1 files changed, 98 insertions, 15 deletions

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index eac0ba56149..2b43ba051ac 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -53,6 +53,7 @@
 #include <linux/hugetlb.h>
 #include <linux/memory_hotplug.h>
 #include <linux/mm_inline.h>
+#include <linux/kfifo.h>
 #include "internal.h"
 
 int sysctl_memory_failure_early_kill __read_mostly = 0;
@@ -391,10 +392,11 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 	struct task_struct *tsk;
 	struct anon_vma *av;
 
-	read_lock(&tasklist_lock);
 	av = page_lock_anon_vma(page);
 	if (av == NULL)	/* Not actually mapped anymore */
-		goto out;
+		return;
+
+	read_lock(&tasklist_lock);
 	for_each_process (tsk) {
 		struct anon_vma_chain *vmac;
 
@@ -408,9 +410,8 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 				add_to_kill(tsk, page, vma, to_kill, tkc);
 		}
 	}
-	page_unlock_anon_vma(av);
-out:
 	read_unlock(&tasklist_lock);
+	page_unlock_anon_vma(av);
 }
 
 /*
@@ -424,17 +425,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 	struct prio_tree_iter iter;
 	struct address_space *mapping = page->mapping;
 
-	/*
-	 * A note on the locking order between the two locks.
-	 * We don't rely on this particular order.
-	 * If you have some other code that needs a different order
-	 * feel free to switch them around. Or add a reverse link
-	 * from mm_struct to task_struct, then this could be all
-	 * done without taking tasklist_lock and looping over all tasks.
-	 */
-
-	read_lock(&tasklist_lock);
 	mutex_lock(&mapping->i_mmap_mutex);
+	read_lock(&tasklist_lock);
 	for_each_process(tsk) {
 		pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
 
@@ -454,8 +446,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 				add_to_kill(tsk, page, vma, to_kill, tkc);
 		}
 	}
-	mutex_unlock(&mapping->i_mmap_mutex);
 	read_unlock(&tasklist_lock);
+	mutex_unlock(&mapping->i_mmap_mutex);
 }
 
 /*
@@ -1187,6 +1179,97 @@ void memory_failure(unsigned long pfn, int trapno)
 	__memory_failure(pfn, trapno, 0);
 }
 
+#define MEMORY_FAILURE_FIFO_ORDER	4
+#define MEMORY_FAILURE_FIFO_SIZE	(1 << MEMORY_FAILURE_FIFO_ORDER)
+
+struct memory_failure_entry {
+	unsigned long pfn;
+	int trapno;
+	int flags;
+};
+
+struct memory_failure_cpu {
+	DECLARE_KFIFO(fifo, struct memory_failure_entry,
+		      MEMORY_FAILURE_FIFO_SIZE);
+	spinlock_t lock;
+	struct work_struct work;
+};
+
+static DEFINE_PER_CPU(struct memory_failure_cpu, memory_failure_cpu);
+
+/**
+ * memory_failure_queue - Schedule handling memory failure of a page.
+ * @pfn: Page Number of the corrupted page
+ * @trapno: Trap number reported in the signal to user space.
+ * @flags: Flags for memory failure handling
+ *
+ * This function is called by the low level hardware error handler
+ * when it detects hardware memory corruption of a page. It schedules
+ * the recovering of error page, including dropping pages, killing
+ * processes etc.
+ *
+ * The function is primarily of use for corruptions that
+ * happen outside the current execution context (e.g. when
+ * detected by a background scrubber)
+ *
+ * Can run in IRQ context.
+ */
+void memory_failure_queue(unsigned long pfn, int trapno, int flags)
+{
+	struct memory_failure_cpu *mf_cpu;
+	unsigned long proc_flags;
+	struct memory_failure_entry entry = {
+		.pfn =		pfn,
+		.trapno =	trapno,
+		.flags =	flags,
+	};
+
+	mf_cpu = &get_cpu_var(memory_failure_cpu);
+	spin_lock_irqsave(&mf_cpu->lock, proc_flags);
+	if (kfifo_put(&mf_cpu->fifo, &entry))
+		schedule_work_on(smp_processor_id(), &mf_cpu->work);
+	else
+		pr_err("Memory failure: buffer overflow when queuing memory failure at 0x%#lx\n",
+		       pfn);
+	spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
+	put_cpu_var(memory_failure_cpu);
+}
+EXPORT_SYMBOL_GPL(memory_failure_queue);
+
+static void memory_failure_work_func(struct work_struct *work)
+{
+	struct memory_failure_cpu *mf_cpu;
+	struct memory_failure_entry entry = { 0, };
+	unsigned long proc_flags;
+	int gotten;
+
+	mf_cpu = &__get_cpu_var(memory_failure_cpu);
+	for (;;) {
+		spin_lock_irqsave(&mf_cpu->lock, proc_flags);
+		gotten = kfifo_get(&mf_cpu->fifo, &entry);
+		spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
+		if (!gotten)
+			break;
+		__memory_failure(entry.pfn, entry.trapno, entry.flags);
+	}
+}
+
+static int __init memory_failure_init(void)
+{
+	struct memory_failure_cpu *mf_cpu;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		mf_cpu = &per_cpu(memory_failure_cpu, cpu);
+		spin_lock_init(&mf_cpu->lock);
+		INIT_KFIFO(mf_cpu->fifo);
+		INIT_WORK(&mf_cpu->work, memory_failure_work_func);
+	}
+
+	return 0;
+}
+core_initcall(memory_failure_init);
+
 /**
  * unpoison_memory - Unpoison a previously poisoned page
  * @pfn: Page number of the to be unpoisoned page