KVM: arm64: vgic-v3: Log which GICv3 system registers are trapped

[mirror_ubuntu-zesty-kernel.git] / fs / exec.c

diff --git a/fs/exec.c b/fs/exec.c
index 923c57d96899f821f65a68359e8657c576691fdf..8cf76e2a0b83e2777f01f51a0a89efd68e4b7127 100644 (file)
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -19,7 +19,7 @@
  * current->executable is only used by the procfs.  This allows a dispatch
  * table to check for several different types  of binary formats.  We keep
  * trying until we recognize the file or we run out of supported binary
- * formats. 
+ * formats.
  */
 
 #include <linux/slab.h>
@@ -58,7 +58,9 @@
 #include <linux/compat.h>
 #include <linux/vmalloc.h>
 
-#include <asm/uaccess.h>
+#include <trace/events/fs.h>
+
+#include <linux/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/tlb.h>
 
@@ -104,6 +106,14 @@ bool path_noexec(const struct path *path)
        return (path->mnt->mnt_flags & MNT_NOEXEC) ||
               (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC);
 }
+EXPORT_SYMBOL_GPL(path_noexec);
+
+bool path_nosuid(const struct path *path)
+{
+       return !mnt_may_suid(path->mnt) ||
+              (path->mnt->mnt_sb->s_iflags & SB_I_NOSUID);
+}
+EXPORT_SYMBOL(path_nosuid);
 
 #ifdef CONFIG_USELIB
 /*
@@ -209,14 +219,32 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
         * doing the exec and bprm->mm is the new process's mm.
         */
        ret = get_user_pages_remote(current, bprm->mm, pos, 1, gup_flags,
-                       &page, NULL);
+                       &page, NULL, NULL);
        if (ret <= 0)
                return NULL;
 
        if (write) {
                unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start;
+               unsigned long ptr_size;
                struct rlimit *rlim;
 
+               /*
+                * Since the stack will hold pointers to the strings, we
+                * must account for them as well.
+                *
+                * The size calculation is the entire vma while each arg page is
+                * built, so each time we get here it's calculating how far it
+                * is currently (rather than each call being just the newly
+                * added size from the arg page).  As a result, we need to
+                * always add the entire size of the pointers, so that on the
+                * last call to get_arg_page() we'll actually have the entire
+                * correct size.
+                */
+               ptr_size = (bprm->argc + bprm->envc) * sizeof(void *);
+               if (ptr_size > ULONG_MAX - size)
+                       goto fail;
+               size += ptr_size;
+
                acct_arg_size(bprm, size / PAGE_SIZE);
 
                /*
@@ -234,13 +262,15 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
                 *    to work from.
                 */
                rlim = current->signal->rlim;
-               if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4) {
-                       put_page(page);
-                       return NULL;
-               }
+               if (size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4)
+                       goto fail;
        }
 
        return page;
+
+fail:
+       put_page(page);
+       return NULL;
 }
 
 static void put_arg_page(struct page *page)
@@ -838,6 +868,8 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags)
        if (name->name[0] != '\0')
                fsnotify_open(file);
 
+       trace_open_exec(name->name);
+
 out:
        return file;
 
@@ -1268,6 +1300,13 @@ int flush_old_exec(struct linux_binprm * bprm)
        flush_thread();
        current->personality &= ~bprm->per_clear;
 
+       /*
+        * We have to apply CLOEXEC before we change whether the process is
+        * dumpable (in setup_new_exec) to avoid a race with a process in userspace
+        * trying to access the should-be-closed file descriptors of a process
+        * undergoing exec(2).
+        */
+       do_close_on_exec(current->files);
        return 0;
 
 out:
@@ -1277,8 +1316,22 @@ EXPORT_SYMBOL(flush_old_exec);
 
 void would_dump(struct linux_binprm *bprm, struct file *file)
 {
-       if (inode_permission(file_inode(file), MAY_READ) < 0)
+       struct inode *inode = file_inode(file);
+       if (inode_permission(inode, MAY_READ) < 0) {
+               struct user_namespace *old, *user_ns;
                bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP;
+
+               /* Ensure mm->user_ns contains the executable */
+               user_ns = old = bprm->mm->user_ns;
+               while ((user_ns != &init_user_ns) &&
+                      !privileged_wrt_inode_uidgid(user_ns, inode))
+                       user_ns = user_ns->parent;
+
+               if (old != user_ns) {
+                       bprm->mm->user_ns = get_user_ns(user_ns);
+                       put_user_ns(old);
+               }
+       }
 }
 EXPORT_SYMBOL(would_dump);
 
@@ -1308,7 +1361,6 @@ void setup_new_exec(struct linux_binprm * bprm)
            !gid_eq(bprm->cred->gid, current_egid())) {
                current->pdeath_signal = 0;
        } else {
-               would_dump(bprm, bprm->file);
                if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP)
                        set_dumpable(current->mm, suid_dumpable);
        }
@@ -1317,7 +1369,6 @@ void setup_new_exec(struct linux_binprm * bprm)
           group */
        current->self_exec_id++;
        flush_signal_handlers(current, 0);
-       do_close_on_exec(current->files);
 }
 EXPORT_SYMBOL(setup_new_exec);
 
@@ -1406,9 +1457,10 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
 {
        struct task_struct *p = current, *t;
        unsigned n_fs;
+       bool fs_recheck;
 
        if (p->ptrace) {
-               if (p->ptrace & PT_PTRACE_CAP)
+               if (ptracer_capable(p, current_user_ns()))
                        bprm->unsafe |= LSM_UNSAFE_PTRACE_CAP;
                else
                        bprm->unsafe |= LSM_UNSAFE_PTRACE;
@@ -1421,6 +1473,8 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
        if (task_no_new_privs(current))
                bprm->unsafe |= LSM_UNSAFE_NO_NEW_PRIVS;
 
+recheck:
+       fs_recheck = false;
        t = p;
        n_fs = 1;
        spin_lock(&p->fs->lock);
@@ -1428,12 +1482,18 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
        while_each_thread(p, t) {
                if (t->fs == p->fs)
                        n_fs++;
+               if (t->flags & (PF_EXITING | PF_FORKNOEXEC))
+                       fs_recheck  = true;
        }
        rcu_read_unlock();
 
-       if (p->fs->users > n_fs)
+       if (p->fs->users > n_fs) {
+               if (fs_recheck) {
+                       spin_unlock(&p->fs->lock);
+                       goto recheck;
+               }
                bprm->unsafe |= LSM_UNSAFE_SHARE;
-       else
+       } else
                p->fs->in_exec = 1;
        spin_unlock(&p->fs->lock);
 }
@@ -1454,7 +1514,7 @@ static void bprm_fill_uid(struct linux_binprm *bprm)
        bprm->cred->euid = current_euid();
        bprm->cred->egid = current_egid();
 
-       if (!mnt_may_suid(bprm->file->f_path.mnt))
+       if (path_nosuid(&bprm->file->f_path))
                return;
 
        if (task_no_new_privs(current))
@@ -1743,6 +1803,8 @@ static int do_execveat_common(int fd, struct filename *filename,
        if (retval < 0)
                goto out;
 
+       would_dump(bprm, bprm->file);
+
        retval = exec_binprm(bprm);
        if (retval < 0)
                goto out;