diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/compat.c | 1 | ||||
-rw-r--r-- | kernel/fork.c | 394 | ||||
-rw-r--r-- | kernel/module.c | 3 | ||||
-rw-r--r-- | kernel/power/console.c | 4 | ||||
-rw-r--r-- | kernel/power/power.h | 16 | ||||
-rw-r--r-- | kernel/power/swsusp.c | 6 | ||||
-rw-r--r-- | kernel/signal.c | 9 | ||||
-rw-r--r-- | kernel/sys.c | 2 | ||||
-rw-r--r-- | kernel/timer.c | 2 |
9 files changed, 354 insertions, 83 deletions
diff --git a/kernel/compat.c b/kernel/compat.c index 1867290c37e..8c9cd88b678 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -23,7 +23,6 @@ #include <linux/security.h> #include <asm/uaccess.h> -#include <asm/bug.h> int get_compat_timespec(struct timespec *ts, const struct compat_timespec __user *cts) { diff --git a/kernel/fork.c b/kernel/fork.c index 7f0ab5ee948..8e88b374cee 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -446,6 +446,55 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm) } } +/* + * Allocate a new mm structure and copy contents from the + * mm structure of the passed in task structure. + */ +static struct mm_struct *dup_mm(struct task_struct *tsk) +{ + struct mm_struct *mm, *oldmm = current->mm; + int err; + + if (!oldmm) + return NULL; + + mm = allocate_mm(); + if (!mm) + goto fail_nomem; + + memcpy(mm, oldmm, sizeof(*mm)); + + if (!mm_init(mm)) + goto fail_nomem; + + if (init_new_context(tsk, mm)) + goto fail_nocontext; + + err = dup_mmap(mm, oldmm); + if (err) + goto free_pt; + + mm->hiwater_rss = get_mm_rss(mm); + mm->hiwater_vm = mm->total_vm; + + return mm; + +free_pt: + mmput(mm); + +fail_nomem: + return NULL; + +fail_nocontext: + /* + * If init_new_context() failed, we cannot use mmput() to free the mm + * because it calls destroy_context() + */ + mm_free_pgd(mm); + free_mm(mm); + return NULL; +} + static int copy_mm(unsigned long clone_flags, struct task_struct * tsk) { struct mm_struct * mm, *oldmm; @@ -473,43 +522,17 @@ static int copy_mm(unsigned long clone_flags, struct task_struct * tsk) } retval = -ENOMEM; - mm = allocate_mm(); + mm = dup_mm(tsk); if (!mm) goto fail_nomem; - /* Copy the current MM stuff.. */ - memcpy(mm, oldmm, sizeof(*mm)); - if (!mm_init(mm)) - goto fail_nomem; - - if (init_new_context(tsk,mm)) - goto fail_nocontext; - - retval = dup_mmap(mm, oldmm); - if (retval) - goto free_pt; - - mm->hiwater_rss = get_mm_rss(mm); - mm->hiwater_vm = mm->total_vm; - good_mm: tsk->mm = mm; tsk->active_mm = mm; return 0; -free_pt: - mmput(mm); fail_nomem: return retval; - -fail_nocontext: - /* - * If init_new_context() failed, we cannot use mmput() to free the mm - * because it calls destroy_context() - */ - mm_free_pgd(mm); - free_mm(mm); - return retval; } static inline struct fs_struct *__copy_fs_struct(struct fs_struct *old) @@ -597,32 +620,17 @@ out: return newf; } -static int copy_files(unsigned long clone_flags, struct task_struct * tsk) +/* + * Allocate a new files structure and copy contents from the + * passed in files structure. + */ +static struct files_struct *dup_fd(struct files_struct *oldf, int *errorp) { - struct files_struct *oldf, *newf; + struct files_struct *newf; struct file **old_fds, **new_fds; - int open_files, size, i, error = 0, expand; + int open_files, size, i, expand; struct fdtable *old_fdt, *new_fdt; - /* - * A background process may not have any files ... - */ - oldf = current->files; - if (!oldf) - goto out; - - if (clone_flags & CLONE_FILES) { - atomic_inc(&oldf->count); - goto out; - } - - /* - * Note: we may be using current for both targets (See exec.c) - * This works because we cache current->files (old) as oldf. Don't - * break this. - */ - tsk->files = NULL; - error = -ENOMEM; newf = alloc_files(); if (!newf) goto out; @@ -651,9 +659,9 @@ static int copy_files(unsigned long clone_flags, struct task_struct * tsk) if (expand) { spin_unlock(&oldf->file_lock); spin_lock(&newf->file_lock); - error = expand_files(newf, open_files-1); + *errorp = expand_files(newf, open_files-1); spin_unlock(&newf->file_lock); - if (error < 0) + if (*errorp < 0) goto out_release; new_fdt = files_fdtable(newf); /* @@ -702,10 +710,8 @@ static int copy_files(unsigned long clone_flags, struct task_struct * tsk) memset(&new_fdt->close_on_exec->fds_bits[start], 0, left); } - tsk->files = newf; - error = 0; out: - return error; + return newf; out_release: free_fdset (new_fdt->close_on_exec, new_fdt->max_fdset); @@ -715,6 +721,40 @@ out_release: goto out; } +static int copy_files(unsigned long clone_flags, struct task_struct * tsk) +{ + struct files_struct *oldf, *newf; + int error = 0; + + /* + * A background process may not have any files ... + */ + oldf = current->files; + if (!oldf) + goto out; + + if (clone_flags & CLONE_FILES) { + atomic_inc(&oldf->count); + goto out; + } + + /* + * Note: we may be using current for both targets (See exec.c) + * This works because we cache current->files (old) as oldf. Don't + * break this. + */ + tsk->files = NULL; + error = -ENOMEM; + newf = dup_fd(oldf, &error); + if (!newf) + goto out; + + tsk->files = newf; + error = 0; +out: + return error; +} + /* * Helper to unshare the files of the current task. * We don't want to expose copy_files internals to @@ -1323,3 +1363,249 @@ void __init proc_caches_init(void) sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); } + + +/* + * Check constraints on flags passed to the unshare system call and + * force unsharing of additional process context as appropriate. + */ +static inline void check_unshare_flags(unsigned long *flags_ptr) +{ + /* + * If unsharing a thread from a thread group, must also + * unshare vm. + */ + if (*flags_ptr & CLONE_THREAD) + *flags_ptr |= CLONE_VM; + + /* + * If unsharing vm, must also unshare signal handlers. + */ + if (*flags_ptr & CLONE_VM) + *flags_ptr |= CLONE_SIGHAND; + + /* + * If unsharing signal handlers and the task was created + * using CLONE_THREAD, then must unshare the thread + */ + if ((*flags_ptr & CLONE_SIGHAND) && + (atomic_read(¤t->signal->count) > 1)) + *flags_ptr |= CLONE_THREAD; + + /* + * If unsharing namespace, must also unshare filesystem information. + */ + if (*flags_ptr & CLONE_NEWNS) + *flags_ptr |= CLONE_FS; +} + +/* + * Unsharing of tasks created with CLONE_THREAD is not supported yet + */ +static int unshare_thread(unsigned long unshare_flags) +{ + if (unshare_flags & CLONE_THREAD) + return -EINVAL; + + return 0; +} + +/* + * Unshare the filesystem structure if it is being shared + */ +static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) +{ + struct fs_struct *fs = current->fs; + + if ((unshare_flags & CLONE_FS) && + (fs && atomic_read(&fs->count) > 1)) { + *new_fsp = __copy_fs_struct(current->fs); + if (!*new_fsp) + return -ENOMEM; + } + + return 0; +} + +/* + * Unshare the namespace structure if it is being shared + */ +static int unshare_namespace(unsigned long unshare_flags, struct namespace **new_nsp, struct fs_struct *new_fs) +{ + struct namespace *ns = current->namespace; + + if ((unshare_flags & CLONE_NEWNS) && + (ns && atomic_read(&ns->count) > 1)) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + *new_nsp = dup_namespace(current, new_fs ? new_fs : current->fs); + if (!*new_nsp) + return -ENOMEM; + } + + return 0; +} + +/* + * Unsharing of sighand for tasks created with CLONE_SIGHAND is not + * supported yet + */ +static int unshare_sighand(unsigned long unshare_flags, struct sighand_struct **new_sighp) +{ + struct sighand_struct *sigh = current->sighand; + + if ((unshare_flags & CLONE_SIGHAND) && + (sigh && atomic_read(&sigh->count) > 1)) + return -EINVAL; + else + return 0; +} + +/* + * Unshare vm if it is being shared + */ +static int unshare_vm(unsigned long unshare_flags, struct mm_struct **new_mmp) +{ + struct mm_struct *mm = current->mm; + + if ((unshare_flags & CLONE_VM) && + (mm && atomic_read(&mm->mm_users) > 1)) { + *new_mmp = dup_mm(current); + if (!*new_mmp) + return -ENOMEM; + } + + return 0; +} + +/* + * Unshare file descriptor table if it is being shared + */ +static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp) +{ + struct files_struct *fd = current->files; + int error = 0; + + if ((unshare_flags & CLONE_FILES) && + (fd && atomic_read(&fd->count) > 1)) { + *new_fdp = dup_fd(fd, &error); + if (!*new_fdp) + return error; + } + + return 0; +} + +/* + * Unsharing of semundo for tasks created with CLONE_SYSVSEM is not + * supported yet + */ +static int unshare_semundo(unsigned long unshare_flags, struct sem_undo_list **new_ulistp) +{ + if (unshare_flags & CLONE_SYSVSEM) + return -EINVAL; + + return 0; +} + +/* + * unshare allows a process to 'unshare' part of the process + * context which was originally shared using clone. copy_* + * functions used by do_fork() cannot be used here directly + * because they modify an inactive task_struct that is being + * constructed. Here we are modifying the current, active, + * task_struct. + */ +asmlinkage long sys_unshare(unsigned long unshare_flags) +{ + int err = 0; + struct fs_struct *fs, *new_fs = NULL; + struct namespace *ns, *new_ns = NULL; + struct sighand_struct *sigh, *new_sigh = NULL; + struct mm_struct *mm, *new_mm = NULL, *active_mm = NULL; + struct files_struct *fd, *new_fd = NULL; + struct sem_undo_list *new_ulist = NULL; + + check_unshare_flags(&unshare_flags); + + if ((err = unshare_thread(unshare_flags))) + goto bad_unshare_out; + if ((err = unshare_fs(unshare_flags, &new_fs))) + goto bad_unshare_cleanup_thread; + if ((err = unshare_namespace(unshare_flags, &new_ns, new_fs))) + goto bad_unshare_cleanup_fs; + if ((err = unshare_sighand(unshare_flags, &new_sigh))) + goto bad_unshare_cleanup_ns; + if ((err = unshare_vm(unshare_flags, &new_mm))) + goto bad_unshare_cleanup_sigh; + if ((err = unshare_fd(unshare_flags, &new_fd))) + goto bad_unshare_cleanup_vm; + if ((err = unshare_semundo(unshare_flags, &new_ulist))) + goto bad_unshare_cleanup_fd; + + if (new_fs || new_ns || new_sigh || new_mm || new_fd || new_ulist) { + + task_lock(current); + + if (new_fs) { + fs = current->fs; + current->fs = new_fs; + new_fs = fs; + } + + if (new_ns) { + ns = current->namespace; + current->namespace = new_ns; + new_ns = ns; + } + + if (new_sigh) { + sigh = current->sighand; + current->sighand = new_sigh; + new_sigh = sigh; + } + + if (new_mm) { + mm = current->mm; + active_mm = current->active_mm; + current->mm = new_mm; + current->active_mm = new_mm; + activate_mm(active_mm, new_mm); + new_mm = mm; + } + + if (new_fd) { + fd = current->files; + current->files = new_fd; + new_fd = fd; + } + + task_unlock(current); + } + +bad_unshare_cleanup_fd: + if (new_fd) + put_files_struct(new_fd); + +bad_unshare_cleanup_vm: + if (new_mm) + mmput(new_mm); + +bad_unshare_cleanup_sigh: + if (new_sigh) + if (atomic_dec_and_test(&new_sigh->count)) + kmem_cache_free(sighand_cachep, new_sigh); + +bad_unshare_cleanup_ns: + if (new_ns) + put_namespace(new_ns); + +bad_unshare_cleanup_fs: + if (new_fs) + put_fs_struct(new_fs); + +bad_unshare_cleanup_thread: +bad_unshare_out: + return err; +} diff --git a/kernel/module.c b/kernel/module.c index e058aedf6b9..5aad477ddc7 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1670,6 +1670,9 @@ static struct module *load_module(void __user *umod, goto free_mod; } + /* Userspace could have altered the string after the strlen_user() */ + args[arglen - 1] = '\0'; + if (find_module(mod->name)) { err = -EEXIST; goto free_mod; diff --git a/kernel/power/console.c b/kernel/power/console.c index 579d239d129..623786d4415 100644 --- a/kernel/power/console.c +++ b/kernel/power/console.c @@ -9,7 +9,9 @@ #include <linux/console.h> #include "power.h" -#ifdef SUSPEND_CONSOLE +#if defined(CONFIG_VT) && defined(CONFIG_VT_CONSOLE) +#define SUSPEND_CONSOLE (MAX_NR_CONSOLES-1) + static int orig_fgconsole, orig_kmsg; int pm_prepare_console(void) diff --git a/kernel/power/power.h b/kernel/power/power.h index d8f0d1a76ba..388dba68084 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -1,14 +1,6 @@ #include <linux/suspend.h> #include <linux/utsname.h> -/* With SUSPEND_CONSOLE defined suspend looks *really* cool, but - we probably do not take enough locks for switching consoles, etc, - so bad things might happen. -*/ -#if defined(CONFIG_VT) && defined(CONFIG_VT_CONSOLE) -#define SUSPEND_CONSOLE (MAX_NR_CONSOLES-1) -#endif - struct swsusp_info { struct new_utsname uts; u32 version_code; @@ -42,14 +34,6 @@ static struct subsys_attribute _name##_attr = { \ extern struct subsystem power_subsys; -#ifdef SUSPEND_CONSOLE -extern int pm_prepare_console(void); -extern void pm_restore_console(void); -#else -static int pm_prepare_console(void) { return 0; } -static void pm_restore_console(void) {} -#endif - /* References to section boundaries */ extern const void __nosave_begin, __nosave_end; diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c index 59c91c148e8..4e90905f0e8 100644 --- a/kernel/power/swsusp.c +++ b/kernel/power/swsusp.c @@ -743,7 +743,6 @@ static int submit(int rw, pgoff_t page_off, void *page) if (!bio) return -ENOMEM; bio->bi_sector = page_off * (PAGE_SIZE >> 9); - bio_get(bio); bio->bi_bdev = resume_bdev; bio->bi_end_io = end_io; @@ -753,14 +752,13 @@ static int submit(int rw, pgoff_t page_off, void *page) goto Done; } - if (rw == WRITE) - bio_set_pages_dirty(bio); atomic_set(&io_done, 1); submit_bio(rw | (1 << BIO_RW_SYNC), bio); while (atomic_read(&io_done)) yield(); - + if (rw == READ) + bio_set_pages_dirty(bio); Done: bio_put(bio); return error; diff --git a/kernel/signal.c b/kernel/signal.c index b373fc2420d..ea154104a00 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2430,7 +2430,7 @@ sys_rt_sigqueueinfo(int pid, int sig, siginfo_t __user *uinfo) } int -do_sigaction(int sig, const struct k_sigaction *act, struct k_sigaction *oact) +do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact) { struct k_sigaction *k; sigset_t mask; @@ -2454,6 +2454,8 @@ do_sigaction(int sig, const struct k_sigaction *act, struct k_sigaction *oact) *oact = *k; if (act) { + sigdelsetmask(&act->sa.sa_mask, + sigmask(SIGKILL) | sigmask(SIGSTOP)); /* * POSIX 3.3.1.3: * "Setting a signal action to SIG_IGN for a signal that is @@ -2479,8 +2481,6 @@ do_sigaction(int sig, const struct k_sigaction *act, struct k_sigaction *oact) read_lock(&tasklist_lock); spin_lock_irq(&t->sighand->siglock); *k = *act; - sigdelsetmask(&k->sa.sa_mask, - sigmask(SIGKILL) | sigmask(SIGSTOP)); sigemptyset(&mask); sigaddset(&mask, sig); rm_from_queue_full(&mask, &t->signal->shared_pending); @@ -2495,8 +2495,6 @@ do_sigaction(int sig, const struct k_sigaction *act, struct k_sigaction *oact) } *k = *act; - sigdelsetmask(&k->sa.sa_mask, - sigmask(SIGKILL) | sigmask(SIGSTOP)); } spin_unlock_irq(¤t->sighand->siglock); @@ -2702,6 +2700,7 @@ sys_signal(int sig, __sighandler_t handler) new_sa.sa.sa_handler = handler; new_sa.sa.sa_flags = SA_ONESHOT | SA_NOMASK; + sigemptyset(&new_sa.sa.sa_mask); ret = do_sigaction(sig, &new_sa, &old_sa); diff --git a/kernel/sys.c b/kernel/sys.c index 0929c698aff..f91218a5463 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -428,7 +428,7 @@ void kernel_kexec(void) { #ifdef CONFIG_KEXEC struct kimage *image; - image = xchg(&kexec_image, 0); + image = xchg(&kexec_image, NULL); if (!image) { return; } diff --git a/kernel/timer.c b/kernel/timer.c index 4f1cb0ab525..b9dad399467 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -495,7 +495,7 @@ unsigned long next_timer_interrupt(void) base = &__get_cpu_var(tvec_bases); spin_lock(&base->t_base.lock); expires = base->timer_jiffies + (LONG_MAX >> 1); - list = 0; + list = NULL; /* Look for timer events in tv1. */ j = base->timer_jiffies & TVR_MASK; |