summaryrefslogtreecommitdiffstats
path: root/fs/exec.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/exec.c')
-rw-r--r--fs/exec.c124
1 files changed, 76 insertions, 48 deletions
diff --git a/fs/exec.c b/fs/exec.c
index 2f2b0acec..f11cfd7bc 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -66,6 +66,8 @@
#include <linux/coredump.h>
#include <linux/time_namespace.h>
#include <linux/user_events.h>
+#include <linux/rseq.h>
+#include <linux/ksm.h>
#include <linux/uaccess.h>
#include <asm/mmu_context.h>
@@ -127,7 +129,7 @@ SYSCALL_DEFINE1(uselib, const char __user *, library)
struct filename *tmp = getname(library);
int error = PTR_ERR(tmp);
static const struct open_flags uselib_flags = {
- .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
+ .open_flag = O_LARGEFILE | O_RDONLY,
.acc_mode = MAY_READ | MAY_EXEC,
.intent = LOOKUP_OPEN,
.lookup_flags = LOOKUP_FOLLOW,
@@ -267,6 +269,14 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
}
/*
+ * Need to be called with mmap write lock
+ * held, to avoid race with ksmd.
+ */
+ err = ksm_execve(mm);
+ if (err)
+ goto err_ksm;
+
+ /*
* Place the stack at the largest stack address the architecture
* supports. Later, we'll move this to an appropriate place. We don't
* use STACK_TOP because that can depend on attributes which aren't
@@ -287,6 +297,8 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
bprm->p = vma->vm_end - sizeof(void *);
return 0;
err:
+ ksm_exit(mm);
+err_ksm:
mmap_write_unlock(mm);
err_free:
bprm->vma = NULL;
@@ -713,7 +725,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
* process cleanup to remove whatever mess we made.
*/
if (length != move_page_tables(vma, old_start,
- vma, new_start, length, false))
+ vma, new_start, length, false, true))
return -ENOMEM;
lru_add_drain();
@@ -894,6 +906,7 @@ int transfer_args_to_stack(struct linux_binprm *bprm,
goto out;
}
+ bprm->exec += *sp_location - MAX_ARG_PAGES * PAGE_SIZE;
*sp_location = sp;
out:
@@ -903,6 +916,10 @@ EXPORT_SYMBOL(transfer_args_to_stack);
#endif /* CONFIG_MMU */
+/*
+ * On success, caller must call do_close_execat() on the returned
+ * struct file to close it.
+ */
static struct file *do_open_execat(int fd, struct filename *name, int flags)
{
struct file *file;
@@ -947,6 +964,17 @@ exit:
return ERR_PTR(err);
}
+/**
+ * open_exec - Open a path name for execution
+ *
+ * @name: path name to open with the intent of executing it.
+ *
+ * Returns ERR_PTR on failure or allocated struct file on success.
+ *
+ * As this is a wrapper for the internal do_open_execat(), callers
+ * must call allow_write_access() before fput() on release. Also see
+ * do_close_execat().
+ */
struct file *open_exec(const char *name)
{
struct filename *filename = getname_kernel(name);
@@ -986,8 +1014,6 @@ static int exec_mmap(struct mm_struct *mm)
tsk = current;
old_mm = current->mm;
exec_mm_release(tsk, old_mm);
- if (old_mm)
- sync_mm_rss(old_mm);
ret = down_write_killable(&tsk->signal->exec_update_lock);
if (ret)
@@ -1488,6 +1514,15 @@ static int prepare_bprm_creds(struct linux_binprm *bprm)
return -ENOMEM;
}
+/* Matches do_open_execat() */
+static void do_close_execat(struct file *file)
+{
+ if (!file)
+ return;
+ allow_write_access(file);
+ fput(file);
+}
+
static void free_bprm(struct linux_binprm *bprm)
{
if (bprm->mm) {
@@ -1499,10 +1534,7 @@ static void free_bprm(struct linux_binprm *bprm)
mutex_unlock(&current->signal->cred_guard_mutex);
abort_creds(bprm->cred);
}
- if (bprm->file) {
- allow_write_access(bprm->file);
- fput(bprm->file);
- }
+ do_close_execat(bprm->file);
if (bprm->executable)
fput(bprm->executable);
/* If a binfmt changed the interp, free it. */
@@ -1512,12 +1544,23 @@ static void free_bprm(struct linux_binprm *bprm)
kfree(bprm);
}
-static struct linux_binprm *alloc_bprm(int fd, struct filename *filename)
+static struct linux_binprm *alloc_bprm(int fd, struct filename *filename, int flags)
{
- struct linux_binprm *bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
+ struct linux_binprm *bprm;
+ struct file *file;
int retval = -ENOMEM;
- if (!bprm)
- goto out;
+
+ file = do_open_execat(fd, filename, flags);
+ if (IS_ERR(file))
+ return ERR_CAST(file);
+
+ bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
+ if (!bprm) {
+ do_close_execat(file);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ bprm->file = file;
if (fd == AT_FDCWD || filename->name[0] == '/') {
bprm->filename = filename->name;
@@ -1530,18 +1573,28 @@ static struct linux_binprm *alloc_bprm(int fd, struct filename *filename)
if (!bprm->fdpath)
goto out_free;
+ /*
+ * Record that a name derived from an O_CLOEXEC fd will be
+ * inaccessible after exec. This allows the code in exec to
+ * choose to fail when the executable is not mmaped into the
+ * interpreter and an open file descriptor is not passed to
+ * the interpreter. This makes for a better user experience
+ * than having the interpreter start and then immediately fail
+ * when it finds the executable is inaccessible.
+ */
+ if (get_close_on_exec(fd))
+ bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE;
+
bprm->filename = bprm->fdpath;
}
bprm->interp = bprm->filename;
retval = bprm_mm_init(bprm);
- if (retval)
- goto out_free;
- return bprm;
+ if (!retval)
+ return bprm;
out_free:
free_bprm(bprm);
-out:
return ERR_PTR(retval);
}
@@ -1583,16 +1636,16 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
* will be able to manipulate the current directory, etc.
* It would be nice to force an unshare instead...
*/
- t = p;
n_fs = 1;
spin_lock(&p->fs->lock);
rcu_read_lock();
- while_each_thread(p, t) {
+ for_other_threads(p, t) {
if (t->fs == p->fs)
n_fs++;
}
rcu_read_unlock();
+ /* "users" and "in_exec" locked for copy_fs() */
if (p->fs->users > n_fs)
bprm->unsafe |= LSM_UNSAFE_SHARE;
else
@@ -1809,13 +1862,8 @@ static int exec_binprm(struct linux_binprm *bprm)
return 0;
}
-/*
- * sys_execve() executes a new program.
- */
-static int bprm_execve(struct linux_binprm *bprm,
- int fd, struct filename *filename, int flags)
+static int bprm_execve(struct linux_binprm *bprm)
{
- struct file *file;
int retval;
retval = prepare_bprm_creds(bprm);
@@ -1831,26 +1879,8 @@ static int bprm_execve(struct linux_binprm *bprm,
current->in_execve = 1;
sched_mm_cid_before_execve(current);
- file = do_open_execat(fd, filename, flags);
- retval = PTR_ERR(file);
- if (IS_ERR(file))
- goto out_unmark;
-
sched_exec();
- bprm->file = file;
- /*
- * Record that a name derived from an O_CLOEXEC fd will be
- * inaccessible after exec. This allows the code in exec to
- * choose to fail when the executable is not mmaped into the
- * interpreter and an open file descriptor is not passed to
- * the interpreter. This makes for a better user experience
- * than having the interpreter start and then immediately fail
- * when it finds the executable is inaccessible.
- */
- if (bprm->fdpath && get_close_on_exec(fd))
- bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE;
-
/* Set the unchanging part of bprm->cred */
retval = security_bprm_creds_for_exec(bprm);
if (retval)
@@ -1880,7 +1910,6 @@ out:
if (bprm->point_of_no_return && !fatal_signal_pending(current))
force_fatal_sig(SIGSEGV);
-out_unmark:
sched_mm_cid_after_execve(current);
current->fs->in_exec = 0;
current->in_execve = 0;
@@ -1915,7 +1944,7 @@ static int do_execveat_common(int fd, struct filename *filename,
* further execve() calls fail. */
current->flags &= ~PF_NPROC_EXCEEDED;
- bprm = alloc_bprm(fd, filename);
+ bprm = alloc_bprm(fd, filename, flags);
if (IS_ERR(bprm)) {
retval = PTR_ERR(bprm);
goto out_ret;
@@ -1964,7 +1993,7 @@ static int do_execveat_common(int fd, struct filename *filename,
bprm->argc = 1;
}
- retval = bprm_execve(bprm, fd, filename, flags);
+ retval = bprm_execve(bprm);
out_free:
free_bprm(bprm);
@@ -1989,7 +2018,7 @@ int kernel_execve(const char *kernel_filename,
if (IS_ERR(filename))
return PTR_ERR(filename);
- bprm = alloc_bprm(fd, filename);
+ bprm = alloc_bprm(fd, filename, 0);
if (IS_ERR(bprm)) {
retval = PTR_ERR(bprm);
goto out_ret;
@@ -2024,7 +2053,7 @@ int kernel_execve(const char *kernel_filename,
if (retval < 0)
goto out_free;
- retval = bprm_execve(bprm, fd, filename, 0);
+ retval = bprm_execve(bprm);
out_free:
free_bprm(bprm);
out_ret:
@@ -2170,7 +2199,6 @@ static struct ctl_table fs_exec_sysctls[] = {
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_TWO,
},
- { }
};
static int __init init_fs_exec_sysctls(void)
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-08 23:22:24 +0000