nvme-pci: remove the inline scatterlist optimization

We'll have a better way to optimize for small I/O that doesn't
require it soon, so remove the existing inline_sg case to make that
optimization easier to implement.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>

drivers/nvme/host/pci.c

@@ -223,7 +223,6 @@ struct nvme_iod {
 	dma_addr_t first_dma;
 	dma_addr_t meta_dma;
 	struct scatterlist *sg;
-	struct scatterlist inline_sg[0];
 };
 
 /*
@@ -370,12 +369,6 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db,
 	return true;
 }
 
-/*
- * Max size of iod being embedded in the request payload
- */
-#define NVME_INT_PAGES		2
-#define NVME_INT_BYTES(dev)	(NVME_INT_PAGES * (dev)->ctrl.page_size)
-
 /*
  * Will slightly overestimate the number of pages needed.  This is OK
  * as it only leads to a small amount of wasted memory for the lifetime of
@@ -410,15 +403,6 @@ static unsigned int nvme_pci_iod_alloc_size(struct nvme_dev *dev,
 	return alloc_size + sizeof(struct scatterlist) * nseg;
 }
 
-static unsigned int nvme_pci_cmd_size(struct nvme_dev *dev, bool use_sgl)
-{
-	unsigned int alloc_size = nvme_pci_iod_alloc_size(dev,
-				    NVME_INT_BYTES(dev), NVME_INT_PAGES,
-				    use_sgl);
-
-	return sizeof(struct nvme_iod) + alloc_size;
-}
-
 static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 				unsigned int hctx_idx)
 {
@@ -621,8 +605,7 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
 		dma_addr = next_dma_addr;
 	}
 
-	if (iod->sg != iod->inline_sg)
-		mempool_free(iod->sg, dev->iod_mempool);
+	mempool_free(iod->sg, dev->iod_mempool);
 }
 
 static void nvme_print_sgl(struct scatterlist *sgl, int nents)
@@ -822,14 +805,9 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 	blk_status_t ret = BLK_STS_IOERR;
 	int nr_mapped;
 
-	if (blk_rq_payload_bytes(req) > NVME_INT_BYTES(dev) ||
-	    blk_rq_nr_phys_segments(req) > NVME_INT_PAGES) {
-		iod->sg = mempool_alloc(dev->iod_mempool, GFP_ATOMIC);
-		if (!iod->sg)
-			return BLK_STS_RESOURCE;
-	} else {
-		iod->sg = iod->inline_sg;
-	}
+	iod->sg = mempool_alloc(dev->iod_mempool, GFP_ATOMIC);
+	if (!iod->sg)
+		return BLK_STS_RESOURCE;
 
 	iod->use_sgl = nvme_pci_use_sgls(dev, req);
 
@@ -1612,7 +1590,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
 		dev->admin_tagset.queue_depth = NVME_AQ_MQ_TAG_DEPTH;
 		dev->admin_tagset.timeout = ADMIN_TIMEOUT;
 		dev->admin_tagset.numa_node = dev_to_node(dev->dev);
-		dev->admin_tagset.cmd_size = nvme_pci_cmd_size(dev, false);
+		dev->admin_tagset.cmd_size = sizeof(struct nvme_iod);
 		dev->admin_tagset.flags = BLK_MQ_F_NO_SCHED;
 		dev->admin_tagset.driver_data = dev;
 
@@ -2257,11 +2235,7 @@ static int nvme_dev_add(struct nvme_dev *dev)
 		dev->tagset.numa_node = dev_to_node(dev->dev);
 		dev->tagset.queue_depth =
 				min_t(int, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1;
-		dev->tagset.cmd_size = nvme_pci_cmd_size(dev, false);
-		if ((dev->ctrl.sgls & ((1 << 0) | (1 << 1))) && sgl_threshold) {
-			dev->tagset.cmd_size = max(dev->tagset.cmd_size,
-					nvme_pci_cmd_size(dev, true));
-		}
+		dev->tagset.cmd_size = sizeof(struct nvme_iod);
 		dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE;
 		dev->tagset.driver_data = dev;