nvmet: Optionally use PCI P2P memory

Create a configfs attribute in each nvme-fabrics namespace to enable P2P
memory use.  The attribute may be enabled (with a boolean) or a specific
P2P device may be given (with the device's PCI name).

When enabled, the namespace will ensure the underlying block device
supports P2P and is compatible with any specified P2P device.  If no device
was specified it will ensure there is compatible P2P memory somewhere in
the system.  Enabling a namespace with P2P memory will fail with EINVAL
(and an appropriate dmesg error) if any of these conditions are not met.

Once a controller is set up on a specific port, the P2P device to use for
each namespace will be found and stored in a radix tree by namespace ID.
When memory is allocated for a request, the tree is used to look up the P2P
device to allocate memory against.  If no device is in the tree (because no
appropriate device was found), or if allocation of P2P memory fails, fall
back to using regular memory.

Signed-off-by: Stephen Bates <sbates@raithlin.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
[hch: partial rewrite of the initial code]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>

1 files changed, 47 insertions, 0 deletions

diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index b37a8e3e3f80..d895579b6c5d 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -17,6 +17,8 @@
 #include <linux/slab.h>
 #include <linux/stat.h>
 #include <linux/ctype.h>
+#include <linux/pci.h>
+#include <linux/pci-p2pdma.h>
 
 #include "nvmet.h"
 
@@ -340,6 +342,48 @@ out_unlock:
 
 CONFIGFS_ATTR(nvmet_ns_, device_path);
 
+#ifdef CONFIG_PCI_P2PDMA
+static ssize_t nvmet_ns_p2pmem_show(struct config_item *item, char *page)
+{
+	struct nvmet_ns *ns = to_nvmet_ns(item);
+
+	return pci_p2pdma_enable_show(page, ns->p2p_dev, ns->use_p2pmem);
+}
+
+static ssize_t nvmet_ns_p2pmem_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_ns *ns = to_nvmet_ns(item);
+	struct pci_dev *p2p_dev = NULL;
+	bool use_p2pmem;
+	int ret = count;
+	int error;
+
+	mutex_lock(&ns->subsys->lock);
+	if (ns->enabled) {
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+
+	error = pci_p2pdma_enable_store(page, &p2p_dev, &use_p2pmem);
+	if (error) {
+		ret = error;
+		goto out_unlock;
+	}
+
+	ns->use_p2pmem = use_p2pmem;
+	pci_dev_put(ns->p2p_dev);
+	ns->p2p_dev = p2p_dev;
+
+out_unlock:
+	mutex_unlock(&ns->subsys->lock);
+
+	return ret;
+}
+
+CONFIGFS_ATTR(nvmet_ns_, p2pmem);
+#endif /* CONFIG_PCI_P2PDMA */
+
 static ssize_t nvmet_ns_device_uuid_show(struct config_item *item, char *page)
 {
 	return sprintf(page, "%pUb\n", &to_nvmet_ns(item)->uuid);
@@ -509,6 +553,9 @@ static struct configfs_attribute *nvmet_ns_attrs[] = {
 	&nvmet_ns_attr_ana_grpid,
 	&nvmet_ns_attr_enable,
 	&nvmet_ns_attr_buffered_io,
+#ifdef CONFIG_PCI_P2PDMA
+	&nvmet_ns_attr_p2pmem,
+#endif
 	NULL,
 };