[RFC] genalloc:add an gen_pool_alloc_align func to genalloc

[Zhao Qiang <B45475@freescale.com>]

Bytes alignment is required to manage some special ram,
so add gen_pool_alloc_align func to genalloc.
rename gen_pool_alloc to gen_pool_alloc_align with a align parameter,
then provide gen_pool_alloc to call gen_pool_alloc_align with
align = 1 Byte.

Signed-off-by: Zhao Qiang <B45475@freescale.com>
---
FSL's IP block QE require this function to manage muram.
QE supported only PowerPC, and its code was put under arch/powerpc directory,
using arch/powerpc/lib/rheap.c to manage muram.
Now it support both arm(ls1021,ls1043,ls2085 and such on) and powerpc,
the code need to move from arch/powerpc to public direcory,
Scott wood hopes to use genalloc to manage the muram, after discussing 
with scott, we decide to add gen_pool_alloc_align to meet the requirement
for bytes-alignment.

 include/linux/genalloc.h | 10 +++++++---
 lib/genalloc.c           | 38 ++++++++++++++++++++++++++++++--------
 2 files changed, 37 insertions(+), 11 deletions(-)

diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h
index 1ccaab4..65fdf14 100644
--- a/include/linux/genalloc.h
+++ b/include/linux/genalloc.h
@@ -96,6 +96,8 @@ static inline int gen_pool_add(struct gen_pool *pool, unsigned long addr,
 }
 extern void gen_pool_destroy(struct gen_pool *);
 extern unsigned long gen_pool_alloc(struct gen_pool *, size_t);
+extern unsigned long gen_pool_alloc_align(struct gen_pool *, size_t,
+		unsigned long align);
 extern void *gen_pool_dma_alloc(struct gen_pool *pool, size_t size,
 		dma_addr_t *dma);
 extern void gen_pool_free(struct gen_pool *, unsigned long, size_t);
@@ -108,14 +110,16 @@ extern void gen_pool_set_algo(struct gen_pool *pool, genpool_algo_t algo,
 		void *data);
 
 extern unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size,
-		unsigned long start, unsigned int nr, void *data);
+		unsigned long start, unsigned int nr, void *data,
+		unsigned long align_mask);
 
 extern unsigned long gen_pool_first_fit_order_align(unsigned long *map,
 		unsigned long size, unsigned long start, unsigned int nr,
-		void *data);
+		void *data, unsigned long align_mask);
 
 extern unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size,
-		unsigned long start, unsigned int nr, void *data);
+		unsigned long start, unsigned int nr, void *data,
+		unsigned long align_mask);
 
 extern struct gen_pool *devm_gen_pool_create(struct device *dev,
 		int min_alloc_order, int nid);
diff --git a/lib/genalloc.c b/lib/genalloc.c
index d214866..dd63448 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -258,19 +258,22 @@ void gen_pool_destroy(struct gen_pool *pool)
 EXPORT_SYMBOL(gen_pool_destroy);
 
 /**
- * gen_pool_alloc - allocate special memory from the pool
+ * gen_pool_alloc_align - allocate special memory from the pool
  * @pool: pool to allocate from
  * @size: number of bytes to allocate from the pool
+ * @align: number of bytes to align
  *
  * Allocate the requested number of bytes from the specified pool.
  * Uses the pool allocation function (with first-fit algorithm by default).
  * Can not be used in NMI handler on architectures without
  * NMI-safe cmpxchg implementation.
  */
-unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
+unsigned long gen_pool_alloc_align(struct gen_pool *pool, size_t size,
+		unsigned long align)
 {
 	struct gen_pool_chunk *chunk;
 	unsigned long addr = 0;
+	unsigned long align_mask;
 	int order = pool->min_alloc_order;
 	int nbits, start_bit = 0, end_bit, remain;
 
@@ -281,6 +284,7 @@ unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
 	if (size == 0)
 		return 0;
 
+	align_mask = ((align + (1UL << order) - 1) >> order) - 1;
 	nbits = (size + (1UL << order) - 1) >> order;
 	rcu_read_lock();
 	list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
@@ -290,7 +294,7 @@ unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
 		end_bit = chunk_size(chunk) >> order;
 retry:
 		start_bit = pool->algo(chunk->bits, end_bit, start_bit, nbits,
-				pool->data);
+				pool->data, align_mask);
 		if (start_bit >= end_bit)
 			continue;
 		remain = bitmap_set_ll(chunk->bits, start_bit, nbits);
@@ -309,6 +313,22 @@ retry:
 	rcu_read_unlock();
 	return addr;
 }
+EXPORT_SYMBOL(gen_pool_alloc_align);
+
+/**
+ * gen_pool_alloc - allocate special memory from the pool
+ * @pool: pool to allocate from
+ * @size: number of bytes to allocate from the pool
+ *
+ * Allocate the requested number of bytes from the specified pool.
+ * Uses the pool allocation function (with first-fit algorithm by default).
+ * Can not be used in NMI handler on architectures without
+ * NMI-safe cmpxchg implementation.
+ */
+unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
+{
+	return gen_pool_alloc_align(pool, size, 1);
+}
 EXPORT_SYMBOL(gen_pool_alloc);
 
 /**
@@ -502,9 +522,10 @@ EXPORT_SYMBOL(gen_pool_set_algo);
  * @data: additional data - unused
  */
 unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size,
-		unsigned long start, unsigned int nr, void *data)
+		unsigned long start, unsigned int nr, void *data,
+		unsigned long align_mask)
 {
-	return bitmap_find_next_zero_area(map, size, start, nr, 0);
+	return bitmap_find_next_zero_area(map, size, start, nr, align_mask);
 }
 EXPORT_SYMBOL(gen_pool_first_fit);
 
@@ -520,7 +541,7 @@ EXPORT_SYMBOL(gen_pool_first_fit);
  */
 unsigned long gen_pool_first_fit_order_align(unsigned long *map,
 		unsigned long size, unsigned long start,
-		unsigned int nr, void *data)
+		unsigned int nr, void *data, unsigned long align_mask)
 {
 	unsigned long align_mask = roundup_pow_of_two(nr) - 1;
 
@@ -541,13 +562,14 @@ EXPORT_SYMBOL(gen_pool_first_fit_order_align);
  * which we can allocate the memory.
  */
 unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size,
-		unsigned long start, unsigned int nr, void *data)
+				unsigned long start, unsigned int nr,
+				void *data, unsigned long align_mask)
 {
 	unsigned long start_bit = size;
 	unsigned long len = size + 1;
 	unsigned long index;
 
-	index = bitmap_find_next_zero_area(map, size, start, nr, 0);
+	index = bitmap_find_next_zero_area(map, size, start, nr, align_mask);
 
 	while (index < size) {
 		int next_bit = find_next_bit(map, size, index + nr);
-- 
2.1.0.27.g96db324