summaryrefslogtreecommitdiffstats
path: root/mm/huge_memory.c
diff options
context:
space:
mode:
authorMel Gorman <mgorman@suse.de>2012-10-25 14:16:31 +0200
committerMel Gorman <mgorman@suse.de>2012-12-11 14:42:39 +0000
commitd10e63f29488b0f312a443f9507ea9b6fd3c9090 (patch)
treeb39e3caa5d25e9e5ebad84c606a724e25c6b8e91 /mm/huge_memory.c
parent1ba6e0b50b479cbadb8f05ebde3020da9ac87201 (diff)
downloadlinux-d10e63f29488b0f312a443f9507ea9b6fd3c9090.tar.gz
linux-d10e63f29488b0f312a443f9507ea9b6fd3c9090.tar.bz2
linux-d10e63f29488b0f312a443f9507ea9b6fd3c9090.zip
mm: numa: Create basic numa page hinting infrastructure
Note: This patch started as "mm/mpol: Create special PROT_NONE infrastructure" and preserves the basic idea but steals *very* heavily from "autonuma: numa hinting page faults entry points" for the actual fault handlers without the migration parts. The end result is barely recognisable as either patch so all Signed-off and Reviewed-bys are dropped. If Peter, Ingo and Andrea are ok with this version, I will re-add the signed-offs-by to reflect the history. In order to facilitate a lazy -- fault driven -- migration of pages, create a special transient PAGE_NUMA variant, we can then use the 'spurious' protection faults to drive our migrations from. The meaning of PAGE_NUMA depends on the architecture but on x86 it is effectively PROT_NONE. Actual PROT_NONE mappings will not generate these NUMA faults for the reason that the page fault code checks the permission on the VMA (and will throw a segmentation fault on actual PROT_NONE mappings), before it ever calls handle_mm_fault. [dhillf@gmail.com: Fix typo] Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
Diffstat (limited to 'mm/huge_memory.c')
-rw-r--r--mm/huge_memory.c22
1 files changed, 22 insertions, 0 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index cd24aa562144..f5f37630c54d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1018,6 +1018,28 @@ out:
return page;
}
+/* NUMA hinting page fault entry point for trans huge pmds */
+int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr,
+ pmd_t pmd, pmd_t *pmdp)
+{
+ struct page *page;
+ unsigned long haddr = addr & HPAGE_PMD_MASK;
+
+ spin_lock(&mm->page_table_lock);
+ if (unlikely(!pmd_same(pmd, *pmdp)))
+ goto out_unlock;
+
+ page = pmd_page(pmd);
+ pmd = pmd_mknonnuma(pmd);
+ set_pmd_at(mm, haddr, pmdp, pmd);
+ VM_BUG_ON(pmd_numa(*pmdp));
+ update_mmu_cache_pmd(vma, addr, pmdp);
+
+out_unlock:
+ spin_unlock(&mm->page_table_lock);
+ return 0;
+}
+
int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
pmd_t *pmd, unsigned long addr)
{