1 files changed, 199 insertions, 295 deletions

diff --git a/fs/exec.c b/fs/exec.c
index 8b9011b6704..a3d33fe592d 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -26,6 +26,7 @@
 #include <linux/file.h>
 #include <linux/fdtable.h>
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/stat.h>
 #include <linux/fcntl.h>
 #include <linux/swap.h>
@@ -62,7 +63,6 @@
 
 #include <trace/events/task.h>
 #include "internal.h"
-#include "coredump.h"
 
 #include <trace/events/sched.h>
 
@@ -74,6 +74,8 @@ static DEFINE_RWLOCK(binfmt_lock);
 void __register_binfmt(struct linux_binfmt * fmt, int insert)
 {
 	BUG_ON(!fmt);
+	if (WARN_ON(!fmt->load_binary))
+		return;
 	write_lock(&binfmt_lock);
 	insert ? list_add(&fmt->lh, &formats) :
 		 list_add_tail(&fmt->lh, &formats);
@@ -96,6 +98,7 @@ static inline void put_binfmt(struct linux_binfmt * fmt)
 	module_put(fmt->module);
 }
 
+#ifdef CONFIG_USELIB
 /*
  * Note that a shared library must be both readable and executable due to
  * security reasons.
@@ -104,26 +107,28 @@ static inline void put_binfmt(struct linux_binfmt * fmt)
  */
 SYSCALL_DEFINE1(uselib, const char __user *, library)
 {
+	struct linux_binfmt *fmt;
 	struct file *file;
 	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,
 		.acc_mode = MAY_READ | MAY_EXEC | MAY_OPEN,
-		.intent = LOOKUP_OPEN
+		.intent = LOOKUP_OPEN,
+		.lookup_flags = LOOKUP_FOLLOW,
 	};
 
 	if (IS_ERR(tmp))
 		goto out;
 
-	file = do_filp_open(AT_FDCWD, tmp, &uselib_flags, LOOKUP_FOLLOW);
+	file = do_filp_open(AT_FDCWD, tmp, &uselib_flags);
 	putname(tmp);
 	error = PTR_ERR(file);
 	if (IS_ERR(file))
 		goto out;
 
 	error = -EINVAL;
-	if (!S_ISREG(file->f_path.dentry->d_inode->i_mode))
+	if (!S_ISREG(file_inode(file)->i_mode))
 		goto exit;
 
 	error = -EACCES;
@@ -133,29 +138,27 @@ SYSCALL_DEFINE1(uselib, const char __user *, library)
 	fsnotify_open(file);
 
 	error = -ENOEXEC;
-	if(file->f_op) {
-		struct linux_binfmt * fmt;
 
-		read_lock(&binfmt_lock);
-		list_for_each_entry(fmt, &formats, lh) {
-			if (!fmt->load_shlib)
-				continue;
-			if (!try_module_get(fmt->module))
-				continue;
-			read_unlock(&binfmt_lock);
-			error = fmt->load_shlib(file);
-			read_lock(&binfmt_lock);
-			put_binfmt(fmt);
-			if (error != -ENOEXEC)
-				break;
-		}
+	read_lock(&binfmt_lock);
+	list_for_each_entry(fmt, &formats, lh) {
+		if (!fmt->load_shlib)
+			continue;
+		if (!try_module_get(fmt->module))
+			continue;
 		read_unlock(&binfmt_lock);
+		error = fmt->load_shlib(file);
+		read_lock(&binfmt_lock);
+		put_binfmt(fmt);
+		if (error != -ENOEXEC)
+			break;
 	}
+	read_unlock(&binfmt_lock);
 exit:
 	fput(file);
 out:
   	return error;
 }
+#endif /* #ifdef CONFIG_USELIB */
 
 #ifdef CONFIG_MMU
 /*
@@ -265,7 +268,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
 	BUILD_BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP);
 	vma->vm_end = STACK_TOP_MAX;
 	vma->vm_start = vma->vm_end - PAGE_SIZE;
-	vma->vm_flags = VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP;
+	vma->vm_flags = VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP;
 	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
 	INIT_LIST_HEAD(&vma->anon_vma_chain);
 
@@ -355,7 +358,7 @@ static bool valid_arg_len(struct linux_binprm *bprm, long len)
  * flags, permissions, and offset, so we use temporary values.  We'll update
  * them later in setup_arg_pages().
  */
-int bprm_mm_init(struct linux_binprm *bprm)
+static int bprm_mm_init(struct linux_binprm *bprm)
 {
 	int err;
 	struct mm_struct *mm = NULL;
@@ -434,8 +437,9 @@ static int count(struct user_arg_ptr argv, int max)
 			if (IS_ERR(p))
 				return -EFAULT;
 
-			if (i++ >= max)
+			if (i >= max)
 				return -E2BIG;
+			++i;
 
 			if (fatal_signal_pending(current))
 				return -ERESTARTNOHAND;
@@ -606,13 +610,13 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
 		return -ENOMEM;
 
 	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm, 0);
+	tlb_gather_mmu(&tlb, mm, old_start, old_end);
 	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,
-			vma->vm_next ? vma->vm_next->vm_start : 0);
+			vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING);
 	} else {
 		/*
 		 * otherwise, clean from old_start; this is done to not touch
@@ -621,9 +625,9 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
 		 * for the others its just a little faster.
 		 */
 		free_pgd_range(&tlb, old_start, old_end, new_end,
-			vma->vm_next ? vma->vm_next->vm_start : 0);
+			vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING);
 	}
-	tlb_finish_mmu(&tlb, new_end, old_end);
+	tlb_finish_mmu(&tlb, old_start, old_end);
 
 	/*
 	 * Shrink the vma to just the new range.  Always succeeds.
@@ -653,10 +657,10 @@ int setup_arg_pages(struct linux_binprm *bprm,
 	unsigned long rlim_stack;
 
 #ifdef CONFIG_STACK_GROWSUP
-	/* Limit stack size to 1GB */
+	/* Limit stack size */
 	stack_base = rlimit_max(RLIMIT_STACK);
-	if (stack_base > (1 << 30))
-		stack_base = 1 << 30;
+	if (stack_base > STACK_SIZE_MAX)
+		stack_base = STACK_SIZE_MAX;
 
 	/* Make sure we didn't let the argument array grow too large. */
 	if (vma->vm_end - vma->vm_start > stack_base)
@@ -747,23 +751,23 @@ EXPORT_SYMBOL(setup_arg_pages);
 
 #endif /* CONFIG_MMU */
 
-struct file *open_exec(const char *name)
+static struct file *do_open_exec(struct filename *name)
 {
 	struct file *file;
 	int err;
-	struct filename tmp = { .name = name };
 	static const struct open_flags open_exec_flags = {
 		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
 		.acc_mode = MAY_EXEC | MAY_OPEN,
-		.intent = LOOKUP_OPEN
+		.intent = LOOKUP_OPEN,
+		.lookup_flags = LOOKUP_FOLLOW,
 	};
 
-	file = do_filp_open(AT_FDCWD, &tmp, &open_exec_flags, LOOKUP_FOLLOW);
+	file = do_filp_open(AT_FDCWD, name, &open_exec_flags);
 	if (IS_ERR(file))
 		goto out;
 
 	err = -EACCES;
-	if (!S_ISREG(file->f_path.dentry->d_inode->i_mode))
+	if (!S_ISREG(file_inode(file)->i_mode))
 		goto exit;
 
 	if (file->f_path.mnt->mnt_flags & MNT_NOEXEC)
@@ -782,6 +786,12 @@ exit:
 	fput(file);
 	return ERR_PTR(err);
 }
+
+struct file *open_exec(const char *name)
+{
+	struct filename tmp = { .name = name };
+	return do_open_exec(&tmp);
+}
 EXPORT_SYMBOL(open_exec);
 
 int kernel_read(struct file *file, loff_t offset,
@@ -801,10 +811,19 @@ int kernel_read(struct file *file, loff_t offset,
 
 EXPORT_SYMBOL(kernel_read);
 
+ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len)
+{
+	ssize_t res = vfs_read(file, (void __user *)addr, len, &pos);
+	if (res > 0)
+		flush_icache_range(addr, addr + len);
+	return res;
+}
+EXPORT_SYMBOL(read_code);
+
 static int exec_mmap(struct mm_struct *mm)
 {
 	struct task_struct *tsk;
-	struct mm_struct * old_mm, *active_mm;
+	struct mm_struct *old_mm, *active_mm;
 
 	/* Notify parent that we're no longer interested in the old VM */
 	tsk = current;
@@ -830,8 +849,9 @@ static int exec_mmap(struct mm_struct *mm)
 	tsk->mm = mm;
 	tsk->active_mm = mm;
 	activate_mm(active_mm, mm);
+	tsk->mm->vmacache_seqnum = 0;
+	vmacache_flush(tsk);
 	task_unlock(tsk);
-	arch_pick_mmap_layout(mm);
 	if (old_mm) {
 		up_read(&old_mm->mmap_sem);
 		BUG_ON(active_mm != old_mm);
@@ -897,11 +917,13 @@ static int de_thread(struct task_struct *tsk)
 
 		sig->notify_count = -1;	/* for exit_notify() */
 		for (;;) {
+			threadgroup_change_begin(tsk);
 			write_lock_irq(&tasklist_lock);
 			if (likely(leader->exit_state))
 				break;
 			__set_current_state(TASK_KILLABLE);
 			write_unlock_irq(&tasklist_lock);
+			threadgroup_change_end(tsk);
 			schedule();
 			if (unlikely(__fatal_signal_pending(tsk)))
 				goto killed;
@@ -918,6 +940,7 @@ static int de_thread(struct task_struct *tsk)
 		 * also take its birthdate (always earlier than our own).
 		 */
 		tsk->start_time = leader->start_time;
+		tsk->real_start_time = leader->real_start_time;
 
 		BUG_ON(!same_thread_group(leader, tsk));
 		BUG_ON(has_group_leader_pid(tsk));
@@ -933,9 +956,8 @@ static int de_thread(struct task_struct *tsk)
 		 * Note: The old leader also uses this pid until release_task
 		 *       is called.  Odd but simple and correct.
 		 */
-		detach_pid(tsk, PIDTYPE_PID);
 		tsk->pid = leader->pid;
-		attach_pid(tsk, PIDTYPE_PID,  task_pid(leader));
+		change_pid(tsk, PIDTYPE_PID, task_pid(leader));
 		transfer_pid(leader, tsk, PIDTYPE_PGID);
 		transfer_pid(leader, tsk, PIDTYPE_SID);
 
@@ -959,6 +981,7 @@ static int de_thread(struct task_struct *tsk)
 		if (unlikely(leader->ptrace))
 			__wake_up_parent(leader, leader->parent);
 		write_unlock_irq(&tasklist_lock);
+		threadgroup_change_end(tsk);
 
 		release_task(leader);
 	}
@@ -1023,38 +1046,13 @@ EXPORT_SYMBOL_GPL(get_task_comm);
  * so that a new one can be started
  */
 
-void set_task_comm(struct task_struct *tsk, char *buf)
+void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec)
 {
 	task_lock(tsk);
-
 	trace_task_rename(tsk, buf);
-
-	/*
-	 * 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);
-}
-
-static void filename_to_taskname(char *tcomm, const char *fn, unsigned int len)
-{
-	int i, ch;
-
-	/* Copies the binary name from after last slash */
-	for (i = 0; (ch = *(fn++)) != '\0';) {
-		if (ch == '/')
-			i = 0; /* overwrite what we wrote */
-		else
-			if (i < len - 1)
-				tcomm[i++] = ch;
-	}
-	tcomm[i] = '\0';
+	perf_event_comm(tsk, exec);
 }
 
 int flush_old_exec(struct linux_binprm * bprm)
@@ -1070,8 +1068,6 @@ int flush_old_exec(struct linux_binprm * bprm)
 		goto out;
 
 	set_mm_exe_file(bprm->mm, bprm->file);
-
-	filename_to_taskname(bprm->tcomm, bprm->filename, sizeof(bprm->tcomm));
 	/*
 	 * Release all of the old mmap stuff
 	 */
@@ -1083,7 +1079,8 @@ int flush_old_exec(struct linux_binprm * bprm)
 	bprm->mm = NULL;		/* We're using it now */
 
 	set_fs(USER_DS);
-	current->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD);
+	current->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD |
+					PF_NOFREEZE | PF_NO_SETAFFINITY);
 	flush_thread();
 	current->personality &= ~bprm->per_clear;
 
@@ -1096,7 +1093,7 @@ EXPORT_SYMBOL(flush_old_exec);
 
 void would_dump(struct linux_binprm *bprm, struct file *file)
 {
-	if (inode_permission(file->f_path.dentry->d_inode, MAY_READ) < 0)
+	if (inode_permission(file_inode(file), MAY_READ) < 0)
 		bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP;
 }
 EXPORT_SYMBOL(would_dump);
@@ -1109,11 +1106,12 @@ void setup_new_exec(struct linux_binprm * bprm)
 	current->sas_ss_sp = current->sas_ss_size = 0;
 
 	if (uid_eq(current_euid(), current_uid()) && gid_eq(current_egid(), current_gid()))
-		set_dumpable(current->mm, SUID_DUMPABLE_ENABLED);
+		set_dumpable(current->mm, SUID_DUMP_USER);
 	else
 		set_dumpable(current->mm, suid_dumpable);
 
-	set_task_comm(current, bprm->tcomm);
+	perf_event_exec();
+	__set_task_comm(current, kbasename(bprm->filename), true);
 
 	/* 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
@@ -1131,18 +1129,9 @@ void setup_new_exec(struct linux_binprm * bprm)
 			set_dumpable(current->mm, suid_dumpable);
 	}
 
-	/*
-	 * 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 */
-
 	current->self_exec_id++;
-			
 	flush_signal_handlers(current, 0);
 	do_close_on_exec(current->files);
 }
@@ -1167,16 +1156,35 @@ int prepare_bprm_creds(struct linux_binprm *bprm)
 	return -ENOMEM;
 }
 
-void free_bprm(struct linux_binprm *bprm)
+static void free_bprm(struct linux_binprm *bprm)
 {
 	free_arg_pages(bprm);
 	if (bprm->cred) {
 		mutex_unlock(&current->signal->cred_guard_mutex);
 		abort_creds(bprm->cred);
 	}
+	if (bprm->file) {
+		allow_write_access(bprm->file);
+		fput(bprm->file);
+	}
+	/* If a binfmt changed the interp, free it. */
+	if (bprm->interp != bprm->filename)
+		kfree(bprm->interp);
 	kfree(bprm);
 }
 
+int bprm_change_interp(char *interp, struct linux_binprm *bprm)
+{
+	/* If a binfmt changed the interp, free it first. */
+	if (bprm->interp != bprm->filename)
+		kfree(bprm->interp);
+	bprm->interp = kstrdup(interp, GFP_KERNEL);
+	if (!bprm->interp)
+		return -ENOMEM;
+	return 0;
+}
+EXPORT_SYMBOL(bprm_change_interp);
+
 /*
  * install the new credentials for this executable
  */
@@ -1186,6 +1194,15 @@ void install_exec_creds(struct linux_binprm *bprm)
 
 	commit_creds(bprm->cred);
 	bprm->cred = NULL;
+
+	/*
+	 * Disable monitoring for regular users
+	 * when executing setuid binaries. Must
+	 * wait until new credentials are committed
+	 * by commit_creds() above
+	 */
+	if (get_dumpable(current->mm) != SUID_DUMP_USER)
+		perf_event_exit_task(current);
 	/*
 	 * cred_guard_mutex must be held at least to this point to prevent
 	 * ptrace_attach() from altering our determination of the task's
@@ -1201,11 +1218,10 @@ EXPORT_SYMBOL(install_exec_creds);
  * - the caller must hold ->cred_guard_mutex to protect against
  *   PTRACE_ATTACH
  */
-static int check_unsafe_exec(struct linux_binprm *bprm)
+static void check_unsafe_exec(struct linux_binprm *bprm)
 {
 	struct task_struct *p = current, *t;
 	unsigned n_fs;
-	int res = 0;
 
 	if (p->ptrace) {
 		if (p->ptrace & PT_PTRACE_CAP)
@@ -1221,58 +1237,48 @@ static int check_unsafe_exec(struct linux_binprm *bprm)
 	if (current->no_new_privs)
 		bprm->unsafe |= LSM_UNSAFE_NO_NEW_PRIVS;
 
+	t = p;
 	n_fs = 1;
 	spin_lock(&p->fs->lock);
 	rcu_read_lock();
-	for (t = next_thread(p); t != p; t = next_thread(t)) {
+	while_each_thread(p, t) {
 		if (t->fs == p->fs)
 			n_fs++;
 	}
 	rcu_read_unlock();
 
-	if (p->fs->users > n_fs) {
+	if (p->fs->users > n_fs)
 		bprm->unsafe |= LSM_UNSAFE_SHARE;
-	} else {
-		res = -EAGAIN;
-		if (!p->fs->in_exec) {
-			p->fs->in_exec = 1;
-			res = 1;
-		}
-	}
+	else
+		p->fs->in_exec = 1;
 	spin_unlock(&p->fs->lock);
-
-	return res;
 }
 
-/* 
- * Fill the binprm structure from the inode. 
+/*
+ * Fill the binprm structure from the inode.
  * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes
  *
  * This may be called multiple times for binary chains (scripts for example).
  */
 int prepare_binprm(struct linux_binprm *bprm)
 {
-	umode_t mode;
-	struct inode * inode = bprm->file->f_path.dentry->d_inode;
+	struct inode *inode = file_inode(bprm->file);
+	umode_t mode = inode->i_mode;
 	int retval;
 
-	mode = inode->i_mode;
-	if (bprm->file->f_op == NULL)
-		return -EACCES;
 
 	/* clear any previous set[ug]id data from a previous binary */
 	bprm->cred->euid = current_euid();
 	bprm->cred->egid = current_egid();
 
 	if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) &&
-	    !current->no_new_privs) {
+	    !current->no_new_privs &&
+	    kuid_has_mapping(bprm->cred->user_ns, inode->i_uid) &&
+	    kgid_has_mapping(bprm->cred->user_ns, inode->i_gid)) {
 		/* Set-uid? */
 		if (mode & S_ISUID) {
-			if (!kuid_has_mapping(bprm->cred->user_ns, inode->i_uid))
-				return -EPERM;
 			bprm->per_clear |= PER_CLEAR_ON_SETID;
 			bprm->cred->euid = inode->i_uid;
-
 		}
 
 		/* Set-gid? */
@@ -1282,8 +1288,6 @@ int prepare_binprm(struct linux_binprm *bprm)
 		 * executable.
 		 */
 		if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
-			if (!kgid_has_mapping(bprm->cred->user_ns, inode->i_gid))
-				return -EPERM;
 			bprm->per_clear |= PER_CLEAR_ON_SETID;
 			bprm->cred->egid = inode->i_gid;
 		}
@@ -1345,23 +1349,62 @@ out:
 }
 EXPORT_SYMBOL(remove_arg_zero);
 
+#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e))
 /*
  * cycle the list of binary formats handler, until one recognizes the image
  */
-int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
+int search_binary_handler(struct linux_binprm *bprm)
 {
-	unsigned int depth = bprm->recursion_depth;
-	int try,retval;
+	bool need_retry = IS_ENABLED(CONFIG_MODULES);
 	struct linux_binfmt *fmt;
-	pid_t old_pid, old_vpid;
+	int retval;
+
+	/* This allows 4 levels of binfmt rewrites before failing hard. */
+	if (bprm->recursion_depth > 5)
+		return -ELOOP;
 
 	retval = security_bprm_check(bprm);
 	if (retval)
 		return retval;
 
-	retval = audit_bprm(bprm);
-	if (retval)
-		return retval;
+	retval = -ENOENT;
+ retry:
+	read_lock(&binfmt_lock);
+	list_for_each_entry(fmt, &formats, lh) {
+		if (!try_module_get(fmt->module))
+			continue;
+		read_unlock(&binfmt_lock);
+		bprm->recursion_depth++;
+		retval = fmt->load_binary(bprm);
+		bprm->recursion_depth--;
+		if (retval >= 0 || retval != -ENOEXEC ||
+		    bprm->mm == NULL || bprm->file == NULL) {
+			put_binfmt(fmt);
+			return retval;
+		}
+		read_lock(&binfmt_lock);
+		put_binfmt(fmt);
+	}
+	read_unlock(&binfmt_lock);
+
+	if (need_retry && retval == -ENOEXEC) {
+		if (printable(bprm->buf[0]) && printable(bprm->buf[1]) &&
+		    printable(bprm->buf[2]) && printable(bprm->buf[3]))
+			return retval;
+		if (request_module("binfmt-%04x", *(ushort *)(bprm->buf + 2)) < 0)
+			return retval;
+		need_retry = false;
+		goto retry;
+	}
+
+	return retval;
+}
+EXPORT_SYMBOL(search_binary_handler);
+
+static int exec_binprm(struct linux_binprm *bprm)
+{
+	pid_t old_pid, old_vpid;
+	int ret;
 
 	/* Need to fetch pid before load_binary changes it */
 	old_pid = current->pid;
@@ -1369,84 +1412,31 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 	old_vpid = task_pid_nr_ns(current, task_active_pid_ns(current->parent));
 	rcu_read_unlock();
 
-	retval = -ENOENT;
-	for (try=0; try<2; try++) {
-		read_lock(&binfmt_lock);
-		list_for_each_entry(fmt, &formats, lh) {
-			int (*fn)(struct linux_binprm *, struct pt_regs *) = fmt->load_binary;
-			if (!fn)
-				continue;
-			if (!try_module_get(fmt->module))
-				continue;
-			read_unlock(&binfmt_lock);
-			retval = fn(bprm, regs);
-			/*
-			 * Restore the depth counter to its starting value
-			 * in this call, so we don't have to rely on every
-			 * load_binary function to restore it on return.
-			 */
-			bprm->recursion_depth = depth;
-			if (retval >= 0) {
-				if (depth == 0) {
-					trace_sched_process_exec(current, old_pid, bprm);
-					ptrace_event(PTRACE_EVENT_EXEC, old_vpid);
-				}
-				put_binfmt(fmt);
-				allow_write_access(bprm->file);
-				if (bprm->file)
-					fput(bprm->file);
-				bprm->file = NULL;
-				current->did_exec = 1;
-				proc_exec_connector(current);
-				return retval;
-			}
-			read_lock(&binfmt_lock);
-			put_binfmt(fmt);
-			if (retval != -ENOEXEC || bprm->mm == NULL)
-				break;
-			if (!bprm->file) {
-				read_unlock(&binfmt_lock);
-				return retval;
-			}
-		}
-		read_unlock(&binfmt_lock);
-#ifdef CONFIG_MODULES
-		if (retval != -ENOEXEC || bprm->mm == NULL) {
-			break;
-		} else {
-#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e))
-			if (printable(bprm->buf[0]) &&
-			    printable(bprm->buf[1]) &&
-			    printable(bprm->buf[2]) &&
-			    printable(bprm->buf[3]))
-				break; /* -ENOEXEC */
-			if (try)
-				break; /* -ENOEXEC */
-			request_module("binfmt-%04x", *(unsigned short *)(&bprm->buf[2]));
-		}
-#else
-		break;
-#endif
+	ret = search_binary_handler(bprm);
+	if (ret >= 0) {
+		audit_bprm(bprm);
+		trace_sched_process_exec(current, old_pid, bprm);
+		ptrace_event(PTRACE_EVENT_EXEC, old_vpid);
+		proc_exec_connector(current);
 	}
-	return retval;
-}
 
-EXPORT_SYMBOL(search_binary_handler);
+	return ret;
+}
 
 /*
  * sys_execve() executes a new program.
  */
-static int do_execve_common(const char *filename,
+static int do_execve_common(struct filename *filename,
 				struct user_arg_ptr argv,
-				struct user_arg_ptr envp,
-				struct pt_regs *regs)
+				struct user_arg_ptr envp)
 {
 	struct linux_binprm *bprm;
 	struct file *file;
 	struct files_struct *displaced;
-	bool clear_in_exec;
 	int retval;
-	const struct cred *cred = current_cred();
+
+	if (IS_ERR(filename))
+		return PTR_ERR(filename);
 
 	/*
 	 * We move the actual failure in case of RLIMIT_NPROC excess from
@@ -1455,7 +1445,7 @@ static int do_execve_common(const char *filename,
 	 * whether NPROC limit is still exceeded.
 	 */
 	if ((current->flags & PF_NPROC_EXCEEDED) &&
-	    atomic_read(&cred->user->processes) > rlimit(RLIMIT_NPROC)) {
+	    atomic_read(&current_user()->processes) > rlimit(RLIMIT_NPROC)) {
 		retval = -EAGAIN;
 		goto out_ret;
 	}
@@ -1477,13 +1467,10 @@ static int do_execve_common(const char *filename,
 	if (retval)
 		goto out_free;
 
-	retval = check_unsafe_exec(bprm);
-	if (retval < 0)
-		goto out_free;
-	clear_in_exec = retval;
+	check_unsafe_exec(bprm);
 	current->in_execve = 1;
 
-	file = open_exec(filename);
+	file = do_open_exec(filename);
 	retval = PTR_ERR(file);
 	if (IS_ERR(file))
 		goto out_unmark;
@@ -1491,12 +1478,11 @@ static int do_execve_common(const char *filename,
 	sched_exec();
 
 	bprm->file = file;
-	bprm->filename = filename;
-	bprm->interp = filename;
+	bprm->filename = bprm->interp = filename->name;
 
 	retval = bprm_mm_init(bprm);
 	if (retval)
-		goto out_file;
+		goto out_unmark;
 
 	bprm->argc = count(argv, MAX_ARG_STRINGS);
 	if ((retval = bprm->argc) < 0)
@@ -1523,7 +1509,7 @@ static int do_execve_common(const char *filename,
 	if (retval < 0)
 		goto out;
 
-	retval = search_binary_handler(bprm,regs);
+	retval = exec_binprm(bprm);
 	if (retval < 0)
 		goto out;
 
@@ -1531,7 +1517,9 @@ static int do_execve_common(const char *filename,
 	current->fs->in_exec = 0;
 	current->in_execve = 0;
 	acct_update_integrals(current);
+	task_numa_free(current);
 	free_bprm(bprm);
+	putname(filename);
 	if (displaced)
 		put_files_struct(displaced);
 	return retval;
@@ -1542,15 +1530,8 @@ out:
 		mmput(bprm->mm);
 	}
 
-out_file:
-	if (bprm->file) {
-		allow_write_access(bprm->file);
-		fput(bprm->file);
-	}
-
 out_unmark:
-	if (clear_in_exec)
-		current->fs->in_exec = 0;
+	current->fs->in_exec = 0;
 	current->in_execve = 0;
 
 out_free:
@@ -1560,24 +1541,23 @@ out_files:
 	if (displaced)
 		reset_files_struct(displaced);
 out_ret:
+	putname(filename);
 	return retval;
 }
 
-int do_execve(const char *filename,
+int do_execve(struct filename *filename,
 	const char __user *const __user *__argv,
-	const char __user *const __user *__envp,
-	struct pt_regs *regs)
+	const char __user *const __user *__envp)
 {
 	struct user_arg_ptr argv = { .ptr.native = __argv };
 	struct user_arg_ptr envp = { .ptr.native = __envp };
-	return do_execve_common(filename, argv, envp, regs);
+	return do_execve_common(filename, argv, envp);
 }
 
 #ifdef CONFIG_COMPAT
-int compat_do_execve(const char *filename,
+static int compat_do_execve(struct filename *filename,
 	const compat_uptr_t __user *__argv,
-	const compat_uptr_t __user *__envp,
-	struct pt_regs *regs)
+	const compat_uptr_t __user *__envp)
 {
 	struct user_arg_ptr argv = {
 		.is_compat = true,
@@ -1587,7 +1567,7 @@ int compat_do_execve(const char *filename,
 		.is_compat = true,
 		.ptr.compat = __envp,
 	};
-	return do_execve_common(filename, argv, envp, regs);
+	return do_execve_common(filename, argv, envp);
 }
 #endif
 
@@ -1602,112 +1582,36 @@ void set_binfmt(struct linux_binfmt *new)
 	if (new)
 		__module_get(new->module);
 }
-
 EXPORT_SYMBOL(set_binfmt);
 
 /*
- * set_dumpable converts traditional three-value dumpable to two flags and
- * stores them into mm->flags.  It modifies lower two bits of mm->flags, but
- * these bits are not changed atomically.  So get_dumpable can observe the
- * intermediate state.  To avoid doing unexpected behavior, get get_dumpable
- * return either old dumpable or new one by paying attention to the order of
- * modifying the bits.
- *
- * dumpable |   mm->flags (binary)
- * old  new | initial interim  final
- * ---------+-----------------------
- *  0    1  |   00      01      01
- *  0    2  |   00      10(*)   11
- *  1    0  |   01      00      00
- *  1    2  |   01      11      11
- *  2    0  |   11      10(*)   00
- *  2    1  |   11      11      01
- *
- * (*) get_dumpable regards interim value of 10 as 11.
+ * set_dumpable stores three-value SUID_DUMP_* into mm->flags.
  */
 void set_dumpable(struct mm_struct *mm, int value)
 {
-	switch (value) {
-	case SUID_DUMPABLE_DISABLED:
-		clear_bit(MMF_DUMPABLE, &mm->flags);
-		smp_wmb();
-		clear_bit(MMF_DUMP_SECURELY, &mm->flags);
-		break;
-	case SUID_DUMPABLE_ENABLED:
-		set_bit(MMF_DUMPABLE, &mm->flags);
-		smp_wmb();
-		clear_bit(MMF_DUMP_SECURELY, &mm->flags);
-		break;
-	case SUID_DUMPABLE_SAFE:
-		set_bit(MMF_DUMP_SECURELY, &mm->flags);
-		smp_wmb();
-		set_bit(MMF_DUMPABLE, &mm->flags);
-		break;
-	}
-}
-
-int __get_dumpable(unsigned long mm_flags)
-{
-	int ret;
+	unsigned long old, new;
 
-	ret = mm_flags & MMF_DUMPABLE_MASK;
-	return (ret > SUID_DUMPABLE_ENABLED) ? SUID_DUMPABLE_SAFE : ret;
-}
+	if (WARN_ON((unsigned)value > SUID_DUMP_ROOT))
+		return;
 
-int get_dumpable(struct mm_struct *mm)
-{
-	return __get_dumpable(mm->flags);
+	do {
+		old = ACCESS_ONCE(mm->flags);
+		new = (old & ~MMF_DUMPABLE_MASK) | value;
+	} while (cmpxchg(&mm->flags, old, new) != old);
 }
 
-#ifdef __ARCH_WANT_SYS_EXECVE
 SYSCALL_DEFINE3(execve,
 		const char __user *, filename,
 		const char __user *const __user *, argv,
 		const char __user *const __user *, envp)
 {
-	struct filename *path = getname(filename);
-	int error = PTR_ERR(path);
-	if (!IS_ERR(path)) {
-		error = do_execve(path->name, argv, envp, current_pt_regs());
-		putname(path);
-	}
-	return error;
+	return do_execve(getname(filename), argv, envp);
 }
 #ifdef CONFIG_COMPAT
-asmlinkage long compat_sys_execve(const char __user * filename,
-	const compat_uptr_t __user * argv,
-	const compat_uptr_t __user * envp)
-{
-	struct filename *path = getname(filename);
-	int error = PTR_ERR(path);
-	if (!IS_ERR(path)) {
-		error = compat_do_execve(path->name, argv, envp,
-							current_pt_regs());
-		putname(path);
-	}
-	return error;
-}
-#endif
-#endif
-
-#ifdef __ARCH_WANT_KERNEL_EXECVE
-int kernel_execve(const char *filename,
-		  const char *const argv[],
-		  const char *const envp[])
+COMPAT_SYSCALL_DEFINE3(execve, const char __user *, filename,
+	const compat_uptr_t __user *, argv,
+	const compat_uptr_t __user *, envp)
 {
-	struct pt_regs *p = current_pt_regs();
-	int ret;
-
-	ret = do_execve(filename,
-			(const char __user *const __user *)argv,
-			(const char __user *const __user *)envp, p);
-	if (ret < 0)
-		return ret;
-
-	/*
-	 * We were successful.  We won't be returning to our caller, but
-	 * instead to user space by manipulating the kernel stack.
-	 */
-	ret_from_kernel_execve(p);
+	return compat_do_execve(getname(filename), argv, envp);
 }
 #endif