diff options
Diffstat (limited to 'kernel')
35 files changed, 1182 insertions, 530 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index ac0d533eb7d..6c072b6da23 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -54,7 +54,7 @@ obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o obj-$(CONFIG_PROVE_LOCKING) += spinlock.o obj-$(CONFIG_UID16) += uid16.o obj-$(CONFIG_MODULES) += module.o -obj-$(CONFIG_MODULE_SIG) += module_signing.o modsign_pubkey.o +obj-$(CONFIG_MODULE_SIG) += module_signing.o modsign_pubkey.o modsign_certificate.o obj-$(CONFIG_KALLSYMS) += kallsyms.o obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o obj-$(CONFIG_KEXEC) += kexec.o @@ -137,10 +137,14 @@ ifeq ($(CONFIG_MODULE_SIG),y) # # Pull the signing certificate and any extra certificates into the kernel # + +quiet_cmd_touch = TOUCH $@ + cmd_touch = touch $@ + extra_certificates: - touch $@ + $(call cmd,touch) -kernel/modsign_pubkey.o: signing_key.x509 extra_certificates +kernel/modsign_certificate.o: signing_key.x509 extra_certificates ############################################################################### # diff --git a/kernel/cgroup.c b/kernel/cgroup.c index f34c41bfaa3..4855892798f 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1333,7 +1333,6 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data) if (ret) goto out_unlock; - /* See feature-removal-schedule.txt */ if (opts.subsys_mask != root->actual_subsys_mask || opts.release_agent) pr_warning("cgroup: option changes via remount are deprecated (pid=%d comm=%s)\n", task_tgid_nr(current), current->comm); @@ -3409,7 +3408,7 @@ static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp, { struct cgroup_pidlist *l; /* don't need task_nsproxy() if we're looking at ourself */ - struct pid_namespace *ns = current->nsproxy->pid_ns; + struct pid_namespace *ns = task_active_pid_ns(current); /* * We can't drop the pidlist_mutex before taking the l->mutex in case diff --git a/kernel/compat.c b/kernel/compat.c index c28a306ae05..f6150e92dfc 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -1215,6 +1215,23 @@ compat_sys_sysinfo(struct compat_sysinfo __user *info) return 0; } +#ifdef __ARCH_WANT_COMPAT_SYS_SCHED_RR_GET_INTERVAL +asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid, + struct compat_timespec __user *interval) +{ + struct timespec t; + int ret; + mm_segment_t old_fs = get_fs(); + + set_fs(KERNEL_DS); + ret = sys_sched_rr_get_interval(pid, (struct timespec __user *)&t); + set_fs(old_fs); + if (put_compat_timespec(&t, interval)) + return -EFAULT; + return ret; +} +#endif /* __ARCH_WANT_COMPAT_SYS_SCHED_RR_GET_INTERVAL */ + /* * Allocate user-space memory for the duration of a single system call, * in order to marshall parameters inside a compat thunk. diff --git a/kernel/cred.c b/kernel/cred.c index 48cea3da6d0..e0573a43c7d 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -30,17 +30,6 @@ static struct kmem_cache *cred_jar; /* - * The common credentials for the initial task's thread group - */ -#ifdef CONFIG_KEYS -static struct thread_group_cred init_tgcred = { - .usage = ATOMIC_INIT(2), - .tgid = 0, - .lock = __SPIN_LOCK_UNLOCKED(init_cred.tgcred.lock), -}; -#endif - -/* * The initial credentials for the initial task */ struct cred init_cred = { @@ -65,9 +54,6 @@ struct cred init_cred = { .user = INIT_USER, .user_ns = &init_user_ns, .group_info = &init_groups, -#ifdef CONFIG_KEYS - .tgcred = &init_tgcred, -#endif }; static inline void set_cred_subscribers(struct cred *cred, int n) @@ -96,36 +82,6 @@ static inline void alter_cred_subscribers(const struct cred *_cred, int n) } /* - * Dispose of the shared task group credentials - */ -#ifdef CONFIG_KEYS -static void release_tgcred_rcu(struct rcu_head *rcu) -{ - struct thread_group_cred *tgcred = - container_of(rcu, struct thread_group_cred, rcu); - - BUG_ON(atomic_read(&tgcred->usage) != 0); - - key_put(tgcred->session_keyring); - key_put(tgcred->process_keyring); - kfree(tgcred); -} -#endif - -/* - * Release a set of thread group credentials. - */ -static void release_tgcred(struct cred *cred) -{ -#ifdef CONFIG_KEYS - struct thread_group_cred *tgcred = cred->tgcred; - - if (atomic_dec_and_test(&tgcred->usage)) - call_rcu(&tgcred->rcu, release_tgcred_rcu); -#endif -} - -/* * The RCU callback to actually dispose of a set of credentials */ static void put_cred_rcu(struct rcu_head *rcu) @@ -150,9 +106,10 @@ static void put_cred_rcu(struct rcu_head *rcu) #endif security_cred_free(cred); + key_put(cred->session_keyring); + key_put(cred->process_keyring); key_put(cred->thread_keyring); key_put(cred->request_key_auth); - release_tgcred(cred); if (cred->group_info) put_group_info(cred->group_info); free_uid(cred->user); @@ -246,15 +203,6 @@ struct cred *cred_alloc_blank(void) if (!new) return NULL; -#ifdef CONFIG_KEYS - new->tgcred = kzalloc(sizeof(*new->tgcred), GFP_KERNEL); - if (!new->tgcred) { - kmem_cache_free(cred_jar, new); - return NULL; - } - atomic_set(&new->tgcred->usage, 1); -#endif - atomic_set(&new->usage, 1); #ifdef CONFIG_DEBUG_CREDENTIALS new->magic = CRED_MAGIC; @@ -308,9 +256,10 @@ struct cred *prepare_creds(void) get_user_ns(new->user_ns); #ifdef CONFIG_KEYS + key_get(new->session_keyring); + key_get(new->process_keyring); key_get(new->thread_keyring); key_get(new->request_key_auth); - atomic_inc(&new->tgcred->usage); #endif #ifdef CONFIG_SECURITY @@ -334,39 +283,20 @@ EXPORT_SYMBOL(prepare_creds); */ struct cred *prepare_exec_creds(void) { - struct thread_group_cred *tgcred = NULL; struct cred *new; -#ifdef CONFIG_KEYS - tgcred = kmalloc(sizeof(*tgcred), GFP_KERNEL); - if (!tgcred) - return NULL; -#endif - new = prepare_creds(); - if (!new) { - kfree(tgcred); + if (!new) return new; - } #ifdef CONFIG_KEYS /* newly exec'd tasks don't get a thread keyring */ key_put(new->thread_keyring); new->thread_keyring = NULL; - /* create a new per-thread-group creds for all this set of threads to - * share */ - memcpy(tgcred, new->tgcred, sizeof(struct thread_group_cred)); - - atomic_set(&tgcred->usage, 1); - spin_lock_init(&tgcred->lock); - /* inherit the session keyring; new process keyring */ - key_get(tgcred->session_keyring); - tgcred->process_keyring = NULL; - - release_tgcred(new); - new->tgcred = tgcred; + key_put(new->process_keyring); + new->process_keyring = NULL; #endif return new; @@ -383,9 +313,6 @@ struct cred *prepare_exec_creds(void) */ int copy_creds(struct task_struct *p, unsigned long clone_flags) { -#ifdef CONFIG_KEYS - struct thread_group_cred *tgcred; -#endif struct cred *new; int ret; @@ -425,22 +352,12 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) install_thread_keyring_to_cred(new); } - /* we share the process and session keyrings between all the threads in - * a process - this is slightly icky as we violate COW credentials a - * bit */ + /* The process keyring is only shared between the threads in a process; + * anything outside of those threads doesn't inherit. + */ if (!(clone_flags & CLONE_THREAD)) { - tgcred = kmalloc(sizeof(*tgcred), GFP_KERNEL); - if (!tgcred) { - ret = -ENOMEM; - goto error_put; - } - atomic_set(&tgcred->usage, 1); - spin_lock_init(&tgcred->lock); - tgcred->process_keyring = NULL; - tgcred->session_keyring = key_get(new->tgcred->session_keyring); - - release_tgcred(new); - new->tgcred = tgcred; + key_put(new->process_keyring); + new->process_keyring = NULL; } #endif @@ -455,6 +372,31 @@ error_put: return ret; } +static bool cred_cap_issubset(const struct cred *set, const struct cred *subset) +{ + const struct user_namespace *set_ns = set->user_ns; + const struct user_namespace *subset_ns = subset->user_ns; + + /* If the two credentials are in the same user namespace see if + * the capabilities of subset are a subset of set. + */ + if (set_ns == subset_ns) + return cap_issubset(subset->cap_permitted, set->cap_permitted); + + /* The credentials are in a different user namespaces + * therefore one is a subset of the other only if a set is an + * ancestor of subset and set->euid is owner of subset or one + * of subsets ancestors. + */ + for (;subset_ns != &init_user_ns; subset_ns = subset_ns->parent) { + if ((set_ns == subset_ns->parent) && + uid_eq(subset_ns->owner, set->euid)) + return true; + } + + return false; +} + /** * commit_creds - Install new credentials upon the current task * @new: The credentials to be assigned @@ -493,7 +435,7 @@ int commit_creds(struct cred *new) !gid_eq(old->egid, new->egid) || !uid_eq(old->fsuid, new->fsuid) || !gid_eq(old->fsgid, new->fsgid) || - !cap_issubset(new->cap_permitted, old->cap_permitted)) { + !cred_cap_issubset(old, new)) { if (task->mm) set_dumpable(task->mm, suid_dumpable); task->pdeath_signal = 0; @@ -643,9 +585,6 @@ void __init cred_init(void) */ struct cred *prepare_kernel_cred(struct task_struct *daemon) { -#ifdef CONFIG_KEYS - struct thread_group_cred *tgcred; -#endif const struct cred *old; struct cred *new; @@ -653,14 +592,6 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) if (!new) return NULL; -#ifdef CONFIG_KEYS - tgcred = kmalloc(sizeof(*tgcred), GFP_KERNEL); - if (!tgcred) { - kmem_cache_free(cred_jar, new); - return NULL; - } -#endif - kdebug("prepare_kernel_cred() alloc %p", new); if (daemon) @@ -678,13 +609,10 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) get_group_info(new->group_info); #ifdef CONFIG_KEYS - atomic_set(&tgcred->usage, 1); - spin_lock_init(&tgcred->lock); - tgcred->process_keyring = NULL; - tgcred->session_keyring = NULL; - new->tgcred = tgcred; - new->request_key_auth = NULL; + new->session_keyring = NULL; + new->process_keyring = NULL; new->thread_keyring = NULL; + new->request_key_auth = NULL; new->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING; #endif diff --git a/kernel/events/core.c b/kernel/events/core.c index f9ff5493171..301079d06f2 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6155,7 +6155,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, event->parent = parent_event; - event->ns = get_pid_ns(current->nsproxy->pid_ns); + event->ns = get_pid_ns(task_active_pid_ns(current)); event->id = atomic64_inc_return(&perf_event_id); event->state = PERF_EVENT_STATE_INACTIVE; diff --git a/kernel/exit.c b/kernel/exit.c index 50d2e93c36e..b4df2193721 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -72,18 +72,6 @@ static void __unhash_process(struct task_struct *p, bool group_dead) list_del_rcu(&p->tasks); list_del_init(&p->sibling); __this_cpu_dec(process_counts); - /* - * If we are the last child process in a pid namespace to be - * reaped, notify the reaper sleeping zap_pid_ns_processes(). - */ - if (IS_ENABLED(CONFIG_PID_NS)) { - struct task_struct *parent = p->real_parent; - - if ((task_active_pid_ns(parent)->child_reaper == parent) && - list_empty(&parent->children) && - (parent->flags & PF_EXITING)) - wake_up_process(parent); - } } list_del_rcu(&p->thread_group); } diff --git a/kernel/fork.c b/kernel/fork.c index 3c31e874afa..85f6d536608 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -146,7 +146,7 @@ void __weak arch_release_thread_info(struct thread_info *ti) static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, int node) { - struct page *page = alloc_pages_node(node, THREADINFO_GFP, + struct page *page = alloc_pages_node(node, THREADINFO_GFP_ACCOUNTED, THREAD_SIZE_ORDER); return page ? page_address(page) : NULL; @@ -154,7 +154,7 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, static inline void free_thread_info(struct thread_info *ti) { - free_pages((unsigned long)ti, THREAD_SIZE_ORDER); + free_memcg_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER); } # else static struct kmem_cache *thread_info_cache; @@ -823,6 +823,9 @@ struct mm_struct *dup_mm(struct task_struct *tsk) #ifdef CONFIG_TRANSPARENT_HUGEPAGE mm->pmd_huge_pte = NULL; #endif +#ifdef CONFIG_NUMA_BALANCING + mm->first_nid = NUMA_PTE_SCAN_INIT; +#endif if (!mm_init(mm, tsk)) goto fail_nomem; @@ -1041,8 +1044,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) atomic_set(&sig->live, 1); atomic_set(&sig->sigcnt, 1); init_waitqueue_head(&sig->wait_chldexit); - if (clone_flags & CLONE_NEWPID) - sig->flags |= SIGNAL_UNKILLABLE; sig->curr_target = tsk; init_sigpending(&sig->shared_pending); INIT_LIST_HEAD(&sig->posix_timers); @@ -1435,8 +1436,10 @@ static struct task_struct *copy_process(unsigned long clone_flags, ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); if (thread_group_leader(p)) { - if (is_child_reaper(pid)) - p->nsproxy->pid_ns->child_reaper = p; + if (is_child_reaper(pid)) { + ns_of_pid(pid)->child_reaper = p; + p->signal->flags |= SIGNAL_UNKILLABLE; + } p->signal->leader_pid = pid; p->signal->tty = tty_kref_get(current->signal->tty); @@ -1470,8 +1473,6 @@ bad_fork_cleanup_io: if (p->io_context) exit_io_context(p); bad_fork_cleanup_namespaces: - if (unlikely(clone_flags & CLONE_NEWPID)) - pid_ns_release_proc(p->nsproxy->pid_ns); exit_task_namespaces(p); bad_fork_cleanup_mm: if (p->mm) @@ -1551,15 +1552,9 @@ long do_fork(unsigned long clone_flags, * Do some preliminary argument and permissions checking before we * actually start allocating stuff */ - if (clone_flags & CLONE_NEWUSER) { - if (clone_flags & CLONE_THREAD) + if (clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) { + if (clone_flags & (CLONE_THREAD|CLONE_PARENT)) return -EINVAL; - /* hopefully this check will go away when userns support is - * complete - */ - if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SETUID) || - !capable(CAP_SETGID)) - return -EPERM; } /* @@ -1721,7 +1716,8 @@ static int check_unshare_flags(unsigned long unshare_flags) { if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| - CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET)) + CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET| + CLONE_NEWUSER|CLONE_NEWPID)) return -EINVAL; /* * Not implemented, but pretend it works if there is nothing to @@ -1788,19 +1784,40 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) { struct fs_struct *fs, *new_fs = NULL; struct files_struct *fd, *new_fd = NULL; + struct cred *new_cred = NULL; struct nsproxy *new_nsproxy = NULL; int do_sysvsem = 0; int err; - err = check_unshare_flags(unshare_flags); - if (err) - goto bad_unshare_out; - + /* + * If unsharing a user namespace must also unshare the thread. + */ + if (unshare_flags & CLONE_NEWUSER) + unshare_flags |= CLONE_THREAD; + /* + * If unsharing a pid namespace must also unshare the thread. + */ + if (unshare_flags & CLONE_NEWPID) + unshare_flags |= CLONE_THREAD; + /* + * If unsharing a thread from a thread group, must also unshare vm. + */ + if (unshare_flags & CLONE_THREAD) + unshare_flags |= CLONE_VM; + /* + * If unsharing vm, must also unshare signal handlers. + */ + if (unshare_flags & CLONE_VM) + unshare_flags |= CLONE_SIGHAND; /* * If unsharing namespace, must also unshare filesystem information. */ if (unshare_flags & CLONE_NEWNS) unshare_flags |= CLONE_FS; + + err = check_unshare_flags(unshare_flags); + if (err) + goto bad_unshare_out; /* * CLONE_NEWIPC must also detach from the undolist: after switching * to a new ipc namespace, the semaphore arrays from the old @@ -1814,11 +1831,15 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) err = unshare_fd(unshare_flags, &new_fd); if (err) goto bad_unshare_cleanup_fs; - err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_fs); + err = unshare_userns(unshare_flags, &new_cred); if (err) goto bad_unshare_cleanup_fd; + err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, + new_cred, new_fs); + if (err) + goto bad_unshare_cleanup_cred; - if (new_fs || new_fd || do_sysvsem || new_nsproxy) { + if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) { if (do_sysvsem) { /* * CLONE_SYSVSEM is equivalent to sys_exit(). @@ -1851,11 +1872,20 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) } task_unlock(current); + + if (new_cred) { + /* Install the new user namespace */ + commit_creds(new_cred); + new_cred = NULL; + } } if (new_nsproxy) put_nsproxy(new_nsproxy); +bad_unshare_cleanup_cred: + if (new_cred) + put_cred(new_cred); bad_unshare_cleanup_fd: if (new_fd) put_files_struct(new_fd); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 35c70c9e24d..e49a288fa47 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -818,7 +818,7 @@ static void irq_thread_dtor(struct callback_head *unused) action = kthread_data(tsk); pr_err("exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n", - tsk->comm ? tsk->comm : "", tsk->pid, action->irq); + tsk->comm, tsk->pid, action->irq); desc = irq_to_desc(action->irq); diff --git a/kernel/modsign_certificate.S b/kernel/modsign_certificate.S new file mode 100644 index 00000000000..246b4c6e613 --- /dev/null +++ b/kernel/modsign_certificate.S @@ -0,0 +1,19 @@ +/* SYMBOL_PREFIX defined on commandline from CONFIG_SYMBOL_PREFIX */ +#ifndef SYMBOL_PREFIX +#define ASM_SYMBOL(sym) sym +#else +#define PASTE2(x,y) x##y +#define PASTE(x,y) PASTE2(x,y) +#define ASM_SYMBOL(sym) PASTE(SYMBOL_PREFIX, sym) +#endif + +#define GLOBAL(name) \ + .globl ASM_SYMBOL(name); \ + ASM_SYMBOL(name): + + .section ".init.data","aw" + +GLOBAL(modsign_certificate_list) + .incbin "signing_key.x509" + .incbin "extra_certificates" +GLOBAL(modsign_certificate_list_end) diff --git a/kernel/modsign_pubkey.c b/kernel/modsign_pubkey.c index 767e559dfb1..045504fffbb 100644 --- a/kernel/modsign_pubkey.c +++ b/kernel/modsign_pubkey.c @@ -20,12 +20,6 @@ struct key *modsign_keyring; extern __initdata const u8 modsign_certificate_list[]; extern __initdata const u8 modsign_certificate_list_end[]; -asm(".section .init.data,\"aw\"\n" - SYMBOL_PREFIX "modsign_certificate_list:\n" - ".incbin \"signing_key.x509\"\n" - ".incbin \"extra_certificates\"\n" - SYMBOL_PREFIX "modsign_certificate_list_end:" - ); /* * We need to make sure ccache doesn't cache the .o file as it doesn't notice diff --git a/kernel/module.c b/kernel/module.c index 6e48c3a4359..250092c1d57 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -21,6 +21,7 @@ #include <linux/ftrace_event.h> #include <linux/init.h> #include <linux/kallsyms.h> +#include <linux/file.h> #include <linux/fs.h> #include <linux/sysfs.h> #include <linux/kernel.h> @@ -28,6 +29,7 @@ #include <linux/vmalloc.h> #include <linux/elf.h> #include <linux/proc_fs.h> +#include <linux/security.h> #include <linux/seq_file.h> #include <linux/syscalls.h> #include <linux/fcntl.h> @@ -59,6 +61,7 @@ #include <linux/pfn.h> #include <linux/bsearch.h> #include <linux/fips.h> +#include <uapi/linux/module.h> #include "module-internal.h" #define CREATE_TRACE_POINTS @@ -372,9 +375,6 @@ static bool check_symbol(const struct symsearch *syms, printk(KERN_WARNING "Symbol %s is being used " "by a non-GPL module, which will not " "be allowed in the future\n", fsa->name); - printk(KERN_WARNING "Please see the file " - "Documentation/feature-removal-schedule.txt " - "in the kernel source tree for more details.\n"); } } @@ -2282,7 +2282,7 @@ static void layout_symtab(struct module *mod, struct load_info *info) Elf_Shdr *symsect = info->sechdrs + info->index.sym; Elf_Shdr *strsect = info->sechdrs + info->index.str; const Elf_Sym *src; - unsigned int i, nsrc, ndst, strtab_size; + unsigned int i, nsrc, ndst, strtab_size = 0; /* Put symbol section at end of init part of module. */ symsect->sh_flags |= SHF_ALLOC; @@ -2293,9 +2293,6 @@ static void layout_symtab(struct module *mod, struct load_info *info) src = (void *)info->hdr + symsect->sh_offset; nsrc = symsect->sh_size / sizeof(*src); - /* strtab always starts with a nul, so offset 0 is the empty string. */ - strtab_size = 1; - /* Compute total space required for the core symbols' strtab. */ for (ndst = i = 0; i < nsrc; i++) { if (i == 0 || @@ -2337,7 +2334,6 @@ static void add_kallsyms(struct module *mod, const struct load_info *info) mod->core_symtab = dst = mod->module_core + info->symoffs; mod->core_strtab = s = mod->module_core + info->stroffs; src = mod->symtab; - *s++ = 0; for (ndst = i = 0; i < mod->num_symtab; i++) { if (i == 0 || is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum)) { @@ -2378,7 +2374,7 @@ static void dynamic_debug_remove(struct _ddebug *debug) void * __weak module_alloc(unsigned long size) { - return size == 0 ? NULL : vmalloc_exec(size); + return vmalloc_exec(size); } static void *module_alloc_update_bounds(unsigned long size) @@ -2425,18 +2421,17 @@ static inline void kmemleak_load_module(const struct module *mod, #endif #ifdef CONFIG_MODULE_SIG -static int module_sig_check(struct load_info *info, - const void *mod, unsigned long *_len) +static int module_sig_check(struct load_info *info) { int err = -ENOKEY; - unsigned long markerlen = sizeof(MODULE_SIG_STRING) - 1; - unsigned long len = *_len; + const unsigned long markerlen = sizeof(MODULE_SIG_STRING) - 1; + const void *mod = info->hdr; - if (len > markerlen && - memcmp(mod + len - markerlen, MODULE_SIG_STRING, markerlen) == 0) { + if (info->len > markerlen && + memcmp(mod + info->len - markerlen, MODULE_SIG_STRING, markerlen) == 0) { /* We truncate the module to discard the signature */ - *_len -= markerlen; - err = mod_verify_sig(mod, _len); + info->len -= markerlen; + err = mod_verify_sig(mod, &info->len); } if (!err) { @@ -2454,59 +2449,107 @@ static int module_sig_check(struct load_info *info, return err; } #else /* !CONFIG_MODULE_SIG */ -static int module_sig_check(struct load_info *info, - void *mod, unsigned long *len) +static int module_sig_check(struct load_info *info) { return 0; } #endif /* !CONFIG_MODULE_SIG */ -/* Sets info->hdr, info->len and info->sig_ok. */ -static int copy_and_check(struct load_info *info, - const void __user *umod, unsigned long len, - const char __user *uargs) +/* Sanity checks against invalid binaries, wrong arch, weird elf version. */ +static int elf_header_check(struct load_info *info) +{ + if (info->len < sizeof(*(info->hdr))) + return -ENOEXEC; + + if (memcmp(info->hdr->e_ident, ELFMAG, SELFMAG) != 0 + || info->hdr->e_type != ET_REL + || !elf_check_arch(info->hdr) + || info->hdr->e_shentsize != sizeof(Elf_Shdr)) + return -ENOEXEC; + + if (info->hdr->e_shoff >= info->len + || (info->hdr->e_shnum * sizeof(Elf_Shdr) > + info->len - info->hdr->e_shoff)) + return -ENOEXEC; + + return 0; +} + +/* Sets info->hdr and info->len. */ +static int copy_module_from_user(const void __user *umod, unsigned long len, + struct load_info *info) { int err; - Elf_Ehdr *hdr; - if (len < sizeof(*hdr)) + info->len = len; + if (info->len < sizeof(*(info->hdr))) return -ENOEXEC; + err = security_kernel_module_from_file(NULL); + if (err) + return err; + /* Suck in entire file: we'll want most of it. */ - if ((hdr = vmalloc(len)) == NULL) + info->hdr = vmalloc(info->len); + if (!info->hdr) return -ENOMEM; - if (copy_from_user(hdr, umod, len) != 0) { - err = -EFAULT; - goto free_hdr; + if (copy_from_user(info->hdr, umod, info->len) != 0) { + vfree(info->hdr); + return -EFAULT; } - err = module_sig_check(info, hdr, &len); + return 0; +} + +/* Sets info->hdr and info->len. */ +static int copy_module_from_fd(int fd, struct load_info *info) +{ + struct file *file; + int err; + struct kstat stat; + loff_t pos; + ssize_t bytes = 0; + + file = fget(fd); + if (!file) + return -ENOEXEC; + + err = security_kernel_module_from_file(file); if (err) - goto free_hdr; + goto out; - /* Sanity checks against insmoding binaries or wrong arch, - weird elf version */ - if (memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0 - || hdr->e_type != ET_REL - || !elf_check_arch(hdr) - || hdr->e_shentsize != sizeof(Elf_Shdr)) { - err = -ENOEXEC; - goto free_hdr; - } + err = vfs_getattr(file->f_vfsmnt, file->f_dentry, &stat); + if (err) + goto out; - if (hdr->e_shoff >= len || - hdr->e_shnum * sizeof(Elf_Shdr) > len - hdr->e_shoff) { - err = -ENOEXEC; - goto free_hdr; + if (stat.size > INT_MAX) { + err = -EFBIG; + goto out; + } + info->hdr = vmalloc(stat.size); + if (!info->hdr) { + err = -ENOMEM; + goto out; } - info->hdr = hdr; - info->len = len; - return 0; + pos = 0; + while (pos < stat.size) { + bytes = kernel_read(file, pos, (char *)(info->hdr) + pos, + stat.size - pos); + if (bytes < 0) { + vfree(info->hdr); + err = bytes; + goto out; + } + if (bytes == 0) + break; + pos += bytes; + } + info->len = pos; -free_hdr: - vfree(hdr); +out: + fput(file); return err; } @@ -2515,7 +2558,7 @@ static void free_copy(struct load_info *info) vfree(info->hdr); } -static int rewrite_section_headers(struct load_info *info) +static int rewrite_section_headers(struct load_info *info, int flags) { unsigned int i; @@ -2543,7 +2586,10 @@ static int rewrite_section_headers(struct load_info *info) } /* Track but don't keep modinfo and version sections. */ - info->index.vers = find_sec(info, "__versions"); + if (flags & MODULE_INIT_IGNORE_MODVERSIONS) + info->index.vers = 0; /* Pretend no __versions section! */ + else + info->index.vers = find_sec(info, "__versions"); info->index.info = find_sec(info, ".modinfo"); info->sechdrs[info->index.info].sh_flags &= ~(unsigned long)SHF_ALLOC; info->sechdrs[info->index.vers].sh_flags &= ~(unsigned long)SHF_ALLOC; @@ -2558,7 +2604,7 @@ static int rewrite_section_headers(struct load_info *info) * Return the temporary module pointer (we'll replace it with the final * one when we move the module sections around). */ -static struct module *setup_load_info(struct load_info *info) +static struct module *setup_load_info(struct load_info *info, int flags) { unsigned int i; int err; @@ -2569,7 +2615,7 @@ static struct module *setup_load_info(struct load_info *info) info->secstrings = (void *)info->hdr + info->sechdrs[info->hdr->e_shstrndx].sh_offset; - err = rewrite_section_headers(info); + err = rewrite_section_headers(info, flags); if (err) return ERR_PTR(err); @@ -2607,11 +2653,14 @@ static struct module *setup_load_info(struct load_info *info) return mod; } -static int check_modinfo(struct module *mod, struct load_info *info) +static int check_modinfo(struct module *mod, struct load_info *info, int flags) { const char *modmagic = get_modinfo(info, "vermagic"); int err; + if (flags & MODULE_INIT_IGNORE_VERMAGIC) + modmagic = NULL; + /* This is allowed: modprobe --force will invalidate it. */ if (!modmagic) { err = try_to_force_load(mod, "bad vermagic"); @@ -2741,20 +2790,23 @@ static int move_module(struct module *mod, struct load_info *info) memset(ptr, 0, mod->core_size); mod->module_core = ptr; - ptr = module_alloc_update_bounds(mod->init_size); - /* - * The pointer to this block is stored in the module structure - * which is inside the block. This block doesn't need to be - * scanned as it contains data and code that will be freed - * after the module is initialized. - */ - kmemleak_ignore(ptr); - if (!ptr && mod->init_size) { - module_free(mod, mod->module_core); - return -ENOMEM; - } - memset(ptr, 0, mod->init_size); - mod->module_init = ptr; + if (mod->init_size) { + ptr = module_alloc_update_bounds(mod->init_size); + /* + * The pointer to this block is stored in the module structure + * which is inside the block. This block doesn't need to be + * scanned as it contains data and code that will be freed + * after the module is initialized. + */ + kmemleak_ignore(ptr); + if (!ptr) { + module_free(mod, mod->module_core); + return -ENOMEM; + } + memset(ptr, 0, mod->init_size); + mod->module_init = ptr; + } else + mod->module_init = NULL; /* Transfer each section which specifies SHF_ALLOC */ pr_debug("final section addresses:\n"); @@ -2847,18 +2899,18 @@ int __weak module_frob_arch_sections(Elf_Ehdr *hdr, return 0; } -static struct module *layout_and_allocate(struct load_info *info) +static struct module *layout_and_allocate(struct load_info *info, int flags) { /* Module within temporary copy. */ struct module *mod; Elf_Shdr *pcpusec; int err; - mod = setup_load_info(info); + mod = setup_load_info(info, flags); if (IS_ERR(mod)) return mod; - err = check_modinfo(mod, info); + err = check_modinfo(mod, info, flags); if (err) return ERR_PTR(err); @@ -2945,33 +2997,124 @@ static bool finished_loading(const char *name) return ret; } +/* Call module constructors. */ +static void do_mod_ctors(struct module *mod) +{ +#ifdef CONFIG_CONSTRUCTORS + unsigned long i; + + for (i = 0; i < mod->num_ctors; i++) + mod->ctors[i](); +#endif +} + +/* This is where the real work happens */ +static int do_init_module(struct module *mod) +{ + int ret = 0; + + blocking_notifier_call_chain(&module_notify_list, + MODULE_STATE_COMING, mod); + + /* Set RO and NX regions for core */ + set_section_ro_nx(mod->module_core, + mod->core_text_size, + mod->core_ro_size, + mod->core_size); + + /* Set RO and NX regions for init */ + set_section_ro_nx(mod->module_init, + mod->init_text_size, + mod->init_ro_size, + mod->init_size); + + do_mod_ctors(mod); + /* Start the module */ + if (mod->init != NULL) + ret = do_one_initcall(mod->init); + if (ret < 0) { + /* Init routine failed: abort. Try to protect us from + buggy refcounters. */ + mod->state = MODULE_STATE_GOING; + synchronize_sched(); + module_put(mod); + blocking_notifier_call_chain(&module_notify_list, + MODULE_STATE_GOING, mod); + free_module(mod); + wake_up_all(&module_wq); + return ret; + } + if (ret > 0) { + printk(KERN_WARNING +"%s: '%s'->init suspiciously returned %d, it should follow 0/-E convention\n" +"%s: loading module anyway...\n", + __func__, mod->name, ret, + __func__); + dump_stack(); + } + + /* Now it's a first class citizen! */ + mod->state = MODULE_STATE_LIVE; + blocking_notifier_call_chain(&module_notify_list, + MODULE_STATE_LIVE, mod); + + /* We need to finish all async code before the module init sequence is done */ + async_synchronize_full(); + + mutex_lock(&module_mutex); + /* Drop initial reference. */ + module_put(mod); + trim_init_extable(mod); +#ifdef CONFIG_KALLSYMS + mod->num_symtab = mod->core_num_syms; + mod->symtab = mod->core_symtab; + mod->strtab = mod->core_strtab; +#endif + unset_module_init_ro_nx(mod); + module_free(mod, mod->module_init); + mod->module_init = NULL; + mod->init_size = 0; + mod->init_ro_size = 0; + mod->init_text_size = 0; + mutex_unlock(&module_mutex); + wake_up_all(&module_wq); + + return 0; +} + +static int may_init_module(void) +{ + if (!capable(CAP_SYS_MODULE) || modules_disabled) + return -EPERM; + + return 0; +} + /* Allocate and load the module: note that size of section 0 is always zero, and we rely on this for optional sections. */ -static struct module *load_module(void __user *umod, - unsigned long len, - const char __user *uargs) +static int load_module(struct load_info *info, const char __user *uargs, + int flags) { - struct load_info info = { NULL, }; struct module *mod, *old; long err; - pr_debug("load_module: umod=%p, len=%lu, uargs=%p\n", - umod, len, uargs); + err = module_sig_check(info); + if (err) + goto free_copy; - /* Copy in the blobs from userspace, check they are vaguely sane. */ - err = copy_and_check(&info, umod, len, uargs); + err = elf_header_check(info); if (err) - return ERR_PTR(err); + goto free_copy; /* Figure out module layout, and allocate all the memory. */ - mod = layout_and_allocate(&info); + mod = layout_and_allocate(info, flags); if (IS_ERR(mod)) { err = PTR_ERR(mod); goto free_copy; } #ifdef CONFIG_MODULE_SIG - mod->sig_ok = info.sig_ok; + mod->sig_ok = info->sig_ok; if (!mod->sig_ok) add_taint_module(mod, TAINT_FORCED_MODULE); #endif @@ -2983,25 +3126,25 @@ static struct module *load_module(void __user *umod, /* Now we've got everything in the final locations, we can * find optional sections. */ - find_module_sections(mod, &info); + find_module_sections(mod, info); err = check_module_license_and_versions(mod); if (err) goto free_unload; /* Set up MODINFO_ATTR fields */ - setup_modinfo(mod, &info); + setup_modinfo(mod, info); /* Fix up syms, so that st_value is a pointer to location. */ - err = simplify_symbols(mod, &info); + err = simplify_symbols(mod, info); if (err < 0) goto free_modinfo; - err = apply_relocations(mod, &info); + err = apply_relocations(mod, info); if (err < 0) goto free_modinfo; - err = post_relocation(mod, &info); + err = post_relocation(mod, info); if (err < 0) goto free_modinfo; @@ -3041,14 +3184,14 @@ again: } /* This has to be done once we're sure module name is unique. */ - dynamic_debug_setup(info.debug, info.num_debug); + dynamic_debug_setup(info->debug, info->num_debug); /* Find duplicate symbols */ err = verify_export_symbols(mod); if (err < 0) goto ddebug; - module_bug_finalize(info.hdr, info.sechdrs, mod); + module_bug_finalize(info->hdr, info->sechdrs, mod); list_add_rcu(&mod->list, &modules); mutex_unlock(&module_mutex); @@ -3059,16 +3202,17 @@ again: goto unlink; /* Link in to syfs. */ - err = mod_sysfs_setup(mod, &info, mod->kp, mod->num_kp); + err = mod_sysfs_setup(mod, info, mod->kp, mod->num_kp); if (err < 0) goto unlink; /* Get rid of temporary copy. */ - free_copy(&info); + free_copy(info); /* Done! */ trace_module_load(mod); - return mod; + + return do_init_module(mod); unlink: mutex_lock(&module_mutex); @@ -3077,7 +3221,7 @@ again: module_bug_cleanup(mod); wake_up_all(&module_wq); ddebug: - dynamic_debug_remove(info.debug); + dynamic_debug_remove(info->debug); unlock: mutex_unlock(&module_mutex); synchronize_sched(); @@ -3089,106 +3233,52 @@ again: free_unload: module_unload_free(mod); free_module: - module_deallocate(mod, &info); + module_deallocate(mod, info); free_copy: - free_copy(&info); - return ERR_PTR(err); -} - -/* Call module constructors. */ -static void do_mod_ctors(struct module *mod) -{ -#ifdef CONFIG_CONSTRUCTORS - unsigned long i; - - for (i = 0; i < mod->num_ctors; i++) - mod->ctors[i](); -#endif + free_copy(info); + return err; } -/* This is where the real work happens */ SYSCALL_DEFINE3(init_module, void __user *, umod, unsigned long, len, const char __user *, uargs) { - struct module *mod; - int ret = 0; + int err; + struct load_info info = { }; - /* Must have permission */ - if (!capable(CAP_SYS_MODULE) || modules_disabled) - return -EPERM; + err = may_init_module(); + if (err) + return err; - /* Do all the hard work */ - mod = load_module(umod, len, uargs); - if (IS_ERR(mod)) - return PTR_ERR(mod); + pr_debug("init_module: umod=%p, len=%lu, uargs=%p\n", + umod, len, uargs); - blocking_notifier_call_chain(&module_notify_list, - MODULE_STATE_COMING, mod); + err = copy_module_from_user(umod, len, &info); + if (err) + return err; - /* Set RO and NX regions for core */ - set_section_ro_nx(mod->module_core, - mod->core_text_size, - mod->core_ro_size, - mod->core_size); + return load_module(&info, uargs, 0); +} - /* Set RO and NX regions for init */ - set_section_ro_nx(mod->module_init, - mod->init_text_size, - mod->init_ro_size, - mod->init_size); +SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) +{ + int err; + struct load_info info = { }; - do_mod_ctors(mod); - /* Start the module */ - if (mod->init != NULL) - ret = do_one_initcall(mod->init); - if (ret < 0) { - /* Init routine failed: abort. Try to protect us from - buggy refcounters. */ - mod->state = MODULE_STATE_GOING; - synchronize_sched(); - module_put(mod); - blocking_notifier_call_chain(&module_notify_list, - MODULE_STATE_GOING, mod); - free_module(mod); - wake_up_all(&module_wq); - return ret; - } - if (ret > 0) { - printk(KERN_WARNING -"%s: '%s'->init suspiciously returned %d, it should follow 0/-E convention\n" -"%s: loading module anyway...\n", - __func__, mod->name, ret, - __func__); - dump_stack(); - } + err = may_init_module(); + if (err) + return err; - /* Now it's a first class citizen! */ - mod->state = MODULE_STATE_LIVE; - blocking_notifier_call_chain(&module_notify_list, - MODULE_STATE_LIVE, mod); + pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); - /* We need to finish all async code before the module init sequence is done */ - async_synchronize_full(); + if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS + |MODULE_INIT_IGNORE_VERMAGIC)) + return -EINVAL; - mutex_lock(&module_mutex); - /* Drop initial reference. */ - module_put(mod); - trim_init_extable(mod); -#ifdef CONFIG_KALLSYMS - mod->num_symtab = mod->core_num_syms; - mod->symtab = mod->core_symtab; - mod->strtab = mod->core_strtab; -#endif - unset_module_init_ro_nx(mod); - module_free(mod, mod->module_init); - mod->module_init = NULL; - mod->init_size = 0; - mod->init_ro_size = 0; - mod->init_text_size = 0; - mutex_unlock(&module_mutex); - wake_up_all(&module_wq); + err = copy_module_from_fd(fd, &info); + if (err) + return err; - return 0; + return load_module(&info, uargs, flags); } static inline int within(unsigned long addr, void *start, unsigned long size) diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index 7e1c3de1ce4..78e2ecb2016 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -57,7 +57,8 @@ static inline struct nsproxy *create_nsproxy(void) * leave it to the caller to do proper locking and attach it to task. */ static struct nsproxy *create_new_namespaces(unsigned long flags, - struct task_struct *tsk, struct fs_struct *new_fs) + struct task_struct *tsk, struct user_namespace *user_ns, + struct fs_struct *new_fs) { struct nsproxy *new_nsp; int err; @@ -66,31 +67,31 @@ static struct nsproxy *create_new_namespaces(unsigned long flags, if (!new_nsp) return ERR_PTR(-ENOMEM); - new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, new_fs); + new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, user_ns, new_fs); if (IS_ERR(new_nsp->mnt_ns)) { err = PTR_ERR(new_nsp->mnt_ns); goto out_ns; } - new_nsp->uts_ns = copy_utsname(flags, tsk); + new_nsp->uts_ns = copy_utsname(flags, user_ns, tsk->nsproxy->uts_ns); if (IS_ERR(new_nsp->uts_ns)) { err = PTR_ERR(new_nsp->uts_ns); goto out_uts; } - new_nsp->ipc_ns = copy_ipcs(flags, tsk); + new_nsp->ipc_ns = copy_ipcs(flags, user_ns, tsk->nsproxy->ipc_ns); if (IS_ERR(new_nsp->ipc_ns)) { err = PTR_ERR(new_nsp->ipc_ns); goto out_ipc; } - new_nsp->pid_ns = copy_pid_ns(flags, task_active_pid_ns(tsk)); + new_nsp->pid_ns = copy_pid_ns(flags, user_ns, tsk->nsproxy->pid_ns); if (IS_ERR(new_nsp->pid_ns)) { err = PTR_ERR(new_nsp->pid_ns); goto out_pid; } - new_nsp->net_ns = copy_net_ns(flags, task_cred_xxx(tsk, user_ns), tsk->nsproxy->net_ns); + new_nsp->net_ns = copy_net_ns(flags, user_ns, tsk->nsproxy->net_ns); if (IS_ERR(new_nsp->net_ns)) { err = PTR_ERR(new_nsp->net_ns); goto out_net; @@ -122,6 +123,7 @@ out_ns: int copy_namespaces(unsigned long flags, struct task_struct *tsk) { struct nsproxy *old_ns = tsk->nsproxy; + struct user_namespace *user_ns = task_cred_xxx(tsk, user_ns); struct nsproxy *new_ns; int err = 0; @@ -134,7 +136,7 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk) CLONE_NEWPID | CLONE_NEWNET))) return 0; - if (!capable(CAP_SYS_ADMIN)) { + if (!ns_capable(user_ns, CAP_SYS_ADMIN)) { err = -EPERM; goto out; } @@ -151,7 +153,8 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk) goto out; } - new_ns = create_new_namespaces(flags, tsk, tsk->fs); + new_ns = create_new_namespaces(flags, tsk, + task_cred_xxx(tsk, user_ns), tsk->fs); if (IS_ERR(new_ns)) { err = PTR_ERR(new_ns); goto out; @@ -183,19 +186,21 @@ void free_nsproxy(struct nsproxy *ns) * On success, returns the new nsproxy. */ int unshare_nsproxy_namespaces(unsigned long unshare_flags, - struct nsproxy **new_nsp, struct fs_struct *new_fs) + struct nsproxy **new_nsp, struct cred *new_cred, struct fs_struct *new_fs) { + struct user_namespace *user_ns; int err = 0; if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | - CLONE_NEWNET))) + CLONE_NEWNET | CLONE_NEWPID))) return 0; - if (!capable(CAP_SYS_ADMIN)) + user_ns = new_cred ? new_cred->user_ns : current_user_ns(); + if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; - *new_nsp = create_new_namespaces(unshare_flags, current, - new_fs ? new_fs : current->fs); + *new_nsp = create_new_namespaces(unshare_flags, current, user_ns, + new_fs ? new_fs : current->fs); if (IS_ERR(*new_nsp)) { err = PTR_ERR(*new_nsp); goto out; @@ -241,9 +246,6 @@ SYSCALL_DEFINE2(setns, int, fd, int, nstype) struct file *file; int err; - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - file = proc_ns_fget(fd); if (IS_ERR(file)) return PTR_ERR(file); @@ -254,7 +256,7 @@ SYSCALL_DEFINE2(setns, int, fd, int, nstype) if (nstype && (ops->type != nstype)) goto out; - new_nsproxy = create_new_namespaces(0, tsk, tsk->fs); + new_nsproxy = create_new_namespaces(0, tsk, current_user_ns(), tsk->fs); if (IS_ERR(new_nsproxy)) { err = PTR_ERR(new_nsproxy); goto out; diff --git a/kernel/pid.c b/kernel/pid.c index fd996c1ed9f..36aa02ff17d 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -36,6 +36,7 @@ #include <linux/pid_namespace.h> #include <linux/init_task.h> #include <linux/syscalls.h> +#include <linux/proc_fs.h> #define pid_hashfn(nr, ns) \ hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift) @@ -78,24 +79,11 @@ struct pid_namespace init_pid_ns = { .last_pid = 0, .level = 0, .child_reaper = &init_task, + .user_ns = &init_user_ns, + .proc_inum = PROC_PID_INIT_INO, }; EXPORT_SYMBOL_GPL(init_pid_ns); -int is_container_init(struct task_struct *tsk) -{ - int ret = 0; - struct pid *pid; - - rcu_read_lock(); - pid = task_pid(tsk); - if (pid != NULL && pid->numbers[pid->level].nr == 1) - ret = 1; - rcu_read_unlock(); - - return ret; -} -EXPORT_SYMBOL(is_container_init); - /* * Note: disable interrupts while the pidmap_lock is held as an * interrupt might come in and do read_lock(&tasklist_lock). @@ -269,8 +257,24 @@ void free_pid(struct pid *pid) unsigned long flags; spin_lock_irqsave(&pidmap_lock, flags); - for (i = 0; i <= pid->level; i++) - hlist_del_rcu(&pid->numbers[i].pid_chain); + for (i = 0; i <= pid->level; i++) { + struct upid *upid = pid->numbers + i; + struct pid_namespace *ns = upid->ns; + hlist_del_rcu(&upid->pid_chain); + switch(--ns->nr_hashed) { + case 1: + /* When all that is left in the pid namespace + * is the reaper wake up the reaper. The reaper + * may be sleeping in zap_pid_ns_processes(). + */ + wake_up_process(ns->child_reaper); + break; + case 0: + ns->nr_hashed = -1; + schedule_work(&ns->proc_work); + break; + } + } spin_unlock_irqrestore(&pidmap_lock, flags); for (i = 0; i <= pid->level; i++) @@ -292,6 +296,7 @@ struct pid *alloc_pid(struct pid_namespace *ns) goto out; tmp = ns; + pid->level = ns->level; for (i = ns->level; i >= 0; i--) { nr = alloc_pidmap(tmp); if (nr < 0) @@ -302,22 +307,32 @@ struct pid *alloc_pid(struct pid_namespace *ns) tmp = tmp->parent; } + if (unlikely(is_child_reaper(pid))) { + if (pid_ns_prepare_proc(ns)) + goto out_free; + } + get_pid_ns(ns); - pid->level = ns->level; atomic_set(&pid->count, 1); for (type = 0; type < PIDTYPE_MAX; ++type) INIT_HLIST_HEAD(&pid->tasks[type]); upid = pid->numbers + ns->level; spin_lock_irq(&pidmap_lock); - for ( ; upid >= pid->numbers; --upid) + if (ns->nr_hashed < 0) + goto out_unlock; + for ( ; upid >= pid->numbers; --upid) { hlist_add_head_rcu(&upid->pid_chain, &pid_hash[pid_hashfn(upid->nr, upid->ns)]); + upid->ns->nr_hashed++; + } spin_unlock_irq(&pidmap_lock); out: return pid; +out_unlock: + spin_unlock(&pidmap_lock); out_free: while (++i <= ns->level) free_pidmap(pid->numbers + i); @@ -344,7 +359,7 @@ EXPORT_SYMBOL_GPL(find_pid_ns); struct pid *find_vpid(int nr) { - return find_pid_ns(nr, current->nsproxy->pid_ns); + return find_pid_ns(nr, task_active_pid_ns(current)); } EXPORT_SYMBOL_GPL(find_vpid); @@ -428,7 +443,7 @@ struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns) struct task_struct *find_task_by_vpid(pid_t vnr) { - return find_task_by_pid_ns(vnr, current->nsproxy->pid_ns); + return find_task_by_pid_ns(vnr, task_active_pid_ns(current)); } struct pid *get_task_pid(struct task_struct *task, enum pid_type type) @@ -483,7 +498,7 @@ EXPORT_SYMBOL_GPL(pid_nr_ns); pid_t pid_vnr(struct pid *pid) { - return pid_nr_ns(pid, current->nsproxy->pid_ns); + return pid_nr_ns(pid, task_active_pid_ns(current)); } EXPORT_SYMBOL_GPL(pid_vnr); @@ -494,7 +509,7 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, rcu_read_lock(); if (!ns) - ns = current->nsproxy->pid_ns; + ns = task_active_pid_ns(current); if (likely(pid_alive(task))) { if (type != PIDTYPE_PID) task = task->group_leader; @@ -569,6 +584,7 @@ void __init pidmap_init(void) /* Reserve PID 0. We never call free_pidmap(0) */ set_bit(0, init_pid_ns.pidmap[0].page); atomic_dec(&init_pid_ns.pidmap[0].nr_free); + init_pid_ns.nr_hashed = 1; init_pid_ns.pid_cachep = KMEM_CACHE(pid, SLAB_HWCACHE_ALIGN | SLAB_PANIC); diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 7b07cc0dfb7..fdbd0cdf271 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -10,6 +10,7 @@ #include <linux/pid.h> #include <linux/pid_namespace.h> +#include <linux/user_namespace.h> #include <linux/syscalls.h> #include <linux/err.h> #include <linux/acct.h> @@ -71,10 +72,17 @@ err_alloc: return NULL; } +static void proc_cleanup_work(struct work_struct *work) +{ + struct pid_namespace *ns = container_of(work, struct pid_namespace, proc_work); + pid_ns_release_proc(ns); +} + /* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */ #define MAX_PID_NS_LEVEL 32 -static struct pid_namespace *create_pid_namespace(struct pid_namespace *parent_pid_ns) +static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns, + struct pid_namespace *parent_pid_ns) { struct pid_namespace *ns; unsigned int level = parent_pid_ns->level + 1; @@ -99,9 +107,15 @@ static struct pid_namespace *create_pid_namespace(struct pid_namespace *parent_p if (ns->pid_cachep == NULL) goto out_free_map; + err = proc_alloc_inum(&ns->proc_inum); + if (err) + goto out_free_map; + kref_init(&ns->kref); ns->level = level; ns->parent = get_pid_ns(parent_pid_ns); + ns->user_ns = get_user_ns(user_ns); + INIT_WORK(&ns->proc_work, proc_cleanup_work); set_bit(0, ns->pidmap[0].page); atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1); @@ -109,14 +123,8 @@ static struct pid_namespace *create_pid_namespace(struct pid_namespace *parent_p for (i = 1; i < PIDMAP_ENTRIES; i++) atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE); - err = pid_ns_prepare_proc(ns); - if (err) - goto out_put_parent_pid_ns; - return ns; -out_put_parent_pid_ns: - put_pid_ns(parent_pid_ns); out_free_map: kfree(ns->pidmap[0].page); out_free: @@ -129,18 +137,21 @@ static void destroy_pid_namespace(struct pid_namespace *ns) { int i; + proc_free_inum(ns->proc_inum); for (i = 0; i < PIDMAP_ENTRIES; i++) kfree(ns->pidmap[i].page); + put_user_ns(ns->user_ns); kmem_cache_free(pid_ns_cachep, ns); } -struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *old_ns) +struct pid_namespace *copy_pid_ns(unsigned long flags, + struct user_namespace *user_ns, struct pid_namespace *old_ns) { if (!(flags & CLONE_NEWPID)) return get_pid_ns(old_ns); - if (flags & (CLONE_THREAD|CLONE_PARENT)) + if (task_active_pid_ns(current) != old_ns) return ERR_PTR(-EINVAL); - return create_pid_namespace(old_ns); + return create_pid_namespace(user_ns, old_ns); } static void free_pid_ns(struct kref *kref) @@ -211,22 +222,15 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) /* * sys_wait4() above can't reap the TASK_DEAD children. - * Make sure they all go away, see __unhash_process(). + * Make sure they all go away, see free_pid(). */ for (;;) { - bool need_wait = false; - - read_lock(&tasklist_lock); - if (!list_empty(¤t->children)) { - __set_current_state(TASK_UNINTERRUPTIBLE); - need_wait = true; - } - read_unlock(&tasklist_lock); - - if (!need_wait) + set_current_state(TASK_UNINTERRUPTIBLE); + if (pid_ns->nr_hashed == 1) break; schedule(); } + __set_current_state(TASK_RUNNING); if (pid_ns->reboot) current->signal->group_exit_code = pid_ns->reboot; @@ -239,9 +243,10 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) static int pid_ns_ctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + struct pid_namespace *pid_ns = task_active_pid_ns(current); struct ctl_table tmp = *table; - if (write && !capable(CAP_SYS_ADMIN)) + if (write && !ns_capable(pid_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; /* @@ -250,7 +255,7 @@ static int pid_ns_ctl_handler(struct ctl_table *table, int write, * it should synchronize its usage with external means. */ - tmp.data = ¤t->nsproxy->pid_ns->last_pid; + tmp.data = &pid_ns->last_pid; return proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); } @@ -299,6 +304,68 @@ int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) return 0; } +static void *pidns_get(struct task_struct *task) +{ + struct pid_namespace *ns; + + rcu_read_lock(); + ns = get_pid_ns(task_active_pid_ns(task)); + rcu_read_unlock(); + + return ns; +} + +static void pidns_put(void *ns) +{ + put_pid_ns(ns); +} + +static int pidns_install(struct nsproxy *nsproxy, void *ns) +{ + struct pid_namespace *active = task_active_pid_ns(current); + struct pid_namespace *ancestor, *new = ns; + + if (!ns_capable(new->user_ns, CAP_SYS_ADMIN) || + !nsown_capable(CAP_SYS_ADMIN)) + return -EPERM; + + /* + * Only allow entering the current active pid namespace + * or a child of the current active pid namespace. + * + * This is required for fork to return a usable pid value and + * this maintains the property that processes and their + * children can not escape their current pid namespace. + */ + if (new->level < active->level) + return -EINVAL; + + ancestor = new; + while (ancestor->level > active->level) + ancestor = ancestor->parent; + if (ancestor != active) + return -EINVAL; + + put_pid_ns(nsproxy->pid_ns); + nsproxy->pid_ns = get_pid_ns(new); + return 0; +} + +static unsigned int pidns_inum(void *ns) +{ + struct pid_namespace *pid_ns = ns; + return pid_ns->proc_inum; +} + +const struct proc_ns_operations pidns_operations = { + .name = "pid", + .type = CLONE_NEWPID, + .get = pidns_get, + .put = pidns_put, + .install = pidns_install, + .inum = pidns_inum, +}; + static __init int pid_namespaces_init(void) { pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC); diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index d73840271dc..a278cad1d5d 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -9,6 +9,7 @@ #include <asm/uaccess.h> #include <linux/kernel_stat.h> #include <trace/events/timer.h> +#include <linux/random.h> /* * Called after updating RLIMIT_CPU to run cpu timer and update @@ -470,6 +471,8 @@ static void cleanup_timers(struct list_head *head, */ void posix_cpu_timers_exit(struct task_struct *tsk) { + add_device_randomness((const void*) &tsk->se.sum_exec_runtime, + sizeof(unsigned long long)); cleanup_timers(tsk->cpu_timers, tsk->utime, tsk->stime, tsk->se.sum_exec_runtime); diff --git a/kernel/printk.c b/kernel/printk.c index 22e070f3470..19c0d7bcf24 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -747,6 +747,21 @@ void __init setup_log_buf(int early) free, (free * 100) / __LOG_BUF_LEN); } +static bool __read_mostly ignore_loglevel; + +static int __init ignore_loglevel_setup(char *str) +{ + ignore_loglevel = 1; + printk(KERN_INFO "debug: ignoring loglevel setting.\n"); + + return 0; +} + +early_param("ignore_loglevel", ignore_loglevel_setup); +module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(ignore_loglevel, "ignore loglevel setting, to" + "print all kernel messages to the console."); + #ifdef CONFIG_BOOT_PRINTK_DELAY static int boot_delay; /* msecs delay after each printk during bootup */ @@ -770,13 +785,15 @@ static int __init boot_delay_setup(char *str) } __setup("boot_delay=", boot_delay_setup); -static void boot_delay_msec(void) +static void boot_delay_msec(int level) { unsigned long long k; unsigned long timeout; - if (boot_delay == 0 || system_state != SYSTEM_BOOTING) + if ((boot_delay == 0 || system_state != SYSTEM_BOOTING) + || (level >= console_loglevel && !ignore_loglevel)) { return; + } k = (unsigned long long)loops_per_msec * boot_delay; @@ -795,7 +812,7 @@ static void boot_delay_msec(void) } } #else -static inline void boot_delay_msec(void) +static inline void boot_delay_msec(int level) { } #endif @@ -1238,21 +1255,6 @@ SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) return do_syslog(type, buf, len, SYSLOG_FROM_CALL); } -static bool __read_mostly ignore_loglevel; - -static int __init ignore_loglevel_setup(char *str) -{ - ignore_loglevel = 1; - printk(KERN_INFO "debug: ignoring loglevel setting.\n"); - - return 0; -} - -early_param("ignore_loglevel", ignore_loglevel_setup); -module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR); -MODULE_PARM_DESC(ignore_loglevel, "ignore loglevel setting, to" - "print all kernel messages to the console."); - /* * Call the console drivers, asking them to write out * log_buf[start] to log_buf[end - 1]. @@ -1498,7 +1500,7 @@ asmlinkage int vprintk_emit(int facility, int level, int this_cpu; int printed_len = 0; - boot_delay_msec(); + boot_delay_msec(level); printk_delay(); /* This stops the holder of console_sem just where we want him */ diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 1f5e55dda95..1599157336a 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -215,8 +215,12 @@ ok: smp_rmb(); if (task->mm) dumpable = get_dumpable(task->mm); - if (!dumpable && !ptrace_has_cap(task_user_ns(task), mode)) + rcu_read_lock(); + if (!dumpable && !ptrace_has_cap(__task_cred(task)->user_ns, mode)) { + rcu_read_unlock(); return -EPERM; + } + rcu_read_unlock(); return security_ptrace_access_check(task, mode); } @@ -280,8 +284,10 @@ static int ptrace_attach(struct task_struct *task, long request, if (seize) flags |= PT_SEIZED; - if (ns_capable(task_user_ns(task), CAP_SYS_PTRACE)) + rcu_read_lock(); + if (ns_capable(__task_cred(task)->user_ns, CAP_SYS_PTRACE)) flags |= PT_PTRACE_CAP; + rcu_read_unlock(); task->ptrace = flags; __ptrace_link(task, current); @@ -457,6 +463,9 @@ void exit_ptrace(struct task_struct *tracer) return; list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) { + if (unlikely(p->ptrace & PT_EXITKILL)) + send_sig_info(SIGKILL, SEND_SIG_FORCED, p); + if (__ptrace_detach(tracer, p)) list_add(&p->ptrace_entry, &ptrace_dead); } diff --git a/kernel/res_counter.c b/kernel/res_counter.c index 3920d593e63..ff55247e704 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -86,33 +86,39 @@ int res_counter_charge_nofail(struct res_counter *counter, unsigned long val, return __res_counter_charge(counter, val, limit_fail_at, true); } -void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val) +u64 res_counter_uncharge_locked(struct res_counter *counter, unsigned long val) { if (WARN_ON(counter->usage < val)) val = counter->usage; counter->usage -= val; + return counter->usage; } -void res_counter_uncharge_until(struct res_counter *counter, - struct res_counter *top, - unsigned long val) +u64 res_counter_uncharge_until(struct res_counter *counter, + struct res_counter *top, + unsigned long val) { unsigned long flags; struct res_counter *c; + u64 ret = 0; local_irq_save(flags); for (c = counter; c != top; c = c->parent) { + u64 r; spin_lock(&c->lock); - res_counter_uncharge_locked(c, val); + r = res_counter_uncharge_locked(c, val); + if (c == counter) + ret = r; spin_unlock(&c->lock); } local_irq_restore(flags); + return ret; } -void res_counter_uncharge(struct res_counter *counter, unsigned long val) +u64 res_counter_uncharge(struct res_counter *counter, unsigned long val) { - res_counter_uncharge_until(counter, NULL, val); + return res_counter_uncharge_until(counter, NULL, val); } static inline unsigned long long * diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0533496b622..257002c13bb 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -193,23 +193,10 @@ static void sched_feat_disable(int i) { }; static void sched_feat_enable(int i) { }; #endif /* HAVE_JUMP_LABEL */ -static ssize_t -sched_feat_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) +static int sched_feat_set(char *cmp) { - char buf[64]; - char *cmp; - int neg = 0; int i; - - if (cnt > 63) - cnt = 63; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - cmp = strstrip(buf); + int neg = 0; if (strncmp(cmp, "NO_", 3) == 0) { neg = 1; @@ -229,6 +216,27 @@ sched_feat_write(struct file *filp, const char __user *ubuf, } } + return i; +} + +static ssize_t +sched_feat_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + char *cmp; + int i; + + if (cnt > 63) + cnt = 63; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + cmp = strstrip(buf); + + i = sched_feat_set(cmp); if (i == __SCHED_FEAT_NR) return -EINVAL; @@ -1560,7 +1568,40 @@ static void __sched_fork(struct task_struct *p) #ifdef CONFIG_PREEMPT_NOTIFIERS INIT_HLIST_HEAD(&p->preempt_notifiers); #endif + +#ifdef CONFIG_NUMA_BALANCING + if (p->mm && atomic_read(&p->mm->mm_users) == 1) { + p->mm->numa_next_scan = jiffies; + p->mm->numa_next_reset = jiffies; + p->mm->numa_scan_seq = 0; + } + + p->node_stamp = 0ULL; + p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0; + p->numa_migrate_seq = p->mm ? p->mm->numa_scan_seq - 1 : 0; + p->numa_scan_period = sysctl_numa_balancing_scan_delay; + p->numa_work.next = &p->numa_work; +#endif /* CONFIG_NUMA_BALANCING */ +} + +#ifdef CONFIG_NUMA_BALANCING +#ifdef CONFIG_SCHED_DEBUG +void set_numabalancing_state(bool enabled) +{ + if (enabled) + sched_feat_set("NUMA"); + else + sched_feat_set("NO_NUMA"); } +#else +__read_mostly bool numabalancing_enabled; + +void set_numabalancing_state(bool enabled) +{ + numabalancing_enabled = enabled; +} +#endif /* CONFIG_SCHED_DEBUG */ +#endif /* CONFIG_NUMA_BALANCING */ /* * fork()/clone()-time setup: @@ -4056,8 +4097,14 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) goto out_free_cpus_allowed; } retval = -EPERM; - if (!check_same_owner(p) && !ns_capable(task_user_ns(p), CAP_SYS_NICE)) - goto out_unlock; + if (!check_same_owner(p)) { + rcu_read_lock(); + if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { + rcu_read_unlock(); + goto out_unlock; + } + rcu_read_unlock(); + } retval = security_task_setscheduler(p); if (retval) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 756f9f9e854..5eea8707234 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -26,6 +26,9 @@ #include <linux/slab.h> #include <linux/profile.h> #include <linux/interrupt.h> +#include <linux/mempolicy.h> +#include <linux/migrate.h> +#include <linux/task_work.h> #include <trace/events/sched.h> @@ -774,6 +777,230 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) * Scheduling class queueing methods: */ +#ifdef CONFIG_NUMA_BALANCING +/* + * numa task sample period in ms + */ +unsigned int sysctl_numa_balancing_scan_period_min = 100; +unsigned int sysctl_numa_balancing_scan_period_max = 100*50; +unsigned int sysctl_numa_balancing_scan_period_reset = 100*600; + +/* Portion of address space to scan in MB */ +unsigned int sysctl_numa_balancing_scan_size = 256; + +/* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */ +unsigned int sysctl_numa_balancing_scan_delay = 1000; + +static void task_numa_placement(struct task_struct *p) +{ + int seq; + + if (!p->mm) /* for example, ksmd faulting in a user's mm */ + return; + seq = ACCESS_ONCE(p->mm->numa_scan_seq); + if (p->numa_scan_seq == seq) + return; + p->numa_scan_seq = seq; + + /* FIXME: Scheduling placement policy hints go here */ +} + +/* + * Got a PROT_NONE fault for a page on @node. + */ +void task_numa_fault(int node, int pages, bool migrated) +{ + struct task_struct *p = current; + + if (!sched_feat_numa(NUMA)) + return; + + /* FIXME: Allocate task-specific structure for placement policy here */ + + /* + * If pages are properly placed (did not migrate) then scan slower. + * This is reset periodically in case of phase changes + */ + if (!migrated) + p->numa_scan_period = min(sysctl_numa_balancing_scan_period_max, + p->numa_scan_period + jiffies_to_msecs(10)); + + task_numa_placement(p); +} + +static void reset_ptenuma_scan(struct task_struct *p) +{ + ACCESS_ONCE(p->mm->numa_scan_seq)++; + p->mm->numa_scan_offset = 0; +} + +/* + * The expensive part of numa migration is done from task_work context. + * Triggered from task_tick_numa(). + */ +void task_numa_work(struct callback_head *work) +{ + unsigned long migrate, next_scan, now = jiffies; + struct task_struct *p = current; + struct mm_struct *mm = p->mm; + struct vm_area_struct *vma; + unsigned long start, end; + long pages; + + WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work)); + + work->next = work; /* protect against double add */ + /* + * Who cares about NUMA placement when they're dying. + * + * NOTE: make sure not to dereference p->mm before this check, + * exit_task_work() happens _after_ exit_mm() so we could be called + * without p->mm even though we still had it when we enqueued this + * work. + */ + if (p->flags & PF_EXITING) + return; + + /* + * We do not care about task placement until a task runs on a node + * other than the first one used by the address space. This is + * largely because migrations are driven by what CPU the task + * is running on. If it's never scheduled on another node, it'll + * not migrate so why bother trapping the fault. + */ + if (mm->first_nid == NUMA_PTE_SCAN_INIT) + mm->first_nid = numa_node_id(); + if (mm->first_nid != NUMA_PTE_SCAN_ACTIVE) { + /* Are we running on a new node yet? */ + if (numa_node_id() == mm->first_nid && + !sched_feat_numa(NUMA_FORCE)) + return; + + mm->first_nid = NUMA_PTE_SCAN_ACTIVE; + } + + /* + * Reset the scan period if enough time has gone by. Objective is that + * scanning will be reduced if pages are properly placed. As tasks + * can enter different phases this needs to be re-examined. Lacking + * proper tracking of reference behaviour, this blunt hammer is used. + */ + migrate = mm->numa_next_reset; + if (time_after(now, migrate)) { + p->numa_scan_period = sysctl_numa_balancing_scan_period_min; + next_scan = now + msecs_to_jiffies(sysctl_numa_balancing_scan_period_reset); + xchg(&mm->numa_next_reset, next_scan); + } + + /* + * Enforce maximal scan/migration frequency.. + */ + migrate = mm->numa_next_scan; + if (time_before(now, migrate)) + return; + + if (p->numa_scan_period == 0) + p->numa_scan_period = sysctl_numa_balancing_scan_period_min; + + next_scan = now + msecs_to_jiffies(p->numa_scan_period); + if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate) + return; + + /* + * Do not set pte_numa if the current running node is rate-limited. + * This loses statistics on the fault but if we are unwilling to + * migrate to this node, it is less likely we can do useful work + */ + if (migrate_ratelimited(numa_node_id())) + return; + + start = mm->numa_scan_offset; + pages = sysctl_numa_balancing_scan_size; + pages <<= 20 - PAGE_SHIFT; /* MB in pages */ + if (!pages) + return; + + down_read(&mm->mmap_sem); + vma = find_vma(mm, start); + if (!vma) { + reset_ptenuma_scan(p); + start = 0; + vma = mm->mmap; + } + for (; vma; vma = vma->vm_next) { + if (!vma_migratable(vma)) + continue; + + /* Skip small VMAs. They are not likely to be of relevance */ + if (vma->vm_end - vma->vm_start < HPAGE_SIZE) + continue; + + do { + start = max(start, vma->vm_start); + end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE); + end = min(end, vma->vm_end); + pages -= change_prot_numa(vma, start, end); + + start = end; + if (pages <= 0) + goto out; + } while (end != vma->vm_end); + } + +out: + /* + * It is possible to reach the end of the VMA list but the last few VMAs are + * not guaranteed to the vma_migratable. If they are not, we would find the + * !migratable VMA on the next scan but not reset the scanner to the start + * so check it now. + */ + if (vma) + mm->numa_scan_offset = start; + else + reset_ptenuma_scan(p); + up_read(&mm->mmap_sem); +} + +/* + * Drive the periodic memory faults.. + */ +void task_tick_numa(struct rq *rq, struct task_struct *curr) +{ + struct callback_head *work = &curr->numa_work; + u64 period, now; + + /* + * We don't care about NUMA placement if we don't have memory. + */ + if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work) + return; + + /* + * Using runtime rather than walltime has the dual advantage that + * we (mostly) drive the selection from busy threads and that the + * task needs to have done some actual work before we bother with + * NUMA placement. + */ + now = curr->se.sum_exec_runtime; + period = (u64)curr->numa_scan_period * NSEC_PER_MSEC; + + if (now - curr->node_stamp > period) { + if (!curr->node_stamp) + curr->numa_scan_period = sysctl_numa_balancing_scan_period_min; + curr->node_stamp = now; + + if (!time_before(jiffies, curr->mm->numa_next_scan)) { + init_task_work(work, task_numa_work); /* TODO: move this into sched_fork() */ + task_work_add(curr, work, true); + } + } +} +#else +static void task_tick_numa(struct rq *rq, struct task_struct *curr) +{ +} +#endif /* CONFIG_NUMA_BALANCING */ + static void account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) { @@ -5501,6 +5728,9 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) entity_tick(cfs_rq, se, queued); } + if (sched_feat_numa(NUMA)) + task_tick_numa(rq, curr); + update_rq_runnable_avg(rq, 1); } diff --git a/kernel/sched/features.h b/kernel/sched/features.h index e68e69ab917..1ad1d2b5395 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -66,3 +66,14 @@ SCHED_FEAT(TTWU_QUEUE, true) SCHED_FEAT(FORCE_SD_OVERLAP, false) SCHED_FEAT(RT_RUNTIME_SHARE, true) SCHED_FEAT(LB_MIN, false) + +/* + * Apply the automatic NUMA scheduling policy. Enabled automatically + * at runtime if running on a NUMA machine. Can be controlled via + * numa_balancing=. Allow PTE scanning to be forced on UMA machines + * for debugging the core machinery. + */ +#ifdef CONFIG_NUMA_BALANCING +SCHED_FEAT(NUMA, false) +SCHED_FEAT(NUMA_FORCE, false) +#endif diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 5eca173b563..fc886441436 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -663,6 +663,18 @@ extern struct static_key sched_feat_keys[__SCHED_FEAT_NR]; #define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x)) #endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */ +#ifdef CONFIG_NUMA_BALANCING +#define sched_feat_numa(x) sched_feat(x) +#ifdef CONFIG_SCHED_DEBUG +#define numabalancing_enabled sched_feat_numa(NUMA) +#else +extern bool numabalancing_enabled; +#endif /* CONFIG_SCHED_DEBUG */ +#else +#define sched_feat_numa(x) (0) +#define numabalancing_enabled (0) +#endif /* CONFIG_NUMA_BALANCING */ + static inline u64 global_rt_period(void) { return (u64)sysctl_sched_rt_period * NSEC_PER_USEC; diff --git a/kernel/seccomp.c b/kernel/seccomp.c index ee376beedaf..5af44b59377 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -396,25 +396,29 @@ int __secure_computing(int this_syscall) #ifdef CONFIG_SECCOMP_FILTER case SECCOMP_MODE_FILTER: { int data; + struct pt_regs *regs = task_pt_regs(current); ret = seccomp_run_filters(this_syscall); data = ret & SECCOMP_RET_DATA; ret &= SECCOMP_RET_ACTION; switch (ret) { case SECCOMP_RET_ERRNO: /* Set the low-order 16-bits as a errno. */ - syscall_set_return_value(current, task_pt_regs(current), + syscall_set_return_value(current, regs, -data, 0); goto skip; case SECCOMP_RET_TRAP: /* Show the handler the original registers. */ - syscall_rollback(current, task_pt_regs(current)); + syscall_rollback(current, regs); /* Let the filter pass back 16 bits of data. */ seccomp_send_sigsys(this_syscall, data); goto skip; case SECCOMP_RET_TRACE: /* Skip these calls if there is no tracer. */ - if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) + if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) { + syscall_set_return_value(current, regs, + -ENOSYS, 0); goto skip; + } /* Allow the BPF to provide the event message */ ptrace_event(PTRACE_EVENT_SECCOMP, data); /* @@ -425,6 +429,9 @@ int __secure_computing(int this_syscall) */ if (fatal_signal_pending(current)) break; + if (syscall_get_nr(current, regs) < 0) + goto skip; /* Explicit request to skip. */ + return 0; case SECCOMP_RET_ALLOW: return 0; diff --git a/kernel/signal.c b/kernel/signal.c index a49c7f36ceb..580a91e6347 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1753,7 +1753,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, * see comment in do_notify_parent() about the following 4 lines */ rcu_read_lock(); - info.si_pid = task_pid_nr_ns(tsk, parent->nsproxy->pid_ns); + info.si_pid = task_pid_nr_ns(tsk, task_active_pid_ns(parent)); info.si_uid = from_kuid_munged(task_cred_xxx(parent, user_ns), task_uid(tsk)); rcu_read_unlock(); diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index dbff751e408..395084d4ce1 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -25,6 +25,7 @@ cond_syscall(sys_swapoff); cond_syscall(sys_kexec_load); cond_syscall(compat_sys_kexec_load); cond_syscall(sys_init_module); +cond_syscall(sys_finit_module); cond_syscall(sys_delete_module); cond_syscall(sys_socketpair); cond_syscall(sys_bind); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 33f71f37267..c88878db491 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -256,9 +256,11 @@ static int min_sched_granularity_ns = 100000; /* 100 usecs */ static int max_sched_granularity_ns = NSEC_PER_SEC; /* 1 second */ static int min_wakeup_granularity_ns; /* 0 usecs */ static int max_wakeup_granularity_ns = NSEC_PER_SEC; /* 1 second */ +#ifdef CONFIG_SMP static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE; static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1; -#endif +#endif /* CONFIG_SMP */ +#endif /* CONFIG_SCHED_DEBUG */ #ifdef CONFIG_COMPACTION static int min_extfrag_threshold; @@ -301,6 +303,7 @@ static struct ctl_table kern_table[] = { .extra1 = &min_wakeup_granularity_ns, .extra2 = &max_wakeup_granularity_ns, }, +#ifdef CONFIG_SMP { .procname = "sched_tunable_scaling", .data = &sysctl_sched_tunable_scaling, @@ -347,7 +350,45 @@ static struct ctl_table kern_table[] = { .extra1 = &zero, .extra2 = &one, }, -#endif +#endif /* CONFIG_SMP */ +#ifdef CONFIG_NUMA_BALANCING + { + .procname = "numa_balancing_scan_delay_ms", + .data = &sysctl_numa_balancing_scan_delay, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "numa_balancing_scan_period_min_ms", + .data = &sysctl_numa_balancing_scan_period_min, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "numa_balancing_scan_period_reset", + .data = &sysctl_numa_balancing_scan_period_reset, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "numa_balancing_scan_period_max_ms", + .data = &sysctl_numa_balancing_scan_period_max, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "numa_balancing_scan_size_mb", + .data = &sysctl_numa_balancing_scan_size, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif /* CONFIG_NUMA_BALANCING */ +#endif /* CONFIG_SCHED_DEBUG */ { .procname = "sched_rt_period_us", .data = &sysctl_sched_rt_period, diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index 65bdcf198d4..5a638445050 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -1344,7 +1344,7 @@ static ssize_t binary_sysctl(const int *name, int nlen, goto out_putname; } - mnt = current->nsproxy->pid_ns->proc_mnt; + mnt = task_active_pid_ns(current)->proc_mnt; file = file_open_root(mnt->mnt_root, mnt, pathname, flags); result = PTR_ERR(file); if (IS_ERR(file)) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index afd092de45b..3ffe4c5ad3f 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2675,12 +2675,12 @@ ftrace_notrace_open(struct inode *inode, struct file *file) } loff_t -ftrace_regex_lseek(struct file *file, loff_t offset, int origin) +ftrace_regex_lseek(struct file *file, loff_t offset, int whence) { loff_t ret; if (file->f_mode & FMODE_READ) - ret = seq_lseek(file, offset, origin); + ret = seq_lseek(file, offset, whence); else file->f_pos = ret = 1; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 61e081b4ba1..e5125677efa 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3034,6 +3034,31 @@ static void set_buffer_entries(struct trace_array *tr, unsigned long val) tr->data[cpu]->entries = val; } +/* resize @tr's buffer to the size of @size_tr's entries */ +static int resize_buffer_duplicate_size(struct trace_array *tr, + struct trace_array *size_tr, int cpu_id) +{ + int cpu, ret = 0; + + if (cpu_id == RING_BUFFER_ALL_CPUS) { + for_each_tracing_cpu(cpu) { + ret = ring_buffer_resize(tr->buffer, + size_tr->data[cpu]->entries, cpu); + if (ret < 0) + break; + tr->data[cpu]->entries = size_tr->data[cpu]->entries; + } + } else { + ret = ring_buffer_resize(tr->buffer, + size_tr->data[cpu_id]->entries, cpu_id); + if (ret == 0) + tr->data[cpu_id]->entries = + size_tr->data[cpu_id]->entries; + } + + return ret; +} + static int __tracing_resize_ring_buffer(unsigned long size, int cpu) { int ret; @@ -3058,23 +3083,8 @@ static int __tracing_resize_ring_buffer(unsigned long size, int cpu) ret = ring_buffer_resize(max_tr.buffer, size, cpu); if (ret < 0) { - int r = 0; - - if (cpu == RING_BUFFER_ALL_CPUS) { - int i; - for_each_tracing_cpu(i) { - r = ring_buffer_resize(global_trace.buffer, - global_trace.data[i]->entries, - i); - if (r < 0) - break; - } - } else { - r = ring_buffer_resize(global_trace.buffer, - global_trace.data[cpu]->entries, - cpu); - } - + int r = resize_buffer_duplicate_size(&global_trace, + &global_trace, cpu); if (r < 0) { /* * AARGH! We are left with different @@ -3212,17 +3222,11 @@ static int tracing_set_tracer(const char *buf) topts = create_trace_option_files(t); if (t->use_max_tr) { - int cpu; /* we need to make per cpu buffer sizes equivalent */ - for_each_tracing_cpu(cpu) { - ret = ring_buffer_resize(max_tr.buffer, - global_trace.data[cpu]->entries, - cpu); - if (ret < 0) - goto out; - max_tr.data[cpu]->entries = - global_trace.data[cpu]->entries; - } + ret = resize_buffer_duplicate_size(&max_tr, &global_trace, + RING_BUFFER_ALL_CPUS); + if (ret < 0) + goto out; } if (t->init) { @@ -4271,13 +4275,11 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, return -ENOMEM; if (*ppos & (PAGE_SIZE - 1)) { - WARN_ONCE(1, "Ftrace: previous read must page-align\n"); ret = -EINVAL; goto out; } if (len & (PAGE_SIZE - 1)) { - WARN_ONCE(1, "Ftrace: splice_read should page-align\n"); if (len < PAGE_SIZE) { ret = -EINVAL; goto out; diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 0c1b165778e..42ca822fc70 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -33,7 +33,6 @@ static unsigned long max_stack_size; static arch_spinlock_t max_stack_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; -static int stack_trace_disabled __read_mostly; static DEFINE_PER_CPU(int, trace_active); static DEFINE_MUTEX(stack_sysctl_mutex); @@ -116,9 +115,6 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip, { int cpu; - if (unlikely(!ftrace_enabled || stack_trace_disabled)) - return; - preempt_disable_notrace(); cpu = raw_smp_processor_id(); diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 9614db8b0f8..c86e6d4f67f 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -22,6 +22,7 @@ #include <linux/uaccess.h> #include <linux/uprobes.h> #include <linux/namei.h> +#include <linux/string.h> #include "trace_probe.h" @@ -263,16 +264,15 @@ static int create_trace_uprobe(int argc, char **argv) /* setup a probe */ if (!event) { - char *tail = strrchr(filename, '/'); + char *tail; char *ptr; - ptr = kstrdup((tail ? tail + 1 : filename), GFP_KERNEL); - if (!ptr) { + tail = kstrdup(kbasename(filename), GFP_KERNEL); + if (!tail) { ret = -ENOMEM; goto fail_address_parse; } - tail = ptr; ptr = strpbrk(tail, ".-_"); if (ptr) *ptr = '\0'; diff --git a/kernel/user.c b/kernel/user.c index 750acffbe9e..33acb5e53a5 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -16,6 +16,7 @@ #include <linux/interrupt.h> #include <linux/export.h> #include <linux/user_namespace.h> +#include <linux/proc_fs.h> /* * userns count is 1 for root user, 1 for init_uts_ns, @@ -51,6 +52,7 @@ struct user_namespace init_user_ns = { }, .owner = GLOBAL_ROOT_UID, .group = GLOBAL_ROOT_GID, + .proc_inum = PROC_USER_INIT_INO, }; EXPORT_SYMBOL_GPL(init_user_ns); diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 456a6b9fba3..2b042c42fbc 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -9,6 +9,7 @@ #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/user_namespace.h> +#include <linux/proc_fs.h> #include <linux/highuid.h> #include <linux/cred.h> #include <linux/securebits.h> @@ -26,6 +27,24 @@ static struct kmem_cache *user_ns_cachep __read_mostly; static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid, struct uid_gid_map *map); +static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns) +{ + /* Start with the same capabilities as init but useless for doing + * anything as the capabilities are bound to the new user namespace. + */ + cred->securebits = SECUREBITS_DEFAULT; + cred->cap_inheritable = CAP_EMPTY_SET; + cred->cap_permitted = CAP_FULL_SET; + cred->cap_effective = CAP_FULL_SET; + cred->cap_bset = CAP_FULL_SET; +#ifdef CONFIG_KEYS + key_put(cred->request_key_auth); + cred->request_key_auth = NULL; +#endif + /* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */ + cred->user_ns = user_ns; +} + /* * Create a new user namespace, deriving the creator from the user in the * passed credentials, and replacing that user with the new root user for the @@ -39,6 +58,7 @@ int create_user_ns(struct cred *new) struct user_namespace *ns, *parent_ns = new->user_ns; kuid_t owner = new->euid; kgid_t group = new->egid; + int ret; /* The creator needs a mapping in the parent user namespace * or else we won't be able to reasonably tell userspace who @@ -52,38 +72,45 @@ int create_user_ns(struct cred *new) if (!ns) return -ENOMEM; + ret = proc_alloc_inum(&ns->proc_inum); + if (ret) { + kmem_cache_free(user_ns_cachep, ns); + return ret; + } + kref_init(&ns->kref); + /* Leave the new->user_ns reference with the new user namespace. */ ns->parent = parent_ns; ns->owner = owner; ns->group = group; - /* Start with the same capabilities as init but useless for doing - * anything as the capabilities are bound to the new user namespace. - */ - new->securebits = SECUREBITS_DEFAULT; - new->cap_inheritable = CAP_EMPTY_SET; - new->cap_permitted = CAP_FULL_SET; - new->cap_effective = CAP_FULL_SET; - new->cap_bset = CAP_FULL_SET; -#ifdef CONFIG_KEYS - key_put(new->request_key_auth); - new->request_key_auth = NULL; -#endif - /* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */ - - /* Leave the new->user_ns reference with the new user namespace. */ - /* Leave the reference to our user_ns with the new cred. */ - new->user_ns = ns; + set_cred_user_ns(new, ns); return 0; } +int unshare_userns(unsigned long unshare_flags, struct cred **new_cred) +{ + struct cred *cred; + + if (!(unshare_flags & CLONE_NEWUSER)) + return 0; + + cred = prepare_creds(); + if (!cred) + return -ENOMEM; + + *new_cred = cred; + return create_user_ns(cred); +} + void free_user_ns(struct kref *kref) { struct user_namespace *parent, *ns = container_of(kref, struct user_namespace, kref); parent = ns->parent; + proc_free_inum(ns->proc_inum); kmem_cache_free(user_ns_cachep, ns); put_user_ns(parent); } @@ -372,7 +399,7 @@ static int uid_m_show(struct seq_file *seq, void *v) struct user_namespace *lower_ns; uid_t lower; - lower_ns = current_user_ns(); + lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; @@ -393,7 +420,7 @@ static int gid_m_show(struct seq_file *seq, void *v) struct user_namespace *lower_ns; gid_t lower; - lower_ns = current_user_ns(); + lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; @@ -669,10 +696,14 @@ ssize_t proc_uid_map_write(struct file *file, const char __user *buf, size_t siz { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; + struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; + if ((seq_ns != ns) && (seq_ns != ns->parent)) + return -EPERM; + return map_write(file, buf, size, ppos, CAP_SETUID, &ns->uid_map, &ns->parent->uid_map); } @@ -681,10 +712,14 @@ ssize_t proc_gid_map_write(struct file *file, const char __user *buf, size_t siz { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; + struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; + if ((seq_ns != ns) && (seq_ns != ns->parent)) + return -EPERM; + return map_write(file, buf, size, ppos, CAP_SETGID, &ns->gid_map, &ns->parent->gid_map); } @@ -709,6 +744,21 @@ ssize_t proc_projid_map_write(struct file *file, const char __user *buf, size_t static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid, struct uid_gid_map *new_map) { + /* Allow mapping to your own filesystem ids */ + if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1)) { + u32 id = new_map->extent[0].lower_first; + if (cap_setid == CAP_SETUID) { + kuid_t uid = make_kuid(ns->parent, id); + if (uid_eq(uid, current_fsuid())) + return true; + } + else if (cap_setid == CAP_SETGID) { + kgid_t gid = make_kgid(ns->parent, id); + if (gid_eq(gid, current_fsgid())) + return true; + } + } + /* Allow anyone to set a mapping that doesn't require privilege */ if (!cap_valid(cap_setid)) return true; @@ -722,6 +772,65 @@ static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid, return false; } +static void *userns_get(struct task_struct *task) +{ + struct user_namespace *user_ns; + + rcu_read_lock(); + user_ns = get_user_ns(__task_cred(task)->user_ns); + rcu_read_unlock(); + + return user_ns; +} + +static void userns_put(void *ns) +{ + put_user_ns(ns); +} + +static int userns_install(struct nsproxy *nsproxy, void *ns) +{ + struct user_namespace *user_ns = ns; + struct cred *cred; + + /* Don't allow gaining capabilities by reentering + * the same user namespace. + */ + if (user_ns == current_user_ns()) + return -EINVAL; + + /* Threaded processes may not enter a different user namespace */ + if (atomic_read(¤t->mm->mm_users) > 1) + return -EINVAL; + + if (!ns_capable(user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + cred = prepare_creds(); + if (!cred) + return -ENOMEM; + + put_user_ns(cred->user_ns); + set_cred_user_ns(cred, get_user_ns(user_ns)); + + return commit_creds(cred); +} + +static unsigned int userns_inum(void *ns) +{ + struct user_namespace *user_ns = ns; + return user_ns->proc_inum; +} + +const struct proc_ns_operations userns_operations = { + .name = "user", + .type = CLONE_NEWUSER, + .get = userns_get, + .put = userns_put, + .install = userns_install, + .inum = userns_inum, +}; + static __init int user_namespaces_init(void) { user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC); diff --git a/kernel/utsname.c b/kernel/utsname.c index 679d97a5d3f..08b197e8c48 100644 --- a/kernel/utsname.c +++ b/kernel/utsname.c @@ -32,18 +32,25 @@ static struct uts_namespace *create_uts_ns(void) * @old_ns: namespace to clone * Return NULL on error (failure to kmalloc), new ns otherwise */ -static struct uts_namespace *clone_uts_ns(struct task_struct *tsk, +static struct uts_namespace *clone_uts_ns(struct user_namespace *user_ns, struct uts_namespace *old_ns) { struct uts_namespace *ns; + int err; ns = create_uts_ns(); if (!ns) return ERR_PTR(-ENOMEM); + err = proc_alloc_inum(&ns->proc_inum); + if (err) { + kfree(ns); + return ERR_PTR(err); + } + down_read(&uts_sem); memcpy(&ns->name, &old_ns->name, sizeof(ns->name)); - ns->user_ns = get_user_ns(task_cred_xxx(tsk, user_ns)); + ns->user_ns = get_user_ns(user_ns); up_read(&uts_sem); return ns; } @@ -55,9 +62,8 @@ static struct uts_namespace *clone_uts_ns(struct task_struct *tsk, * versa. */ struct uts_namespace *copy_utsname(unsigned long flags, - struct task_struct *tsk) + struct user_namespace *user_ns, struct uts_namespace *old_ns) { - struct uts_namespace *old_ns = tsk->nsproxy->uts_ns; struct uts_namespace *new_ns; BUG_ON(!old_ns); @@ -66,7 +72,7 @@ struct uts_namespace *copy_utsname(unsigned long flags, if (!(flags & CLONE_NEWUTS)) return old_ns; - new_ns = clone_uts_ns(tsk, old_ns); + new_ns = clone_uts_ns(user_ns, old_ns); put_uts_ns(old_ns); return new_ns; @@ -78,6 +84,7 @@ void free_uts_ns(struct kref *kref) ns = container_of(kref, struct uts_namespace, kref); put_user_ns(ns->user_ns); + proc_free_inum(ns->proc_inum); kfree(ns); } @@ -102,19 +109,32 @@ static void utsns_put(void *ns) put_uts_ns(ns); } -static int utsns_install(struct nsproxy *nsproxy, void *ns) +static int utsns_install(struct nsproxy *nsproxy, void *new) { + struct uts_namespace *ns = new; + + if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) || + !nsown_capable(CAP_SYS_ADMIN)) + return -EPERM; + get_uts_ns(ns); put_uts_ns(nsproxy->uts_ns); nsproxy->uts_ns = ns; return 0; } +static unsigned int utsns_inum(void *vp) +{ + struct uts_namespace *ns = vp; + + return ns->proc_inum; +} + const struct proc_ns_operations utsns_operations = { .name = "uts", .type = CLONE_NEWUTS, .get = utsns_get, .put = utsns_put, .install = utsns_install, + .inum = utsns_inum, }; - diff --git a/kernel/watchdog.c b/kernel/watchdog.c index c8c21be11ab..75a2ab3d0b0 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -31,6 +31,7 @@ int watchdog_enabled = 1; int __read_mostly watchdog_thresh = 10; static int __read_mostly watchdog_disabled; +static u64 __read_mostly sample_period; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog); @@ -116,7 +117,7 @@ static unsigned long get_timestamp(int this_cpu) return cpu_clock(this_cpu) >> 30LL; /* 2^30 ~= 10^9 */ } -static u64 get_sample_period(void) +static void set_sample_period(void) { /* * convert watchdog_thresh from seconds to ns @@ -125,7 +126,7 @@ static u64 get_sample_period(void) * and hard thresholds) to increment before the * hardlockup detector generates a warning */ - return get_softlockup_thresh() * ((u64)NSEC_PER_SEC / 5); + sample_period = get_softlockup_thresh() * ((u64)NSEC_PER_SEC / 5); } /* Commands for resetting the watchdog */ @@ -275,7 +276,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) wake_up_process(__this_cpu_read(softlockup_watchdog)); /* .. and repeat */ - hrtimer_forward_now(hrtimer, ns_to_ktime(get_sample_period())); + hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); if (touch_ts == 0) { if (unlikely(__this_cpu_read(softlockup_touch_sync))) { @@ -343,6 +344,10 @@ static void watchdog_enable(unsigned int cpu) { struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer); + /* kick off the timer for the hardlockup detector */ + hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer->function = watchdog_timer_fn; + if (!watchdog_enabled) { kthread_park(current); return; @@ -351,12 +356,8 @@ static void watchdog_enable(unsigned int cpu) /* Enable the perf event */ watchdog_nmi_enable(cpu); - /* kick off the timer for the hardlockup detector */ - hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - hrtimer->function = watchdog_timer_fn; - /* done here because hrtimer_start can only pin to smp_processor_id() */ - hrtimer_start(hrtimer, ns_to_ktime(get_sample_period()), + hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL_PINNED); /* initialize timestamp */ @@ -368,9 +369,6 @@ static void watchdog_disable(unsigned int cpu) { struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer); - if (!watchdog_enabled) - return; - watchdog_set_prio(SCHED_NORMAL, 0); hrtimer_cancel(hrtimer); /* disable the perf event */ @@ -386,7 +384,7 @@ static int watchdog_should_run(unsigned int cpu) /* * The watchdog thread function - touches the timestamp. * - * It only runs once every get_sample_period() seconds (4 seconds by + * It only runs once every sample_period seconds (4 seconds by * default) to reset the softlockup timestamp. If this gets delayed * for more than 2*watchdog_thresh seconds then the debug-printout * triggers in watchdog_timer_fn(). @@ -519,6 +517,7 @@ int proc_dowatchdog(struct ctl_table *table, int write, if (ret || !write) return ret; + set_sample_period(); if (watchdog_enabled && watchdog_thresh) watchdog_enable_all_cpus(); else @@ -540,6 +539,7 @@ static struct smp_hotplug_thread watchdog_threads = { void __init lockup_detector_init(void) { + set_sample_period(); if (smpboot_register_percpu_thread(&watchdog_threads)) { pr_err("Failed to create watchdog threads, disabled\n"); watchdog_disabled = -ENODEV; |