summaryrefslogtreecommitdiffstats
path: root/include/asm-generic/pgtable.h
diff options
context:
space:
mode:
Diffstat (limited to 'include/asm-generic/pgtable.h')
-rw-r--r--include/asm-generic/pgtable.h61
1 files changed, 61 insertions, 0 deletions
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 76bff2bff15..a03c098b0cc 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -425,6 +425,8 @@ extern void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
unsigned long size);
#endif
+#ifdef CONFIG_MMU
+
#ifndef CONFIG_TRANSPARENT_HUGEPAGE
static inline int pmd_trans_huge(pmd_t pmd)
{
@@ -441,7 +443,66 @@ static inline int pmd_write(pmd_t pmd)
return 0;
}
#endif /* __HAVE_ARCH_PMD_WRITE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+/*
+ * This function is meant to be used by sites walking pagetables with
+ * the mmap_sem hold in read mode to protect against MADV_DONTNEED and
+ * transhuge page faults. MADV_DONTNEED can convert a transhuge pmd
+ * into a null pmd and the transhuge page fault can convert a null pmd
+ * into an hugepmd or into a regular pmd (if the hugepage allocation
+ * fails). While holding the mmap_sem in read mode the pmd becomes
+ * stable and stops changing under us only if it's not null and not a
+ * transhuge pmd. When those races occurs and this function makes a
+ * difference vs the standard pmd_none_or_clear_bad, the result is
+ * undefined so behaving like if the pmd was none is safe (because it
+ * can return none anyway). The compiler level barrier() is critically
+ * important to compute the two checks atomically on the same pmdval.
+ */
+static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd)
+{
+ /* depend on compiler for an atomic pmd read */
+ pmd_t pmdval = *pmd;
+ /*
+ * The barrier will stabilize the pmdval in a register or on
+ * the stack so that it will stop changing under the code.
+ */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ barrier();
+#endif
+ if (pmd_none(pmdval))
+ return 1;
+ if (unlikely(pmd_bad(pmdval))) {
+ if (!pmd_trans_huge(pmdval))
+ pmd_clear_bad(pmd);
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * This is a noop if Transparent Hugepage Support is not built into
+ * the kernel. Otherwise it is equivalent to
+ * pmd_none_or_trans_huge_or_clear_bad(), and shall only be called in
+ * places that already verified the pmd is not none and they want to
+ * walk ptes while holding the mmap sem in read mode (write mode don't
+ * need this). If THP is not enabled, the pmd can't go away under the
+ * code even if MADV_DONTNEED runs, but if THP is enabled we need to
+ * run a pmd_trans_unstable before walking the ptes after
+ * split_huge_page_pmd returns (because it may have run when the pmd
+ * become null, but then a page fault can map in a THP and not a
+ * regular page).
+ */
+static inline int pmd_trans_unstable(pmd_t *pmd)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ return pmd_none_or_trans_huge_or_clear_bad(pmd);
+#else
+ return 0;
#endif
+}
+
+#endif /* CONFIG_MMU */
#endif /* !__ASSEMBLY__ */