1 files changed, 173 insertions, 157 deletions

diff --git a/fs/exec.c b/fs/exec.c
index 7776209d98c1..d60794372963 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,
@@ -265,6 +267,14 @@ 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
@@ -285,6 +295,8 @@ 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;
@@ -472,6 +484,35 @@ static int count_strings_kernel(const char *const *argv)
 	return i;
 }
 
+static inline int bprm_set_stack_limit(struct linux_binprm *bprm,
+				       unsigned long limit)
+{
+#ifdef CONFIG_MMU
+	/* Avoid a pathological bprm->p. */
+	if (bprm->p < limit)
+		return -E2BIG;
+	bprm->argmin = bprm->p - limit;
+#endif
+	return 0;
+}
+static inline bool bprm_hit_stack_limit(struct linux_binprm *bprm)
+{
+#ifdef CONFIG_MMU
+	return bprm->p < bprm->argmin;
+#else
+	return false;
+#endif
+}
+
+/*
+ * Calculate bprm->argmin from:
+ * - _STK_LIM
+ * - ARG_MAX
+ * - bprm->rlim_stack.rlim_cur
+ * - bprm->argc
+ * - bprm->envc
+ * - bprm->p
+ */
 static int bprm_stack_limits(struct linux_binprm *bprm)
 {
 	unsigned long limit, ptr_size;
@@ -491,6 +532,9 @@ static int bprm_stack_limits(struct linux_binprm *bprm)
 	 * of argument strings even with small stacks
 	 */
 	limit = max_t(unsigned long, limit, ARG_MAX);
+	/* Reject totally pathological counts. */
+	if (bprm->argc < 0 || bprm->envc < 0)
+		return -E2BIG;
 	/*
 	 * We must account for the size of all the argv and envp pointers to
 	 * the argv and envp strings, since they will also take up space in
@@ -504,13 +548,14 @@ static int bprm_stack_limits(struct linux_binprm *bprm)
 	 * argc can never be 0, to keep them from walking envp by accident.
 	 * See do_execveat_common().
 	 */
-	ptr_size = (max(bprm->argc, 1) + bprm->envc) * sizeof(void *);
+	if (check_add_overflow(max(bprm->argc, 1), bprm->envc, &ptr_size) ||
+	    check_mul_overflow(ptr_size, sizeof(void *), &ptr_size))
+		return -E2BIG;
 	if (limit <= ptr_size)
 		return -E2BIG;
 	limit -= ptr_size;
 
-	bprm->argmin = bprm->p - limit;
-	return 0;
+	return bprm_set_stack_limit(bprm, limit);
 }
 
 /*
@@ -548,10 +593,8 @@ static int copy_strings(int argc, struct user_arg_ptr argv,
 		pos = bprm->p;
 		str += len;
 		bprm->p -= len;
-#ifdef CONFIG_MMU
-		if (bprm->p < bprm->argmin)
+		if (bprm_hit_stack_limit(bprm))
 			goto out;
-#endif
 
 		while (len > 0) {
 			int offset, bytes_to_copy;
@@ -626,7 +669,7 @@ int copy_string_kernel(const char *arg, struct linux_binprm *bprm)
 	/* We're going to work our way backwards. */
 	arg += len;
 	bprm->p -= len;
-	if (IS_ENABLED(CONFIG_MMU) && bprm->p < bprm->argmin)
+	if (bprm_hit_stack_limit(bprm))
 		return -E2BIG;
 
 	while (len > 0) {
@@ -667,80 +710,6 @@ static int copy_strings_kernel(int argc, const char *const *argv,
 #ifdef CONFIG_MMU
 
 /*
- * During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX.  Once
- * the binfmt code determines where the new stack should reside, we shift it to
- * its final location.  The process proceeds as follows:
- *
- * 1) Use shift to calculate the new vma endpoints.
- * 2) Extend vma to cover both the old and new ranges.  This ensures the
- *    arguments passed to subsequent functions are consistent.
- * 3) Move vma's page tables to the new range.
- * 4) Free up any cleared pgd range.
- * 5) Shrink the vma to cover only the new range.
- */
-static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
-{
-	struct mm_struct *mm = vma->vm_mm;
-	unsigned long old_start = vma->vm_start;
-	unsigned long old_end = vma->vm_end;
-	unsigned long length = old_end - old_start;
-	unsigned long new_start = old_start - shift;
-	unsigned long new_end = old_end - shift;
-	VMA_ITERATOR(vmi, mm, new_start);
-	struct vm_area_struct *next;
-	struct mmu_gather tlb;
-
-	BUG_ON(new_start > new_end);
-
-	/*
-	 * ensure there are no vmas between where we want to go
-	 * and where we are
-	 */
-	if (vma != vma_next(&vmi))
-		return -EFAULT;
-
-	vma_iter_prev_range(&vmi);
-	/*
-	 * cover the whole range: [new_start, old_end)
-	 */
-	if (vma_expand(&vmi, vma, new_start, old_end, vma->vm_pgoff, NULL))
-		return -ENOMEM;
-
-	/*
-	 * move the page tables downwards, on failure we rely on
-	 * process cleanup to remove whatever mess we made.
-	 */
-	if (length != move_page_tables(vma, old_start,
-				       vma, new_start, length, false))
-		return -ENOMEM;
-
-	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm);
-	next = vma_next(&vmi);
-	if (new_end > old_start) {
-		/*
-		 * when the old and new regions overlap clear from new_end.
-		 */
-		free_pgd_range(&tlb, new_end, old_end, new_end,
-			next ? next->vm_start : USER_PGTABLES_CEILING);
-	} else {
-		/*
-		 * otherwise, clean from old_start; this is done to not touch
-		 * the address space in [new_end, old_start) some architectures
-		 * have constraints on va-space that make this illegal (IA64) -
-		 * for the others its just a little faster.
-		 */
-		free_pgd_range(&tlb, old_start, old_end, new_end,
-			next ? next->vm_start : USER_PGTABLES_CEILING);
-	}
-	tlb_finish_mmu(&tlb);
-
-	vma_prev(&vmi);
-	/* Shrink the vma to just the new range */
-	return vma_shrink(&vmi, vma, new_start, new_end, vma->vm_pgoff);
-}
-
-/*
  * Finalizes the stack vm_area_struct. The flags and permissions are updated,
  * the stack is optionally relocated, and some extra space is added.
  */
@@ -833,7 +802,12 @@ int setup_arg_pages(struct linux_binprm *bprm,
 
 	/* Move stack pages down in memory. */
 	if (stack_shift) {
-		ret = shift_arg_pages(vma, stack_shift);
+		/*
+		 * During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX.  Once
+		 * the binfmt code determines where the new stack should reside, we shift it to
+		 * its final location.
+		 */
+		ret = relocate_vma_down(vma, stack_shift);
 		if (ret)
 			goto out_unlock;
 	}
@@ -903,10 +877,14 @@ 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;
 	int err;
+	struct file *file __free(fput) = NULL;
 	struct open_flags open_exec_flags = {
 		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
 		.acc_mode = MAY_EXEC,
@@ -930,22 +908,28 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags)
 	 * 633fb6ac3980 ("exec: move S_ISREG() check earlier"). Since then it is
 	 * an invariant that all non-regular files error out before we get here.
 	 */
-	err = -EACCES;
 	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)) ||
 	    path_noexec(&file->f_path))
-		goto exit;
+		return ERR_PTR(-EACCES);
 
 	err = deny_write_access(file);
 	if (err)
-		goto exit;
+		return ERR_PTR(err);
 
-	return file;
-
-exit:
-	fput(file);
-	return ERR_PTR(err);
+	return no_free_ptr(file);
 }
 
+/**
+ * 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);
@@ -985,8 +969,6 @@ 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)
@@ -1143,7 +1125,6 @@ static int de_thread(struct task_struct *tsk)
 
 		BUG_ON(leader->exit_state != EXIT_ZOMBIE);
 		leader->exit_state = EXIT_DEAD;
-
 		/*
 		 * We are going to release_task()->ptrace_unlink() silently,
 		 * the tracer can sleep in do_wait(). EXIT_DEAD guarantees
@@ -1253,17 +1234,24 @@ int begin_new_exec(struct linux_binprm * bprm)
 		return retval;
 
 	/*
-	 * Ensure all future errors are fatal.
+	 * This tracepoint marks the point before flushing the old exec where
+	 * the current task is still unchanged, but errors are fatal (point of
+	 * no return). The later "sched_process_exec" tracepoint is called after
+	 * the current task has successfully switched to the new exec.
 	 */
-	bprm->point_of_no_return = true;
+	trace_sched_prepare_exec(current, bprm);
 
 	/*
-	 * Make this the only thread in the thread group.
+	 * Ensure all future errors are fatal.
 	 */
+	bprm->point_of_no_return = true;
+
+	/* Make this the only thread in the thread group */
 	retval = de_thread(me);
 	if (retval)
 		goto out;
-
+	/* see the comment in check_unsafe_exec() */
+	current->fs->in_exec = 0;
 	/*
 	 * Cancel any io_uring activity across execve
 	 */
@@ -1362,7 +1350,28 @@ int begin_new_exec(struct linux_binprm * bprm)
 		set_dumpable(current->mm, SUID_DUMP_USER);
 
 	perf_event_exec();
-	__set_task_comm(me, kbasename(bprm->filename), true);
+
+	/*
+	 * If the original filename was empty, alloc_bprm() made up a path
+	 * that will probably not be useful to admins running ps or similar.
+	 * Let's fix it up to be something reasonable.
+	 */
+	if (bprm->comm_from_dentry) {
+		/*
+		 * Hold RCU lock to keep the name from being freed behind our back.
+		 * Use acquire semantics to make sure the terminating NUL from
+		 * __d_alloc() is seen.
+		 *
+		 * Note, we're deliberately sloppy here. We don't need to care about
+		 * detecting a concurrent rename and just want a terminated name.
+		 */
+		rcu_read_lock();
+		__set_task_comm(me, smp_load_acquire(&bprm->file->f_path.dentry->d_name.name),
+				true);
+		rcu_read_unlock();
+	} else {
+		__set_task_comm(me, kbasename(bprm->filename), true);
+	}
 
 	/* An exec changes our domain. We are no longer part of the thread
 	   group */
@@ -1487,6 +1496,15 @@ 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) {
@@ -1495,13 +1513,12 @@ static void free_bprm(struct linux_binprm *bprm)
 	}
 	free_arg_pages(bprm);
 	if (bprm->cred) {
+		/* in case exec fails before de_thread() succeeds */
+		current->fs->in_exec = 0;
 		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. */
@@ -1511,36 +1528,59 @@ 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;
 	} else {
-		if (filename->name[0] == '\0')
+		if (filename->name[0] == '\0') {
 			bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d", fd);
-		else
+			bprm->comm_from_dentry = 1;
+		} else {
 			bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d/%s",
 						  fd, filename->name);
+		}
 		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);
 }
 
@@ -1581,17 +1621,21 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
 	 * suid exec because the differently privileged task
 	 * will be able to manipulate the current directory, etc.
 	 * It would be nice to force an unshare instead...
+	 *
+	 * Otherwise we set fs->in_exec = 1 to deny clone(CLONE_FS)
+	 * from another sub-thread until de_thread() succeeds, this
+	 * state is protected by cred_guard_mutex we hold.
 	 */
-	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
@@ -1684,7 +1728,6 @@ static int prepare_binprm(struct linux_binprm *bprm)
  */
 int remove_arg_zero(struct linux_binprm *bprm)
 {
-	int ret = 0;
 	unsigned long offset;
 	char *kaddr;
 	struct page *page;
@@ -1695,10 +1738,8 @@ int remove_arg_zero(struct linux_binprm *bprm)
 	do {
 		offset = bprm->p & ~PAGE_MASK;
 		page = get_arg_page(bprm, bprm->p, 0);
-		if (!page) {
-			ret = -EFAULT;
-			goto out;
-		}
+		if (!page)
+			return -EFAULT;
 		kaddr = kmap_local_page(page);
 
 		for (; offset < PAGE_SIZE && kaddr[offset];
@@ -1711,10 +1752,8 @@ int remove_arg_zero(struct linux_binprm *bprm)
 
 	bprm->p++;
 	bprm->argc--;
-	ret = 0;
 
-out:
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(remove_arg_zero);
 
@@ -1814,13 +1853,8 @@ 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);
@@ -1836,26 +1870,8 @@ 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)
@@ -1867,7 +1883,6 @@ static int bprm_execve(struct linux_binprm *bprm,
 
 	sched_mm_cid_after_execve(current);
 	/* execve succeeded */
-	current->fs->in_exec = 0;
 	current->in_execve = 0;
 	rseq_execve(current);
 	user_events_execve(current);
@@ -1885,9 +1900,7 @@ 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;
 
 	return retval;
@@ -1920,7 +1933,7 @@ 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;
@@ -1969,7 +1982,7 @@ 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);
 
@@ -1994,7 +2007,7 @@ 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;
@@ -2029,7 +2042,7 @@ 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:
@@ -2155,7 +2168,7 @@ COMPAT_SYSCALL_DEFINE5(execveat, int, fd,
 
 #ifdef CONFIG_SYSCTL
 
-static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write,
+static int proc_dointvec_minmax_coredump(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
@@ -2175,7 +2188,6 @@ static struct ctl_table fs_exec_sysctls[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_TWO,
 	},
-	{ }
 };
 
 static int __init init_fs_exec_sysctls(void)
@@ -2186,3 +2198,7 @@ static int __init init_fs_exec_sysctls(void)
 
 fs_initcall(init_fs_exec_sysctls);
 #endif /* CONFIG_SYSCTL */
+
+#ifdef CONFIG_EXEC_KUNIT_TEST
+#include "tests/exec_kunit.c"
+#endif