Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Logan Gunthorpe <logang@deltatee.com>
To:     linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org,
        linux-nvme@lists.infradead.org, linux-rdma@vger.kernel.org,
        linux-nvdimm@lists.01.org, linux-block@vger.kernel.org
Cc:     Stephen Bates <sbates@raithlin.com>,
        Christoph Hellwig <hch@lst.de>, Jens Axboe <axboe@kernel.dk>,
        Keith Busch <keith.busch@intel.com>,
        Sagi Grimberg <sagi@grimberg.me>,
        Bjorn Helgaas <bhelgaas@google.com>,
        Jason Gunthorpe <jgg@mellanox.com>,
        Max Gurtovoy <maxg@mellanox.com>,
        Dan Williams <dan.j.williams@intel.com>,
        =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= <jglisse@redhat.com>,
        Benjamin Herrenschmidt <benh@kernel.crashing.org>,
        Alex Williamson <alex.williamson@redhat.com>,
        =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>,
        Logan Gunthorpe <logang@deltatee.com>
Date:   Mon, 23 Apr 2018 17:30:41 -0600
Message-Id: <20180423233046.21476-10-logang@deltatee.com>
In-Reply-To: <20180423233046.21476-1-logang@deltatee.com>
References: <20180423233046.21476-1-logang@deltatee.com>
Subject: [PATCH v4 09/14] nvme-pci: Use PCI p2pmem subsystem to manage the CMB
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Register the CMB buffer as p2pmem and use the appropriate allocation
functions to create and destroy the IO submission queues.

If the CMB supports WDS and RDS, publish it for use as P2P memory
by other devices.

We can now drop the __iomem safety on the buffer seeing that, by
convention, devm_memremap_pages() allocates regular memory without
side effects that's accessible without the iomem accessors.

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
---
 drivers/nvme/host/pci.c | 75 +++++++++++++++++++++++++++----------------------
 1 file changed, 41 insertions(+), 34 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index fbc71fac6f1e..514da4de3c85 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -29,6 +29,7 @@
 #include <linux/types.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/sed-opal.h>
+#include <linux/pci-p2pdma.h>
 
 #include "nvme.h"
 
@@ -92,9 +93,8 @@ struct nvme_dev {
 	struct work_struct remove_work;
 	struct mutex shutdown_lock;
 	bool subsystem;
-	void __iomem *cmb;
-	pci_bus_addr_t cmb_bus_addr;
 	u64 cmb_size;
+	bool cmb_use_sqes;
 	u32 cmbsz;
 	u32 cmbloc;
 	struct nvme_ctrl ctrl;
@@ -149,7 +149,7 @@ struct nvme_queue {
 	struct nvme_dev *dev;
 	spinlock_t q_lock;
 	struct nvme_command *sq_cmds;
-	struct nvme_command __iomem *sq_cmds_io;
+	bool sq_cmds_is_io;
 	volatile struct nvme_completion *cqes;
 	struct blk_mq_tags **tags;
 	dma_addr_t sq_dma_addr;
@@ -431,10 +431,7 @@ static void __nvme_submit_cmd(struct nvme_queue *nvmeq,
 {
 	u16 tail = nvmeq->sq_tail;
 
-	if (nvmeq->sq_cmds_io)
-		memcpy_toio(&nvmeq->sq_cmds_io[tail], cmd, sizeof(*cmd));
-	else
-		memcpy(&nvmeq->sq_cmds[tail], cmd, sizeof(*cmd));
+	memcpy(&nvmeq->sq_cmds[tail], cmd, sizeof(*cmd));
 
 	if (++tail == nvmeq->q_depth)
 		tail = 0;
@@ -1289,9 +1286,18 @@ static void nvme_free_queue(struct nvme_queue *nvmeq)
 {
 	dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
 				(void *)nvmeq->cqes, nvmeq->cq_dma_addr);
-	if (nvmeq->sq_cmds)
-		dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
-					nvmeq->sq_cmds, nvmeq->sq_dma_addr);
+
+	if (nvmeq->sq_cmds) {
+		if (nvmeq->sq_cmds_is_io)
+			pci_free_p2pmem(to_pci_dev(nvmeq->q_dmadev),
+					nvmeq->sq_cmds,
+					SQ_SIZE(nvmeq->q_depth));
+		else
+			dma_free_coherent(nvmeq->q_dmadev,
+					  SQ_SIZE(nvmeq->q_depth),
+					  nvmeq->sq_cmds,
+					  nvmeq->sq_dma_addr);
+	}
 }
 
 static void nvme_free_queues(struct nvme_dev *dev, int lowest)
@@ -1371,12 +1377,21 @@ static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
 static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq,
 				int qid, int depth)
 {
-	/* CMB SQEs will be mapped before creation */
-	if (qid && dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS))
-		return 0;
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
+
+	if (qid && dev->cmb_use_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) {
+		nvmeq->sq_cmds = pci_alloc_p2pmem(pdev, SQ_SIZE(depth));
+		nvmeq->sq_dma_addr = pci_p2pmem_virt_to_bus(pdev,
+						nvmeq->sq_cmds);
+		nvmeq->sq_cmds_is_io = true;
+	}
+
+	if (!nvmeq->sq_cmds) {
+		nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
+					&nvmeq->sq_dma_addr, GFP_KERNEL);
+		nvmeq->sq_cmds_is_io = false;
+	}
 
-	nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
-					    &nvmeq->sq_dma_addr, GFP_KERNEL);
 	if (!nvmeq->sq_cmds)
 		return -ENOMEM;
 	return 0;
@@ -1451,13 +1466,6 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 	struct nvme_dev *dev = nvmeq->dev;
 	int result;
 
-	if (dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) {
-		unsigned offset = (qid - 1) * roundup(SQ_SIZE(nvmeq->q_depth),
-						      dev->ctrl.page_size);
-		nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset;
-		nvmeq->sq_cmds_io = dev->cmb + offset;
-	}
-
 	/*
 	 * A queue's vector matches the queue identifier unless the controller
 	 * has only one vector available.
@@ -1691,9 +1699,6 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 		return;
 	dev->cmbloc = readl(dev->bar + NVME_REG_CMBLOC);
 
-	if (!use_cmb_sqes)
-		return;
-
 	size = nvme_cmb_size_unit(dev) * nvme_cmb_size(dev);
 	offset = nvme_cmb_size_unit(dev) * NVME_CMB_OFST(dev->cmbloc);
 	bar = NVME_CMB_BIR(dev->cmbloc);
@@ -1710,11 +1715,15 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 	if (size > bar_size - offset)
 		size = bar_size - offset;
 
-	dev->cmb = ioremap_wc(pci_resource_start(pdev, bar) + offset, size);
-	if (!dev->cmb)
+	if (pci_p2pdma_add_resource(pdev, bar, size, offset))
 		return;
-	dev->cmb_bus_addr = pci_bus_address(pdev, bar) + offset;
+
 	dev->cmb_size = size;
+	dev->cmb_use_sqes = use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS);
+
+	if ((dev->cmbsz & (NVME_CMBSZ_WDS | NVME_CMBSZ_RDS)) ==
+			(NVME_CMBSZ_WDS | NVME_CMBSZ_RDS))
+		pci_p2pmem_publish(pdev, true);
 
 	if (sysfs_add_file_to_group(&dev->ctrl.device->kobj,
 				    &dev_attr_cmb.attr, NULL))
@@ -1724,12 +1733,10 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 
 static inline void nvme_release_cmb(struct nvme_dev *dev)
 {
-	if (dev->cmb) {
-		iounmap(dev->cmb);
-		dev->cmb = NULL;
+	if (dev->cmb_size) {
 		sysfs_remove_file_from_group(&dev->ctrl.device->kobj,
 					     &dev_attr_cmb.attr, NULL);
-		dev->cmbsz = 0;
+		dev->cmb_size = 0;
 	}
 }
 
@@ -1928,13 +1935,13 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	if (nr_io_queues == 0)
 		return 0;
 
-	if (dev->cmb && (dev->cmbsz & NVME_CMBSZ_SQS)) {
+	if (dev->cmb_use_sqes) {
 		result = nvme_cmb_qdepth(dev, nr_io_queues,
 				sizeof(struct nvme_command));
 		if (result > 0)
 			dev->q_depth = result;
 		else
-			nvme_release_cmb(dev);
+			dev->cmb_use_sqes = false;
 	}
 
 	do {
-- 
2.11.0