From c05ae9d85b47211edb187b854b62ec68fb2a1e93 Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Wed, 24 Jan 2024 12:03:46 -0800 Subject: dax/bus.c: replace driver-core lock usage by a local rwsem Patch series "Add DAX ABI for memmap_on_memory", v7. This series adds sysfs ABI to control memmap_on_memory behavior for DAX devices. Patch 1 replaces incorrect device_lock() usage with a local rwsem - this was identified during review. Patch 2 is also a preparatory patch that replaces sprintf() for sysfs operations with sysfs_emit() Patch 3 adds the missing documentation for the sysfs ABI for DAX regions and Dax devices. Patch 4 exports mhp_supports_memmap_on_memory(). Patch 5 adds the new ABI for toggling memmap_on_memory semantics for dax devices. This patch (of 5): The dax driver incorrectly used driver-core device locks to protect internal dax region and dax device configuration structures. Replace the device lock usage with a local rwsem, one each for dax region configuration and dax device configuration. As a result of this conversion, no device_lock() usage remains in dax/bus.c. Link: https://lkml.kernel.org/r/20240124-vv-dax_abi-v7-0-20d16cb8d23d@intel.com Link: https://lkml.kernel.org/r/20240124-vv-dax_abi-v7-1-20d16cb8d23d@intel.com Signed-off-by: Vishal Verma Reported-by: Greg Kroah-Hartman Reviewed-by: Alison Schofield Cc: Dan Williams Cc: Dave Hansen Cc: Dave Jiang Cc: David Hildenbrand Cc: Huang Ying Cc: Jonathan Cameron Cc: Li Zhijian Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Oscar Salvador Signed-off-by: Andrew Morton --- drivers/dax/bus.c | 218 ++++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 156 insertions(+), 62 deletions(-) (limited to 'drivers/dax') diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 1ff1ab5fa105..cb148f74ceda 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); + WARN_ON_ONCE(!rwsem_is_locked(&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); @@ -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); + WARN_ON_ONCE(!rwsem_is_locked(&dax_region_rwsem)); for_each_dax_region_resource(dax_region, res) size -= resource_size(res); @@ -295,10 +314,13 @@ 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); } @@ -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); + 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); + 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); + WARN_ON_ONCE(!rwsem_is_locked(&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); @@ -435,7 +465,7 @@ static void free_dev_dax_ranges(struct dev_dax *dev_dax) trim_dev_dax_range(dev_dax); } -static void unregister_dev_dax(void *dev) +static void __unregister_dev_dax(void *dev) { struct dev_dax *dev_dax = to_dev_dax(dev); @@ -447,6 +477,17 @@ static void unregister_dev_dax(void *dev) put_device(dev); } +static void unregister_dev_dax(void *dev) +{ + if (rwsem_is_locked(&dax_region_rwsem)) + return __unregister_dev_dax(dev); + + if (WARN_ON_ONCE(down_write_killable(&dax_region_rwsem) != 0)) + return; + __unregister_dev_dax(dev); + up_write(&dax_region_rwsem); +} + static void dax_region_free(struct kref *kref) { struct dax_region *dax_region; @@ -463,11 +504,10 @@ 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); + WARN_ON_ONCE(!rwsem_is_locked(&dax_dev_rwsem)); if (!dev_dax->dyn_id || dev_dax->id < 0) return -1; @@ -480,12 +520,13 @@ 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; } @@ -519,8 +560,14 @@ static ssize_t delete_store(struct device *dev, struct device_attribute *attr, if (!victim) return -ENXIO; - device_lock(dev); - device_lock(victim); + rc = down_write_killable(&dax_region_rwsem); + if (rc) + return rc; + rc = down_write_killable(&dax_dev_rwsem); + if (rc) { + up_write(&dax_region_rwsem); + return rc; + } dev_dax = to_dev_dax(victim); if (victim->driver || dev_dax_size(dev_dax)) rc = -EBUSY; @@ -541,12 +588,12 @@ static ssize_t delete_store(struct device *dev, struct device_attribute *attr, } else rc = -EBUSY; } - device_unlock(victim); + up_write(&dax_dev_rwsem); /* won the race to invalidate the device, clean it up */ if (do_del) devm_release_action(dev, unregister_dev_dax, victim); - device_unlock(dev); + up_write(&dax_region_rwsem); put_device(victim); return rc; @@ -658,16 +705,15 @@ static void dax_mapping_release(struct device *dev) put_device(parent); } -static void unregister_dax_mapping(void *data) +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); + WARN_ON_ONCE(!rwsem_is_locked(&dax_region_rwsem)); dev_dax->ranges[mapping->range_id].mapping = NULL; mapping->range_id = -1; @@ -675,28 +721,37 @@ static void unregister_dax_mapping(void *data) device_unregister(dev); } +static void unregister_dax_mapping(void *data) +{ + if (rwsem_is_locked(&dax_region_rwsem)) + return __unregister_dax_mapping(data); + + if (WARN_ON_ONCE(down_write_killable(&dax_region_rwsem) != 0)) + return; + __unregister_dax_mapping(data); + up_write(&dax_region_rwsem); +} + 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, @@ -709,7 +764,7 @@ static ssize_t start_show(struct device *dev, if (!dax_range) return -ENXIO; rc = sprintf(buf, "%#llx\n", dax_range->range.start); - put_dax_range(dax_range); + put_dax_range(); return rc; } @@ -725,7 +780,7 @@ static ssize_t end_show(struct device *dev, if (!dax_range) return -ENXIO; rc = sprintf(buf, "%#llx\n", dax_range->range.end); - put_dax_range(dax_range); + put_dax_range(); return rc; } @@ -741,7 +796,7 @@ static ssize_t pgoff_show(struct device *dev, if (!dax_range) return -ENXIO; rc = sprintf(buf, "%#lx\n", dax_range->pgoff); - put_dax_range(dax_range); + put_dax_range(); return rc; } @@ -775,7 +830,7 @@ 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); + WARN_ON_ONCE(!rwsem_is_locked(&dax_region_rwsem)); if (dev_WARN_ONCE(&dev_dax->dev, !dax_region->dev->driver, "region disabled\n")) @@ -821,7 +876,7 @@ 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); + WARN_ON_ONCE(!rwsem_is_locked(&dax_region_rwsem)); /* handle the seed alloc special case */ if (!size) { @@ -875,13 +930,12 @@ 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); + WARN_ON_ONCE(!rwsem_is_locked(&dax_region_rwsem)); if (dev_WARN_ONCE(dev, !size, "deletion is handled by dev_dax_shrink\n")) return -EINVAL; @@ -907,10 +961,13 @@ 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_write_killable(&dax_dev_rwsem); + if (rc) + return rc; size = dev_dax_size(dev_dax); - device_unlock(dev); + up_write(&dax_dev_rwsem); return sprintf(buf, "%llu\n", size); } @@ -1080,17 +1137,27 @@ 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 +1205,24 @@ 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; } @@ -1196,13 +1269,19 @@ 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 +1293,8 @@ 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); @@ -1325,7 +1404,7 @@ 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 +1519,21 @@ err_id: return ERR_PTR(rc); } + +struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data) +{ + struct dev_dax *dev_dax; + int rc; + + rc = down_write_killable(&dax_region_rwsem); + if (rc) + return ERR_PTR(rc); + + 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, -- cgit v1.2.3-70-g09d2 From 6ebed0007f082cd80a63a8849c54e7cad0069469 Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Wed, 24 Jan 2024 12:03:47 -0800 Subject: dax/bus.c: replace several sprintf() with sysfs_emit() There were several places where drivers/dax/bus.c uses 'sprintf' to print sysfs data. Since a sysfs_emit() helper is available specifically for this purpose, replace all the sprintf() usage for sysfs with sysfs_emit() in this file. Link: https://lkml.kernel.org/r/20240124-vv-dax_abi-v7-2-20d16cb8d23d@intel.com Signed-off-by: Vishal Verma Reported-by: Greg Kroah-Hartman Reviewed-by: Alison Schofield Cc: Dan Williams Cc: Dave Hansen Cc: Dave Jiang Cc: David Hildenbrand Cc: Huang Ying Cc: Jonathan Cameron Cc: Li Zhijian Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Oscar Salvador Signed-off-by: Andrew Morton --- drivers/dax/bus.c | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) (limited to 'drivers/dax') diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index cb148f74ceda..0fd948a4443e 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -269,7 +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); @@ -278,8 +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); @@ -289,7 +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); @@ -322,7 +322,7 @@ static ssize_t available_size_show(struct device *dev, size = dax_region_avail_size(dax_region); up_read(&dax_region_rwsem); - return sprintf(buf, "%llu\n", size); + return sysfs_emit(buf, "%llu\n", size); } static DEVICE_ATTR_RO(available_size); @@ -340,7 +340,7 @@ static ssize_t seed_show(struct device *dev, if (rc) return rc; seed = dax_region->seed; - rc = sprintf(buf, "%s\n", seed ? dev_name(seed) : ""); + rc = sysfs_emit(buf, "%s\n", seed ? dev_name(seed) : ""); up_read(&dax_region_rwsem); return rc; @@ -361,7 +361,7 @@ static ssize_t create_show(struct device *dev, if (rc) return rc; youngest = dax_region->youngest; - rc = sprintf(buf, "%s\n", youngest ? dev_name(youngest) : ""); + rc = sysfs_emit(buf, "%s\n", youngest ? dev_name(youngest) : ""); up_read(&dax_region_rwsem); return rc; @@ -763,7 +763,7 @@ 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); + rc = sysfs_emit(buf, "%#llx\n", dax_range->range.start); put_dax_range(); return rc; @@ -779,7 +779,7 @@ 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); + rc = sysfs_emit(buf, "%#llx\n", dax_range->range.end); put_dax_range(); return rc; @@ -795,7 +795,7 @@ 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); + rc = sysfs_emit(buf, "%#lx\n", dax_range->pgoff); put_dax_range(); return rc; @@ -969,7 +969,7 @@ static ssize_t size_show(struct device *dev, size = dev_dax_size(dev_dax); up_write(&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) @@ -1233,7 +1233,7 @@ 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) @@ -1311,7 +1311,7 @@ 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); @@ -1327,7 +1327,7 @@ 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); @@ -1338,14 +1338,14 @@ 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); -- cgit v1.2.3-70-g09d2 From 73954d379efd176e9b011142c55aa8da93ac740a Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Wed, 24 Jan 2024 12:03:50 -0800 Subject: dax: add a sysfs knob to control memmap_on_memory behavior Add a sysfs knob for dax devices to control the memmap_on_memory setting if the dax device were to be hotplugged as system memory. The default memmap_on_memory setting for dax devices originating via pmem or hmem is set to 'false' - i.e. no memmap_on_memory semantics, to preserve legacy behavior. For dax devices via CXL, the default is on. The sysfs control allows the administrator to override the above defaults if needed. Link: https://lkml.kernel.org/r/20240124-vv-dax_abi-v7-5-20d16cb8d23d@intel.com Signed-off-by: Vishal Verma Tested-by: Li Zhijian Reviewed-by: Jonathan Cameron Reviewed-by: David Hildenbrand Reviewed-by: Huang, Ying Reviewed-by: Alison Schofield Cc: Dan Williams Cc: Dave Jiang Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Oscar Salvador Signed-off-by: Andrew Morton --- Documentation/ABI/testing/sysfs-bus-dax | 17 +++++++++++++ drivers/dax/bus.c | 43 +++++++++++++++++++++++++++++++++ 2 files changed, 60 insertions(+) (limited to 'drivers/dax') diff --git a/Documentation/ABI/testing/sysfs-bus-dax b/Documentation/ABI/testing/sysfs-bus-dax index 6359f7bc9bf4..b34266bfae49 100644 --- a/Documentation/ABI/testing/sysfs-bus-dax +++ b/Documentation/ABI/testing/sysfs-bus-dax @@ -134,3 +134,20 @@ KernelVersion: v5.1 Contact: nvdimm@lists.linux.dev Description: (RO) The id attribute indicates the region id of a dax region. + +What: /sys/bus/dax/devices/daxX.Y/memmap_on_memory +Date: January, 2024 +KernelVersion: v6.8 +Contact: nvdimm@lists.linux.dev +Description: + (RW) Control the memmap_on_memory setting if the dax device + were to be hotplugged as system memory. This determines whether + the 'altmap' for the hotplugged memory will be placed on the + device being hotplugged (memmap_on_memory=1) or if it will be + placed on regular memory (memmap_on_memory=0). This attribute + must be set before the device is handed over to the 'kmem' + driver (i.e. hotplugged into system-ram). Additionally, this + depends on CONFIG_MHP_MEMMAP_ON_MEMORY, and a globally enabled + memmap_on_memory parameter for memory_hotplug. This is + typically set on the kernel command line - + memory_hotplug.memmap_on_memory set to 'true' or 'force'." diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 0fd948a4443e..27c86d0ca711 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -1349,6 +1349,48 @@ static ssize_t numa_node_show(struct device *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); @@ -1375,6 +1417,7 @@ 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, }; -- cgit v1.2.3-70-g09d2 From 6d439c18d9b190ab1e0f1196bc45590f95752bf1 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Thu, 15 Feb 2024 09:46:26 -0500 Subject: dax: alloc_dax() return ERR_PTR(-EOPNOTSUPP) for CONFIG_DAX=n Change the return value from NULL to PTR_ERR(-EOPNOTSUPP) for CONFIG_DAX=n to be consistent with the fact that CONFIG_DAX=y never returns NULL. This is done in preparation for using cpu_dcache_is_aliasing() in a following change which will properly support architectures which detect data cache aliasing at runtime. Link: https://lkml.kernel.org/r/20240215144633.96437-3-mathieu.desnoyers@efficios.com Fixes: 4e4ced93794a ("dax: Move mandatory ->zero_page_range() check in alloc_dax()") Signed-off-by: Mathieu Desnoyers Reviewed-by: Dan Williams Cc: Dan Williams Cc: Vishal Verma Cc: Dave Jiang Cc: Matthew Wilcox Cc: Arnd Bergmann Cc: Russell King Cc: Alasdair Kergon Cc: Christoph Hellwig Cc: Dave Chinner Cc: Heiko Carstens Cc: kernel test robot Cc: Michael Sclafani Cc: Mike Snitzer Cc: Mikulas Patocka Signed-off-by: Andrew Morton --- drivers/dax/super.c | 5 +++++ include/linux/dax.h | 6 +----- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'drivers/dax') diff --git a/drivers/dax/super.c b/drivers/dax/super.c index f4b635526345..97ef2a9d878d 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -319,6 +319,11 @@ 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) { diff --git a/include/linux/dax.h b/include/linux/dax.h index e3ffe7c7f01d..9d3e3327af4c 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -88,11 +88,7 @@ static inline void *dax_holder(struct dax_device *dax_dev) static inline struct dax_device *alloc_dax(void *private, const struct dax_operations *ops) { - /* - * Callers should check IS_ENABLED(CONFIG_DAX) to know if this - * NULL is an error or expected. - */ - return NULL; + return ERR_PTR(-EOPNOTSUPP); } static inline void put_dax(struct dax_device *dax_dev) { -- cgit v1.2.3-70-g09d2 From 1df4ca0155acb37b9b1d03ab91323d70a309ff54 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Thu, 15 Feb 2024 09:46:31 -0500 Subject: dax: check for data cache aliasing at runtime Replace the following fs/Kconfig:FS_DAX dependency: depends on !(ARM || MIPS || SPARC) By a runtime check within alloc_dax(). This runtime check returns ERR_PTR(-EOPNOTSUPP) if the @ops parameter is non-NULL (which means the kernel is using an aliased mapping) on an architecture which has data cache aliasing. Change the return value from NULL to PTR_ERR(-EOPNOTSUPP) for CONFIG_DAX=n for consistency. This is done in preparation for using cpu_dcache_is_aliasing() in a following change which will properly support architectures which detect data cache aliasing at runtime. Link: https://lkml.kernel.org/r/20240215144633.96437-8-mathieu.desnoyers@efficios.com Fixes: d92576f1167c ("dax: does not work correctly with virtual aliasing caches") Signed-off-by: Mathieu Desnoyers Reviewed-by: Dan Williams Cc: Dan Williams Cc: Vishal Verma Cc: Dave Jiang Cc: Matthew Wilcox Cc: Arnd Bergmann Cc: Russell King Cc: Alasdair Kergon Cc: Christoph Hellwig Cc: Dave Chinner Cc: Heiko Carstens Cc: kernel test robot Cc: Michael Sclafani Cc: Mike Snitzer Cc: Mikulas Patocka Signed-off-by: Andrew Morton --- drivers/dax/super.c | 10 ++++++++++ fs/Kconfig | 1 - 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'drivers/dax') diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 97ef2a9d878d..7643b1a078d9 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -451,6 +451,16 @@ 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 && (IS_ENABLED(CONFIG_ARM) || + IS_ENABLED(CONFIG_MIPS) || + IS_ENABLED(CONFIG_SPARC))) + return ERR_PTR(-EOPNOTSUPP); + if (WARN_ON_ONCE(ops && !ops->zero_page_range)) return ERR_PTR(-EINVAL); diff --git a/fs/Kconfig b/fs/Kconfig index 89fdbefd1075..713c8655fa0a 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -60,7 +60,6 @@ endif # BLOCK config FS_DAX bool "File system based Direct Access (DAX) support" depends on MMU - depends on !(ARM || MIPS || SPARC) depends on ZONE_DEVICE || FS_DAX_LIMITED select FS_IOMAP select DAX -- cgit v1.2.3-70-g09d2 From 902ccb86ed02eea5b81c2afb514c0a7d72f63de2 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Thu, 15 Feb 2024 09:46:33 -0500 Subject: dax: fix incorrect list of data cache aliasing architectures commit d92576f1167c ("dax: does not work correctly with virtual aliasing caches") prevents DAX from building on architectures with virtually aliased dcache with: depends on !(ARM || MIPS || SPARC) This check is too broad (e.g. recent ARMv7 don't have virtually aliased dcaches), and also misses many other architectures with virtually aliased data cache. This is a regression introduced in the v4.0 Linux kernel where the dax mount option is removed for 32-bit ARMv7 boards which have no data cache aliasing, and therefore should work fine with FS_DAX. This was turned into the following check in alloc_dax() by a preparatory change: if (ops && (IS_ENABLED(CONFIG_ARM) || IS_ENABLED(CONFIG_MIPS) || IS_ENABLED(CONFIG_SPARC))) return NULL; Use cpu_dcache_is_aliasing() instead to figure out whether the environment has aliasing data caches. Link: https://lkml.kernel.org/r/20240215144633.96437-10-mathieu.desnoyers@efficios.com Fixes: d92576f1167c ("dax: does not work correctly with virtual aliasing caches") Signed-off-by: Mathieu Desnoyers Reviewed-by: Dan Williams Cc: Dan Williams Cc: Vishal Verma Cc: Dave Jiang Cc: Matthew Wilcox Cc: Arnd Bergmann Cc: Russell King Cc: Alasdair Kergon Cc: Christoph Hellwig Cc: Dave Chinner Cc: Heiko Carstens Cc: kernel test robot Cc: Michael Sclafani Cc: Mike Snitzer Cc: Mikulas Patocka Signed-off-by: Andrew Morton --- drivers/dax/super.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'drivers/dax') diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 7643b1a078d9..54e528779877 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "dax-private.h" /** @@ -456,9 +457,7 @@ struct dax_device *alloc_dax(void *private, const struct dax_operations *ops) * except for device-dax (NULL operations pointer), which does * not use aliased mappings from the kernel. */ - if (ops && (IS_ENABLED(CONFIG_ARM) || - IS_ENABLED(CONFIG_MIPS) || - IS_ENABLED(CONFIG_SPARC))) + if (ops && cpu_dcache_is_aliasing()) return ERR_PTR(-EOPNOTSUPP); if (WARN_ON_ONCE(ops && !ops->zero_page_range)) -- cgit v1.2.3-70-g09d2