#include <linux/proc_fs.h>
#include <linux/mount.h>
#include <linux/security.h>
-#include <linux/ima.h>
#include <linux/syscalls.h>
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.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>
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 */
* 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;
}
vma->vm_start = vma->vm_end - PAGE_SIZE;
vma->vm_flags = VM_STACK_FLAGS;
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)
goto 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;
/* 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;
}
+ 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
ret = expand_stack(vma, stack_base);
if (ret)
out_unlock:
up_write(&mm->mmap_sem);
- return 0;
+ return ret;
}
EXPORT_SYMBOL(setup_arg_pages);
/* 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) {
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:
flush_signal_handlers(current, 0);
flush_old_files(current->files);
-
- return 0;
-
-out:
- return retval;
}
-
-EXPORT_SYMBOL(flush_old_exec);
+EXPORT_SYMBOL(setup_new_exec);
/*
* Prepare credentials and lock ->cred_guard_mutex.
retval = security_bprm_check(bprm);
if (retval)
return retval;
- retval = ima_bprm_check(bprm);
- if (retval)
- return retval;
/* kernel module loader fixup */
/* so we don't try to load run modprobe in kernel space. */
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;
}
}
-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 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);
+
+}
+
+
void do_coredump(long signr, int exit_code, struct pt_regs *regs)
{
struct core_state core_state;
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 dump_count = 0;
+ 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;
/*
* If another thread got here first, or we are not dumpable, bail out.
*/
- if (mm->core_state || !get_dumpable(mm)) {
+ if (mm->core_state || !__get_dumpable(cprm.mm_flags)) {
up_write(&mm->mmap_sem);
put_cred(cred);
goto fail;
* 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 */
}
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))
+
+ if ((!ispipe) && (cprm.limit < binfmt->min_coredump))
goto fail_unlock;
if (ispipe) {
+ if (cprm.limit == 0) {
+ /*
+ * Normally core limits are irrelevant to pipes, since
+ * we're not writing to the file system, but we use
+ * cprm.limit of 0 here as a speacial value. Any
+ * non-zero 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 = !0
+ * 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 0\n",
+ task_tgid_vnr(current), current->comm);
+ printk(KERN_WARNING "Aborting core\n");
+ goto fail_unlock;
+ }
+
+ 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;
+ }
+
helper_argv = argv_split(GFP_KERNEL, corename+1, &helper_argc);
if (!helper_argv) {
printk(KERN_WARNING "%s failed to allocate memory\n",
__func__);
- goto fail_unlock;
- }
- /* 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");
- goto fail_unlock;
+ goto fail_dropcount;
}
- core_limit = RLIM_INFINITY;
+ cprm.limit = RLIM_INFINITY;
/* SIGPIPE can happen, but it's just never processed */
- if (call_usermodehelper_pipe(corename+1, helper_argv, NULL,
- &file)) {
+ if (call_usermodehelper_pipe(helper_argv[0], helper_argv, NULL,
+ &cprm.file)) {
printk(KERN_INFO "Core dump to %s pipe failed\n",
corename);
- goto fail_unlock;
+ goto fail_dropcount;
}
} else
- file = filp_open(corename,
+ 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 (IS_ERR(cprm.file))
+ goto fail_dropcount;
+ inode = cprm.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))
+ if (!ispipe && d_unhashed(cprm.file->f_path.dentry))
goto close_fail;
/* AK: actually i see no reason to not allow this for named pipes etc.,
/*
* Dont allow local users get cute and trick others to coredump
* into their pre-created files:
+ * Note, this is not relevant for pipes
*/
- if (inode->i_uid != current_fsuid())
+ if (!ispipe && (inode->i_uid != current_fsuid()))
goto close_fail;
- if (!file->f_op)
+ if (!cprm.file->f_op)
goto close_fail;
- if (!file->f_op->write)
+ if (!cprm.file->f_op->write)
goto close_fail;
- if (!ispipe && do_truncate(file->f_path.dentry, 0, 0, file) != 0)
+ if (!ispipe &&
+ do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file) != 0)
goto close_fail;
- retval = binfmt->core_dump(signr, regs, file, core_limit);
+ retval = binfmt->core_dump(&cprm);
if (retval)
current->signal->group_exit_code |= 0x80;
close_fail:
- filp_close(file, NULL);
+ if (ispipe && core_pipe_limit)
+ wait_for_dump_helpers(cprm.file);
+ filp_close(cprm.file, NULL);
+fail_dropcount:
+ if (dump_count)
+ atomic_dec(&core_dump_count);
fail_unlock:
if (helper_argv)
argv_free(helper_argv);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff