = debugfs_create_dir(buf, d_ext); - - debugfs_create_file("runtime", 0644, d_cpu, (void *) cpu, &ext_server_runtime_fops); - debugfs_create_file("period", 0644, d_cpu, (void *) cpu, &ext_server_period_fops); - } -} -#endif /* CONFIG_SCHED_CLASS_EXT */ - static __init int sched_init_debug(void) { - struct dentry __maybe_unused *numa; + struct dentry __maybe_unused *numa, *llc; debugfs_sched = debugfs_create_dir("sched", NULL); @@ -626,6 +668,22 @@ static __init int sched_init_debug(void) debugfs_create_u32("hot_threshold_ms", 0644, numa, &sysctl_numa_balancing_hot_threshold); #endif /* CONFIG_NUMA_BALANCING */ +#ifdef CONFIG_SCHED_CACHE + llc = debugfs_create_dir("llc_balancing", debugfs_sched); + debugfs_create_file("enabled", 0644, llc, NULL, + &sched_cache_enable_fops); + debugfs_create_u32("aggr_tolerance", 0644, llc, + &llc_aggr_tolerance); + debugfs_create_u32("epoch_period", 0644, llc, + &llc_epoch_period); + debugfs_create_u32("epoch_affinity_timeout", 0644, llc, + &llc_epoch_affinity_timeout); + debugfs_create_u32("overaggr_pct", 0644, llc, + &llc_overaggr_pct); + debugfs_create_u32("imb_pct", 0644, llc, + &llc_imb_pct); +#endif + debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops); debugfs_fair_server_init(); @@ -750,7 +808,7 @@ void dirty_sched_domain_sysctl(int cpu) #ifdef CONFIG_FAIR_GROUP_SCHED static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg) { - struct sched_entity *se = tg->se[cpu]; + struct sched_entity *se = tg_se(tg, cpu); #define P(F) SEQ_printf(m, " .%-30s: %lld\n", #F, (long long)F) #define P_SCHEDSTAT(F) SEQ_printf(m, " .%-30s: %lld\n", \ diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 65631e577ee9..f5a3233ead1a 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -4402,11 +4402,13 @@ void scx_cgroup_move_task(struct task_struct *p) return; /* - * @p must have ops.cgroup_prep_move() called on it and thus - * cgrp_moving_from set. + * scx_cgroup_can_attach() sets cgrp_moving_from only when the task's + * cgroup changes. Migration keys off css rather than cgroup identity, + * so it can hand an unchanged-cgroup task here with cgrp_moving_from + * NULL. Nothing to report to the BPF scheduler then, so skip it and + * keep prep_move and move paired. */ - if (SCX_HAS_OP(sch, cgroup_move) && - !WARN_ON_ONCE(!p->scx.cgrp_moving_from)) + if (SCX_HAS_OP(sch, cgroup_move) && p->scx.cgrp_moving_from) SCX_CALL_OP_TASK(sch, cgroup_move, task_rq(p), p, p->scx.cgrp_moving_from, tg_cgrp(task_group(p))); @@ -5909,6 +5911,7 @@ static void scx_root_disable(struct scx_sched *sch) struct scx_exit_info *ei = sch->exit_info; struct scx_task_iter sti; struct task_struct *p; + bool was_switched_all; int cpu; /* guarantee forward progress and wait for descendants to be disabled */ @@ -5935,6 +5938,8 @@ static void scx_root_disable(struct scx_sched *sch) */ mutex_lock(&scx_enable_mutex); + was_switched_all = scx_switched_all(); + static_branch_disable(&__scx_switched_all); WRITE_ONCE(scx_switching_all, false); @@ -5984,10 +5989,34 @@ static void scx_root_disable(struct scx_sched *sch) /* * Invalidate all the rq clocks to prevent getting outdated * rq clocks from a previous scx scheduler. + * + * Also re-balance the dl_server bandwidth reservations: detach + * ext_server (no more sched_ext tasks) and reinstate fair_server if it + * was previously detached because we were running in full mode. + * + * Unlike the enable path, this runs on a recovery path that cannot + * fail, so we use dl_server_swap_bw() to atomically free ext_server's + * bandwidth and reclaim it for fair_server under the same dl_b lock. + * + * The swap can still fail with -EBUSY if someone bumped ext_server's + * runtime via debugfs between enable and disable; in that narrow case + * both servers end up detached and we just WARN. */ for_each_possible_cpu(cpu) { struct rq *rq = cpu_rq(cpu); + scx_rq_clock_invalidate(rq); + + scoped_guard(rq_lock_irqsave, rq) { + update_rq_clock(rq); + if (was_switched_all) { + if (WARN_ON_ONCE(dl_server_swap_bw(&rq->ext_server, + &rq->fair_server))) + pr_warn("failed to re-attach fair_server on CPU %d\n", cpu); + } else { + dl_server_detach_bw(&rq->ext_server); + } + } } /* no task is on scx, turn off all the switches and flush in-progress calls */ @@ -6926,6 +6955,31 @@ static void scx_root_enable_workfn(struct kthread_work *work) goto err_disable; /* + * Attach the ext_server bandwidth reservation before anything is + * committed so that we can fail the enable if the root domain cannot + * accommodate it. The matching fair_server detach is deferred to the + * tail of this function, after the switch is fully committed and can no + * longer fail. + * + * On failure, err_disable funnels into scx_root_disable() which + * detaches ext_server, so partially-attached state is cleaned up + * automatically. + */ + for_each_possible_cpu(cpu) { + struct rq *rq = cpu_rq(cpu); + + scoped_guard(rq_lock_irqsave, rq) { + update_rq_clock(rq); + ret = dl_server_attach_bw(&rq->ext_server); + } + if (ret) { + pr_warn("sched_ext: failed to attach ext_server on CPU %d (%d)\n", + cpu, ret); + goto err_disable; + } + } + + /* * Once __scx_enabled is set, %current can be switched to SCX anytime. * This can lead to stalls as some BPF schedulers (e.g. userspace * scheduling) may not function correctly before all tasks are switched. @@ -7071,6 +7125,25 @@ static void scx_root_enable_workfn(struct kthread_work *work) if (!(ops->flags & SCX_OPS_SWITCH_PARTIAL)) static_branch_enable(&__scx_switched_all); + /* + * Detach the fair_server bandwidth reservation now that the switch + * is fully committed. In full mode (!SCX_OPS_SWITCH_PARTIAL) no + * task will ever run in the fair class, so give that bandwidth + * back to the RT class. The matching ext_server attach already + * happened earlier; this only releases bandwidth and cannot fail. + * + * In partial mode keep fair_server attached. + */ + if (scx_switched_all()) { + for_each_possible_cpu(cpu) { + struct rq *rq = cpu_rq(cpu); + + guard(rq_lock_irqsave)(rq); + update_rq_clock(rq); + dl_server_detach_bw(&rq->fair_server); + } + } + pr_info("sched_ext: BPF scheduler \"%s\" enabled%s\n", sch->ops.name, scx_switched_all() ? "" : " (partial)"); kobject_uevent(&sch->kobj, KOBJ_ADD); diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c index 6e1980763270..9f5ad6b071f9 100644 --- a/kernel/sched/ext_idle.c +++ b/kernel/sched/ext_idle.c @@ -79,7 +79,6 @@ static bool scx_idle_test_and_clear_cpu(int cpu) int node = scx_cpu_node_if_enabled(cpu); struct cpumask *idle_cpus = idle_cpumask(node)->cpu; -#ifdef CONFIG_SCHED_SMT /* * SMT mask should be cleared whether we can claim @cpu or not. The SMT * cluster is not wholly idle either way. This also prevents @@ -104,7 +103,6 @@ static bool scx_idle_test_and_clear_cpu(int cpu) else if (cpumask_test_cpu(cpu, idle_smts)) __cpumask_clear_cpu(cpu, idle_smts); } -#endif return cpumask_test_and_clear_cpu(cpu, idle_cpus); } @@ -622,7 +620,6 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, goto out_unlock; } -#ifdef CONFIG_SCHED_SMT /* * Use @prev_cpu's sibling if it's idle. */ @@ -634,7 +631,6 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, goto out_unlock; } } -#endif /* * Search for any idle CPU in the same LLC domain. @@ -714,7 +710,6 @@ static void update_builtin_idle(int cpu, bool idle) assign_cpu(cpu, idle_cpus, idle); -#ifdef CONFIG_SCHED_SMT if (sched_smt_active()) { const struct cpumask *smt = cpu_smt_mask(cpu); struct cpumask *idle_smts = idle_cpumask(node)->smt; @@ -731,7 +726,6 @@ static void update_builtin_idle(int cpu, bool idle) cpumask_andnot(idle_smts, idle_smts, smt); } } -#endif } /* diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 3ebec186f982..d78467ec6ee1 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -334,7 +334,7 @@ static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) * to a tree or when we reach the top of the tree */ if (cfs_rq->tg->parent && - cfs_rq->tg->parent->cfs_rq[cpu]->on_list) { + tg_cfs_rq(cfs_rq->tg->parent, cpu)->on_list) { /* * If parent is already on the list, we add the child * just before. Thanks to circular linked property of @@ -342,7 +342,7 @@ static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) * of the list that starts by parent. */ list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list, - &(cfs_rq->tg->parent->cfs_rq[cpu]->leaf_cfs_rq_list)); + &(tg_cfs_rq(cfs_rq->tg->parent, cpu)->leaf_cfs_rq_list)); /* * The branch is now connected to its tree so we can * reset tmp_alone_branch to the beginning of the @@ -525,7 +525,7 @@ static int se_is_idle(struct sched_entity *se) #endif /* !CONFIG_FAIR_GROUP_SCHED */ static __always_inline -void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec); +bool account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec); /************************************************************** * Scheduling class tree data structure manipulation methods: @@ -1350,6 +1350,8 @@ void post_init_entity_util_avg(struct task_struct *p) sa->runnable_avg = sa->util_avg; } +static inline void account_mm_sched(struct rq *rq, struct task_struct *p, s64 delta_exec); + static s64 update_se(struct rq *rq, struct sched_entity *se) { u64 now = rq_clock_task(rq); @@ -1372,6 +1374,7 @@ static s64 update_se(struct rq *rq, struct sched_entity *se) trace_sched_stat_runtime(running, delta_exec); account_group_exec_runtime(running, delta_exec); + account_mm_sched(rq, running, delta_exec); /* cgroup time is always accounted against the donor */ cgroup_account_cputime(donor, delta_exec); @@ -1393,6 +1396,581 @@ static s64 update_se(struct rq *rq, struct sched_entity *se) static void set_next_buddy(struct sched_entity *se); +#ifdef CONFIG_SCHED_CACHE + +/* + * XXX numbers come from a place the sun don't shine -- probably wants to be SD + * tunable or so. + */ +#define EPOCH_PERIOD (HZ / 100) /* 10 ms */ +#define EPOCH_LLC_AFFINITY_TIMEOUT 5 /* 50 ms */ +__read_mostly unsigned int llc_aggr_tolerance = 1; +__read_mostly unsigned int llc_epoch_period = EPOCH_PERIOD; +__read_mostly unsigned int llc_epoch_affinity_timeout = EPOCH_LLC_AFFINITY_TIMEOUT; +__read_mostly unsigned int llc_imb_pct = 20; +__read_mostly unsigned int llc_overaggr_pct = 50; + +static int llc_id(int cpu) +{ + if (cpu < 0) + return -1; + + return per_cpu(sd_llc_id, cpu); +} + +static inline int get_sched_cache_scale(int mul) +{ + unsigned int tol = READ_ONCE(llc_aggr_tolerance); + + if (!tol) + return 0; + + if (tol >= 100) + return INT_MAX; + + return (1 + (tol - 1) * mul); +} + +static bool exceed_llc_capacity(struct mm_struct *mm, int cpu) +{ +#ifdef CONFIG_NUMA_BALANCING + unsigned long llc, footprint; + struct sched_domain *sd; + int scale; + + guard(rcu)(); + + sd = rcu_dereference_sched_domain(cpu_rq(cpu)->sd); + if (!sd) + return true; + + if (static_branch_likely(&sched_numa_balancing)) { + /* + * TBD: RDT exclusive LLC ways reserved should be + * excluded. + */ + llc = sd->llc_bytes; + footprint = READ_ONCE(mm->sc_stat.footprint); + + /* + * Scale the LLC size by 256*llc_aggr_tolerance + * and compare it to the task's footprint. + * + * Suppose the L3 size is 32MB. If the + * llc_aggr_tolerance is 1: + * When the footprint is larger than 32MB, the + * process is regarded as exceeding the LLC + * capacity. If the llc_aggr_tolerance is 99: + * When the footprint is larger than 784GB, the + * process is regarded as exceeding the LLC + * capacity: + * 784GB = (1 + (99 - 1) * 256) * 32MB + * If the llc_aggr_tolerance is 100: + * ignore the footprint and do the aggregation + * anyway. + */ + scale = get_sched_cache_scale(256); + if (scale == INT_MAX) + return false; + + return ((llc * (u64)scale) < (footprint * PAGE_SIZE)); + } +#endif + return false; +} + +static bool invalid_llc_nr(struct mm_struct *mm, struct task_struct *p, + int cpu) +{ + int scale; + + if (get_nr_threads(p) <= 1) + return true; + + /* + * Scale the number of 'cores' in a LLC by llc_aggr_tolerance + * and compare it to the task's active threads. + */ + scale = get_sched_cache_scale(1); + if (scale == INT_MAX) + return false; + + return !fits_capacity((mm->sc_stat.nr_running_avg * cpu_smt_num_threads), + (scale * per_cpu(sd_llc_size, cpu))); +} + +static void account_llc_enqueue(struct rq *rq, struct task_struct *p) +{ + int pref_llc, pref_llc_queued; + struct sched_domain *sd; + + pref_llc = p->preferred_llc; + if (pref_llc < 0) + return; + + pref_llc_queued = (pref_llc == task_llc(p)); + rq->nr_llc_running++; + rq->nr_pref_llc_running += pref_llc_queued; + + /* + * Record whether p is enqueued on its preferred + * LLC, in order to pair with account_llc_dequeue() + * to maintain a consistent nr_pref_llc_running per + * runqueue. + * This is necessary because a race condition exists: + * after a task is enqueued on a runqueue, task_llc(p) + * may change due to CPU hotplug. Therefore, checking + * task_llc(p) to determine whether the task is being + * dequeued from its preferred LLC is unreliable and + * can cause inconsistent values - checking the + * p->pref_llc_queued in account_llc_dequeue() would + * be reliable. + */ + p->pref_llc_queued = pref_llc_queued; + + sd = rcu_dereference_all(rq->sd); + if (sd && (unsigned int)pref_llc < sd->llc_max) + sd->llc_counts[pref_llc]++; +} + +static void account_llc_dequeue(struct rq *rq, struct task_struct *p) +{ + struct sched_domain *sd; + int pref_llc; + + pref_llc = p->preferred_llc; + if (pref_llc < 0) + return; + + rq->nr_llc_running--; + if (p->pref_llc_queued) { + rq->nr_pref_llc_running--; + /* + * Update the status in case + * other logic might query + * this. + */ + p->pref_llc_queued = 0; + } + + sd = rcu_dereference_all(rq->sd); + if (sd && (unsigned int)pref_llc < sd->llc_max) { + /* + * There is a race condition between dequeue + * and CPU hotplug. After a task has been enqueued + * on CPUx, a CPU hotplug event occurs, and all online + * CPUs (including CPUx) rebuild their sched_domains + * and reset statistics to zero(including sd->llc_counts). + * This can cause temporary undercount and we have to + * check for such underflow in sd->llc_counts. + * + * This undercount is temporary and accurate accounting + * will resume once the rq has a chance to be idle. + */ + if (sd->llc_counts[pref_llc]) + sd->llc_counts[pref_llc]--; + } +} + +void mm_init_sched(struct mm_struct *mm, + struct sched_cache_time __percpu *_pcpu_sched) +{ + unsigned long epoch = 0; + int i; + + for_each_possible_cpu(i) { + struct sched_cache_time *pcpu_sched = per_cpu_ptr(_pcpu_sched, i); + struct rq *rq = cpu_rq(i); + + pcpu_sched->runtime = 0; + /* a slightly stale cpu epoch is acceptible */ + pcpu_sched->epoch = rq->cpu_epoch; + epoch = rq->cpu_epoch; + } + + raw_spin_lock_init(&mm->sc_stat.lock); + mm->sc_stat.epoch = epoch; + mm->sc_stat.cpu = -1; + mm->sc_stat.next_scan = jiffies; + mm->sc_stat.nr_running_avg = 0; + mm->sc_stat.footprint = 0; + /* + * The update to mm->sc_stat should not be reordered + * before initialization to mm's other fields, in case + * the readers may get invalid mm_sched_epoch, etc. + */ + smp_store_release(&mm->sc_stat.pcpu_sched, _pcpu_sched); +} + +/* because why would C be fully specified */ +static __always_inline void __shr_u64(u64 *val, unsigned int n) +{ + if (n >= 64) { + *val = 0; + return; + } + *val >>= n; +} + +static inline void __update_mm_sched(struct rq *rq, + struct sched_cache_time *pcpu_sched) +{ + lockdep_assert_held(&rq->cpu_epoch_lock); + + unsigned int period = max(READ_ONCE(llc_epoch_period), 1U); + unsigned long n, now = jiffies; + long delta = now - rq->cpu_epoch_next; + + if (delta > 0) { + n = (delta + period - 1) / period; + rq->cpu_epoch += n; + rq->cpu_epoch_next += n * period; + __shr_u64(&rq->cpu_runtime, n); + } + + n = rq->cpu_epoch - pcpu_sched->epoch; + if (n) { + pcpu_sched->epoch += n; + __shr_u64(&pcpu_sched->runtime, n); + } +} + +static unsigned long fraction_mm_sched(struct rq *rq, + struct sched_cache_time *pcpu_sched) +{ + guard(raw_spinlock_irqsave)(&rq->cpu_epoch_lock); + + __update_mm_sched(rq, pcpu_sched); + + /* + * Runtime is a geometric series (r=0.5) and as such will sum to twice + * the accumulation period, this means the multiplcation here should + * not overflow. + */ + return div64_u64(NICE_0_LOAD * pcpu_sched->runtime, rq->cpu_runtime + 1); +} + +static int get_pref_llc(struct task_struct *p, struct mm_struct *mm) +{ + int mm_sched_llc = -1, mm_sched_cpu; + + if (!mm) + return -1; + + mm_sched_cpu = READ_ONCE(mm->sc_stat.cpu); + if (mm_sched_cpu != -1) { + mm_sched_llc = llc_id(mm_sched_cpu); + +#ifdef CONFIG_NUMA_BALANCING + /* + * Don't assign preferred LLC if it + * conflicts with NUMA balancing. + * This can happen when sched_setnuma() gets + * called, however it is not much of an issue + * because we expect account_mm_sched() to get + * called fairly regularly -- at a higher rate + * than sched_setnuma() at least -- and thus the + * conflict only exists for a short period of time. + */ + if (static_branch_likely(&sched_numa_balancing) && + p->numa_preferred_nid >= 0 && + cpu_to_node(mm_sched_cpu) != p->numa_preferred_nid) + mm_sched_llc = -1; +#endif + } + + return mm_sched_llc; +} + +static unsigned int task_running_on_cpu(int cpu, struct task_struct *p); + +static inline +void account_mm_sched(struct rq *rq, struct task_struct *p, s64 delta_exec) +{ + struct sched_cache_time *pcpu_sched; + struct mm_struct *mm = p->mm; + int mm_sched_llc = -1; + unsigned long epoch; + + if (!sched_cache_enabled()) + return; + + if (p->sched_class != &fair_sched_class) + return; + /* + * init_task, kthreads and user thread created + * by user_mode_thread() don't have mm. + */ + if (!mm || !mm->sc_stat.pcpu_sched) + return; + + pcpu_sched = per_cpu_ptr(mm->sc_stat.pcpu_sched, cpu_of(rq)); + + scoped_guard (raw_spinlock, &rq->cpu_epoch_lock) { + __update_mm_sched(rq, pcpu_sched); + pcpu_sched->runtime += delta_exec; + rq->cpu_runtime += delta_exec; + epoch = rq->cpu_epoch; + } + + /* + * If this process hasn't hit task_cache_work() for a while invalidate + * its preferred state. + */ + if ((long)(epoch - READ_ONCE(mm->sc_stat.epoch)) > llc_epoch_affinity_timeout || + invalid_llc_nr(mm, p, cpu_of(rq)) || + exceed_llc_capacity(mm, cpu_of(rq))) { + if (READ_ONCE(mm->sc_stat.cpu) != -1) + WRITE_ONCE(mm->sc_stat.cpu, -1); + } + + mm_sched_llc = get_pref_llc(p, mm); + + /* task not on rq accounted later in account_entity_enqueue() */ + if (task_running_on_cpu(rq->cpu, p) && + READ_ONCE(p->preferred_llc) != mm_sched_llc) { + account_llc_dequeue(rq, p); + WRITE_ONCE(p->preferred_llc, mm_sched_llc); + account_llc_enqueue(rq, p); + } +} + +static void task_tick_cache(struct rq *rq, struct task_struct *p) +{ + struct callback_head *work = &p->cache_work; + struct mm_struct *mm = p->mm; + unsigned long epoch; + + if (!sched_cache_enabled()) + return; + + if (!mm || p->flags & PF_KTHREAD || + !mm->sc_stat.pcpu_sched) + return; + + epoch = rq->cpu_epoch; + /* avoid moving backwards */ + if (time_after_eq(mm->sc_stat.epoch, epoch)) + return; + + guard(raw_spinlock)(&mm->sc_stat.lock); + + if (work->next == work) { + task_work_add(p, work, TWA_RESUME); + WRITE_ONCE(mm->sc_stat.epoch, epoch); + } +} + +static void get_scan_cpumasks(cpumask_var_t cpus, struct task_struct *p) +{ +#ifdef CONFIG_NUMA_BALANCING + int cpu, curr_cpu, nid, pref_nid; + + if (!static_branch_likely(&sched_numa_balancing)) + goto out; + + cpu = READ_ONCE(p->mm->sc_stat.cpu); + if (cpu != -1) + nid = cpu_to_node(cpu); + curr_cpu = task_cpu(p); + + /* + * Scanning in the preferred NUMA node is ideal. However, the NUMA + * preferred node is per-task rather than per-process. It is possible + * for different threads of the process to have distinct preferred + * nodes; consequently, the process-wide preferred LLC may bounce + * between different nodes. As a workaround, maintain the scan + * CPU mask to also cover the process's current preferred LLC and the + * current running node to mitigate the bouncing risk. + * TBD: numa_group should be considered during task aggregation. + */ + pref_nid = p->numa_preferred_nid; + /* honor the task's preferred node */ + if (pref_nid == NUMA_NO_NODE) + goto out; + + cpumask_or(cpus, cpus, cpumask_of_node(pref_nid)); + + /* honor the task's preferred LLC CPU */ + if (cpu != -1 && !cpumask_test_cpu(cpu, cpus) && nid != NUMA_NO_NODE) + cpumask_or(cpus, cpus, cpumask_of_node(nid)); + + /* make sure the task's current running node is included */ + if (!cpumask_test_cpu(curr_cpu, cpus)) + cpumask_or(cpus, cpus, cpumask_of_node(cpu_to_node(curr_cpu))); + + return; + +out: +#endif + cpumask_copy(cpus, cpu_online_mask); +} + +static inline void update_avg_scale(u64 *avg, u64 sample) +{ + int factor = per_cpu(sd_llc_size, raw_smp_processor_id()); + s64 diff = sample - *avg; + u32 divisor; + + /* + * Scale the divisor based on the number of CPUs contained + * in the LLC. This scaling ensures smaller LLC domains use + * a smaller divisor to achieve more precise sensitivity to + * changes in nr_running, while larger LLC domains are capped + * at a maximum divisor of 8 which is the default smoothing + * factor of EWMA in update_avg(). + */ + divisor = clamp_t(u32, (factor >> 2), 2, 8); + *avg += div64_s64(diff, divisor); +} + +static void task_cache_work(struct callback_head *work) +{ + int cpu, m_a_cpu = -1, nr_running = 0, curr_cpu; + unsigned long next_scan, now = jiffies; + struct task_struct *p = current, *cur; + unsigned long curr_m_a_occ = 0; + struct mm_struct *mm = p->mm; + unsigned long m_a_occ = 0; + cpumask_var_t cpus; + + WARN_ON_ONCE(work != &p->cache_work); + + work->next = work; + + if (p->flags & PF_EXITING) + return; + + next_scan = READ_ONCE(mm->sc_stat.next_scan); + if (time_before(now, next_scan)) + return; + + /* only 1 thread is allowed to scan */ + if (!try_cmpxchg(&mm->sc_stat.next_scan, &next_scan, + now + max_t(unsigned long, + READ_ONCE(llc_epoch_period), 1))) + return; + + curr_cpu = task_cpu(p); + if (invalid_llc_nr(mm, p, curr_cpu) || + exceed_llc_capacity(mm, curr_cpu)) { + if (READ_ONCE(mm->sc_stat.cpu) != -1) + WRITE_ONCE(mm->sc_stat.cpu, -1); + + return; + } + + if (!zalloc_cpumask_var(&cpus, GFP_KERNEL)) + return; + + scoped_guard (cpus_read_lock) { + guard(rcu)(); + + get_scan_cpumasks(cpus, p); + + for_each_cpu(cpu, cpus) { + /* XXX sched_cluster_active */ + struct sched_domain *sd = rcu_dereference_all(per_cpu(sd_llc, cpu)); + unsigned long occ, m_occ = 0, a_occ = 0; + int m_cpu = -1, i; + + if (!sd) + continue; + + for_each_cpu(i, sched_domain_span(sd)) { + occ = fraction_mm_sched(cpu_rq(i), + per_cpu_ptr(mm->sc_stat.pcpu_sched, i)); + a_occ += occ; + if (occ > m_occ) { + m_occ = occ; + m_cpu = i; + } + + cur = rcu_dereference_all(cpu_rq(i)->curr); + if (cur && !(cur->flags & (PF_EXITING | PF_KTHREAD)) && + cur->mm == mm) + nr_running++; + } + + /* + * Compare the accumulated occupancy of each LLC. The + * reason for using accumulated occupancy rather than average + * per CPU occupancy is that it works better in asymmetric LLC + * scenarios. + * For example, if there are 2 threads in a 4CPU LLC and 3 + * threads in an 8CPU LLC, it might be better to choose the one + * with 3 threads. However, this would not be the case if the + * occupancy is divided by the number of CPUs in an LLC (i.e., + * if average per CPU occupancy is used). + * Besides, NUMA balancing fault statistics behave similarly: + * the total number of faults per node is compared rather than + * the average number of faults per CPU. This strategy is also + * followed here. + */ + if (a_occ > m_a_occ) { + m_a_occ = a_occ; + m_a_cpu = m_cpu; + } + + if (llc_id(cpu) == llc_id(READ_ONCE(mm->sc_stat.cpu))) + curr_m_a_occ = a_occ; + + cpumask_andnot(cpus, cpus, sched_domain_span(sd)); + } + } + + if (m_a_occ > (2 * curr_m_a_occ)) { + /* + * Avoid switching sc_stat.cpu too fast. + * The reason to choose 2X is because: + * 1. It is better to keep the preferred LLC stable, + * rather than changing it frequently and cause migrations + * 2. 2X means the new preferred LLC has at least 1 more + * busy CPU than the old one(200% vs 100%, eg) + * 3. 2X is chosen based on test results, as it delivers + * the optimal performance gain so far. + */ + WRITE_ONCE(mm->sc_stat.cpu, m_a_cpu); + } + + update_avg_scale(&mm->sc_stat.nr_running_avg, nr_running); + free_cpumask_var(cpus); +} + +void init_sched_mm(struct task_struct *p) +{ + struct callback_head *work = &p->cache_work; + + init_task_work(work, task_cache_work); + work->next = work; + /* + * Reset new task's preference to avoid + * polluting account_llc_enqueue(). + */ + p->preferred_llc = -1; +} + +#else /* CONFIG_SCHED_CACHE */ + +static inline void account_mm_sched(struct rq *rq, struct task_struct *p, + s64 delta_exec) { } + +void init_sched_mm(struct task_struct *p) { } + +static void task_tick_cache(struct rq *rq, struct task_struct *p) { } + +static inline int get_pref_llc(struct task_struct *p, + struct mm_struct *mm) +{ + return -1; +} + +static void account_llc_enqueue(struct rq *rq, struct task_struct *p) {} + +static void account_llc_dequeue(struct rq *rq, struct task_struct *p) {} + +#endif /* CONFIG_SCHED_CACHE */ + /* * Used by other classes to account runtime. */ @@ -1578,13 +2156,9 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) se->exec_start = rq_clock_task(rq_of(cfs_rq)); } -/************************************************** - * Scheduling class queueing methods: - */ - +/* Check sched_smt_active before calling this to avoid overheads in fastpaths */ static inline bool is_core_idle(int cpu) { -#ifdef CONFIG_SCHED_SMT int sibling; for_each_cpu(sibling, cpu_smt_mask(cpu)) { @@ -1594,7 +2168,6 @@ static inline bool is_core_idle(int cpu) if (!idle_cpu(sibling)) return false; } -#endif return true; } @@ -2277,12 +2850,11 @@ numa_type numa_classify(unsigned int imbalance_pct, return node_fully_busy; } -#ifdef CONFIG_SCHED_SMT /* Forward declarations of select_idle_sibling helpers */ static inline bool test_idle_cores(int cpu); static inline int numa_idle_core(int idle_core, int cpu) { - if (!static_branch_likely(&sched_smt_present) || + if (!sched_smt_active() || idle_core >= 0 || !test_idle_cores(cpu)) return idle_core; @@ -2295,12 +2867,6 @@ static inline int numa_idle_core(int idle_core, int cpu) return idle_core; } -#else /* !CONFIG_SCHED_SMT: */ -static inline int numa_idle_core(int idle_core, int cpu) -{ - return idle_core; -} -#endif /* !CONFIG_SCHED_SMT */ /* * Gather all necessary information to make NUMA balancing placement @@ -3079,6 +3645,7 @@ static void task_numa_placement(struct task_struct *p) unsigned long total_faults; u64 runtime, period; spinlock_t *group_lock = NULL; + long __maybe_unused new_fp; struct numa_group *ng; /* @@ -3153,6 +3720,31 @@ static void task_numa_placement(struct task_struct *p) ng->total_faults += diff; group_faults += ng->faults[mem_idx]; } +#ifdef CONFIG_SCHED_CACHE + /* + * Per task p->numa_faults[mem_idx] converges, + * so the accumulation of each task's faults + * converges too - Given the number of threads, + * it cannot overflow an unsigned long. + * Racy with concurrent updates from other threads + * sharing this mm. Acceptable since footprint is a + * heuristic and occasional lost updates are tolerable. + * + * If a task exits, its corresponding footprint must + * be subtracted from the mm->sc_stat.footprint, otherwise + * the mm->sc_stat.footprint will not converge: + * the exiting thread's footprint remains unchanged/undecayed + * in mm->sc_stat.footprint. See exit_mm(). + * + * Lost updates and unsynchronized subtraction + * in exit_mm() can cause footprint + diff to + * go negative. Clamp to zero to prevent the + * unsigned footprint from wrapping. + */ + new_fp = (long)READ_ONCE(p->mm->sc_stat.footprint) + diff; + WRITE_ONCE(p->mm->sc_stat.footprint, + max(new_fp, 0L)); +#endif } if (!ng) { @@ -3877,9 +4469,11 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) { update_load_add(&cfs_rq->load, se->load.weight); if (entity_is_task(se)) { + struct task_struct *p = task_of(se); struct rq *rq = rq_of(cfs_rq); - account_numa_enqueue(rq, task_of(se)); + account_numa_enqueue(rq, p); + account_llc_enqueue(rq, p); list_add(&se->group_node, &rq->cfs_tasks); } cfs_rq->nr_queued++; @@ -3890,7 +4484,11 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) { update_load_sub(&cfs_rq->load, se->load.weight); if (entity_is_task(se)) { - account_numa_dequeue(rq_of(cfs_rq), task_of(se)); + struct task_struct *p = task_of(se); + struct rq *rq = rq_of(cfs_rq); + + account_numa_dequeue(rq, p); + account_llc_dequeue(rq, p); list_del_init(&se->group_node); } cfs_rq->nr_queued--; @@ -4393,7 +4991,7 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq) * For migration heavy workloads, access to tg->load_avg can be * unbound. Limit the update rate to at most once per ms. */ - now = sched_clock_cpu(cpu_of(rq_of(cfs_rq))); + now = rq_clock(rq_of(cfs_rq)); if (now - cfs_rq->last_update_tg_load_avg < NSEC_PER_MSEC) return; @@ -4416,7 +5014,7 @@ static inline void clear_tg_load_avg(struct cfs_rq *cfs_rq) if (cfs_rq->tg == &root_task_group) return; - now = sched_clock_cpu(cpu_of(rq_of(cfs_rq))); + now = rq_clock(rq_of(cfs_rq)); delta = 0 - cfs_rq->tg_load_avg_contrib; atomic_long_add(delta, &cfs_rq->tg->load_avg); cfs_rq->tg_load_avg_contrib = 0; @@ -4437,13 +5035,13 @@ static void __maybe_unused clear_tg_offline_cfs_rqs(struct rq *rq) */ rq_clock_start_loop_update(rq); - rcu_read_lock(); + guard(rcu)(); + list_for_each_entry_rcu(tg, &task_groups, list) { - struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; + struct cfs_rq *cfs_rq = tg_cfs_rq(tg, cpu_of(rq)); clear_tg_load_avg(cfs_rq); } - rcu_read_unlock(); rq_clock_stop_loop_update(rq); } @@ -4959,13 +5557,86 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s trace_pelt_cfs_tp(cfs_rq); } +#define UTIL_EST_MARGIN (SCHED_CAPACITY_SCALE / 100) + +static inline void util_est_update(struct sched_entity *se) +{ + unsigned int ewma, dequeued, last_ewma_diff; + + if (!sched_feat(UTIL_EST)) + return; + + /* Get current estimate of utilization */ + ewma = READ_ONCE(se->avg.util_est); + + /* + * If the PELT values haven't changed since enqueue time, + * skip the util_est update. + */ + if (ewma & UTIL_AVG_UNCHANGED) + return; + + /* Get utilization at dequeue */ + dequeued = READ_ONCE(se->avg.util_avg); + + /* + * Reset EWMA on utilization increases, the moving average is used only + * to smooth utilization decreases. + */ + if (ewma <= dequeued) { + ewma = dequeued; + goto done; + } + + /* + * Skip update of task's estimated utilization when its members are + * already ~1% close to its last activation value. + */ + last_ewma_diff = ewma - dequeued; + if (last_ewma_diff < UTIL_EST_MARGIN) + goto done; + + /* + * To avoid underestimate of task utilization, skip updates of EWMA if + * we cannot grant that thread got all CPU time it wanted. + */ + if ((dequeued + UTIL_EST_MARGIN) < READ_ONCE(se->avg.runnable_avg)) + goto done; + + /* + * Update Task's estimated utilization + * + * When *p completes an activation we can consolidate another sample + * of the task size. This is done by using this value to update the + * Exponential Weighted Moving Average (EWMA): + * + * ewma(t) = w * task_util(p) + (1-w) * ewma(t-1) + * = w * task_util(p) + ewma(t-1) - w * ewma(t-1) + * = w * (task_util(p) - ewma(t-1)) + ewma(t-1) + * = w * ( -last_ewma_diff ) + ewma(t-1) + * = w * (-last_ewma_diff + ewma(t-1) / w) + * + * Where 'w' is the weight of new samples, which is configured to be + * 0.25, thus making w=1/4 ( >>= UTIL_EST_WEIGHT_SHIFT) + */ + ewma <<= UTIL_EST_WEIGHT_SHIFT; + ewma -= last_ewma_diff; + ewma >>= UTIL_EST_WEIGHT_SHIFT; +done: + ewma |= UTIL_AVG_UNCHANGED; + WRITE_ONCE(se->avg.util_est, ewma); + + trace_sched_util_est_se_tp(se); +} + /* * Optional action to be done while updating the load average */ -#define UPDATE_TG 0x1 -#define SKIP_AGE_LOAD 0x2 -#define DO_ATTACH 0x4 -#define DO_DETACH 0x8 +#define UPDATE_TG 0x01 +#define SKIP_AGE_LOAD 0x02 +#define DO_ATTACH 0x04 +#define DO_DETACH 0x08 +#define UPDATE_UTIL_EST 0x10 /* Update task and its cfs_rq load average */ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) @@ -5008,6 +5679,9 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s if (flags & UPDATE_TG) update_tg_load_avg(cfs_rq); } + + if (flags & UPDATE_UTIL_EST) + util_est_update(se); } /* @@ -5066,11 +5740,6 @@ static inline unsigned long task_util(struct task_struct *p) return READ_ONCE(p->se.avg.util_avg); } -static inline unsigned long task_runnable(struct task_struct *p) -{ - return READ_ONCE(p->se.avg.runnable_avg); -} - static inline unsigned long _task_util_est(struct task_struct *p) { return READ_ONCE(p->se.avg.util_est) & ~UTIL_AVG_UNCHANGED; @@ -5113,88 +5782,6 @@ static inline void util_est_dequeue(struct cfs_rq *cfs_rq, trace_sched_util_est_cfs_tp(cfs_rq); } -#define UTIL_EST_MARGIN (SCHED_CAPACITY_SCALE / 100) - -static inline void util_est_update(struct cfs_rq *cfs_rq, - struct task_struct *p, - bool task_sleep) -{ - unsigned int ewma, dequeued, last_ewma_diff; - - if (!sched_feat(UTIL_EST)) - return; - - /* - * Skip update of task's estimated utilization when the task has not - * yet completed an activation, e.g. being migrated. - */ - if (!task_sleep) - return; - - /* Get current estimate of utilization */ - ewma = READ_ONCE(p->se.avg.util_est); - - /* - * If the PELT values haven't changed since enqueue time, - * skip the util_est update. - */ - if (ewma & UTIL_AVG_UNCHANGED) - return; - - /* Get utilization at dequeue */ - dequeued = task_util(p); - - /* - * Reset EWMA on utilization increases, the moving average is used only - * to smooth utilization decreases. - */ - if (ewma <= dequeued) { - ewma = dequeued; - goto done; - } - - /* - * Skip update of task's estimated utilization when its members are - * already ~1% close to its last activation value. - */ - last_ewma_diff = ewma - dequeued; - if (last_ewma_diff < UTIL_EST_MARGIN) - goto done; - - /* - * To avoid underestimate of task utilization, skip updates of EWMA if - * we cannot grant that thread got all CPU time it wanted. - */ - if ((dequeued + UTIL_EST_MARGIN) < task_runnable(p)) - goto done; - - - /* - * Update Task's estimated utilization - * - * When *p completes an activation we can consolidate another sample - * of the task size. This is done by using this value to update the - * Exponential Weighted Moving Average (EWMA): - * - * ewma(t) = w * task_util(p) + (1-w) * ewma(t-1) - * = w * task_util(p) + ewma(t-1) - w * ewma(t-1) - * = w * (task_util(p) - ewma(t-1)) + ewma(t-1) - * = w * ( -last_ewma_diff ) + ewma(t-1) - * = w * (-last_ewma_diff + ewma(t-1) / w) - * - * Where 'w' is the weight of new samples, which is configured to be - * 0.25, thus making w=1/4 ( >>= UTIL_EST_WEIGHT_SHIFT) - */ - ewma <<= UTIL_EST_WEIGHT_SHIFT; - ewma -= last_ewma_diff; - ewma >>= UTIL_EST_WEIGHT_SHIFT; -done: - ewma |= UTIL_AVG_UNCHANGED; - WRITE_ONCE(p->se.avg.util_est, ewma); - - trace_sched_util_est_se_tp(&p->se); -} - static inline unsigned long get_actual_cpu_capacity(int cpu) { unsigned long capacity = arch_scale_cpu_capacity(cpu); @@ -5647,7 +6234,7 @@ static bool dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { bool sleep = flags & DEQUEUE_SLEEP; - int action = UPDATE_TG; + int action = 0; update_curr(cfs_rq); clear_buddies(cfs_rq, se); @@ -5667,15 +6254,23 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (sched_feat(DELAY_DEQUEUE) && delay && !entity_eligible(cfs_rq, se)) { - update_load_avg(cfs_rq, se, 0); + if (entity_is_task(se)) + action |= UPDATE_UTIL_EST; + update_load_avg(cfs_rq, se, action); update_entity_lag(cfs_rq, se); set_delayed(se); return false; } } - if (entity_is_task(se) && task_on_rq_migrating(task_of(se))) - action |= DO_DETACH; + action = UPDATE_TG; + if (entity_is_task(se)) { + if (task_on_rq_migrating(task_of(se))) + action |= DO_DETACH; + + if (sleep && !(flags & DEQUEUE_DELAYED)) + action |= UPDATE_UTIL_EST; + } /* * When dequeuing a sched_entity, we must: @@ -5793,8 +6388,6 @@ pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq, bool protect) return se; } -static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq); - static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev) { /* @@ -5804,9 +6397,6 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev) if (prev->on_rq) update_curr(cfs_rq); - /* throttle cfs_rqs exceeding runtime */ - check_cfs_rq_runtime(cfs_rq); - if (prev->on_rq) { update_stats_wait_start_fair(cfs_rq, prev); /* Put 'current' back into the tree. */ @@ -5941,44 +6531,32 @@ static int __assign_cfs_rq_runtime(struct cfs_bandwidth *cfs_b, return cfs_rq->runtime_remaining > 0; } -/* returns 0 on failure to allocate runtime */ -static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) -{ - struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); - int ret; +static bool throttle_cfs_rq(struct cfs_rq *cfs_rq); - raw_spin_lock(&cfs_b->lock); - ret = __assign_cfs_rq_runtime(cfs_b, cfs_rq, sched_cfs_bandwidth_slice()); - raw_spin_unlock(&cfs_b->lock); - - return ret; -} - -static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) +static bool __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; if (likely(cfs_rq->runtime_remaining > 0)) - return; + return false; if (cfs_rq->throttled) - return; + return true; /* - * if we're unable to extend our runtime we resched so that the active - * hierarchy can be throttled + * throttle_cfs_rq() will try to extend the runtime first + * before throttling the hierarchy. */ - if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr)) - resched_curr(rq_of(cfs_rq)); + return throttle_cfs_rq(cfs_rq); } static __always_inline -void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) +bool account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) { if (!cfs_bandwidth_used() || !cfs_rq->runtime_enabled) - return; + return false; - __account_cfs_rq_runtime(cfs_rq, delta_exec); + return __account_cfs_rq_runtime(cfs_rq, delta_exec); } static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq) @@ -5999,7 +6577,7 @@ static inline int throttled_hierarchy(struct cfs_rq *cfs_rq) static inline int lb_throttled_hierarchy(struct task_struct *p, int dst_cpu) { - return throttled_hierarchy(task_group(p)->cfs_rq[dst_cpu]); + return throttled_hierarchy(tg_cfs_rq(task_group(p), dst_cpu)); } static inline bool task_is_throttled(struct task_struct *p) @@ -6145,8 +6723,18 @@ static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags); static int tg_unthrottle_up(struct task_group *tg, void *data) { struct rq *rq = data; - struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; + struct cfs_rq *cfs_rq = tg_cfs_rq(tg, cpu_of(rq)); struct task_struct *p, *tmp; + LIST_HEAD(throttled_tasks); + + /* + * If cfs_rq->curr is set, the cfs_rq might not have caught up + * since the last clock update. Do it now before we begin + * queueing task onto it to save the need for unnecessarily + * unthrottle the hierarchy for this cfs_rq to be throttled + * right back again. + */ + update_curr(cfs_rq); if (--cfs_rq->throttle_count) return 0; @@ -6168,13 +6756,31 @@ static int tg_unthrottle_up(struct task_group *tg, void *data) cfs_rq->throttled_clock_self_time += delta; } + /* + * Move the tasks to a local list since an update_curr() during + * enqueue_task_fair() can throttle a higher cfs_rq, and it can + * see the "throttled_limbo_list" being non-empty in + * tg_throttle_down() if throttle_count turned 0 above. + */ + list_splice_init(&cfs_rq->throttled_limbo_list, &throttled_tasks); + /* Re-enqueue the tasks that have been throttled at this level. */ - list_for_each_entry_safe(p, tmp, &cfs_rq->throttled_limbo_list, throttle_node) { + list_for_each_entry_safe(p, tmp, &throttled_tasks, throttle_node) { + /* + * Back to being throttled! Break out and put the remaining + * tasks back onto the limbo_list to prevent running them + * unnecessarily. + */ + if (cfs_rq->throttle_count) + break; + list_del_init(&p->throttle_node); p->throttled = false; - enqueue_task_fair(rq_of(cfs_rq), p, ENQUEUE_WAKEUP); + enqueue_task_fair(rq, p, ENQUEUE_WAKEUP); } + list_splice(&throttled_tasks, &cfs_rq->throttled_limbo_list); + /* Add cfs_rq with load or one or more already running entities to the list */ if (!cfs_rq_is_decayed(cfs_rq)) list_add_leaf_cfs_rq(cfs_rq); @@ -6216,7 +6822,7 @@ static void record_throttle_clock(struct cfs_rq *cfs_rq) static int tg_throttle_down(struct task_group *tg, void *data) { struct rq *rq = data; - struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; + struct cfs_rq *cfs_rq = tg_cfs_rq(tg, cpu_of(rq)); if (cfs_rq->throttle_count++) return 0; @@ -6238,35 +6844,48 @@ static int tg_throttle_down(struct task_group *tg, void *data) static bool 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); - int dequeue = 1; + struct sched_entity *curr = cfs_rq->curr; + struct rq *rq = rq_of(cfs_rq); + + scoped_guard(raw_spinlock, &cfs_b->lock) { + u64 target_runtime = 1; - raw_spin_lock(&cfs_b->lock); - /* This will start the period timer if necessary */ - if (__assign_cfs_rq_runtime(cfs_b, cfs_rq, 1)) { /* - * We have raced with bandwidth becoming available, and if we - * actually throttled the timer might not unthrottle us for an - * entire period. We additionally needed to make sure that any - * subsequent check_cfs_rq_runtime calls agree not to throttle - * us, as we may commit to do cfs put_prev+pick_next, so we ask - * for 1ns of runtime rather than just check cfs_b. + * If cfs_rq->curr is still runnable, we are here from an + * update_curr(). Request sysctl_sched_cfs_bandwidth_slice + * worth of bandwidth to continue running. + * + * If the curr is not runnable, just request enough bandwidth + * to be runnable next time the pick selects this cfs_rq. + */ + if (curr && curr->on_rq) + target_runtime = sched_cfs_bandwidth_slice(); + + /* + * Check if We have raced with bandwidth becoming available. If + * we actually throttled the timer might not unthrottle us for + * an entire period. We additionally needed to make sure that + * any subsequent check_cfs_rq_runtime calls agree not to + * throttle us, as we may commit to do cfs put_prev+pick_next, + * so we ask for 1ns of runtime rather than just check cfs_b. + * + * This will start the period timer if necessary. + */ + if (__assign_cfs_rq_runtime(cfs_b, cfs_rq, target_runtime)) + return false; + + /* + * No bandwidth available; Add ourselves on the list to be + * unthrottled later. */ - dequeue = 0; - } else { list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); } - raw_spin_unlock(&cfs_b->lock); - - if (!dequeue) - return false; /* Throttle no longer required. */ /* freeze hierarchy runnable averages while throttled */ - rcu_read_lock(); - walk_tg_tree_from(cfs_rq->tg, tg_throttle_down, tg_nop, (void *)rq); - rcu_read_unlock(); + scoped_guard(rcu) + walk_tg_tree_from(cfs_rq->tg, tg_throttle_down, tg_nop, (void *)rq); /* * Note: distribution will already see us throttled via the @@ -6274,6 +6893,17 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) */ cfs_rq->throttled = 1; WARN_ON_ONCE(cfs_rq->throttled_clock); + + /* + * If current hierarchy was throttled, add throttle work to the + * current donor. In case of proxy-execution, the execution + * context cannot exit to the userspace while holding a mutex + * and the rule of throttle deferral to only throttle the + * throttled context at exit to userspace is still preserved. + */ + if (curr && curr->on_rq) + task_throttle_setup_work(rq->donor); + return true; } @@ -6281,7 +6911,7 @@ void unthrottle_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 = cfs_rq->tg->se[cpu_of(rq)]; + struct sched_entity *se = cfs_rq_se(cfs_rq); /* * It's possible we are called with runtime_remaining < 0 due to things @@ -6291,21 +6921,25 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) * We can't unthrottle this cfs_rq without any runtime remaining because * any enqueue in tg_unthrottle_up() will immediately trigger a throttle, * which is not supposed to happen on unthrottle path. + * + * Catch up on the remaining runtime since last clock update before + * checking runtime remaining. */ + update_curr(cfs_rq); if (cfs_rq->runtime_enabled && cfs_rq->runtime_remaining <= 0) return; cfs_rq->throttled = 0; - update_rq_clock(rq); + scoped_guard(raw_spinlock, &cfs_b->lock) { + list_del_rcu(&cfs_rq->throttled_list); + + if (!cfs_rq->throttled_clock) + break; - raw_spin_lock(&cfs_b->lock); - if (cfs_rq->throttled_clock) { cfs_b->throttled_time += rq_clock(rq) - cfs_rq->throttled_clock; cfs_rq->throttled_clock = 0; } - list_del_rcu(&cfs_rq->throttled_list); - raw_spin_unlock(&cfs_b->lock); /* update hierarchical throttle state */ walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq); @@ -6334,9 +6968,8 @@ static void __cfsb_csd_unthrottle(void *arg) { struct cfs_rq *cursor, *tmp; struct rq *rq = arg; - struct rq_flags rf; - rq_lock(rq, &rf); + guard(rq_lock)(rq); /* * Iterating over the list can trigger several call to @@ -6353,7 +6986,7 @@ static void __cfsb_csd_unthrottle(void *arg) * race with group being freed in the window between removing it * from the list and advancing to the next entry in the list. */ - rcu_read_lock(); + guard(rcu)(); list_for_each_entry_safe(cursor, tmp, &rq->cfsb_csd_list, throttled_csd_list) { @@ -6363,10 +6996,7 @@ static void __cfsb_csd_unthrottle(void *arg) unthrottle_cfs_rq(cursor); } - rcu_read_unlock(); - rq_clock_stop_loop_update(rq); - rq_unlock(rq, &rf); } static inline void __unthrottle_cfs_rq_async(struct cfs_rq *cfs_rq) @@ -6375,6 +7005,7 @@ static inline void __unthrottle_cfs_rq_async(struct cfs_rq *cfs_rq) bool first; if (rq == this_rq()) { + update_rq_clock(rq); unthrottle_cfs_rq(cfs_rq); return; } @@ -6402,15 +7033,14 @@ static void unthrottle_cfs_rq_async(struct cfs_rq *cfs_rq) static bool distribute_cfs_runtime(struct cfs_bandwidth *cfs_b) { + bool throttled = false, unthrottle_local = false; int this_cpu = smp_processor_id(); u64 runtime, remaining = 1; - bool throttled = false; - struct cfs_rq *cfs_rq, *tmp; - struct rq_flags rf; + struct cfs_rq *cfs_rq; struct rq *rq; - LIST_HEAD(local_unthrottle); - rcu_read_lock(); + guard(rcu)(); + list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq, throttled_list) { rq = rq_of(cfs_rq); @@ -6420,64 +7050,66 @@ static bool distribute_cfs_runtime(struct cfs_bandwidth *cfs_b) break; } - rq_lock_irqsave(rq, &rf); + guard(rq_lock_irqsave)(rq); + if (!cfs_rq_throttled(cfs_rq)) - goto next; + continue; /* Already queued for async unthrottle */ if (!list_empty(&cfs_rq->throttled_csd_list)) - goto next; + continue; + + if (cfs_rq->curr) { + update_rq_clock(rq); + update_curr(cfs_rq); + } /* By the above checks, this should never be true */ WARN_ON_ONCE(cfs_rq->runtime_remaining > 0); - raw_spin_lock(&cfs_b->lock); - runtime = -cfs_rq->runtime_remaining + 1; - if (runtime > cfs_b->runtime) - runtime = cfs_b->runtime; - cfs_b->runtime -= runtime; - remaining = cfs_b->runtime; - raw_spin_unlock(&cfs_b->lock); + scoped_guard(raw_spinlock, &cfs_b->lock) { + runtime = -cfs_rq->runtime_remaining + 1; + if (runtime > cfs_b->runtime) + runtime = cfs_b->runtime; + cfs_b->runtime -= runtime; + remaining = cfs_b->runtime; + } cfs_rq->runtime_remaining += runtime; - /* we check whether we're throttled above */ - if (cfs_rq->runtime_remaining > 0) { - if (cpu_of(rq) != this_cpu) { - unthrottle_cfs_rq_async(cfs_rq); - } else { - /* - * We currently only expect to be unthrottling - * a single cfs_rq locally. - */ - WARN_ON_ONCE(!list_empty(&local_unthrottle)); - list_add_tail(&cfs_rq->throttled_csd_list, - &local_unthrottle); - } - } else { + /* + * Ran out of bandwidth during distribution! + * Indicate throttled entities and break early. + */ + if (cfs_rq->runtime_remaining <= 0) { throttled = true; + break; } -next: - rq_unlock_irqrestore(rq, &rf); - } - - list_for_each_entry_safe(cfs_rq, tmp, &local_unthrottle, - throttled_csd_list) { - struct rq *rq = rq_of(cfs_rq); - - rq_lock_irqsave(rq, &rf); - - list_del_init(&cfs_rq->throttled_csd_list); - - if (cfs_rq_throttled(cfs_rq)) - unthrottle_cfs_rq(cfs_rq); + /* we check whether we're throttled above */ + if (cpu_of(rq) != this_cpu) { + unthrottle_cfs_rq_async(cfs_rq); + continue; + } - rq_unlock_irqrestore(rq, &rf); + /* + * Allow a parallel async unthrottle to unthrottle + * this cfs_rq too via __cfsb_csd_unthrottle(). + * If we are first, do it ourselves at the end and + * save on an IPI from remote CPUs. + */ + unthrottle_local = list_empty(&rq->cfsb_csd_list); + list_add_tail(&cfs_rq->throttled_csd_list, &rq->cfsb_csd_list); } - WARN_ON_ONCE(!list_empty(&local_unthrottle)); - rcu_read_unlock(); + if (unthrottle_local) { + /* + * Protect against an IPI that is also trying to flush + * the unthrottled cfs_rq(s) from this CPU's csd_list. + */ + scoped_guard(irqsave) + __cfsb_csd_unthrottle(cpu_rq(this_cpu)); + } return throttled; } @@ -6601,7 +7233,8 @@ static void __return_cfs_rq_runtime(struct cfs_rq *cfs_rq) if (slack_runtime <= 0) return; - raw_spin_lock(&cfs_b->lock); + guard(raw_spinlock)(&cfs_b->lock); + if (cfs_b->quota != RUNTIME_INF) { cfs_b->runtime += slack_runtime; @@ -6610,7 +7243,6 @@ static void __return_cfs_rq_runtime(struct cfs_rq *cfs_rq) !list_empty(&cfs_b->throttled_cfs_rq)) start_cfs_slack_bandwidth(cfs_b); } - raw_spin_unlock(&cfs_b->lock); /* even if it's not valid for return we don't want to try again */ cfs_rq->runtime_remaining -= slack_runtime; @@ -6633,25 +7265,21 @@ static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) */ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) { - u64 runtime = 0, slice = sched_cfs_bandwidth_slice(); - unsigned long flags; - /* confirm we're still not at a refresh boundary */ - raw_spin_lock_irqsave(&cfs_b->lock, flags); - cfs_b->slack_started = false; + scoped_guard(raw_spinlock_irqsave, &cfs_b->lock) { + u64 runtime = 0, slice = sched_cfs_bandwidth_slice(); - if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) { - raw_spin_unlock_irqrestore(&cfs_b->lock, flags); - return; - } + cfs_b->slack_started = false; - if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) - runtime = cfs_b->runtime; + if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) + return; - raw_spin_unlock_irqrestore(&cfs_b->lock, flags); + if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) + runtime = cfs_b->runtime; - if (!runtime) - return; + if (!runtime) + return; + } distribute_cfs_runtime(cfs_b); } @@ -6666,7 +7294,7 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq) if (!cfs_bandwidth_used()) return; - /* an active group must be handled by the update_curr()->put() path */ + /* an active group must be handled by the update_curr() path */ if (!cfs_rq->runtime_enabled || cfs_rq->curr) return; @@ -6676,8 +7304,6 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq) /* update runtime allocation */ account_cfs_rq_runtime(cfs_rq, 0); - if (cfs_rq->runtime_remaining <= 0) - throttle_cfs_rq(cfs_rq); } static void sync_throttle(struct task_group *tg, int cpu) @@ -6690,8 +7316,8 @@ static void sync_throttle(struct task_group *tg, int cpu) if (!tg->parent) return; - cfs_rq = tg->cfs_rq[cpu]; - pcfs_rq = tg->parent->cfs_rq[cpu]; + cfs_rq = tg_cfs_rq(tg, cpu); + pcfs_rq = tg_cfs_rq(tg->parent, cpu); cfs_rq->throttle_count = pcfs_rq->throttle_count; cfs_rq->throttled_clock_pelt = rq_clock_pelt(cpu_rq(cpu)); @@ -6707,25 +7333,6 @@ static void sync_throttle(struct task_group *tg, int cpu) cfs_rq->pelt_clock_throttled = 1; } -/* conditionally throttle active cfs_rq's from put_prev_entity() */ -static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) -{ - if (!cfs_bandwidth_used()) - return false; - - if (likely(!cfs_rq->runtime_enabled || cfs_rq->runtime_remaining > 0)) - return false; - - /* - * it's possible for a throttled entity to be forced into a running - * state (e.g. set_curr_task), in this case we're finished. - */ - if (cfs_rq_throttled(cfs_rq)) - return true; - - return throttle_cfs_rq(cfs_rq); -} - static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) { struct cfs_bandwidth *cfs_b = @@ -6740,18 +7347,18 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) { struct cfs_bandwidth *cfs_b = container_of(timer, struct cfs_bandwidth, period_timer); - unsigned long flags; int overrun; int idle = 0; int count = 0; - raw_spin_lock_irqsave(&cfs_b->lock, flags); + CLASS(raw_spinlock_irqsave, cfsb_guard)(&cfs_b->lock); + for (;;) { overrun = hrtimer_forward_now(timer, cfs_b->period); if (!overrun) break; - idle = do_sched_cfs_period_timer(cfs_b, overrun, flags); + idle = do_sched_cfs_period_timer(cfs_b, overrun, cfsb_guard.flags); if (++count > 3) { u64 new, old = ktime_to_ns(cfs_b->period); @@ -6784,11 +7391,13 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) count = 0; } } - if (idle) + + if (idle) { cfs_b->period_active = 0; - raw_spin_unlock_irqrestore(&cfs_b->lock, flags); + return HRTIMER_NORESTART; + } - return idle ? HRTIMER_NORESTART : HRTIMER_RESTART; + return HRTIMER_RESTART; } void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent) @@ -6855,14 +7464,12 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) */ for_each_possible_cpu(i) { struct rq *rq = cpu_rq(i); - unsigned long flags; if (list_empty(&rq->cfsb_csd_list)) continue; - local_irq_save(flags); - __cfsb_csd_unthrottle(rq); - local_irq_restore(flags); + scoped_guard(irqsave) + __cfsb_csd_unthrottle(rq); } } @@ -6880,16 +7487,15 @@ static void __maybe_unused update_runtime_enabled(struct rq *rq) lockdep_assert_rq_held(rq); - rcu_read_lock(); + guard(rcu)(); + list_for_each_entry_rcu(tg, &task_groups, list) { struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth; - struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; + struct cfs_rq *cfs_rq = tg_cfs_rq(tg, cpu_of(rq)); - raw_spin_lock(&cfs_b->lock); - cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF; - raw_spin_unlock(&cfs_b->lock); + scoped_guard(raw_spinlock, &cfs_b->lock) + cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF; } - rcu_read_unlock(); } /* cpu offline callback */ @@ -6910,9 +7516,10 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) */ rq_clock_start_loop_update(rq); - rcu_read_lock(); + guard(rcu)(); + list_for_each_entry_rcu(tg, &task_groups, list) { - struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; + struct cfs_rq *cfs_rq = tg_cfs_rq(tg, cpu_of(rq)); if (!cfs_rq->runtime_enabled) continue; @@ -6933,7 +7540,6 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) cfs_rq->runtime_remaining = 1; unthrottle_cfs_rq(cfs_rq); } - rcu_read_unlock(); rq_clock_stop_loop_update(rq); } @@ -6980,8 +7586,7 @@ static void sched_fair_update_stop_tick(struct rq *rq, struct task_struct *p) #else /* !CONFIG_CFS_BANDWIDTH: */ -static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {} -static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { return false; } +static bool account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) { return false; } static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {} static inline void sync_throttle(struct task_group *tg, int cpu) {} static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} @@ -7438,7 +8043,6 @@ static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (!p->se.sched_delayed) util_est_dequeue(&rq->cfs, p); - util_est_update(&rq->cfs, p, flags & DEQUEUE_SLEEP); if (dequeue_entities(rq, &p->se, flags) < 0) return false; @@ -7811,7 +8415,6 @@ static inline int __select_idle_cpu(int cpu, struct task_struct *p) return -1; } -#ifdef CONFIG_SCHED_SMT DEFINE_STATIC_KEY_FALSE(sched_smt_present); EXPORT_SYMBOL_GPL(sched_smt_present); @@ -7819,7 +8422,7 @@ static inline void set_idle_cores(int cpu, int val) { struct sched_domain_shared *sds; - sds = rcu_dereference_all(per_cpu(sd_llc_shared, cpu)); + sds = rcu_dereference_all(per_cpu(sd_balance_shared, cpu)); if (sds) WRITE_ONCE(sds->has_idle_cores, val); } @@ -7828,7 +8431,7 @@ static inline bool test_idle_cores(int cpu) { struct sched_domain_shared *sds; - sds = rcu_dereference_all(per_cpu(sd_llc_shared, cpu)); + sds = rcu_dereference_all(per_cpu(sd_balance_shared, cpu)); if (sds) return READ_ONCE(sds->has_idle_cores); @@ -7837,7 +8440,7 @@ static inline bool test_idle_cores(int cpu) /* * Scans the local SMT mask to see if the entire core is idle, and records this - * information in sd_llc_shared->has_idle_cores. + * information in sd_balance_shared->has_idle_cores. * * Since SMT siblings share all cache levels, inspecting this limited remote * state should be fairly cheap. @@ -7867,7 +8470,8 @@ unlock: /* * Scan the entire LLC domain for idle cores; this dynamically switches off if * there are no idle cores left in the system; tracked through - * sd_llc->shared->has_idle_cores and enabled through update_idle_core() above. + * sd_balance_shared->has_idle_cores and enabled through update_idle_core() + * above. */ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpus, int *idle_cpu) { @@ -7921,29 +8525,6 @@ static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int t return -1; } -#else /* !CONFIG_SCHED_SMT: */ - -static inline void set_idle_cores(int cpu, int val) -{ -} - -static inline bool test_idle_cores(int cpu) -{ - return false; -} - -static inline int select_idle_core(struct task_struct *p, int core, struct cpumask *cpus, int *idle_cpu) -{ - return __select_idle_cpu(core, p); -} - -static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target) -{ - return -1; -} - -#endif /* !CONFIG_SCHED_SMT */ - /* * Scan the LLC domain for idle CPUs; this is dynamically regulated by * comparing the average scan cost (tracked in sd->avg_scan_cost) against the @@ -7954,7 +8535,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_rq_mask); int i, cpu, idle_cpu = -1, nr = INT_MAX; - if (sched_feat(SIS_UTIL)) { + if (sched_feat(SIS_UTIL) && sd->shared) { /* * Increment because !--nr is the condition to stop scan. * @@ -8019,6 +8600,54 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool } /* + * Idle-capacity scan converts util_fits_cpu() outcomes into preference ranks, + * where lower values indicate a better fit - see select_idle_capacity(). + * + * A CPU that both fits the task and sits on a fully-idle SMT core is returned + * immediately and is never assigned one of these ranks. On !SMT every CPU is + * its own "core", so the early return covers all fits-and-idle cases and the + * core-tier ranks below become unreachable. + * + * Rank Val Tier Meaning + * ------------------------------ --- ------ --------------------------- + * ASYM_IDLE_UCLAMP_MISFIT -4 core Idle core; capacity fits + * util but uclamp_min misses. + * ASYM_IDLE_COMPLETE_MISFIT -3 core Idle core; capacity does + * not fit. Still beats every + * thread-tier rank: a busy + * sibling cuts effective + * capacity more than a + * misfit hurts a quiet core. + * ASYM_IDLE_THREAD_FITS -2 thread Busy SMT sibling; capacity + * fits util + uclamp. + * ASYM_IDLE_THREAD_UCLAMP_MISFIT -1 thread Busy SMT sibling; capacity + * fits but uclamp_min misses + * (native util_fits_cpu() + * return value). + * ASYM_IDLE_THREAD_MISFIT 0 thread Busy SMT sibling; capacity + * does not fit. + * + * ASYM_IDLE_CORE_BIAS (-3) is an offset, not a state. On an idle core, + * fits += ASYM_IDLE_CORE_BIAS rebases thread-tier ranks into the core tier: + * + * ASYM_IDLE_THREAD_UCLAMP_MISFIT (-1) + BIAS -> ASYM_IDLE_UCLAMP_MISFIT (-4) + * ASYM_IDLE_THREAD_MISFIT (0) + BIAS -> ASYM_IDLE_COMPLETE_MISFIT (-3) + * + * ASYM_IDLE_THREAD_FITS (-2) is never rebased because a fully-fitting idle-core + * candidate early-returns from select_idle_capacity(). + */ +enum asym_fits_state { + ASYM_IDLE_UCLAMP_MISFIT = -4, + ASYM_IDLE_COMPLETE_MISFIT, + ASYM_IDLE_THREAD_FITS, + ASYM_IDLE_THREAD_UCLAMP_MISFIT, + ASYM_IDLE_THREAD_MISFIT, + + /* util_fits_cpu() bias for idle core */ + ASYM_IDLE_CORE_BIAS = -3, +}; + +/* * Scan the asym_capacity domain for idle CPUs; pick the first idle one on which * the task fits. If no CPU is big enough, but there are idle ones, try to * maximize capacity. @@ -8026,10 +8655,17 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool static int select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) { + /* + * On !SMT systems, has_idle_core is always false and preferred_core + * is always true (CPU == core), so the SMT preference logic below + * collapses to the plain capacity scan. + */ + bool has_idle_core = sched_smt_active() && test_idle_cores(target); unsigned long task_util, util_min, util_max, best_cap = 0; - int fits, best_fits = 0; + int fits, best_fits = ASYM_IDLE_THREAD_MISFIT; int cpu, best_cpu = -1; struct cpumask *cpus; + int nr = INT_MAX; cpus = this_cpu_cpumask_var_ptr(select_rq_mask); cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr); @@ -8038,16 +8674,41 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) util_min = uclamp_eff_value(p, UCLAMP_MIN); util_max = uclamp_eff_value(p, UCLAMP_MAX); + if (sched_feat(SIS_UTIL) && sd->shared) { + /* + * Same nr_idle_scan hint as select_idle_cpu(), nr only limits + * the scan when not preferring an idle core. + */ + nr = READ_ONCE(sd->shared->nr_idle_scan) + 1; + /* overloaded domain is unlikely to have idle cpu/core */ + if (nr == 1) + return -1; + } + for_each_cpu_wrap(cpu, cpus, target) { + bool preferred_core = !has_idle_core || is_core_idle(cpu); unsigned long cpu_cap = capacity_of(cpu); + /* + * Stop when the nr_idle_scan is exhausted (mirrors + * select_idle_cpu() logic). + */ + if (!has_idle_core && --nr <= 0) + return best_cpu; + if (!choose_idle_cpu(cpu, p)) continue; fits = util_fits_cpu(task_util, util_min, util_max, cpu); - /* This CPU fits with all requirements */ - if (fits > 0) + /* + * Perfect fit: capacity satisfies util + uclamp and the CPU + * sits on a fully-idle SMT core, this is a !SMT system, or + * there is no idle core to find. + * Short-circuit the rank-based selection and return + * immediately. + */ + if (fits > 0 && preferred_core) return cpu; /* * Only the min performance hint (i.e. uclamp_min) doesn't fit. @@ -8055,9 +8716,33 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) */ else if (fits < 0) cpu_cap = get_actual_cpu_capacity(cpu); + /* + * fits > 0 implies we are not on a preferred core, but the util + * fits CPU capacity. Set fits to ASYM_IDLE_THREAD_FITS + * so the effective range becomes + * [ASYM_IDLE_THREAD_FITS, ASYM_IDLE_THREAD_MISFIT], where: + * ASYM_IDLE_THREAD_MISFIT - does not fit + * ASYM_IDLE_THREAD_UCLAMP_MISFIT - fits with the exception of UCLAMP_MIN + * ASYM_IDLE_THREAD_FITS - fits with the exception of preferred_core + */ + else if (fits > 0) + fits = ASYM_IDLE_THREAD_FITS; /* - * First, select CPU which fits better (-1 being better than 0). + * If we are on a preferred core, translate the range of fits + * of [ASYM_IDLE_THREAD_UCLAMP_MISFIT, ASYM_IDLE_THREAD_MISFIT] to + * [ASYM_IDLE_UCLAMP_MISFIT, ASYM_IDLE_COMPLETE_MISFIT]. + * This ensures that an idle core is always given priority over + * (partially) busy core. + * + * A fully fitting idle core would have returned early and hence + * fits > 0 for preferred_core need not be dealt with. + */ + if (preferred_core) + fits += ASYM_IDLE_CORE_BIAS; + + /* + * First, select CPU which fits better (lower is more preferred). * Then, select the one with best capacity at same level. */ if ((fits < best_fits) || @@ -8068,6 +8753,19 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) } } + /* + * A value in the [ASYM_IDLE_UCLAMP_MISFIT, ASYM_IDLE_COMPLETE_MISFIT] + * range means the chosen CPU is in a fully idle SMT core. Values above + * ASYM_IDLE_COMPLETE_MISFIT mean we never ranked such a CPU best. + * + * The asym-capacity wakeup path returns from select_idle_sibling() + * after this function and never runs select_idle_cpu(), so the usual + * select_idle_cpu() tail that clears idle cores must live here when the + * idle-core preference did not win. + */ + if (has_idle_core && best_fits > ASYM_IDLE_COMPLETE_MISFIT) + set_idle_cores(target, false); + return best_cpu; } @@ -8076,12 +8774,22 @@ static inline bool asym_fits_cpu(unsigned long util, unsigned long util_max, int cpu) { - if (sched_asym_cpucap_active()) + if (sched_asym_cpucap_active()) { /* * Return true only if the cpu fully fits the task requirements * which include the utilization and the performance hints. + * + * When SMT is active, also require that the core has no busy + * siblings. + * + * Note: gating on is_core_idle() also makes the early-bailout + * candidates in select_idle_sibling() (target, prev, + * recent_used_cpu) idle-core-aware on ASYM+SMT, which the + * NO_ASYM path does not do. */ - return (util_fits_cpu(util, util_min, util_max, cpu) > 0); + return (!sched_smt_active() || is_core_idle(cpu)) && + (util_fits_cpu(util, util_min, util_max, cpu) > 0); + } return true; } @@ -8260,25 +8968,32 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) static unsigned long cpu_util(int cpu, struct task_struct *p, int dst_cpu, int boost) { + bool add_task = p && task_cpu(p) != cpu && dst_cpu == cpu; + bool sub_task = p && task_cpu(p) == cpu && dst_cpu != cpu; struct cfs_rq *cfs_rq = &cpu_rq(cpu)->cfs; unsigned long util = READ_ONCE(cfs_rq->avg.util_avg); unsigned long runnable; - if (boost) { - runnable = READ_ONCE(cfs_rq->avg.runnable_avg); - util = max(util, runnable); - } - /* * If @dst_cpu is -1 or @p migrates from @cpu to @dst_cpu remove its * contribution. If @p migrates from another CPU to @cpu add its * contribution. In all the other cases @cpu is not impacted by the * migration so its util_avg is already correct. */ - if (p && task_cpu(p) == cpu && dst_cpu != cpu) - lsub_positive(&util, task_util(p)); - else if (p && task_cpu(p) != cpu && dst_cpu == cpu) + if (add_task) util += task_util(p); + else if (sub_task) + lsub_positive(&util, task_util(p)); + + if (boost) { + runnable = READ_ONCE(cfs_rq->avg.runnable_avg); + if (add_task) + runnable += READ_ONCE(p->se.avg.runnable_avg); + else if (sub_task) + lsub_positive(&runnable, + READ_ONCE(p->se.avg.runnable_avg)); + util = max(util, runnable); + } if (sched_feat(UTIL_EST)) { unsigned long util_est; @@ -9194,17 +9909,19 @@ preempt: resched_curr_lazy(rq); } -static struct task_struct *pick_task_fair(struct rq *rq, struct rq_flags *rf) +struct task_struct *pick_task_fair(struct rq *rq, struct rq_flags *rf) + __must_hold(__rq_lockp(rq)) { struct sched_entity *se; struct cfs_rq *cfs_rq; struct task_struct *p; bool throttled; + int new_tasks; again: cfs_rq = &rq->cfs; if (!cfs_rq->nr_queued) - return NULL; + goto idle; throttled = false; @@ -9213,8 +9930,6 @@ again: if (cfs_rq->curr && cfs_rq->curr->on_rq) update_curr(cfs_rq); - throttled |= check_cfs_rq_runtime(cfs_rq); - se = pick_next_entity(rq, cfs_rq, true); if (!se) goto again; @@ -9225,95 +9940,22 @@ again: if (unlikely(throttled)) task_throttle_setup_work(p); return p; -} - -static void __set_next_task_fair(struct rq *rq, struct task_struct *p, bool first); -static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first); - -struct task_struct * -pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) - __must_hold(__rq_lockp(rq)) -{ - struct sched_entity *se; - struct task_struct *p; - int new_tasks; - -again: - p = pick_task_fair(rq, rf); - if (!p) - goto idle; - se = &p->se; - -#ifdef CONFIG_FAIR_GROUP_SCHED - if (prev->sched_class != &fair_sched_class) - goto simple; - - __put_prev_set_next_dl_server(rq, prev, p); - - /* - * Because of the set_next_buddy() in dequeue_task_fair() it is rather - * likely that a next task is from the same cgroup as the current. - * - * Therefore attempt to avoid putting and setting the entire cgroup - * hierarchy, only change the part that actually changes. - * - * Since we haven't yet done put_prev_entity and if the selected task - * is a different task than we started out with, try and touch the - * least amount of cfs_rqs. - */ - if (prev != p) { - struct sched_entity *pse = &prev->se; - struct cfs_rq *cfs_rq; - - while (!(cfs_rq = is_same_group(se, pse))) { - int se_depth = se->depth; - int pse_depth = pse->depth; - - if (se_depth <= pse_depth) { - put_prev_entity(cfs_rq_of(pse), pse); - pse = parent_entity(pse); - } - if (se_depth >= pse_depth) { - set_next_entity(cfs_rq_of(se), se, true); - se = parent_entity(se); - } - } - - put_prev_entity(cfs_rq, pse); - set_next_entity(cfs_rq, se, true); - - __set_next_task_fair(rq, p, true); - } - - return p; - -simple: -#endif /* CONFIG_FAIR_GROUP_SCHED */ - put_prev_set_next_task(rq, prev, p); - return p; idle: - if (rf) { - new_tasks = sched_balance_newidle(rq, rf); - - /* - * Because sched_balance_newidle() 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. - */ - if (new_tasks < 0) - return RETRY_TASK; - - if (new_tasks > 0) - goto again; - } + if (sched_core_enabled(rq)) + return NULL; + new_tasks = sched_balance_newidle(rq, rf); + if (new_tasks < 0) + return RETRY_TASK; + if (new_tasks > 0) + goto again; return NULL; } static struct task_struct * fair_server_pick_task(struct sched_dl_entity *dl_se, struct rq_flags *rf) + __must_hold(__rq_lockp(dl_se->rq)) { return pick_task_fair(dl_se->rq, rf); } @@ -9334,10 +9976,33 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct t { struct sched_entity *se = &prev->se; struct cfs_rq *cfs_rq; + struct sched_entity *nse = NULL; - for_each_sched_entity(se) { +#ifdef CONFIG_FAIR_GROUP_SCHED + if (next && next->sched_class == &fair_sched_class) + nse = &next->se; +#endif + + while (se) { cfs_rq = cfs_rq_of(se); - put_prev_entity(cfs_rq, se); + if (!nse || cfs_rq->curr) + put_prev_entity(cfs_rq, se); +#ifdef CONFIG_FAIR_GROUP_SCHED + if (nse) { + if (is_same_group(se, nse)) + break; + + int d = nse->depth - se->depth; + if (d >= 0) { + /* nse has equal or greater depth, ascend */ + nse = parent_entity(nse); + /* if nse is the deeper, do not ascend se */ + if (d > 0) + continue; + } + } +#endif + se = parent_entity(se); } } @@ -9559,6 +10224,16 @@ enum group_type { */ group_imbalanced, /* + * There are tasks running on non-preferred LLC, possible to move + * them to their preferred LLC without creating too much imbalance. + * The priority of group_llc_balance is lower than that of + * group_overloaded and higher than that of all other group types. + * This is because group_llc_balance may exacerbate load imbalance. + * If the LLC balancing attempt fails, the nr_balance_failed + * mechanism will trigger other group types to rebalance the load. + */ + group_llc_balance, + /* * The CPU is overloaded and can't provide expected CPU cycles to all * tasks. */ @@ -9569,7 +10244,8 @@ enum migration_type { migrate_load = 0, migrate_util, migrate_task, - migrate_misfit + migrate_misfit, + migrate_llc_task }; #define LBF_ALL_PINNED 0x01 @@ -9577,6 +10253,7 @@ enum migration_type { #define LBF_DST_PINNED 0x04 #define LBF_SOME_PINNED 0x08 #define LBF_ACTIVE_LB 0x10 +#define LBF_LLC_PINNED 0x20 struct lb_env { struct sched_domain *sd; @@ -9586,6 +10263,7 @@ struct lb_env { int dst_cpu; struct rq *dst_rq; + bool dst_core_idle; struct cpumask *dst_grpmask; int new_dst_cpu; @@ -9722,7 +10400,7 @@ static inline int task_is_ineligible_on_dst_cpu(struct task_struct *p, int dest_ struct cfs_rq *dst_cfs_rq; #ifdef CONFIG_FAIR_GROUP_SCHED - dst_cfs_rq = task_group(p)->cfs_rq[dest_cpu]; + dst_cfs_rq = tg_cfs_rq(task_group(p), dest_cpu); #else dst_cfs_rq = &cpu_rq(dest_cpu)->cfs; #endif @@ -9733,6 +10411,298 @@ static inline int task_is_ineligible_on_dst_cpu(struct task_struct *p, int dest_ return 0; } +#ifdef CONFIG_SCHED_CACHE +/* + * The margin used when comparing LLC utilization with CPU capacity. + * It determines the LLC load level where active LLC aggregation is + * done. + * Derived from fits_capacity(). + * + * (default: ~50%, tunable via debugfs) + */ +static bool fits_llc_capacity(unsigned long util, unsigned long max) +{ + u32 aggr_pct = llc_overaggr_pct; + + /* + * For single core systems, raise the aggregation + * threshold to accommodate more tasks. + */ + if (cpu_smt_num_threads == 1) + aggr_pct = (aggr_pct * 3 / 2); + + return util * 100 < max * aggr_pct; +} + +/* + * The margin used when comparing utilization. + * is 'util1' noticeably greater than 'util2' + * Derived from capacity_greater(). + * Bias is in perentage. + */ +/* Allows dst util to be bigger than src util by up to bias percent */ +#define util_greater(util1, util2) \ + ((util1) * 100 > (util2) * (100 + llc_imb_pct)) + +static __maybe_unused bool get_llc_stats(int cpu, unsigned long *util, + unsigned long *cap) +{ + struct sched_domain_shared *sd_share; + + sd_share = rcu_dereference_all(per_cpu(sd_llc_shared, cpu)); + if (!sd_share) + return false; + + *util = READ_ONCE(sd_share->util_avg); + *cap = READ_ONCE(sd_share->capacity); + + return true; +} + +/* + * Decision matrix according to the LLC utilization. To + * decide whether we can do task aggregation across LLC. + * + * By default, 50% is the threshold for treating the LLC + * as busy. The reason for choosing 50% is to avoid saturation + * of SMT-2, and it is also a safe cutoff for other SMT-n + * platforms. SMT-1 has higher threshold because it is + * supposed to accommodate more tasks, see fits_llc_capacity(). + * + * 20% is the utilization imbalance percentage to decide + * if the preferred LLC is busier than the non-preferred LLC. + * 20 is a little higher than the LLC domain's imbalance_pct + * 17. The hysteresis is used to avoid task bouncing between the + * preferred LLC and the non-preferred LLC, and it will + * be turned into tunable debugfs. + * + * 1. moving towards the preferred LLC, dst is the preferred + * LLC, src is not. + * + * src \ dst 30% 40% 50% 60% + * 30% Y Y Y N + * 40% Y Y Y Y + * 50% Y Y G G + * 60% Y Y G G + * + * 2. moving out of the preferred LLC, src is the preferred + * LLC, dst is not: + * + * src \ dst 30% 40% 50% 60% + * 30% N N N N + * 40% N N N N + * 50% N N G G + * 60% Y N G G + * + * src : src_util + * dst : dst_util + * Y : Yes, migrate + * N : No, do not migrate + * G : let the Generic load balance to even the load. + * + * The intention is that if both LLCs are quite busy, cache aware + * load balance should not be performed, and generic load balance + * should take effect. However, if one is busy and the other is not, + * the preferred LLC capacity(50%) and imbalance criteria(20%) should + * be considered to determine whether LLC aggregation should be + * performed to bias the load towards the preferred LLC. + */ + +/* migration decision, 3 states are orthogonal. */ +enum llc_mig { + mig_forbid = 0, /* N: Don't migrate task, respect LLC preference */ + mig_llc, /* Y: Do LLC preference based migration */ + mig_unrestricted /* G: Don't restrict generic load balance migration */ +}; + +/* + * Check if task can be moved from the source LLC to the + * destination LLC without breaking cache aware preferrence. + * src_cpu and dst_cpu are arbitrary CPUs within the source + * and destination LLCs, respectively. + */ +static enum llc_mig can_migrate_llc(int src_cpu, int dst_cpu, + unsigned long tsk_util, + bool to_pref) +{ + unsigned long src_util, dst_util, src_cap, dst_cap; + + if (!get_llc_stats(src_cpu, &src_util, &src_cap) || + !get_llc_stats(dst_cpu, &dst_util, &dst_cap)) + return mig_unrestricted; + + src_util = src_util < tsk_util ? 0 : src_util - tsk_util; + dst_util = dst_util + tsk_util; + + if (!fits_llc_capacity(dst_util, dst_cap) && + !fits_llc_capacity(src_util, src_cap)) + return mig_unrestricted; + + if (to_pref) { + /* + * Don't migrate if we will get preferred LLC too + * heavily loaded and if the dest is much busier + * than the src, in which case migration will + * increase the imbalance too much. + */ + if (!fits_llc_capacity(dst_util, dst_cap) && + util_greater(dst_util, src_util)) + return mig_forbid; + } else { + /* + * Don't migrate if we will leave preferred LLC + * too idle, or if this migration leads to the + * non-preferred LLC falls within sysctl_aggr_imb percent + * of preferred LLC, leading to migration again + * back to preferred LLC. + */ + if (fits_llc_capacity(src_util, src_cap) || + !util_greater(src_util, dst_util)) + return mig_forbid; + } + return mig_llc; +} + +/* + * Check if task p can migrate from source LLC to + * destination LLC in terms of cache aware load balance. + */ +static enum llc_mig can_migrate_llc_task(int src_cpu, int dst_cpu, + struct task_struct *p) +{ + struct mm_struct *mm; + bool to_pref; + int cpu; + + mm = p->mm; + if (!mm) + return mig_unrestricted; + + cpu = READ_ONCE(mm->sc_stat.cpu); + if (cpu < 0 || cpus_share_cache(src_cpu, dst_cpu)) + return mig_unrestricted; + + /* skip cache aware load balance for too many threads */ + if (invalid_llc_nr(mm, p, dst_cpu) || + exceed_llc_capacity(mm, dst_cpu)) { + if (READ_ONCE(mm->sc_stat.cpu) != -1) + WRITE_ONCE(mm->sc_stat.cpu, -1); + return mig_unrestricted; + } + + if (cpus_share_cache(dst_cpu, cpu)) + to_pref = true; + else if (cpus_share_cache(src_cpu, cpu)) + to_pref = false; + else + return mig_unrestricted; + + return can_migrate_llc(src_cpu, dst_cpu, + task_util(p), to_pref); +} + +/* + * Check if active load balance breaks LLC locality in + * terms of cache aware load balance. The load level and + * imbalance do not warrant breaking LLC preference per + * the can_migrate_llc() policy. Here, the benefit of + * LLC locality outweighs the power efficiency gained from + * migrating the only runnable task away. + */ +static inline bool +alb_break_llc(struct lb_env *env) +{ + if (!sched_cache_enabled()) + return false; + + if (cpus_share_cache(env->src_cpu, env->dst_cpu)) + return false; + /* + * All tasks prefer to stay on their current CPU. + * Do not pull a task from its preferred CPU if: + * 1. It is the only task running and does not exceed + * imbalance allowance; OR + * 2. Migrating it away from its preferred LLC would violate + * the cache-aware scheduling policy. + */ + if (env->src_rq->nr_pref_llc_running && + env->src_rq->nr_pref_llc_running == env->src_rq->cfs.h_nr_runnable) { + unsigned long util = 0; + struct task_struct *cur; + + if (env->src_rq->nr_running <= 1) + return true; + + cur = rcu_dereference_all(env->src_rq->curr); + if (cur && cur->sched_class == &fair_sched_class) + util = task_util(cur); + + if (can_migrate_llc(env->src_cpu, env->dst_cpu, + util, false) == mig_forbid) + return true; + } + + return false; +} + +/* + * Check if migrating task p from env->src_cpu to + * env->dst_cpu breaks LLC localiy. + */ +static bool migrate_degrades_llc(struct task_struct *p, struct lb_env *env) +{ + if (!sched_cache_enabled()) + return false; + + if (task_has_sched_core(p)) + return false; + /* + * Skip over tasks that would degrade LLC locality; + * only when nr_balanced_failed is sufficiently high do we + * ignore this constraint. + * + * Threshold of cache_nice_tries is set to 1 higher + * than nr_balance_failed to avoid excessive task + * migration at the same time. + */ + if (env->sd->nr_balance_failed >= env->sd->cache_nice_tries + 1) + return false; + + /* + * We know the env->src_cpu has some tasks prefer to + * run on env->dst_cpu, skip the tasks do not prefer + * env->dst_cpu, and find the one that prefers. + */ + if (env->migration_type == migrate_llc_task && + READ_ONCE(p->preferred_llc) != llc_id(env->dst_cpu)) + return true; + + if (can_migrate_llc_task(env->src_cpu, + env->dst_cpu, p) != mig_forbid) + return false; + + return true; +} + +#else +static inline bool get_llc_stats(int cpu, unsigned long *util, + unsigned long *cap) +{ + return false; +} + +static inline bool +alb_break_llc(struct lb_env *env) +{ + return false; +} + +static inline bool +migrate_degrades_llc(struct task_struct *p, struct lb_env *env) +{ + return false; +} +#endif /* * can_migrate_task - may task p from runqueue rq be migrated to this_cpu? */ @@ -9829,10 +10799,29 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) return 1; degrades = migrate_degrades_locality(p, env); - if (!degrades) + if (!degrades) { + /* + * If the NUMA locality is not broken, + * further check if migration would hurt + * LLC locality. + */ + if (migrate_degrades_llc(p, env)) { + /* + * If regular load balancing fails to pull a task + * due to LLC locality, this is expected behavior + * and we set LBF_LLC_PINNED so we don't increase + * nr_balance_failed unecessarily. + */ + if (env->migration_type != migrate_llc_task) + env->flags |= LBF_LLC_PINNED; + + return 0; + } + hot = task_hot(p, env); - else + } else { hot = degrades > 0; + } if (!hot || env->sd->nr_balance_failed > env->sd->cache_nice_tries) { if (hot) @@ -9994,6 +10983,10 @@ static int detach_tasks(struct lb_env *env) env->imbalance = 0; break; + + case migrate_llc_task: + env->imbalance--; + break; } detach_task(p, env); @@ -10127,7 +11120,6 @@ static bool __update_blocked_fair(struct rq *rq, bool *done) { struct cfs_rq *cfs_rq, *pos; bool decayed = false; - int cpu = cpu_of(rq); /* * Iterates the task_group tree in a bottom up fashion, see @@ -10147,7 +11139,7 @@ static bool __update_blocked_fair(struct rq *rq, bool *done) } /* Propagate pending load changes to the parent, if any: */ - se = cfs_rq->tg->se[cpu]; + se = cfs_rq_se(cfs_rq); if (se && !skip_blocked_update(se)) update_load_avg(cfs_rq_of(se), se, UPDATE_TG); @@ -10173,8 +11165,7 @@ static bool __update_blocked_fair(struct rq *rq, bool *done) */ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq) { - struct rq *rq = rq_of(cfs_rq); - struct sched_entity *se = cfs_rq->tg->se[cpu_of(rq)]; + struct sched_entity *se = cfs_rq_se(cfs_rq); unsigned long now = jiffies; unsigned long load; @@ -10272,12 +11263,16 @@ struct sg_lb_stats { enum group_type group_type; unsigned int group_asym_packing; /* Tasks should be moved to preferred CPU */ unsigned int group_smt_balance; /* Task on busy SMT be moved */ + unsigned int group_llc_balance; /* Tasks should be moved to preferred LLC */ unsigned long group_misfit_task_load; /* A CPU has a task too big for its capacity */ unsigned int group_overutilized; /* At least one CPU is overutilized in the group */ #ifdef CONFIG_NUMA_BALANCING unsigned int nr_numa_running; unsigned int nr_preferred_running; #endif +#ifdef CONFIG_SCHED_CACHE + unsigned int nr_pref_dst_llc; +#endif }; /* @@ -10535,6 +11530,9 @@ group_type group_classify(unsigned int imbalance_pct, if (group_is_overloaded(imbalance_pct, sgs)) return group_overloaded; + if (sgs->group_llc_balance) + return group_llc_balance; + if (sg_imbalanced(group)) return group_imbalanced; @@ -10689,6 +11687,105 @@ sched_reduced_capacity(struct rq *rq, struct sched_domain *sd) return check_cpu_capacity(rq, sd); } +#ifdef CONFIG_SCHED_CACHE +/* + * Record the statistics for this scheduler group for later + * use. These values guide load balancing on aggregating tasks + * to a LLC. + */ +static void record_sg_llc_stats(struct lb_env *env, + struct sg_lb_stats *sgs, + struct sched_group *group) +{ + struct sched_domain_shared *sd_share; + int cpu; + + if (!sched_cache_enabled() || env->idle == CPU_NEWLY_IDLE) + return; + + /* Only care about sched domain spanning multiple LLCs */ + if (env->sd->child != rcu_dereference_all(per_cpu(sd_llc, env->dst_cpu))) + return; + + /* + * At this point we know this group spans a LLC domain. + * Record the statistic of this group in its corresponding + * shared LLC domain. + * Note: sd_share cannot be obtained via sd->child->shared, + * because the latter refers to the domain that covers the + * local group. Instead, sd_share should be located using + * the first CPU of the LLC group. + */ + cpu = cpumask_first(sched_group_span(group)); + sd_share = rcu_dereference_all(per_cpu(sd_llc_shared, cpu)); + if (!sd_share) + return; + + if (READ_ONCE(sd_share->util_avg) != sgs->group_util) + WRITE_ONCE(sd_share->util_avg, sgs->group_util); + + if (unlikely(READ_ONCE(sd_share->capacity) != sgs->group_capacity)) + WRITE_ONCE(sd_share->capacity, sgs->group_capacity); +} + +/* + * Do LLC balance on sched group that contains LLC, and have tasks preferring + * to run on LLC in idle dst_cpu. + */ +static inline bool llc_balance(struct lb_env *env, struct sg_lb_stats *sgs, + struct sched_group *group) +{ + if (!sched_cache_enabled()) + return false; + + if (env->sd->flags & SD_SHARE_LLC) + return false; + + /* + * Skip cache aware tagging if nr_balanced_failed is sufficiently high. + * Threshold of cache_nice_tries is set to 1 higher than nr_balance_failed + * to avoid excessive task migration at the same time. + */ + if (env->sd->nr_balance_failed >= env->sd->cache_nice_tries + 1) + return false; + + if (sgs->nr_pref_dst_llc && + can_migrate_llc(cpumask_first(sched_group_span(group)), + env->dst_cpu, 0, true) == mig_llc) + return true; + + return false; +} + +static bool update_llc_busiest(struct lb_env *env, + struct sg_lb_stats *busiest, + struct sg_lb_stats *sgs) +{ + /* + * There are more tasks that want to run on dst_cpu's LLC. + */ + return sgs->nr_pref_dst_llc > busiest->nr_pref_dst_llc; +} +#else +static inline void record_sg_llc_stats(struct lb_env *env, struct sg_lb_stats *sgs, + struct sched_group *group) +{ +} + +static inline bool llc_balance(struct lb_env *env, struct sg_lb_stats *sgs, + struct sched_group *group) +{ + return false; +} + +static bool update_llc_busiest(struct lb_env *env, + struct sg_lb_stats *busiest, + struct sg_lb_stats *sgs) +{ + return false; +} +#endif + /** * update_sg_lb_stats - Update sched_group's statistics for load balancing. * @env: The load balancing environment. @@ -10725,6 +11822,20 @@ static inline void update_sg_lb_stats(struct lb_env *env, if (cpu_overutilized(i)) sgs->group_overutilized = 1; +#ifdef CONFIG_SCHED_CACHE + if (sched_cache_enabled()) { + struct sched_domain *sd_tmp; + int dst_llc; + + dst_llc = llc_id(env->dst_cpu); + if (llc_id(i) != dst_llc) { + sd_tmp = rcu_dereference_all(rq->sd); + if (sd_tmp && (unsigned int)dst_llc < sd_tmp->llc_max) + sgs->nr_pref_dst_llc += sd_tmp->llc_counts[dst_llc]; + } + } +#endif + /* * No need to call idle_cpu() if nr_running is not 0 */ @@ -10765,17 +11876,24 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->group_weight = group->group_weight; - /* Check if dst CPU is idle and preferred to this group */ - if (!local_group && env->idle && sgs->sum_h_nr_running && - sched_group_asym(env, sgs, group)) - sgs->group_asym_packing = 1; + if (!local_group) { + /* Check if dst CPU is idle and preferred to this group */ + if (env->idle && sgs->sum_h_nr_running && + sched_group_asym(env, sgs, group)) + sgs->group_asym_packing = 1; + + /* Check for loaded SMT group to be balanced to dst CPU */ + if (smt_balance(env, sgs, group)) + sgs->group_smt_balance = 1; - /* Check for loaded SMT group to be balanced to dst CPU */ - if (!local_group && smt_balance(env, sgs, group)) - sgs->group_smt_balance = 1; + /* Check for tasks in this group can be moved to their preferred LLC */ + if (llc_balance(env, sgs, group)) + sgs->group_llc_balance = 1; + } sgs->group_type = group_classify(env->sd->imbalance_pct, group, sgs); + record_sg_llc_stats(env, sgs, group); /* Computing avg_load makes sense only when group is overloaded */ if (sgs->group_type == group_overloaded) sgs->avg_load = (sgs->group_load * SCHED_CAPACITY_SCALE) / @@ -10811,10 +11929,16 @@ static bool update_sd_pick_busiest(struct lb_env *env, * We can use max_capacity here as reduction in capacity on some * CPUs in the group should either be possible to resolve * internally or be covered by avg_load imbalance (eventually). + * + * When SMT is active, only pull a misfit to dst_cpu if it is on a + * fully idle core; otherwise the effective capacity of the core is + * reduced and we may not actually provide more capacity than the + * source. */ if ((env->sd->flags & SD_ASYM_CPUCAPACITY) && (sgs->group_type == group_misfit_task) && - (!capacity_greater(capacity_of(env->dst_cpu), sg->sgc->max_capacity) || + (!env->dst_core_idle || + !capacity_greater(capacity_of(env->dst_cpu), sg->sgc->max_capacity) || sds->local_stat.group_type != group_has_spare)) return false; @@ -10834,6 +11958,10 @@ static bool update_sd_pick_busiest(struct lb_env *env, /* Select the overloaded group with highest avg_load. */ return sgs->avg_load > busiest->avg_load; + case group_llc_balance: + /* Select the group with most tasks preferring dst LLC */ + return update_llc_busiest(env, busiest, sgs); + case group_imbalanced: /* * Select the 1st imbalanced group as we don't have any way to @@ -11096,6 +12224,7 @@ static bool update_pick_idlest(struct sched_group *idlest, return false; break; + case group_llc_balance: case group_imbalanced: case group_asym_packing: case group_smt_balance: @@ -11228,6 +12357,7 @@ sched_balance_find_dst_group(struct sched_domain *sd, struct task_struct *p, int return NULL; break; + case group_llc_balance: case group_imbalanced: case group_asym_packing: case group_smt_balance: @@ -11378,6 +12508,8 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd unsigned long sum_util = 0; bool sg_overloaded = 0, sg_overutilized = 0; + env->dst_core_idle = !sched_smt_active() || is_core_idle(env->dst_cpu); + do { struct sg_lb_stats *sgs = &tmp_sgs; int local_group; @@ -11480,6 +12612,15 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s return; } +#ifdef CONFIG_SCHED_CACHE + if (busiest->group_type == group_llc_balance) { + /* Move a task that prefer local LLC */ + env->migration_type = migrate_llc_task; + env->imbalance = 1; + return; + } +#endif + if (busiest->group_type == group_imbalanced) { /* * In the group_imb case we cannot rely on group-wide averages @@ -11726,7 +12867,8 @@ static struct sched_group *sched_balance_find_src_group(struct lb_env *env) * group's child domain. */ if (sds.prefer_sibling && local->group_type == group_has_spare && - sibling_imbalance(env, &sds, busiest, local) > 1) + (busiest->group_type == group_llc_balance || + sibling_imbalance(env, &sds, busiest, local) > 1)) goto force_balance; if (busiest->group_type != group_overloaded) { @@ -11785,7 +12927,10 @@ static struct rq *sched_balance_find_src_rq(struct lb_env *env, { struct rq *busiest = NULL, *rq; unsigned long busiest_util = 0, busiest_load = 0, busiest_capacity = 1; + unsigned int __maybe_unused busiest_pref_llc = 0; + struct sched_domain __maybe_unused *sd_tmp; unsigned int busiest_nr = 0; + int __maybe_unused dst_llc; int i; for_each_cpu_and(i, sched_group_span(group), env->cpus) { @@ -11913,6 +13058,23 @@ static struct rq *sched_balance_find_src_rq(struct lb_env *env, break; + case migrate_llc_task: +#ifdef CONFIG_SCHED_CACHE + sd_tmp = rcu_dereference_all(rq->sd); + dst_llc = llc_id(env->dst_cpu); + + if (sd_tmp && (unsigned)dst_llc < sd_tmp->llc_max) { + unsigned int this_pref_llc = + sd_tmp->llc_counts[dst_llc]; + + if (busiest_pref_llc < this_pref_llc) { + busiest_pref_llc = this_pref_llc; + busiest = rq; + } + } +#endif + break; + } } @@ -11964,6 +13126,9 @@ static int need_active_balance(struct lb_env *env) { struct sched_domain *sd = env->sd; + if (alb_break_llc(env)) + return 0; + if (asym_active_balance(env)) return 1; @@ -11983,7 +13148,8 @@ static int need_active_balance(struct lb_env *env) return 1; } - if (env->migration_type == migrate_misfit) + if (env->migration_type == migrate_misfit || + env->migration_type == migrate_llc_task) return 1; return 0; @@ -12028,7 +13194,9 @@ static int should_we_balance(struct lb_env *env) * balancing cores, but remember the first idle SMT CPU for * later consideration. Find CPU on an idle core first. */ - if (!(env->sd->flags & SD_SHARE_CPUCAPACITY) && !is_core_idle(cpu)) { + if (sched_smt_active() && + !(env->sd->flags & SD_SHARE_CPUCAPACITY) && + !is_core_idle(cpu)) { if (idle_smt == -1) idle_smt = cpu; /* @@ -12036,9 +13204,7 @@ static int should_we_balance(struct lb_env *env) * idle has been found, then its not needed to check other * SMT siblings for idleness: */ -#ifdef CONFIG_SCHED_SMT cpumask_andnot(swb_cpus, swb_cpus, cpu_smt_mask(cpu)); -#endif continue; } @@ -12076,6 +13242,8 @@ static void update_lb_imbalance_stat(struct lb_env *env, struct sched_domain *sd case migrate_misfit: __schedstat_add(sd->lb_imbalance_misfit[idle], env->imbalance); break; + case migrate_llc_task: + break; } } @@ -12279,9 +13447,16 @@ more_balance: * * Similarly for migration_misfit which is not related to * load/util migration, don't pollute nr_balance_failed. + * + * The same for cache aware scheduling's allowance for + * load imbalance. If regular load balance does not + * migrate task due to LLC locality, it is a expected + * behavior and don't pollute nr_balance_failed. + * See can_migrate_task(). */ if (idle != CPU_NEWLY_IDLE && - env.migration_type != migrate_misfit) + env.migration_type != migrate_misfit && + !(env.flags & LBF_LLC_PINNED)) sd->nr_balance_failed++; if (need_active_balance(&env)) { @@ -12785,8 +13960,6 @@ static void nohz_balancer_kick(struct rq *rq) goto out; } - rcu_read_lock(); - sd = rcu_dereference_all(rq->sd); if (sd) { /* @@ -12794,8 +13967,8 @@ static void nohz_balancer_kick(struct rq *rq) * capacity, kick the ILB to see if there's a better CPU to run on: */ if (rq->cfs.h_nr_runnable >= 1 && check_cpu_capacity(rq, sd)) { - flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; - goto unlock; + flags |= NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; + goto out; } } @@ -12811,8 +13984,8 @@ static void nohz_balancer_kick(struct rq *rq) */ for_each_cpu_and(i, sched_domain_span(sd), nohz.idle_cpus_mask) { if (sched_asym(sd, i, cpu)) { - flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; - goto unlock; + flags |= NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; + goto out; } } } @@ -12823,10 +13996,8 @@ static void nohz_balancer_kick(struct rq *rq) * When ASYM_CPUCAPACITY; see if there's a higher capacity CPU * to run the misfit task on. */ - if (check_misfit_status(rq)) { - flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; - goto unlock; - } + if (check_misfit_status(rq)) + flags |= NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; /* * For asymmetric systems, we do not want to nicely balance @@ -12835,10 +14006,10 @@ static void nohz_balancer_kick(struct rq *rq) * * Skip the LLC logic because it's not relevant in that case. */ - goto unlock; + goto out; } - sds = rcu_dereference_all(per_cpu(sd_llc_shared, cpu)); + sds = rcu_dereference_all(per_cpu(sd_balance_shared, cpu)); if (sds) { /* * If there is an imbalance between LLC domains (IOW we could @@ -12850,13 +14021,9 @@ static void nohz_balancer_kick(struct rq *rq) * like this LLC domain has tasks we could move. */ nr_busy = atomic_read(&sds->nr_busy_cpus); - if (nr_busy > 1) { - flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; - goto unlock; - } + if (nr_busy > 1) + flags |= NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; } -unlock: - rcu_read_unlock(); out: if (READ_ONCE(nohz.needs_update)) flags |= NOHZ_NEXT_KICK; @@ -12868,17 +14035,17 @@ out: static void set_cpu_sd_state_busy(int cpu) { struct sched_domain *sd; - - rcu_read_lock(); sd = rcu_dereference_all(per_cpu(sd_llc, cpu)); - if (!sd || !sd->nohz_idle) - goto unlock; + /* + * sd->nohz_idle only pairs with nr_busy_cpus on sd->shared; if this + * domain has no shared object there is nothing to clear or account. + */ + if (!sd || !sd->shared || !sd->nohz_idle) + return; sd->nohz_idle = 0; atomic_inc(&sd->shared->nr_busy_cpus); -unlock: - rcu_read_unlock(); } void nohz_balance_exit_idle(struct rq *rq) @@ -12897,17 +14064,14 @@ void nohz_balance_exit_idle(struct rq *rq) static void set_cpu_sd_state_idle(int cpu) { struct sched_domain *sd; - - rcu_read_lock(); sd = rcu_dereference_all(per_cpu(sd_llc, cpu)); - if (!sd || sd->nohz_idle) - goto unlock; + /* See set_cpu_sd_state_busy(): nohz_idle is only used with sd->shared. */ + if (!sd || !sd->shared || sd->nohz_idle) + return; sd->nohz_idle = 1; atomic_dec(&sd->shared->nr_busy_cpus); -unlock: - rcu_read_unlock(); } /* @@ -13666,7 +14830,7 @@ static int task_is_throttled_fair(struct task_struct *p, int cpu) struct cfs_rq *cfs_rq; #ifdef CONFIG_FAIR_GROUP_SCHED - cfs_rq = task_group(p)->cfs_rq[cpu]; + cfs_rq = tg_cfs_rq(task_group(p), cpu); #else cfs_rq = &cpu_rq(cpu)->cfs; #endif @@ -13686,8 +14850,8 @@ static inline void task_tick_core(struct rq *rq, struct task_struct *curr) {} */ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) { - struct cfs_rq *cfs_rq; struct sched_entity *se = &curr->se; + struct cfs_rq *cfs_rq; for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); @@ -13700,6 +14864,8 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) if (static_branch_unlikely(&sched_numa_balancing)) task_tick_numa(rq, curr); + task_tick_cache(rq, curr); + update_misfit_status(curr, rq); check_update_overutilized_status(task_rq(curr)); @@ -13858,9 +15024,33 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p) } } -static void __set_next_task_fair(struct rq *rq, struct task_struct *p, bool first) +/* + * Account for a task changing its policy or group. + * + * This routine is mostly called to set cfs_rq->curr field when a task + * migrates between groups/classes. + */ +static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first) { struct sched_entity *se = &p->se; + bool throttled = false; + + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + if (IS_ENABLED(CONFIG_FAIR_GROUP_SCHED) && + first && cfs_rq->curr) + break; + + set_next_entity(cfs_rq, se, first); + /* ensure bandwidth has been allocated on our new cfs_rq */ + throttled |= account_cfs_rq_runtime(cfs_rq, 0); + } + + if (throttled) + task_throttle_setup_work(p); + + se = &p->se; if (task_on_rq_queued(p)) { /* @@ -13881,27 +15071,6 @@ static void __set_next_task_fair(struct rq *rq, struct task_struct *p, bool firs sched_fair_update_stop_tick(rq, p); } -/* - * Account for a task changing its policy or group. - * - * This routine is mostly called to set cfs_rq->curr field when a task - * migrates between groups/classes. - */ -static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first) -{ - struct sched_entity *se = &p->se; - - for_each_sched_entity(se) { - struct cfs_rq *cfs_rq = cfs_rq_of(se); - - set_next_entity(cfs_rq, se, first); - /* ensure bandwidth has been allocated on our new cfs_rq */ - account_cfs_rq_runtime(cfs_rq, 0); - } - - __set_next_task_fair(rq, p, first); -} - void init_cfs_rq(struct cfs_rq *cfs_rq) { cfs_rq->tasks_timeline = RB_ROOT_CACHED; @@ -13929,56 +15098,38 @@ static void task_change_group_fair(struct task_struct *p) void free_fair_sched_group(struct task_group *tg) { - int i; - - for_each_possible_cpu(i) { - if (tg->cfs_rq) - kfree(tg->cfs_rq[i]); - if (tg->se) - kfree(tg->se[i]); - } - - kfree(tg->cfs_rq); - kfree(tg->se); + free_percpu(tg->cfs_rq); } int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) { + struct cfs_tg_state __percpu *state; struct sched_entity *se; struct cfs_rq *cfs_rq; int i; - tg->cfs_rq = kzalloc_objs(cfs_rq, nr_cpu_ids); - if (!tg->cfs_rq) - goto err; - tg->se = kzalloc_objs(se, nr_cpu_ids); - if (!tg->se) + state = alloc_percpu_gfp(struct cfs_tg_state, GFP_KERNEL); + if (!state) goto err; + tg->cfs_rq = &state->cfs_rq; tg->shares = NICE_0_LOAD; init_cfs_bandwidth(tg_cfs_bandwidth(tg), tg_cfs_bandwidth(parent)); for_each_possible_cpu(i) { - cfs_rq = kzalloc_node(sizeof(struct cfs_rq), - GFP_KERNEL, cpu_to_node(i)); + cfs_rq = tg_cfs_rq(tg, i); if (!cfs_rq) goto err; - se = kzalloc_node(sizeof(struct sched_entity_stats), - GFP_KERNEL, cpu_to_node(i)); - if (!se) - goto err_free_rq; - + se = tg_se(tg, i); init_cfs_rq(cfs_rq); - init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]); + init_tg_cfs_entry(tg, cfs_rq, se, i, tg_se(parent, i)); init_entity_runnable_average(se); } return 1; -err_free_rq: - kfree(cfs_rq); err: return 0; } @@ -13992,7 +15143,7 @@ void online_fair_sched_group(struct task_group *tg) for_each_possible_cpu(i) { rq = cpu_rq(i); - se = tg->se[i]; + se = tg_se(tg, i); rq_lock_irq(rq, &rf); update_rq_clock(rq); attach_entity_cfs_rq(se); @@ -14008,8 +15159,8 @@ void unregister_fair_sched_group(struct task_group *tg) destroy_cfs_bandwidth(tg_cfs_bandwidth(tg)); for_each_possible_cpu(cpu) { - struct cfs_rq *cfs_rq = tg->cfs_rq[cpu]; - struct sched_entity *se = tg->se[cpu]; + struct cfs_rq *cfs_rq = tg_cfs_rq(tg, cpu); + struct sched_entity *se = tg_se(tg, cpu); struct rq *rq = cpu_rq(cpu); if (se) { @@ -14045,9 +15196,6 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, cfs_rq->rq = rq; init_cfs_rq_runtime(cfs_rq); - tg->cfs_rq[cpu] = cfs_rq; - tg->se[cpu] = se; - /* se could be NULL for root_task_group */ if (!se) return; @@ -14077,7 +15225,7 @@ static int __sched_group_set_shares(struct task_group *tg, unsigned long shares) /* * We can't change the weight of the root cgroup. */ - if (!tg->se[0]) + if (is_root_task_group(tg)) return -EINVAL; shares = clamp(shares, scale_load(MIN_SHARES), scale_load(MAX_SHARES)); @@ -14088,7 +15236,7 @@ static int __sched_group_set_shares(struct task_group *tg, unsigned long shares) tg->shares = shares; for_each_possible_cpu(i) { struct rq *rq = cpu_rq(i); - struct sched_entity *se = tg->se[i]; + struct sched_entity *se = tg_se(tg, i); struct rq_flags rf; /* Propagate contribution to hierarchy */ @@ -14139,8 +15287,8 @@ int sched_group_set_idle(struct task_group *tg, long idle) for_each_possible_cpu(i) { struct rq *rq = cpu_rq(i); - struct sched_entity *se = tg->se[i]; - struct cfs_rq *grp_cfs_rq = tg->cfs_rq[i]; + struct sched_entity *se = tg_se(tg, i); + struct cfs_rq *grp_cfs_rq = tg_cfs_rq(tg, i); bool was_idle = cfs_rq_is_idle(grp_cfs_rq); long idle_task_delta; struct rq_flags rf; @@ -14213,7 +15361,6 @@ DEFINE_SCHED_CLASS(fair) = { .wakeup_preempt = wakeup_preempt_fair, .pick_task = pick_task_fair, - .pick_next_task = pick_next_task_fair, .put_prev_task = put_prev_task_fair, .set_next_task = set_next_task_fair, diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 84c4fe3abd74..8f0dee8fc475 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -110,8 +110,16 @@ SCHED_FEAT(WARN_DOUBLE_CLOCK, false) * rq lock and possibly create a large contention, sending an * IPI to that CPU and let that CPU push the RT task to where * it should go may be a better scenario. + * + * This is best for PREEMPT_RT, but for non-RT it can cause issues + * when preemption is disabled for long periods of time. Have + * it only default enabled for PREEMPT_RT. */ +# ifdef CONFIG_PREEMPT_RT SCHED_FEAT(RT_PUSH_IPI, true) +# else +SCHED_FEAT(RT_PUSH_IPI, false) +# endif #endif SCHED_FEAT(RT_RUNTIME_SHARE, false) diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index a83be0c834dd..052435f4d3e3 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -280,6 +280,14 @@ static void do_idle(void) int cpu = smp_processor_id(); bool got_tick = false; + if (cpu_is_offline(cpu)) { + local_irq_disable(); + /* All per-CPU kernel threads should be done by now. */ + WARN_ON_ONCE(need_resched()); + cpuhp_report_idle_dead(); + arch_cpu_idle_dead(); + } + /* * Check if we need to update blocked load */ @@ -331,11 +339,6 @@ static void do_idle(void) */ local_irq_disable(); - if (cpu_is_offline(cpu)) { - cpuhp_report_idle_dead(); - arch_cpu_idle_dead(); - } - arch_cpu_idle_enter(); rcu_nocb_flush_deferred_wakeup(); @@ -462,7 +465,7 @@ select_task_rq_idle(struct task_struct *p, int cpu, int flags) } static int -balance_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +balance_idle(struct rq *rq, struct rq_flags *rf) { return WARN_ON_ONCE(1); } diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 226a6329f3e9..cb957b8f1946 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -164,8 +164,26 @@ | MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK \ | MEMBARRIER_CMD_GET_REGISTRATIONS) +/* + * Scoped guard for memory barriers on entry and exit. + * Matches memory barriers before & after rq->curr modification in scheduler. + */ +DEFINE_LOCK_GUARD_0(mb, smp_mb(), smp_mb()) static DEFINE_MUTEX(membarrier_ipi_mutex); +static DEFINE_PER_CPU(struct mutex, membarrier_cpu_mutexes); + #define SERIALIZE_IPI() guard(mutex)(&membarrier_ipi_mutex) +#define SERIALIZE_IPI_CPU(cpu_id) guard(mutex)(&per_cpu(membarrier_cpu_mutexes, cpu_id)) + +static int __init membarrier_init(void) +{ + int i; + + for_each_possible_cpu(i) + mutex_init(&per_cpu(membarrier_cpu_mutexes, i)); + return 0; +} +core_initcall(membarrier_init); static void ipi_mb(void *info) { @@ -258,23 +276,19 @@ void membarrier_update_current_mm(struct mm_struct *next_mm) static int membarrier_global_expedited(void) { + cpumask_var_t __free(free_cpumask_var) tmpmask = CPUMASK_VAR_NULL; int cpu; - cpumask_var_t tmpmask; if (num_online_cpus() == 1) return 0; - /* - * Matches memory barriers after rq->curr modification in - * scheduler. - */ - smp_mb(); /* system call entry is not a mb. */ - if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) return -ENOMEM; + guard(mb)(); SERIALIZE_IPI(); - cpus_read_lock(); + guard(cpus_read_lock)(); + rcu_read_lock(); for_each_online_cpu(cpu) { struct task_struct *p; @@ -310,21 +324,11 @@ static int membarrier_global_expedited(void) smp_call_function_many(tmpmask, ipi_mb, NULL, 1); preempt_enable(); - free_cpumask_var(tmpmask); - cpus_read_unlock(); - - /* - * Memory barrier on the caller thread _after_ we finished - * waiting for the last IPI. Matches memory barriers before - * rq->curr modification in scheduler. - */ - smp_mb(); /* exit from system call is not a mb */ return 0; } static int membarrier_private_expedited(int flags, int cpu_id) { - cpumask_var_t tmpmask; struct mm_struct *mm = current->mm; smp_call_func_t ipi_func = ipi_mb; @@ -361,30 +365,45 @@ static int membarrier_private_expedited(int flags, int cpu_id) * On RISC-V, this barrier pairing is also needed for the * SYNC_CORE command when switching between processes, cf. * the inline comments in membarrier_arch_switch_mm(). + * + * Memory barrier on the caller thread _after_ we finished + * waiting for the last IPI. Matches memory barriers before + * rq->curr modification in scheduler. */ - smp_mb(); /* system call entry is not a mb. */ - - if (cpu_id < 0 && !zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) - return -ENOMEM; - - SERIALIZE_IPI(); - cpus_read_lock(); - + guard(mb)(); if (cpu_id >= 0) { + if (cpu_id >= nr_cpu_ids || !cpu_possible(cpu_id)) + return 0; + + SERIALIZE_IPI_CPU(cpu_id); + guard(cpus_read_lock)(); struct task_struct *p; - if (cpu_id >= nr_cpu_ids || !cpu_online(cpu_id)) - goto out; + if (!cpu_online(cpu_id)) + return 0; + rcu_read_lock(); p = rcu_dereference(cpu_rq(cpu_id)->curr); if (!p || p->mm != mm) { rcu_read_unlock(); - goto out; + return 0; } rcu_read_unlock(); + /* + * smp_call_function_single() will call ipi_func() if cpu_id + * is the calling CPU. + */ + smp_call_function_single(cpu_id, ipi_func, NULL, 1); } else { + cpumask_var_t __free(free_cpumask_var) tmpmask = CPUMASK_VAR_NULL; int cpu; + if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) + return -ENOMEM; + + SERIALIZE_IPI(); + guard(cpus_read_lock)(); + rcu_read_lock(); for_each_online_cpu(cpu) { struct task_struct *p; @@ -394,15 +413,6 @@ static int membarrier_private_expedited(int flags, int cpu_id) __cpumask_set_cpu(cpu, tmpmask); } rcu_read_unlock(); - } - - if (cpu_id >= 0) { - /* - * smp_call_function_single() will call ipi_func() if cpu_id - * is the calling CPU. - */ - smp_call_function_single(cpu_id, ipi_func, NULL, 1); - } else { /* * For regular membarrier, we can save a few cycles by * skipping the current cpu -- we're about to do smp_mb() @@ -429,18 +439,6 @@ static int membarrier_private_expedited(int flags, int cpu_id) } } -out: - if (cpu_id < 0) - free_cpumask_var(tmpmask); - cpus_read_unlock(); - - /* - * Memory barrier on the caller thread _after_ we finished - * waiting for the last IPI. Matches memory barriers before - * rq->curr modification in scheduler. - */ - smp_mb(); /* exit from system call is not a mb */ - return 0; } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 4ee8faf01441..e474c31d8fe6 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -19,9 +19,9 @@ int sysctl_sched_rt_period = 1000000; /* * part of the period that we allow rt tasks to run in us. - * default: 0.95s + * default: 1s */ -int sysctl_sched_rt_runtime = 950000; +int sysctl_sched_rt_runtime = 1000000; #ifdef CONFIG_SYSCTL static int sysctl_sched_rr_timeslice = (MSEC_PER_SEC * RR_TIMESLICE) / HZ; @@ -1596,8 +1596,14 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) resched_curr(rq); } -static int balance_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf) +static int balance_rt(struct rq *rq, struct rq_flags *rf) { + /* + * Note, rq->donor may change during rq lock drops, + * so don't re-use p across lock drops + */ + struct task_struct *p = rq->donor; + if (!on_rt_rq(&p->rt) && need_pull_rt_task(rq, p)) { /* * This is OK, because current is on_cpu, which avoids it being diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 9f63b15d309d..c7c2dea65edd 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -421,6 +421,10 @@ extern void ext_server_init(struct rq *rq); extern void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq); extern int dl_server_apply_params(struct sched_dl_entity *dl_se, u64 runtime, u64 period, bool init); +extern int dl_server_attach_bw(struct sched_dl_entity *dl_se); +extern void dl_server_detach_bw(struct sched_dl_entity *dl_se); +extern int dl_server_swap_bw(struct sched_dl_entity *detach_se, + struct sched_dl_entity *attach_se); static inline bool dl_server_active(struct sched_dl_entity *dl_se) { @@ -480,10 +484,8 @@ struct task_group { #endif #ifdef CONFIG_FAIR_GROUP_SCHED - /* schedulable entities of this group on each CPU */ - struct sched_entity **se; /* runqueue "owned" by this group on each CPU */ - struct cfs_rq **cfs_rq; + struct cfs_rq __percpu *cfs_rq; unsigned long shares; /* * load_avg can be heavily contended at clock tick time, so put @@ -889,6 +891,7 @@ struct dl_rq { bool overloaded; + struct sched_dl_entity *curr; /* * Tasks on this rq that can be pushed away. They are kept in * an rb-tree, ordered by tasks' deadlines, with caching @@ -929,7 +932,8 @@ struct dl_rq { }; #ifdef CONFIG_FAIR_GROUP_SCHED - +/* Check whether a task group is root tg */ +#define is_root_task_group(tg) ((tg) == &root_task_group) /* An entity is a task if it doesn't "own" a runqueue */ #define entity_is_task(se) (!se->my_q) @@ -1187,6 +1191,12 @@ struct rq { struct scx_rq scx; struct sched_dl_entity ext_server; #endif +#ifdef CONFIG_SCHED_CACHE + raw_spinlock_t cpu_epoch_lock ____cacheline_aligned; + u64 cpu_runtime; + unsigned long cpu_epoch; + unsigned long cpu_epoch_next; +#endif struct sched_dl_entity fair_server; @@ -1199,6 +1209,12 @@ struct rq { #ifdef CONFIG_NUMA_BALANCING unsigned int numa_migrate_on; #endif + +#ifdef CONFIG_SCHED_CACHE + unsigned int nr_pref_llc_running; + unsigned int nr_llc_running; +#endif + /* * This is part of a global counter where only the total sum * over all CPUs matters. A task can increase this counter on @@ -1546,6 +1562,14 @@ extern void sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags); extern void sched_core_get(void); extern void sched_core_put(void); +static inline bool task_has_sched_core(struct task_struct *p) +{ + if (sched_core_disabled()) + return false; + + return !!p->core_cookie; +} + #else /* !CONFIG_SCHED_CORE: */ static inline bool sched_core_enabled(struct rq *rq) @@ -1586,6 +1610,11 @@ static inline bool sched_group_cookie_match(struct rq *rq, return true; } +static inline bool task_has_sched_core(struct task_struct *p) +{ + return false; +} + #endif /* !CONFIG_SCHED_CORE */ #ifdef CONFIG_RT_GROUP_SCHED @@ -1667,21 +1696,15 @@ do { \ flags = _raw_spin_rq_lock_irqsave(rq); \ } while (0) -#ifdef CONFIG_SCHED_SMT extern void __update_idle_core(struct rq *rq); static inline void update_idle_core(struct rq *rq) { - if (static_branch_unlikely(&sched_smt_present)) + if (sched_smt_active()) __update_idle_core(rq); } -#else /* !CONFIG_SCHED_SMT: */ -static inline void update_idle_core(struct rq *rq) { } -#endif /* !CONFIG_SCHED_SMT */ - #ifdef CONFIG_FAIR_GROUP_SCHED - static inline struct task_struct *task_of(struct sched_entity *se) { WARN_ON_ONCE(!entity_is_task(se)); @@ -2082,6 +2105,8 @@ init_numa_balancing(u64 clone_flags, struct task_struct *p) #endif /* !CONFIG_NUMA_BALANCING */ +int task_llc(const struct task_struct *p); + static inline void queue_balance_callback(struct rq *rq, struct balance_callback *head, @@ -2171,6 +2196,7 @@ DECLARE_PER_CPU(int, sd_llc_size); DECLARE_PER_CPU(int, sd_llc_id); DECLARE_PER_CPU(int, sd_share_id); DECLARE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared); +DECLARE_PER_CPU(struct sched_domain_shared __rcu *, sd_balance_shared); DECLARE_PER_CPU(struct sched_domain __rcu *, sd_numa); DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing); DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity); @@ -2267,6 +2293,46 @@ static inline struct task_group *task_group(struct task_struct *p) return p->sched_task_group; } +#ifdef CONFIG_FAIR_GROUP_SCHED +/* + * Defined here to be available before stats.h is included, since + * stats.h has dependencies on things defined later in this file. + */ +struct cfs_tg_state { + struct cfs_rq cfs_rq; + struct sched_entity se; + struct sched_statistics stats; +} __no_randomize_layout; + +/* Access a specific CPU's cfs_rq from a task group */ +static inline struct cfs_rq *tg_cfs_rq(struct task_group *tg, int cpu) +{ + return per_cpu_ptr(tg->cfs_rq, cpu); +} + +static inline struct sched_entity *tg_se(struct task_group *tg, int cpu) +{ + struct cfs_tg_state *state; + + if (is_root_task_group(tg)) + return NULL; + + state = container_of(tg_cfs_rq(tg, cpu), struct cfs_tg_state, cfs_rq); + return &state->se; +} + +static inline struct sched_entity *cfs_rq_se(struct cfs_rq *cfs_rq) +{ + struct cfs_tg_state *state; + + if (is_root_task_group(cfs_rq->tg)) + return NULL; + + state = container_of(cfs_rq, struct cfs_tg_state, cfs_rq); + return &state->se; +} +#endif + /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */ static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { @@ -2275,10 +2341,10 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu) #endif #ifdef CONFIG_FAIR_GROUP_SCHED - set_task_rq_fair(&p->se, p->se.cfs_rq, tg->cfs_rq[cpu]); - p->se.cfs_rq = tg->cfs_rq[cpu]; - p->se.parent = tg->se[cpu]; - p->se.depth = tg->se[cpu] ? tg->se[cpu]->depth + 1 : 0; + set_task_rq_fair(&p->se, p->se.cfs_rq, tg_cfs_rq(tg, cpu)); + p->se.cfs_rq = tg_cfs_rq(tg, cpu); + p->se.parent = tg_se(tg, cpu); + p->se.depth = p->se.parent ? p->se.parent->depth + 1 : 0; #endif #ifdef CONFIG_RT_GROUP_SCHED @@ -2561,23 +2627,12 @@ struct sched_class { /* * schedule/pick_next_task/prev_balance: rq->lock */ - int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf); + int (*balance)(struct rq *rq, struct rq_flags *rf); /* * schedule/pick_next_task: rq->lock */ struct task_struct *(*pick_task)(struct rq *rq, struct rq_flags *rf); - /* - * Optional! When implemented pick_next_task() should be equivalent to: - * - * next = pick_task(); - * if (next) { - * put_prev_task(prev); - * set_next_task_first(next); - * } - */ - struct task_struct *(*pick_next_task)(struct rq *rq, struct task_struct *prev, - struct rq_flags *rf); /* * sched_change: @@ -2801,8 +2856,7 @@ static inline bool sched_fair_runnable(struct rq *rq) return rq->cfs.nr_queued > 0; } -extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev, - struct rq_flags *rf); +extern struct task_struct *pick_task_fair(struct rq *rq, struct rq_flags *rf); extern struct task_struct *pick_task_idle(struct rq *rq, struct rq_flags *rf); #define SCA_CHECK 0x01 @@ -4037,6 +4091,29 @@ static inline void mm_cid_switch_to(struct task_struct *prev, struct task_struct static inline void mm_cid_switch_to(struct task_struct *prev, struct task_struct *next) { } #endif /* !CONFIG_SCHED_MM_CID */ +#ifdef CONFIG_SCHED_CACHE +DECLARE_STATIC_KEY_FALSE(sched_cache_present); +DECLARE_STATIC_KEY_FALSE(sched_cache_active); +extern int sysctl_sched_cache_user; +extern unsigned int llc_aggr_tolerance; +extern unsigned int llc_epoch_period; +extern unsigned int llc_epoch_affinity_timeout; +extern unsigned int llc_imb_pct; +extern unsigned int llc_overaggr_pct; + +static inline bool sched_cache_enabled(void) +{ + return static_branch_unlikely(&sched_cache_active); +} + +extern void sched_cache_active_set(void); + +#endif + +void sched_domains_free_llc_id(int cpu); + +extern void init_sched_mm(struct task_struct *p); + extern u64 avg_vruntime(struct cfs_rq *cfs_rq); extern int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se); static inline diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index a612cf253c87..ebe0a7765f98 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -89,19 +89,12 @@ static inline void rq_sched_info_depart (struct rq *rq, unsigned long long delt #endif /* CONFIG_SCHEDSTATS */ -#ifdef CONFIG_FAIR_GROUP_SCHED -struct sched_entity_stats { - struct sched_entity se; - struct sched_statistics stats; -} __no_randomize_layout; -#endif - static inline struct sched_statistics * __schedstats_from_se(struct sched_entity *se) { #ifdef CONFIG_FAIR_GROUP_SCHED if (!entity_is_task(se)) - return &container_of(se, struct sched_entity_stats, se)->stats; + return &container_of(se, struct cfs_tg_state, se)->stats; #endif return &task_of(se)->stats; } diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index f95798baddeb..c909ca0d8c87 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -16,7 +16,7 @@ select_task_rq_stop(struct task_struct *p, int cpu, int flags) } static int -balance_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +balance_stop(struct rq *rq, struct rq_flags *rf) { return sched_stop_runnable(rq); } diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 5847b83d9d55..622e2e01974c 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -19,8 +19,10 @@ void sched_domains_mutex_unlock(void) } /* Protected by sched_domains_mutex: */ +static cpumask_var_t sched_domains_llc_id_allocmask; static cpumask_var_t sched_domains_tmpmask; static cpumask_var_t sched_domains_tmpmask2; +int max_lid; static int __init sched_debug_setup(char *str) { @@ -621,6 +623,12 @@ static void free_sched_groups(struct sched_group *sg, int free_sgc) } while (sg != first); } +static void free_sched_domain_shared(struct sched_domain_shared *sds) +{ + if (sds && atomic_dec_and_test(&sds->ref)) + kfree(sds); +} + static void destroy_sched_domain(struct sched_domain *sd) { /* @@ -629,9 +637,12 @@ static void destroy_sched_domain(struct sched_domain *sd) * dropping group/capacity references, freeing where none remain. */ free_sched_groups(sd->groups, 1); + free_sched_domain_shared(sd->shared); - if (sd->shared && atomic_dec_and_test(&sd->shared->ref)) - kfree(sd->shared); +#ifdef CONFIG_SCHED_CACHE + /* only the bottom sd has llc_counts array */ + kfree(sd->llc_counts); +#endif kfree(sd); } @@ -663,9 +674,10 @@ static void destroy_sched_domains(struct sched_domain *sd) */ DEFINE_PER_CPU(struct sched_domain __rcu *, sd_llc); DEFINE_PER_CPU(int, sd_llc_size); -DEFINE_PER_CPU(int, sd_llc_id); +DEFINE_PER_CPU(int, sd_llc_id) = -1; DEFINE_PER_CPU(int, sd_share_id); DEFINE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared); +DEFINE_PER_CPU(struct sched_domain_shared __rcu *, sd_balance_shared); DEFINE_PER_CPU(struct sched_domain __rcu *, sd_numa); DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing); DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity); @@ -692,7 +704,6 @@ static void update_top_cache_domain(int cpu) rcu_assign_pointer(per_cpu(sd_llc, cpu), sd); per_cpu(sd_llc_size, cpu) = size; - per_cpu(sd_llc_id, cpu) = id; rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds); sd = lowest_flag_domain(cpu, SD_CLUSTER); @@ -713,7 +724,18 @@ static void update_top_cache_domain(int cpu) rcu_assign_pointer(per_cpu(sd_asym_packing, cpu), sd); sd = lowest_flag_domain(cpu, SD_ASYM_CPUCAPACITY_FULL); + /* + * The shared object is attached to sd_asym_cpucapacity only when the + * asym domain is non-overlapping (i.e., not built from SD_NUMA). + * On overlapping (NUMA) asym domains we fall back to letting the + * SD_SHARE_LLC path own the shared object, so sd->shared may be NULL + * here. + */ + if (sd && sd->shared) + sds = sd->shared; + rcu_assign_pointer(per_cpu(sd_asym_cpucapacity, cpu), sd); + rcu_assign_pointer(per_cpu(sd_balance_shared, cpu), sds); } /* @@ -737,7 +759,14 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) /* Pick reference to parent->shared. */ if (parent->shared) { - WARN_ON_ONCE(tmp->shared); + /* + * It is safe to free a sd->shared that + * has not been published yet. If a + * sd->shared was published, the refcount + * will end up being non-zero and it will + * not be freed here. + */ + free_sched_domain_shared(tmp->shared); tmp->shared = parent->shared; parent->shared = NULL; } @@ -762,10 +791,20 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) if (sd && sd_degenerate(sd)) { tmp = sd; sd = sd->parent; - destroy_sched_domain(tmp); + if (sd) { struct sched_group *sg = sd->groups; +#ifdef CONFIG_SCHED_CACHE + /* move buffer to parent as child is being destroyed */ + sd->llc_counts = tmp->llc_counts; + sd->llc_max = tmp->llc_max; + sd->llc_bytes = tmp->llc_bytes; + /* make sure destroy_sched_domain() does not free it */ + tmp->llc_counts = NULL; + tmp->llc_max = 0; + tmp->llc_bytes = 0; +#endif /* * sched groups hold the flags of the child sched * domain for convenience. Clear such flags since @@ -777,6 +816,8 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) sd->child = NULL; } + + destroy_sched_domain(tmp); } sched_domain_debug(sd, cpu); @@ -804,6 +845,239 @@ enum s_alloc { sa_none, }; +#ifdef CONFIG_SCHED_CACHE +/* hardware support for cache aware scheduling */ +DEFINE_STATIC_KEY_FALSE(sched_cache_present); +/* + * Indicator of whether cache aware scheduling + * is active, used by the scheduler. + */ +DEFINE_STATIC_KEY_FALSE(sched_cache_active); +/* user wants cache aware scheduling [0 or 1] */ +int sysctl_sched_cache_user = 1; + +/* + * Get the effective LLC size in bytes that @cpu's bottom sched_domain + * can use. A CPU within a cpuset partition can only use a proportion + * of the physical LLC, scaled by the ratio of the partition's span + * weight to the hardware LLC sharing weight. @sd should be the + * topmost domain with SD_SHARE_LLC. + * + * Returns 0 if cacheinfo is not yet populated. This happens during + * early boot when build_sched_domains() runs before the generic + * cacheinfo framework has been initialized (cacheinfo_cpu_online() + * is a device_initcall cpuhp callback). In that case, + * cacheinfo_cpu_online() will later call sched_update_llc_bytes() + * to fill in the bottom domain's llc_bytes once the cache attributes + * are available. + */ +static unsigned long get_effective_llc_bytes(int cpu, + struct sched_domain *sd) +{ + struct cacheinfo *ci; + unsigned int hw_weight; + + ci = get_cpu_cacheinfo_llc(cpu); + if (!ci) + return 0; + + hw_weight = cpumask_weight(&ci->shared_cpu_map); + if (!hw_weight) + return 0; + + return div_u64((u64)ci->size * sd->span_weight, hw_weight); +} + +static bool alloc_sd_llc(const struct cpumask *cpu_map, + struct s_data *d) +{ + struct sched_domain *sd, *top_llc, *parent; + unsigned int *p; + int i; + + for_each_cpu(i, cpu_map) { + sd = *per_cpu_ptr(d->sd, i); + if (!sd) + goto err; + + p = kcalloc_node(max_lid + 1, sizeof(unsigned int), + GFP_KERNEL, cpu_to_node(i)); + if (!p) + goto err; + + top_llc = sd; + /* + * Find the topmost SD_SHARE_LLC domain. + * Not yet attached to the CPU, so per_cpu(sd_llc, i) + * can not be used. + */ + while ((parent = rcu_dereference_protected(top_llc->parent, true)) && + (parent->flags & SD_SHARE_LLC)) + top_llc = parent; + + if (top_llc->flags & SD_SHARE_LLC) { + sd->llc_max = max_lid + 1; + sd->llc_counts = p; + sd->llc_bytes = get_effective_llc_bytes(i, top_llc); + } else { + /* avoid memory leak */ + kfree(p); + } + } + + return true; +err: + for_each_cpu(i, cpu_map) { + sd = *per_cpu_ptr(d->sd, i); + if (sd) { + kfree(sd->llc_counts); + sd->llc_counts = NULL; + sd->llc_max = 0; + sd->llc_bytes = 0; + } + } + + return false; +} + +/* + * Enable/disable cache aware scheduling according to + * user input and the presence of hardware support. + */ +static void _sched_cache_active_set(void) +{ + lockdep_assert_cpus_held(); + lockdep_assert_held(&sched_domains_mutex); + + /* hardware does not support */ + if (!static_branch_likely(&sched_cache_present)) { + static_branch_disable_cpuslocked(&sched_cache_active); + if (sched_debug()) + pr_info("%s: cache aware scheduling not supported on this platform\n", __func__); + return; + } + + /* + * user wants it or not ? + * TBD: read before writing the static key. + * It is not in the critical path, leave as-is + * for now. + */ + if (sysctl_sched_cache_user) { + static_branch_enable_cpuslocked(&sched_cache_active); + if (sched_debug()) + pr_info("%s: enabling cache aware scheduling\n", __func__); + } else { + static_branch_disable_cpuslocked(&sched_cache_active); + if (sched_debug()) + pr_info("%s: disabling cache aware scheduling\n", __func__); + } +} + +/* used by debugfs */ +void sched_cache_active_set(void) +{ + cpus_read_lock(); + sched_domains_mutex_lock(); + _sched_cache_active_set(); + sched_domains_mutex_unlock(); + cpus_read_unlock(); +} + +/* + * Update the bottom sched_domain's llc_bytes for @cpu and all its + * LLC siblings. Called from cacheinfo_cpu_online() or + * cacheinfo_cpu_pre_down() with cpu hotplug lock held. + * + * Note: get_effective_llc_bytes() returns 0 on PowerPC. + * thus cache aware scheduling is disabled on PowerPC for + * now. PowerPC does not use the generic cacheinfo framework -- + * it has its own cacheinfo with a separate struct cache hierarchy + * and does not populates the per-CPU struct cpu_cacheinfo array + * that get_cpu_cacheinfo_llc() reads. + */ +void sched_update_llc_bytes(unsigned int cpu) +{ + struct sched_domain *sd, *sdp; + unsigned int i; + + sched_domains_mutex_lock(); + + sdp = rcu_dereference_sched_domain(per_cpu(sd_llc, cpu)); + if (!sdp) + goto unlock; + + /* + * ci->shared_cpu_map is built incrementally as CPUs come + * online, so the first CPU in an LLC initially sees + * hw_weight == 1 and computes an inflated llc_bytes in + * get_effective_llc_bytes(). Re-evaluating every LLC + * sibling on each online event corrects this once the full + * shared_cpu_map is known. + */ + for_each_cpu(i, sched_domain_span(sdp)) { + sd = rcu_dereference_sched_domain(cpu_rq(i)->sd); + if (sd) + sd->llc_bytes = get_effective_llc_bytes(i, sdp); + } + +unlock: + sched_domains_mutex_unlock(); +} + +static void sched_cache_set(bool has_multi_llcs) +{ + /* + * TBD: check before writing to it. sched domain rebuild + * is not in the critical path, leave as-is for now. + */ + if (has_multi_llcs) + static_branch_enable_cpuslocked(&sched_cache_present); + else + static_branch_disable_cpuslocked(&sched_cache_present); + + _sched_cache_active_set(); +} +#else +static bool alloc_sd_llc(const struct cpumask *cpu_map, + struct s_data *d) +{ + return false; +} +static inline void sched_cache_set(bool has_multi_llcs) { } +#endif + +/* + * Return true if @sd belongs to an LLC group whose enclosing + * partition spans more than one LLC. @sd must be the topmost + * SD_SHARE_LLC domain. + * + * Any duplicated parent domains with the same span as @sd are + * skipped: before cpu_attach_domain() degeneration these still + * exist, after degeneration the loop is a no-op. This makes the + * helper usable both during sched domain build and against an + * already-attached domain tree. + * + * Note: For systems with a single LLC per node, cache-aware + * scheduling is still enabled when multiple nodes exist. + * However, NUMA balancing decisions take precedence over + * cache-aware scheduling. Conversely, if there is only one + * LLC per partition, cache-aware scheduling should be disabled. + */ +static bool sd_in_multi_llcs(struct sched_domain *sd) +{ + struct sched_domain *sdp = sd->parent; + + /* it does not make sense to aggregate to 1 CPU */ + if (sd->span_weight == 1) + return false; + + while (sdp && sdp->span_weight == sd->span_weight) + sdp = sdp->parent; + + return !!sdp; +} + /* * Return the canonical balance CPU for this group, this is the first CPU * of this group that's also in the balance mask. @@ -1310,9 +1584,7 @@ static void init_sched_groups_capacity(int cpu, struct sched_domain *sd) cpumask_copy(mask, sched_group_span(sg)); for_each_cpu(cpu, mask) { cores++; -#ifdef CONFIG_SCHED_SMT cpumask_andnot(mask, mask, cpu_smt_mask(cpu)); -#endif } sg->cores = cores; @@ -1790,8 +2062,22 @@ const struct cpumask *tl_mc_mask(struct sched_domain_topology_level *tl, int cpu { return cpu_coregroup_mask(cpu); } + +/* + * Majority of architectures have LLC at MC domain level with exception + * such as powerpc. Provide a way for arch to specify where its LLC is + * if it falls in exception category + */ +# ifndef arch_llc_mask +#define arch_llc_mask(cpu) cpu_coregroup_mask(cpu) +# endif + +#else +#define arch_llc_mask(cpu) cpumask_of(cpu) #endif +#define llc_mask(cpu) arch_llc_mask(cpu) + const struct cpumask *tl_pkg_mask(struct sched_domain_topology_level *tl, int cpu) { return cpu_node_mask(cpu); @@ -2650,14 +2936,153 @@ static void adjust_numa_imbalance(struct sched_domain *sd_llc) } } +static void +init_sched_domain_shared(struct s_data *d, struct sched_domain *sd, int flags) +{ + struct sched_domain_shared *sds = NULL; + int cpu; + + /* + * Multiple domains can try to claim a shared object like + * SD_ASYM_CPUCAPACITY and SD_SHARE_LLC which can alias to + * same cpumask_first(sched_domain_span(sd)) CPU and can + * cause "nr_idle_scan" to be populated incorrectly during + * load balancing. + * + * Find the first CPU in sched_domain_span(sd) with an + * unclaimed domain (!alloc_flags) or where the alloc_flag + * matches the requested flag (SD_* flag) + * + * If the domain only has single CPU, allow temporary overlap + * in allocation since the domains will be degenerated later. + */ + for_each_cpu(cpu, sched_domain_span(sd)) { + sds = *per_cpu_ptr(d->sds, cpu); + + if (!sds->alloc_flags || + sd->span_weight == 1 || + sds->alloc_flags == flags) { + sds->alloc_flags = flags; + sd->shared = sds; + break; + } + } + + /* + * Use the sd_shared corresponding to the last + * CPU in the span if none are avaialable. + */ + if (WARN_ON_ONCE(!sd->shared)) + sd->shared = sds; + + /* + * nr_busy_cpus is consumed only by the NOHZ kick path via + * sd_balance_shared; on the asym-capacity path it is initialized but + * never read. + */ + atomic_set(&sd->shared->nr_busy_cpus, sd->span_weight); + atomic_inc(&sd->shared->ref); +} + +/* + * For asymmetric CPU capacity, attach sched_domain_shared on the innermost + * SD_ASYM_CPUCAPACITY_FULL ancestor of @cpu's base domain when that ancestor is + * not an overlapping NUMA-built domain (then LLC should claim shared). + * + * A CPU may lack any FULL ancestor (e.g., exclusive cpuset symmetric island), + * then LLC must claim shared instead. + * + * Note: SD_ASYM_CPUCAPACITY_FULL is only set when all CPU capacity values + * are present in the domain span, so the asym domain we attach to cannot + * degenerate into a single-capacity group. The relevant edge cases are instead + * covered by the caveats above. + * + * Return true if this CPU's asym path claimed sd->shared, false otherwise. + */ +static bool claim_asym_sched_domain_shared(struct s_data *d, int cpu) +{ + struct sched_domain *sd = *per_cpu_ptr(d->sd, cpu); + struct sched_domain *sd_asym; + + if (!sd) + return false; + + sd_asym = sd; + while (sd_asym && !(sd_asym->flags & SD_ASYM_CPUCAPACITY_FULL)) + sd_asym = sd_asym->parent; + + if (!sd_asym || (sd_asym->flags & SD_NUMA)) + return false; + + init_sched_domain_shared(d, sd_asym, SD_ASYM_CPUCAPACITY); + return true; +} + +static int __sched_domains_alloc_llc_id(void) +{ + int lid, max; + + lockdep_assert_held(&sched_domains_mutex); + + lid = cpumask_first_zero(sched_domains_llc_id_allocmask); + /* + * llc_id space should never grow larger than the + * possible number of CPUs in the system. + */ + if (lid >= nr_cpu_ids) + return -1; + + __cpumask_set_cpu(lid, sched_domains_llc_id_allocmask); + max = cpumask_last(sched_domains_llc_id_allocmask); + if (max > max_lid) + max_lid = max; + + return lid; +} + +static void __sched_domains_free_llc_id(int cpu) +{ + int i, lid, max; + + lockdep_assert_held(&sched_domains_mutex); + + lid = per_cpu(sd_llc_id, cpu); + if (lid == -1 || lid >= nr_cpu_ids) + return; + + per_cpu(sd_llc_id, cpu) = -1; + + for_each_cpu(i, llc_mask(cpu)) { + /* An online CPU owns the llc_id. */ + if (per_cpu(sd_llc_id, i) == lid) + return; + } + + __cpumask_clear_cpu(lid, sched_domains_llc_id_allocmask); + + max = cpumask_last(sched_domains_llc_id_allocmask); + /* shrink max lid to save memory */ + if (max < max_lid) + max_lid = max; +} + +void sched_domains_free_llc_id(int cpu) +{ + sched_domains_mutex_lock(); + __sched_domains_free_llc_id(cpu); + sched_domains_mutex_unlock(); +} + /* * Build sched domains for a given set of CPUs and attach the sched domains * to the individual CPUs */ static int -build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *attr) +build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *attr, + bool *multi_llcs) { enum s_alloc alloc_state = sa_none; + bool has_multi_llcs = false; struct sched_domain *sd; struct s_data d; struct rq *rq = NULL; @@ -2675,6 +3100,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att /* Set up domains for CPUs specified by the cpu_map: */ for_each_cpu(i, cpu_map) { struct sched_domain_topology_level *tl; + int lid; sd = NULL; for_each_sd_topology(tl) { @@ -2688,6 +3114,29 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att if (cpumask_equal(cpu_map, sched_domain_span(sd))) break; } + + lid = per_cpu(sd_llc_id, i); + if (lid == -1) { + /* try to reuse the llc_id of its siblings */ + for (int j = cpumask_first(llc_mask(i)); + j < nr_cpu_ids; + j = cpumask_next(j, llc_mask(i))) { + if (i == j) + continue; + + lid = per_cpu(sd_llc_id, j); + + if (lid != -1) { + per_cpu(sd_llc_id, i) = lid; + + break; + } + } + + /* a new LLC is detected */ + if (lid == -1) + per_cpu(sd_llc_id, i) = __sched_domains_alloc_llc_id(); + } } if (WARN_ON(!topology_span_sane(cpu_map))) @@ -2712,23 +3161,27 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att if (!sd) continue; + if (has_asym) + claim_asym_sched_domain_shared(&d, i); + /* First, find the topmost SD_SHARE_LLC domain */ while (sd->parent && (sd->parent->flags & SD_SHARE_LLC)) sd = sd->parent; if (sd->flags & SD_SHARE_LLC) { - int sd_id = cpumask_first(sched_domain_span(sd)); - - sd->shared = *per_cpu_ptr(d.sds, sd_id); - atomic_set(&sd->shared->nr_busy_cpus, sd->span_weight); - atomic_inc(&sd->shared->ref); + init_sched_domain_shared(&d, sd, SD_SHARE_LLC); /* * In presence of higher domains, adjust the * NUMA imbalance stats for the hierarchy. */ - if (IS_ENABLED(CONFIG_NUMA) && sd->parent) - adjust_numa_imbalance(sd); + if (sd->parent) { + if (IS_ENABLED(CONFIG_NUMA)) + adjust_numa_imbalance(sd); + + if (sd_in_multi_llcs(sd)) + has_multi_llcs = true; + } } } @@ -2743,6 +3196,8 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att init_sched_groups_capacity(i, sd); } + alloc_sd_llc(cpu_map, &d); + /* Attach the domains */ rcu_read_lock(); for_each_cpu(i, cpu_map) { @@ -2767,6 +3222,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att ret = 0; error: + *multi_llcs = has_multi_llcs; __free_domain_allocs(&d, alloc_state, cpu_map); return ret; @@ -2829,8 +3285,10 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms) */ int __init sched_init_domains(const struct cpumask *cpu_map) { + bool multi_llcs; int err; + zalloc_cpumask_var(&sched_domains_llc_id_allocmask, GFP_KERNEL); zalloc_cpumask_var(&sched_domains_tmpmask, GFP_KERNEL); zalloc_cpumask_var(&sched_domains_tmpmask2, GFP_KERNEL); zalloc_cpumask_var(&fallback_doms, GFP_KERNEL); @@ -2842,7 +3300,9 @@ int __init sched_init_domains(const struct cpumask *cpu_map) if (!doms_cur) doms_cur = &fallback_doms; cpumask_and(doms_cur[0], cpu_map, housekeeping_cpumask(HK_TYPE_DOMAIN)); - err = build_sched_domains(doms_cur[0], NULL); + err = build_sched_domains(doms_cur[0], NULL, &multi_llcs); + if (!err) + sched_cache_set(multi_llcs); return err; } @@ -2915,6 +3375,7 @@ static 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; + bool has_multi_llcs = false, multi_llcs; int i, j, n; int new_topology; @@ -2964,14 +3425,41 @@ match1: for (i = 0; i < ndoms_new; i++) { for (j = 0; j < n && !new_topology; j++) { if (cpumask_equal(doms_new[i], doms_cur[j]) && - dattrs_equal(dattr_new, i, dattr_cur, j)) + dattrs_equal(dattr_new, i, dattr_cur, j)) { + /* + * Reused partition has to be taken care + * of here, because there could be a corner + * case that if the reused partition is skipped + * and only new partition is considered, an + * incorrect has_multi_llcs would be set. For + * example: + * If the only multi-LLC partition is reused + * and a new single-LLC partition is built, + * sched_cache_set(false) disables cache-aware + * scheduling globally despite the reused + * multi-LLC partition still being active. + */ + struct sched_domain *sd; + int cpu = cpumask_first(doms_cur[j]); + + guard(rcu)(); + sd = rcu_dereference(cpu_rq(cpu)->sd); + while (sd && sd->parent && (sd->parent->flags & SD_SHARE_LLC)) + sd = sd->parent; + if (sd && (sd->flags & SD_SHARE_LLC) && sd->parent && + sd_in_multi_llcs(sd)) + has_multi_llcs = true; goto match2; + } } /* No match - add a new doms_new */ - build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL); + build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL, + &multi_llcs); + has_multi_llcs |= multi_llcs; match2: ; } + sched_cache_set(has_multi_llcs); #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) /* Build perf domains: */ diff --git a/kernel/signal.c b/kernel/signal.c index 2d102e025883..9c2b32c4d755 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1338,6 +1338,7 @@ int zap_other_threads(struct task_struct *p) int count = 0; p->signal->group_stop_count = 0; + task_clear_jobctl_pending(p, JOBCTL_PENDING_MASK); for_other_threads(p, t) { task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 3fe6b0c99f3d..773d8e9ae30c 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -633,6 +633,11 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) EXPORT_SYMBOL_GPL(stop_machine); #ifdef CONFIG_SCHED_SMT +/* + * INTEL_IFS is the only user of this API. That selftest can + * only be compiled if SMP=y. On x86 it selects SCHED_SMT. + * Keep the ifdefs for now. + */ int stop_core_cpuslocked(unsigned int cpu, cpu_stop_fn_t fn, void *data) { const struct cpumask *smt_mask = cpu_smt_mask(cpu); diff --git a/kernel/sys.c b/kernel/sys.c index 62e842055cc9..df69bd71de03 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2565,14 +2565,14 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, error = put_user(me->pdeath_signal, (int __user *)arg2); break; case PR_GET_DUMPABLE: - error = get_dumpable(me->mm); + error = task_exec_state_get_dumpable(me); break; case PR_SET_DUMPABLE: - if (arg2 != SUID_DUMP_DISABLE && arg2 != SUID_DUMP_USER) { + if (arg2 != TASK_DUMPABLE_OFF && arg2 != TASK_DUMPABLE_OWNER) { error = -EINVAL; break; } - set_dumpable(me->mm, arg2); + task_exec_state_set_dumpable(arg2); break; case PR_SET_UNALIGN: diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index 02aac7c5aa76..d098ac39bde4 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -16,10 +16,6 @@ config ARCH_CLOCKSOURCE_INIT config ARCH_WANTS_CLOCKSOURCE_READ_INLINE bool -# Timekeeping vsyscall support -config GENERIC_TIME_VSYSCALL - bool - # The generic clock events infrastructure config GENERIC_CLOCKEVENTS def_bool !LEGACY_TIMER_TICK diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 6e173d70d825..ea5be5870e51 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -337,48 +337,32 @@ void alarm_init(struct alarm *alarm, enum alarmtimer_type type, EXPORT_SYMBOL_GPL(alarm_init); /** - * alarm_start - Sets an absolute alarm to fire - * @alarm: ptr to alarm to set - * @start: time to run the alarm + * alarm_start_timer - Sets an alarm to fire + * @alarm: Pointer to alarm to set + * @expires: Expiry time + * @relative: True if @expires is relative + * + * Returns: True if the alarm was queued. False if it already expired */ -void alarm_start(struct alarm *alarm, ktime_t start) +bool alarm_start_timer(struct alarm *alarm, ktime_t expires, bool relative) { struct alarm_base *base = &alarm_bases[alarm->type]; - scoped_guard(spinlock_irqsave, &base->lock) { - alarm->node.expires = start; - alarmtimer_enqueue(base, alarm); - hrtimer_start(&alarm->timer, alarm->node.expires, HRTIMER_MODE_ABS); - } + if (relative) + expires = ktime_add_safe(expires, base->get_ktime()); trace_alarmtimer_start(alarm, base->get_ktime()); -} -EXPORT_SYMBOL_GPL(alarm_start); - -/** - * alarm_start_relative - Sets a relative alarm to fire - * @alarm: ptr to alarm to set - * @start: time relative to now to run the alarm - */ -void alarm_start_relative(struct alarm *alarm, ktime_t start) -{ - struct alarm_base *base = &alarm_bases[alarm->type]; - - start = ktime_add_safe(start, base->get_ktime()); - alarm_start(alarm, start); -} -EXPORT_SYMBOL_GPL(alarm_start_relative); - -void alarm_restart(struct alarm *alarm) -{ - struct alarm_base *base = &alarm_bases[alarm->type]; guard(spinlock_irqsave)(&base->lock); - hrtimer_set_expires(&alarm->timer, alarm->node.expires); - hrtimer_restart(&alarm->timer); + alarm->node.expires = expires; alarmtimer_enqueue(base, alarm); + if (!hrtimer_start_range_ns_user(&alarm->timer, expires, 0, HRTIMER_MODE_ABS)) { + alarmtimer_dequeue(base, alarm); + return false; + } + return true; } -EXPORT_SYMBOL_GPL(alarm_restart); +EXPORT_SYMBOL_GPL(alarm_start_timer); /** * alarm_try_to_cancel - Tries to cancel an alarm timer @@ -512,8 +496,6 @@ static enum alarmtimer_type clock2alarm(clockid_t clockid) * @now: time at the timer expiration * * Posix timer callback for expired alarm timers. - * - * Return: whether the timer is to be restarted */ static void alarm_handle_timer(struct alarm *alarm, ktime_t now) { @@ -527,12 +509,12 @@ static void alarm_handle_timer(struct alarm *alarm, ktime_t now) * alarm_timer_rearm - Posix timer callback for rearming timer * @timr: Pointer to the posixtimer data struct */ -static void alarm_timer_rearm(struct k_itimer *timr) +static bool alarm_timer_rearm(struct k_itimer *timr) { struct alarm *alarm = &timr->it.alarm.alarmtimer; timr->it_overrun += alarm_forward_now(alarm, timr->it_interval); - alarm_start(alarm, alarm->node.expires); + return alarm_start_timer(alarm, alarm->node.expires, false); } /** @@ -588,7 +570,7 @@ static void alarm_timer_wait_running(struct k_itimer *timr) * @absolute: Expiry value is absolute time * @sigev_none: Posix timer does not deliver signals */ -static void alarm_timer_arm(struct k_itimer *timr, ktime_t expires, +static bool alarm_timer_arm(struct k_itimer *timr, ktime_t expires, bool absolute, bool sigev_none) { struct alarm *alarm = &timr->it.alarm.alarmtimer; @@ -596,10 +578,16 @@ static void alarm_timer_arm(struct k_itimer *timr, ktime_t expires, if (!absolute) expires = ktime_add_safe(expires, base->get_ktime()); - if (sigev_none) + + /* + * sigev_none needs to update the expires value and pretend + * that the timer is queued + */ + if (sigev_none) { alarm->node.expires = expires; - else - alarm_start(&timr->it.alarm.alarmtimer, expires); + return true; + } + return alarm_start_timer(&timr->it.alarm.alarmtimer, expires, false); } /** @@ -706,7 +694,9 @@ static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp, alarm->data = (void *)current; do { set_current_state(TASK_INTERRUPTIBLE); - alarm_start(alarm, absexp); + if (!alarm_start_timer(alarm, absexp, false)) + alarm->data = NULL; + if (likely(alarm->data)) schedule(); diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 5e22697b098d..0014d163f989 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -301,7 +301,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev) #include <asm/clock_inlined.h> #else static __always_inline void -arch_inlined_clockevent_set_next_coupled(u64 u64 cycles, struct clock_event_device *dev) { } +arch_inlined_clockevent_set_next_coupled(u64 cycles, struct clock_event_device *dev) { } #endif static inline bool clockevent_set_next_coupled(struct clock_event_device *dev, ktime_t expires) diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index baee13a1f87f..e48c4d379a7c 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -1222,14 +1222,8 @@ static void clocksource_enqueue(struct clocksource *cs) * @cs: clocksource to be registered * @scale: Scale factor multiplied against freq to get clocksource hz * @freq: clocksource frequency (cycles per second) divided by scale - * - * This should only be called from the clocksource->enable() method. - * - * This *SHOULD NOT* be called directly! Please use the - * __clocksource_update_freq_hz() or __clocksource_update_freq_khz() helper - * functions. */ -void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq) +static void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq) { u64 sec; @@ -1287,7 +1281,6 @@ void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq pr_info("%s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n", cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns); } -EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale); /** * __clocksource_register_scale - Used to install new clocksources @@ -1338,6 +1331,26 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) } EXPORT_SYMBOL_GPL(__clocksource_register_scale); +static void __devm_clocksource_unregister(void *data) +{ + struct clocksource *cs = data; + + clocksource_unregister(cs); +} + +int __devm_clocksource_register_scale(struct device *dev, struct clocksource *cs, + u32 scale, u32 freq) +{ + int ret; + + ret = __clocksource_register_scale(cs, scale, freq); + if (ret) + return ret; + + return devm_add_action_or_reset(dev, __devm_clocksource_unregister, cs); +} +EXPORT_SYMBOL_GPL(__devm_clocksource_register_scale); + /* * Unbind clocksource @cs. Called with clocksource_mutex held */ diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 5bd6efe598f0..638ce623c342 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1352,8 +1352,14 @@ static inline bool hrtimer_keep_base(struct hrtimer *timer, bool is_local, bool return hrtimer_prefer_local(is_local, is_first, is_pinned); } -static bool __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, - const enum hrtimer_mode mode, struct hrtimer_clock_base *base) +enum { + HRTIMER_REPROGRAM_NONE, + HRTIMER_REPROGRAM, + HRTIMER_REPROGRAM_FORCE, +}; + +static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, + const enum hrtimer_mode mode, struct hrtimer_clock_base *base) { struct hrtimer_cpu_base *this_cpu_base = this_cpu_ptr(&hrtimer_bases); bool is_pinned, first, was_first, keep_base = false; @@ -1410,7 +1416,7 @@ static bool __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 del /* If a deferred rearm is pending skip reprogramming the device */ if (cpu_base->deferred_rearm) { cpu_base->deferred_needs_update = true; - return false; + return HRTIMER_REPROGRAM_NONE; } if (!was_first || cpu_base != this_cpu_base) { @@ -1423,7 +1429,7 @@ static bool __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 del * callbacks. */ if (likely(hrtimer_base_is_online(this_cpu_base))) - return first; + return first ? HRTIMER_REPROGRAM : HRTIMER_REPROGRAM_NONE; /* * Timer was enqueued remote because the current base is @@ -1432,7 +1438,7 @@ static bool __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 del */ if (first) smp_call_function_single_async(cpu_base->cpu, &cpu_base->csd); - return false; + return HRTIMER_REPROGRAM_NONE; } /* @@ -1446,7 +1452,7 @@ static bool __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 del */ if (timer->is_lazy) { if (cpu_base->expires_next <= hrtimer_get_expires(timer)) - return false; + return HRTIMER_REPROGRAM_NONE; } /* @@ -1455,8 +1461,24 @@ static bool __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 del * reprogram the hardware by evaluating the new first expiring * timer. */ - hrtimer_force_reprogram(cpu_base, /* skip_equal */ true); - return false; + return HRTIMER_REPROGRAM_FORCE; +} + +static int hrtimer_start_range_ns_common(struct hrtimer *timer, ktime_t tim, + u64 delta_ns, const enum hrtimer_mode mode, + struct hrtimer_clock_base *base) +{ + /* + * Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft + * match on CONFIG_PREEMPT_RT = n. With PREEMPT_RT check the hard + * expiry mode because unmarked timers are moved to softirq expiry. + */ + 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); + + return __hrtimer_start_range_ns(timer, tim, delta_ns, mode, base); } /** @@ -1476,24 +1498,104 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, debug_hrtimer_assert_init(timer); + base = lock_hrtimer_base(timer, &flags); + + switch (hrtimer_start_range_ns_common(timer, tim, delta_ns, mode, base)) { + case HRTIMER_REPROGRAM: + hrtimer_reprogram(timer, true); + break; + case HRTIMER_REPROGRAM_FORCE: + hrtimer_force_reprogram(timer->base->cpu_base, 1); + break; + case HRTIMER_REPROGRAM_NONE: + break; + } + + unlock_hrtimer_base(timer, &flags); +} +EXPORT_SYMBOL_GPL(hrtimer_start_range_ns); + +static inline bool hrtimer_check_user_timer(struct hrtimer *timer) +{ + struct hrtimer_cpu_base *cpu_base = timer->base->cpu_base; + ktime_t expires; + /* - * Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft - * match on CONFIG_PREEMPT_RT = n. With PREEMPT_RT check the hard - * expiry mode because unmarked timers are moved to softirq expiry. + * This uses soft expires because that's the user provided + * expiry time, while expires can be further in the past + * due to a slack value added to the user expiry time. */ - 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); + expires = hrtimer_get_softexpires(timer); + + /* Convert to monotonic */ + expires = ktime_sub(expires, timer->base->offset); + + /* + * Check whether this timer will end up as the first expiring timer in + * the CPU base. If not, no further checks required as it's then + * guaranteed to expire in the future. + */ + if (expires >= cpu_base->expires_next) + return true; + + /* Validate that the expiry time is in the future. */ + if (expires > ktime_get()) + return true; + + debug_hrtimer_deactivate(timer); + __remove_hrtimer(timer, timer->base, HRTIMER_STATE_INACTIVE, false); + trace_hrtimer_start_expired(timer); + return false; +} + +/** + * hrtimer_start_range_ns_user - (re)start an user controlled hrtimer + * @timer: the timer to be added + * @tim: expiry time + * @delta_ns: "slack" range for the timer + * @mode: timer mode: absolute (HRTIMER_MODE_ABS) or + * relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED); + * softirq based mode is considered for debug purpose only! + * + * Returns: True when the timer was queued, false if it was already expired + * + * This function cannot invoke the timer callback for expired timers as it might + * be called under a lock which the timer callback needs to acquire. So the + * caller has to handle that case. + */ +bool hrtimer_start_range_ns_user(struct hrtimer *timer, ktime_t tim, + u64 delta_ns, const enum hrtimer_mode mode) +{ + struct hrtimer_clock_base *base; + unsigned long flags; + bool ret = true; + + debug_hrtimer_assert_init(timer); base = lock_hrtimer_base(timer, &flags); - if (__hrtimer_start_range_ns(timer, tim, delta_ns, mode, base)) - hrtimer_reprogram(timer, true); + switch (hrtimer_start_range_ns_common(timer, tim, delta_ns, mode, base)) { + case HRTIMER_REPROGRAM: + ret = hrtimer_check_user_timer(timer); + if (ret) + hrtimer_reprogram(timer, true); + break; + case HRTIMER_REPROGRAM_FORCE: + ret = hrtimer_check_user_timer(timer); + /* + * The base must always be reevaluated, independent of the + * result above because the timer was the first pending timer. + */ + hrtimer_force_reprogram(timer->base->cpu_base, 1); + break; + case HRTIMER_REPROGRAM_NONE: + break; + } unlock_hrtimer_base(timer, &flags); + return ret; } -EXPORT_SYMBOL_GPL(hrtimer_start_range_ns); +EXPORT_SYMBOL_GPL(hrtimer_start_range_ns_user); /** * hrtimer_try_to_cancel - try to deactivate a timer @@ -1681,10 +1783,10 @@ EXPORT_SYMBOL_GPL(__hrtimer_get_remaining); * * Returns the next expiry time or KTIME_MAX if no timer is pending. */ -u64 hrtimer_get_next_event(void) +ktime_t hrtimer_get_next_event(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); - u64 expires = KTIME_MAX; + ktime_t expires = KTIME_MAX; guard(raw_spinlock_irqsave)(&cpu_base->lock); if (!hrtimer_hres_active(cpu_base)) @@ -1700,10 +1802,10 @@ u64 hrtimer_get_next_event(void) * Returns the next expiry time over all timers except for the @exclude one or * KTIME_MAX if none of them is pending. */ -u64 hrtimer_next_event_without(const struct hrtimer *exclude) +ktime_t hrtimer_next_event_without(const struct hrtimer *exclude) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); - u64 expires = KTIME_MAX; + ktime_t expires = KTIME_MAX; unsigned int active; guard(raw_spinlock_irqsave)(&cpu_base->lock); @@ -2213,7 +2315,11 @@ void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl, enum hrtimer_mode if (IS_ENABLED(CONFIG_PREEMPT_RT) && sl->timer.is_hard) mode |= HRTIMER_MODE_HARD; - hrtimer_start_expires(&sl->timer, mode); + /* If already expired, clear the task pointer and set current state to running */ + if (!hrtimer_start_expires_user(&sl->timer, mode)) { + sl->task = NULL; + __set_current_state(TASK_RUNNING); + } } EXPORT_SYMBOL_GPL(hrtimer_sleeper_start_expires); diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 1c954f330dfe..d51428867a33 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -60,15 +60,14 @@ EXPORT_SYMBOL(get_jiffies_64); EXPORT_SYMBOL(jiffies); -static int __init init_jiffies_clocksource(void) -{ - return __clocksource_register(&clocksource_jiffies); -} - -core_initcall(init_jiffies_clocksource); +static bool cs_jiffies_registered __initdata; struct clocksource * __init __weak clocksource_default_clock(void) { + if (!cs_jiffies_registered) { + __clocksource_register(&clocksource_jiffies); + cs_jiffies_registered = true; + } return &clocksource_jiffies; } diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c index 4bca3f78c8ea..5fa0af66cf3f 100644 --- a/kernel/time/namespace.c +++ b/kernel/time/namespace.c @@ -57,6 +57,7 @@ ktime_t do_timens_ktime_to_host(clockid_t clockid, ktime_t tim, return tim; } +EXPORT_SYMBOL_GPL(do_timens_ktime_to_host); static struct ucounts *inc_time_namespaces(struct user_namespace *ns) { @@ -351,6 +352,7 @@ struct time_namespace init_time_ns = { .user_ns = &init_user_ns, .frozen_offsets = true, }; +EXPORT_SYMBOL_GPL(init_time_ns); void __init time_ns_init(void) { diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 0de2bb7cbec0..74775b94d11b 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -19,7 +19,7 @@ #include "posix-timers.h" -static void posix_cpu_timer_rearm(struct k_itimer *timer); +static bool posix_cpu_timer_rearm(struct k_itimer *timer); void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit) { @@ -1011,24 +1011,27 @@ static void check_process_timers(struct task_struct *tsk, /* * This is called from the signal code (via posixtimer_rearm) * when the last timer signal was delivered and we have to reload the timer. + * + * Return true unconditionally so the core code assumes the timer to be + * armed. Otherwise it would requeue the signal. */ -static void posix_cpu_timer_rearm(struct k_itimer *timer) +static bool posix_cpu_timer_rearm(struct k_itimer *timer) { clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); - struct task_struct *p; struct sighand_struct *sighand; + struct task_struct *p; unsigned long flags; u64 now; - rcu_read_lock(); + guard(rcu)(); p = cpu_timer_task_rcu(timer); if (!p) - goto out; + return true; /* Protect timer list r/w in arm_timer() */ sighand = lock_task_sighand(p, &flags); if (unlikely(sighand == NULL)) - goto out; + return true; /* * Fetch the current sample and update the timer's expiry time. @@ -1045,8 +1048,7 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer) */ arm_timer(timer, p); unlock_task_sighand(p, &flags); -out: - rcu_read_unlock(); + return true; } /** @@ -1504,6 +1506,7 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, spin_lock_irq(&timer.it_lock); error = posix_cpu_timer_set(&timer, flags, &it, NULL); if (error) { + posix_cpu_timer_del(&timer); spin_unlock_irq(&timer.it_lock); return error; } diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 9331e1614124..436ba794cc0b 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -288,16 +288,18 @@ static inline int timer_overrun_to_int(struct k_itimer *timr) return (int)timr->it_overrun_last; } -static void common_hrtimer_rearm(struct k_itimer *timr) +static bool common_hrtimer_rearm(struct k_itimer *timr) { struct hrtimer *timer = &timr->it.real.timer; timr->it_overrun += hrtimer_forward_now(timer, timr->it_interval); - hrtimer_restart(timer); + return hrtimer_start_expires_user(timer, HRTIMER_MODE_ABS); } static bool __posixtimer_deliver_signal(struct kernel_siginfo *info, struct k_itimer *timr) { + bool queued; + guard(spinlock)(&timr->it_lock); /* @@ -311,12 +313,18 @@ static bool __posixtimer_deliver_signal(struct kernel_siginfo *info, struct k_it if (!timr->it_interval || WARN_ON_ONCE(timr->it_status != POSIX_TIMER_REQUEUE_PENDING)) return true; - timr->kclock->timer_rearm(timr); - timr->it_status = POSIX_TIMER_ARMED; + /* timer_rearm() updates timr::it_overrun */ + queued = timr->kclock->timer_rearm(timr); + timr->it_overrun_last = timr->it_overrun; timr->it_overrun = -1LL; ++timr->it_signal_seq; info->si_overrun = timer_overrun_to_int(timr); + + if (queued) + timr->it_status = POSIX_TIMER_ARMED; + else + posix_timer_queue_signal(timr); return true; } @@ -795,7 +803,7 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id) return timer_overrun_to_int(scoped_timer); } -static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires, +static bool common_hrtimer_arm(struct k_itimer *timr, ktime_t expires, bool absolute, bool sigev_none) { struct hrtimer *timer = &timr->it.real.timer; @@ -820,8 +828,11 @@ static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires, expires = ktime_add_safe(expires, hrtimer_cb_get_time(timer)); hrtimer_set_expires(timer, expires); - if (!sigev_none) - hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + /* For sigev_none pretend that the timer is queued */ + if (sigev_none) + return true; + + return hrtimer_start_expires_user(timer, HRTIMER_MODE_ABS); } static int common_hrtimer_try_to_cancel(struct k_itimer *timr) @@ -903,9 +914,13 @@ int common_timer_set(struct k_itimer *timr, int flags, expires = timens_ktime_to_host(timr->it_clock, expires); sigev_none = timr->it_sigev_notify == SIGEV_NONE; - kc->timer_arm(timr, expires, flags & TIMER_ABSTIME, sigev_none); - if (!sigev_none) - timr->it_status = POSIX_TIMER_ARMED; + if (kc->timer_arm(timr, expires, flags & TIMER_ABSTIME, sigev_none)) { + if (!sigev_none) + timr->it_status = POSIX_TIMER_ARMED; + } else { + /* Timer was already expired, queue the signal */ + posix_timer_queue_signal(timr); + } return 0; } diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h index 7f259e845d24..4ea9611dd716 100644 --- a/kernel/time/posix-timers.h +++ b/kernel/time/posix-timers.h @@ -27,11 +27,11 @@ struct k_clock { int (*timer_del)(struct k_itimer *timr); void (*timer_get)(struct k_itimer *timr, struct itimerspec64 *cur_setting); - void (*timer_rearm)(struct k_itimer *timr); + bool (*timer_rearm)(struct k_itimer *timr); s64 (*timer_forward)(struct k_itimer *timr, ktime_t now); ktime_t (*timer_remaining)(struct k_itimer *timr, ktime_t now); int (*timer_try_to_cancel)(struct k_itimer *timr); - void (*timer_arm)(struct k_itimer *timr, ktime_t expires, + bool (*timer_arm)(struct k_itimer *timr, ktime_t expires, bool absolute, bool sigev_none); void (*timer_wait_running)(struct k_itimer *timr); }; diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index cbbb87a0c6e7..98a9cae915c0 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -285,8 +285,6 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { touch_softlockup_watchdog_sched(); - if (is_idle_task(current)) - ts->idle_jiffies++; /* * In case the current tick fired too early past its expected * expiration, make sure we don't bypass the next clock reprogramming @@ -751,119 +749,6 @@ static void tick_nohz_update_jiffies(ktime_t now) touch_softlockup_watchdog_sched(); } -static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now) -{ - ktime_t delta; - - if (WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE))) - return; - - delta = ktime_sub(now, ts->idle_entrytime); - - write_seqcount_begin(&ts->idle_sleeptime_seq); - if (nr_iowait_cpu(smp_processor_id()) > 0) - ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta); - else - ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta); - - ts->idle_entrytime = now; - tick_sched_flag_clear(ts, TS_FLAG_IDLE_ACTIVE); - write_seqcount_end(&ts->idle_sleeptime_seq); - - sched_clock_idle_wakeup_event(); -} - -static void tick_nohz_start_idle(struct tick_sched *ts) -{ - write_seqcount_begin(&ts->idle_sleeptime_seq); - ts->idle_entrytime = ktime_get(); - tick_sched_flag_set(ts, TS_FLAG_IDLE_ACTIVE); - write_seqcount_end(&ts->idle_sleeptime_seq); - - sched_clock_idle_sleep_event(); -} - -static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime, - bool compute_delta, u64 *last_update_time) -{ - ktime_t now, idle; - unsigned int seq; - - if (!tick_nohz_active) - return -1; - - now = ktime_get(); - if (last_update_time) - *last_update_time = ktime_to_us(now); - - do { - seq = read_seqcount_begin(&ts->idle_sleeptime_seq); - - if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE) && compute_delta) { - ktime_t delta = ktime_sub(now, ts->idle_entrytime); - - idle = ktime_add(*sleeptime, delta); - } else { - idle = *sleeptime; - } - } while (read_seqcount_retry(&ts->idle_sleeptime_seq, seq)); - - return ktime_to_us(idle); - -} - -/** - * get_cpu_idle_time_us - get the total idle time of a CPU - * @cpu: CPU number to query - * @last_update_time: variable to store update time in. Do not update - * counters if NULL. - * - * Return the cumulative idle time (since boot) for a given - * CPU, in microseconds. Note that this is partially broken due to - * the counter of iowait tasks that can be remotely updated without - * any synchronization. Therefore it is possible to observe backward - * values within two consecutive reads. - * - * This time is measured via accounting rather than sampling, - * and is as accurate as ktime_get() is. - * - * Return: -1 if NOHZ is not enabled, else total idle time of the @cpu - */ -u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time) -{ - struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); - - return get_cpu_sleep_time_us(ts, &ts->idle_sleeptime, - !nr_iowait_cpu(cpu), last_update_time); -} -EXPORT_SYMBOL_GPL(get_cpu_idle_time_us); - -/** - * get_cpu_iowait_time_us - get the total iowait time of a CPU - * @cpu: CPU number to query - * @last_update_time: variable to store update time in. Do not update - * counters if NULL. - * - * Return the cumulative iowait time (since boot) for a given - * CPU, in microseconds. Note this is partially broken due to - * the counter of iowait tasks that can be remotely updated without - * any synchronization. Therefore it is possible to observe backward - * values within two consecutive reads. - * - * This time is measured via accounting rather than sampling, - * and is as accurate as ktime_get() is. - * - * Return: -1 if NOHZ is not enabled, else total iowait time of @cpu - */ -u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) -{ - struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); - - return get_cpu_sleep_time_us(ts, &ts->iowait_sleeptime, - nr_iowait_cpu(cpu), last_update_time); -} -EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us); - /* Simplified variant of hrtimer_forward_now() */ static ktime_t tick_forward_now(ktime_t expires, ktime_t now) { @@ -1273,7 +1158,7 @@ void tick_nohz_idle_stop_tick(void) ts->idle_expires = expires; if (!was_stopped && tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { - ts->idle_jiffies = ts->last_jiffies; + kcpustat_dyntick_start(ts->idle_entrytime); nohz_balance_enter_idle(cpu); } } else { @@ -1286,6 +1171,20 @@ void tick_nohz_idle_retain_tick(void) tick_nohz_retain_tick(this_cpu_ptr(&tick_cpu_sched)); } +static void tick_nohz_clock_sleep(struct tick_sched *ts) +{ + tick_sched_flag_set(ts, TS_FLAG_IDLE_ACTIVE); + sched_clock_idle_sleep_event(); +} + +static void tick_nohz_clock_wakeup(struct tick_sched *ts) +{ + if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE)) { + tick_sched_flag_clear(ts, TS_FLAG_IDLE_ACTIVE); + sched_clock_idle_wakeup_event(); + } +} + /** * tick_nohz_idle_enter - prepare for entering idle on the current CPU * @@ -1300,11 +1199,10 @@ void tick_nohz_idle_enter(void) local_irq_disable(); ts = this_cpu_ptr(&tick_cpu_sched); - WARN_ON_ONCE(ts->timer_expires_base); - tick_sched_flag_set(ts, TS_FLAG_INIDLE); - tick_nohz_start_idle(ts); + ts->idle_entrytime = ktime_get(); + tick_nohz_clock_sleep(ts); local_irq_enable(); } @@ -1332,10 +1230,14 @@ void tick_nohz_irq_exit(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); - if (tick_sched_flag_test(ts, TS_FLAG_INIDLE)) - tick_nohz_start_idle(ts); - else + if (tick_sched_flag_test(ts, TS_FLAG_INIDLE)) { + tick_nohz_clock_sleep(ts); + ts->idle_entrytime = ktime_get(); + if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) + kcpustat_irq_exit(ts->idle_entrytime); + } else { tick_nohz_full_update_tick(ts); + } } /** @@ -1407,8 +1309,7 @@ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) * If the next highres timer to expire is earlier than 'next_event', the * idle governor needs to know that. */ - next_event = min_t(u64, next_event, - hrtimer_next_event_without(&ts->sched_timer)); + next_event = min(next_event, hrtimer_next_event_without(&ts->sched_timer)); return ktime_sub(next_event, now); } @@ -1429,36 +1330,20 @@ unsigned long tick_nohz_get_idle_calls_cpu(int cpu) return ts->idle_calls; } -static void tick_nohz_account_idle_time(struct tick_sched *ts, - ktime_t now) -{ - unsigned long ticks; - - ts->idle_exittime = now; - - if (vtime_accounting_enabled_this_cpu()) - return; - /* - * We stopped the tick in idle. update_process_times() would miss the - * time we slept, as it does only a 1 tick accounting. - * Enforce that this is accounted to idle ! - */ - ticks = jiffies - ts->idle_jiffies; - /* - * We might be one off. Do not randomly account a huge number of ticks! - */ - if (ticks && ticks < LONG_MAX) - account_idle_ticks(ticks); -} - void tick_nohz_idle_restart_tick(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { - ktime_t now = ktime_get(); - tick_nohz_restart_sched_tick(ts, now); - tick_nohz_account_idle_time(ts, now); + /* + * Update entrytime here in case the tick restart is due to temporary + * polling on forced broadcast. The tick may be stopped again later within + * the same idle trip. The idle_entrytime was updated recently but make sure + * no tiny amount of idle time is accounted twice. + */ + ts->idle_entrytime = ktime_get(); + kcpustat_dyntick_stop(ts->idle_entrytime); + tick_nohz_restart_sched_tick(ts, ts->idle_entrytime); } } @@ -1468,8 +1353,6 @@ static void tick_nohz_idle_update_tick(struct tick_sched *ts, ktime_t now) __tick_nohz_full_update_tick(ts, now); else tick_nohz_restart_sched_tick(ts, now); - - tick_nohz_account_idle_time(ts, now); } /** @@ -1491,7 +1374,6 @@ static void tick_nohz_idle_update_tick(struct tick_sched *ts, ktime_t now) void tick_nohz_idle_exit(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); - bool idle_active, tick_stopped; ktime_t now; local_irq_disable(); @@ -1500,17 +1382,13 @@ void tick_nohz_idle_exit(void) WARN_ON_ONCE(ts->timer_expires_base); tick_sched_flag_clear(ts, TS_FLAG_INIDLE); - idle_active = tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE); - tick_stopped = tick_sched_flag_test(ts, TS_FLAG_STOPPED); + tick_nohz_clock_wakeup(ts); - if (idle_active || tick_stopped) + if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { now = ktime_get(); - - if (idle_active) - tick_nohz_stop_idle(ts, now); - - if (tick_stopped) + kcpustat_dyntick_stop(now); tick_nohz_idle_update_tick(ts, now); + } local_irq_enable(); } @@ -1565,11 +1443,14 @@ static inline void tick_nohz_irq_enter(void) struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); ktime_t now; - if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED | TS_FLAG_IDLE_ACTIVE)) + tick_nohz_clock_wakeup(ts); + + if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED)) return; + now = ktime_get(); - if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE)) - tick_nohz_stop_idle(ts, now); + kcpustat_irq_enter(now); + /* * If all CPUs are idle we may need to update a stale jiffies value. * Note nohz_full is a special case: a timekeeper is guaranteed to stay @@ -1577,8 +1458,7 @@ static inline void tick_nohz_irq_enter(void) * rare case (typically stop machine). So we must make sure we have a * last resort. */ - if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) - tick_nohz_update_jiffies(now); + tick_nohz_update_jiffies(now); } #else @@ -1648,20 +1528,15 @@ void tick_setup_sched_timer(bool hrtimer) void tick_sched_timer_dying(int cpu) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); - ktime_t idle_sleeptime, iowait_sleeptime; unsigned long idle_calls, idle_sleeps; /* This must happen before hrtimers are migrated! */ if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) hrtimer_cancel(&ts->sched_timer); - idle_sleeptime = ts->idle_sleeptime; - iowait_sleeptime = ts->iowait_sleeptime; idle_calls = ts->idle_calls; idle_sleeps = ts->idle_sleeps; memset(ts, 0, sizeof(*ts)); - ts->idle_sleeptime = idle_sleeptime; - ts->iowait_sleeptime = iowait_sleeptime; ts->idle_calls = idle_calls; ts->idle_sleeps = idle_sleeps; } diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index b4a7822f495d..79b9252047b1 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -44,9 +44,7 @@ struct tick_device { * to resume the tick timer operation in the timeline * when the CPU returns from nohz sleep. * @next_tick: Next tick to be fired when in dynticks mode. - * @idle_jiffies: jiffies at the entry to idle for idle time accounting * @idle_waketime: Time when the idle was interrupted - * @idle_sleeptime_seq: sequence counter for data consistency * @idle_entrytime: Time when the idle call was entered * @last_jiffies: Base jiffies snapshot when next event was last computed * @timer_expires_base: Base time clock monotonic for @timer_expires @@ -55,9 +53,6 @@ struct tick_device { * @idle_expires: Next tick in idle, for debugging purpose only * @idle_calls: Total number of idle calls * @idle_sleeps: Number of idle calls, where the sched tick was stopped - * @idle_exittime: Time when the idle state was left - * @idle_sleeptime: Sum of the time slept in idle with sched tick stopped - * @iowait_sleeptime: Sum of the time slept in idle with sched tick stopped, with IO outstanding * @tick_dep_mask: Tick dependency mask - is set, if someone needs the tick * @check_clocks: Notification mechanism about clocksource changes */ @@ -73,12 +68,10 @@ struct tick_sched { struct hrtimer sched_timer; ktime_t last_tick; ktime_t next_tick; - unsigned long idle_jiffies; ktime_t idle_waketime; unsigned int got_idle_tick; /* Idle entry */ - seqcount_t idle_sleeptime_seq; ktime_t idle_entrytime; /* Tick stop */ @@ -90,11 +83,6 @@ struct tick_sched { unsigned long idle_calls; unsigned long idle_sleeps; - /* Idle exit */ - ktime_t idle_exittime; - ktime_t idle_sleeptime; - ktime_t iowait_sleeptime; - /* Full dynticks handling */ atomic_t tick_dep_mask; diff --git a/kernel/time/time.c b/kernel/time/time.c index 0d832317d576..771cef87ad3b 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -207,7 +207,7 @@ SYSCALL_DEFINE2(settimeofday, struct __kernel_old_timeval __user *, tv, get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; - if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) + if (new_ts.tv_nsec >= USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; new_ts.tv_nsec *= NSEC_PER_USEC; diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index c493a4010305..0d5b67f609bb 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -67,6 +67,7 @@ static inline bool tk_is_aux(const struct timekeeper *tk) { return tk->id >= TIMEKEEPER_AUX_FIRST && tk->id <= TIMEKEEPER_AUX_LAST; } +static inline struct tk_data *aux_get_tk_data(clockid_t id); #else static inline bool tk_get_aux_ts64(unsigned int tkid, struct timespec64 *ts) { @@ -77,6 +78,10 @@ static inline bool tk_is_aux(const struct timekeeper *tk) { return false; } +static inline struct tk_data *aux_get_tk_data(clockid_t id) +{ + return NULL; +} #endif static inline void tk_update_aux_offs(struct timekeeper *tk, ktime_t offs) @@ -315,6 +320,7 @@ static __always_inline u64 tk_clock_read(const struct tk_read_base *tkr) return clock->read(clock); } + static inline void clocksource_disable_inline_read(void) { } static inline void clocksource_enable_inline_read(void) { } #endif @@ -1182,44 +1188,107 @@ noinstr time64_t __ktime_get_real_seconds(void) return tk->xtime_sec; } -/** - * ktime_get_snapshot - snapshots the realtime/monotonic raw clocks with counter - * @systime_snapshot: pointer to struct receiving the system time snapshot - */ -void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) +static inline u64 tk_clock_read_snapshot(const struct tk_read_base *tkr, + struct clocksource_hw_snapshot *chs) { - struct timekeeper *tk = &tk_core.timekeeper; + struct clocksource *clock = READ_ONCE(tkr->clock); + + if (unlikely(clock->read_snapshot)) + return clock->read_snapshot(clock, chs); + + return clock->read(clock); +} + + +/** + * ktime_get_snapshot_id - Simultaneously snapshot a given clock ID with + * CLOCK_MONOTONIC_RAW and the underlying + * clocksource counter value. + * @clock_id: The clock ID to snapshot + * @systime_snapshot: Pointer to struct receiving the system time snapshot + */ +void ktime_get_snapshot_id(clockid_t clock_id, struct system_time_snapshot *systime_snapshot) +{ + ktime_t base_raw, base_sys, offs_sys, *offs, offs_zero = 0; + u64 nsec_raw, nsec_sys, now; + struct timekeeper *tk; + struct tk_data *tkd; unsigned int seq; - ktime_t base_raw; - ktime_t base_real; - ktime_t base_boot; - u64 nsec_raw; - u64 nsec_real; - u64 now; - WARN_ON_ONCE(timekeeping_suspended); + /* Invalidate the snapshot for all failure cases */ + systime_snapshot->valid = false; + + if (WARN_ON_ONCE(timekeeping_suspended)) + return; + + switch (clock_id) { + case CLOCK_REALTIME: + tkd = &tk_core; + offs = &tk_core.timekeeper.offs_real; + break; + /* Map RAW to MONOTONIC so the loop below is trivial */ + case CLOCK_MONOTONIC_RAW: + case CLOCK_MONOTONIC: + tkd = &tk_core; + offs = &offs_zero; + break; + case CLOCK_BOOTTIME: + tkd = &tk_core; + offs = &tk_core.timekeeper.offs_boot; + break; + case CLOCK_AUX ... CLOCK_AUX_LAST: + tkd = aux_get_tk_data(clock_id); + if (!tkd) + return; + offs = &tkd->timekeeper.offs_aux; + break; + default: + WARN_ON_ONCE(1); + return; + } + + tk = &tkd->timekeeper; do { - seq = read_seqcount_begin(&tk_core.seq); - now = tk_clock_read(&tk->tkr_mono); + struct clocksource_hw_snapshot chs = { }; + + seq = read_seqcount_begin(&tkd->seq); + + /* Aux clocks can be invalid */ + if (!tk->clock_valid) + return; + + now = tk_clock_read_snapshot(&tk->tkr_mono, &chs); systime_snapshot->cs_id = tk->tkr_mono.clock->id; + + systime_snapshot->hw_cycles = chs.hw_cycles; + systime_snapshot->hw_csid = chs.hw_csid; + systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq; systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; - base_real = ktime_add(tk->tkr_mono.base, - tk_core.timekeeper.offs_real); - base_boot = ktime_add(tk->tkr_mono.base, - tk_core.timekeeper.offs_boot); + + base_sys = tk->tkr_mono.base; + offs_sys = *offs; base_raw = tk->tkr_raw.base; - nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now); - nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now); - } while (read_seqcount_retry(&tk_core.seq, seq)); + + nsec_sys = timekeeping_cycles_to_ns(&tk->tkr_mono, now); + nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now); + } while (read_seqcount_retry(&tkd->seq, seq)); systime_snapshot->cycles = now; - systime_snapshot->real = ktime_add_ns(base_real, nsec_real); - systime_snapshot->boot = ktime_add_ns(base_boot, nsec_real); - systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw); + systime_snapshot->systime = ktime_add_ns(base_sys, offs_sys + nsec_sys); + systime_snapshot->monoraw = ktime_add_ns(base_raw, nsec_raw); + + /* + * Special case for PTP. Just transfer the raw time into sys, + * so the call sites can consistently use snap::systime. + */ + if (clock_id == CLOCK_MONOTONIC_RAW) + systime_snapshot->systime = systime_snapshot->monoraw; + /* Tell the consumer that this snapshot is valid */ + systime_snapshot->valid = true; } -EXPORT_SYMBOL_GPL(ktime_get_snapshot); +EXPORT_SYMBOL_GPL(ktime_get_snapshot_id); /* Scale base by mult/div checking for overflow */ static int scale64_check_overflow(u64 mult, u64 div, u64 *base) @@ -1262,7 +1331,7 @@ static int adjust_historical_crosststamp(struct system_time_snapshot *history, struct system_device_crosststamp *ts) { struct timekeeper *tk = &tk_core.timekeeper; - u64 corr_raw, corr_real; + u64 corr_raw, corr_sys; bool interp_forward; int ret; @@ -1279,8 +1348,7 @@ static int adjust_historical_crosststamp(struct system_time_snapshot *history, * Scale the monotonic raw time delta by: * partial_history_cycles / total_history_cycles */ - corr_raw = (u64)ktime_to_ns( - ktime_sub(ts->sys_monoraw, history->raw)); + corr_raw = (u64)ktime_to_ns(ktime_sub(ts->sys_monoraw, history->monoraw)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_raw); if (ret) @@ -1288,30 +1356,29 @@ static int adjust_historical_crosststamp(struct system_time_snapshot *history, /* * If there is a discontinuity in the history, scale monotonic raw - * correction by: - * mult(real)/mult(raw) yielding the realtime correction - * Otherwise, calculate the realtime correction similar to monotonic - * raw calculation + * correction by: + * mult(sys)/mult(raw) yielding the system time correction + * + * Otherwise, calculate the system time correction similar to monotonic + * raw calculation */ if (discontinuity) { - corr_real = mul_u64_u32_div - (corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult); + corr_sys = mul_u64_u32_div(corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult); } else { - corr_real = (u64)ktime_to_ns( - ktime_sub(ts->sys_realtime, history->real)); - ret = scale64_check_overflow(partial_history_cycles, - total_history_cycles, &corr_real); + corr_sys = (u64)ktime_to_ns(ktime_sub(ts->sys_systime, history->systime)); + ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, + &corr_sys); if (ret) return ret; } - /* Fixup monotonic raw and real time time values */ + /* Fixup monotonic raw and system time time values */ if (interp_forward) { - ts->sys_monoraw = ktime_add_ns(history->raw, corr_raw); - ts->sys_realtime = ktime_add_ns(history->real, corr_real); + ts->sys_monoraw = ktime_add_ns(history->monoraw, corr_raw); + ts->sys_systime = ktime_add_ns(history->systime, corr_sys); } else { ts->sys_monoraw = ktime_sub_ns(ts->sys_monoraw, corr_raw); - ts->sys_realtime = ktime_sub_ns(ts->sys_realtime, corr_real); + ts->sys_systime = ktime_sub_ns(ts->sys_systime, corr_sys); } return 0; @@ -1368,6 +1435,8 @@ static bool convert_base_to_cs(struct system_counterval_t *scv) return false; scv->cycles += base->offset; + /* Set the clocksource ID as scv::cycles is now clocksource based */ + scv->cs_id = cs->id; return true; } @@ -1435,11 +1504,11 @@ EXPORT_SYMBOL_GPL(ktime_real_to_base_clock); /** * get_device_system_crosststamp - Synchronously capture system/device timestamp - * @get_time_fn: Callback to get simultaneous device time and - * system counter from the device driver + * @get_time_fn: Callback to get simultaneous device time and system counter + * from the device driver * @ctx: Context passed to get_time_fn() - * @history_begin: Historical reference point used to interpolate system - * time when counter provided by the driver is before the current interval + * @history_begin: Historical reference point used to interpolate system time when + * the counter value provided by the driver is before the current interval * @xtstamp: Receives simultaneously captured system and device time * * Reads a timestamp from a device and correlates it to system time @@ -1452,36 +1521,54 @@ int get_device_system_crosststamp(int (*get_time_fn) struct system_time_snapshot *history_begin, struct system_device_crosststamp *xtstamp) { - struct system_counterval_t system_counterval = {}; - struct timekeeper *tk = &tk_core.timekeeper; - u64 cycles, now, interval_start; - unsigned int clock_was_set_seq = 0; - ktime_t base_real, base_raw; - u64 nsec_real, nsec_raw; + u64 syscnt_cycles, cycles, now, interval_start; + unsigned int seq, clock_was_set_seq = 0; + ktime_t base_sys, base_raw, *offs; + u64 nsec_sys, nsec_raw; u8 cs_was_changed_seq; - unsigned int seq; bool do_interp; + struct timekeeper *tk; + struct tk_data *tkd; int ret; + switch (xtstamp->clock_id) { + case CLOCK_REALTIME: + tkd = &tk_core; + offs = &tk_core.timekeeper.offs_real; + break; + case CLOCK_AUX ... CLOCK_AUX_LAST: + tkd = aux_get_tk_data(xtstamp->clock_id); + if (!tkd) + return -ENODEV; + offs = &tkd->timekeeper.offs_aux; + break; + default: + WARN_ON_ONCE(1); + return -ENODEV; + } + + tk = &tkd->timekeeper; + do { - seq = read_seqcount_begin(&tk_core.seq); + seq = read_seqcount_begin(&tkd->seq); /* * Try to synchronously capture device time and a system * counter value calling back into the device driver */ - ret = get_time_fn(&xtstamp->device, &system_counterval, ctx); + ret = get_time_fn(&xtstamp->device, &xtstamp->sys_counter, ctx); if (ret) return ret; /* * Verify that the clocksource ID associated with the captured * system counter value is the same as for the currently - * installed timekeeper clocksource + * installed timekeeper clocksource and convert to it. */ - if (system_counterval.cs_id == CSID_GENERIC || - !convert_base_to_cs(&system_counterval)) + if (xtstamp->sys_counter.cs_id == CSID_GENERIC || + !convert_base_to_cs(&xtstamp->sys_counter)) return -ENODEV; - cycles = system_counterval.cycles; + + cycles = syscnt_cycles = xtstamp->sys_counter.cycles; /* * Check whether the system counter value provided by the @@ -1498,15 +1585,14 @@ int get_device_system_crosststamp(int (*get_time_fn) do_interp = false; } - base_real = ktime_add(tk->tkr_mono.base, - tk_core.timekeeper.offs_real); + base_sys = ktime_add(tk->tkr_mono.base, *offs); base_raw = tk->tkr_raw.base; - nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles); + nsec_sys = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, cycles); - } while (read_seqcount_retry(&tk_core.seq, seq)); + } while (read_seqcount_retry(&tkd->seq, seq)); - xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real); + xtstamp->sys_systime = ktime_add_ns(base_sys, nsec_sys); xtstamp->sys_monoraw = ktime_add_ns(base_raw, nsec_raw); /* @@ -1523,24 +1609,19 @@ int get_device_system_crosststamp(int (*get_time_fn) * clocksource change */ if (!history_begin || - !timestamp_in_interval(history_begin->cycles, - cycles, system_counterval.cycles) || + !timestamp_in_interval(history_begin->cycles, cycles, syscnt_cycles) || history_begin->cs_was_changed_seq != cs_was_changed_seq) return -EINVAL; - partial_history_cycles = cycles - system_counterval.cycles; + + partial_history_cycles = cycles - syscnt_cycles; total_history_cycles = cycles - history_begin->cycles; - discontinuity = - history_begin->clock_was_set_seq != clock_was_set_seq; + discontinuity = history_begin->clock_was_set_seq != clock_was_set_seq; - ret = adjust_historical_crosststamp(history_begin, - partial_history_cycles, - total_history_cycles, - discontinuity, xtstamp); - if (ret) - return ret; + ret = adjust_historical_crosststamp(history_begin, partial_history_cycles, + total_history_cycles, discontinuity, xtstamp); } - return 0; + return ret; } EXPORT_SYMBOL_GPL(get_device_system_crosststamp); diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 04d928c21aba..655a8c6cd84d 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1932,7 +1932,7 @@ static void timer_recalc_next_expiry(struct timer_base *base) */ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires) { - u64 nextevt = hrtimer_get_next_event(); + u64 nextevt = ktime_to_ns(hrtimer_get_next_event()); /* * If high resolution timers are enabled diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index 427d7ddea3af..514802def1e0 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -152,14 +152,10 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now) P_flag(highres, TS_FLAG_HIGHRES); P_ns(last_tick); P_flag(tick_stopped, TS_FLAG_STOPPED); - P(idle_jiffies); P(idle_calls); P(idle_sleeps); P_ns(idle_entrytime); P_ns(idle_waketime); - P_ns(idle_exittime); - P_ns(idle_sleeptime); - P_ns(iowait_sleeptime); P(last_jiffies); P(next_timer); P_ns(idle_expires); @@ -256,7 +252,7 @@ static void timer_list_show_tickdevices_header(struct seq_file *m) static inline void timer_list_header(struct seq_file *m, u64 now) { - SEQ_printf(m, "Timer List Version: v0.10\n"); + SEQ_printf(m, "Timer List Version: v0.11\n"); SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES); SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now); SEQ_printf(m, "\n"); diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index 1d0d3a4058d5..806c23cf71fc 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -102,7 +102,7 @@ * active CPU/group information atomic_try_cmpxchg() is used instead and only * the per CPU tmigr_cpu->lock is held. * - * During the setup of groups tmigr_level_list is required. It is protected by + * During the setup of groups, hier->level_list is required. It is protected by * @tmigr_mutex. * * When @timer_base->lock as well as tmigr related locks are required, the lock @@ -416,13 +416,12 @@ */ static DEFINE_MUTEX(tmigr_mutex); -static struct list_head *tmigr_level_list __read_mostly; + +static LIST_HEAD(tmigr_hierarchy_list); static unsigned int tmigr_hierarchy_levels __read_mostly; static unsigned int tmigr_crossnode_level __read_mostly; -static struct tmigr_group *tmigr_root; - static DEFINE_PER_CPU(struct tmigr_cpu, tmigr_cpu); /* @@ -978,8 +977,12 @@ static void tmigr_handle_remote_cpu(unsigned int cpu, u64 now, /* Drop the lock to allow the remote CPU to exit idle */ raw_spin_unlock_irq(&tmc->lock); - if (cpu != smp_processor_id()) - timer_expire_remote(cpu); + /* + * This can't exclude the local CPU because jiffies might have advanced + * after the timer softirq invoked run_timer_base(BASE_GLOBAL) and the + * point where the jiffies snapshot @jif was taken in tmigr_handle_remote(). + */ + timer_expire_remote(cpu); /* * Lock ordering needs to be preserved - timer_base locks before tmigr @@ -1465,6 +1468,34 @@ static long tmigr_trigger_active(void *unused) return 0; } +static unsigned int tmigr_get_capacity(int cpu) +{ + /* + * nohz_full CPUs need to make sure there is always an available (online) + * and never idle migrator to handle all their global timers. That duty + * is served by the timekeeper which then never stops its tick. But the + * timekeeper must then belong to the same hierarchy as all the nohz_full + * CPUs. Simply turn off capacity awareness when nohz_full is running. + */ + if (tick_nohz_full_enabled() || !IS_ENABLED(CONFIG_BROKEN)) + return SCHED_CAPACITY_SCALE; + else + return arch_scale_cpu_capacity(cpu); +} + +static struct tmigr_hierarchy *__tmigr_get_hierarchy(int cpu) +{ + unsigned int capacity = tmigr_get_capacity(cpu); + struct tmigr_hierarchy *iter; + + list_for_each_entry(iter, &tmigr_hierarchy_list, node) { + if (iter->capacity == capacity) + return iter; + } + + return NULL; +} + static int tmigr_clear_cpu_available(unsigned int cpu) { struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); @@ -1489,8 +1520,21 @@ static int tmigr_clear_cpu_available(unsigned int cpu) } if (firstexp != KTIME_MAX) { - migrator = cpumask_any(tmigr_available_cpumask); - work_on_cpu(migrator, tmigr_trigger_active, NULL); + struct tmigr_hierarchy *hier = __tmigr_get_hierarchy(cpu); + + if (WARN_ON_ONCE(!hier)) + return -EINVAL; + + migrator = cpumask_any_and(tmigr_available_cpumask, hier->cpumask); + if (migrator < nr_cpu_ids) { + work_on_cpu(migrator, tmigr_trigger_active, NULL); + } else { + /* + * If deactivation returned an expiration, it belongs to an available + * nohz CPU in the hierarchy. + */ + WARN_ONCE(1, "Expected available CPU in the hierarchy\n"); + } } return 0; @@ -1653,14 +1697,14 @@ static void tmigr_init_group(struct tmigr_group *group, unsigned int lvl, group->groupevt.ignore = true; } -static struct tmigr_group *tmigr_get_group(int node, unsigned int lvl) +static struct tmigr_group *tmigr_get_group(struct tmigr_hierarchy *hier, int node, unsigned int lvl) { struct tmigr_group *tmp, *group = NULL; lockdep_assert_held(&tmigr_mutex); /* Try to attach to an existing group first */ - list_for_each_entry(tmp, &tmigr_level_list[lvl], list) { + list_for_each_entry(tmp, &hier->level_list[lvl], list) { /* * If @lvl is below the cross NUMA node level, check whether * this group belongs to the same NUMA node. @@ -1694,14 +1738,14 @@ static struct tmigr_group *tmigr_get_group(int node, unsigned int lvl) tmigr_init_group(group, lvl, node); /* Setup successful. Add it to the hierarchy */ - list_add(&group->list, &tmigr_level_list[lvl]); + list_add(&group->list, &hier->level_list[lvl]); trace_tmigr_group_set(group); return group; } -static bool tmigr_init_root(struct tmigr_group *group, bool activate) +static bool tmigr_init_root(struct tmigr_hierarchy *hier, struct tmigr_group *group, bool activate) { - if (!group->parent && group != tmigr_root) { + if (!group->parent && group != hier->root) { /* * This is the new top-level, prepare its groupmask in advance * to avoid accidents where yet another new top-level is @@ -1717,11 +1761,10 @@ static bool tmigr_init_root(struct tmigr_group *group, bool activate) } -static void tmigr_connect_child_parent(struct tmigr_group *child, - struct tmigr_group *parent, - bool activate) +static void tmigr_connect_child_parent(struct tmigr_hierarchy *hier, struct tmigr_group *child, + struct tmigr_group *parent, bool activate) { - if (tmigr_init_root(parent, activate)) { + if (tmigr_init_root(hier, parent, activate)) { /* * The previous top level had prepared its groupmask already, * simply account it in advance as the first child. If some groups @@ -1754,13 +1797,13 @@ static void tmigr_connect_child_parent(struct tmigr_group *child, */ smp_store_release(&child->parent, parent); - trace_tmigr_connect_child_parent(child); + trace_tmigr_connect_child_parent(hier, child); } -static int tmigr_setup_groups(unsigned int cpu, unsigned int node, - struct tmigr_group *start, bool activate) +static int tmigr_setup_groups(struct tmigr_hierarchy *hier, unsigned int cpu, + unsigned int node, struct tmigr_group *start, bool activate) { - struct tmigr_group *group, *child, **stack; + struct tmigr_group *root = hier->root, *group, *child, **stack; int i, top = 0, err = 0, start_lvl = 0; bool root_mismatch = false; @@ -1773,11 +1816,11 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node, start_lvl = start->level + 1; } - if (tmigr_root) - root_mismatch = tmigr_root->numa_node != node; + if (root) + root_mismatch = root->numa_node != node; for (i = start_lvl; i < tmigr_hierarchy_levels; i++) { - group = tmigr_get_group(node, i); + group = tmigr_get_group(hier, node, i); if (IS_ERR(group)) { err = PTR_ERR(group); i--; @@ -1799,7 +1842,7 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node, if (group->parent) break; if ((!root_mismatch || i >= tmigr_crossnode_level) && - list_is_singular(&tmigr_level_list[i])) + list_is_singular(&hier->level_list[i])) break; } @@ -1827,15 +1870,15 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node, tmc->tmgroup = group; tmc->groupmask = BIT(group->num_children++); - tmigr_init_root(group, activate); + tmigr_init_root(hier, group, activate); - trace_tmigr_connect_cpu_parent(tmc); + trace_tmigr_connect_cpu_parent(hier, tmc); /* There are no children that need to be connected */ continue; } else { child = stack[i - 1]; - tmigr_connect_child_parent(child, group, activate); + tmigr_connect_child_parent(hier, child, group, activate); } } @@ -1891,18 +1934,23 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node, data.childmask = start->groupmask; __walk_groups_from(tmigr_active_up, &data, start, start->parent); } + } else if (start) { + union tmigr_state state; + + /* Remote activation assumes the whole target's hierarchy is inactive */ + state.state = atomic_read(&start->migr_state); + WARN_ON_ONCE(state.active); } /* Root update */ - if (list_is_singular(&tmigr_level_list[top])) { - group = list_first_entry(&tmigr_level_list[top], - typeof(*group), list); + if (list_is_singular(&hier->level_list[top])) { + group = list_first_entry(&hier->level_list[top], typeof(*group), list); WARN_ON_ONCE(group->parent); - if (tmigr_root) { + if (root) { /* Old root should be the same or below */ - WARN_ON_ONCE(tmigr_root->level > top); + WARN_ON_ONCE(root->level > top); } - tmigr_root = group; + hier->root = group; } out: kfree(stack); @@ -1910,34 +1958,123 @@ out: return err; } +static struct tmigr_hierarchy *tmigr_get_hierarchy(int cpu) +{ + struct tmigr_hierarchy *hier; + + hier = __tmigr_get_hierarchy(cpu); + + if (hier) + return hier; + + hier = kzalloc_flex(*hier, level_list, tmigr_hierarchy_levels); + if (!hier) + return ERR_PTR(-ENOMEM); + + hier->cpumask = kzalloc(cpumask_size(), GFP_KERNEL); + if (!hier->cpumask) { + kfree(hier); + return ERR_PTR(-ENOMEM); + } + + for (int i = 0; i < tmigr_hierarchy_levels; i++) + INIT_LIST_HEAD(&hier->level_list[i]); + + hier->capacity = tmigr_get_capacity(cpu); + list_add_tail(&hier->node, &tmigr_hierarchy_list); + + return hier; +} + +static int tmigr_connect_old_root(struct tmigr_hierarchy *hier, int cpu, + struct tmigr_group *old_root, bool activate) +{ + /* + * The target CPU must never do the prepare work, except + * on early boot when the boot CPU is the target. Otherwise + * it may spuriously activate the old top level group inside + * the new one (nevertheless whether old top level group is + * active or not) and/or release an uninitialized childmask. + */ + WARN_ON_ONCE(cpu == smp_processor_id()); + if (activate) { + /* + * The current CPU is expected to be online in the hierarchy, + * otherwise the old root may not be active as expected. + */ + WARN_ON_ONCE(!__this_cpu_read(tmigr_cpu.available)); + } + + return tmigr_setup_groups(hier, -1, old_root->numa_node, old_root, activate); +} + +static long connect_old_root_work(void *arg) +{ + struct tmigr_group *old_root = arg; + struct tmigr_hierarchy *hier; + int cpu = smp_processor_id(); + + hier = __tmigr_get_hierarchy(cpu); + if (WARN_ON_ONCE(!hier)) + return -EINVAL; + + return tmigr_connect_old_root(hier, cpu, old_root, true); +} + static int tmigr_add_cpu(unsigned int cpu) { - struct tmigr_group *old_root = tmigr_root; + struct tmigr_hierarchy *hier; + struct tmigr_group *old_root; int node = cpu_to_node(cpu); int ret; guard(mutex)(&tmigr_mutex); - ret = tmigr_setup_groups(cpu, node, NULL, false); + hier = tmigr_get_hierarchy(cpu); + if (IS_ERR(hier)) + return PTR_ERR(hier); + + old_root = hier->root; + + ret = tmigr_setup_groups(hier, cpu, node, NULL, false); + + if (ret < 0) + return ret; /* Root has changed? Connect the old one to the new */ - if (ret >= 0 && old_root && old_root != tmigr_root) { - /* - * The target CPU must never do the prepare work, except - * on early boot when the boot CPU is the target. Otherwise - * it may spuriously activate the old top level group inside - * the new one (nevertheless whether old top level group is - * active or not) and/or release an uninitialized childmask. - */ - WARN_ON_ONCE(cpu == raw_smp_processor_id()); - /* - * The (likely) current CPU is expected to be online in the hierarchy, - * otherwise the old root may not be active as expected. - */ - WARN_ON_ONCE(!per_cpu_ptr(&tmigr_cpu, raw_smp_processor_id())->available); - ret = tmigr_setup_groups(-1, old_root->numa_node, old_root, true); + if (old_root && old_root != hier->root) { + guard(migrate)(); + + if (cpumask_test_cpu(smp_processor_id(), hier->cpumask)) { + /* + * If the target belong to the same hierarchy, the old root is expected + * to be active. Link and propagate to the new root. + */ + ret = tmigr_connect_old_root(hier, cpu, old_root, true); + } else { + int target = cpumask_first_and(hier->cpumask, tmigr_available_cpumask); + + if (target < nr_cpu_ids) { + /* + * If the target doesn't belong to the same hierarchy as the current + * CPU, activate from a relevant one to make sure the old root is + * active. + */ + ret = work_on_cpu(target, connect_old_root_work, old_root); + } else { + /* + * No other available CPUs in the remote hierarchy. Link the + * old root remotely but don't propagate activation since the + * old root is not expected to be active. + */ + ret = tmigr_connect_old_root(hier, cpu, old_root, false); + } + } } + if (ret >= 0) + cpumask_set_cpu(cpu, hier->cpumask); + return ret; } @@ -1970,7 +2107,7 @@ static int tmigr_cpu_prepare(unsigned int cpu) static int __init tmigr_init(void) { - unsigned int cpulvl, nodelvl, cpus_per_node, i; + unsigned int cpulvl, nodelvl, cpus_per_node; unsigned int nnodes = num_possible_nodes(); unsigned int ncpus = num_possible_cpus(); int ret = -ENOMEM; @@ -2017,14 +2154,6 @@ static int __init tmigr_init(void) */ tmigr_crossnode_level = cpulvl; - tmigr_level_list = kzalloc_objs(struct list_head, - tmigr_hierarchy_levels); - if (!tmigr_level_list) - goto err; - - for (i = 0; i < tmigr_hierarchy_levels; i++) - INIT_LIST_HEAD(&tmigr_level_list[i]); - pr_info("Timer migration: %d hierarchy levels; %d children per group;" " %d crossnode level\n", tmigr_hierarchy_levels, TMIGR_CHILDREN_PER_GROUP, diff --git a/kernel/time/timer_migration.h b/kernel/time/timer_migration.h index 70879cde6fdd..31735dd52327 100644 --- a/kernel/time/timer_migration.h +++ b/kernel/time/timer_migration.h @@ -6,6 +6,24 @@ #define TMIGR_CHILDREN_PER_GROUP 8 /** + * struct tmigr_hierarchy - a hierarchy associated to a given CPU capacity. + * Homogeneous systems have only one hierarchy. + * Heterogenous have one hierarchy per CPU capacity. + * @cpumask: CPUs belonging to this hierarchy + * @root: The current root of the hierarchy + * @capacity: CPU capacity associated to this hierarchy + * @node: Node in the global hierarchy list + * @level_list: Per level lists of tmigr groups + */ +struct tmigr_hierarchy { + struct cpumask *cpumask; + struct tmigr_group *root; + unsigned long capacity; + struct list_head node; + struct list_head level_list[]; +}; + +/** * struct tmigr_event - a timer event associated to a CPU * @nextevt: The node to enqueue an event in the parent group queue * @cpu: The CPU to which this event belongs @@ -75,15 +93,17 @@ struct tmigr_group { /** * struct tmigr_cpu - timer migration per CPU group * @lock: Lock protecting the tmigr_cpu group information - * @online: Indicates whether the CPU is online; In deactivate path - * it is required to know whether the migrator in the top - * level group is to be set offline, while a timer is - * pending. Then another online CPU needs to be notified to - * take over the migrator role. Furthermore the information - * is required in CPU hotplug path as the CPU is able to go - * idle before the timer migration hierarchy hotplug AP is - * reached. During this phase, the CPU has to handle the + * @available: Indicates whether the CPU is available for handling + * global timers. In the deactivate path it is required to + * know whether the migrator in the top level group is to + * be set offline, while a timer is pending. Then another + * available CPU needs to be notified to take over the + * migrator role. Furthermore the information is required + * in the CPU hotplug path as the CPU is able to go idle + * before the timer migration hierarchy hotplug callback is + * reached. During this phase, the CPU has to handle the * global timers on its own and must not act as a migrator. + * @idle: Indicates whether the CPU is idle in the timer migration * hierarchy * @remote: Is set when timers of the CPU are expired remotely diff --git a/kernel/torture.c b/kernel/torture.c index 62c1ac777694..77cb3589b19f 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -972,3 +972,19 @@ void _torture_stop_kthread(char *m, struct task_struct **tp) *tp = NULL; } EXPORT_SYMBOL_GPL(_torture_stop_kthread); + +/* + * Set the specified task's niceness value, saturating at limits. + * Saturating noisily, but saturating. + */ +void torture_sched_set_normal(struct task_struct *t, int nice) +{ + int realnice = nice; + + if (WARN_ON_ONCE(realnice > MAX_NICE)) + realnice = MAX_NICE; + if (WARN_ON_ONCE(realnice < MIN_NICE)) + realnice = MIN_NICE; + sched_set_normal(t, realnice); +} +EXPORT_SYMBOL_GPL(torture_sched_set_normal); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 06fb365bb86e..56a328e94395 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3958,13 +3958,6 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer, return skip_time_extend(event); } -#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK -static inline bool sched_clock_stable(void) -{ - return true; -} -#endif - static void rb_check_timestamp(struct ring_buffer_per_cpu *cpu_buffer, struct rb_event_info *info) diff --git a/kernel/trace/rv/monitors/deadline/deadline.h b/kernel/trace/rv/monitors/deadline/deadline.h index 0bbfd2543329..78fca873d61e 100644 --- a/kernel/trace/rv/monitors/deadline/deadline.h +++ b/kernel/trace/rv/monitors/deadline/deadline.h @@ -95,7 +95,8 @@ static inline u8 get_server_type(struct task_struct *tsk) static inline int extract_params(struct pt_regs *regs, long id, pid_t *pid_out) { size_t size = offsetofend(struct sched_attr, sched_flags); - struct sched_attr __user *uattr, attr; + struct sched_attr __user *uattr; + struct sched_attr attr; int new_policy = -1, ret; unsigned long args[6]; diff --git a/kernel/trace/rv/monitors/nomiss/nomiss.c b/kernel/trace/rv/monitors/nomiss/nomiss.c index 31f90f3638d8..8ead8783c29f 100644 --- a/kernel/trace/rv/monitors/nomiss/nomiss.c +++ b/kernel/trace/rv/monitors/nomiss/nomiss.c @@ -227,7 +227,7 @@ static int enable_nomiss(void) { int retval; - retval = da_monitor_init(); + retval = ha_monitor_init(); if (retval) return retval; @@ -263,7 +263,7 @@ static void disable_nomiss(void) rv_detach_trace_probe("nomiss", sched_switch, handle_sched_switch); rv_detach_trace_probe("nomiss", sched_wakeup, handle_sched_wakeup); - da_monitor_destroy(); + ha_monitor_destroy(); } static struct rv_monitor rv_this = { diff --git a/kernel/trace/rv/monitors/opid/opid.c b/kernel/trace/rv/monitors/opid/opid.c index 4594c7c46601..3b6a85e815b8 100644 --- a/kernel/trace/rv/monitors/opid/opid.c +++ b/kernel/trace/rv/monitors/opid/opid.c @@ -22,14 +22,8 @@ static u64 ha_get_env(struct ha_monitor *ha_mon, enum envs_opid env, u64 time_ns if (env == irq_off_opid) return irqs_disabled(); else if (env == preempt_off_opid) { - /* - * 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 consider 1 as still enabled. - */ if (IS_ENABLED(CONFIG_PREEMPTION)) - return (preempt_count() & PREEMPT_MASK) > 1; + return (preempt_count() & PREEMPT_MASK) > 0; return true; } return ENV_INVALID_VALUE; @@ -73,7 +67,7 @@ static int enable_opid(void) { int retval; - retval = da_monitor_init(); + retval = ha_monitor_init(); if (retval) return retval; @@ -90,7 +84,7 @@ static void disable_opid(void) rv_detach_trace_probe("opid", sched_set_need_resched_tp, handle_sched_need_resched); rv_detach_trace_probe("opid", sched_waking, handle_sched_waking); - da_monitor_destroy(); + ha_monitor_destroy(); } /* diff --git a/kernel/trace/rv/monitors/stall/stall.c b/kernel/trace/rv/monitors/stall/stall.c index 9ccfda6b0e73..3c38fb1a0159 100644 --- a/kernel/trace/rv/monitors/stall/stall.c +++ b/kernel/trace/rv/monitors/stall/stall.c @@ -103,7 +103,7 @@ static int enable_stall(void) { int retval; - retval = da_monitor_init(); + retval = ha_monitor_init(); if (retval) return retval; @@ -120,7 +120,7 @@ static void disable_stall(void) rv_detach_trace_probe("stall", sched_switch, handle_sched_switch); rv_detach_trace_probe("stall", sched_wakeup, handle_sched_wakeup); - da_monitor_destroy(); + ha_monitor_destroy(); } static struct rv_monitor rv_this = { diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 33b721a9af02..0c265eac903a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -8212,11 +8212,7 @@ static bool __init cpus_dont_share(int cpu0, int cpu1) static bool __init cpus_share_smt(int cpu0, int cpu1) { -#ifdef CONFIG_SCHED_SMT return cpumask_test_cpu(cpu0, cpu_smt_mask(cpu1)); -#else - return false; -#endif } static bool __init cpus_share_numa(int cpu0, int cpu1) |