lib/genalloc.c: fix allocation of aligned buffer from non-aligned chunk

[ Upstream commit 52fbf1134d479234d7e64ba9dcbaea23405f229e ]

gen_pool_alloc_algo() uses different allocation functions implementing
different allocation algorithms.  With gen_pool_first_fit_align()
allocation function, the returned address should be aligned on the
requested boundary.

If chunk start address isn't aligned on the requested boundary, the
returned address isn't aligned too.  The only way to get properly
aligned address is to initialize the pool with chunks aligned on the
requested boundary.  If want to have an ability to allocate buffers
aligned on different boundaries (for example, 4K, 1MB, ...), the chunk
start address should be aligned on the max possible alignment.

This happens because gen_pool_first_fit_align() looks for properly
aligned memory block without taking into account the chunk start address
alignment.

To fix this, we provide chunk start address to
gen_pool_first_fit_align() and change its implementation such that it
starts looking for properly aligned block with appropriate offset
(exactly as is done in CMA).

Link: https://lkml.kernel.org/lkml/a170cf65-6884-3592-1de9-4c235888cc8a@intel.com
Link: http://lkml.kernel.org/r/1541690953-4623-1-git-send-email-alexey.skidanov@intel.com
Signed-off-by: Alexey Skidanov <alexey.skidanov@intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Daniel Mentz <danielmentz@google.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Laura Abbott <labbott@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h
index 872f930..dd0a452 100644
--- a/include/linux/genalloc.h
+++ b/include/linux/genalloc.h
@@ -51,7 +51,8 @@
 			unsigned long size,
 			unsigned long start,
 			unsigned int nr,
-			void *data, struct gen_pool *pool);
+			void *data, struct gen_pool *pool,
+			unsigned long start_addr);
 
 /*
  *  General purpose special memory pool descriptor.
@@ -131,24 +132,24 @@
 
 extern unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size,
 		unsigned long start, unsigned int nr, void *data,
-		struct gen_pool *pool);
+		struct gen_pool *pool, unsigned long start_addr);
 
 extern unsigned long gen_pool_fixed_alloc(unsigned long *map,
 		unsigned long size, unsigned long start, unsigned int nr,
-		void *data, struct gen_pool *pool);
+		void *data, struct gen_pool *pool, unsigned long start_addr);
 
 extern unsigned long gen_pool_first_fit_align(unsigned long *map,
 		unsigned long size, unsigned long start, unsigned int nr,
-		void *data, struct gen_pool *pool);
+		void *data, struct gen_pool *pool, unsigned long start_addr);
 
 
 extern unsigned long gen_pool_first_fit_order_align(unsigned long *map,
 		unsigned long size, unsigned long start, unsigned int nr,
-		void *data, struct gen_pool *pool);
+		void *data, struct gen_pool *pool, unsigned long start_addr);
 
 extern unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size,
 		unsigned long start, unsigned int nr, void *data,
-		struct gen_pool *pool);
+		struct gen_pool *pool, unsigned long start_addr);
 
 
 extern struct gen_pool *devm_gen_pool_create(struct device *dev,
diff --git a/lib/genalloc.c b/lib/genalloc.c
index ca06adc..5deb25c 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -311,7 +311,7 @@
 		end_bit = chunk_size(chunk) >> order;
 retry:
 		start_bit = algo(chunk->bits, end_bit, start_bit,
-				 nbits, data, pool);
+				 nbits, data, pool, chunk->start_addr);
 		if (start_bit >= end_bit)
 			continue;
 		remain = bitmap_set_ll(chunk->bits, start_bit, nbits);
@@ -525,7 +525,7 @@
  */
 unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size,
 		unsigned long start, unsigned int nr, void *data,
-		struct gen_pool *pool)
+		struct gen_pool *pool, unsigned long start_addr)
 {
 	return bitmap_find_next_zero_area(map, size, start, nr, 0);
 }
@@ -543,16 +543,19 @@
  */
 unsigned long gen_pool_first_fit_align(unsigned long *map, unsigned long size,
 		unsigned long start, unsigned int nr, void *data,
-		struct gen_pool *pool)
+		struct gen_pool *pool, unsigned long start_addr)
 {
 	struct genpool_data_align *alignment;
-	unsigned long align_mask;
+	unsigned long align_mask, align_off;
 	int order;
 
 	alignment = data;
 	order = pool->min_alloc_order;
 	align_mask = ((alignment->align + (1UL << order) - 1) >> order) - 1;
-	return bitmap_find_next_zero_area(map, size, start, nr, align_mask);
+	align_off = (start_addr & (alignment->align - 1)) >> order;
+
+	return bitmap_find_next_zero_area_off(map, size, start, nr,
+					      align_mask, align_off);
 }
 EXPORT_SYMBOL(gen_pool_first_fit_align);
 
@@ -567,7 +570,7 @@
  */
 unsigned long gen_pool_fixed_alloc(unsigned long *map, unsigned long size,
 		unsigned long start, unsigned int nr, void *data,
-		struct gen_pool *pool)
+		struct gen_pool *pool, unsigned long start_addr)
 {
 	struct genpool_data_fixed *fixed_data;
 	int order;
@@ -601,7 +604,8 @@
  */
 unsigned long gen_pool_first_fit_order_align(unsigned long *map,
 		unsigned long size, unsigned long start,
-		unsigned int nr, void *data, struct gen_pool *pool)
+		unsigned int nr, void *data, struct gen_pool *pool,
+		unsigned long start_addr)
 {
 	unsigned long align_mask = roundup_pow_of_two(nr) - 1;
 
@@ -624,7 +628,7 @@
  */
 unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size,
 		unsigned long start, unsigned int nr, void *data,
-		struct gen_pool *pool)
+		struct gen_pool *pool, unsigned long start_addr)
 {
 	unsigned long start_bit = size;
 	unsigned long len = size + 1;