hugetlb: restrict hugepage_migration_support() to x86_64

commit c177c81e09e517bbf75b67762cdab1b83aba6976 upstream.

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>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>

diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c
index 54ee6163c1814453298272fdb182341e3a5ffcdf..66781bf34077cb540a67f845eeeb919c2decfc4e 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 31eb959e9aa81d05f16269e3bb500a965cb7cd48..023747bf4dd7dd2025a17c3fc44244aa1b0f7b00 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 68232db98baa74856752a86fc63cc12678e76787..76069c18ee42c186edf37c680ee78249d553b4fc 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 042431509b5664bca9bc6c930b296c77a064079a..3c52fa6d0f8e24030294fecacc26498f5de9ffe5 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 01fda4419ed09de2e5adbfcd0b318023f3cc7664..a7fee0dfb7a9daaeb67616804f00cac7365d778f 100644 (file)
--- a/arch/mips/mm/hugetlbpage.c
+++ b/arch/mips/mm/hugetlbpage.c
@@ -85,11 +85,6 @@ 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 d67db4bd672dd4223065c9b5470ee368a9456d1d..834ca8eb38f202e01c5151fdb56b13197ed6acc8 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 d261c62e40a68f8c885d6019e6a0ef27d9497c4c..248445f92604efff09a5188352c3e6fba1248bb0 100644 (file)
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -223,11 +223,6 @@ 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 0d676a41081e873582a68cf3c1d179ab51dd529d..d7762349ea4869be1b40898a5ae7e6ff8e79c6aa 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 96399646570a780e1b38a6324994c5f71470bb0b..d2b59441ebddfb84080da0fcadff6921e71342f6 100644 (file)
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -234,11 +234,6 @@ 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 0cb3bbaa580c5dbc5ed00417ffd4b6e002c03813..e514899e1100319dc83fe69530f1aad67b17ceea 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 f67e839f06c845e406d81c8b2be285ced8b57448..eb2dfa61eabe569d2a5125ae334132576360e551 100644 (file)
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1881,6 +1881,10 @@ config USE_PERCPU_NUMA_NODE_ID
        def_bool y
        depends on NUMA
 
+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 9d980d88b7477a82f757e75d0efda0c867c76d43..fa029fb2afaec9cbc31c9bcbf63a6087f842aee1 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
 
 /* x86_64 also uses this file */

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 6125579b52076014d681332a586b701563ee2d75..5214ff63c35123a081e003e18e3991c3709c8f91 100644 (file)
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -387,15 +387,13 @@ 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
 }
 
 #else  /* CONFIG_HUGETLB_PAGE */
@@ -425,7 +423,6 @@ 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
 #endif /* CONFIG_HUGETLB_PAGE */
 

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index da6716b9e3fea8148f45f57ac556367b547f839f..ccc1b718c8f340543094c2b17065a1670c66e1fa 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 394838f489ebae1b9d00660af54ceac857538653..2a092f5fa95ad14018c9734c252348f8b4125a56 100644 (file)
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -254,6 +254,9 @@ 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