Merge tag 'dma-mapping-5.4' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - add dma-mapping and block layer helpers to take care of IOMMU merging
   for mmc plus subsequent fixups (Yoshihiro Shimoda)

 - rework handling of the pgprot bits for remapping (me)

 - take care of the dma direct infrastructure for swiotlb-xen (me)

 - improve the dma noncoherent remapping infrastructure (me)

 - better defaults for ->mmap, ->get_sgtable and ->get_required_mask
   (me)

 - cleanup mmaping of coherent DMA allocations (me)

 - various misc cleanups (Andy Shevchenko, me)

* tag 'dma-mapping-5.4' of git://git.infradead.org/users/hch/dma-mapping: (41 commits)
  mmc: renesas_sdhi_internal_dmac: Add MMC_CAP2_MERGE_CAPABLE
  mmc: queue: Fix bigger segments usage
  arm64: use asm-generic/dma-mapping.h
  swiotlb-xen: merge xen_unmap_single into xen_swiotlb_unmap_page
  swiotlb-xen: simplify cache maintainance
  swiotlb-xen: use the same foreign page check everywhere
  swiotlb-xen: remove xen_swiotlb_dma_mmap and xen_swiotlb_dma_get_sgtable
  xen: remove the exports for xen_{create,destroy}_contiguous_region
  xen/arm: remove xen_dma_ops
  xen/arm: simplify dma_cache_maint
  xen/arm: use dev_is_dma_coherent
  xen/arm: consolidate page-coherent.h
  xen/arm: use dma-noncoherent.h calls for xen-swiotlb cache maintainance
  arm: remove wrappers for the generic dma remap helpers
  dma-mapping: introduce a dma_common_find_pages helper
  dma-mapping: always use VM_DMA_COHERENT for generic DMA remap
  vmalloc: lift the arm flag for coherent mappings to common code
  dma-mapping: provide a better default ->get_required_mask
  dma-mapping: remove the dma_declare_coherent_memory export
  remoteproc: don't allow modular build
  ...

2 files changed, 39 insertions, 4 deletions

diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index 7102e2ebc614..9edc08685e86 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -21,6 +21,8 @@
 #include "card.h"
 #include "host.h"
 
+#define MMC_DMA_MAP_MERGE_SEGMENTS	512
+
 static inline bool mmc_cqe_dcmd_busy(struct mmc_queue *mq)
 {
 	/* Allow only 1 DCMD at a time */
@@ -193,6 +195,12 @@ static void mmc_queue_setup_discard(struct request_queue *q,
 		blk_queue_flag_set(QUEUE_FLAG_SECERASE, q);
 }
 
+static unsigned int mmc_get_max_segments(struct mmc_host *host)
+{
+	return host->can_dma_map_merge ? MMC_DMA_MAP_MERGE_SEGMENTS :
+					 host->max_segs;
+}
+
 /**
  * mmc_init_request() - initialize the MMC-specific per-request data
  * @q: the request queue
@@ -206,7 +214,7 @@ static int __mmc_init_request(struct mmc_queue *mq, struct request *req,
 	struct mmc_card *card = mq->card;
 	struct mmc_host *host = card->host;
 
-	mq_rq->sg = mmc_alloc_sg(host->max_segs, gfp);
+	mq_rq->sg = mmc_alloc_sg(mmc_get_max_segments(host), gfp);
 	if (!mq_rq->sg)
 		return -ENOMEM;
 
@@ -362,13 +370,23 @@ static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card)
 		blk_queue_bounce_limit(mq->queue, BLK_BOUNCE_HIGH);
 	blk_queue_max_hw_sectors(mq->queue,
 		min(host->max_blk_count, host->max_req_size / 512));
-	blk_queue_max_segments(mq->queue, host->max_segs);
+	if (host->can_dma_map_merge)
+		WARN(!blk_queue_can_use_dma_map_merging(mq->queue,
+							mmc_dev(host)),
+		     "merging was advertised but not possible");
+	blk_queue_max_segments(mq->queue, mmc_get_max_segments(host));
 
 	if (mmc_card_mmc(card))
 		block_size = card->ext_csd.data_sector_size;
 
 	blk_queue_logical_block_size(mq->queue, block_size);
-	blk_queue_max_segment_size(mq->queue,
+	/*
+	 * After blk_queue_can_use_dma_map_merging() was called with succeed,
+	 * since it calls blk_queue_virt_boundary(), the mmc should not call
+	 * both blk_queue_max_segment_size().
+	 */
+	if (!host->can_dma_map_merge)
+		blk_queue_max_segment_size(mq->queue,
 			round_down(host->max_seg_size, block_size));
 
 	dma_set_max_seg_size(mmc_dev(host), queue_max_segment_size(mq->queue));
@@ -381,6 +399,11 @@ static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card)
 	init_waitqueue_head(&mq->wait);
 }
 
+static inline bool mmc_merge_capable(struct mmc_host *host)
+{
+	return host->caps2 & MMC_CAP2_MERGE_CAPABLE;
+}
+
 /* Set queue depth to get a reasonable value for q->nr_requests */
 #define MMC_QUEUE_DEPTH 64
 
@@ -418,6 +441,18 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card)
 	mq->tag_set.cmd_size = sizeof(struct mmc_queue_req);
 	mq->tag_set.driver_data = mq;
 
+	/*
+	 * Since blk_mq_alloc_tag_set() calls .init_request() of mmc_mq_ops,
+	 * the host->can_dma_map_merge should be set before to get max_segs
+	 * from mmc_get_max_segments().
+	 */
+	if (mmc_merge_capable(host) &&
+	    host->max_segs < MMC_DMA_MAP_MERGE_SEGMENTS &&
+	    dma_get_merge_boundary(mmc_dev(host)))
+		host->can_dma_map_merge = 1;
+	else
+		host->can_dma_map_merge = 0;
+
 	ret = blk_mq_alloc_tag_set(&mq->tag_set);
 	if (ret)
 		return ret;
diff --git a/drivers/mmc/host/renesas_sdhi_internal_dmac.c b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
index 751fe91c7571..a66f8d6d61d1 100644
--- a/drivers/mmc/host/renesas_sdhi_internal_dmac.c
+++ b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
@@ -106,7 +106,7 @@ static const struct renesas_sdhi_of_data of_rcar_gen3_compatible = {
 			  TMIO_MMC_HAVE_CBSY | TMIO_MMC_MIN_RCAR2,
 	.capabilities	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ |
 			  MMC_CAP_CMD23,
-	.capabilities2	= MMC_CAP2_NO_WRITE_PROTECT,
+	.capabilities2	= MMC_CAP2_NO_WRITE_PROTECT | MMC_CAP2_MERGE_CAPABLE,
 	.bus_shift	= 2,
 	.scc_offset	= 0x1000,
 	.taps		= rcar_gen3_scc_taps,