Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Fun set of conflict resolutions here...

For the mac80211 stuff, these were fortunately just parallel
adds.  Trivially resolved.

In drivers/net/phy/phy.c we had a bug fix in 'net' that moved the
function phy_disable_interrupts() earlier in the file, whilst in
'net-next' the phy_error() call from this function was removed.

In net/ipv4/xfrm4_policy.c, David Ahern's changes to remove the
'rt_table_id' member of rtable collided with a bug fix in 'net' that
added a new struct member "rt_mtu_locked" which needs to be copied
over here.

The mlxsw driver conflict consisted of net-next separating
the span code and definitions into separate files, whilst
a 'net' bug fix made some changes to that moved code.

The mlx5 infiniband conflict resolution was quite non-trivial,
the RDMA tree's merge commit was used as a guide here, and
here are their notes:

====================

    Due to bug fixes found by the syzkaller bot and taken into the for-rc
    branch after development for the 4.17 merge window had already started
    being taken into the for-next branch, there were fairly non-trivial
    merge issues that would need to be resolved between the for-rc branch
    and the for-next branch.  This merge resolves those conflicts and
    provides a unified base upon which ongoing development for 4.17 can
    be based.

    Conflicts:
            drivers/infiniband/hw/mlx5/main.c - Commit 42cea83f9524
            (IB/mlx5: Fix cleanup order on unload) added to for-rc and
            commit b5ca15ad7e61 (IB/mlx5: Add proper representors support)
            add as part of the devel cycle both needed to modify the
            init/de-init functions used by mlx5.  To support the new
            representors, the new functions added by the cleanup patch
            needed to be made non-static, and the init/de-init list
            added by the representors patch needed to be modified to
            match the init/de-init list changes made by the cleanup
            patch.
    Updates:
            drivers/infiniband/hw/mlx5/mlx5_ib.h - Update function
            prototypes added by representors patch to reflect new function
            names as changed by cleanup patch
            drivers/infiniband/hw/mlx5/ib_rep.c - Update init/de-init
            stage list to match new order from cleanup patch
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 44 insertions, 23 deletions

diff --git a/mm/percpu.c b/mm/percpu.c
index 50e7fdf84055..9297098519a6 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -80,6 +80,7 @@
 #include <linux/vmalloc.h>
 #include <linux/workqueue.h>
 #include <linux/kmemleak.h>
+#include <linux/sched.h>
 
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
@@ -447,26 +448,25 @@ static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits,
 /**
  * pcpu_mem_zalloc - allocate memory
  * @size: bytes to allocate
+ * @gfp: allocation flags
  *
  * Allocate @size bytes.  If @size is smaller than PAGE_SIZE,
- * kzalloc() is used; otherwise, vzalloc() is used.  The returned
- * memory is always zeroed.
- *
- * CONTEXT:
- * Does GFP_KERNEL allocation.
+ * kzalloc() is used; otherwise, the equivalent of vzalloc() is used.
+ * This is to facilitate passing through whitelisted flags.  The
+ * returned memory is always zeroed.
  *
  * RETURNS:
  * Pointer to the allocated area on success, NULL on failure.
  */
-static void *pcpu_mem_zalloc(size_t size)
+static void *pcpu_mem_zalloc(size_t size, gfp_t gfp)
 {
 	if (WARN_ON_ONCE(!slab_is_available()))
 		return NULL;
 
 	if (size <= PAGE_SIZE)
-		return kzalloc(size, GFP_KERNEL);
+		return kzalloc(size, gfp);
 	else
-		return vzalloc(size);
+		return __vmalloc(size, gfp | __GFP_ZERO, PAGE_KERNEL);
 }
 
 /**
@@ -1154,12 +1154,12 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr,
 	return chunk;
 }
 
-static struct pcpu_chunk *pcpu_alloc_chunk(void)
+static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp)
 {
 	struct pcpu_chunk *chunk;
 	int region_bits;
 
-	chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size);
+	chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size, gfp);
 	if (!chunk)
 		return NULL;
 
@@ -1168,17 +1168,17 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
 	region_bits = pcpu_chunk_map_bits(chunk);
 
 	chunk->alloc_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits) *
-					   sizeof(chunk->alloc_map[0]));
+					   sizeof(chunk->alloc_map[0]), gfp);
 	if (!chunk->alloc_map)
 		goto alloc_map_fail;
 
 	chunk->bound_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits + 1) *
-					   sizeof(chunk->bound_map[0]));
+					   sizeof(chunk->bound_map[0]), gfp);
 	if (!chunk->bound_map)
 		goto bound_map_fail;
 
 	chunk->md_blocks = pcpu_mem_zalloc(pcpu_chunk_nr_blocks(chunk) *
-					   sizeof(chunk->md_blocks[0]));
+					   sizeof(chunk->md_blocks[0]), gfp);
 	if (!chunk->md_blocks)
 		goto md_blocks_fail;
 
@@ -1277,9 +1277,11 @@ static void pcpu_chunk_depopulated(struct pcpu_chunk *chunk,
  * pcpu_addr_to_page		- translate address to physical address
  * pcpu_verify_alloc_info	- check alloc_info is acceptable during init
  */
-static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size);
-static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size);
-static struct pcpu_chunk *pcpu_create_chunk(void);
+static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
+			       int page_start, int page_end, gfp_t gfp);
+static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
+				  int page_start, int page_end);
+static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp);
 static void pcpu_destroy_chunk(struct pcpu_chunk *chunk);
 static struct page *pcpu_addr_to_page(void *addr);
 static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai);
@@ -1339,6 +1341,8 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
 static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 				 gfp_t gfp)
 {
+	/* whitelisted flags that can be passed to the backing allocators */
+	gfp_t pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
 	bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL;
 	bool do_warn = !(gfp & __GFP_NOWARN);
 	static int warn_limit = 10;
@@ -1369,8 +1373,17 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 		return NULL;
 	}
 
-	if (!is_atomic)
-		mutex_lock(&pcpu_alloc_mutex);
+	if (!is_atomic) {
+		/*
+		 * pcpu_balance_workfn() allocates memory under this mutex,
+		 * and it may wait for memory reclaim. Allow current task
+		 * to become OOM victim, in case of memory pressure.
+		 */
+		if (gfp & __GFP_NOFAIL)
+			mutex_lock(&pcpu_alloc_mutex);
+		else if (mutex_lock_killable(&pcpu_alloc_mutex))
+			return NULL;
+	}
 
 	spin_lock_irqsave(&pcpu_lock, flags);
 
@@ -1421,7 +1434,7 @@ restart:
 	}
 
 	if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) {
-		chunk = pcpu_create_chunk();
+		chunk = pcpu_create_chunk(pcpu_gfp);
 		if (!chunk) {
 			err = "failed to allocate new chunk";
 			goto fail;
@@ -1450,7 +1463,7 @@ area_found:
 					   page_start, page_end) {
 			WARN_ON(chunk->immutable);
 
-			ret = pcpu_populate_chunk(chunk, rs, re);
+			ret = pcpu_populate_chunk(chunk, rs, re, pcpu_gfp);
 
 			spin_lock_irqsave(&pcpu_lock, flags);
 			if (ret) {
@@ -1561,10 +1574,17 @@ void __percpu *__alloc_reserved_percpu(size_t size, size_t align)
  * pcpu_balance_workfn - manage the amount of free chunks and populated pages
  * @work: unused
  *
- * Reclaim all fully free chunks except for the first one.
+ * Reclaim all fully free chunks except for the first one.  This is also
+ * responsible for maintaining the pool of empty populated pages.  However,
+ * it is possible that this is called when physical memory is scarce causing
+ * OOM killer to be triggered.  We should avoid doing so until an actual
+ * allocation causes the failure as it is possible that requests can be
+ * serviced from already backed regions.
  */
 static void pcpu_balance_workfn(struct work_struct *work)
 {
+	/* gfp flags passed to underlying allocators */
+	const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
 	LIST_HEAD(to_free);
 	struct list_head *free_head = &pcpu_slot[pcpu_nr_slots - 1];
 	struct pcpu_chunk *chunk, *next;
@@ -1600,6 +1620,7 @@ static void pcpu_balance_workfn(struct work_struct *work)
 			spin_unlock_irq(&pcpu_lock);
 		}
 		pcpu_destroy_chunk(chunk);
+		cond_resched();
 	}
 
 	/*
@@ -1645,7 +1666,7 @@ retry_pop:
 					   chunk->nr_pages) {
 			int nr = min(re - rs, nr_to_pop);
 
-			ret = pcpu_populate_chunk(chunk, rs, rs + nr);
+			ret = pcpu_populate_chunk(chunk, rs, rs + nr, gfp);
 			if (!ret) {
 				nr_to_pop -= nr;
 				spin_lock_irq(&pcpu_lock);
@@ -1662,7 +1683,7 @@ retry_pop:
 
 	if (nr_to_pop) {
 		/* ran out of chunks to populate, create a new one and retry */
-		chunk = pcpu_create_chunk();
+		chunk = pcpu_create_chunk(gfp);
 		if (chunk) {
 			spin_lock_irq(&pcpu_lock);
 			pcpu_chunk_relocate(chunk, -1);