diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/Makefile | 4 | ||||
| -rw-r--r-- | kernel/events/uprobes.c | 7 | ||||
| -rw-r--r-- | kernel/exit.c | 32 | ||||
| -rw-r--r-- | kernel/fork.c | 21 | ||||
| -rw-r--r-- | kernel/kexec.c | 109 | ||||
| -rw-r--r-- | kernel/kexec_core.c | 9 | ||||
| -rw-r--r-- | kernel/kexec_file.c | 8 | ||||
| -rw-r--r-- | kernel/signal.c | 10 | ||||
| -rw-r--r-- | kernel/sys.c | 3 |
9 files changed, 120 insertions, 83 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index f0c40bf49d9f..e2ec54e2b952 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -91,9 +91,7 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o obj-$(CONFIG_TRACEPOINTS) += tracepoint.o obj-$(CONFIG_LATENCYTOP) += latencytop.o -obj-$(CONFIG_BINFMT_ELF) += elfcore.o -obj-$(CONFIG_COMPAT_BINFMT_ELF) += elfcore.o -obj-$(CONFIG_BINFMT_ELF_FDPIC) += elfcore.o +obj-$(CONFIG_ELFCORE) += elfcore.o obj-$(CONFIG_FUNCTION_TRACER) += trace/ obj-$(CONFIG_TRACING) += trace/ obj-$(CONFIG_TRACE_CLOCK) += trace/ diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index c01f733ff2e1..b7a525ab2083 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1130,7 +1130,9 @@ static int xol_add_vma(struct mm_struct *mm, struct xol_area *area) struct vm_area_struct *vma; int ret; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; + if (mm->uprobes_state.xol_area) { ret = -EALREADY; goto fail; @@ -1469,7 +1471,8 @@ static void dup_xol_work(struct callback_head *work) if (current->flags & PF_EXITING) return; - if (!__create_xol_area(current->utask->dup_xol_addr)) + if (!__create_xol_area(current->utask->dup_xol_addr) && + !fatal_signal_pending(current)) uprobe_warn(current, "dup xol area"); } diff --git a/kernel/exit.c b/kernel/exit.c index 75b34fe835b2..9e6e1356e6bb 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -918,17 +918,28 @@ static int eligible_pid(struct wait_opts *wo, struct task_struct *p) task_pid_type(p, wo->wo_type) == wo->wo_pid; } -static int eligible_child(struct wait_opts *wo, struct task_struct *p) +static int +eligible_child(struct wait_opts *wo, bool ptrace, struct task_struct *p) { if (!eligible_pid(wo, p)) return 0; - /* Wait for all children (clone and not) if __WALL is set; - * otherwise, wait for clone children *only* if __WCLONE is - * set; otherwise, wait for non-clone children *only*. (Note: - * A "clone" child here is one that reports to its parent - * using a signal other than SIGCHLD.) */ - if (((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE)) - && !(wo->wo_flags & __WALL)) + + /* + * Wait for all children (clone and not) if __WALL is set or + * if it is traced by us. + */ + if (ptrace || (wo->wo_flags & __WALL)) + return 1; + + /* + * Otherwise, wait for clone children *only* if __WCLONE is set; + * otherwise, wait for non-clone children *only*. + * + * Note: a "clone" child here is one that reports to its parent + * using a signal other than SIGCHLD, or a non-leader thread which + * we can only see if it is traced by us. + */ + if ((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE)) return 0; return 1; @@ -1300,7 +1311,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace, if (unlikely(exit_state == EXIT_DEAD)) return 0; - ret = eligible_child(wo, p); + ret = eligible_child(wo, ptrace, p); if (!ret) return ret; @@ -1524,7 +1535,8 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, enum pid_type type; long ret; - if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED)) + if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED| + __WNOTHREAD|__WCLONE|__WALL)) return -EINVAL; if (!(options & (WEXITED|WSTOPPED|WCONTINUED))) return -EINVAL; diff --git a/kernel/fork.c b/kernel/fork.c index 103d78fd8f75..47887bba944f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -340,13 +340,14 @@ void set_task_stack_end_magic(struct task_struct *tsk) *stackend = STACK_END_MAGIC; /* for overflow detection */ } -static struct task_struct *dup_task_struct(struct task_struct *orig) +static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; struct thread_info *ti; - int node = tsk_fork_get_node(orig); int err; + if (node == NUMA_NO_NODE) + node = tsk_fork_get_node(orig); tsk = alloc_task_struct_node(node); if (!tsk) return NULL; @@ -413,7 +414,10 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) unsigned long charge; uprobe_start_dup_mmap(); - down_write(&oldmm->mmap_sem); + if (down_write_killable(&oldmm->mmap_sem)) { + retval = -EINTR; + goto fail_uprobe_end; + } flush_cache_dup_mm(oldmm); uprobe_dup_mmap(oldmm, mm); /* @@ -525,6 +529,7 @@ out: up_write(&mm->mmap_sem); flush_tlb_mm(oldmm); up_write(&oldmm->mmap_sem); +fail_uprobe_end: uprobe_end_dup_mmap(); return retval; fail_nomem_anon_vma_fork: @@ -1276,7 +1281,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, int __user *child_tidptr, struct pid *pid, int trace, - unsigned long tls) + unsigned long tls, + int node) { int retval; struct task_struct *p; @@ -1328,7 +1334,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, goto fork_out; retval = -ENOMEM; - p = dup_task_struct(current); + p = dup_task_struct(current, node); if (!p) goto fork_out; @@ -1706,7 +1712,8 @@ static inline void init_idle_pids(struct pid_link *links) struct task_struct *fork_idle(int cpu) { struct task_struct *task; - task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0); + task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0, + cpu_to_node(cpu)); if (!IS_ERR(task)) { init_idle_pids(task->pids); init_idle(task, cpu); @@ -1751,7 +1758,7 @@ long _do_fork(unsigned long clone_flags, } p = copy_process(clone_flags, stack_start, stack_size, - child_tidptr, NULL, trace, tls); + child_tidptr, NULL, trace, tls, NUMA_NO_NODE); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. diff --git a/kernel/kexec.c b/kernel/kexec.c index ee70aef5cd81..4384672d3245 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -103,6 +103,65 @@ out_free_image: return ret; } +static int do_kexec_load(unsigned long entry, unsigned long nr_segments, + struct kexec_segment __user *segments, unsigned long flags) +{ + struct kimage **dest_image, *image; + unsigned long i; + int ret; + + if (flags & KEXEC_ON_CRASH) { + dest_image = &kexec_crash_image; + if (kexec_crash_image) + arch_kexec_unprotect_crashkres(); + } else { + dest_image = &kexec_image; + } + + if (nr_segments == 0) { + /* Uninstall image */ + kimage_free(xchg(dest_image, NULL)); + return 0; + } + if (flags & KEXEC_ON_CRASH) { + /* + * Loading another kernel to switch to if this one + * crashes. Free any current crash dump kernel before + * we corrupt it. + */ + kimage_free(xchg(&kexec_crash_image, NULL)); + } + + ret = kimage_alloc_init(&image, entry, nr_segments, segments, flags); + if (ret) + return ret; + + if (flags & KEXEC_PRESERVE_CONTEXT) + image->preserve_context = 1; + + ret = machine_kexec_prepare(image); + if (ret) + goto out; + + for (i = 0; i < nr_segments; i++) { + ret = kimage_load_segment(image, &image->segment[i]); + if (ret) + goto out; + } + + kimage_terminate(image); + + /* Install the new kernel and uninstall the old */ + image = xchg(dest_image, image); + +out: + if ((flags & KEXEC_ON_CRASH) && kexec_crash_image) + arch_kexec_protect_crashkres(); + + kimage_free(image); + return ret; +} + /* * Exec Kernel system call: for obvious reasons only root may call it. * @@ -127,7 +186,6 @@ out_free_image: SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, struct kexec_segment __user *, segments, unsigned long, flags) { - struct kimage **dest_image, *image; int result; /* We only trust the superuser with rebooting the system. */ @@ -152,9 +210,6 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, if (nr_segments > KEXEC_SEGMENT_MAX) return -EINVAL; - image = NULL; - result = 0; - /* Because we write directly to the reserved memory * region when loading crash kernels we need a mutex here to * prevent multiple crash kernels from attempting to load @@ -166,53 +221,9 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, if (!mutex_trylock(&kexec_mutex)) return -EBUSY; - dest_image = &kexec_image; - if (flags & KEXEC_ON_CRASH) - dest_image = &kexec_crash_image; - if (nr_segments > 0) { - unsigned long i; - - if (flags & KEXEC_ON_CRASH) { - /* - * Loading another kernel to switch to if this one - * crashes. Free any current crash dump kernel before - * we corrupt it. - */ - - kimage_free(xchg(&kexec_crash_image, NULL)); - result = kimage_alloc_init(&image, entry, nr_segments, - segments, flags); - crash_map_reserved_pages(); - } else { - /* Loading another kernel to reboot into. */ - - result = kimage_alloc_init(&image, entry, nr_segments, - segments, flags); - } - if (result) - goto out; - - if (flags & KEXEC_PRESERVE_CONTEXT) - image->preserve_context = 1; - result = machine_kexec_prepare(image); - if (result) - goto out; - - for (i = 0; i < nr_segments; i++) { - result = kimage_load_segment(image, &image->segment[i]); - if (result) - goto out; - } - kimage_terminate(image); - if (flags & KEXEC_ON_CRASH) - crash_unmap_reserved_pages(); - } - /* Install the new kernel, and Uninstall the old */ - image = xchg(dest_image, image); + result = do_kexec_load(entry, nr_segments, segments, flags); -out: mutex_unlock(&kexec_mutex); - kimage_free(image); return result; } diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index d5d408252992..56b3ed0927b0 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -954,7 +954,6 @@ int crash_shrink_memory(unsigned long new_size) start = roundup(start, KEXEC_CRASH_MEM_ALIGN); end = roundup(start + new_size, KEXEC_CRASH_MEM_ALIGN); - crash_map_reserved_pages(); crash_free_reserved_phys_range(end, crashk_res.end); if ((start == end) && (crashk_res.parent != NULL)) @@ -968,7 +967,6 @@ int crash_shrink_memory(unsigned long new_size) crashk_res.end = end - 1; insert_resource(&iomem_resource, ram_res); - crash_unmap_reserved_pages(); unlock: mutex_unlock(&kexec_mutex); @@ -1553,13 +1551,14 @@ int kernel_kexec(void) } /* - * Add and remove page tables for crashkernel memory + * Protection mechanism for crashkernel reserved memory after + * the kdump kernel is loaded. * * Provide an empty default implementation here -- architecture * code may override this */ -void __weak crash_map_reserved_pages(void) +void __weak arch_kexec_protect_crashkres(void) {} -void __weak crash_unmap_reserved_pages(void) +void __weak arch_kexec_unprotect_crashkres(void) {} diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index c72d2ff5896e..503bc2d348e5 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -274,8 +274,11 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, return -EBUSY; dest_image = &kexec_image; - if (flags & KEXEC_FILE_ON_CRASH) + if (flags & KEXEC_FILE_ON_CRASH) { dest_image = &kexec_crash_image; + if (kexec_crash_image) + arch_kexec_unprotect_crashkres(); + } if (flags & KEXEC_FILE_UNLOAD) goto exchange; @@ -324,6 +327,9 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, exchange: image = xchg(dest_image, image); out: + if ((flags & KEXEC_FILE_ON_CRASH) && kexec_crash_image) + arch_kexec_protect_crashkres(); + mutex_unlock(&kexec_mutex); kimage_free(image); return ret; diff --git a/kernel/signal.c b/kernel/signal.c index ab122a2cee41..96e9bc40667f 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -224,7 +224,7 @@ static inline void print_dropped_signal(int sig) if (!__ratelimit(&ratelimit_state)) return; - printk(KERN_INFO "%s/%d: reached RLIMIT_SIGPENDING, dropped signal %d\n", + pr_info("%s/%d: reached RLIMIT_SIGPENDING, dropped signal %d\n", current->comm, current->pid, sig); } @@ -1089,10 +1089,10 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t, static void print_fatal_signal(int signr) { struct pt_regs *regs = signal_pt_regs(); - printk(KERN_INFO "potentially unexpected fatal signal %d.\n", signr); + pr_info("potentially unexpected fatal signal %d.\n", signr); #if defined(__i386__) && !defined(__arch_um__) - printk(KERN_INFO "code at %08lx: ", regs->ip); + pr_info("code at %08lx: ", regs->ip); { int i; for (i = 0; i < 16; i++) { @@ -1100,10 +1100,10 @@ static void print_fatal_signal(int signr) if (get_user(insn, (unsigned char *)(regs->ip + i))) break; - printk(KERN_CONT "%02x ", insn); + pr_cont("%02x ", insn); } } - printk(KERN_CONT "\n"); + pr_cont("\n"); #endif preempt_disable(); show_regs(regs); diff --git a/kernel/sys.c b/kernel/sys.c index cf8ba545c7d3..89d5be418157 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2246,7 +2246,8 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_SET_THP_DISABLE: if (arg3 || arg4 || arg5) return -EINVAL; - down_write(&me->mm->mmap_sem); + if (down_write_killable(&me->mm->mmap_sem)) + return -EINTR; if (arg2) me->mm->def_flags |= VM_NOHUGEPAGE; else |