hugetlb: restrict hugepage_migration_support() to x86_64

Currently hugepage migration is available for all archs which support
pmd-level hugepage, but testing is done only for x86_64 and there're
bugs for other archs.  So to avoid breaking such archs, this patch
limits the availability strictly to x86_64 until developers of other
archs get interested in enabling this feature.

Simply disabling hugepage migration on non-x86_64 archs is not enough to
fix the reported problem where sys_move_pages() hits the BUG_ON() in
follow_page(FOLL_GET), so let's fix this by checking if hugepage
migration is supported in vma_migratable().

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Reported-by: Michael Ellerman <mpe@ellerman.id.au>
Tested-by: Michael Ellerman <mpe@ellerman.id.au>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Miller <davem@davemloft.net>
Cc: <stable@vger.kernel.org>	[3.12+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c
index 54ee616..66781bf 100644 (file)
--- a/arch/arm/mm/hugetlbpage.c
+++ b/arch/arm/mm/hugetlbpage.c
@@ -56,8 +56,3 @@ int pmd_huge(pmd_t pmd)
 {
        return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
 }
-
-int pmd_huge_support(void)
-{
-       return 1;
-}

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 31eb959..023747b 100644 (file)
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -58,11 +58,6 @@ int pud_huge(pud_t pud)
 #endif
 }
 
-int pmd_huge_support(void)
-{
-       return 1;
-}
-
 static __init int setup_hugepagesz(char *opt)
 {
        unsigned long ps = memparse(opt, &opt);

diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c
index 68232db..76069c1 100644 (file)
--- a/arch/ia64/mm/hugetlbpage.c
+++ b/arch/ia64/mm/hugetlbpage.c
@@ -114,11 +114,6 @@ int pud_huge(pud_t pud)
        return 0;
 }
 
-int pmd_huge_support(void)
-{
-       return 0;
-}
-
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write)
 {

diff --git a/arch/metag/mm/hugetlbpage.c b/arch/metag/mm/hugetlbpage.c
index 0424315..3c52fa6 100644 (file)
--- a/arch/metag/mm/hugetlbpage.c
+++ b/arch/metag/mm/hugetlbpage.c
@@ -110,11 +110,6 @@ int pud_huge(pud_t pud)
        return 0;
 }
 
-int pmd_huge_support(void)
-{
-       return 1;
-}
-
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
                             pmd_t *pmd, int write)
 {

diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c
index 77e0ae0..4ec8ee1 100644 (file)
--- a/arch/mips/mm/hugetlbpage.c
+++ b/arch/mips/mm/hugetlbpage.c
@@ -84,11 +84,6 @@ int pud_huge(pud_t pud)
        return (pud_val(pud) & _PAGE_HUGE) != 0;
 }
 
-int pmd_huge_support(void)
-{
-       return 1;
-}
-
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address,
                pmd_t *pmd, int write)

diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index eb92365..7e70ae9 100644 (file)
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -86,11 +86,6 @@ int pgd_huge(pgd_t pgd)
         */
        return ((pgd_val(pgd) & 0x3) != 0x0);
 }
-
-int pmd_huge_support(void)
-{
-       return 1;
-}
 #else
 int pmd_huge(pmd_t pmd)
 {
@@ -106,11 +101,6 @@ int pgd_huge(pgd_t pgd)
 {
        return 0;
 }
-
-int pmd_huge_support(void)
-{
-       return 0;
-}
 #endif
 
 pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)

diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 0727a55..0ff66a7 100644 (file)
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -220,11 +220,6 @@ int pud_huge(pud_t pud)
        return 0;
 }
 
-int pmd_huge_support(void)
-{
-       return 1;
-}
-
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
                             pmd_t *pmdp, int write)
 {

diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c
index 0d676a4..d776234 100644 (file)
--- a/arch/sh/mm/hugetlbpage.c
+++ b/arch/sh/mm/hugetlbpage.c
@@ -83,11 +83,6 @@ int pud_huge(pud_t pud)
        return 0;
 }
 
-int pmd_huge_support(void)
-{
-       return 0;
-}
-
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
                             pmd_t *pmd, int write)
 {

diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index 9bd9ce8..d329537 100644 (file)
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -231,11 +231,6 @@ int pud_huge(pud_t pud)
        return 0;
 }
 
-int pmd_huge_support(void)
-{
-       return 0;
-}
-
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
                             pmd_t *pmd, int write)
 {

diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c
index 0cb3bba..e514899 100644 (file)
--- a/arch/tile/mm/hugetlbpage.c
+++ b/arch/tile/mm/hugetlbpage.c
@@ -166,11 +166,6 @@ int pud_huge(pud_t pud)
        return !!(pud_val(pud) & _PAGE_HUGE_PAGE);
 }
 
-int pmd_huge_support(void)
-{
-       return 1;
-}
-
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
                             pmd_t *pmd, int write)
 {

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7d5feb5..e41b258 100644 (file)
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1873,6 +1873,10 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK
        def_bool y
        depends on X86_64 || X86_PAE
 
+config ARCH_ENABLE_HUGEPAGE_MIGRATION
+       def_bool y
+       depends on X86_64 && HUGETLB_PAGE && MIGRATION
+
 menu "Power management and ACPI options"
 
 config ARCH_HIBERNATION_HEADER

diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 8c9f647..8b977eb 100644 (file)
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -58,11 +58,6 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 {
        return NULL;
 }
-
-int pmd_huge_support(void)
-{
-       return 0;
-}
 #else
 
 struct page *
@@ -80,11 +75,6 @@ int pud_huge(pud_t pud)
 {
        return !!(pud_val(pud) & _PAGE_PSE);
 }
-
-int pmd_huge_support(void)
-{
-       return 1;
-}
 #endif
 
 #ifdef CONFIG_HUGETLB_PAGE

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index b65166d..d0bad1a 100644 (file)
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -392,15 +392,13 @@ static inline pgoff_t basepage_index(struct page *page)
 
 extern void dissolve_free_huge_pages(unsigned long start_pfn,
                                     unsigned long end_pfn);
-int pmd_huge_support(void);
-/*
- * Currently hugepage migration is enabled only for pmd-based hugepage.
- * This function will be updated when hugepage migration is more widely
- * supported.
- */
 static inline int hugepage_migration_support(struct hstate *h)
 {
-       return pmd_huge_support() && (huge_page_shift(h) == PMD_SHIFT);
+#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
+       return huge_page_shift(h) == PMD_SHIFT;
+#else
+       return 0;
+#endif
 }
 
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
@@ -450,7 +448,6 @@ static inline pgoff_t basepage_index(struct page *page)
        return page->index;
 }
 #define dissolve_free_huge_pages(s, e) do {} while (0)
-#define pmd_huge_support()     0
 #define hugepage_migration_support(h)  0
 
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 3c1b968..f230a97 100644 (file)
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -175,6 +175,12 @@ static inline int vma_migratable(struct vm_area_struct *vma)
 {
        if (vma->vm_flags & (VM_IO | VM_PFNMAP))
                return 0;
+
+#ifndef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
+       if (vma->vm_flags & VM_HUGETLB)
+               return 0;
+#endif
+
        /*
         * Migration allocates pages in the highest zone. If we cannot
         * do so then migration (at least from node to node) is not

diff --git a/mm/Kconfig b/mm/Kconfig
index 28cec51..75ac479 100644 (file)
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -267,6 +267,9 @@ config MIGRATION
          pages as migration can relocate pages to satisfy a huge page
          allocation instead of reclaiming.
 
+config ARCH_ENABLE_HUGEPAGE_MIGRATION
+       boolean
+
 config PHYS_ADDR_T_64BIT
        def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT