hugetlb: support larger than MAX_ORDER

This is needed on x86-64 to handle GB pages in hugetlbfs, because it is
not practical to enlarge MAX_ORDER to 1GB.

Instead the 1GB pages are only allocated at boot using the bootmem
allocator using the hugepages=...  option.

These 1G bootmem pages are never freed.  In theory it would be possible to
implement that with some complications, but since it would be a one-way
street (>= MAX_ORDER pages cannot be allocated later) I decided not to
currently.

The >= MAX_ORDER code is not ifdef'ed per architecture.  It is not very
big and the ifdef uglyness seemed not be worth it.

Known problems: /proc/meminfo and "free" do not display the memory
allocated for gb pages in "Total".  This is a little confusing for the
user.

Acked-by: Andrew Hastings <abh@cray.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 81 insertions, 2 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5e620e25cf08..1a6fe87555b2 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -14,6 +14,7 @@
 #include <linux/mempolicy.h>
 #include <linux/cpuset.h>
 #include <linux/mutex.h>
+#include <linux/bootmem.h>
 #include <linux/sysfs.h>
 
 #include <asm/page.h>
@@ -489,7 +490,7 @@ static void free_huge_page(struct page *page)
         INIT_LIST_HEAD(&page->lru);
 
         spin_lock(&hugetlb_lock);
-        if (h->surplus_huge_pages_node[nid]) {
+        if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) {
                 update_and_free_page(h, page);
                 h->surplus_huge_pages--;
                 h->surplus_huge_pages_node[nid]--;
@@ -550,6 +551,9 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 {
         struct page *page;
 
+        if (h->order >= MAX_ORDER)
+                return NULL;
+
         page = alloc_pages_node(nid,
                 htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
                                                 __GFP_REPEAT|__GFP_NOWARN,
@@ -616,6 +620,9 @@ static struct page *alloc_buddy_huge_page(struct hstate *h,
         struct page *page;
         unsigned int nid;
 
+        if (h->order >= MAX_ORDER)
+                return NULL;
+
         /*
          * Assume we will successfully allocate the surplus page to
          * prevent racing processes from causing the surplus to exceed
@@ -792,6 +799,10 @@ static void return_unused_surplus_pages(struct hstate *h,
         /* Uncommit the reservation */
         h->resv_huge_pages -= unused_resv_pages;
 
+        /* Cannot return gigantic pages currently */
+        if (h->order >= MAX_ORDER)
+                return;
+
         nr_pages = min(unused_resv_pages, h->surplus_huge_pages);
 
         while (remaining_iterations-- && nr_pages) {
@@ -913,6 +924,63 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
         return page;
 }
 
+static __initdata LIST_HEAD(huge_boot_pages);
+
+struct huge_bootmem_page {
+        struct list_head list;
+        struct hstate *hstate;
+};
+
+static int __init alloc_bootmem_huge_page(struct hstate *h)
+{
+        struct huge_bootmem_page *m;
+        int nr_nodes = nodes_weight(node_online_map);
+
+        while (nr_nodes) {
+                void *addr;
+
+                addr = __alloc_bootmem_node_nopanic(
+                                NODE_DATA(h->hugetlb_next_nid),
+                                huge_page_size(h), huge_page_size(h), 0);
+
+                if (addr) {
+                        /*
+                         * Use the beginning of the huge page to store the
+                         * huge_bootmem_page struct (until gather_bootmem
+                         * puts them into the mem_map).
+                         */
+                        m = addr;
+                        if (m)
+                                goto found;
+                }
+                hstate_next_node(h);
+                nr_nodes--;
+        }
+        return 0;
+
+found:
+        BUG_ON((unsigned long)virt_to_phys(m) & (huge_page_size(h) - 1));
+        /* Put them into a private list first because mem_map is not up yet */
+        list_add(&m->list, &huge_boot_pages);
+        m->hstate = h;
+        return 1;
+}
+
+/* Put bootmem huge pages into the standard lists after mem_map is up */
+static void __init gather_bootmem_prealloc(void)
+{
+        struct huge_bootmem_page *m;
+
+        list_for_each_entry(m, &huge_boot_pages, list) {
+                struct page *page = virt_to_page(m);
+                struct hstate *h = m->hstate;
+                __ClearPageReserved(page);
+                WARN_ON(page_count(page) != 1);
+                prep_compound_page(page, h->order);
+                prep_new_huge_page(h, page, page_to_nid(page));
+        }
+}
+
 static void __init hugetlb_init_one_hstate(struct hstate *h)
 {
         unsigned long i;
@@ -923,7 +991,10 @@ static void __init hugetlb_init_one_hstate(struct hstate *h)
         h->hugetlb_next_nid = first_node(node_online_map);
 
         for (i = 0; i < h->max_huge_pages; ++i) {
-                if (!alloc_fresh_huge_page(h))
+                if (h->order >= MAX_ORDER) {
+                        if (!alloc_bootmem_huge_page(h))
+                                break;
+                } else if (!alloc_fresh_huge_page(h))
                         break;
         }
         h->max_huge_pages = h->free_huge_pages = h->nr_huge_pages = i;
@@ -956,6 +1027,9 @@ static void try_to_free_low(struct hstate *h, unsigned long count)
 {
         int i;
 
+        if (h->order >= MAX_ORDER)
+                return;
+
         for (i = 0; i < MAX_NUMNODES; ++i) {
                 struct page *page, *next;
                 struct list_head *freel = &h->hugepage_freelists[i];
@@ -982,6 +1056,9 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count)
 {
         unsigned long min_count, ret;
 
+        if (h->order >= MAX_ORDER)
+                return h->max_huge_pages;
+
         /*
          * Increase the pool size
          * First take pages out of surplus state.  Then make up the
@@ -1210,6 +1287,8 @@ static int __init hugetlb_init(void)
 
         hugetlb_init_hstates();
 
+        gather_bootmem_prealloc();
+
         report_hugepages();
 
         hugetlb_sysfs_init();