diff options
Diffstat (limited to 'kernel')
44 files changed, 1787 insertions, 832 deletions
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index d2b32ac27a3..35536d9c096 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -223,3 +223,10 @@ endif config MUTEX_SPIN_ON_OWNER def_bool y depends on SMP && !DEBUG_MUTEXES + +config ARCH_USE_QUEUE_RWLOCK + bool + +config QUEUE_RWLOCK + def_bool y if ARCH_USE_QUEUE_RWLOCK + depends on SMP diff --git a/kernel/audit.c b/kernel/audit.c index f30106459a3..3ef2e0e797e 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -424,6 +424,38 @@ static void kauditd_send_skb(struct sk_buff *skb) } /* + * kauditd_send_multicast_skb - send the skb to multicast userspace listeners + * + * This function doesn't consume an skb as might be expected since it has to + * copy it anyways. + */ +static void kauditd_send_multicast_skb(struct sk_buff *skb) +{ + struct sk_buff *copy; + struct audit_net *aunet = net_generic(&init_net, audit_net_id); + struct sock *sock = aunet->nlsk; + + if (!netlink_has_listeners(sock, AUDIT_NLGRP_READLOG)) + return; + + /* + * The seemingly wasteful skb_copy() rather than bumping the refcount + * using skb_get() is necessary because non-standard mods are made to + * the skb by the original kaudit unicast socket send routine. The + * existing auditd daemon assumes this breakage. Fixing this would + * require co-ordinating a change in the established protocol between + * the kaudit kernel subsystem and the auditd userspace code. There is + * no reason for new multicast clients to continue with this + * non-compliance. + */ + copy = skb_copy(skb, GFP_KERNEL); + if (!copy) + return; + + nlmsg_multicast(sock, copy, 0, AUDIT_NLGRP_READLOG, GFP_KERNEL); +} + +/* * flush_hold_queue - empty the hold queue if auditd appears * * If auditd just started, drain the queue of messages already @@ -1076,10 +1108,22 @@ static void audit_receive(struct sk_buff *skb) mutex_unlock(&audit_cmd_mutex); } +/* Run custom bind function on netlink socket group connect or bind requests. */ +static int audit_bind(int group) +{ + if (!capable(CAP_AUDIT_READ)) + return -EPERM; + + return 0; +} + static int __net_init audit_net_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = audit_receive, + .bind = audit_bind, + .flags = NL_CFG_F_NONROOT_RECV, + .groups = AUDIT_NLGRP_MAX, }; struct audit_net *aunet = net_generic(net, audit_net_id); @@ -1901,10 +1945,10 @@ out: * audit_log_end - end one audit record * @ab: the audit_buffer * - * The netlink_* functions cannot be called inside an irq context, so - * the audit buffer is placed on a queue and a tasklet is scheduled to - * remove them from the queue outside the irq context. May be called in - * any context. + * netlink_unicast() cannot be called inside an irq context because it blocks + * (last arg, flags, is not set to MSG_DONTWAIT), so the audit buffer is placed + * on a queue and a tasklet is scheduled to remove them from the queue outside + * the irq context. May be called in any context. */ void audit_log_end(struct audit_buffer *ab) { @@ -1914,6 +1958,18 @@ void audit_log_end(struct audit_buffer *ab) audit_log_lost("rate limit exceeded"); } else { struct nlmsghdr *nlh = nlmsg_hdr(ab->skb); + + kauditd_send_multicast_skb(ab->skb); + + /* + * The original kaudit unicast socket sends up messages with + * nlmsg_len set to the payload length rather than the entire + * message length. This breaks the standard set by netlink. + * The existing auditd daemon assumes this breakage. Fixing + * this would require co-ordinating a change in the established + * protocol between the kaudit kernel subsystem and the auditd + * userspace code. + */ nlh->nlmsg_len = ab->skb->len - NLMSG_HDRLEN; if (audit_pid) { diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 019d4500844..5664985c46a 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -19,6 +19,7 @@ #include <linux/sched.h> #include <linux/hardirq.h> #include <linux/export.h> +#include <linux/kprobes.h> #define CREATE_TRACE_POINTS #include <trace/events/context_tracking.h> @@ -104,6 +105,7 @@ void context_tracking_user_enter(void) } local_irq_restore(flags); } +NOKPROBE_SYMBOL(context_tracking_user_enter); #ifdef CONFIG_PREEMPT /** @@ -181,6 +183,7 @@ void context_tracking_user_exit(void) } local_irq_restore(flags); } +NOKPROBE_SYMBOL(context_tracking_user_exit); /** * __context_tracking_task_switch - context switch the syscall callbacks diff --git a/kernel/cpu.c b/kernel/cpu.c index acf791c55b7..a343bde710b 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -20,6 +20,7 @@ #include <linux/gfp.h> #include <linux/suspend.h> #include <linux/lockdep.h> +#include <trace/events/power.h> #include "smpboot.h" @@ -520,7 +521,9 @@ int disable_nonboot_cpus(void) for_each_online_cpu(cpu) { if (cpu == first_cpu) continue; + trace_suspend_resume(TPS("CPU_OFF"), cpu, true); error = _cpu_down(cpu, 1); + trace_suspend_resume(TPS("CPU_OFF"), cpu, false); if (!error) cpumask_set_cpu(cpu, frozen_cpus); else { @@ -563,7 +566,9 @@ void __ref enable_nonboot_cpus(void) arch_enable_nonboot_cpus_begin(); for_each_cpu(cpu, frozen_cpus) { + trace_suspend_resume(TPS("CPU_ON"), cpu, true); error = _cpu_up(cpu, 1); + trace_suspend_resume(TPS("CPU_ON"), cpu, false); if (!error) { pr_info("CPU%d is up\n", cpu); continue; diff --git a/kernel/events/core.c b/kernel/events/core.c index 24d35cc38e4..a33d9a2bcbd 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -40,6 +40,7 @@ #include <linux/mm_types.h> #include <linux/cgroup.h> #include <linux/module.h> +#include <linux/mman.h> #include "internal.h" @@ -2974,6 +2975,22 @@ out: local_irq_restore(flags); } +void perf_event_exec(void) +{ + struct perf_event_context *ctx; + int ctxn; + + rcu_read_lock(); + for_each_task_context_nr(ctxn) { + ctx = current->perf_event_ctxp[ctxn]; + if (!ctx) + continue; + + perf_event_enable_on_exec(ctx); + } + rcu_read_unlock(); +} + /* * Cross CPU call to read the hardware event */ @@ -5075,21 +5092,9 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event) NULL); } -void perf_event_comm(struct task_struct *task) +void perf_event_comm(struct task_struct *task, bool exec) { struct perf_comm_event comm_event; - struct perf_event_context *ctx; - int ctxn; - - rcu_read_lock(); - for_each_task_context_nr(ctxn) { - ctx = task->perf_event_ctxp[ctxn]; - if (!ctx) - continue; - - perf_event_enable_on_exec(ctx); - } - rcu_read_unlock(); if (!atomic_read(&nr_comm_events)) return; @@ -5101,7 +5106,7 @@ void perf_event_comm(struct task_struct *task) .event_id = { .header = { .type = PERF_RECORD_COMM, - .misc = 0, + .misc = exec ? PERF_RECORD_MISC_COMM_EXEC : 0, /* .size */ }, /* .pid */ @@ -5124,6 +5129,7 @@ struct perf_mmap_event { int maj, min; u64 ino; u64 ino_generation; + u32 prot, flags; struct { struct perf_event_header header; @@ -5165,6 +5171,8 @@ static void perf_event_mmap_output(struct perf_event *event, mmap_event->event_id.header.size += sizeof(mmap_event->min); mmap_event->event_id.header.size += sizeof(mmap_event->ino); mmap_event->event_id.header.size += sizeof(mmap_event->ino_generation); + mmap_event->event_id.header.size += sizeof(mmap_event->prot); + mmap_event->event_id.header.size += sizeof(mmap_event->flags); } perf_event_header__init_id(&mmap_event->event_id.header, &sample, event); @@ -5183,6 +5191,8 @@ static void perf_event_mmap_output(struct perf_event *event, perf_output_put(&handle, mmap_event->min); perf_output_put(&handle, mmap_event->ino); perf_output_put(&handle, mmap_event->ino_generation); + perf_output_put(&handle, mmap_event->prot); + perf_output_put(&handle, mmap_event->flags); } __output_copy(&handle, mmap_event->file_name, @@ -5201,6 +5211,7 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) struct file *file = vma->vm_file; int maj = 0, min = 0; u64 ino = 0, gen = 0; + u32 prot = 0, flags = 0; unsigned int size; char tmp[16]; char *buf = NULL; @@ -5231,6 +5242,28 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) gen = inode->i_generation; maj = MAJOR(dev); min = MINOR(dev); + + if (vma->vm_flags & VM_READ) + prot |= PROT_READ; + if (vma->vm_flags & VM_WRITE) + prot |= PROT_WRITE; + if (vma->vm_flags & VM_EXEC) + prot |= PROT_EXEC; + + if (vma->vm_flags & VM_MAYSHARE) + flags = MAP_SHARED; + else + flags = MAP_PRIVATE; + + if (vma->vm_flags & VM_DENYWRITE) + flags |= MAP_DENYWRITE; + if (vma->vm_flags & VM_MAYEXEC) + flags |= MAP_EXECUTABLE; + if (vma->vm_flags & VM_LOCKED) + flags |= MAP_LOCKED; + if (vma->vm_flags & VM_HUGETLB) + flags |= MAP_HUGETLB; + goto got_name; } else { name = (char *)arch_vma_name(vma); @@ -5271,6 +5304,8 @@ got_name: mmap_event->min = min; mmap_event->ino = ino; mmap_event->ino_generation = gen; + mmap_event->prot = prot; + mmap_event->flags = flags; if (!(vma->vm_flags & VM_EXEC)) mmap_event->event_id.header.misc |= PERF_RECORD_MISC_MMAP_DATA; @@ -5311,6 +5346,8 @@ void perf_event_mmap(struct vm_area_struct *vma) /* .min (attr_mmap2 only) */ /* .ino (attr_mmap2 only) */ /* .ino_generation (attr_mmap2 only) */ + /* .prot (attr_mmap2 only) */ + /* .flags (attr_mmap2 only) */ }; perf_event_mmap_event(&mmap_event); @@ -6893,10 +6930,6 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, if (ret) return -EFAULT; - /* disabled for now */ - if (attr->mmap2) - return -EINVAL; - if (attr->__reserved_1) return -EINVAL; @@ -7122,6 +7155,13 @@ SYSCALL_DEFINE5(perf_event_open, } } + if (is_sampling_event(event)) { + if (event->pmu->capabilities & PERF_PMU_CAP_NO_INTERRUPT) { + err = -ENOTSUPP; + goto err_alloc; + } + } + account_event(event); /* @@ -7433,7 +7473,7 @@ __perf_event_exit_task(struct perf_event *child_event, static void perf_event_exit_task_context(struct task_struct *child, int ctxn) { - struct perf_event *child_event; + struct perf_event *child_event, *next; struct perf_event_context *child_ctx; unsigned long flags; @@ -7487,7 +7527,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) */ mutex_lock(&child_ctx->mutex); - list_for_each_entry_rcu(child_event, &child_ctx->event_list, event_entry) + list_for_each_entry_safe(child_event, next, &child_ctx->event_list, event_entry) __perf_event_exit_task(child_event, child_ctx, child); mutex_unlock(&child_ctx->mutex); diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index adcd76a9683..6f3254e8c13 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -36,6 +36,7 @@ #include "../../mm/internal.h" /* munlock_vma_page */ #include <linux/percpu-rwsem.h> #include <linux/task_work.h> +#include <linux/shmem_fs.h> #include <linux/uprobes.h> @@ -127,7 +128,7 @@ struct xol_area { */ static bool valid_vma(struct vm_area_struct *vma, bool is_register) { - vm_flags_t flags = VM_HUGETLB | VM_MAYEXEC | VM_SHARED; + vm_flags_t flags = VM_HUGETLB | VM_MAYEXEC | VM_MAYSHARE; if (is_register) flags |= VM_WRITE; @@ -279,18 +280,13 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t * supported by that architecture then we need to modify is_trap_at_addr and * uprobe_write_opcode accordingly. This would never be a problem for archs * that have fixed length instructions. - */ - -/* + * * uprobe_write_opcode - write the opcode at a given virtual address. * @mm: the probed process address space. * @vaddr: the virtual address to store the opcode. * @opcode: opcode to be written at @vaddr. * - * Called with mm->mmap_sem held (for read and with a reference to - * mm). - * - * For mm @mm, write the opcode at @vaddr. + * Called with mm->mmap_sem held for write. * Return 0 (success) or a negative errno. */ int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr, @@ -310,21 +306,25 @@ retry: if (ret <= 0) goto put_old; + ret = anon_vma_prepare(vma); + if (ret) + goto put_old; + ret = -ENOMEM; new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr); if (!new_page) goto put_old; - __SetPageUptodate(new_page); + if (mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL)) + goto put_new; + __SetPageUptodate(new_page); copy_highpage(new_page, old_page); copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE); - ret = anon_vma_prepare(vma); - if (ret) - goto put_new; - ret = __replace_page(vma, vaddr, old_page, new_page); + if (ret) + mem_cgroup_uncharge_page(new_page); put_new: page_cache_release(new_page); @@ -537,14 +537,15 @@ static int __copy_insn(struct address_space *mapping, struct file *filp, void *insn, int nbytes, loff_t offset) { struct page *page; - - if (!mapping->a_ops->readpage) - return -EIO; /* - * Ensure that the page that has the original instruction is - * populated and in page-cache. + * Ensure that the page that has the original instruction is populated + * and in page-cache. If ->readpage == NULL it must be shmem_mapping(), + * see uprobe_register(). */ - page = read_mapping_page(mapping, offset >> PAGE_CACHE_SHIFT, filp); + if (mapping->a_ops->readpage) + page = read_mapping_page(mapping, offset >> PAGE_CACHE_SHIFT, filp); + else + page = shmem_read_mapping_page(mapping, offset >> PAGE_CACHE_SHIFT); if (IS_ERR(page)) return PTR_ERR(page); @@ -845,7 +846,7 @@ static void __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *u { int err; - if (!consumer_del(uprobe, uc)) /* WARN? */ + if (WARN_ON(!consumer_del(uprobe, uc))) return; err = register_for_each_vma(uprobe, NULL); @@ -880,6 +881,9 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer * if (!uc->handler && !uc->ret_handler) return -EINVAL; + /* copy_insn() uses read_mapping_page() or shmem_read_mapping_page() */ + if (!inode->i_mapping->a_ops->readpage && !shmem_mapping(inode->i_mapping)) + return -EIO; /* Racy, just to catch the obvious mistakes */ if (offset > i_size_read(inode)) return -EINVAL; @@ -923,7 +927,7 @@ int uprobe_apply(struct inode *inode, loff_t offset, int ret = -ENOENT; uprobe = find_uprobe(inode, offset); - if (!uprobe) + if (WARN_ON(!uprobe)) return ret; down_write(&uprobe->register_rwsem); @@ -948,7 +952,7 @@ void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consume struct uprobe *uprobe; uprobe = find_uprobe(inode, offset); - if (!uprobe) + if (WARN_ON(!uprobe)) return; down_write(&uprobe->register_rwsem); @@ -1361,6 +1365,16 @@ unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs) return instruction_pointer(regs) - UPROBE_SWBP_INSN_SIZE; } +unsigned long uprobe_get_trap_addr(struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + if (unlikely(utask && utask->active_uprobe)) + return utask->vaddr; + + return instruction_pointer(regs); +} + /* * Called with no locks held. * Called in context of a exiting or a exec-ing thread. diff --git a/kernel/fork.c b/kernel/fork.c index d2799d1fc95..6a13c46cd87 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1487,7 +1487,9 @@ static struct task_struct *copy_process(unsigned long clone_flags, total_forks++; spin_unlock(¤t->sighand->siglock); + syscall_tracepoint_update(p); write_unlock_irq(&tasklist_lock); + proc_fork_connector(p); cgroup_post_fork(p); if (clone_flags & CLONE_THREAD) diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 7339e42a85a..1487a123db5 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -455,9 +455,9 @@ EXPORT_SYMBOL_GPL(irq_alloc_hwirqs); */ void irq_free_hwirqs(unsigned int from, int cnt) { - int i; + int i, j; - for (i = from; cnt > 0; i++, cnt--) { + for (i = from, j = cnt; j > 0; i++, j--) { irq_set_status_flags(i, _IRQ_NOREQUEST | _IRQ_NOPROBE); arch_teardown_hwirq(i); } diff --git a/kernel/kexec.c b/kernel/kexec.c index 6748688813d..369f41a9412 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -1617,6 +1617,7 @@ static int __init crash_save_vmcoreinfo_init(void) #ifdef CONFIG_MEMORY_FAILURE VMCOREINFO_NUMBER(PG_hwpoison); #endif + VMCOREINFO_NUMBER(PG_head_mask); VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); arch_crash_save_vmcoreinfo(); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index ceeadfcabb7..3214289df5a 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -86,21 +86,8 @@ static raw_spinlock_t *kretprobe_table_lock_ptr(unsigned long hash) return &(kretprobe_table_locks[hash].lock); } -/* - * Normally, functions that we'd want to prohibit kprobes in, are marked - * __kprobes. But, there are cases where such functions already belong to - * a different section (__sched for preempt_schedule) - * - * For such cases, we now have a blacklist - */ -static struct kprobe_blackpoint kprobe_blacklist[] = { - {"preempt_schedule",}, - {"native_get_debugreg",}, - {"irq_entries_start",}, - {"common_interrupt",}, - {"mcount",}, /* mcount can be called from everywhere */ - {NULL} /* Terminator */ -}; +/* Blacklist -- list of struct kprobe_blacklist_entry */ +static LIST_HEAD(kprobe_blacklist); #ifdef __ARCH_WANT_KPROBES_INSN_SLOT /* @@ -151,13 +138,13 @@ struct kprobe_insn_cache kprobe_insn_slots = { .insn_size = MAX_INSN_SIZE, .nr_garbage = 0, }; -static int __kprobes collect_garbage_slots(struct kprobe_insn_cache *c); +static int collect_garbage_slots(struct kprobe_insn_cache *c); /** * __get_insn_slot() - Find a slot on an executable page for an instruction. * We allocate an executable page if there's no room on existing ones. */ -kprobe_opcode_t __kprobes *__get_insn_slot(struct kprobe_insn_cache *c) +kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c) { struct kprobe_insn_page *kip; kprobe_opcode_t *slot = NULL; @@ -214,7 +201,7 @@ out: } /* Return 1 if all garbages are collected, otherwise 0. */ -static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx) +static int collect_one_slot(struct kprobe_insn_page *kip, int idx) { kip->slot_used[idx] = SLOT_CLEAN; kip->nused--; @@ -235,7 +222,7 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx) return 0; } -static int __kprobes collect_garbage_slots(struct kprobe_insn_cache *c) +static int collect_garbage_slots(struct kprobe_insn_cache *c) { struct kprobe_insn_page *kip, *next; @@ -257,8 +244,8 @@ static int __kprobes collect_garbage_slots(struct kprobe_insn_cache *c) return 0; } -void __kprobes __free_insn_slot(struct kprobe_insn_cache *c, - kprobe_opcode_t *slot, int dirty) +void __free_insn_slot(struct kprobe_insn_cache *c, + kprobe_opcode_t *slot, int dirty) { struct kprobe_insn_page *kip; @@ -314,7 +301,7 @@ static inline void reset_kprobe_instance(void) * OR * - with preemption disabled - from arch/xxx/kernel/kprobes.c */ -struct kprobe __kprobes *get_kprobe(void *addr) +struct kprobe *get_kprobe(void *addr) { struct hlist_head *head; struct kprobe *p; @@ -327,8 +314,9 @@ struct kprobe __kprobes *get_kprobe(void *addr) return NULL; } +NOKPROBE_SYMBOL(get_kprobe); -static int __kprobes aggr_pre_handler(struct kprobe *p, struct pt_regs *regs); +static int aggr_pre_handler(struct kprobe *p, struct pt_regs *regs); /* Return true if the kprobe is an aggregator */ static inline int kprobe_aggrprobe(struct kprobe *p) @@ -360,7 +348,7 @@ static bool kprobes_allow_optimization; * Call all pre_handler on the list, but ignores its return value. * This must be called from arch-dep optimized caller. */ -void __kprobes opt_pre_handler(struct kprobe *p, struct pt_regs *regs) +void opt_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct kprobe *kp; @@ -372,9 +360,10 @@ void __kprobes opt_pre_handler(struct kprobe *p, struct pt_regs *regs) reset_kprobe_instance(); } } +NOKPROBE_SYMBOL(opt_pre_handler); /* Free optimized instructions and optimized_kprobe */ -static __kprobes void free_aggr_kprobe(struct kprobe *p) +static void free_aggr_kprobe(struct kprobe *p) { struct optimized_kprobe *op; @@ -412,7 +401,7 @@ static inline int kprobe_disarmed(struct kprobe *p) } /* Return true(!0) if the probe is queued on (un)optimizing lists */ -static int __kprobes kprobe_queued(struct kprobe *p) +static int kprobe_queued(struct kprobe *p) { struct optimized_kprobe *op; @@ -428,7 +417,7 @@ static int __kprobes kprobe_queued(struct kprobe *p) * Return an optimized kprobe whose optimizing code replaces * instructions including addr (exclude breakpoint). */ -static struct kprobe *__kprobes get_optimized_kprobe(unsigned long addr) +static struct kprobe *get_optimized_kprobe(unsigned long addr) { int i; struct kprobe *p = NULL; @@ -460,7 +449,7 @@ static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer); * Optimize (replace a breakpoint with a jump) kprobes listed on * optimizing_list. */ -static __kprobes void do_optimize_kprobes(void) +static void do_optimize_kprobes(void) { /* Optimization never be done when disarmed */ if (kprobes_all_disarmed || !kprobes_allow_optimization || @@ -488,7 +477,7 @@ static __kprobes void do_optimize_kprobes(void) * Unoptimize (replace a jump with a breakpoint and remove the breakpoint * if need) kprobes listed on unoptimizing_list. */ -static __kprobes void do_unoptimize_kprobes(void) +static void do_unoptimize_kprobes(void) { struct optimized_kprobe *op, *tmp; @@ -520,7 +509,7 @@ static __kprobes void do_unoptimize_kprobes(void) } /* Reclaim all kprobes on the free_list */ -static __kprobes void do_free_cleaned_kprobes(void) +static void do_free_cleaned_kprobes(void) { struct optimized_kprobe *op, *tmp; @@ -532,13 +521,13 @@ static __kprobes void do_free_cleaned_kprobes(void) } /* Start optimizer after OPTIMIZE_DELAY passed */ -static __kprobes void kick_kprobe_optimizer(void) +static void kick_kprobe_optimizer(void) { schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY); } /* Kprobe jump optimizer */ -static __kprobes void kprobe_optimizer(struct work_struct *work) +static void kprobe_optimizer(struct work_struct *work) { mutex_lock(&kprobe_mutex); /* Lock modules while optimizing kprobes */ @@ -574,7 +563,7 @@ static __kprobes void kprobe_optimizer(struct work_struct *work) } /* Wait for completing optimization and unoptimization */ -static __kprobes void wait_for_kprobe_optimizer(void) +static void wait_for_kprobe_optimizer(void) { mutex_lock(&kprobe_mutex); @@ -593,7 +582,7 @@ static __kprobes void wait_for_kprobe_optimizer(void) } /* Optimize kprobe if p is ready to be optimized */ -static __kprobes void optimize_kprobe(struct kprobe *p) +static void optimize_kprobe(struct kprobe *p) { struct optimized_kprobe *op; @@ -627,7 +616,7 @@ static __kprobes void optimize_kprobe(struct kprobe *p) } /* Short cut to direct unoptimizing */ -static __kprobes void force_unoptimize_kprobe(struct optimized_kprobe *op) +static void force_unoptimize_kprobe(struct optimized_kprobe *op) { get_online_cpus(); arch_unoptimize_kprobe(op); @@ -637,7 +626,7 @@ static __kprobes void force_unoptimize_kprobe(struct optimized_kprobe *op) } /* Unoptimize a kprobe if p is optimized */ -static __kprobes void unoptimize_kprobe(struct kprobe *p, bool force) +static void unoptimize_kprobe(struct kprobe *p, bool force) { struct optimized_kprobe *op; @@ -697,7 +686,7 @@ static void reuse_unused_kprobe(struct kprobe *ap) } /* Remove optimized instructions */ -static void __kprobes kill_optimized_kprobe(struct kprobe *p) +static void kill_optimized_kprobe(struct kprobe *p) { struct optimized_kprobe *op; @@ -723,7 +712,7 @@ static void __kprobes kill_optimized_kprobe(struct kprobe *p) } /* Try to prepare optimized instructions */ -static __kprobes void prepare_optimized_kprobe(struct kprobe *p) +static void prepare_optimized_kprobe(struct kprobe *p) { struct optimized_kprobe *op; @@ -732,7 +721,7 @@ static __kprobes void prepare_optimized_kprobe(struct kprobe *p) } /* Allocate new optimized_kprobe and try to prepare optimized instructions */ -static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p) +static struct kprobe *alloc_aggr_kprobe(struct kprobe *p) { struct optimized_kprobe *op; @@ -747,13 +736,13 @@ static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p) return &op->kp; } -static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p); +static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p); /* * Prepare an optimized_kprobe and optimize it * NOTE: p must be a normal registered kprobe */ -static __kprobes void try_to_optimize_kprobe(struct kprobe *p) +static void try_to_optimize_kprobe(struct kprobe *p) { struct kprobe *ap; struct optimized_kprobe *op; @@ -787,7 +776,7 @@ out: } #ifdef CONFIG_SYSCTL -static void __kprobes optimize_all_kprobes(void) +static void optimize_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; @@ -810,7 +799,7 @@ out: mutex_unlock(&kprobe_mutex); } -static void __kprobes unoptimize_all_kprobes(void) +static void unoptimize_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; @@ -861,7 +850,7 @@ int proc_kprobes_optimization_handler(struct ctl_table *table, int write, #endif /* CONFIG_SYSCTL */ /* Put a breakpoint for a probe. Must be called with text_mutex locked */ -static void __kprobes __arm_kprobe(struct kprobe *p) +static void __arm_kprobe(struct kprobe *p) { struct kprobe *_p; @@ -876,7 +865,7 @@ static void __kprobes __arm_kprobe(struct kprobe *p) } /* Remove the breakpoint of a probe. Must be called with text_mutex locked */ -static void __kprobes __disarm_kprobe(struct kprobe *p, bool reopt) +static void __disarm_kprobe(struct kprobe *p, bool reopt) { struct kprobe *_p; @@ -911,13 +900,13 @@ static void reuse_unused_kprobe(struct kprobe *ap) BUG_ON(kprobe_unused(ap)); } -static __kprobes void free_aggr_kprobe(struct kprobe *p) +static void free_aggr_kprobe(struct kprobe *p) { arch_remove_kprobe(p); kfree(p); } -static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p) +static struct kprobe *alloc_aggr_kprobe(struct kprobe *p) { return kzalloc(sizeof(struct kprobe), GFP_KERNEL); } @@ -931,7 +920,7 @@ static struct ftrace_ops kprobe_ftrace_ops __read_mostly = { static int kprobe_ftrace_enabled; /* Must ensure p->addr is really on ftrace */ -static int __kprobes prepare_kprobe(struct kprobe *p) +static int prepare_kprobe(struct kprobe *p) { if (!kprobe_ftrace(p)) return arch_prepare_kprobe(p); @@ -940,7 +929,7 @@ static int __kprobes prepare_kprobe(struct kprobe *p) } /* Caller must lock kprobe_mutex */ -static void __kprobes arm_kprobe_ftrace(struct kprobe *p) +static void arm_kprobe_ftrace(struct kprobe *p) { int ret; @@ -955,7 +944,7 @@ static void __kprobes arm_kprobe_ftrace(struct kprobe *p) } /* Caller must lock kprobe_mutex */ -static void __kprobes disarm_kprobe_ftrace(struct kprobe *p) +static void disarm_kprobe_ftrace(struct kprobe *p) { int ret; @@ -975,7 +964,7 @@ static void __kprobes disarm_kprobe_ftrace(struct kprobe *p) #endif /* Arm a kprobe with text_mutex */ -static void __kprobes arm_kprobe(struct kprobe *kp) +static void arm_kprobe(struct kprobe *kp) { if (unlikely(kprobe_ftrace(kp))) { arm_kprobe_ftrace(kp); @@ -992,7 +981,7 @@ static void __kprobes arm_kprobe(struct kprobe *kp) } /* Disarm a kprobe with text_mutex */ -static void __kprobes disarm_kprobe(struct kprobe *kp, bool reopt) +static void disarm_kprobe(struct kprobe *kp, bool reopt) { if (unlikely(kprobe_ftrace(kp))) { disarm_kprobe_ftrace(kp); @@ -1008,7 +997,7 @@ static void __kprobes disarm_kprobe(struct kprobe *kp, bool reopt) * Aggregate handlers for multiple kprobes support - these handlers * take care of invoking the individual kprobe handlers on p->list */ -static int __kprobes aggr_pre_handler(struct kprobe *p, struct pt_regs *regs) +static int aggr_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct kprobe *kp; @@ -1022,9 +1011,10 @@ static int __kprobes aggr_pre_handler(struct kprobe *p, struct pt_regs *regs) } return 0; } +NOKPROBE_SYMBOL(aggr_pre_handler); -static void __kprobes aggr_post_handler(struct kprobe *p, struct pt_regs *regs, - unsigned long flags) +static void aggr_post_handler(struct kprobe *p, struct pt_regs *regs, + unsigned long flags) { struct kprobe *kp; @@ -1036,9 +1026,10 @@ static void __kprobes aggr_post_handler(struct kprobe *p, struct pt_regs *regs, } } } +NOKPROBE_SYMBOL(aggr_post_handler); -static int __kprobes aggr_fault_handler(struct kprobe *p, struct pt_regs *regs, - int trapnr) +static int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs, + int trapnr) { struct kprobe *cur = __this_cpu_read(kprobe_instance); @@ -1052,8 +1043,9 @@ static int __kprobes aggr_fault_handler(struct kprobe *p, struct pt_regs *regs, } return 0; } +NOKPROBE_SYMBOL(aggr_fault_handler); -static int __kprobes aggr_break_handler(struct kprobe *p, struct pt_regs *regs) +static int aggr_break_handler(struct kprobe *p, struct pt_regs *regs) { struct kprobe *cur = __this_cpu_read(kprobe_instance); int ret = 0; @@ -1065,9 +1057,10 @@ static int __kprobes aggr_break_handler(struct kprobe *p, struct pt_regs *regs) reset_kprobe_instance(); return ret; } +NOKPROBE_SYMBOL(aggr_break_handler); /* Walks the list and increments nmissed count for multiprobe case */ -void __kprobes kprobes_inc_nmissed_count(struct kprobe *p) +void kprobes_inc_nmissed_count(struct kprobe *p) { struct kprobe *kp; if (!kprobe_aggrprobe(p)) { @@ -1078,9 +1071,10 @@ void __kprobes kprobes_inc_nmissed_count(struct kprobe *p) } return; } +NOKPROBE_SYMBOL(kprobes_inc_nmissed_count); -void __kprobes recycle_rp_inst(struct kretprobe_instance *ri, - struct hlist_head *head) +void recycle_rp_inst(struct kretprobe_instance *ri, + struct hlist_head *head) { struct kretprobe *rp = ri->rp; @@ -1095,8 +1089,9 @@ void __kprobes recycle_rp_inst(struct kretprobe_instance *ri, /* Unregistering */ hlist_add_head(&ri->hlist, head); } +NOKPROBE_SYMBOL(recycle_rp_inst); -void __kprobes kretprobe_hash_lock(struct task_struct *tsk, +void kretprobe_hash_lock(struct task_struct *tsk, struct hlist_head **head, unsigned long *flags) __acquires(hlist_lock) { @@ -1107,17 +1102,19 @@ __acquires(hlist_lock) hlist_lock = kretprobe_table_lock_ptr(hash); raw_spin_lock_irqsave(hlist_lock, *flags); } +NOKPROBE_SYMBOL(kretprobe_hash_lock); -static void __kprobes kretprobe_table_lock(unsigned long hash, - unsigned long *flags) +static void kretprobe_table_lock(unsigned long hash, + unsigned long *flags) __acquires(hlist_lock) { raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); raw_spin_lock_irqsave(hlist_lock, *flags); } +NOKPROBE_SYMBOL(kretprobe_table_lock); -void __kprobes kretprobe_hash_unlock(struct task_struct *tsk, - unsigned long *flags) +void kretprobe_hash_unlock(struct task_struct *tsk, + unsigned long *flags) __releases(hlist_lock) { unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS); @@ -1126,14 +1123,16 @@ __releases(hlist_lock) hlist_lock = kretprobe_table_lock_ptr(hash); raw_spin_unlock_irqrestore(hlist_lock, *flags); } +NOKPROBE_SYMBOL(kretprobe_hash_unlock); -static void __kprobes kretprobe_table_unlock(unsigned long hash, - unsigned long *flags) +static void kretprobe_table_unlock(unsigned long hash, + unsigned long *flags) __releases(hlist_lock) { raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); raw_spin_unlock_irqrestore(hlist_lock, *flags); } +NOKPROBE_SYMBOL(kretprobe_table_unlock); /* * This function is called from finish_task_switch when task tk becomes dead, @@ -1141,7 +1140,7 @@ __releases(hlist_lock) * with this task. These left over instances represent probed functions * that have been called but will never return. */ -void __kprobes kprobe_flush_task(struct task_struct *tk) +void kprobe_flush_task(struct task_struct *tk) { struct kretprobe_instance *ri; struct hlist_head *head, empty_rp; @@ -1166,6 +1165,7 @@ void __kprobes kprobe_flush_task(struct task_struct *tk) kfree(ri); } } +NOKPROBE_SYMBOL(kprobe_flush_task); static inline void free_rp_inst(struct kretprobe *rp) { @@ -1178,7 +1178,7 @@ static inline void free_rp_inst(struct kretprobe *rp) } } -static void __kprobes cleanup_rp_inst(struct kretprobe *rp) +static void cleanup_rp_inst(struct kretprobe *rp) { unsigned long flags, hash; struct kretprobe_instance *ri; @@ -1197,12 +1197,13 @@ static void __kprobes cleanup_rp_inst(struct kretprobe *rp) } free_rp_inst(rp); } +NOKPROBE_SYMBOL(cleanup_rp_inst); /* * Add the new probe to ap->list. Fail if this is the * second jprobe at the address - two jprobes can't coexist */ -static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p) +static int add_new_kprobe(struct kprobe *ap, struct kprobe *p) { BUG_ON(kprobe_gone(ap) || kprobe_gone(p)); @@ -1226,7 +1227,7 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p) * Fill in the required fields of the "manager kprobe". Replace the * earlier kprobe in the hlist with the manager kprobe */ -static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p) +static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p) { /* Copy p's insn slot to ap */ copy_kprobe(p, ap); @@ -1252,8 +1253,7 @@ static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p) * This is the second or subsequent kprobe at the address - handle * the intricacies */ -static int __kprobes register_aggr_kprobe(struct kprobe *orig_p, - struct kprobe *p) +static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) { int ret = 0; struct kprobe *ap = orig_p; @@ -1324,25 +1324,29 @@ out: return ret; } -static int __kprobes in_kprobes_functions(unsigned long addr) +bool __weak arch_within_kprobe_blacklist(unsigned long addr) { - struct kprobe_blackpoint *kb; + /* The __kprobes marked functions and entry code must not be probed */ + return addr >= (unsigned long)__kprobes_text_start && + addr < (unsigned long)__kprobes_text_end; +} - if (addr >= (unsigned long)__kprobes_text_start && - addr < (unsigned long)__kprobes_text_end) - return -EINVAL; +static bool within_kprobe_blacklist(unsigned long addr) +{ + struct kprobe_blacklist_entry *ent; + + if (arch_within_kprobe_blacklist(addr)) + return true; /* * If there exists a kprobe_blacklist, verify and * fail any probe registration in the prohibited area */ - for (kb = kprobe_blacklist; kb->name != NULL; kb++) { - if (kb->start_addr) { - if (addr >= kb->start_addr && - addr < (kb->start_addr + kb->range)) - return -EINVAL; - } + list_for_each_entry(ent, &kprobe_blacklist, list) { + if (addr >= ent->start_addr && addr < ent->end_addr) + return true; } - return 0; + + return false; } /* @@ -1351,7 +1355,7 @@ static int __kprobes in_kprobes_functions(unsigned long addr) * This returns encoded errors if it fails to look up symbol or invalid * combination of parameters. */ -static kprobe_opcode_t __kprobes *kprobe_addr(struct kprobe *p) +static kprobe_opcode_t *kprobe_addr(struct kprobe *p) { kprobe_opcode_t *addr = p->addr; @@ -1374,7 +1378,7 @@ invalid: } /* Check passed kprobe is valid and return kprobe in kprobe_table. */ -static struct kprobe * __kprobes __get_valid_kprobe(struct kprobe *p) +static struct kprobe *__get_valid_kprobe(struct kprobe *p) { struct kprobe *ap, *list_p; @@ -1406,8 +1410,8 @@ static inline int check_kprobe_rereg(struct kprobe *p) return ret; } -static __kprobes int check_kprobe_address_safe(struct kprobe *p, - struct module **probed_mod) +static int check_kprobe_address_safe(struct kprobe *p, + struct module **probed_mod) { int ret = 0; unsigned long ftrace_addr; @@ -1433,7 +1437,7 @@ static __kprobes int check_kprobe_address_safe(struct kprobe *p, /* Ensure it is not in reserved area nor out of text */ if (!kernel_text_address((unsigned long) p->addr) || - in_kprobes_functions((unsigned long) p->addr) || + within_kprobe_blacklist((unsigned long) p->addr) || jump_label_text_reserved(p->addr, p->addr)) { ret = -EINVAL; goto out; @@ -1469,7 +1473,7 @@ out: return ret; } -int __kprobes register_kprobe(struct kprobe *p) +int register_kprobe(struct kprobe *p) { int ret; struct kprobe *old_p; @@ -1531,7 +1535,7 @@ out: EXPORT_SYMBOL_GPL(register_kprobe); /* Check if all probes on the aggrprobe are disabled */ -static int __kprobes aggr_kprobe_disabled(struct kprobe *ap) +static int aggr_kprobe_disabled(struct kprobe *ap) { struct kprobe *kp; @@ -1547,7 +1551,7 @@ static int __kprobes aggr_kprobe_disabled(struct kprobe *ap) } /* Disable one kprobe: Make sure called under kprobe_mutex is locked */ -static struct kprobe *__kprobes __disable_kprobe(struct kprobe *p) +static struct kprobe *__disable_kprobe(struct kprobe *p) { struct kprobe *orig_p; @@ -1574,7 +1578,7 @@ static struct kprobe *__kprobes __disable_kprobe(struct kprobe *p) /* * Unregister a kprobe without a scheduler synchronization. */ -static int __kprobes __unregister_kprobe_top(struct kprobe *p) +static int __unregister_kprobe_top(struct kprobe *p) { struct kprobe *ap, *list_p; @@ -1631,7 +1635,7 @@ disarmed: return 0; } -static void __kprobes __unregister_kprobe_bottom(struct kprobe *p) +static void __unregister_kprobe_bottom(struct kprobe *p) { struct kprobe *ap; @@ -1647,7 +1651,7 @@ static void __kprobes __unregister_kprobe_bottom(struct kprobe *p) /* Otherwise, do nothing. */ } -int __kprobes register_kprobes(struct kprobe **kps, int num) +int register_kprobes(struct kprobe **kps, int num) { int i, ret = 0; @@ -1665,13 +1669,13 @@ int __kprobes register_kprobes(struct kprobe **kps, int num) } EXPORT_SYMBOL_GPL(register_kprobes); -void __kprobes unregister_kprobe(struct kprobe *p) +void unregister_kprobe(struct kprobe *p) { unregister_kprobes(&p, 1); } EXPORT_SYMBOL_GPL(unregister_kprobe); -void __kprobes unregister_kprobes(struct kprobe **kps, int num) +void unregister_kprobes(struct kprobe **kps, int num) { int i; @@ -1700,7 +1704,7 @@ unsigned long __weak arch_deref_entry_point(void *entry) return (unsigned long)entry; } -int __kprobes register_jprobes(struct jprobe **jps, int num) +int register_jprobes(struct jprobe **jps, int num) { struct jprobe *jp; int ret = 0, i; @@ -1731,19 +1735,19 @@ int __kprobes register_jprobes(struct jprobe **jps, int num) } EXPORT_SYMBOL_GPL(register_jprobes); -int __kprobes register_jprobe(struct jprobe *jp) +int register_jprobe(struct jprobe *jp) { return register_jprobes(&jp, 1); } EXPORT_SYMBOL_GPL(register_jprobe); -void __kprobes unregister_jprobe(struct jprobe *jp) +void unregister_jprobe(struct jprobe *jp) { unregister_jprobes(&jp, 1); } EXPORT_SYMBOL_GPL(unregister_jprobe); -void __kprobes unregister_jprobes(struct jprobe **jps, int num) +void unregister_jprobes(struct jprobe **jps, int num) { int i; @@ -1768,8 +1772,7 @@ EXPORT_SYMBOL_GPL(unregister_jprobes); * This kprobe pre_handler is registered with every kretprobe. When probe * hits it will set up the return probe. */ -static int __kprobes pre_handler_kretprobe(struct kprobe *p, - struct pt_regs *regs) +static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs) { struct kretprobe *rp = container_of(p, struct kretprobe, kp); unsigned long hash, flags = 0; @@ -1807,8 +1810,9 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p, } return 0; } +NOKPROBE_SYMBOL(pre_handler_kretprobe); -int __kprobes register_kretprobe(struct kretprobe *rp) +int register_kretprobe(struct kretprobe *rp) { int ret = 0; struct kretprobe_instance *inst; @@ -1861,7 +1865,7 @@ int __kprobes register_kretprobe(struct kretprobe *rp) } EXPORT_SYMBOL_GPL(register_kretprobe); -int __kprobes register_kretprobes(struct kretprobe **rps, int num) +int register_kretprobes(struct kretprobe **rps, int num) { int ret = 0, i; @@ -1879,13 +1883,13 @@ int __kprobes register_kretprobes(struct kretprobe **rps, int num) } EXPORT_SYMBOL_GPL(register_kretprobes); -void __kprobes unregister_kretprobe(struct kretprobe *rp) +void unregister_kretprobe(struct kretprobe *rp) { unregister_kretprobes(&rp, 1); } EXPORT_SYMBOL_GPL(unregister_kretprobe); -void __kprobes unregister_kretprobes(struct kretprobe **rps, int num) +void unregister_kretprobes(struct kretprobe **rps, int num) { int i; @@ -1908,38 +1912,38 @@ void __kprobes unregister_kretprobes(struct kretprobe **rps, int num) EXPORT_SYMBOL_GPL(unregister_kretprobes); #else /* CONFIG_KRETPROBES */ -int __kprobes register_kretprobe(struct kretprobe *rp) +int register_kretprobe(struct kretprobe *rp) { return -ENOSYS; } EXPORT_SYMBOL_GPL(register_kretprobe); -int __kprobes register_kretprobes(struct kretprobe **rps, int num) +int register_kretprobes(struct kretprobe **rps, int num) { return -ENOSYS; } EXPORT_SYMBOL_GPL(register_kretprobes); -void __kprobes unregister_kretprobe(struct kretprobe *rp) +void unregister_kretprobe(struct kretprobe *rp) { } EXPORT_SYMBOL_GPL(unregister_kretprobe); -void __kprobes unregister_kretprobes(struct kretprobe **rps, int num) +void unregister_kretprobes(struct kretprobe **rps, int num) { } EXPORT_SYMBOL_GPL(unregister_kretprobes); -static int __kprobes pre_handler_kretprobe(struct kprobe *p, - struct pt_regs *regs) +static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs) { return 0; } +NOKPROBE_SYMBOL(pre_handler_kretprobe); #endif /* CONFIG_KRETPROBES */ /* Set the kprobe gone and remove its instruction buffer. */ -static void __kprobes kill_kprobe(struct kprobe *p) +static void kill_kprobe(struct kprobe *p) { struct kprobe *kp; @@ -1963,7 +1967,7 @@ static void __kprobes kill_kprobe(struct kprobe *p) } /* Disable one kprobe */ -int __kprobes disable_kprobe(struct kprobe *kp) +int disable_kprobe(struct kprobe *kp) { int ret = 0; @@ -1979,7 +1983,7 @@ int __kprobes disable_kprobe(struct kprobe *kp) EXPORT_SYMBOL_GPL(disable_kprobe); /* Enable one kprobe */ -int __kprobes enable_kprobe(struct kprobe *kp) +int enable_kprobe(struct kprobe *kp) { int ret = 0; struct kprobe *p; @@ -2012,16 +2016,49 @@ out: } EXPORT_SYMBOL_GPL(enable_kprobe); -void __kprobes dump_kprobe(struct kprobe *kp) +void dump_kprobe(struct kprobe *kp) { printk(KERN_WARNING "Dumping kprobe:\n"); printk(KERN_WARNING "Name: %s\nAddress: %p\nOffset: %x\n", kp->symbol_name, kp->addr, kp->offset); } +NOKPROBE_SYMBOL(dump_kprobe); + +/* + * Lookup and populate the kprobe_blacklist. + * + * Unlike the kretprobe blacklist, we'll need to determine + * the range of addresses that belong to the said functions, + * since a kprobe need not necessarily be at the beginning + * of a function. + */ +static int __init populate_kprobe_blacklist(unsigned long *start, + unsigned long *end) +{ + unsigned long *iter; + struct kprobe_blacklist_entry *ent; + unsigned long offset = 0, size = 0; + + for (iter = start; iter < end; iter++) { + if (!kallsyms_lookup_size_offset(*iter, &size, &offset)) { + pr_err("Failed to find blacklist %p\n", (void *)*iter); + continue; + } + + ent = kmalloc(sizeof(*ent), GFP_KERNEL); + if (!ent) + return -ENOMEM; + ent->start_addr = *iter; + ent->end_addr = *iter + size; + INIT_LIST_HEAD(&ent->list); + list_add_tail(&ent->list, &kprobe_blacklist); + } + return 0; +} /* Module notifier call back, checking kprobes on the module */ -static int __kprobes kprobes_module_callback(struct notifier_block *nb, - unsigned long val, void *data) +static int kprobes_module_callback(struct notifier_block *nb, + unsigned long val, void *data) { struct module *mod = data; struct hlist_head *head; @@ -2062,14 +2099,13 @@ static struct notifier_block kprobe_module_nb = { .priority = 0 }; +/* Markers of _kprobe_blacklist section */ +extern unsigned long __start_kprobe_blacklist[]; +extern unsigned long __stop_kprobe_blacklist[]; + static int __init init_kprobes(void) { int i, err = 0; - unsigned long offset = 0, size = 0; - char *modname, namebuf[KSYM_NAME_LEN]; - const char *symbol_name; - void *addr; - struct kprobe_blackpoint *kb; /* FIXME allocate the probe table, currently defined statically */ /* initialize all list heads */ @@ -2079,26 +2115,11 @@ static int __init init_kprobes(void) raw_spin_lock_init(&(kretprobe_table_locks[i].lock)); } - /* - * Lookup and populate the kprobe_blacklist. - * - * Unlike the kretprobe blacklist, we'll need to determine - * the range of addresses that belong to the said functions, - * since a kprobe need not necessarily be at the beginning - * of a function. - */ - for (kb = kprobe_blacklist; kb->name != NULL; kb++) { - kprobe_lookup_name(kb->name, addr); - if (!addr) - continue; - - kb->start_addr = (unsigned long)addr; - symbol_name = kallsyms_lookup(kb->start_addr, - &size, &offset, &modname, namebuf); - if (!symbol_name) - kb->range = 0; - else - kb->range = size; + err = populate_kprobe_blacklist(__start_kprobe_blacklist, + __stop_kprobe_blacklist); + if (err) { + pr_err("kprobes: failed to populate blacklist: %d\n", err); + pr_err("Please take care of using kprobes.\n"); } if (kretprobe_blacklist_size) { @@ -2138,7 +2159,7 @@ static int __init init_kprobes(void) } #ifdef CONFIG_DEBUG_FS -static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p, +static void report_probe(struct seq_file *pi, struct kprobe *p, const char *sym, int offset, char *modname, struct kprobe *pp) { char *kprobe_type; @@ -2167,12 +2188,12 @@ static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p, (kprobe_ftrace(pp) ? "[FTRACE]" : "")); } -static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos) +static void *kprobe_seq_start(struct seq_file *f, loff_t *pos) { return (*pos < KPROBE_TABLE_SIZE) ? pos : NULL; } -static void __kprobes *kprobe_seq_next(struct seq_file *f, void *v, loff_t *pos) +static void *kprobe_seq_next(struct seq_file *f, void *v, loff_t *pos) { (*pos)++; if (*pos >= KPROBE_TABLE_SIZE) @@ -2180,12 +2201,12 @@ static void __kprobes *kprobe_seq_next(struct seq_file *f, void *v, loff_t *pos) return pos; } -static void __kprobes kprobe_seq_stop(struct seq_file *f, void *v) +static void kprobe_seq_stop(struct seq_file *f, void *v) { /* Nothing to do */ } -static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v) +static int show_kprobe_addr(struct seq_file *pi, void *v) { struct hlist_head *head; struct kprobe *p, *kp; @@ -2216,7 +2237,7 @@ static const struct seq_operations kprobes_seq_ops = { .show = show_kprobe_addr }; -static int __kprobes kprobes_open(struct inode *inode, struct file *filp) +static int kprobes_open(struct inode *inode, struct file *filp) { return seq_open(filp, &kprobes_seq_ops); } @@ -2228,7 +2249,47 @@ static const struct file_operations debugfs_kprobes_operations = { .release = seq_release, }; -static void __kprobes arm_all_kprobes(void) +/* kprobes/blacklist -- shows which functions can not be probed */ +static void *kprobe_blacklist_seq_start(struct seq_file *m, loff_t *pos) +{ + return seq_list_start(&kprobe_blacklist, *pos); +} + +static void *kprobe_blacklist_seq_next(struct seq_file *m, void *v, loff_t *pos) +{ + return seq_list_next(v, &kprobe_blacklist, pos); +} + +static int kprobe_blacklist_seq_show(struct seq_file *m, void *v) +{ + struct kprobe_blacklist_entry *ent = + list_entry(v, struct kprobe_blacklist_entry, list); + + seq_printf(m, "0x%p-0x%p\t%ps\n", (void *)ent->start_addr, + (void *)ent->end_addr, (void *)ent->start_addr); + return 0; +} + +static const struct seq_operations kprobe_blacklist_seq_ops = { + .start = kprobe_blacklist_seq_start, + .next = kprobe_blacklist_seq_next, + .stop = kprobe_seq_stop, /* Reuse void function */ + .show = kprobe_blacklist_seq_show, +}; + +static int kprobe_blacklist_open(struct inode *inode, struct file *filp) +{ + return seq_open(filp, &kprobe_blacklist_seq_ops); +} + +static const struct file_operations debugfs_kprobe_blacklist_ops = { + .open = kprobe_blacklist_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static void arm_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; @@ -2256,7 +2317,7 @@ already_enabled: return; } -static void __kprobes disarm_all_kprobes(void) +static void disarm_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; @@ -2340,7 +2401,7 @@ static const struct file_operations fops_kp = { .llseek = default_llseek, }; -static int __kprobes debugfs_kprobe_init(void) +static int __init debugfs_kprobe_init(void) { struct dentry *dir, *file; unsigned int value = 1; @@ -2351,19 +2412,24 @@ static int __kprobes debugfs_kprobe_init(void) file = debugfs_create_file("list", 0444, dir, NULL, &debugfs_kprobes_operations); - if (!file) { - debugfs_remove(dir); - return -ENOMEM; - } + if (!file) + goto error; file = debugfs_create_file("enabled", 0600, dir, &value, &fops_kp); - if (!file) { - debugfs_remove(dir); - return -ENOMEM; - } + if (!file) + goto error; + + file = debugfs_create_file("blacklist", 0444, dir, NULL, + &debugfs_kprobe_blacklist_ops); + if (!file) + goto error; return 0; + +error: + debugfs_remove(dir); + return -ENOMEM; } late_initcall(debugfs_kprobe_init); diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index b8bdcd4785b..8541bfdfd23 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -24,4 +24,5 @@ obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o +obj-$(CONFIG_QUEUE_RWLOCK) += qrwlock.o obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c new file mode 100644 index 00000000000..fb5b8ac411a --- /dev/null +++ b/kernel/locking/qrwlock.c @@ -0,0 +1,133 @@ +/* + * Queue read/write lock + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * (C) Copyright 2013-2014 Hewlett-Packard Development Company, L.P. + * + * Authors: Waiman Long <waiman.long@hp.com> + */ +#include <linux/smp.h> +#include <linux/bug.h> +#include <linux/cpumask.h> +#include <linux/percpu.h> +#include <linux/hardirq.h> +#include <linux/mutex.h> +#include <asm/qrwlock.h> + +/** + * rspin_until_writer_unlock - inc reader count & spin until writer is gone + * @lock : Pointer to queue rwlock structure + * @writer: Current queue rwlock writer status byte + * + * In interrupt context or at the head of the queue, the reader will just + * increment the reader count & wait until the writer releases the lock. + */ +static __always_inline void +rspin_until_writer_unlock(struct qrwlock *lock, u32 cnts) +{ + while ((cnts & _QW_WMASK) == _QW_LOCKED) { + arch_mutex_cpu_relax(); + cnts = smp_load_acquire((u32 *)&lock->cnts); + } +} + +/** + * queue_read_lock_slowpath - acquire read lock of a queue rwlock + * @lock: Pointer to queue rwlock structure + */ +void queue_read_lock_slowpath(struct qrwlock *lock) +{ + u32 cnts; + + /* + * Readers come here when they cannot get the lock without waiting + */ + if (unlikely(in_interrupt())) { + /* + * Readers in interrupt context will spin until the lock is + * available without waiting in the queue. + */ + cnts = smp_load_acquire((u32 *)&lock->cnts); + rspin_until_writer_unlock(lock, cnts); + return; + } + atomic_sub(_QR_BIAS, &lock->cnts); + + /* + * Put the reader into the wait queue + */ + arch_spin_lock(&lock->lock); + + /* + * At the head of the wait queue now, wait until the writer state + * goes to 0 and then try to increment the reader count and get + * the lock. It is possible that an incoming writer may steal the + * lock in the interim, so it is necessary to check the writer byte + * to make sure that the write lock isn't taken. + */ + while (atomic_read(&lock->cnts) & _QW_WMASK) + arch_mutex_cpu_relax(); + + cnts = atomic_add_return(_QR_BIAS, &lock->cnts) - _QR_BIAS; + rspin_until_writer_unlock(lock, cnts); + + /* + * Signal the next one in queue to become queue head + */ + arch_spin_unlock(&lock->lock); +} +EXPORT_SYMBOL(queue_read_lock_slowpath); + +/** + * queue_write_lock_slowpath - acquire write lock of a queue rwlock + * @lock : Pointer to queue rwlock structure + */ +void queue_write_lock_slowpath(struct qrwlock *lock) +{ + u32 cnts; + + /* Put the writer into the wait queue */ + arch_spin_lock(&lock->lock); + + /* Try to acquire the lock directly if no reader is present */ + if (!atomic_read(&lock->cnts) && + (atomic_cmpxchg(&lock->cnts, 0, _QW_LOCKED) == 0)) + goto unlock; + + /* + * Set the waiting flag to notify readers that a writer is pending, + * or wait for a previous writer to go away. + */ + for (;;) { + cnts = atomic_read(&lock->cnts); + if (!(cnts & _QW_WMASK) && + (atomic_cmpxchg(&lock->cnts, cnts, + cnts | _QW_WAITING) == cnts)) + break; + + arch_mutex_cpu_relax(); + } + + /* When no more readers, set the locked flag */ + for (;;) { + cnts = atomic_read(&lock->cnts); + if ((cnts == _QW_WAITING) && + (atomic_cmpxchg(&lock->cnts, _QW_WAITING, + _QW_LOCKED) == _QW_WAITING)) + break; + + arch_mutex_cpu_relax(); + } +unlock: + arch_spin_unlock(&lock->lock); +} +EXPORT_SYMBOL(queue_write_lock_slowpath); diff --git a/kernel/locking/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h index 14193d596d7..ab29b6a2266 100644 --- a/kernel/locking/rtmutex-debug.h +++ b/kernel/locking/rtmutex-debug.h @@ -31,3 +31,8 @@ static inline int debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter, { return (waiter != NULL); } + +static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w) +{ + debug_rt_mutex_print_deadlock(w); +} diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index a620d4d08ca..fc605941b9b 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -83,6 +83,47 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) owner = *p; } while (cmpxchg(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner); } + +/* + * Safe fastpath aware unlock: + * 1) Clear the waiters bit + * 2) Drop lock->wait_lock + * 3) Try to unlock the lock with cmpxchg + */ +static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock) + __releases(lock->wait_lock) +{ + struct task_struct *owner = rt_mutex_owner(lock); + + clear_rt_mutex_waiters(lock); + raw_spin_unlock(&lock->wait_lock); + /* + * If a new waiter comes in between the unlock and the cmpxchg + * we have two situations: + * + * unlock(wait_lock); + * lock(wait_lock); + * cmpxchg(p, owner, 0) == owner + * mark_rt_mutex_waiters(lock); + * acquire(lock); + * or: + * + * unlock(wait_lock); + * lock(wait_lock); + * mark_rt_mutex_waiters(lock); + * + * cmpxchg(p, owner, 0) != owner + * enqueue_waiter(); + * unlock(wait_lock); + * lock(wait_lock); + * wake waiter(); + * unlock(wait_lock); + * lock(wait_lock); + * acquire(lock); + */ + return rt_mutex_cmpxchg(lock, owner, NULL); +} + #else # define rt_mutex_cmpxchg(l,c,n) (0) static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) @@ -90,6 +131,17 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) lock->owner = (struct task_struct *) ((unsigned long)lock->owner | RT_MUTEX_HAS_WAITERS); } + +/* + * Simple slow path only version: lock->owner is protected by lock->wait_lock. + */ +static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock) + __releases(lock->wait_lock) +{ + lock->owner = NULL; + raw_spin_unlock(&lock->wait_lock); + return true; +} #endif static inline int @@ -260,27 +312,36 @@ static void rt_mutex_adjust_prio(struct task_struct *task) */ int max_lock_depth = 1024; +static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p) +{ + return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL; +} + /* * Adjust the priority chain. Also used for deadlock detection. * Decreases task's usage by one - may thus free the task. * - * @task: the task owning the mutex (owner) for which a chain walk is probably - * needed + * @task: the task owning the mutex (owner) for which a chain walk is + * probably needed * @deadlock_detect: do we have to carry out deadlock detection? - * @orig_lock: the mutex (can be NULL if we are walking the chain to recheck - * things for a task that has just got its priority adjusted, and - * is waiting on a mutex) + * @orig_lock: the mutex (can be NULL if we are walking the chain to recheck + * things for a task that has just got its priority adjusted, and + * is waiting on a mutex) + * @next_lock: the mutex on which the owner of @orig_lock was blocked before + * we dropped its pi_lock. Is never dereferenced, only used for + * comparison to detect lock chain changes. * @orig_waiter: rt_mutex_waiter struct for the task that has just donated - * its priority to the mutex owner (can be NULL in the case - * depicted above or if the top waiter is gone away and we are - * actually deboosting the owner) - * @top_task: the current top waiter + * its priority to the mutex owner (can be NULL in the case + * depicted above or if the top waiter is gone away and we are + * actually deboosting the owner) + * @top_task: the current top waiter * * Returns 0 or -EDEADLK. */ static int rt_mutex_adjust_prio_chain(struct task_struct *task, int deadlock_detect, struct rt_mutex *orig_lock, + struct rt_mutex *next_lock, struct rt_mutex_waiter *orig_waiter, struct task_struct *top_task) { @@ -314,7 +375,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, } put_task_struct(task); - return deadlock_detect ? -EDEADLK : 0; + return -EDEADLK; } retry: /* @@ -339,6 +400,18 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, goto out_unlock_pi; /* + * We dropped all locks after taking a refcount on @task, so + * the task might have moved on in the lock chain or even left + * the chain completely and blocks now on an unrelated lock or + * on @orig_lock. + * + * We stored the lock on which @task was blocked in @next_lock, + * so we can detect the chain change. + */ + if (next_lock != waiter->lock) + goto out_unlock_pi; + + /* * Drop out, when the task has no waiters. Note, * top_waiter can be NULL, when we are in the deboosting * mode! @@ -377,7 +450,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, if (lock == orig_lock || rt_mutex_owner(lock) == top_task) { debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock); raw_spin_unlock(&lock->wait_lock); - ret = deadlock_detect ? -EDEADLK : 0; + ret = -EDEADLK; goto out_unlock_pi; } @@ -422,11 +495,26 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, __rt_mutex_adjust_prio(task); } + /* + * Check whether the task which owns the current lock is pi + * blocked itself. If yes we store a pointer to the lock for + * the lock chain change detection above. After we dropped + * task->pi_lock next_lock cannot be dereferenced anymore. + */ + next_lock = task_blocked_on_lock(task); + raw_spin_unlock_irqrestore(&task->pi_lock, flags); top_waiter = rt_mutex_top_waiter(lock); raw_spin_unlock(&lock->wait_lock); + /* + * We reached the end of the lock chain. Stop right here. No + * point to go back just to figure that out. + */ + if (!next_lock) + goto out_put_task; + if (!detect_deadlock && waiter != top_waiter) goto out_put_task; @@ -536,8 +624,9 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, { struct task_struct *owner = rt_mutex_owner(lock); struct rt_mutex_waiter *top_waiter = waiter; - unsigned long flags; + struct rt_mutex *next_lock; int chain_walk = 0, res; + unsigned long flags; /* * Early deadlock detection. We really don't want the task to @@ -548,7 +637,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, * which is wrong, as the other waiter is not in a deadlock * situation. */ - if (detect_deadlock && owner == task) + if (owner == task) return -EDEADLK; raw_spin_lock_irqsave(&task->pi_lock, flags); @@ -569,20 +658,28 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, if (!owner) return 0; + raw_spin_lock_irqsave(&owner->pi_lock, flags); if (waiter == rt_mutex_top_waiter(lock)) { - raw_spin_lock_irqsave(&owner->pi_lock, flags); rt_mutex_dequeue_pi(owner, top_waiter); rt_mutex_enqueue_pi(owner, waiter); __rt_mutex_adjust_prio(owner); if (owner->pi_blocked_on) chain_walk = 1; - raw_spin_unlock_irqrestore(&owner->pi_lock, flags); - } - else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock)) + } else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock)) { chain_walk = 1; + } - if (!chain_walk) + /* Store the lock on which owner is blocked or NULL */ + next_lock = task_blocked_on_lock(owner); + + raw_spin_unlock_irqrestore(&owner->pi_lock, flags); + /* + * Even if full deadlock detection is on, if the owner is not + * blocked itself, we can avoid finding this out in the chain + * walk. + */ + if (!chain_walk || !next_lock) return 0; /* @@ -594,8 +691,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, raw_spin_unlock(&lock->wait_lock); - res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter, - task); + res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, + next_lock, waiter, task); raw_spin_lock(&lock->wait_lock); @@ -605,7 +702,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, /* * Wake up the next waiter on the lock. * - * Remove the top waiter from the current tasks waiter list and wake it up. + * Remove the top waiter from the current tasks pi waiter list and + * wake it up. * * Called with lock->wait_lock held. */ @@ -626,10 +724,23 @@ static void wakeup_next_waiter(struct rt_mutex *lock) */ rt_mutex_dequeue_pi(current, waiter); - rt_mutex_set_owner(lock, NULL); + /* + * As we are waking up the top waiter, and the waiter stays + * queued on the lock until it gets the lock, this lock + * obviously has waiters. Just set the bit here and this has + * the added benefit of forcing all new tasks into the + * slow path making sure no task of lower priority than + * the top waiter can steal this lock. + */ + lock->owner = (void *) RT_MUTEX_HAS_WAITERS; raw_spin_unlock_irqrestore(¤t->pi_lock, flags); + /* + * It's safe to dereference waiter as it cannot go away as + * long as we hold lock->wait_lock. The waiter task needs to + * acquire it in order to dequeue the waiter. + */ wake_up_process(waiter->task); } @@ -644,8 +755,8 @@ static void remove_waiter(struct rt_mutex *lock, { int first = (waiter == rt_mutex_top_waiter(lock)); struct task_struct *owner = rt_mutex_owner(lock); + struct rt_mutex *next_lock = NULL; unsigned long flags; - int chain_walk = 0; raw_spin_lock_irqsave(¤t->pi_lock, flags); rt_mutex_dequeue(lock, waiter); @@ -669,13 +780,13 @@ static void remove_waiter(struct rt_mutex *lock, } __rt_mutex_adjust_prio(owner); - if (owner->pi_blocked_on) - chain_walk = 1; + /* Store the lock on which owner is blocked or NULL */ + next_lock = task_blocked_on_lock(owner); raw_spin_unlock_irqrestore(&owner->pi_lock, flags); } - if (!chain_walk) + if (!next_lock) return; /* gets dropped in rt_mutex_adjust_prio_chain()! */ @@ -683,7 +794,7 @@ static void remove_waiter(struct rt_mutex *lock, raw_spin_unlock(&lock->wait_lock); - rt_mutex_adjust_prio_chain(owner, 0, lock, NULL, current); + rt_mutex_adjust_prio_chain(owner, 0, lock, next_lock, NULL, current); raw_spin_lock(&lock->wait_lock); } @@ -696,6 +807,7 @@ static void remove_waiter(struct rt_mutex *lock, void rt_mutex_adjust_pi(struct task_struct *task) { struct rt_mutex_waiter *waiter; + struct rt_mutex *next_lock; unsigned long flags; raw_spin_lock_irqsave(&task->pi_lock, flags); @@ -706,12 +818,13 @@ void rt_mutex_adjust_pi(struct task_struct *task) raw_spin_unlock_irqrestore(&task->pi_lock, flags); return; } - + next_lock = waiter->lock; raw_spin_unlock_irqrestore(&task->pi_lock, flags); /* gets dropped in rt_mutex_adjust_prio_chain()! */ get_task_struct(task); - rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task); + + rt_mutex_adjust_prio_chain(task, 0, NULL, next_lock, NULL, task); } /** @@ -763,6 +876,26 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state, return ret; } +static void rt_mutex_handle_deadlock(int res, int detect_deadlock, + struct rt_mutex_waiter *w) +{ + /* + * If the result is not -EDEADLOCK or the caller requested + * deadlock detection, nothing to do here. + */ + if (res != -EDEADLOCK || detect_deadlock) + return; + + /* + * Yell lowdly and stop the task right here. + */ + rt_mutex_print_deadlock(w); + while (1) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + } +} + /* * Slow path lock function: */ @@ -802,8 +935,10 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, set_current_state(TASK_RUNNING); - if (unlikely(ret)) + if (unlikely(ret)) { remove_waiter(lock, &waiter); + rt_mutex_handle_deadlock(ret, detect_deadlock, &waiter); + } /* * try_to_take_rt_mutex() sets the waiter bit @@ -859,12 +994,49 @@ rt_mutex_slowunlock(struct rt_mutex *lock) rt_mutex_deadlock_account_unlock(current); - if (!rt_mutex_has_waiters(lock)) { - lock->owner = NULL; - raw_spin_unlock(&lock->wait_lock); - return; + /* + * We must be careful here if the fast path is enabled. If we + * have no waiters queued we cannot set owner to NULL here + * because of: + * + * foo->lock->owner = NULL; + * rtmutex_lock(foo->lock); <- fast path + * free = atomic_dec_and_test(foo->refcnt); + * rtmutex_unlock(foo->lock); <- fast path + * if (free) + * kfree(foo); + * raw_spin_unlock(foo->lock->wait_lock); + * + * So for the fastpath enabled kernel: + * + * Nothing can set the waiters bit as long as we hold + * lock->wait_lock. So we do the following sequence: + * + * owner = rt_mutex_owner(lock); + * clear_rt_mutex_waiters(lock); + * raw_spin_unlock(&lock->wait_lock); + * if (cmpxchg(&lock->owner, owner, 0) == owner) + * return; + * goto retry; + * + * The fastpath disabled variant is simple as all access to + * lock->owner is serialized by lock->wait_lock: + * + * lock->owner = NULL; + * raw_spin_unlock(&lock->wait_lock); + */ + while (!rt_mutex_has_waiters(lock)) { + /* Drops lock->wait_lock ! */ + if (unlock_rt_mutex_safe(lock) == true) + return; + /* Relock the rtmutex and try again */ + raw_spin_lock(&lock->wait_lock); } + /* + * The wakeup next waiter path does not suffer from the above + * race. See the comments there. + */ wakeup_next_waiter(lock); raw_spin_unlock(&lock->wait_lock); @@ -1112,7 +1284,8 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, return 1; } - ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock); + /* We enforce deadlock detection for futexes */ + ret = task_blocks_on_rt_mutex(lock, waiter, task, 1); if (ret && !rt_mutex_owner(lock)) { /* diff --git a/kernel/locking/rtmutex.h b/kernel/locking/rtmutex.h index a1a1dd06421..f6a1f3c133b 100644 --- a/kernel/locking/rtmutex.h +++ b/kernel/locking/rtmutex.h @@ -24,3 +24,8 @@ #define debug_rt_mutex_print_deadlock(w) do { } while (0) #define debug_rt_mutex_detect_deadlock(w,d) (d) #define debug_rt_mutex_reset_waiter(w) do { } while (0) + +static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w) +{ + WARN(1, "rtmutex deadlock detected\n"); +} diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index b4219ff87b8..dacc32142fc 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -5,11 +5,17 @@ * * Writer lock-stealing by Alex Shi <alex.shi@intel.com> * and Michel Lespinasse <walken@google.com> + * + * Optimistic spinning by Tim Chen <tim.c.chen@intel.com> + * and Davidlohr Bueso <davidlohr@hp.com>. Based on mutexes. */ #include <linux/rwsem.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/export.h> +#include <linux/sched/rt.h> + +#include "mcs_spinlock.h" /* * Guide to the rw_semaphore's count field for common values. @@ -76,6 +82,10 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name, sem->count = RWSEM_UNLOCKED_VALUE; raw_spin_lock_init(&sem->wait_lock); INIT_LIST_HEAD(&sem->wait_list); +#ifdef CONFIG_SMP + sem->owner = NULL; + sem->osq = NULL; +#endif } EXPORT_SYMBOL(__init_rwsem); @@ -190,7 +200,7 @@ __rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type) } /* - * wait for the read lock to be granted + * Wait for the read lock to be granted */ __visible struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) @@ -237,64 +247,221 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) return sem; } +static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem) +{ + if (!(count & RWSEM_ACTIVE_MASK)) { + /* try acquiring the write lock */ + if (sem->count == RWSEM_WAITING_BIAS && + cmpxchg(&sem->count, RWSEM_WAITING_BIAS, + RWSEM_ACTIVE_WRITE_BIAS) == RWSEM_WAITING_BIAS) { + if (!list_is_singular(&sem->wait_list)) + rwsem_atomic_update(RWSEM_WAITING_BIAS, sem); + return true; + } + } + return false; +} + +#ifdef CONFIG_SMP /* - * wait until we successfully acquire the write lock + * Try to acquire write lock before the writer has been put on wait queue. + */ +static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem) +{ + long old, count = ACCESS_ONCE(sem->count); + + while (true) { + if (!(count == 0 || count == RWSEM_WAITING_BIAS)) + return false; + + old = cmpxchg(&sem->count, count, count + RWSEM_ACTIVE_WRITE_BIAS); + if (old == count) + return true; + + count = old; + } +} + +static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem) +{ + struct task_struct *owner; + bool on_cpu = true; + + if (need_resched()) + return 0; + + rcu_read_lock(); + owner = ACCESS_ONCE(sem->owner); + if (owner) + on_cpu = owner->on_cpu; + rcu_read_unlock(); + + /* + * If sem->owner is not set, the rwsem owner may have + * just acquired it and not set the owner yet or the rwsem + * has been released. + */ + return on_cpu; +} + +static inline bool owner_running(struct rw_semaphore *sem, + struct task_struct *owner) +{ + if (sem->owner != owner) + return false; + + /* + * Ensure we emit the owner->on_cpu, dereference _after_ checking + * sem->owner still matches owner, if that fails, owner might + * point to free()d memory, if it still matches, the rcu_read_lock() + * ensures the memory stays valid. + */ + barrier(); + + return owner->on_cpu; +} + +static noinline +bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner) +{ + rcu_read_lock(); + while (owner_running(sem, owner)) { + if (need_resched()) + break; + + arch_mutex_cpu_relax(); + } + rcu_read_unlock(); + + /* + * We break out the loop above on need_resched() or when the + * owner changed, which is a sign for heavy contention. Return + * success only when sem->owner is NULL. + */ + return sem->owner == NULL; +} + +static bool rwsem_optimistic_spin(struct rw_semaphore *sem) +{ + struct task_struct *owner; + bool taken = false; + + preempt_disable(); + + /* sem->wait_lock should not be held when doing optimistic spinning */ + if (!rwsem_can_spin_on_owner(sem)) + goto done; + + if (!osq_lock(&sem->osq)) + goto done; + + while (true) { + owner = ACCESS_ONCE(sem->owner); + if (owner && !rwsem_spin_on_owner(sem, owner)) + break; + + /* wait_lock will be acquired if write_lock is obtained */ + if (rwsem_try_write_lock_unqueued(sem)) { + taken = true; + break; + } + + /* + * When there's no owner, we might have preempted between the + * owner acquiring the lock and setting the owner field. If + * we're an RT task that will live-lock because we won't let + * the owner complete. + */ + if (!owner && (need_resched() || rt_task(current))) + break; + + /* + * The cpu_relax() call is a compiler barrier which forces + * everything in this loop to be re-loaded. We don't need + * memory barriers as we'll eventually observe the right + * values at the cost of a few extra spins. + */ + arch_mutex_cpu_relax(); + } + osq_unlock(&sem->osq); +done: + preempt_enable(); + return taken; +} + +#else +static bool rwsem_optimistic_spin(struct rw_semaphore *sem) +{ + return false; +} +#endif + +/* + * Wait until we successfully acquire the write lock */ __visible struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) { - long count, adjustment = -RWSEM_ACTIVE_WRITE_BIAS; + long count; + bool waiting = true; /* any queued threads before us */ struct rwsem_waiter waiter; - struct task_struct *tsk = current; - /* set up my own style of waitqueue */ - waiter.task = tsk; + /* undo write bias from down_write operation, stop active locking */ + count = rwsem_atomic_update(-RWSEM_ACTIVE_WRITE_BIAS, sem); + + /* do optimistic spinning and steal lock if possible */ + if (rwsem_optimistic_spin(sem)) + return sem; + + /* + * Optimistic spinning failed, proceed to the slowpath + * and block until we can acquire the sem. + */ + waiter.task = current; waiter.type = RWSEM_WAITING_FOR_WRITE; raw_spin_lock_irq(&sem->wait_lock); + + /* account for this before adding a new element to the list */ if (list_empty(&sem->wait_list)) - adjustment += RWSEM_WAITING_BIAS; + waiting = false; + list_add_tail(&waiter.list, &sem->wait_list); /* we're now waiting on the lock, but no longer actively locking */ - count = rwsem_atomic_update(adjustment, sem); + if (waiting) { + count = ACCESS_ONCE(sem->count); - /* If there were already threads queued before us and there are no - * active writers, the lock must be read owned; so we try to wake - * any read locks that were queued ahead of us. */ - if (count > RWSEM_WAITING_BIAS && - adjustment == -RWSEM_ACTIVE_WRITE_BIAS) - sem = __rwsem_do_wake(sem, RWSEM_WAKE_READERS); + /* + * If there were already threads queued before us and there are + * no active writers, the lock must be read owned; so we try to + * wake any read locks that were queued ahead of us. + */ + if (count > RWSEM_WAITING_BIAS) + sem = __rwsem_do_wake(sem, RWSEM_WAKE_READERS); + + } else + count = rwsem_atomic_update(RWSEM_WAITING_BIAS, sem); /* wait until we successfully acquire the lock */ - set_task_state(tsk, TASK_UNINTERRUPTIBLE); + set_current_state(TASK_UNINTERRUPTIBLE); while (true) { - if (!(count & RWSEM_ACTIVE_MASK)) { - /* Try acquiring the write lock. */ - count = RWSEM_ACTIVE_WRITE_BIAS; - if (!list_is_singular(&sem->wait_list)) - count += RWSEM_WAITING_BIAS; - - if (sem->count == RWSEM_WAITING_BIAS && - cmpxchg(&sem->count, RWSEM_WAITING_BIAS, count) == - RWSEM_WAITING_BIAS) - break; - } - + if (rwsem_try_write_lock(count, sem)) + break; raw_spin_unlock_irq(&sem->wait_lock); /* Block until there are no active lockers. */ do { schedule(); - set_task_state(tsk, TASK_UNINTERRUPTIBLE); + set_current_state(TASK_UNINTERRUPTIBLE); } while ((count = sem->count) & RWSEM_ACTIVE_MASK); raw_spin_lock_irq(&sem->wait_lock); } + __set_current_state(TASK_RUNNING); list_del(&waiter.list); raw_spin_unlock_irq(&sem->wait_lock); - tsk->state = TASK_RUNNING; return sem; } diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index cfff1435bdf..42f806de49d 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -12,6 +12,27 @@ #include <linux/atomic.h> +#if defined(CONFIG_SMP) && defined(CONFIG_RWSEM_XCHGADD_ALGORITHM) +static inline void rwsem_set_owner(struct rw_semaphore *sem) +{ + sem->owner = current; +} + +static inline void rwsem_clear_owner(struct rw_semaphore *sem) +{ + sem->owner = NULL; +} + +#else +static inline void rwsem_set_owner(struct rw_semaphore *sem) +{ +} + +static inline void rwsem_clear_owner(struct rw_semaphore *sem) +{ +} +#endif + /* * lock for reading */ @@ -48,6 +69,7 @@ void __sched down_write(struct rw_semaphore *sem) rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_); LOCK_CONTENDED(sem, __down_write_trylock, __down_write); + rwsem_set_owner(sem); } EXPORT_SYMBOL(down_write); @@ -59,8 +81,11 @@ int down_write_trylock(struct rw_semaphore *sem) { int ret = __down_write_trylock(sem); - if (ret == 1) + if (ret == 1) { rwsem_acquire(&sem->dep_map, 0, 1, _RET_IP_); + rwsem_set_owner(sem); + } + return ret; } @@ -85,6 +110,7 @@ void up_write(struct rw_semaphore *sem) { rwsem_release(&sem->dep_map, 1, _RET_IP_); + rwsem_clear_owner(sem); __up_write(sem); } @@ -99,6 +125,7 @@ void downgrade_write(struct rw_semaphore *sem) * lockdep: a downgraded write will live on as a write * dependency. */ + rwsem_clear_owner(sem); __downgrade_write(sem); } @@ -122,6 +149,7 @@ void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest) rwsem_acquire_nest(&sem->dep_map, 0, 0, nest, _RET_IP_); LOCK_CONTENDED(sem, __down_write_trylock, __down_write); + rwsem_set_owner(sem); } EXPORT_SYMBOL(_down_write_nest_lock); @@ -141,6 +169,7 @@ void down_write_nested(struct rw_semaphore *sem, int subclass) rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_); LOCK_CONTENDED(sem, __down_write_trylock, __down_write); + rwsem_set_owner(sem); } EXPORT_SYMBOL(down_write_nested); diff --git a/kernel/notifier.c b/kernel/notifier.c index db4c8b08a50..4803da6eab6 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -71,9 +71,9 @@ static int notifier_chain_unregister(struct notifier_block **nl, * @returns: notifier_call_chain returns the value returned by the * last notifier function called. */ -static int __kprobes notifier_call_chain(struct notifier_block **nl, - unsigned long val, void *v, - int nr_to_call, int *nr_calls) +static int notifier_call_chain(struct notifier_block **nl, + unsigned long val, void *v, + int nr_to_call, int *nr_calls) { int ret = NOTIFY_DONE; struct notifier_block *nb, *next_nb; @@ -102,6 +102,7 @@ static int __kprobes notifier_call_chain(struct notifier_block **nl, } return ret; } +NOKPROBE_SYMBOL(notifier_call_chain); /* * Atomic notifier chain routines. Registration and unregistration @@ -172,9 +173,9 @@ EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister); * Otherwise the return value is the return value * of the last notifier function called. */ -int __kprobes __atomic_notifier_call_chain(struct atomic_notifier_head *nh, - unsigned long val, void *v, - int nr_to_call, int *nr_calls) +int __atomic_notifier_call_chain(struct atomic_notifier_head *nh, + unsigned long val, void *v, + int nr_to_call, int *nr_calls) { int ret; @@ -184,13 +185,15 @@ int __kprobes __atomic_notifier_call_chain(struct atomic_notifier_head *nh, return ret; } EXPORT_SYMBOL_GPL(__atomic_notifier_call_chain); +NOKPROBE_SYMBOL(__atomic_notifier_call_chain); -int __kprobes atomic_notifier_call_chain(struct atomic_notifier_head *nh, - unsigned long val, void *v) +int atomic_notifier_call_chain(struct atomic_notifier_head *nh, + unsigned long val, void *v) { return __atomic_notifier_call_chain(nh, val, v, -1, NULL); } EXPORT_SYMBOL_GPL(atomic_notifier_call_chain); +NOKPROBE_SYMBOL(atomic_notifier_call_chain); /* * Blocking notifier chain routines. All access to the chain is @@ -527,7 +530,7 @@ EXPORT_SYMBOL_GPL(srcu_init_notifier_head); static ATOMIC_NOTIFIER_HEAD(die_chain); -int notrace __kprobes notify_die(enum die_val val, const char *str, +int notrace notify_die(enum die_val val, const char *str, struct pt_regs *regs, long err, int trap, int sig) { struct die_args args = { @@ -540,6 +543,7 @@ int notrace __kprobes notify_die(enum die_val val, const char *str, }; return atomic_notifier_call_chain(&die_chain, val, &args); } +NOKPROBE_SYMBOL(notify_die); int register_die_notifier(struct notifier_block *nb) { diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index df88d55dc43..fcc2611d3f1 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -28,12 +28,14 @@ #include <linux/syscore_ops.h> #include <linux/ctype.h> #include <linux/genhd.h> +#include <trace/events/power.h> #include "power.h" static int nocompress; static int noresume; +static int nohibernate; static int resume_wait; static unsigned int resume_delay; static char resume_file[256] = CONFIG_PM_STD_PARTITION; @@ -61,6 +63,11 @@ bool freezer_test_done; static const struct platform_hibernation_ops *hibernation_ops; +bool hibernation_available(void) +{ + return (nohibernate == 0); +} + /** * hibernation_set_ops - Set the global hibernate operations. * @ops: Hibernation operations to use in subsequent hibernation transitions. @@ -292,7 +299,9 @@ static int create_image(int platform_mode) in_suspend = 1; save_processor_state(); + trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, true); error = swsusp_arch_suspend(); + trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false); if (error) printk(KERN_ERR "PM: Error %d creating hibernation image\n", error); @@ -639,6 +648,11 @@ int hibernate(void) { int error; + if (!hibernation_available()) { + pr_debug("PM: Hibernation not available.\n"); + return -EPERM; + } + lock_system_sleep(); /* The snapshot device should not be opened while we're running */ if (!atomic_add_unless(&snapshot_device_available, -1, 0)) { @@ -731,7 +745,7 @@ static int software_resume(void) /* * If the user said "noresume".. bail out early. */ - if (noresume) + if (noresume || !hibernation_available()) return 0; /* @@ -897,6 +911,9 @@ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr, int i; char *start = buf; + if (!hibernation_available()) + return sprintf(buf, "[disabled]\n"); + for (i = HIBERNATION_FIRST; i <= HIBERNATION_MAX; i++) { if (!hibernation_modes[i]) continue; @@ -931,6 +948,9 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr, char *p; int mode = HIBERNATION_INVALID; + if (!hibernation_available()) + return -EPERM; + p = memchr(buf, '\n', n); len = p ? p - buf : n; @@ -1098,6 +1118,10 @@ static int __init hibernate_setup(char *str) noresume = 1; else if (!strncmp(str, "nocompress", 10)) nocompress = 1; + else if (!strncmp(str, "no", 2)) { + noresume = 1; + nohibernate = 1; + } return 1; } @@ -1122,9 +1146,23 @@ static int __init resumedelay_setup(char *str) return 1; } +static int __init nohibernate_setup(char *str) +{ + noresume = 1; + nohibernate = 1; + return 1; +} + +static int __init kaslr_nohibernate_setup(char *str) +{ + return nohibernate_setup(str); +} + __setup("noresume", noresume_setup); __setup("resume_offset=", resume_offset_setup); __setup("resume=", resume_setup); __setup("hibernate=", hibernate_setup); __setup("resumewait", resumewait_setup); __setup("resumedelay=", resumedelay_setup); +__setup("nohibernate", nohibernate_setup); +__setup("kaslr", kaslr_nohibernate_setup); diff --git a/kernel/power/main.c b/kernel/power/main.c index 573410d6647..8e90f330f13 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -300,13 +300,11 @@ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr, s += sprintf(s,"%s ", pm_states[i].label); #endif -#ifdef CONFIG_HIBERNATION - s += sprintf(s, "%s\n", "disk"); -#else + if (hibernation_available()) + s += sprintf(s, "disk "); if (s != buf) /* convert the last space to a newline */ *(s-1) = '\n'; -#endif return (s - buf); } diff --git a/kernel/power/process.c b/kernel/power/process.c index 06ec8869dbf..0ca8d83e236 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -17,6 +17,7 @@ #include <linux/delay.h> #include <linux/workqueue.h> #include <linux/kmod.h> +#include <trace/events/power.h> /* * Timeout for stopping processes @@ -175,6 +176,7 @@ void thaw_processes(void) struct task_struct *g, *p; struct task_struct *curr = current; + trace_suspend_resume(TPS("thaw_processes"), 0, true); if (pm_freezing) atomic_dec(&system_freezing_cnt); pm_freezing = false; @@ -201,6 +203,7 @@ void thaw_processes(void) schedule(); printk("done.\n"); + trace_suspend_resume(TPS("thaw_processes"), 0, false); } void thaw_kernel_threads(void) diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 963e6d0f050..4dd8822f732 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -177,7 +177,9 @@ static int suspend_prepare(suspend_state_t state) if (error) goto Finish; + trace_suspend_resume(TPS("freeze_processes"), 0, true); error = suspend_freeze_processes(); + trace_suspend_resume(TPS("freeze_processes"), 0, false); if (!error) return 0; @@ -240,7 +242,9 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) * all the devices are suspended. */ if (state == PM_SUSPEND_FREEZE) { + trace_suspend_resume(TPS("machine_suspend"), state, true); freeze_enter(); + trace_suspend_resume(TPS("machine_suspend"), state, false); goto Platform_wake; } @@ -256,7 +260,11 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) if (!error) { *wakeup = pm_wakeup_pending(); if (!(suspend_test(TEST_CORE) || *wakeup)) { + trace_suspend_resume(TPS("machine_suspend"), + state, true); error = suspend_ops->enter(state); + trace_suspend_resume(TPS("machine_suspend"), + state, false); events_check_enabled = false; } syscore_resume(); @@ -294,7 +302,6 @@ int suspend_devices_and_enter(suspend_state_t state) if (need_suspend_ops(state) && !suspend_ops) return -ENOSYS; - trace_machine_suspend(state); if (need_suspend_ops(state) && suspend_ops->begin) { error = suspend_ops->begin(state); if (error) @@ -331,7 +338,6 @@ int suspend_devices_and_enter(suspend_state_t state) else if (state == PM_SUSPEND_FREEZE && freeze_ops->end) freeze_ops->end(); - trace_machine_suspend(PWR_EVENT_EXIT); return error; Recover_platform: @@ -365,6 +371,7 @@ static int enter_state(suspend_state_t state) { int error; + trace_suspend_resume(TPS("suspend_enter"), state, true); if (state == PM_SUSPEND_FREEZE) { #ifdef CONFIG_PM_DEBUG if (pm_test_level != TEST_NONE && pm_test_level <= TEST_CPUS) { @@ -382,9 +389,11 @@ static int enter_state(suspend_state_t state) if (state == PM_SUSPEND_FREEZE) freeze_begin(); + trace_suspend_resume(TPS("sync_filesystems"), 0, true); printk(KERN_INFO "PM: Syncing filesystems ... "); sys_sync(); printk("done.\n"); + trace_suspend_resume(TPS("sync_filesystems"), 0, false); pr_debug("PM: Preparing system for %s sleep\n", pm_states[state].label); error = suspend_prepare(state); @@ -394,6 +403,7 @@ static int enter_state(suspend_state_t state) if (suspend_test(TEST_FREEZER)) goto Finish; + trace_suspend_resume(TPS("suspend_enter"), state, false); pr_debug("PM: Entering %s sleep\n", pm_states[state].label); pm_restrict_gfp_mask(); error = suspend_devices_and_enter(state); diff --git a/kernel/power/user.c b/kernel/power/user.c index 98d357584cd..526e8911460 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -49,6 +49,9 @@ static int snapshot_open(struct inode *inode, struct file *filp) struct snapshot_data *data; int error; + if (!hibernation_available()) + return -EPERM; + lock_system_sleep(); if (!atomic_add_unless(&snapshot_device_available, -1, 0)) { diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index ea2d5f6962e..13e839dbca0 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1416,9 +1416,10 @@ static int have_callable_console(void) /* * Can we actually use the console at this time on this cpu? * - * Console drivers may assume that per-cpu resources have been allocated. So - * unless they're explicitly marked as being able to cope (CON_ANYTIME) don't - * call them until this CPU is officially up. + * Console drivers may assume that per-cpu resources have + * been allocated. So unless they're explicitly marked as + * being able to cope (CON_ANYTIME) don't call them until + * this CPU is officially up. */ static inline int can_use_console(unsigned int cpu) { @@ -1431,10 +1432,8 @@ static inline int can_use_console(unsigned int cpu) * console_lock held, and 'console_locked' set) if it * is successful, false otherwise. */ -static int console_trylock_for_printk(void) +static int console_trylock_for_printk(unsigned int cpu) { - unsigned int cpu = smp_processor_id(); - if (!console_trylock()) return 0; /* @@ -1609,8 +1608,7 @@ asmlinkage int vprintk_emit(int facility, int level, */ if (!oops_in_progress && !lockdep_recursing(current)) { recursion_bug = 1; - local_irq_restore(flags); - return 0; + goto out_restore_irqs; } zap_locks(); } @@ -1718,27 +1716,21 @@ asmlinkage int vprintk_emit(int facility, int level, logbuf_cpu = UINT_MAX; raw_spin_unlock(&logbuf_lock); - lockdep_on(); - local_irq_restore(flags); /* If called from the scheduler, we can not call up(). */ - if (in_sched) - return printed_len; - - /* - * Disable preemption to avoid being preempted while holding - * console_sem which would prevent anyone from printing to console - */ - preempt_disable(); - /* - * Try to acquire and then immediately release the console semaphore. - * The release will print out buffers and wake up /dev/kmsg and syslog() - * users. - */ - if (console_trylock_for_printk()) - console_unlock(); - preempt_enable(); + if (!in_sched) { + /* + * Try to acquire and then immediately release the console + * semaphore. The release will print out buffers and wake up + * /dev/kmsg and syslog() users. + */ + if (console_trylock_for_printk(this_cpu)) + console_unlock(); + } + lockdep_on(); +out_restore_irqs: + local_irq_restore(flags); return printed_len; } EXPORT_SYMBOL(vprintk_emit); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c6b98793d64..3bdf01b494f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -535,7 +535,7 @@ static inline void init_hrtick(void) __old; \ }) -#ifdef TIF_POLLING_NRFLAG +#if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG) /* * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG, * this avoids any races wrt polling state changes and thereby avoids @@ -546,12 +546,44 @@ static bool set_nr_and_not_polling(struct task_struct *p) struct thread_info *ti = task_thread_info(p); return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG); } + +/* + * Atomically set TIF_NEED_RESCHED if TIF_POLLING_NRFLAG is set. + * + * If this returns true, then the idle task promises to call + * sched_ttwu_pending() and reschedule soon. + */ +static bool set_nr_if_polling(struct task_struct *p) +{ + struct thread_info *ti = task_thread_info(p); + typeof(ti->flags) old, val = ACCESS_ONCE(ti->flags); + + for (;;) { + if (!(val & _TIF_POLLING_NRFLAG)) + return false; + if (val & _TIF_NEED_RESCHED) + return true; + old = cmpxchg(&ti->flags, val, val | _TIF_NEED_RESCHED); + if (old == val) + break; + val = old; + } + return true; +} + #else static bool set_nr_and_not_polling(struct task_struct *p) { set_tsk_need_resched(p); return true; } + +#ifdef CONFIG_SMP +static bool set_nr_if_polling(struct task_struct *p) +{ + return false; +} +#endif #endif /* @@ -580,6 +612,8 @@ void resched_task(struct task_struct *p) if (set_nr_and_not_polling(p)) smp_send_reschedule(cpu); + else + trace_sched_wake_idle_without_ipi(cpu); } void resched_cpu(int cpu) @@ -642,27 +676,10 @@ static void wake_up_idle_cpu(int cpu) if (cpu == smp_processor_id()) return; - /* - * This is safe, as this function is called with the timer - * wheel base lock of (cpu) held. When the CPU is on the way - * to idle and has not yet set rq->curr to idle then it will - * be serialized on the timer wheel base lock and take the new - * timer into account automatically. - */ - if (rq->curr != rq->idle) - return; - - /* - * We can set TIF_RESCHED on the idle task of the other CPU - * lockless. The worst case is that the other CPU runs the - * idle task through an additional NOOP schedule() - */ - set_tsk_need_resched(rq->idle); - - /* NEED_RESCHED must be visible before we test polling */ - smp_mb(); - if (!tsk_is_polling(rq->idle)) + if (set_nr_and_not_polling(rq->idle)) smp_send_reschedule(cpu); + else + trace_sched_wake_idle_without_ipi(cpu); } static bool wake_up_full_nohz_cpu(int cpu) @@ -888,7 +905,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) rq->clock_task += delta; #if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) - if ((irq_delta + steal) && sched_feat(NONTASK_POWER)) + if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY)) sched_rt_avg_update(rq, irq_delta + steal); #endif } @@ -1521,13 +1538,17 @@ static int ttwu_remote(struct task_struct *p, int wake_flags) } #ifdef CONFIG_SMP -static void sched_ttwu_pending(void) +void sched_ttwu_pending(void) { struct rq *rq = this_rq(); struct llist_node *llist = llist_del_all(&rq->wake_list); struct task_struct *p; + unsigned long flags; - raw_spin_lock(&rq->lock); + if (!llist) + return; + + raw_spin_lock_irqsave(&rq->lock, flags); while (llist) { p = llist_entry(llist, struct task_struct, wake_entry); @@ -1535,7 +1556,7 @@ static void sched_ttwu_pending(void) ttwu_do_activate(rq, p, 0); } - raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&rq->lock, flags); } void scheduler_ipi(void) @@ -1581,8 +1602,14 @@ void scheduler_ipi(void) static void ttwu_queue_remote(struct task_struct *p, int cpu) { - if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) - smp_send_reschedule(cpu); + struct rq *rq = cpu_rq(cpu); + + if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) { + if (!set_nr_if_polling(rq->idle)) + smp_send_reschedule(cpu); + else + trace_sched_wake_idle_without_ipi(cpu); + } } bool cpus_share_cache(int this_cpu, int that_cpu) @@ -2527,7 +2554,7 @@ notrace unsigned long get_parent_ip(unsigned long addr) #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ defined(CONFIG_PREEMPT_TRACER)) -void __kprobes preempt_count_add(int val) +void preempt_count_add(int val) { #ifdef CONFIG_DEBUG_PREEMPT /* @@ -2553,8 +2580,9 @@ void __kprobes preempt_count_add(int val) } } EXPORT_SYMBOL(preempt_count_add); +NOKPROBE_SYMBOL(preempt_count_add); -void __kprobes preempt_count_sub(int val) +void preempt_count_sub(int val) { #ifdef CONFIG_DEBUG_PREEMPT /* @@ -2575,6 +2603,7 @@ void __kprobes preempt_count_sub(int val) __preempt_count_sub(val); } EXPORT_SYMBOL(preempt_count_sub); +NOKPROBE_SYMBOL(preempt_count_sub); #endif @@ -2857,6 +2886,7 @@ asmlinkage __visible void __sched notrace preempt_schedule(void) barrier(); } while (need_resched()); } +NOKPROBE_SYMBOL(preempt_schedule); EXPORT_SYMBOL(preempt_schedule); #endif /* CONFIG_PREEMPT */ @@ -4216,7 +4246,7 @@ EXPORT_SYMBOL(yield); * false (0) if we failed to boost the target. * -ESRCH if there's no task to yield to. */ -bool __sched yield_to(struct task_struct *p, bool preempt) +int __sched yield_to(struct task_struct *p, bool preempt) { struct task_struct *curr = current; struct rq *rq, *p_rq; @@ -5242,14 +5272,13 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, } /* - * Even though we initialize ->power to something semi-sane, - * we leave power_orig unset. This allows us to detect if + * Even though we initialize ->capacity to something semi-sane, + * we leave capacity_orig unset. This allows us to detect if * domain iteration is still funny without causing /0 traps. */ - if (!group->sgp->power_orig) { + if (!group->sgc->capacity_orig) { printk(KERN_CONT "\n"); - printk(KERN_ERR "ERROR: domain->cpu_power not " - "set\n"); + printk(KERN_ERR "ERROR: domain->cpu_capacity not set\n"); break; } @@ -5271,9 +5300,9 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group)); printk(KERN_CONT " %s", str); - if (group->sgp->power != SCHED_POWER_SCALE) { - printk(KERN_CONT " (cpu_power = %d)", - group->sgp->power); + if (group->sgc->capacity != SCHED_CAPACITY_SCALE) { + printk(KERN_CONT " (cpu_capacity = %d)", + group->sgc->capacity); } group = group->next; @@ -5331,7 +5360,7 @@ static int sd_degenerate(struct sched_domain *sd) SD_BALANCE_NEWIDLE | SD_BALANCE_FORK | SD_BALANCE_EXEC | - SD_SHARE_CPUPOWER | + SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES | SD_SHARE_POWERDOMAIN)) { if (sd->groups != sd->groups->next) @@ -5362,7 +5391,7 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) SD_BALANCE_NEWIDLE | SD_BALANCE_FORK | SD_BALANCE_EXEC | - SD_SHARE_CPUPOWER | + SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES | SD_PREFER_SIBLING | SD_SHARE_POWERDOMAIN); @@ -5487,7 +5516,7 @@ static struct root_domain *alloc_rootdomain(void) return rd; } -static void free_sched_groups(struct sched_group *sg, int free_sgp) +static void free_sched_groups(struct sched_group *sg, int free_sgc) { struct sched_group *tmp, *first; @@ -5498,8 +5527,8 @@ static void free_sched_groups(struct sched_group *sg, int free_sgp) do { tmp = sg->next; - if (free_sgp && atomic_dec_and_test(&sg->sgp->ref)) - kfree(sg->sgp); + if (free_sgc && atomic_dec_and_test(&sg->sgc->ref)) + kfree(sg->sgc); kfree(sg); sg = tmp; @@ -5517,7 +5546,7 @@ static void free_sched_domain(struct rcu_head *rcu) if (sd->flags & SD_OVERLAP) { free_sched_groups(sd->groups, 1); } else if (atomic_dec_and_test(&sd->groups->ref)) { - kfree(sd->groups->sgp); + kfree(sd->groups->sgc); kfree(sd->groups); } kfree(sd); @@ -5728,17 +5757,17 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) cpumask_or(covered, covered, sg_span); - sg->sgp = *per_cpu_ptr(sdd->sgp, i); - if (atomic_inc_return(&sg->sgp->ref) == 1) + sg->sgc = *per_cpu_ptr(sdd->sgc, i); + if (atomic_inc_return(&sg->sgc->ref) == 1) build_group_mask(sd, sg); /* - * Initialize sgp->power such that even if we mess up the + * Initialize sgc->capacity such that even if we mess up the * domains and no possible iteration will get us here, we won't * die on a /0 trap. */ - sg->sgp->power = SCHED_POWER_SCALE * cpumask_weight(sg_span); - sg->sgp->power_orig = sg->sgp->power; + sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span); + sg->sgc->capacity_orig = sg->sgc->capacity; /* * Make sure the first group of this domain contains the @@ -5776,8 +5805,8 @@ static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg) if (sg) { *sg = *per_cpu_ptr(sdd->sg, cpu); - (*sg)->sgp = *per_cpu_ptr(sdd->sgp, cpu); - atomic_set(&(*sg)->sgp->ref, 1); /* for claim_allocations */ + (*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu); + atomic_set(&(*sg)->sgc->ref, 1); /* for claim_allocations */ } return cpu; @@ -5786,7 +5815,7 @@ static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg) /* * build_sched_groups will build a circular linked list of the groups * covered by the given span, and will set each group's ->cpumask correctly, - * and ->cpu_power to 0. + * and ->cpu_capacity to 0. * * Assumes the sched_domain tree is fully constructed */ @@ -5840,16 +5869,16 @@ build_sched_groups(struct sched_domain *sd, int cpu) } /* - * Initialize sched groups cpu_power. + * Initialize sched groups cpu_capacity. * - * cpu_power indicates the capacity of sched group, which is used while + * cpu_capacity indicates the capacity of sched group, which is used while * distributing the load between different sched groups in a sched domain. - * Typically cpu_power for all the groups in a sched domain will be same unless - * there are asymmetries in the topology. If there are asymmetries, group - * having more cpu_power will pickup more load compared to the group having - * less cpu_power. + * Typically cpu_capacity for all the groups in a sched domain will be same + * unless there are asymmetries in the topology. If there are asymmetries, + * group having more cpu_capacity will pickup more load compared to the + * group having less cpu_capacity. */ -static void init_sched_groups_power(int cpu, struct sched_domain *sd) +static void init_sched_groups_capacity(int cpu, struct sched_domain *sd) { struct sched_group *sg = sd->groups; @@ -5863,8 +5892,8 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd) if (cpu != group_balance_cpu(sg)) return; - update_group_power(sd, cpu); - atomic_set(&sg->sgp->nr_busy_cpus, sg->group_weight); + update_group_capacity(sd, cpu); + atomic_set(&sg->sgc->nr_busy_cpus, sg->group_weight); } /* @@ -5955,8 +5984,8 @@ static void claim_allocations(int cpu, struct sched_domain *sd) if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref)) *per_cpu_ptr(sdd->sg, cpu) = NULL; - if (atomic_read(&(*per_cpu_ptr(sdd->sgp, cpu))->ref)) - *per_cpu_ptr(sdd->sgp, cpu) = NULL; + if (atomic_read(&(*per_cpu_ptr(sdd->sgc, cpu))->ref)) + *per_cpu_ptr(sdd->sgc, cpu) = NULL; } #ifdef CONFIG_NUMA @@ -5969,7 +5998,7 @@ static int sched_domains_curr_level; /* * SD_flags allowed in topology descriptions. * - * SD_SHARE_CPUPOWER - describes SMT topologies + * SD_SHARE_CPUCAPACITY - describes SMT topologies * SD_SHARE_PKG_RESOURCES - describes shared caches * SD_NUMA - describes NUMA topologies * SD_SHARE_POWERDOMAIN - describes shared power domain @@ -5978,7 +6007,7 @@ static int sched_domains_curr_level; * SD_ASYM_PACKING - describes SMT quirks */ #define TOPOLOGY_SD_FLAGS \ - (SD_SHARE_CPUPOWER | \ + (SD_SHARE_CPUCAPACITY | \ SD_SHARE_PKG_RESOURCES | \ SD_NUMA | \ SD_ASYM_PACKING | \ @@ -6024,7 +6053,7 @@ sd_init(struct sched_domain_topology_level *tl, int cpu) | 1*SD_BALANCE_FORK | 0*SD_BALANCE_WAKE | 1*SD_WAKE_AFFINE - | 0*SD_SHARE_CPUPOWER + | 0*SD_SHARE_CPUCAPACITY | 0*SD_SHARE_PKG_RESOURCES | 0*SD_SERIALIZE | 0*SD_PREFER_SIBLING @@ -6046,7 +6075,7 @@ sd_init(struct sched_domain_topology_level *tl, int cpu) * Convert topological properties into behaviour. */ - if (sd->flags & SD_SHARE_CPUPOWER) { + if (sd->flags & SD_SHARE_CPUCAPACITY) { sd->imbalance_pct = 110; sd->smt_gain = 1178; /* ~15% */ @@ -6358,14 +6387,14 @@ static int __sdt_alloc(const struct cpumask *cpu_map) if (!sdd->sg) return -ENOMEM; - sdd->sgp = alloc_percpu(struct sched_group_power *); - if (!sdd->sgp) + sdd->sgc = alloc_percpu(struct sched_group_capacity *); + if (!sdd->sgc) return -ENOMEM; for_each_cpu(j, cpu_map) { struct sched_domain *sd; struct sched_group *sg; - struct sched_group_power *sgp; + struct sched_group_capacity *sgc; sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(), GFP_KERNEL, cpu_to_node(j)); @@ -6383,12 +6412,12 @@ static int __sdt_alloc(const struct cpumask *cpu_map) *per_cpu_ptr(sdd->sg, j) = sg; - sgp = kzalloc_node(sizeof(struct sched_group_power) + cpumask_size(), + sgc = kzalloc_node(sizeof(struct sched_group_capacity) + cpumask_size(), GFP_KERNEL, cpu_to_node(j)); - if (!sgp) + if (!sgc) return -ENOMEM; - *per_cpu_ptr(sdd->sgp, j) = sgp; + *per_cpu_ptr(sdd->sgc, j) = sgc; } } @@ -6415,15 +6444,15 @@ static void __sdt_free(const struct cpumask *cpu_map) if (sdd->sg) kfree(*per_cpu_ptr(sdd->sg, j)); - if (sdd->sgp) - kfree(*per_cpu_ptr(sdd->sgp, j)); + if (sdd->sgc) + kfree(*per_cpu_ptr(sdd->sgc, j)); } free_percpu(sdd->sd); sdd->sd = NULL; free_percpu(sdd->sg); sdd->sg = NULL; - free_percpu(sdd->sgp); - sdd->sgp = NULL; + free_percpu(sdd->sgc); + sdd->sgc = NULL; } } @@ -6493,14 +6522,14 @@ static int build_sched_domains(const struct cpumask *cpu_map, } } - /* Calculate CPU power for physical packages and nodes */ + /* Calculate CPU capacity for physical packages and nodes */ for (i = nr_cpumask_bits-1; i >= 0; i--) { if (!cpumask_test_cpu(i, cpu_map)) continue; for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { claim_allocations(i, sd); - init_sched_groups_power(i, sd); + init_sched_groups_capacity(i, sd); } } @@ -6943,7 +6972,7 @@ void __init sched_init(void) #ifdef CONFIG_SMP rq->sd = NULL; rq->rd = NULL; - rq->cpu_power = SCHED_POWER_SCALE; + rq->cpu_capacity = SCHED_CAPACITY_SCALE; rq->post_schedule = 0; rq->active_balance = 0; rq->next_balance = jiffies; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 2b8cbf09d1a..fc4f98b1258 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -57,8 +57,6 @@ void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime) dl_b->dl_runtime = runtime; } -extern unsigned long to_ratio(u64 period, u64 runtime); - void init_dl_bw(struct dl_bw *dl_b) { raw_spin_lock_init(&dl_b->lock); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 9855e87d671..fea7d3335e1 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1017,7 +1017,7 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, static unsigned long weighted_cpuload(const int cpu); static unsigned long source_load(int cpu, int type); static unsigned long target_load(int cpu, int type); -static unsigned long power_of(int cpu); +static unsigned long capacity_of(int cpu); static long effective_load(struct task_group *tg, int cpu, long wl, long wg); /* Cached statistics for all CPUs within a node */ @@ -1026,11 +1026,11 @@ struct numa_stats { unsigned long load; /* Total compute capacity of CPUs on a node */ - unsigned long power; + unsigned long compute_capacity; /* Approximate capacity in terms of runnable tasks on a node */ - unsigned long capacity; - int has_capacity; + unsigned long task_capacity; + int has_free_capacity; }; /* @@ -1046,7 +1046,7 @@ static void update_numa_stats(struct numa_stats *ns, int nid) ns->nr_running += rq->nr_running; ns->load += weighted_cpuload(cpu); - ns->power += power_of(cpu); + ns->compute_capacity += capacity_of(cpu); cpus++; } @@ -1056,15 +1056,16 @@ static void update_numa_stats(struct numa_stats *ns, int nid) * the @ns structure is NULL'ed and task_numa_compare() will * not find this node attractive. * - * We'll either bail at !has_capacity, or we'll detect a huge imbalance - * and bail there. + * We'll either bail at !has_free_capacity, or we'll detect a huge + * imbalance and bail there. */ if (!cpus) return; - ns->load = (ns->load * SCHED_POWER_SCALE) / ns->power; - ns->capacity = DIV_ROUND_CLOSEST(ns->power, SCHED_POWER_SCALE); - ns->has_capacity = (ns->nr_running < ns->capacity); + ns->load = (ns->load * SCHED_CAPACITY_SCALE) / ns->compute_capacity; + ns->task_capacity = + DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE); + ns->has_free_capacity = (ns->nr_running < ns->task_capacity); } struct task_numa_env { @@ -1195,8 +1196,8 @@ static void task_numa_compare(struct task_numa_env *env, if (!cur) { /* Is there capacity at our destination? */ - if (env->src_stats.has_capacity && - !env->dst_stats.has_capacity) + if (env->src_stats.has_free_capacity && + !env->dst_stats.has_free_capacity) goto unlock; goto balance; @@ -1213,7 +1214,7 @@ balance: orig_dst_load = env->dst_stats.load; orig_src_load = env->src_stats.load; - /* XXX missing power terms */ + /* XXX missing capacity terms */ load = task_h_load(env->p); dst_load = orig_dst_load + load; src_load = orig_src_load - load; @@ -1301,8 +1302,8 @@ static int task_numa_migrate(struct task_struct *p) groupimp = group_weight(p, env.dst_nid) - groupweight; update_numa_stats(&env.dst_stats, env.dst_nid); - /* If the preferred nid has capacity, try to use it. */ - if (env.dst_stats.has_capacity) + /* If the preferred nid has free capacity, try to use it. */ + if (env.dst_stats.has_free_capacity) task_numa_find_cpu(&env, taskimp, groupimp); /* No space available on the preferred nid. Look elsewhere. */ @@ -3225,10 +3226,12 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq) * has not truly expired. * * Fortunately we can check determine whether this the case by checking - * whether the global deadline has advanced. + * whether the global deadline has advanced. It is valid to compare + * cfs_b->runtime_expires without any locks since we only care about + * exact equality, so a partial write will still work. */ - if ((s64)(cfs_rq->runtime_expires - cfs_b->runtime_expires) >= 0) { + if (cfs_rq->runtime_expires != cfs_b->runtime_expires) { /* extend local deadline, drift is bounded above by 2 ticks */ cfs_rq->runtime_expires += TICK_NSEC; } else { @@ -3457,21 +3460,21 @@ next: static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) { u64 runtime, runtime_expires; - int idle = 1, throttled; + int throttled; - raw_spin_lock(&cfs_b->lock); /* no need to continue the timer with no bandwidth constraint */ if (cfs_b->quota == RUNTIME_INF) - goto out_unlock; + goto out_deactivate; throttled = !list_empty(&cfs_b->throttled_cfs_rq); - /* idle depends on !throttled (for the case of a large deficit) */ - idle = cfs_b->idle && !throttled; cfs_b->nr_periods += overrun; - /* if we're going inactive then everything else can be deferred */ - if (idle) - goto out_unlock; + /* + * idle depends on !throttled (for the case of a large deficit), and if + * we're going inactive then everything else can be deferred + */ + if (cfs_b->idle && !throttled) + goto out_deactivate; /* * if we have relooped after returning idle once, we need to update our @@ -3485,7 +3488,7 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) if (!throttled) { /* mark as potentially idle for the upcoming period */ cfs_b->idle = 1; - goto out_unlock; + return 0; } /* account preceding periods in which throttling occurred */ @@ -3525,12 +3528,12 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) * timer to remain active while there are any throttled entities.) */ cfs_b->idle = 0; -out_unlock: - if (idle) - cfs_b->timer_active = 0; - raw_spin_unlock(&cfs_b->lock); - return idle; + return 0; + +out_deactivate: + cfs_b->timer_active = 0; + return 1; } /* a cfs_rq won't donate quota below this amount */ @@ -3707,6 +3710,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) int overrun; int idle = 0; + raw_spin_lock(&cfs_b->lock); for (;;) { now = hrtimer_cb_get_time(timer); overrun = hrtimer_forward(timer, now, cfs_b->period); @@ -3716,6 +3720,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) idle = do_sched_cfs_period_timer(cfs_b, overrun); } + raw_spin_unlock(&cfs_b->lock); return idle ? HRTIMER_NORESTART : HRTIMER_RESTART; } @@ -3775,8 +3780,6 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) struct cfs_rq *cfs_rq; for_each_leaf_cfs_rq(rq, cfs_rq) { - struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); - if (!cfs_rq->runtime_enabled) continue; @@ -3784,7 +3787,7 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) * clock_task is not advancing so we just need to make sure * there's some valid quota amount */ - cfs_rq->runtime_remaining = cfs_b->quota; + cfs_rq->runtime_remaining = 1; if (cfs_rq_throttled(cfs_rq)) unthrottle_cfs_rq(cfs_rq); } @@ -4041,9 +4044,9 @@ static unsigned long target_load(int cpu, int type) return max(rq->cpu_load[type-1], total); } -static unsigned long power_of(int cpu) +static unsigned long capacity_of(int cpu) { - return cpu_rq(cpu)->cpu_power; + return cpu_rq(cpu)->cpu_capacity; } static unsigned long cpu_avg_load_per_task(int cpu) @@ -4065,7 +4068,7 @@ static void record_wakee(struct task_struct *p) * about the boundary, really active task won't care * about the loss. */ - if (jiffies > current->wakee_flip_decay_ts + HZ) { + if (time_after(jiffies, current->wakee_flip_decay_ts + HZ)) { current->wakee_flips >>= 1; current->wakee_flip_decay_ts = jiffies; } @@ -4286,12 +4289,12 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) s64 this_eff_load, prev_eff_load; this_eff_load = 100; - this_eff_load *= power_of(prev_cpu); + this_eff_load *= capacity_of(prev_cpu); this_eff_load *= this_load + effective_load(tg, this_cpu, weight, weight); prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2; - prev_eff_load *= power_of(this_cpu); + prev_eff_load *= capacity_of(this_cpu); prev_eff_load *= load + effective_load(tg, prev_cpu, 0, weight); balanced = this_eff_load <= prev_eff_load; @@ -4367,8 +4370,8 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, avg_load += load; } - /* Adjust by relative CPU power of the group */ - avg_load = (avg_load * SCHED_POWER_SCALE) / group->sgp->power; + /* Adjust by relative CPU capacity of the group */ + avg_load = (avg_load * SCHED_CAPACITY_SCALE) / group->sgc->capacity; if (local_group) { this_load = avg_load; @@ -4948,14 +4951,14 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preemp * * W'_i,n = (2^n - 1) / 2^n * W_i,n + 1 / 2^n * W_i,0 (3) * - * P_i is the cpu power (or compute capacity) of cpu i, typically it is the + * C_i is the compute capacity of cpu i, typically it is the * fraction of 'recent' time available for SCHED_OTHER task execution. But it * can also include other factors [XXX]. * * To achieve this balance we define a measure of imbalance which follows * directly from (1): * - * imb_i,j = max{ avg(W/P), W_i/P_i } - min{ avg(W/P), W_j/P_j } (4) + * imb_i,j = max{ avg(W/C), W_i/C_i } - min{ avg(W/C), W_j/C_j } (4) * * We them move tasks around to minimize the imbalance. In the continuous * function space it is obvious this converges, in the discrete case we get @@ -5530,13 +5533,13 @@ struct sg_lb_stats { unsigned long group_load; /* Total load over the CPUs of the group */ unsigned long sum_weighted_load; /* Weighted load of group's tasks */ unsigned long load_per_task; - unsigned long group_power; + unsigned long group_capacity; unsigned int sum_nr_running; /* Nr tasks running in the group */ - unsigned int group_capacity; + unsigned int group_capacity_factor; unsigned int idle_cpus; unsigned int group_weight; int group_imb; /* Is there an imbalance in the group ? */ - int group_has_capacity; /* Is there extra capacity in the group? */ + int group_has_free_capacity; #ifdef CONFIG_NUMA_BALANCING unsigned int nr_numa_running; unsigned int nr_preferred_running; @@ -5551,7 +5554,7 @@ struct sd_lb_stats { struct sched_group *busiest; /* Busiest group in this sd */ struct sched_group *local; /* Local group in this sd */ unsigned long total_load; /* Total load of all groups in sd */ - unsigned long total_pwr; /* Total power of all groups in sd */ + unsigned long total_capacity; /* Total capacity of all groups in sd */ unsigned long avg_load; /* Average load across all groups in sd */ struct sg_lb_stats busiest_stat;/* Statistics of the busiest group */ @@ -5570,7 +5573,7 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds) .busiest = NULL, .local = NULL, .total_load = 0UL, - .total_pwr = 0UL, + .total_capacity = 0UL, .busiest_stat = { .avg_load = 0UL, }, @@ -5605,17 +5608,17 @@ static inline int get_sd_load_idx(struct sched_domain *sd, return load_idx; } -static unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu) +static unsigned long default_scale_capacity(struct sched_domain *sd, int cpu) { - return SCHED_POWER_SCALE; + return SCHED_CAPACITY_SCALE; } -unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu) +unsigned long __weak arch_scale_freq_capacity(struct sched_domain *sd, int cpu) { - return default_scale_freq_power(sd, cpu); + return default_scale_capacity(sd, cpu); } -static unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu) +static unsigned long default_scale_smt_capacity(struct sched_domain *sd, int cpu) { unsigned long weight = sd->span_weight; unsigned long smt_gain = sd->smt_gain; @@ -5625,12 +5628,12 @@ static unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu) return smt_gain; } -unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu) +unsigned long __weak arch_scale_smt_capacity(struct sched_domain *sd, int cpu) { - return default_scale_smt_power(sd, cpu); + return default_scale_smt_capacity(sd, cpu); } -static unsigned long scale_rt_power(int cpu) +static unsigned long scale_rt_capacity(int cpu) { struct rq *rq = cpu_rq(cpu); u64 total, available, age_stamp, avg; @@ -5650,71 +5653,71 @@ static unsigned long scale_rt_power(int cpu) total = sched_avg_period() + delta; if (unlikely(total < avg)) { - /* Ensures that power won't end up being negative */ + /* Ensures that capacity won't end up being negative */ available = 0; } else { available = total - avg; } - if (unlikely((s64)total < SCHED_POWER_SCALE)) - total = SCHED_POWER_SCALE; + if (unlikely((s64)total < SCHED_CAPACITY_SCALE)) + total = SCHED_CAPACITY_SCALE; - total >>= SCHED_POWER_SHIFT; + total >>= SCHED_CAPACITY_SHIFT; return div_u64(available, total); } -static void update_cpu_power(struct sched_domain *sd, int cpu) +static void update_cpu_capacity(struct sched_domain *sd, int cpu) { unsigned long weight = sd->span_weight; - unsigned long power = SCHED_POWER_SCALE; + unsigned long capacity = SCHED_CAPACITY_SCALE; struct sched_group *sdg = sd->groups; - if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) { - if (sched_feat(ARCH_POWER)) - power *= arch_scale_smt_power(sd, cpu); + if ((sd->flags & SD_SHARE_CPUCAPACITY) && weight > 1) { + if (sched_feat(ARCH_CAPACITY)) + capacity *= arch_scale_smt_capacity(sd, cpu); else - power *= default_scale_smt_power(sd, cpu); + capacity *= default_scale_smt_capacity(sd, cpu); - power >>= SCHED_POWER_SHIFT; + capacity >>= SCHED_CAPACITY_SHIFT; } - sdg->sgp->power_orig = power; + sdg->sgc->capacity_orig = capacity; - if (sched_feat(ARCH_POWER)) - power *= arch_scale_freq_power(sd, cpu); + if (sched_feat(ARCH_CAPACITY)) + capacity *= arch_scale_freq_capacity(sd, cpu); else - power *= default_scale_freq_power(sd, cpu); + capacity *= default_scale_capacity(sd, cpu); - power >>= SCHED_POWER_SHIFT; + capacity >>= SCHED_CAPACITY_SHIFT; - power *= scale_rt_power(cpu); - power >>= SCHED_POWER_SHIFT; + capacity *= scale_rt_capacity(cpu); + capacity >>= SCHED_CAPACITY_SHIFT; - if (!power) - power = 1; + if (!capacity) + capacity = 1; - cpu_rq(cpu)->cpu_power = power; - sdg->sgp->power = power; + cpu_rq(cpu)->cpu_capacity = capacity; + sdg->sgc->capacity = capacity; } -void update_group_power(struct sched_domain *sd, int cpu) +void update_group_capacity(struct sched_domain *sd, int cpu) { struct sched_domain *child = sd->child; struct sched_group *group, *sdg = sd->groups; - unsigned long power, power_orig; + unsigned long capacity, capacity_orig; unsigned long interval; interval = msecs_to_jiffies(sd->balance_interval); interval = clamp(interval, 1UL, max_load_balance_interval); - sdg->sgp->next_update = jiffies + interval; + sdg->sgc->next_update = jiffies + interval; if (!child) { - update_cpu_power(sd, cpu); + update_cpu_capacity(sd, cpu); return; } - power_orig = power = 0; + capacity_orig = capacity = 0; if (child->flags & SD_OVERLAP) { /* @@ -5723,31 +5726,31 @@ void update_group_power(struct sched_domain *sd, int cpu) */ for_each_cpu(cpu, sched_group_cpus(sdg)) { - struct sched_group_power *sgp; + struct sched_group_capacity *sgc; struct rq *rq = cpu_rq(cpu); /* - * build_sched_domains() -> init_sched_groups_power() + * build_sched_domains() -> init_sched_groups_capacity() * gets here before we've attached the domains to the * runqueues. * - * Use power_of(), which is set irrespective of domains - * in update_cpu_power(). + * Use capacity_of(), which is set irrespective of domains + * in update_cpu_capacity(). * - * This avoids power/power_orig from being 0 and + * This avoids capacity/capacity_orig from being 0 and * causing divide-by-zero issues on boot. * - * Runtime updates will correct power_orig. + * Runtime updates will correct capacity_orig. */ if (unlikely(!rq->sd)) { - power_orig += power_of(cpu); - power += power_of(cpu); + capacity_orig += capacity_of(cpu); + capacity += capacity_of(cpu); continue; } - sgp = rq->sd->groups->sgp; - power_orig += sgp->power_orig; - power += sgp->power; + sgc = rq->sd->groups->sgc; + capacity_orig += sgc->capacity_orig; + capacity += sgc->capacity; } } else { /* @@ -5757,14 +5760,14 @@ void update_group_power(struct sched_domain *sd, int cpu) group = child->groups; do { - power_orig += group->sgp->power_orig; - power += group->sgp->power; + capacity_orig += group->sgc->capacity_orig; + capacity += group->sgc->capacity; group = group->next; } while (group != child->groups); } - sdg->sgp->power_orig = power_orig; - sdg->sgp->power = power; + sdg->sgc->capacity_orig = capacity_orig; + sdg->sgc->capacity = capacity; } /* @@ -5778,15 +5781,15 @@ static inline int fix_small_capacity(struct sched_domain *sd, struct sched_group *group) { /* - * Only siblings can have significantly less than SCHED_POWER_SCALE + * Only siblings can have significantly less than SCHED_CAPACITY_SCALE */ - if (!(sd->flags & SD_SHARE_CPUPOWER)) + if (!(sd->flags & SD_SHARE_CPUCAPACITY)) return 0; /* - * If ~90% of the cpu_power is still there, we're good. + * If ~90% of the cpu_capacity is still there, we're good. */ - if (group->sgp->power * 32 > group->sgp->power_orig * 29) + if (group->sgc->capacity * 32 > group->sgc->capacity_orig * 29) return 1; return 0; @@ -5823,34 +5826,35 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group) static inline int sg_imbalanced(struct sched_group *group) { - return group->sgp->imbalance; + return group->sgc->imbalance; } /* - * Compute the group capacity. + * Compute the group capacity factor. * - * Avoid the issue where N*frac(smt_power) >= 1 creates 'phantom' cores by + * Avoid the issue where N*frac(smt_capacity) >= 1 creates 'phantom' cores by * first dividing out the smt factor and computing the actual number of cores - * and limit power unit capacity with that. + * and limit unit capacity with that. */ -static inline int sg_capacity(struct lb_env *env, struct sched_group *group) +static inline int sg_capacity_factor(struct lb_env *env, struct sched_group *group) { - unsigned int capacity, smt, cpus; - unsigned int power, power_orig; + unsigned int capacity_factor, smt, cpus; + unsigned int capacity, capacity_orig; - power = group->sgp->power; - power_orig = group->sgp->power_orig; + capacity = group->sgc->capacity; + capacity_orig = group->sgc->capacity_orig; cpus = group->group_weight; - /* smt := ceil(cpus / power), assumes: 1 < smt_power < 2 */ - smt = DIV_ROUND_UP(SCHED_POWER_SCALE * cpus, power_orig); - capacity = cpus / smt; /* cores */ + /* smt := ceil(cpus / capacity), assumes: 1 < smt_capacity < 2 */ + smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, capacity_orig); + capacity_factor = cpus / smt; /* cores */ - capacity = min_t(unsigned, capacity, DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE)); - if (!capacity) - capacity = fix_small_capacity(env->sd, group); + capacity_factor = min_t(unsigned, + capacity_factor, DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE)); + if (!capacity_factor) + capacity_factor = fix_small_capacity(env->sd, group); - return capacity; + return capacity_factor; } /** @@ -5890,9 +5894,9 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->idle_cpus++; } - /* Adjust by relative CPU power of the group */ - sgs->group_power = group->sgp->power; - sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / sgs->group_power; + /* Adjust by relative CPU capacity of the group */ + sgs->group_capacity = group->sgc->capacity; + sgs->avg_load = (sgs->group_load*SCHED_CAPACITY_SCALE) / sgs->group_capacity; if (sgs->sum_nr_running) sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running; @@ -5900,10 +5904,10 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->group_weight = group->group_weight; sgs->group_imb = sg_imbalanced(group); - sgs->group_capacity = sg_capacity(env, group); + sgs->group_capacity_factor = sg_capacity_factor(env, group); - if (sgs->group_capacity > sgs->sum_nr_running) - sgs->group_has_capacity = 1; + if (sgs->group_capacity_factor > sgs->sum_nr_running) + sgs->group_has_free_capacity = 1; } /** @@ -5927,7 +5931,7 @@ static bool update_sd_pick_busiest(struct lb_env *env, if (sgs->avg_load <= sds->busiest_stat.avg_load) return false; - if (sgs->sum_nr_running > sgs->group_capacity) + if (sgs->sum_nr_running > sgs->group_capacity_factor) return true; if (sgs->group_imb) @@ -6007,8 +6011,8 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd sgs = &sds->local_stat; if (env->idle != CPU_NEWLY_IDLE || - time_after_eq(jiffies, sg->sgp->next_update)) - update_group_power(env->sd, env->dst_cpu); + time_after_eq(jiffies, sg->sgc->next_update)) + update_group_capacity(env->sd, env->dst_cpu); } update_sg_lb_stats(env, sg, load_idx, local_group, sgs); @@ -6018,17 +6022,17 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd /* * In case the child domain prefers tasks go to siblings - * first, lower the sg capacity to one so that we'll try + * first, lower the sg capacity factor to one so that we'll try * and move all the excess tasks away. We lower the capacity * of a group only if the local group has the capacity to fit - * these excess tasks, i.e. nr_running < group_capacity. The + * these excess tasks, i.e. nr_running < group_capacity_factor. The * extra check prevents the case where you always pull from the * heaviest group when it is already under-utilized (possible * with a large weight task outweighs the tasks on the system). */ if (prefer_sibling && sds->local && - sds->local_stat.group_has_capacity) - sgs->group_capacity = min(sgs->group_capacity, 1U); + sds->local_stat.group_has_free_capacity) + sgs->group_capacity_factor = min(sgs->group_capacity_factor, 1U); if (update_sd_pick_busiest(env, sds, sg, sgs)) { sds->busiest = sg; @@ -6038,7 +6042,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd next_group: /* Now, start updating sd_lb_stats */ sds->total_load += sgs->group_load; - sds->total_pwr += sgs->group_power; + sds->total_capacity += sgs->group_capacity; sg = sg->next; } while (sg != env->sd->groups); @@ -6085,8 +6089,8 @@ static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds) return 0; env->imbalance = DIV_ROUND_CLOSEST( - sds->busiest_stat.avg_load * sds->busiest_stat.group_power, - SCHED_POWER_SCALE); + sds->busiest_stat.avg_load * sds->busiest_stat.group_capacity, + SCHED_CAPACITY_SCALE); return 1; } @@ -6101,7 +6105,7 @@ static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds) static inline void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds) { - unsigned long tmp, pwr_now = 0, pwr_move = 0; + unsigned long tmp, capa_now = 0, capa_move = 0; unsigned int imbn = 2; unsigned long scaled_busy_load_per_task; struct sg_lb_stats *local, *busiest; @@ -6115,8 +6119,8 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds) imbn = 1; scaled_busy_load_per_task = - (busiest->load_per_task * SCHED_POWER_SCALE) / - busiest->group_power; + (busiest->load_per_task * SCHED_CAPACITY_SCALE) / + busiest->group_capacity; if (busiest->avg_load + scaled_busy_load_per_task >= local->avg_load + (scaled_busy_load_per_task * imbn)) { @@ -6126,38 +6130,38 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds) /* * OK, we don't have enough imbalance to justify moving tasks, - * however we may be able to increase total CPU power used by + * however we may be able to increase total CPU capacity used by * moving them. */ - pwr_now += busiest->group_power * + capa_now += busiest->group_capacity * min(busiest->load_per_task, busiest->avg_load); - pwr_now += local->group_power * + capa_now += local->group_capacity * min(local->load_per_task, local->avg_load); - pwr_now /= SCHED_POWER_SCALE; + capa_now /= SCHED_CAPACITY_SCALE; /* Amount of load we'd subtract */ if (busiest->avg_load > scaled_busy_load_per_task) { - pwr_move += busiest->group_power * + capa_move += busiest->group_capacity * min(busiest->load_per_task, busiest->avg_load - scaled_busy_load_per_task); } /* Amount of load we'd add */ - if (busiest->avg_load * busiest->group_power < - busiest->load_per_task * SCHED_POWER_SCALE) { - tmp = (busiest->avg_load * busiest->group_power) / - local->group_power; + if (busiest->avg_load * busiest->group_capacity < + busiest->load_per_task * SCHED_CAPACITY_SCALE) { + tmp = (busiest->avg_load * busiest->group_capacity) / + local->group_capacity; } else { - tmp = (busiest->load_per_task * SCHED_POWER_SCALE) / - local->group_power; + tmp = (busiest->load_per_task * SCHED_CAPACITY_SCALE) / + local->group_capacity; } - pwr_move += local->group_power * + capa_move += local->group_capacity * min(local->load_per_task, local->avg_load + tmp); - pwr_move /= SCHED_POWER_SCALE; + capa_move /= SCHED_CAPACITY_SCALE; /* Move if we gain throughput */ - if (pwr_move > pwr_now) + if (capa_move > capa_now) env->imbalance = busiest->load_per_task; } @@ -6187,7 +6191,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s /* * In the presence of smp nice balancing, certain scenarios can have * max load less than avg load(as we skip the groups at or below - * its cpu_power, while calculating max_load..) + * its cpu_capacity, while calculating max_load..) */ if (busiest->avg_load <= sds->avg_load || local->avg_load >= sds->avg_load) { @@ -6202,10 +6206,10 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * have to drop below capacity to reach cpu-load equilibrium. */ load_above_capacity = - (busiest->sum_nr_running - busiest->group_capacity); + (busiest->sum_nr_running - busiest->group_capacity_factor); - load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_POWER_SCALE); - load_above_capacity /= busiest->group_power; + load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_CAPACITY_SCALE); + load_above_capacity /= busiest->group_capacity; } /* @@ -6220,9 +6224,9 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s /* How much load to actually move to equalise the imbalance */ env->imbalance = min( - max_pull * busiest->group_power, - (sds->avg_load - local->avg_load) * local->group_power - ) / SCHED_POWER_SCALE; + max_pull * busiest->group_capacity, + (sds->avg_load - local->avg_load) * local->group_capacity + ) / SCHED_CAPACITY_SCALE; /* * if *imbalance is less than the average load per runnable task @@ -6276,7 +6280,8 @@ static struct sched_group *find_busiest_group(struct lb_env *env) if (!sds.busiest || busiest->sum_nr_running == 0) goto out_balanced; - sds.avg_load = (SCHED_POWER_SCALE * sds.total_load) / sds.total_pwr; + sds.avg_load = (SCHED_CAPACITY_SCALE * sds.total_load) + / sds.total_capacity; /* * If the busiest group is imbalanced the below checks don't @@ -6287,8 +6292,8 @@ static struct sched_group *find_busiest_group(struct lb_env *env) goto force_balance; /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */ - if (env->idle == CPU_NEWLY_IDLE && local->group_has_capacity && - !busiest->group_has_capacity) + if (env->idle == CPU_NEWLY_IDLE && local->group_has_free_capacity && + !busiest->group_has_free_capacity) goto force_balance; /* @@ -6342,11 +6347,11 @@ static struct rq *find_busiest_queue(struct lb_env *env, struct sched_group *group) { struct rq *busiest = NULL, *rq; - unsigned long busiest_load = 0, busiest_power = 1; + unsigned long busiest_load = 0, busiest_capacity = 1; int i; for_each_cpu_and(i, sched_group_cpus(group), env->cpus) { - unsigned long power, capacity, wl; + unsigned long capacity, capacity_factor, wl; enum fbq_type rt; rq = cpu_rq(i); @@ -6374,34 +6379,34 @@ static struct rq *find_busiest_queue(struct lb_env *env, if (rt > env->fbq_type) continue; - power = power_of(i); - capacity = DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE); - if (!capacity) - capacity = fix_small_capacity(env->sd, group); + capacity = capacity_of(i); + capacity_factor = DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE); + if (!capacity_factor) + capacity_factor = fix_small_capacity(env->sd, group); wl = weighted_cpuload(i); /* * When comparing with imbalance, use weighted_cpuload() - * which is not scaled with the cpu power. + * which is not scaled with the cpu capacity. */ - if (capacity && rq->nr_running == 1 && wl > env->imbalance) + if (capacity_factor && rq->nr_running == 1 && wl > env->imbalance) continue; /* * For the load comparisons with the other cpu's, consider - * the weighted_cpuload() scaled with the cpu power, so that - * the load can be moved away from the cpu that is potentially - * running at a lower capacity. + * the weighted_cpuload() scaled with the cpu capacity, so + * that the load can be moved away from the cpu that is + * potentially running at a lower capacity. * - * Thus we're looking for max(wl_i / power_i), crosswise + * Thus we're looking for max(wl_i / capacity_i), crosswise * multiplication to rid ourselves of the division works out - * to: wl_i * power_j > wl_j * power_i; where j is our - * previous maximum. + * to: wl_i * capacity_j > wl_j * capacity_i; where j is + * our previous maximum. */ - if (wl * busiest_power > busiest_load * power) { + if (wl * busiest_capacity > busiest_load * capacity) { busiest_load = wl; - busiest_power = power; + busiest_capacity = capacity; busiest = rq; } } @@ -6609,7 +6614,7 @@ more_balance: * We failed to reach balance because of affinity. */ if (sd_parent) { - int *group_imbalance = &sd_parent->groups->sgp->imbalance; + int *group_imbalance = &sd_parent->groups->sgc->imbalance; if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) { *group_imbalance = 1; @@ -6996,7 +7001,7 @@ static inline void set_cpu_sd_state_busy(void) goto unlock; sd->nohz_idle = 0; - atomic_inc(&sd->groups->sgp->nr_busy_cpus); + atomic_inc(&sd->groups->sgc->nr_busy_cpus); unlock: rcu_read_unlock(); } @@ -7013,7 +7018,7 @@ void set_cpu_sd_state_idle(void) goto unlock; sd->nohz_idle = 1; - atomic_dec(&sd->groups->sgp->nr_busy_cpus); + atomic_dec(&sd->groups->sgc->nr_busy_cpus); unlock: rcu_read_unlock(); } @@ -7192,12 +7197,17 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) rq = cpu_rq(balance_cpu); - raw_spin_lock_irq(&rq->lock); - update_rq_clock(rq); - update_idle_cpu_load(rq); - raw_spin_unlock_irq(&rq->lock); - - rebalance_domains(rq, CPU_IDLE); + /* + * If time for next balance is due, + * do the balance. + */ + if (time_after_eq(jiffies, rq->next_balance)) { + raw_spin_lock_irq(&rq->lock); + update_rq_clock(rq); + update_idle_cpu_load(rq); + raw_spin_unlock_irq(&rq->lock); + rebalance_domains(rq, CPU_IDLE); + } if (time_after(this_rq->next_balance, rq->next_balance)) this_rq->next_balance = rq->next_balance; @@ -7212,7 +7222,7 @@ end: * of an idle cpu is the system. * - This rq has more than one task. * - At any scheduler domain level, this cpu's scheduler group has multiple - * busy cpu's exceeding the group's power. + * busy cpu's exceeding the group's capacity. * - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler * domain span are idle. */ @@ -7220,7 +7230,7 @@ static inline int nohz_kick_needed(struct rq *rq) { unsigned long now = jiffies; struct sched_domain *sd; - struct sched_group_power *sgp; + struct sched_group_capacity *sgc; int nr_busy, cpu = rq->cpu; if (unlikely(rq->idle_balance)) @@ -7250,8 +7260,8 @@ static inline int nohz_kick_needed(struct rq *rq) sd = rcu_dereference(per_cpu(sd_busy, cpu)); if (sd) { - sgp = sd->groups->sgp; - nr_busy = atomic_read(&sgp->nr_busy_cpus); + sgc = sd->groups->sgc; + nr_busy = atomic_read(&sgc->nr_busy_cpus); if (nr_busy > 1) goto need_kick_unlock; diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 5716929a2e3..90284d117fe 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -37,18 +37,18 @@ SCHED_FEAT(CACHE_HOT_BUDDY, true) SCHED_FEAT(WAKEUP_PREEMPTION, true) /* - * Use arch dependent cpu power functions + * Use arch dependent cpu capacity functions */ -SCHED_FEAT(ARCH_POWER, true) +SCHED_FEAT(ARCH_CAPACITY, true) SCHED_FEAT(HRTICK, false) SCHED_FEAT(DOUBLE_TICK, false) SCHED_FEAT(LB_BIAS, true) /* - * Decrement CPU power based on time not spent running tasks + * Decrement CPU capacity based on time not spent running tasks */ -SCHED_FEAT(NONTASK_POWER, true) +SCHED_FEAT(NONTASK_CAPACITY, true) /* * Queue remote wakeups on the target CPU and process them diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 25b9423abce..cf009fb0bc2 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -12,6 +12,8 @@ #include <trace/events/power.h> +#include "sched.h" + static int __read_mostly cpu_idle_force_poll; void cpu_idle_poll_ctrl(bool enable) @@ -67,6 +69,10 @@ void __weak arch_cpu_idle(void) * cpuidle_idle_call - the main idle function * * NOTE: no locks or semaphores should be used here + * + * On archs that support TIF_POLLING_NRFLAG, is called with polling + * set, and it returns with polling set. If it ever stops polling, it + * must clear the polling bit. */ static void cpuidle_idle_call(void) { @@ -175,10 +181,22 @@ exit_idle: /* * Generic idle loop implementation + * + * Called with polling cleared. */ static void cpu_idle_loop(void) { while (1) { + /* + * If the arch has a polling bit, we maintain an invariant: + * + * Our polling bit is clear if we're not scheduled (i.e. if + * rq->curr != rq->idle). This means that, if rq->idle has + * the polling bit set, then setting need_resched is + * guaranteed to cause the cpu to reschedule. + */ + + __current_set_polling(); tick_nohz_idle_enter(); while (!need_resched()) { @@ -218,6 +236,17 @@ static void cpu_idle_loop(void) */ preempt_set_need_resched(); tick_nohz_idle_exit(); + __current_clr_polling(); + + /* + * We promise to call sched_ttwu_pending and reschedule + * if need_resched is set while polling is set. That + * means that clearing polling needs to be visible + * before doing these things. + */ + smp_mb__after_atomic(); + + sched_ttwu_pending(); schedule_preempt_disabled(); } } @@ -239,7 +268,6 @@ void cpu_startup_entry(enum cpuhp_state state) */ boot_init_stack_canary(); #endif - __current_set_polling(); arch_cpu_idle_prepare(); cpu_idle_loop(); } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index b3512f1afce..a49083192c6 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -918,7 +918,6 @@ static void update_curr_rt(struct rq *rq) { struct task_struct *curr = rq->curr; struct sched_rt_entity *rt_se = &curr->rt; - struct rt_rq *rt_rq = rt_rq_of_se(rt_se); u64 delta_exec; if (curr->sched_class != &rt_sched_class) @@ -943,7 +942,7 @@ static void update_curr_rt(struct rq *rq) return; for_each_sched_rt_entity(rt_se) { - rt_rq = rt_rq_of_se(rt_se); + struct rt_rq *rt_rq = rt_rq_of_se(rt_se); if (sched_rt_runtime(rt_rq) != RUNTIME_INF) { raw_spin_lock(&rt_rq->rt_runtime_lock); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index e47679b04d1..31cc02ebc54 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -567,7 +567,7 @@ struct rq { struct root_domain *rd; struct sched_domain *sd; - unsigned long cpu_power; + unsigned long cpu_capacity; unsigned char idle_balance; /* For active balancing */ @@ -670,6 +670,8 @@ extern int migrate_swap(struct task_struct *, struct task_struct *); #ifdef CONFIG_SMP +extern void sched_ttwu_pending(void); + #define rcu_dereference_check_sched_domain(p) \ rcu_dereference_check((p), \ lockdep_is_held(&sched_domains_mutex)) @@ -728,15 +730,15 @@ DECLARE_PER_CPU(struct sched_domain *, sd_numa); DECLARE_PER_CPU(struct sched_domain *, sd_busy); DECLARE_PER_CPU(struct sched_domain *, sd_asym); -struct sched_group_power { +struct sched_group_capacity { atomic_t ref; /* - * CPU power of this group, SCHED_LOAD_SCALE being max power for a - * single CPU. + * CPU capacity of this group, SCHED_LOAD_SCALE being max capacity + * for a single CPU. */ - unsigned int power, power_orig; + unsigned int capacity, capacity_orig; unsigned long next_update; - int imbalance; /* XXX unrelated to power but shared group state */ + int imbalance; /* XXX unrelated to capacity but shared group state */ /* * Number of busy cpus in this group. */ @@ -750,7 +752,7 @@ struct sched_group { atomic_t ref; unsigned int group_weight; - struct sched_group_power *sgp; + struct sched_group_capacity *sgc; /* * The CPUs this group covers. @@ -773,7 +775,7 @@ static inline struct cpumask *sched_group_cpus(struct sched_group *sg) */ static inline struct cpumask *sched_group_mask(struct sched_group *sg) { - return to_cpumask(sg->sgp->cpumask); + return to_cpumask(sg->sgc->cpumask); } /** @@ -787,6 +789,10 @@ static inline unsigned int group_first_cpu(struct sched_group *group) extern int group_balance_cpu(struct sched_group *sg); +#else + +static inline void sched_ttwu_pending(void) { } + #endif /* CONFIG_SMP */ #include "stats.h" @@ -1167,7 +1173,7 @@ extern const struct sched_class idle_sched_class; #ifdef CONFIG_SMP -extern void update_group_power(struct sched_domain *sd, int cpu); +extern void update_group_capacity(struct sched_domain *sd, int cpu); extern void trigger_load_balance(struct rq *rq); diff --git a/kernel/seccomp.c b/kernel/seccomp.c index f6d76bebe69..301bbc24739 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -54,8 +54,7 @@ struct seccomp_filter { atomic_t usage; struct seccomp_filter *prev; - unsigned short len; /* Instruction count */ - struct sock_filter_int insnsi[]; + struct sk_filter *prog; }; /* Limit any path through the tree to 256KB worth of instructions. */ @@ -104,60 +103,59 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) u32 k = ftest->k; switch (code) { - case BPF_S_LD_W_ABS: + case BPF_LD | BPF_W | BPF_ABS: ftest->code = BPF_LDX | BPF_W | BPF_ABS; /* 32-bit aligned and not out of bounds. */ if (k >= sizeof(struct seccomp_data) || k & 3) return -EINVAL; continue; - case BPF_S_LD_W_LEN: + case BPF_LD | BPF_W | BPF_LEN: ftest->code = BPF_LD | BPF_IMM; ftest->k = sizeof(struct seccomp_data); continue; - case BPF_S_LDX_W_LEN: + case BPF_LDX | BPF_W | BPF_LEN: ftest->code = BPF_LDX | BPF_IMM; ftest->k = sizeof(struct seccomp_data); continue; /* Explicitly include allowed calls. */ - case BPF_S_RET_K: - case BPF_S_RET_A: - case BPF_S_ALU_ADD_K: - case BPF_S_ALU_ADD_X: - case BPF_S_ALU_SUB_K: - case BPF_S_ALU_SUB_X: - case BPF_S_ALU_MUL_K: - case BPF_S_ALU_MUL_X: - case BPF_S_ALU_DIV_X: - case BPF_S_ALU_AND_K: - case BPF_S_ALU_AND_X: - case BPF_S_ALU_OR_K: - case BPF_S_ALU_OR_X: - case BPF_S_ALU_XOR_K: - case BPF_S_ALU_XOR_X: - case BPF_S_ALU_LSH_K: - case BPF_S_ALU_LSH_X: - case BPF_S_ALU_RSH_K: - case BPF_S_ALU_RSH_X: - case BPF_S_ALU_NEG: - case BPF_S_LD_IMM: - case BPF_S_LDX_IMM: - case BPF_S_MISC_TAX: - case BPF_S_MISC_TXA: - case BPF_S_ALU_DIV_K: - case BPF_S_LD_MEM: - case BPF_S_LDX_MEM: - case BPF_S_ST: - case BPF_S_STX: - case BPF_S_JMP_JA: - case BPF_S_JMP_JEQ_K: - case BPF_S_JMP_JEQ_X: - case BPF_S_JMP_JGE_K: - case BPF_S_JMP_JGE_X: - case BPF_S_JMP_JGT_K: - case BPF_S_JMP_JGT_X: - case BPF_S_JMP_JSET_K: - case BPF_S_JMP_JSET_X: - sk_decode_filter(ftest, ftest); + case BPF_RET | BPF_K: + case BPF_RET | BPF_A: + case BPF_ALU | BPF_ADD | BPF_K: + case BPF_ALU | BPF_ADD | BPF_X: + case BPF_ALU | BPF_SUB | BPF_K: + case BPF_ALU | BPF_SUB | BPF_X: + case BPF_ALU | BPF_MUL | BPF_K: + case BPF_ALU | BPF_MUL | BPF_X: + case BPF_ALU | BPF_DIV | BPF_K: + case BPF_ALU | BPF_DIV | BPF_X: + case BPF_ALU | BPF_AND | BPF_K: + case BPF_ALU | BPF_AND | BPF_X: + case BPF_ALU | BPF_OR | BPF_K: + case BPF_ALU | BPF_OR | BPF_X: + case BPF_ALU | BPF_XOR | BPF_K: + case BPF_ALU | BPF_XOR | BPF_X: + case BPF_ALU | BPF_LSH | BPF_K: + case BPF_ALU | BPF_LSH | BPF_X: + case BPF_ALU | BPF_RSH | BPF_K: + case BPF_ALU | BPF_RSH | BPF_X: + case BPF_ALU | BPF_NEG: + case BPF_LD | BPF_IMM: + case BPF_LDX | BPF_IMM: + case BPF_MISC | BPF_TAX: + case BPF_MISC | BPF_TXA: + case BPF_LD | BPF_MEM: + case BPF_LDX | BPF_MEM: + case BPF_ST: + case BPF_STX: + case BPF_JMP | BPF_JA: + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP | BPF_JSET | BPF_X: continue; default: return -EINVAL; @@ -189,7 +187,8 @@ static u32 seccomp_run_filters(int syscall) * value always takes priority (ignoring the DATA). */ for (f = current->seccomp.filter; f; f = f->prev) { - u32 cur_ret = sk_run_filter_int_seccomp(&sd, f->insnsi); + u32 cur_ret = SK_RUN_FILTER(f->prog, (void *)&sd); + if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION)) ret = cur_ret; } @@ -215,7 +214,7 @@ static long seccomp_attach_filter(struct sock_fprog *fprog) return -EINVAL; for (filter = current->seccomp.filter; filter; filter = filter->prev) - total_insns += filter->len + 4; /* include a 4 instr penalty */ + total_insns += filter->prog->len + 4; /* include a 4 instr penalty */ if (total_insns > MAX_INSNS_PER_PATH) return -ENOMEM; @@ -256,19 +255,25 @@ static long seccomp_attach_filter(struct sock_fprog *fprog) /* Allocate a new seccomp_filter */ ret = -ENOMEM; - filter = kzalloc(sizeof(struct seccomp_filter) + - sizeof(struct sock_filter_int) * new_len, + filter = kzalloc(sizeof(struct seccomp_filter), GFP_KERNEL|__GFP_NOWARN); if (!filter) goto free_prog; - ret = sk_convert_filter(fp, fprog->len, filter->insnsi, &new_len); - if (ret) + filter->prog = kzalloc(sk_filter_size(new_len), + GFP_KERNEL|__GFP_NOWARN); + if (!filter->prog) goto free_filter; + + ret = sk_convert_filter(fp, fprog->len, filter->prog->insnsi, &new_len); + if (ret) + goto free_filter_prog; kfree(fp); atomic_set(&filter->usage, 1); - filter->len = new_len; + filter->prog->len = new_len; + + sk_filter_select_runtime(filter->prog); /* * If there is an existing filter, make it the prev and don't drop its @@ -278,6 +283,8 @@ static long seccomp_attach_filter(struct sock_fprog *fprog) current->seccomp.filter = filter; return 0; +free_filter_prog: + kfree(filter->prog); free_filter: kfree(filter); free_prog: @@ -330,6 +337,7 @@ void put_seccomp_filter(struct task_struct *tsk) while (orig && atomic_dec_and_test(&orig->usage)) { struct seccomp_filter *freeme = orig; orig = orig->prev; + sk_filter_free(freeme->prog); kfree(freeme); } } diff --git a/kernel/smp.c b/kernel/smp.c index 306f8180b0d..80c33f8de14 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -29,6 +29,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data); static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue); +static void flush_smp_call_function_queue(bool warn_cpu_offline); + static int hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu) { @@ -51,12 +53,27 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu) #ifdef CONFIG_HOTPLUG_CPU case CPU_UP_CANCELED: case CPU_UP_CANCELED_FROZEN: + /* Fall-through to the CPU_DEAD[_FROZEN] case. */ case CPU_DEAD: case CPU_DEAD_FROZEN: free_cpumask_var(cfd->cpumask); free_percpu(cfd->csd); break; + + case CPU_DYING: + case CPU_DYING_FROZEN: + /* + * The IPIs for the smp-call-function callbacks queued by other + * CPUs might arrive late, either due to hardware latencies or + * because this CPU disabled interrupts (inside stop-machine) + * before the IPIs were sent. So flush out any pending callbacks + * explicitly (without waiting for the IPIs to arrive), to + * ensure that the outgoing CPU doesn't go offline with work + * still pending. + */ + flush_smp_call_function_queue(false); + break; #endif }; @@ -177,23 +194,47 @@ static int generic_exec_single(int cpu, struct call_single_data *csd, return 0; } -/* - * Invoked by arch to handle an IPI for call function single. Must be - * called from the arch with interrupts disabled. +/** + * generic_smp_call_function_single_interrupt - Execute SMP IPI callbacks + * + * Invoked by arch to handle an IPI for call function single. + * Must be called with interrupts disabled. */ void generic_smp_call_function_single_interrupt(void) { + flush_smp_call_function_queue(true); +} + +/** + * flush_smp_call_function_queue - Flush pending smp-call-function callbacks + * + * @warn_cpu_offline: If set to 'true', warn if callbacks were queued on an + * offline CPU. Skip this check if set to 'false'. + * + * Flush any pending smp-call-function callbacks queued on this CPU. This is + * invoked by the generic IPI handler, as well as by a CPU about to go offline, + * to ensure that all pending IPI callbacks are run before it goes completely + * offline. + * + * Loop through the call_single_queue and run all the queued callbacks. + * Must be called with interrupts disabled. + */ +static void flush_smp_call_function_queue(bool warn_cpu_offline) +{ + struct llist_head *head; struct llist_node *entry; struct call_single_data *csd, *csd_next; static bool warned; - entry = llist_del_all(&__get_cpu_var(call_single_queue)); + WARN_ON(!irqs_disabled()); + + head = &__get_cpu_var(call_single_queue); + entry = llist_del_all(head); entry = llist_reverse_order(entry); - /* - * Shouldn't receive this interrupt on a cpu that is not yet online. - */ - if (unlikely(!cpu_online(smp_processor_id()) && !warned)) { + /* There shouldn't be any pending callbacks on an offline CPU. */ + if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) && + !warned && !llist_empty(head))) { warned = true; WARN(1, "IPI on offline CPU %d\n", smp_processor_id()); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index db19e3e2aa4..75b22e22a72 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -136,7 +136,6 @@ static unsigned long dirty_bytes_min = 2 * PAGE_SIZE; /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ static int maxolduid = 65535; static int minolduid; -static int min_percpu_pagelist_fract = 8; static int ngroups_max = NGROUPS_MAX; static const int cap_last_cap = CAP_LAST_CAP; @@ -152,10 +151,6 @@ static unsigned long hung_task_timeout_max = (LONG_MAX/HZ); #ifdef CONFIG_SPARC #endif -#ifdef CONFIG_SPARC64 -extern int sysctl_tsb_ratio; -#endif - #ifdef __hppa__ extern int pwrsw_enabled; #endif @@ -865,6 +860,17 @@ static struct ctl_table kern_table[] = { .extra1 = &zero, .extra2 = &one, }, +#ifdef CONFIG_SMP + { + .procname = "softlockup_all_cpu_backtrace", + .data = &sysctl_softlockup_all_cpu_backtrace, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, +#endif /* CONFIG_SMP */ { .procname = "nmi_watchdog", .data = &watchdog_user_enabled, @@ -1321,7 +1327,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(percpu_pagelist_fraction), .mode = 0644, .proc_handler = percpu_pagelist_fraction_sysctl_handler, - .extra1 = &min_percpu_pagelist_fract, + .extra1 = &zero, }, #ifdef CONFIG_MMU { @@ -2568,11 +2574,11 @@ int proc_do_large_bitmap(struct ctl_table *table, int write, bool first = 1; size_t left = *lenp; unsigned long bitmap_len = table->maxlen; - unsigned long *bitmap = (unsigned long *) table->data; + unsigned long *bitmap = *(unsigned long **) table->data; unsigned long *tmp_bitmap = NULL; char tr_a[] = { '-', ',', '\n' }, tr_b[] = { ',', '\n', 0 }, c; - if (!bitmap_len || !left || (*ppos && !write)) { + if (!bitmap || !bitmap_len || !left || (*ppos && !write)) { *lenp = 0; return 0; } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index c634868c292..7c56c3d0694 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -543,7 +543,7 @@ static void rb_wake_up_waiters(struct irq_work *work) * as data is added to any of the @buffer's cpu buffers. Otherwise * it will wait for data to be added to a specific cpu buffer. */ -void ring_buffer_wait(struct ring_buffer *buffer, int cpu) +int ring_buffer_wait(struct ring_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; DEFINE_WAIT(wait); @@ -557,6 +557,8 @@ void ring_buffer_wait(struct ring_buffer *buffer, int cpu) if (cpu == RING_BUFFER_ALL_CPUS) work = &buffer->irq_work; else { + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return -ENODEV; cpu_buffer = buffer->buffers[cpu]; work = &cpu_buffer->irq_work; } @@ -591,6 +593,7 @@ void ring_buffer_wait(struct ring_buffer *buffer, int cpu) schedule(); finish_wait(&work->waiters, &wait); + return 0; } /** diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 16f7038d1f4..f243444a377 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1085,13 +1085,13 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) } #endif /* CONFIG_TRACER_MAX_TRACE */ -static void wait_on_pipe(struct trace_iterator *iter) +static int wait_on_pipe(struct trace_iterator *iter) { /* Iterators are static, they should be filled or empty */ if (trace_buffer_iter(iter, iter->cpu_file)) - return; + return 0; - ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file); + return ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file); } #ifdef CONFIG_FTRACE_STARTUP_TEST @@ -1338,7 +1338,7 @@ static int trace_create_savedcmd(void) { int ret; - savedcmd = kmalloc(sizeof(struct saved_cmdlines_buffer), GFP_KERNEL); + savedcmd = kmalloc(sizeof(*savedcmd), GFP_KERNEL); if (!savedcmd) return -ENOMEM; @@ -1396,7 +1396,6 @@ void tracing_start(void) arch_spin_unlock(&global_trace.max_lock); - ftrace_start(); out: raw_spin_unlock_irqrestore(&global_trace.start_lock, flags); } @@ -1443,7 +1442,6 @@ void tracing_stop(void) struct ring_buffer *buffer; unsigned long flags; - ftrace_stop(); raw_spin_lock_irqsave(&global_trace.start_lock, flags); if (global_trace.stop_count++) goto out; @@ -3840,7 +3838,7 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf, int r; arch_spin_lock(&trace_cmdline_lock); - r = sprintf(buf, "%u\n", savedcmd->cmdline_num); + r = scnprintf(buf, sizeof(buf), "%u\n", savedcmd->cmdline_num); arch_spin_unlock(&trace_cmdline_lock); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); @@ -3857,7 +3855,7 @@ static int tracing_resize_saved_cmdlines(unsigned int val) { struct saved_cmdlines_buffer *s, *savedcmd_temp; - s = kmalloc(sizeof(struct saved_cmdlines_buffer), GFP_KERNEL); + s = kmalloc(sizeof(*s), GFP_KERNEL); if (!s) return -ENOMEM; @@ -4378,6 +4376,7 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table) static int tracing_wait_pipe(struct file *filp) { struct trace_iterator *iter = filp->private_data; + int ret; while (trace_empty(iter)) { @@ -4399,10 +4398,13 @@ static int tracing_wait_pipe(struct file *filp) mutex_unlock(&iter->mutex); - wait_on_pipe(iter); + ret = wait_on_pipe(iter); mutex_lock(&iter->mutex); + if (ret) + return ret; + if (signal_pending(current)) return -EINTR; } @@ -5327,8 +5329,12 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, goto out_unlock; } mutex_unlock(&trace_types_lock); - wait_on_pipe(iter); + ret = wait_on_pipe(iter); mutex_lock(&trace_types_lock); + if (ret) { + size = ret; + goto out_unlock; + } if (signal_pending(current)) { size = -EINTR; goto out_unlock; @@ -5538,8 +5544,10 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, goto out; } mutex_unlock(&trace_types_lock); - wait_on_pipe(iter); + ret = wait_on_pipe(iter); mutex_lock(&trace_types_lock); + if (ret) + goto out; if (signal_pending(current)) { ret = -EINTR; goto out; @@ -6232,22 +6240,25 @@ static int allocate_trace_buffers(struct trace_array *tr, int size) return 0; } +static void free_trace_buffer(struct trace_buffer *buf) +{ + if (buf->buffer) { + ring_buffer_free(buf->buffer); + buf->buffer = NULL; + free_percpu(buf->data); + buf->data = NULL; + } +} + static void free_trace_buffers(struct trace_array *tr) { if (!tr) return; - if (tr->trace_buffer.buffer) { - ring_buffer_free(tr->trace_buffer.buffer); - tr->trace_buffer.buffer = NULL; - free_percpu(tr->trace_buffer.data); - } + free_trace_buffer(&tr->trace_buffer); #ifdef CONFIG_TRACER_MAX_TRACE - if (tr->max_buffer.buffer) { - ring_buffer_free(tr->max_buffer.buffer); - tr->max_buffer.buffer = NULL; - } + free_trace_buffer(&tr->max_buffer); #endif } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 9e82551dd56..9258f5a815d 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -252,7 +252,7 @@ static inline struct trace_array *top_trace_array(void) { struct trace_array *tr; - if (list_empty(ftrace_trace_arrays.prev)) + if (list_empty(&ftrace_trace_arrays)) return NULL; tr = list_entry(ftrace_trace_arrays.prev, diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index c894614de14..5d12bb407b4 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -248,8 +248,8 @@ void perf_trace_del(struct perf_event *p_event, int flags) tp_event->class->reg(tp_event, TRACE_REG_PERF_DEL, p_event); } -__kprobes void *perf_trace_buf_prepare(int size, unsigned short type, - struct pt_regs *regs, int *rctxp) +void *perf_trace_buf_prepare(int size, unsigned short type, + struct pt_regs *regs, int *rctxp) { struct trace_entry *entry; unsigned long flags; @@ -281,6 +281,7 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type, return raw_data; } EXPORT_SYMBOL_GPL(perf_trace_buf_prepare); +NOKPROBE_SYMBOL(perf_trace_buf_prepare); #ifdef CONFIG_FUNCTION_TRACER static void diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index ef2fba1f46b..282f6e4e553 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -40,27 +40,27 @@ struct trace_kprobe { (sizeof(struct probe_arg) * (n))) -static __kprobes bool trace_kprobe_is_return(struct trace_kprobe *tk) +static nokprobe_inline bool trace_kprobe_is_return(struct trace_kprobe *tk) { return tk->rp.handler != NULL; } -static __kprobes const char *trace_kprobe_symbol(struct trace_kprobe *tk) +static nokprobe_inline const char *trace_kprobe_symbol(struct trace_kprobe *tk) { return tk->symbol ? tk->symbol : "unknown"; } -static __kprobes unsigned long trace_kprobe_offset(struct trace_kprobe *tk) +static nokprobe_inline unsigned long trace_kprobe_offset(struct trace_kprobe *tk) { return tk->rp.kp.offset; } -static __kprobes bool trace_kprobe_has_gone(struct trace_kprobe *tk) +static nokprobe_inline bool trace_kprobe_has_gone(struct trace_kprobe *tk) { return !!(kprobe_gone(&tk->rp.kp)); } -static __kprobes bool trace_kprobe_within_module(struct trace_kprobe *tk, +static nokprobe_inline bool trace_kprobe_within_module(struct trace_kprobe *tk, struct module *mod) { int len = strlen(mod->name); @@ -68,7 +68,7 @@ static __kprobes bool trace_kprobe_within_module(struct trace_kprobe *tk, return strncmp(mod->name, name, len) == 0 && name[len] == ':'; } -static __kprobes bool trace_kprobe_is_on_module(struct trace_kprobe *tk) +static nokprobe_inline bool trace_kprobe_is_on_module(struct trace_kprobe *tk) { return !!strchr(trace_kprobe_symbol(tk), ':'); } @@ -132,19 +132,21 @@ struct symbol_cache *alloc_symbol_cache(const char *sym, long offset) * Kprobes-specific fetch functions */ #define DEFINE_FETCH_stack(type) \ -static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\ +static void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs, \ void *offset, void *dest) \ { \ *(type *)dest = (type)regs_get_kernel_stack_nth(regs, \ (unsigned int)((unsigned long)offset)); \ -} +} \ +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(stack, type)); + DEFINE_BASIC_FETCH_FUNCS(stack) /* No string on the stack entry */ #define fetch_stack_string NULL #define fetch_stack_string_size NULL #define DEFINE_FETCH_memory(type) \ -static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\ +static void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs, \ void *addr, void *dest) \ { \ type retval; \ @@ -152,14 +154,16 @@ static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\ *(type *)dest = 0; \ else \ *(type *)dest = retval; \ -} +} \ +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, type)); + DEFINE_BASIC_FETCH_FUNCS(memory) /* * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max * length and relative data location. */ -static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs, - void *addr, void *dest) +static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs, + void *addr, void *dest) { long ret; int maxlen = get_rloc_len(*(u32 *)dest); @@ -193,10 +197,11 @@ static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs, get_rloc_offs(*(u32 *)dest)); } } +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, string)); /* Return the length of string -- including null terminal byte */ -static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs, - void *addr, void *dest) +static void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs, + void *addr, void *dest) { mm_segment_t old_fs; int ret, len = 0; @@ -219,17 +224,19 @@ static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs, else *(u32 *)dest = len; } +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, string_size)); #define DEFINE_FETCH_symbol(type) \ -__kprobes void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs, \ - void *data, void *dest) \ +void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs, void *data, void *dest)\ { \ struct symbol_cache *sc = data; \ if (sc->addr) \ fetch_memory_##type(regs, (void *)sc->addr, dest); \ else \ *(type *)dest = 0; \ -} +} \ +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(symbol, type)); + DEFINE_BASIC_FETCH_FUNCS(symbol) DEFINE_FETCH_symbol(string) DEFINE_FETCH_symbol(string_size) @@ -907,7 +914,7 @@ static const struct file_operations kprobe_profile_ops = { }; /* Kprobe handler */ -static __kprobes void +static nokprobe_inline void __kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs, struct ftrace_event_file *ftrace_file) { @@ -943,7 +950,7 @@ __kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs, entry, irq_flags, pc, regs); } -static __kprobes void +static void kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs) { struct event_file_link *link; @@ -951,9 +958,10 @@ kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs) list_for_each_entry_rcu(link, &tk->tp.files, list) __kprobe_trace_func(tk, regs, link->file); } +NOKPROBE_SYMBOL(kprobe_trace_func); /* Kretprobe handler */ -static __kprobes void +static nokprobe_inline void __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, struct pt_regs *regs, struct ftrace_event_file *ftrace_file) @@ -991,7 +999,7 @@ __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, entry, irq_flags, pc, regs); } -static __kprobes void +static void kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, struct pt_regs *regs) { @@ -1000,6 +1008,7 @@ kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, list_for_each_entry_rcu(link, &tk->tp.files, list) __kretprobe_trace_func(tk, ri, regs, link->file); } +NOKPROBE_SYMBOL(kretprobe_trace_func); /* Event entry printers */ static enum print_line_t @@ -1131,7 +1140,7 @@ static int kretprobe_event_define_fields(struct ftrace_event_call *event_call) #ifdef CONFIG_PERF_EVENTS /* Kprobe profile handler */ -static __kprobes void +static void kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) { struct ftrace_event_call *call = &tk->tp.call; @@ -1158,9 +1167,10 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize); perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL); } +NOKPROBE_SYMBOL(kprobe_perf_func); /* Kretprobe profile handler */ -static __kprobes void +static void kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, struct pt_regs *regs) { @@ -1188,6 +1198,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize); perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL); } +NOKPROBE_SYMBOL(kretprobe_perf_func); #endif /* CONFIG_PERF_EVENTS */ /* @@ -1196,9 +1207,8 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, * kprobe_trace_self_tests_init() does enable_trace_probe/disable_trace_probe * lockless, but we can't race with this __init function. */ -static __kprobes -int kprobe_register(struct ftrace_event_call *event, - enum trace_reg type, void *data) +static int kprobe_register(struct ftrace_event_call *event, + enum trace_reg type, void *data) { struct trace_kprobe *tk = (struct trace_kprobe *)event->data; struct ftrace_event_file *file = data; @@ -1224,8 +1234,7 @@ int kprobe_register(struct ftrace_event_call *event, return 0; } -static __kprobes -int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs) +static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs) { struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp); @@ -1239,9 +1248,10 @@ int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs) #endif return 0; /* We don't tweek kernel, so just return 0 */ } +NOKPROBE_SYMBOL(kprobe_dispatcher); -static __kprobes -int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs) +static int +kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs) { struct trace_kprobe *tk = container_of(ri->rp, struct trace_kprobe, rp); @@ -1255,6 +1265,7 @@ int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs) #endif return 0; /* We don't tweek kernel, so just return 0 */ } +NOKPROBE_SYMBOL(kretprobe_dispatcher); static struct trace_event_functions kretprobe_funcs = { .trace = print_kretprobe_event diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 8364a421b4d..d4b9fc22cd2 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -37,13 +37,13 @@ const char *reserved_field_names[] = { /* Printing in basic type function template */ #define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt) \ -__kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, \ - const char *name, \ - void *data, void *ent) \ +int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, const char *name, \ + void *data, void *ent) \ { \ return trace_seq_printf(s, " %s=" fmt, name, *(type *)data); \ } \ -const char PRINT_TYPE_FMT_NAME(type)[] = fmt; +const char PRINT_TYPE_FMT_NAME(type)[] = fmt; \ +NOKPROBE_SYMBOL(PRINT_TYPE_FUNC_NAME(type)); DEFINE_BASIC_PRINT_TYPE_FUNC(u8 , "0x%x") DEFINE_BASIC_PRINT_TYPE_FUNC(u16, "0x%x") @@ -55,9 +55,8 @@ DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%d") DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%Ld") /* Print type function for string type */ -__kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s, - const char *name, - void *data, void *ent) +int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s, const char *name, + void *data, void *ent) { int len = *(u32 *)data >> 16; @@ -67,6 +66,7 @@ __kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s, return trace_seq_printf(s, " %s=\"%s\"", name, (const char *)get_loc_data(data, ent)); } +NOKPROBE_SYMBOL(PRINT_TYPE_FUNC_NAME(string)); const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\""; @@ -81,23 +81,24 @@ const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\""; /* Data fetch function templates */ #define DEFINE_FETCH_reg(type) \ -__kprobes void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs, \ - void *offset, void *dest) \ +void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs, void *offset, void *dest) \ { \ *(type *)dest = (type)regs_get_register(regs, \ (unsigned int)((unsigned long)offset)); \ -} +} \ +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(reg, type)); DEFINE_BASIC_FETCH_FUNCS(reg) /* No string on the register */ #define fetch_reg_string NULL #define fetch_reg_string_size NULL #define DEFINE_FETCH_retval(type) \ -__kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs, \ - void *dummy, void *dest) \ +void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs, \ + void *dummy, void *dest) \ { \ *(type *)dest = (type)regs_return_value(regs); \ -} +} \ +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(retval, type)); DEFINE_BASIC_FETCH_FUNCS(retval) /* No string on the retval */ #define fetch_retval_string NULL @@ -112,8 +113,8 @@ struct deref_fetch_param { }; #define DEFINE_FETCH_deref(type) \ -__kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs, \ - void *data, void *dest) \ +void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs, \ + void *data, void *dest) \ { \ struct deref_fetch_param *dprm = data; \ unsigned long addr; \ @@ -123,12 +124,13 @@ __kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs, \ dprm->fetch(regs, (void *)addr, dest); \ } else \ *(type *)dest = 0; \ -} +} \ +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(deref, type)); DEFINE_BASIC_FETCH_FUNCS(deref) DEFINE_FETCH_deref(string) -__kprobes void FETCH_FUNC_NAME(deref, string_size)(struct pt_regs *regs, - void *data, void *dest) +void FETCH_FUNC_NAME(deref, string_size)(struct pt_regs *regs, + void *data, void *dest) { struct deref_fetch_param *dprm = data; unsigned long addr; @@ -140,16 +142,18 @@ __kprobes void FETCH_FUNC_NAME(deref, string_size)(struct pt_regs *regs, } else *(string_size *)dest = 0; } +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(deref, string_size)); -static __kprobes void update_deref_fetch_param(struct deref_fetch_param *data) +static void update_deref_fetch_param(struct deref_fetch_param *data) { if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) update_deref_fetch_param(data->orig.data); else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) update_symbol_cache(data->orig.data); } +NOKPROBE_SYMBOL(update_deref_fetch_param); -static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data) +static void free_deref_fetch_param(struct deref_fetch_param *data) { if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) free_deref_fetch_param(data->orig.data); @@ -157,6 +161,7 @@ static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data) free_symbol_cache(data->orig.data); kfree(data); } +NOKPROBE_SYMBOL(free_deref_fetch_param); /* Bitfield fetch function */ struct bitfield_fetch_param { @@ -166,8 +171,8 @@ struct bitfield_fetch_param { }; #define DEFINE_FETCH_bitfield(type) \ -__kprobes void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs, \ - void *data, void *dest) \ +void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs, \ + void *data, void *dest) \ { \ struct bitfield_fetch_param *bprm = data; \ type buf = 0; \ @@ -177,13 +182,13 @@ __kprobes void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs, \ buf >>= bprm->low_shift; \ } \ *(type *)dest = buf; \ -} - +} \ +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(bitfield, type)); DEFINE_BASIC_FETCH_FUNCS(bitfield) #define fetch_bitfield_string NULL #define fetch_bitfield_string_size NULL -static __kprobes void +static void update_bitfield_fetch_param(struct bitfield_fetch_param *data) { /* @@ -196,7 +201,7 @@ update_bitfield_fetch_param(struct bitfield_fetch_param *data) update_symbol_cache(data->orig.data); } -static __kprobes void +static void free_bitfield_fetch_param(struct bitfield_fetch_param *data) { /* @@ -255,17 +260,17 @@ fail: } /* Special function : only accept unsigned long */ -static __kprobes void fetch_kernel_stack_address(struct pt_regs *regs, - void *dummy, void *dest) +static void fetch_kernel_stack_address(struct pt_regs *regs, void *dummy, void *dest) { *(unsigned long *)dest = kernel_stack_pointer(regs); } +NOKPROBE_SYMBOL(fetch_kernel_stack_address); -static __kprobes void fetch_user_stack_address(struct pt_regs *regs, - void *dummy, void *dest) +static void fetch_user_stack_address(struct pt_regs *regs, void *dummy, void *dest) { *(unsigned long *)dest = user_stack_pointer(regs); } +NOKPROBE_SYMBOL(fetch_user_stack_address); static fetch_func_t get_fetch_size_function(const struct fetch_type *type, fetch_func_t orig_fn, diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index fb1ab5dfbd4..4f815fbce16 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -81,13 +81,13 @@ */ #define convert_rloc_to_loc(dl, offs) ((u32)(dl) + (offs)) -static inline void *get_rloc_data(u32 *dl) +static nokprobe_inline void *get_rloc_data(u32 *dl) { return (u8 *)dl + get_rloc_offs(*dl); } /* For data_loc conversion */ -static inline void *get_loc_data(u32 *dl, void *ent) +static nokprobe_inline void *get_loc_data(u32 *dl, void *ent) { return (u8 *)ent + get_rloc_offs(*dl); } @@ -136,9 +136,8 @@ typedef u32 string_size; /* Printing in basic type function template */ #define DECLARE_BASIC_PRINT_TYPE_FUNC(type) \ -__kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, \ - const char *name, \ - void *data, void *ent); \ +int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, const char *name, \ + void *data, void *ent); \ extern const char PRINT_TYPE_FMT_NAME(type)[] DECLARE_BASIC_PRINT_TYPE_FUNC(u8); @@ -303,7 +302,7 @@ static inline bool trace_probe_is_registered(struct trace_probe *tp) return !!(tp->flags & TP_FLAG_REGISTERED); } -static inline __kprobes void call_fetch(struct fetch_param *fprm, +static nokprobe_inline void call_fetch(struct fetch_param *fprm, struct pt_regs *regs, void *dest) { return fprm->fn(regs, fprm->data, dest); @@ -351,7 +350,7 @@ extern ssize_t traceprobe_probes_write(struct file *file, extern int traceprobe_command(const char *buf, int (*createfn)(int, char**)); /* Sum up total data length for dynamic arraies (strings) */ -static inline __kprobes int +static nokprobe_inline int __get_data_size(struct trace_probe *tp, struct pt_regs *regs) { int i, ret = 0; @@ -367,7 +366,7 @@ __get_data_size(struct trace_probe *tp, struct pt_regs *regs) } /* Store the value of each argument */ -static inline __kprobes void +static nokprobe_inline void store_trace_args(int ent_size, struct trace_probe *tp, struct pt_regs *regs, u8 *data, int maxlen) { diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index c082a744134..3c9b97e6b1f 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -108,8 +108,8 @@ static unsigned long get_user_stack_nth(struct pt_regs *regs, unsigned int n) * Uprobes-specific fetch functions */ #define DEFINE_FETCH_stack(type) \ -static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\ - void *offset, void *dest) \ +static void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs, \ + void *offset, void *dest) \ { \ *(type *)dest = (type)get_user_stack_nth(regs, \ ((unsigned long)offset)); \ @@ -120,8 +120,8 @@ DEFINE_BASIC_FETCH_FUNCS(stack) #define fetch_stack_string_size NULL #define DEFINE_FETCH_memory(type) \ -static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\ - void *addr, void *dest) \ +static void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs, \ + void *addr, void *dest) \ { \ type retval; \ void __user *vaddr = (void __force __user *) addr; \ @@ -136,8 +136,8 @@ DEFINE_BASIC_FETCH_FUNCS(memory) * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max * length and relative data location. */ -static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs, - void *addr, void *dest) +static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs, + void *addr, void *dest) { long ret; u32 rloc = *(u32 *)dest; @@ -158,8 +158,8 @@ static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs, } } -static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs, - void *addr, void *dest) +static void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs, + void *addr, void *dest) { int len; void __user *vaddr = (void __force __user *) addr; @@ -184,8 +184,8 @@ static unsigned long translate_user_vaddr(void *file_offset) } #define DEFINE_FETCH_file_offset(type) \ -static __kprobes void FETCH_FUNC_NAME(file_offset, type)(struct pt_regs *regs,\ - void *offset, void *dest) \ +static void FETCH_FUNC_NAME(file_offset, type)(struct pt_regs *regs, \ + void *offset, void *dest)\ { \ void *vaddr = (void *)translate_user_vaddr(offset); \ \ @@ -893,6 +893,9 @@ probe_event_enable(struct trace_uprobe *tu, struct ftrace_event_file *file, int ret; if (file) { + if (tu->tp.flags & TP_FLAG_PROFILE) + return -EINTR; + link = kmalloc(sizeof(*link), GFP_KERNEL); if (!link) return -ENOMEM; @@ -901,29 +904,40 @@ probe_event_enable(struct trace_uprobe *tu, struct ftrace_event_file *file, list_add_tail_rcu(&link->list, &tu->tp.files); tu->tp.flags |= TP_FLAG_TRACE; - } else - tu->tp.flags |= TP_FLAG_PROFILE; + } else { + if (tu->tp.flags & TP_FLAG_TRACE) + return -EINTR; - ret = uprobe_buffer_enable(); - if (ret < 0) - return ret; + tu->tp.flags |= TP_FLAG_PROFILE; + } WARN_ON(!uprobe_filter_is_empty(&tu->filter)); if (enabled) return 0; + ret = uprobe_buffer_enable(); + if (ret) + goto err_flags; + tu->consumer.filter = filter; ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); - if (ret) { - if (file) { - list_del(&link->list); - kfree(link); - tu->tp.flags &= ~TP_FLAG_TRACE; - } else - tu->tp.flags &= ~TP_FLAG_PROFILE; - } + if (ret) + goto err_buffer; + + return 0; + err_buffer: + 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; + } return ret; } @@ -1009,56 +1023,60 @@ uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event) return __uprobe_perf_filter(&tu->filter, event->hw.tp_target->mm); } -static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) +static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event) { bool done; write_lock(&tu->filter.rwlock); if (event->hw.tp_target) { - /* - * event->parent != NULL means copy_process(), we can avoid - * uprobe_apply(). current->mm must be probed and we can rely - * on dup_mmap() which preserves the already installed bp's. - * - * attr.enable_on_exec means that exec/mmap will install the - * breakpoints we need. - */ + list_del(&event->hw.tp_list); done = tu->filter.nr_systemwide || - event->parent || event->attr.enable_on_exec || + (event->hw.tp_target->flags & PF_EXITING) || uprobe_filter_event(tu, event); - list_add(&event->hw.tp_list, &tu->filter.perf_events); } else { + tu->filter.nr_systemwide--; done = tu->filter.nr_systemwide; - tu->filter.nr_systemwide++; } write_unlock(&tu->filter.rwlock); if (!done) - uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); + return uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); return 0; } -static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event) +static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) { bool done; + int err; write_lock(&tu->filter.rwlock); if (event->hw.tp_target) { - list_del(&event->hw.tp_list); + /* + * event->parent != NULL means copy_process(), we can avoid + * uprobe_apply(). current->mm must be probed and we can rely + * on dup_mmap() which preserves the already installed bp's. + * + * attr.enable_on_exec means that exec/mmap will install the + * breakpoints we need. + */ done = tu->filter.nr_systemwide || - (event->hw.tp_target->flags & PF_EXITING) || + event->parent || event->attr.enable_on_exec || uprobe_filter_event(tu, event); + list_add(&event->hw.tp_list, &tu->filter.perf_events); } else { - tu->filter.nr_systemwide--; done = tu->filter.nr_systemwide; + tu->filter.nr_systemwide++; } write_unlock(&tu->filter.rwlock); - if (!done) - uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); - - return 0; + err = 0; + if (!done) { + err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); + if (err) + uprobe_perf_close(tu, event); + } + return err; } static bool uprobe_perf_filter(struct uprobe_consumer *uc, @@ -1197,12 +1215,6 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) current->utask->vaddr = (unsigned long) &udd; -#ifdef CONFIG_PERF_EVENTS - if ((tu->tp.flags & TP_FLAG_TRACE) == 0 && - !uprobe_perf_filter(&tu->consumer, 0, current->mm)) - return UPROBE_HANDLER_REMOVE; -#endif - if (WARN_ON_ONCE(!uprobe_cpu_buffer)) return 0; diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 33cbd8c203f..3490407dc7b 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -492,33 +492,29 @@ static int sys_tracepoint_refcount; void syscall_regfunc(void) { - unsigned long flags; - struct task_struct *g, *t; + struct task_struct *p, *t; if (!sys_tracepoint_refcount) { - read_lock_irqsave(&tasklist_lock, flags); - do_each_thread(g, t) { - /* Skip kernel threads. */ - if (t->mm) - set_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT); - } while_each_thread(g, t); - read_unlock_irqrestore(&tasklist_lock, flags); + read_lock(&tasklist_lock); + for_each_process_thread(p, t) { + set_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT); + } + read_unlock(&tasklist_lock); } sys_tracepoint_refcount++; } void syscall_unregfunc(void) { - unsigned long flags; - struct task_struct *g, *t; + struct task_struct *p, *t; sys_tracepoint_refcount--; if (!sys_tracepoint_refcount) { - read_lock_irqsave(&tasklist_lock, flags); - do_each_thread(g, t) { + read_lock(&tasklist_lock); + for_each_process_thread(p, t) { clear_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT); - } while_each_thread(g, t); - read_unlock_irqrestore(&tasklist_lock, flags); + } + read_unlock(&tasklist_lock); } } #endif diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 516203e665f..c3319bd1b04 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -31,6 +31,12 @@ int watchdog_user_enabled = 1; int __read_mostly watchdog_thresh = 10; +#ifdef CONFIG_SMP +int __read_mostly sysctl_softlockup_all_cpu_backtrace; +#else +#define sysctl_softlockup_all_cpu_backtrace 0 +#endif + static int __read_mostly watchdog_running; static u64 __read_mostly sample_period; @@ -47,6 +53,7 @@ static DEFINE_PER_CPU(bool, watchdog_nmi_touch); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); #endif +static unsigned long soft_lockup_nmi_warn; /* boot commands */ /* @@ -95,6 +102,15 @@ static int __init nosoftlockup_setup(char *str) } __setup("nosoftlockup", nosoftlockup_setup); /* */ +#ifdef CONFIG_SMP +static int __init softlockup_all_cpu_backtrace_setup(char *str) +{ + sysctl_softlockup_all_cpu_backtrace = + !!simple_strtol(str, NULL, 0); + return 1; +} +__setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup); +#endif /* * Hard-lockup warnings should be triggered after just a few seconds. Soft- @@ -271,6 +287,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) unsigned long touch_ts = __this_cpu_read(watchdog_touch_ts); struct pt_regs *regs = get_irq_regs(); int duration; + int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; /* kick the hardlockup detector */ watchdog_interrupt_count(); @@ -317,6 +334,17 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) if (__this_cpu_read(soft_watchdog_warn) == true) return HRTIMER_RESTART; + if (softlockup_all_cpu_backtrace) { + /* Prevent multiple soft-lockup reports if one cpu is already + * engaged in dumping cpu back traces + */ + if (test_and_set_bit(0, &soft_lockup_nmi_warn)) { + /* Someone else will report us. Let's give up */ + __this_cpu_write(soft_watchdog_warn, true); + return HRTIMER_RESTART; + } + } + printk(KERN_EMERG "BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); @@ -327,6 +355,17 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) else dump_stack(); + if (softlockup_all_cpu_backtrace) { + /* Avoid generating two back traces for current + * given that one is already made above + */ + trigger_allbutself_cpu_backtrace(); + + clear_bit(0, &soft_lockup_nmi_warn); + /* Barrier to sync with other cpus */ + smp_mb__after_atomic(); + } + if (softlockup_panic) panic("softlockup: hung tasks"); __this_cpu_write(soft_watchdog_warn, true); @@ -527,10 +566,8 @@ static void update_timers_all_cpus(void) int cpu; get_online_cpus(); - preempt_disable(); for_each_online_cpu(cpu) update_timers(cpu); - preempt_enable(); put_online_cpus(); } |