Merge branch 'linus' into core/rcu

Conflicts:
	fs/fs-writeback.c

Merge reason: Resolve the conflict

Note, i picked the version from Linus's tree, which effectively reverts
the fs-writeback.c bits of:

  b97181f: fs: remove all rcu head initializations, except on_stack initializations

As the upstream changes to this file changed this code heavily and the
first attempt to resolve the conflict resulted in a non-booting kernel.
It's safer to re-try this portion of the commit cleanly.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

4 files changed, 40 insertions, 14 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c6ece0a5759..20a8193a7af 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1370,7 +1370,7 @@ static void memcg_wakeup_oom(struct mem_cgroup *mem)
 
 static void memcg_oom_recover(struct mem_cgroup *mem)
 {
-	if (mem->oom_kill_disable && atomic_read(&mem->oom_lock))
+	if (atomic_read(&mem->oom_lock))
 		memcg_wakeup_oom(mem);
 }
 
@@ -3781,6 +3781,8 @@ static int mem_cgroup_oom_control_write(struct cgroup *cgrp,
 		return -EINVAL;
 	}
 	mem->oom_kill_disable = val;
+	if (!val)
+		memcg_oom_recover(mem);
 	cgroup_unlock();
 	return 0;
 }
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 5d6fb339de0..5bc0a96beb5 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2094,7 +2094,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
 		NODEMASK_SCRATCH(scratch);
 
 		if (!scratch)
-			return;
+			goto put_mpol;
 		/* contextualize the tmpfs mount point mempolicy */
 		new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask);
 		if (IS_ERR(new))
@@ -2103,19 +2103,20 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
 		task_lock(current);
 		ret = mpol_set_nodemask(new, &mpol->w.user_nodemask, scratch);
 		task_unlock(current);
-		mpol_put(mpol);	/* drop our ref on sb mpol */
 		if (ret)
-			goto put_free;
+			goto put_new;
 
 		/* Create pseudo-vma that contains just the policy */
 		memset(&pvma, 0, sizeof(struct vm_area_struct));
 		pvma.vm_end = TASK_SIZE;	/* policy covers entire file */
 		mpol_set_shared_policy(sp, &pvma, new); /* adds ref */
 
-put_free:
+put_new:
 		mpol_put(new);			/* drop initial ref */
 free_scratch:
 		NODEMASK_SCRATCH_FREE(scratch);
+put_mpol:
+		mpol_put(mpol);	/* drop our incoming ref on sb mpol */
 	}
 }
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index bbd396ac954..54f28bd493d 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -597,7 +597,7 @@ static void balance_dirty_pages(struct address_space *mapping,
 	    (!laptop_mode && ((global_page_state(NR_FILE_DIRTY)
 			       + global_page_state(NR_UNSTABLE_NFS))
 					  > background_thresh)))
-		bdi_start_writeback(bdi, NULL, 0);
+		bdi_start_background_writeback(bdi);
 }
 
 void set_page_dirty_balance(struct page *page, int page_mkwrite)
@@ -705,9 +705,8 @@ void laptop_mode_timer_fn(unsigned long data)
 	 * We want to write everything out, not just down to the dirty
 	 * threshold
 	 */
-
 	if (bdi_has_dirty_io(&q->backing_dev_info))
-		bdi_start_writeback(&q->backing_dev_info, NULL, nr_pages);
+		bdi_start_writeback(&q->backing_dev_info, nr_pages);
 }
 
 /*
diff --git a/mm/percpu.c b/mm/percpu.c
index 39f7dfd5958..6470e771023 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -229,8 +229,8 @@ static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx)
 	return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx;
 }
 
-static unsigned long __maybe_unused pcpu_chunk_addr(struct pcpu_chunk *chunk,
-						unsigned int cpu, int page_idx)
+static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk,
+				     unsigned int cpu, int page_idx)
 {
 	return (unsigned long)chunk->base_addr + pcpu_unit_offsets[cpu] +
 		(page_idx << PAGE_SHIFT);
@@ -978,7 +978,32 @@ bool is_kernel_percpu_address(unsigned long addr)
  */
 phys_addr_t per_cpu_ptr_to_phys(void *addr)
 {
-	if (pcpu_addr_in_first_chunk(addr)) {
+	void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr);
+	bool in_first_chunk = false;
+	unsigned long first_start, first_end;
+	unsigned int cpu;
+
+	/*
+	 * The following test on first_start/end isn't strictly
+	 * necessary but will speed up lookups of addresses which
+	 * aren't in the first chunk.
+	 */
+	first_start = pcpu_chunk_addr(pcpu_first_chunk, pcpu_first_unit_cpu, 0);
+	first_end = pcpu_chunk_addr(pcpu_first_chunk, pcpu_last_unit_cpu,
+				    pcpu_unit_pages);
+	if ((unsigned long)addr >= first_start &&
+	    (unsigned long)addr < first_end) {
+		for_each_possible_cpu(cpu) {
+			void *start = per_cpu_ptr(base, cpu);
+
+			if (addr >= start && addr < start + pcpu_unit_size) {
+				in_first_chunk = true;
+				break;
+			}
+		}
+	}
+
+	if (in_first_chunk) {
 		if ((unsigned long)addr < VMALLOC_START ||
 		    (unsigned long)addr >= VMALLOC_END)
 			return __pa(addr);
@@ -1086,7 +1111,7 @@ struct pcpu_alloc_info * __init pcpu_build_alloc_info(
 	static int group_map[NR_CPUS] __initdata;
 	static int group_cnt[NR_CPUS] __initdata;
 	const size_t static_size = __per_cpu_end - __per_cpu_start;
-	int group_cnt_max = 0, nr_groups = 1, nr_units = 0;
+	int nr_groups = 1, nr_units = 0;
 	size_t size_sum, min_unit_size, alloc_size;
 	int upa, max_upa, uninitialized_var(best_upa);	/* units_per_alloc */
 	int last_allocs, group, unit;
@@ -1096,7 +1121,7 @@ struct pcpu_alloc_info * __init pcpu_build_alloc_info(
 
 	/* this function may be called multiple times */
 	memset(group_map, 0, sizeof(group_map));
-	memset(group_cnt, 0, sizeof(group_map));
+	memset(group_cnt, 0, sizeof(group_cnt));
 
 	/*
 	 * Determine min_unit_size, alloc_size and max_upa such that
@@ -1130,7 +1155,6 @@ struct pcpu_alloc_info * __init pcpu_build_alloc_info(
 		}
 		group_map[cpu] = group;
 		group_cnt[group]++;
-		group_cnt_max = max(group_cnt_max, group_cnt[group]);
 	}
 
 	/*