diff options
author | Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> | 2015-02-12 00:28:11 +0100 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-02-12 02:06:06 +0100 |
commit | 1e25a271c8ac1c9faebf4eb3fa609189e4e7b1b6 (patch) | |
tree | bed90c6a138544e00ec6220737ba7516e6705240 | |
parent | mm: /proc/pid/clear_refs: avoid split_huge_page() (diff) | |
download | linux-1e25a271c8ac1c9faebf4eb3fa609189e4e7b1b6.tar.xz linux-1e25a271c8ac1c9faebf4eb3fa609189e4e7b1b6.zip |
mincore: apply page table walker on do_mincore()
This patch makes do_mincore() use walk_page_vma(), which reduces many
lines of code by using common page table walk code.
[daeseok.youn@gmail.com: remove unneeded variable 'err']
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Daeseok Youn <daeseok.youn@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r-- | mm/huge_memory.c | 20 | ||||
-rw-r--r-- | mm/mincore.c | 166 |
2 files changed, 60 insertions, 126 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 0531ea7dd7cf..29bc6e471df4 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1412,26 +1412,6 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, return ret; } -int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, unsigned long end, - unsigned char *vec) -{ - spinlock_t *ptl; - int ret = 0; - - if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { - /* - * All logical pages in the range are present - * if backed by a huge page. - */ - spin_unlock(ptl); - memset(vec, 1, (end - addr) >> PAGE_SHIFT); - ret = 1; - } - - return ret; -} - int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long old_end, diff --git a/mm/mincore.c b/mm/mincore.c index 46527c023e0c..be25efde64a4 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -19,38 +19,25 @@ #include <asm/uaccess.h> #include <asm/pgtable.h> -static void mincore_hugetlb_page_range(struct vm_area_struct *vma, - unsigned long addr, unsigned long end, - unsigned char *vec) +static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, + unsigned long end, struct mm_walk *walk) { #ifdef CONFIG_HUGETLB_PAGE - struct hstate *h; + unsigned char present; + unsigned char *vec = walk->private; - h = hstate_vma(vma); - while (1) { - unsigned char present; - pte_t *ptep; - /* - * Huge pages are always in RAM for now, but - * theoretically it needs to be checked. - */ - ptep = huge_pte_offset(current->mm, - addr & huge_page_mask(h)); - present = ptep && !huge_pte_none(huge_ptep_get(ptep)); - while (1) { - *vec = present; - vec++; - addr += PAGE_SIZE; - if (addr == end) - return; - /* check hugepage border */ - if (!(addr & ~huge_page_mask(h))) - break; - } - } + /* + * Hugepages under user process are always in RAM and never + * swapped out, but theoretically it needs to be checked. + */ + present = pte && !huge_pte_none(huge_ptep_get(pte)); + for (; addr != end; vec++, addr += PAGE_SIZE) + *vec = present; + walk->private = vec; #else BUG(); #endif + return 0; } /* @@ -94,9 +81,8 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) return present; } -static void mincore_unmapped_range(struct vm_area_struct *vma, - unsigned long addr, unsigned long end, - unsigned char *vec) +static int __mincore_unmapped_range(unsigned long addr, unsigned long end, + struct vm_area_struct *vma, unsigned char *vec) { unsigned long nr = (end - addr) >> PAGE_SHIFT; int i; @@ -111,23 +97,44 @@ static void mincore_unmapped_range(struct vm_area_struct *vma, for (i = 0; i < nr; i++) vec[i] = 0; } + return nr; +} + +static int mincore_unmapped_range(unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + walk->private += __mincore_unmapped_range(addr, end, + walk->vma, walk->private); + return 0; } -static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, unsigned long end, - unsigned char *vec) +static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, + struct mm_walk *walk) { - unsigned long next; spinlock_t *ptl; + struct vm_area_struct *vma = walk->vma; pte_t *ptep; + unsigned char *vec = walk->private; + int nr = (end - addr) >> PAGE_SHIFT; + + if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { + memset(vec, 1, nr); + spin_unlock(ptl); + goto out; + } + + if (pmd_trans_unstable(pmd)) { + __mincore_unmapped_range(addr, end, vma, vec); + goto out; + } - ptep = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); - do { + ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + for (; addr != end; ptep++, addr += PAGE_SIZE) { pte_t pte = *ptep; - next = addr + PAGE_SIZE; if (pte_none(pte)) - mincore_unmapped_range(vma, addr, next, vec); + __mincore_unmapped_range(addr, addr + PAGE_SIZE, + vma, vec); else if (pte_present(pte)) *vec = 1; else { /* pte is a swap entry */ @@ -150,69 +157,12 @@ static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd, } } vec++; - } while (ptep++, addr = next, addr != end); + } pte_unmap_unlock(ptep - 1, ptl); -} - -static void mincore_pmd_range(struct vm_area_struct *vma, pud_t *pud, - unsigned long addr, unsigned long end, - unsigned char *vec) -{ - unsigned long next; - pmd_t *pmd; - - pmd = pmd_offset(pud, addr); - do { - next = pmd_addr_end(addr, end); - if (pmd_trans_huge(*pmd)) { - if (mincore_huge_pmd(vma, pmd, addr, next, vec)) { - vec += (next - addr) >> PAGE_SHIFT; - continue; - } - /* fall through */ - } - if (pmd_none_or_trans_huge_or_clear_bad(pmd)) - mincore_unmapped_range(vma, addr, next, vec); - else - mincore_pte_range(vma, pmd, addr, next, vec); - vec += (next - addr) >> PAGE_SHIFT; - } while (pmd++, addr = next, addr != end); -} - -static void mincore_pud_range(struct vm_area_struct *vma, pgd_t *pgd, - unsigned long addr, unsigned long end, - unsigned char *vec) -{ - unsigned long next; - pud_t *pud; - - pud = pud_offset(pgd, addr); - do { - next = pud_addr_end(addr, end); - if (pud_none_or_clear_bad(pud)) - mincore_unmapped_range(vma, addr, next, vec); - else - mincore_pmd_range(vma, pud, addr, next, vec); - vec += (next - addr) >> PAGE_SHIFT; - } while (pud++, addr = next, addr != end); -} - -static void mincore_page_range(struct vm_area_struct *vma, - unsigned long addr, unsigned long end, - unsigned char *vec) -{ - unsigned long next; - pgd_t *pgd; - - pgd = pgd_offset(vma->vm_mm, addr); - do { - next = pgd_addr_end(addr, end); - if (pgd_none_or_clear_bad(pgd)) - mincore_unmapped_range(vma, addr, next, vec); - else - mincore_pud_range(vma, pgd, addr, next, vec); - vec += (next - addr) >> PAGE_SHIFT; - } while (pgd++, addr = next, addr != end); +out: + walk->private += nr; + cond_resched(); + return 0; } /* @@ -224,18 +174,22 @@ static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *v { struct vm_area_struct *vma; unsigned long end; + int err; + struct mm_walk mincore_walk = { + .pmd_entry = mincore_pte_range, + .pte_hole = mincore_unmapped_range, + .hugetlb_entry = mincore_hugetlb, + .private = vec, + }; vma = find_vma(current->mm, addr); if (!vma || addr < vma->vm_start) return -ENOMEM; - + mincore_walk.mm = vma->vm_mm; end = min(vma->vm_end, addr + (pages << PAGE_SHIFT)); - - if (is_vm_hugetlb_page(vma)) - mincore_hugetlb_page_range(vma, addr, end, vec); - else - mincore_page_range(vma, addr, end, vec); - + err = walk_page_range(addr, end, &mincore_walk); + if (err < 0) + return err; return (end - addr) >> PAGE_SHIFT; } |