linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Maxim Levitsky <mlevitsk@redhat.com>
To: linux-nvme@lists.infradead.org
Cc: Maxim Levitsky <mlevitsk@redhat.com>,
	linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
	Jens Axboe <axboe@fb.com>,
	Alex Williamson <alex.williamson@redhat.com>,
	Keith Busch <keith.busch@intel.com>,
	Christoph Hellwig <hch@lst.de>, Sagi Grimberg <sagi@grimberg.me>,
	Kirti Wankhede <kwankhede@nvidia.com>,
	"David S . Miller" <davem@davemloft.net>,
	Mauro Carvalho Chehab <mchehab+samsung@kernel.org>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Wolfram Sang <wsa@the-dreams.de>,
	Nicolas Ferre <nicolas.ferre@microchip.com>,
	"Paul E . McKenney " <paulmck@linux.ibm.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Liang Cunming <cunming.liang@intel.com>,
	Liu Changpeng <changpeng.liu@intel.com>,
	Fam Zheng <fam@euphon.net>, Amnon Ilan <ailan@redhat.com>,
	John Ferlan <jferlan@redhat.com>
Subject: [PATCH v2 06/10] nvme/core: add mdev interfaces
Date: Thu,  2 May 2019 14:47:57 +0300	[thread overview]
Message-ID: <20190502114801.23116-7-mlevitsk@redhat.com> (raw)
In-Reply-To: <20190502114801.23116-1-mlevitsk@redhat.com>

This adds infrastructure for a nvme-mdev
to attach to the core driver, to be able to
know which nvme controllers are present and which
namespaces they have.

It also adds an interface to nvme device drivers
which expose the its queues in a controlled manner
to the nvme mdev core driver. A driver must opt-in
for this using a new flag NVME_F_MDEV_SUPPORTED

If the mdev device driver also sets the
NVME_F_MDEV_DMA_SUPPORTED, the mdev core will
dma map all the guest memory into the nvme device,
so that nvme device driver can use dma addresses as passed
from the mdev core driver

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
---
 drivers/nvme/host/core.c | 125 ++++++++++++++++++++++++++++++++++++++-
 drivers/nvme/host/nvme.h |  54 +++++++++++++++--
 2 files changed, 172 insertions(+), 7 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 22db0c51a0bf..3c1b91089631 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -89,11 +89,111 @@ static dev_t nvme_chr_devt;
 static struct class *nvme_class;
 static struct class *nvme_subsys_class;
 
+static void nvme_ns_remove(struct nvme_ns *ns);
 static int nvme_revalidate_disk(struct gendisk *disk);
 static void nvme_put_subsystem(struct nvme_subsystem *subsys);
 static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 					   unsigned nsid);
 
+#ifdef CONFIG_NVME_MDEV
+
+static struct nvme_mdev_driver *mdev_driver_interface;
+static DEFINE_MUTEX(mdev_ctrl_lock);
+static LIST_HEAD(mdev_ctrl_list);
+
+static bool nvme_ctrl_has_mdev(struct nvme_ctrl *ctrl)
+{
+	return  (ctrl->ops->flags & NVME_F_MDEV_SUPPORTED) != 0;
+}
+
+static void nvme_mdev_add_ctrl(struct nvme_ctrl *ctrl)
+{
+	if (nvme_ctrl_has_mdev(ctrl)) {
+		mutex_lock(&mdev_ctrl_lock);
+		list_add_tail(&ctrl->link, &mdev_ctrl_list);
+		mutex_unlock(&mdev_ctrl_lock);
+	}
+}
+
+static void nvme_mdev_remove_ctrl(struct nvme_ctrl *ctrl)
+{
+	if (nvme_ctrl_has_mdev(ctrl)) {
+		mutex_lock(&mdev_ctrl_lock);
+		list_del_init(&ctrl->link);
+		mutex_unlock(&mdev_ctrl_lock);
+	}
+}
+
+int nvme_core_register_mdev_driver(struct nvme_mdev_driver *driver_ops)
+{
+	struct nvme_ctrl *ctrl;
+
+	if (mdev_driver_interface)
+		return -EEXIST;
+
+	mdev_driver_interface = driver_ops;
+
+	mutex_lock(&mdev_ctrl_lock);
+	list_for_each_entry(ctrl, &mdev_ctrl_list, link)
+		mdev_driver_interface->nvme_ctrl_state_changed(ctrl);
+
+	mutex_unlock(&mdev_ctrl_lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nvme_core_register_mdev_driver);
+
+void nvme_core_unregister_mdev_driver(struct nvme_mdev_driver *driver_ops)
+{
+	if (WARN_ON(driver_ops != mdev_driver_interface))
+		return;
+	mdev_driver_interface = NULL;
+}
+EXPORT_SYMBOL_GPL(nvme_core_unregister_mdev_driver);
+
+static void nvme_mdev_ctrl_state_changed(struct nvme_ctrl *ctrl)
+{
+	if (!mdev_driver_interface || !nvme_ctrl_has_mdev(ctrl))
+		return;
+	if (!try_module_get(mdev_driver_interface->owner))
+		return;
+
+	mdev_driver_interface->nvme_ctrl_state_changed(ctrl);
+	module_put(mdev_driver_interface->owner);
+}
+
+static void nvme_mdev_ns_state_changed(struct nvme_ctrl *ctrl,
+				       struct nvme_ns *ns, bool removed)
+{
+	if (!mdev_driver_interface || !nvme_ctrl_has_mdev(ctrl))
+		return;
+	if (!try_module_get(mdev_driver_interface->owner))
+		return;
+
+	mdev_driver_interface->nvme_ns_state_changed(ctrl,
+			ns->head->ns_id, removed);
+	module_put(mdev_driver_interface->owner);
+}
+
+#else
+static void nvme_mdev_ctrl_state_changed(struct nvme_ctrl *ctrl)
+{
+}
+
+static void nvme_mdev_ns_state_changed(struct nvme_ctrl *ctrl,
+				       struct nvme_ns *ns, bool removed)
+{
+}
+
+static void nvme_mdev_add_ctrl(struct nvme_ctrl *ctrl)
+{
+}
+
+static void nvme_mdev_remove_ctrl(struct nvme_ctrl *ctrl)
+{
+}
+
+#endif
+
 static void nvme_set_queue_dying(struct nvme_ns *ns)
 {
 	/*
@@ -387,10 +487,13 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 
 	if (changed)
 		ctrl->state = new_state;
-
 	spin_unlock_irqrestore(&ctrl->lock, flags);
+
+	nvme_mdev_ctrl_state_changed(ctrl);
+
 	if (changed && ctrl->state == NVME_CTRL_LIVE)
 		nvme_kick_requeue_lists(ctrl);
+
 	return changed;
 }
 EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
@@ -426,10 +529,11 @@ static void nvme_free_ns(struct kref *kref)
 	kfree(ns);
 }
 
-static void nvme_put_ns(struct nvme_ns *ns)
+void nvme_put_ns(struct nvme_ns *ns)
 {
 	kref_put(&ns->kref, nvme_free_ns);
 }
+EXPORT_SYMBOL_GPL(nvme_put_ns);
 
 static inline void nvme_clear_nvme_request(struct request *req)
 {
@@ -1289,6 +1393,11 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	return effects;
 }
 
+static void nvme_update_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns)
+{
+	nvme_mdev_ns_state_changed(ctrl, ns, false);
+}
+
 static void nvme_update_formats(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
@@ -1297,6 +1406,8 @@ static void nvme_update_formats(struct nvme_ctrl *ctrl)
 	list_for_each_entry(ns, &ctrl->namespaces, list)
 		if (ns->disk && nvme_revalidate_disk(ns->disk))
 			nvme_set_queue_dying(ns);
+		else
+			nvme_update_ns(ctrl, ns);
 	up_read(&ctrl->namespaces_rwsem);
 
 	nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL);
@@ -3186,7 +3297,7 @@ static int ns_cmp(void *priv, struct list_head *a, struct list_head *b)
 	return nsa->head->ns_id - nsb->head->ns_id;
 }
 
-static struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid)
+struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned int nsid)
 {
 	struct nvme_ns *ns, *ret = NULL;
 
@@ -3204,6 +3315,7 @@ static struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	up_read(&ctrl->namespaces_rwsem);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(nvme_find_get_ns);
 
 static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns)
 {
@@ -3336,6 +3448,8 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 	if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
 		return;
 
+	nvme_mdev_ns_state_changed(ns->ctrl, ns, true);
+
 	nvme_fault_inject_fini(ns);
 	if (ns->disk && ns->disk->flags & GENHD_FL_UP) {
 		del_gendisk(ns->disk);
@@ -3366,6 +3480,8 @@ static void nvme_validate_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	if (ns) {
 		if (ns->disk && revalidate_disk(ns->disk))
 			nvme_ns_remove(ns);
+		else
+			nvme_update_ns(ctrl, ns);
 		nvme_put_ns(ns);
 	} else
 		nvme_alloc_ns(ctrl, nsid);
@@ -3717,6 +3833,7 @@ static void nvme_free_ctrl(struct device *dev)
 		sysfs_remove_link(&subsys->dev.kobj, dev_name(ctrl->device));
 	}
 
+	nvme_mdev_remove_ctrl(ctrl);
 	ctrl->ops->free_ctrl(ctrl);
 
 	if (subsys)
@@ -3789,6 +3906,8 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	dev_pm_qos_update_user_latency_tolerance(ctrl->device,
 		min(default_ps_max_latency_us, (unsigned long)S32_MAX));
 
+	nvme_mdev_add_ctrl(ctrl);
+
 	return 0;
 out_free_name:
 	kfree_const(ctrl->device->kobj.name);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index d040eb00e880..6ec14ce0d015 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -148,6 +148,7 @@ enum nvme_ctrl_state {
 };
 
 struct nvme_ctrl {
+	struct list_head link;
 	bool comp_seen;
 	enum nvme_ctrl_state state;
 	bool identified;
@@ -255,6 +256,23 @@ enum nvme_iopolicy {
 	NVME_IOPOLICY_RR,
 };
 
+#ifdef CONFIG_NVME_MDEV
+/* Interface to the host driver  */
+struct nvme_mdev_driver {
+	struct module *owner;
+
+	/* a controller state has changed*/
+	void (*nvme_ctrl_state_changed)(struct nvme_ctrl *ctrl);
+
+	/* NS is updated in some way (after format or so) */
+	void (*nvme_ns_state_changed)(struct nvme_ctrl *ctrl,
+				      u32 nsid, bool removed);
+};
+
+int nvme_core_register_mdev_driver(struct nvme_mdev_driver *driver_ops);
+void nvme_core_unregister_mdev_driver(struct nvme_mdev_driver *driver_ops);
+#endif
+
 struct nvme_subsystem {
 	int			instance;
 	struct device		dev;
@@ -280,7 +298,7 @@ struct nvme_subsystem {
 };
 
 /*
- * Container structure for uniqueue namespace identifiers.
+ * Container structure for unique namespace identifiers.
  */
 struct nvme_ns_ids {
 	u8	eui64[8];
@@ -356,13 +374,22 @@ struct nvme_ns {
 
 };
 
+struct nvme_ext_data_iter;
+struct nvme_ext_cmd_result {
+	u32 tag;
+	u16 status;
+};
+
 struct nvme_ctrl_ops {
 	const char *name;
 	struct module *module;
 	unsigned int flags;
-#define NVME_F_FABRICS			(1 << 0)
-#define NVME_F_METADATA_SUPPORTED	(1 << 1)
-#define NVME_F_PCI_P2PDMA		(1 << 2)
+#define NVME_F_FABRICS			BIT(0)
+#define NVME_F_METADATA_SUPPORTED	BIT(1)
+#define NVME_F_PCI_P2PDMA		BIT(2)
+#define NVME_F_MDEV_SUPPORTED		BIT(3)
+#define NVME_F_MDEV_DMA_SUPPORTED	BIT(4)
+
 	int (*reg_read32)(struct nvme_ctrl *ctrl, u32 off, u32 *val);
 	int (*reg_write32)(struct nvme_ctrl *ctrl, u32 off, u32 val);
 	int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);
@@ -370,6 +397,23 @@ struct nvme_ctrl_ops {
 	void (*submit_async_event)(struct nvme_ctrl *ctrl);
 	void (*delete_ctrl)(struct nvme_ctrl *ctrl);
 	int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size);
+
+#ifdef CONFIG_NVME_MDEV
+	int (*ext_queues_available)(struct nvme_ctrl *ctrl);
+	int (*ext_queue_alloc)(struct nvme_ctrl *ctrl, u16 *qid);
+	void (*ext_queue_free)(struct nvme_ctrl *ctrl, u16 qid);
+
+	int (*ext_queue_submit)(struct nvme_ctrl *ctrl,
+				u16 qid, u32 tag,
+				struct nvme_command *command,
+				struct nvme_ext_data_iter *iter);
+
+	bool (*ext_queue_full)(struct nvme_ctrl *ctrl, u16 qid);
+
+	int (*ext_queue_poll)(struct nvme_ctrl *ctrl, u16 qid,
+			      struct nvme_ext_cmd_result *results,
+			      unsigned int max_len);
+#endif
 };
 
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
@@ -431,6 +475,8 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl);
 void nvme_put_ctrl(struct nvme_ctrl *ctrl);
 int nvme_init_identify(struct nvme_ctrl *ctrl);
 
+struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned int nsid);
+void nvme_put_ns(struct nvme_ns *ns);
 void nvme_remove_namespaces(struct nvme_ctrl *ctrl);
 
 int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
-- 
2.17.2


  parent reply	other threads:[~2019-05-02 11:49 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-02 11:47 [PATCH v2 00/10] RFC: NVME MDEV Maxim Levitsky
2019-05-02 11:47 ` [PATCH v2 01/10] vfio/mdev: add notifier for map events Maxim Levitsky
2019-05-02 11:47 ` [PATCH v2 02/10] vfio/mdev: add .request callback Maxim Levitsky
2019-05-02 11:47 ` [PATCH v2 03/10] nvme/core: add some more values from the spec Maxim Levitsky
2019-05-02 11:47 ` [PATCH v2 04/10] nvme/core: add NVME_CTRL_SUSPENDED controller state Maxim Levitsky
2019-05-02 11:47 ` [PATCH v2 05/10] nvme/pci: use the NVME_CTRL_SUSPENDED state Maxim Levitsky
2019-05-02 11:47 ` Maxim Levitsky [this message]
2019-05-03 12:29   ` [PATCH v2 06/10] nvme/core: add mdev interfaces Christoph Hellwig
2019-05-03 19:00     ` Max Gurtovoy
2019-05-04  6:49       ` Christoph Hellwig
2019-05-06  8:31         ` Maxim Levitsky
2019-05-06  8:34           ` Maxim Levitsky
2019-05-06 12:59           ` Christoph Hellwig
2019-05-02 11:47 ` [PATCH v2 07/10] nvme/core: add nvme-mdev core driver Maxim Levitsky
2019-05-02 11:47 ` [PATCH v2 08/10] nvme/pci: implement the mdev external queue allocation interface Maxim Levitsky
2019-05-02 14:20   ` Maxim Levitsky
2019-05-02 21:12   ` Heitke, Kenneth
2019-05-02 21:20     ` Maxim Levitsky
2019-05-03 12:09       ` Keith Busch
2019-05-06  7:55         ` Maxim Levitsky
2019-05-02 11:48 ` [PATCH v2 09/10] nvme/mdev - Add inline performance measurments Maxim Levitsky
2019-05-02 11:48 ` [PATCH v2 10/10] nvme/mdev - generic block IO code Maxim Levitsky
2019-05-03 12:18 ` [PATCH v2 00/10] RFC: NVME MDEV Christoph Hellwig
2019-05-06  9:04   ` Maxim Levitsky
2019-05-06 12:57     ` Christoph Hellwig
2019-05-06 16:43       ` Keith Busch
2019-05-08 12:39       ` Paolo Bonzini
2019-05-09  9:12     ` Stefan Hajnoczi
2019-05-09 13:49       ` Keith Busch

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=20190502114801.23116-7-mlevitsk@redhat.com \
    --to=mlevitsk@redhat.com \
    --cc=ailan@redhat.com \
    --cc=alex.williamson@redhat.com \
    --cc=axboe@fb.com \
    --cc=changpeng.liu@intel.com \
    --cc=cunming.liang@intel.com \
    --cc=davem@davemloft.net \
    --cc=fam@euphon.net \
    --cc=gregkh@linuxfoundation.org \
    --cc=hch@lst.de \
    --cc=jferlan@redhat.com \
    --cc=keith.busch@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=kwankhede@nvidia.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=mchehab+samsung@kernel.org \
    --cc=nicolas.ferre@microchip.com \
    --cc=paulmck@linux.ibm.com \
    --cc=pbonzini@redhat.com \
    --cc=sagi@grimberg.me \
    --cc=wsa@the-dreams.de \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
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).