page_pool: fragment API support for 32-bit arch with 64-bit DMA

Currently page_pool_alloc_frag() is not supported in 32-bit
arch with 64-bit DMA because of the overlap issue between
pp_frag_count and dma_addr_upper in 'struct page' for those
arches, which seems to be quite common, see [1], which means
driver may need to handle it when using fragment API.

It is assumed that the combination of the above arch with an
address space >16TB does not exist, as all those arches have
64b equivalent, it seems logical to use the 64b version for a
system with a large address space. It is also assumed that dma
address is page aligned when we are dma mapping a page aligned
buffer, see [2].

That means we're storing 12 bits of 0 at the lower end for a
dma address, we can reuse those bits for the above arches to
support 32b+12b, which is 16TB of memory.

If we make a wrong assumption, a warning is emitted so that
user can report to us.

1. https://lore.kernel.org/all/20211117075652.58299-1-linyunsheng@huawei.com/
2. https://lore.kernel.org/all/20230818145145.4b357c89@kernel.org/

Tested-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
CC: Lorenzo Bianconi <lorenzo@kernel.org>
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: Liang Chen <liangchen.linux@gmail.com>
CC: Guillaume Tucker <guillaume.tucker@collabora.com>
CC: Matthew Wilcox <willy@infradead.org>
CC: Linux-MM <linux-mm@kvack.org>
Link: https://lore.kernel.org/r/20231013064827.61135-2-linyunsheng@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/linux/mm_types.h

@@ -125,19 +125,8 @@ struct page {
 			struct page_pool *pp;
 			unsigned long _pp_mapping_pad;
 			unsigned long dma_addr;
-			union {
-				/**
-				 * dma_addr_upper: might require a 64-bit
-				 * value on 32-bit architectures.
-				 */
-				unsigned long dma_addr_upper;
-				/**
-				 * For frag page support, not supported in
-				 * 32-bit architectures with 64-bit DMA.
-				 */
 			atomic_long_t pp_frag_count;
 		};
-		};
 		struct {	/* Tail pages of compound page */
 			unsigned long compound_head;	/* Bit zero is set */
 		};

include/net/page_pool/helpers.h

@@ -197,7 +197,7 @@ static inline void page_pool_recycle_direct(struct page_pool *pool,
 	page_pool_put_full_page(pool, page, true);
 }
 
-#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT	\
+#define PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA	\
 		(sizeof(dma_addr_t) > sizeof(unsigned long))
 
 /**
@@ -211,17 +211,25 @@ static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
 {
 	dma_addr_t ret = page->dma_addr;
 
-	if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
+	if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA)
-		ret |= (dma_addr_t)page->dma_addr_upper << 16 << 16;
+		ret <<= PAGE_SHIFT;
 
 	return ret;
 }
 
-static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
+static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
 {
+	if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) {
+		page->dma_addr = addr >> PAGE_SHIFT;
+
+		/* We assume page alignment to shave off bottom bits,
+		 * if this "compression" doesn't work we need to drop.
+		 */
+		return addr != (dma_addr_t)page->dma_addr << PAGE_SHIFT;
+	}
+
 	page->dma_addr = addr;
-	if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
+	return false;
-		page->dma_addr_upper = upper_32_bits(addr);
 }
 
 static inline bool page_pool_put(struct page_pool *pool)

net/core/page_pool.c

@@ -211,10 +211,6 @@ static int page_pool_init(struct page_pool *pool,
 		 */
 	}
 
-	if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT &&
-	    pool->p.flags & PP_FLAG_PAGE_FRAG)
-		return -EINVAL;
-
 #ifdef CONFIG_PAGE_POOL_STATS
 	pool->recycle_stats = alloc_percpu(struct page_pool_recycle_stats);
 	if (!pool->recycle_stats)
@@ -359,12 +355,20 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
 	if (dma_mapping_error(pool->p.dev, dma))
 		return false;
 
-	page_pool_set_dma_addr(page, dma);
+	if (page_pool_set_dma_addr(page, dma))
+		goto unmap_failed;
 
 	if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
 		page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
 
 	return true;
+
+unmap_failed:
+	WARN_ON_ONCE("unexpected DMA address, please report to netdev@");
+	dma_unmap_page_attrs(pool->p.dev, dma,
+			     PAGE_SIZE << pool->p.order, pool->p.dma_dir,
+			     DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
+	return false;
 }
 
 static void page_pool_set_pp_info(struct page_pool *pool,