From b3a81d0841a954a3d3e782059960f53e63b37066 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 10 Aug 2017 15:24:15 -0700 Subject: [PATCH] mm: fix KSM data corruption Nadav reported KSM can corrupt the user data by the TLB batching race[1]. That means data user written can be lost. Quote from Nadav Amit: "For this race we need 4 CPUs: CPU0: Caches a writable and dirty PTE entry, and uses the stale value for write later. CPU1: Runs madvise_free on the range that includes the PTE. It would clear the dirty-bit. It batches TLB flushes. CPU2: Writes 4 to /proc/PID/clear_refs , clearing the PTEs soft-dirty. We care about the fact that it clears the PTE write-bit, and of course, batches TLB flushes. CPU3: Runs KSM. Our purpose is to pass the following test in write_protect_page(): if (pte_write(*pvmw.pte) || pte_dirty(*pvmw.pte) || (pte_protnone(*pvmw.pte) && pte_savedwrite(*pvmw.pte))) Since it will avoid TLB flush. And we want to do it while the PTE is stale. Later, and before replacing the page, we would be able to change the page. Note that all the operations the CPU1-3 perform canhappen in parallel since they only acquire mmap_sem for read. We start with two identical pages. Everything below regards the same page/PTE. CPU0 CPU1 CPU2 CPU3 ---- ---- ---- ---- Write the same value on page [cache PTE as dirty in TLB] MADV_FREE pte_mkclean() 4 > clear_refs pte_wrprotect() write_protect_page() [ success, no flush ] pages_indentical() [ ok ] Write to page different value [Ok, using stale PTE] replace_page() Later, CPU1, CPU2 and CPU3 would flush the TLB, but that is too late. CPU0 already wrote on the page, but KSM ignored this write, and it got lost" In above scenario, MADV_FREE is fixed by changing TLB batching API including [set|clear]_tlb_flush_pending. Remained thing is soft-dirty part. This patch changes soft-dirty uses TLB batching API instead of flush_tlb_mm and KSM checks pending TLB flush by using mm_tlb_flush_pending so that it will flush TLB to avoid data lost if there are other parallel threads pending TLB flush. [1] http://lkml.kernel.org/r/BD3A0EBE-ECF4-41D4-87FA-C755EA9AB6BD@gmail.com Link: http://lkml.kernel.org/r/20170802000818.4760-8-namit@vmware.com Signed-off-by: Minchan Kim Signed-off-by: Nadav Amit Reported-by: Nadav Amit Tested-by: Nadav Amit Reviewed-by: Andrea Arcangeli Cc: Mel Gorman Cc: Hugh Dickins Cc: "David S. Miller" Cc: Andy Lutomirski Cc: Heiko Carstens Cc: Ingo Molnar Cc: Jeff Dike Cc: Martin Schwidefsky Cc: Mel Gorman Cc: Nadav Amit Cc: Rik van Riel Cc: Russell King Cc: Sergey Senozhatsky Cc: Tony Luck Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 7 +++++-- mm/ksm.c | 3 ++- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index b836fd61ed87..fe8f3265e877 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -16,9 +16,10 @@ #include #include #include +#include #include -#include +#include #include #include "internal.h" @@ -1008,6 +1009,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, struct mm_struct *mm; struct vm_area_struct *vma; enum clear_refs_types type; + struct mmu_gather tlb; int itype; int rv; @@ -1054,6 +1056,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, } down_read(&mm->mmap_sem); + tlb_gather_mmu(&tlb, mm, 0, -1); if (type == CLEAR_REFS_SOFT_DIRTY) { for (vma = mm->mmap; vma; vma = vma->vm_next) { if (!(vma->vm_flags & VM_SOFTDIRTY)) @@ -1075,7 +1078,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, walk_page_range(0, mm->highest_vm_end, &clear_refs_walk); if (type == CLEAR_REFS_SOFT_DIRTY) mmu_notifier_invalidate_range_end(mm, 0, -1); - flush_tlb_mm(mm); + tlb_finish_mmu(&tlb, 0, -1); up_read(&mm->mmap_sem); out_mm: mmput(mm); diff --git a/mm/ksm.c b/mm/ksm.c index 4dc92f138786..db20f8436bc3 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1038,7 +1038,8 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, goto out_unlock; if (pte_write(*pvmw.pte) || pte_dirty(*pvmw.pte) || - (pte_protnone(*pvmw.pte) && pte_savedwrite(*pvmw.pte))) { + (pte_protnone(*pvmw.pte) && pte_savedwrite(*pvmw.pte)) || + mm_tlb_flush_pending(mm)) { pte_t entry; swapped = PageSwapCache(page);