percpu: allow select gfp to be passed to underlying allocators

The prior patch added support for passing gfp flags through to the
underlying allocators. This patch allows users to pass along gfp flags
(currently only __GFP_NORETRY and __GFP_NOWARN) to the underlying
allocators. This should allow users to decide if they are ok with
failing allocations recovering in a more graceful way.

Additionally, gfp passing was done as additional flags in the previous
patch. Instead, change this to caller passed semantics. GFP_KERNEL is
also removed as the default flag. It continues to be used for internally
caused underlying percpu allocations.

V2:
Removed gfp_percpu_mask in favor of doing it inline.
Removed GFP_KERNEL as a default flag for __alloc_percpu_gfp.

Signed-off-by: Dennis Zhou <dennisszhou@gmail.com>
Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

1 files changed, 7 insertions, 9 deletions

diff --git a/mm/percpu.c b/mm/percpu.c
index f97443d488a8..fa3f854634a1 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -454,9 +454,6 @@ static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits,
  * This is to facilitate passing through whitelisted flags.  The
  * returned memory is always zeroed.
  *
- * CONTEXT:
- * Does GFP_KERNEL allocation.
- *
  * RETURNS:
  * Pointer to the allocated area on success, NULL on failure.
  */
@@ -466,10 +463,9 @@ static void *pcpu_mem_zalloc(size_t size, gfp_t gfp)
 		return NULL;
 
 	if (size <= PAGE_SIZE)
-		return kzalloc(size, gfp | GFP_KERNEL);
+		return kzalloc(size, gfp);
 	else
-		return __vmalloc(size, gfp | GFP_KERNEL | __GFP_ZERO,
-				 PAGE_KERNEL);
+		return __vmalloc(size, gfp | __GFP_ZERO, PAGE_KERNEL);
 }
 
 /**
@@ -1344,6 +1340,8 @@ 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;
@@ -1426,7 +1424,7 @@ restart:
 	}
 
 	if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) {
-		chunk = pcpu_create_chunk(0);
+		chunk = pcpu_create_chunk(pcpu_gfp);
 		if (!chunk) {
 			err = "failed to allocate new chunk";
 			goto fail;
@@ -1455,7 +1453,7 @@ area_found:
 					   page_start, page_end) {
 			WARN_ON(chunk->immutable);
 
-			ret = pcpu_populate_chunk(chunk, rs, re, 0);
+			ret = pcpu_populate_chunk(chunk, rs, re, pcpu_gfp);
 
 			spin_lock_irqsave(&pcpu_lock, flags);
 			if (ret) {
@@ -1576,7 +1574,7 @@ void __percpu *__alloc_reserved_percpu(size_t size, size_t align)
 static void pcpu_balance_workfn(struct work_struct *work)
 {
 	/* gfp flags passed to underlying allocators */
-	const gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN;
+	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;