7 files changed, 143 insertions, 142 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 12327b2bb785..7dbd5d9c29a4 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -653,6 +653,21 @@ config DEBUG_NOTIFIERS
           This is a relatively cheap check but if you care about maximum
           performance, say N.
 
+config DEBUG_CREDENTIALS
+        bool "Debug credential management"
+        depends on DEBUG_KERNEL
+        help
+          Enable this to turn on some debug checking for credential
+          management.  The additional code keeps track of the number of
+          pointers from task_structs to any given cred struct, and checks to
+          see that this number never exceeds the usage count of the cred
+          struct.
+
+          Furthermore, if SELinux is enabled, this also checks that the
+          security pointer in the cred struct is never seen to be invalid.
+
+          If unsure, say N.
+
 #
 # Select this config option from the architecture Kconfig, if it
 # it is preferred to always offer frame pointers as a config
@@ -725,7 +740,7 @@ config RCU_TORTURE_TEST_RUNNABLE
 
 config RCU_CPU_STALL_DETECTOR
         bool "Check for stalled CPUs delaying RCU grace periods"
-        depends on CLASSIC_RCU || TREE_RCU
+        depends on TREE_RCU || TREE_PREEMPT_RCU
         default n
         help
           This option causes RCU to printk information on which
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 35a1f7ff4149..702565821c99 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -179,14 +179,16 @@ void __bitmap_shift_left(unsigned long *dst,
 }
 EXPORT_SYMBOL(__bitmap_shift_left);
 
-void __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
+int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
                                 const unsigned long *bitmap2, int bits)
 {
         int k;
         int nr = BITS_TO_LONGS(bits);
+        unsigned long result = 0;
 
         for (k = 0; k < nr; k++)
-                dst[k] = bitmap1[k] & bitmap2[k];
+                result |= (dst[k] = bitmap1[k] & bitmap2[k]);
+        return result != 0;
 }
 EXPORT_SYMBOL(__bitmap_and);
 
@@ -212,14 +214,16 @@ void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
 }
 EXPORT_SYMBOL(__bitmap_xor);
 
-void __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
+int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
                                 const unsigned long *bitmap2, int bits)
 {
         int k;
         int nr = BITS_TO_LONGS(bits);
+        unsigned long result = 0;
 
         for (k = 0; k < nr; k++)
-                dst[k] = bitmap1[k] & ~bitmap2[k];
+                result |= (dst[k] = bitmap1[k] & ~bitmap2[k]);
+        return result != 0;
 }
 EXPORT_SYMBOL(__bitmap_andnot);
 
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 65b0d99b6d0a..58a9f9fc609a 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -156,9 +156,13 @@ static bool driver_filter(struct device *dev)
                 return true;
 
         /* driver filter on and initialized */
-        if (current_driver && dev->driver == current_driver)
+        if (current_driver && dev && dev->driver == current_driver)
                 return true;
 
+        /* driver filter on, but we can't filter on a NULL device... */
+        if (!dev)
+                return false;
+
         if (current_driver || !current_driver_name[0])
                 return false;
 
@@ -183,17 +187,17 @@ static bool driver_filter(struct device *dev)
         return ret;
 }
 
-#define err_printk(dev, entry, format, arg...) do {             \
-                error_count += 1;                               \
-                if (driver_filter(dev) &&                       \
-                    (show_all_errors || show_num_errors > 0)) { \
-                        WARN(1, "%s %s: " format,               \
-                             dev_driver_string(dev),            \
-                             dev_name(dev) , ## arg);           \
-                        dump_entry_trace(entry);                \
-                }                                               \
-                if (!show_all_errors && show_num_errors > 0)    \
-                        show_num_errors -= 1;                   \
+#define err_printk(dev, entry, format, arg...) do {                     \
+                error_count += 1;                                       \
+                if (driver_filter(dev) &&                               \
+                    (show_all_errors || show_num_errors > 0)) {         \
+                        WARN(1, "%s %s: " format,                       \
+                             dev ? dev_driver_string(dev) : "NULL",     \
+                             dev ? dev_name(dev) : "NULL", ## arg);     \
+                        dump_entry_trace(entry);                        \
+                }                                                       \
+                if (!show_all_errors && show_num_errors > 0)            \
+                        show_num_errors -= 1;                           \
         } while (0);
 
 /*
diff --git a/lib/flex_array.c b/lib/flex_array.c
index 08f1636d296a..7baed2fc3bc8 100644
--- a/lib/flex_array.c
+++ b/lib/flex_array.c
@@ -99,7 +99,8 @@ static inline int elements_fit_in_base(struct flex_array *fa)
  * capacity in the base structure.  Also note that no effort is made
  * to efficiently pack objects across page boundaries.
  */
-struct flex_array *flex_array_alloc(int element_size, int total, gfp_t flags)
+struct flex_array *flex_array_alloc(int element_size, unsigned int total,
+                                        gfp_t flags)
 {
         struct flex_array *ret;
         int max_size = nr_base_part_ptrs() * __elements_per_part(element_size);
@@ -115,16 +116,14 @@ struct flex_array *flex_array_alloc(int element_size, int total, gfp_t flags)
         return ret;
 }
 
-static int fa_element_to_part_nr(struct flex_array *fa, int element_nr)
+static int fa_element_to_part_nr(struct flex_array *fa,
+                                        unsigned int element_nr)
 {
         return element_nr / __elements_per_part(fa->element_size);
 }
 
 /**
  * flex_array_free_parts - just free the second-level pages
- * @src:        address of data to copy into the array
- * @element_nr: index of the position in which to insert
- *              the new element.
  *
  * This is to be used in cases where the base 'struct flex_array'
  * has been statically allocated and should not be free.
@@ -146,14 +145,12 @@ void flex_array_free(struct flex_array *fa)
         kfree(fa);
 }
 
-static int fa_index_inside_part(struct flex_array *fa, int element_nr)
+static unsigned int index_inside_part(struct flex_array *fa,
+                                        unsigned int element_nr)
 {
-        return element_nr % __elements_per_part(fa->element_size);
-}
+        unsigned int part_offset;
 
-static int index_inside_part(struct flex_array *fa, int element_nr)
-{
-        int part_offset = fa_index_inside_part(fa, element_nr);
+        part_offset = element_nr % __elements_per_part(fa->element_size);
         return part_offset * fa->element_size;
 }
 
@@ -188,7 +185,8 @@ __fa_get_part(struct flex_array *fa, int part_nr, gfp_t flags)
  *
  * Locking must be provided by the caller.
  */
-int flex_array_put(struct flex_array *fa, int element_nr, void *src, gfp_t flags)
+int flex_array_put(struct flex_array *fa, unsigned int element_nr, void *src,
+                        gfp_t flags)
 {
         int part_nr = fa_element_to_part_nr(fa, element_nr);
         struct flex_array_part *part;
@@ -198,10 +196,11 @@ int flex_array_put(struct flex_array *fa, int element_nr, void *src, gfp_t flags
                 return -ENOSPC;
         if (elements_fit_in_base(fa))
                 part = (struct flex_array_part *)&fa->parts[0];
-        else
+        else {
                 part = __fa_get_part(fa, part_nr, flags);
-        if (!part)
-                return -ENOMEM;
+                if (!part)
+                        return -ENOMEM;
+        }
         dst = &part->elements[index_inside_part(fa, element_nr)];
         memcpy(dst, src, fa->element_size);
         return 0;
@@ -219,7 +218,8 @@ int flex_array_put(struct flex_array *fa, int element_nr, void *src, gfp_t flags
  *
  * Locking must be provided by the caller.
  */
-int flex_array_prealloc(struct flex_array *fa, int start, int end, gfp_t flags)
+int flex_array_prealloc(struct flex_array *fa, unsigned int start,
+                        unsigned int end, gfp_t flags)
 {
         int start_part;
         int end_part;
@@ -250,18 +250,19 @@ int flex_array_prealloc(struct flex_array *fa, int start, int end, gfp_t flags)
  *
  * Locking must be provided by the caller.
  */
-void *flex_array_get(struct flex_array *fa, int element_nr)
+void *flex_array_get(struct flex_array *fa, unsigned int element_nr)
 {
         int part_nr = fa_element_to_part_nr(fa, element_nr);
         struct flex_array_part *part;
 
         if (element_nr >= fa->total_nr_elements)
                 return NULL;
-        if (!fa->parts[part_nr])
-                return NULL;
         if (elements_fit_in_base(fa))
                 part = (struct flex_array_part *)&fa->parts[0];
-        else
+        else {
                 part = fa->parts[part_nr];
+                if (!part)
+                        return NULL;
+        }
         return &part->elements[index_inside_part(fa, element_nr)];
 }
diff --git a/lib/is_single_threaded.c b/lib/is_single_threaded.c
index f1ed2fe76c65..bd2bea963364 100644
--- a/lib/is_single_threaded.c
+++ b/lib/is_single_threaded.c
@@ -12,34 +12,47 @@
 
 #include <linux/sched.h>
 
-/**
- * is_single_threaded - Determine if a thread group is single-threaded or not
- * @p: A task in the thread group in question
- *
- * This returns true if the thread group to which a task belongs is single
- * threaded, false if it is not.
+/*
+ * Returns true if the task does not share ->mm with another thread/process.
  */
-bool is_single_threaded(struct task_struct *p)
+bool current_is_single_threaded(void)
 {
-        struct task_struct *g, *t;
-        struct mm_struct *mm = p->mm;
+        struct task_struct *task = current;
+        struct mm_struct *mm = task->mm;
+        struct task_struct *p, *t;
+        bool ret;
 
-        if (atomic_read(&p->signal->count) != 1)
-                goto no;
+        if (atomic_read(&task->signal->live) != 1)
+                return false;
 
-        if (atomic_read(&p->mm->mm_users) != 1) {
-                read_lock(&tasklist_lock);
-                do_each_thread(g, t) {
-                        if (t->mm == mm && t != p)
-                                goto no_unlock;
-                } while_each_thread(g, t);
-                read_unlock(&tasklist_lock);
-        }
+        if (atomic_read(&mm->mm_users) == 1)
+                return true;
 
-        return true;
+        ret = false;
+        rcu_read_lock();
+        for_each_process(p) {
+                if (unlikely(p->flags & PF_KTHREAD))
+                        continue;
+                if (unlikely(p == task->group_leader))
+                        continue;
+
+                t = p;
+                do {
+                        if (unlikely(t->mm == mm))
+                                goto found;
+                        if (likely(t->mm))
+                                break;
+                        /*
+                         * t->mm == NULL. Make sure next_thread/next_task
+                         * will see other CLONE_VM tasks which might be
+                         * forked before exiting.
+                         */
+                        smp_rmb();
+                } while_each_thread(p, t);
+        }
+        ret = true;
+found:
+        rcu_read_unlock();
 
-no_unlock:
-        read_unlock(&tasklist_lock);
-no:
-        return false;
+        return ret;
 }
diff --git a/lib/lmb.c b/lib/lmb.c
index e4a6482d8b26..0343c05609f0 100644
--- a/lib/lmb.c
+++ b/lib/lmb.c
@@ -429,7 +429,7 @@ u64 __init lmb_phys_mem_size(void)
         return lmb.memory.size;
 }
 
-u64 __init lmb_end_of_DRAM(void)
+u64 lmb_end_of_DRAM(void)
 {
         int idx = lmb.memory.cnt - 1;
 
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index bffe6d7ef9d9..ac25cd28e807 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -114,46 +114,11 @@ setup_io_tlb_npages(char *str)
 __setup("swiotlb=", setup_io_tlb_npages);
 /* make io_tlb_overflow tunable too? */
 
-void * __weak __init swiotlb_alloc_boot(size_t size, unsigned long nslabs)
-{
-        return alloc_bootmem_low_pages(size);
-}
-
-void * __weak swiotlb_alloc(unsigned order, unsigned long nslabs)
-{
-        return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order);
-}
-
-dma_addr_t __weak swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
-{
-        return paddr;
-}
-
-phys_addr_t __weak swiotlb_bus_to_phys(struct device *hwdev, dma_addr_t baddr)
-{
-        return baddr;
-}
-
+/* Note that this doesn't work with highmem page */
 static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
                                       volatile void *address)
 {
-        return swiotlb_phys_to_bus(hwdev, virt_to_phys(address));
-}
-
-void * __weak swiotlb_bus_to_virt(struct device *hwdev, dma_addr_t address)
-{
-        return phys_to_virt(swiotlb_bus_to_phys(hwdev, address));
-}
-
-int __weak swiotlb_arch_address_needs_mapping(struct device *hwdev,
-                                               dma_addr_t addr, size_t size)
-{
-        return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
-}
-
-int __weak swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size)
-{
-        return 0;
+        return phys_to_dma(hwdev, virt_to_phys(address));
 }
 
 static void swiotlb_print_info(unsigned long bytes)
@@ -189,7 +154,7 @@ swiotlb_init_with_default_size(size_t default_size)
         /*
          * Get IO TLB memory from the low pages
          */
-        io_tlb_start = swiotlb_alloc_boot(bytes, io_tlb_nslabs);
+        io_tlb_start = alloc_bootmem_low_pages(bytes);
         if (!io_tlb_start)
                 panic("Cannot allocate SWIOTLB buffer");
         io_tlb_end = io_tlb_start + bytes;
@@ -245,7 +210,8 @@ swiotlb_late_init_with_default_size(size_t default_size)
         bytes = io_tlb_nslabs << IO_TLB_SHIFT;
 
         while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
-                io_tlb_start = swiotlb_alloc(order, io_tlb_nslabs);
+                io_tlb_start = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
+                                                        order);
                 if (io_tlb_start)
                         break;
                 order--;
@@ -315,20 +281,10 @@ cleanup1:
         return -ENOMEM;
 }
 
-static inline int
-address_needs_mapping(struct device *hwdev, dma_addr_t addr, size_t size)
+static int is_swiotlb_buffer(phys_addr_t paddr)
 {
-        return swiotlb_arch_address_needs_mapping(hwdev, addr, size);
-}
-
-static inline int range_needs_mapping(phys_addr_t paddr, size_t size)
-{
-        return swiotlb_force || swiotlb_arch_range_needs_mapping(paddr, size);
-}
-
-static int is_swiotlb_buffer(char *addr)
-{
-        return addr >= io_tlb_start && addr < io_tlb_end;
+        return paddr >= virt_to_phys(io_tlb_start) &&
+                paddr < virt_to_phys(io_tlb_end);
 }
 
 /*
@@ -561,9 +517,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
                 dma_mask = hwdev->coherent_dma_mask;
 
         ret = (void *)__get_free_pages(flags, order);
-        if (ret &&
-            !is_buffer_dma_capable(dma_mask, swiotlb_virt_to_bus(hwdev, ret),
-                                   size)) {
+        if (ret && swiotlb_virt_to_bus(hwdev, ret) + size > dma_mask) {
                 /*
                  * The allocated memory isn't reachable by the device.
                  */
@@ -585,7 +539,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
         dev_addr = swiotlb_virt_to_bus(hwdev, ret);
 
         /* Confirm address can be DMA'd by device */
-        if (!is_buffer_dma_capable(dma_mask, dev_addr, size)) {
+        if (dev_addr + size > dma_mask) {
                 printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
                        (unsigned long long)dma_mask,
                        (unsigned long long)dev_addr);
@@ -601,11 +555,13 @@ EXPORT_SYMBOL(swiotlb_alloc_coherent);
 
 void
 swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
-                      dma_addr_t dma_handle)
+                      dma_addr_t dev_addr)
 {
+        phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
+
         WARN_ON(irqs_disabled());
-        if (!is_swiotlb_buffer(vaddr))
-                free_pages((unsigned long) vaddr, get_order(size));
+        if (!is_swiotlb_buffer(paddr))
+                free_pages((unsigned long)vaddr, get_order(size));
         else
                 /* DMA_TO_DEVICE to avoid memcpy in unmap_single */
                 do_unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
@@ -625,12 +581,15 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
         printk(KERN_ERR "DMA: Out of SW-IOMMU space for %zu bytes at "
                "device %s\n", size, dev ? dev_name(dev) : "?");
 
-        if (size > io_tlb_overflow && do_panic) {
-                if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
-                        panic("DMA: Memory would be corrupted\n");
-                if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
-                        panic("DMA: Random memory would be DMAed\n");
-        }
+        if (size <= io_tlb_overflow || !do_panic)
+                return;
+
+        if (dir == DMA_BIDIRECTIONAL)
+                panic("DMA: Random memory could be DMA accessed\n");
+        if (dir == DMA_FROM_DEVICE)
+                panic("DMA: Random memory could be DMA written\n");
+        if (dir == DMA_TO_DEVICE)
+                panic("DMA: Random memory could be DMA read\n");
 }
 
 /*
@@ -646,7 +605,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
                             struct dma_attrs *attrs)
 {
         phys_addr_t phys = page_to_phys(page) + offset;
-        dma_addr_t dev_addr = swiotlb_phys_to_bus(dev, phys);
+        dma_addr_t dev_addr = phys_to_dma(dev, phys);
         void *map;
 
         BUG_ON(dir == DMA_NONE);
@@ -655,8 +614,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
          * we can safely return the device addr and not worry about bounce
          * buffering it.
          */
-        if (!address_needs_mapping(dev, dev_addr, size) &&
-            !range_needs_mapping(phys, size))
+        if (dma_capable(dev, dev_addr, size) && !swiotlb_force)
                 return dev_addr;
 
         /*
@@ -673,7 +631,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
         /*
          * Ensure that the address returned is DMA'ble
          */
-        if (address_needs_mapping(dev, dev_addr, size))
+        if (!dma_capable(dev, dev_addr, size))
                 panic("map_single: bounce buffer is not DMA'ble");
 
         return dev_addr;
@@ -691,19 +649,25 @@ EXPORT_SYMBOL_GPL(swiotlb_map_page);
 static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
                          size_t size, int dir)
 {
-        char *dma_addr = swiotlb_bus_to_virt(hwdev, dev_addr);
+        phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
 
         BUG_ON(dir == DMA_NONE);
 
-        if (is_swiotlb_buffer(dma_addr)) {
-                do_unmap_single(hwdev, dma_addr, size, dir);
+        if (is_swiotlb_buffer(paddr)) {
+                do_unmap_single(hwdev, phys_to_virt(paddr), size, dir);
                 return;
         }
 
         if (dir != DMA_FROM_DEVICE)
                 return;
 
-        dma_mark_clean(dma_addr, size);
+        /*
+         * phys_to_virt doesn't work with hihgmem page but we could
+         * call dma_mark_clean() with hihgmem page here. However, we
+         * are fine since dma_mark_clean() is null on POWERPC. We can
+         * make dma_mark_clean() take a physical address if necessary.
+         */
+        dma_mark_clean(phys_to_virt(paddr), size);
 }
 
 void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
@@ -728,19 +692,19 @@ static void
 swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
                     size_t size, int dir, int target)
 {
-        char *dma_addr = swiotlb_bus_to_virt(hwdev, dev_addr);
+        phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
 
         BUG_ON(dir == DMA_NONE);
 
-        if (is_swiotlb_buffer(dma_addr)) {
-                sync_single(hwdev, dma_addr, size, dir, target);
+        if (is_swiotlb_buffer(paddr)) {
+                sync_single(hwdev, phys_to_virt(paddr), size, dir, target);
                 return;
         }
 
         if (dir != DMA_FROM_DEVICE)
                 return;
 
-        dma_mark_clean(dma_addr, size);
+        dma_mark_clean(phys_to_virt(paddr), size);
 }
 
 void
@@ -817,10 +781,10 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
 
         for_each_sg(sgl, sg, nelems, i) {
                 phys_addr_t paddr = sg_phys(sg);
-                dma_addr_t dev_addr = swiotlb_phys_to_bus(hwdev, paddr);
+                dma_addr_t dev_addr = phys_to_dma(hwdev, paddr);
 
-                if (range_needs_mapping(paddr, sg->length) ||
-                    address_needs_mapping(hwdev, dev_addr, sg->length)) {
+                if (swiotlb_force ||
+                    !dma_capable(hwdev, dev_addr, sg->length)) {
                         void *map = map_single(hwdev, sg_phys(sg),
                                                sg->length, dir);
                         if (!map) {