mm/thp: make is_huge_zero_pmd() safe and quicker

Most callers of is_huge_zero_pmd() supply a pmd already verified
present; but a few (notably zap_huge_pmd()) do not - it might be a pmd
migration entry, in which the pfn is encoded differently from a present
pmd: which might pass the is_huge_zero_pmd() test (though not on x86,
since L1TF forced us to protect against that); or perhaps even crash in
pmd_page() applied to a swap-like entry.

Make it safe by adding pmd_present() check into is_huge_zero_pmd()
itself; and make it quicker by saving huge_zero_pfn, so that
is_huge_zero_pmd() will not need to do that pmd_page() lookup each time.

__split_huge_pmd_locked() checked pmd_trans_huge() before: that worked,
but is unnecessary now that is_huge_zero_pmd() checks present.

Link: https://lkml.kernel.org/r/21ea9ca-a1f5-8b90-5e88-95fb1c49bbfa@google.com
Fixes: e71769ae5260 ("mm: enable thp migration for shmem thp")
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jue Wang <juew@google.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: 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>

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 9626fda5efcea02d28d54c48079b5e5e0ab62235..2a8ebe6c222ef977bac26902cbb3013c1f45840a 100644 (file)
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -286,6 +286,7 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
 vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd);
 
 extern struct page *huge_zero_page;
+extern unsigned long huge_zero_pfn;
 
 static inline bool is_huge_zero_page(struct page *page)
 {
@@ -294,7 +295,7 @@ static inline bool is_huge_zero_page(struct page *page)
 
 static inline bool is_huge_zero_pmd(pmd_t pmd)
 {
-       return is_huge_zero_page(pmd_page(pmd));
+       return READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd) && pmd_present(pmd);
 }
 
 static inline bool is_huge_zero_pud(pud_t pud)
@@ -440,6 +441,11 @@ static inline bool is_huge_zero_page(struct page *page)
        return false;
 }
 
+static inline bool is_huge_zero_pmd(pmd_t pmd)
+{
+       return false;
+}
+
 static inline bool is_huge_zero_pud(pud_t pud)
 {
        return false;

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 42cfefc6e66e3c5421c1863b1a1cbd4df7d41923..5885c5f5836f4aa6a7eb8e925e9009a0c8135e5c 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -62,6 +62,7 @@ static struct shrinker deferred_split_shrinker;
 
 static atomic_t huge_zero_refcount;
 struct page *huge_zero_page __read_mostly;
+unsigned long huge_zero_pfn __read_mostly = ~0UL;
 
 bool transparent_hugepage_enabled(struct vm_area_struct *vma)
 {
@@ -98,6 +99,7 @@ retry:
                __free_pages(zero_page, compound_order(zero_page));
                goto retry;
        }
+       WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page));
 
        /* We take additional reference here. It will be put back by shrinker */
        atomic_set(&huge_zero_refcount, 2);
@@ -147,6 +149,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
        if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
                struct page *zero_page = xchg(&huge_zero_page, NULL);
                BUG_ON(zero_page == NULL);
+               WRITE_ONCE(huge_zero_pfn, ~0UL);
                __free_pages(zero_page, compound_order(zero_page));
                return HPAGE_PMD_NR;
        }
@@ -2071,7 +2074,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
                return;
        }
 
-       if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) {
+       if (is_huge_zero_pmd(*pmd)) {
                /*
                 * FIXME: Do we want to invalidate secondary mmu by calling
                 * mmu_notifier_invalidate_range() see comments below inside