device-dax: introduce 'seed' devices

Add a seed device concept for dynamic dax regions to be able to split the
region amongst multiple sub-instances.  The seed device, similar to
libnvdimm seed devices, is a device that starts with zero capacity
allocated and unbound to a driver.  In contrast to libnvdimm seed devices
explicit 'create' and 'delete' interfaces are added to the region to
trigger seeds to be created and unused devices to be reclaimed.  The
explicit create and delete replaces implicit create as a side effect of
probe and implicit delete when writing 0 to the size that libnvdimm
implements.

Delete can be performed on any 0-sized and idle device.  This avoids the
gymnastics of needing to move device_unregister() to its own async
context.  Specifically, it avoids the deadlock of deleting a device via
one of its own attributes.  It is also less surprising to userspace which
never sees an extra device it did not request.

For now just add the device creation, teardown, and ->probe() prevention.
A later patch will arrange for the 'dax/size' attribute to be writable to
allocate capacity from the region.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jia He <justin.he@arm.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: David Airlie <airlied@linux.ie>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Hulk Robot <hulkci@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jason Yan <yanaijie@huawei.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/r/159643101583.4062302.12255093902950754962.stgit@dwillia2-desk3.amr.corp.intel.com
Link: https://lkml.kernel.org/r/160106113873.30709.15168756050631539431.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 262 insertions, 39 deletions

diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 9549f11ebed0..dce9413a4394 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -139,8 +139,26 @@ static int dax_bus_probe(struct device *dev)
 {
 	struct dax_device_driver *dax_drv = to_dax_drv(dev->driver);
 	struct dev_dax *dev_dax = to_dev_dax(dev);
+	struct dax_region *dax_region = dev_dax->region;
+	struct range *range = &dev_dax->range;
+	int rc;
+
+	if (range_len(range) == 0 || dev_dax->id < 0)
+		return -ENXIO;
+
+	rc = dax_drv->probe(dev_dax);
+
+	if (rc || is_static(dax_region))
+		return rc;
+
+	/*
+	 * Track new seed creation only after successful probe of the
+	 * previous seed.
+	 */
+	if (dax_region->seed == dev)
+		dax_region->seed = NULL;
 
-	return dax_drv->probe(dev_dax);
+	return 0;
 }
 
 static int dax_bus_remove(struct device *dev)
@@ -237,14 +255,216 @@ static ssize_t available_size_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(available_size);
 
+static ssize_t seed_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct dax_region *dax_region = dev_get_drvdata(dev);
+	struct device *seed;
+	ssize_t rc;
+
+	if (is_static(dax_region))
+		return -EINVAL;
+
+	device_lock(dev);
+	seed = dax_region->seed;
+	rc = sprintf(buf, "%s\n", seed ? dev_name(seed) : "");
+	device_unlock(dev);
+
+	return rc;
+}
+static DEVICE_ATTR_RO(seed);
+
+static ssize_t create_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct dax_region *dax_region = dev_get_drvdata(dev);
+	struct device *youngest;
+	ssize_t rc;
+
+	if (is_static(dax_region))
+		return -EINVAL;
+
+	device_lock(dev);
+	youngest = dax_region->youngest;
+	rc = sprintf(buf, "%s\n", youngest ? dev_name(youngest) : "");
+	device_unlock(dev);
+
+	return rc;
+}
+
+static ssize_t create_store(struct device *dev, struct device_attribute *attr,
+		const char *buf, size_t len)
+{
+	struct dax_region *dax_region = dev_get_drvdata(dev);
+	unsigned long long avail;
+	ssize_t rc;
+	int val;
+
+	if (is_static(dax_region))
+		return -EINVAL;
+
+	rc = kstrtoint(buf, 0, &val);
+	if (rc)
+		return rc;
+	if (val != 1)
+		return -EINVAL;
+
+	device_lock(dev);
+	avail = dax_region_avail_size(dax_region);
+	if (avail == 0)
+		rc = -ENOSPC;
+	else {
+		struct dev_dax_data data = {
+			.dax_region = dax_region,
+			.size = 0,
+			.id = -1,
+		};
+		struct dev_dax *dev_dax = devm_create_dev_dax(&data);
+
+		if (IS_ERR(dev_dax))
+			rc = PTR_ERR(dev_dax);
+		else {
+			/*
+			 * In support of crafting multiple new devices
+			 * simultaneously multiple seeds can be created,
+			 * but only the first one that has not been
+			 * successfully bound is tracked as the region
+			 * seed.
+			 */
+			if (!dax_region->seed)
+				dax_region->seed = &dev_dax->dev;
+			dax_region->youngest = &dev_dax->dev;
+			rc = len;
+		}
+	}
+	device_unlock(dev);
+
+	return rc;
+}
+static DEVICE_ATTR_RW(create);
+
+void kill_dev_dax(struct dev_dax *dev_dax)
+{
+	struct dax_device *dax_dev = dev_dax->dax_dev;
+	struct inode *inode = dax_inode(dax_dev);
+
+	kill_dax(dax_dev);
+	unmap_mapping_range(inode->i_mapping, 0, 0, 1);
+}
+EXPORT_SYMBOL_GPL(kill_dev_dax);
+
+static void free_dev_dax_range(struct dev_dax *dev_dax)
+{
+	struct dax_region *dax_region = dev_dax->region;
+	struct range *range = &dev_dax->range;
+
+	device_lock_assert(dax_region->dev);
+	if (range_len(range))
+		__release_region(&dax_region->res, range->start,
+				range_len(range));
+}
+
+static void unregister_dev_dax(void *dev)
+{
+	struct dev_dax *dev_dax = to_dev_dax(dev);
+
+	dev_dbg(dev, "%s\n", __func__);
+
+	kill_dev_dax(dev_dax);
+	free_dev_dax_range(dev_dax);
+	device_del(dev);
+	put_device(dev);
+}
+
+/* a return value >= 0 indicates this invocation invalidated the id */
+static int __free_dev_dax_id(struct dev_dax *dev_dax)
+{
+	struct dax_region *dax_region = dev_dax->region;
+	struct device *dev = &dev_dax->dev;
+	int rc = dev_dax->id;
+
+	device_lock_assert(dev);
+
+	if (is_static(dax_region) || dev_dax->id < 0)
+		return -1;
+	ida_free(&dax_region->ida, dev_dax->id);
+	dev_dax->id = -1;
+	return rc;
+}
+
+static int free_dev_dax_id(struct dev_dax *dev_dax)
+{
+	struct device *dev = &dev_dax->dev;
+	int rc;
+
+	device_lock(dev);
+	rc = __free_dev_dax_id(dev_dax);
+	device_unlock(dev);
+	return rc;
+}
+
+static ssize_t delete_store(struct device *dev, struct device_attribute *attr,
+		const char *buf, size_t len)
+{
+	struct dax_region *dax_region = dev_get_drvdata(dev);
+	struct dev_dax *dev_dax;
+	struct device *victim;
+	bool do_del = false;
+	int rc;
+
+	if (is_static(dax_region))
+		return -EINVAL;
+
+	victim = device_find_child_by_name(dax_region->dev, buf);
+	if (!victim)
+		return -ENXIO;
+
+	device_lock(dev);
+	device_lock(victim);
+	dev_dax = to_dev_dax(victim);
+	if (victim->driver || range_len(&dev_dax->range))
+		rc = -EBUSY;
+	else {
+		/*
+		 * Invalidate the device so it does not become active
+		 * again, but always preserve device-id-0 so that
+		 * /sys/bus/dax/ is guaranteed to be populated while any
+		 * dax_region is registered.
+		 */
+		if (dev_dax->id > 0) {
+			do_del = __free_dev_dax_id(dev_dax) >= 0;
+			rc = len;
+			if (dax_region->seed == victim)
+				dax_region->seed = NULL;
+			if (dax_region->youngest == victim)
+				dax_region->youngest = NULL;
+		} else
+			rc = -EBUSY;
+	}
+	device_unlock(victim);
+
+	/* won the race to invalidate the device, clean it up */
+	if (do_del)
+		devm_release_action(dev, unregister_dev_dax, victim);
+	device_unlock(dev);
+	put_device(victim);
+
+	return rc;
+}
+static DEVICE_ATTR_WO(delete);
+
 static umode_t dax_region_visible(struct kobject *kobj, struct attribute *a,
 		int n)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
 	struct dax_region *dax_region = dev_get_drvdata(dev);
 
-	if (is_static(dax_region) && a == &dev_attr_available_size.attr)
-		return 0;
+	if (is_static(dax_region))
+		if (a == &dev_attr_available_size.attr
+				|| a == &dev_attr_create.attr
+				|| a == &dev_attr_seed.attr
+				|| a == &dev_attr_delete.attr)
+			return 0;
 	return a->mode;
 }
 
@@ -252,6 +472,9 @@ static struct attribute *dax_region_attributes[] = {
 	&dev_attr_available_size.attr,
 	&dev_attr_region_size.attr,
 	&dev_attr_align.attr,
+	&dev_attr_create.attr,
+	&dev_attr_seed.attr,
+	&dev_attr_delete.attr,
 	&dev_attr_id.attr,
 	NULL,
 };
@@ -320,6 +543,7 @@ struct dax_region *alloc_dax_region(struct device *parent, int region_id,
 	dax_region->align = align;
 	dax_region->dev = parent;
 	dax_region->target_node = target_node;
+	ida_init(&dax_region->ida);
 	dax_region->res = (struct resource) {
 		.start = res->start,
 		.end = res->end,
@@ -347,6 +571,15 @@ static int alloc_dev_dax_range(struct dev_dax *dev_dax, resource_size_t size)
 
 	device_lock_assert(dax_region->dev);
 
+	/* handle the seed alloc special case */
+	if (!size) {
+		dev_dax->range = (struct range) {
+			.start = res->start,
+			.end = res->start - 1,
+		};
+		return 0;
+	}
+
 	/* TODO: handle multiple allocations per region */
 	if (res->child)
 		return -ENOMEM;
@@ -448,33 +681,15 @@ static const struct attribute_group *dax_attribute_groups[] = {
 	NULL,
 };
 
-void kill_dev_dax(struct dev_dax *dev_dax)
-{
-	struct dax_device *dax_dev = dev_dax->dax_dev;
-	struct inode *inode = dax_inode(dax_dev);
-
-	kill_dax(dax_dev);
-	unmap_mapping_range(inode->i_mapping, 0, 0, 1);
-}
-EXPORT_SYMBOL_GPL(kill_dev_dax);
-
-static void free_dev_dax_range(struct dev_dax *dev_dax)
-{
-	struct dax_region *dax_region = dev_dax->region;
-	struct range *range = &dev_dax->range;
-
-	device_lock_assert(dax_region->dev);
-	__release_region(&dax_region->res, range->start, range_len(range));
-}
-
 static void dev_dax_release(struct device *dev)
 {
 	struct dev_dax *dev_dax = to_dev_dax(dev);
 	struct dax_region *dax_region = dev_dax->region;
 	struct dax_device *dax_dev = dev_dax->dax_dev;
 
-	dax_region_put(dax_region);
 	put_dax(dax_dev);
+	free_dev_dax_id(dev_dax);
+	dax_region_put(dax_region);
 	kfree(dev_dax->pgmap);
 	kfree(dev_dax);
 }
@@ -484,18 +699,6 @@ static const struct device_type dev_dax_type = {
 	.groups = dax_attribute_groups,
 };
 
-static void unregister_dev_dax(void *dev)
-{
-	struct dev_dax *dev_dax = to_dev_dax(dev);
-
-	dev_dbg(dev, "%s\n", __func__);
-
-	kill_dev_dax(dev_dax);
-	free_dev_dax_range(dev_dax);
-	device_del(dev);
-	put_device(dev);
-}
-
 struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
 {
 	struct dax_region *dax_region = data->dax_region;
@@ -506,17 +709,35 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
 	struct device *dev;
 	int rc;
 
-	if (data->id < 0)
-		return ERR_PTR(-EINVAL);
-
 	dev_dax = kzalloc(sizeof(*dev_dax), GFP_KERNEL);
 	if (!dev_dax)
 		return ERR_PTR(-ENOMEM);
 
+	if (is_static(dax_region)) {
+		if (dev_WARN_ONCE(parent, data->id < 0,
+				"dynamic id specified to static region\n")) {
+			rc = -EINVAL;
+			goto err_id;
+		}
+
+		dev_dax->id = data->id;
+	} else {
+		if (dev_WARN_ONCE(parent, data->id >= 0,
+				"static id specified to dynamic region\n")) {
+			rc = -EINVAL;
+			goto err_id;
+		}
+
+		rc = ida_alloc(&dax_region->ida, GFP_KERNEL);
+		if (rc < 0)
+			goto err_id;
+		dev_dax->id = rc;
+	}
+
 	dev_dax->region = dax_region;
 	dev = &dev_dax->dev;
 	device_initialize(dev);
-	dev_set_name(dev, "dax%d.%d", dax_region->id, data->id);
+	dev_set_name(dev, "dax%d.%d", dax_region->id, dev_dax->id);
 
 	rc = alloc_dev_dax_range(dev_dax, data->size);
 	if (rc)
@@ -579,6 +800,8 @@ err_alloc_dax:
 err_pgmap:
 	free_dev_dax_range(dev_dax);
 err_range:
+	free_dev_dax_id(dev_dax);
+err_id:
 	kfree(dev_dax);
 
 	return ERR_PTR(rc);