Btrfs: fix deadlock on page lock when doing auto-defragment

[linux-2.6.git] / fs / exec.c

diff --git a/fs/exec.c b/fs/exec.c
index 842d5700c15595df6de6508a91a1927fdb462304..36254645b7cc4d81f7c73b2940767fe06de1642c 100644 (file)
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -181,14 +181,7 @@ static void acct_arg_size(struct linux_binprm *bprm, unsigned long pages)
                return;
 
        bprm->vma_pages = pages;
-
-#ifdef SPLIT_RSS_COUNTING
-       add_mm_counter(mm, MM_ANONPAGES, diff);
-#else
-       spin_lock(&mm->page_table_lock);
        add_mm_counter(mm, MM_ANONPAGES, diff);
-       spin_unlock(&mm->page_table_lock);
-#endif
 }
 
 static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
@@ -277,7 +270,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
         * use STACK_TOP because that can depend on attributes which aren't
         * configured yet.
         */
-       BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP);
+       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;
@@ -848,10 +841,6 @@ static int exec_mmap(struct mm_struct *mm)
        tsk->mm = mm;
        tsk->active_mm = mm;
        activate_mm(active_mm, mm);
-       if (old_mm && tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
-               atomic_dec(&old_mm->oom_disable_count);
-               atomic_inc(&tsk->mm->oom_disable_count);
-       }
        task_unlock(tsk);
        arch_pick_mmap_layout(mm);
        if (old_mm) {
@@ -1430,9 +1419,9 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
                        }
                }
                read_unlock(&binfmt_lock);
+#ifdef CONFIG_MODULES
                if (retval != -ENOEXEC || bprm->mm == NULL) {
                        break;
-#ifdef CONFIG_MODULES
                } else {
 #define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e))
                        if (printable(bprm->buf[0]) &&
@@ -1440,9 +1429,13 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
                            printable(bprm->buf[2]) &&
                            printable(bprm->buf[3]))
                                break; /* -ENOEXEC */
+                       if (try)
+                               break; /* -ENOEXEC */
                        request_module("binfmt-%04x", *(unsigned short *)(&bprm->buf[2]));
-#endif
                }
+#else
+               break;
+#endif
        }
        return retval;
 }
@@ -1462,6 +1455,23 @@ static int do_execve_common(const char *filename,
        struct files_struct *displaced;
        bool clear_in_exec;
        int retval;
+       const struct cred *cred = current_cred();
+
+       /*
+        * We move the actual failure in case of RLIMIT_NPROC excess from
+        * set*uid() to execve() because too many poorly written programs
+        * don't check setuid() return code.  Here we additionally recheck
+        * whether NPROC limit is still exceeded.
+        */
+       if ((current->flags & PF_NPROC_EXCEEDED) &&
+           atomic_read(&cred->user->processes) > rlimit(RLIMIT_NPROC)) {
+               retval = -EAGAIN;
+               goto out_ret;
+       }
+
+       /* We're below the limit (still or again), so we don't want to make
+        * further execve() calls fail. */
+       current->flags &= ~PF_NPROC_EXCEEDED;
 
        retval = unshare_files(&displaced);
        if (retval)
@@ -1649,15 +1659,26 @@ expand_fail:
        return ret;
 }
 
+static void cn_escape(char *str)
+{
+       for (; *str; str++)
+               if (*str == '/')
+                       *str = '!';
+}
+
 static int cn_print_exe_file(struct core_name *cn)
 {
        struct file *exe_file;
-       char *pathbuf, *path, *p;
+       char *pathbuf, *path;
        int ret;
 
        exe_file = get_mm_exe_file(current->mm);
-       if (!exe_file)
-               return cn_printf(cn, "(unknown)");
+       if (!exe_file) {
+               char *commstart = cn->corename + cn->used;
+               ret = cn_printf(cn, "%s (path unknown)", current->comm);
+               cn_escape(commstart);
+               return ret;
+       }
 
        pathbuf = kmalloc(PATH_MAX, GFP_TEMPORARY);
        if (!pathbuf) {
@@ -1671,9 +1692,7 @@ static int cn_print_exe_file(struct core_name *cn)
                goto free_buf;
        }
 
-       for (p = path; *p; p++)
-               if (*p == '/')
-                       *p = '!';
+       cn_escape(path);
 
        ret = cn_printf(cn, "%s", path);
 
@@ -1745,16 +1764,22 @@ static int format_corename(struct core_name *cn, long signr)
                                break;
                        }
                        /* hostname */
-                       case 'h':
+                       case 'h': {
+                               char *namestart = cn->corename + cn->used;
                                down_read(&uts_sem);
                                err = cn_printf(cn, "%s",
                                              utsname()->nodename);
                                up_read(&uts_sem);
+                               cn_escape(namestart);
                                break;
+                       }
                        /* executable */
-                       case 'e':
+                       case 'e': {
+                               char *commstart = cn->corename + cn->used;
                                err = cn_printf(cn, "%s", current->comm);
+                               cn_escape(commstart);
                                break;
+                       }
                        case 'E':
                                err = cn_print_exe_file(cn);
                                break;
@@ -2118,16 +2143,16 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
 
        ispipe = format_corename(&cn, signr);
 
-       if (ispipe == -ENOMEM) {
-               printk(KERN_WARNING "format_corename failed\n");
-               printk(KERN_WARNING "Aborting core\n");
-               goto fail_corename;
-       }
-
        if (ispipe) {
                int dump_count;
                char **helper_argv;
 
+               if (ispipe < 0) {
+                       printk(KERN_WARNING "format_corename failed\n");
+                       printk(KERN_WARNING "Aborting core\n");
+                       goto fail_corename;
+               }
+
                if (cprm.limit == 1) {
                        /*
                         * Normally core limits are irrelevant to pipes, since