1 files changed, 80 insertions, 28 deletions

diff --git a/mm/cma.c b/mm/cma.c
index 963bc4add9af..a85ae28709a3 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -33,6 +33,7 @@
 #include <linux/log2.h>
 #include <linux/cma.h>
 #include <linux/highmem.h>
+#include <linux/io.h>
 
 struct cma {
 	unsigned long	base_pfn;
@@ -63,6 +64,17 @@ static unsigned long cma_bitmap_aligned_mask(struct cma *cma, int align_order)
 	return (1UL << (align_order - cma->order_per_bit)) - 1;
 }
 
+static unsigned long cma_bitmap_aligned_offset(struct cma *cma, int align_order)
+{
+	unsigned int alignment;
+
+	if (align_order <= cma->order_per_bit)
+		return 0;
+	alignment = 1UL << (align_order - cma->order_per_bit);
+	return ALIGN(cma->base_pfn, alignment) -
+		(cma->base_pfn >> cma->order_per_bit);
+}
+
 static unsigned long cma_bitmap_maxno(struct cma *cma)
 {
 	return cma->count >> cma->order_per_bit;
@@ -124,6 +136,7 @@ static int __init cma_activate_area(struct cma *cma)
 
 err:
 	kfree(cma->bitmap);
+	cma->count = 0;
 	return -EINVAL;
 }
 
@@ -214,12 +227,23 @@ int __init cma_declare_contiguous(phys_addr_t base,
 			bool fixed, struct cma **res_cma)
 {
 	phys_addr_t memblock_end = memblock_end_of_DRAM();
-	phys_addr_t highmem_start = __pa(high_memory);
+	phys_addr_t highmem_start;
 	int ret = 0;
 
-	pr_debug("%s(size %lx, base %08lx, limit %08lx alignment %08lx)\n",
-		__func__, (unsigned long)size, (unsigned long)base,
-		(unsigned long)limit, (unsigned long)alignment);
+#ifdef CONFIG_X86
+	/*
+	 * high_memory isn't direct mapped memory so retrieving its physical
+	 * address isn't appropriate.  But it would be useful to check the
+	 * physical address of the highmem boundary so it's justfiable to get
+	 * the physical address from it.  On x86 there is a validation check for
+	 * this case, so the following workaround is needed to avoid it.
+	 */
+	highmem_start = __pa_nodebug(high_memory);
+#else
+	highmem_start = __pa(high_memory);
+#endif
+	pr_debug("%s(size %pa, base %pa, limit %pa alignment %pa)\n",
+		__func__, &size, &base, &limit, &alignment);
 
 	if (cma_area_count == ARRAY_SIZE(cma_areas)) {
 		pr_err("Not enough slots for CMA reserved regions!\n");
@@ -244,52 +268,78 @@ int __init cma_declare_contiguous(phys_addr_t base,
 	size = ALIGN(size, alignment);
 	limit &= ~(alignment - 1);
 
+	if (!base)
+		fixed = false;
+
 	/* size should be aligned with order_per_bit */
 	if (!IS_ALIGNED(size >> PAGE_SHIFT, 1 << order_per_bit))
 		return -EINVAL;
 
 	/*
-	 * adjust limit to avoid crossing low/high memory boundary for
-	 * automatically allocated regions
+	 * If allocating at a fixed base the request region must not cross the
+	 * low/high memory boundary.
 	 */
-	if (((limit == 0 || limit > memblock_end) &&
-	     (memblock_end - size < highmem_start &&
-	      memblock_end > highmem_start)) ||
-	    (!fixed && limit > highmem_start && limit - size < highmem_start)) {
-		limit = highmem_start;
-	}
-
-	if (fixed && base < highmem_start && base+size > highmem_start) {
+	if (fixed && base < highmem_start && base + size > highmem_start) {
 		ret = -EINVAL;
-		pr_err("Region at %08lx defined on low/high memory boundary (%08lx)\n",
-			(unsigned long)base, (unsigned long)highmem_start);
+		pr_err("Region at %pa defined on low/high memory boundary (%pa)\n",
+			&base, &highmem_start);
 		goto err;
 	}
 
+	/*
+	 * If the limit is unspecified or above the memblock end, its effective
+	 * value will be the memblock end. Set it explicitly to simplify further
+	 * checks.
+	 */
+	if (limit == 0 || limit > memblock_end)
+		limit = memblock_end;
+
 	/* Reserve memory */
-	if (base && fixed) {
+	if (fixed) {
 		if (memblock_is_region_reserved(base, size) ||
 		    memblock_reserve(base, size) < 0) {
 			ret = -EBUSY;
 			goto err;
 		}
 	} else {
-		phys_addr_t addr = memblock_alloc_range(size, alignment, base,
-							limit);
+		phys_addr_t addr = 0;
+
+		/*
+		 * All pages in the reserved area must come from the same zone.
+		 * If the requested region crosses the low/high memory boundary,
+		 * try allocating from high memory first and fall back to low
+		 * memory in case of failure.
+		 */
+		if (base < highmem_start && limit > highmem_start) {
+			addr = memblock_alloc_range(size, alignment,
+						    highmem_start, limit);
+			limit = highmem_start;
+		}
+
 		if (!addr) {
-			ret = -ENOMEM;
-			goto err;
-		} else {
-			base = addr;
+			addr = memblock_alloc_range(size, alignment, base,
+						    limit);
+			if (!addr) {
+				ret = -ENOMEM;
+				goto err;
+			}
 		}
+
+		/*
+		 * kmemleak scans/reads tracked objects for pointers to other
+		 * objects but this address isn't mapped and accessible
+		 */
+		kmemleak_ignore(phys_to_virt(addr));
+		base = addr;
 	}
 
 	ret = cma_init_reserved_mem(base, size, order_per_bit, res_cma);
 	if (ret)
 		goto err;
 
-	pr_info("Reserved %ld MiB at %08lx\n", (unsigned long)size / SZ_1M,
-		(unsigned long)base);
+	totalcma_pages += (size / PAGE_SIZE);
+	pr_info("Reserved %ld MiB at %pa\n", (unsigned long)size / SZ_1M,
+		&base);
 	return 0;
 
 err:
@@ -308,7 +358,7 @@ err:
  */
 struct page *cma_alloc(struct cma *cma, int count, unsigned int align)
 {
-	unsigned long mask, pfn, start = 0;
+	unsigned long mask, offset, pfn, start = 0;
 	unsigned long bitmap_maxno, bitmap_no, bitmap_count;
 	struct page *page = NULL;
 	int ret;
@@ -323,13 +373,15 @@ struct page *cma_alloc(struct cma *cma, int count, unsigned int align)
 		return NULL;
 
 	mask = cma_bitmap_aligned_mask(cma, align);
+	offset = cma_bitmap_aligned_offset(cma, align);
 	bitmap_maxno = cma_bitmap_maxno(cma);
 	bitmap_count = cma_bitmap_pages_to_bits(cma, count);
 
 	for (;;) {
 		mutex_lock(&cma->lock);
-		bitmap_no = bitmap_find_next_zero_area(cma->bitmap,
-				bitmap_maxno, start, bitmap_count, mask);
+		bitmap_no = bitmap_find_next_zero_area_off(cma->bitmap,
+				bitmap_maxno, start, bitmap_count, mask,
+				offset);
 		if (bitmap_no >= bitmap_maxno) {
 			mutex_unlock(&cma->lock);
 			break;