hugetlb: allow to free gigantic pages regardless of the configuration

On systems without CONTIG_ALLOC activated but that support gigantic pages,
boottime reserved gigantic pages can not be freed at all.  This patch
simply enables the possibility to hand back those pages to memory
allocator.

Link: http://lkml.kernel.org/r/20190327063626.18421-5-alex@ghiti.fr
Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
Acked-by: David S. Miller <davem@davemloft.net> [sparc]
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Andy Lutomirsky <luto@kernel.org>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 38 insertions, 16 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index dffe5d9d03ae..2f901a6e13d2 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1059,6 +1059,7 @@ static void free_gigantic_page(struct page *page, unsigned int order)
 	free_contig_range(page_to_pfn(page), 1 << order);
 }
 
+#ifdef CONFIG_CONTIG_ALLOC
 static int __alloc_gigantic_page(unsigned long start_pfn,
 				unsigned long nr_pages, gfp_t gfp_mask)
 {
@@ -1143,11 +1144,20 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
 
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid);
 static void prep_compound_gigantic_page(struct page *page, unsigned int order);
+#else /* !CONFIG_CONTIG_ALLOC */
+static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
+					int nid, nodemask_t *nodemask)
+{
+	return NULL;
+}
+#endif /* CONFIG_CONTIG_ALLOC */
 
 #else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */
-static inline bool gigantic_page_supported(void) { return false; }
 static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
-		int nid, nodemask_t *nodemask) { return NULL; }
+					int nid, nodemask_t *nodemask)
+{
+	return NULL;
+}
 static inline void free_gigantic_page(struct page *page, unsigned int order) { }
 static inline void destroy_compound_gigantic_page(struct page *page,
 						unsigned int order) { }
@@ -1157,7 +1167,7 @@ static void update_and_free_page(struct hstate *h, struct page *page)
 {
 	int i;
 
-	if (hstate_is_gigantic(h) && !gigantic_page_supported())
+	if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
 		return;
 
 	h->nr_huge_pages--;
@@ -2278,13 +2288,27 @@ found:
 }
 
 #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
-static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
-						nodemask_t *nodes_allowed)
+static int set_max_huge_pages(struct hstate *h, unsigned long count,
+			      nodemask_t *nodes_allowed)
 {
 	unsigned long min_count, ret;
 
-	if (hstate_is_gigantic(h) && !gigantic_page_supported())
-		return h->max_huge_pages;
+	spin_lock(&hugetlb_lock);
+
+	/*
+	 * Gigantic pages runtime allocation depend on the capability for large
+	 * page range allocation.
+	 * If the system does not provide this feature, return an error when
+	 * the user tries to allocate gigantic pages but let the user free the
+	 * boottime allocated gigantic pages.
+	 */
+	if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) {
+		if (count > persistent_huge_pages(h)) {
+			spin_unlock(&hugetlb_lock);
+			return -EINVAL;
+		}
+		/* Fall through to decrease pool */
+	}
 
 	/*
 	 * Increase the pool size
@@ -2297,7 +2321,6 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
 	 * pool might be one hugepage larger than it needs to be, but
 	 * within all the constraints specified by the sysctls.
 	 */
-	spin_lock(&hugetlb_lock);
 	while (h->surplus_huge_pages && count > persistent_huge_pages(h)) {
 		if (!adjust_pool_surplus(h, nodes_allowed, -1))
 			break;
@@ -2352,9 +2375,10 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
 			break;
 	}
 out:
-	ret = persistent_huge_pages(h);
+	h->max_huge_pages = persistent_huge_pages(h);
 	spin_unlock(&hugetlb_lock);
-	return ret;
+
+	return 0;
 }
 
 #define HSTATE_ATTR_RO(_name) \
@@ -2406,7 +2430,7 @@ static ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
 	int err;
 	NODEMASK_ALLOC(nodemask_t, nodes_allowed, GFP_KERNEL | __GFP_NORETRY);
 
-	if (hstate_is_gigantic(h) && !gigantic_page_supported()) {
+	if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) {
 		err = -EINVAL;
 		goto out;
 	}
@@ -2430,15 +2454,13 @@ static ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
 	} else
 		nodes_allowed = &node_states[N_MEMORY];
 
-	h->max_huge_pages = set_max_huge_pages(h, count, nodes_allowed);
+	err = set_max_huge_pages(h, count, nodes_allowed);
 
+out:
 	if (nodes_allowed != &node_states[N_MEMORY])
 		NODEMASK_FREE(nodes_allowed);
 
-	return len;
-out:
-	NODEMASK_FREE(nodes_allowed);
-	return err;
+	return err ? err : len;
 }
 
 static ssize_t nr_hugepages_store_common(bool obey_mempolicy,