diff options
Diffstat (limited to 'kernel')
47 files changed, 302 insertions, 180 deletions
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index f0b93ced5a7f..d1249340fd6b 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -1,6 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 obj-y := core.o -CFLAGS_core.o += $(call cc-disable-warning, override-init) +ifneq ($(CONFIG_BPF_JIT_ALWAYS_ON),y) +# ___bpf_prog_run() needs GCSE disabled on x86; see 3193c0836f203 for details +cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse +endif +CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index aed74b853415..553107f4706a 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -27,7 +27,11 @@ noinline RET bpf_lsm_##NAME(__VA_ARGS__) \ #include <linux/lsm_hook_defs.h> #undef LSM_HOOK -#define BPF_LSM_SYM_PREFX "bpf_lsm_" +#define LSM_HOOK(RET, DEFAULT, NAME, ...) BTF_ID(func, bpf_lsm_##NAME) +BTF_SET_START(bpf_lsm_hooks) +#include <linux/lsm_hook_defs.h> +#undef LSM_HOOK +BTF_SET_END(bpf_lsm_hooks) int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, const struct bpf_prog *prog) @@ -38,8 +42,7 @@ int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, return -EINVAL; } - if (strncmp(BPF_LSM_SYM_PREFX, prog->aux->attach_func_name, - sizeof(BPF_LSM_SYM_PREFX) - 1)) { + if (!btf_id_set_contains(&bpf_lsm_hooks, prog->aux->attach_btf_id)) { bpf_log(vlog, "attach_btf_id %u points to wrong type name %s\n", prog->aux->attach_btf_id, prog->aux->attach_func_name); return -EINVAL; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9268d77898b7..55454d2278b1 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1369,7 +1369,7 @@ u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) * * Decode and execute eBPF instructions. */ -static u64 __no_fgcse ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack) +static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack) { #define BPF_INSN_2_LBL(x, y) [BPF_##x | BPF_##y] = &&x##_##y #define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 7bf18d92af41..ec46266aaf1c 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -855,6 +855,32 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, } } +static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr, + void *value, bool onallcpus) +{ + /* When using prealloc and not setting the initial value on all cpus, + * zero-fill element values for other cpus (just as what happens when + * not using prealloc). Otherwise, bpf program has no way to ensure + * known initial values for cpus other than current one + * (onallcpus=false always when coming from bpf prog). + */ + if (htab_is_prealloc(htab) && !onallcpus) { + u32 size = round_up(htab->map.value_size, 8); + int current_cpu = raw_smp_processor_id(); + int cpu; + + for_each_possible_cpu(cpu) { + if (cpu == current_cpu) + bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value, + size); + else + memset(per_cpu_ptr(pptr, cpu), 0, size); + } + } else { + pcpu_copy_value(htab, pptr, value, onallcpus); + } +} + static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab) { return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS && @@ -925,7 +951,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, } } - pcpu_copy_value(htab, pptr, value, onallcpus); + pcpu_init_value(htab, pptr, value, onallcpus); if (!prealloc) htab_elem_set_ptr(l_new, key_size, pptr); @@ -1225,7 +1251,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size), value, onallcpus); } else { - pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size), + pcpu_init_value(htab, htab_elem_get_ptr(l_new, key_size), value, onallcpus); hlist_nulls_add_head_rcu(&l_new->hash_node, head); l_new = NULL; diff --git a/kernel/bpf/preload/Kconfig b/kernel/bpf/preload/Kconfig index ace49111d3a3..26bced262473 100644 --- a/kernel/bpf/preload/Kconfig +++ b/kernel/bpf/preload/Kconfig @@ -6,6 +6,7 @@ config USERMODE_DRIVER menuconfig BPF_PRELOAD bool "Preload BPF file system with kernel specific program and map iterators" depends on BPF + depends on BPF_SYSCALL # The dependency on !COMPILE_TEST prevents it from being enabled # in allmodconfig or allyesconfig configurations depends on !COMPILE_TEST diff --git a/kernel/capability.c b/kernel/capability.c index 7c59b096c98a..de7eac903a2a 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -418,7 +418,7 @@ EXPORT_SYMBOL(ns_capable_noaudit); /** * ns_capable_setid - Determine if the current task has a superior capability * in effect, while signalling that this check is being done from within a - * setid syscall. + * setid or setgroups syscall. * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index 78b23f089cf1..905c3fa005f1 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -2,7 +2,7 @@ /* * Copyright (c) 2014 The Linux Foundation */ -#include <linux/dma-mapping.h> +#include <linux/dma-map-ops.h> #include <linux/slab.h> #include <linux/vmalloc.h> diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index b4eea0abc3f0..781b9dca197c 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -229,6 +229,7 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; } io_tlb_index = 0; + no_iotlb_memory = false; if (verbose) swiotlb_print_info(); @@ -260,9 +261,11 @@ swiotlb_init(int verbose) if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose)) return; - if (io_tlb_start) + if (io_tlb_start) { memblock_free_early(io_tlb_start, PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + io_tlb_start = 0; + } pr_warn("Cannot allocate buffer"); no_iotlb_memory = true; } @@ -360,6 +363,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; } io_tlb_index = 0; + no_iotlb_memory = false; swiotlb_print_info(); @@ -441,14 +445,11 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr, } } -phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, - dma_addr_t tbl_dma_addr, - phys_addr_t orig_addr, - size_t mapping_size, - size_t alloc_size, - enum dma_data_direction dir, - unsigned long attrs) +phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr, + size_t mapping_size, size_t alloc_size, + enum dma_data_direction dir, unsigned long attrs) { + dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(hwdev, io_tlb_start); unsigned long flags; phys_addr_t tlb_addr; unsigned int nslots, stride, index, wrap; @@ -667,9 +668,8 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size, swiotlb_force); - swiotlb_addr = swiotlb_tbl_map_single(dev, - phys_to_dma_unencrypted(dev, io_tlb_start), - paddr, size, size, dir, attrs); + swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, dir, + attrs); if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR) return DMA_MAPPING_ERROR; diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 2b8366693d5c..e9e2df3f3f9e 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -337,10 +337,10 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs) * already contains a warning when RCU is not watching, so no point * in having another one here. */ + lockdep_hardirqs_off(CALLER_ADDR0); instrumentation_begin(); rcu_irq_enter_check_tick(); - /* Use the combo lockdep/tracing function */ - trace_hardirqs_off(); + trace_hardirqs_off_finish(); instrumentation_end(); return ret; diff --git a/kernel/events/core.c b/kernel/events/core.c index da467e1dd49a..5a29ab09e72d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10085,6 +10085,7 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, if (token == IF_SRC_FILE || token == IF_SRC_FILEADDR) { int fpos = token == IF_SRC_FILE ? 2 : 1; + kfree(filename); filename = match_strdup(&args[fpos]); if (!filename) { ret = -ENOMEM; @@ -10131,16 +10132,13 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, */ ret = -EOPNOTSUPP; if (!event->ctx->task) - goto fail_free_name; + goto fail; /* look up the path and grab its inode */ ret = kern_path(filename, LOOKUP_FOLLOW, &filter->path); if (ret) - goto fail_free_name; - - kfree(filename); - filename = NULL; + goto fail; ret = -EINVAL; if (!filter->path.dentry || @@ -10160,13 +10158,13 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, if (state != IF_STATE_ACTION) goto fail; + kfree(filename); kfree(orig); return 0; -fail_free_name: - kfree(filename); fail: + kfree(filename); free_filters_list(filters); kfree(orig); diff --git a/kernel/exit.c b/kernel/exit.c index 87a2d515de0d..1f236ed375f8 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -454,7 +454,10 @@ static void exit_mm(void) mmap_read_unlock(mm); self.task = current; - self.next = xchg(&core_state->dumper.next, &self); + if (self.task->flags & PF_SIGNALED) + self.next = xchg(&core_state->dumper.next, &self); + else + self.task = NULL; /* * Implies mb(), the result of xchg() must be visible * to core_state->dumper. diff --git a/kernel/fork.c b/kernel/fork.c index 32083db7a2a2..6d266388d380 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2167,14 +2167,9 @@ static __latent_entropy struct task_struct *copy_process( /* ok, now we should be set up.. */ p->pid = pid_nr(pid); if (clone_flags & CLONE_THREAD) { - p->exit_signal = -1; p->group_leader = current->group_leader; p->tgid = current->tgid; } else { - if (clone_flags & CLONE_PARENT) - p->exit_signal = current->group_leader->exit_signal; - else - p->exit_signal = args->exit_signal; p->group_leader = p; p->tgid = p->pid; } @@ -2218,9 +2213,14 @@ static __latent_entropy struct task_struct *copy_process( if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { p->real_parent = current->real_parent; p->parent_exec_id = current->parent_exec_id; + if (clone_flags & CLONE_THREAD) + p->exit_signal = -1; + else + p->exit_signal = current->group_leader->exit_signal; } else { p->real_parent = current; p->parent_exec_id = current->self_exec_id; + p->exit_signal = args->exit_signal; } klp_copy_process(p); diff --git a/kernel/futex.c b/kernel/futex.c index 680854dcf156..ac328874f6e5 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -39,6 +39,7 @@ #include <linux/freezer.h> #include <linux/memblock.h> #include <linux/fault-inject.h> +#include <linux/time_namespace.h> #include <asm/futex.h> @@ -1502,8 +1503,10 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_ */ newval = FUTEX_WAITERS | task_pid_vnr(new_owner); - if (unlikely(should_fail_futex(true))) + if (unlikely(should_fail_futex(true))) { ret = -EFAULT; + goto out_unlock; + } ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval); if (!ret && (curval != uval)) { @@ -2377,10 +2380,22 @@ retry: } /* - * Since we just failed the trylock; there must be an owner. + * The trylock just failed, so either there is an owner or + * there is a higher priority waiter than this one. */ newowner = rt_mutex_owner(&pi_state->pi_mutex); - BUG_ON(!newowner); + /* + * If the higher priority waiter has not yet taken over the + * rtmutex then newowner is NULL. We can't return here with + * that state because it's inconsistent vs. the user space + * state. So drop the locks and try again. It's a valid + * situation and not any different from the other retry + * conditions. + */ + if (unlikely(!newowner)) { + err = -EAGAIN; + goto handle_err; + } } else { WARN_ON_ONCE(argowner != current); if (oldowner == current) { @@ -3797,6 +3812,8 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, t = timespec64_to_ktime(ts); if (cmd == FUTEX_WAIT) t = ktime_add_safe(ktime_get(), t); + else if (!(op & FUTEX_CLOCK_REALTIME)) + t = timens_ktime_to_host(CLOCK_MONOTONIC, t); tp = &t; } /* @@ -3989,6 +4006,8 @@ SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val, t = timespec64_to_ktime(ts); if (cmd == FUTEX_WAIT) t = ktime_add_safe(ktime_get(), t); + else if (!(op & FUTEX_CLOCK_REALTIME)) + t = timens_ktime_to_host(CLOCK_MONOTONIC, t); tp = &t; } if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE || diff --git a/kernel/groups.c b/kernel/groups.c index 6ee6691f6839..fe7e6385530e 100644 --- a/kernel/groups.c +++ b/kernel/groups.c @@ -178,7 +178,7 @@ bool may_setgroups(void) { struct user_namespace *user_ns = current_user_ns(); - return ns_capable(user_ns, CAP_SETGID) && + return ns_capable_setid(user_ns, CAP_SETGID) && userns_may_setgroups(user_ns); } diff --git a/kernel/hung_task.c b/kernel/hung_task.c index ce76f490126c..396ebaebea3f 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -225,8 +225,7 @@ static long hung_timeout_jiffies(unsigned long last_checked, * Process updating of timeout sysctl */ int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { int ret; diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 10a5aff4eecc..164a031cfdb6 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -82,6 +82,7 @@ config IRQ_FASTEOI_HIERARCHY_HANDLERS # Generic IRQ IPI support config GENERIC_IRQ_IPI bool + select IRQ_DOMAIN_HIERARCHY # Generic MSI interrupt support config GENERIC_MSI_IRQ diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 4fb15fa96734..fe9de067771c 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -40,10 +40,10 @@ extern const u8 kallsyms_names[] __weak; * has one (eg: FRV). */ extern const unsigned int kallsyms_num_syms -__attribute__((weak, section(".rodata"))); +__section(".rodata") __attribute__((weak)); extern const unsigned long kallsyms_relative_base -__attribute__((weak, section(".rodata"))); +__section(".rodata") __attribute__((weak)); extern const char kallsyms_token_table[] __weak; extern const u16 kallsyms_token_index[] __weak; diff --git a/kernel/kcov.c b/kernel/kcov.c index 6b8368be89c8..80bfe71bbe13 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -1023,6 +1023,8 @@ EXPORT_SYMBOL(kcov_remote_stop); /* See the comment before kcov_remote_start() for usage details. */ u64 kcov_common_handle(void) { + if (!in_task()) + return 0; return current->kcov_handle; } EXPORT_SYMBOL(kcov_common_handle); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 8a12a25fa40d..41fdbb7953c6 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1249,7 +1249,13 @@ __acquires(hlist_lock) *head = &kretprobe_inst_table[hash]; hlist_lock = kretprobe_table_lock_ptr(hash); - raw_spin_lock_irqsave(hlist_lock, *flags); + /* + * Nested is a workaround that will soon not be needed. + * There's other protections that make sure the same lock + * is not taken on the same CPU that lockdep is unaware of. + * Differentiate when it is taken in NMI context. + */ + raw_spin_lock_irqsave_nested(hlist_lock, *flags, !!in_nmi()); } NOKPROBE_SYMBOL(kretprobe_hash_lock); @@ -1258,7 +1264,13 @@ static void kretprobe_table_lock(unsigned long hash, __acquires(hlist_lock) { raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); - raw_spin_lock_irqsave(hlist_lock, *flags); + /* + * Nested is a workaround that will soon not be needed. + * There's other protections that make sure the same lock + * is not taken on the same CPU that lockdep is unaware of. + * Differentiate when it is taken in NMI context. + */ + raw_spin_lock_irqsave_nested(hlist_lock, *flags, !!in_nmi()); } NOKPROBE_SYMBOL(kretprobe_table_lock); @@ -2028,7 +2040,12 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs) /* TODO: consider to only swap the RA after the last pre_handler fired */ hash = hash_ptr(current, KPROBE_HASH_BITS); - raw_spin_lock_irqsave(&rp->lock, flags); + /* + * Nested is a workaround that will soon not be needed. + * There's other protections that make sure the same lock + * is not taken on the same CPU that lockdep is unaware of. + */ + raw_spin_lock_irqsave_nested(&rp->lock, flags, 1); if (!hlist_empty(&rp->free_instances)) { ri = hlist_entry(rp->free_instances.first, struct kretprobe_instance, hlist); @@ -2039,7 +2056,7 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs) ri->task = current; if (rp->entry_handler && rp->entry_handler(ri, regs)) { - raw_spin_lock_irqsave(&rp->lock, flags); + raw_spin_lock_irqsave_nested(&rp->lock, flags, 1); hlist_add_head(&ri->hlist, &rp->free_instances); raw_spin_unlock_irqrestore(&rp->lock, flags); return 0; diff --git a/kernel/kthread.c b/kernel/kthread.c index e29773c82b70..933a625621b8 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -897,7 +897,8 @@ void kthread_delayed_work_timer_fn(struct timer_list *t) /* Move the work from worker->delayed_work_list. */ WARN_ON_ONCE(list_empty(&work->node)); list_del_init(&work->node); - kthread_insert_work(worker, work, &worker->work_list); + if (!work->canceling) + kthread_insert_work(worker, work, &worker->work_list); raw_spin_unlock_irqrestore(&worker->lock, flags); } diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 3e99dfef8408..b71ad8d9f1c9 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -84,7 +84,7 @@ static inline bool lockdep_enabled(void) if (!debug_locks) return false; - if (raw_cpu_read(lockdep_recursion)) + if (this_cpu_read(lockdep_recursion)) return false; if (current->lockdep_recursion) @@ -4057,7 +4057,7 @@ void lockdep_hardirqs_on_prepare(unsigned long ip) if (unlikely(in_nmi())) return; - if (unlikely(__this_cpu_read(lockdep_recursion))) + if (unlikely(this_cpu_read(lockdep_recursion))) return; if (unlikely(lockdep_hardirqs_enabled())) { @@ -4126,7 +4126,7 @@ void noinstr lockdep_hardirqs_on(unsigned long ip) goto skip_checks; } - if (unlikely(__this_cpu_read(lockdep_recursion))) + if (unlikely(this_cpu_read(lockdep_recursion))) return; if (lockdep_hardirqs_enabled()) { @@ -4396,6 +4396,9 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, if (unlikely(hlock_class(this)->usage_mask & new_mask)) goto unlock; + if (!hlock_class(this)->usage_mask) + debug_atomic_dec(nr_unused_locks); + hlock_class(this)->usage_mask |= new_mask; if (new_bit < LOCK_TRACE_STATES) { @@ -4403,19 +4406,10 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, return 0; } - switch (new_bit) { - case 0 ... LOCK_USED-1: + if (new_bit < LOCK_USED) { ret = mark_lock_irq(curr, this, new_bit); if (!ret) return 0; - break; - - case LOCK_USED: - debug_atomic_dec(nr_unused_locks); - break; - - default: - break; } unlock: diff --git a/kernel/params.c b/kernel/params.c index 3835fb82c64b..164d79330849 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -530,7 +530,7 @@ struct module_param_attrs { unsigned int num; struct attribute_group grp; - struct param_attribute attrs[0]; + struct param_attribute attrs[]; }; #ifdef CONFIG_SYSFS diff --git a/kernel/power/process.c b/kernel/power/process.c index 4b6a54da7e65..45b054b7b5ec 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -146,7 +146,7 @@ int freeze_processes(void) BUG_ON(in_atomic()); /* - * Now that the whole userspace is frozen we need to disbale + * Now that the whole userspace is frozen we need to disable * the OOM killer to disallow any further interference with * killable tasks. There is no guarantee oom victims will * ever reach a point they go away we have to wait with a timeout. diff --git a/kernel/printk/printk_ringbuffer.c b/kernel/printk/printk_ringbuffer.c index 24a960a89aa8..6b1525685277 100644 --- a/kernel/printk/printk_ringbuffer.c +++ b/kernel/printk/printk_ringbuffer.c @@ -345,7 +345,7 @@ DESC_ID((id) - DESCS_COUNT(desc_ring)) */ struct prb_data_block { unsigned long id; - char data[0]; + char data[]; }; /* diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 06895ef85d69..2a52f42f64b6 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -409,7 +409,7 @@ bool rcu_eqs_special_set(int cpu) * * The caller must have disabled interrupts and must not be idle. */ -void rcu_momentary_dyntick_idle(void) +notrace void rcu_momentary_dyntick_idle(void) { int special; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 8160ab5263f8..d2003a7d5ab5 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -44,7 +44,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp); DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); -#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_JUMP_LABEL) +#ifdef CONFIG_SCHED_DEBUG /* * Debugging: various feature bits * diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 5ae7b4e6e8d6..97d318b0cd0c 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -102,8 +102,12 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time) static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time, unsigned int next_freq) { - if (sg_policy->next_freq == next_freq) - return false; + if (!sg_policy->need_freq_update) { + if (sg_policy->next_freq == next_freq) + return false; + } else { + sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS); + } sg_policy->next_freq = next_freq; sg_policy->last_freq_update_time = time; @@ -164,7 +168,6 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update) return sg_policy->next_freq; - sg_policy->need_freq_update = false; sg_policy->cached_raw_freq = freq; return cpufreq_driver_resolve_freq(policy, freq); } @@ -440,7 +443,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, struct sugov_policy *sg_policy = sg_cpu->sg_policy; unsigned long util, max; unsigned int next_f; - bool busy; + unsigned int cached_freq = sg_policy->cached_raw_freq; sugov_iowait_boost(sg_cpu, time, flags); sg_cpu->last_update = time; @@ -450,9 +453,6 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, if (!sugov_should_update_freq(sg_policy, time)) return; - /* Limits may have changed, don't skip frequency update */ - busy = !sg_policy->need_freq_update && sugov_cpu_is_busy(sg_cpu); - util = sugov_get_util(sg_cpu); max = sg_cpu->max; util = sugov_iowait_apply(sg_cpu, time, util, max); @@ -461,11 +461,11 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, * Do not reduce the frequency if the CPU has not been idle * recently, as the reduction is likely to be premature then. */ - if (busy && next_f < sg_policy->next_freq) { + if (sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) { next_f = sg_policy->next_freq; - /* Reset cached freq as next_freq has changed */ - sg_policy->cached_raw_freq = 0; + /* Restore cached freq as next_freq has changed */ + sg_policy->cached_raw_freq = cached_freq; } /* @@ -826,9 +826,10 @@ static int sugov_start(struct cpufreq_policy *policy) sg_policy->next_freq = 0; sg_policy->work_in_progress = false; sg_policy->limits_changed = false; - sg_policy->need_freq_update = false; sg_policy->cached_raw_freq = 0; + sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS); + for_each_cpu(cpu, policy->cpus) { struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu); @@ -880,7 +881,7 @@ static void sugov_limits(struct cpufreq_policy *policy) struct cpufreq_governor schedutil_gov = { .name = "schedutil", .owner = THIS_MODULE, - .dynamic_switching = true, + .flags = CPUFREQ_GOV_DYNAMIC_SWITCHING, .init = sugov_init, .exit = sugov_exit, .start = sugov_start, diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 6d93f4518734..f232305dcefe 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2504,7 +2504,7 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p, } const struct sched_class dl_sched_class - __attribute__((section("__dl_sched_class"))) = { + __section("__dl_sched_class") = { .enqueue_task = enqueue_task_dl, .dequeue_task = dequeue_task_dl, .yield_task = yield_task_dl, diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index e17012be4d14..290f9e38378c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -11159,7 +11159,7 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task * All the scheduling class methods: */ const struct sched_class fair_sched_class - __attribute__((section("__fair_sched_class"))) = { + __section("__fair_sched_class") = { .enqueue_task = enqueue_task_fair, .dequeue_task = dequeue_task_fair, .yield_task = yield_task_fair, diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index f324dc36fc43..24d0ee26377d 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -458,7 +458,7 @@ static void update_curr_idle(struct rq *rq) * Simple, special scheduling class for the per-CPU idle tasks: */ const struct sched_class idle_sched_class - __attribute__((section("__idle_sched_class"))) = { + __section("__idle_sched_class") = { /* no enqueue/yield_task for idle tasks */ /* dequeue is not valid, we print a debug message there: */ diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index f215eea6a966..49ec096a8aa1 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -2430,7 +2430,7 @@ static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task) } const struct sched_class rt_sched_class - __attribute__((section("__rt_sched_class"))) = { + __section("__rt_sched_class") = { .enqueue_task = enqueue_task_rt, .dequeue_task = dequeue_task_rt, .yield_task = yield_task_rt, diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 28709f6b0975..df80bfcea92e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1471,7 +1471,7 @@ struct sched_group_capacity { int id; #endif - unsigned long cpumask[0]; /* Balance mask */ + unsigned long cpumask[]; /* Balance mask */ }; struct sched_group { @@ -1629,7 +1629,7 @@ enum { #undef SCHED_FEAT -#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_JUMP_LABEL) +#ifdef CONFIG_SCHED_DEBUG /* * To support run-time toggling of sched features, all the translation units @@ -1637,6 +1637,7 @@ enum { */ extern const_debug unsigned int sysctl_sched_features; +#ifdef CONFIG_JUMP_LABEL #define SCHED_FEAT(name, enabled) \ static __always_inline bool static_branch_##name(struct static_key *key) \ { \ @@ -1649,7 +1650,13 @@ static __always_inline bool static_branch_##name(struct static_key *key) \ extern struct static_key sched_feat_keys[__SCHED_FEAT_NR]; #define sched_feat(x) (static_branch_##x(&sched_feat_keys[__SCHED_FEAT_##x])) -#else /* !(SCHED_DEBUG && CONFIG_JUMP_LABEL) */ +#else /* !CONFIG_JUMP_LABEL */ + +#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x)) + +#endif /* CONFIG_JUMP_LABEL */ + +#else /* !SCHED_DEBUG */ /* * Each translation unit has its own copy of sysctl_sched_features to allow @@ -1665,7 +1672,7 @@ static const_debug __maybe_unused unsigned int sysctl_sched_features = #define sched_feat(x) !!(sysctl_sched_features & (1UL << __SCHED_FEAT_##x)) -#endif /* SCHED_DEBUG && CONFIG_JUMP_LABEL */ +#endif /* SCHED_DEBUG */ extern struct static_key_false sched_numa_balancing; extern struct static_key_false sched_schedstats; diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index 394bc8126a1e..ceb5b6b12561 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -110,7 +110,7 @@ static void update_curr_stop(struct rq *rq) * Simple, special scheduling class for the per-CPU stop tasks: */ const struct sched_class stop_sched_class - __attribute__((section("__stop_sched_class"))) = { + __section("__stop_sched_class") = { .enqueue_task = enqueue_task_stop, .dequeue_task = dequeue_task_stop, diff --git a/kernel/signal.c b/kernel/signal.c index a38b3edc6851..ef8f2a28d37c 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -391,16 +391,17 @@ static bool task_participate_group_stop(struct task_struct *task) void task_join_group_stop(struct task_struct *task) { + unsigned long mask = current->jobctl & JOBCTL_STOP_SIGMASK; + struct signal_struct *sig = current->signal; + + if (sig->group_stop_count) { + sig->group_stop_count++; + mask |= JOBCTL_STOP_CONSUME; + } else if (!(sig->flags & SIGNAL_STOP_STOPPED)) + return; + /* Have the new thread join an on-going signal group stop */ - unsigned long jobctl = current->jobctl; - if (jobctl & JOBCTL_STOP_PENDING) { - struct signal_struct *sig = current->signal; - unsigned long signr = jobctl & JOBCTL_STOP_SIGMASK; - unsigned long gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME; - if (task_set_jobctl_pending(task, signr | gstop)) { - sig->group_stop_count++; - } - } + task_set_jobctl_pending(task, mask | JOBCTL_STOP_PENDING); } /* diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 865bb0228ab6..890b79cf0e7c 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -178,7 +178,7 @@ static void ack_state(struct multi_stop_data *msdata) set_state(msdata, msdata->state + 1); } -void __weak stop_machine_yield(const struct cpumask *cpumask) +notrace void __weak stop_machine_yield(const struct cpumask *cpumask) { cpu_relax(); } diff --git a/kernel/sys.c b/kernel/sys.c index 6401880dff74..a730c03ee607 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -373,7 +373,7 @@ long __sys_setregid(gid_t rgid, gid_t egid) if (rgid != (gid_t) -1) { if (gid_eq(old->gid, krgid) || gid_eq(old->egid, krgid) || - ns_capable(old->user_ns, CAP_SETGID)) + ns_capable_setid(old->user_ns, CAP_SETGID)) new->gid = krgid; else goto error; @@ -382,7 +382,7 @@ long __sys_setregid(gid_t rgid, gid_t egid) if (gid_eq(old->gid, kegid) || gid_eq(old->egid, kegid) || gid_eq(old->sgid, kegid) || - ns_capable(old->user_ns, CAP_SETGID)) + ns_capable_setid(old->user_ns, CAP_SETGID)) new->egid = kegid; else goto error; @@ -432,7 +432,7 @@ long __sys_setgid(gid_t gid) old = current_cred(); retval = -EPERM; - if (ns_capable(old->user_ns, CAP_SETGID)) + if (ns_capable_setid(old->user_ns, CAP_SETGID)) new->gid = new->egid = new->sgid = new->fsgid = kgid; else if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->sgid)) new->egid = new->fsgid = kgid; @@ -744,7 +744,7 @@ long __sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid) old = current_cred(); retval = -EPERM; - if (!ns_capable(old->user_ns, CAP_SETGID)) { + if (!ns_capable_setid(old->user_ns, CAP_SETGID)) { if (rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) && !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid)) goto error; @@ -871,7 +871,7 @@ long __sys_setfsgid(gid_t gid) if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->egid) || gid_eq(kgid, old->sgid) || gid_eq(kgid, old->fsgid) || - ns_capable(old->user_ns, CAP_SETGID)) { + ns_capable_setid(old->user_ns, CAP_SETGID)) { if (!gid_eq(kgid, old->fsgid)) { new->fsgid = kgid; if (security_task_fix_setgid(new,old,LSM_SETID_FS) == 0) @@ -2238,12 +2238,12 @@ out: } #ifdef CONFIG_CHECKPOINT_RESTORE -static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr) +static int prctl_get_tid_address(struct task_struct *me, int __user * __user *tid_addr) { return put_user(me->clear_child_tid, tid_addr); } #else -static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr) +static int prctl_get_tid_address(struct task_struct *me, int __user * __user *tid_addr) { return -EINVAL; } @@ -2427,7 +2427,7 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, error = prctl_set_mm(arg2, arg3, arg4, arg5); break; case PR_GET_TID_ADDRESS: - error = prctl_get_tid_address(me, (int __user **)arg2); + error = prctl_get_tid_address(me, (int __user * __user *)arg2); break; case PR_SET_CHILD_SUBREAPER: me->signal->is_child_subreaper = !!arg2; diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 3624b9b5835d..387b4bef7dd1 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -425,11 +425,6 @@ static inline void debug_hrtimer_deactivate(struct hrtimer *timer) debug_object_deactivate(timer, &hrtimer_debug_descr); } -static inline void debug_hrtimer_free(struct hrtimer *timer) -{ - debug_object_free(timer, &hrtimer_debug_descr); -} - static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode); diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c index ca4e6d57d68b..00629e658ca1 100644 --- a/kernel/time/itimer.c +++ b/kernel/time/itimer.c @@ -172,10 +172,6 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id, u64 oval, nval, ointerval, ninterval; struct cpu_itimer *it = &tsk->signal->it[clock_id]; - /* - * Use the to_ktime conversion because that clamps the maximum - * value to KTIME_MAX and avoid multiplication overflows. - */ nval = timespec64_to_ns(&value->it_value); ninterval = timespec64_to_ns(&value->it_interval); diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index 0642013dace4..b1b9b12899f5 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -68,13 +68,13 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) return (cyc * mult) >> shift; } -struct clock_read_data *sched_clock_read_begin(unsigned int *seq) +notrace struct clock_read_data *sched_clock_read_begin(unsigned int *seq) { *seq = raw_read_seqcount_latch(&cd.seq); return cd.read_data + (*seq & 1); } -int sched_clock_read_retry(unsigned int seq) +notrace int sched_clock_read_retry(unsigned int seq) { return read_seqcount_latch_retry(&cd.seq, seq); } diff --git a/kernel/time/timer.c b/kernel/time/timer.c index dda05f4b7a1f..c3ad64fb9d8b 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -732,11 +732,6 @@ static inline void debug_timer_deactivate(struct timer_list *timer) debug_object_deactivate(timer, &timer_debug_descr); } -static inline void debug_timer_free(struct timer_list *timer) -{ - debug_object_free(timer, &timer_debug_descr); -} - static inline void debug_timer_assert_init(struct timer_list *timer) { debug_object_assert_init(timer, &timer_debug_descr); @@ -1706,6 +1701,8 @@ void update_process_times(int user_tick) { struct task_struct *p = current; + PRANDOM_ADD_NOISE(jiffies, user_tick, p, 0); + /* Note: this timer irq context must be accounted for as well. */ account_process_tick(p, user_tick); run_local_timers(); @@ -1717,13 +1714,6 @@ void update_process_times(int user_tick) scheduler_tick(); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) run_posix_cpu_timers(); - - /* The current CPU might make use of net randoms without receiving IRQs - * to renew them often enough. Let's update the net_rand_state from a - * non-constant value that's not affine to the number of calls to make - * sure it's updated when there's some activity (we don't care in idle). - */ - this_cpu_add(net_rand_state.s1, rol32(jiffies, 24) + user_tick); } /** diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 15bf28b13e50..dc83b3fa9fe7 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -438,14 +438,16 @@ enum { }; /* * Used for which event context the event is in. - * NMI = 0 - * IRQ = 1 - * SOFTIRQ = 2 - * NORMAL = 3 + * TRANSITION = 0 + * NMI = 1 + * IRQ = 2 + * SOFTIRQ = 3 + * NORMAL = 4 * * See trace_recursive_lock() comment below for more details. */ enum { + RB_CTX_TRANSITION, RB_CTX_NMI, RB_CTX_IRQ, RB_CTX_SOFTIRQ, @@ -793,7 +795,7 @@ static void rb_wake_up_waiters(struct irq_work *work) * ring_buffer_wait - wait for input to the ring buffer * @buffer: buffer to wait on * @cpu: the cpu buffer to wait on - * @full: wait until a full page is available, if @cpu != RING_BUFFER_ALL_CPUS + * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS * * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon * as data is added to any of the @buffer's cpu buffers. Otherwise @@ -1952,18 +1954,18 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, { struct ring_buffer_per_cpu *cpu_buffer; unsigned long nr_pages; - int cpu, err = 0; + int cpu, err; /* * Always succeed at resizing a non-existent buffer: */ if (!buffer) - return size; + return 0; /* Make sure the requested buffer exists */ if (cpu_id != RING_BUFFER_ALL_CPUS && !cpumask_test_cpu(cpu_id, buffer->cpumask)) - return size; + return 0; nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); @@ -2119,7 +2121,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, } mutex_unlock(&buffer->mutex); - return size; + return 0; out_err: for_each_buffer_cpu(buffer, cpu) { @@ -3014,10 +3016,10 @@ rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) * a bit of overhead in something as critical as function tracing, * we use a bitmask trick. * - * bit 0 = NMI context - * bit 1 = IRQ context - * bit 2 = SoftIRQ context - * bit 3 = normal context. + * bit 1 = NMI context + * bit 2 = IRQ context + * bit 3 = SoftIRQ context + * bit 4 = normal context. * * This works because this is the order of contexts that can * preempt other contexts. A SoftIRQ never preempts an IRQ @@ -3040,6 +3042,30 @@ rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) * The least significant bit can be cleared this way, and it * just so happens that it is the same bit corresponding to * the current context. + * + * Now the TRANSITION bit breaks the above slightly. The TRANSITION bit + * is set when a recursion is detected at the current context, and if + * the TRANSITION bit is already set, it will fail the recursion. + * This is needed because there's a lag between the changing of + * interrupt context and updating the preempt count. In this case, + * a false positive will be found. To handle this, one extra recursion + * is allowed, and this is done by the TRANSITION bit. If the TRANSITION + * bit is already set, then it is considered a recursion and the function + * ends. Otherwise, the TRANSITION bit is set, and that bit is returned. + * + * On the trace_recursive_unlock(), the TRANSITION bit will be the first + * to be cleared. Even if it wasn't the context that set it. That is, + * if an interrupt comes in while NORMAL bit is set and the ring buffer + * is called before preempt_count() is updated, since the check will + * be on the NORMAL bit, the TRANSITION bit will then be set. If an + * NMI then comes in, it will set the NMI bit, but when the NMI code + * does the trace_recursive_unlock() it will clear the TRANSTION bit + * and leave the NMI bit set. But this is fine, because the interrupt + * code that set the TRANSITION bit will then clear the NMI bit when it + * calls trace_recursive_unlock(). If another NMI comes in, it will + * set the TRANSITION bit and continue. + * + * Note: The TRANSITION bit only handles a single transition between context. */ static __always_inline int @@ -3055,8 +3081,16 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) bit = pc & NMI_MASK ? RB_CTX_NMI : pc & HARDIRQ_MASK ? RB_CTX_IRQ : RB_CTX_SOFTIRQ; - if (unlikely(val & (1 << (bit + cpu_buffer->nest)))) - return 1; + if (unlikely(val & (1 << (bit + cpu_buffer->nest)))) { + /* + * It is possible that this was called by transitioning + * between interrupt context, and preempt_count() has not + * been updated yet. In this case, use the TRANSITION bit. + */ + bit = RB_CTX_TRANSITION; + if (val & (1 << (bit + cpu_buffer->nest))) + return 1; + } val |= (1 << (bit + cpu_buffer->nest)); cpu_buffer->current_context = val; @@ -3071,8 +3105,8 @@ trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->current_context - (1 << cpu_buffer->nest); } -/* The recursive locking above uses 4 bits */ -#define NESTED_BITS 4 +/* The recursive locking above uses 5 bits */ +#define NESTED_BITS 5 /** * ring_buffer_nest_start - Allow to trace while nested diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 528971714fc6..410cfeb16db5 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2750,7 +2750,7 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb, /* * If tracing is off, but we have triggers enabled * we still need to look at the event data. Use the temp_buffer - * to store the trace event for the tigger to use. It's recusive + * to store the trace event for the trigger to use. It's recursive * safe and will not be recorded anywhere. */ if (!entry && trace_file->flags & EVENT_FILE_FL_TRIGGER_COND) { @@ -2952,7 +2952,7 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer, stackidx = __this_cpu_inc_return(ftrace_stack_reserve) - 1; /* This should never happen. If it does, yell once and skip */ - if (WARN_ON_ONCE(stackidx > FTRACE_KSTACK_NESTING)) + if (WARN_ON_ONCE(stackidx >= FTRACE_KSTACK_NESTING)) goto out; /* @@ -3132,7 +3132,7 @@ static char *get_trace_buf(void) /* Interrupts must see nesting incremented before we use the buffer */ barrier(); - return &buffer->buffer[buffer->nesting][0]; + return &buffer->buffer[buffer->nesting - 1][0]; } static void put_trace_buf(void) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 34e0c4d5a6e7..1dadef445cd1 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -99,7 +99,7 @@ enum trace_type { /* Use this for memory failure errors */ #define MEM_FAIL(condition, fmt, ...) ({ \ - static bool __section(.data.once) __warned; \ + static bool __section(".data.once") __warned; \ int __ret_warn_once = !!(condition); \ \ if (unlikely(__ret_warn_once && !__warned)) { \ @@ -637,6 +637,12 @@ enum { * function is called to clear it. */ TRACE_GRAPH_NOTRACE_BIT, + + /* + * When transitioning between context, the preempt_count() may + * not be correct. Allow for a single recursion to cover this case. + */ + TRACE_TRANSITION_BIT, }; #define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0) @@ -691,14 +697,27 @@ static __always_inline int trace_test_and_set_recursion(int start, int max) return 0; bit = trace_get_context_bit() + start; - if (unlikely(val & (1 << bit))) - return -1; + if (unlikely(val & (1 << bit))) { + /* + * It could be that preempt_count has not been updated during + * a switch between contexts. Allow for a single recursion. + */ + bit = TRACE_TRANSITION_BIT; + if (trace_recursion_test(bit)) + return -1; + trace_recursion_set(bit); + barrier(); + return bit + 1; + } + + /* Normal check passed, clear the transition to allow it again */ + trace_recursion_clear(TRACE_TRANSITION_BIT); val |= 1 << bit; current->trace_recursion = val; barrier(); - return bit; + return bit + 1; } static __always_inline void trace_clear_recursion(int bit) @@ -708,6 +727,7 @@ static __always_inline void trace_clear_recursion(int bit) if (!bit) return; + bit--; bit = 1 << bit; val &= ~bit; diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 3212e2c653b3..881df991742a 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -584,7 +584,8 @@ static struct synth_field *parse_synth_field(int argc, const char **argv, { struct synth_field *field; const char *prefix = NULL, *field_type = argv[0], *field_name, *array; - int len, ret = 0; + int len, ret = -ENOMEM; + struct seq_buf s; ssize_t size; if (field_type[0] == ';') @@ -616,10 +617,9 @@ static struct synth_field *parse_synth_field(int argc, const char **argv, len--; field->name = kmemdup_nul(field_name, len, GFP_KERNEL); - if (!field->name) { - ret = -ENOMEM; + if (!field->name) goto free; - } + if (!is_good_name(field->name)) { synth_err(SYNTH_ERR_BAD_NAME, errpos(field_name)); ret = -EINVAL; @@ -630,29 +630,29 @@ static struct synth_field *parse_synth_field(int argc, const char **argv, field_type++; len = strlen(field_type) + 1; - if (array) { - int l = strlen(array); + if (array) + len += strlen(array); - if (l && array[l - 1] == ';') - l--; - len += l; - } if (prefix) len += strlen(prefix); field->type = kzalloc(len, GFP_KERNEL); - if (!field->type) { - ret = -ENOMEM; + if (!field->type) goto free; - } + + seq_buf_init(&s, field->type, len); if (prefix) - strcat(field->type, prefix); - strcat(field->type, field_type); + seq_buf_puts(&s, prefix); + seq_buf_puts(&s, field_type); if (array) { - strcat(field->type, array); - if (field->type[len - 1] == ';') - field->type[len - 1] = '\0'; + seq_buf_puts(&s, array); + if (s.buffer[s.len - 1] == ';') + s.len--; } + if (WARN_ON_ONCE(!seq_buf_buffer_left(&s))) + goto free; + + s.buffer[s.len] = '\0'; size = synth_field_size(field->type); if (size < 0) { @@ -663,14 +663,19 @@ static struct synth_field *parse_synth_field(int argc, const char **argv, if (synth_field_is_string(field->type)) { char *type; - type = kzalloc(sizeof("__data_loc ") + strlen(field->type) + 1, GFP_KERNEL); - if (!type) { - ret = -ENOMEM; + len = sizeof("__data_loc ") + strlen(field->type) + 1; + type = kzalloc(len, GFP_KERNEL); + if (!type) goto free; - } - strcat(type, "__data_loc "); - strcat(type, field->type); + seq_buf_init(&s, type, len); + seq_buf_puts(&s, "__data_loc "); + seq_buf_puts(&s, field->type); + + if (WARN_ON_ONCE(!seq_buf_buffer_left(&s))) + goto free; + s.buffer[s.len] = '\0'; + kfree(field->type); field->type = type; diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 70d3d0a09053..90f81d33fa3f 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -176,7 +176,7 @@ struct trace_event_call __used event_##call = { \ .flags = TRACE_EVENT_FL_IGNORE_ENABLE, \ }; \ static struct trace_event_call __used \ -__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call; +__section("_ftrace_events") *__event_##call = &event_##call; #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, etype, tstruct, print) \ diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index b5e3496cf803..4738ad48a667 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -492,8 +492,13 @@ trace_selftest_function_recursion(void) unregister_ftrace_function(&test_rec_probe); ret = -1; - if (trace_selftest_recursion_cnt != 1) { - pr_cont("*callback not called once (%d)* ", + /* + * Recursion allows for transitions between context, + * and may call the callback twice. + */ + if (trace_selftest_recursion_cnt != 1 && + trace_selftest_recursion_cnt != 2) { + pr_cont("*callback not called once (or twice) (%d)* ", trace_selftest_recursion_cnt); goto out; } diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 26efd22f0633..3f659f855074 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -50,7 +50,7 @@ static bool ok_to_free_tracepoints; */ struct tp_probes { struct rcu_head rcu; - struct tracepoint_func probes[0]; + struct tracepoint_func probes[]; }; static inline void *allocate_probes(int count) |