summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorHugh Dickins <hughd@google.com>2021-06-15 18:23:53 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-06-16 09:24:42 -0700
commit732ed55823fc3ad998d43b86bf771887bcc5ec67 (patch)
treea1df9c1b8e346b6c861d8c6b2d5ec08ebc1e3aaf /mm
parent3b77e8c8cde581dadab9a0f1543a347e24315f11 (diff)
downloadlinux-732ed55823fc3ad998d43b86bf771887bcc5ec67.tar.bz2
mm/thp: try_to_unmap() use TTU_SYNC for safe splitting
Stressing huge tmpfs often crashed on unmap_page()'s VM_BUG_ON_PAGE (!unmap_success): with dump_page() showing mapcount:1, but then its raw struct page output showing _mapcount ffffffff i.e. mapcount 0. And even if that particular VM_BUG_ON_PAGE(!unmap_success) is removed, it is immediately followed by a VM_BUG_ON_PAGE(compound_mapcount(head)), and further down an IS_ENABLED(CONFIG_DEBUG_VM) total_mapcount BUG(): all indicative of some mapcount difficulty in development here perhaps. But the !CONFIG_DEBUG_VM path handles the failures correctly and silently. I believe the problem is that once a racing unmap has cleared pte or pmd, try_to_unmap_one() may skip taking the page table lock, and emerge from try_to_unmap() before the racing task has reached decrementing mapcount. Instead of abandoning the unsafe VM_BUG_ON_PAGE(), and the ones that follow, use PVMW_SYNC in try_to_unmap_one() in this case: adding TTU_SYNC to the options, and passing that from unmap_page(). When CONFIG_DEBUG_VM, or for non-debug too? Consensus is to do the same for both: the slight overhead added should rarely matter, except perhaps if splitting sparsely-populated multiply-mapped shmem. Once confident that bugs are fixed, TTU_SYNC here can be removed, and the race tolerated. Link: https://lkml.kernel.org/r/c1e95853-8bcd-d8fd-55fa-e7f2488e78f@google.com Fixes: fec89c109f3a ("thp: rewrite freeze_page()/unfreeze_page() with generic rmap walkers") Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Jan Kara <jack@suse.cz> Cc: Jue Wang <juew@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/huge_memory.c2
-rw-r--r--mm/page_vma_mapped.c11
-rw-r--r--mm/rmap.c17
3 files changed, 28 insertions, 2 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 5885c5f5836f..84ab735139dc 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2350,7 +2350,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
static void unmap_page(struct page *page)
{
- enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK |
+ enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_SYNC |
TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
bool unmap_success;
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index 2cf01d933f13..5b559967410e 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -212,6 +212,17 @@ restart:
pvmw->ptl = NULL;
}
} else if (!pmd_present(pmde)) {
+ /*
+ * If PVMW_SYNC, take and drop THP pmd lock so that we
+ * cannot return prematurely, while zap_huge_pmd() has
+ * cleared *pmd but not decremented compound_mapcount().
+ */
+ if ((pvmw->flags & PVMW_SYNC) &&
+ PageTransCompound(pvmw->page)) {
+ spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);
+
+ spin_unlock(ptl);
+ }
return false;
}
if (!map_pte(pvmw))
diff --git a/mm/rmap.c b/mm/rmap.c
index 693a610e181d..07811b4ae793 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1405,6 +1405,15 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
struct mmu_notifier_range range;
enum ttu_flags flags = (enum ttu_flags)(long)arg;
+ /*
+ * When racing against e.g. zap_pte_range() on another cpu,
+ * in between its ptep_get_and_clear_full() and page_remove_rmap(),
+ * try_to_unmap() may return false when it is about to become true,
+ * if page table locking is skipped: use TTU_SYNC to wait for that.
+ */
+ if (flags & TTU_SYNC)
+ pvmw.flags = PVMW_SYNC;
+
/* munlock has nothing to gain from examining un-locked vmas */
if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED))
return true;
@@ -1777,7 +1786,13 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags)
else
rmap_walk(page, &rwc);
- return !page_mapcount(page) ? true : false;
+ /*
+ * When racing against e.g. zap_pte_range() on another cpu,
+ * in between its ptep_get_and_clear_full() and page_remove_rmap(),
+ * try_to_unmap() may return false when it is about to become true,
+ * if page table locking is skipped: use TTU_SYNC to wait for that.
+ */
+ return !page_mapcount(page);
}
/**