The patch titled
Subject: mm/gup: handle hugetlb for no_page_table()
has been added to the -mm mm-unstable branch. Its filename is
mm-gup-handle-hugetlb-for-no_page_table.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-gup-handle-hugetlb-for-no_page_table.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
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/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Peter Xu <peterx@xxxxxxxxxx>
Subject: mm/gup: handle hugetlb for no_page_table()
Date: Wed, 27 Mar 2024 11:23:27 -0400
no_page_table() is not yet used for hugetlb code paths. Make it prepared.
The major difference here is hugetlb will return -EFAULT as long as page
cache does not exist, even if VM_SHARED. See hugetlb_follow_page_mask().
Pass "address" into no_page_table() too, as hugetlb will need it.
Link: https://lkml.kernel.org/r/20240327152332.950956-9-peterx@xxxxxxxxxx
Signed-off-by: Peter Xu <peterx@xxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Reviewed-by: Jason Gunthorpe <jgg@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Andrew Jones <andrew.jones@xxxxxxxxx>
Cc: Aneesh Kumar K.V (IBM) <aneesh.kumar@xxxxxxxxxx>
Cc: Axel Rasmussen <axelrasmussen@xxxxxxxxxx>
Cc: Christophe Leroy <christophe.leroy@xxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: James Houghton <jthoughton@xxxxxxxxxx>
Cc: John Hubbard <jhubbard@xxxxxxxxxx>
Cc: Kirill A. Shutemov <kirill@xxxxxxxxxxxxx>
Cc: Lorenzo Stoakes <lstoakes@xxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: "Mike Rapoport (IBM)" <rppt@xxxxxxxxxx>
Cc: Muchun Song <muchun.song@xxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Yang Shi <shy828301@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/gup.c | 44 ++++++++++++++++++++++++++------------------
1 file changed, 26 insertions(+), 18 deletions(-)
--- a/mm/gup.c~mm-gup-handle-hugetlb-for-no_page_table
+++ a/mm/gup.c
@@ -501,19 +501,27 @@ static inline void mm_set_has_pinned_fla
#ifdef CONFIG_MMU
static struct page *no_page_table(struct vm_area_struct *vma,
- unsigned int flags)
+ unsigned int flags, unsigned long address)
{
+ if (!(flags & FOLL_DUMP))
+ return NULL;
+
/*
- * When core dumping an enormous anonymous area that nobody
- * has touched so far, we don't want to allocate unnecessary pages or
+ * When core dumping, we don't want to allocate unnecessary pages or
* page tables. Return error instead of NULL to skip handle_mm_fault,
* then get_dump_page() will return NULL to leave a hole in the dump.
* But we can only make this optimization where a hole would surely
* be zero-filled if handle_mm_fault() actually did handle it.
*/
- if ((flags & FOLL_DUMP) &&
- (vma_is_anonymous(vma) || !vma->vm_ops->fault))
+ if (is_vm_hugetlb_page(vma)) {
+ struct hstate *h = hstate_vma(vma);
+
+ if (!hugetlbfs_pagecache_present(h, vma, address))
+ return ERR_PTR(-EFAULT);
+ } else if ((vma_is_anonymous(vma) || !vma->vm_ops->fault)) {
return ERR_PTR(-EFAULT);
+ }
+
return NULL;
}
@@ -593,7 +601,7 @@ static struct page *follow_page_pte(stru
ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
if (!ptep)
- return no_page_table(vma, flags);
+ return no_page_table(vma, flags, address);
pte = ptep_get(ptep);
if (!pte_present(pte))
goto no_page;
@@ -685,7 +693,7 @@ no_page:
pte_unmap_unlock(ptep, ptl);
if (!pte_none(pte))
return NULL;
- return no_page_table(vma, flags);
+ return no_page_table(vma, flags, address);
}
static struct page *follow_pmd_mask(struct vm_area_struct *vma,
@@ -701,27 +709,27 @@ static struct page *follow_pmd_mask(stru
pmd = pmd_offset(pudp, address);
pmdval = pmdp_get_lockless(pmd);
if (pmd_none(pmdval))
- return no_page_table(vma, flags);
+ return no_page_table(vma, flags, address);
if (!pmd_present(pmdval))
- return no_page_table(vma, flags);
+ return no_page_table(vma, flags, address);
if (pmd_devmap(pmdval)) {
ptl = pmd_lock(mm, pmd);
page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap);
spin_unlock(ptl);
if (page)
return page;
- return no_page_table(vma, flags);
+ return no_page_table(vma, flags, address);
}
if (likely(!pmd_trans_huge(pmdval)))
return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
if (pmd_protnone(pmdval) && !gup_can_follow_protnone(vma, flags))
- return no_page_table(vma, flags);
+ return no_page_table(vma, flags, address);
ptl = pmd_lock(mm, pmd);
if (unlikely(!pmd_present(*pmd))) {
spin_unlock(ptl);
- return no_page_table(vma, flags);
+ return no_page_table(vma, flags, address);
}
if (unlikely(!pmd_trans_huge(*pmd))) {
spin_unlock(ptl);
@@ -752,17 +760,17 @@ static struct page *follow_pud_mask(stru
pud = pud_offset(p4dp, address);
if (pud_none(*pud))
- return no_page_table(vma, flags);
+ return no_page_table(vma, flags, address);
if (pud_devmap(*pud)) {
ptl = pud_lock(mm, pud);
page = follow_devmap_pud(vma, address, pud, flags, &ctx->pgmap);
spin_unlock(ptl);
if (page)
return page;
- return no_page_table(vma, flags);
+ return no_page_table(vma, flags, address);
}
if (unlikely(pud_bad(*pud)))
- return no_page_table(vma, flags);
+ return no_page_table(vma, flags, address);
return follow_pmd_mask(vma, address, pud, flags, ctx);
}
@@ -777,10 +785,10 @@ static struct page *follow_p4d_mask(stru
p4dp = p4d_offset(pgdp, address);
p4d = READ_ONCE(*p4dp);
if (!p4d_present(p4d))
- return no_page_table(vma, flags);
+ return no_page_table(vma, flags, address);
BUILD_BUG_ON(p4d_leaf(p4d));
if (unlikely(p4d_bad(p4d)))
- return no_page_table(vma, flags);
+ return no_page_table(vma, flags, address);
return follow_pud_mask(vma, address, p4dp, flags, ctx);
}
@@ -830,7 +838,7 @@ static struct page *follow_page_mask(str
pgd = pgd_offset(mm, address);
if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
- return no_page_table(vma, flags);
+ return no_page_table(vma, flags, address);
return follow_p4d_mask(vma, address, pgd, flags, ctx);
}
_
Patches currently in -mm which might be from peterx@xxxxxxxxxx are
mm-hmm-process-pud-swap-entry-without-pud_huge.patch
mm-gup-cache-p4d-in-follow_p4d_mask.patch
mm-gup-check-p4d-presence-before-going-on.patch
mm-x86-change-pxd_huge-behavior-to-exclude-swap-entries.patch
mm-sparc-change-pxd_huge-behavior-to-exclude-swap-entries.patch
mm-arm-use-macros-to-define-pmd-pud-helpers.patch
mm-arm-redefine-pmd_huge-with-pmd_leaf.patch
mm-arm64-merge-pxd_huge-and-pxd_leaf-definitions.patch
mm-powerpc-redefine-pxd_huge-with-pxd_leaf.patch
mm-gup-merge-pxd-huge-mapping-checks.patch
mm-treewide-replace-pxd_huge-with-pxd_leaf.patch
mm-treewide-remove-pxd_huge.patch
mm-arm-remove-pmd_thp_or_huge.patch
mm-document-pxd_leaf-api.patch
selftests-mm-run_vmtestssh-fix-hugetlb-mem-size-calculation.patch
mm-kconfig-config_pgtable_has_huge_leaves.patch
mm-hugetlb-declare-hugetlbfs_pagecache_present-non-static.patch
mm-make-hpage_pxd_-macros-even-if-thp.patch
mm-introduce-vma_pgtable_walk_beginend.patch
mm-arch-provide-pud_pfn-fallback.patch
mm-gup-drop-folio_fast_pin_allowed-in-hugepd-processing.patch
mm-gup-refactor-record_subpages-to-find-1st-small-page.patch
mm-gup-handle-hugetlb-for-no_page_table.patch
mm-gup-cache-pudp-in-follow_pud_mask.patch
mm-gup-handle-huge-pud-for-follow_pud_mask.patch
mm-gup-handle-huge-pmd-for-follow_pmd_mask.patch
mm-gup-handle-hugepd-for-follow_page.patch
mm-gup-handle-hugetlb-in-the-generic-follow_page_mask-code.patch
