The patch titled
Subject: mm/hugetlb: support FOLL_FORCE|FOLL_WRITE
has been added to the -mm mm-unstable branch. Its filename is
mm-hugetlb-support-foll_forcefoll_write.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-hugetlb-support-foll_forcefoll_write.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: Guillaume Morin <guillaume@xxxxxxxxxxx>
Subject: mm/hugetlb: support FOLL_FORCE|FOLL_WRITE
Date: Thu, 5 Dec 2024 03:02:26 +0100
Eric reported that PTRACE_POKETEXT fails when applications use hugetlb
for mapping text using huge pages. Before commit 1d8d14641fd9
("mm/hugetlb: support write-faults in shared mappings"), PTRACE_POKETEXT
worked by accident, but it was buggy and silently ended up mapping pages
writable into the page tables even though VM_WRITE was not set.
In general, FOLL_FORCE|FOLL_WRITE does currently not work with hugetlb.
Let's implement FOLL_FORCE|FOLL_WRITE properly for hugetlb, such that
what used to work in the past by accident now properly works, allowing
applications using hugetlb for text etc. to get properly debugged.
This change might also be required to implement uprobes support for
hugetlb [1].
[1] https://lore.kernel.org/lkml/ZiK50qob9yl5e0Xz@xxxxxxxxxxxxxxxxxx/
Link: https://lkml.kernel.org/r/Z1EJssqd93w2erMZ@xxxxxxxxxxxxxxxxxx
Cc: Muchun Song <muchun.song@xxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Eric Hagberg <ehagberg@xxxxxxxxxxxxxx>
Signed-off-by: Guillaume Morin <guillaume@xxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/pgtable.h | 5 +
mm/gup.c | 99 +++++++++++++++++++-------------------
mm/hugetlb.c | 20 ++++---
3 files changed, 66 insertions(+), 58 deletions(-)
--- a/include/linux/pgtable.h~mm-hugetlb-support-foll_forcefoll_write
+++ a/include/linux/pgtable.h
@@ -1429,6 +1429,11 @@ static inline int pmd_soft_dirty(pmd_t p
return 0;
}
+static inline int pud_soft_dirty(pud_t pud)
+{
+ return 0;
+}
+
static inline pte_t pte_mksoft_dirty(pte_t pte)
{
return pte;
--- a/mm/gup.c~mm-hugetlb-support-foll_forcefoll_write
+++ a/mm/gup.c
@@ -596,6 +596,33 @@ static struct folio *try_grab_folio_fast
}
#endif /* CONFIG_HAVE_GUP_FAST */
+/* Common code for can_follow_write_* */
+static inline bool can_follow_write_common(struct page *page,
+ struct vm_area_struct *vma, unsigned int flags)
+{
+ /* Maybe FOLL_FORCE is set to override it? */
+ if (!(flags & FOLL_FORCE))
+ return false;
+
+ /* But FOLL_FORCE has no effect on shared mappings */
+ if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED))
+ return false;
+
+ /* ... or read-only private ones */
+ if (!(vma->vm_flags & VM_MAYWRITE))
+ return false;
+
+ /* ... or already writable ones that just need to take a write fault */
+ if (vma->vm_flags & VM_WRITE)
+ return false;
+
+ /*
+ * See can_change_pte_writable(): we broke COW and could map the page
+ * writable if we have an exclusive anonymous page ...
+ */
+ return page && PageAnon(page) && PageAnonExclusive(page);
+}
+
static struct page *no_page_table(struct vm_area_struct *vma,
unsigned int flags, unsigned long address)
{
@@ -622,6 +649,22 @@ static struct page *no_page_table(struct
}
#ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES
+/* FOLL_FORCE can write to even unwritable PUDs in COW mappings. */
+static inline bool can_follow_write_pud(pud_t pud, struct page *page,
+ struct vm_area_struct *vma,
+ unsigned int flags)
+{
+ /* If the pud is writable, we can write to the page. */
+ if (pud_write(pud))
+ return true;
+
+ if (!can_follow_write_common(page, vma, flags))
+ return false;
+
+ /* ... and a write-fault isn't required for other reasons. */
+ return !vma_soft_dirty_enabled(vma) || pud_soft_dirty(pud);
+}
+
static struct page *follow_huge_pud(struct vm_area_struct *vma,
unsigned long addr, pud_t *pudp,
int flags, struct follow_page_context *ctx)
@@ -634,13 +677,16 @@ static struct page *follow_huge_pud(stru
assert_spin_locked(pud_lockptr(mm, pudp));
- if ((flags & FOLL_WRITE) && !pud_write(pud))
+ pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT;
+ page = pfn_to_page(pfn);
+
+ if ((flags & FOLL_WRITE) &&
+ !can_follow_write_pud(pud, page, vma, flags))
return NULL;
if (!pud_present(pud))
return NULL;
- pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT;
if (IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) &&
pud_devmap(pud)) {
@@ -662,8 +708,6 @@ static struct page *follow_huge_pud(stru
return ERR_PTR(-EFAULT);
}
- page = pfn_to_page(pfn);
-
if (!pud_devmap(pud) && !pud_write(pud) &&
gup_must_unshare(vma, flags, page))
return ERR_PTR(-EMLINK);
@@ -686,27 +730,7 @@ static inline bool can_follow_write_pmd(
if (pmd_write(pmd))
return true;
- /* Maybe FOLL_FORCE is set to override it? */
- if (!(flags & FOLL_FORCE))
- return false;
-
- /* But FOLL_FORCE has no effect on shared mappings */
- if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED))
- return false;
-
- /* ... or read-only private ones */
- if (!(vma->vm_flags & VM_MAYWRITE))
- return false;
-
- /* ... or already writable ones that just need to take a write fault */
- if (vma->vm_flags & VM_WRITE)
- return false;
-
- /*
- * See can_change_pte_writable(): we broke COW and could map the page
- * writable if we have an exclusive anonymous page ...
- */
- if (!page || !PageAnon(page) || !PageAnonExclusive(page))
+ if (!can_follow_write_common(page, vma, flags))
return false;
/* ... and a write-fault isn't required for other reasons. */
@@ -807,27 +831,7 @@ static inline bool can_follow_write_pte(
if (pte_write(pte))
return true;
- /* Maybe FOLL_FORCE is set to override it? */
- if (!(flags & FOLL_FORCE))
- return false;
-
- /* But FOLL_FORCE has no effect on shared mappings */
- if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED))
- return false;
-
- /* ... or read-only private ones */
- if (!(vma->vm_flags & VM_MAYWRITE))
- return false;
-
- /* ... or already writable ones that just need to take a write fault */
- if (vma->vm_flags & VM_WRITE)
- return false;
-
- /*
- * See can_change_pte_writable(): we broke COW and could map the page
- * writable if we have an exclusive anonymous page ...
- */
- if (!page || !PageAnon(page) || !PageAnonExclusive(page))
+ if (!can_follow_write_common(page, vma, flags))
return false;
/* ... and a write-fault isn't required for other reasons. */
@@ -1294,9 +1298,6 @@ static int check_vma_flags(struct vm_are
if (!(vm_flags & VM_WRITE) || (vm_flags & VM_SHADOW_STACK)) {
if (!(gup_flags & FOLL_FORCE))
return -EFAULT;
- /* hugetlb does not support FOLL_FORCE|FOLL_WRITE. */
- if (is_vm_hugetlb_page(vma))
- return -EFAULT;
/*
* We used to let the write,force case do COW in a
* VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could
--- a/mm/hugetlb.c~mm-hugetlb-support-foll_forcefoll_write
+++ a/mm/hugetlb.c
@@ -5183,6 +5183,13 @@ static void set_huge_ptep_writable(struc
update_mmu_cache(vma, address, ptep);
}
+static void set_huge_ptep_maybe_writable(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep)
+{
+ if (vma->vm_flags & VM_WRITE)
+ set_huge_ptep_writable(vma, address, ptep);
+}
+
bool is_hugetlb_entry_migration(pte_t pte)
{
swp_entry_t swp;
@@ -5816,13 +5823,6 @@ static vm_fault_t hugetlb_wp(struct foli
if (!unshare && huge_pte_uffd_wp(pte))
return 0;
- /*
- * hugetlb does not support FOLL_FORCE-style write faults that keep the
- * PTE mapped R/O such as maybe_mkwrite() would do.
- */
- if (WARN_ON_ONCE(!unshare && !(vma->vm_flags & VM_WRITE)))
- return VM_FAULT_SIGSEGV;
-
/* Let's take out MAP_SHARED mappings first. */
if (vma->vm_flags & VM_MAYSHARE) {
set_huge_ptep_writable(vma, vmf->address, vmf->pte);
@@ -5851,7 +5851,8 @@ retry_avoidcopy:
SetPageAnonExclusive(&old_folio->page);
}
if (likely(!unshare))
- set_huge_ptep_writable(vma, vmf->address, vmf->pte);
+ set_huge_ptep_maybe_writable(vma, vmf->address,
+ vmf->pte);
delayacct_wpcopy_end();
return 0;
@@ -5957,7 +5958,8 @@ retry_avoidcopy:
spin_lock(vmf->ptl);
vmf->pte = hugetlb_walk(vma, vmf->address, huge_page_size(h));
if (likely(vmf->pte && pte_same(huge_ptep_get(mm, vmf->address, vmf->pte), pte))) {
- pte_t newpte = make_huge_pte(vma, &new_folio->page, !unshare);
+ const bool writable = !unshare && (vma->vm_flags & VM_WRITE);
+ pte_t newpte = make_huge_pte(vma, &new_folio->page, writable);
/* Break COW or unshare */
huge_ptep_clear_flush(vma, vmf->address, vmf->pte);
_
Patches currently in -mm which might be from guillaume@xxxxxxxxxxx are
mm-hugetlb-support-foll_forcefoll_write.patch
