page_pool: disable sync for cpu for dmabuf memory provider

dmabuf dma-addresses should not be dma_sync'd for CPU/device. Typically
its the driver responsibility to dma_sync for CPU, but the driver should
not dma_sync for CPU if the netmem is actually coming from a dmabuf
memory provider.

The page_pool already exposes a helper for dma_sync_for_cpu:
page_pool_dma_sync_for_cpu. Upgrade this existing helper to handle
netmem, and have it skip dma_sync if the memory is from a dmabuf memory
provider. Drivers should migrate to using this helper when adding
support for netmem.

Also minimize the impact on the dma syncing performance for pages. Special
case the dma-sync path for pages to not go through the overhead checks
for dma-syncing and conversion to netmem.

Cc: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Link: https://patch.msgid.link/20241211212033.1684197-5-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/net/page_pool/helpers.h

@@ -422,7 +422,21 @@ static inline dma_addr_t page_pool_get_dma_addr_netmem(netmem_ref netmem)
  */
 static inline dma_addr_t page_pool_get_dma_addr(const struct page *page)
 {
-	return page_pool_get_dma_addr_netmem(page_to_netmem((struct page *)page));
+	dma_addr_t ret = page->dma_addr;
+
+	if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA)
+		ret <<= PAGE_SHIFT;
+
+	return ret;
+}
+
+static inline void __page_pool_dma_sync_for_cpu(const struct page_pool *pool,
+						const dma_addr_t dma_addr,
+						u32 offset, u32 dma_sync_size)
+{
+	dma_sync_single_range_for_cpu(pool->p.dev, dma_addr,
+				      offset + pool->p.offset, dma_sync_size,
+				      page_pool_get_dma_dir(pool));
 }
 
 /**
@@ -441,10 +455,21 @@ static inline void page_pool_dma_sync_for_cpu(const struct page_pool *pool,
 					      const struct page *page,
 					      u32 offset, u32 dma_sync_size)
 {
-	dma_sync_single_range_for_cpu(pool->p.dev,
-				      page_pool_get_dma_addr(page),
-				      offset + pool->p.offset, dma_sync_size,
-				      page_pool_get_dma_dir(pool));
+	__page_pool_dma_sync_for_cpu(pool, page_pool_get_dma_addr(page), offset,
+				     dma_sync_size);
+}
+
+static inline void
+page_pool_dma_sync_netmem_for_cpu(const struct page_pool *pool,
+				  const netmem_ref netmem, u32 offset,
+				  u32 dma_sync_size)
+{
+	if (!pool->dma_sync_for_cpu)
+		return;
+
+	__page_pool_dma_sync_for_cpu(pool,
+				     page_pool_get_dma_addr_netmem(netmem),
+				     offset, dma_sync_size);
 }
 
 static inline bool page_pool_put(struct page_pool *pool)

include/net/page_pool/types.h

@@ -164,7 +164,8 @@ struct page_pool {
 
 	bool has_init_callback:1;	/* slow::init_callback is set */
 	bool dma_map:1;			/* Perform DMA mapping */
-	bool dma_sync:1;		/* Perform DMA sync */
+	bool dma_sync:1;		/* Perform DMA sync for device */
+	bool dma_sync_for_cpu:1;	/* Perform DMA sync for cpu */
 #ifdef CONFIG_PAGE_POOL_STATS
 	bool system:1;			/* This is a global percpu pool */
 #endif

net/core/devmem.c

@@ -335,6 +335,7 @@ int mp_dmabuf_devmem_init(struct page_pool *pool)
 	 * dma_sync_for_cpu/device. Force disable dma_sync.
 	 */
 	pool->dma_sync = false;
+	pool->dma_sync_for_cpu = false;
 
 	if (pool->p.order != 0)
 		return -E2BIG;

net/core/page_pool.c

@@ -201,6 +201,7 @@ static int page_pool_init(struct page_pool *pool,
 	memcpy(&pool->slow, &params->slow, sizeof(pool->slow));
 
 	pool->cpuid = cpuid;
+	pool->dma_sync_for_cpu = true;
 
 	/* Validate only known flags were used */
 	if (pool->slow.flags & ~PP_FLAG_ALL)