nvdimm.lists.linux.dev archive mirror
 help / color / mirror / Atom feed
From: Sagi Grimberg <sagi@grimberg.me>
To: Logan Gunthorpe <logang@deltatee.com>,
	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: "Jens Axboe" <axboe@kernel.dk>,
	"Christian König" <christian.koenig@amd.com>,
	"Benjamin Herrenschmidt" <benh@kernel.crashing.org>,
	"Steve Wise" <swise@opengridcomputing.com>,
	"Alex Williamson" <alex.williamson@redhat.com>,
	"Jérôme Glisse" <jglisse@redhat.com>,
	"Jason Gunthorpe" <jgg@mellanox.com>,
	"Bjorn Helgaas" <bhelgaas@google.com>,
	"Max Gurtovoy" <maxg@mellanox.com>,
	"Christoph Hellwig" <hch@lst.de>
Subject: Re: [PATCH v8 13/13] nvmet: Optionally use PCI P2P memory
Date: Mon, 1 Oct 2018 14:34:20 -0700	[thread overview]
Message-ID: <5ddeed51-0580-9581-cf12-c75e18b4f7cc@grimberg.me> (raw)
In-Reply-To: <20180927165420.5290-14-logang@deltatee.com>



On 09/27/2018 09:54 AM, Logan Gunthorpe wrote:
> We create a configfs attribute in each nvme-fabrics target port to
> enable p2p memory use. When enabled, the port will only then use the
> p2p memory if a p2p memory device can be found which is behind the
> same switch hierarchy as the RDMA port and all the block devices in
> use. If the user enabled it and no devices are found, then the system
> will silently fall back on using regular memory.
> 
> If appropriate, that port will allocate memory for the RDMA buffers
> for queues from the p2pmem device falling back to system memory should
> anything fail.
> 
> Ideally, we'd want to use an NVME CMB buffer as p2p memory. This would
> save an extra PCI transfer as the NVME card could just take the data
> out of it's own memory. However, at this time, only a limited number
> of cards with CMB buffers seem to be available.
> 
> 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>
> ---
>   drivers/nvme/target/configfs.c    |  36 ++++++++
>   drivers/nvme/target/core.c        | 138 +++++++++++++++++++++++++++++-
>   drivers/nvme/target/io-cmd-bdev.c |   3 +
>   drivers/nvme/target/nvmet.h       |  13 +++
>   drivers/nvme/target/rdma.c        |   2 +
>   5 files changed, 191 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
> index b37a8e3e3f80..0dfb0e0c3d21 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"
>   
> @@ -1094,6 +1096,37 @@ static void nvmet_port_release(struct config_item *item)
>   	kfree(port);
>   }
>   
> +#ifdef CONFIG_PCI_P2PDMA
> +static ssize_t nvmet_p2pmem_show(struct config_item *item, char *page)
> +{
> +	struct nvmet_port *port = to_nvmet_port(item);
> +
> +	return pci_p2pdma_enable_show(page, port->p2p_dev, port->use_p2pmem);
> +}
> +
> +static ssize_t nvmet_p2pmem_store(struct config_item *item,
> +		const char *page, size_t count)
> +{
> +	struct nvmet_port *port = to_nvmet_port(item);
> +	struct pci_dev *p2p_dev = NULL;
> +	bool use_p2pmem;
> +	int error;
> +
> +	error = pci_p2pdma_enable_store(page, &p2p_dev, &use_p2pmem);
> +	if (error)
> +		return error;
> +
> +	down_write(&nvmet_config_sem);
> +	port->use_p2pmem = use_p2pmem;
> +	pci_dev_put(port->p2p_dev);
> +	port->p2p_dev = p2p_dev;
> +	up_write(&nvmet_config_sem);
> +
> +	return count;
> +}
> +CONFIGFS_ATTR(nvmet_, p2pmem);
> +#endif /* CONFIG_PCI_P2PDMA */
> +
>   static struct configfs_attribute *nvmet_port_attrs[] = {
>   	&nvmet_attr_addr_adrfam,
>   	&nvmet_attr_addr_treq,
> @@ -1101,6 +1134,9 @@ static struct configfs_attribute *nvmet_port_attrs[] = {
>   	&nvmet_attr_addr_trsvcid,
>   	&nvmet_attr_addr_trtype,
>   	&nvmet_attr_param_inline_data_size,
> +#ifdef CONFIG_PCI_P2PDMA
> +	&nvmet_attr_p2pmem,
> +#endif
>   	NULL,
>   };
>   
> diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
> index bddd1599b826..7ade16cb4ed3 100644
> --- a/drivers/nvme/target/core.c
> +++ b/drivers/nvme/target/core.c
> @@ -15,6 +15,7 @@
>   #include <linux/module.h>
>   #include <linux/random.h>
>   #include <linux/rculist.h>
> +#include <linux/pci-p2pdma.h>
>   
>   #include "nvmet.h"
>   
> @@ -365,9 +366,29 @@ static void nvmet_ns_dev_disable(struct nvmet_ns *ns)
>   	nvmet_file_ns_disable(ns);
>   }
>   
> +static int nvmet_p2pdma_add_client(struct nvmet_ctrl *ctrl,
> +		struct nvmet_ns *ns)
> +{
> +	int ret;
> +
> +	if (!blk_queue_pci_p2pdma(ns->bdev->bd_queue)) {
> +		pr_err("peer-to-peer DMA is not supported by %s\n",
> +		       ns->device_path);
> +		return -EINVAL;
> +	}
> +
> +	ret = pci_p2pdma_add_client(&ctrl->p2p_clients, nvmet_ns_dev(ns));
> +	if (ret)
> +		pr_err("failed to add peer-to-peer DMA client %s: %d\n",
> +		       ns->device_path, ret);
> +
> +	return ret;
> +}
> +
>   int nvmet_ns_enable(struct nvmet_ns *ns)
>   {
>   	struct nvmet_subsys *subsys = ns->subsys;
> +	struct nvmet_ctrl *ctrl;
>   	int ret;
>   
>   	mutex_lock(&subsys->lock);
> @@ -389,6 +410,14 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
>   	if (ret)
>   		goto out_dev_put;
>   
> +	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
> +		if (ctrl->p2p_dev) {
> +			ret = nvmet_p2pdma_add_client(ctrl, ns);
> +			if (ret)
> +				goto out_remove_clients;
> +		}
> +	}
> +
>   	if (ns->nsid > subsys->max_nsid)
>   		subsys->max_nsid = ns->nsid;
>   
> @@ -417,6 +446,9 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
>   out_unlock:
>   	mutex_unlock(&subsys->lock);
>   	return ret;
> +out_remove_clients:
> +	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
> +		pci_p2pdma_remove_client(&ctrl->p2p_clients, nvmet_ns_dev(ns));
>   out_dev_put:
>   	nvmet_ns_dev_disable(ns);
>   	goto out_unlock;
> @@ -425,6 +457,7 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
>   void nvmet_ns_disable(struct nvmet_ns *ns)
>   {
>   	struct nvmet_subsys *subsys = ns->subsys;
> +	struct nvmet_ctrl *ctrl;
>   
>   	mutex_lock(&subsys->lock);
>   	if (!ns->enabled)
> @@ -450,6 +483,12 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
>   	percpu_ref_exit(&ns->ref);
>   
>   	mutex_lock(&subsys->lock);
> +
> +	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
> +		pci_p2pdma_remove_client(&ctrl->p2p_clients, nvmet_ns_dev(ns));
> +		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE, 0, 0);

Hi Logan, what is this event here?

> +	}
> +
>   	subsys->nr_namespaces--;
>   	nvmet_ns_changed(subsys, ns->nsid);
>   	nvmet_ns_dev_disable(ns);
> @@ -727,6 +766,23 @@ EXPORT_SYMBOL_GPL(nvmet_req_execute);
>   
>   int nvmet_req_alloc_sgl(struct nvmet_req *req, struct nvmet_sq *sq)
>   {
> +	struct pci_dev *p2p_dev = NULL;
> +
> +	if (IS_ENABLED(CONFIG_PCI_P2PDMA)) {
> +		if (sq->ctrl)
> +			p2p_dev = sq->ctrl->p2p_dev;
> +
> +		req->p2p_dev = NULL;
> +		if (sq->qid && p2p_dev) {
> +			req->sg = pci_p2pmem_alloc_sgl(p2p_dev, &req->sg_cnt,
> +						       req->transfer_len);
> +			if (req->sg) {
> +				req->p2p_dev = p2p_dev;
> +				return 0;
> +			}

Would be useful to comment that we fall to normal sgl allocation.

> +		}
> +	}
> +
>   	req->sg = sgl_alloc(req->transfer_len, GFP_KERNEL, &req->sg_cnt);
>   	if (!req->sg)
>   		return -ENOMEM;
> @@ -737,7 +793,11 @@ EXPORT_SYMBOL_GPL(nvmet_req_alloc_sgl);
>   
>   void nvmet_req_free_sgl(struct nvmet_req *req)
>   {
> -	sgl_free(req->sg);
> +	if (req->p2p_dev)
> +		pci_p2pmem_free_sgl(req->p2p_dev, req->sg);
> +	else
> +		sgl_free(req->sg);
> +
>   	req->sg = NULL;
>   	req->sg_cnt = 0;
>   }
> @@ -939,6 +999,79 @@ bool nvmet_host_allowed(struct nvmet_req *req, struct nvmet_subsys *subsys,
>   		return __nvmet_host_allowed(subsys, hostnqn);
>   }
>   
> +/*
> + * If allow_p2pmem is set, we will try to use P2P memory for the SGL lists for
> + * Ι/O commands. This requires the PCI p2p device to be compatible with the
> + * backing device for every namespace on this controller.
> + */
> +static void nvmet_setup_p2pmem(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
> +{
> +	struct nvmet_ns *ns;
> +	int ret;
> +
> +	if (!req->port->use_p2pmem || !req->p2p_client)
> +		return;

Nit, IMO would be better to check at the call-site, but not a hard
must...

I still do not fully understand why p2p_dev has to be ctrl-wide and not
per namespace. Sorry to keep bringing this up (again). But if people are
OK with it then I guess I can stop asking about this...


> +
> +	mutex_lock(&ctrl->subsys->lock);
> +
> +	ret = pci_p2pdma_add_client(&ctrl->p2p_clients, req->p2p_client);
> +	if (ret) {
> +		pr_err("failed adding peer-to-peer DMA client %s: %d\n",
> +		       dev_name(req->p2p_client), ret);
> +		goto free_devices;
> +	}
> +
> +	list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link) {
> +		ret = nvmet_p2pdma_add_client(ctrl, ns);
> +		if (ret)
> +			goto free_devices;

I think that at some point we said that this looks like it should fall
back to host memory for those namespaces.. when we allocate the sgl we
already assigned a namespace to the request (nvmet_req_init).

Aside from my questions the patch looks good.
_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm

  parent reply	other threads:[~2018-10-01 21:34 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-09-27 16:54 [PATCH v8 00/13] Copy Offload in NVMe Fabrics with P2P PCI Memory Logan Gunthorpe
2018-09-27 16:54 ` [PATCH v8 01/13] PCI/P2PDMA: Support peer-to-peer memory Logan Gunthorpe
2018-09-27 16:54 ` [PATCH v8 02/13] PCI/P2PDMA: Add sysfs group to display p2pmem stats Logan Gunthorpe
2018-09-27 16:54 ` [PATCH v8 03/13] PCI/P2PDMA: Add PCI p2pmem DMA mappings to adjust the bus offset Logan Gunthorpe
2018-09-27 16:54 ` [PATCH v8 04/13] PCI/P2PDMA: Introduce configfs/sysfs enable attribute helpers Logan Gunthorpe
2018-09-27 16:54 ` [PATCH v8 05/13] docs-rst: Add a new directory for PCI documentation Logan Gunthorpe
2018-09-27 16:54 ` [PATCH v8 06/13] PCI/P2PDMA: Add P2P DMA driver writer's documentation Logan Gunthorpe
2018-09-27 16:54 ` [PATCH v8 07/13] block: Add PCI P2P flag for request queue and check support for requests Logan Gunthorpe
2018-09-27 16:54 ` [PATCH v8 08/13] IB/core: Ensure we map P2P memory correctly in rdma_rw_ctx_[init|destroy]() Logan Gunthorpe
2018-09-27 16:54 ` [PATCH v8 09/13] nvme-pci: Use PCI p2pmem subsystem to manage the CMB Logan Gunthorpe
2018-09-27 17:10   ` Keith Busch
2018-09-27 16:54 ` [PATCH v8 10/13] nvme-pci: Add support for P2P memory in requests Logan Gunthorpe
2018-09-27 17:10   ` Keith Busch
2018-09-27 16:54 ` [PATCH v8 11/13] nvme-pci: Add a quirk for a pseudo CMB Logan Gunthorpe
2018-09-27 17:09   ` Keith Busch
2018-09-27 16:54 ` [PATCH v8 12/13] nvmet: Introduce helper functions to allocate and free request SGLs Logan Gunthorpe
2018-09-27 16:54 ` [PATCH v8 13/13] nvmet: Optionally use PCI P2P memory Logan Gunthorpe
2018-09-27 17:12   ` Keith Busch
2018-09-27 17:29     ` Logan Gunthorpe
2018-10-01 21:34   ` Sagi Grimberg [this message]
2018-10-01 21:55     ` Logan Gunthorpe
2018-10-01 22:23       ` Sagi Grimberg
2018-10-01 23:43         ` Logan Gunthorpe

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=5ddeed51-0580-9581-cf12-c75e18b4f7cc@grimberg.me \
    --to=sagi@grimberg.me \
    --cc=alex.williamson@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=benh@kernel.crashing.org \
    --cc=bhelgaas@google.com \
    --cc=christian.koenig@amd.com \
    --cc=hch@lst.de \
    --cc=jgg@mellanox.com \
    --cc=jglisse@redhat.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=logang@deltatee.com \
    --cc=maxg@mellanox.com \
    --cc=swise@opengridcomputing.com \
    --subject='Re: [PATCH v8 13/13] nvmet: Optionally use PCI P2P memory' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).