From: Greg Kroah-Hartman Date: Fri, 2 Nov 2018 17:00:14 +0000 (+0100) Subject: 4.4-stable patches X-Git-Tag: v4.19.1~8 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=adf0bba8ebe45e7c39f80d8aa6f0b12824732a95;p=thirdparty%2Fkernel%2Fstable-queue.git 4.4-stable patches added patches: mremap-properly-flush-tlb-before-releasing-the-page.patch --- diff --git a/queue-4.4/mremap-properly-flush-tlb-before-releasing-the-page.patch b/queue-4.4/mremap-properly-flush-tlb-before-releasing-the-page.patch new file mode 100644 index 00000000000..500a60e32e9 --- /dev/null +++ b/queue-4.4/mremap-properly-flush-tlb-before-releasing-the-page.patch @@ -0,0 +1,143 @@ +From will.deacon@arm.com Fri Nov 2 17:52:03 2018 +From: Will Deacon +Date: Fri, 2 Nov 2018 13:22:42 +0000 +Subject: mremap: properly flush TLB before releasing the page +To: gregkh@linuxfoundation.org +Cc: stable@vger.kernel.org, linux-kernel@vger.kernel.org, jannh@google.com, mingo@kernel.org, peterz@infradead.org, torvalds@linux-foundation.org, Will Deacon +Message-ID: <1541164962-28533-1-git-send-email-will.deacon@arm.com> + + +From: Linus Torvalds + +Commit eb66ae030829605d61fbef1909ce310e29f78821 upstream. + +This is a backport to stable 4.4.y. + +Jann Horn points out that our TLB flushing was subtly wrong for the +mremap() case. What makes mremap() special is that we don't follow the +usual "add page to list of pages to be freed, then flush tlb, and then +free pages". No, mremap() obviously just _moves_ the page from one page +table location to another. + +That matters, because mremap() thus doesn't directly control the +lifetime of the moved page with a freelist: instead, the lifetime of the +page is controlled by the page table locking, that serializes access to +the entry. + +As a result, we need to flush the TLB not just before releasing the lock +for the source location (to avoid any concurrent accesses to the entry), +but also before we release the destination page table lock (to avoid the +TLB being flushed after somebody else has already done something to that +page). + +This also makes the whole "need_flush" logic unnecessary, since we now +always end up flushing the TLB for every valid entry. + +Reported-and-tested-by: Jann Horn +Acked-by: Will Deacon +Tested-by: Ingo Molnar +Acked-by: Peter Zijlstra (Intel) +Signed-off-by: Linus Torvalds +Signed-off-by: Greg Kroah-Hartman +[will: backport to 4.4 stable] +Signed-off-by: Will Deacon +Signed-off-by: Greg Kroah-Hartman +--- + mm/huge_memory.c | 6 +++++- + mm/mremap.c | 21 ++++++++++++++++----- + 2 files changed, 21 insertions(+), 6 deletions(-) + +--- a/mm/huge_memory.c ++++ b/mm/huge_memory.c +@@ -1511,7 +1511,7 @@ int move_huge_pmd(struct vm_area_struct + spinlock_t *old_ptl, *new_ptl; + int ret = 0; + pmd_t pmd; +- ++ bool force_flush = false; + struct mm_struct *mm = vma->vm_mm; + + if ((old_addr & ~HPAGE_PMD_MASK) || +@@ -1539,6 +1539,8 @@ int move_huge_pmd(struct vm_area_struct + if (new_ptl != old_ptl) + spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); + pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd); ++ if (pmd_present(pmd)) ++ force_flush = true; + VM_BUG_ON(!pmd_none(*new_pmd)); + + if (pmd_move_must_withdraw(new_ptl, old_ptl)) { +@@ -1547,6 +1549,8 @@ int move_huge_pmd(struct vm_area_struct + pgtable_trans_huge_deposit(mm, new_pmd, pgtable); + } + set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd)); ++ if (force_flush) ++ flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE); + if (new_ptl != old_ptl) + spin_unlock(new_ptl); + spin_unlock(old_ptl); +--- a/mm/mremap.c ++++ b/mm/mremap.c +@@ -96,6 +96,8 @@ static void move_ptes(struct vm_area_str + struct mm_struct *mm = vma->vm_mm; + pte_t *old_pte, *new_pte, pte; + spinlock_t *old_ptl, *new_ptl; ++ bool force_flush = false; ++ unsigned long len = old_end - old_addr; + + /* + * When need_rmap_locks is true, we take the i_mmap_rwsem and anon_vma +@@ -143,12 +145,26 @@ static void move_ptes(struct vm_area_str + if (pte_none(*old_pte)) + continue; + pte = ptep_get_and_clear(mm, old_addr, old_pte); ++ /* ++ * If we are remapping a valid PTE, make sure ++ * to flush TLB before we drop the PTL for the PTE. ++ * ++ * NOTE! Both old and new PTL matter: the old one ++ * for racing with page_mkclean(), the new one to ++ * make sure the physical page stays valid until ++ * the TLB entry for the old mapping has been ++ * flushed. ++ */ ++ if (pte_present(pte)) ++ force_flush = true; + pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr); + pte = move_soft_dirty_pte(pte); + set_pte_at(mm, new_addr, new_pte, pte); + } + + arch_leave_lazy_mmu_mode(); ++ if (force_flush) ++ flush_tlb_range(vma, old_end - len, old_end); + if (new_ptl != old_ptl) + spin_unlock(new_ptl); + pte_unmap(new_pte - 1); +@@ -168,7 +184,6 @@ unsigned long move_page_tables(struct vm + { + unsigned long extent, next, old_end; + pmd_t *old_pmd, *new_pmd; +- bool need_flush = false; + unsigned long mmun_start; /* For mmu_notifiers */ + unsigned long mmun_end; /* For mmu_notifiers */ + +@@ -207,7 +222,6 @@ unsigned long move_page_tables(struct vm + anon_vma_unlock_write(vma->anon_vma); + } + if (err > 0) { +- need_flush = true; + continue; + } else if (!err) { + split_huge_page_pmd(vma, old_addr, old_pmd); +@@ -224,10 +238,7 @@ unsigned long move_page_tables(struct vm + extent = LATENCY_LIMIT; + move_ptes(vma, old_pmd, old_addr, old_addr + extent, + new_vma, new_pmd, new_addr, need_rmap_locks); +- need_flush = true; + } +- if (likely(need_flush)) +- flush_tlb_range(vma, old_end-len, old_addr); + + mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end); + diff --git a/queue-4.4/series b/queue-4.4/series index 5c61d79d641..b192851e092 100644 --- a/queue-4.4/series +++ b/queue-4.4/series @@ -99,3 +99,4 @@ sctp-fix-race-on-sctp_id2asoc.patch net-drop-skb-on-failure-in-ip_check_defrag.patch vhost-fix-spectre-v1-vulnerability.patch rtnetlink-disallow-fdb-configuration-for-non-ethernet-device.patch +mremap-properly-flush-tlb-before-releasing-the-page.patch