diff options
Diffstat (limited to 'drivers/dax')
| -rw-r--r-- | drivers/dax/bus.c | 255 | ||||
| -rw-r--r-- | drivers/dax/super.c | 17 |
2 files changed, 196 insertions, 76 deletions
diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 1ff1ab5fa1..f24b67c64d 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -12,6 +12,18 @@ 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 30 struct dax_id { struct list_head list; @@ -180,7 +192,7 @@ static u64 dev_dax_size(struct dev_dax *dev_dax) u64 size = 0; int i; - device_lock_assert(&dev_dax->dev); + lockdep_assert_held(&dax_dev_rwsem); for (i = 0; i < dev_dax->nr_range; i++) size += range_len(&dev_dax->ranges[i].range); @@ -194,8 +206,15 @@ static int dax_bus_probe(struct device *dev) struct dev_dax *dev_dax = to_dev_dax(dev); struct dax_region *dax_region = dev_dax->region; int rc; + u64 size; - if (dev_dax_size(dev_dax) == 0 || dev_dax->id < 0) + 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); @@ -222,7 +241,7 @@ static void dax_bus_remove(struct device *dev) dax_drv->remove(dev_dax); } -static struct bus_type dax_bus_type = { +static const struct bus_type dax_bus_type = { .name = "dax", .uevent = dax_bus_uevent, .match = dax_bus_match, @@ -250,7 +269,7 @@ static ssize_t id_show(struct device *dev, { struct dax_region *dax_region = dev_get_drvdata(dev); - return sprintf(buf, "%d\n", dax_region->id); + return sysfs_emit(buf, "%d\n", dax_region->id); } static DEVICE_ATTR_RO(id); @@ -259,8 +278,8 @@ static ssize_t region_size_show(struct device *dev, { struct dax_region *dax_region = dev_get_drvdata(dev); - return sprintf(buf, "%llu\n", (unsigned long long) - resource_size(&dax_region->res)); + 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); @@ -270,7 +289,7 @@ static ssize_t region_align_show(struct device *dev, { struct dax_region *dax_region = dev_get_drvdata(dev); - return sprintf(buf, "%u\n", dax_region->align); + return sysfs_emit(buf, "%u\n", dax_region->align); } static struct device_attribute dev_attr_region_align = __ATTR(align, 0400, region_align_show, NULL); @@ -283,7 +302,7 @@ 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; - device_lock_assert(dax_region->dev); + lockdep_assert_held(&dax_region_rwsem); for_each_dax_region_resource(dax_region, res) size -= resource_size(res); @@ -295,12 +314,15 @@ static ssize_t available_size_show(struct device *dev, { struct dax_region *dax_region = dev_get_drvdata(dev); unsigned long long size; + int rc; - device_lock(dev); + rc = down_read_interruptible(&dax_region_rwsem); + if (rc) + return rc; size = dax_region_avail_size(dax_region); - device_unlock(dev); + up_read(&dax_region_rwsem); - return sprintf(buf, "%llu\n", size); + return sysfs_emit(buf, "%llu\n", size); } static DEVICE_ATTR_RO(available_size); @@ -314,10 +336,12 @@ static ssize_t seed_show(struct device *dev, if (is_static(dax_region)) return -EINVAL; - device_lock(dev); + rc = down_read_interruptible(&dax_region_rwsem); + if (rc) + return rc; seed = dax_region->seed; - rc = sprintf(buf, "%s\n", seed ? dev_name(seed) : ""); - device_unlock(dev); + rc = sysfs_emit(buf, "%s\n", seed ? dev_name(seed) : ""); + up_read(&dax_region_rwsem); return rc; } @@ -333,14 +357,18 @@ static ssize_t create_show(struct device *dev, if (is_static(dax_region)) return -EINVAL; - device_lock(dev); + rc = down_read_interruptible(&dax_region_rwsem); + if (rc) + return rc; youngest = dax_region->youngest; - rc = sprintf(buf, "%s\n", youngest ? dev_name(youngest) : ""); - device_unlock(dev); + 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) { @@ -358,7 +386,9 @@ static ssize_t create_store(struct device *dev, struct device_attribute *attr, if (val != 1) return -EINVAL; - device_lock(dev); + rc = down_write_killable(&dax_region_rwsem); + if (rc) + return rc; avail = dax_region_avail_size(dax_region); if (avail == 0) rc = -ENOSPC; @@ -369,7 +399,7 @@ static ssize_t create_store(struct device *dev, struct device_attribute *attr, .id = -1, .memmap_on_memory = false, }; - struct dev_dax *dev_dax = devm_create_dev_dax(&data); + struct dev_dax *dev_dax = __devm_create_dev_dax(&data); if (IS_ERR(dev_dax)) rc = PTR_ERR(dev_dax); @@ -387,7 +417,7 @@ static ssize_t create_store(struct device *dev, struct device_attribute *attr, rc = len; } } - device_unlock(dev); + up_write(&dax_region_rwsem); return rc; } @@ -417,7 +447,7 @@ static void trim_dev_dax_range(struct dev_dax *dev_dax) struct range *range = &dev_dax->ranges[i].range; struct dax_region *dax_region = dev_dax->region; - device_lock_assert(dax_region->dev); + 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); @@ -441,10 +471,12 @@ static void unregister_dev_dax(void *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) @@ -463,11 +495,10 @@ static void dax_region_put(struct dax_region *dax_region) /* a return value >= 0 indicates this invocation invalidated the id */ static int __free_dev_dax_id(struct dev_dax *dev_dax) { - struct device *dev = &dev_dax->dev; struct dax_region *dax_region; int rc = dev_dax->id; - device_lock_assert(dev); + lockdep_assert_held_write(&dax_dev_rwsem); if (!dev_dax->dyn_id || dev_dax->id < 0) return -1; @@ -480,12 +511,13 @@ static int __free_dev_dax_id(struct dev_dax *dev_dax) static int free_dev_dax_id(struct dev_dax *dev_dax) { - struct device *dev = &dev_dax->dev; int rc; - device_lock(dev); + rc = down_write_killable(&dax_dev_rwsem); + if (rc) + return rc; rc = __free_dev_dax_id(dev_dax); - device_unlock(dev); + up_write(&dax_dev_rwsem); return rc; } @@ -522,6 +554,7 @@ static ssize_t delete_store(struct device *dev, struct device_attribute *attr, device_lock(dev); device_lock(victim); dev_dax = to_dev_dax(victim); + down_write(&dax_dev_rwsem); if (victim->driver || dev_dax_size(dev_dax)) rc = -EBUSY; else { @@ -541,6 +574,7 @@ static ssize_t delete_store(struct device *dev, struct device_attribute *attr, } else rc = -EBUSY; } + up_write(&dax_dev_rwsem); device_unlock(victim); /* won the race to invalidate the device, clean it up */ @@ -663,12 +697,9 @@ static void unregister_dax_mapping(void *data) struct device *dev = data; struct dax_mapping *mapping = to_dax_mapping(dev); struct dev_dax *dev_dax = to_dev_dax(dev->parent); - struct dax_region *dax_region = dev_dax->region; dev_dbg(dev, "%s\n", __func__); - device_lock_assert(dax_region->dev); - dev_dax->ranges[mapping->range_id].mapping = NULL; mapping->range_id = -1; @@ -679,24 +710,22 @@ static struct dev_dax_range *get_dax_range(struct device *dev) { struct dax_mapping *mapping = to_dax_mapping(dev); struct dev_dax *dev_dax = to_dev_dax(dev->parent); - struct dax_region *dax_region = dev_dax->region; + int rc; - device_lock(dax_region->dev); + rc = down_write_killable(&dax_region_rwsem); + if (rc) + return NULL; if (mapping->range_id < 0) { - device_unlock(dax_region->dev); + up_write(&dax_region_rwsem); return NULL; } return &dev_dax->ranges[mapping->range_id]; } -static void put_dax_range(struct dev_dax_range *dax_range) +static void put_dax_range(void) { - struct dax_mapping *mapping = dax_range->mapping; - struct dev_dax *dev_dax = to_dev_dax(mapping->dev.parent); - struct dax_region *dax_region = dev_dax->region; - - device_unlock(dax_region->dev); + up_write(&dax_region_rwsem); } static ssize_t start_show(struct device *dev, @@ -708,8 +737,8 @@ static ssize_t start_show(struct device *dev, dax_range = get_dax_range(dev); if (!dax_range) return -ENXIO; - rc = sprintf(buf, "%#llx\n", dax_range->range.start); - put_dax_range(dax_range); + rc = sysfs_emit(buf, "%#llx\n", dax_range->range.start); + put_dax_range(); return rc; } @@ -724,8 +753,8 @@ static ssize_t end_show(struct device *dev, dax_range = get_dax_range(dev); if (!dax_range) return -ENXIO; - rc = sprintf(buf, "%#llx\n", dax_range->range.end); - put_dax_range(dax_range); + rc = sysfs_emit(buf, "%#llx\n", dax_range->range.end); + put_dax_range(); return rc; } @@ -740,8 +769,8 @@ static ssize_t pgoff_show(struct device *dev, dax_range = get_dax_range(dev); if (!dax_range) return -ENXIO; - rc = sprintf(buf, "%#lx\n", dax_range->pgoff); - put_dax_range(dax_range); + rc = sysfs_emit(buf, "%#lx\n", dax_range->pgoff); + put_dax_range(); return rc; } @@ -775,7 +804,7 @@ static int devm_register_dax_mapping(struct dev_dax *dev_dax, int range_id) struct device *dev; int rc; - device_lock_assert(dax_region->dev); + lockdep_assert_held_write(&dax_region_rwsem); if (dev_WARN_ONCE(&dev_dax->dev, !dax_region->dev->driver, "region disabled\n")) @@ -821,7 +850,7 @@ static int alloc_dev_dax_range(struct dev_dax *dev_dax, u64 start, struct resource *alloc; int i, rc; - device_lock_assert(dax_region->dev); + lockdep_assert_held_write(&dax_region_rwsem); /* handle the seed alloc special case */ if (!size) { @@ -875,13 +904,12 @@ static int adjust_dev_dax_range(struct dev_dax *dev_dax, struct resource *res, r { int last_range = dev_dax->nr_range - 1; struct dev_dax_range *dax_range = &dev_dax->ranges[last_range]; - struct dax_region *dax_region = dev_dax->region; bool is_shrink = resource_size(res) > size; struct range *range = &dax_range->range; struct device *dev = &dev_dax->dev; int rc; - device_lock_assert(dax_region->dev); + lockdep_assert_held_write(&dax_region_rwsem); if (dev_WARN_ONCE(dev, !size, "deletion is handled by dev_dax_shrink\n")) return -EINVAL; @@ -907,12 +935,15 @@ static ssize_t size_show(struct device *dev, { struct dev_dax *dev_dax = to_dev_dax(dev); unsigned long long size; + int rc; - device_lock(dev); + rc = down_read_interruptible(&dax_dev_rwsem); + if (rc) + return rc; size = dev_dax_size(dev_dax); - device_unlock(dev); + up_read(&dax_dev_rwsem); - return sprintf(buf, "%llu\n", size); + return sysfs_emit(buf, "%llu\n", size); } static bool alloc_is_aligned(struct dev_dax *dev_dax, resource_size_t size) @@ -1080,17 +1111,27 @@ static ssize_t size_store(struct device *dev, struct device_attribute *attr, return -EINVAL; } - device_lock(dax_region->dev); + rc = down_write_killable(&dax_region_rwsem); + if (rc) + return rc; if (!dax_region->dev->driver) { - device_unlock(dax_region->dev); - return -ENXIO; + rc = -ENXIO; + goto err_region; } - device_lock(dev); + rc = down_write_killable(&dax_dev_rwsem); + if (rc) + goto err_dev; + rc = dev_dax_resize(dax_region, dev_dax, val); - device_unlock(dev); - device_unlock(dax_region->dev); - return rc == 0 ? len : rc; +err_dev: + up_write(&dax_dev_rwsem); +err_region: + up_write(&dax_region_rwsem); + + if (rc == 0) + return len; + return rc; } static DEVICE_ATTR_RW(size); @@ -1138,18 +1179,24 @@ static ssize_t mapping_store(struct device *dev, struct device_attribute *attr, return rc; rc = -ENXIO; - device_lock(dax_region->dev); + rc = down_write_killable(&dax_region_rwsem); + if (rc) + return rc; if (!dax_region->dev->driver) { - device_unlock(dax_region->dev); + up_write(&dax_region_rwsem); + return rc; + } + rc = down_write_killable(&dax_dev_rwsem); + if (rc) { + up_write(&dax_region_rwsem); return rc; } - device_lock(dev); to_alloc = range_len(&r); if (alloc_is_aligned(dev_dax, to_alloc)) rc = alloc_dev_dax_range(dev_dax, r.start, to_alloc); - device_unlock(dev); - device_unlock(dax_region->dev); + up_write(&dax_dev_rwsem); + up_write(&dax_region_rwsem); return rc == 0 ? len : rc; } @@ -1160,7 +1207,7 @@ static ssize_t align_show(struct device *dev, { struct dev_dax *dev_dax = to_dev_dax(dev); - return sprintf(buf, "%d\n", dev_dax->align); + return sysfs_emit(buf, "%d\n", dev_dax->align); } static ssize_t dev_dax_validate_align(struct dev_dax *dev_dax) @@ -1196,13 +1243,19 @@ static ssize_t align_store(struct device *dev, struct device_attribute *attr, if (!dax_align_valid(val)) return -EINVAL; - device_lock(dax_region->dev); + rc = down_write_killable(&dax_region_rwsem); + if (rc) + return rc; if (!dax_region->dev->driver) { - device_unlock(dax_region->dev); + up_write(&dax_region_rwsem); return -ENXIO; } - device_lock(dev); + rc = down_write_killable(&dax_dev_rwsem); + if (rc) { + up_write(&dax_region_rwsem); + return rc; + } if (dev->driver) { rc = -EBUSY; goto out_unlock; @@ -1214,8 +1267,8 @@ static ssize_t align_store(struct device *dev, struct device_attribute *attr, if (rc) dev_dax->align = align_save; out_unlock: - device_unlock(dev); - device_unlock(dax_region->dev); + up_write(&dax_dev_rwsem); + up_write(&dax_region_rwsem); return rc == 0 ? len : rc; } static DEVICE_ATTR_RW(align); @@ -1232,7 +1285,7 @@ static ssize_t target_node_show(struct device *dev, { struct dev_dax *dev_dax = to_dev_dax(dev); - return sprintf(buf, "%d\n", dev_dax_target_node(dev_dax)); + return sysfs_emit(buf, "%d\n", dev_dax_target_node(dev_dax)); } static DEVICE_ATTR_RO(target_node); @@ -1248,7 +1301,7 @@ static ssize_t resource_show(struct device *dev, else start = dev_dax->ranges[0].range.start; - return sprintf(buf, "%#llx\n", start); + return sysfs_emit(buf, "%#llx\n", start); } static DEVICE_ATTR(resource, 0400, resource_show, NULL); @@ -1259,17 +1312,59 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, * We only ever expect to handle device-dax instances, i.e. the * @type argument to MODULE_ALIAS_DAX_DEVICE() is always zero */ - return sprintf(buf, DAX_DEVICE_MODALIAS_FMT "\n", 0); + return sysfs_emit(buf, DAX_DEVICE_MODALIAS_FMT "\n", 0); } static DEVICE_ATTR_RO(modalias); static ssize_t numa_node_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", dev_to_node(dev)); + return sysfs_emit(buf, "%d\n", dev_to_node(dev)); } static DEVICE_ATTR_RO(numa_node); +static ssize_t memmap_on_memory_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct dev_dax *dev_dax = to_dev_dax(dev); + + return sysfs_emit(buf, "%d\n", dev_dax->memmap_on_memory); +} + +static ssize_t memmap_on_memory_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct dev_dax *dev_dax = to_dev_dax(dev); + bool val; + int rc; + + rc = kstrtobool(buf, &val); + if (rc) + return rc; + + if (val == true && !mhp_supports_memmap_on_memory()) { + dev_dbg(dev, "memmap_on_memory is not available\n"); + return -EOPNOTSUPP; + } + + rc = down_write_killable(&dax_dev_rwsem); + if (rc) + return rc; + + if (dev_dax->memmap_on_memory != val && dev->driver && + to_dax_drv(dev->driver)->type == DAXDRV_KMEM_TYPE) { + up_write(&dax_dev_rwsem); + return -EBUSY; + } + + dev_dax->memmap_on_memory = val; + up_write(&dax_dev_rwsem); + + return len; +} +static DEVICE_ATTR_RW(memmap_on_memory); + static umode_t dev_dax_visible(struct kobject *kobj, struct attribute *a, int n) { struct device *dev = container_of(kobj, struct device, kobj); @@ -1296,6 +1391,7 @@ static struct attribute *dev_dax_attributes[] = { &dev_attr_align.attr, &dev_attr_resource.attr, &dev_attr_numa_node.attr, + &dev_attr_memmap_on_memory.attr, NULL, }; @@ -1325,7 +1421,7 @@ static const struct device_type dev_dax_type = { .groups = dax_attribute_groups, }; -struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data) +static struct dev_dax *__devm_create_dev_dax(struct dev_dax_data *data) { struct dax_region *dax_region = data->dax_region; struct device *parent = dax_region->dev; @@ -1440,6 +1536,17 @@ err_id: return ERR_PTR(rc); } + +struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data) +{ + struct dev_dax *dev_dax; + + down_write(&dax_region_rwsem); + dev_dax = __devm_create_dev_dax(data); + up_write(&dax_region_rwsem); + + return dev_dax; +} EXPORT_SYMBOL_GPL(devm_create_dev_dax); int __dax_driver_register(struct dax_device_driver *dax_drv, diff --git a/drivers/dax/super.c b/drivers/dax/super.c index f4b6355263..aca71d7fcc 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -13,6 +13,7 @@ #include <linux/uio.h> #include <linux/dax.h> #include <linux/fs.h> +#include <linux/cacheinfo.h> #include "dax-private.h" /** @@ -319,6 +320,11 @@ EXPORT_SYMBOL_GPL(dax_alive); * that any fault handlers or operations that might have seen * dax_alive(), have completed. Any operations that start after * synchronize_srcu() has run will abort upon seeing !dax_alive(). + * + * Note, because alloc_dax() returns an ERR_PTR() on error, callers + * typically store its result into a local variable in order to check + * the result. Therefore, care must be taken to populate the struct + * device dax_dev field make sure the dax_dev is not leaked. */ void kill_dax(struct dax_device *dax_dev) { @@ -446,6 +452,14 @@ struct dax_device *alloc_dax(void *private, const struct dax_operations *ops) dev_t devt; int minor; + /* + * Unavailable on architectures with virtually aliased data caches, + * except for device-dax (NULL operations pointer), which does + * not use aliased mappings from the kernel. + */ + if (ops && cpu_dcache_is_aliasing()) + return ERR_PTR(-EOPNOTSUPP); + if (WARN_ON_ONCE(ops && !ops->zero_page_range)) return ERR_PTR(-EINVAL); @@ -532,8 +546,7 @@ static int dax_fs_init(void) int rc; dax_cache = kmem_cache_create("dax_cache", sizeof(struct dax_device), 0, - (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD|SLAB_ACCOUNT), + SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, init_once); if (!dax_cache) return -ENOMEM; |