diff options
Diffstat (limited to 'kernel')
38 files changed, 1220 insertions, 807 deletions
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 546ebee39e2a..5fcc7a17eb5a 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -1073,11 +1073,18 @@ const struct btf_type *btf_type_id_size(const struct btf *btf, !btf_type_is_var(size_type))) return NULL; - size = btf->resolved_sizes[size_type_id]; size_type_id = btf->resolved_ids[size_type_id]; size_type = btf_type_by_id(btf, size_type_id); if (btf_type_nosize_or_null(size_type)) return NULL; + else if (btf_type_has_size(size_type)) + size = size_type->size; + else if (btf_type_is_array(size_type)) + size = btf->resolved_sizes[size_type_id]; + else if (btf_type_is_ptr(size_type)) + size = sizeof(void *); + else + return NULL; } *type_id = size_type_id; @@ -1602,7 +1609,6 @@ static int btf_modifier_resolve(struct btf_verifier_env *env, const struct btf_type *next_type; u32 next_type_id = t->type; struct btf *btf = env->btf; - u32 next_type_size = 0; next_type = btf_type_by_id(btf, next_type_id); if (!next_type || btf_type_is_resolve_source_only(next_type)) { @@ -1620,7 +1626,7 @@ static int btf_modifier_resolve(struct btf_verifier_env *env, * save us a few type-following when we use it later (e.g. in * pretty print). */ - if (!btf_type_id_size(btf, &next_type_id, &next_type_size)) { + if (!btf_type_id_size(btf, &next_type_id, NULL)) { if (env_type_is_resolved(env, next_type_id)) next_type = btf_type_id_resolve(btf, &next_type_id); @@ -1633,7 +1639,7 @@ static int btf_modifier_resolve(struct btf_verifier_env *env, } } - env_stack_pop_resolved(env, next_type_id, next_type_size); + env_stack_pop_resolved(env, next_type_id, 0); return 0; } @@ -1645,7 +1651,6 @@ static int btf_var_resolve(struct btf_verifier_env *env, const struct btf_type *t = v->t; u32 next_type_id = t->type; struct btf *btf = env->btf; - u32 next_type_size; next_type = btf_type_by_id(btf, next_type_id); if (!next_type || btf_type_is_resolve_source_only(next_type)) { @@ -1675,12 +1680,12 @@ static int btf_var_resolve(struct btf_verifier_env *env, * forward types or similar that would resolve to size of * zero is allowed. */ - if (!btf_type_id_size(btf, &next_type_id, &next_type_size)) { + if (!btf_type_id_size(btf, &next_type_id, NULL)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } - env_stack_pop_resolved(env, next_type_id, next_type_size); + env_stack_pop_resolved(env, next_type_id, 0); return 0; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a2e763703c30..5900cbb966b1 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1519,9 +1519,9 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, return -EFAULT; } *stack_mask |= 1ull << spi; - } else if (class == BPF_STX) { + } else if (class == BPF_STX || class == BPF_ST) { if (*reg_mask & dreg) - /* stx shouldn't be using _scalar_ dst_reg + /* stx & st shouldn't be using _scalar_ dst_reg * to access memory. It means backtracking * encountered a case of pointer subtraction. */ @@ -1540,7 +1540,8 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, if (!(*stack_mask & (1ull << spi))) return 0; *stack_mask &= ~(1ull << spi); - *reg_mask |= sreg; + if (class == BPF_STX) + *reg_mask |= sreg; } else if (class == BPF_JMP || class == BPF_JMP32) { if (opcode == BPF_CALL) { if (insn->src_reg == BPF_PSEUDO_CALL) @@ -1569,10 +1570,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, if (mode == BPF_IND || mode == BPF_ABS) /* to be analyzed */ return -ENOTSUPP; - } else if (class == BPF_ST) { - if (*reg_mask & dreg) - /* likely pointer subtraction */ - return -ENOTSUPP; } return 0; } @@ -6106,11 +6103,13 @@ static int check_return_code(struct bpf_verifier_env *env) if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG || env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG) range = tnum_range(1, 1); + break; case BPF_PROG_TYPE_CGROUP_SKB: if (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS) { range = tnum_range(0, 3); enforce_attach_type_range = tnum_range(2, 3); } + break; case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_CGROUP_DEVICE: diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 300b0c416341..753afbca549f 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2201,8 +2201,7 @@ static int cgroup_init_fs_context(struct fs_context *fc) fc->ops = &cgroup_fs_context_ops; else fc->ops = &cgroup1_fs_context_ops; - if (fc->user_ns) - put_user_ns(fc->user_ns); + put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(ctx->ns->user_ns); fc->global = true; return 0; @@ -2243,6 +2242,50 @@ static struct file_system_type cgroup2_fs_type = { .fs_flags = FS_USERNS_MOUNT, }; +#ifdef CONFIG_CPUSETS +static const struct fs_context_operations cpuset_fs_context_ops = { + .get_tree = cgroup1_get_tree, + .free = cgroup_fs_context_free, +}; + +/* + * This is ugly, but preserves the userspace API for existing cpuset + * users. If someone tries to mount the "cpuset" filesystem, we + * silently switch it to mount "cgroup" instead + */ +static int cpuset_init_fs_context(struct fs_context *fc) +{ + char *agent = kstrdup("/sbin/cpuset_release_agent", GFP_USER); + struct cgroup_fs_context *ctx; + int err; + + err = cgroup_init_fs_context(fc); + if (err) { + kfree(agent); + return err; + } + + fc->ops = &cpuset_fs_context_ops; + + ctx = cgroup_fc2context(fc); + ctx->subsys_mask = 1 << cpuset_cgrp_id; + ctx->flags |= CGRP_ROOT_NOPREFIX; + ctx->release_agent = agent; + + get_filesystem(&cgroup_fs_type); + put_filesystem(fc->fs_type); + fc->fs_type = &cgroup_fs_type; + + return 0; +} + +static struct file_system_type cpuset_fs_type = { + .name = "cpuset", + .init_fs_context = cpuset_init_fs_context, + .fs_flags = FS_USERNS_MOUNT, +}; +#endif + int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns) { @@ -5761,6 +5804,9 @@ int __init cgroup_init(void) WARN_ON(register_filesystem(&cgroup_fs_type)); WARN_ON(register_filesystem(&cgroup2_fs_type)); WARN_ON(!proc_create_single("cgroups", 0, NULL, proc_cgroupstats_show)); +#ifdef CONFIG_CPUSETS + WARN_ON(register_filesystem(&cpuset_fs_type)); +#endif return 0; } diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index b3b02b9c4405..5aa37531ce76 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -356,59 +356,6 @@ static inline bool is_in_v2_mode(void) } /* - * This is ugly, but preserves the userspace API for existing cpuset - * users. If someone tries to mount the "cpuset" filesystem, we - * silently switch it to mount "cgroup" instead - */ -static int cpuset_get_tree(struct fs_context *fc) -{ - struct file_system_type *cgroup_fs; - struct fs_context *new_fc; - int ret; - - cgroup_fs = get_fs_type("cgroup"); - if (!cgroup_fs) - return -ENODEV; - - new_fc = fs_context_for_mount(cgroup_fs, fc->sb_flags); - if (IS_ERR(new_fc)) { - ret = PTR_ERR(new_fc); - } else { - static const char agent_path[] = "/sbin/cpuset_release_agent"; - ret = vfs_parse_fs_string(new_fc, "cpuset", NULL, 0); - if (!ret) - ret = vfs_parse_fs_string(new_fc, "noprefix", NULL, 0); - if (!ret) - ret = vfs_parse_fs_string(new_fc, "release_agent", - agent_path, sizeof(agent_path) - 1); - if (!ret) - ret = vfs_get_tree(new_fc); - if (!ret) { /* steal the result */ - fc->root = new_fc->root; - new_fc->root = NULL; - } - put_fs_context(new_fc); - } - put_filesystem(cgroup_fs); - return ret; -} - -static const struct fs_context_operations cpuset_fs_context_ops = { - .get_tree = cpuset_get_tree, -}; - -static int cpuset_init_fs_context(struct fs_context *fc) -{ - fc->ops = &cpuset_fs_context_ops; - return 0; -} - -static struct file_system_type cpuset_fs_type = { - .name = "cpuset", - .init_fs_context = cpuset_init_fs_context, -}; - -/* * Return in pmask the portion of a cpusets's cpus_allowed that * are online. If none are online, walk up the cpuset hierarchy * until we find one that does have some online cpus. @@ -729,7 +676,7 @@ static inline int nr_cpusets(void) * load balancing domains (sched domains) as specified by that partial * partition. * - * See "What is sched_load_balance" in Documentation/cgroup-v1/cpusets.rst + * See "What is sched_load_balance" in Documentation/admin-guide/cgroup-v1/cpusets.rst * for a background explanation of this. * * Does not return errors, on the theory that the callers of this @@ -2853,13 +2800,11 @@ struct cgroup_subsys cpuset_cgrp_subsys = { /** * cpuset_init - initialize cpusets at system boot * - * Description: Initialize top_cpuset and the cpuset internal file system, + * Description: Initialize top_cpuset **/ int __init cpuset_init(void) { - int err = 0; - BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&top_cpuset.subparts_cpus, GFP_KERNEL)); @@ -2873,10 +2818,6 @@ int __init cpuset_init(void) set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags); top_cpuset.relax_domain_level = -1; - err = register_filesystem(&cpuset_fs_type); - if (err < 0) - return err; - BUG_ON(!alloc_cpumask_var(&cpus_attach, GFP_KERNEL)); return 0; diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 62fa5a82a065..9de232229063 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -129,15 +129,17 @@ setup_io_tlb_npages(char *str) } early_param("swiotlb", setup_io_tlb_npages); +static bool no_iotlb_memory; + unsigned long swiotlb_nr_tbl(void) { - return io_tlb_nslabs; + return unlikely(no_iotlb_memory) ? 0 : io_tlb_nslabs; } EXPORT_SYMBOL_GPL(swiotlb_nr_tbl); unsigned int swiotlb_max_segment(void) { - return max_segment; + return unlikely(no_iotlb_memory) ? 0 : max_segment; } EXPORT_SYMBOL_GPL(swiotlb_max_segment); @@ -160,8 +162,6 @@ unsigned long swiotlb_size_or_default(void) return size ? size : (IO_TLB_DEFAULT_SIZE); } -static bool no_iotlb_memory; - void swiotlb_print_info(void) { unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT; @@ -317,6 +317,14 @@ swiotlb_late_init_with_default_size(size_t default_size) return rc; } +static void swiotlb_cleanup(void) +{ + io_tlb_end = 0; + io_tlb_start = 0; + io_tlb_nslabs = 0; + max_segment = 0; +} + int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) { @@ -367,10 +375,7 @@ cleanup4: sizeof(int))); io_tlb_list = NULL; cleanup3: - io_tlb_end = 0; - io_tlb_start = 0; - io_tlb_nslabs = 0; - max_segment = 0; + swiotlb_cleanup(); return -ENOMEM; } @@ -394,10 +399,7 @@ void __init swiotlb_exit(void) memblock_free_late(io_tlb_start, PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); } - io_tlb_start = 0; - io_tlb_end = 0; - io_tlb_nslabs = 0; - max_segment = 0; + swiotlb_cleanup(); } /* @@ -546,7 +548,7 @@ not_found: if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n", size, io_tlb_nslabs, tmp_io_tlb_used); - return DMA_MAPPING_ERROR; + return (phys_addr_t)DMA_MAPPING_ERROR; found: io_tlb_used += nslots; spin_unlock_irqrestore(&io_tlb_lock, flags); @@ -664,7 +666,7 @@ bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr, /* Oh well, have to allocate and map a bounce buffer. */ *phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start), *phys, size, dir, attrs); - if (*phys == DMA_MAPPING_ERROR) + if (*phys == (phys_addr_t)DMA_MAPPING_ERROR) return false; /* Ensure that the address returned is DMA'ble */ diff --git a/kernel/events/core.c b/kernel/events/core.c index 785d708f8553..026a14541a38 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2553,6 +2553,9 @@ unlock: return ret; } +static bool exclusive_event_installable(struct perf_event *event, + struct perf_event_context *ctx); + /* * Attach a performance event to a context. * @@ -2567,6 +2570,8 @@ perf_install_in_context(struct perf_event_context *ctx, lockdep_assert_held(&ctx->mutex); + WARN_ON_ONCE(!exclusive_event_installable(event, ctx)); + if (event->cpu != -1) event->cpu = cpu; @@ -4360,7 +4365,7 @@ static int exclusive_event_init(struct perf_event *event) { struct pmu *pmu = event->pmu; - if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE)) + if (!is_exclusive_pmu(pmu)) return 0; /* @@ -4391,7 +4396,7 @@ static void exclusive_event_destroy(struct perf_event *event) { struct pmu *pmu = event->pmu; - if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE)) + if (!is_exclusive_pmu(pmu)) return; /* see comment in exclusive_event_init() */ @@ -4411,14 +4416,15 @@ static bool exclusive_event_match(struct perf_event *e1, struct perf_event *e2) return false; } -/* Called under the same ctx::mutex as perf_install_in_context() */ static bool exclusive_event_installable(struct perf_event *event, struct perf_event_context *ctx) { struct perf_event *iter_event; struct pmu *pmu = event->pmu; - if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE)) + lockdep_assert_held(&ctx->mutex); + + if (!is_exclusive_pmu(pmu)) return true; list_for_each_entry(iter_event, &ctx->event_list, event_entry) { @@ -4465,12 +4471,20 @@ static void _free_event(struct perf_event *event) if (event->destroy) event->destroy(event); - if (event->ctx) - put_ctx(event->ctx); - + /* + * Must be after ->destroy(), due to uprobe_perf_close() using + * hw.target. + */ if (event->hw.target) put_task_struct(event->hw.target); + /* + * perf_event_free_task() relies on put_ctx() being 'last', in particular + * all task references must be cleaned up. + */ + if (event->ctx) + put_ctx(event->ctx); + exclusive_event_destroy(event); module_put(event->pmu->module); @@ -4650,8 +4664,17 @@ again: mutex_unlock(&event->child_mutex); list_for_each_entry_safe(child, tmp, &free_list, child_list) { + void *var = &child->ctx->refcount; + list_del(&child->child_list); free_event(child); + + /* + * Wake any perf_event_free_task() waiting for this event to be + * freed. + */ + smp_mb(); /* pairs with wait_var_event() */ + wake_up_var(var); } no_ctx: @@ -10930,11 +10953,6 @@ SYSCALL_DEFINE5(perf_event_open, goto err_alloc; } - if ((pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) && group_leader) { - err = -EBUSY; - goto err_context; - } - /* * Look up the group leader (we will attach this event to it): */ @@ -11022,6 +11040,18 @@ SYSCALL_DEFINE5(perf_event_open, move_group = 0; } } + + /* + * Failure to create exclusive events returns -EBUSY. + */ + err = -EBUSY; + if (!exclusive_event_installable(group_leader, ctx)) + goto err_locked; + + for_each_sibling_event(sibling, group_leader) { + if (!exclusive_event_installable(sibling, ctx)) + goto err_locked; + } } else { mutex_lock(&ctx->mutex); } @@ -11058,9 +11088,6 @@ SYSCALL_DEFINE5(perf_event_open, * because we need to serialize with concurrent event creation. */ if (!exclusive_event_installable(event, ctx)) { - /* exclusive and group stuff are assumed mutually exclusive */ - WARN_ON_ONCE(move_group); - err = -EBUSY; goto err_locked; } @@ -11527,11 +11554,11 @@ static void perf_free_event(struct perf_event *event, } /* - * Free an unexposed, unused context as created by inheritance by - * perf_event_init_task below, used by fork() in case of fail. + * Free a context as created by inheritance by perf_event_init_task() below, + * used by fork() in case of fail. * - * Not all locks are strictly required, but take them anyway to be nice and - * help out with the lockdep assertions. + * Even though the task has never lived, the context and events have been + * exposed through the child_list, so we must take care tearing it all down. */ void perf_event_free_task(struct task_struct *task) { @@ -11561,7 +11588,23 @@ void perf_event_free_task(struct task_struct *task) perf_free_event(event, ctx); mutex_unlock(&ctx->mutex); - put_ctx(ctx); + + /* + * perf_event_release_kernel() could've stolen some of our + * child events and still have them on its free_list. In that + * case we must wait for these events to have been freed (in + * particular all their references to this task must've been + * dropped). + * + * Without this copy_process() will unconditionally free this + * task (irrespective of its reference count) and + * _free_event()'s put_task_struct(event->hw.target) will be a + * use-after-free. + * + * Wait for all events to drop their context reference. + */ + wait_var_event(&ctx->refcount, refcount_read(&ctx->refcount) == 1); + put_ctx(ctx); /* must be last */ } } @@ -11575,9 +11618,7 @@ void perf_event_delayed_put(struct task_struct *task) struct file *perf_event_get(unsigned int fd) { - struct file *file; - - file = fget_raw(fd); + struct file *file = fget(fd); if (!file) return ERR_PTR(-EBADF); diff --git a/kernel/fork.c b/kernel/fork.c index 8f3e2d97d771..d8ae0f1b4148 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -677,7 +677,6 @@ void __mmdrop(struct mm_struct *mm) WARN_ON_ONCE(mm == current->active_mm); mm_free_pgd(mm); destroy_context(mm); - hmm_mm_destroy(mm); mmu_notifier_mm_destroy(mm); check_mm(mm); put_user_ns(mm->user_ns); @@ -2406,6 +2405,16 @@ long _do_fork(struct kernel_clone_args *args) return nr; } +bool legacy_clone_args_valid(const struct kernel_clone_args *kargs) +{ + /* clone(CLONE_PIDFD) uses parent_tidptr to return a pidfd */ + if ((kargs->flags & CLONE_PIDFD) && + (kargs->flags & CLONE_PARENT_SETTID)) + return false; + + return true; +} + #ifndef CONFIG_HAVE_COPY_THREAD_TLS /* For compatibility with architectures that call do_fork directly rather than * using the syscall entry points below. */ @@ -2417,6 +2426,7 @@ long do_fork(unsigned long clone_flags, { struct kernel_clone_args args = { .flags = (clone_flags & ~CSIGNAL), + .pidfd = parent_tidptr, .child_tid = child_tidptr, .parent_tid = parent_tidptr, .exit_signal = (clone_flags & CSIGNAL), @@ -2424,6 +2434,9 @@ long do_fork(unsigned long clone_flags, .stack_size = stack_size, }; + if (!legacy_clone_args_valid(&args)) + return -EINVAL; + return _do_fork(&args); } #endif @@ -2505,8 +2518,7 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, .tls = tls, }; - /* clone(CLONE_PIDFD) uses parent_tidptr to return a pidfd */ - if ((clone_flags & CLONE_PIDFD) && (clone_flags & CLONE_PARENT_SETTID)) + if (!legacy_clone_args_valid(&args)) return -EINVAL; return _do_fork(&args); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 9f5433a52488..9873fc627d61 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2276,6 +2276,7 @@ static int __init init_kprobes(void) init_test_probes(); return err; } +subsys_initcall(init_kprobes); #ifdef CONFIG_DEBUG_FS static void report_probe(struct seq_file *pi, struct kprobe *p, @@ -2588,5 +2589,3 @@ static int __init debugfs_kprobe_init(void) late_initcall(debugfs_kprobe_init); #endif /* CONFIG_DEBUG_FS */ - -module_init(init_kprobes); diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index 9c49ec645d8b..65b6a1600c8f 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -210,6 +210,7 @@ static int lockdep_stats_show(struct seq_file *m, void *v) nr_hardirq_read_safe = 0, nr_hardirq_read_unsafe = 0, sum_forward_deps = 0; +#ifdef CONFIG_PROVE_LOCKING list_for_each_entry(class, &all_lock_classes, lock_entry) { if (class->usage_mask == 0) @@ -241,13 +242,13 @@ static int lockdep_stats_show(struct seq_file *m, void *v) if (class->usage_mask & LOCKF_ENABLED_HARDIRQ_READ) nr_hardirq_read_unsafe++; -#ifdef CONFIG_PROVE_LOCKING sum_forward_deps += lockdep_count_forward_deps(class); -#endif } #ifdef CONFIG_DEBUG_LOCKDEP DEBUG_LOCKS_WARN_ON(debug_atomic_read(nr_unused_locks) != nr_unused); #endif + +#endif seq_printf(m, " lock-classes: %11lu [max: %lu]\n", nr_lock_classes, MAX_LOCKDEP_KEYS); seq_printf(m, " direct dependencies: %11lu [max: %lu]\n", diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 0c601ae072b3..edd1c082dbf5 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -16,7 +16,7 @@ * by Steven Rostedt, based on work by Gregory Haskins, Peter Morreale * and Sven Dietrich. * - * Also see Documentation/locking/mutex-design.txt. + * Also see Documentation/locking/mutex-design.rst. */ #include <linux/mutex.h> #include <linux/ww_mutex.h> diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 38fbf9fa7f1b..fa83d36e30c6 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -9,7 +9,7 @@ * Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt * Copyright (C) 2006 Esben Nielsen * - * See Documentation/locking/rt-mutex-design.txt for details. + * See Documentation/locking/rt-mutex-design.rst for details. */ #include <linux/spinlock.h> #include <linux/export.h> diff --git a/kernel/memremap.c b/kernel/memremap.c index 6e1970719dc2..6ee03a816d67 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -11,41 +11,39 @@ #include <linux/types.h> #include <linux/wait_bit.h> #include <linux/xarray.h> -#include <linux/hmm.h> static DEFINE_XARRAY(pgmap_array); #define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1) #define SECTION_SIZE (1UL << PA_SECTION_SHIFT) -#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) -vm_fault_t device_private_entry_fault(struct vm_area_struct *vma, - unsigned long addr, - swp_entry_t entry, - unsigned int flags, - pmd_t *pmdp) +#ifdef CONFIG_DEV_PAGEMAP_OPS +DEFINE_STATIC_KEY_FALSE(devmap_managed_key); +EXPORT_SYMBOL(devmap_managed_key); +static atomic_t devmap_managed_enable; + +static void devmap_managed_enable_put(void *data) { - struct page *page = device_private_entry_to_page(entry); - struct hmm_devmem *devmem; + if (atomic_dec_and_test(&devmap_managed_enable)) + static_branch_disable(&devmap_managed_key); +} - devmem = container_of(page->pgmap, typeof(*devmem), pagemap); +static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap) +{ + if (!pgmap->ops || !pgmap->ops->page_free) { + WARN(1, "Missing page_free method\n"); + return -EINVAL; + } - /* - * The page_fault() callback must migrate page back to system memory - * so that CPU can access it. This might fail for various reasons - * (device issue, device was unsafely unplugged, ...). When such - * error conditions happen, the callback must return VM_FAULT_SIGBUS. - * - * Note that because memory cgroup charges are accounted to the device - * memory, this should never fail because of memory restrictions (but - * allocation of regular system page might still fail because we are - * out of memory). - * - * There is a more in-depth description of what that callback can and - * cannot do, in include/linux/memremap.h - */ - return devmem->page_fault(vma, addr, page, flags, pmdp); + if (atomic_inc_return(&devmap_managed_enable) == 1) + static_branch_enable(&devmap_managed_key); + return devm_add_action_or_reset(dev, devmap_managed_enable_put, NULL); } -#endif /* CONFIG_DEVICE_PRIVATE */ +#else +static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap) +{ + return -EINVAL; +} +#endif /* CONFIG_DEV_PAGEMAP_OPS */ static void pgmap_array_delete(struct resource *res) { @@ -56,14 +54,8 @@ static void pgmap_array_delete(struct resource *res) static unsigned long pfn_first(struct dev_pagemap *pgmap) { - const struct resource *res = &pgmap->res; - struct vmem_altmap *altmap = &pgmap->altmap; - unsigned long pfn; - - pfn = res->start >> PAGE_SHIFT; - if (pgmap->altmap_valid) - pfn += vmem_altmap_offset(altmap); - return pfn; + return PHYS_PFN(pgmap->res.start) + + vmem_altmap_offset(pgmap_altmap(pgmap)); } static unsigned long pfn_end(struct dev_pagemap *pgmap) @@ -83,59 +75,81 @@ static unsigned long pfn_next(unsigned long pfn) #define for_each_device_pfn(pfn, map) \ for (pfn = pfn_first(map); pfn < pfn_end(map); pfn = pfn_next(pfn)) +static void dev_pagemap_kill(struct dev_pagemap *pgmap) +{ + if (pgmap->ops && pgmap->ops->kill) + pgmap->ops->kill(pgmap); + else + percpu_ref_kill(pgmap->ref); +} + +static void dev_pagemap_cleanup(struct dev_pagemap *pgmap) +{ + if (pgmap->ops && pgmap->ops->cleanup) { + pgmap->ops->cleanup(pgmap); + } else { + wait_for_completion(&pgmap->done); + percpu_ref_exit(pgmap->ref); + } +} + static void devm_memremap_pages_release(void *data) { struct dev_pagemap *pgmap = data; struct device *dev = pgmap->dev; struct resource *res = &pgmap->res; - resource_size_t align_start, align_size; unsigned long pfn; int nid; - pgmap->kill(pgmap->ref); + dev_pagemap_kill(pgmap); for_each_device_pfn(pfn, pgmap) put_page(pfn_to_page(pfn)); - pgmap->cleanup(pgmap->ref); + dev_pagemap_cleanup(pgmap); /* pages are dead and unused, undo the arch mapping */ - align_start = res->start & ~(SECTION_SIZE - 1); - align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) - - align_start; - - nid = page_to_nid(pfn_to_page(align_start >> PAGE_SHIFT)); + nid = page_to_nid(pfn_to_page(PHYS_PFN(res->start))); mem_hotplug_begin(); if (pgmap->type == MEMORY_DEVICE_PRIVATE) { - pfn = align_start >> PAGE_SHIFT; + pfn = PHYS_PFN(res->start); __remove_pages(page_zone(pfn_to_page(pfn)), pfn, - align_size >> PAGE_SHIFT, NULL); + PHYS_PFN(resource_size(res)), NULL); } else { - arch_remove_memory(nid, align_start, align_size, - pgmap->altmap_valid ? &pgmap->altmap : NULL); - kasan_remove_zero_shadow(__va(align_start), align_size); + arch_remove_memory(nid, res->start, resource_size(res), + pgmap_altmap(pgmap)); + kasan_remove_zero_shadow(__va(res->start), resource_size(res)); } mem_hotplug_done(); - untrack_pfn(NULL, PHYS_PFN(align_start), align_size); + untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res)); pgmap_array_delete(res); dev_WARN_ONCE(dev, pgmap->altmap.alloc, "%s: failed to free all reserved pages\n", __func__); } +static void dev_pagemap_percpu_release(struct percpu_ref *ref) +{ + struct dev_pagemap *pgmap = + container_of(ref, struct dev_pagemap, internal_ref); + + complete(&pgmap->done); +} + /** * devm_memremap_pages - remap and provide memmap backing for the given resource * @dev: hosting device for @res * @pgmap: pointer to a struct dev_pagemap * * Notes: - * 1/ At a minimum the res, ref and type members of @pgmap must be initialized + * 1/ At a minimum the res and type members of @pgmap must be initialized * by the caller before passing it to this function * - * 2/ The altmap field may optionally be initialized, in which case altmap_valid - * must be set to true + * 2/ The altmap field may optionally be initialized, in which case + * PGMAP_ALTMAP_VALID must be set in pgmap->flags. * - * 3/ pgmap->ref must be 'live' on entry and will be killed and reaped - * at devm_memremap_pages_release() time, or if this routine fails. + * 3/ The ref field may optionally be provided, in which pgmap->ref must be + * 'live' on entry and will be killed and reaped at + * devm_memremap_pages_release() time, or if this routine fails. * * 4/ res is expected to be a host memory range that could feasibly be * treated as a "System RAM" range, i.e. not a device mmio range, but @@ -143,31 +157,69 @@ static void devm_memremap_pages_release(void *data) */ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) { - resource_size_t align_start, align_size, align_end; - struct vmem_altmap *altmap = pgmap->altmap_valid ? - &pgmap->altmap : NULL; struct resource *res = &pgmap->res; struct dev_pagemap *conflict_pgmap; struct mhp_restrictions restrictions = { /* * We do not want any optional features only our own memmap - */ - .altmap = altmap, + */ + .altmap = pgmap_altmap(pgmap), }; pgprot_t pgprot = PAGE_KERNEL; int error, nid, is_ram; + bool need_devmap_managed = true; + + switch (pgmap->type) { + case MEMORY_DEVICE_PRIVATE: + if (!IS_ENABLED(CONFIG_DEVICE_PRIVATE)) { + WARN(1, "Device private memory not supported\n"); + return ERR_PTR(-EINVAL); + } + if (!pgmap->ops || !pgmap->ops->migrate_to_ram) { + WARN(1, "Missing migrate_to_ram method\n"); + return ERR_PTR(-EINVAL); + } + break; + case MEMORY_DEVICE_FS_DAX: + if (!IS_ENABLED(CONFIG_ZONE_DEVICE) || + IS_ENABLED(CONFIG_FS_DAX_LIMITED)) { + WARN(1, "File system DAX not supported\n"); + return ERR_PTR(-EINVAL); + } + break; + case MEMORY_DEVICE_DEVDAX: + case MEMORY_DEVICE_PCI_P2PDMA: + need_devmap_managed = false; + break; + default: + WARN(1, "Invalid pgmap type %d\n", pgmap->type); + break; + } + + if (!pgmap->ref) { + if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup)) + return ERR_PTR(-EINVAL); - if (!pgmap->ref || !pgmap->kill || !pgmap->cleanup) { - WARN(1, "Missing reference count teardown definition\n"); - return ERR_PTR(-EINVAL); + init_completion(&pgmap->done); + error = percpu_ref_init(&pgmap->internal_ref, + dev_pagemap_percpu_release, 0, GFP_KERNEL); + if (error) + return ERR_PTR(error); + pgmap->ref = &pgmap->internal_ref; + } else { + if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) { + WARN(1, "Missing reference count teardown definition\n"); + return ERR_PTR(-EINVAL); + } } - align_start = res->start & ~(SECTION_SIZE - 1); - align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) - - align_start; - align_end = align_start + align_size - 1; + if (need_devmap_managed) { + error = devmap_managed_enable_get(dev, pgmap); + if (error) + return ERR_PTR(error); + } - conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_start), NULL); + conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->start), NULL); if (conflict_pgmap) { dev_WARN(dev, "Conflicting mapping in same section\n"); put_dev_pagemap(conflict_pgmap); @@ -175,7 +227,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) goto err_array; } - conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_end), NULL); + conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->end), NULL); if (conflict_pgmap) { dev_WARN(dev, "Conflicting mapping in same section\n"); put_dev_pagemap(conflict_pgmap); @@ -183,7 +235,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) goto err_array; } - is_ram = region_intersects(align_start, align_size, + is_ram = region_intersects(res->start, resource_size(res), IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); if (is_ram != REGION_DISJOINT) { @@ -204,8 +256,8 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) if (nid < 0) nid = numa_mem_id(); - error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(align_start), 0, - align_size); + error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(res->start), 0, + resource_size(res)); if (error) goto err_pfn_remap; @@ -223,16 +275,16 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) * arch_add_memory(). */ if (pgmap->type == MEMORY_DEVICE_PRIVATE) { - error = add_pages(nid, align_start >> PAGE_SHIFT, - align_size >> PAGE_SHIFT, &restrictions); + error = add_pages(nid, PHYS_PFN(res->start), + PHYS_PFN(resource_size(res)), &restrictions); } else { - error = kasan_add_zero_shadow(__va(align_start), align_size); + error = kasan_add_zero_shadow(__va(res->start), resource_size(res)); if (error) { mem_hotplug_done(); goto err_kasan; } - error = arch_add_memory(nid, align_start, align_size, + error = arch_add_memory(nid, res->start, resource_size(res), &restrictions); } @@ -240,8 +292,8 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) struct zone *zone; zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE]; - move_pfn_range_to_zone(zone, align_start >> PAGE_SHIFT, - align_size >> PAGE_SHIFT, altmap); + move_pfn_range_to_zone(zone, PHYS_PFN(res->start), + PHYS_PFN(resource_size(res)), restrictions.altmap); } mem_hotplug_done(); @@ -253,8 +305,8 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) * to allow us to do the work while not holding the hotplug lock. */ memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE], - align_start >> PAGE_SHIFT, - align_size >> PAGE_SHIFT, pgmap); + PHYS_PFN(res->start), + PHYS_PFN(resource_size(res)), pgmap); percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap)); error = devm_add_action_or_reset(dev, devm_memremap_pages_release, @@ -265,15 +317,14 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) return __va(res->start); err_add_memory: - kasan_remove_zero_shadow(__va(align_start), align_size); + kasan_remove_zero_shadow(__va(res->start), resource_size(res)); err_kasan: - untrack_pfn(NULL, PHYS_PFN(align_start), align_size); + untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res)); err_pfn_remap: pgmap_array_delete(res); err_array: - pgmap->kill(pgmap->ref); - pgmap->cleanup(pgmap->ref); - + dev_pagemap_kill(pgmap); + dev_pagemap_cleanup(pgmap); return ERR_PTR(error); } EXPORT_SYMBOL_GPL(devm_memremap_pages); @@ -287,7 +338,9 @@ EXPORT_SYMBOL_GPL(devm_memunmap_pages); unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) { /* number of pfns from base where pfn_to_page() is valid */ - return altmap->reserve + altmap->free; + if (altmap) + return altmap->reserve + altmap->free; + return 0; } void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) @@ -329,28 +382,6 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn, EXPORT_SYMBOL_GPL(get_dev_pagemap); #ifdef CONFIG_DEV_PAGEMAP_OPS -DEFINE_STATIC_KEY_FALSE(devmap_managed_key); -EXPORT_SYMBOL(devmap_managed_key); -static atomic_t devmap_enable; - -/* - * Toggle the static key for ->page_free() callbacks when dev_pagemap - * pages go idle. - */ -void dev_pagemap_get_ops(void) -{ - if (atomic_inc_return(&devmap_enable) == 1) - static_branch_enable(&devmap_managed_key); -} -EXPORT_SYMBOL_GPL(dev_pagemap_get_ops); - -void dev_pagemap_put_ops(void) -{ - if (atomic_dec_and_test(&devmap_enable)) - static_branch_disable(&devmap_managed_key); -} -EXPORT_SYMBOL_GPL(dev_pagemap_put_ops); - void __put_devmap_managed_page(struct page *page) { int count = page_ref_dec_return(page); @@ -366,7 +397,7 @@ void __put_devmap_managed_page(struct page *page) mem_cgroup_uncharge(page); - page->pgmap->page_free(page, page->pgmap->data); + page->pgmap->ops->page_free(page); } else if (!count) __put_page(page); } diff --git a/kernel/module.c b/kernel/module.c index a2cee14a83f3..5933395af9a0 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1492,8 +1492,7 @@ static void add_sect_attrs(struct module *mod, const struct load_info *info) for (i = 0; i < info->hdr->e_shnum; i++) if (!sect_empty(&info->sechdrs[i])) nloaded++; - size[0] = ALIGN(sizeof(*sect_attrs) - + nloaded * sizeof(sect_attrs->attrs[0]), + size[0] = ALIGN(struct_size(sect_attrs, attrs, nloaded), sizeof(sect_attrs->grp.attrs[0])); size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.attrs[0]); sect_attrs = kzalloc(size[0] + size[1], GFP_KERNEL); @@ -1697,6 +1696,8 @@ static int add_usage_links(struct module *mod) return ret; } +static void module_remove_modinfo_attrs(struct module *mod, int end); + static int module_add_modinfo_attrs(struct module *mod) { struct module_attribute *attr; @@ -1711,24 +1712,34 @@ static int module_add_modinfo_attrs(struct module *mod) return -ENOMEM; temp_attr = mod->modinfo_attrs; - for (i = 0; (attr = modinfo_attrs[i]) && !error; i++) { + for (i = 0; (attr = modinfo_attrs[i]); i++) { if (!attr->test || attr->test(mod)) { memcpy(temp_attr, attr, sizeof(*temp_attr)); sysfs_attr_init(&temp_attr->attr); error = sysfs_create_file(&mod->mkobj.kobj, &temp_attr->attr); + if (error) + goto error_out; ++temp_attr; } } + + return 0; + +error_out: + if (i > 0) + module_remove_modinfo_attrs(mod, --i); return error; } -static void module_remove_modinfo_attrs(struct module *mod) +static void module_remove_modinfo_attrs(struct module *mod, int end) { struct module_attribute *attr; int i; for (i = 0; (attr = &mod->modinfo_attrs[i]); i++) { + if (end >= 0 && i > end) + break; /* pick a field to test for end of list */ if (!attr->attr.name) break; @@ -1816,7 +1827,7 @@ static int mod_sysfs_setup(struct module *mod, return 0; out_unreg_modinfo_attrs: - module_remove_modinfo_attrs(mod); + module_remove_modinfo_attrs(mod, -1); out_unreg_param: module_param_sysfs_remove(mod); out_unreg_holders: @@ -1852,7 +1863,7 @@ static void mod_sysfs_fini(struct module *mod) { } -static void module_remove_modinfo_attrs(struct module *mod) +static void module_remove_modinfo_attrs(struct module *mod, int end) { } @@ -1868,14 +1879,14 @@ static void init_param_lock(struct module *mod) static void mod_sysfs_teardown(struct module *mod) { del_usage_links(mod); - module_remove_modinfo_attrs(mod); + module_remove_modinfo_attrs(mod, -1); module_param_sysfs_remove(mod); kobject_put(mod->mkobj.drivers_dir); kobject_put(mod->holders_dir); mod_sysfs_fini(mod); } -#ifdef CONFIG_STRICT_MODULE_RWX +#ifdef CONFIG_ARCH_HAS_STRICT_MODULE_RWX /* * LKM RO/NX protection: protect module's text/ro-data * from modification and any data from execution. @@ -1898,6 +1909,7 @@ static void frob_text(const struct module_layout *layout, layout->text_size >> PAGE_SHIFT); } +#ifdef CONFIG_STRICT_MODULE_RWX static void frob_rodata(const struct module_layout *layout, int (*set_memory)(unsigned long start, int num_pages)) { @@ -1949,13 +1961,9 @@ void module_enable_ro(const struct module *mod, bool after_init) set_vm_flush_reset_perms(mod->core_layout.base); set_vm_flush_reset_perms(mod->init_layout.base); frob_text(&mod->core_layout, set_memory_ro); - frob_text(&mod->core_layout, set_memory_x); frob_rodata(&mod->core_layout, set_memory_ro); - frob_text(&mod->init_layout, set_memory_ro); - frob_text(&mod->init_layout, set_memory_x); - frob_rodata(&mod->init_layout, set_memory_ro); if (after_init) @@ -2014,9 +2022,19 @@ void set_all_modules_text_ro(void) } mutex_unlock(&module_mutex); } -#else +#else /* !CONFIG_STRICT_MODULE_RWX */ static void module_enable_nx(const struct module *mod) { } -#endif +#endif /* CONFIG_STRICT_MODULE_RWX */ +static void module_enable_x(const struct module *mod) +{ + frob_text(&mod->core_layout, set_memory_x); + frob_text(&mod->init_layout, set_memory_x); +} +#else /* !CONFIG_ARCH_HAS_STRICT_MODULE_RWX */ +static void module_enable_nx(const struct module *mod) { } +static void module_enable_x(const struct module *mod) { } +#endif /* CONFIG_ARCH_HAS_STRICT_MODULE_RWX */ + #ifdef CONFIG_LIVEPATCH /* @@ -2723,6 +2741,11 @@ void * __weak module_alloc(unsigned long size) return vmalloc_exec(size); } +bool __weak module_exit_section(const char *name) +{ + return strstarts(name, ".exit"); +} + #ifdef CONFIG_DEBUG_KMEMLEAK static void kmemleak_load_module(const struct module *mod, const struct load_info *info) @@ -2912,7 +2935,7 @@ static int rewrite_section_headers(struct load_info *info, int flags) #ifndef CONFIG_MODULE_UNLOAD /* Don't load .exit sections */ - if (strstarts(info->secstrings+shdr->sh_name, ".exit")) + if (module_exit_section(info->secstrings+shdr->sh_name)) shdr->sh_flags &= ~(unsigned long)SHF_ALLOC; #endif } @@ -3390,8 +3413,7 @@ static bool finished_loading(const char *name) sched_annotate_sleep(); mutex_lock(&module_mutex); mod = find_module_all(name, strlen(name), true); - ret = !mod || mod->state == MODULE_STATE_LIVE - || mod->state == MODULE_STATE_GOING; + ret = !mod || mod->state == MODULE_STATE_LIVE; mutex_unlock(&module_mutex); return ret; @@ -3581,8 +3603,7 @@ again: mutex_lock(&module_mutex); old = find_module_all(mod->name, strlen(mod->name), true); if (old != NULL) { - if (old->state == MODULE_STATE_COMING - || old->state == MODULE_STATE_UNFORMED) { + if (old->state != MODULE_STATE_LIVE) { /* Wait in case it fails to load. */ mutex_unlock(&module_mutex); err = wait_event_interruptible(module_wq, @@ -3621,6 +3642,7 @@ static int complete_formation(struct module *mod, struct load_info *info) module_enable_ro(mod, false); module_enable_nx(mod); + module_enable_x(mod); /* Mark state as coming so strong_try_module_get() ignores us, * but kallsyms etc. can see us. */ diff --git a/kernel/padata.c b/kernel/padata.c index 2d2fddbb7a4c..15a8ad63f4ff 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -267,7 +267,12 @@ static void padata_reorder(struct parallel_data *pd) * The next object that needs serialization might have arrived to * the reorder queues in the meantime, we will be called again * from the timer function if no one else cares for it. + * + * Ensure reorder_objects is read after pd->lock is dropped so we see + * an increment from another task in padata_do_serial. Pairs with + * smp_mb__after_atomic in padata_do_serial. */ + smp_mb(); if (atomic_read(&pd->reorder_objects) && !(pinst->flags & PADATA_RESET)) mod_timer(&pd->timer, jiffies + HZ); @@ -387,6 +392,13 @@ void padata_do_serial(struct padata_priv *padata) list_add_tail(&padata->list, &pqueue->reorder.list); spin_unlock(&pqueue->reorder.lock); + /* + * Ensure the atomic_inc of reorder_objects above is ordered correctly + * with the trylock of pd->lock in padata_reorder. Pairs with smp_mb + * in padata_reorder. + */ + smp_mb__after_atomic(); + put_cpu(); /* If we're running on the wrong CPU, call padata_reorder() via a diff --git a/kernel/panic.c b/kernel/panic.c index 4d9f55bf7d38..057540b6eee9 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -372,7 +372,7 @@ const struct taint_flag taint_flags[TAINT_FLAGS_COUNT] = { /** * print_tainted - return a string to represent the kernel taint state. * - * For individual taint flag meanings, see Documentation/sysctl/kernel.txt + * For individual taint flag meanings, see Documentation/admin-guide/sysctl/kernel.rst * * The string is overwritten by the next call to print_tainted(), * but is always NULL terminated. diff --git a/kernel/pid.c b/kernel/pid.c index 16263b526560..0a9f2e437217 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -37,14 +37,14 @@ #include <linux/init_task.h> #include <linux/syscalls.h> #include <linux/proc_ns.h> -#include <linux/proc_fs.h> +#include <linux/refcount.h> #include <linux/anon_inodes.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/idr.h> struct pid init_struct_pid = { - .count = ATOMIC_INIT(1), + .count = REFCOUNT_INIT(1), .tasks = { { .first = NULL }, { .first = NULL }, @@ -108,8 +108,7 @@ void put_pid(struct pid *pid) return; ns = pid->numbers[pid->level].ns; - if ((atomic_read(&pid->count) == 1) || - atomic_dec_and_test(&pid->count)) { + if (refcount_dec_and_test(&pid->count)) { kmem_cache_free(ns->pid_cachep, pid); put_pid_ns(ns); } @@ -212,7 +211,7 @@ struct pid *alloc_pid(struct pid_namespace *ns) } get_pid_ns(ns); - atomic_set(&pid->count, 1); + refcount_set(&pid->count, 1); for (type = 0; type < PIDTYPE_MAX; ++type) INIT_HLIST_HEAD(&pid->tasks[type]); diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 6d726cef241c..a6a79f85c81a 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -291,14 +291,13 @@ static int pid_ns_ctl_handler(struct ctl_table *table, int write, } extern int pid_max; -static int zero = 0; static struct ctl_table pid_ns_ctl_table[] = { { .procname = "ns_last_pid", .maxlen = sizeof(int), .mode = 0666, /* permissions are checked in the handler */ .proc_handler = pid_ns_ctl_handler, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, .extra2 = &pid_max, }, { } diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index ff8592ddedee..d3667b4075c1 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -66,7 +66,7 @@ config HIBERNATION need to run mkswap against the swap partition used for the suspend. It also works with swap files to a limited extent (for details see - <file:Documentation/power/swsusp-and-swap-files.txt>). + <file:Documentation/power/swsusp-and-swap-files.rst>). Right now you may boot without resuming and resume later but in the meantime you cannot use the swap partition(s)/file(s) involved in @@ -75,7 +75,7 @@ config HIBERNATION MOUNT any journaled filesystems mounted before the suspend or they will get corrupted in a nasty way. - For more information take a look at <file:Documentation/power/swsusp.txt>. + For more information take a look at <file:Documentation/power/swsusp.rst>. config ARCH_SAVE_PAGE_KEYS bool @@ -256,7 +256,7 @@ config APM_EMULATION notification of APM "events" (e.g. battery status change). In order to use APM, you will need supporting software. For location - and more information, read <file:Documentation/power/apm-acpi.txt> + and more information, read <file:Documentation/power/apm-acpi.rst> and the Battery Powered Linux mini-HOWTO, available from <http://www.tldp.org/docs.html#howto>. diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 83a531cea2f3..cb9ddcc08119 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -32,6 +32,8 @@ #include <linux/compat.h> #include <linux/sched/signal.h> +#include <asm/syscall.h> /* for syscall_get_* */ + /* * Access another process' address space via ptrace. * Source/target buffer must be kernel space, @@ -897,7 +899,100 @@ static int ptrace_regset(struct task_struct *task, int req, unsigned int type, * to ensure no machine forgets it. */ EXPORT_SYMBOL_GPL(task_user_regset_view); -#endif + +static unsigned long +ptrace_get_syscall_info_entry(struct task_struct *child, struct pt_regs *regs, + struct ptrace_syscall_info *info) +{ + unsigned long args[ARRAY_SIZE(info->entry.args)]; + int i; + + info->op = PTRACE_SYSCALL_INFO_ENTRY; + info->entry.nr = syscall_get_nr(child, regs); + syscall_get_arguments(child, regs, args); + for (i = 0; i < ARRAY_SIZE(args); i++) + info->entry.args[i] = args[i]; + + /* args is the last field in struct ptrace_syscall_info.entry */ + return offsetofend(struct ptrace_syscall_info, entry.args); +} + +static unsigned long +ptrace_get_syscall_info_seccomp(struct task_struct *child, struct pt_regs *regs, + struct ptrace_syscall_info *info) +{ + /* + * As struct ptrace_syscall_info.entry is currently a subset + * of struct ptrace_syscall_info.seccomp, it makes sense to + * initialize that subset using ptrace_get_syscall_info_entry(). + * This can be reconsidered in the future if these structures + * diverge significantly enough. + */ + ptrace_get_syscall_info_entry(child, regs, info); + info->op = PTRACE_SYSCALL_INFO_SECCOMP; + info->seccomp.ret_data = child->ptrace_message; + + /* ret_data is the last field in struct ptrace_syscall_info.seccomp */ + return offsetofend(struct ptrace_syscall_info, seccomp.ret_data); +} + +static unsigned long +ptrace_get_syscall_info_exit(struct task_struct *child, struct pt_regs *regs, + struct ptrace_syscall_info *info) +{ + info->op = PTRACE_SYSCALL_INFO_EXIT; + info->exit.rval = syscall_get_error(child, regs); + info->exit.is_error = !!info->exit.rval; + if (!info->exit.is_error) + info->exit.rval = syscall_get_return_value(child, regs); + + /* is_error is the last field in struct ptrace_syscall_info.exit */ + return offsetofend(struct ptrace_syscall_info, exit.is_error); +} + +static int +ptrace_get_syscall_info(struct task_struct *child, unsigned long user_size, + void __user *datavp) +{ + struct pt_regs *regs = task_pt_regs(child); + struct ptrace_syscall_info info = { + .op = PTRACE_SYSCALL_INFO_NONE, + .arch = syscall_get_arch(child), + .instruction_pointer = instruction_pointer(regs), + .stack_pointer = user_stack_pointer(regs), + }; + unsigned long actual_size = offsetof(struct ptrace_syscall_info, entry); + unsigned long write_size; + + /* + * This does not need lock_task_sighand() to access + * child->last_siginfo because ptrace_freeze_traced() + * called earlier by ptrace_check_attach() ensures that + * the tracee cannot go away and clear its last_siginfo. + */ + switch (child->last_siginfo ? child->last_siginfo->si_code : 0) { + case SIGTRAP | 0x80: + switch (child->ptrace_message) { + case PTRACE_EVENTMSG_SYSCALL_ENTRY: + actual_size = ptrace_get_syscall_info_entry(child, regs, + &info); + break; + case PTRACE_EVENTMSG_SYSCALL_EXIT: + actual_size = ptrace_get_syscall_info_exit(child, regs, + &info); + break; + } + break; + case SIGTRAP | (PTRACE_EVENT_SECCOMP << 8): + actual_size = ptrace_get_syscall_info_seccomp(child, regs, + &info); + break; + } + + write_size = min(actual_size, user_size); + return copy_to_user(datavp, &info, write_size) ? -EFAULT : actual_size; +} +#endif /* CONFIG_HAVE_ARCH_TRACEHOOK */ int ptrace_request(struct task_struct *child, long request, unsigned long addr, unsigned long data) @@ -1114,6 +1209,10 @@ int ptrace_request(struct task_struct *child, long request, ret = __put_user(kiov.iov_len, &uiov->iov_len); break; } + + case PTRACE_GET_SYSCALL_INFO: + ret = ptrace_get_syscall_info(child, addr, datavp); + break; #endif case PTRACE_SECCOMP_GET_FILTER: diff --git a/kernel/resource.c b/kernel/resource.c index 158f04ec1d4f..7ea4306503c5 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -326,7 +326,7 @@ EXPORT_SYMBOL(release_resource); * * If a resource is found, returns 0 and @*res is overwritten with the part * of the resource that's within [@start..@end]; if none is found, returns - * -1 or -EINVAL for other invalid parameters. + * -ENODEV. Returns -EINVAL for invalid parameters. * * This function walks the whole tree and not just first level children * unless @first_lvl is true. @@ -342,6 +342,7 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end, unsigned long flags, unsigned long desc, bool first_lvl, struct resource *res) { + bool siblings_only = true; struct resource *p; if (!res) @@ -352,29 +353,43 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end, read_lock(&resource_lock); - for (p = iomem_resource.child; p; p = next_resource(p, first_lvl)) { - if ((p->flags & flags) != flags) - continue; - if ((desc != IORES_DESC_NONE) && (desc != p->desc)) - continue; + for (p = iomem_resource.child; p; p = next_resource(p, siblings_only)) { + /* If we passed the resource we are looking for, stop */ if (p->start > end) { p = NULL; break; } - if ((p->end >= start) && (p->start <= end)) - break; + + /* Skip until we find a range that matches what we look for */ + if (p->end < start) + continue; + + /* + * Now that we found a range that matches what we look for, + * check the flags and the descriptor. If we were not asked to + * use only the first level, start looking at children as well. + */ + siblings_only = first_lvl; + + if ((p->flags & flags) != flags) + continue; + if ((desc != IORES_DESC_NONE) && (desc != p->desc)) + continue; + + /* Found a match, break */ + break; + } + + if (p) { + /* copy data */ + res->start = max(start, p->start); + res->end = min(end, p->end); + res->flags = p->flags; + res->desc = p->desc; } read_unlock(&resource_lock); - if (!p) - return -1; - - /* copy data */ - res->start = max(start, p->start); - res->end = min(end, p->end); - res->flags = p->flags; - res->desc = p->desc; - return 0; + return p ? 0 : -ENODEV; } static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end, @@ -1628,6 +1643,45 @@ void resource_list_free(struct list_head *head) } EXPORT_SYMBOL(resource_list_free); +#ifdef CONFIG_DEVICE_PRIVATE +/** + * devm_request_free_mem_region - find free region for device private memory + * + * @dev: device struct to bind the resource to + * @size: size in bytes of the device memory to add + * @base: resource tree to look in + * + * This function tries to find an empty range of physical address big enough to + * contain the new resource, so that it can later be hotplugged as ZONE_DEVICE + * memory, which in turn allocates struct pages. + */ +struct resource *devm_request_free_mem_region(struct device *dev, + struct resource *base, unsigned long size) +{ + resource_size_t end, addr; + struct resource *res; + + size = ALIGN(size, 1UL << PA_SECTION_SHIFT); + end = min_t(unsigned long, base->end, (1UL << MAX_PHYSMEM_BITS) - 1); + addr = end - size + 1UL; + + for (; addr > size && addr >= base->start; addr -= size) { + if (region_intersects(addr, size, 0, IORES_DESC_NONE) != + REGION_DISJOINT) + continue; + + res = devm_request_mem_region(dev, addr, size, dev_name(dev)); + if (!res) + return ERR_PTR(-ENOMEM); + res->desc = IORES_DESC_DEVICE_PRIVATE_MEMORY; + return res; + } + + return ERR_PTR(-ERANGE); +} +EXPORT_SYMBOL_GPL(devm_request_free_mem_region); +#endif /* CONFIG_DEVICE_PRIVATE */ + static int __init strict_iomem(char *str) { if (strstr(str, "relaxed")) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index fa43ce3962e7..2b037f195473 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2399,6 +2399,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) unsigned long flags; int cpu, success = 0; + preempt_disable(); if (p == current) { /* * We're waking current, this means 'p->on_rq' and 'task_cpu(p) @@ -2412,7 +2413,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * it disabling IRQs (this allows not taking ->pi_lock). */ if (!(p->state & state)) - return false; + goto out; success = 1; cpu = task_cpu(p); @@ -2526,6 +2527,7 @@ unlock: out: if (success) ttwu_stat(p, cpu, wake_flags); + preempt_enable(); return success; } diff --git a/kernel/signal.c b/kernel/signal.c index dabe100d2091..91b789dd6e72 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2951,80 +2951,49 @@ EXPORT_SYMBOL(sigprocmask); * * This is useful for syscalls such as ppoll, pselect, io_pgetevents and * epoll_pwait where a new sigmask is passed from userland for the syscalls. + * + * Note that it does set_restore_sigmask() in advance, so it must be always + * paired with restore_saved_sigmask_unless() before return from syscall. */ -int set_user_sigmask(const sigset_t __user *usigmask, sigset_t *set, - sigset_t *oldset, size_t sigsetsize) +int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize) { - if (!usigmask) - return 0; + sigset_t kmask; + if (!umask) + return 0; if (sigsetsize != sizeof(sigset_t)) return -EINVAL; - if (copy_from_user(set, usigmask, sizeof(sigset_t))) + if (copy_from_user(&kmask, umask, sizeof(sigset_t))) return -EFAULT; - *oldset = current->blocked; - set_current_blocked(set); + set_restore_sigmask(); + current->saved_sigmask = current->blocked; + set_current_blocked(&kmask); return 0; } -EXPORT_SYMBOL(set_user_sigmask); #ifdef CONFIG_COMPAT -int set_compat_user_sigmask(const compat_sigset_t __user *usigmask, - sigset_t *set, sigset_t *oldset, +int set_compat_user_sigmask(const compat_sigset_t __user *umask, size_t sigsetsize) { - if (!usigmask) - return 0; + sigset_t kmask; + if (!umask) + return 0; if (sigsetsize != sizeof(compat_sigset_t)) return -EINVAL; - if (get_compat_sigset(set, usigmask)) + if (get_compat_sigset(&kmask, umask)) return -EFAULT; - *oldset = current->blocked; - set_current_blocked(set); + set_restore_sigmask(); + current->saved_sigmask = current->blocked; + set_current_blocked(&kmask); return 0; } -EXPORT_SYMBOL(set_compat_user_sigmask); #endif -/* - * restore_user_sigmask: - * usigmask: sigmask passed in from userland. - * sigsaved: saved sigmask when the syscall started and changed the sigmask to - * usigmask. - * - * This is useful for syscalls such as ppoll, pselect, io_pgetevents and - * epoll_pwait where a new sigmask is passed in from userland for the syscalls. - */ -void restore_user_sigmask(const void __user *usigmask, sigset_t *sigsaved, - bool interrupted) -{ - - if (!usigmask) - return; - /* - * When signals are pending, do not restore them here. - * Restoring sigmask here can lead to delivering signals that the above - * syscalls are intended to block because of the sigmask passed in. - */ - if (interrupted) { - current->saved_sigmask = *sigsaved; - set_restore_sigmask(); - return; - } - - /* - * This is needed because the fast syscall return path does not restore - * saved_sigmask when signals are not pending. - */ - set_current_blocked(sigsaved); -} -EXPORT_SYMBOL(restore_user_sigmask); - /** * sys_rt_sigprocmask - change the list of currently blocked signals * @how: whether to add, remove, or set signals diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 1c1ad1e14f21..078950d9605b 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -125,9 +125,6 @@ static int sixty = 60; #endif static int __maybe_unused neg_one = -1; - -static int zero; -static int __maybe_unused one = 1; static int __maybe_unused two = 2; static int __maybe_unused four = 4; static unsigned long zero_ul; @@ -188,17 +185,17 @@ extern int no_unaligned_warning; * enum sysctl_writes_mode - supported sysctl write modes * * @SYSCTL_WRITES_LEGACY: each write syscall must fully contain the sysctl value - * to be written, and multiple writes on the same sysctl file descriptor - * will rewrite the sysctl value, regardless of file position. No warning - * is issued when the initial position is not 0. + * to be written, and multiple writes on the same sysctl file descriptor + * will rewrite the sysctl value, regardless of file position. No warning + * is issued when the initial position is not 0. * @SYSCTL_WRITES_WARN: same as above but warn when the initial file position is - * not 0. + * not 0. * @SYSCTL_WRITES_STRICT: writes to numeric sysctl entries must always be at - * file position 0 and the value must be fully contained in the buffer - * sent to the write syscall. If dealing with strings respect the file - * position, but restrict this to the max length of the buffer, anything - * passed the max lenght will be ignored. Multiple writes will append - * to the buffer. + * file position 0 and the value must be fully contained in the buffer + * sent to the write syscall. If dealing with strings respect the file + * position, but restrict this to the max length of the buffer, anything + * passed the max length will be ignored. Multiple writes will append + * to the buffer. * * These write modes control how current file position affects the behavior of * updating sysctl values through the proc interface on each write. @@ -385,8 +382,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = sysctl_schedstats, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #endif /* CONFIG_SCHEDSTATS */ #endif /* CONFIG_SMP */ @@ -418,7 +415,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = SYSCTL_ONE, }, { .procname = "numa_balancing", @@ -426,8 +423,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = sysctl_numa_balancing, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_SCHED_DEBUG */ @@ -475,8 +472,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #endif #ifdef CONFIG_CFS_BANDWIDTH @@ -486,7 +483,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = SYSCTL_ONE, }, #endif #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) @@ -496,8 +493,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = sched_energy_aware_handler, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #endif #ifdef CONFIG_PROVE_LOCKING @@ -562,7 +559,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &neg_one, - .extra2 = &one, + .extra2 = SYSCTL_ONE, }, #endif #ifdef CONFIG_LATENCYTOP @@ -696,8 +693,8 @@ static struct ctl_table kern_table[] = { .mode = 0644, /* only handle a transition from default "0" to "1" */ .proc_handler = proc_dointvec_minmax, - .extra1 = &one, - .extra2 = &one, + .extra1 = SYSCTL_ONE, + .extra2 = SYSCTL_ONE, }, #endif #ifdef CONFIG_MODULES @@ -715,8 +712,8 @@ static struct ctl_table kern_table[] = { .mode = 0644, /* only handle a transition from default "0" to "1" */ .proc_handler = proc_dointvec_minmax, - .extra1 = &one, - .extra2 = &one, + .extra1 = SYSCTL_ONE, + .extra2 = SYSCTL_ONE, }, #endif #ifdef CONFIG_UEVENT_HELPER @@ -875,7 +872,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, .extra2 = &ten_thousand, }, { @@ -891,8 +888,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax_sysadmin, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, { .procname = "kptr_restrict", @@ -900,7 +897,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax_sysadmin, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, .extra2 = &two, }, #endif @@ -925,8 +922,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_watchdog, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, { .procname = "watchdog_thresh", @@ -934,7 +931,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_watchdog_thresh, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, .extra2 = &sixty, }, { @@ -943,8 +940,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = NMI_WATCHDOG_SYSCTL_PERM, .proc_handler = proc_nmi_watchdog, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, { .procname = "watchdog_cpumask", @@ -960,8 +957,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_soft_watchdog, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, { .procname = "softlockup_panic", @@ -969,8 +966,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #ifdef CONFIG_SMP { @@ -979,8 +976,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #endif /* CONFIG_SMP */ #endif @@ -991,8 +988,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #ifdef CONFIG_SMP { @@ -1001,8 +998,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #endif /* CONFIG_SMP */ #endif @@ -1115,8 +1112,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, { .procname = "hung_task_check_count", @@ -1124,7 +1121,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, }, { .procname = "hung_task_timeout_secs", @@ -1201,7 +1198,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(sysctl_perf_event_sample_rate), .mode = 0644, .proc_handler = perf_proc_update_handler, - .extra1 = &one, + .extra1 = SYSCTL_ONE, }, { .procname = "perf_cpu_time_max_percent", @@ -1209,7 +1206,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(sysctl_perf_cpu_time_max_percent), .mode = 0644, .proc_handler = perf_cpu_time_max_percent_handler, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, .extra2 = &one_hundred, }, { @@ -1218,7 +1215,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(sysctl_perf_event_max_stack), .mode = 0644, .proc_handler = perf_event_max_stack_handler, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, .extra2 = &six_hundred_forty_kb, }, { @@ -1227,7 +1224,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(sysctl_perf_event_max_contexts_per_stack), .mode = 0644, .proc_handler = perf_event_max_stack_handler, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, .extra2 = &one_thousand, }, #endif @@ -1237,8 +1234,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) { @@ -1247,8 +1244,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = timer_migration_handler, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #endif #ifdef CONFIG_BPF_SYSCALL @@ -1259,8 +1256,8 @@ static struct ctl_table kern_table[] = { .mode = 0644, /* only handle a transition from default "0" to "1" */ .proc_handler = proc_dointvec_minmax, - .extra1 = &one, - .extra2 = &one, + .extra1 = SYSCTL_ONE, + .extra2 = SYSCTL_ONE, }, { .procname = "bpf_stats_enabled", @@ -1277,8 +1274,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(sysctl_panic_on_rcu_stall), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #endif #ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE @@ -1288,8 +1285,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0600, .proc_handler = stack_erasing_sysctl, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #endif { } @@ -1302,7 +1299,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(sysctl_overcommit_memory), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, .extra2 = &two, }, { @@ -1311,7 +1308,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(sysctl_panic_on_oom), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, .extra2 = &two, }, { @@ -1348,7 +1345,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, }, { .procname = "dirty_background_ratio", @@ -1356,7 +1353,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(dirty_background_ratio), .mode = 0644, .proc_handler = dirty_background_ratio_handler, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, .extra2 = &one_hundred, }, { @@ -1373,7 +1370,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(vm_dirty_ratio), .mode = 0644, .proc_handler = dirty_ratio_handler, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, .extra2 = &one_hundred, }, { @@ -1397,7 +1394,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(dirty_expire_interval), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, }, { .procname = "dirtytime_expire_seconds", @@ -1405,7 +1402,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(dirtytime_expire_interval), .mode = 0644, .proc_handler = dirtytime_interval_handler, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, }, { .procname = "swappiness", @@ -1413,7 +1410,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(vm_swappiness), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, .extra2 = &one_hundred, }, #ifdef CONFIG_HUGETLB_PAGE @@ -1438,8 +1435,8 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = sysctl_vm_numa_stat_handler, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #endif { @@ -1470,7 +1467,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = drop_caches_sysctl_handler, - .extra1 = &one, + .extra1 = SYSCTL_ONE, .extra2 = &four, }, #ifdef CONFIG_COMPACTION @@ -1496,8 +1493,8 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #endif /* CONFIG_COMPACTION */ @@ -1507,7 +1504,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(min_free_kbytes), .mode = 0644, .proc_handler = min_free_kbytes_sysctl_handler, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, }, { .procname = "watermark_boost_factor", @@ -1515,7 +1512,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(watermark_boost_factor), .mode = 0644, .proc_handler = watermark_boost_factor_sysctl_handler, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, }, { .procname = "watermark_scale_factor", @@ -1523,7 +1520,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(watermark_scale_factor), .mode = 0644, .proc_handler = watermark_scale_factor_sysctl_handler, - .extra1 = &one, + .extra1 = SYSCTL_ONE, .extra2 = &one_thousand, }, { @@ -1532,7 +1529,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(percpu_pagelist_fraction), .mode = 0644, .proc_handler = percpu_pagelist_fraction_sysctl_handler, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, }, #ifdef CONFIG_MMU { @@ -1541,7 +1538,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(sysctl_max_map_count), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, }, #else { @@ -1550,7 +1547,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(sysctl_nr_trim_pages), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, }, #endif { @@ -1566,7 +1563,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(block_dump), .mode = 0644, .proc_handler = proc_dointvec, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, }, { .procname = "vfs_cache_pressure", @@ -1574,7 +1571,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(sysctl_vfs_cache_pressure), .mode = 0644, .proc_handler = proc_dointvec, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, }, #ifdef HAVE_ARCH_PICK_MMAP_LAYOUT { @@ -1583,7 +1580,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(sysctl_legacy_va_layout), .mode = 0644, .proc_handler = proc_dointvec, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, }, #endif #ifdef CONFIG_NUMA @@ -1593,7 +1590,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(node_reclaim_mode), .mode = 0644, .proc_handler = proc_dointvec, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, }, { .procname = "min_unmapped_ratio", @@ -1601,7 +1598,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(sysctl_min_unmapped_ratio), .mode = 0644, .proc_handler = sysctl_min_unmapped_ratio_sysctl_handler, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, .extra2 = &one_hundred, }, { @@ -1610,7 +1607,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(sysctl_min_slab_ratio), .mode = 0644, .proc_handler = sysctl_min_slab_ratio_sysctl_handler, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, .extra2 = &one_hundred, }, #endif @@ -1661,7 +1658,7 @@ static struct ctl_table vm_table[] = { #endif .mode = 0644, .proc_handler = proc_dointvec, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, }, #endif #ifdef CONFIG_HIGHMEM @@ -1671,8 +1668,8 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(vm_highmem_is_dirtyable), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #endif #ifdef CONFIG_MEMORY_FAILURE @@ -1682,8 +1679,8 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(sysctl_memory_failure_early_kill), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, { .procname = "memory_failure_recovery", @@ -1691,8 +1688,8 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(sysctl_memory_failure_recovery), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #endif { @@ -1738,8 +1735,8 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(sysctl_unprivileged_userfaultfd), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #endif { } @@ -1875,8 +1872,8 @@ static struct ctl_table fs_table[] = { .maxlen = sizeof(int), .mode = 0600, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, { .procname = "protected_hardlinks", @@ -1884,8 +1881,8 @@ static struct ctl_table fs_table[] = { .maxlen = sizeof(int), .mode = 0600, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, { .procname = "protected_fifos", @@ -1893,7 +1890,7 @@ static struct ctl_table fs_table[] = { .maxlen = sizeof(int), .mode = 0600, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, .extra2 = &two, }, { @@ -1902,7 +1899,7 @@ static struct ctl_table fs_table[] = { .maxlen = sizeof(int), .mode = 0600, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, .extra2 = &two, }, { @@ -1911,7 +1908,7 @@ static struct ctl_table fs_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax_coredump, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, .extra2 = &two, }, #if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE) @@ -1948,7 +1945,7 @@ static struct ctl_table fs_table[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = SYSCTL_ONE, }, { } }; @@ -1970,8 +1967,8 @@ static struct ctl_table debug_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_kprobes_optimization_handler, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #endif { } @@ -3395,8 +3392,8 @@ int proc_do_static_key(struct ctl_table *table, int write, .data = &val, .maxlen = sizeof(val), .mode = table->mode, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }; if (write && !capable(CAP_SYS_ADMIN)) diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 564e5fdb025f..98da8998c25c 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -597,9 +597,19 @@ config FTRACE_STARTUP_TEST functioning properly. It will do tests on all the configured tracers of ftrace. +config EVENT_TRACE_STARTUP_TEST + bool "Run selftest on trace events" + depends on FTRACE_STARTUP_TEST + default y + help + This option performs a test on all trace events in the system. + It basically just enables each event and runs some code that + will trigger events (not necessarily the event it enables) + This may take some time run as there are a lot of events. + config EVENT_TRACE_TEST_SYSCALLS bool "Run selftest on syscall events" - depends on FTRACE_STARTUP_TEST + depends on EVENT_TRACE_STARTUP_TEST help This option will also enable testing every syscall event. It only enables the event and disables it and runs various loads diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 576c41644e77..eca34503f178 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1622,6 +1622,11 @@ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec) return keep_regs; } +static struct ftrace_ops * +ftrace_find_tramp_ops_any(struct dyn_ftrace *rec); +static struct ftrace_ops * +ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *ops); + static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, int filter_hash, bool inc) @@ -1750,15 +1755,17 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, } /* - * If the rec had TRAMP enabled, then it needs to - * be cleared. As TRAMP can only be enabled iff - * there is only a single ops attached to it. - * In otherwords, always disable it on decrementing. - * In the future, we may set it if rec count is - * decremented to one, and the ops that is left - * has a trampoline. + * The TRAMP needs to be set only if rec count + * is decremented to one, and the ops that is + * left has a trampoline. As TRAMP can only be + * enabled if there is only a single ops attached + * to it. */ - rec->flags &= ~FTRACE_FL_TRAMP; + if (ftrace_rec_count(rec) == 1 && + ftrace_find_tramp_ops_any(rec)) + rec->flags |= FTRACE_FL_TRAMP; + else + rec->flags &= ~FTRACE_FL_TRAMP; /* * flags will be cleared in ftrace_check_record() @@ -1768,7 +1775,7 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, count++; /* Must match FTRACE_UPDATE_CALLS in ftrace_modify_all_code() */ - update |= ftrace_test_record(rec, 1) != FTRACE_UPDATE_IGNORE; + update |= ftrace_test_record(rec, true) != FTRACE_UPDATE_IGNORE; /* Shortcut, if we handled all records, we are done. */ if (!all && count == hash->count) @@ -1951,11 +1958,6 @@ static void print_ip_ins(const char *fmt, const unsigned char *p) printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]); } -static struct ftrace_ops * -ftrace_find_tramp_ops_any(struct dyn_ftrace *rec); -static struct ftrace_ops * -ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *ops); - enum ftrace_bug_type ftrace_bug_type; const void *ftrace_expected; @@ -2047,7 +2049,7 @@ void ftrace_bug(int failed, struct dyn_ftrace *rec) } } -static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update) +static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) { unsigned long flag = 0UL; @@ -2146,28 +2148,28 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update) /** * ftrace_update_record, set a record that now is tracing or not * @rec: the record to update - * @enable: set to 1 if the record is tracing, zero to force disable + * @enable: set to true if the record is tracing, false to force disable * * The records that represent all functions that can be traced need * to be updated when tracing has been enabled. */ -int ftrace_update_record(struct dyn_ftrace *rec, int enable) +int ftrace_update_record(struct dyn_ftrace *rec, bool enable) { - return ftrace_check_record(rec, enable, 1); + return ftrace_check_record(rec, enable, true); } /** * ftrace_test_record, check if the record has been enabled or not * @rec: the record to test - * @enable: set to 1 to check if enabled, 0 if it is disabled + * @enable: set to true to check if enabled, false if it is disabled * * The arch code may need to test if a record is already set to * tracing to determine how to modify the function code that it * represents. */ -int ftrace_test_record(struct dyn_ftrace *rec, int enable) +int ftrace_test_record(struct dyn_ftrace *rec, bool enable) { - return ftrace_check_record(rec, enable, 0); + return ftrace_check_record(rec, enable, false); } static struct ftrace_ops * @@ -2356,7 +2358,7 @@ unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec) } static int -__ftrace_replace_code(struct dyn_ftrace *rec, int enable) +__ftrace_replace_code(struct dyn_ftrace *rec, bool enable) { unsigned long ftrace_old_addr; unsigned long ftrace_addr; @@ -2395,7 +2397,7 @@ void __weak ftrace_replace_code(int mod_flags) { struct dyn_ftrace *rec; struct ftrace_page *pg; - int enable = mod_flags & FTRACE_MODIFY_ENABLE_FL; + bool enable = mod_flags & FTRACE_MODIFY_ENABLE_FL; int schedulable = mod_flags & FTRACE_MODIFY_MAY_SLEEP_FL; int failed; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 05b0b3139ebc..66358d66c933 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -128,16 +128,7 @@ int ring_buffer_print_entry_header(struct trace_seq *s) #define RB_ALIGNMENT 4U #define RB_MAX_SMALL_DATA (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX) #define RB_EVNT_MIN_SIZE 8U /* two 32bit words */ - -#ifndef CONFIG_HAVE_64BIT_ALIGNED_ACCESS -# define RB_FORCE_8BYTE_ALIGNMENT 0 -# define RB_ARCH_ALIGNMENT RB_ALIGNMENT -#else -# define RB_FORCE_8BYTE_ALIGNMENT 1 -# define RB_ARCH_ALIGNMENT 8U -#endif - -#define RB_ALIGN_DATA __aligned(RB_ARCH_ALIGNMENT) +#define RB_ALIGN_DATA __aligned(RB_ALIGNMENT) /* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */ #define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX @@ -2373,7 +2364,7 @@ rb_update_event(struct ring_buffer_per_cpu *cpu_buffer, event->time_delta = delta; length -= RB_EVNT_HDR_SIZE; - if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT) { + if (length > RB_MAX_SMALL_DATA) { event->type_len = 0; event->array[0] = length; } else @@ -2388,11 +2379,11 @@ static unsigned rb_calculate_event_length(unsigned length) if (!length) length++; - if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT) + if (length > RB_MAX_SMALL_DATA) length += sizeof(event.array[0]); length += RB_EVNT_HDR_SIZE; - length = ALIGN(length, RB_ARCH_ALIGNMENT); + length = ALIGN(length, RB_ALIGNMENT); /* * In case the time delta is larger than the 27 bits for it diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c90c687cf950..525a97fbbc60 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -366,7 +366,7 @@ trace_ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct } /** - * trace_pid_filter_add_remove_task - Add or remove a task from a pid_list + * trace_filter_add_remove_task - Add or remove a task from a pid_list * @pid_list: The list to modify * @self: The current task for fork or NULL for exit * @task: The task to add or remove @@ -743,8 +743,7 @@ trace_event_setup(struct ring_buffer_event *event, { struct trace_entry *ent = ring_buffer_event_data(event); - tracing_generic_entry_update(ent, flags, pc); - ent->type = type; + tracing_generic_entry_update(ent, type, flags, pc); } static __always_inline struct ring_buffer_event * @@ -2312,13 +2311,14 @@ enum print_line_t trace_handle_return(struct trace_seq *s) EXPORT_SYMBOL_GPL(trace_handle_return); void -tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, - int pc) +tracing_generic_entry_update(struct trace_entry *entry, unsigned short type, + unsigned long flags, int pc) { struct task_struct *tsk = current; entry->preempt_count = pc & 0xff; entry->pid = (tsk) ? tsk->pid : 0; + entry->type = type; entry->flags = #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | @@ -4842,12 +4842,13 @@ static const char readme_msg[] = "\t args: <name>=fetcharg[:type]\n" "\t fetcharg: %<register>, @<address>, @<symbol>[+|-<offset>],\n" #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API - "\t $stack<index>, $stack, $retval, $comm, $arg<N>\n" + "\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n" #else - "\t $stack<index>, $stack, $retval, $comm\n" + "\t $stack<index>, $stack, $retval, $comm,\n" #endif + "\t +|-[u]<offset>(<fetcharg>)\n" "\t type: s8/16/32/64, u8/16/32/64, x8/16/32/64, string, symbol,\n" - "\t b<bit-width>@<bit-offset>/<container-size>,\n" + "\t b<bit-width>@<bit-offset>/<container-size>, ustring,\n" "\t <type>\\[<array-size>\\]\n" #ifdef CONFIG_HIST_TRIGGERS "\t field: <stype> <name>;\n" diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 4629a6104474..0892e38ed6fb 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -416,8 +416,7 @@ void perf_trace_buf_update(void *record, u16 type) unsigned long flags; local_save_flags(flags); - tracing_generic_entry_update(entry, flags, pc); - entry->type = type; + tracing_generic_entry_update(entry, type, flags, pc); } NOKPROBE_SYMBOL(perf_trace_buf_update); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 0ce3db67f556..c7506bc81b75 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -70,14 +70,6 @@ static int system_refcount_dec(struct event_subsystem *system) #define while_for_each_event_file() \ } -static struct list_head * -trace_get_fields(struct trace_event_call *event_call) -{ - if (!event_call->class->get_fields) - return &event_call->class->fields; - return event_call->class->get_fields(event_call); -} - static struct ftrace_event_field * __find_event_field(struct list_head *head, char *name) { @@ -3190,7 +3182,7 @@ void __init trace_event_init(void) event_trace_enable(); } -#ifdef CONFIG_FTRACE_STARTUP_TEST +#ifdef CONFIG_EVENT_TRACE_STARTUP_TEST static DEFINE_SPINLOCK(test_spinlock); static DEFINE_SPINLOCK(test_spinlock_irq); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 5079d1db3754..c773b8fb270c 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1084,6 +1084,9 @@ int filter_assign_type(const char *type) if (strchr(type, '[') && strstr(type, "char")) return FILTER_STATIC_STRING; + if (strcmp(type, "char *") == 0 || strcmp(type, "const char *") == 0) + return FILTER_PTR_STRING; + return FILTER_OTHER; } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 7d736248a070..9d483ad9bb6c 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -12,6 +12,8 @@ #include <linux/rculist.h> #include <linux/error-injection.h> +#include <asm/setup.h> /* for COMMAND_LINE_SIZE */ + #include "trace_dynevent.h" #include "trace_kprobe_selftest.h" #include "trace_probe.h" @@ -19,6 +21,18 @@ #define KPROBE_EVENT_SYSTEM "kprobes" #define KRETPROBE_MAXACTIVE_MAX 4096 +#define MAX_KPROBE_CMDLINE_SIZE 1024 + +/* Kprobe early definition from command line */ +static char kprobe_boot_events_buf[COMMAND_LINE_SIZE] __initdata; +static bool kprobe_boot_events_enabled __initdata; + +static int __init set_kprobe_boot_events(char *str) +{ + strlcpy(kprobe_boot_events_buf, str, COMMAND_LINE_SIZE); + return 0; +} +__setup("kprobe_event=", set_kprobe_boot_events); static int trace_kprobe_create(int argc, const char **argv); static int trace_kprobe_show(struct seq_file *m, struct dyn_event *ev); @@ -128,8 +142,8 @@ static bool trace_kprobe_match(const char *system, const char *event, { struct trace_kprobe *tk = to_trace_kprobe(ev); - return strcmp(trace_event_name(&tk->tp.call), event) == 0 && - (!system || strcmp(tk->tp.call.class->system, system) == 0); + return strcmp(trace_probe_name(&tk->tp), event) == 0 && + (!system || strcmp(trace_probe_group_name(&tk->tp), system) == 0); } static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk) @@ -143,6 +157,12 @@ static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk) return nhit; } +static nokprobe_inline bool trace_kprobe_is_registered(struct trace_kprobe *tk) +{ + return !(list_empty(&tk->rp.kp.list) && + hlist_unhashed(&tk->rp.kp.hlist)); +} + /* Return 0 if it fails to find the symbol address */ static nokprobe_inline unsigned long trace_kprobe_address(struct trace_kprobe *tk) @@ -183,6 +203,16 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs); static int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs); +static void free_trace_kprobe(struct trace_kprobe *tk) +{ + if (tk) { + trace_probe_cleanup(&tk->tp); + kfree(tk->symbol); + free_percpu(tk->nhit); + kfree(tk); + } +} + /* * Allocate new trace_probe and initialize it (including kprobes). */ @@ -220,49 +250,20 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, tk->rp.kp.pre_handler = kprobe_dispatcher; tk->rp.maxactive = maxactive; + INIT_HLIST_NODE(&tk->rp.kp.hlist); + INIT_LIST_HEAD(&tk->rp.kp.list); - if (!event || !group) { - ret = -EINVAL; - goto error; - } - - tk->tp.call.class = &tk->tp.class; - tk->tp.call.name = kstrdup(event, GFP_KERNEL); - if (!tk->tp.call.name) - goto error; - - tk->tp.class.system = kstrdup(group, GFP_KERNEL); - if (!tk->tp.class.system) + ret = trace_probe_init(&tk->tp, event, group); + if (ret < 0) goto error; dyn_event_init(&tk->devent, &trace_kprobe_ops); - INIT_LIST_HEAD(&tk->tp.files); return tk; error: - kfree(tk->tp.call.name); - kfree(tk->symbol); - free_percpu(tk->nhit); - kfree(tk); + free_trace_kprobe(tk); return ERR_PTR(ret); } -static void free_trace_kprobe(struct trace_kprobe *tk) -{ - int i; - - if (!tk) - return; - - for (i = 0; i < tk->tp.nr_args; i++) - traceprobe_free_probe_arg(&tk->tp.args[i]); - - kfree(tk->tp.call.class->system); - kfree(tk->tp.call.name); - kfree(tk->symbol); - free_percpu(tk->nhit); - kfree(tk); -} - static struct trace_kprobe *find_trace_kprobe(const char *event, const char *group) { @@ -270,8 +271,8 @@ static struct trace_kprobe *find_trace_kprobe(const char *event, struct trace_kprobe *tk; for_each_trace_kprobe(tk, pos) - if (strcmp(trace_event_name(&tk->tp.call), event) == 0 && - strcmp(tk->tp.call.class->system, group) == 0) + if (strcmp(trace_probe_name(&tk->tp), event) == 0 && + strcmp(trace_probe_group_name(&tk->tp), group) == 0) return tk; return NULL; } @@ -280,7 +281,7 @@ static inline int __enable_trace_kprobe(struct trace_kprobe *tk) { int ret = 0; - if (trace_probe_is_registered(&tk->tp) && !trace_kprobe_has_gone(tk)) { + if (trace_kprobe_is_registered(tk) && !trace_kprobe_has_gone(tk)) { if (trace_kprobe_is_return(tk)) ret = enable_kretprobe(&tk->rp); else @@ -297,34 +298,27 @@ static inline int __enable_trace_kprobe(struct trace_kprobe *tk) static int enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) { - struct event_file_link *link; + bool enabled = trace_probe_is_enabled(&tk->tp); int ret = 0; if (file) { - link = kmalloc(sizeof(*link), GFP_KERNEL); - if (!link) { - ret = -ENOMEM; - goto out; - } - - link->file = file; - list_add_tail_rcu(&link->list, &tk->tp.files); + ret = trace_probe_add_file(&tk->tp, file); + if (ret) + return ret; + } else + trace_probe_set_flag(&tk->tp, TP_FLAG_PROFILE); - tk->tp.flags |= TP_FLAG_TRACE; - ret = __enable_trace_kprobe(tk); - if (ret) { - list_del_rcu(&link->list); - kfree(link); - tk->tp.flags &= ~TP_FLAG_TRACE; - } + if (enabled) + return 0; - } else { - tk->tp.flags |= TP_FLAG_PROFILE; - ret = __enable_trace_kprobe(tk); - if (ret) - tk->tp.flags &= ~TP_FLAG_PROFILE; + ret = __enable_trace_kprobe(tk); + if (ret) { + if (file) + trace_probe_remove_file(&tk->tp, file); + else + trace_probe_clear_flag(&tk->tp, TP_FLAG_PROFILE); } - out: + return ret; } @@ -335,54 +329,34 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) static int disable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) { - struct event_file_link *link = NULL; - int wait = 0; + struct trace_probe *tp = &tk->tp; int ret = 0; if (file) { - link = find_event_file_link(&tk->tp, file); - if (!link) { - ret = -EINVAL; - goto out; - } - - list_del_rcu(&link->list); - wait = 1; - if (!list_empty(&tk->tp.files)) + if (!trace_probe_get_file_link(tp, file)) + return -ENOENT; + if (!trace_probe_has_single_file(tp)) goto out; - - tk->tp.flags &= ~TP_FLAG_TRACE; + trace_probe_clear_flag(tp, TP_FLAG_TRACE); } else - tk->tp.flags &= ~TP_FLAG_PROFILE; + trace_probe_clear_flag(tp, TP_FLAG_PROFILE); - if (!trace_probe_is_enabled(&tk->tp) && trace_probe_is_registered(&tk->tp)) { + if (!trace_probe_is_enabled(tp) && trace_kprobe_is_registered(tk)) { if (trace_kprobe_is_return(tk)) disable_kretprobe(&tk->rp); else disable_kprobe(&tk->rp.kp); - wait = 1; } - /* - * if tk is not added to any list, it must be a local trace_kprobe - * created with perf_event_open. We don't need to wait for these - * trace_kprobes - */ - if (list_empty(&tk->devent.list)) - wait = 0; out: - if (wait) { + if (file) /* - * Synchronize with kprobe_trace_func/kretprobe_trace_func - * to ensure disabled (all running handlers are finished). - * This is not only for kfree(), but also the caller, - * trace_remove_event_call() supposes it for releasing - * event_call related objects, which will be accessed in - * the kprobe_trace_func/kretprobe_trace_func. + * Synchronization is done in below function. For perf event, + * file == NULL and perf_trace_event_unreg() calls + * tracepoint_synchronize_unregister() to ensure synchronize + * event. We don't need to care about it. */ - synchronize_rcu(); - kfree(link); /* Ignored if link == NULL */ - } + trace_probe_remove_file(tp, file); return ret; } @@ -415,7 +389,7 @@ static int __register_trace_kprobe(struct trace_kprobe *tk) { int i, ret; - if (trace_probe_is_registered(&tk->tp)) + if (trace_kprobe_is_registered(tk)) return -EINVAL; if (within_notrace_func(tk)) { @@ -441,21 +415,20 @@ static int __register_trace_kprobe(struct trace_kprobe *tk) else ret = register_kprobe(&tk->rp.kp); - if (ret == 0) - tk->tp.flags |= TP_FLAG_REGISTERED; return ret; } /* Internal unregister function - just handle k*probes and flags */ static void __unregister_trace_kprobe(struct trace_kprobe *tk) { - if (trace_probe_is_registered(&tk->tp)) { + if (trace_kprobe_is_registered(tk)) { if (trace_kprobe_is_return(tk)) unregister_kretprobe(&tk->rp); else unregister_kprobe(&tk->rp.kp); - tk->tp.flags &= ~TP_FLAG_REGISTERED; - /* Cleanup kprobe for reuse */ + /* Cleanup kprobe for reuse and mark it unregistered */ + INIT_HLIST_NODE(&tk->rp.kp.hlist); + INIT_LIST_HEAD(&tk->rp.kp.list); if (tk->rp.kp.symbol_name) tk->rp.kp.addr = NULL; } @@ -487,8 +460,8 @@ static int register_trace_kprobe(struct trace_kprobe *tk) mutex_lock(&event_mutex); /* Delete old (same name) event if exist */ - old_tk = find_trace_kprobe(trace_event_name(&tk->tp.call), - tk->tp.call.class->system); + old_tk = find_trace_kprobe(trace_probe_name(&tk->tp), + trace_probe_group_name(&tk->tp)); if (old_tk) { ret = unregister_trace_kprobe(old_tk); if (ret < 0) @@ -541,7 +514,7 @@ static int trace_kprobe_module_callback(struct notifier_block *nb, ret = __register_trace_kprobe(tk); if (ret) pr_warn("Failed to re-register probe %s on %s: %d\n", - trace_event_name(&tk->tp.call), + trace_probe_name(&tk->tp), mod->name, ret); } } @@ -716,6 +689,10 @@ static int trace_kprobe_create(int argc, const char *argv[]) goto error; /* This can be -ENOMEM */ } + ret = traceprobe_set_print_fmt(&tk->tp, is_return); + if (ret < 0) + goto error; + ret = register_trace_kprobe(tk); if (ret) { trace_probe_log_set_index(1); @@ -767,8 +744,8 @@ static int trace_kprobe_show(struct seq_file *m, struct dyn_event *ev) int i; seq_putc(m, trace_kprobe_is_return(tk) ? 'r' : 'p'); - seq_printf(m, ":%s/%s", tk->tp.call.class->system, - trace_event_name(&tk->tp.call)); + seq_printf(m, ":%s/%s", trace_probe_group_name(&tk->tp), + trace_probe_name(&tk->tp)); if (!tk->symbol) seq_printf(m, " 0x%p", tk->rp.kp.addr); @@ -842,7 +819,7 @@ static int probes_profile_seq_show(struct seq_file *m, void *v) tk = to_trace_kprobe(ev); seq_printf(m, " %-44s %15lu %15lu\n", - trace_event_name(&tk->tp.call), + trace_probe_name(&tk->tp), trace_kprobe_nhit(tk), tk->rp.kp.nmissed); @@ -886,6 +863,15 @@ fetch_store_strlen(unsigned long addr) return (ret < 0) ? ret : len; } +/* Return the length of string -- including null terminal byte */ +static nokprobe_inline int +fetch_store_strlen_user(unsigned long addr) +{ + const void __user *uaddr = (__force const void __user *)addr; + + return strnlen_unsafe_user(uaddr, MAX_STRING_SIZE); +} + /* * Fetch a null-terminated string. Caller MUST set *(u32 *)buf with max * length and relative data location. @@ -894,19 +880,46 @@ static nokprobe_inline int fetch_store_string(unsigned long addr, void *dest, void *base) { int maxlen = get_loc_len(*(u32 *)dest); - u8 *dst = get_loc_data(dest, base); + void *__dest; long ret; if (unlikely(!maxlen)) return -ENOMEM; + + __dest = get_loc_data(dest, base); + /* * Try to get string again, since the string can be changed while * probing. */ - ret = strncpy_from_unsafe(dst, (void *)addr, maxlen); + ret = strncpy_from_unsafe(__dest, (void *)addr, maxlen); + if (ret >= 0) + *(u32 *)dest = make_data_loc(ret, __dest - base); + + return ret; +} +/* + * Fetch a null-terminated string from user. Caller MUST set *(u32 *)buf + * with max length and relative data location. + */ +static nokprobe_inline int +fetch_store_string_user(unsigned long addr, void *dest, void *base) +{ + const void __user *uaddr = (__force const void __user *)addr; + int maxlen = get_loc_len(*(u32 *)dest); + void *__dest; + long ret; + + if (unlikely(!maxlen)) + return -ENOMEM; + + __dest = get_loc_data(dest, base); + + ret = strncpy_from_unsafe_user(__dest, uaddr, maxlen); if (ret >= 0) - *(u32 *)dest = make_data_loc(ret, (void *)dst - base); + *(u32 *)dest = make_data_loc(ret, __dest - base); + return ret; } @@ -916,6 +929,14 @@ probe_mem_read(void *dest, void *src, size_t size) return probe_kernel_read(dest, src, size); } +static nokprobe_inline int +probe_mem_read_user(void *dest, void *src, size_t size) +{ + const void __user *uaddr = (__force const void __user *)src; + + return probe_user_read(dest, uaddr, size); +} + /* Note that we don't verify it, since the code does not come from user space */ static int process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest, @@ -971,7 +992,7 @@ __kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs, struct ring_buffer *buffer; int size, dsize, pc; unsigned long irq_flags; - struct trace_event_call *call = &tk->tp.call; + struct trace_event_call *call = trace_probe_event_call(&tk->tp); WARN_ON(call != trace_file->event_call); @@ -1003,7 +1024,7 @@ kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs) { struct event_file_link *link; - list_for_each_entry_rcu(link, &tk->tp.files, list) + trace_probe_for_each_link_rcu(link, &tk->tp) __kprobe_trace_func(tk, regs, link->file); } NOKPROBE_SYMBOL(kprobe_trace_func); @@ -1019,7 +1040,7 @@ __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, struct ring_buffer *buffer; int size, pc, dsize; unsigned long irq_flags; - struct trace_event_call *call = &tk->tp.call; + struct trace_event_call *call = trace_probe_event_call(&tk->tp); WARN_ON(call != trace_file->event_call); @@ -1053,7 +1074,7 @@ kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, { struct event_file_link *link; - list_for_each_entry_rcu(link, &tk->tp.files, list) + trace_probe_for_each_link_rcu(link, &tk->tp) __kretprobe_trace_func(tk, ri, regs, link->file); } NOKPROBE_SYMBOL(kretprobe_trace_func); @@ -1070,7 +1091,7 @@ print_kprobe_event(struct trace_iterator *iter, int flags, field = (struct kprobe_trace_entry_head *)iter->ent; tp = container_of(event, struct trace_probe, call.event); - trace_seq_printf(s, "%s: (", trace_event_name(&tp->call)); + trace_seq_printf(s, "%s: (", trace_probe_name(tp)); if (!seq_print_ip_sym(s, field->ip, flags | TRACE_ITER_SYM_OFFSET)) goto out; @@ -1097,7 +1118,7 @@ print_kretprobe_event(struct trace_iterator *iter, int flags, field = (struct kretprobe_trace_entry_head *)iter->ent; tp = container_of(event, struct trace_probe, call.event); - trace_seq_printf(s, "%s: (", trace_event_name(&tp->call)); + trace_seq_printf(s, "%s: (", trace_probe_name(tp)); if (!seq_print_ip_sym(s, field->ret_ip, flags | TRACE_ITER_SYM_OFFSET)) goto out; @@ -1149,7 +1170,7 @@ static int kretprobe_event_define_fields(struct trace_event_call *event_call) static int kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) { - struct trace_event_call *call = &tk->tp.call; + struct trace_event_call *call = trace_probe_event_call(&tk->tp); struct kprobe_trace_entry_head *entry; struct hlist_head *head; int size, __size, dsize; @@ -1199,7 +1220,7 @@ static void kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, struct pt_regs *regs) { - struct trace_event_call *call = &tk->tp.call; + struct trace_event_call *call = trace_probe_event_call(&tk->tp); struct kretprobe_trace_entry_head *entry; struct hlist_head *head; int size, __size, dsize; @@ -1299,10 +1320,10 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs) raw_cpu_inc(*tk->nhit); - if (tk->tp.flags & TP_FLAG_TRACE) + if (trace_probe_test_flag(&tk->tp, TP_FLAG_TRACE)) kprobe_trace_func(tk, regs); #ifdef CONFIG_PERF_EVENTS - if (tk->tp.flags & TP_FLAG_PROFILE) + if (trace_probe_test_flag(&tk->tp, TP_FLAG_PROFILE)) ret = kprobe_perf_func(tk, regs); #endif return ret; @@ -1316,10 +1337,10 @@ kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs) raw_cpu_inc(*tk->nhit); - if (tk->tp.flags & TP_FLAG_TRACE) + if (trace_probe_test_flag(&tk->tp, TP_FLAG_TRACE)) kretprobe_trace_func(tk, ri, regs); #ifdef CONFIG_PERF_EVENTS - if (tk->tp.flags & TP_FLAG_PROFILE) + if (trace_probe_test_flag(&tk->tp, TP_FLAG_PROFILE)) kretprobe_perf_func(tk, ri, regs); #endif return 0; /* We don't tweek kernel, so just return 0 */ @@ -1334,10 +1355,10 @@ static struct trace_event_functions kprobe_funcs = { .trace = print_kprobe_event }; -static inline void init_trace_event_call(struct trace_kprobe *tk, - struct trace_event_call *call) +static inline void init_trace_event_call(struct trace_kprobe *tk) { - INIT_LIST_HEAD(&call->class->fields); + struct trace_event_call *call = trace_probe_event_call(&tk->tp); + if (trace_kprobe_is_return(tk)) { call->event.funcs = &kretprobe_funcs; call->class->define_fields = kretprobe_event_define_fields; @@ -1353,37 +1374,14 @@ static inline void init_trace_event_call(struct trace_kprobe *tk, static int register_kprobe_event(struct trace_kprobe *tk) { - struct trace_event_call *call = &tk->tp.call; - int ret = 0; - - init_trace_event_call(tk, call); + init_trace_event_call(tk); - if (traceprobe_set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0) - return -ENOMEM; - ret = register_trace_event(&call->event); - if (!ret) { - kfree(call->print_fmt); - return -ENODEV; - } - ret = trace_add_event_call(call); - if (ret) { - pr_info("Failed to register kprobe event: %s\n", - trace_event_name(call)); - kfree(call->print_fmt); - unregister_trace_event(&call->event); - } - return ret; + return trace_probe_register_event_call(&tk->tp); } static int unregister_kprobe_event(struct trace_kprobe *tk) { - int ret; - - /* tp->event is unregistered in trace_remove_event_call() */ - ret = trace_remove_event_call(&tk->tp.call); - if (!ret) - kfree(tk->tp.call.print_fmt); - return ret; + return trace_probe_unregister_event_call(&tk->tp); } #ifdef CONFIG_PERF_EVENTS @@ -1413,7 +1411,7 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs, return ERR_CAST(tk); } - init_trace_event_call(tk, &tk->tp.call); + init_trace_event_call(tk); if (traceprobe_set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0) { ret = -ENOMEM; @@ -1421,12 +1419,10 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs, } ret = __register_trace_kprobe(tk); - if (ret < 0) { - kfree(tk->tp.call.print_fmt); + if (ret < 0) goto error; - } - return &tk->tp.call; + return trace_probe_event_call(&tk->tp); error: free_trace_kprobe(tk); return ERR_PTR(ret); @@ -1445,11 +1441,50 @@ void destroy_local_trace_kprobe(struct trace_event_call *event_call) __unregister_trace_kprobe(tk); - kfree(tk->tp.call.print_fmt); free_trace_kprobe(tk); } #endif /* CONFIG_PERF_EVENTS */ +static __init void enable_boot_kprobe_events(void) +{ + struct trace_array *tr = top_trace_array(); + struct trace_event_file *file; + struct trace_kprobe *tk; + struct dyn_event *pos; + + mutex_lock(&event_mutex); + for_each_trace_kprobe(tk, pos) { + list_for_each_entry(file, &tr->events, list) + if (file->event_call == trace_probe_event_call(&tk->tp)) + trace_event_enable_disable(file, 1, 0); + } + mutex_unlock(&event_mutex); +} + +static __init void setup_boot_kprobe_events(void) +{ + char *p, *cmd = kprobe_boot_events_buf; + int ret; + + strreplace(kprobe_boot_events_buf, ',', ' '); + + while (cmd && *cmd != '\0') { + p = strchr(cmd, ';'); + if (p) + *p++ = '\0'; + + ret = trace_run_command(cmd, create_or_delete_trace_kprobe); + if (ret) + pr_warn("Failed to add event(%d): %s\n", ret, cmd); + else + kprobe_boot_events_enabled = true; + + cmd = p; + } + + enable_boot_kprobe_events(); +} + /* Make a tracefs interface for controlling probe points */ static __init int init_kprobe_trace(void) { @@ -1481,6 +1516,9 @@ static __init int init_kprobe_trace(void) if (!entry) pr_warn("Could not create tracefs 'kprobe_profile' entry\n"); + + setup_boot_kprobe_events(); + return 0; } fs_initcall(init_kprobe_trace); @@ -1493,7 +1531,7 @@ find_trace_probe_file(struct trace_kprobe *tk, struct trace_array *tr) struct trace_event_file *file; list_for_each_entry(file, &tr->events, list) - if (file->event_call == &tk->tp.call) + if (file->event_call == trace_probe_event_call(&tk->tp)) return file; return NULL; @@ -1513,6 +1551,11 @@ static __init int kprobe_trace_self_tests_init(void) if (tracing_is_disabled()) return -ENODEV; + if (kprobe_boot_events_enabled) { + pr_info("Skipping kprobe tests due to kprobe_event on cmdline\n"); + return 0; + } + target = kprobe_trace_selftest_target; pr_info("Testing kprobe tracing: "); diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index ba751f993c3b..cab4a5398f1d 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -1109,17 +1109,10 @@ static enum print_line_t trace_user_stack_print(struct trace_iterator *iter, for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { unsigned long ip = field->caller[i]; - if (ip == ULONG_MAX || trace_seq_has_overflowed(s)) + if (!ip || trace_seq_has_overflowed(s)) break; trace_seq_puts(s, " => "); - - if (!ip) { - trace_seq_puts(s, "??"); - trace_seq_putc(s, '\n'); - continue; - } - seq_print_user_ip(s, mm, ip, flags); trace_seq_putc(s, '\n'); } diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index a347faced959..dbef0d135075 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -78,6 +78,8 @@ static const struct fetch_type probe_fetch_types[] = { /* Special types */ __ASSIGN_FETCH_TYPE("string", string, string, sizeof(u32), 1, "__data_loc char[]"), + __ASSIGN_FETCH_TYPE("ustring", string, string, sizeof(u32), 1, + "__data_loc char[]"), /* Basic types */ ASSIGN_FETCH_TYPE(u8, u8, 0), ASSIGN_FETCH_TYPE(u16, u16, 0), @@ -322,6 +324,7 @@ parse_probe_arg(char *arg, const struct fetch_type *type, { struct fetch_insn *code = *pcode; unsigned long param; + int deref = FETCH_OP_DEREF; long offset = 0; char *tmp; int ret = 0; @@ -394,9 +397,14 @@ parse_probe_arg(char *arg, const struct fetch_type *type, break; case '+': /* deref memory */ - arg++; /* Skip '+', because kstrtol() rejects it. */ - /* fall through */ case '-': + if (arg[1] == 'u') { + deref = FETCH_OP_UDEREF; + arg[1] = arg[0]; + arg++; + } + if (arg[0] == '+') + arg++; /* Skip '+', because kstrtol() rejects it. */ tmp = strchr(arg, '('); if (!tmp) { trace_probe_log_err(offs, DEREF_NEED_BRACE); @@ -432,7 +440,7 @@ parse_probe_arg(char *arg, const struct fetch_type *type, } *pcode = code; - code->op = FETCH_OP_DEREF; + code->op = deref; code->offset = offset; } break; @@ -569,15 +577,17 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size, goto fail; /* Store operation */ - if (!strcmp(parg->type->name, "string")) { - if (code->op != FETCH_OP_DEREF && code->op != FETCH_OP_IMM && - code->op != FETCH_OP_COMM) { + if (!strcmp(parg->type->name, "string") || + !strcmp(parg->type->name, "ustring")) { + if (code->op != FETCH_OP_DEREF && code->op != FETCH_OP_UDEREF && + code->op != FETCH_OP_IMM && code->op != FETCH_OP_COMM) { trace_probe_log_err(offset + (t ? (t - arg) : 0), BAD_STRING); ret = -EINVAL; goto fail; } - if (code->op != FETCH_OP_DEREF || parg->count) { + if ((code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM) || + parg->count) { /* * IMM and COMM is pointing actual address, those must * be kept, and if parg->count != 0, this is an array @@ -590,12 +600,20 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size, goto fail; } } - code->op = FETCH_OP_ST_STRING; /* In DEREF case, replace it */ + /* If op == DEREF, replace it with STRING */ + if (!strcmp(parg->type->name, "ustring") || + code->op == FETCH_OP_UDEREF) + code->op = FETCH_OP_ST_USTRING; + else + code->op = FETCH_OP_ST_STRING; code->size = parg->type->size; parg->dynamic = true; } else if (code->op == FETCH_OP_DEREF) { code->op = FETCH_OP_ST_MEM; code->size = parg->type->size; + } else if (code->op == FETCH_OP_UDEREF) { + code->op = FETCH_OP_ST_UMEM; + code->size = parg->type->size; } else { code++; if (code->op != FETCH_OP_NOP) { @@ -618,7 +636,8 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size, /* Loop(Array) operation */ if (parg->count) { if (scode->op != FETCH_OP_ST_MEM && - scode->op != FETCH_OP_ST_STRING) { + scode->op != FETCH_OP_ST_STRING && + scode->op != FETCH_OP_ST_USTRING) { trace_probe_log_err(offset + (t ? (t - arg) : 0), BAD_STRING); ret = -EINVAL; @@ -825,6 +844,7 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len, int traceprobe_set_print_fmt(struct trace_probe *tp, bool is_return) { + struct trace_event_call *call = trace_probe_event_call(tp); int len; char *print_fmt; @@ -836,7 +856,7 @@ int traceprobe_set_print_fmt(struct trace_probe *tp, bool is_return) /* Second: actually write the @print_fmt */ __set_print_fmt(tp, print_fmt, len + 1, is_return); - tp->call.print_fmt = print_fmt; + call->print_fmt = print_fmt; return 0; } @@ -865,3 +885,105 @@ int traceprobe_define_arg_fields(struct trace_event_call *event_call, } return 0; } + + +void trace_probe_cleanup(struct trace_probe *tp) +{ + struct trace_event_call *call = trace_probe_event_call(tp); + int i; + + for (i = 0; i < tp->nr_args; i++) + traceprobe_free_probe_arg(&tp->args[i]); + + kfree(call->class->system); + kfree(call->name); + kfree(call->print_fmt); +} + +int trace_probe_init(struct trace_probe *tp, const char *event, + const char *group) +{ + struct trace_event_call *call = trace_probe_event_call(tp); + + if (!event || !group) + return -EINVAL; + + call->class = &tp->class; + call->name = kstrdup(event, GFP_KERNEL); + if (!call->name) + return -ENOMEM; + + tp->class.system = kstrdup(group, GFP_KERNEL); + if (!tp->class.system) { + kfree(call->name); + call->name = NULL; + return -ENOMEM; + } + INIT_LIST_HEAD(&tp->files); + INIT_LIST_HEAD(&tp->class.fields); + + return 0; +} + +int trace_probe_register_event_call(struct trace_probe *tp) +{ + struct trace_event_call *call = trace_probe_event_call(tp); + int ret; + + ret = register_trace_event(&call->event); + if (!ret) + return -ENODEV; + + ret = trace_add_event_call(call); + if (ret) + unregister_trace_event(&call->event); + + return ret; +} + +int trace_probe_add_file(struct trace_probe *tp, struct trace_event_file *file) +{ + struct event_file_link *link; + + link = kmalloc(sizeof(*link), GFP_KERNEL); + if (!link) + return -ENOMEM; + + link->file = file; + INIT_LIST_HEAD(&link->list); + list_add_tail_rcu(&link->list, &tp->files); + trace_probe_set_flag(tp, TP_FLAG_TRACE); + return 0; +} + +struct event_file_link *trace_probe_get_file_link(struct trace_probe *tp, + struct trace_event_file *file) +{ + struct event_file_link *link; + + trace_probe_for_each_link(link, tp) { + if (link->file == file) + return link; + } + + return NULL; +} + +int trace_probe_remove_file(struct trace_probe *tp, + struct trace_event_file *file) +{ + struct event_file_link *link; + + link = trace_probe_get_file_link(tp, file); + if (!link) + return -ENOENT; + + list_del_rcu(&link->list); + synchronize_rcu(); + kfree(link); + + if (list_empty(&tp->files)) + trace_probe_clear_flag(tp, TP_FLAG_TRACE); + + return 0; +} diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index f9a8c632188b..d1714820efe1 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -55,7 +55,6 @@ /* Flags for trace_probe */ #define TP_FLAG_TRACE 1 #define TP_FLAG_PROFILE 2 -#define TP_FLAG_REGISTERED 4 /* data_loc: data location, compatible with u32 */ #define make_data_loc(len, offs) \ @@ -92,10 +91,13 @@ enum fetch_op { FETCH_OP_FOFFS, /* File offset: .immediate */ // Stage 2 (dereference) op FETCH_OP_DEREF, /* Dereference: .offset */ + FETCH_OP_UDEREF, /* User-space Dereference: .offset */ // Stage 3 (store) ops FETCH_OP_ST_RAW, /* Raw: .size */ FETCH_OP_ST_MEM, /* Mem: .offset, .size */ + FETCH_OP_ST_UMEM, /* Mem: .offset, .size */ FETCH_OP_ST_STRING, /* String: .offset, .size */ + FETCH_OP_ST_USTRING, /* User String: .offset, .size */ // Stage 4 (modify) op FETCH_OP_MOD_BF, /* Bitfield: .basesize, .lshift, .rshift */ // Stage 5 (loop) op @@ -235,16 +237,71 @@ struct event_file_link { struct list_head list; }; +static inline bool trace_probe_test_flag(struct trace_probe *tp, + unsigned int flag) +{ + return !!(tp->flags & flag); +} + +static inline void trace_probe_set_flag(struct trace_probe *tp, + unsigned int flag) +{ + tp->flags |= flag; +} + +static inline void trace_probe_clear_flag(struct trace_probe *tp, + unsigned int flag) +{ + tp->flags &= ~flag; +} + static inline bool trace_probe_is_enabled(struct trace_probe *tp) { - return !!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE)); + return trace_probe_test_flag(tp, TP_FLAG_TRACE | TP_FLAG_PROFILE); } -static inline bool trace_probe_is_registered(struct trace_probe *tp) +static inline const char *trace_probe_name(struct trace_probe *tp) { - return !!(tp->flags & TP_FLAG_REGISTERED); + return trace_event_name(&tp->call); } +static inline const char *trace_probe_group_name(struct trace_probe *tp) +{ + return tp->call.class->system; +} + +static inline struct trace_event_call * + trace_probe_event_call(struct trace_probe *tp) +{ + return &tp->call; +} + +static inline int trace_probe_unregister_event_call(struct trace_probe *tp) +{ + /* tp->event is unregistered in trace_remove_event_call() */ + return trace_remove_event_call(&tp->call); +} + +static inline bool trace_probe_has_single_file(struct trace_probe *tp) +{ + return !!list_is_singular(&tp->files); +} + +int trace_probe_init(struct trace_probe *tp, const char *event, + const char *group); +void trace_probe_cleanup(struct trace_probe *tp); +int trace_probe_register_event_call(struct trace_probe *tp); +int trace_probe_add_file(struct trace_probe *tp, struct trace_event_file *file); +int trace_probe_remove_file(struct trace_probe *tp, + struct trace_event_file *file); +struct event_file_link *trace_probe_get_file_link(struct trace_probe *tp, + struct trace_event_file *file); + +#define trace_probe_for_each_link(pos, tp) \ + list_for_each_entry(pos, &(tp)->files, list) +#define trace_probe_for_each_link_rcu(pos, tp) \ + list_for_each_entry_rcu(pos, &(tp)->files, list) + /* Check the name is good for event/group/fields */ static inline bool is_good_name(const char *name) { @@ -257,18 +314,6 @@ static inline bool is_good_name(const char *name) return true; } -static inline struct event_file_link * -find_event_file_link(struct trace_probe *tp, struct trace_event_file *file) -{ - struct event_file_link *link; - - list_for_each_entry(link, &tp->files, list) - if (link->file == file) - return link; - - return NULL; -} - #define TPARG_FL_RETURN BIT(0) #define TPARG_FL_KERNEL BIT(1) #define TPARG_FL_FENTRY BIT(2) diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h index c30c61f12ddd..e5282828f4a6 100644 --- a/kernel/trace/trace_probe_tmpl.h +++ b/kernel/trace/trace_probe_tmpl.h @@ -59,8 +59,13 @@ process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, static nokprobe_inline int fetch_store_strlen(unsigned long addr); static nokprobe_inline int fetch_store_string(unsigned long addr, void *dest, void *base); +static nokprobe_inline int fetch_store_strlen_user(unsigned long addr); +static nokprobe_inline int +fetch_store_string_user(unsigned long addr, void *dest, void *base); static nokprobe_inline int probe_mem_read(void *dest, void *src, size_t size); +static nokprobe_inline int +probe_mem_read_user(void *dest, void *src, size_t size); /* From the 2nd stage, routine is same */ static nokprobe_inline int @@ -74,14 +79,21 @@ process_fetch_insn_bottom(struct fetch_insn *code, unsigned long val, stage2: /* 2nd stage: dereference memory if needed */ - while (code->op == FETCH_OP_DEREF) { - lval = val; - ret = probe_mem_read(&val, (void *)val + code->offset, - sizeof(val)); + do { + if (code->op == FETCH_OP_DEREF) { + lval = val; + ret = probe_mem_read(&val, (void *)val + code->offset, + sizeof(val)); + } else if (code->op == FETCH_OP_UDEREF) { + lval = val; + ret = probe_mem_read_user(&val, + (void *)val + code->offset, sizeof(val)); + } else + break; if (ret) return ret; code++; - } + } while (1); s3 = code; stage3: @@ -91,6 +103,10 @@ stage3: ret = fetch_store_strlen(val + code->offset); code++; goto array; + } else if (code->op == FETCH_OP_ST_USTRING) { + ret += fetch_store_strlen_user(val + code->offset); + code++; + goto array; } else return -EILSEQ; } @@ -102,10 +118,17 @@ stage3: case FETCH_OP_ST_MEM: probe_mem_read(dest, (void *)val + code->offset, code->size); break; + case FETCH_OP_ST_UMEM: + probe_mem_read_user(dest, (void *)val + code->offset, code->size); + break; case FETCH_OP_ST_STRING: loc = *(u32 *)dest; ret = fetch_store_string(val + code->offset, dest, base); break; + case FETCH_OP_ST_USTRING: + loc = *(u32 *)dest; + ret = fetch_store_string_user(val + code->offset, dest, base); + break; default: return -EILSEQ; } @@ -123,7 +146,8 @@ array: total += ret; if (++i < code->param) { code = s3; - if (s3->op != FETCH_OP_ST_STRING) { + if (s3->op != FETCH_OP_ST_STRING && + s3->op != FETCH_OP_ST_USTRING) { dest += s3->size; val += s3->size; goto stage3; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 7860e3f59fad..1ceedb9146b1 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -140,6 +140,13 @@ probe_mem_read(void *dest, void *src, size_t size) return copy_from_user(dest, vaddr, size) ? -EFAULT : 0; } + +static nokprobe_inline int +probe_mem_read_user(void *dest, void *src, size_t size) +{ + return probe_mem_read(dest, src, size); +} + /* * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max * length and relative data location. @@ -176,6 +183,12 @@ fetch_store_string(unsigned long addr, void *dest, void *base) return ret; } +static nokprobe_inline int +fetch_store_string_user(unsigned long addr, void *dest, void *base) +{ + return fetch_store_string(addr, dest, base); +} + /* Return the length of string -- including null terminal byte */ static nokprobe_inline int fetch_store_strlen(unsigned long addr) @@ -191,6 +204,12 @@ fetch_store_strlen(unsigned long addr) return (len > MAX_STRING_SIZE) ? 0 : len; } +static nokprobe_inline int +fetch_store_strlen_user(unsigned long addr) +{ + return fetch_store_strlen(addr); +} + static unsigned long translate_user_vaddr(unsigned long file_offset) { unsigned long base_addr; @@ -270,8 +289,8 @@ static bool trace_uprobe_match(const char *system, const char *event, { struct trace_uprobe *tu = to_trace_uprobe(ev); - return strcmp(trace_event_name(&tu->tp.call), event) == 0 && - (!system || strcmp(tu->tp.call.class->system, system) == 0); + return strcmp(trace_probe_name(&tu->tp), event) == 0 && + (!system || strcmp(trace_probe_group_name(&tu->tp), system) == 0); } /* @@ -281,25 +300,17 @@ static struct trace_uprobe * alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) { struct trace_uprobe *tu; - - if (!event || !group) - return ERR_PTR(-EINVAL); + int ret; tu = kzalloc(SIZEOF_TRACE_UPROBE(nargs), GFP_KERNEL); if (!tu) return ERR_PTR(-ENOMEM); - tu->tp.call.class = &tu->tp.class; - tu->tp.call.name = kstrdup(event, GFP_KERNEL); - if (!tu->tp.call.name) - goto error; - - tu->tp.class.system = kstrdup(group, GFP_KERNEL); - if (!tu->tp.class.system) + ret = trace_probe_init(&tu->tp, event, group); + if (ret < 0) goto error; dyn_event_init(&tu->devent, &trace_uprobe_ops); - INIT_LIST_HEAD(&tu->tp.files); tu->consumer.handler = uprobe_dispatcher; if (is_ret) tu->consumer.ret_handler = uretprobe_dispatcher; @@ -307,25 +318,18 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) return tu; error: - kfree(tu->tp.call.name); kfree(tu); - return ERR_PTR(-ENOMEM); + return ERR_PTR(ret); } static void free_trace_uprobe(struct trace_uprobe *tu) { - int i; - if (!tu) return; - for (i = 0; i < tu->tp.nr_args; i++) - traceprobe_free_probe_arg(&tu->tp.args[i]); - path_put(&tu->path); - kfree(tu->tp.call.class->system); - kfree(tu->tp.call.name); + trace_probe_cleanup(&tu->tp); kfree(tu->filename); kfree(tu); } @@ -336,8 +340,8 @@ static struct trace_uprobe *find_probe_event(const char *event, const char *grou struct trace_uprobe *tu; for_each_trace_uprobe(tu, pos) - if (strcmp(trace_event_name(&tu->tp.call), event) == 0 && - strcmp(tu->tp.call.class->system, group) == 0) + if (strcmp(trace_probe_name(&tu->tp), event) == 0 && + strcmp(trace_probe_group_name(&tu->tp), group) == 0) return tu; return NULL; @@ -372,8 +376,8 @@ static struct trace_uprobe *find_old_trace_uprobe(struct trace_uprobe *new) struct trace_uprobe *tmp, *old = NULL; struct inode *new_inode = d_real_inode(new->path.dentry); - old = find_probe_event(trace_event_name(&new->tp.call), - new->tp.call.class->system); + old = find_probe_event(trace_probe_name(&new->tp), + trace_probe_group_name(&new->tp)); for_each_trace_uprobe(tmp, pos) { if ((old ? old != tmp : true) && @@ -578,6 +582,10 @@ static int trace_uprobe_create(int argc, const char **argv) goto error; } + ret = traceprobe_set_print_fmt(&tu->tp, is_ret_probe(tu)); + if (ret < 0) + goto error; + ret = register_trace_uprobe(tu); if (!ret) goto out; @@ -621,8 +629,8 @@ static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev) char c = is_ret_probe(tu) ? 'r' : 'p'; int i; - seq_printf(m, "%c:%s/%s %s:0x%0*lx", c, tu->tp.call.class->system, - trace_event_name(&tu->tp.call), tu->filename, + seq_printf(m, "%c:%s/%s %s:0x%0*lx", c, trace_probe_group_name(&tu->tp), + trace_probe_name(&tu->tp), tu->filename, (int)(sizeof(void *) * 2), tu->offset); if (tu->ref_ctr_offset) @@ -692,7 +700,7 @@ static int probes_profile_seq_show(struct seq_file *m, void *v) tu = to_trace_uprobe(ev); seq_printf(m, " %s %-44s %15lu\n", tu->filename, - trace_event_name(&tu->tp.call), tu->nhit); + trace_probe_name(&tu->tp), tu->nhit); return 0; } @@ -818,7 +826,7 @@ static void __uprobe_trace_func(struct trace_uprobe *tu, struct ring_buffer *buffer; void *data; int size, esize; - struct trace_event_call *call = &tu->tp.call; + struct trace_event_call *call = trace_probe_event_call(&tu->tp); WARN_ON(call != trace_file->event_call); @@ -860,7 +868,7 @@ static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs, return 0; rcu_read_lock(); - list_for_each_entry_rcu(link, &tu->tp.files, list) + trace_probe_for_each_link_rcu(link, &tu->tp) __uprobe_trace_func(tu, 0, regs, ucb, dsize, link->file); rcu_read_unlock(); @@ -874,7 +882,7 @@ static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func, struct event_file_link *link; rcu_read_lock(); - list_for_each_entry_rcu(link, &tu->tp.files, list) + trace_probe_for_each_link_rcu(link, &tu->tp) __uprobe_trace_func(tu, func, regs, ucb, dsize, link->file); rcu_read_unlock(); } @@ -893,12 +901,12 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e if (is_ret_probe(tu)) { trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", - trace_event_name(&tu->tp.call), + trace_probe_name(&tu->tp), entry->vaddr[1], entry->vaddr[0]); data = DATAOF_TRACE_ENTRY(entry, true); } else { trace_seq_printf(s, "%s: (0x%lx)", - trace_event_name(&tu->tp.call), + trace_probe_name(&tu->tp), entry->vaddr[0]); data = DATAOF_TRACE_ENTRY(entry, false); } @@ -921,26 +929,20 @@ probe_event_enable(struct trace_uprobe *tu, struct trace_event_file *file, filter_func_t filter) { bool enabled = trace_probe_is_enabled(&tu->tp); - struct event_file_link *link = NULL; int ret; if (file) { - if (tu->tp.flags & TP_FLAG_PROFILE) + if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE)) return -EINTR; - link = kmalloc(sizeof(*link), GFP_KERNEL); - if (!link) - return -ENOMEM; - - link->file = file; - list_add_tail_rcu(&link->list, &tu->tp.files); - - tu->tp.flags |= TP_FLAG_TRACE; + ret = trace_probe_add_file(&tu->tp, file); + if (ret < 0) + return ret; } else { - if (tu->tp.flags & TP_FLAG_TRACE) + if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE)) return -EINTR; - tu->tp.flags |= TP_FLAG_PROFILE; + trace_probe_set_flag(&tu->tp, TP_FLAG_PROFILE); } WARN_ON(!uprobe_filter_is_empty(&tu->filter)); @@ -970,13 +972,11 @@ probe_event_enable(struct trace_uprobe *tu, struct trace_event_file *file, uprobe_buffer_disable(); err_flags: - if (file) { - list_del(&link->list); - kfree(link); - tu->tp.flags &= ~TP_FLAG_TRACE; - } else { - tu->tp.flags &= ~TP_FLAG_PROFILE; - } + if (file) + trace_probe_remove_file(&tu->tp, file); + else + trace_probe_clear_flag(&tu->tp, TP_FLAG_PROFILE); + return ret; } @@ -987,26 +987,18 @@ probe_event_disable(struct trace_uprobe *tu, struct trace_event_file *file) return; if (file) { - struct event_file_link *link; - - link = find_event_file_link(&tu->tp, file); - if (!link) + if (trace_probe_remove_file(&tu->tp, file) < 0) return; - list_del_rcu(&link->list); - /* synchronize with u{,ret}probe_trace_func */ - synchronize_rcu(); - kfree(link); - - if (!list_empty(&tu->tp.files)) + if (trace_probe_is_enabled(&tu->tp)) return; - } + } else + trace_probe_clear_flag(&tu->tp, TP_FLAG_PROFILE); WARN_ON(!uprobe_filter_is_empty(&tu->filter)); uprobe_unregister(tu->inode, tu->offset, &tu->consumer); tu->inode = NULL; - tu->tp.flags &= file ? ~TP_FLAG_TRACE : ~TP_FLAG_PROFILE; uprobe_buffer_disable(); } @@ -1126,7 +1118,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, struct uprobe_cpu_buffer *ucb, int dsize) { - struct trace_event_call *call = &tu->tp.call; + struct trace_event_call *call = trace_probe_event_call(&tu->tp); struct uprobe_trace_entry_head *entry; struct hlist_head *head; void *data; @@ -1279,11 +1271,11 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) ucb = uprobe_buffer_get(); store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize); - if (tu->tp.flags & TP_FLAG_TRACE) + if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE)) ret |= uprobe_trace_func(tu, regs, ucb, dsize); #ifdef CONFIG_PERF_EVENTS - if (tu->tp.flags & TP_FLAG_PROFILE) + if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE)) ret |= uprobe_perf_func(tu, regs, ucb, dsize); #endif uprobe_buffer_put(ucb); @@ -1314,11 +1306,11 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con, ucb = uprobe_buffer_get(); store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize); - if (tu->tp.flags & TP_FLAG_TRACE) + if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE)) uretprobe_trace_func(tu, func, regs, ucb, dsize); #ifdef CONFIG_PERF_EVENTS - if (tu->tp.flags & TP_FLAG_PROFILE) + if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE)) uretprobe_perf_func(tu, func, regs, ucb, dsize); #endif uprobe_buffer_put(ucb); @@ -1329,10 +1321,10 @@ static struct trace_event_functions uprobe_funcs = { .trace = print_uprobe_event }; -static inline void init_trace_event_call(struct trace_uprobe *tu, - struct trace_event_call *call) +static inline void init_trace_event_call(struct trace_uprobe *tu) { - INIT_LIST_HEAD(&call->class->fields); + struct trace_event_call *call = trace_probe_event_call(&tu->tp); + call->event.funcs = &uprobe_funcs; call->class->define_fields = uprobe_event_define_fields; @@ -1343,43 +1335,14 @@ static inline void init_trace_event_call(struct trace_uprobe *tu, static int register_uprobe_event(struct trace_uprobe *tu) { - struct trace_event_call *call = &tu->tp.call; - int ret = 0; - - init_trace_event_call(tu, call); - - if (traceprobe_set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0) - return -ENOMEM; + init_trace_event_call(tu); - ret = register_trace_event(&call->event); - if (!ret) { - kfree(call->print_fmt); - return -ENODEV; - } - - ret = trace_add_event_call(call); - - if (ret) { - pr_info("Failed to register uprobe event: %s\n", - trace_event_name(call)); - kfree(call->print_fmt); - unregister_trace_event(&call->event); - } - - return ret; + return trace_probe_register_event_call(&tu->tp); } static int unregister_uprobe_event(struct trace_uprobe *tu) { - int ret; - - /* tu->event is unregistered in trace_remove_event_call() */ - ret = trace_remove_event_call(&tu->tp.call); - if (ret) - return ret; - kfree(tu->tp.call.print_fmt); - tu->tp.call.print_fmt = NULL; - return 0; + return trace_probe_unregister_event_call(&tu->tp); } #ifdef CONFIG_PERF_EVENTS @@ -1419,14 +1382,14 @@ create_local_trace_uprobe(char *name, unsigned long offs, tu->path = path; tu->ref_ctr_offset = ref_ctr_offset; tu->filename = kstrdup(name, GFP_KERNEL); - init_trace_event_call(tu, &tu->tp.call); + init_trace_event_call(tu); if (traceprobe_set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0) { ret = -ENOMEM; goto error; } - return &tu->tp.call; + return trace_probe_event_call(&tu->tp); error: free_trace_uprobe(tu); return ERR_PTR(ret); @@ -1438,9 +1401,6 @@ void destroy_local_trace_uprobe(struct trace_event_call *event_call) tu = container_of(event_call, struct trace_uprobe, tp.call); - kfree(tu->tp.call.print_fmt); - tu->tp.call.print_fmt = NULL; - free_trace_uprobe(tu); } #endif /* CONFIG_PERF_EVENTS */ diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index df3ade14ccbd..73956eaff8a9 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -55,8 +55,8 @@ struct tp_probes { static inline void *allocate_probes(int count) { - struct tp_probes *p = kmalloc(count * sizeof(struct tracepoint_func) - + sizeof(struct tp_probes), GFP_KERNEL); + struct tp_probes *p = kmalloc(struct_size(p, probes, count), + GFP_KERNEL); return p == NULL ? NULL : p->probes; } diff --git a/kernel/ucount.c b/kernel/ucount.c index feb128c7b5d9..a53cc2b4179c 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -52,16 +52,14 @@ static struct ctl_table_root set_root = { .permissions = set_permissions, }; -static int zero = 0; -static int int_max = INT_MAX; #define UCOUNT_ENTRY(name) \ { \ .procname = name, \ .maxlen = sizeof(int), \ .mode = 0644, \ .proc_handler = proc_dointvec_minmax, \ - .extra1 = &zero, \ - .extra2 = &int_max, \ + .extra1 = SYSCTL_ZERO, \ + .extra2 = SYSCTL_INT_MAX, \ } static struct ctl_table user_table[] = { UCOUNT_ENTRY("max_user_namespaces"), |