1625 lines · 38.4 KB · C
RawDownload
// SPDX-License-Identifier: GPL-2.0/* Copyright(c) 2017-2018 Intel Corporation. All rights reserved. */#include <linux/memremap.h>#include <linux/device.h>#include <linux/mutex.h>#include <linux/list.h>#include <linux/slab.h>#include <linux/dax.h>#include <linux/io.h>#include "dax-private.h"#include "bus.h" static struct resource dax_regions = DEFINE_RES_MEM_NAMED(0, -1, "DAX Regions");static DEFINE_MUTEX(dax_bus_lock); /* * All changes to the dax region configuration occur with this lock held * for write. */DECLARE_RWSEM(dax_region_rwsem); /* * All changes to the dax device configuration occur with this lock held * for write. */DECLARE_RWSEM(dax_dev_rwsem); #define DAX_NAME_LEN 30struct dax_id {	struct list_head list;	char dev_name[DAX_NAME_LEN];}; static int dax_bus_uevent(const struct device *dev, struct kobj_uevent_env *env){	/*	 * We only ever expect to handle device-dax instances, i.e. the	 * @type argument to MODULE_ALIAS_DAX_DEVICE() is always zero	 */	return add_uevent_var(env, "MODALIAS=" DAX_DEVICE_MODALIAS_FMT, 0);} static struct dax_id *__dax_match_id(const struct dax_device_driver *dax_drv,		const char *dev_name){	struct dax_id *dax_id; 	lockdep_assert_held(&dax_bus_lock); 	list_for_each_entry(dax_id, &dax_drv->ids, list)		if (sysfs_streq(dax_id->dev_name, dev_name))			return dax_id;	return NULL;} static int dax_match_id(const struct dax_device_driver *dax_drv, struct device *dev){	int match; 	mutex_lock(&dax_bus_lock);	match = !!__dax_match_id(dax_drv, dev_name(dev));	mutex_unlock(&dax_bus_lock); 	return match;} static int dax_match_type(const struct dax_device_driver *dax_drv, struct device *dev){	enum dax_driver_type type = DAXDRV_DEVICE_TYPE;	struct dev_dax *dev_dax = to_dev_dax(dev); 	if (dev_dax->region->res.flags & IORESOURCE_DAX_KMEM)		type = DAXDRV_KMEM_TYPE; 	if (dax_drv->type == type)		return 1; 	/* default to device mode if dax_kmem is disabled */	if (dax_drv->type == DAXDRV_DEVICE_TYPE &&	    !IS_ENABLED(CONFIG_DEV_DAX_KMEM))		return 1; 	return 0;} enum id_action {	ID_REMOVE,	ID_ADD,}; static ssize_t do_id_store(struct device_driver *drv, const char *buf,		size_t count, enum id_action action){	struct dax_device_driver *dax_drv = to_dax_drv(drv);	unsigned int region_id, id;	char devname[DAX_NAME_LEN];	struct dax_id *dax_id;	ssize_t rc = count;	int fields; 	fields = sscanf(buf, "dax%d.%d", &region_id, &id);	if (fields != 2)		return -EINVAL;	sprintf(devname, "dax%d.%d", region_id, id);	if (!sysfs_streq(buf, devname))		return -EINVAL; 	mutex_lock(&dax_bus_lock);	dax_id = __dax_match_id(dax_drv, buf);	if (!dax_id) {		if (action == ID_ADD) {			dax_id = kzalloc_obj(*dax_id);			if (dax_id) {				strscpy(dax_id->dev_name, buf, DAX_NAME_LEN);				list_add(&dax_id->list, &dax_drv->ids);			} else				rc = -ENOMEM;		}	} else if (action == ID_REMOVE) {		list_del(&dax_id->list);		kfree(dax_id);	}	mutex_unlock(&dax_bus_lock); 	if (rc < 0)		return rc;	if (action == ID_ADD)		rc = driver_attach(drv);	if (rc)		return rc;	return count;} static ssize_t new_id_store(struct device_driver *drv, const char *buf,		size_t count){	return do_id_store(drv, buf, count, ID_ADD);}static DRIVER_ATTR_WO(new_id); static ssize_t remove_id_store(struct device_driver *drv, const char *buf,		size_t count){	return do_id_store(drv, buf, count, ID_REMOVE);}static DRIVER_ATTR_WO(remove_id); static struct attribute *dax_drv_attrs[] = {	&driver_attr_new_id.attr,	&driver_attr_remove_id.attr,	NULL,};ATTRIBUTE_GROUPS(dax_drv); static int dax_bus_match(struct device *dev, const struct device_driver *drv); /* * Static dax regions are regions created by an external subsystem * nvdimm where a single range is assigned. Its boundaries are by the external * subsystem and are usually limited to one physical memory range. For example, * for PMEM it is usually defined by NVDIMM Namespace boundaries (i.e. a * single contiguous range) * * On dynamic dax regions, the assigned region can be partitioned by dax core * into multiple subdivisions. A subdivision is represented into one * /dev/daxN.M device composed by one or more potentially discontiguous ranges. * * When allocating a dax region, drivers must set whether it's static * (IORESOURCE_DAX_STATIC).  On static dax devices, the @pgmap is pre-assigned * to dax core when calling devm_create_dev_dax(), whereas in dynamic dax * devices it is NULL but afterwards allocated by dax core on device ->probe(). * Care is needed to make sure that dynamic dax devices are torn down with a * cleared @pgmap field (see kill_dev_dax()). */static bool is_static(struct dax_region *dax_region){	return (dax_region->res.flags & IORESOURCE_DAX_STATIC) != 0;} bool static_dev_dax(struct dev_dax *dev_dax){	return is_static(dev_dax->region);}EXPORT_SYMBOL_GPL(static_dev_dax); static u64 dev_dax_size(struct dev_dax *dev_dax){	u64 size = 0;	int i; 	lockdep_assert_held(&dax_dev_rwsem); 	for (i = 0; i < dev_dax->nr_range; i++)		size += range_len(&dev_dax->ranges[i].range); 	return size;} 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;	int rc;	u64 size; 	rc = down_read_interruptible(&dax_dev_rwsem);	if (rc)		return rc;	size = dev_dax_size(dev_dax);	up_read(&dax_dev_rwsem); 	if (size == 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 0;} static void dax_bus_remove(struct device *dev){	struct dax_device_driver *dax_drv = to_dax_drv(dev->driver);	struct dev_dax *dev_dax = to_dev_dax(dev); 	if (dax_drv->remove)		dax_drv->remove(dev_dax);} static const struct bus_type dax_bus_type = {	.name = "dax",	.uevent = dax_bus_uevent,	.match = dax_bus_match,	.probe = dax_bus_probe,	.remove = dax_bus_remove,	.drv_groups = dax_drv_groups,}; static int dax_bus_match(struct device *dev, const struct device_driver *drv){	const struct dax_device_driver *dax_drv = to_dax_drv(drv); 	if (dax_match_id(dax_drv, dev))		return 1;	return dax_match_type(dax_drv, dev);} /* * Rely on the fact that drvdata is set before the attributes are * registered, and that the attributes are unregistered before drvdata * is cleared to assume that drvdata is always valid. */static ssize_t id_show(struct device *dev,		struct device_attribute *attr, char *buf){	struct dax_region *dax_region = dev_get_drvdata(dev); 	return sysfs_emit(buf, "%d\n", dax_region->id);}static DEVICE_ATTR_RO(id); static ssize_t region_size_show(struct device *dev,		struct device_attribute *attr, char *buf){	struct dax_region *dax_region = dev_get_drvdata(dev); 	return sysfs_emit(buf, "%llu\n",			  (unsigned long long)resource_size(&dax_region->res));}static struct device_attribute dev_attr_region_size = __ATTR(size, 0444,		region_size_show, NULL); static ssize_t region_align_show(struct device *dev,		struct device_attribute *attr, char *buf){	struct dax_region *dax_region = dev_get_drvdata(dev); 	return sysfs_emit(buf, "%u\n", dax_region->align);}static struct device_attribute dev_attr_region_align =		__ATTR(align, 0400, region_align_show, NULL); #define for_each_dax_region_resource(dax_region, res) \	for (res = (dax_region)->res.child; res; res = res->sibling) static unsigned long long dax_region_avail_size(struct dax_region *dax_region){	resource_size_t size = resource_size(&dax_region->res);	struct resource *res; 	lockdep_assert_held(&dax_region_rwsem); 	for_each_dax_region_resource(dax_region, res)		size -= resource_size(res);	return size;} static ssize_t available_size_show(struct device *dev,		struct device_attribute *attr, char *buf){	struct dax_region *dax_region = dev_get_drvdata(dev);	unsigned long long size;	int rc; 	rc = down_read_interruptible(&dax_region_rwsem);	if (rc)		return rc;	size = dax_region_avail_size(dax_region);	up_read(&dax_region_rwsem); 	return sysfs_emit(buf, "%llu\n", size);}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; 	rc = down_read_interruptible(&dax_region_rwsem);	if (rc)		return rc;	seed = dax_region->seed;	rc = sysfs_emit(buf, "%s\n", seed ? dev_name(seed) : "");	up_read(&dax_region_rwsem); 	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; 	rc = down_read_interruptible(&dax_region_rwsem);	if (rc)		return rc;	youngest = dax_region->youngest;	rc = sysfs_emit(buf, "%s\n", youngest ? dev_name(youngest) : "");	up_read(&dax_region_rwsem); 	return rc;} static struct dev_dax *__devm_create_dev_dax(struct dev_dax_data *data); 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; 	rc = down_write_killable(&dax_region_rwsem);	if (rc)		return rc;	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,			.memmap_on_memory = false,		};		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;		}	}	up_write(&dax_region_rwsem); 	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); 	/*	 * Dynamic dax region have the pgmap allocated via dev_kzalloc()	 * and thus freed by devm. Clear the pgmap to not have stale pgmap	 * ranges on probe() from previous reconfigurations of region devices.	 */	if (!static_dev_dax(dev_dax))		dev_dax->pgmap = NULL;}EXPORT_SYMBOL_GPL(kill_dev_dax); static void trim_dev_dax_range(struct dev_dax *dev_dax){	int i = dev_dax->nr_range - 1;	struct range *range = &dev_dax->ranges[i].range;	struct dax_region *dax_region = dev_dax->region; 	lockdep_assert_held_write(&dax_region_rwsem);	dev_dbg(&dev_dax->dev, "delete range[%d]: %#llx:%#llx\n", i,		(unsigned long long)range->start,		(unsigned long long)range->end); 	__release_region(&dax_region->res, range->start, range_len(range));	if (--dev_dax->nr_range == 0) {		kfree(dev_dax->ranges);		dev_dax->ranges = NULL;	}} static void free_dev_dax_ranges(struct dev_dax *dev_dax){	while (dev_dax->nr_range)		trim_dev_dax_range(dev_dax);} static void unregister_dev_dax(void *dev){	struct dev_dax *dev_dax = to_dev_dax(dev); 	dev_dbg(dev, "%s\n", __func__); 	down_write(&dax_region_rwsem);	kill_dev_dax(dev_dax);	device_del(dev);	free_dev_dax_ranges(dev_dax);	put_device(dev);	up_write(&dax_region_rwsem);} static void dax_region_free(struct kref *kref){	struct dax_region *dax_region; 	dax_region = container_of(kref, struct dax_region, kref);	kfree(dax_region);} static void dax_region_put(struct dax_region *dax_region){	kref_put(&dax_region->kref, dax_region_free);} /* 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;	int rc = dev_dax->id; 	lockdep_assert_held_write(&dax_dev_rwsem); 	if (!dev_dax->dyn_id || dev_dax->id < 0)		return -1;

Lines 1–500 of 1625.