nvme : Add sysfs entry for NVMe CMBs when appropriate

Add a sysfs attribute that contains salient information about the NVMe
Controller Memory Buffer when one is present. For now, just display the
information about the CMB available from the control registers. We attach
the CMB attribute file to the existing nvme_ctrl sysfs group so it can
handle the sysfs teardown.

Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Jay Freyensee <james_p_freyensee@linux.intel.com>
Signed-off-by: Stephen Bates <sbates@raithlin.com>
Acked-by Jon Derrick: <jonathan.derrick@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

1 files changed, 35 insertions, 9 deletions

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 12357d616eeb..a7c6e9d74943 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -99,6 +99,7 @@ struct nvme_dev {
         dma_addr_t cmb_dma_addr;
         u64 cmb_size;
         u32 cmbsz;
+        u32 cmbloc;
         struct nvme_ctrl ctrl;
         struct completion ioq_wait;
 };
@@ -1330,28 +1331,37 @@ static int nvme_create_io_queues(struct nvme_dev *dev)
         return ret >= 0 ? 0 : ret;
 }
 
+static ssize_t nvme_cmb_show(struct device *dev,
+                             struct device_attribute *attr,
+                             char *buf)
+{
+        struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev));
+
+        return snprintf(buf, PAGE_SIZE, "cmbloc : x%08x\ncmbsz  : x%08x\n",
+                       ndev->cmbloc, ndev->cmbsz);
+}
+static DEVICE_ATTR(cmb, S_IRUGO, nvme_cmb_show, NULL);
+
 static void __iomem *nvme_map_cmb(struct nvme_dev *dev)
 {
         u64 szu, size, offset;
-        u32 cmbloc;
         resource_size_t bar_size;
         struct pci_dev *pdev = to_pci_dev(dev->dev);
         void __iomem *cmb;
         dma_addr_t dma_addr;
 
-        if (!use_cmb_sqes)
-                return NULL;
-
         dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ);
         if (!(NVME_CMB_SZ(dev->cmbsz)))
                 return NULL;
+        dev->cmbloc = readl(dev->bar + NVME_REG_CMBLOC);
 
-        cmbloc = readl(dev->bar + NVME_REG_CMBLOC);
+        if (!use_cmb_sqes)
+                return NULL;
 
         szu = (u64)1 << (12 + 4 * NVME_CMB_SZU(dev->cmbsz));
         size = szu * NVME_CMB_SZ(dev->cmbsz);
-        offset = szu * NVME_CMB_OFST(cmbloc);
-        bar_size = pci_resource_len(pdev, NVME_CMB_BIR(cmbloc));
+        offset = szu * NVME_CMB_OFST(dev->cmbloc);
+        bar_size = pci_resource_len(pdev, NVME_CMB_BIR(dev->cmbloc));
 
         if (offset > bar_size)
                 return NULL;
@@ -1364,7 +1374,7 @@ static void __iomem *nvme_map_cmb(struct nvme_dev *dev)
         if (size > bar_size - offset)
                 size = bar_size - offset;
 
-        dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(cmbloc)) + offset;
+        dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(dev->cmbloc)) + offset;
         cmb = ioremap_wc(dma_addr, size);
         if (!cmb)
                 return NULL;
@@ -1615,9 +1625,25 @@ static int nvme_pci_enable(struct nvme_dev *dev)
                         dev->q_depth);
         }
 
-        if (readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 2))
+        /*
+         * CMBs can currently only exist on >=1.2 PCIe devices. We only
+         * populate sysfs if a CMB is implemented. Note that we add the
+         * CMB attribute to the nvme_ctrl kobj which removes the need to remove
+         * it on exit. Since nvme_dev_attrs_group has no name we can pass
+         * NULL as final argument to sysfs_add_file_to_group.
+         */
+
+        if (readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 2)) {
                 dev->cmb = nvme_map_cmb(dev);
 
+                if (dev->cmbsz) {
+                        if (sysfs_add_file_to_group(&dev->ctrl.device->kobj,
+                                                    &dev_attr_cmb.attr, NULL))
+                                dev_warn(dev->dev,
+                                         "failed to add sysfs attribute for CMB\n");
+                }
+        }
+
         pci_enable_pcie_error_reporting(pdev);
         pci_save_state(pdev);
         return 0;