Merge commit 'v3.0.1' into android-3.0

4 files changed, 62 insertions, 3 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index f032e6e1e09a..e56fe35cef05 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -606,6 +606,7 @@ static void bdi_prune_sb(struct backing_dev_info *bdi)
 void bdi_unregister(struct backing_dev_info *bdi)
 {
 	if (bdi->dev) {
+		bdi_set_min_ratio(bdi, 0);
 		trace_writeback_bdi_unregister(bdi);
 		bdi_prune_sb(bdi);
 		del_timer_sync(&bdi->wb.wakeup_timer);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e013b8e57d25..59ac5d6de478 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1730,7 +1730,7 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
 	excess = res_counter_soft_limit_excess(&root_mem->res) >> PAGE_SHIFT;
 
 	/* If memsw_is_minimum==1, swap-out is of-no-use. */
-	if (!check_soft && root_mem->memsw_is_minimum)
+	if (!check_soft && !shrink && root_mem->memsw_is_minimum)
 		noswap = true;
 
 	while (1) {
diff --git a/mm/memory.c b/mm/memory.c
index 9b8a01d941cb..d961e1914d17 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1816,7 +1816,63 @@ next_page:
 }
 EXPORT_SYMBOL(__get_user_pages);
 
-/**
+/*
+ * fixup_user_fault() - manually resolve a user page fault
+ * @tsk:	the task_struct to use for page fault accounting, or
+ *		NULL if faults are not to be recorded.
+ * @mm:		mm_struct of target mm
+ * @address:	user address
+ * @fault_flags:flags to pass down to handle_mm_fault()
+ *
+ * This is meant to be called in the specific scenario where for locking reasons
+ * we try to access user memory in atomic context (within a pagefault_disable()
+ * section), this returns -EFAULT, and we want to resolve the user fault before
+ * trying again.
+ *
+ * Typically this is meant to be used by the futex code.
+ *
+ * The main difference with get_user_pages() is that this function will
+ * unconditionally call handle_mm_fault() which will in turn perform all the
+ * necessary SW fixup of the dirty and young bits in the PTE, while
+ * handle_mm_fault() only guarantees to update these in the struct page.
+ *
+ * This is important for some architectures where those bits also gate the
+ * access permission to the page because they are maintained in software.  On
+ * such architectures, gup() will not be enough to make a subsequent access
+ * succeed.
+ *
+ * This should be called with the mm_sem held for read.
+ */
+int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
+		     unsigned long address, unsigned int fault_flags)
+{
+	struct vm_area_struct *vma;
+	int ret;
+
+	vma = find_extend_vma(mm, address);
+	if (!vma || address < vma->vm_start)
+		return -EFAULT;
+
+	ret = handle_mm_fault(mm, vma, address, fault_flags);
+	if (ret & VM_FAULT_ERROR) {
+		if (ret & VM_FAULT_OOM)
+			return -ENOMEM;
+		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
+			return -EHWPOISON;
+		if (ret & VM_FAULT_SIGBUS)
+			return -EFAULT;
+		BUG();
+	}
+	if (tsk) {
+		if (ret & VM_FAULT_MAJOR)
+			tsk->maj_flt++;
+		else
+			tsk->min_flt++;
+	}
+	return 0;
+}
+
+/*
  * get_user_pages() - pin user pages in memory
  * @tsk:	the task_struct to use for page fault accounting, or
  *		NULL if faults are not to be recorded.
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index e4b0991ca351..8093fc766d16 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -303,7 +303,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 	do_each_thread(g, p) {
 		unsigned int points;
 
-		if (!p->mm)
+		if (p->exit_state)
 			continue;
 		if (oom_unkillable_task(p, mem, nodemask))
 			continue;
@@ -319,6 +319,8 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 		 */
 		if (test_tsk_thread_flag(p, TIF_MEMDIE))
 			return ERR_PTR(-1UL);
+		if (!p->mm)
+			continue;
 
 		if (p->flags & PF_EXITING) {
 			/*