1 files changed, 159 insertions, 39 deletions

diff --git a/fs/exec.c b/fs/exec.c
index 52a447d9b6ab..ea5f748906a8 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -42,7 +42,6 @@
 #include <linux/pid_namespace.h>
 #include <linux/module.h>
 #include <linux/namei.h>
-#include <linux/proc_fs.h>
 #include <linux/mount.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
@@ -55,6 +54,7 @@
 #include <linux/fs_struct.h>
 #include <linux/pipe_fs_i.h>
 #include <linux/oom.h>
+#include <linux/compat.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -115,13 +115,16 @@ SYSCALL_DEFINE1(uselib, const char __user *, library)
         struct file *file;
         char *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
+        };
 
         if (IS_ERR(tmp))
                 goto out;
 
-        file = do_filp_open(AT_FDCWD, tmp,
-                                O_LARGEFILE | O_RDONLY | __FMODE_EXEC, 0,
-                                MAY_READ | MAY_EXEC | MAY_OPEN);
+        file = do_filp_open(AT_FDCWD, tmp, &uselib_flags, LOOKUP_FOLLOW);
         putname(tmp);
         error = PTR_ERR(file);
         if (IS_ERR(file))
@@ -163,8 +166,13 @@ out:
 }
 
 #ifdef CONFIG_MMU
-
-void acct_arg_size(struct linux_binprm *bprm, unsigned long pages)
+/*
+ * The nascent bprm->mm is not visible until exec_mmap() but it can
+ * use a lot of memory, account these pages in current->mm temporary
+ * for oom_badness()->get_mm_rss(). Once exec succeeds or fails, we
+ * change the counter back via acct_arg_size(0).
+ */
+static void acct_arg_size(struct linux_binprm *bprm, unsigned long pages)
 {
         struct mm_struct *mm = current->mm;
         long diff = (long)(pages - bprm->vma_pages);
@@ -183,7 +191,7 @@ void acct_arg_size(struct linux_binprm *bprm, unsigned long pages)
 #endif
 }
 
-struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
+static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
                 int write)
 {
         struct page *page;
@@ -191,7 +199,7 @@ struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 
 #ifdef CONFIG_STACK_GROWSUP
         if (write) {
-                ret = expand_stack_downwards(bprm->vma, pos);
+                ret = expand_downwards(bprm->vma, pos);
                 if (ret < 0)
                         return NULL;
         }
@@ -302,11 +310,11 @@ static bool valid_arg_len(struct linux_binprm *bprm, long len)
 
 #else
 
-void acct_arg_size(struct linux_binprm *bprm, unsigned long pages)
+static inline void acct_arg_size(struct linux_binprm *bprm, unsigned long pages)
 {
 }
 
-struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
+static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
                 int write)
 {
         struct page *page;
@@ -395,22 +403,56 @@ err:
         return err;
 }
 
+struct user_arg_ptr {
+#ifdef CONFIG_COMPAT
+        bool is_compat;
+#endif
+        union {
+                const char __user *const __user *native;
+#ifdef CONFIG_COMPAT
+                compat_uptr_t __user *compat;
+#endif
+        } ptr;
+};
+
+static const char __user *get_user_arg_ptr(struct user_arg_ptr argv, int nr)
+{
+        const char __user *native;
+
+#ifdef CONFIG_COMPAT
+        if (unlikely(argv.is_compat)) {
+                compat_uptr_t compat;
+
+                if (get_user(compat, argv.ptr.compat + nr))
+                        return ERR_PTR(-EFAULT);
+
+                return compat_ptr(compat);
+        }
+#endif
+
+        if (get_user(native, argv.ptr.native + nr))
+                return ERR_PTR(-EFAULT);
+
+        return native;
+}
+
 /*
  * count() counts the number of strings in array ARGV.
  */
-static int count(const char __user * const __user * argv, int max)
+static int count(struct user_arg_ptr argv, int max)
 {
         int i = 0;
 
-        if (argv != NULL) {
+        if (argv.ptr.native != NULL) {
                 for (;;) {
-                        const char __user * p;
+                        const char __user *p = get_user_arg_ptr(argv, i);
 
-                        if (get_user(p, argv))
-                                return -EFAULT;
                         if (!p)
                                 break;
-                        argv++;
+
+                        if (IS_ERR(p))
+                                return -EFAULT;
+
                         if (i++ >= max)
                                 return -E2BIG;
 
@@ -427,7 +469,7 @@ static int count(const char __user * const __user * argv, int max)
  * processes's memory to the new process's stack.  The call to get_user_pages()
  * ensures the destination page is created and not swapped out.
  */
-static int copy_strings(int argc, const char __user *const __user *argv,
+static int copy_strings(int argc, struct user_arg_ptr argv,
                         struct linux_binprm *bprm)
 {
         struct page *kmapped_page = NULL;
@@ -440,16 +482,18 @@ static int copy_strings(int argc, const char __user *const __user *argv,
                 int len;
                 unsigned long pos;
 
-                if (get_user(str, argv+argc) ||
-                                !(len = strnlen_user(str, MAX_ARG_STRLEN))) {
-                        ret = -EFAULT;
+                ret = -EFAULT;
+                str = get_user_arg_ptr(argv, argc);
+                if (IS_ERR(str))
                         goto out;
-                }
 
-                if (!valid_arg_len(bprm, len)) {
-                        ret = -E2BIG;
+                len = strnlen_user(str, MAX_ARG_STRLEN);
+                if (!len)
+                        goto out;
+
+                ret = -E2BIG;
+                if (!valid_arg_len(bprm, len))
                         goto out;
-                }
 
                 /* We're going to work our way backwords. */
                 pos = bprm->p;
@@ -516,14 +560,19 @@ out:
 /*
  * Like copy_strings, but get argv and its values from kernel memory.
  */
-int copy_strings_kernel(int argc, const char *const *argv,
+int copy_strings_kernel(int argc, const char *const *__argv,
                         struct linux_binprm *bprm)
 {
         int r;
         mm_segment_t oldfs = get_fs();
+        struct user_arg_ptr argv = {
+                .ptr.native = (const char __user *const  __user *)__argv,
+        };
+
         set_fs(KERNEL_DS);
-        r = copy_strings(argc, (const char __user *const  __user *)argv, bprm);
+        r = copy_strings(argc, argv, bprm);
         set_fs(oldfs);
+
         return r;
 }
 EXPORT_SYMBOL(copy_strings_kernel);
@@ -550,7 +599,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
         unsigned long length = old_end - old_start;
         unsigned long new_start = old_start - shift;
         unsigned long new_end = old_end - shift;
-        struct mmu_gather *tlb;
+        struct mmu_gather tlb;
 
         BUG_ON(new_start > new_end);
 
@@ -576,12 +625,12 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
                 return -ENOMEM;
 
         lru_add_drain();
-        tlb = tlb_gather_mmu(mm, 0);
+        tlb_gather_mmu(&tlb, mm, 0);
         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,
+                free_pgd_range(&tlb, new_end, old_end, new_end,
                         vma->vm_next ? vma->vm_next->vm_start : 0);
         } else {
                 /*
@@ -590,10 +639,10 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
                  * 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,
+                free_pgd_range(&tlb, old_start, old_end, new_end,
                         vma->vm_next ? vma->vm_next->vm_start : 0);
         }
-        tlb_finish_mmu(tlb, new_end, old_end);
+        tlb_finish_mmu(&tlb, new_end, old_end);
 
         /*
          * Shrink the vma to just the new range.  Always succeeds.
@@ -721,10 +770,13 @@ struct file *open_exec(const char *name)
 {
         struct file *file;
         int err;
+        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
+        };
 
-        file = do_filp_open(AT_FDCWD, name,
-                                O_LARGEFILE | O_RDONLY | __FMODE_EXEC, 0,
-                                MAY_EXEC | MAY_OPEN);
+        file = do_filp_open(AT_FDCWD, name, &open_exec_flags, LOOKUP_FOLLOW);
         if (IS_ERR(file))
                 goto out;
 
@@ -998,6 +1050,7 @@ char *get_task_comm(char *buf, struct task_struct *tsk)
         task_unlock(tsk);
         return buf;
 }
+EXPORT_SYMBOL_GPL(get_task_comm);
 
 void set_task_comm(struct task_struct *tsk, char *buf)
 {
@@ -1373,10 +1426,10 @@ EXPORT_SYMBOL(search_binary_handler);
 /*
  * sys_execve() executes a new program.
  */
-int do_execve(const char * filename,
-        const char __user *const __user *argv,
-        const char __user *const __user *envp,
-        struct pt_regs * regs)
+static int do_execve_common(const char *filename,
+                                struct user_arg_ptr argv,
+                                struct user_arg_ptr envp,
+                                struct pt_regs *regs)
 {
         struct linux_binprm *bprm;
         struct file *file;
@@ -1483,6 +1536,34 @@ out_ret:
         return retval;
 }
 
+int do_execve(const char *filename,
+        const char __user *const __user *__argv,
+        const char __user *const __user *__envp,
+        struct pt_regs *regs)
+{
+        struct user_arg_ptr argv = { .ptr.native = __argv };
+        struct user_arg_ptr envp = { .ptr.native = __envp };
+        return do_execve_common(filename, argv, envp, regs);
+}
+
+#ifdef CONFIG_COMPAT
+int compat_do_execve(char *filename,
+        compat_uptr_t __user *__argv,
+        compat_uptr_t __user *__envp,
+        struct pt_regs *regs)
+{
+        struct user_arg_ptr argv = {
+                .is_compat = true,
+                .ptr.compat = __argv,
+        };
+        struct user_arg_ptr envp = {
+                .is_compat = true,
+                .ptr.compat = __envp,
+        };
+        return do_execve_common(filename, argv, envp, regs);
+}
+#endif
+
 void set_binfmt(struct linux_binfmt *new)
 {
         struct mm_struct *mm = current->mm;
@@ -1542,6 +1623,41 @@ expand_fail:
         return ret;
 }
 
+static int cn_print_exe_file(struct core_name *cn)
+{
+        struct file *exe_file;
+        char *pathbuf, *path, *p;
+        int ret;
+
+        exe_file = get_mm_exe_file(current->mm);
+        if (!exe_file)
+                return cn_printf(cn, "(unknown)");
+
+        pathbuf = kmalloc(PATH_MAX, GFP_TEMPORARY);
+        if (!pathbuf) {
+                ret = -ENOMEM;
+                goto put_exe_file;
+        }
+
+        path = d_path(&exe_file->f_path, pathbuf, PATH_MAX);
+        if (IS_ERR(path)) {
+                ret = PTR_ERR(path);
+                goto free_buf;
+        }
+
+        for (p = path; *p; p++)
+                if (*p == '/')
+                        *p = '!';
+
+        ret = cn_printf(cn, "%s", path);
+
+free_buf:
+        kfree(pathbuf);
+put_exe_file:
+        fput(exe_file);
+        return ret;
+}
+
 /* format_corename will inspect the pattern parameter, and output a
  * name into corename, which must have space for at least
  * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator.
@@ -1613,6 +1729,9 @@ static int format_corename(struct core_name *cn, long signr)
                         case 'e':
                                 err = cn_printf(cn, "%s", current->comm);
                                 break;
+                        case 'E':
+                                err = cn_print_exe_file(cn);
+                                break;
                         /* core limit size */
                         case 'c':
                                 err = cn_printf(cn, "%lu",
@@ -1653,6 +1772,7 @@ static int zap_process(struct task_struct *start, int exit_code)
 
         t = start;
         do {
+                task_clear_group_stop_pending(t);
                 if (t != current && t->mm) {
                         sigaddset(&t->pending.signal, SIGKILL);
                         signal_wake_up(t, 1);
@@ -1869,7 +1989,7 @@ static void wait_for_dump_helpers(struct file *file)
 
 
 /*
- * uhm_pipe_setup
+ * umh_pipe_setup
  * helper function to customize the process used
  * to collect the core in userspace.  Specifically
  * it sets up a pipe and installs it as fd 0 (stdin)