Merge tag 'v4.8-rc8' into drm-next

Linux 4.8-rc8

There was a lot of fallout in the imx/amdgpu/i915 drivers, so backmerge
it now to avoid troubles.

* tag 'v4.8-rc8': (1442 commits)
  Linux 4.8-rc8
  fault_in_multipages_readable() throws set-but-unused error
  mm: check VMA flags to avoid invalid PROT_NONE NUMA balancing
  radix tree: fix sibling entry handling in radix_tree_descend()
  radix tree test suite: Test radix_tree_replace_slot() for multiorder entries
  fix memory leaks in tracing_buffers_splice_read()
  tracing: Move mutex to protect against resetting of seq data
  MIPS: Fix delay slot emulation count in debugfs
  MIPS: SMP: Fix possibility of deadlock when bringing CPUs online
  mm: delete unnecessary and unsafe init_tlb_ubc()
  huge tmpfs: fix Committed_AS leak
  shmem: fix tmpfs to handle the huge= option properly
  blk-mq: skip unmapped queues in blk_mq_alloc_request_hctx
  MIPS: Fix pre-r6 emulation FPU initialisation
  arm64: kgdb: handle read-only text / modules
  arm64: Call numa_store_cpu_info() earlier.
  locking/hung_task: Fix typo in CONFIG_DETECT_HUNG_TASK help text
  nvme-rdma: only clear queue flags after successful connect
  i2c: qup: skip qup_i2c_suspend if the device is already runtime suspended
  perf/core: Limit matching exclusive events to one PMU
  ...

1 files changed, 13 insertions, 7 deletions

diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 5d845ffd7982..56054e541a0f 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -30,7 +30,7 @@
 
 #define HASH_DEFAULT_SIZE	64UL
 #define HASH_MIN_SIZE		4U
-#define BUCKET_LOCKS_PER_CPU   128UL
+#define BUCKET_LOCKS_PER_CPU	32UL
 
 static u32 head_hashfn(struct rhashtable *ht,
 		       const struct bucket_table *tbl,
@@ -70,21 +70,25 @@ static int alloc_bucket_locks(struct rhashtable *ht, struct bucket_table *tbl,
 	unsigned int nr_pcpus = num_possible_cpus();
 #endif
 
-	nr_pcpus = min_t(unsigned int, nr_pcpus, 32UL);
+	nr_pcpus = min_t(unsigned int, nr_pcpus, 64UL);
 	size = roundup_pow_of_two(nr_pcpus * ht->p.locks_mul);
 
 	/* Never allocate more than 0.5 locks per bucket */
 	size = min_t(unsigned int, size, tbl->size >> 1);
 
 	if (sizeof(spinlock_t) != 0) {
+		tbl->locks = NULL;
 #ifdef CONFIG_NUMA
 		if (size * sizeof(spinlock_t) > PAGE_SIZE &&
 		    gfp == GFP_KERNEL)
 			tbl->locks = vmalloc(size * sizeof(spinlock_t));
-		else
 #endif
-		tbl->locks = kmalloc_array(size, sizeof(spinlock_t),
-					   gfp);
+		if (gfp != GFP_KERNEL)
+			gfp |= __GFP_NOWARN | __GFP_NORETRY;
+
+		if (!tbl->locks)
+			tbl->locks = kmalloc_array(size, sizeof(spinlock_t),
+						   gfp);
 		if (!tbl->locks)
 			return -ENOMEM;
 		for (i = 0; i < size; i++)
@@ -321,12 +325,14 @@ static int rhashtable_expand(struct rhashtable *ht)
 static int rhashtable_shrink(struct rhashtable *ht)
 {
 	struct bucket_table *new_tbl, *old_tbl = rht_dereference(ht->tbl, ht);
-	unsigned int size;
+	unsigned int nelems = atomic_read(&ht->nelems);
+	unsigned int size = 0;
 	int err;
 
 	ASSERT_RHT_MUTEX(ht);
 
-	size = roundup_pow_of_two(atomic_read(&ht->nelems) * 3 / 2);
+	if (nelems)
+		size = roundup_pow_of_two(nelems * 3 / 2);
 	if (size < ht->p.min_size)
 		size = ht->p.min_size;