summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorHugh Dickins <hughd@google.com>2021-06-24 18:39:26 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-06-24 19:40:53 -0700
commita9a7504d9beaf395481faa91e70e2fd08f7a3dde (patch)
tree02b96e9bf0891ded5ff4592f097b76c2f01ac05f
parenta765c417d876cc635f628365ec9aa6f09470069a (diff)
mm/thp: fix page_vma_mapped_walk() if THP mapped by ptes
Running certain tests with a DEBUG_VM kernel would crash within hours, on the total_mapcount BUG() in split_huge_page_to_list(), while trying to free up some memory by punching a hole in a shmem huge page: split's try_to_unmap() was unable to find all the mappings of the page (which, on a !DEBUG_VM kernel, would then keep the huge page pinned in memory). Crash dumps showed two tail pages of a shmem huge page remained mapped by pte: ptes in a non-huge-aligned vma of a gVisor process, at the end of a long unmapped range; and no page table had yet been allocated for the head of the huge page to be mapped into. Although designed to handle these odd misaligned huge-page-mapped-by-pte cases, page_vma_mapped_walk() falls short by returning false prematurely when !pmd_present or !pud_present or !p4d_present or !pgd_present: there are cases when a huge page may span the boundary, with ptes present in the next. Restructure page_vma_mapped_walk() as a loop to continue in these cases, while keeping its layout much as before. Add a step_forward() helper to advance pvmw->address across those boundaries: originally I tried to use mm's standard p?d_addr_end() macros, but hit the same crash 512 times less often: because of the way redundant levels are folded together, but folded differently in different configurations, it was just too difficult to use them correctly; and step_forward() is simpler anyway. Link: https://lkml.kernel.org/r/fedb8632-1798-de42-f39e-873551d5bc81@google.com Fixes: ace71a19cec5 ("mm: introduce page_vma_mapped_walk()") Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Will Deacon <will@kernel.org> 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>
-rw-r--r--mm/page_vma_mapped.c34
1 files changed, 25 insertions, 9 deletions
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index df89ea3df4f4..a4e962b510c7 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -116,6 +116,13 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
return pfn_is_match(pvmw->page, pfn);
}
+static void step_forward(struct page_vma_mapped_walk *pvmw, unsigned long size)
+{
+ pvmw->address = (pvmw->address + size) & ~(size - 1);
+ if (!pvmw->address)
+ pvmw->address = ULONG_MAX;
+}
+
/**
* page_vma_mapped_walk - check if @pvmw->page is mapped in @pvmw->vma at
* @pvmw->address
@@ -183,16 +190,22 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
if (pvmw->pte)
goto next_pte;
restart:
- {
+ do {
pgd = pgd_offset(mm, pvmw->address);
- if (!pgd_present(*pgd))
- return false;
+ if (!pgd_present(*pgd)) {
+ step_forward(pvmw, PGDIR_SIZE);
+ continue;
+ }
p4d = p4d_offset(pgd, pvmw->address);
- if (!p4d_present(*p4d))
- return false;
+ if (!p4d_present(*p4d)) {
+ step_forward(pvmw, P4D_SIZE);
+ continue;
+ }
pud = pud_offset(p4d, pvmw->address);
- if (!pud_present(*pud))
- return false;
+ if (!pud_present(*pud)) {
+ step_forward(pvmw, PUD_SIZE);
+ continue;
+ }
pvmw->pmd = pmd_offset(pud, pvmw->address);
/*
@@ -239,7 +252,8 @@ restart:
spin_unlock(ptl);
}
- return false;
+ step_forward(pvmw, PMD_SIZE);
+ continue;
}
if (!map_pte(pvmw))
goto next_pte;
@@ -269,7 +283,9 @@ next_pte:
spin_lock(pvmw->ptl);
}
goto this_pte;
- }
+ } while (pvmw->address < end);
+
+ return false;
}
/**