The patch titled
Subject: mm/gup: replace FOLL_NUMA by gup_can_follow_protnone()
has been added to the -mm mm-unstable branch. Its filename is
mm-gup-replace-foll_numa-by-gup_can_follow_protnone.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-gup-replace-foll_numa-by-gup_can_follow_protnone.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: David Hildenbrand <david@xxxxxxxxxx>
Subject: mm/gup: replace FOLL_NUMA by gup_can_follow_protnone()
Date: Thu, 25 Aug 2022 18:46:57 +0200
Patch series "mm: minor cleanups around NUMA hinting".
Working on some GUP cleanups (e.g., getting rid of some FOLL_ flags) and
preparing for other GUP changes (getting rid of FOLL_FORCE|FOLL_WRITE for
for taking a R/O longterm pin), this is something I can easily send out
independently.
Get rid of FOLL_NUMA, allow FOLL_FORCE access to PROT_NONE mapped pages in
GUP-fast, and fixup some documentation around NUMA hinting.
This patch (of 3):
No need for a special flag that is not even properly documented to be
internal-only.
Let's just factor this check out and get rid of this flag. The separate
function has the nice benefit that we can centralize comments.
Link: https://lkml.kernel.org/r/20220825164659.89824-2-david@xxxxxxxxxx
Link: https://lkml.kernel.org/r/20220825164659.89824-1-david@xxxxxxxxxx
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxxxx>
Cc: John Hubbard <jhubbard@xxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mm.h | 16 +++++++++++++++-
mm/gup.c | 12 ++----------
mm/huge_memory.c | 2 +-
3 files changed, 18 insertions(+), 12 deletions(-)
--- a/include/linux/mm.h~mm-gup-replace-foll_numa-by-gup_can_follow_protnone
+++ a/include/linux/mm.h
@@ -2937,7 +2937,6 @@ struct page *follow_page(struct vm_area_
* and return without waiting upon it */
#define FOLL_NOFAULT 0x80 /* do not fault in pages */
#define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */
-#define FOLL_NUMA 0x200 /* force NUMA hinting page fault */
#define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */
#define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */
#define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */
@@ -3054,6 +3053,21 @@ static inline bool gup_must_unshare(unsi
return !PageAnonExclusive(page);
}
+/*
+ * Indicates whether GUP can follow a PROT_NONE mapped page, or whether
+ * a (NUMA hinting) fault is required.
+ */
+static inline bool gup_can_follow_protnone(unsigned int flags)
+{
+ /*
+ * FOLL_FORCE has to be able to make progress even if the VMA is
+ * inaccessible. Further, FOLL_FORCE access usually does not represent
+ * application behaviour and we should avoid triggering NUMA hinting
+ * faults.
+ */
+ return flags & FOLL_FORCE;
+}
+
typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data);
extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
unsigned long size, pte_fn_t fn, void *data);
--- a/mm/gup.c~mm-gup-replace-foll_numa-by-gup_can_follow_protnone
+++ a/mm/gup.c
@@ -526,7 +526,7 @@ retry:
migration_entry_wait(mm, pmd, address);
goto retry;
}
- if ((flags & FOLL_NUMA) && pte_protnone(pte))
+ if (pte_protnone(pte) && !gup_can_follow_protnone(flags))
goto no_page;
if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) {
pte_unmap_unlock(ptep, ptl);
@@ -672,7 +672,7 @@ retry:
if (likely(!pmd_trans_huge(pmdval)))
return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
- if ((flags & FOLL_NUMA) && pmd_protnone(pmdval))
+ if (pmd_protnone(pmdval) && !gup_can_follow_protnone(flags))
return no_page_table(vma, flags);
retry_locked:
@@ -1129,14 +1129,6 @@ static long __get_user_pages(struct mm_s
VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN)));
- /*
- * If FOLL_FORCE is set then do not force a full fault as the hinting
- * fault information is unrelated to the reference behaviour of a task
- * using the address space
- */
- if (!(gup_flags & FOLL_FORCE))
- gup_flags |= FOLL_NUMA;
-
do {
struct page *page;
unsigned int foll_flags = gup_flags;
--- a/mm/huge_memory.c~mm-gup-replace-foll_numa-by-gup_can_follow_protnone
+++ a/mm/huge_memory.c
@@ -1421,7 +1421,7 @@ struct page *follow_trans_huge_pmd(struc
return ERR_PTR(-EFAULT);
/* Full NUMA hinting faults to serialise migration in fault paths */
- if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
+ if (pmd_protnone(*pmd) && !gup_can_follow_protnone(flags))
goto out;
page = pmd_page(*pmd);
_
Patches currently in -mm which might be from david@xxxxxxxxxx are
mm-gup-replace-foll_numa-by-gup_can_follow_protnone.patch
mm-gup-use-gup_can_follow_protnone-also-in-gup-fast.patch
mm-fixup-documentation-regarding-pte_numa-and-prot_numa.patch
