The patch titled
Subject: shmem, thp: respect MADV_{NO,}HUGEPAGE for file mappings
has been added to the -mm tree. Its filename is
shmem-thp-respect-madv_nohugepage-for-file-mappings.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/shmem-thp-respect-madv_nohugepage-for-file-mappings.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/shmem-thp-respect-madv_nohugepage-for-file-mappings.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: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Subject: shmem, thp: respect MADV_{NO,}HUGEPAGE for file mappings
Let's wire up existing madvise() hugepage hints for file mappings.
MADV_HUGEPAGE advise shmem to allocate huge page on page fault in the
VMA. It only has effect if the filesystem is mounted with huge=advise or
huge=within_size.
MADV_NOHUGEPAGE prevents hugepage from being allocated on page fault in
the VMA. It doesn't prevent a huge page from being allocated by other
means, i.e. page fault into different mapping or write(2) into file.
Link: http://lkml.kernel.org/r/1466021202-61880-31-git-send-email-kirill.shutemov@xxxxxxxxxxxxxxx
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/huge_memory.c | 19 +++++--------------
mm/shmem.c | 20 +++++++++++++++++---
2 files changed, 22 insertions(+), 17 deletions(-)
diff -puN mm/huge_memory.c~shmem-thp-respect-madv_nohugepage-for-file-mappings mm/huge_memory.c
--- a/mm/huge_memory.c~shmem-thp-respect-madv_nohugepage-for-file-mappings
+++ a/mm/huge_memory.c
@@ -1835,7 +1835,7 @@ spinlock_t *__pmd_trans_huge_lock(pmd_t
return NULL;
}
-#define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE)
+#define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE)
int hugepage_madvise(struct vm_area_struct *vma,
unsigned long *vm_flags, int advice)
@@ -1851,11 +1851,6 @@ int hugepage_madvise(struct vm_area_stru
if (mm_has_pgste(vma->vm_mm))
return 0;
#endif
- /*
- * Be somewhat over-protective like KSM for now!
- */
- if (*vm_flags & VM_NO_THP)
- return -EINVAL;
*vm_flags &= ~VM_NOHUGEPAGE;
*vm_flags |= VM_HUGEPAGE;
/*
@@ -1863,15 +1858,11 @@ int hugepage_madvise(struct vm_area_stru
* register it here without waiting a page fault that
* may not happen any time soon.
*/
- if (unlikely(khugepaged_enter_vma_merge(vma, *vm_flags)))
+ if (!(*vm_flags & VM_NO_KHUGEPAGED) &&
+ khugepaged_enter_vma_merge(vma, *vm_flags))
return -ENOMEM;
break;
case MADV_NOHUGEPAGE:
- /*
- * Be somewhat over-protective like KSM for now!
- */
- if (*vm_flags & VM_NO_THP)
- return -EINVAL;
*vm_flags &= ~VM_HUGEPAGE;
*vm_flags |= VM_NOHUGEPAGE;
/*
@@ -1979,7 +1970,7 @@ int khugepaged_enter_vma_merge(struct vm
* page fault if needed.
*/
return 0;
- if (vma->vm_ops || (vm_flags & VM_NO_THP))
+ if (vma->vm_ops || (vm_flags & VM_NO_KHUGEPAGED))
/* khugepaged not yet working on file or special mappings */
return 0;
hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
@@ -2371,7 +2362,7 @@ static bool hugepage_vma_check(struct vm
return false;
if (is_vma_temporary_stack(vma))
return false;
- return !(vma->vm_flags & VM_NO_THP);
+ return !(vma->vm_flags & VM_NO_KHUGEPAGED);
}
/*
diff -puN mm/shmem.c~shmem-thp-respect-madv_nohugepage-for-file-mappings mm/shmem.c
--- a/mm/shmem.c~shmem-thp-respect-madv_nohugepage-for-file-mappings
+++ a/mm/shmem.c
@@ -101,6 +101,8 @@ struct shmem_falloc {
enum sgp_type {
SGP_READ, /* don't exceed i_size, don't allocate page */
SGP_CACHE, /* don't exceed i_size, may allocate page */
+ SGP_NOHUGE, /* like SGP_CACHE, but no huge pages */
+ SGP_HUGE, /* like SGP_CACHE, huge pages preferred */
SGP_WRITE, /* may exceed i_size, may allocate !Uptodate page */
SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */
};
@@ -1409,6 +1411,7 @@ static int shmem_getpage_gfp(struct inod
struct mem_cgroup *memcg;
struct page *page;
swp_entry_t swap;
+ enum sgp_type sgp_huge = sgp;
pgoff_t hindex = index;
int error;
int once = 0;
@@ -1416,6 +1419,8 @@ static int shmem_getpage_gfp(struct inod
if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT))
return -EFBIG;
+ if (sgp == SGP_NOHUGE || sgp == SGP_HUGE)
+ sgp = SGP_CACHE;
repeat:
swap.val = 0;
page = find_lock_entry(mapping, index);
@@ -1534,7 +1539,7 @@ repeat:
/* shmem_symlink() */
if (mapping->a_ops != &shmem_aops)
goto alloc_nohuge;
- if (shmem_huge == SHMEM_HUGE_DENY)
+ if (shmem_huge == SHMEM_HUGE_DENY || sgp_huge == SGP_NOHUGE)
goto alloc_nohuge;
if (shmem_huge == SHMEM_HUGE_FORCE)
goto alloc_huge;
@@ -1551,7 +1556,9 @@ repeat:
goto alloc_huge;
/* fallthrough */
case SHMEM_HUGE_ADVISE:
- /* TODO: wire up fadvise()/madvise() */
+ if (sgp_huge == SGP_HUGE)
+ goto alloc_huge;
+ /* TODO: implement fadvise() hints */
goto alloc_nohuge;
}
@@ -1680,6 +1687,7 @@ static int shmem_fault(struct vm_area_st
{
struct inode *inode = file_inode(vma->vm_file);
gfp_t gfp = mapping_gfp_mask(inode->i_mapping);
+ enum sgp_type sgp;
int error;
int ret = VM_FAULT_LOCKED;
@@ -1741,7 +1749,13 @@ static int shmem_fault(struct vm_area_st
spin_unlock(&inode->i_lock);
}
- error = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, SGP_CACHE,
+ sgp = SGP_CACHE;
+ if (vma->vm_flags & VM_HUGEPAGE)
+ sgp = SGP_HUGE;
+ else if (vma->vm_flags & VM_NOHUGEPAGE)
+ sgp = SGP_NOHUGE;
+
+ error = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, sgp,
gfp, vma->vm_mm, &ret);
if (error)
return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
_
Patches currently in -mm which might be from kirill.shutemov@xxxxxxxxxxxxxxx are
revert-mm-make-faultaround-produce-old-ptes.patch
revert-mm-disable-fault-around-on-emulated-access-bit-architecture.patch
mm-make-swapin-readahead-to-improve-thp-collapse-rate-fix.patch
mm-make-swapin-readahead-to-improve-thp-collapse-rate-fix-2.patch
mm-make-swapin-readahead-to-improve-thp-collapse-rate-fix-3.patch
mm-thp-make-swapin-readahead-under-down_read-of-mmap_sem-fix.patch
khugepaged-recheck-pmd-after-mmap_sem-re-acquired.patch
thp-mlock-update-unevictable-lrutxt.patch
mm-do-not-pass-mm_struct-into-handle_mm_fault.patch
mm-introduce-fault_env.patch
mm-postpone-page-table-allocation-until-we-have-page-to-map.patch
rmap-support-file-thp.patch
mm-introduce-do_set_pmd.patch
thp-vmstats-add-counters-for-huge-file-pages.patch
thp-support-file-pages-in-zap_huge_pmd.patch
thp-handle-file-pages-in-split_huge_pmd.patch
thp-handle-file-cow-faults.patch
thp-skip-file-huge-pmd-on-copy_huge_pmd.patch
thp-prepare-change_huge_pmd-for-file-thp.patch
thp-run-vma_adjust_trans_huge-outside-i_mmap_rwsem.patch
thp-file-pages-support-for-split_huge_page.patch
thp-mlock-do-not-mlock-pte-mapped-file-huge-pages.patch
vmscan-split-file-huge-pages-before-paging-them-out.patch
page-flags-relax-policy-for-pg_mappedtodisk-and-pg_reclaim.patch
radix-tree-implement-radix_tree_maybe_preload_order.patch
filemap-prepare-find-and-delete-operations-for-huge-pages.patch
truncate-handle-file-thp.patch
mm-rmap-account-shmem-thp-pages.patch
shmem-prepare-huge=-mount-option-and-sysfs-knob.patch
shmem-add-huge-pages-support.patch
shmem-thp-respect-madv_nohugepage-for-file-mappings.patch
thp-extract-khugepaged-from-mm-huge_memoryc.patch
khugepaged-move-up_readmmap_sem-out-of-khugepaged_alloc_page.patch
shmem-make-shmem_inode_info-lock-irq-safe.patch
khugepaged-add-support-of-collapse-for-tmpfs-shmem-pages.patch
thp-introduce-config_transparent_huge_pagecache.patch
shmem-split-huge-pages-beyond-i_size-under-memory-pressure.patch
thp-update-documentation-vm-transhugefilesystems-proctxt.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
