#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/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 */
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)
- goto exit;
-
- error = inode_permission(nd.path.dentry->d_inode,
- MAY_READ | MAY_EXEC | MAY_OPEN);
- if (error)
- goto exit;
- error = ima_path_check(&nd.path, MAY_READ | MAY_EXEC | MAY_OPEN,
- IMA_COUNT_UPDATE);
- if (error)
+ if (file->f_path.mnt->mnt_flags & MNT_NOEXEC)
goto exit;
- file = nameidata_to_filp(&nd, O_RDONLY|O_LARGEFILE);
- error = PTR_ERR(file);
- if (IS_ERR(file))
- goto out;
-
fsnotify_open(file->f_path.dentry);
error = -ENOEXEC;
}
read_unlock(&binfmt_lock);
}
+exit:
fput(file);
out:
return error;
-exit:
- release_open_intent(&nd);
- path_put(&nd.path);
- goto out;
}
#ifdef CONFIG_MMU
/* 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;
}
#ifdef CONFIG_STACK_GROWSUP
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;
-
- err = inode_permission(nd.path.dentry->d_inode, MAY_EXEC | MAY_OPEN);
- if (err)
- goto out_path_put;
- err = ima_path_check(&nd.path, MAY_EXEC | MAY_OPEN, IMA_COUNT_UPDATE);
- if (err)
- goto out_path_put;
+ if (!S_ISREG(file->f_path.dentry->d_inode->i_mode))
+ goto exit;
- file = nameidata_to_filp(&nd, O_RDONLY|O_LARGEFILE);
- if (IS_ERR(file))
- return file;
+ if (file->f_path.mnt->mnt_flags & MNT_NOEXEC)
+ goto exit;
fsnotify_open(file->f_path.dentry);
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;
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)
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 */
EXPORT_SYMBOL(flush_old_exec);
/*
+ * 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;
+
+ bprm->cred = prepare_exec_creds();
+ if (likely(bprm->cred))
+ return 0;
+
+ mutex_unlock(¤t->cred_guard_mutex);
+ return -ENOMEM;
+}
+
+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
*/
void install_exec_creds(struct linux_binprm *bprm)
commit_creds(bprm->cred);
bprm->cred = NULL;
-
- /* cred_guard_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);
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. */
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.
*/
if (!bprm)
goto out_files;
- retval = mutex_lock_interruptible(¤t->cred_guard_mutex);
- if (retval < 0)
+ retval = prepare_bprm_creds(bprm);
+ if (retval)
goto out_free;
- current->in_execve = 1;
-
- retval = -ENOMEM;
- bprm->cred = prepare_exec_creds();
- if (!bprm->cred)
- goto out_unlock;
retval = check_unsafe_exec(bprm);
if (retval < 0)
- goto out_unlock;
+ goto out_free;
clear_in_exec = retval;
+ current->in_execve = 1;
file = open_exec(filename);
retval = PTR_ERR(file);
if (retval < 0)
goto out;
+ current->stack_start = current->mm->start_stack;
+
/* execve succeeded */
current->fs->in_exec = 0;
current->in_execve = 0;
- mutex_unlock(¤t->cred_guard_mutex);
acct_update_integrals(current);
free_bprm(bprm);
if (displaced)
out_unmark:
if (clear_in_exec)
current->fs->in_exec = 0;
-
-out_unlock:
current->in_execve = 0;
- mutex_unlock(¤t->cred_guard_mutex);
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);
return (ret >= 2) ? 2 : ret;
}
+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 = current->signal->rlim[RLIMIT_CORE].rlim_cur,
+ };
audit_core_dumps(signr);
- binfmt = current->binfmt;
+ binfmt = mm->binfmt;
if (!binfmt || !binfmt->core_dump)
goto fail;
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.,
*/
if (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