6 files changed, 125 insertions, 56 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index a48abeac753f..dd7f8858188a 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -980,6 +980,21 @@ config DEBUG_LOCKING_API_SELFTESTS
           The following locking APIs are covered: spinlocks, rwlocks,
           mutexes and rwsems.
 
+config LOCK_TORTURE_TEST
+        tristate "torture tests for locking"
+        depends on DEBUG_KERNEL
+        select TORTURE_TEST
+        default n
+        help
+          This option provides a kernel module that runs torture tests
+          on kernel locking primitives.  The kernel module may be built
+          after the fact on the running kernel to be tested, if desired.
+
+          Say Y here if you want kernel locking-primitive torture tests
+          to be built into the kernel.
+          Say M if you want these torture tests to build as a module.
+          Say N if you are unsure.
+
 endmenu # lock debugging
 
 config TRACE_IRQFLAGS
@@ -1141,9 +1156,14 @@ config SPARSE_RCU_POINTER
 
          Say N if you are unsure.
 
+config TORTURE_TEST
+        tristate
+        default n
+
 config RCU_TORTURE_TEST
         tristate "torture tests for RCU"
         depends on DEBUG_KERNEL
+        select TORTURE_TEST
         default n
         help
           This option provides a kernel module that runs torture tests
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 2defd1308b04..98f2d7e91a91 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -424,111 +424,134 @@ void debug_dma_dump_mappings(struct device *dev)
 EXPORT_SYMBOL(debug_dma_dump_mappings);
 
 /*
- * For each page mapped (initial page in the case of
- * dma_alloc_coherent/dma_map_{single|page}, or each page in a
- * scatterlist) insert into this tree using the pfn as the key. At
+ * For each mapping (initial cacheline in the case of
+ * dma_alloc_coherent/dma_map_page, initial cacheline in each page of a
+ * scatterlist, or the cacheline specified in dma_map_single) insert
+ * into this tree using the cacheline as the key. At
  * dma_unmap_{single|sg|page} or dma_free_coherent delete the entry.  If
- * the pfn already exists at insertion time add a tag as a reference
+ * the entry already exists at insertion time add a tag as a reference
  * count for the overlapping mappings.  For now, the overlap tracking
- * just ensures that 'unmaps' balance 'maps' before marking the pfn
- * idle, but we should also be flagging overlaps as an API violation.
+ * just ensures that 'unmaps' balance 'maps' before marking the
+ * cacheline idle, but we should also be flagging overlaps as an API
+ * violation.
  *
  * Memory usage is mostly constrained by the maximum number of available
  * dma-debug entries in that we need a free dma_debug_entry before
- * inserting into the tree.  In the case of dma_map_{single|page} and
- * dma_alloc_coherent there is only one dma_debug_entry and one pfn to
- * track per event.  dma_map_sg(), on the other hand,
- * consumes a single dma_debug_entry, but inserts 'nents' entries into
- * the tree.
+ * inserting into the tree.  In the case of dma_map_page and
+ * dma_alloc_coherent there is only one dma_debug_entry and one
+ * dma_active_cacheline entry to track per event.  dma_map_sg(), on the
+ * other hand, consumes a single dma_debug_entry, but inserts 'nents'
+ * entries into the tree.
  *
  * At any time debug_dma_assert_idle() can be called to trigger a
- * warning if the given page is in the active set.
+ * warning if any cachelines in the given page are in the active set.
  */
-static RADIX_TREE(dma_active_pfn, GFP_NOWAIT);
+static RADIX_TREE(dma_active_cacheline, GFP_NOWAIT);
 static DEFINE_SPINLOCK(radix_lock);
-#define ACTIVE_PFN_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1)
+#define ACTIVE_CACHELINE_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1)
+#define CACHELINE_PER_PAGE_SHIFT (PAGE_SHIFT - L1_CACHE_SHIFT)
+#define CACHELINES_PER_PAGE (1 << CACHELINE_PER_PAGE_SHIFT)
 
-static int active_pfn_read_overlap(unsigned long pfn)
+static phys_addr_t to_cacheline_number(struct dma_debug_entry *entry)
+{
+        return (entry->pfn << CACHELINE_PER_PAGE_SHIFT) +
+                (entry->offset >> L1_CACHE_SHIFT);
+}
+
+static int active_cacheline_read_overlap(phys_addr_t cln)
 {
         int overlap = 0, i;
 
         for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--)
-                if (radix_tree_tag_get(&dma_active_pfn, pfn, i))
+                if (radix_tree_tag_get(&dma_active_cacheline, cln, i))
                         overlap |= 1 << i;
         return overlap;
 }
 
-static int active_pfn_set_overlap(unsigned long pfn, int overlap)
+static int active_cacheline_set_overlap(phys_addr_t cln, int overlap)
 {
         int i;
 
-        if (overlap > ACTIVE_PFN_MAX_OVERLAP || overlap < 0)
+        if (overlap > ACTIVE_CACHELINE_MAX_OVERLAP || overlap < 0)
                 return overlap;
 
         for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--)
                 if (overlap & 1 << i)
-                        radix_tree_tag_set(&dma_active_pfn, pfn, i);
+                        radix_tree_tag_set(&dma_active_cacheline, cln, i);
                 else
-                        radix_tree_tag_clear(&dma_active_pfn, pfn, i);
+                        radix_tree_tag_clear(&dma_active_cacheline, cln, i);
 
         return overlap;
 }
 
-static void active_pfn_inc_overlap(unsigned long pfn)
+static void active_cacheline_inc_overlap(phys_addr_t cln)
 {
-        int overlap = active_pfn_read_overlap(pfn);
+        int overlap = active_cacheline_read_overlap(cln);
 
-        overlap = active_pfn_set_overlap(pfn, ++overlap);
+        overlap = active_cacheline_set_overlap(cln, ++overlap);
 
         /* If we overflowed the overlap counter then we're potentially
          * leaking dma-mappings.  Otherwise, if maps and unmaps are
          * balanced then this overflow may cause false negatives in
-         * debug_dma_assert_idle() as the pfn may be marked idle
+         * debug_dma_assert_idle() as the cacheline may be marked idle
          * prematurely.
          */
-        WARN_ONCE(overlap > ACTIVE_PFN_MAX_OVERLAP,
-                  "DMA-API: exceeded %d overlapping mappings of pfn %lx\n",
-                  ACTIVE_PFN_MAX_OVERLAP, pfn);
+        WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP,
+                  "DMA-API: exceeded %d overlapping mappings of cacheline %pa\n",
+                  ACTIVE_CACHELINE_MAX_OVERLAP, &cln);
 }
 
-static int active_pfn_dec_overlap(unsigned long pfn)
+static int active_cacheline_dec_overlap(phys_addr_t cln)
 {
-        int overlap = active_pfn_read_overlap(pfn);
+        int overlap = active_cacheline_read_overlap(cln);
 
-        return active_pfn_set_overlap(pfn, --overlap);
+        return active_cacheline_set_overlap(cln, --overlap);
 }
 
-static int active_pfn_insert(struct dma_debug_entry *entry)
+static int active_cacheline_insert(struct dma_debug_entry *entry)
 {
+        phys_addr_t cln = to_cacheline_number(entry);
         unsigned long flags;
         int rc;
 
+        /* If the device is not writing memory then we don't have any
+         * concerns about the cpu consuming stale data.  This mitigates
+         * legitimate usages of overlapping mappings.
+         */
+        if (entry->direction == DMA_TO_DEVICE)
+                return 0;
+
         spin_lock_irqsave(&radix_lock, flags);
-        rc = radix_tree_insert(&dma_active_pfn, entry->pfn, entry);
+        rc = radix_tree_insert(&dma_active_cacheline, cln, entry);
         if (rc == -EEXIST)
-                active_pfn_inc_overlap(entry->pfn);
+                active_cacheline_inc_overlap(cln);
         spin_unlock_irqrestore(&radix_lock, flags);
 
         return rc;
 }
 
-static void active_pfn_remove(struct dma_debug_entry *entry)
+static void active_cacheline_remove(struct dma_debug_entry *entry)
 {
+        phys_addr_t cln = to_cacheline_number(entry);
         unsigned long flags;
 
+        /* ...mirror the insert case */
+        if (entry->direction == DMA_TO_DEVICE)
+                return;
+
         spin_lock_irqsave(&radix_lock, flags);
         /* since we are counting overlaps the final put of the
-         * entry->pfn will occur when the overlap count is 0.
-         * active_pfn_dec_overlap() returns -1 in that case
+         * cacheline will occur when the overlap count is 0.
+         * active_cacheline_dec_overlap() returns -1 in that case
          */
-        if (active_pfn_dec_overlap(entry->pfn) < 0)
-                radix_tree_delete(&dma_active_pfn, entry->pfn);
+        if (active_cacheline_dec_overlap(cln) < 0)
+                radix_tree_delete(&dma_active_cacheline, cln);
         spin_unlock_irqrestore(&radix_lock, flags);
 }
 
 /**
  * debug_dma_assert_idle() - assert that a page is not undergoing dma
- * @page: page to lookup in the dma_active_pfn tree
+ * @page: page to lookup in the dma_active_cacheline tree
  *
  * Place a call to this routine in cases where the cpu touching the page
  * before the dma completes (page is dma_unmapped) will lead to data
@@ -536,22 +559,38 @@ static void active_pfn_remove(struct dma_debug_entry *entry)
  */
 void debug_dma_assert_idle(struct page *page)
 {
+        static struct dma_debug_entry *ents[CACHELINES_PER_PAGE];
+        struct dma_debug_entry *entry = NULL;
+        void **results = (void **) &ents;
+        unsigned int nents, i;
         unsigned long flags;
-        struct dma_debug_entry *entry;
+        phys_addr_t cln;
 
         if (!page)
                 return;
 
+        cln = (phys_addr_t) page_to_pfn(page) << CACHELINE_PER_PAGE_SHIFT;
         spin_lock_irqsave(&radix_lock, flags);
-        entry = radix_tree_lookup(&dma_active_pfn, page_to_pfn(page));
+        nents = radix_tree_gang_lookup(&dma_active_cacheline, results, cln,
+                                       CACHELINES_PER_PAGE);
+        for (i = 0; i < nents; i++) {
+                phys_addr_t ent_cln = to_cacheline_number(ents[i]);
+
+                if (ent_cln == cln) {
+                        entry = ents[i];
+                        break;
+                } else if (ent_cln >= cln + CACHELINES_PER_PAGE)
+                        break;
+        }
         spin_unlock_irqrestore(&radix_lock, flags);
 
         if (!entry)
                 return;
 
+        cln = to_cacheline_number(entry);
         err_printk(entry->dev, entry,
-                   "DMA-API: cpu touching an active dma mapped page "
-                   "[pfn=0x%lx]\n", entry->pfn);
+                   "DMA-API: cpu touching an active dma mapped cacheline [cln=%pa]\n",
+                   &cln);
 }
 
 /*
@@ -568,9 +607,9 @@ static void add_dma_entry(struct dma_debug_entry *entry)
         hash_bucket_add(bucket, entry);
         put_hash_bucket(bucket, &flags);
 
-        rc = active_pfn_insert(entry);
+        rc = active_cacheline_insert(entry);
         if (rc == -ENOMEM) {
-                pr_err("DMA-API: pfn tracking ENOMEM, dma-debug disabled\n");
+                pr_err("DMA-API: cacheline tracking ENOMEM, dma-debug disabled\n");
                 global_disable = true;
         }
 
@@ -631,7 +670,7 @@ static void dma_entry_free(struct dma_debug_entry *entry)
 {
         unsigned long flags;
 
-        active_pfn_remove(entry);
+        active_cacheline_remove(entry);
 
         /*
          * add to beginning of the list - this way the entries are
diff --git a/lib/fonts/Kconfig b/lib/fonts/Kconfig
index 4dc1b990aa23..34fd931b54b5 100644
--- a/lib/fonts/Kconfig
+++ b/lib/fonts/Kconfig
@@ -9,7 +9,7 @@ if FONT_SUPPORT
 
 config FONTS
         bool "Select compiled-in fonts"
-        depends on FRAMEBUFFER_CONSOLE
+        depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE
         help
           Say Y here if you would like to use fonts other than the default
           your frame buffer console usually use.
@@ -22,7 +22,7 @@ config FONTS
 
 config FONT_8x8
         bool "VGA 8x8 font" if FONTS
-        depends on FRAMEBUFFER_CONSOLE
+        depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE
         default y if !SPARC && !FONTS
         help
           This is the "high resolution" font for the VGA frame buffer (the one
@@ -45,7 +45,7 @@ config FONT_8x16
 
 config FONT_6x11
         bool "Mac console 6x11 font (not supported by all drivers)" if FONTS
-        depends on FRAMEBUFFER_CONSOLE
+        depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE
         default y if !SPARC && !FONTS && MAC
         help
           Small console font with Macintosh-style high-half glyphs.  Some Mac
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
index 7be235f1a70b..93d145e5539c 100644
--- a/lib/percpu_ida.c
+++ b/lib/percpu_ida.c
@@ -54,9 +54,7 @@ static inline void move_tags(unsigned *dst, unsigned *dst_nr,
 /*
  * Try to steal tags from a remote cpu's percpu freelist.
  *
- * We first check how many percpu freelists have tags - we don't steal tags
- * unless enough percpu freelists have tags on them that it's possible more than
- * half the total tags could be stuck on remote percpu freelists.
+ * We first check how many percpu freelists have tags
  *
  * Then we iterate through the cpus until we find some tags - we don't attempt
  * to find the "best" cpu to steal from, to keep cacheline bouncing to a
@@ -69,8 +67,7 @@ static inline void steal_tags(struct percpu_ida *pool,
         struct percpu_ida_cpu *remote;
 
         for (cpus_have_tags = cpumask_weight(&pool->cpus_have_tags);
-             cpus_have_tags * pool->percpu_max_size > pool->nr_tags / 2;
-             cpus_have_tags--) {
+             cpus_have_tags; cpus_have_tags--) {
                 cpu = cpumask_next(cpu, &pool->cpus_have_tags);
 
                 if (cpu >= nr_cpu_ids) {
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 7811ed3b4e70..bd4a8dfdf0b8 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -1253,8 +1253,10 @@ unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item)
 
                 node = indirect_to_ptr(node);
                 max_index = radix_tree_maxindex(node->height);
-                if (cur_index > max_index)
+                if (cur_index > max_index) {
+                        rcu_read_unlock();
                         break;
+                }
 
                 cur_index = __locate(node, item, cur_index, &found_index);
                 rcu_read_unlock();
diff --git a/lib/random32.c b/lib/random32.c
index 1e5b2df44291..614896778700 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -244,8 +244,19 @@ static void __prandom_reseed(bool late)
         static bool latch = false;
         static DEFINE_SPINLOCK(lock);
 
+        /* Asking for random bytes might result in bytes getting
+         * moved into the nonblocking pool and thus marking it
+         * as initialized. In this case we would double back into
+         * this function and attempt to do a late reseed.
+         * Ignore the pointless attempt to reseed again if we're
+         * already waiting for bytes when the nonblocking pool
+         * got initialized.
+         */
+
         /* only allow initial seeding (late == false) once */
-        spin_lock_irqsave(&lock, flags);
+        if (!spin_trylock_irqsave(&lock, flags))
+                return;
+
         if (latch && !late)
                 goto out;
         latch = true;