1 files changed, 72 insertions, 44 deletions

diff --git a/fs/exec.c b/fs/exec.c
index 9a1d9f0a60ab..574cf4de4ec3 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -280,10 +280,6 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
 	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
 	INIT_LIST_HEAD(&vma->anon_vma_chain);
 
-	err = security_file_mmap(NULL, 0, 0, 0, vma->vm_start, 1);
-	if (err)
-		goto err;
-
 	err = insert_vm_struct(mm, vma);
 	if (err)
 		goto err;
@@ -823,10 +819,10 @@ static int exec_mmap(struct mm_struct *mm)
 	/* Notify parent that we're no longer interested in the old VM */
 	tsk = current;
 	old_mm = current->mm;
-	sync_mm_rss(old_mm);
 	mm_release(tsk, old_mm);
 
 	if (old_mm) {
+		sync_mm_rss(old_mm);
 		/*
 		 * Make sure that if there is a core dump in progress
 		 * for the old mm, we get out and die instead of going
@@ -1024,7 +1020,7 @@ static void flush_old_files(struct files_struct * files)
 		unsigned long set, i;
 
 		j++;
-		i = j * __NFDBITS;
+		i = j * BITS_PER_LONG;
 		fdt = files_fdtable(files);
 		if (i >= fdt->max_fds)
 			break;
@@ -1139,7 +1135,7 @@ void setup_new_exec(struct linux_binprm * bprm)
 	/* This is the point of no return */
 	current->sas_ss_sp = current->sas_ss_size = 0;
 
-	if (current_euid() == current_uid() && current_egid() == current_gid())
+	if (uid_eq(current_euid(), current_uid()) && gid_eq(current_egid(), current_gid()))
 		set_dumpable(current->mm, 1);
 	else
 		set_dumpable(current->mm, suid_dumpable);
@@ -1153,8 +1149,8 @@ void setup_new_exec(struct linux_binprm * bprm)
 	current->mm->task_size = TASK_SIZE;
 
 	/* install the new credentials */
-	if (bprm->cred->uid != current_euid() ||
-	    bprm->cred->gid != current_egid()) {
+	if (!uid_eq(bprm->cred->uid, current_euid()) ||
+	    !gid_eq(bprm->cred->gid, current_egid())) {
 		current->pdeath_signal = 0;
 	} else {
 		would_dump(bprm, bprm->file);
@@ -1245,6 +1241,13 @@ static int check_unsafe_exec(struct linux_binprm *bprm)
 			bprm->unsafe |= LSM_UNSAFE_PTRACE;
 	}
 
+	/*
+	 * This isn't strictly necessary, but it makes it harder for LSMs to
+	 * mess up.
+	 */
+	if (current->no_new_privs)
+		bprm->unsafe |= LSM_UNSAFE_NO_NEW_PRIVS;
+
 	n_fs = 1;
 	spin_lock(&p->fs->lock);
 	rcu_read_lock();
@@ -1288,11 +1291,15 @@ int prepare_binprm(struct linux_binprm *bprm)
 	bprm->cred->euid = current_euid();
 	bprm->cred->egid = current_egid();
 
-	if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)) {
+	if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) &&
+	    !current->no_new_privs) {
 		/* 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? */
@@ -1302,6 +1309,8 @@ 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;
 		}
@@ -1371,7 +1380,7 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 	unsigned int depth = bprm->recursion_depth;
 	int try,retval;
 	struct linux_binfmt *fmt;
-	pid_t old_pid;
+	pid_t old_pid, old_vpid;
 
 	retval = security_bprm_check(bprm);
 	if (retval)
@@ -1382,8 +1391,9 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 		return retval;
 
 	/* Need to fetch pid before load_binary changes it */
+	old_pid = current->pid;
 	rcu_read_lock();
-	old_pid = task_pid_nr_ns(current, task_active_pid_ns(current->parent));
+	old_vpid = task_pid_nr_ns(current, task_active_pid_ns(current->parent));
 	rcu_read_unlock();
 
 	retval = -ENOENT;
@@ -1406,7 +1416,7 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 			if (retval >= 0) {
 				if (depth == 0) {
 					trace_sched_process_exec(current, old_pid, bprm);
-					ptrace_event(PTRACE_EVENT_EXEC, old_pid);
+					ptrace_event(PTRACE_EVENT_EXEC, old_vpid);
 				}
 				put_binfmt(fmt);
 				allow_write_access(bprm->file);
@@ -1929,8 +1939,21 @@ static int coredump_wait(int exit_code, struct core_state *core_state)
 		core_waiters = zap_threads(tsk, mm, core_state, exit_code);
 	up_write(&mm->mmap_sem);
 
-	if (core_waiters > 0)
+	if (core_waiters > 0) {
+		struct core_thread *ptr;
+
 		wait_for_completion(&core_state->startup);
+		/*
+		 * Wait for all the threads to become inactive, so that
+		 * all the thread context (extended register state, like
+		 * fpu etc) gets copied to the memory.
+		 */
+		ptr = core_state->dumper.next;
+		while (ptr != NULL) {
+			wait_task_inactive(ptr->task, 0);
+			ptr = ptr->next;
+		}
+	}
 
 	return core_waiters;
 }
@@ -1979,17 +2002,17 @@ static void coredump_finish(struct mm_struct *mm)
 void set_dumpable(struct mm_struct *mm, int value)
 {
 	switch (value) {
-	case 0:
+	case SUID_DUMPABLE_DISABLED:
 		clear_bit(MMF_DUMPABLE, &mm->flags);
 		smp_wmb();
 		clear_bit(MMF_DUMP_SECURELY, &mm->flags);
 		break;
-	case 1:
+	case SUID_DUMPABLE_ENABLED:
 		set_bit(MMF_DUMPABLE, &mm->flags);
 		smp_wmb();
 		clear_bit(MMF_DUMP_SECURELY, &mm->flags);
 		break;
-	case 2:
+	case SUID_DUMPABLE_SAFE:
 		set_bit(MMF_DUMP_SECURELY, &mm->flags);
 		smp_wmb();
 		set_bit(MMF_DUMPABLE, &mm->flags);
@@ -2002,7 +2025,7 @@ static int __get_dumpable(unsigned long mm_flags)
 	int ret;
 
 	ret = mm_flags & MMF_DUMPABLE_MASK;
-	return (ret >= 2) ? 2 : ret;
+	return (ret > SUID_DUMPABLE_ENABLED) ? SUID_DUMPABLE_SAFE : ret;
 }
 
 int get_dumpable(struct mm_struct *mm)
@@ -2046,25 +2069,18 @@ static void wait_for_dump_helpers(struct file *file)
  */
 static int umh_pipe_setup(struct subprocess_info *info, struct cred *new)
 {
-	struct file *rp, *wp;
+	struct file *files[2];
 	struct fdtable *fdt;
 	struct coredump_params *cp = (struct coredump_params *)info->data;
 	struct files_struct *cf = current->files;
+	int err = create_pipe_files(files, 0);
+	if (err)
+		return err;
 
-	wp = create_write_pipe(0);
-	if (IS_ERR(wp))
-		return PTR_ERR(wp);
-
-	rp = create_read_pipe(wp, 0);
-	if (IS_ERR(rp)) {
-		free_write_pipe(wp);
-		return PTR_ERR(rp);
-	}
-
-	cp->file = wp;
+	cp->file = files[1];
 
 	sys_close(0);
-	fd_install(0, rp);
+	fd_install(0, files[0]);
 	spin_lock(&cf->file_lock);
 	fdt = files_fdtable(cf);
 	__set_open_fd(0, fdt);
@@ -2088,6 +2104,7 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
 	int retval = 0;
 	int flag = 0;
 	int ispipe;
+	bool need_nonrelative = false;
 	static atomic_t core_dump_count = ATOMIC_INIT(0);
 	struct coredump_params cprm = {
 		.signr = signr,
@@ -2113,14 +2130,16 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
 	if (!cred)
 		goto fail;
 	/*
-	 *	We cannot trust fsuid as being the "true" uid of the
-	 *	process nor do we know its entire history. We only know it
-	 *	was tainted so we dump it as root in mode 2.
+	 * We cannot trust fsuid as being the "true" uid of the process
+	 * nor do we know its entire history. We only know it was tainted
+	 * so we dump it as root in mode 2, and only into a controlled
+	 * environment (pipe handler or fully qualified path).
 	 */
-	if (__get_dumpable(cprm.mm_flags) == 2) {
+	if (__get_dumpable(cprm.mm_flags) == SUID_DUMPABLE_SAFE) {
 		/* Setuid core dump mode */
 		flag = O_EXCL;		/* Stop rewrite attacks */
-		cred->fsuid = 0;	/* Dump root private */
+		cred->fsuid = GLOBAL_ROOT_UID;	/* Dump root private */
+		need_nonrelative = true;
 	}
 
 	retval = coredump_wait(exit_code, &core_state);
@@ -2148,15 +2167,16 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
 		}
 
 		if (cprm.limit == 1) {
-			/*
+			/* See umh_pipe_setup() which sets RLIMIT_CORE = 1.
+			 *
 			 * Normally core limits are irrelevant to pipes, since
 			 * we're not writing to the file system, but we use
-			 * cprm.limit of 1 here as a speacial value. Any
-			 * non-1 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 =  !1
-			 * but it runs as root, and can do lots of stupid things
+			 * cprm.limit of 1 here as a speacial value, this is a
+			 * consistent way to catch recursive crashes.
+			 * We can still crash if the core_pattern binary sets
+			 * RLIM_CORE = !1, 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
@@ -2200,6 +2220,14 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
 		if (cprm.limit < binfmt->min_coredump)
 			goto fail_unlock;
 
+		if (need_nonrelative && cn.corename[0] != '/') {
+			printk(KERN_WARNING "Pid %d(%s) can only dump core "\
+				"to fully qualified path!\n",
+				task_tgid_vnr(current), current->comm);
+			printk(KERN_WARNING "Skipping core dump\n");
+			goto fail_unlock;
+		}
+
 		cprm.file = filp_open(cn.corename,
 				 O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag,
 				 0600);
@@ -2221,7 +2249,7 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
 		 * Dont allow local users get cute and trick others to coredump
 		 * into their pre-created files.
 		 */
-		if (inode->i_uid != current_fsuid())
+		if (!uid_eq(inode->i_uid, current_fsuid()))
 			goto close_fail;
 		if (!cprm.file->f_op || !cprm.file->f_op->write)
 			goto close_fail;