net: page_pool: add the possibility to sync DMA memory for device
Introduce the following parameters in order to add the possibility to sync DMA memory for device before putting allocated pages in the page_pool caches: - PP_FLAG_DMA_SYNC_DEV: if set in page_pool_params flags, all pages that the driver gets from page_pool will be DMA-synced-for-device according to the length provided by the device driver. Please note DMA-sync-for-CPU is still device driver responsibility - offset: DMA address offset where the DMA engine starts copying rx data - max_len: maximum DMA memory size page_pool is allowed to flush. This is currently used in __page_pool_alloc_pages_slow routine when pages are allocated from page allocator These parameters are supposed to be set by device drivers. This optimization reduces the length of the DMA-sync-for-device. The optimization is valid because pages are initially DMA-synced-for-device as defined via max_len. At RX time, the driver will perform a DMA-sync-for-CPU on the memory for the packet length. What is important is the memory occupied by packet payload, because this is the area CPU is allowed to read and modify. As we don't track cache-lines written into by the CPU, simply use the packet payload length as dma_sync_size at page_pool recycle time. This also take into account any tail-extend. Tested-by: Matteo Croce <mcroce@redhat.com> Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
This commit is contained in:
parent
0d1a0cfd7f
commit
926f968742
|
@ -34,8 +34,18 @@
|
|||
#include <linux/ptr_ring.h>
|
||||
#include <linux/dma-direction.h>
|
||||
|
||||
#define PP_FLAG_DMA_MAP 1 /* Should page_pool do the DMA map/unmap */
|
||||
#define PP_FLAG_ALL PP_FLAG_DMA_MAP
|
||||
#define PP_FLAG_DMA_MAP BIT(0) /* Should page_pool do the DMA
|
||||
* map/unmap
|
||||
*/
|
||||
#define PP_FLAG_DMA_SYNC_DEV BIT(1) /* If set all pages that the driver gets
|
||||
* from page_pool will be
|
||||
* DMA-synced-for-device according to
|
||||
* the length provided by the device
|
||||
* driver.
|
||||
* Please note DMA-sync-for-CPU is still
|
||||
* device driver responsibility
|
||||
*/
|
||||
#define PP_FLAG_ALL (PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV)
|
||||
|
||||
/*
|
||||
* Fast allocation side cache array/stack
|
||||
|
@ -65,6 +75,8 @@ struct page_pool_params {
|
|||
int nid; /* Numa node id to allocate from pages from */
|
||||
struct device *dev; /* device, for DMA pre-mapping purposes */
|
||||
enum dma_data_direction dma_dir; /* DMA mapping direction */
|
||||
unsigned int max_len; /* max DMA sync memory size */
|
||||
unsigned int offset; /* DMA addr offset */
|
||||
};
|
||||
|
||||
struct page_pool {
|
||||
|
@ -149,8 +161,8 @@ static inline void page_pool_use_xdp_mem(struct page_pool *pool,
|
|||
#endif
|
||||
|
||||
/* Never call this directly, use helpers below */
|
||||
void __page_pool_put_page(struct page_pool *pool,
|
||||
struct page *page, bool allow_direct);
|
||||
void __page_pool_put_page(struct page_pool *pool, struct page *page,
|
||||
unsigned int dma_sync_size, bool allow_direct);
|
||||
|
||||
static inline void page_pool_put_page(struct page_pool *pool,
|
||||
struct page *page, bool allow_direct)
|
||||
|
@ -159,14 +171,14 @@ static inline void page_pool_put_page(struct page_pool *pool,
|
|||
* allow registering MEM_TYPE_PAGE_POOL, but shield linker.
|
||||
*/
|
||||
#ifdef CONFIG_PAGE_POOL
|
||||
__page_pool_put_page(pool, page, allow_direct);
|
||||
__page_pool_put_page(pool, page, -1, allow_direct);
|
||||
#endif
|
||||
}
|
||||
/* Very limited use-cases allow recycle direct */
|
||||
static inline void page_pool_recycle_direct(struct page_pool *pool,
|
||||
struct page *page)
|
||||
{
|
||||
__page_pool_put_page(pool, page, true);
|
||||
__page_pool_put_page(pool, page, -1, true);
|
||||
}
|
||||
|
||||
/* Disconnects a page (from a page_pool). API users can have a need
|
||||
|
|
|
@ -47,6 +47,21 @@ static int page_pool_init(struct page_pool *pool,
|
|||
(pool->p.dma_dir != DMA_BIDIRECTIONAL))
|
||||
return -EINVAL;
|
||||
|
||||
if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) {
|
||||
/* In order to request DMA-sync-for-device the page
|
||||
* needs to be mapped
|
||||
*/
|
||||
if (!(pool->p.flags & PP_FLAG_DMA_MAP))
|
||||
return -EINVAL;
|
||||
|
||||
if (!pool->p.max_len)
|
||||
return -EINVAL;
|
||||
|
||||
/* pool->p.offset has to be set according to the address
|
||||
* offset used by the DMA engine to start copying rx data
|
||||
*/
|
||||
}
|
||||
|
||||
if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0)
|
||||
return -ENOMEM;
|
||||
|
||||
|
@ -115,6 +130,16 @@ static struct page *__page_pool_get_cached(struct page_pool *pool)
|
|||
return page;
|
||||
}
|
||||
|
||||
static void page_pool_dma_sync_for_device(struct page_pool *pool,
|
||||
struct page *page,
|
||||
unsigned int dma_sync_size)
|
||||
{
|
||||
dma_sync_size = min(dma_sync_size, pool->p.max_len);
|
||||
dma_sync_single_range_for_device(pool->p.dev, page->dma_addr,
|
||||
pool->p.offset, dma_sync_size,
|
||||
pool->p.dma_dir);
|
||||
}
|
||||
|
||||
/* slow path */
|
||||
noinline
|
||||
static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
|
||||
|
@ -159,6 +184,9 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
|
|||
}
|
||||
page_pool_set_dma_addr(page, dma);
|
||||
|
||||
if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
|
||||
page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
|
||||
|
||||
skip_dma_map:
|
||||
/* Track how many pages are held 'in-flight' */
|
||||
pool->pages_state_hold_cnt++;
|
||||
|
@ -292,8 +320,8 @@ static bool pool_page_reusable(struct page_pool *pool, struct page *page)
|
|||
return !page_is_pfmemalloc(page) && page_to_nid(page) == pool->p.nid;
|
||||
}
|
||||
|
||||
void __page_pool_put_page(struct page_pool *pool,
|
||||
struct page *page, bool allow_direct)
|
||||
void __page_pool_put_page(struct page_pool *pool, struct page *page,
|
||||
unsigned int dma_sync_size, bool allow_direct)
|
||||
{
|
||||
/* This allocator is optimized for the XDP mode that uses
|
||||
* one-frame-per-page, but have fallbacks that act like the
|
||||
|
@ -305,6 +333,10 @@ void __page_pool_put_page(struct page_pool *pool,
|
|||
pool_page_reusable(pool, page))) {
|
||||
/* Read barrier done in page_ref_count / READ_ONCE */
|
||||
|
||||
if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
|
||||
page_pool_dma_sync_for_device(pool, page,
|
||||
dma_sync_size);
|
||||
|
||||
if (allow_direct && in_serving_softirq())
|
||||
if (__page_pool_recycle_direct(page, pool))
|
||||
return;
|
||||
|
|
Loading…
Reference in New Issue