3 files changed, 32 insertions, 3 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index e4112aad2964..c2182b53dace 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -51,6 +51,7 @@ struct sched_param {
 #include <linux/cred.h>
 #include <linux/llist.h>
 #include <linux/uidgid.h>
+#include <linux/gfp.h>
 
 #include <asm/processor.h>
 
@@ -1791,6 +1792,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #define PF_FROZEN       0x00010000      /* frozen for system suspend */
 #define PF_FSTRANS      0x00020000      /* inside a filesystem transaction */
 #define PF_KSWAPD       0x00040000      /* I am kswapd */
+#define PF_MEMALLOC_NOIO 0x00080000     /* Allocating memory without IO involved */
 #define PF_LESS_THROTTLE 0x00100000     /* Throttle me less: I clean memory */
 #define PF_KTHREAD      0x00200000      /* I am a kernel thread */
 #define PF_RANDOMIZE    0x00400000      /* randomize virtual address space */
@@ -1828,6 +1830,26 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
 #define used_math() tsk_used_math(current)
 
+/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags */
+static inline gfp_t memalloc_noio_flags(gfp_t flags)
+{
+        if (unlikely(current->flags & PF_MEMALLOC_NOIO))
+                flags &= ~__GFP_IO;
+        return flags;
+}
+
+static inline unsigned int memalloc_noio_save(void)
+{
+        unsigned int flags = current->flags & PF_MEMALLOC_NOIO;
+        current->flags |= PF_MEMALLOC_NOIO;
+        return flags;
+}
+
+static inline void memalloc_noio_restore(unsigned int flags)
+{
+        current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags;
+}
+
 /*
  * task->jobctl flags
  */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e3fb290194c0..3ede25e6686e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2624,10 +2624,17 @@ retry_cpuset:
         page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
                         zonelist, high_zoneidx, alloc_flags,
                         preferred_zone, migratetype);
-        if (unlikely(!page))
+        if (unlikely(!page)) {
+                /*
+                 * Runtime PM, block IO and its error handling path
+                 * can deadlock because I/O on the device might not
+                 * complete.
+                 */
+                gfp_mask = memalloc_noio_flags(gfp_mask);
                 page = __alloc_pages_slowpath(gfp_mask, order,
                                 zonelist, high_zoneidx, nodemask,
                                 preferred_zone, migratetype);
+        }
 
         trace_mm_page_alloc(page, order, gfp_mask, migratetype);
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b93968b71dc6..a68fa20269d9 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2352,7 +2352,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 {
         unsigned long nr_reclaimed;
         struct scan_control sc = {
-                .gfp_mask = gfp_mask,
+                .gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)),
                 .may_writepage = !laptop_mode,
                 .nr_to_reclaim = SWAP_CLUSTER_MAX,
                 .may_unmap = 1,
@@ -3313,7 +3313,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
                 .may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
                 .may_swap = 1,
                 .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
-                .gfp_mask = gfp_mask,
+                .gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)),
                 .order = order,
                 .priority = ZONE_RECLAIM_PRIORITY,
         };