mm: hugetlb: optionally allocate gigantic hugepages using cma

Commit 944d9fec8d ("hugetlb: add support for gigantic page allocation
at runtime") has added the run-time allocation of gigantic pages.

However it actually works only at early stages of the system loading,
when the majority of memory is free.  After some time the memory gets
fragmented by non-movable pages, so the chances to find a contiguous 1GB
block are getting close to zero.  Even dropping caches manually doesn't
help a lot.

At large scale rebooting servers in order to allocate gigantic hugepages
is quite expensive and complex.  At the same time keeping some constant
percentage of memory in reserved hugepages even if the workload isn't
using it is a big waste: not all workloads can benefit from using 1 GB
pages.

The following solution can solve the problem:
1) On boot time a dedicated cma area* is reserved. The size is passed
   as a kernel argument.
2) Run-time allocations of gigantic hugepages are performed using the
   cma allocator and the dedicated cma area

In this case gigantic hugepages can be allocated successfully with a
high probability, however the memory isn't completely wasted if nobody
is using 1GB hugepages: it can be used for pagecache, anon memory, THPs,
etc.

* On a multi-node machine a per-node cma area is allocated on each node.
  Following gigantic hugetlb allocation are using the first available
  numa node if the mask isn't specified by a user.

Usage:
1) configure the kernel to allocate a cma area for hugetlb allocations:
   pass hugetlb_cma=10G as a kernel argument

2) allocate hugetlb pages as usual, e.g.
   echo 10 > /sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages

If the option isn't enabled or the allocation of the cma area failed,
the current behavior of the system is preserved.

x86 and arm-64 are covered by this patch, other architectures can be
trivially added later.

The patch contains clean-ups and fixes proposed and implemented by Aslan
Bakirov and Randy Dunlap.  It also contains ideas and suggestions
proposed by Rik van Riel, Michal Hocko and Mike Kravetz.  Thanks!

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Andreas Schaufler <andreas.schaufler@gmx.de>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Michal Hocko <mhocko@kernel.org>
Cc: Aslan Bakirov <aslan@fb.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Joonsoo Kim <js1304@gmail.com>
Link: http://lkml.kernel.org/r/20200407163840.92263-3-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Documentation/admin-guide/kernel-parameters.txt

@@ -1475,6 +1475,14 @@
 	hpet_mmap=	[X86, HPET_MMAP] Allow userspace to mmap HPET
 			registers.  Default set by CONFIG_HPET_MMAP_DEFAULT.
 
+	hugetlb_cma=	[HW] The size of a cma area used for allocation
+			of gigantic hugepages.
+			Format: nn[KMGTPE]
+
+			Reserve a cma area of given size and allocate gigantic
+			hugepages using the cma allocator. If enabled, the
+			boot-time allocation of gigantic hugepages is skipped.
+
 	hugepages=	[HW,X86-32,IA-64] HugeTLB pages to allocate at boot.
 	hugepagesz=	[HW,IA-64,PPC,X86-64] The size of the HugeTLB pages.
 			On x86-64 and powerpc, this option can be specified

arch/arm64/mm/init.c

@@ -29,6 +29,7 @@
 #include <linux/mm.h>
 #include <linux/kexec.h>
 #include <linux/crash_dump.h>
+#include <linux/hugetlb.h>
 
 #include <asm/boot.h>
 #include <asm/fixmap.h>
@@ -457,6 +458,11 @@ void __init arm64_memblock_init(void)
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
 
 	dma_contiguous_reserve(arm64_dma32_phys_limit);
+
+#ifdef CONFIG_ARM64_4K_PAGES
+	hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT);
+#endif
+
 }
 
 void __init bootmem_init(void)

arch/x86/kernel/setup.c

@@ -16,6 +16,7 @@
 #include <linux/pci.h>
 #include <linux/root_dev.h>
 #include <linux/sfi.h>
+#include <linux/hugetlb.h>
 #include <linux/tboot.h>
 #include <linux/usb/xhci-dbgp.h>
 
@@ -1157,6 +1158,9 @@ void __init setup_arch(char **cmdline_p)
 	initmem_init();
 	dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT);
 
+	if (boot_cpu_has(X86_FEATURE_GBPAGES))
+		hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT);
+
 	/*
 	 * Reserve memory for crash kernel after SRAT is parsed so that it
 	 * won't consume hotpluggable memory.

include/linux/hugetlb.h

@@ -895,4 +895,16 @@ static inline spinlock_t *huge_pte_lock(struct hstate *h,
 	return ptl;
 }
 
+#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA)
+extern void __init hugetlb_cma_reserve(int order);
+extern void __init hugetlb_cma_check(void);
+#else
+static inline __init void hugetlb_cma_reserve(int order)
+{
+}
+static inline __init void hugetlb_cma_check(void)
+{
+}
+#endif
+
 #endif /* _LINUX_HUGETLB_H */

mm/hugetlb.c

@@ -28,6 +28,7 @@
 #include <linux/jhash.h>
 #include <linux/numa.h>
 #include <linux/llist.h>
+#include <linux/cma.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -44,6 +45,9 @@
 int hugetlb_max_hstate __read_mostly;
 unsigned int default_hstate_idx;
 struct hstate hstates[HUGE_MAX_HSTATE];
+
+static struct cma *hugetlb_cma[MAX_NUMNODES];
+
 /*
  * Minimum page order among possible hugepage sizes, set to a proper value
  * at boot time.
@@ -1228,6 +1232,14 @@ static void destroy_compound_gigantic_page(struct page *page,
 
 static void free_gigantic_page(struct page *page, unsigned int order)
 {
+	/*
+	 * If the page isn't allocated using the cma allocator,
+	 * cma_release() returns false.
+	 */
+	if (IS_ENABLED(CONFIG_CMA) &&
+	    cma_release(hugetlb_cma[page_to_nid(page)], page, 1 << order))
+		return;
+
 	free_contig_range(page_to_pfn(page), 1 << order);
 }
 
@@ -1237,6 +1249,21 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
 {
 	unsigned long nr_pages = 1UL << huge_page_order(h);
 
+	if (IS_ENABLED(CONFIG_CMA)) {
+		struct page *page;
+		int node;
+
+		for_each_node_mask(node, *nodemask) {
+			if (!hugetlb_cma[node])
+				continue;
+
+			page = cma_alloc(hugetlb_cma[node], nr_pages,
+					 huge_page_order(h), true);
+			if (page)
+				return page;
+		}
+	}
+
 	return alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask);
 }
 
@@ -1281,8 +1308,14 @@ static void update_and_free_page(struct hstate *h, struct page *page)
 	set_compound_page_dtor(page, NULL_COMPOUND_DTOR);
 	set_page_refcounted(page);
 	if (hstate_is_gigantic(h)) {
+		/*
+		 * Temporarily drop the hugetlb_lock, because
+		 * we might block in free_gigantic_page().
+		 */
+		spin_unlock(&hugetlb_lock);
 		destroy_compound_gigantic_page(page, huge_page_order(h));
 		free_gigantic_page(page, huge_page_order(h));
+		spin_lock(&hugetlb_lock);
 	} else {
 		__free_pages(page, huge_page_order(h));
 	}
@@ -2539,6 +2572,10 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
 
 	for (i = 0; i < h->max_huge_pages; ++i) {
 		if (hstate_is_gigantic(h)) {
+			if (IS_ENABLED(CONFIG_CMA) && hugetlb_cma[0]) {
+				pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n");
+				break;
+			}
 			if (!alloc_bootmem_huge_page(h))
 				break;
 		} else if (!alloc_pool_huge_page(h,
@@ -3194,6 +3231,7 @@ static int __init hugetlb_init(void)
 			default_hstate.max_huge_pages = default_hstate_max_huge_pages;
 	}
 
+	hugetlb_cma_check();
 	hugetlb_init_hstates();
 	gather_bootmem_prealloc();
 	report_hugepages();
@@ -5506,3 +5544,74 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason)
 		spin_unlock(&hugetlb_lock);
 	}
 }
+
+#ifdef CONFIG_CMA
+static unsigned long hugetlb_cma_size __initdata;
+static bool cma_reserve_called __initdata;
+
+static int __init cmdline_parse_hugetlb_cma(char *p)
+{
+	hugetlb_cma_size = memparse(p, &p);
+	return 0;
+}
+
+early_param("hugetlb_cma", cmdline_parse_hugetlb_cma);
+
+void __init hugetlb_cma_reserve(int order)
+{
+	unsigned long size, reserved, per_node;
+	int nid;
+
+	cma_reserve_called = true;
+
+	if (!hugetlb_cma_size)
+		return;
+
+	if (hugetlb_cma_size < (PAGE_SIZE << order)) {
+		pr_warn("hugetlb_cma: cma area should be at least %lu MiB\n",
+			(PAGE_SIZE << order) / SZ_1M);
+		return;
+	}
+
+	/*
+	 * If 3 GB area is requested on a machine with 4 numa nodes,
+	 * let's allocate 1 GB on first three nodes and ignore the last one.
+	 */
+	per_node = DIV_ROUND_UP(hugetlb_cma_size, nr_online_nodes);
+	pr_info("hugetlb_cma: reserve %lu MiB, up to %lu MiB per node\n",
+		hugetlb_cma_size / SZ_1M, per_node / SZ_1M);
+
+	reserved = 0;
+	for_each_node_state(nid, N_ONLINE) {
+		int res;
+
+		size = min(per_node, hugetlb_cma_size - reserved);
+		size = round_up(size, PAGE_SIZE << order);
+
+		res = cma_declare_contiguous_nid(0, size, 0, PAGE_SIZE << order,
+						 0, false, "hugetlb",
+						 &hugetlb_cma[nid], nid);
+		if (res) {
+			pr_warn("hugetlb_cma: reservation failed: err %d, node %d",
+				res, nid);
+			continue;
+		}
+
+		reserved += size;
+		pr_info("hugetlb_cma: reserved %lu MiB on node %d\n",
+			size / SZ_1M, nid);
+
+		if (reserved >= hugetlb_cma_size)
+			break;
+	}
+}
+
+void __init hugetlb_cma_check(void)
+{
+	if (!hugetlb_cma_size || cma_reserve_called)
+		return;
+
+	pr_warn("hugetlb_cma: the option isn't supported by current arch\n");
+}
+
+#endif /* CONFIG_CMA */