From bc02afbd4d73c4424ea12a0c35fa96e27172e8cb Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Mon, 26 Aug 2024 16:43:41 -0400
Subject: [PATCH] mm/fork: accept huge pfnmap entries
Teach the fork code to properly copy pfnmaps for pmd/pud levels. Pud is
much easier, the write bit needs to be persisted though for writable and
shared pud mappings like PFNMAP ones, otherwise a follow up write in
either parent or child process will trigger a write fault.
Do the same for pmd level.
Link: https://lkml.kernel.org/r/20240826204353.2228736-8-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Gavin Shan <gshan@redhat.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Niklas Schnelle <schnelle@linux.ibm.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/huge_memory.c | 29 ++++++++++++++++++++++++++---
1 file changed, 26 insertions(+), 3 deletions(-)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 7ab9a171e3d0..2a73efea02d7 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1583,6 +1583,24 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pgtable_t pgtable = NULL;
int ret = -ENOMEM;
+ pmd = pmdp_get_lockless(src_pmd);
+ if (unlikely(pmd_special(pmd))) {
+ dst_ptl = pmd_lock(dst_mm, dst_pmd);
+ src_ptl = pmd_lockptr(src_mm, src_pmd);
+ spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
+ /*
+ * No need to recheck the pmd, it can't change with write
+ * mmap lock held here.
+ *
+ * Meanwhile, making sure it's not a CoW VMA with writable
+ * mapping, otherwise it means either the anon page wrongly
+ * applied special bit, or we made the PRIVATE mapping be
+ * able to wrongly write to the backend MMIO.
+ */
+ VM_WARN_ON_ONCE(is_cow_mapping(src_vma->vm_flags) && pmd_write(pmd));
+ goto set_pmd;
+ }
+
/* Skip if can be re-fill on fault */
if (!vma_is_anonymous(dst_vma))
return 0;
@@ -1664,7 +1682,9 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pmdp_set_wrprotect(src_mm, addr, src_pmd);
if (!userfaultfd_wp(dst_vma))
pmd = pmd_clear_uffd_wp(pmd);
- pmd = pmd_mkold(pmd_wrprotect(pmd));
+ pmd = pmd_wrprotect(pmd);
+set_pmd:
+ pmd = pmd_mkold(pmd);
set_pmd_at(dst_mm, addr, dst_pmd, pmd);
ret = 0;
@@ -1710,8 +1730,11 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
* TODO: once we support anonymous pages, use
* folio_try_dup_anon_rmap_*() and split if duplicating fails.
*/
- pudp_set_wrprotect(src_mm, addr, src_pud);
- pud = pud_mkold(pud_wrprotect(pud));
+ if (is_cow_mapping(vma->vm_flags) && pud_write(pud)) {
+ pudp_set_wrprotect(src_mm, addr, src_pud);
+ pud = pud_wrprotect(pud);
+ }
+ pud = pud_mkold(pud);
set_pud_at(dst_mm, addr, dst_pud, pud);
ret = 0;
--
GitLab