[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20210217163102.13436-5-peterx@redhat.com>
Date: Wed, 17 Feb 2021 11:31:02 -0500
From: Peter Xu <peterx@...hat.com>
To: linux-kernel@...r.kernel.org, linux-mm@...ck.org
Cc: peterx@...hat.com, Axel Rasmussen <axelrasmussen@...gle.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Matthew Wilcox <willy@...radead.org>,
Mike Rapoport <rppt@...ux.vnet.ibm.com>,
"Kirill A . Shutemov" <kirill@...temov.name>,
Andrea Arcangeli <aarcange@...hat.com>,
Mike Kravetz <mike.kravetz@...cle.com>
Subject: [PATCH 4/4] hugetlb/userfaultfd: Unshare all pmds for hugetlbfs when register wp
Huge pmd sharing for hugetlbfs is racy with userfaultfd-wp because
userfaultfd-wp is always based on pgtable entries, so they cannot be shared.
Walk the hugetlb range and unshare all such mappings if there is, right before
UFFDIO_REGISTER will succeed and return to userspace.
This will pair with want_pmd_share() in hugetlb code so that huge pmd sharing
is completely disabled for userfaultfd-wp registered range.
Signed-off-by: Peter Xu <peterx@...hat.com>
---
fs/userfaultfd.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 57 insertions(+)
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 894cc28142e7..3fbdacc25ff4 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -15,6 +15,7 @@
#include <linux/sched/signal.h>
#include <linux/sched/mm.h>
#include <linux/mm.h>
+#include <linux/mmu_notifier.h>
#include <linux/poll.h>
#include <linux/slab.h>
#include <linux/seq_file.h>
@@ -1190,6 +1191,59 @@ static ssize_t userfaultfd_read(struct file *file, char __user *buf,
}
}
+/*
+ * This function will unconditionally remove all the shared pmd pgtable entries
+ * within the specific vma for a hugetlbfs memory range.
+ */
+static void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
+{
+#ifdef CONFIG_HUGETLB_PAGE
+ struct hstate *h = hstate_vma(vma);
+ unsigned long sz = huge_page_size(h);
+ struct mm_struct *mm = vma->vm_mm;
+ struct mmu_notifier_range range;
+ unsigned long address, start, end;
+ spinlock_t *ptl;
+ pte_t *ptep;
+
+ if (!(vma->vm_flags & VM_MAYSHARE))
+ return;
+
+ start = ALIGN(vma->vm_start, PUD_SIZE);
+ end = ALIGN_DOWN(vma->vm_end, PUD_SIZE);
+
+ if (start >= end)
+ return;
+
+ /*
+ * No need to call adjust_range_if_pmd_sharing_possible(), because
+ * we're going to operate on the whole vma
+ */
+ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm,
+ vma->vm_start, vma->vm_end);
+ mmu_notifier_invalidate_range_start(&range);
+ i_mmap_lock_write(vma->vm_file->f_mapping);
+ for (address = start; address < end; address += PUD_SIZE) {
+ unsigned long tmp = address;
+
+ ptep = huge_pte_offset(mm, address, sz);
+ if (!ptep)
+ continue;
+ ptl = huge_pte_lock(h, mm, ptep);
+ /* We don't want 'address' to be changed */
+ huge_pmd_unshare(mm, vma, &tmp, ptep);
+ spin_unlock(ptl);
+ }
+ flush_hugetlb_tlb_range(vma, vma->vm_start, vma->vm_end);
+ i_mmap_unlock_write(vma->vm_file->f_mapping);
+ /*
+ * No need to call mmu_notifier_invalidate_range(), see
+ * Documentation/vm/mmu_notifier.rst.
+ */
+ mmu_notifier_invalidate_range_end(&range);
+#endif
+}
+
static void __wake_userfault(struct userfaultfd_ctx *ctx,
struct userfaultfd_wake_range *range)
{
@@ -1448,6 +1502,9 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
vma->vm_flags = new_flags;
vma->vm_userfaultfd_ctx.ctx = ctx;
+ if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma))
+ hugetlb_unshare_all_pmds(vma);
+
skip:
prev = vma;
start = vma->vm_end;
--
2.26.2
Powered by blists - more mailing lists