Merge tag 'v3.2.22' into v3.2-rt

This is the 3.2.22 stable release

1 files changed, 30 insertions, 2 deletions

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index a03c098b0cce..bc008761cb6c 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -445,6 +445,18 @@ static inline int pmd_write(pmd_t pmd)
 #endif /* __HAVE_ARCH_PMD_WRITE */
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+#ifndef pmd_read_atomic
+static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
+{
+	/*
+	 * Depend on compiler for an atomic pmd read. NOTE: this is
+	 * only going to work, if the pmdval_t isn't larger than
+	 * an unsigned long.
+	 */
+	return *pmdp;
+}
+#endif
+
 /*
  * 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
@@ -458,14 +470,30 @@ static inline int pmd_write(pmd_t pmd)
  * 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.
+ *
+ * For 32bit kernels with a 64bit large pmd_t this automatically takes
+ * care of reading the pmd atomically to avoid SMP race conditions
+ * against pmd_populate() when the mmap_sem is hold for reading by the
+ * caller (a special atomic read not done by "gcc" as in the generic
+ * version above, is also needed when THP is disabled because the page
+ * fault can populate the pmd from under us).
  */
 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;
+	pmd_t pmdval = pmd_read_atomic(pmd);
 	/*
 	 * The barrier will stabilize the pmdval in a register or on
 	 * the stack so that it will stop changing under the code.
+	 *
+	 * When CONFIG_TRANSPARENT_HUGEPAGE=y on x86 32bit PAE,
+	 * pmd_read_atomic is allowed to return a not atomic pmdval
+	 * (for example pointing to an hugepage that has never been
+	 * mapped in the pmd). The below checks will only care about
+	 * the low part of the pmd with 32bit PAE x86 anyway, with the
+	 * exception of pmd_none(). So the important thing is that if
+	 * the low part of the pmd is found null, the high part will
+	 * be also null or the pmd_none() check below would be
+	 * confused.
 	 */
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	barrier();