[PATCH] mm: hugetlb: optionally allocate gigantic hugepages using cma

[Roman Gushchin]

Commit 944d9fec8d7a ("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
1 GB 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.

Only x86 is covered by this patch, but it's trivial to extend it to
cover other architectures as well.

Signed-off-by: Roman Gushchin <guro@xxxxxx>
---
 .../admin-guide/kernel-parameters.txt         |   7 ++
 arch/x86/kernel/setup.c                       |   3 +
 include/linux/hugetlb.h                       |   2 +
 mm/hugetlb.c                                  | 108 ++++++++++++++++++
 4 files changed, 120 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 0c9894247015..d3349ec1dbef 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1452,6 +1452,13 @@
 	hpet_mmap=	[X86, HPET_MMAP] Allow userspace to mmap HPET
 			registers.  Default set by CONFIG_HPET_MMAP_DEFAULT.
 
+	hugetlb_cma=	[x86-64] The size of a cma area used for allocation
+			of gigantic hugepages.
+			Format: nn[GTPE] | nn%
+
+			If enabled, 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
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index a74262c71484..ceeb06ddfd41 100644
--- a/arch/x86/kernel/setup.c
+++ b/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>
 
@@ -1158,6 +1159,8 @@ void __init setup_arch(char **cmdline_p)
 	initmem_init();
 	dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT);
 
+	hugetlb_cma_reserve();
+
 	/*
 	 * Reserve memory for crash kernel after SRAT is parsed so that it
 	 * won't consume hotpluggable memory.
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 50480d16bd33..50050c981ab9 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -157,6 +157,8 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
 extern int sysctl_hugetlb_shm_group;
 extern struct list_head huge_boot_pages;
 
+extern void __init hugetlb_cma_reserve(void);
+
 /* arch callbacks */
 
 pte_t *huge_pte_alloc(struct mm_struct *mm,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7fb31750e670..f2e6e0a37263 100644
--- a/mm/hugetlb.c
+++ b/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 +1232,11 @@ static void destroy_compound_gigantic_page(struct page *page,
 
 static void free_gigantic_page(struct page *page, unsigned int order)
 {
+	if (hugetlb_cma[0]) {
+		cma_release(hugetlb_cma[page_to_nid(page)], page, 1 << order);
+		return;
+	}
+
 	free_contig_range(page_to_pfn(page), 1 << order);
 }
 
@@ -1237,6 +1246,23 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
 {
 	unsigned long nr_pages = 1UL << huge_page_order(h);
 
+	if (hugetlb_cma[0]) {
+		struct page *page;
+		int nid;
+
+		for_each_node_mask(nid, *nodemask) {
+			if (!hugetlb_cma[nid])
+				break;
+
+			page = cma_alloc(hugetlb_cma[nid], nr_pages,
+					 huge_page_order(h), true);
+			if (page)
+				return page;
+		}
+
+		return NULL;
+	}
+
 	return alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask);
 }
 
@@ -2439,6 +2465,10 @@ 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 (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,
@@ -5372,3 +5402,81 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason)
 		spin_unlock(&hugetlb_lock);
 	}
 }
+
+static unsigned long hugetlb_cma_size __initdata;
+static unsigned long hugetlb_cma_percent __initdata;
+
+static int __init cmdline_parse_hugetlb_cma(char *p)
+{
+	unsigned long long val;
+	char *endptr;
+
+	if (!p)
+		return -EINVAL;
+
+	/* Value may be a percentage of total memory, otherwise bytes */
+	val = simple_strtoull(p, &endptr, 0);
+	if (*endptr == '%')
+		hugetlb_cma_percent = clamp_t(unsigned long, val, 0, 100);
+	else
+		hugetlb_cma_size = memparse(p, &p);
+
+	return 0;
+}
+
+early_param("hugetlb_cma", cmdline_parse_hugetlb_cma);
+
+void __init hugetlb_cma_reserve(void)
+{
+	unsigned long totalpages = 0;
+	unsigned long start_pfn, end_pfn;
+	phys_addr_t size;
+	int nid, i, res;
+
+	if (!hugetlb_cma_size && !hugetlb_cma_percent)
+		return;
+
+	if (hugetlb_cma_percent) {
+		for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn,
+				       NULL)
+			totalpages += end_pfn - start_pfn;
+
+		size = PAGE_SIZE * (hugetlb_cma_percent * 100 * totalpages) /
+			10000UL;
+	} else {
+		size = hugetlb_cma_size;
+	}
+
+	pr_info("hugetlb_cma: reserve %llu, %llu per node\n", size,
+		size / nr_online_nodes);
+
+	size /= nr_online_nodes;
+
+	for_each_node_state(nid, N_ONLINE) {
+		unsigned long min_pfn = 0, max_pfn = 0;
+
+		for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
+			if (!min_pfn)
+				min_pfn = start_pfn;
+			max_pfn = end_pfn;
+		}
+
+		res = cma_declare_contiguous(PFN_PHYS(min_pfn), size,
+					     PFN_PHYS(max_pfn), (1UL << 30),
+					     0, false,
+					     "hugetlb", &hugetlb_cma[nid]);
+		if (res) {
+			pr_warn("hugetlb_cma: reservation failed: err %d, node %d, [%llu, %llu)",
+				res, nid, PFN_PHYS(min_pfn), PFN_PHYS(max_pfn));
+
+			for (; nid >= 0; nid--)
+				hugetlb_cma[nid] = NULL;
+
+			break;
+		}
+
+		pr_info("hugetlb_cma: successfully reserved %llu on node %d\n",
+			size, nid);
+	}
+}
+
-- 
2.24.1