#include <linux/mm.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
-#include <linux/smp_lock.h>
#include <linux/swap.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/pagemap.h>
+#include <linux/perf_event.h>
#include <linux/highmem.h>
#include <linux/spinlock.h>
#include <linux/key.h>
#include <linux/audit.h>
#include <linux/tracehook.h>
#include <linux/kmod.h>
+#include <linux/fsnotify.h>
+#include <linux/fs_struct.h>
+#include <linux/pipe_fs_i.h>
#include <asm/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/tlb.h>
#include "internal.h"
-#ifdef __alpha__
-/* for /sbin/loader handling in search_binary_handler() */
-#include <linux/a.out.h>
-#endif
-
int core_uses_pid;
char core_pattern[CORENAME_MAX_SIZE] = "core";
+unsigned int core_pipe_limit;
int suid_dumpable = 0;
/* The maximal length of core_pattern is also specified in sysctl.c */
static LIST_HEAD(formats);
static DEFINE_RWLOCK(binfmt_lock);
-int register_binfmt(struct linux_binfmt * fmt)
+int __register_binfmt(struct linux_binfmt * fmt, int insert)
{
if (!fmt)
return -EINVAL;
write_lock(&binfmt_lock);
- list_add(&fmt->lh, &formats);
+ insert ? list_add(&fmt->lh, &formats) :
+ list_add_tail(&fmt->lh, &formats);
write_unlock(&binfmt_lock);
return 0;
}
-EXPORT_SYMBOL(register_binfmt);
+EXPORT_SYMBOL(__register_binfmt);
void unregister_binfmt(struct linux_binfmt * fmt)
{
*
* Also note that we take the address to load from from the file itself.
*/
-asmlinkage long sys_uselib(const char __user * library)
+SYSCALL_DEFINE1(uselib, const char __user *, library)
{
struct file *file;
- struct nameidata nd;
char *tmp = getname(library);
int error = PTR_ERR(tmp);
- if (!IS_ERR(tmp)) {
- error = path_lookup_open(AT_FDCWD, tmp,
- LOOKUP_FOLLOW, &nd,
- FMODE_READ|FMODE_EXEC);
- putname(tmp);
- }
- if (error)
+ if (IS_ERR(tmp))
+ goto out;
+
+ file = do_filp_open(AT_FDCWD, tmp,
+ O_LARGEFILE | O_RDONLY | FMODE_EXEC, 0,
+ MAY_READ | MAY_EXEC | MAY_OPEN);
+ putname(tmp);
+ error = PTR_ERR(file);
+ if (IS_ERR(file))
goto out;
error = -EINVAL;
- if (!S_ISREG(nd.path.dentry->d_inode->i_mode))
+ if (!S_ISREG(file->f_path.dentry->d_inode->i_mode))
goto exit;
error = -EACCES;
- if (nd.path.mnt->mnt_flags & MNT_NOEXEC)
+ if (file->f_path.mnt->mnt_flags & MNT_NOEXEC)
goto exit;
- error = inode_permission(nd.path.dentry->d_inode,
- MAY_READ | MAY_EXEC | MAY_OPEN);
- if (error)
- goto exit;
-
- file = nameidata_to_filp(&nd, O_RDONLY|O_LARGEFILE);
- error = PTR_ERR(file);
- if (IS_ERR(file))
- goto out;
+ fsnotify_open(file);
error = -ENOEXEC;
if(file->f_op) {
}
read_unlock(&binfmt_lock);
}
+exit:
fput(file);
out:
return error;
-exit:
- release_open_intent(&nd);
- path_put(&nd.path);
- goto out;
}
#ifdef CONFIG_MMU
* to work from.
*/
rlim = current->signal->rlim;
- if (size > rlim[RLIMIT_STACK].rlim_cur / 4) {
+ if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4) {
put_page(page);
return NULL;
}
static int __bprm_mm_init(struct linux_binprm *bprm)
{
- int err = -ENOMEM;
+ int err;
struct vm_area_struct *vma = NULL;
struct mm_struct *mm = bprm->mm;
bprm->vma = vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
if (!vma)
- goto err;
+ return -ENOMEM;
down_write(&mm->mmap_sem);
vma->vm_mm = mm;
* use STACK_TOP because that can depend on attributes which aren't
* configured yet.
*/
+ BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP);
vma->vm_end = STACK_TOP_MAX;
vma->vm_start = vma->vm_end - PAGE_SIZE;
-
- vma->vm_flags = VM_STACK_FLAGS;
+ vma->vm_flags = VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP;
vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+ INIT_LIST_HEAD(&vma->anon_vma_chain);
err = insert_vm_struct(mm, vma);
- if (err) {
- up_write(&mm->mmap_sem);
+ if (err)
goto err;
- }
mm->stack_vm = mm->total_vm = 1;
up_write(&mm->mmap_sem);
-
bprm->p = vma->vm_end - sizeof(void *);
-
return 0;
-
err:
- if (vma) {
- bprm->vma = NULL;
- kmem_cache_free(vm_area_cachep, vma);
- }
-
+ up_write(&mm->mmap_sem);
+ bprm->vma = NULL;
+ kmem_cache_free(vm_area_cachep, vma);
return err;
}
/*
* cover the whole range: [new_start, old_end)
*/
- vma_adjust(vma, new_start, old_end, vma->vm_pgoff, NULL);
+ if (vma_adjust(vma, new_start, old_end, vma->vm_pgoff, NULL))
+ return -ENOMEM;
/*
* move the page tables downwards, on failure we rely on
tlb_finish_mmu(tlb, new_end, old_end);
/*
- * shrink the vma to just the new range.
+ * Shrink the vma to just the new range. Always succeeds.
*/
vma_adjust(vma, new_start, new_end, vma->vm_pgoff, NULL);
return 0;
}
-#define EXTRA_STACK_VM_PAGES 20 /* random */
-
/*
* Finalizes the stack vm_area_struct. The flags and permissions are updated,
* the stack is optionally relocated, and some extra space is added.
struct vm_area_struct *prev = NULL;
unsigned long vm_flags;
unsigned long stack_base;
+ unsigned long stack_size;
+ unsigned long stack_expand;
+ unsigned long rlim_stack;
#ifdef CONFIG_STACK_GROWSUP
/* Limit stack size to 1GB */
- stack_base = current->signal->rlim[RLIMIT_STACK].rlim_max;
+ stack_base = rlimit_max(RLIMIT_STACK);
if (stack_base > (1 << 30))
stack_base = 1 << 30;
else if (executable_stack == EXSTACK_DISABLE_X)
vm_flags &= ~VM_EXEC;
vm_flags |= mm->def_flags;
+ vm_flags |= VM_STACK_INCOMPLETE_SETUP;
ret = mprotect_fixup(vma, &prev, vma->vm_start, vma->vm_end,
vm_flags);
/* Move stack pages down in memory. */
if (stack_shift) {
ret = shift_arg_pages(vma, stack_shift);
- if (ret) {
- up_write(&mm->mmap_sem);
- return ret;
- }
+ if (ret)
+ goto out_unlock;
}
+ /* mprotect_fixup is overkill to remove the temporary stack flags */
+ vma->vm_flags &= ~VM_STACK_INCOMPLETE_SETUP;
+
+ stack_expand = 131072UL; /* randomly 32*4k (or 2*64k) pages */
+ stack_size = vma->vm_end - vma->vm_start;
+ /*
+ * Align this down to a page boundary as expand_stack
+ * will align it up.
+ */
+ rlim_stack = rlimit(RLIMIT_STACK) & PAGE_MASK;
#ifdef CONFIG_STACK_GROWSUP
- stack_base = vma->vm_end + EXTRA_STACK_VM_PAGES * PAGE_SIZE;
+ if (stack_size + stack_expand > rlim_stack)
+ stack_base = vma->vm_start + rlim_stack;
+ else
+ stack_base = vma->vm_end + stack_expand;
#else
- stack_base = vma->vm_start - EXTRA_STACK_VM_PAGES * PAGE_SIZE;
+ if (stack_size + stack_expand > rlim_stack)
+ stack_base = vma->vm_end - rlim_stack;
+ else
+ stack_base = vma->vm_start - stack_expand;
#endif
+ current->mm->start_stack = bprm->p;
ret = expand_stack(vma, stack_base);
if (ret)
ret = -EFAULT;
out_unlock:
up_write(&mm->mmap_sem);
- return 0;
+ return ret;
}
EXPORT_SYMBOL(setup_arg_pages);
struct file *open_exec(const char *name)
{
- struct nameidata nd;
struct file *file;
int err;
- err = path_lookup_open(AT_FDCWD, name, LOOKUP_FOLLOW, &nd,
- FMODE_READ|FMODE_EXEC);
- if (err)
+ file = do_filp_open(AT_FDCWD, name,
+ O_LARGEFILE | O_RDONLY | FMODE_EXEC, 0,
+ MAY_EXEC | MAY_OPEN);
+ if (IS_ERR(file))
goto out;
err = -EACCES;
- if (!S_ISREG(nd.path.dentry->d_inode->i_mode))
- goto out_path_put;
-
- if (nd.path.mnt->mnt_flags & MNT_NOEXEC)
- goto out_path_put;
+ if (!S_ISREG(file->f_path.dentry->d_inode->i_mode))
+ goto exit;
- err = inode_permission(nd.path.dentry->d_inode, MAY_EXEC | MAY_OPEN);
- if (err)
- goto out_path_put;
+ if (file->f_path.mnt->mnt_flags & MNT_NOEXEC)
+ goto exit;
- file = nameidata_to_filp(&nd, O_RDONLY|O_LARGEFILE);
- if (IS_ERR(file))
- return file;
+ fsnotify_open(file);
err = deny_write_access(file);
- if (err) {
- fput(file);
- goto out;
- }
+ if (err)
+ goto exit;
+out:
return file;
- out_path_put:
- release_open_intent(&nd);
- path_put(&nd.path);
- out:
+exit:
+ fput(file);
return ERR_PTR(err);
}
EXPORT_SYMBOL(open_exec);
-int kernel_read(struct file *file, unsigned long offset,
- char *addr, unsigned long count)
+int kernel_read(struct file *file, loff_t offset,
+ char *addr, unsigned long count)
{
mm_segment_t old_fs;
loff_t pos = offset;
/* Notify parent that we're no longer interested in the old VM */
tsk = current;
old_mm = current->mm;
+ sync_mm_rss(tsk, old_mm);
mm_release(tsk, old_mm);
if (old_mm) {
struct signal_struct *sig = tsk->signal;
struct sighand_struct *oldsighand = tsk->sighand;
spinlock_t *lock = &oldsighand->siglock;
- int count;
if (thread_group_empty(tsk))
goto no_thread_group;
spin_unlock_irq(lock);
return -EAGAIN;
}
+
sig->group_exit_task = tsk;
- zap_other_threads(tsk);
+ sig->notify_count = zap_other_threads(tsk);
+ if (!thread_group_leader(tsk))
+ sig->notify_count--;
- /* Account for the thread group leader hanging around: */
- count = thread_group_leader(tsk) ? 1 : 2;
- sig->notify_count = count;
- while (atomic_read(&sig->count) > count) {
+ while (sig->notify_count) {
__set_current_state(TASK_UNINTERRUPTIBLE);
spin_unlock_irq(lock);
schedule();
attach_pid(tsk, PIDTYPE_PID, task_pid(leader));
transfer_pid(leader, tsk, PIDTYPE_PGID);
transfer_pid(leader, tsk, PIDTYPE_SID);
+
list_replace_rcu(&leader->tasks, &tsk->tasks);
+ list_replace_init(&leader->sibling, &tsk->sibling);
tsk->group_leader = tsk;
leader->group_leader = tsk;
sig->notify_count = 0;
no_thread_group:
+ if (current->mm)
+ setmax_mm_hiwater_rss(&sig->maxrss, current->mm);
+
exit_itimers(sig);
flush_itimer_signals();
void set_task_comm(struct task_struct *tsk, char *buf)
{
task_lock(tsk);
+
+ /*
+ * Threads may access current->comm without holding
+ * the task lock, so write the string carefully.
+ * Readers without a lock may see incomplete new
+ * names but are safe from non-terminating string reads.
+ */
+ memset(tsk->comm, 0, TASK_COMM_LEN);
+ wmb();
strlcpy(tsk->comm, buf, sizeof(tsk->comm));
task_unlock(tsk);
+ perf_event_comm(tsk);
}
int flush_old_exec(struct linux_binprm * bprm)
{
- char * name;
- int i, ch, retval;
- char tcomm[sizeof(current->comm)];
+ int retval;
/*
* Make sure we have a private signal table and that
bprm->mm = NULL; /* We're using it now */
+ current->flags &= ~PF_RANDOMIZE;
+ flush_thread();
+ current->personality &= ~bprm->per_clear;
+
+ return 0;
+
+out:
+ return retval;
+}
+EXPORT_SYMBOL(flush_old_exec);
+
+void setup_new_exec(struct linux_binprm * bprm)
+{
+ int i, ch;
+ char * name;
+ char tcomm[sizeof(current->comm)];
+
+ arch_pick_mmap_layout(current->mm);
+
/* This is the point of no return */
current->sas_ss_sp = current->sas_ss_size = 0;
tcomm[i] = '\0';
set_task_comm(current, tcomm);
- current->flags &= ~PF_RANDOMIZE;
- flush_thread();
-
/* Set the new mm task size. We have to do that late because it may
* depend on TIF_32BIT which is only updated in flush_thread() on
* some architectures like powerpc
set_dumpable(current->mm, suid_dumpable);
}
- current->personality &= ~bprm->per_clear;
+ /*
+ * Flush performance counters when crossing a
+ * security domain:
+ */
+ if (!get_dumpable(current->mm))
+ perf_event_exit_task(current);
/* An exec changes our domain. We are no longer part of the thread
group */
flush_signal_handlers(current, 0);
flush_old_files(current->files);
+}
+EXPORT_SYMBOL(setup_new_exec);
- return 0;
+/*
+ * Prepare credentials and lock ->cred_guard_mutex.
+ * install_exec_creds() commits the new creds and drops the lock.
+ * Or, if exec fails before, free_bprm() should release ->cred and
+ * and unlock.
+ */
+int prepare_bprm_creds(struct linux_binprm *bprm)
+{
+ if (mutex_lock_interruptible(¤t->cred_guard_mutex))
+ return -ERESTARTNOINTR;
-out:
- return retval;
+ bprm->cred = prepare_exec_creds();
+ if (likely(bprm->cred))
+ return 0;
+
+ mutex_unlock(¤t->cred_guard_mutex);
+ return -ENOMEM;
}
-EXPORT_SYMBOL(flush_old_exec);
+void free_bprm(struct linux_binprm *bprm)
+{
+ free_arg_pages(bprm);
+ if (bprm->cred) {
+ mutex_unlock(¤t->cred_guard_mutex);
+ abort_creds(bprm->cred);
+ }
+ kfree(bprm);
+}
/*
* install the new credentials for this executable
commit_creds(bprm->cred);
bprm->cred = NULL;
-
- /* cred_exec_mutex must be held at least to this point to prevent
+ /*
+ * cred_guard_mutex must be held at least to this point to prevent
* ptrace_attach() from altering our determination of the task's
- * credentials; any time after this it may be unlocked */
-
+ * credentials; any time after this it may be unlocked.
+ */
security_bprm_committed_creds(bprm);
+ mutex_unlock(¤t->cred_guard_mutex);
}
EXPORT_SYMBOL(install_exec_creds);
/*
* determine how safe it is to execute the proposed program
- * - the caller must hold current->cred_exec_mutex to protect against
+ * - the caller must hold current->cred_guard_mutex to protect against
* PTRACE_ATTACH
*/
-void check_unsafe_exec(struct linux_binprm *bprm)
+int check_unsafe_exec(struct linux_binprm *bprm)
{
- struct task_struct *p = current;
+ struct task_struct *p = current, *t;
+ unsigned n_fs;
+ int res = 0;
bprm->unsafe = tracehook_unsafe_exec(p);
- if (atomic_read(&p->fs->count) > 1 ||
- atomic_read(&p->files->count) > 1 ||
- atomic_read(&p->sighand->count) > 1)
+ n_fs = 1;
+ spin_lock(&p->fs->lock);
+ rcu_read_lock();
+ for (t = next_thread(p); t != p; t = next_thread(t)) {
+ if (t->fs == p->fs)
+ n_fs++;
+ }
+ rcu_read_unlock();
+
+ if (p->fs->users > n_fs) {
bprm->unsafe |= LSM_UNSAFE_SHARE;
+ } else {
+ res = -EAGAIN;
+ if (!p->fs->in_exec) {
+ p->fs->in_exec = 1;
+ res = 1;
+ }
+ }
+ spin_unlock(&p->fs->lock);
+
+ return res;
}
/*
unsigned int depth = bprm->recursion_depth;
int try,retval;
struct linux_binfmt *fmt;
-#ifdef __alpha__
- /* handle /sbin/loader.. */
- {
- struct exec * eh = (struct exec *) bprm->buf;
-
- if (!bprm->loader && eh->fh.f_magic == 0x183 &&
- (eh->fh.f_flags & 0x3000) == 0x3000)
- {
- struct file * file;
- unsigned long loader;
- allow_write_access(bprm->file);
- fput(bprm->file);
- bprm->file = NULL;
-
- loader = bprm->vma->vm_end - sizeof(void *);
-
- file = open_exec("/sbin/loader");
- retval = PTR_ERR(file);
- if (IS_ERR(file))
- return retval;
-
- /* Remember if the application is TASO. */
- bprm->taso = eh->ah.entry < 0x100000000UL;
-
- bprm->file = file;
- bprm->loader = loader;
- retval = prepare_binprm(bprm);
- if (retval<0)
- return retval;
- /* should call search_binary_handler recursively here,
- but it does not matter */
- }
- }
-#endif
retval = security_bprm_check(bprm);
if (retval)
return retval;
EXPORT_SYMBOL(search_binary_handler);
-void free_bprm(struct linux_binprm *bprm)
-{
- free_arg_pages(bprm);
- if (bprm->cred)
- abort_creds(bprm->cred);
- kfree(bprm);
-}
-
/*
* sys_execve() executes a new program.
*/
struct linux_binprm *bprm;
struct file *file;
struct files_struct *displaced;
+ bool clear_in_exec;
int retval;
retval = unshare_files(&displaced);
if (!bprm)
goto out_files;
- retval = mutex_lock_interruptible(¤t->cred_exec_mutex);
- if (retval < 0)
+ retval = prepare_bprm_creds(bprm);
+ if (retval)
goto out_free;
- retval = -ENOMEM;
- bprm->cred = prepare_exec_creds();
- if (!bprm->cred)
- goto out_unlock;
- check_unsafe_exec(bprm);
+ retval = check_unsafe_exec(bprm);
+ if (retval < 0)
+ goto out_free;
+ clear_in_exec = retval;
+ current->in_execve = 1;
file = open_exec(filename);
retval = PTR_ERR(file);
if (IS_ERR(file))
- goto out_unlock;
+ goto out_unmark;
sched_exec();
goto out;
/* execve succeeded */
- mutex_unlock(¤t->cred_exec_mutex);
+ current->fs->in_exec = 0;
+ current->in_execve = 0;
acct_update_integrals(current);
free_bprm(bprm);
if (displaced)
fput(bprm->file);
}
-out_unlock:
- mutex_unlock(¤t->cred_exec_mutex);
+out_unmark:
+ if (clear_in_exec)
+ current->fs->in_exec = 0;
+ current->in_execve = 0;
out_free:
free_bprm(bprm);
return retval;
}
-int set_binfmt(struct linux_binfmt *new)
+void set_binfmt(struct linux_binfmt *new)
{
- struct linux_binfmt *old = current->binfmt;
+ struct mm_struct *mm = current->mm;
- if (new) {
- if (!try_module_get(new->module))
- return -1;
- }
- current->binfmt = new;
- if (old)
- module_put(old->module);
- return 0;
+ if (mm->binfmt)
+ module_put(mm->binfmt->module);
+
+ mm->binfmt = new;
+ if (new)
+ __module_get(new->module);
}
EXPORT_SYMBOL(set_binfmt);
/* core limit size */
case 'c':
rc = snprintf(out_ptr, out_end - out_ptr,
- "%lu", current->signal->rlim[RLIMIT_CORE].rlim_cur);
+ "%lu", rlimit(RLIMIT_CORE));
if (rc > out_end - out_ptr)
goto out;
out_ptr += rc;
return ispipe;
}
-static int zap_process(struct task_struct *start)
+static int zap_process(struct task_struct *start, int exit_code)
{
struct task_struct *t;
int nr = 0;
start->signal->flags = SIGNAL_GROUP_EXIT;
+ start->signal->group_exit_code = exit_code;
start->signal->group_stop_count = 0;
t = start;
spin_lock_irq(&tsk->sighand->siglock);
if (!signal_group_exit(tsk->signal)) {
mm->core_state = core_state;
- tsk->signal->group_exit_code = exit_code;
- nr = zap_process(tsk);
+ nr = zap_process(tsk, exit_code);
}
spin_unlock_irq(&tsk->sighand->siglock);
if (unlikely(nr < 0))
if (p->mm) {
if (unlikely(p->mm == mm)) {
lock_task_sighand(p, &flags);
- nr += zap_process(p);
+ nr += zap_process(p, exit_code);
unlock_task_sighand(p, &flags);
}
break;
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
struct completion *vfork_done;
- int core_waiters;
+ int core_waiters = -EBUSY;
init_completion(&core_state->startup);
core_state->dumper.task = tsk;
core_state->dumper.next = NULL;
- core_waiters = zap_threads(tsk, mm, core_state, exit_code);
+
+ down_write(&mm->mmap_sem);
+ if (!mm->core_state)
+ core_waiters = zap_threads(tsk, mm, core_state, exit_code);
up_write(&mm->mmap_sem);
if (unlikely(core_waiters < 0))
}
}
-int get_dumpable(struct mm_struct *mm)
+static int __get_dumpable(unsigned long mm_flags)
{
int ret;
- ret = mm->flags & 0x3;
+ ret = mm_flags & MMF_DUMPABLE_MASK;
return (ret >= 2) ? 2 : ret;
}
-int do_coredump(long signr, int exit_code, struct pt_regs * regs)
+int get_dumpable(struct mm_struct *mm)
+{
+ return __get_dumpable(mm->flags);
+}
+
+static void wait_for_dump_helpers(struct file *file)
+{
+ struct pipe_inode_info *pipe;
+
+ pipe = file->f_path.dentry->d_inode->i_pipe;
+
+ pipe_lock(pipe);
+ pipe->readers++;
+ pipe->writers--;
+
+ while ((pipe->readers > 1) && (!signal_pending(current))) {
+ wake_up_interruptible_sync(&pipe->wait);
+ kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
+ pipe_wait(pipe);
+ }
+
+ pipe->readers--;
+ pipe->writers++;
+ pipe_unlock(pipe);
+
+}
+
+
+/*
+ * uhm_pipe_setup
+ * helper function to customize the process used
+ * to collect the core in userspace. Specifically
+ * it sets up a pipe and installs it as fd 0 (stdin)
+ * for the process. Returns 0 on success, or
+ * PTR_ERR on failure.
+ * Note that it also sets the core limit to 1. This
+ * is a special value that we use to trap recursive
+ * core dumps
+ */
+static int umh_pipe_setup(struct subprocess_info *info)
+{
+ struct file *rp, *wp;
+ struct fdtable *fdt;
+ struct coredump_params *cp = (struct coredump_params *)info->data;
+ struct files_struct *cf = current->files;
+
+ wp = create_write_pipe(0);
+ if (IS_ERR(wp))
+ return PTR_ERR(wp);
+
+ rp = create_read_pipe(wp, 0);
+ if (IS_ERR(rp)) {
+ free_write_pipe(wp);
+ return PTR_ERR(rp);
+ }
+
+ cp->file = wp;
+
+ sys_close(0);
+ fd_install(0, rp);
+ spin_lock(&cf->file_lock);
+ fdt = files_fdtable(cf);
+ FD_SET(0, fdt->open_fds);
+ FD_CLR(0, fdt->close_on_exec);
+ spin_unlock(&cf->file_lock);
+
+ /* and disallow core files too */
+ current->signal->rlim[RLIMIT_CORE] = (struct rlimit){1, 1};
+
+ return 0;
+}
+
+void do_coredump(long signr, int exit_code, struct pt_regs *regs)
{
struct core_state core_state;
char corename[CORENAME_MAX_SIZE + 1];
struct mm_struct *mm = current->mm;
struct linux_binfmt * binfmt;
- struct inode * inode;
- struct file * file;
const struct cred *old_cred;
struct cred *cred;
int retval = 0;
int flag = 0;
- int ispipe = 0;
- unsigned long core_limit = current->signal->rlim[RLIMIT_CORE].rlim_cur;
- char **helper_argv = NULL;
- int helper_argc = 0;
- char *delimit;
+ int ispipe;
+ static atomic_t core_dump_count = ATOMIC_INIT(0);
+ struct coredump_params cprm = {
+ .signr = signr,
+ .regs = regs,
+ .limit = rlimit(RLIMIT_CORE),
+ /*
+ * We must use the same mm->flags while dumping core to avoid
+ * inconsistency of bit flags, since this flag is not protected
+ * by any locks.
+ */
+ .mm_flags = mm->flags,
+ };
audit_core_dumps(signr);
- binfmt = current->binfmt;
+ binfmt = mm->binfmt;
if (!binfmt || !binfmt->core_dump)
goto fail;
-
- cred = prepare_creds();
- if (!cred) {
- retval = -ENOMEM;
+ if (!__get_dumpable(cprm.mm_flags))
goto fail;
- }
- down_write(&mm->mmap_sem);
- /*
- * If another thread got here first, or we are not dumpable, bail out.
- */
- if (mm->core_state || !get_dumpable(mm)) {
- up_write(&mm->mmap_sem);
- put_cred(cred);
+ cred = prepare_creds();
+ if (!cred)
goto fail;
- }
-
/*
* We cannot trust fsuid as being the "true" uid of the
* process nor do we know its entire history. We only know it
* was tainted so we dump it as root in mode 2.
*/
- if (get_dumpable(mm) == 2) { /* Setuid core dump mode */
+ if (__get_dumpable(cprm.mm_flags) == 2) {
+ /* Setuid core dump mode */
flag = O_EXCL; /* Stop rewrite attacks */
cred->fsuid = 0; /* Dump root private */
}
retval = coredump_wait(exit_code, &core_state);
- if (retval < 0) {
- put_cred(cred);
- goto fail;
- }
+ if (retval < 0)
+ goto fail_creds;
old_cred = override_creds(cred);
*/
clear_thread_flag(TIF_SIGPENDING);
- /*
- * lock_kernel() because format_corename() is controlled by sysctl, which
- * uses lock_kernel()
- */
- lock_kernel();
ispipe = format_corename(corename, signr);
- unlock_kernel();
- /*
- * Don't bother to check the RLIMIT_CORE value if core_pattern points
- * to a pipe. Since we're not writing directly to the filesystem
- * RLIMIT_CORE doesn't really apply, as no actual core file will be
- * created unless the pipe reader choses to write out the core file
- * at which point file size limits and permissions will be imposed
- * as it does with any other process
- */
- if ((!ispipe) && (core_limit < binfmt->min_coredump))
- goto fail_unlock;
if (ispipe) {
- helper_argv = argv_split(GFP_KERNEL, corename+1, &helper_argc);
- /* Terminate the string before the first option */
- delimit = strchr(corename, ' ');
- if (delimit)
- *delimit = '\0';
- delimit = strrchr(helper_argv[0], '/');
- if (delimit)
- delimit++;
- else
- delimit = helper_argv[0];
- if (!strcmp(delimit, current->comm)) {
- printk(KERN_NOTICE "Recursive core dump detected, "
- "aborting\n");
+ int dump_count;
+ char **helper_argv;
+
+ if (cprm.limit == 1) {
+ /*
+ * Normally core limits are irrelevant to pipes, since
+ * we're not writing to the file system, but we use
+ * cprm.limit of 1 here as a speacial value. Any
+ * non-1 limit gets set to RLIM_INFINITY below, but
+ * a limit of 0 skips the dump. This is a consistent
+ * way to catch recursive crashes. We can still crash
+ * if the core_pattern binary sets RLIM_CORE = !1
+ * but it runs as root, and can do lots of stupid things
+ * Note that we use task_tgid_vnr here to grab the pid
+ * of the process group leader. That way we get the
+ * right pid if a thread in a multi-threaded
+ * core_pattern process dies.
+ */
+ printk(KERN_WARNING
+ "Process %d(%s) has RLIMIT_CORE set to 1\n",
+ task_tgid_vnr(current), current->comm);
+ printk(KERN_WARNING "Aborting core\n");
goto fail_unlock;
}
+ cprm.limit = RLIM_INFINITY;
+
+ dump_count = atomic_inc_return(&core_dump_count);
+ if (core_pipe_limit && (core_pipe_limit < dump_count)) {
+ printk(KERN_WARNING "Pid %d(%s) over core_pipe_limit\n",
+ task_tgid_vnr(current), current->comm);
+ printk(KERN_WARNING "Skipping core dump\n");
+ goto fail_dropcount;
+ }
- core_limit = RLIM_INFINITY;
+ helper_argv = argv_split(GFP_KERNEL, corename+1, NULL);
+ if (!helper_argv) {
+ printk(KERN_WARNING "%s failed to allocate memory\n",
+ __func__);
+ goto fail_dropcount;
+ }
- /* SIGPIPE can happen, but it's just never processed */
- if (call_usermodehelper_pipe(corename+1, helper_argv, NULL,
- &file)) {
+ retval = call_usermodehelper_fns(helper_argv[0], helper_argv,
+ NULL, UMH_WAIT_EXEC, umh_pipe_setup,
+ NULL, &cprm);
+ argv_free(helper_argv);
+ if (retval) {
printk(KERN_INFO "Core dump to %s pipe failed\n",
corename);
- goto fail_unlock;
+ goto close_fail;
}
- } else
- file = filp_open(corename,
+ } else {
+ struct inode *inode;
+
+ if (cprm.limit < binfmt->min_coredump)
+ goto fail_unlock;
+
+ cprm.file = filp_open(corename,
O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag,
0600);
- if (IS_ERR(file))
- goto fail_unlock;
- inode = file->f_path.dentry->d_inode;
- if (inode->i_nlink > 1)
- goto close_fail; /* multiple links - don't dump */
- if (!ispipe && d_unhashed(file->f_path.dentry))
- goto close_fail;
-
- /* AK: actually i see no reason to not allow this for named pipes etc.,
- but keep the previous behaviour for now. */
- if (!ispipe && !S_ISREG(inode->i_mode))
- goto close_fail;
- /*
- * Dont allow local users get cute and trick others to coredump
- * into their pre-created files:
- */
- if (inode->i_uid != current_fsuid())
- goto close_fail;
- if (!file->f_op)
- goto close_fail;
- if (!file->f_op->write)
- goto close_fail;
- if (!ispipe && do_truncate(file->f_path.dentry, 0, 0, file) != 0)
- goto close_fail;
+ if (IS_ERR(cprm.file))
+ goto fail_unlock;
- retval = binfmt->core_dump(signr, regs, file, core_limit);
+ inode = cprm.file->f_path.dentry->d_inode;
+ if (inode->i_nlink > 1)
+ goto close_fail;
+ if (d_unhashed(cprm.file->f_path.dentry))
+ goto close_fail;
+ /*
+ * AK: actually i see no reason to not allow this for named
+ * pipes etc, but keep the previous behaviour for now.
+ */
+ if (!S_ISREG(inode->i_mode))
+ goto close_fail;
+ /*
+ * Dont allow local users get cute and trick others to coredump
+ * into their pre-created files.
+ */
+ if (inode->i_uid != current_fsuid())
+ goto close_fail;
+ if (!cprm.file->f_op || !cprm.file->f_op->write)
+ goto close_fail;
+ if (do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file))
+ goto close_fail;
+ }
+ retval = binfmt->core_dump(&cprm);
if (retval)
current->signal->group_exit_code |= 0x80;
+
+ if (ispipe && core_pipe_limit)
+ wait_for_dump_helpers(cprm.file);
close_fail:
- filp_close(file, NULL);
+ if (cprm.file)
+ filp_close(cprm.file, NULL);
+fail_dropcount:
+ if (ispipe)
+ atomic_dec(&core_dump_count);
fail_unlock:
- if (helper_argv)
- argv_free(helper_argv);
-
+ coredump_finish(mm);
revert_creds(old_cred);
+fail_creds:
put_cred(cred);
- coredump_finish(mm);
fail:
- return retval;
+ return;
}
Code Review / linux-2.6.git / blobdiff