4 files changed, 39 insertions, 5 deletions

diff --git a/include/asm-generic/mutex-xchg.h b/include/asm-generic/mutex-xchg.h
index 580a6d3..c04e0db 100644
--- a/include/asm-generic/mutex-xchg.h
+++ b/include/asm-generic/mutex-xchg.h
@@ -26,7 +26,13 @@ static inline void
 __mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
 {
 	if (unlikely(atomic_xchg(count, 0) != 1))
-		fail_fn(count);
+		/*
+		 * We failed to acquire the lock, so mark it contended
+		 * to ensure that any waiting tasks are woken up by the
+		 * unlock slow path.
+		 */
+		if (likely(atomic_xchg(count, -1) != 1))
+			fail_fn(count);
 }
 
 /**
@@ -43,7 +49,8 @@ static inline int
 __mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *))
 {
 	if (unlikely(atomic_xchg(count, 0) != 1))
-		return fail_fn(count);
+		if (likely(atomic_xchg(count, -1) != 1))
+			return fail_fn(count);
 	return 0;
 }
 
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index a03c098..831924a 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
@@ -458,11 +470,17 @@ 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.
diff --git a/include/asm-generic/statfs.h b/include/asm-generic/statfs.h
index 0fd28e0..c749af9 100644
--- a/include/asm-generic/statfs.h
+++ b/include/asm-generic/statfs.h
@@ -15,7 +15,7 @@ typedef __kernel_fsid_t	fsid_t;
  * with a 10' pole.
  */
 #ifndef __statfs_word
-#if BITS_PER_LONG == 64
+#if __BITS_PER_LONG == 64
 #define __statfs_word long
 #else
 #define __statfs_word __u32
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index e58fa77..34e0274 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -78,6 +78,14 @@ struct mmu_gather_batch {
 #define MAX_GATHER_BATCH	\
 	((PAGE_SIZE - sizeof(struct mmu_gather_batch)) / sizeof(void *))
 
+/*
+ * Limit the maximum number of mmu_gather batches to reduce a risk of soft
+ * lockups for non-preemptible kernels on huge machines when a lot of memory
+ * is zapped during unmapping.
+ * 10K pages freed at once should be safe even without a preemption point.
+ */
+#define MAX_GATHER_BATCH_COUNT	(10000UL/MAX_GATHER_BATCH)
+
 /* struct mmu_gather is an opaque type used by the mm code for passing around
  * any data needed by arch specific code for tlb_remove_page.
  */
@@ -94,6 +102,7 @@ struct mmu_gather {
 	struct mmu_gather_batch *active;
 	struct mmu_gather_batch	local;
 	struct page		*__pages[MMU_GATHER_BUNDLE];
+	unsigned int		batch_count;
 };
 
 #define HAVE_GENERIC_MMU_GATHER