7 files changed, 84 insertions, 14 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index ba2b0c87e65b..b908048f8d6a 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1233,6 +1233,7 @@ config RCU_TORTURE_TEST
         depends on DEBUG_KERNEL
         select TORTURE_TEST
         select SRCU
+        select TASKS_RCU
         default n
         help
           This option provides a kernel module that runs torture tests
@@ -1261,12 +1262,38 @@ config RCU_TORTURE_TEST_RUNNABLE
           Say N here if you want the RCU torture tests to start only
           after being manually enabled via /proc.
 
+config RCU_TORTURE_TEST_SLOW_PREINIT
+        bool "Slow down RCU grace-period pre-initialization to expose races"
+        depends on RCU_TORTURE_TEST
+        help
+          This option delays grace-period pre-initialization (the
+          propagation of CPU-hotplug changes up the rcu_node combining
+          tree) for a few jiffies between initializing each pair of
+          consecutive rcu_node structures.  This helps to expose races
+          involving grace-period pre-initialization, in other words, it
+          makes your kernel less stable.  It can also greatly increase
+          grace-period latency, especially on systems with large numbers
+          of CPUs.  This is useful when torture-testing RCU, but in
+          almost no other circumstance.
+
+          Say Y here if you want your system to crash and hang more often.
+          Say N if you want a sane system.
+
+config RCU_TORTURE_TEST_SLOW_PREINIT_DELAY
+        int "How much to slow down RCU grace-period pre-initialization"
+        range 0 5
+        default 3
+        depends on RCU_TORTURE_TEST_SLOW_PREINIT
+        help
+          This option specifies the number of jiffies to wait between
+          each rcu_node structure pre-initialization step.
+
 config RCU_TORTURE_TEST_SLOW_INIT
         bool "Slow down RCU grace-period initialization to expose races"
         depends on RCU_TORTURE_TEST
         help
-          This option makes grace-period initialization block for a
-          few jiffies between initializing each pair of consecutive
+          This option delays grace-period initialization for a few
+          jiffies between initializing each pair of consecutive
           rcu_node structures.  This helps to expose races involving
           grace-period initialization, in other words, it makes your
           kernel less stable.  It can also greatly increase grace-period
@@ -1286,6 +1313,30 @@ config RCU_TORTURE_TEST_SLOW_INIT_DELAY
           This option specifies the number of jiffies to wait between
           each rcu_node structure initialization.
 
+config RCU_TORTURE_TEST_SLOW_CLEANUP
+        bool "Slow down RCU grace-period cleanup to expose races"
+        depends on RCU_TORTURE_TEST
+        help
+          This option delays grace-period cleanup for a few jiffies
+          between cleaning up each pair of consecutive rcu_node
+          structures.  This helps to expose races involving grace-period
+          cleanup, in other words, it makes your kernel less stable.
+          It can also greatly increase grace-period latency, especially
+          on systems with large numbers of CPUs.  This is useful when
+          torture-testing RCU, but in almost no other circumstance.
+
+          Say Y here if you want your system to crash and hang more often.
+          Say N if you want a sane system.
+
+config RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY
+        int "How much to slow down RCU grace-period cleanup"
+        range 0 5
+        default 3
+        depends on RCU_TORTURE_TEST_SLOW_CLEANUP
+        help
+          This option specifies the number of jiffies to wait between
+          each rcu_node structure cleanup operation.
+
 config RCU_CPU_STALL_TIMEOUT
         int "RCU CPU stall timeout in seconds"
         depends on RCU_STALL_COMMON
@@ -1322,6 +1373,17 @@ config RCU_TRACE
           Say Y here if you want to enable RCU tracing
           Say N if you are unsure.
 
+config RCU_EQS_DEBUG
+        bool "Use this when adding any sort of NO_HZ support to your arch"
+        depends on DEBUG_KERNEL
+        help
+          This option provides consistency checks in RCU's handling of
+          NO_HZ.  These checks have proven quite helpful in detecting
+          bugs in arch-specific NO_HZ code.
+
+          Say N here if you need ultimate kernel/user switch latencies
+          Say Y if you are unsure
+
 endmenu # "RCU Debugging"
 
 config DEBUG_BLOCK_EXT_DEVT
diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c
index 4f134d8907a7..f610b2a10b3e 100644
--- a/lib/cpu_rmap.c
+++ b/lib/cpu_rmap.c
@@ -191,7 +191,7 @@ int cpu_rmap_update(struct cpu_rmap *rmap, u16 index,
         /* Update distances based on topology */
         for_each_cpu(cpu, update_mask) {
                 if (cpu_rmap_copy_neigh(rmap, cpu,
-                                        topology_thread_cpumask(cpu), 1))
+                                        topology_sibling_cpumask(cpu), 1))
                         continue;
                 if (cpu_rmap_copy_neigh(rmap, cpu,
                                         topology_core_cpumask(cpu), 2))
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 5f627084f2e9..5a70f6196f57 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -16,11 +16,10 @@
 int cpumask_next_and(int n, const struct cpumask *src1p,
                      const struct cpumask *src2p)
 {
-        struct cpumask tmp;
-
-        if (cpumask_and(&tmp, src1p, src2p))
-                return cpumask_next(n, &tmp);
-        return nr_cpu_ids;
+        while ((n = cpumask_next(n, src1p)) < nr_cpu_ids)
+                if (cpumask_test_cpu(n, src2p))
+                        break;
+        return n;
 }
 EXPORT_SYMBOL(cpumask_next_and);
 
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 3d2aa27b845b..061550de77bc 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -33,7 +33,7 @@
 #include <linux/string.h>
 #include <linux/bitops.h>
 #include <linux/rcupdate.h>
-#include <linux/preempt_mask.h>         /* in_interrupt() */
+#include <linux/preempt.h>              /* in_interrupt() */
 
 
 /*
diff --git a/lib/raid6/x86.h b/lib/raid6/x86.h
index b7595484a815..8fe9d9662abb 100644
--- a/lib/raid6/x86.h
+++ b/lib/raid6/x86.h
@@ -23,7 +23,7 @@
 
 #ifdef __KERNEL__ /* Real code */
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 #else /* Dummy code for user space testing */
 
diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c
index fe9a32591c24..3a5f2b366d84 100644
--- a/lib/strnlen_user.c
+++ b/lib/strnlen_user.c
@@ -85,7 +85,8 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count,
  * @str: The string to measure.
  * @count: Maximum count (including NUL character)
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Get the size of a NUL-terminated string in user space.
  *
@@ -121,7 +122,8 @@ EXPORT_SYMBOL(strnlen_user);
  * strlen_user: - Get the size of a user string INCLUDING final NUL.
  * @str: The string to measure.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Get the size of a NUL-terminated string in user space.
  *
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 3c365ab6cf5f..42e192decbfd 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -656,7 +656,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
                  */
                 phys_addr_t paddr = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
                 if (paddr == SWIOTLB_MAP_ERROR)
-                        return NULL;
+                        goto err_warn;
 
                 ret = phys_to_virt(paddr);
                 dev_addr = phys_to_dma(hwdev, paddr);
@@ -670,7 +670,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
                         /* DMA_TO_DEVICE to avoid memcpy in unmap_single */
                         swiotlb_tbl_unmap_single(hwdev, paddr,
                                                  size, DMA_TO_DEVICE);
-                        return NULL;
+                        goto err_warn;
                 }
         }
 
@@ -678,6 +678,13 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
         memset(ret, 0, size);
 
         return ret;
+
+err_warn:
+        pr_warn("swiotlb: coherent allocation failed for device %s size=%zu\n",
+                dev_name(hwdev), size);
+        dump_stack();
+
+        return NULL;
 }
 EXPORT_SYMBOL(swiotlb_alloc_coherent);