6 files changed, 46 insertions, 12 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 85cf7ea978aa..7823f8342abf 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -157,4 +157,11 @@ config CHECK_SIGNATURE
 config HAVE_LMB
         boolean
 
+config CPUMASK_OFFSTACK
+        bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS
+        help
+          Use dynamic allocation for cpumask_var_t, instead of putting
+          them on the stack.  This is a bit more expensive, but avoids
+          stack overflow.
+
 endmenu
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index b0f239e443bc..1e3fd3e3436a 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -545,6 +545,16 @@ config DEBUG_SG
 
           If unsure, say N.
 
+config DEBUG_NOTIFIERS
+        bool "Debug notifier call chains"
+        depends on DEBUG_KERNEL
+        help
+          Enable this to turn on sanity checking for notifier call chains.
+          This is most useful for kernel developers to make sure that
+          modules properly unregister themselves from notifier chains.
+          This is a relatively cheap check but if you care about maximum
+          performance, say N.
+
 config FRAME_POINTER
         bool "Compile the kernel with frame pointers"
         depends on DEBUG_KERNEL && \
diff --git a/lib/idr.c b/lib/idr.c
index e728c7fccc4d..1c4f9281f412 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -185,6 +185,7 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa)
                         new = get_from_free_list(idp);
                         if (!new)
                                 return -1;
+                        new->layer = l-1;
                         rcu_assign_pointer(p->ary[m], new);
                         p->count++;
                 }
@@ -210,6 +211,7 @@ build_up:
         if (unlikely(!p)) {
                 if (!(p = get_from_free_list(idp)))
                         return -1;
+                p->layer = 0;
                 layers = 1;
         }
         /*
@@ -218,8 +220,14 @@ build_up:
          */
         while ((layers < (MAX_LEVEL - 1)) && (id >= (1 << (layers*IDR_BITS)))) {
                 layers++;
-                if (!p->count)
+                if (!p->count) {
+                        /* special case: if the tree is currently empty,
+                         * then we grow the tree by moving the top node
+                         * upwards.
+                         */
+                        p->layer++;
                         continue;
+                }
                 if (!(new = get_from_free_list(idp))) {
                         /*
                          * The allocation failed.  If we built part of
@@ -237,6 +245,7 @@ build_up:
                 }
                 new->ary[0] = p;
                 new->count = 1;
+                new->layer = layers-1;
                 if (p->bitmap == IDR_FULL)
                         __set_bit(0, &new->bitmap);
                 p = new;
@@ -493,17 +502,21 @@ void *idr_find(struct idr *idp, int id)
         int n;
         struct idr_layer *p;
 
-        n = idp->layers * IDR_BITS;
         p = rcu_dereference(idp->top);
+        if (!p)
+                return NULL;
+        n = (p->layer+1) * IDR_BITS;
 
         /* Mask off upper bits we don't use for the search. */
         id &= MAX_ID_MASK;
 
         if (id >= (1 << n))
                 return NULL;
+        BUG_ON(n == 0);
 
         while (n > 0 && p) {
                 n -= IDR_BITS;
+                BUG_ON(n != p->layer*IDR_BITS);
                 p = rcu_dereference(p->ary[(id >> n) & IDR_MASK]);
         }
         return((void *)p);
@@ -582,8 +595,11 @@ void *idr_replace(struct idr *idp, void *ptr, int id)
         int n;
         struct idr_layer *p, *old_p;
 
-        n = idp->layers * IDR_BITS;
         p = idp->top;
+        if (!p)
+                return ERR_PTR(-EINVAL);
+
+        n = (p->layer+1) * IDR_BITS;
 
         id &= MAX_ID_MASK;
 
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index a8663890a88c..b255b939bc1b 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -62,10 +62,7 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc)
         for_each_online_cpu(cpu) {
                 s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
                 ret += *pcount;
-                *pcount = 0;
         }
-        fbc->count = ret;
-
         spin_unlock(&fbc->lock);
         return ret;
 }
@@ -104,13 +101,13 @@ void percpu_counter_destroy(struct percpu_counter *fbc)
         if (!fbc->counters)
                 return;
 
-        free_percpu(fbc->counters);
-        fbc->counters = NULL;
 #ifdef CONFIG_HOTPLUG_CPU
         mutex_lock(&percpu_counters_lock);
         list_del(&fbc->list);
         mutex_unlock(&percpu_counters_lock);
 #endif
+        free_percpu(fbc->counters);
+        fbc->counters = NULL;
 }
 EXPORT_SYMBOL(percpu_counter_destroy);
 
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 8d2688ff1352..b7b449dafbe5 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -395,7 +395,7 @@ void sg_miter_stop(struct sg_mapping_iter *miter)
                         WARN_ON(!irqs_disabled());
                         kunmap_atomic(miter->addr, KM_BIO_SRC_IRQ);
                 } else
-                        kunmap(miter->addr);
+                        kunmap(miter->page);
 
                 miter->page = NULL;
                 miter->addr = NULL;
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 78330c37a61b..5f6c629a924d 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -467,9 +467,13 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
         dma_addr_t dev_addr;
         void *ret;
         int order = get_order(size);
+        u64 dma_mask = DMA_32BIT_MASK;
+
+        if (hwdev && hwdev->coherent_dma_mask)
+                dma_mask = hwdev->coherent_dma_mask;
 
         ret = (void *)__get_free_pages(flags, order);
-        if (ret && address_needs_mapping(hwdev, virt_to_bus(ret), size)) {
+        if (ret && !is_buffer_dma_capable(dma_mask, virt_to_bus(ret), size)) {
                 /*
                  * The allocated memory isn't reachable by the device.
                  * Fall back on swiotlb_map_single().
@@ -493,9 +497,9 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
         dev_addr = virt_to_bus(ret);
 
         /* Confirm address can be DMA'd by device */
-        if (address_needs_mapping(hwdev, dev_addr, size)) {
+        if (!is_buffer_dma_capable(dma_mask, dev_addr, size)) {
                 printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
-                       (unsigned long long)*hwdev->dma_mask,
+                       (unsigned long long)dma_mask,
                        (unsigned long long)dev_addr);
 
                 /* DMA_TO_DEVICE to avoid memcpy in unmap_single */