Skip to contentSkip to conversation

mm-uffd-detect-pgtable-allocation-failures.patch removed from -mm tree

merged mm-stable Andrew Morton 1 participant 1 message Jan 19, 2023

lore
Share & tools
lore

Andrew Morton

author tree notice Applied
#0 lore raw

The quilt patch titled
Subject: mm/uffd: detect pgtable allocation failures
has been removed from the -mm tree. Its filename was
mm-uffd-detect-pgtable-allocation-failures.patch

This patch was dropped because it was merged into the mm-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

------------------------------------------------------
From: Peter Xu <[email protected]>
Subject: mm/uffd: detect pgtable allocation failures
Date: Wed, 4 Jan 2023 17:52:07 -0500

Before this patch, when there's any pgtable allocation issues happened during change_protection(), the error will be ignored from the syscall. For shmem, there will be an error dumped into the host dmesg. Two issues with that:

(1) Doing a trace dump when allocation fails is not anything close to grace.

(2) The user should be notified with any kind of such error, so the user can trap it and decide what to do next, either by retrying, or stop the process properly, or anything else.

For userfault users, this will change the API of UFFDIO_WRITEPROTECT when pgtable allocation failure happened. It should not normally break anyone, though. If it breaks, then in good ways.

One man-page update will be on the way to introduce the new -ENOMEM for UFFDIO_WRITEPROTECT. Not marking stable so we keep the old behavior on the 5.19-till-now kernels.

---

 include/linux/userfaultfd_k.h |    2 -
 mm/hugetlb.c                  |    6 ++-
 mm/mempolicy.c                |    2 -
 mm/mprotect.c                 |   63 +++++++++++++++++++++-----------
 mm/userfaultfd.c              |   16 +++++---
 5 files changed, 59 insertions(+), 30 deletions(-)
include/linux/userfaultfd_k.h renamed from include/linux/userfaultfd_k.h~mm-uffd-detect-pgtable-allocation-failures +1 -1
@@ -73,7 +73,7 @@ extern ssize_t mcopy_continue(struct mm_
 extern int mwriteprotect_range(struct mm_struct *dst_mm,
 			       unsigned long start, unsigned long len,
 			       bool enable_wp, atomic_t *mmap_changing);
-extern void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *vma,
+extern long uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *vma,
 			  unsigned long start, unsigned long len, bool enable_wp);
 
 /* mm helpers */
mm/hugetlb.c renamed from mm/hugetlb.c~mm-uffd-detect-pgtable-allocation-failures +4 -2
@@ -6660,8 +6660,10 @@ long hugetlb_change_protection(struct vm
 			 * pre-allocations to install pte markers.
 			 */
 			ptep = huge_pte_alloc(mm, vma, address, psize);
-			if (!ptep)
+			if (!ptep) {
+				pages = -ENOMEM;
 				break;
+			}
 		}
 		ptl = huge_pte_lock(h, mm, ptep);
 		if (huge_pmd_unshare(mm, vma, address, ptep)) {
@@ -6751,7 +6753,7 @@ long hugetlb_change_protection(struct vm
 	hugetlb_vma_unlock_write(vma);
 	mmu_notifier_invalidate_range_end(&range);
 
-	return pages << h->order;
+	return pages > 0 ? (pages << h->order) : pages;
 }
 
 /* Return true if reservation was successful, false otherwise.  */
mm/mempolicy.c renamed from mm/mempolicy.c~mm-uffd-detect-pgtable-allocation-failures +1 -1
@@ -636,7 +636,7 @@ unsigned long change_prot_numa(struct vm
 	tlb_gather_mmu(&tlb, vma->vm_mm);
 
 	nr_updated = change_protection(&tlb, vma, addr, end, MM_CP_PROT_NUMA);
-	if (nr_updated)
+	if (nr_updated > 0)
 		count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated);
 
 	tlb_finish_mmu(&tlb);
mm/mprotect.c renamed from mm/mprotect.c~mm-uffd-detect-pgtable-allocation-failures +42 -21

135 lines not on this page · raw message

mm/userfaultfd.c renamed from mm/userfaultfd.c~mm-uffd-detect-pgtable-allocation-failures +11 -5
@@ -710,11 +710,12 @@ ssize_t mcopy_continue(struct mm_struct
 			      mmap_changing, 0);
 }
 
-void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma,
+long uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma,
 		   unsigned long start, unsigned long len, bool enable_wp)
 {
 	unsigned int mm_cp_flags;
 	struct mmu_gather tlb;
+	long ret;
 
 	if (enable_wp)
 		mm_cp_flags = MM_CP_UFFD_WP;
@@ -730,8 +731,10 @@ void uffd_wp_range(struct mm_struct *dst
 	if (!enable_wp && vma_wants_manual_pte_write_upgrade(dst_vma))
 		mm_cp_flags |= MM_CP_TRY_CHANGE_WRITABLE;
 	tlb_gather_mmu(&tlb, dst_mm);
-	change_protection(&tlb, dst_vma, start, start + len, mm_cp_flags);
+	ret = change_protection(&tlb, dst_vma, start, start + len, mm_cp_flags);
 	tlb_finish_mmu(&tlb);
+
+	return ret;
 }
 
 int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
@@ -740,7 +743,7 @@ int mwriteprotect_range(struct mm_struct
 {
 	struct vm_area_struct *dst_vma;
 	unsigned long page_mask;
-	int err;
+	long err;
 
 	/*
 	 * Sanitize the command parameters:
@@ -779,9 +782,12 @@ int mwriteprotect_range(struct mm_struct
 			goto out_unlock;
 	}
 
-	uffd_wp_range(dst_mm, dst_vma, start, len, enable_wp);
+	err = uffd_wp_range(dst_mm, dst_vma, start, len, enable_wp);
+
+	/* Return 0 on success, <0 on failures */
+	if (err > 0)
+		err = 0;
 
-	err = 0;
 out_unlock:
 	mmap_read_unlock(dst_mm);
 	return err;

_

Patches currently in -mm which might be from [email protected] are

selftests-vm-remove-__use_gnu-in-hugetlb-madvisec.patch