diff options
| author | Palmer Dabbelt <palmer@rivosinc.com> | 2025-03-26 15:54:12 -0700 |
|---|---|---|
| committer | Palmer Dabbelt <palmer@rivosinc.com> | 2025-03-26 15:54:12 -0700 |
| commit | df02351331671abb26788bc13f6d276e26ae068f (patch) | |
| tree | 4e1f8ee707cf6570f39feb47fc5bb151358ebd34 /kernel | |
| parent | 2014c95afecee3e76ca4a56956a936e23283f05b (diff) | |
| parent | 74f4bf9d15ad1d6862b828d486ed10ea0e874a23 (diff) | |
Merge tag 'riscv-mw1-6.15-rc1' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/alexghiti/linux into for-next
riscv patches for 6.15-rc1
* A bunch of fixes:
- We were missing a secondary mmu notifier call when flushing the tlb which is required for IOMMU
- Fix ftrace panics by saving the registers as expected by ftrace
- Fix a couple of stimecmp usage related to cpu hotplug
- Fix a bunch of issues in the misaligned probing handling
* Perf improvements:
- Introduce support for runtime constant improving perf of d_hash()
- Add support for huge pfnmaps to improve tlb utilization
- Use Zawrs to improve smp_cond_load8/16() used by the queued spinlocks
* Hwprobe additions:
- Add support for Zicntr and Zihpm
- Add support for Zaamo and Zalrsc
- Add support for bfloat16 extensiosn
- Add support for Zicbom (only enabling clean and flush, not inval for security reasons)
* Misc:
- Add a kernel parameter to bypass the misaligned speed probing since we can't rely on Zicclsm
* tag 'riscv-mw1-6.15-rc1' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/alexghiti/linux: (1585 commits)
riscv: Add runtime constant support
riscv: Move nop definition to insn-def.h
Documentation/kernel-parameters: Add riscv unaligned speed parameters
riscv: Add parameter for skipping access speed tests
riscv: Fix set up of vector cpu hotplug callback
riscv: Fix set up of cpu hotplug callbacks
riscv: Change check_unaligned_access_speed_all_cpus to void
riscv: Fix check_unaligned_access_all_cpus
riscv: Fix riscv_online_cpu_vec
riscv: Annotate unaligned access init functions
KVM: riscv: selftests: Add Zaamo/Zalrsc extensions to get-reg-list test
RISC-V: KVM: Allow Zaamo/Zalrsc extensions for Guest/VM
riscv: hwprobe: export Zaamo and Zalrsc extensions
riscv: add parsing for Zaamo and Zalrsc extensions
dt-bindings: riscv: add Zaamo and Zalrsc ISA extension description
riscv: fgraph: Fix stack layout to match __arch_ftrace_regs argument of ftrace_return_to_handler
riscv: fgraph: Select HAVE_FUNCTION_GRAPH_TRACER depends on HAVE_DYNAMIC_FTRACE_WITH_ARGS
riscv: Fix missing __free_pages() in check_vector_unaligned_access()
riscv: Fix the __riscv_copy_vec_words_unaligned implementation
riscv: mm: Don't use %pK through printk
...
Diffstat (limited to 'kernel')
47 files changed, 679 insertions, 356 deletions
diff --git a/kernel/acct.c b/kernel/acct.c index 31222e8cd534..6520baa13669 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -103,48 +103,50 @@ struct bsd_acct_struct { atomic_long_t count; struct rcu_head rcu; struct mutex lock; - int active; + bool active; + bool check_space; unsigned long needcheck; struct file *file; struct pid_namespace *ns; struct work_struct work; struct completion done; + acct_t ac; }; -static void do_acct_process(struct bsd_acct_struct *acct); +static void fill_ac(struct bsd_acct_struct *acct); +static void acct_write_process(struct bsd_acct_struct *acct); /* * Check the amount of free space and suspend/resume accordingly. */ -static int check_free_space(struct bsd_acct_struct *acct) +static bool check_free_space(struct bsd_acct_struct *acct) { struct kstatfs sbuf; - if (time_is_after_jiffies(acct->needcheck)) - goto out; + if (!acct->check_space) + return acct->active; /* May block */ if (vfs_statfs(&acct->file->f_path, &sbuf)) - goto out; + return acct->active; if (acct->active) { u64 suspend = sbuf.f_blocks * SUSPEND; do_div(suspend, 100); if (sbuf.f_bavail <= suspend) { - acct->active = 0; + acct->active = false; pr_info("Process accounting paused\n"); } } else { u64 resume = sbuf.f_blocks * RESUME; do_div(resume, 100); if (sbuf.f_bavail >= resume) { - acct->active = 1; + acct->active = true; pr_info("Process accounting resumed\n"); } } acct->needcheck = jiffies + ACCT_TIMEOUT*HZ; -out: return acct->active; } @@ -189,7 +191,11 @@ static void acct_pin_kill(struct fs_pin *pin) { struct bsd_acct_struct *acct = to_acct(pin); mutex_lock(&acct->lock); - do_acct_process(acct); + /* + * Fill the accounting struct with the exiting task's info + * before punting to the workqueue. + */ + fill_ac(acct); schedule_work(&acct->work); wait_for_completion(&acct->done); cmpxchg(&acct->ns->bacct, pin, NULL); @@ -202,6 +208,9 @@ static void close_work(struct work_struct *work) { struct bsd_acct_struct *acct = container_of(work, struct bsd_acct_struct, work); struct file *file = acct->file; + + /* We were fired by acct_pin_kill() which holds acct->lock. */ + acct_write_process(acct); if (file->f_op->flush) file->f_op->flush(file, NULL); __fput_sync(file); @@ -234,6 +243,20 @@ static int acct_on(struct filename *pathname) return -EACCES; } + /* Exclude kernel kernel internal filesystems. */ + if (file_inode(file)->i_sb->s_flags & (SB_NOUSER | SB_KERNMOUNT)) { + kfree(acct); + filp_close(file, NULL); + return -EINVAL; + } + + /* Exclude procfs and sysfs. */ + if (file_inode(file)->i_sb->s_iflags & SB_I_USERNS_VISIBLE) { + kfree(acct); + filp_close(file, NULL); + return -EINVAL; + } + if (!(file->f_mode & FMODE_CAN_WRITE)) { kfree(acct); filp_close(file, NULL); @@ -430,13 +453,27 @@ static u32 encode_float(u64 value) * do_exit() or when switching to a different output file. */ -static void fill_ac(acct_t *ac) +static void fill_ac(struct bsd_acct_struct *acct) { struct pacct_struct *pacct = ¤t->signal->pacct; + struct file *file = acct->file; + acct_t *ac = &acct->ac; u64 elapsed, run_time; time64_t btime; struct tty_struct *tty; + lockdep_assert_held(&acct->lock); + + if (time_is_after_jiffies(acct->needcheck)) { + acct->check_space = false; + + /* Don't fill in @ac if nothing will be written. */ + if (!acct->active) + return; + } else { + acct->check_space = true; + } + /* * Fill the accounting struct with the needed info as recorded * by the different kernel functions. @@ -484,64 +521,61 @@ static void fill_ac(acct_t *ac) ac->ac_majflt = encode_comp_t(pacct->ac_majflt); ac->ac_exitcode = pacct->ac_exitcode; spin_unlock_irq(¤t->sighand->siglock); -} -/* - * do_acct_process does all actual work. Caller holds the reference to file. - */ -static void do_acct_process(struct bsd_acct_struct *acct) -{ - acct_t ac; - unsigned long flim; - const struct cred *orig_cred; - struct file *file = acct->file; - /* - * Accounting records are not subject to resource limits. - */ - flim = rlimit(RLIMIT_FSIZE); - current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY; - /* Perform file operations on behalf of whoever enabled accounting */ - orig_cred = override_creds(file->f_cred); - - /* - * First check to see if there is enough free_space to continue - * the process accounting system. - */ - if (!check_free_space(acct)) - goto out; - - fill_ac(&ac); /* we really need to bite the bullet and change layout */ - ac.ac_uid = from_kuid_munged(file->f_cred->user_ns, orig_cred->uid); - ac.ac_gid = from_kgid_munged(file->f_cred->user_ns, orig_cred->gid); + ac->ac_uid = from_kuid_munged(file->f_cred->user_ns, current_uid()); + ac->ac_gid = from_kgid_munged(file->f_cred->user_ns, current_gid()); #if ACCT_VERSION == 1 || ACCT_VERSION == 2 /* backward-compatible 16 bit fields */ - ac.ac_uid16 = ac.ac_uid; - ac.ac_gid16 = ac.ac_gid; + ac->ac_uid16 = ac->ac_uid; + ac->ac_gid16 = ac->ac_gid; #elif ACCT_VERSION == 3 { struct pid_namespace *ns = acct->ns; - ac.ac_pid = task_tgid_nr_ns(current, ns); + ac->ac_pid = task_tgid_nr_ns(current, ns); rcu_read_lock(); - ac.ac_ppid = task_tgid_nr_ns(rcu_dereference(current->real_parent), - ns); + ac->ac_ppid = task_tgid_nr_ns(rcu_dereference(current->real_parent), ns); rcu_read_unlock(); } #endif +} + +static void acct_write_process(struct bsd_acct_struct *acct) +{ + struct file *file = acct->file; + const struct cred *cred; + acct_t *ac = &acct->ac; + + /* Perform file operations on behalf of whoever enabled accounting */ + cred = override_creds(file->f_cred); + /* - * Get freeze protection. If the fs is frozen, just skip the write - * as we could deadlock the system otherwise. + * First check to see if there is enough free_space to continue + * the process accounting system. Then get freeze protection. If + * the fs is frozen, just skip the write as we could deadlock + * the system otherwise. */ - if (file_start_write_trylock(file)) { + if (check_free_space(acct) && file_start_write_trylock(file)) { /* it's been opened O_APPEND, so position is irrelevant */ loff_t pos = 0; - __kernel_write(file, &ac, sizeof(acct_t), &pos); + __kernel_write(file, ac, sizeof(acct_t), &pos); file_end_write(file); } -out: + + revert_creds(cred); +} + +static void do_acct_process(struct bsd_acct_struct *acct) +{ + unsigned long flim; + + /* Accounting records are not subject to resource limits. */ + flim = rlimit(RLIMIT_FSIZE); + current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY; + fill_ac(acct); + acct_write_process(acct); current->signal->rlim[RLIMIT_FSIZE].rlim_cur = flim; - revert_creds(orig_cred); } /** diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c index 870aeb51d70a..095a9554e1de 100644 --- a/kernel/bpf/arena.c +++ b/kernel/bpf/arena.c @@ -39,7 +39,7 @@ */ /* number of bytes addressable by LDX/STX insn with 16-bit 'off' field */ -#define GUARD_SZ (1ull << sizeof_field(struct bpf_insn, off) * 8) +#define GUARD_SZ round_up(1ull << sizeof_field(struct bpf_insn, off) * 8, PAGE_SIZE << 1) #define KERN_VM_SZ (SZ_4G + GUARD_SZ) struct bpf_arena { diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c index d5dc65bb1755..54ff2a85d4c0 100644 --- a/kernel/bpf/bpf_cgrp_storage.c +++ b/kernel/bpf/bpf_cgrp_storage.c @@ -153,7 +153,7 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) static void cgroup_storage_map_free(struct bpf_map *map) { - bpf_local_storage_map_free(map, &cgroup_cache, NULL); + bpf_local_storage_map_free(map, &cgroup_cache, &bpf_cgrp_storage_busy); } /* *gfp_flags* is a hidden argument provided by the verifier */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 9de6acddd479..c3223e0db2f5 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6507,6 +6507,8 @@ static const struct bpf_raw_tp_null_args raw_tp_null_args[] = { /* rxrpc */ { "rxrpc_recvdata", 0x1 }, { "rxrpc_resend", 0x10 }, + /* skb */ + {"kfree_skb", 0x1000}, /* sunrpc */ { "xs_stream_read_data", 0x1 }, /* ... from xprt_cong_event event class */ diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index e1cfe890e0be..1499d8caa9a3 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -268,8 +268,6 @@ static int ringbuf_map_mmap_kern(struct bpf_map *map, struct vm_area_struct *vma /* allow writable mapping for the consumer_pos only */ if (vma->vm_pgoff != 0 || vma->vm_end - vma->vm_start != PAGE_SIZE) return -EPERM; - } else { - vm_flags_clear(vma, VM_MAYWRITE); } /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, @@ -289,8 +287,6 @@ static int ringbuf_map_mmap_user(struct bpf_map *map, struct vm_area_struct *vma * position, and the ring buffer data itself. */ return -EPERM; - } else { - vm_flags_clear(vma, VM_MAYWRITE); } /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, vma->vm_pgoff + RINGBUF_PGOFF); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index c420edbfb7c8..e1e42e918ba7 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1035,7 +1035,7 @@ static const struct vm_operations_struct bpf_map_default_vmops = { static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) { struct bpf_map *map = filp->private_data; - int err; + int err = 0; if (!map->ops->map_mmap || !IS_ERR_OR_NULL(map->record)) return -ENOTSUPP; @@ -1059,24 +1059,33 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) err = -EACCES; goto out; } + bpf_map_write_active_inc(map); } +out: + mutex_unlock(&map->freeze_mutex); + if (err) + return err; /* set default open/close callbacks */ vma->vm_ops = &bpf_map_default_vmops; vma->vm_private_data = map; vm_flags_clear(vma, VM_MAYEXEC); + /* If mapping is read-only, then disallow potentially re-mapping with + * PROT_WRITE by dropping VM_MAYWRITE flag. This VM_MAYWRITE clearing + * means that as far as BPF map's memory-mapped VMAs are concerned, + * VM_WRITE and VM_MAYWRITE and equivalent, if one of them is set, + * both should be set, so we can forget about VM_MAYWRITE and always + * check just VM_WRITE + */ if (!(vma->vm_flags & VM_WRITE)) - /* disallow re-mapping with PROT_WRITE */ vm_flags_clear(vma, VM_MAYWRITE); err = map->ops->map_mmap(map, vma); - if (err) - goto out; + if (err) { + if (vma->vm_flags & VM_WRITE) + bpf_map_write_active_dec(map); + } - if (vma->vm_flags & VM_MAYWRITE) - bpf_map_write_active_inc(map); -out: - mutex_unlock(&map->freeze_mutex); return err; } @@ -1968,8 +1977,6 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file, return err; } -#define MAP_LOOKUP_RETRIES 3 - int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) @@ -1979,8 +1986,8 @@ int generic_map_lookup_batch(struct bpf_map *map, void __user *values = u64_to_user_ptr(attr->batch.values); void __user *keys = u64_to_user_ptr(attr->batch.keys); void *buf, *buf_prevkey, *prev_key, *key, *value; - int err, retry = MAP_LOOKUP_RETRIES; u32 value_size, cp, max_count; + int err; if (attr->batch.elem_flags & ~BPF_F_LOCK) return -EINVAL; @@ -2026,14 +2033,8 @@ int generic_map_lookup_batch(struct bpf_map *map, err = bpf_map_copy_value(map, key, value, attr->batch.elem_flags); - if (err == -ENOENT) { - if (retry) { - retry--; - continue; - } - err = -EINTR; - break; - } + if (err == -ENOENT) + goto next_key; if (err) goto free_buf; @@ -2048,12 +2049,12 @@ int generic_map_lookup_batch(struct bpf_map *map, goto free_buf; } + cp++; +next_key: if (!prev_key) prev_key = buf_prevkey; swap(prev_key, key); - retry = MAP_LOOKUP_RETRIES; - cp++; cond_resched(); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9971c03adfd5..60611df77957 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1501,6 +1501,8 @@ static int acquire_lock_state(struct bpf_verifier_env *env, int insn_idx, enum r struct bpf_reference_state *s; s = acquire_reference_state(env, insn_idx); + if (!s) + return -ENOMEM; s->type = type; s->id = id; s->ptr = ptr; @@ -9149,10 +9151,11 @@ static int check_reg_const_str(struct bpf_verifier_env *env, return 0; } -/* Returns constant key value if possible, else negative error */ -static s64 get_constant_map_key(struct bpf_verifier_env *env, +/* Returns constant key value in `value` if possible, else negative error */ +static int get_constant_map_key(struct bpf_verifier_env *env, struct bpf_reg_state *key, - u32 key_size) + u32 key_size, + s64 *value) { struct bpf_func_state *state = func(env, key); struct bpf_reg_state *reg; @@ -9179,8 +9182,10 @@ static s64 get_constant_map_key(struct bpf_verifier_env *env, /* First handle precisely tracked STACK_ZERO */ for (i = off; i >= 0 && stype[i] == STACK_ZERO; i--) zero_size++; - if (zero_size >= key_size) + if (zero_size >= key_size) { + *value = 0; return 0; + } /* Check that stack contains a scalar spill of expected size */ if (!is_spilled_scalar_reg(&state->stack[spi])) @@ -9203,9 +9208,12 @@ static s64 get_constant_map_key(struct bpf_verifier_env *env, if (err < 0) return err; - return reg->var_off.value; + *value = reg->var_off.value; + return 0; } +static bool can_elide_value_nullness(enum bpf_map_type type); + static int check_func_arg(struct bpf_verifier_env *env, u32 arg, struct bpf_call_arg_meta *meta, const struct bpf_func_proto *fn, @@ -9354,9 +9362,16 @@ skip_type_check: err = check_helper_mem_access(env, regno, key_size, BPF_READ, false, NULL); if (err) return err; - meta->const_map_key = get_constant_map_key(env, reg, key_size); - if (meta->const_map_key < 0 && meta->const_map_key != -EOPNOTSUPP) - return meta->const_map_key; + if (can_elide_value_nullness(meta->map_ptr->map_type)) { + err = get_constant_map_key(env, reg, key_size, &meta->const_map_key); + if (err < 0) { + meta->const_map_key = -1; + if (err == -EOPNOTSUPP) + err = 0; + else + return err; + } + } break; case ARG_PTR_TO_MAP_VALUE: if (type_may_be_null(arg_type) && register_is_null(reg)) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d9061bd55436..afc665b7b1fe 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4013,7 +4013,7 @@ static void __cgroup_kill(struct cgroup *cgrp) lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); - set_bit(CGRP_KILL, &cgrp->flags); + cgrp->kill_seq++; spin_unlock_irq(&css_set_lock); css_task_iter_start(&cgrp->self, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED, &it); @@ -4029,10 +4029,6 @@ static void __cgroup_kill(struct cgroup *cgrp) send_sig(SIGKILL, task, 0); } css_task_iter_end(&it); - - spin_lock_irq(&css_set_lock); - clear_bit(CGRP_KILL, &cgrp->flags); - spin_unlock_irq(&css_set_lock); } static void cgroup_kill(struct cgroup *cgrp) @@ -6488,6 +6484,10 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) spin_lock_irq(&css_set_lock); cset = task_css_set(current); get_css_set(cset); + if (kargs->cgrp) + kargs->kill_seq = kargs->cgrp->kill_seq; + else + kargs->kill_seq = cset->dfl_cgrp->kill_seq; spin_unlock_irq(&css_set_lock); if (!(kargs->flags & CLONE_INTO_CGROUP)) { @@ -6668,6 +6668,7 @@ void cgroup_post_fork(struct task_struct *child, struct kernel_clone_args *kargs) __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex) { + unsigned int cgrp_kill_seq = 0; unsigned long cgrp_flags = 0; bool kill = false; struct cgroup_subsys *ss; @@ -6681,10 +6682,13 @@ void cgroup_post_fork(struct task_struct *child, /* init tasks are special, only link regular threads */ if (likely(child->pid)) { - if (kargs->cgrp) + if (kargs->cgrp) { cgrp_flags = kargs->cgrp->flags; - else + cgrp_kill_seq = kargs->cgrp->kill_seq; + } else { cgrp_flags = cset->dfl_cgrp->flags; + cgrp_kill_seq = cset->dfl_cgrp->kill_seq; + } WARN_ON_ONCE(!list_empty(&child->cg_list)); cset->nr_tasks++; @@ -6719,7 +6723,7 @@ void cgroup_post_fork(struct task_struct *child, * child down right after we finished preparing it for * userspace. */ - kill = test_bit(CGRP_KILL, &cgrp_flags); + kill = kargs->kill_seq != cgrp_kill_seq; } spin_unlock_irq(&css_set_lock); diff --git a/kernel/cgroup/dmem.c b/kernel/cgroup/dmem.c index fbe34299673d..10b63433f057 100644 --- a/kernel/cgroup/dmem.c +++ b/kernel/cgroup/dmem.c @@ -220,60 +220,32 @@ dmem_cgroup_calculate_protection(struct dmem_cgroup_pool_state *limit_pool, struct dmem_cgroup_pool_state *test_pool) { struct page_counter *climit; - struct cgroup_subsys_state *css, *next_css; + struct cgroup_subsys_state *css; struct dmemcg_state *dmemcg_iter; - struct dmem_cgroup_pool_state *pool, *parent_pool; - bool found_descendant; + struct dmem_cgroup_pool_state *pool, *found_pool; climit = &limit_pool->cnt; rcu_read_lock(); - parent_pool = pool = limit_pool; - css = &limit_pool->cs->css; - /* - * This logic is roughly equivalent to css_foreach_descendant_pre, - * except we also track the parent pool to find out which pool we need - * to calculate protection values for. - * - * We can stop the traversal once we find test_pool among the - * descendants since we don't really care about any others. - */ - while (pool != test_pool) { - next_css = css_next_child(NULL, css); - if (next_css) { - parent_pool = pool; - } else { - while (css != &limit_pool->cs->css) { - next_css = css_next_child(css, css->parent); - if (next_css) - break; - css = css->parent; - parent_pool = pool_parent(parent_pool); - } - /* - * We can only hit this when test_pool is not a - * descendant of limit_pool. - */ - if (WARN_ON_ONCE(css == &limit_pool->cs->css)) - break; - } - css = next_css; - - found_descendant = false; + css_for_each_descendant_pre(css, &limit_pool->cs->css) { dmemcg_iter = container_of(css, struct dmemcg_state, css); + found_pool = NULL; list_for_each_entry_rcu(pool, &dmemcg_iter->pools, css_node) { - if (pool_parent(pool) == parent_pool) { - found_descendant = true; + if (pool->region == limit_pool->region) { + found_pool = pool; break; } } - if (!found_descendant) + if (!found_pool) continue; page_counter_calculate_protection( - climit, &pool->cnt, true); + climit, &found_pool->cnt, true); + + if (found_pool == test_pool) + break; } rcu_read_unlock(); } diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 5877974ece92..aac91466279f 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -590,7 +590,6 @@ static void root_cgroup_cputime(struct cgroup_base_stat *bstat) cputime->sum_exec_runtime += user; cputime->sum_exec_runtime += sys; - cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL]; #ifdef CONFIG_SCHED_CORE bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE]; diff --git a/kernel/events/core.c b/kernel/events/core.c index bcb09e011e9e..823aa0824916 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4950,7 +4950,7 @@ static struct perf_event_pmu_context * find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx, struct perf_event *event) { - struct perf_event_pmu_context *new = NULL, *epc; + struct perf_event_pmu_context *new = NULL, *pos = NULL, *epc; void *task_ctx_data = NULL; if (!ctx->task) { @@ -5007,12 +5007,19 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx, atomic_inc(&epc->refcount); goto found_epc; } + /* Make sure the pmu_ctx_list is sorted by PMU type: */ + if (!pos && epc->pmu->type > pmu->type) + pos = epc; } epc = new; new = NULL; - list_add(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list); + if (!pos) + list_add_tail(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list); + else + list_add(&epc->pmu_ctx_entry, pos->pmu_ctx_entry.prev); + epc->ctx = ctx; found_epc: @@ -5962,14 +5969,15 @@ static int _perf_event_period(struct perf_event *event, u64 value) if (!value) return -EINVAL; - if (event->attr.freq && value > sysctl_perf_event_sample_rate) - return -EINVAL; - - if (perf_event_check_period(event, value)) - return -EINVAL; - - if (!event->attr.freq && (value & (1ULL << 63))) - return -EINVAL; + if (event->attr.freq) { + if (value > sysctl_perf_event_sample_rate) + return -EINVAL; + } else { + if (perf_event_check_period(event, value)) + return -EINVAL; + if (value & (1ULL << 63)) + return -EINVAL; + } event_function_call(event, __perf_event_period, &value); @@ -8321,7 +8329,8 @@ void perf_event_exec(void) perf_event_enable_on_exec(ctx); perf_event_remove_on_exec(ctx); - perf_iterate_ctx(ctx, perf_event_addr_filters_exec, NULL, true); + scoped_guard(rcu) + perf_iterate_ctx(ctx, perf_event_addr_filters_exec, NULL, true); perf_unpin_context(ctx); put_ctx(ctx); @@ -11821,6 +11830,21 @@ free_dev: static struct lock_class_key cpuctx_mutex; static struct lock_class_key cpuctx_lock; +static bool idr_cmpxchg(struct idr *idr, unsigned long id, void *old, void *new) +{ + void *tmp, *val = idr_find(idr, id); + + if (val != old) + return false; + + tmp = idr_replace(idr, new, id); + if (IS_ERR(tmp)) + return false; + + WARN_ON_ONCE(tmp != val); + return true; +} + int perf_pmu_register(struct pmu *pmu, const char *name, int type) { int cpu, ret, max = PERF_TYPE_MAX; @@ -11847,7 +11871,7 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type) if (type >= 0) max = type; - ret = idr_alloc(&pmu_idr, pmu, max, 0, GFP_KERNEL); + ret = idr_alloc(&pmu_idr, NULL, max, 0, GFP_KERNEL); if (ret < 0) goto free_pdc; @@ -11855,6 +11879,7 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type) type = ret; pmu->type = type; + atomic_set(&pmu->exclusive_cnt, 0); if (pmu_bus_running && !pmu->dev) { ret = pmu_dev_alloc(pmu); @@ -11903,14 +11928,22 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type) if (!pmu->event_idx) pmu->event_idx = perf_event_idx_default; + /* + * Now that the PMU is complete, make it visible to perf_try_init_event(). + */ + if (!idr_cmpxchg(&pmu_idr, pmu->type, NULL, pmu)) + goto free_context; list_add_rcu(&pmu->entry, &pmus); - atomic_set(&pmu->exclusive_cnt, 0); + ret = 0; unlock: mutex_unlock(&pmus_lock); return ret; +free_context: + free_percpu(pmu->cpu_pmu_context); + free_dev: if (pmu->dev && pmu->dev != PMU_NULL_DEV) { device_del(pmu->dev); @@ -11930,6 +11963,8 @@ void perf_pmu_unregister(struct pmu *pmu) { mutex_lock(&pmus_lock); list_del_rcu(&pmu->entry); + idr_remove(&pmu_idr, pmu->type); + mutex_unlock(&pmus_lock); /* * We dereference the pmu list under both SRCU and regular RCU, so @@ -11939,7 +11974,6 @@ void perf_pmu_unregister(struct pmu *pmu) synchronize_rcu(); free_percpu(pmu->pmu_disable_count); - idr_remove(&pmu_idr, pmu->type); if (pmu_bus_running && pmu->dev && pmu->dev != PMU_NULL_DEV) { if (pmu->nr_addr_filters) device_remove_file(pmu->dev, &dev_attr_nr_addr_filters); @@ -11947,7 +11981,6 @@ void perf_pmu_unregister(struct pmu *pmu) put_device(pmu->dev); } free_pmu_context(pmu); - mutex_unlock(&pmus_lock); } EXPORT_SYMBOL_GPL(perf_pmu_unregister); diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 2ca797cbe465..b4ca8898fe17 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -417,7 +417,7 @@ static void update_ref_ctr_warn(struct uprobe *uprobe, struct mm_struct *mm, short d) { pr_warn("ref_ctr %s failed for inode: 0x%lx offset: " - "0x%llx ref_ctr_offset: 0x%llx of mm: 0x%pK\n", + "0x%llx ref_ctr_offset: 0x%llx of mm: 0x%p\n", d > 0 ? "increment" : "decrement", uprobe->inode->i_ino, (unsigned long long) uprobe->offset, (unsigned long long) uprobe->ref_ctr_offset, mm); @@ -495,6 +495,11 @@ retry: if (ret <= 0) goto put_old; + if (is_zero_page(old_page)) { + ret = -EINVAL; + goto put_old; + } + if (WARN(!is_register && PageCompound(old_page), "uprobe unregister should never work on compound page\n")) { ret = -EINVAL; @@ -762,10 +767,14 @@ static struct uprobe *hprobe_expire(struct hprobe *hprobe, bool get) enum hprobe_state hstate; /* - * return_instance's hprobe is protected by RCU. - * Underlying uprobe is itself protected from reuse by SRCU. + * Caller should guarantee that return_instance is not going to be + * freed from under us. This can be achieved either through holding + * rcu_read_lock() or by owning return_instance in the first place. + * + * Underlying uprobe is itself protected from reuse by SRCU, so ensure + * SRCU lock is held properly. */ - lockdep_assert(rcu_read_lock_held() && srcu_read_lock_held(&uretprobes_srcu)); + lockdep_assert(srcu_read_lock_held(&uretprobes_srcu)); hstate = READ_ONCE(hprobe->state); switch (hstate) { diff --git a/kernel/futex/core.c b/kernel/futex/core.c index ebdd76b4ecbb..3db8567f5a44 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -532,7 +532,8 @@ void futex_q_unlock(struct futex_hash_bucket *hb) futex_hb_waiters_dec(hb); } -void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb) +void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb, + struct task_struct *task) { int prio; @@ -548,7 +549,7 @@ void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb) plist_node_init(&q->list, prio); plist_add(&q->list, &hb->chain); - q->task = current; + q->task = task; } /** diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h index 99b32e728c4a..6b2f4c7eb720 100644 --- a/kernel/futex/futex.h +++ b/kernel/futex/futex.h @@ -285,13 +285,15 @@ static inline int futex_get_value_locked(u32 *dest, u32 __user *from) } extern void __futex_unqueue(struct futex_q *q); -extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb); +extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb, + struct task_struct *task); extern int futex_unqueue(struct futex_q *q); /** * futex_queue() - Enqueue the futex_q on the futex_hash_bucket * @q: The futex_q to enqueue * @hb: The destination hash bucket + * @task: Task queueing this futex * * The hb->lock must be held by the caller, and is released here. A call to * futex_queue() is typically paired with exactly one call to futex_unqueue(). The @@ -299,11 +301,14 @@ extern int futex_unqueue(struct futex_q *q); * or nothing if the unqueue is done as part of the wake process and the unqueue * state is implicit in the state of woken task (see futex_wait_requeue_pi() for * an example). + * + * Note that @task may be NULL, for async usage of futexes. */ -static inline void futex_queue(struct futex_q *q, struct futex_hash_bucket *hb) +static inline void futex_queue(struct futex_q *q, struct futex_hash_bucket *hb, + struct task_struct *task) __releases(&hb->lock) { - __futex_queue(q, hb); + __futex_queue(q, hb, task); spin_unlock(&hb->lock); } diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c index daea650b16f5..7a941845f7ee 100644 --- a/kernel/futex/pi.c +++ b/kernel/futex/pi.c @@ -982,7 +982,7 @@ retry_private: /* * Only actually queue now that the atomic ops are done: */ - __futex_queue(&q, hb); + __futex_queue(&q, hb, current); if (trylock) { ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex); diff --git a/kernel/futex/waitwake.c b/kernel/futex/waitwake.c index eb86a7ade06a..25877d4f2f8f 100644 --- a/kernel/futex/waitwake.c +++ b/kernel/futex/waitwake.c @@ -349,7 +349,7 @@ void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q, * access to the hash list and forcing another memory barrier. */ set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); - futex_queue(q, hb); + futex_queue(q, hb, current); /* Arm the timer */ if (timeout) @@ -460,7 +460,7 @@ retry: * next futex. Queue each futex at this moment so hb can * be unlocked. */ - futex_queue(q, hb); + futex_queue(q, hb, current); continue; } diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 5432418c0fea..875f25ed6f71 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -31,10 +31,6 @@ config GENERIC_IRQ_EFFECTIVE_AFF_MASK config GENERIC_PENDING_IRQ bool -# Deduce delayed migration from top-level interrupt chip flags -config GENERIC_PENDING_IRQ_CHIPFLAGS - bool - # Support for generic irq migrating off cpu before the cpu is offline. config GENERIC_IRQ_MIGRATION bool diff --git a/kernel/kthread.c b/kernel/kthread.c index 4005b13ebd7f..5dc5b0d7238e 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -859,7 +859,7 @@ int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask) struct kthread *kthread = to_kthread(p); cpumask_var_t affinity; unsigned long flags; - int ret; + int ret = 0; if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE) || kthread->started) { WARN_ON(1); @@ -892,7 +892,7 @@ int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask) out: free_cpumask_var(affinity); - return 0; + return ret; } /* diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index c38a2d2d4a7e..78dd3d8c6554 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -59,8 +59,8 @@ struct rt_mutex_waiter { }; /** - * rt_wake_q_head - Wrapper around regular wake_q_head to support - * "sleeping" spinlocks on RT + * struct rt_wake_q_head - Wrapper around regular wake_q_head to support + * "sleeping" spinlocks on RT * @head: The regular wake_q_head for sleeping lock variants * @rtlock_task: Task pointer for RT lock (spin/rwlock) wakeups */ diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c index 34bfae72f295..de9117c0e671 100644 --- a/kernel/locking/semaphore.c +++ b/kernel/locking/semaphore.c @@ -29,6 +29,7 @@ #include <linux/export.h> #include <linux/sched.h> #include <linux/sched/debug.h> +#include <linux/sched/wake_q.h> #include <linux/semaphore.h> #include <linux/spinlock.h> #include <linux/ftrace.h> @@ -38,7 +39,7 @@ static noinline void __down(struct semaphore *sem); static noinline int __down_interruptible(struct semaphore *sem); static noinline int __down_killable(struct semaphore *sem); static noinline int __down_timeout(struct semaphore *sem, long timeout); -static noinline void __up(struct semaphore *sem); +static noinline void __up(struct semaphore *sem, struct wake_q_head *wake_q); /** * down - acquire the semaphore @@ -183,13 +184,16 @@ EXPORT_SYMBOL(down_timeout); void __sched up(struct semaphore *sem) { unsigned long flags; + DEFINE_WAKE_Q(wake_q); raw_spin_lock_irqsave(&sem->lock, flags); if (likely(list_empty(&sem->wait_list))) sem->count++; else - __up(sem); + __up(sem, &wake_q); raw_spin_unlock_irqrestore(&sem->lock, flags); + if (!wake_q_empty(&wake_q)) + wake_up_q(&wake_q); } EXPORT_SYMBOL(up); @@ -269,11 +273,12 @@ static noinline int __sched __down_timeout(struct semaphore *sem, long timeout) return __down_common(sem, TASK_UNINTERRUPTIBLE, timeout); } -static noinline void __sched __up(struct semaphore *sem) +static noinline void __sched __up(struct semaphore *sem, + struct wake_q_head *wake_q) { struct semaphore_waiter *waiter = list_first_entry(&sem->wait_list, struct semaphore_waiter, list); list_del(&waiter->list); waiter->up = true; - wake_up_process(waiter->task); + wake_q_add(wake_q, waiter->task); } diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 8f6cfec87555..7098ed44e717 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -107,7 +107,7 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns goto out_free_idr; ns->ns.ops = &pidns_operations; - ns->pid_max = parent_pid_ns->pid_max; + ns->pid_max = PID_MAX_LIMIT; err = register_pidns_sysctls(ns); if (err) goto out_free_inum; diff --git a/kernel/rseq.c b/kernel/rseq.c index 442aba29bc4c..2cb16091ec0a 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -507,9 +507,6 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, return -EINVAL; if (!access_ok(rseq, rseq_len)) return -EFAULT; - current->rseq = rseq; - current->rseq_len = rseq_len; - current->rseq_sig = sig; #ifdef CONFIG_DEBUG_RSEQ /* * Initialize the in-kernel rseq fields copy for validation of @@ -522,6 +519,14 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, return -EFAULT; #endif /* + * Activate the registration by setting the rseq area address, length + * and signature in the task struct. + */ + current->rseq = rseq; + current->rseq_len = rseq_len; + current->rseq_sig = sig; + + /* * If rseq was previously inactive, and has just been * registered, ensure the cpu_id_start and cpu_id fields * are updated before returning to user-space. diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c index 83d46b9b8ec8..2b331822c7e7 100644 --- a/kernel/sched/autogroup.c +++ b/kernel/sched/autogroup.c @@ -150,7 +150,7 @@ void sched_autogroup_exit_task(struct task_struct *p) * see this thread after that: we can no longer use signal->autogroup. * See the PF_EXITING check in task_wants_autogroup(). */ - sched_move_task(p); + sched_move_task(p, true); } static void @@ -182,7 +182,7 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag) * sched_autogroup_exit_task(). */ for_each_thread(p, t) - sched_move_task(t); + sched_move_task(t, true); unlock_task_sighand(p, &flags); autogroup_kref_put(prev); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 165c90ba64ea..67189907214d 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1063,9 +1063,10 @@ void wake_up_q(struct wake_q_head *head) struct task_struct *task; task = container_of(node, struct task_struct, wake_q); - /* Task can safely be re-inserted now: */ node = node->next; - task->wake_q.next = NULL; + /* pairs with cmpxchg_relaxed() in __wake_q_add() */ + WRITE_ONCE(task->wake_q.next, NULL); + /* Task can safely be re-inserted now. */ /* * wake_up_process() executes a full barrier, which pairs with @@ -7284,7 +7285,7 @@ out_unlock: #if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) int __sched __cond_resched(void) { - if (should_resched(0)) { + if (should_resched(0) && !irqs_disabled()) { preempt_schedule_common(); return 1; } @@ -9050,7 +9051,7 @@ static void sched_change_group(struct task_struct *tsk, struct task_group *group * now. This function just updates tsk->se.cfs_rq and tsk->se.parent to reflect * its new group. */ -void sched_move_task(struct task_struct *tsk) +void sched_move_task(struct task_struct *tsk, bool for_autogroup) { int queued, running, queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; @@ -9079,7 +9080,8 @@ void sched_move_task(struct task_struct *tsk) put_prev_task(rq, tsk); sched_change_group(tsk, group); - scx_move_task(tsk); + if (!for_autogroup) + scx_cgroup_move_task(tsk); if (queued) enqueue_task(rq, tsk, queue_flags); @@ -9180,7 +9182,7 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset) struct cgroup_subsys_state *css; cgroup_taskset_for_each(task, css, tset) - sched_move_task(task); + sched_move_task(task, false); scx_cgroup_finish_attach(); } diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 5d9143dd0879..6dab4854c6c0 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -9,8 +9,6 @@ #ifdef CONFIG_IRQ_TIME_ACCOUNTING -DEFINE_STATIC_KEY_FALSE(sched_clock_irqtime); - /* * There are no locks covering percpu hardirq/softirq time. * They are only modified in vtime_account, on corresponding CPU @@ -24,14 +22,16 @@ DEFINE_STATIC_KEY_FALSE(sched_clock_irqtime); */ DEFINE_PER_CPU(struct irqtime, cpu_irqtime); +int sched_clock_irqtime; + void enable_sched_clock_irqtime(void) { - static_branch_enable(&sched_clock_irqtime); + sched_clock_irqtime = 1; } void disable_sched_clock_irqtime(void) { - static_branch_disable(&sched_clock_irqtime); + sched_clock_irqtime = 0; } static void irqtime_account_delta(struct irqtime *irqtime, u64 delta, diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 38e4537790af..ff4df16b5186 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -3189,7 +3189,7 @@ int sched_dl_global_validate(void) * value smaller than the currently allocated bandwidth in * any of the root_domains. */ - for_each_possible_cpu(cpu) { + for_each_online_cpu(cpu) { rcu_read_lock_sched(); if (dl_bw_visited(cpu, gen)) diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index fd7e85220715..ef047add7f9e 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -1262,6 +1262,8 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, if (task_has_dl_policy(p)) { P(dl.runtime); P(dl.deadline); + } else if (fair_policy(p->policy)) { + P(se.slice); } #ifdef CONFIG_SCHED_CLASS_EXT __PS("ext.enabled", task_on_scx(p)); diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 8857c0709bdd..7b9dfee858e7 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -123,6 +123,19 @@ enum scx_ops_flags { SCX_OPS_SWITCH_PARTIAL = 1LLU << 3, /* + * A migration disabled task can only execute on its current CPU. By + * default, such tasks are automatically put on the CPU's local DSQ with + * the default slice on enqueue. If this ops flag is set, they also go + * through ops.enqueue(). + * + * A migration disabled task never invokes ops.select_cpu() as it can + * only select the current CPU. Also, p->cpus_ptr will only contain its + * current CPU while p->nr_cpus_allowed keeps tracking p->user_cpus_ptr + * and thus may disagree with cpumask_weight(p->cpus_ptr). + */ + SCX_OPS_ENQ_MIGRATION_DISABLED = 1LLU << 4, + + /* * CPU cgroup support flags */ SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16, /* cpu.weight */ @@ -130,6 +143,7 @@ enum scx_ops_flags { SCX_OPS_ALL_FLAGS = SCX_OPS_KEEP_BUILTIN_IDLE | SCX_OPS_ENQ_LAST | SCX_OPS_ENQ_EXITING | + SCX_OPS_ENQ_MIGRATION_DISABLED | SCX_OPS_SWITCH_PARTIAL | SCX_OPS_HAS_CGROUP_WEIGHT, }; @@ -416,7 +430,7 @@ struct sched_ext_ops { /** * @update_idle: Update the idle state of a CPU - * @cpu: CPU to udpate the idle state for + * @cpu: CPU to update the idle state for * @idle: whether entering or exiting the idle state * * This operation is called when @rq's CPU goes or leaves the idle @@ -882,6 +896,7 @@ static bool scx_warned_zero_slice; static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_last); static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_exiting); +static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_migration_disabled); static DEFINE_STATIC_KEY_FALSE(scx_ops_cpu_preempt); static DEFINE_STATIC_KEY_FALSE(scx_builtin_idle_enabled); @@ -1214,7 +1229,7 @@ static bool scx_kf_allowed_if_unlocked(void) /** * nldsq_next_task - Iterate to the next task in a non-local DSQ - * @dsq: user dsq being interated + * @dsq: user dsq being iterated * @cur: current position, %NULL to start iteration * @rev: walk backwards * @@ -2014,6 +2029,11 @@ static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags, unlikely(p->flags & PF_EXITING)) goto local; + /* see %SCX_OPS_ENQ_MIGRATION_DISABLED */ + if (!static_branch_unlikely(&scx_ops_enq_migration_disabled) && + is_migration_disabled(p)) + goto local; + if (!SCX_HAS_OP(enqueue)) goto global; @@ -2078,7 +2098,7 @@ static void set_task_runnable(struct rq *rq, struct task_struct *p) /* * list_add_tail() must be used. scx_ops_bypass() depends on tasks being - * appened to the runnable_list. + * appended to the runnable_list. */ list_add_tail(&p->scx.runnable_node, &rq->scx.runnable_list); } @@ -2313,12 +2333,35 @@ static void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags, * * - The BPF scheduler is bypassed while the rq is offline and we can always say * no to the BPF scheduler initiated migrations while offline. + * + * The caller must ensure that @p and @rq are on different CPUs. */ static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq, bool trigger_error) { int cpu = cpu_of(rq); + SCHED_WARN_ON(task_cpu(p) == cpu); + + /* + * If @p has migration disabled, @p->cpus_ptr is updated to contain only + * the pinned CPU in migrate_disable_switch() while @p is being switched + * out. However, put_prev_task_scx() is called before @p->cpus_ptr is + * updated and thus another CPU may see @p on a DSQ inbetween leading to + * @p passing the below task_allowed_on_cpu() check while migration is + * disabled. + * + * Test the migration disabled state first as the race window is narrow + * and the BPF scheduler failing to check migration disabled state can + * easily be masked if task_allowed_on_cpu() is done first. + */ + if (unlikely(is_migration_disabled(p))) { + if (trigger_error) + scx_ops_error("SCX_DSQ_LOCAL[_ON] cannot move migration disabled %s[%d] from CPU %d to %d", + p->comm, p->pid, task_cpu(p), cpu); + return false; + } + /* * We don't require the BPF scheduler to avoid dispatching to offline * CPUs mostly for convenience but also because CPUs can go offline @@ -2327,14 +2370,11 @@ static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq, */ if (!task_allowed_on_cpu(p, cpu)) { if (trigger_error) - scx_ops_error("SCX_DSQ_LOCAL[_ON] verdict target cpu %d not allowed for %s[%d]", - cpu_of(rq), p->comm, p->pid); + scx_ops_error("SCX_DSQ_LOCAL[_ON] target CPU %d not allowed for %s[%d]", + cpu, p->comm, p->pid); return false; } - if (unlikely(is_migration_disabled(p))) - return false; - if (!scx_rq_online(rq)) return false; @@ -2437,7 +2477,8 @@ static struct rq *move_task_between_dsqs(struct task_struct *p, u64 enq_flags, if (dst_dsq->id == SCX_DSQ_LOCAL) { dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq); - if (!task_can_run_on_remote_rq(p, dst_rq, true)) { + if (src_rq != dst_rq && + unlikely(!task_can_run_on_remote_rq(p, dst_rq, true))) { dst_dsq = find_global_dsq(p); dst_rq = src_rq; } @@ -2480,7 +2521,7 @@ static struct rq *move_task_between_dsqs(struct task_struct *p, u64 enq_flags, /* * A poorly behaving BPF scheduler can live-lock the system by e.g. incessantly * banging on the same DSQ on a large NUMA system to the point where switching - * to the bypass mode can take a long time. Inject artifical delays while the + * to the bypass mode can take a long time. Inject artificial delays while the * bypass mode is switching to guarantee timely completion. */ static void scx_ops_breather(struct rq *rq) @@ -2575,6 +2616,9 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq, { struct rq *src_rq = task_rq(p); struct rq *dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq); +#ifdef CONFIG_SMP + struct rq *locked_rq = rq; +#endif /* * We're synchronized against dequeue through DISPATCHING. As @p can't @@ -2588,7 +2632,8 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq, } #ifdef CONFIG_SMP - if (unlikely(!task_can_run_on_remote_rq(p, dst_rq, true))) { + if (src_rq != dst_rq && + unlikely(!task_can_run_on_remote_rq(p, dst_rq, true))) { dispatch_enqueue(find_global_dsq(p), p, enq_flags | SCX_ENQ_CLEAR_OPSS); return; @@ -2611,8 +2656,9 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq, atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE); /* switch to @src_rq lock */ - if (rq != src_rq) { - raw_spin_rq_unlock(rq); + if (locked_rq != src_rq) { + raw_spin_rq_unlock(locked_rq); + locked_rq = src_rq; raw_spin_rq_lock(src_rq); } @@ -2630,6 +2676,8 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq, } else { move_remote_task_to_local_dsq(p, enq_flags, src_rq, dst_rq); + /* task has been moved to dst_rq, which is now locked */ + locked_rq = dst_rq; } /* if the destination CPU is idle, wake it up */ @@ -2638,8 +2686,8 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq, } /* switch back to @rq lock */ - if (rq != dst_rq) { - raw_spin_rq_unlock(dst_rq); + if (locked_rq != rq) { + raw_spin_rq_unlock(locked_rq); raw_spin_rq_lock(rq); } #else /* CONFIG_SMP */ @@ -3069,7 +3117,6 @@ static struct task_struct *pick_task_scx(struct rq *rq) { struct task_struct *prev = rq->curr; struct task_struct *p; - bool prev_on_scx = prev->sched_class == &ext_sched_class; bool keep_prev = rq->scx.flags & SCX_RQ_BAL_KEEP; bool kick_idle = false; @@ -3089,14 +3136,18 @@ static struct task_struct *pick_task_scx(struct rq *rq) * if pick_task_scx() is called without preceding balance_scx(). */ if (unlikely(rq->scx.flags & SCX_RQ_BAL_PENDING)) { - if (prev_on_scx) { + if (prev->scx.flags & SCX_TASK_QUEUED) { keep_prev = true; } else { keep_prev = false; kick_idle = true; } - } else if (unlikely(keep_prev && !prev_on_scx)) { - /* only allowed during transitions */ + } else if (unlikely(keep_prev && + prev->sched_class != &ext_sched_class)) { + /* + * Can happen while enabling as SCX_RQ_BAL_PENDING assertion is + * conditional on scx_enabled() and may have been skipped. + */ WARN_ON_ONCE(scx_ops_enable_state() == SCX_OPS_ENABLED); keep_prev = false; } @@ -3144,7 +3195,7 @@ static struct task_struct *pick_task_scx(struct rq *rq) * * Unless overridden by ops.core_sched_before(), @p->scx.core_sched_at is used * to implement the default task ordering. The older the timestamp, the higher - * prority the task - the global FIFO ordering matching the default scheduling + * priority the task - the global FIFO ordering matching the default scheduling * behavior. * * When ops.core_sched_before() is enabled, @p->scx.core_sched_at is used to @@ -3851,7 +3902,7 @@ static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued) curr->scx.slice = 0; touch_core_sched(rq, curr); } else if (SCX_HAS_OP(tick)) { - SCX_CALL_OP(SCX_KF_REST, tick, curr); + SCX_CALL_OP_TASK(SCX_KF_REST, tick, curr); } if (!curr->scx.slice) @@ -3998,7 +4049,7 @@ static void scx_ops_disable_task(struct task_struct *p) WARN_ON_ONCE(scx_get_task_state(p) != SCX_TASK_ENABLED); if (SCX_HAS_OP(disable)) - SCX_CALL_OP(SCX_KF_REST, disable, p); + SCX_CALL_OP_TASK(SCX_KF_REST, disable, p); scx_set_task_state(p, SCX_TASK_READY); } @@ -4027,7 +4078,7 @@ static void scx_ops_exit_task(struct task_struct *p) } if (SCX_HAS_OP(exit_task)) - SCX_CALL_OP(SCX_KF_REST, exit_task, p, &args); + SCX_CALL_OP_TASK(SCX_KF_REST, exit_task, p, &args); scx_set_task_state(p, SCX_TASK_NONE); } @@ -4323,25 +4374,12 @@ err: return ops_sanitize_err("cgroup_prep_move", ret); } -void scx_move_task(struct task_struct *p) +void scx_cgroup_move_task(struct task_struct *p) { if (!scx_cgroup_enabled) return; /* - * We're called from sched_move_task() which handles both cgroup and - * autogroup moves. Ignore the latter. - * - * Also ignore exiting tasks, because in the exit path tasks transition - * from the autogroup to the root group, so task_group_is_autogroup() - * alone isn't able to catch exiting autogroup tasks. This is safe for - * cgroup_move(), because cgroup migrations never happen for PF_EXITING - * tasks. - */ - if (task_group_is_autogroup(task_group(p)) || (p->flags & PF_EXITING)) - return; - - /* * @p must have ops.cgroup_prep_move() called on it and thus * cgrp_moving_from set. */ @@ -4590,7 +4628,7 @@ static int scx_cgroup_init(void) cgroup_warned_missing_idle = false; /* - * scx_tg_on/offline() are excluded thorugh scx_cgroup_rwsem. If we walk + * scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk * cgroups and init, all online cgroups are initialized. */ rcu_read_lock(); @@ -5059,6 +5097,7 @@ static void scx_ops_disable_workfn(struct kthread_work *work) static_branch_disable(&scx_has_op[i]); static_branch_disable(&scx_ops_enq_last); static_branch_disable(&scx_ops_enq_exiting); + static_branch_disable(&scx_ops_enq_migration_disabled); static_branch_disable(&scx_ops_cpu_preempt); static_branch_disable(&scx_builtin_idle_enabled); synchronize_rcu(); @@ -5277,9 +5316,10 @@ static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx, scx_get_task_state(p), p->scx.flags & ~SCX_TASK_STATE_MASK, p->scx.dsq_flags, ops_state & SCX_OPSS_STATE_MASK, ops_state >> SCX_OPSS_QSEQ_SHIFT); - dump_line(s, " sticky/holding_cpu=%d/%d dsq_id=%s dsq_vtime=%llu slice=%llu", - p->scx.sticky_cpu, p->scx.holding_cpu, dsq_id_buf, - p->scx.dsq_vtime, p->scx.slice); + dump_line(s, " sticky/holding_cpu=%d/%d dsq_id=%s", + p->scx.sticky_cpu, p->scx.holding_cpu, dsq_id_buf); + dump_line(s, " dsq_vtime=%llu slice=%llu weight=%u", + p->scx.dsq_vtime, p->scx.slice, p->scx.weight); dump_line(s, " cpus=%*pb", cpumask_pr_args(p->cpus_ptr)); if (SCX_HAS_OP(dump_task)) { @@ -5667,6 +5707,8 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) if (ops->flags & SCX_OPS_ENQ_EXITING) static_branch_enable(&scx_ops_enq_exiting); + if (ops->flags & SCX_OPS_ENQ_MIGRATION_DISABLED) + static_branch_enable(&scx_ops_enq_migration_disabled); if (scx_ops.cpu_acquire || scx_ops.cpu_release) static_branch_enable(&scx_ops_cpu_preempt); @@ -6380,6 +6422,9 @@ static bool check_builtin_idle_enabled(void) __bpf_kfunc s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, bool *is_idle) { + if (!ops_cpu_valid(prev_cpu, NULL)) + goto prev_cpu; + if (!check_builtin_idle_enabled()) goto prev_cpu; diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h index 4d022d17ac7d..1079b56b0f7a 100644 --- a/kernel/sched/ext.h +++ b/kernel/sched/ext.h @@ -73,7 +73,7 @@ static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) {} int scx_tg_online(struct task_group *tg); void scx_tg_offline(struct task_group *tg); int scx_cgroup_can_attach(struct cgroup_taskset *tset); -void scx_move_task(struct task_struct *p); +void scx_cgroup_move_task(struct task_struct *p); void scx_cgroup_finish_attach(void); void scx_cgroup_cancel_attach(struct cgroup_taskset *tset); void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight); @@ -82,7 +82,7 @@ void scx_group_set_idle(struct task_group *tg, bool idle); static inline int scx_tg_online(struct task_group *tg) { return 0; } static inline void scx_tg_offline(struct task_group *tg) {} static inline int scx_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; } -static inline void scx_move_task(struct task_struct *p) {} +static inline void scx_cgroup_move_task(struct task_struct *p) {} static inline void scx_cgroup_finish_attach(void) {} static inline void scx_cgroup_cancel_attach(struct cgroup_taskset *tset) {} static inline void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight) {} diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ce2e94ccad0c..c798d2795243 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4045,15 +4045,17 @@ static inline bool child_cfs_rq_on_list(struct cfs_rq *cfs_rq) { struct cfs_rq *prev_cfs_rq; struct list_head *prev; + struct rq *rq = rq_of(cfs_rq); if (cfs_rq->on_list) { prev = cfs_rq->leaf_cfs_rq_list.prev; } else { - struct rq *rq = rq_of(cfs_rq); - prev = rq->tmp_alone_branch; } + if (prev == &rq->leaf_cfs_rq_list) + return false; + prev_cfs_rq = container_of(prev, struct cfs_rq, leaf_cfs_rq_list); return (prev_cfs_rq->tg->parent == cfs_rq->tg); @@ -5385,6 +5387,15 @@ static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq); static void set_delayed(struct sched_entity *se) { se->sched_delayed = 1; + + /* + * Delayed se of cfs_rq have no tasks queued on them. + * Do not adjust h_nr_runnable since dequeue_entities() + * will account it for blocked tasks. + */ + if (!entity_is_task(se)) + return; + for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); @@ -5397,6 +5408,16 @@ static void set_delayed(struct sched_entity *se) static void clear_delayed(struct sched_entity *se) { se->sched_delayed = 0; + + /* + * Delayed se of cfs_rq have no tasks queued on them. + * Do not adjust h_nr_runnable since a dequeue has + * already accounted for it or an enqueue of a task + * below it will account for it in enqueue_task_fair(). + */ + if (!entity_is_task(se)) + return; + for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 38e0e323dda2..023b844159c9 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -572,7 +572,7 @@ extern void sched_online_group(struct task_group *tg, extern void sched_destroy_group(struct task_group *tg); extern void sched_release_group(struct task_group *tg); -extern void sched_move_task(struct task_struct *tsk); +extern void sched_move_task(struct task_struct *tsk, bool for_autogroup); #ifdef CONFIG_FAIR_GROUP_SCHED extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); @@ -3259,11 +3259,11 @@ struct irqtime { }; DECLARE_PER_CPU(struct irqtime, cpu_irqtime); -DECLARE_STATIC_KEY_FALSE(sched_clock_irqtime); +extern int sched_clock_irqtime; static inline int irqtime_enabled(void) { - return static_branch_likely(&sched_clock_irqtime); + return sched_clock_irqtime; } /* @@ -3698,10 +3698,28 @@ static inline int __mm_cid_try_get(struct task_struct *t, struct mm_struct *mm) { struct cpumask *cidmask = mm_cidmask(mm); struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid; - int cid = __this_cpu_read(pcpu_cid->recent_cid); + int cid, max_nr_cid, allowed_max_nr_cid; + /* + * After shrinking the number of threads or reducing the number + * of allowed cpus, reduce the value of max_nr_cid so expansion + * of cid allocation will preserve cache locality if the number + * of threads or allowed cpus increase again. + */ + max_nr_cid = atomic_read(&mm->max_nr_cid); + while ((allowed_max_nr_cid = min_t(int, READ_ONCE(mm->nr_cpus_allowed), + atomic_read(&mm->mm_users))), + max_nr_cid > allowed_max_nr_cid) { + /* atomic_try_cmpxchg loads previous mm->max_nr_cid into max_nr_cid. */ + if (atomic_try_cmpxchg(&mm->max_nr_cid, &max_nr_cid, allowed_max_nr_cid)) { + max_nr_cid = allowed_max_nr_cid; + break; + } + } /* Try to re-use recent cid. This improves cache locality. */ - if (!mm_cid_is_unset(cid) && !cpumask_test_and_set_cpu(cid, cidmask)) + cid = __this_cpu_read(pcpu_cid->recent_cid); + if (!mm_cid_is_unset(cid) && cid < max_nr_cid && + !cpumask_test_and_set_cpu(cid, cidmask)) return cid; /* * Expand cid allocation if the maximum number of concurrency @@ -3709,8 +3727,9 @@ static inline int __mm_cid_try_get(struct task_struct *t, struct mm_struct *mm) * and number of threads. Expanding cid allocation as much as * possible improves cache locality. */ - cid = atomic_read(&mm->max_nr_cid); + cid = max_nr_cid; while (cid < READ_ONCE(mm->nr_cpus_allowed) && cid < atomic_read(&mm->mm_users)) { + /* atomic_try_cmpxchg loads previous mm->max_nr_cid into cid. */ if (!atomic_try_cmpxchg(&mm->max_nr_cid, &cid, cid + 1)) continue; if (!cpumask_test_and_set_cpu(cid, cidmask)) diff --git a/kernel/seccomp.c b/kernel/seccomp.c index f59381c4a2ff..7bbb408431eb 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -749,6 +749,15 @@ static bool seccomp_is_const_allow(struct sock_fprog_kern *fprog, if (WARN_ON_ONCE(!fprog)) return false; + /* Our single exception to filtering. */ +#ifdef __NR_uretprobe +#ifdef SECCOMP_ARCH_COMPAT + if (sd->arch == SECCOMP_ARCH_NATIVE) +#endif + if (sd->nr == __NR_uretprobe) + return true; +#endif + for (pc = 0; pc < fprog->len; pc++) { struct sock_filter *insn = &fprog->filter[pc]; u16 code = insn->code; @@ -1023,6 +1032,9 @@ static inline void seccomp_log(unsigned long syscall, long signr, u32 action, */ static const int mode1_syscalls[] = { __NR_seccomp_read, __NR_seccomp_write, __NR_seccomp_exit, __NR_seccomp_sigreturn, +#ifdef __NR_uretprobe + __NR_uretprobe, +#endif -1, /* negative terminated */ }; diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 7304d7cf47f2..2a7802ec480c 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -373,16 +373,18 @@ void clocksource_verify_percpu(struct clocksource *cs) cpumask_clear(&cpus_ahead); cpumask_clear(&cpus_behind); cpus_read_lock(); - preempt_disable(); + migrate_disable(); clocksource_verify_choose_cpus(); if (cpumask_empty(&cpus_chosen)) { - preempt_enable(); + migrate_enable(); cpus_read_unlock(); pr_warn("Not enough CPUs to check clocksource '%s'.\n", cs->name); return; } testcpu = smp_processor_id(); - pr_warn("Checking clocksource %s synchronization from CPU %d to CPUs %*pbl.\n", cs->name, testcpu, cpumask_pr_args(&cpus_chosen)); + pr_info("Checking clocksource %s synchronization from CPU %d to CPUs %*pbl.\n", + cs->name, testcpu, cpumask_pr_args(&cpus_chosen)); + preempt_disable(); for_each_cpu(cpu, &cpus_chosen) { if (cpu == testcpu) continue; @@ -402,6 +404,7 @@ void clocksource_verify_percpu(struct clocksource *cs) cs_nsec_min = cs_nsec; } preempt_enable(); + migrate_enable(); cpus_read_unlock(); if (!cpumask_empty(&cpus_ahead)) pr_warn(" CPUs %*pbl ahead of CPU %d for clocksource %s.\n", diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index f6d8df94045c..deb1aa32814e 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -58,6 +58,8 @@ #define HRTIMER_ACTIVE_SOFT (HRTIMER_ACTIVE_HARD << MASK_SHIFT) #define HRTIMER_ACTIVE_ALL (HRTIMER_ACTIVE_SOFT | HRTIMER_ACTIVE_HARD) +static void retrigger_next_event(void *arg); + /* * The timer bases: * @@ -111,7 +113,8 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = .clockid = CLOCK_TAI, .get_time = &ktime_get_clocktai, }, - } + }, + .csd = CSD_INIT(retrigger_next_event, NULL) }; static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = { @@ -124,6 +127,14 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = { [CLOCK_TAI] = HRTIMER_BASE_TAI, }; +static inline bool hrtimer_base_is_online(struct hrtimer_cpu_base *base) +{ + if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) + return true; + else + return likely(base->online); +} + /* * Functions and macros which are different for UP/SMP systems are kept in a * single place @@ -145,11 +156,6 @@ static struct hrtimer_cpu_base migration_cpu_base = { #define migration_base migration_cpu_base.clock_base[0] -static inline bool is_migration_base(struct hrtimer_clock_base *base) -{ - return base == &migration_base; -} - /* * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock * means that all timers which are tied to this base via timer->base are @@ -183,27 +189,54 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, } /* - * We do not migrate the timer when it is expiring before the next - * event on the target cpu. When high resolution is enabled, we cannot - * reprogram the target cpu hardware and we would cause it to fire - * late. To keep it simple, we handle the high resolution enabled and - * disabled case similar. + * Check if the elected target is suitable considering its next + * event and the hotplug state of the current CPU. + * + * If the elected target is remote and its next event is after the timer + * to queue, then a remote reprogram is necessary. However there is no + * guarantee the IPI handling the operation would arrive in time to meet + * the high resolution deadline. In this case the local CPU becomes a + * preferred target, unless it is offline. + * + * High and low resolution modes are handled the same way for simplicity. * * Called with cpu_base->lock of target cpu held. */ -static int -hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base) +static bool hrtimer_suitable_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base, + struct hrtimer_cpu_base *new_cpu_base, + struct hrtimer_cpu_base *this_cpu_base) { ktime_t expires; + /* + * The local CPU clockevent can be reprogrammed. Also get_target_base() + * guarantees it is online. + */ + if (new_cpu_base == this_cpu_base) + return true; + + /* + * The offline local CPU can't be the default target if the + * next remote target event is after this timer. Keep the + * elected new base. An IPI will we issued to reprogram + * it as a last resort. + */ + if (!hrtimer_base_is_online(this_cpu_base)) + return true; + expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset); - return expires < new_base->cpu_base->expires_next; + + return expires >= new_base->cpu_base->expires_next; } -static inline -struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, - int pinned) +static inline struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, int pinned) { + if (!hrtimer_base_is_online(base)) { + int cpu = cpumask_any_and(cpu_online_mask, housekeeping_cpumask(HK_TYPE_TIMER)); + + return &per_cpu(hrtimer_bases, cpu); + } + #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) if (static_branch_likely(&timers_migration_enabled) && !pinned) return &per_cpu(hrtimer_bases, get_nohz_timer_target()); @@ -254,8 +287,8 @@ again: raw_spin_unlock(&base->cpu_base->lock); raw_spin_lock(&new_base->cpu_base->lock); - if (new_cpu_base != this_cpu_base && - hrtimer_check_target(timer, new_base)) { + if (!hrtimer_suitable_target(timer, new_base, new_cpu_base, + this_cpu_base)) { raw_spin_unlock(&new_base->cpu_base->lock); raw_spin_lock(&base->cpu_base->lock); new_cpu_base = this_cpu_base; @@ -264,8 +297,7 @@ again: } WRITE_ONCE(timer->base, new_base); } else { - if (new_cpu_base != this_cpu_base && - hrtimer_check_target(timer, new_base)) { + if (!hrtimer_suitable_target(timer, new_base, new_cpu_base, this_cpu_base)) { new_cpu_base = this_cpu_base; goto again; } @@ -275,11 +307,6 @@ again: #else /* CONFIG_SMP */ -static inline bool is_migration_base(struct hrtimer_clock_base *base) -{ - return false; -} - static inline struct hrtimer_clock_base * lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __acquires(&timer->base->cpu_base->lock) @@ -716,8 +743,6 @@ static inline int hrtimer_is_hres_enabled(void) return hrtimer_hres_enabled; } -static void retrigger_next_event(void *arg); - /* * Switch to high resolution mode */ @@ -1205,6 +1230,7 @@ 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); struct hrtimer_clock_base *new_base; bool force_local, first; @@ -1216,10 +1242,16 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, * and enforce reprogramming after it is queued no matter whether * it is the new first expiring timer again or not. */ - force_local = base->cpu_base == this_cpu_ptr(&hrtimer_bases); + force_local = base->cpu_base == this_cpu_base; force_local &= base->cpu_base->next_timer == timer; /* + * Don't force local queuing if this enqueue happens on a unplugged + * CPU after hrtimer_cpu_dying() has been invoked. + */ + force_local &= this_cpu_base->online; + + /* * Remove an active timer from the queue. In case it is not queued * on the current CPU, make sure that remove_hrtimer() updates the * remote data correctly. @@ -1248,8 +1280,27 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, } first = enqueue_hrtimer(timer, new_base, mode); - if (!force_local) - return first; + if (!force_local) { + /* + * If the current CPU base is online, then the timer is + * never queued on a remote CPU if it would be the first + * expiring timer there. + */ + if (hrtimer_base_is_online(this_cpu_base)) + return first; + + /* + * Timer was enqueued remote because the current base is + * already offline. If the timer is the first to expire, + * kick the remote CPU to reprogram the clock event. + */ + if (first) { + struct hrtimer_cpu_base *new_cpu_base = new_base->cpu_base; + + smp_call_function_single_async(new_cpu_base->cpu, &new_cpu_base->csd); + } + return 0; + } /* * Timer was forced to stay on the current CPU to avoid @@ -1370,6 +1421,18 @@ static void hrtimer_sync_wait_running(struct hrtimer_cpu_base *cpu_base, } } +#ifdef CONFIG_SMP +static __always_inline bool is_migration_base(struct hrtimer_clock_base *base) +{ + return base == &migration_base; +} +#else +static __always_inline bool is_migration_base(struct hrtimer_clock_base *base) +{ + return false; +} +#endif + /* * This function is called on PREEMPT_RT kernels when the fast path * deletion of a timer failed because the timer callback function was diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index 9cb9b6584ea1..2f6330831f08 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -1675,6 +1675,9 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node) } while (i < tmigr_hierarchy_levels); + /* Assert single root */ + WARN_ON_ONCE(!err && !group->parent && !list_is_singular(&tmigr_level_list[top])); + while (i > 0) { group = stack[--i]; @@ -1716,7 +1719,12 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node) WARN_ON_ONCE(top == 0); lvllist = &tmigr_level_list[top]; - if (group->num_children == 1 && list_is_singular(lvllist)) { + + /* + * Newly created root level should have accounted the upcoming + * CPU's child group and pre-accounted the old root. + */ + if (group->num_children == 2 && list_is_singular(lvllist)) { /* * The target CPU must never do the prepare work, except * on early boot when the boot CPU is the target. Otherwise diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 2560b312ad57..33082c4e8154 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -403,13 +403,12 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num) lockdep_assert_held(&fprobe_mutex); fprobe_graph_active--; - if (!fprobe_graph_active) { - /* Q: should we unregister it ? */ + /* Q: should we unregister it ? */ + if (!fprobe_graph_active) unregister_ftrace_graph(&fprobe_graph_ops); - return; - } - ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); + if (num) + ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); } static int symbols_cmp(const void *a, const void *b) @@ -679,8 +678,7 @@ int unregister_fprobe(struct fprobe *fp) } del_fprobe_hash(fp); - if (count) - fprobe_graph_remove_ips(addrs, count); + fprobe_graph_remove_ips(addrs, count); kfree_rcu(hlist_array, rcu); fp->hlist_array = NULL; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 728ecda6e8d4..fc88e0688daf 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -540,6 +540,7 @@ static int function_stat_show(struct seq_file *m, void *v) static struct trace_seq s; unsigned long long avg; unsigned long long stddev; + unsigned long long stddev_denom; #endif guard(mutex)(&ftrace_profile_lock); @@ -559,23 +560,19 @@ static int function_stat_show(struct seq_file *m, void *v) #ifdef CONFIG_FUNCTION_GRAPH_TRACER seq_puts(m, " "); - /* Sample standard deviation (s^2) */ - if (rec->counter <= 1) - stddev = 0; - else { - /* - * Apply Welford's method: - * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2) - */ + /* + * Variance formula: + * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2) + * Maybe Welford's method is better here? + * Divide only by 1000 for ns^2 -> us^2 conversion. + * trace_print_graph_duration will divide by 1000 again. + */ + stddev = 0; + stddev_denom = rec->counter * (rec->counter - 1) * 1000; + if (stddev_denom) { stddev = rec->counter * rec->time_squared - rec->time * rec->time; - - /* - * Divide only 1000 for ns^2 -> us^2 conversion. - * trace_print_graph_duration will divide 1000 again. - */ - stddev = div64_ul(stddev, - rec->counter * (rec->counter - 1) * 1000); + stddev = div64_ul(stddev, stddev_denom); } trace_seq_init(&s); @@ -3220,15 +3217,22 @@ static struct ftrace_hash *copy_hash(struct ftrace_hash *src) * The filter_hash updates uses just the append_hash() function * and the notrace_hash does not. */ -static int append_hash(struct ftrace_hash **hash, struct ftrace_hash *new_hash) +static int append_hash(struct ftrace_hash **hash, struct ftrace_hash *new_hash, + int size_bits) { struct ftrace_func_entry *entry; int size; int i; - /* An empty hash does everything */ - if (ftrace_hash_empty(*hash)) - return 0; + if (*hash) { + /* An empty hash does everything */ + if (ftrace_hash_empty(*hash)) + return 0; + } else { + *hash = alloc_ftrace_hash(size_bits); + if (!*hash) + return -ENOMEM; + } /* If new_hash has everything make hash have everything */ if (ftrace_hash_empty(new_hash)) { @@ -3292,16 +3296,18 @@ static int intersect_hash(struct ftrace_hash **hash, struct ftrace_hash *new_has /* Return a new hash that has a union of all @ops->filter_hash entries */ static struct ftrace_hash *append_hashes(struct ftrace_ops *ops) { - struct ftrace_hash *new_hash; + struct ftrace_hash *new_hash = NULL; struct ftrace_ops *subops; + int size_bits; int ret; - new_hash = alloc_ftrace_hash(ops->func_hash->filter_hash->size_bits); - if (!new_hash) - return NULL; + if (ops->func_hash->filter_hash) + size_bits = ops->func_hash->filter_hash->size_bits; + else + size_bits = FTRACE_HASH_DEFAULT_BITS; list_for_each_entry(subops, &ops->subop_list, list) { - ret = append_hash(&new_hash, subops->func_hash->filter_hash); + ret = append_hash(&new_hash, subops->func_hash->filter_hash, size_bits); if (ret < 0) { free_ftrace_hash(new_hash); return NULL; @@ -3310,7 +3316,8 @@ static struct ftrace_hash *append_hashes(struct ftrace_ops *ops) if (ftrace_hash_empty(new_hash)) break; } - return new_hash; + /* Can't return NULL as that means this failed */ + return new_hash ? : EMPTY_HASH; } /* Make @ops trace evenything except what all its subops do not trace */ @@ -3505,7 +3512,8 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int filter_hash = alloc_and_copy_ftrace_hash(size_bits, ops->func_hash->filter_hash); if (!filter_hash) return -ENOMEM; - ret = append_hash(&filter_hash, subops->func_hash->filter_hash); + ret = append_hash(&filter_hash, subops->func_hash->filter_hash, + size_bits); if (ret < 0) { free_ftrace_hash(filter_hash); return ret; @@ -5707,6 +5715,9 @@ __ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) return -ENOENT; free_hash_entry(hash, entry); return 0; + } else if (__ftrace_lookup_ip(hash, ip) != NULL) { + /* Already exists */ + return 0; } entry = add_hash_entry(hash, ip); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index b8e0ae15ca5b..bb6089c2951e 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1672,7 +1672,8 @@ static void *rb_range_buffer(struct ring_buffer_per_cpu *cpu_buffer, int idx) * must be the same. */ static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu, - struct trace_buffer *buffer, int nr_pages) + struct trace_buffer *buffer, int nr_pages, + unsigned long *subbuf_mask) { int subbuf_size = PAGE_SIZE; struct buffer_data_page *subbuf; @@ -1680,6 +1681,9 @@ static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu, unsigned long buffers_end; int i; + if (!subbuf_mask) + return false; + /* Check the meta magic and meta struct size */ if (meta->magic != RING_BUFFER_META_MAGIC || meta->struct_size != sizeof(*meta)) { @@ -1712,6 +1716,8 @@ static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu, subbuf = rb_subbufs_from_meta(meta); + bitmap_clear(subbuf_mask, 0, meta->nr_subbufs); + /* Is the meta buffers and the subbufs themselves have correct data? */ for (i = 0; i < meta->nr_subbufs; i++) { if (meta->buffers[i] < 0 || @@ -1725,6 +1731,12 @@ static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu, return false; } + if (test_bit(meta->buffers[i], subbuf_mask)) { + pr_info("Ring buffer boot meta [%d] array has duplicates\n", cpu); + return false; + } + + set_bit(meta->buffers[i], subbuf_mask); subbuf = (void *)subbuf + subbuf_size; } @@ -1838,6 +1850,11 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->cpu); goto invalid; } + + /* If the buffer has content, update pages_touched */ + if (ret) + local_inc(&cpu_buffer->pages_touched); + entries += ret; entry_bytes += local_read(&head_page->page->commit); local_set(&cpu_buffer->head_page->entries, ret); @@ -1889,17 +1906,22 @@ static void rb_meta_init_text_addr(struct ring_buffer_meta *meta) static void rb_range_meta_init(struct trace_buffer *buffer, int nr_pages) { struct ring_buffer_meta *meta; + unsigned long *subbuf_mask; unsigned long delta; void *subbuf; int cpu; int i; + /* Create a mask to test the subbuf array */ + subbuf_mask = bitmap_alloc(nr_pages + 1, GFP_KERNEL); + /* If subbuf_mask fails to allocate, then rb_meta_valid() will return false */ + for (cpu = 0; cpu < nr_cpu_ids; cpu++) { void *next_meta; meta = rb_range_meta(buffer, nr_pages, cpu); - if (rb_meta_valid(meta, cpu, buffer, nr_pages)) { + if (rb_meta_valid(meta, cpu, buffer, nr_pages, subbuf_mask)) { /* Make the mappings match the current address */ subbuf = rb_subbufs_from_meta(meta); delta = (unsigned long)subbuf - meta->first_buffer; @@ -1943,6 +1965,7 @@ static void rb_range_meta_init(struct trace_buffer *buffer, int nr_pages) subbuf += meta->subbuf_size; } } + bitmap_free(subbuf_mask); } static void *rbm_start(struct seq_file *m, loff_t *pos) @@ -7126,6 +7149,7 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu, kfree(cpu_buffer->subbuf_ids); cpu_buffer->subbuf_ids = NULL; rb_free_meta_page(cpu_buffer); + atomic_dec(&cpu_buffer->resize_disabled); } unlock: diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 1496a5ac33ae..0e6d517e74e0 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5977,8 +5977,6 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, ssize_t tracing_resize_ring_buffer(struct trace_array *tr, unsigned long size, int cpu_id) { - int ret; - guard(mutex)(&trace_types_lock); if (cpu_id != RING_BUFFER_ALL_CPUS) { @@ -5987,11 +5985,7 @@ ssize_t tracing_resize_ring_buffer(struct trace_array *tr, return -EINVAL; } - ret = __tracing_resize_ring_buffer(tr, size, cpu_id); - if (ret < 0) - ret = -ENOMEM; - - return ret; + return __tracing_resize_ring_buffer(tr, size, cpu_id); } static void update_last_data(struct trace_array *tr) @@ -8285,6 +8279,10 @@ static int tracing_buffers_mmap(struct file *filp, struct vm_area_struct *vma) struct trace_iterator *iter = &info->iter; int ret = 0; + /* Currently the boot mapped buffer is not supported for mmap */ + if (iter->tr->flags & TRACE_ARRAY_FL_BOOT) + return -ENODEV; + ret = get_snapshot_map(iter->tr); if (ret) return ret; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 4cb275316e51..513de9ceb80e 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1591,6 +1591,13 @@ s_next(struct seq_file *m, void *v, loff_t *pos) return iter; #endif + /* + * The iter is allocated in s_start() and passed via the 'v' + * parameter. To stop the iterator, NULL must be returned. But + * the return value is what the 'v' parameter in s_stop() receives + * and frees. Free iter here as it will no longer be used. + */ + kfree(iter); return NULL; } @@ -1667,9 +1674,9 @@ static int s_show(struct seq_file *m, void *v) } #endif -static void s_stop(struct seq_file *m, void *p) +static void s_stop(struct seq_file *m, void *v) { - kfree(p); + kfree(v); t_stop(m, NULL); } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 261163b00137..53dc6719181e 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5689,12 +5689,16 @@ static int event_hist_open(struct inode *inode, struct file *file) guard(mutex)(&event_mutex); event_file = event_file_data(file); - if (!event_file) - return -ENODEV; + if (!event_file) { + ret = -ENODEV; + goto err; + } hist_file = kzalloc(sizeof(*hist_file), GFP_KERNEL); - if (!hist_file) - return -ENOMEM; + if (!hist_file) { + ret = -ENOMEM; + goto err; + } hist_file->file = file; hist_file->last_act = get_hist_hit_count(event_file); @@ -5702,9 +5706,14 @@ static int event_hist_open(struct inode *inode, struct file *file) /* Clear private_data to avoid warning in single_open() */ file->private_data = NULL; ret = single_open(file, hist_show, hist_file); - if (ret) + if (ret) { kfree(hist_file); + goto err; + } + return 0; +err: + tracing_release_file_tr(inode, file); return ret; } @@ -5979,7 +5988,10 @@ static int event_hist_debug_open(struct inode *inode, struct file *file) /* Clear private_data to avoid warning in single_open() */ file->private_data = NULL; - return single_open(file, hist_debug_show, file); + ret = single_open(file, hist_debug_show, file); + if (ret) + tracing_release_file_tr(inode, file); + return ret; } const struct file_operations event_hist_debug_fops = { @@ -6724,27 +6736,27 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops, if (existing_hist_update_only(glob, trigger_data, file)) goto out_free; - ret = event_trigger_register(cmd_ops, file, glob, trigger_data); - if (ret < 0) - goto out_free; + if (!get_named_trigger_data(trigger_data)) { - if (get_named_trigger_data(trigger_data)) - goto enable; + ret = create_actions(hist_data); + if (ret) + goto out_free; - ret = create_actions(hist_data); - if (ret) - goto out_unreg; + if (has_hist_vars(hist_data) || hist_data->n_var_refs) { + ret = save_hist_vars(hist_data); + if (ret) + goto out_free; + } - if (has_hist_vars(hist_data) || hist_data->n_var_refs) { - ret = save_hist_vars(hist_data); + ret = tracing_map_init(hist_data->map); if (ret) - goto out_unreg; + goto out_free; } - ret = tracing_map_init(hist_data->map); - if (ret) - goto out_unreg; -enable: + ret = event_trigger_register(cmd_ops, file, glob, trigger_data); + if (ret < 0) + goto out_free; + ret = hist_trigger_enable(trigger_data, file); if (ret) goto out_unreg; diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c index b8f3c4ba309b..e27305d31fc5 100644 --- a/kernel/trace/trace_fprobe.c +++ b/kernel/trace/trace_fprobe.c @@ -1049,6 +1049,19 @@ static int parse_symbol_and_return(int argc, const char *argv[], if (*is_return) return 0; + if (is_tracepoint) { + tmp = *symbol; + while (*tmp && (isalnum(*tmp) || *tmp == '_')) + tmp++; + if (*tmp) { + /* find a wrong character. */ + trace_probe_log_err(tmp - *symbol, BAD_TP_NAME); + kfree(*symbol); + *symbol = NULL; + return -EINVAL; + } + } + /* If there is $retval, this should be a return fprobe. */ for (i = 2; i < argc; i++) { tmp = strstr(argv[i], "$retval"); @@ -1056,6 +1069,8 @@ static int parse_symbol_and_return(int argc, const char *argv[], if (is_tracepoint) { trace_probe_log_set_index(i); trace_probe_log_err(tmp - argv[i], RETVAL_ON_PROBE); + kfree(*symbol); + *symbol = NULL; return -EINVAL; } *is_return = true; @@ -1215,6 +1230,11 @@ static int trace_fprobe_create_internal(int argc, const char *argv[], if (is_return && tf->tp.entry_arg) { tf->fp.entry_handler = trace_fprobe_entry_handler; tf->fp.entry_data_size = traceprobe_get_entry_data_size(&tf->tp); + if (ALIGN(tf->fp.entry_data_size, sizeof(long)) > MAX_FPROBE_DATA_SIZE) { + trace_probe_log_set_index(2); + trace_probe_log_err(0, TOO_MANY_EARGS); + return -E2BIG; + } } ret = traceprobe_set_print_fmt(&tf->tp, diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index d358c9935164..df56f9b76010 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -216,7 +216,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip, parent_ip = function_get_true_parent_ip(parent_ip, fregs); - trace_ctx = tracing_gen_ctx(); + trace_ctx = tracing_gen_ctx_dec(); data = this_cpu_ptr(tr->array_buffer.data); if (!atomic_read(&data->disabled)) @@ -321,7 +321,6 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip, struct trace_array *tr = op->private; struct trace_array_cpu *data; unsigned int trace_ctx; - unsigned long flags; int bit; if (unlikely(!tr->function_enabled)) @@ -347,8 +346,7 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip, if (is_repeat_check(tr, last_info, ip, parent_ip)) goto out; - local_save_flags(flags); - trace_ctx = tracing_gen_ctx_flags(flags); + trace_ctx = tracing_gen_ctx_dec(); process_repeats(tr, ip, parent_ip, last_info, trace_ctx); trace_function(tr, ip, parent_ip, trace_ctx); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 54d850997c0a..136c750b0b4d 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -198,7 +198,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace, * returning from the function. */ if (ftrace_graph_notrace_addr(trace->func)) { - *task_var |= TRACE_GRAPH_NOTRACE_BIT; + *task_var |= TRACE_GRAPH_NOTRACE; /* * Need to return 1 to have the return called * that will clear the NOTRACE bit. diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 5803e6a41570..96792bc4b092 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -36,7 +36,6 @@ #define MAX_BTF_ARGS_LEN 128 #define MAX_DENTRY_ARGS_LEN 256 #define MAX_STRING_SIZE PATH_MAX -#define MAX_ARG_BUF_LEN (MAX_TRACE_ARGS * MAX_ARG_NAME_LEN) /* Reserved field names */ #define FIELD_STRING_IP "__probe_ip" @@ -481,6 +480,7 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call, C(NON_UNIQ_SYMBOL, "The symbol is not unique"), \ C(BAD_RETPROBE, "Retprobe address must be an function entry"), \ C(NO_TRACEPOINT, "Tracepoint is not found"), \ + C(BAD_TP_NAME, "Invalid character in tracepoint name"),\ C(BAD_ADDR_SUFFIX, "Invalid probed address suffix"), \ C(NO_GROUP_NAME, "Group name is not specified"), \ C(GROUP_TOO_LONG, "Group name is too long"), \ @@ -544,7 +544,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call, C(NO_BTF_FIELD, "This field is not found."), \ C(BAD_BTF_TID, "Failed to get BTF type info."),\ C(BAD_TYPE4STR, "This type does not fit for string."),\ - C(NEED_STRING_TYPE, "$comm and immediate-string only accepts string type"), + C(NEED_STRING_TYPE, "$comm and immediate-string only accepts string type"),\ + C(TOO_MANY_EARGS, "Too many entry arguments specified"), #undef C #define C(a, b) TP_ERR_##a diff --git a/kernel/vhost_task.c b/kernel/vhost_task.c index 8800f5acc007..2ef2e1b80091 100644 --- a/kernel/vhost_task.c +++ b/kernel/vhost_task.c @@ -133,7 +133,7 @@ struct vhost_task *vhost_task_create(bool (*fn)(void *), vtsk = kzalloc(sizeof(*vtsk), GFP_KERNEL); if (!vtsk) - return NULL; + return ERR_PTR(-ENOMEM); init_completion(&vtsk->exited); mutex_init(&vtsk->exit_mutex); vtsk->data = arg; @@ -145,7 +145,7 @@ struct vhost_task *vhost_task_create(bool (*fn)(void *), tsk = copy_process(NULL, 0, NUMA_NO_NODE, &args); if (IS_ERR(tsk)) { kfree(vtsk); - return NULL; + return ERR_PTR(PTR_ERR(tsk)); } vtsk->task = tsk; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3c2c45313c88..bfe030b443e2 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2254,8 +2254,10 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, * queues a new work item to a wq after destroy_workqueue(wq). */ if (unlikely(wq->flags & (__WQ_DESTROYING | __WQ_DRAINING) && - WARN_ON_ONCE(!is_chained_work(wq)))) + WARN_ONCE(!is_chained_work(wq), "workqueue: cannot queue %ps on wq %s\n", + work->func, wq->name))) { return; + } rcu_read_lock(); retry: /* pwq which will be used unless @work is executing elsewhere */ @@ -3517,12 +3519,6 @@ repeat: } /* - * Put the reference grabbed by send_mayday(). @pool won't - * go away while we're still attached to it. - */ - put_pwq(pwq); - - /* * Leave this pool. Notify regular workers; otherwise, we end up * with 0 concurrency and stalling the execution. */ @@ -3532,6 +3528,12 @@ repeat: worker_detach_from_pool(rescuer); + /* + * Put the reference grabbed by send_mayday(). @pool might + * go away any time after it. + */ + put_pwq_unlocked(pwq); + raw_spin_lock_irq(&wq_mayday_lock); } |