@@ -1856,44 +1856,16 @@ static int exec_binprm(struct linux_binprm *bprm)
/*
* sys_execve() executes a new program.
*/
-static int do_execveat_common(int fd, struct filename *filename,
- struct user_arg_ptr argv,
- struct user_arg_ptr envp,
- int flags)
+static int bprm_execve(struct linux_binprm *bprm,
+ int fd, struct filename *filename, int flags)
{
- struct linux_binprm *bprm;
struct file *file;
struct files_struct *displaced;
int retval;
- if (IS_ERR(filename))
- return PTR_ERR(filename);
-
- /*
- * We move the actual failure in case of RLIMIT_NPROC excess from
- * set*uid() to execve() because too many poorly written programs
- * don't check setuid() return code. Here we additionally recheck
- * whether NPROC limit is still exceeded.
- */
- if ((current->flags & PF_NPROC_EXCEEDED) &&
- atomic_read(¤t_user()->processes) > rlimit(RLIMIT_NPROC)) {
- retval = -EAGAIN;
- goto out_ret;
- }
-
- /* We're below the limit (still or again), so we don't want to make
- * further execve() calls fail. */
- current->flags &= ~PF_NPROC_EXCEEDED;
-
- bprm = alloc_bprm(fd, filename);
- if (IS_ERR(bprm)) {
- retval = PTR_ERR(bprm);
- goto out_ret;
- }
-
retval = unshare_files(&displaced);
if (retval)
- goto out_free;
+ return retval;
retval = prepare_bprm_creds(bprm);
if (retval)
@@ -1919,28 +1891,11 @@ static int do_execveat_common(int fd, struct filename *filename,
close_on_exec(fd, rcu_dereference_raw(current->files->fdt)))
bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE;
- retval = prepare_arg_pages(bprm, argv, envp);
- if (retval < 0)
- goto out;
-
/* Set the unchanging part of bprm->cred */
retval = security_bprm_creds_for_exec(bprm);
if (retval)
goto out;
- retval = copy_string_kernel(bprm->filename, bprm);
- if (retval < 0)
- goto out;
-
- bprm->exec = bprm->p;
- retval = copy_strings(bprm->envc, envp, bprm);
- if (retval < 0)
- goto out;
-
- retval = copy_strings(bprm->argc, argv, bprm);
- if (retval < 0)
- goto out;
-
retval = exec_binprm(bprm);
if (retval < 0)
goto out;
@@ -1951,8 +1906,6 @@ static int do_execveat_common(int fd, struct filename *filename,
rseq_execve(current);
acct_update_integrals(current);
task_numa_free(current, false);
- free_bprm(bprm);
- putname(filename);
if (displaced)
put_files_struct(displaced);
return retval;
@@ -1974,6 +1927,61 @@ static int do_execveat_common(int fd, struct filename *filename,
out_files:
if (displaced)
reset_files_struct(displaced);
+
+ return retval;
+}
+
+static int do_execveat_common(int fd, struct filename *filename,
+ struct user_arg_ptr argv,
+ struct user_arg_ptr envp,
+ int flags)
+{
+ struct linux_binprm *bprm;
+ int retval;
+
+ if (IS_ERR(filename))
+ return PTR_ERR(filename);
+
+ /*
+ * We move the actual failure in case of RLIMIT_NPROC excess from
+ * set*uid() to execve() because too many poorly written programs
+ * don't check setuid() return code. Here we additionally recheck
+ * whether NPROC limit is still exceeded.
+ */
+ if ((current->flags & PF_NPROC_EXCEEDED) &&
+ atomic_read(¤t_user()->processes) > rlimit(RLIMIT_NPROC)) {
+ retval = -EAGAIN;
+ goto out_ret;
+ }
+
+ /* We're below the limit (still or again), so we don't want to make
+ * further execve() calls fail. */
+ current->flags &= ~PF_NPROC_EXCEEDED;
+
+ bprm = alloc_bprm(fd, filename);
+ if (IS_ERR(bprm)) {
+ retval = PTR_ERR(bprm);
+ goto out_ret;
+ }
+
+ retval = prepare_arg_pages(bprm, argv, envp);
+ if (retval < 0)
+ goto out_free;
+
+ retval = copy_string_kernel(bprm->filename, bprm);
+ if (retval < 0)
+ goto out_free;
+ bprm->exec = bprm->p;
+
+ retval = copy_strings(bprm->envc, envp, bprm);
+ if (retval < 0)
+ goto out_free;
+
+ retval = copy_strings(bprm->argc, argv, bprm);
+ if (retval < 0)
+ goto out_free;
+
+ retval = bprm_execve(bprm, fd, filename, flags);
out_free:
free_bprm(bprm);
Currently it is necessary for the usermode helper code and the code that launches init to use set_fs so that pages coming from the kernel look like they are coming from userspace. To allow that usage of set_fs to be removed cleanly the argument copying from userspace needs to happen earlier. Factor bprm_execve out of do_execve_common to separate out the copying of arguments to the newe stack, and the rest of exec. In separating bprm_execve from do_execve_common the copying of the arguments onto the new stack happens earlier. As the copying of the arguments does not depend any security hooks, files, the file table, current->in_execve, current->fs->in_exec, bprm->unsafe, or creds this is safe. Likewise the security hook security_creds_for_exec does not depend upon preventing the argument copying from happening. In addition to making it possible to implement kernel_execve that performs the copying differently, this separation of bprm_execve from do_execve_common makes for a nice separation of responsibilities making the exec code easier to navigate. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> --- fs/exec.c | 108 +++++++++++++++++++++++++++++------------------------- 1 file changed, 58 insertions(+), 50 deletions(-)