Merge branch 'next' (accumulated 3.16 merge window patches) into master

Now that 3.15 is released, this merges the 'next' branch into 'master',
bringing us to the normal situation where my 'master' branch is the
merge window.

* accumulated work in next: (6809 commits)
  ufs: sb mutex merge + mutex_destroy
  powerpc: update comments for generic idle conversion
  cris: update comments for generic idle conversion
  idle: remove cpu_idle() forward declarations
  nbd: zero from and len fields in NBD_CMD_DISCONNECT.
  mm: convert some level-less printks to pr_*
  MAINTAINERS: adi-buildroot-devel is moderated
  MAINTAINERS: add linux-api for review of API/ABI changes
  mm/kmemleak-test.c: use pr_fmt for logging
  fs/dlm/debug_fs.c: replace seq_printf by seq_puts
  fs/dlm/lockspace.c: convert simple_str to kstr
  fs/dlm/config.c: convert simple_str to kstr
  mm: mark remap_file_pages() syscall as deprecated
  mm: memcontrol: remove unnecessary memcg argument from soft limit functions
  mm: memcontrol: clean up memcg zoneinfo lookup
  mm/memblock.c: call kmemleak directly from memblock_(alloc|free)
  mm/mempool.c: update the kmemleak stack trace for mempool allocations
  lib/radix-tree.c: update the kmemleak stack trace for radix tree allocations
  mm: introduce kmemleak_update_trace()
  mm/kmemleak.c: use %u to print ->checksum
  ...

1 files changed, 58 insertions, 18 deletions

diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c
index 165c2c299e5..83969f8c572 100644
--- a/drivers/base/dma-contiguous.c
+++ b/drivers/base/dma-contiguous.c
@@ -37,6 +37,7 @@ struct cma {
 	unsigned long	base_pfn;
 	unsigned long	count;
 	unsigned long	*bitmap;
+	struct mutex	lock;
 };
 
 struct cma *dma_contiguous_default_area;
@@ -59,11 +60,22 @@ struct cma *dma_contiguous_default_area;
  */
 static const phys_addr_t size_bytes = CMA_SIZE_MBYTES * SZ_1M;
 static phys_addr_t size_cmdline = -1;
+static phys_addr_t base_cmdline;
+static phys_addr_t limit_cmdline;
 
 static int __init early_cma(char *p)
 {
 	pr_debug("%s(%s)\n", __func__, p);
 	size_cmdline = memparse(p, &p);
+	if (*p != '@')
+		return 0;
+	base_cmdline = memparse(p + 1, &p);
+	if (*p != '-') {
+		limit_cmdline = base_cmdline + size_cmdline;
+		return 0;
+	}
+	limit_cmdline = memparse(p + 1, &p);
+
 	return 0;
 }
 early_param("cma", early_cma);
@@ -107,11 +119,18 @@ static inline __maybe_unused phys_addr_t cma_early_percent_memory(void)
 void __init dma_contiguous_reserve(phys_addr_t limit)
 {
 	phys_addr_t selected_size = 0;
+	phys_addr_t selected_base = 0;
+	phys_addr_t selected_limit = limit;
+	bool fixed = false;
 
 	pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit);
 
 	if (size_cmdline != -1) {
 		selected_size = size_cmdline;
+		selected_base = base_cmdline;
+		selected_limit = min_not_zero(limit_cmdline, limit);
+		if (base_cmdline + size_cmdline == limit_cmdline)
+			fixed = true;
 	} else {
 #ifdef CONFIG_CMA_SIZE_SEL_MBYTES
 		selected_size = size_bytes;
@@ -128,10 +147,12 @@ void __init dma_contiguous_reserve(phys_addr_t limit)
 		pr_debug("%s: reserving %ld MiB for global area\n", __func__,
 			 (unsigned long)selected_size / SZ_1M);
 
-		dma_contiguous_reserve_area(selected_size, 0, limit,
-					    &dma_contiguous_default_area);
+		dma_contiguous_reserve_area(selected_size, selected_base,
+					    selected_limit,
+					    &dma_contiguous_default_area,
+					    fixed);
 	}
-};
+}
 
 static DEFINE_MUTEX(cma_mutex);
 
@@ -161,6 +182,7 @@ static int __init cma_activate_area(struct cma *cma)
 		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
 	} while (--i);
 
+	mutex_init(&cma->lock);
 	return 0;
 }
 
@@ -187,15 +209,20 @@ core_initcall(cma_init_reserved_areas);
  * @base: Base address of the reserved area optional, use 0 for any
  * @limit: End address of the reserved memory (optional, 0 for any).
  * @res_cma: Pointer to store the created cma region.
+ * @fixed: hint about where to place the reserved area
  *
  * This function reserves memory from early allocator. It should be
  * called by arch specific code once the early allocator (memblock or bootmem)
  * has been activated and all other subsystems have already allocated/reserved
  * memory. This function allows to create custom reserved areas for specific
  * devices.
+ *
+ * If @fixed is true, reserve contiguous area at exactly @base.  If false,
+ * reserve in range from @base to @limit.
  */
 int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
-				       phys_addr_t limit, struct cma **res_cma)
+				       phys_addr_t limit, struct cma **res_cma,
+				       bool fixed)
 {
 	struct cma *cma = &cma_areas[cma_area_count];
 	phys_addr_t alignment;
@@ -221,18 +248,15 @@ int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
 	limit &= ~(alignment - 1);
 
 	/* Reserve memory */
-	if (base) {
+	if (base && fixed) {
 		if (memblock_is_region_reserved(base, size) ||
 		    memblock_reserve(base, size) < 0) {
 			ret = -EBUSY;
 			goto err;
 		}
 	} else {
-		/*
-		 * Use __memblock_alloc_base() since
-		 * memblock_alloc_base() panic()s.
-		 */
-		phys_addr_t addr = __memblock_alloc_base(size, alignment, limit);
+		phys_addr_t addr = memblock_alloc_range(size, alignment, base,
+							limit);
 		if (!addr) {
 			ret = -ENOMEM;
 			goto err;
@@ -261,6 +285,13 @@ err:
 	return ret;
 }
 
+static void clear_cma_bitmap(struct cma *cma, unsigned long pfn, int count)
+{
+	mutex_lock(&cma->lock);
+	bitmap_clear(cma->bitmap, pfn - cma->base_pfn, count);
+	mutex_unlock(&cma->lock);
+}
+
 /**
  * dma_alloc_from_contiguous() - allocate pages from contiguous area
  * @dev:   Pointer to device for which the allocation is performed.
@@ -269,7 +300,7 @@ err:
  *
  * This function allocates memory buffer for specified device. It uses
  * device specific contiguous memory area if available or the default
- * global one. Requires architecture specific get_dev_cma_area() helper
+ * global one. Requires architecture specific dev_get_cma_area() helper
  * function.
  */
 struct page *dma_alloc_from_contiguous(struct device *dev, int count,
@@ -294,30 +325,41 @@ struct page *dma_alloc_from_contiguous(struct device *dev, int count,
 
 	mask = (1 << align) - 1;
 
-	mutex_lock(&cma_mutex);
 
 	for (;;) {
+		mutex_lock(&cma->lock);
 		pageno = bitmap_find_next_zero_area(cma->bitmap, cma->count,
 						    start, count, mask);
-		if (pageno >= cma->count)
+		if (pageno >= cma->count) {
+			mutex_unlock(&cma->lock);
 			break;
+		}
+		bitmap_set(cma->bitmap, pageno, count);
+		/*
+		 * It's safe to drop the lock here. We've marked this region for
+		 * our exclusive use. If the migration fails we will take the
+		 * lock again and unmark it.
+		 */
+		mutex_unlock(&cma->lock);
 
 		pfn = cma->base_pfn + pageno;
+		mutex_lock(&cma_mutex);
 		ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA);
+		mutex_unlock(&cma_mutex);
 		if (ret == 0) {
-			bitmap_set(cma->bitmap, pageno, count);
 			page = pfn_to_page(pfn);
 			break;
 		} else if (ret != -EBUSY) {
+			clear_cma_bitmap(cma, pfn, count);
 			break;
 		}
+		clear_cma_bitmap(cma, pfn, count);
 		pr_debug("%s(): memory range at %p is busy, retrying\n",
 			 __func__, pfn_to_page(pfn));
 		/* try again with a bit different memory target */
 		start = pageno + mask + 1;
 	}
 
-	mutex_unlock(&cma_mutex);
 	pr_debug("%s(): returned %p\n", __func__, page);
 	return page;
 }
@@ -350,10 +392,8 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 
 	VM_BUG_ON(pfn + count > cma->base_pfn + cma->count);
 
-	mutex_lock(&cma_mutex);
-	bitmap_clear(cma->bitmap, pfn - cma->base_pfn, count);
 	free_contig_range(pfn, count);
-	mutex_unlock(&cma_mutex);
+	clear_cma_bitmap(cma, pfn, count);
 
 	return true;
 }