Merge tag 'v4.1.39' into 4.1-2.0.x-imx

Linux 4.1.39

* tag 'v4.1.39': (138 commits)
  Linux 4.1.39
  KVM: x86: remove data variable from kvm_get_msr_common
  KVM: VMX: Fix host initiated access to guest MSR_TSC_AUX
  KVM: x86: pass host_initiated to functions that read MSRs
  perf/core: Fix the perf_cpu_time_max_percent check
  perf/core: Make sysctl_perf_cpu_time_max_percent conform to documentation
  perf/core: Fix implicitly enable dynamic interrupt throttle
  perf/core: Fix dynamic interrupt throttle
  Fix missing sanity check in /dev/sg
  printk: use rcuidle console tracepoint
  vfs: fix uninitialized flags in splice_to_pipe()
  drm/radeon: Use mode h/vdisplay fields to hide out of bounds HW cursor
  ARM: 8658/1: uaccess: fix zeroing of 64-bit get_user()
  drm/dp/mst: fix kernel oops when turning off secondary monitor
  [media] siano: make it work again with CONFIG_VMAP_STACK
  mmc: core: fix multi-bit bus width without high-speed mode
  futex: Move futex_init() to core_initcall
  xen-netfront: Delete rx_refill_timer in xennet_disconnect_backend()
  scsi: aacraid: Fix INTx/MSI-x issue with older controllers
  cpumask: use nr_cpumask_bits for parsing functions
  ...

Signed-off-by: Otavio Salvador <otavio@ossystems.com.br>

1 files changed, 28 insertions, 9 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 88b472bec71d..2f47f0332a2c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1387,23 +1387,32 @@ free:
 }
 
 /*
- * When releasing a hugetlb pool reservation, any surplus pages that were
- * allocated to satisfy the reservation must be explicitly freed if they were
- * never used.
- * Called with hugetlb_lock held.
+ * This routine has two main purposes:
+ * 1) Decrement the reservation count (resv_huge_pages) by the value passed
+ *    in unused_resv_pages.  This corresponds to the prior adjustments made
+ *    to the associated reservation map.
+ * 2) Free any unused surplus pages that may have been allocated to satisfy
+ *    the reservation.  As many as unused_resv_pages may be freed.
+ *
+ * Called with hugetlb_lock held.  However, the lock could be dropped (and
+ * reacquired) during calls to cond_resched_lock.  Whenever dropping the lock,
+ * we must make sure nobody else can claim pages we are in the process of
+ * freeing.  Do this by ensuring resv_huge_page always is greater than the
+ * number of huge pages we plan to free when dropping the lock.
  */
 static void return_unused_surplus_pages(struct hstate *h,
 					unsigned long unused_resv_pages)
 {
 	unsigned long nr_pages;
 
-	/* Uncommit the reservation */
-	h->resv_huge_pages -= unused_resv_pages;
-
 	/* Cannot return gigantic pages currently */
 	if (hstate_is_gigantic(h))
-		return;
+		goto out;
 
+	/*
+	 * Part (or even all) of the reservation could have been backed
+	 * by pre-allocated pages. Only free surplus pages.
+	 */
 	nr_pages = min(unused_resv_pages, h->surplus_huge_pages);
 
 	/*
@@ -1413,12 +1422,22 @@ static void return_unused_surplus_pages(struct hstate *h,
 	 * when the nodes with surplus pages have no free pages.
 	 * free_pool_huge_page() will balance the the freed pages across the
 	 * on-line nodes with memory and will handle the hstate accounting.
+	 *
+	 * Note that we decrement resv_huge_pages as we free the pages.  If
+	 * we drop the lock, resv_huge_pages will still be sufficiently large
+	 * to cover subsequent pages we may free.
 	 */
 	while (nr_pages--) {
+		h->resv_huge_pages--;
+		unused_resv_pages--;
 		if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1))
-			break;
+			goto out;
 		cond_resched_lock(&hugetlb_lock);
 	}
+
+out:
+	/* Fully uncommit the reservation */
+	h->resv_huge_pages -= unused_resv_pages;
 }
 
 /*