3.14-stable review patch. If anyone has any objections, please let me know.
------------------
From: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
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@xxxxxxxxxxxxx>
Reported-by: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Tested-by: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Acked-by: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: Russell King <rmk@xxxxxxxxxxxxxxxx>
Cc: Martin Schwidefsky <schwidefsky@xxxxxxxxxx>
Cc: James Hogan <james.hogan@xxxxxxxxxx>
Cc: Ralf Baechle <ralf@xxxxxxxxxxxxxx>
Cc: David Miller <davem@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/arm/mm/hugetlbpage.c | 5 -----
arch/arm64/mm/hugetlbpage.c | 5 -----
arch/ia64/mm/hugetlbpage.c | 5 -----
arch/metag/mm/hugetlbpage.c | 5 -----
arch/mips/mm/hugetlbpage.c | 5 -----
arch/powerpc/mm/hugetlbpage.c | 10 ----------
arch/s390/mm/hugetlbpage.c | 5 -----
arch/sh/mm/hugetlbpage.c | 5 -----
arch/sparc/mm/hugetlbpage.c | 5 -----
arch/tile/mm/hugetlbpage.c | 5 -----
arch/x86/Kconfig | 4 ++++
arch/x86/mm/hugetlbpage.c | 10 ----------
include/linux/hugetlb.h | 13 +++++--------
include/linux/mempolicy.h | 6 ++++++
mm/Kconfig | 3 +++
15 files changed, 18 insertions(+), 73 deletions(-)
--- 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;
-}
--- 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);
--- 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)
{
--- 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)
{
--- 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)
--- 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)
--- 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)
{
--- 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)
{
--- 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)
{
--- 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)
{
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1909,6 +1909,10 @@ 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
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -58,11 +58,6 @@ follow_huge_pmd(struct mm_struct *mm, un
{
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
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -382,15 +382,13 @@ static inline pgoff_t basepage_index(str
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,
@@ -430,7 +428,6 @@ static inline pgoff_t basepage_index(str
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,
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -176,6 +176,12 @@ static inline int vma_migratable(struct
{
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
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -263,6 +263,9 @@ 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
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html