The patch titled
Subject: mm/memory: enhance insert_page_into_pte_locked() to create writable mappings
has been added to the -mm mm-unstable branch. Its filename is
mm-memory-enhance-insert_page_into_pte_locked-to-create-writable-mappings.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-memory-enhance-insert_page_into_pte_locked-to-create-writable-mappings.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: Alistair Popple <apopple@xxxxxxxxxx>
Subject: mm/memory: enhance insert_page_into_pte_locked() to create writable mappings
Date: Wed, 5 Feb 2025 09:48:09 +1100
In preparation for using insert_page() for DAX, enhance
insert_page_into_pte_locked() to handle establishing writable mappings.
Recall that DAX returns VM_FAULT_NOPAGE after installing a PTE which
bypasses the typical set_pte_range() in finish_fault.
Link: https://lkml.kernel.org/r/7db953c8cc5a066b4aa23dbdf049c6f35cce7b99.1738709036.git-series.apopple@xxxxxxxxxx
Signed-off-by: Alistair Popple <apopple@xxxxxxxxxx>
Suggested-by: Dan Williams <dan.j.williams@xxxxxxxxx>
Reviewed-by: Dan Williams <dan.j.williams@xxxxxxxxx>
Tested-by: Alison Schofield <alison.schofield@xxxxxxxxx>
Cc: Alexander Gordeev <agordeev@xxxxxxxxxxxxx>
Cc: Asahi Lina <lina@xxxxxxxxxxxxx>
Cc: Bjorn Helgaas <bhelgaas@xxxxxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Christian Borntraeger <borntraeger@xxxxxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Chunyan Zhang <zhang.lyra@xxxxxxxxx>
Cc: "Darrick J. Wong" <djwong@xxxxxxxxxx>
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Dave Jiang <dave.jiang@xxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Gerald Schaefer <gerald.schaefer@xxxxxxxxxxxxx>
Cc: Heiko Carstens <hca@xxxxxxxxxxxxx>
Cc: Huacai Chen <chenhuacai@xxxxxxxxxx>
Cc: Ira Weiny <ira.weiny@xxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxx>
Cc: John Hubbard <jhubbard@xxxxxxxxxx>
Cc: linmiaohe <linmiaohe@xxxxxxxxxx>
Cc: Logan Gunthorpe <logang@xxxxxxxxxxxx>
Cc: Mattew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Nicholas Piggin <npiggin@xxxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: Sven Schnelle <svens@xxxxxxxxxxxxx>
Cc: Ted Ts'o <tytso@xxxxxxx>
Cc: Vasily Gorbik <gor@xxxxxxxxxxxxx>
Cc: Vishal Verma <vishal.l.verma@xxxxxxxxx>
Cc: Vivek Goyal <vgoyal@xxxxxxxxxx>
Cc: WANG Xuerui <kernel@xxxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memory.c | 38 +++++++++++++++++++++++++++++---------
1 file changed, 29 insertions(+), 9 deletions(-)
--- a/mm/memory.c~mm-memory-enhance-insert_page_into_pte_locked-to-create-writable-mappings
+++ a/mm/memory.c
@@ -2127,19 +2127,39 @@ static int validate_page_before_insert(s
}
static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte,
- unsigned long addr, struct page *page, pgprot_t prot)
+ unsigned long addr, struct page *page,
+ pgprot_t prot, bool mkwrite)
{
struct folio *folio = page_folio(page);
- pte_t pteval;
+ pte_t pteval = ptep_get(pte);
+
+ if (!pte_none(pteval)) {
+ if (!mkwrite)
+ return -EBUSY;
+
+ /* see insert_pfn(). */
+ if (pte_pfn(pteval) != page_to_pfn(page)) {
+ WARN_ON_ONCE(!is_zero_pfn(pte_pfn(pteval)));
+ return -EFAULT;
+ }
+ pteval = maybe_mkwrite(pteval, vma);
+ pteval = pte_mkyoung(pteval);
+ if (ptep_set_access_flags(vma, addr, pte, pteval, 1))
+ update_mmu_cache(vma, addr, pte);
+ return 0;
+ }
- if (!pte_none(ptep_get(pte)))
- return -EBUSY;
/* Ok, finally just insert the thing.. */
pteval = mk_pte(page, prot);
if (unlikely(is_zero_folio(folio))) {
pteval = pte_mkspecial(pteval);
} else {
folio_get(folio);
+ pteval = mk_pte(page, prot);
+ if (mkwrite) {
+ pteval = pte_mkyoung(pteval);
+ pteval = maybe_mkwrite(pte_mkdirty(pteval), vma);
+ }
inc_mm_counter(vma->vm_mm, mm_counter_file(folio));
folio_add_file_rmap_pte(folio, page, vma);
}
@@ -2148,7 +2168,7 @@ static int insert_page_into_pte_locked(s
}
static int insert_page(struct vm_area_struct *vma, unsigned long addr,
- struct page *page, pgprot_t prot)
+ struct page *page, pgprot_t prot, bool mkwrite)
{
int retval;
pte_t *pte;
@@ -2161,7 +2181,7 @@ static int insert_page(struct vm_area_st
pte = get_locked_pte(vma->vm_mm, addr, &ptl);
if (!pte)
goto out;
- retval = insert_page_into_pte_locked(vma, pte, addr, page, prot);
+ retval = insert_page_into_pte_locked(vma, pte, addr, page, prot, mkwrite);
pte_unmap_unlock(pte, ptl);
out:
return retval;
@@ -2175,7 +2195,7 @@ static int insert_page_in_batch_locked(s
err = validate_page_before_insert(vma, page);
if (err)
return err;
- return insert_page_into_pte_locked(vma, pte, addr, page, prot);
+ return insert_page_into_pte_locked(vma, pte, addr, page, prot, false);
}
/* insert_pages() amortizes the cost of spinlock operations
@@ -2311,7 +2331,7 @@ int vm_insert_page(struct vm_area_struct
BUG_ON(vma->vm_flags & VM_PFNMAP);
vm_flags_set(vma, VM_MIXEDMAP);
}
- return insert_page(vma, addr, page, vma->vm_page_prot);
+ return insert_page(vma, addr, page, vma->vm_page_prot, false);
}
EXPORT_SYMBOL(vm_insert_page);
@@ -2591,7 +2611,7 @@ static vm_fault_t __vm_insert_mixed(stru
* result in pfn_t_has_page() == false.
*/
page = pfn_to_page(pfn_t_to_pfn(pfn));
- err = insert_page(vma, addr, page, pgprot);
+ err = insert_page(vma, addr, page, pgprot, mkwrite);
} else {
return insert_pfn(vma, addr, pfn, pgprot, mkwrite);
}
_
Patches currently in -mm which might be from apopple@xxxxxxxxxx are
fuse-fix-dax-truncate-punch_hole-fault-path.patch
fs-dax-return-unmapped-busy-pages-from-dax_layout_busy_page_range.patch
fs-dax-dont-skip-locked-entries-when-scanning-entries.patch
fs-dax-refactor-wait-for-dax-idle-page.patch
fs-dax-create-a-common-implementation-to-break-dax-layouts.patch
fs-dax-always-remove-dax-page-cache-entries-when-breaking-layouts.patch
fs-dax-ensure-all-pages-are-idle-prior-to-filesystem-unmount.patch
fs-dax-remove-page_mapping_dax_shared-mapping-flag.patch
mm-gup-remove-redundant-check-for-pci-p2pdma-page.patch
mm-mm_init-move-p2pdma-page-refcount-initialisation-to-p2pdma.patch
mm-allow-compound-zone-device-pages.patch
mm-memory-enhance-insert_page_into_pte_locked-to-create-writable-mappings.patch
mm-memory-add-vmf_insert_page_mkwrite.patch
rmap-add-support-for-pud-sized-mappings-to-rmap.patch
huge_memory-add-vmf_insert_folio_pud.patch
huge_memory-add-vmf_insert_folio_pmd.patch
mm-gup-dont-allow-foll_longterm-pinning-of-fs-dax-pages.patch
fs-dax-properly-refcount-fs-dax-pages.patch
device-dax-properly-refcount-device-dax-pages-when-mapping.patch
