Merge commit 'v2.6.34-rc7' into perf/nmi

Merge reason: catch up with latest softlockup detector changes.

1 files changed, 70 insertions, 34 deletions

diff --git a/fs/exec.c b/fs/exec.c
index 632b02e34ec7..49cdaa19e5b9 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -195,7 +195,7 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 		 *    to work from.
 		 */
 		rlim = current->signal->rlim;
-		if (size > rlim[RLIMIT_STACK].rlim_cur / 4) {
+		if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4) {
 			put_page(page);
 			return NULL;
 		}
@@ -246,6 +246,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
 	vma->vm_start = vma->vm_end - PAGE_SIZE;
 	vma->vm_flags = VM_STACK_FLAGS;
 	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+	INIT_LIST_HEAD(&vma->anon_vma_chain);
 	err = insert_vm_struct(mm, vma);
 	if (err)
 		goto err;
@@ -516,7 +517,8 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
 	/*
 	 * cover the whole range: [new_start, old_end)
 	 */
-	vma_adjust(vma, new_start, old_end, vma->vm_pgoff, NULL);
+	if (vma_adjust(vma, new_start, old_end, vma->vm_pgoff, NULL))
+		return -ENOMEM;
 
 	/*
 	 * move the page tables downwards, on failure we rely on
@@ -547,15 +549,13 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
 	tlb_finish_mmu(tlb, new_end, old_end);
 
 	/*
-	 * shrink the vma to just the new range.
+	 * Shrink the vma to just the new range.  Always succeeds.
 	 */
 	vma_adjust(vma, new_start, new_end, vma->vm_pgoff, NULL);
 
 	return 0;
 }
 
-#define EXTRA_STACK_VM_PAGES	20	/* random */
-
 /*
  * Finalizes the stack vm_area_struct. The flags and permissions are updated,
  * the stack is optionally relocated, and some extra space is added.
@@ -571,10 +571,13 @@ int setup_arg_pages(struct linux_binprm *bprm,
 	struct vm_area_struct *prev = NULL;
 	unsigned long vm_flags;
 	unsigned long stack_base;
+	unsigned long stack_size;
+	unsigned long stack_expand;
+	unsigned long rlim_stack;
 
 #ifdef CONFIG_STACK_GROWSUP
 	/* Limit stack size to 1GB */
-	stack_base = current->signal->rlim[RLIMIT_STACK].rlim_max;
+	stack_base = rlimit_max(RLIMIT_STACK);
 	if (stack_base > (1 << 30))
 		stack_base = 1 << 30;
 
@@ -627,10 +630,23 @@ int setup_arg_pages(struct linux_binprm *bprm,
 			goto out_unlock;
 	}
 
+	stack_expand = 131072UL; /* randomly 32*4k (or 2*64k) pages */
+	stack_size = vma->vm_end - vma->vm_start;
+	/*
+	 * Align this down to a page boundary as expand_stack
+	 * will align it up.
+	 */
+	rlim_stack = rlimit(RLIMIT_STACK) & PAGE_MASK;
 #ifdef CONFIG_STACK_GROWSUP
-	stack_base = vma->vm_end + EXTRA_STACK_VM_PAGES * PAGE_SIZE;
+	if (stack_size + stack_expand > rlim_stack)
+		stack_base = vma->vm_start + rlim_stack;
+	else
+		stack_base = vma->vm_end + stack_expand;
 #else
-	stack_base = vma->vm_start - EXTRA_STACK_VM_PAGES * PAGE_SIZE;
+	if (stack_size + stack_expand > rlim_stack)
+		stack_base = vma->vm_end - rlim_stack;
+	else
+		stack_base = vma->vm_start - stack_expand;
 #endif
 	ret = expand_stack(vma, stack_base);
 	if (ret)
@@ -702,6 +718,7 @@ 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(tsk, old_mm);
 	mm_release(tsk, old_mm);
 
 	if (old_mm) {
@@ -941,9 +958,7 @@ void set_task_comm(struct task_struct *tsk, char *buf)
 
 int flush_old_exec(struct linux_binprm * bprm)
 {
-	char * name;
-	int i, ch, retval;
-	char tcomm[sizeof(current->comm)];
+	int retval;
 
 	/*
 	 * Make sure we have a private signal table and that
@@ -964,6 +979,25 @@ int flush_old_exec(struct linux_binprm * bprm)
 
 	bprm->mm = NULL;		/* We're using it now */
 
+	current->flags &= ~PF_RANDOMIZE;
+	flush_thread();
+	current->personality &= ~bprm->per_clear;
+
+	return 0;
+
+out:
+	return retval;
+}
+EXPORT_SYMBOL(flush_old_exec);
+
+void setup_new_exec(struct linux_binprm * bprm)
+{
+	int i, ch;
+	char * name;
+	char tcomm[sizeof(current->comm)];
+
+	arch_pick_mmap_layout(current->mm);
+
 	/* This is the point of no return */
 	current->sas_ss_sp = current->sas_ss_size = 0;
 
@@ -985,9 +1019,6 @@ int flush_old_exec(struct linux_binprm * bprm)
 	tcomm[i] = '\0';
 	set_task_comm(current, tcomm);
 
-	current->flags &= ~PF_RANDOMIZE;
-	flush_thread();
-
 	/* Set the new mm task size. We have to do that late because it may
 	 * depend on TIF_32BIT which is only updated in flush_thread() on
 	 * some architectures like powerpc
@@ -1003,8 +1034,6 @@ int flush_old_exec(struct linux_binprm * bprm)
 		set_dumpable(current->mm, suid_dumpable);
 	}
 
-	current->personality &= ~bprm->per_clear;
-
 	/*
 	 * Flush performance counters when crossing a
 	 * security domain:
@@ -1019,14 +1048,8 @@ int flush_old_exec(struct linux_binprm * bprm)
 			
 	flush_signal_handlers(current, 0);
 	flush_old_files(current->files);
-
-	return 0;
-
-out:
-	return retval;
 }
-
-EXPORT_SYMBOL(flush_old_exec);
+EXPORT_SYMBOL(setup_new_exec);
 
 /*
  * Prepare credentials and lock ->cred_guard_mutex.
@@ -1510,7 +1533,7 @@ static int format_corename(char *corename, long signr)
 			/* core limit size */
 			case 'c':
 				rc = snprintf(out_ptr, out_end - out_ptr,
-					      "%lu", current->signal->rlim[RLIMIT_CORE].rlim_cur);
+					      "%lu", rlimit(RLIMIT_CORE));
 				if (rc > out_end - out_ptr)
 					goto out;
 				out_ptr += rc;
@@ -1538,12 +1561,13 @@ out:
 	return ispipe;
 }
 
-static int zap_process(struct task_struct *start)
+static int zap_process(struct task_struct *start, int exit_code)
 {
 	struct task_struct *t;
 	int nr = 0;
 
 	start->signal->flags = SIGNAL_GROUP_EXIT;
+	start->signal->group_exit_code = exit_code;
 	start->signal->group_stop_count = 0;
 
 	t = start;
@@ -1568,8 +1592,7 @@ static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
 	spin_lock_irq(&tsk->sighand->siglock);
 	if (!signal_group_exit(tsk->signal)) {
 		mm->core_state = core_state;
-		tsk->signal->group_exit_code = exit_code;
-		nr = zap_process(tsk);
+		nr = zap_process(tsk, exit_code);
 	}
 	spin_unlock_irq(&tsk->sighand->siglock);
 	if (unlikely(nr < 0))
@@ -1618,7 +1641,7 @@ static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
 			if (p->mm) {
 				if (unlikely(p->mm == mm)) {
 					lock_task_sighand(p, &flags);
-					nr += zap_process(p);
+					nr += zap_process(p, exit_code);
 					unlock_task_sighand(p, &flags);
 				}
 				break;
@@ -1725,14 +1748,19 @@ void set_dumpable(struct mm_struct *mm, int value)
 	}
 }
 
-int get_dumpable(struct mm_struct *mm)
+static int __get_dumpable(unsigned long mm_flags)
 {
 	int ret;
 
-	ret = mm->flags & 0x3;
+	ret = mm_flags & MMF_DUMPABLE_MASK;
 	return (ret >= 2) ? 2 : ret;
 }
 
+int get_dumpable(struct mm_struct *mm)
+{
+	return __get_dumpable(mm->flags);
+}
+
 static void wait_for_dump_helpers(struct file *file)
 {
 	struct pipe_inode_info *pipe;
@@ -1775,7 +1803,13 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
 	struct coredump_params cprm = {
 		.signr = signr,
 		.regs = regs,
-		.limit = current->signal->rlim[RLIMIT_CORE].rlim_cur,
+		.limit = rlimit(RLIMIT_CORE),
+		/*
+		 * We must use the same mm->flags while dumping core to avoid
+		 * inconsistency of bit flags, since this flag is not protected
+		 * by any locks.
+		 */
+		.mm_flags = mm->flags,
 	};
 
 	audit_core_dumps(signr);
@@ -1794,7 +1828,7 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
 	/*
 	 * If another thread got here first, or we are not dumpable, bail out.
 	 */
-	if (mm->core_state || !get_dumpable(mm)) {
+	if (mm->core_state || !__get_dumpable(cprm.mm_flags)) {
 		up_write(&mm->mmap_sem);
 		put_cred(cred);
 		goto fail;
@@ -1805,7 +1839,8 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
 	 *	process nor do we know its entire history. We only know it
 	 *	was tainted so we dump it as root in mode 2.
 	 */
-	if (get_dumpable(mm) == 2) {	/* Setuid core dump mode */
+	if (__get_dumpable(cprm.mm_flags) == 2) {
+		/* Setuid core dump mode */
 		flag = O_EXCL;		/* Stop rewrite attacks */
 		cred->fsuid = 0;	/* Dump root private */
 	}
@@ -1901,8 +1936,9 @@ 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:
+	 * Note, this is not relevant for pipes
 	 */
-	if (inode->i_uid != current_fsuid())
+	if (!ispipe && (inode->i_uid != current_fsuid()))
 		goto close_fail;
 	if (!cprm.file->f_op)
 		goto close_fail;