The patch titled
Subject: mm: accelerate mm_populate() treatment of THP pages
has been added to the -mm tree. Its filename is
mm-accelerate-mm_populate-treatment-of-thp-pages.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Michel Lespinasse <walken@xxxxxxxxxx>
Subject: mm: accelerate mm_populate() treatment of THP pages
This change adds a follow_page_mask function which is equivalent to
follow_page, but with an extra page_mask argument.
follow_page_mask sets *page_mask to HPAGE_PMD_NR - 1 when it encounters a
THP page, and to 0 in other cases.
__get_user_pages() makes use of this in order to accelerate populating THP
ranges - that is, when both the pages and vmas arrays are NULL, we don't
need to iterate HPAGE_PMD_NR times to cover a single THP page (and we also
avoid taking mm->page_table_lock that many times).
Signed-off-by: Michel Lespinasse <walken@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mm.h | 13 +++++++++++--
mm/memory.c | 31 +++++++++++++++++++++++--------
mm/nommu.c | 6 ++++--
3 files changed, 38 insertions(+), 12 deletions(-)
diff -puN include/linux/mm.h~mm-accelerate-mm_populate-treatment-of-thp-pages include/linux/mm.h
--- a/include/linux/mm.h~mm-accelerate-mm_populate-treatment-of-thp-pages
+++ a/include/linux/mm.h
@@ -1626,8 +1626,17 @@ int vm_insert_pfn(struct vm_area_struct
int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn);
-struct page *follow_page(struct vm_area_struct *, unsigned long address,
- unsigned int foll_flags);
+struct page *follow_page_mask(struct vm_area_struct *vma,
+ unsigned long address, unsigned int foll_flags,
+ unsigned int *page_mask);
+
+static inline struct page *follow_page(struct vm_area_struct *vma,
+ unsigned long address, unsigned int foll_flags)
+{
+ unsigned int unused_page_mask;
+ return follow_page_mask(vma, address, foll_flags, &unused_page_mask);
+}
+
#define FOLL_WRITE 0x01 /* check pte is writable */
#define FOLL_TOUCH 0x02 /* mark page accessed */
#define FOLL_GET 0x04 /* do get_page on page */
diff -puN mm/memory.c~mm-accelerate-mm_populate-treatment-of-thp-pages mm/memory.c
--- a/mm/memory.c~mm-accelerate-mm_populate-treatment-of-thp-pages
+++ a/mm/memory.c
@@ -1462,10 +1462,11 @@ int zap_vma_ptes(struct vm_area_struct *
EXPORT_SYMBOL_GPL(zap_vma_ptes);
/**
- * follow_page - look up a page descriptor from a user-virtual address
+ * follow_page_mask - look up a page descriptor from a user-virtual address
* @vma: vm_area_struct mapping @address
* @address: virtual address to look up
* @flags: flags modifying lookup behaviour
+ * @page_mask: on output, *page_mask is set according to the size of the page
*
* @flags can have FOLL_ flags set, defined in <linux/mm.h>
*
@@ -1473,8 +1474,9 @@ EXPORT_SYMBOL_GPL(zap_vma_ptes);
* an error pointer if there is a mapping to something not represented
* by a page descriptor (see also vm_normal_page()).
*/
-struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
- unsigned int flags)
+struct page *follow_page_mask(struct vm_area_struct *vma,
+ unsigned long address, unsigned int flags,
+ unsigned int *page_mask)
{
pgd_t *pgd;
pud_t *pud;
@@ -1484,6 +1486,8 @@ struct page *follow_page(struct vm_area_
struct page *page;
struct mm_struct *mm = vma->vm_mm;
+ *page_mask = 0;
+
page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
if (!IS_ERR(page)) {
BUG_ON(flags & FOLL_GET);
@@ -1530,6 +1534,7 @@ struct page *follow_page(struct vm_area_
page = follow_trans_huge_pmd(vma, address,
pmd, flags);
spin_unlock(&mm->page_table_lock);
+ *page_mask = HPAGE_PMD_NR - 1;
goto out;
}
} else
@@ -1684,6 +1689,7 @@ long __get_user_pages(struct task_struct
{
long i;
unsigned long vm_flags;
+ unsigned int page_mask;
if (!nr_pages)
return 0;
@@ -1761,6 +1767,7 @@ long __get_user_pages(struct task_struct
get_page(page);
}
pte_unmap(pte);
+ page_mask = 0;
goto next_page;
}
@@ -1778,6 +1785,7 @@ long __get_user_pages(struct task_struct
do {
struct page *page;
unsigned int foll_flags = gup_flags;
+ unsigned int page_increm;
/*
* If we have a pending SIGKILL, don't keep faulting
@@ -1787,7 +1795,8 @@ long __get_user_pages(struct task_struct
return i ? i : -ERESTARTSYS;
cond_resched();
- while (!(page = follow_page(vma, start, foll_flags))) {
+ while (!(page = follow_page_mask(vma, start,
+ foll_flags, &page_mask))) {
int ret;
unsigned int fault_flags = 0;
@@ -1861,13 +1870,19 @@ long __get_user_pages(struct task_struct
flush_anon_page(vma, page, start);
flush_dcache_page(page);
+ page_mask = 0;
}
next_page:
- if (vmas)
+ if (vmas) {
vmas[i] = vma;
- i++;
- start += PAGE_SIZE;
- nr_pages--;
+ page_mask = 0;
+ }
+ page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
+ if (page_increm > nr_pages)
+ page_increm = nr_pages;
+ i += page_increm;
+ start += page_increm * PAGE_SIZE;
+ nr_pages -= page_increm;
} while (nr_pages && start < vma->vm_end);
} while (nr_pages);
return i;
diff -puN mm/nommu.c~mm-accelerate-mm_populate-treatment-of-thp-pages mm/nommu.c
--- a/mm/nommu.c~mm-accelerate-mm_populate-treatment-of-thp-pages
+++ a/mm/nommu.c
@@ -1817,9 +1817,11 @@ SYSCALL_DEFINE5(mremap, unsigned long, a
return ret;
}
-struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
- unsigned int foll_flags)
+struct page *follow_page_mask(struct vm_area_struct *vma,
+ unsigned long address, unsigned int flags,
+ unsigned int *page_mask)
{
+ *page_mask = 0;
return NULL;
}
_
Patches currently in -mm which might be from walken@xxxxxxxxxx are
thp-avoid-dumping-huge-zero-page.patch
linux-next.patch
mm-remove-free_area_cache-use-in-powerpc-architecture.patch
mm-use-vm_unmapped_area-on-powerpc-architecture.patch
mm-use-vm_unmapped_area-on-ia64-architecture.patch
mm-use-vm_unmapped_area-in-hugetlbfs-on-ia64-architecture.patch
mm-use-vm_unmapped_area-on-parisc-architecture.patch
mm-make-mlockall-preserve-flags-other-than-vm_locked-in-def_flags.patch
mm-remap_file_pages-fixes.patch
mm-introduce-mm_populate-for-populating-new-vmas.patch
mm-use-mm_populate-for-blocking-remap_file_pages.patch
mm-use-mm_populate-when-adjusting-brk-with-mcl_future-in-effect.patch
mm-use-mm_populate-for-mremap-of-vm_locked-vmas.patch
mm-remove-flags-argument-to-mmap_region.patch
mm-remove-flags-argument-to-mmap_region-fix.patch
mm-directly-use-__mlock_vma_pages_range-in-find_extend_vma.patch
mm-introduce-vm_populate-flag-to-better-deal-with-racy-userspace-programs.patch
mm-make-do_mmap_pgoff-return-populate-as-a-size-in-bytes-not-as-a-bool.patch
mm-use-long-type-for-page-counts-in-mm_populate-and-get_user_pages.patch
mm-use-long-type-for-page-counts-in-mm_populate-and-get_user_pages-fix.patch
mm-accelerate-mm_populate-treatment-of-thp-pages.patch
mm-accelerate-munlock-treatment-of-thp-pages.patch
mm-remove-free_area_cache.patch
mm-use-vm_unmapped_area-on-frv-architecture.patch
mm-use-vm_unmapped_area-on-alpha-architecture.patch
mtd-mtd_nandecctest-use-prandom_bytes-instead-of-get_random_bytes.patch
mtd-mtd_oobtest-convert-to-use-prandom-library.patch
mtd-mtd_pagetest-convert-to-use-prandom-library.patch
mtd-mtd_speedtest-use-prandom_bytes.patch
mtd-mtd_subpagetest-convert-to-use-prandom-library.patch
mtd-mtd_stresstest-use-prandom_bytes.patch
mutex-subsystem-synchro-test-module.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
