[PATCH RFC 16/19] mm/page_alloc: introduce ALLOC_NOBLOCK

[Brendan Jackman <jackmanb@google.com>]

This flag is set unless we can be sure the caller isn't in an atomic
context.

The allocator will soon start needing to call set_direct_map_* APIs
which cannot be called with IRQs off. It will need to do this even
before direct reclaim is possible.

Despite the fact that, in principle, ALLOC_NOBLOCK is distinct from
__GFP_DIRECT_RECLAIM, in order to avoid introducing a GFP flag, just
infer the former based on whether the caller set the latter. This means
that, in practice, ALLOC_NOBLOCK is just !__GFP_DIRECT_RECLAIM, except
that it is not influenced by gfp_allowed_mask. This could change later,
though.

Call it ALLOC_NOBLOCK in order to try and mitigate confusion vs the
recently-removed ALLOC_NON_BLOCK, which meant something different.

Signed-off-by: Brendan Jackman <jackmanb@google.com>
---
 mm/internal.h   |  1 +
 mm/page_alloc.c | 29 ++++++++++++++++++++++-------
 2 files changed, 23 insertions(+), 7 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h
index 5be53d25c89b7..6f2eacf3d8f2c 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1390,6 +1390,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
 #define ALLOC_HIGHATOMIC	0x200 /* Allows access to MIGRATE_HIGHATOMIC */
 #define ALLOC_TRYLOCK		0x400 /* Only use spin_trylock in allocation path */
 #define ALLOC_KSWAPD		0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */
+#define ALLOC_NOBLOCK	       0x1000 /* Caller may be atomic */
 
 /* Flags that allow allocations below the min watermark. */
 #define ALLOC_RESERVES (ALLOC_HARDER|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 42b807faca5fe..5576bd6a26b7b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4646,6 +4646,8 @@ gfp_to_alloc_flags(gfp_t gfp_mask, unsigned int order)
 		(gfp_mask & (__GFP_HIGH | __GFP_KSWAPD_RECLAIM));
 
 	if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) {
+		alloc_flags |= ALLOC_NOBLOCK;
+
 		/*
 		 * Not worth trying to allocate harder for __GFP_NOMEMALLOC even
 		 * if it can't schedule.
@@ -4839,14 +4841,13 @@ check_retry_cpuset(int cpuset_mems_cookie, struct alloc_context *ac)
 
 static inline struct page *
 __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
-						struct alloc_context *ac)
+		       struct alloc_context *ac, unsigned int alloc_flags)
 {
 	bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM;
 	bool can_compact = can_direct_reclaim && gfp_compaction_allowed(gfp_mask);
 	bool nofail = gfp_mask & __GFP_NOFAIL;
 	const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER;
 	struct page *page = NULL;
-	unsigned int alloc_flags;
 	unsigned long did_some_progress;
 	enum compact_priority compact_priority;
 	enum compact_result compact_result;
@@ -4898,7 +4899,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	 * kswapd needs to be woken up, and to avoid the cost of setting up
 	 * alloc_flags precisely. So we do that now.
 	 */
-	alloc_flags = gfp_to_alloc_flags(gfp_mask, order);
+	alloc_flags |= gfp_to_alloc_flags(gfp_mask, order);
 
 	/*
 	 * We need to recalculate the starting point for the zonelist iterator
@@ -5124,6 +5125,18 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	return page;
 }
 
+static inline unsigned int init_alloc_flags(gfp_t gfp_mask, unsigned int flags)
+{
+	/*
+	 * If the caller allowed __GFP_DIRECT_RECLAIM, they can't be atomic.
+	 * Note this is a separate determination from whether direct reclaim is
+	 * actually allowed, it must happen before applying gfp_allowed_mask.
+	 */
+	if (!(gfp_mask & __GFP_DIRECT_RECLAIM))
+		flags |= ALLOC_NOBLOCK;
+	return flags;
+}
+
 static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
 		int preferred_nid, nodemask_t *nodemask,
 		struct alloc_context *ac, gfp_t *alloc_gfp,
@@ -5205,7 +5218,7 @@ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid,
 	struct list_head *pcp_list;
 	struct alloc_context ac;
 	gfp_t alloc_gfp;
-	unsigned int alloc_flags = ALLOC_WMARK_LOW;
+	unsigned int alloc_flags = init_alloc_flags(gfp, ALLOC_WMARK_LOW);
 	int nr_populated = 0, nr_account = 0;
 
 	/*
@@ -5346,7 +5359,7 @@ struct page *__alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order,
 		int preferred_nid, nodemask_t *nodemask)
 {
 	struct page *page;
-	unsigned int alloc_flags = ALLOC_WMARK_LOW;
+	unsigned int alloc_flags = init_alloc_flags(gfp, ALLOC_WMARK_LOW);
 	gfp_t alloc_gfp; /* The gfp_t that was actually used for allocation */
 	struct alloc_context ac = { };
 
@@ -5391,7 +5404,7 @@ struct page *__alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order,
 	 */
 	ac.nodemask = nodemask;
 
-	page = __alloc_pages_slowpath(alloc_gfp, order, &ac);
+	page = __alloc_pages_slowpath(alloc_gfp, order, &ac, alloc_flags);
 
 out:
 	if (memcg_kmem_online() && (gfp & __GFP_ACCOUNT) && page &&
@@ -7911,11 +7924,13 @@ struct page *alloc_frozen_pages_nolock_noprof(gfp_t gfp_flags, int nid, unsigned
 	 */
 	gfp_t alloc_gfp = __GFP_NOWARN | __GFP_ZERO | __GFP_NOMEMALLOC | __GFP_COMP
 			| gfp_flags;
-	unsigned int alloc_flags = ALLOC_TRYLOCK;
+	unsigned int alloc_flags = init_alloc_flags(alloc_gfp, ALLOC_TRYLOCK);
 	struct alloc_context ac = { };
 	struct page *page;
 
 	VM_WARN_ON_ONCE(gfp_flags & ~__GFP_ACCOUNT);
+	VM_WARN_ON_ONCE(!(alloc_flags & ALLOC_NOBLOCK));
+
 	/*
 	 * In PREEMPT_RT spin_trylock() will call raw_spin_lock() which is
 	 * unsafe in NMI. If spin_trylock() is called from hard IRQ the current

-- 
2.51.2