Merge tag 'dma-mapping-6.10-2024-05-20' of git://git.infradead.org/users/hch/dma...

Pull dma-mapping updates from Christoph Hellwig:

 - optimize DMA sync calls when they are no-ops (Alexander Lobakin)

 - fix swiotlb padding for untrusted devices (Michael Kelley)

 - add documentation for swiotb (Michael Kelley)

* tag 'dma-mapping-6.10-2024-05-20' of git://git.infradead.org/users/hch/dma-mapping:
  dma: fix DMA sync for drivers not calling dma_set_mask*()
  xsk: use generic DMA sync shortcut instead of a custom one
  page_pool: check for DMA sync shortcut earlier
  page_pool: don't use driver-set flags field directly
  page_pool: make sure frag API fields don't span between cachelines
  iommu/dma: avoid expensive indirect calls for sync operations
  dma: avoid redundant calls for sync operations
  dma: compile-out DMA sync op calls when not used
  iommu/dma: fix zeroing of bounce buffer padding used by untrusted devices
  swiotlb: remove alloc_size argument to swiotlb_tbl_map_single()
  Documentation/core-api: add swiotlb documentation

diff --cc drivers/iommu/dma-iommu.c
index eca1afa365085b78efffa7d86c224fb193cfaaee,2a1dbe5867c454b4c3987a2ac1718c5b996993c8..f731e4b2a41724e76459c767efe78ab7d1a41e7f
--- 1/drivers/iommu/dma-iommu.c
--- 2/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@@ -1718,10 -1723,11 +1721,11 @@@ static size_t iommu_dma_max_mapping_siz
  }
  
  static const struct dma_map_ops iommu_dma_ops = {
-       .flags                  = DMA_F_PCI_P2PDMA_SUPPORTED,
+       .flags                  = DMA_F_PCI_P2PDMA_SUPPORTED |
+                                 DMA_F_CAN_SKIP_SYNC,
        .alloc                  = iommu_dma_alloc,
        .free                   = iommu_dma_free,
 -      .alloc_pages            = dma_common_alloc_pages,
 +      .alloc_pages_op         = dma_common_alloc_pages,
        .free_pages             = dma_common_free_pages,
        .alloc_noncontiguous    = iommu_dma_alloc_noncontiguous,
        .free_noncontiguous     = iommu_dma_free_noncontiguous,

diff --cc drivers/net/ethernet/intel/i40e/i40e_xsk.c
Simple merge

diff --cc drivers/net/ethernet/intel/ice/ice_xsk.c
Simple merge

diff --cc drivers/net/ethernet/intel/igc/igc_main.c
Simple merge

diff --cc drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
Simple merge

diff --cc drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
Simple merge

diff --cc drivers/xen/swiotlb-xen.c
Simple merge

diff --cc include/linux/dma-map-ops.h
Simple merge

diff --cc include/net/page_pool/types.h
Simple merge

diff --cc kernel/dma/mapping.c
Simple merge

diff --cc kernel/dma/swiotlb.c
Simple merge

diff --cc net/core/page_pool.c
index 8bcc7014a61a006d1cdaffed352c38cca8689334,4f9d1bd7f4d187778480fa1f388fbbf428584473..f4444b4e39e63a4fa0ad24f36db24123068a0152
--- 1/net/core/page_pool.c
--- 2/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@@ -384,16 -398,26 +399,26 @@@ static struct page *__page_pool_get_cac
        return page;
  }
  
- static void page_pool_dma_sync_for_device(const struct page_pool *pool,
-                                         const struct page *page,
-                                         unsigned int dma_sync_size)
+ static void __page_pool_dma_sync_for_device(const struct page_pool *pool,
 -                                          struct page *page,
++                                          const struct page *page,
+                                           u32 dma_sync_size)
  {
+ #if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC)
        dma_addr_t dma_addr = page_pool_get_dma_addr(page);
  
        dma_sync_size = min(dma_sync_size, pool->p.max_len);
-       dma_sync_single_range_for_device(pool->p.dev, dma_addr,
-                                        pool->p.offset, dma_sync_size,
-                                        pool->p.dma_dir);
+       __dma_sync_single_for_device(pool->p.dev, dma_addr + pool->p.offset,
+                                    dma_sync_size, pool->p.dma_dir);
+ #endif
+ }
+ 
+ static __always_inline void
+ page_pool_dma_sync_for_device(const struct page_pool *pool,
 -                            struct page *page,
++                            const struct page *page,
+                             u32 dma_sync_size)
+ {
+       if (pool->dma_sync && dma_dev_need_sync(pool->p.dev))
+               __page_pool_dma_sync_for_device(pool, page, dma_sync_size);
  }
  
  static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
@@@ -688,11 -708,10 +710,9 @@@ __page_pool_put_page(struct page_pool *
        if (likely(__page_pool_page_can_be_recycled(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);
+               page_pool_dma_sync_for_device(pool, page, dma_sync_size);
  
 -              if (allow_direct && in_softirq() &&
 -                  page_pool_recycle_in_cache(page, pool))
 +              if (allow_direct && page_pool_recycle_in_cache(page, pool))
                        return NULL;
  
                /* Page found as candidate for recycling */