diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/bpf/syscall.c | 30 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 9 | ||||
-rw-r--r-- | kernel/dma/contiguous.c | 8 | ||||
-rw-r--r-- | kernel/dma/direct.c | 10 | ||||
-rw-r--r-- | kernel/irq/irqdesc.c | 15 | ||||
-rw-r--r-- | kernel/kprobes.c | 8 | ||||
-rw-r--r-- | kernel/module.c | 4 | ||||
-rw-r--r-- | kernel/sched/core.c | 5 | ||||
-rw-r--r-- | kernel/sched/psi.c | 8 | ||||
-rw-r--r-- | kernel/signal.c | 5 | ||||
-rw-r--r-- | kernel/time/timekeeping.c | 5 | ||||
-rw-r--r-- | kernel/time/vsyscall.c | 22 |
12 files changed, 89 insertions, 40 deletions
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5d141f16f6fa..272071e9112f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1707,20 +1707,26 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) if (err) goto free_used_maps; - err = bpf_prog_new_fd(prog); - if (err < 0) { - /* failed to allocate fd. - * bpf_prog_put() is needed because the above - * bpf_prog_alloc_id() has published the prog - * to the userspace and the userspace may - * have refcnt-ed it through BPF_PROG_GET_FD_BY_ID. - */ - bpf_prog_put(prog); - return err; - } - + /* Upon success of bpf_prog_alloc_id(), the BPF prog is + * effectively publicly exposed. However, retrieving via + * bpf_prog_get_fd_by_id() will take another reference, + * therefore it cannot be gone underneath us. + * + * Only for the time /after/ successful bpf_prog_new_fd() + * and before returning to userspace, we might just hold + * one reference and any parallel close on that fd could + * rip everything out. Hence, below notifications must + * happen before bpf_prog_new_fd(). + * + * Also, any failure handling from this point onwards must + * be using bpf_prog_put() given the program is exposed. + */ bpf_prog_kallsyms_add(prog); perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0); + + err = bpf_prog_new_fd(prog); + if (err < 0) + bpf_prog_put(prog); return err; free_used_maps: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 10c0ff93f52b..16d66bd7af09 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -985,9 +985,6 @@ static void __mark_reg_unbounded(struct bpf_reg_state *reg) reg->smax_value = S64_MAX; reg->umin_value = 0; reg->umax_value = U64_MAX; - - /* constant backtracking is enabled for root only for now */ - reg->precise = capable(CAP_SYS_ADMIN) ? false : true; } /* Mark a register as having a completely unknown (scalar) value. */ @@ -1014,7 +1011,11 @@ static void mark_reg_unknown(struct bpf_verifier_env *env, __mark_reg_not_init(regs + regno); return; } - __mark_reg_unknown(regs + regno); + regs += regno; + __mark_reg_unknown(regs); + /* constant backtracking is enabled for root without bpf2bpf calls */ + regs->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ? + true : false; } static void __mark_reg_not_init(struct bpf_reg_state *reg) diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c index 2bd410f934b3..69cfb4345388 100644 --- a/kernel/dma/contiguous.c +++ b/kernel/dma/contiguous.c @@ -230,9 +230,7 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages, */ struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp) { - int node = dev ? dev_to_node(dev) : NUMA_NO_NODE; - size_t count = PAGE_ALIGN(size) >> PAGE_SHIFT; - size_t align = get_order(PAGE_ALIGN(size)); + size_t count = size >> PAGE_SHIFT; struct page *page = NULL; struct cma *cma = NULL; @@ -243,14 +241,12 @@ struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp) /* CMA can be used only in the context which permits sleeping */ if (cma && gfpflags_allow_blocking(gfp)) { + size_t align = get_order(size); size_t cma_align = min_t(size_t, align, CONFIG_CMA_ALIGNMENT); page = cma_alloc(cma, count, cma_align, gfp & __GFP_NOWARN); } - /* Fallback allocation of normal pages */ - if (!page) - page = alloc_pages_node(node, gfp, align); return page; } diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 795c9b095d75..706113c6bebc 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -85,6 +85,8 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { + size_t alloc_size = PAGE_ALIGN(size); + int node = dev_to_node(dev); struct page *page = NULL; u64 phys_mask; @@ -95,8 +97,14 @@ struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, gfp &= ~__GFP_ZERO; gfp |= __dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask, &phys_mask); + page = dma_alloc_contiguous(dev, alloc_size, gfp); + if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { + dma_free_contiguous(dev, page, alloc_size); + page = NULL; + } again: - page = dma_alloc_contiguous(dev, size, gfp); + if (!page) + page = alloc_pages_node(node, gfp, get_order(alloc_size)); if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { dma_free_contiguous(dev, page, size); page = NULL; diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 9484e88dabc2..9be995fc3c5a 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -295,6 +295,18 @@ static void irq_sysfs_add(int irq, struct irq_desc *desc) } } +static void irq_sysfs_del(struct irq_desc *desc) +{ + /* + * If irq_sysfs_init() has not yet been invoked (early boot), then + * irq_kobj_base is NULL and the descriptor was never added. + * kobject_del() complains about a object with no parent, so make + * it conditional. + */ + if (irq_kobj_base) + kobject_del(&desc->kobj); +} + static int __init irq_sysfs_init(void) { struct irq_desc *desc; @@ -325,6 +337,7 @@ static struct kobj_type irq_kobj_type = { }; static void irq_sysfs_add(int irq, struct irq_desc *desc) {} +static void irq_sysfs_del(struct irq_desc *desc) {} #endif /* CONFIG_SYSFS */ @@ -438,7 +451,7 @@ static void free_desc(unsigned int irq) * The sysfs entry must be serialized against a concurrent * irq_sysfs_init() as well. */ - kobject_del(&desc->kobj); + irq_sysfs_del(desc); delete_irq_desc(irq); /* diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 9873fc627d61..d9770a5393c8 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -470,6 +470,7 @@ static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer); */ static void do_optimize_kprobes(void) { + lockdep_assert_held(&text_mutex); /* * The optimization/unoptimization refers online_cpus via * stop_machine() and cpu-hotplug modifies online_cpus. @@ -487,9 +488,7 @@ static void do_optimize_kprobes(void) list_empty(&optimizing_list)) return; - mutex_lock(&text_mutex); arch_optimize_kprobes(&optimizing_list); - mutex_unlock(&text_mutex); } /* @@ -500,6 +499,7 @@ static void do_unoptimize_kprobes(void) { struct optimized_kprobe *op, *tmp; + lockdep_assert_held(&text_mutex); /* See comment in do_optimize_kprobes() */ lockdep_assert_cpus_held(); @@ -507,7 +507,6 @@ static void do_unoptimize_kprobes(void) if (list_empty(&unoptimizing_list)) return; - mutex_lock(&text_mutex); arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list); /* Loop free_list for disarming */ list_for_each_entry_safe(op, tmp, &freeing_list, list) { @@ -524,7 +523,6 @@ static void do_unoptimize_kprobes(void) } else list_del_init(&op->list); } - mutex_unlock(&text_mutex); } /* Reclaim all kprobes on the free_list */ @@ -556,6 +554,7 @@ static void kprobe_optimizer(struct work_struct *work) { mutex_lock(&kprobe_mutex); cpus_read_lock(); + mutex_lock(&text_mutex); /* Lock modules while optimizing kprobes */ mutex_lock(&module_mutex); @@ -583,6 +582,7 @@ static void kprobe_optimizer(struct work_struct *work) do_free_cleaned_kprobes(); mutex_unlock(&module_mutex); + mutex_unlock(&text_mutex); cpus_read_unlock(); mutex_unlock(&kprobe_mutex); diff --git a/kernel/module.c b/kernel/module.c index 5933395af9a0..9ee93421269c 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -65,9 +65,9 @@ /* * Modules' sections will be aligned on page boundaries * to ensure complete separation of code and data, but - * only when CONFIG_STRICT_MODULE_RWX=y + * only when CONFIG_ARCH_HAS_STRICT_MODULE_RWX=y */ -#ifdef CONFIG_STRICT_MODULE_RWX +#ifdef CONFIG_ARCH_HAS_STRICT_MODULE_RWX # define debug_align(X) ALIGN(X, PAGE_SIZE) #else # define debug_align(X) (X) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2b037f195473..010d578118d6 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3904,7 +3904,7 @@ void __noreturn do_task_dead(void) static inline void sched_submit_work(struct task_struct *tsk) { - if (!tsk->state || tsk_is_pi_blocked(tsk)) + if (!tsk->state) return; /* @@ -3920,6 +3920,9 @@ static inline void sched_submit_work(struct task_struct *tsk) preempt_enable_no_resched(); } + if (tsk_is_pi_blocked(tsk)) + return; + /* * If we are going to sleep and we have plugged IO queued, * make sure to submit it to avoid deadlocks. diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 23fbbcc414d5..6e52b67b420e 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1131,7 +1131,15 @@ static void psi_trigger_destroy(struct kref *ref) * deadlock while waiting for psi_poll_work to acquire trigger_lock */ if (kworker_to_destroy) { + /* + * After the RCU grace period has expired, the worker + * can no longer be found through group->poll_kworker. + * But it might have been already scheduled before + * that - deschedule it cleanly before destroying it. + */ kthread_cancel_delayed_work_sync(&group->poll_work); + atomic_set(&group->poll_scheduled, 0); + kthread_destroy_worker(kworker_to_destroy); } kfree(t); diff --git a/kernel/signal.c b/kernel/signal.c index e667be6907d7..534fec266a33 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -90,6 +90,11 @@ static bool sig_task_ignored(struct task_struct *t, int sig, bool force) handler == SIG_DFL && !(force && sig_kernel_only(sig))) return true; + /* Only allow kernel generated signals to this kthread */ + if (unlikely((t->flags & PF_KTHREAD) && + (handler == SIG_KTHREAD_KERNEL) && !force)) + return true; + return sig_handler_ignored(handler, sig); } diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index d911c8470149..ca69290bee2a 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -146,6 +146,11 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { tk->offs_boot = ktime_add(tk->offs_boot, delta); + /* + * Timespec representation for VDSO update to avoid 64bit division + * on every update. + */ + tk->monotonic_to_boot = ktime_to_timespec64(tk->offs_boot); } /* diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c index 8cf3596a4ce6..4bc37ac3bb05 100644 --- a/kernel/time/vsyscall.c +++ b/kernel/time/vsyscall.c @@ -17,7 +17,7 @@ static inline void update_vdso_data(struct vdso_data *vdata, struct timekeeper *tk) { struct vdso_timestamp *vdso_ts; - u64 nsec; + u64 nsec, sec; vdata[CS_HRES_COARSE].cycle_last = tk->tkr_mono.cycle_last; vdata[CS_HRES_COARSE].mask = tk->tkr_mono.mask; @@ -45,23 +45,27 @@ static inline void update_vdso_data(struct vdso_data *vdata, } vdso_ts->nsec = nsec; - /* CLOCK_MONOTONIC_RAW */ - vdso_ts = &vdata[CS_RAW].basetime[CLOCK_MONOTONIC_RAW]; - vdso_ts->sec = tk->raw_sec; - vdso_ts->nsec = tk->tkr_raw.xtime_nsec; + /* Copy MONOTONIC time for BOOTTIME */ + sec = vdso_ts->sec; + /* Add the boot offset */ + sec += tk->monotonic_to_boot.tv_sec; + nsec += (u64)tk->monotonic_to_boot.tv_nsec << tk->tkr_mono.shift; /* CLOCK_BOOTTIME */ vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_BOOTTIME]; - vdso_ts->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - nsec = tk->tkr_mono.xtime_nsec; - nsec += ((u64)(tk->wall_to_monotonic.tv_nsec + - ktime_to_ns(tk->offs_boot)) << tk->tkr_mono.shift); + vdso_ts->sec = sec; + while (nsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) { nsec -= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift); vdso_ts->sec++; } vdso_ts->nsec = nsec; + /* CLOCK_MONOTONIC_RAW */ + vdso_ts = &vdata[CS_RAW].basetime[CLOCK_MONOTONIC_RAW]; + vdso_ts->sec = tk->raw_sec; + vdso_ts->nsec = tk->tkr_raw.xtime_nsec; + /* CLOCK_TAI */ vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_TAI]; vdso_ts->sec = tk->xtime_sec + (s64)tk->tai_offset; |