1 files changed, 122 insertions, 66 deletions

diff --git a/fs/exec.c b/fs/exec.c
index fb4f3cdda78c..d49be6bc1793 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -33,7 +33,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/pagemap.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
 #include <linux/highmem.h>
 #include <linux/spinlock.h>
 #include <linux/key.h>
@@ -55,6 +55,7 @@
 #include <linux/kmod.h>
 #include <linux/fsnotify.h>
 #include <linux/fs_struct.h>
+#include <linux/pipe_fs_i.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -63,6 +64,7 @@
 
 int core_uses_pid;
 char core_pattern[CORENAME_MAX_SIZE] = "core";
+unsigned int core_pipe_limit;
 int suid_dumpable = 0;
 
 /* The maximal length of core_pattern is also specified in sysctl.c */
@@ -845,6 +847,9 @@ static int de_thread(struct task_struct *tsk)
         sig->notify_count = 0;
 
 no_thread_group:
+        if (current->mm)
+                setmax_mm_hiwater_rss(&sig->maxrss, current->mm);
+
         exit_itimers(sig);
         flush_itimer_signals();
 
@@ -923,7 +928,7 @@ void set_task_comm(struct task_struct *tsk, char *buf)
         task_lock(tsk);
         strlcpy(tsk->comm, buf, sizeof(tsk->comm));
         task_unlock(tsk);
-        perf_counter_comm(tsk);
+        perf_event_comm(tsk);
 }
 
 int flush_old_exec(struct linux_binprm * bprm)
@@ -997,7 +1002,7 @@ int flush_old_exec(struct linux_binprm * bprm)
          * security domain:
          */
         if (!get_dumpable(current->mm))
-                perf_counter_exit_task(current);
+                perf_event_exit_task(current);
 
         /* An exec changes our domain. We are no longer part of the thread
            group */
@@ -1016,6 +1021,35 @@ out:
 EXPORT_SYMBOL(flush_old_exec);
 
 /*
+ * Prepare credentials and lock ->cred_guard_mutex.
+ * install_exec_creds() commits the new creds and drops the lock.
+ * Or, if exec fails before, free_bprm() should release ->cred and
+ * and unlock.
+ */
+int prepare_bprm_creds(struct linux_binprm *bprm)
+{
+        if (mutex_lock_interruptible(&current->cred_guard_mutex))
+                return -ERESTARTNOINTR;
+
+        bprm->cred = prepare_exec_creds();
+        if (likely(bprm->cred))
+                return 0;
+
+        mutex_unlock(&current->cred_guard_mutex);
+        return -ENOMEM;
+}
+
+void free_bprm(struct linux_binprm *bprm)
+{
+        free_arg_pages(bprm);
+        if (bprm->cred) {
+                mutex_unlock(&current->cred_guard_mutex);
+                abort_creds(bprm->cred);
+        }
+        kfree(bprm);
+}
+
+/*
  * install the new credentials for this executable
  */
 void install_exec_creds(struct linux_binprm *bprm)
@@ -1024,12 +1058,13 @@ void install_exec_creds(struct linux_binprm *bprm)
 
         commit_creds(bprm->cred);
         bprm->cred = NULL;
-
-        /* cred_guard_mutex must be held at least to this point to prevent
+        /*
+         * cred_guard_mutex must be held at least to this point to prevent
          * ptrace_attach() from altering our determination of the task's
-         * credentials; any time after this it may be unlocked */
-
+         * credentials; any time after this it may be unlocked.
+         */
         security_bprm_committed_creds(bprm);
+        mutex_unlock(&current->cred_guard_mutex);
 }
 EXPORT_SYMBOL(install_exec_creds);
 
@@ -1246,14 +1281,6 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 
 EXPORT_SYMBOL(search_binary_handler);
 
-void free_bprm(struct linux_binprm *bprm)
-{
-        free_arg_pages(bprm);
-        if (bprm->cred)
-                abort_creds(bprm->cred);
-        kfree(bprm);
-}
-
 /*
  * sys_execve() executes a new program.
  */
@@ -1277,20 +1304,15 @@ int do_execve(char * filename,
         if (!bprm)
                 goto out_files;
 
-        retval = -ERESTARTNOINTR;
-        if (mutex_lock_interruptible(&current->cred_guard_mutex))
+        retval = prepare_bprm_creds(bprm);
+        if (retval)
                 goto out_free;
-        current->in_execve = 1;
-
-        retval = -ENOMEM;
-        bprm->cred = prepare_exec_creds();
-        if (!bprm->cred)
-                goto out_unlock;
 
         retval = check_unsafe_exec(bprm);
         if (retval < 0)
-                goto out_unlock;
+                goto out_free;
         clear_in_exec = retval;
+        current->in_execve = 1;
 
         file = open_exec(filename);
         retval = PTR_ERR(file);
@@ -1337,10 +1359,11 @@ int do_execve(char * filename,
         if (retval < 0)
                 goto out;
 
+        current->stack_start = current->mm->start_stack;
+
         /* execve succeeded */
         current->fs->in_exec = 0;
         current->in_execve = 0;
-        mutex_unlock(&current->cred_guard_mutex);
         acct_update_integrals(current);
         free_bprm(bprm);
         if (displaced)
@@ -1360,10 +1383,7 @@ out_file:
 out_unmark:
         if (clear_in_exec)
                 current->fs->in_exec = 0;
-
-out_unlock:
         current->in_execve = 0;
-        mutex_unlock(&current->cred_guard_mutex);
 
 out_free:
         free_bprm(bprm);
@@ -1375,18 +1395,16 @@ out_ret:
         return retval;
 }
 
-int set_binfmt(struct linux_binfmt *new)
+void set_binfmt(struct linux_binfmt *new)
 {
-        struct linux_binfmt *old = current->binfmt;
+        struct mm_struct *mm = current->mm;
 
-        if (new) {
-                if (!try_module_get(new->module))
-                        return -1;
-        }
-        current->binfmt = new;
-        if (old)
-                module_put(old->module);
-        return 0;
+        if (mm->binfmt)
+                module_put(mm->binfmt->module);
+
+        mm->binfmt = new;
+        if (new)
+                __module_get(new->module);
 }
 
 EXPORT_SYMBOL(set_binfmt);
@@ -1710,6 +1728,29 @@ int get_dumpable(struct mm_struct *mm)
         return (ret >= 2) ? 2 : ret;
 }
 
+static void wait_for_dump_helpers(struct file *file)
+{
+        struct pipe_inode_info *pipe;
+
+        pipe = file->f_path.dentry->d_inode->i_pipe;
+
+        pipe_lock(pipe);
+        pipe->readers++;
+        pipe->writers--;
+
+        while ((pipe->readers > 1) && (!signal_pending(current))) {
+                wake_up_interruptible_sync(&pipe->wait);
+                kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
+                pipe_wait(pipe);
+        }
+
+        pipe->readers--;
+        pipe->writers++;
+        pipe_unlock(pipe);
+
+}
+
+
 void do_coredump(long signr, int exit_code, struct pt_regs *regs)
 {
         struct core_state core_state;
@@ -1726,11 +1767,12 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
         unsigned long core_limit = current->signal->rlim[RLIMIT_CORE].rlim_cur;
         char **helper_argv = NULL;
         int helper_argc = 0;
-        char *delimit;
+        int dump_count = 0;
+        static atomic_t core_dump_count = ATOMIC_INIT(0);
 
         audit_core_dumps(signr);
 
-        binfmt = current->binfmt;
+        binfmt = mm->binfmt;
         if (!binfmt || !binfmt->core_dump)
                 goto fail;
 
@@ -1781,54 +1823,63 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
         lock_kernel();
         ispipe = format_corename(corename, signr);
         unlock_kernel();
-        /*
-         * Don't bother to check the RLIMIT_CORE value if core_pattern points
-         * to a pipe.  Since we're not writing directly to the filesystem
-         * RLIMIT_CORE doesn't really apply, as no actual core file will be
-         * created unless the pipe reader choses to write out the core file
-         * at which point file size limits and permissions will be imposed
-         * as it does with any other process
-         */
+
         if ((!ispipe) && (core_limit < binfmt->min_coredump))
                 goto fail_unlock;
 
         if (ispipe) {
+                if (core_limit == 0) {
+                        /*
+                         * Normally core limits are irrelevant to pipes, since
+                         * we're not writing to the file system, but we use
+                         * core_limit of 0 here as a speacial value. Any
+                         * non-zero 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 =  !0
+                         * 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
+                         * core_pattern process dies.
+                         */
+                        printk(KERN_WARNING
+                                "Process %d(%s) has RLIMIT_CORE set to 0\n",
+                                task_tgid_vnr(current), current->comm);
+                        printk(KERN_WARNING "Aborting core\n");
+                        goto fail_unlock;
+                }
+
+                dump_count = atomic_inc_return(&core_dump_count);
+                if (core_pipe_limit && (core_pipe_limit < dump_count)) {
+                        printk(KERN_WARNING "Pid %d(%s) over core_pipe_limit\n",
+                               task_tgid_vnr(current), current->comm);
+                        printk(KERN_WARNING "Skipping core dump\n");
+                        goto fail_dropcount;
+                }
+
                 helper_argv = argv_split(GFP_KERNEL, corename+1, &helper_argc);
                 if (!helper_argv) {
                         printk(KERN_WARNING "%s failed to allocate memory\n",
                                __func__);
-                        goto fail_unlock;
-                }
-                /* Terminate the string before the first option */
-                delimit = strchr(corename, ' ');
-                if (delimit)
-                        *delimit = '\0';
-                delimit = strrchr(helper_argv[0], '/');
-                if (delimit)
-                        delimit++;
-                else
-                        delimit = helper_argv[0];
-                if (!strcmp(delimit, current->comm)) {
-                        printk(KERN_NOTICE "Recursive core dump detected, "
-                                        "aborting\n");
-                        goto fail_unlock;
+                        goto fail_dropcount;
                 }
 
                 core_limit = RLIM_INFINITY;
 
                 /* SIGPIPE can happen, but it's just never processed */
-                if (call_usermodehelper_pipe(corename+1, helper_argv, NULL,
+                if (call_usermodehelper_pipe(helper_argv[0], helper_argv, NULL,
                                 &file)) {
                         printk(KERN_INFO "Core dump to %s pipe failed\n",
                                corename);
-                        goto fail_unlock;
+                        goto fail_dropcount;
                 }
         } else
                 file = filp_open(corename,
                                  O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag,
                                  0600);
         if (IS_ERR(file))
-                goto fail_unlock;
+                goto fail_dropcount;
         inode = file->f_path.dentry->d_inode;
         if (inode->i_nlink > 1)
                 goto close_fail;        /* multiple links - don't dump */
@@ -1857,7 +1908,12 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
         if (retval)
                 current->signal->group_exit_code |= 0x80;
 close_fail:
+        if (ispipe && core_pipe_limit)
+                wait_for_dump_helpers(file);
         filp_close(file, NULL);
+fail_dropcount:
+        if (dump_count)
+                atomic_dec(&core_dump_count);
 fail_unlock:
         if (helper_argv)
                 argv_free(helper_argv);