--- /dev/null
+From 70cbc3cc78a997d8247b50389d37c4e1736019da Mon Sep 17 00:00:00 2001
+From: Yang Shi <shy828301@gmail.com>
+Date: Wed, 7 Sep 2022 11:01:43 -0700
+Subject: mm: gup: fix the fast GUP race against THP collapse
+
+From: Yang Shi <shy828301@gmail.com>
+
+commit 70cbc3cc78a997d8247b50389d37c4e1736019da upstream.
+
+Since general RCU GUP fast was introduced in commit 2667f50e8b81 ("mm:
+introduce a general RCU get_user_pages_fast()"), a TLB flush is no longer
+sufficient to handle concurrent GUP-fast in all cases, it only handles
+traditional IPI-based GUP-fast correctly. On architectures that send an
+IPI broadcast on TLB flush, it works as expected. But on the
+architectures that do not use IPI to broadcast TLB flush, it may have the
+below race:
+
+ CPU A CPU B
+THP collapse fast GUP
+ gup_pmd_range() <-- see valid pmd
+ gup_pte_range() <-- work on pte
+pmdp_collapse_flush() <-- clear pmd and flush
+__collapse_huge_page_isolate()
+ check page pinned <-- before GUP bump refcount
+ pin the page
+ check PTE <-- no change
+__collapse_huge_page_copy()
+ copy data to huge page
+ ptep_clear()
+install huge pmd for the huge page
+ return the stale page
+discard the stale page
+
+The race can be fixed by checking whether PMD is changed or not after
+taking the page pin in fast GUP, just like what it does for PTE. If the
+PMD is changed it means there may be parallel THP collapse, so GUP should
+back off.
+
+Also update the stale comment about serializing against fast GUP in
+khugepaged.
+
+Link: https://lkml.kernel.org/r/20220907180144.555485-1-shy828301@gmail.com
+Fixes: 2667f50e8b81 ("mm: introduce a general RCU get_user_pages_fast()")
+Acked-by: David Hildenbrand <david@redhat.com>
+Acked-by: Peter Xu <peterx@redhat.com>
+Signed-off-by: Yang Shi <shy828301@gmail.com>
+Reviewed-by: John Hubbard <jhubbard@nvidia.com>
+Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
+Cc: Hugh Dickins <hughd@google.com>
+Cc: Jason Gunthorpe <jgg@nvidia.com>
+Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
+Cc: Michael Ellerman <mpe@ellerman.id.au>
+Cc: Nicholas Piggin <npiggin@gmail.com>
+Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
+Cc: <stable@vger.kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ mm/gup.c | 34 ++++++++++++++++++++++++++++------
+ mm/khugepaged.c | 10 ++++++----
+ 2 files changed, 34 insertions(+), 10 deletions(-)
+
+--- a/mm/gup.c
++++ b/mm/gup.c
+@@ -2128,8 +2128,28 @@ static void __maybe_unused undo_dev_page
+ }
+
+ #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
+-static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
+- unsigned int flags, struct page **pages, int *nr)
++/*
++ * Fast-gup relies on pte change detection to avoid concurrent pgtable
++ * operations.
++ *
++ * To pin the page, fast-gup needs to do below in order:
++ * (1) pin the page (by prefetching pte), then (2) check pte not changed.
++ *
++ * For the rest of pgtable operations where pgtable updates can be racy
++ * with fast-gup, we need to do (1) clear pte, then (2) check whether page
++ * is pinned.
++ *
++ * Above will work for all pte-level operations, including THP split.
++ *
++ * For THP collapse, it's a bit more complicated because fast-gup may be
++ * walking a pgtable page that is being freed (pte is still valid but pmd
++ * can be cleared already). To avoid race in such condition, we need to
++ * also check pmd here to make sure pmd doesn't change (corresponds to
++ * pmdp_collapse_flush() in the THP collapse code path).
++ */
++static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
++ unsigned long end, unsigned int flags,
++ struct page **pages, int *nr)
+ {
+ struct dev_pagemap *pgmap = NULL;
+ int nr_start = *nr, ret = 0;
+@@ -2169,7 +2189,8 @@ static int gup_pte_range(pmd_t pmd, unsi
+ if (!head)
+ goto pte_unmap;
+
+- if (unlikely(pte_val(pte) != pte_val(*ptep))) {
++ if (unlikely(pmd_val(pmd) != pmd_val(*pmdp)) ||
++ unlikely(pte_val(pte) != pte_val(*ptep))) {
+ put_compound_head(head, 1, flags);
+ goto pte_unmap;
+ }
+@@ -2214,8 +2235,9 @@ pte_unmap:
+ * get_user_pages_fast_only implementation that can pin pages. Thus it's still
+ * useful to have gup_huge_pmd even if we can't operate on ptes.
+ */
+-static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
+- unsigned int flags, struct page **pages, int *nr)
++static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
++ unsigned long end, unsigned int flags,
++ struct page **pages, int *nr)
+ {
+ return 0;
+ }
+@@ -2522,7 +2544,7 @@ static int gup_pmd_range(pud_t *pudp, pu
+ if (!gup_huge_pd(__hugepd(pmd_val(pmd)), addr,
+ PMD_SHIFT, next, flags, pages, nr))
+ return 0;
+- } else if (!gup_pte_range(pmd, addr, next, flags, pages, nr))
++ } else if (!gup_pte_range(pmd, pmdp, addr, next, flags, pages, nr))
+ return 0;
+ } while (pmdp++, addr = next, addr != end);
+
+--- a/mm/khugepaged.c
++++ b/mm/khugepaged.c
+@@ -1144,10 +1144,12 @@ static void collapse_huge_page(struct mm
+
+ pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */
+ /*
+- * After this gup_fast can't run anymore. This also removes
+- * any huge TLB entry from the CPU so we won't allow
+- * huge and small TLB entries for the same virtual address
+- * to avoid the risk of CPU bugs in that area.
++ * This removes any huge TLB entry from the CPU so we won't allow
++ * huge and small TLB entries for the same virtual address to
++ * avoid the risk of CPU bugs in that area.
++ *
++ * Parallel fast GUP is fine since fast GUP will back off when
++ * it detects PMD is changed.
+ */
+ _pmd = pmdp_collapse_flush(vma, address, pmd);
+ spin_unlock(pmd_ptl);
--- /dev/null
+From bedf03416913d88c796288f9dca109a53608c745 Mon Sep 17 00:00:00 2001
+From: Yang Shi <shy828301@gmail.com>
+Date: Wed, 7 Sep 2022 11:01:44 -0700
+Subject: powerpc/64s/radix: don't need to broadcast IPI for radix pmd collapse flush
+
+From: Yang Shi <shy828301@gmail.com>
+
+commit bedf03416913d88c796288f9dca109a53608c745 upstream.
+
+The IPI broadcast is used to serialize against fast-GUP, but fast-GUP will
+move to use RCU instead of disabling local interrupts in fast-GUP. Using
+an IPI is the old-styled way of serializing against fast-GUP although it
+still works as expected now.
+
+And fast-GUP now fixed the potential race with THP collapse by checking
+whether PMD is changed or not. So IPI broadcast in radix pmd collapse
+flush is not necessary anymore. But it is still needed for hash TLB.
+
+Link: https://lkml.kernel.org/r/20220907180144.555485-2-shy828301@gmail.com
+Suggested-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
+Signed-off-by: Yang Shi <shy828301@gmail.com>
+Acked-by: David Hildenbrand <david@redhat.com>
+Acked-by: Peter Xu <peterx@redhat.com>
+Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
+Cc: Hugh Dickins <hughd@google.com>
+Cc: Jason Gunthorpe <jgg@nvidia.com>
+Cc: John Hubbard <jhubbard@nvidia.com>
+Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
+Cc: Michael Ellerman <mpe@ellerman.id.au>
+Cc: Nicholas Piggin <npiggin@gmail.com>
+Cc: <stable@vger.kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ arch/powerpc/mm/book3s64/radix_pgtable.c | 9 ---------
+ 1 file changed, 9 deletions(-)
+
+--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
++++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
+@@ -997,15 +997,6 @@ pmd_t radix__pmdp_collapse_flush(struct
+ pmd = *pmdp;
+ pmd_clear(pmdp);
+
+- /*
+- * pmdp collapse_flush need to ensure that there are no parallel gup
+- * walk after this call. This is needed so that we can have stable
+- * page ref count when collapsing a page. We don't allow a collapse page
+- * if we have gup taken on the page. We can ensure that by sending IPI
+- * because gup walk happens with IRQ disabled.
+- */
+- serialize_against_pte_lookup(vma->vm_mm);
+-
+ radix__flush_tlb_collapsed_pmd(vma->vm_mm, address);
+
+ return pmd;
projects / thirdparty / kernel / stable-queue.git / commitdiff
