* [to-be-updated] mm-hugetlb-add-a-new-function-to-allocate-a-new-gigantic-page.patch removed from -mm tree
@ 2016-12-03 0:37 akpm
0 siblings, 0 replies; only message in thread
From: akpm @ 2016-12-03 0:37 UTC (permalink / raw)
To: shijie.huang, aneesh.kumar, catalin.marinas, gerald.schaefer,
kaly.xin, kirill.shutemov, mhocko, mike.kravetz, n-horiguchi,
steve.capper, will.deacon, mm-commits
The patch titled
Subject: mm: hugetlb: add a new function to allocate a new gigantic page
has been removed from the -mm tree. Its filename was
mm-hugetlb-add-a-new-function-to-allocate-a-new-gigantic-page.patch
This patch was dropped because an updated version will be merged
------------------------------------------------------
From: Huang Shijie <shijie.huang@arm.com>
Subject: mm: hugetlb: add a new function to allocate a new gigantic page
There are three ways we can allocate a new gigantic page:
1. When the NUMA is not enabled, use alloc_gigantic_page() to get
the gigantic page.
2. The NUMA is enabled, but the vma is NULL.
There is no memory policy we can refer to.
So create a @nodes_allowed, initialize it with init_nodemask_of_mempolicy()
or init_nodemask_of_node(). Then use alloc_fresh_gigantic_page() to get
the gigantic page.
3. The NUMA is enabled, and the vma is valid.
We can follow the memory policy of the @vma.
Get @nodes_mask by huge_nodemask(), and use alloc_fresh_gigantic_page()
to get the gigantic page.
Link: http://lkml.kernel.org/r/1479107259-2011-6-git-send-email-shijie.huang@arm.com
Signed-off-by: Huang Shijie <shijie.huang@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Kirill A . Shutemov <kirill.shutemov@linux.intel.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Steve Capper <steve.capper@arm.com>
Cc: Kaly Xin <kaly.xin@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/hugetlb.c | 67 +++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 67 insertions(+)
diff -puN mm/hugetlb.c~mm-hugetlb-add-a-new-function-to-allocate-a-new-gigantic-page mm/hugetlb.c
--- a/mm/hugetlb.c~mm-hugetlb-add-a-new-function-to-allocate-a-new-gigantic-page
+++ a/mm/hugetlb.c
@@ -1502,6 +1502,73 @@ int dissolve_free_huge_pages(unsigned lo
/*
* There are 3 ways this can get called:
+ *
+ * 1. When the NUMA is not enabled, use alloc_gigantic_page() to get
+ * the gigantic page.
+ *
+ * 2. The NUMA is enabled, but the vma is NULL.
+ * Create a @nodes_allowed, use alloc_fresh_gigantic_page() to get
+ * the gigantic page.
+ *
+ * 3. The NUMA is enabled, and the vma is valid.
+ * Use the @vma's memory policy.
+ * Get @nodes_mask by huge_nodemask(), and use alloc_fresh_gigantic_page()
+ * to get the gigantic page.
+ */
+static struct page *__hugetlb_alloc_gigantic_page(struct hstate *h,
+ struct vm_area_struct *vma, unsigned long addr, int nid)
+{
+ struct page *page;
+ nodemask_t *nodes_mask;
+
+ /* Not NUMA */
+ if (!IS_ENABLED(CONFIG_NUMA)) {
+ if (nid == NUMA_NO_NODE)
+ nid = numa_mem_id();
+
+ page = alloc_gigantic_page(nid, huge_page_order(h));
+ if (page)
+ prep_compound_gigantic_page(page, huge_page_order(h));
+
+ return page;
+ }
+
+ /* NUMA && !vma */
+ if (!vma) {
+ NODEMASK_ALLOC(nodemask_t, nodes_allowed,
+ GFP_KERNEL | __GFP_NORETRY);
+
+ if (nid == NUMA_NO_NODE) {
+ if (!init_nodemask_of_mempolicy(nodes_allowed)) {
+ NODEMASK_FREE(nodes_allowed);
+ nodes_allowed = &node_states[N_MEMORY];
+ }
+ } else if (nodes_allowed) {
+ init_nodemask_of_node(nodes_allowed, nid);
+ } else {
+ nodes_allowed = &node_states[N_MEMORY];
+ }
+
+ page = alloc_fresh_gigantic_page(h, nodes_allowed, true);
+
+ if (nodes_allowed != &node_states[N_MEMORY])
+ NODEMASK_FREE(nodes_allowed);
+
+ return page;
+ }
+
+ /* NUMA && vma */
+ nodes_mask = huge_nodemask(vma, addr);
+ if (nodes_mask) {
+ page = alloc_fresh_gigantic_page(h, nodes_mask, true);
+ if (page)
+ return page;
+ }
+ return NULL;
+}
+
+/*
+ * There are 3 ways this can get called:
* 1. With vma+addr: we use the VMA's memory policy
* 2. With !vma, but nid=NUMA_NO_NODE: We try to allocate a huge
* page from any node, and let the buddy allocator itself figure
_
Patches currently in -mm which might be from shijie.huang@arm.com are
mm-hugetlb-add-a-new-function-to-allocate-a-new-gigantic-page-v2.patch
mm-hugetlb-support-gigantic-surplus-pages.patch
mm-hugetlb-add-description-for-alloc_gigantic_page.patch
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2016-12-03 0:37 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2016-12-03 0:37 [to-be-updated] mm-hugetlb-add-a-new-function-to-allocate-a-new-gigantic-page.patch removed from -mm tree akpm
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).