From: Dan Williams <dan.j.williams@xxxxxxxxx> Subject: device-dax: add an allocation interface for device-dax instances In preparation for a facility that enables dax regions to be sub-divided, introduce infrastructure to track and allocate region capacity. The new dax_region/available_size attribute is only enabled for volatile hmem devices, not pmem devices that are defined by nvdimm namespace boundaries. This is per Jeff's feedback the last time dynamic device-dax capacity allocation support was discussed. Link: https://lore.kernel.org/linux-nvdimm/x49shpp3zn8.fsf@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx Link: https://lkml.kernel.org/r/159643101035.4062302.6785857915652647857.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx Link: https://lkml.kernel.org/r/160106112801.30709.14601438735305335071.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx> Cc: Vishal Verma <vishal.l.verma@xxxxxxxxx> Cc: Brice Goglin <Brice.Goglin@xxxxxxxx> Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx> Cc: Dave Jiang <dave.jiang@xxxxxxxxx> Cc: David Hildenbrand <david@xxxxxxxxxx> Cc: Ira Weiny <ira.weiny@xxxxxxxxx> Cc: Jia He <justin.he@xxxxxxx> Cc: Joao Martins <joao.m.martins@xxxxxxxxxx> Cc: Jonathan Cameron <Jonathan.Cameron@xxxxxxxxxx> Cc: Andy Lutomirski <luto@xxxxxxxxxx> Cc: Ard Biesheuvel <ard.biesheuvel@xxxxxxxxxx> Cc: Ard Biesheuvel <ardb@xxxxxxxxxx> Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx> Cc: Ben Skeggs <bskeggs@xxxxxxxxxx> Cc: Bjorn Helgaas <bhelgaas@xxxxxxxxxx> Cc: Borislav Petkov <bp@xxxxxxxxx> Cc: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx> Cc: Catalin Marinas <catalin.marinas@xxxxxxx> Cc: Daniel Vetter <daniel@xxxxxxxx> Cc: David Airlie <airlied@xxxxxxxx> Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> Cc: "H. Peter Anvin" <hpa@xxxxxxxxx> Cc: Hulk Robot <hulkci@xxxxxxxxxx> Cc: Ingo Molnar <mingo@xxxxxxxxxx> Cc: Jason Gunthorpe <jgg@xxxxxxxxxxxx> Cc: Jason Yan <yanaijie@xxxxxxxxxx> Cc: Jeff Moyer <jmoyer@xxxxxxxxxx> Cc: "Jérôme Glisse" <jglisse@xxxxxxxxxx> Cc: Juergen Gross <jgross@xxxxxxxx> Cc: kernel test robot <lkp@xxxxxxxxx> Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx> Cc: Mike Rapoport <rppt@xxxxxxxxxxxxx> Cc: Paul Mackerras <paulus@xxxxxxxxxx> Cc: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@xxxxxxxxx> Cc: Randy Dunlap <rdunlap@xxxxxxxxxxxxx> Cc: Stefano Stabellini <sstabellini@xxxxxxxxxx> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Cc: Tom Lendacky <thomas.lendacky@xxxxxxx> Cc: Vivek Goyal <vgoyal@xxxxxxxxxx> Cc: Wei Yang <richard.weiyang@xxxxxxxxxxxxxxxxx> Cc: Will Deacon <will@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- drivers/dax/bus.c | 120 +++++++++++++++++++++++++++++++++--- drivers/dax/bus.h | 7 +- drivers/dax/dax-private.h | 2 drivers/dax/hmem/hmem.c | 7 -- drivers/dax/pmem/core.c | 8 -- 5 files changed, 121 insertions(+), 23 deletions(-) --- a/drivers/dax/bus.c~device-dax-add-an-allocation-interface-for-device-dax-instances +++ a/drivers/dax/bus.c @@ -130,6 +130,11 @@ ATTRIBUTE_GROUPS(dax_drv); static int dax_bus_match(struct device *dev, struct device_driver *drv); +static bool is_static(struct dax_region *dax_region) +{ + return (dax_region->res.flags & IORESOURCE_DAX_STATIC) != 0; +} + static struct bus_type dax_bus_type = { .name = "dax", .uevent = dax_bus_uevent, @@ -185,7 +190,48 @@ static ssize_t align_show(struct device } static DEVICE_ATTR_RO(align); +#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; + + device_lock_assert(dax_region->dev); + + 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; + + device_lock(dev); + size = dax_region_avail_size(dax_region); + device_unlock(dev); + + return sprintf(buf, "%llu\n", size); +} +static DEVICE_ATTR_RO(available_size); + +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; + return a->mode; +} + static struct attribute *dax_region_attributes[] = { + &dev_attr_available_size.attr, &dev_attr_region_size.attr, &dev_attr_align.attr, &dev_attr_id.attr, @@ -195,6 +241,7 @@ static struct attribute *dax_region_attr static const struct attribute_group dax_region_attribute_group = { .name = "dax_region", .attrs = dax_region_attributes, + .is_visible = dax_region_visible, }; static const struct attribute_group *dax_region_attribute_groups[] = { @@ -226,7 +273,8 @@ static void dax_region_unregister(void * } struct dax_region *alloc_dax_region(struct device *parent, int region_id, - struct resource *res, int target_node, unsigned int align) + struct resource *res, int target_node, unsigned int align, + unsigned long flags) { struct dax_region *dax_region; @@ -249,12 +297,17 @@ struct dax_region *alloc_dax_region(stru return NULL; dev_set_drvdata(parent, dax_region); - memcpy(&dax_region->res, res, sizeof(*res)); kref_init(&dax_region->kref); dax_region->id = region_id; dax_region->align = align; dax_region->dev = parent; dax_region->target_node = target_node; + dax_region->res = (struct resource) { + .start = res->start, + .end = res->end, + .flags = IORESOURCE_MEM | flags, + }; + if (sysfs_create_groups(&parent->kobj, dax_region_attribute_groups)) { kfree(dax_region); return NULL; @@ -267,6 +320,32 @@ struct dax_region *alloc_dax_region(stru } EXPORT_SYMBOL_GPL(alloc_dax_region); +static int alloc_dev_dax_range(struct dev_dax *dev_dax, resource_size_t size) +{ + struct dax_region *dax_region = dev_dax->region; + struct resource *res = &dax_region->res; + struct device *dev = &dev_dax->dev; + struct resource *alloc; + + device_lock_assert(dax_region->dev); + + /* TODO: handle multiple allocations per region */ + if (res->child) + return -ENOMEM; + + alloc = __request_region(res, res->start, size, dev_name(dev), 0); + + if (!alloc) + return -ENOMEM; + + dev_dax->range = (struct range) { + .start = alloc->start, + .end = alloc->end, + }; + + return 0; +} + static ssize_t size_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -361,6 +440,15 @@ void kill_dev_dax(struct dev_dax *dev_da } 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); @@ -385,6 +473,7 @@ static void unregister_dev_dax(void *dev dev_dbg(dev, "%s\n", __func__); kill_dev_dax(dev_dax); + free_dev_dax_range(dev_dax); device_del(dev); put_device(dev); } @@ -397,7 +486,7 @@ struct dev_dax *devm_create_dev_dax(stru struct dev_dax *dev_dax; struct inode *inode; struct device *dev; - int rc = -ENOMEM; + int rc; if (data->id < 0) return ERR_PTR(-EINVAL); @@ -406,11 +495,25 @@ struct dev_dax *devm_create_dev_dax(stru if (!dev_dax) return ERR_PTR(-ENOMEM); + dev_dax->region = dax_region; + dev = &dev_dax->dev; + device_initialize(dev); + dev_set_name(dev, "dax%d.%d", dax_region->id, data->id); + + rc = alloc_dev_dax_range(dev_dax, data->size); + if (rc) + goto err_range; + if (data->pgmap) { + dev_WARN_ONCE(parent, !is_static(dax_region), + "custom dev_pagemap requires a static dax_region\n"); + dev_dax->pgmap = kmemdup(data->pgmap, sizeof(struct dev_pagemap), GFP_KERNEL); - if (!dev_dax->pgmap) + if (!dev_dax->pgmap) { + rc = -ENOMEM; goto err_pgmap; + } } /* @@ -427,12 +530,7 @@ struct dev_dax *devm_create_dev_dax(stru kill_dax(dax_dev); /* from here on we're committed to teardown via dev_dax_release() */ - dev = &dev_dax->dev; - device_initialize(dev); - dev_dax->dax_dev = dax_dev; - dev_dax->region = dax_region; - dev_dax->range = data->range; dev_dax->target_node = dax_region->target_node; kref_get(&dax_region->kref); @@ -444,7 +542,6 @@ struct dev_dax *devm_create_dev_dax(stru dev->class = dax_class; dev->parent = parent; dev->type = &dev_dax_type; - dev_set_name(dev, "dax%d.%d", dax_region->id, data->id); rc = device_add(dev); if (rc) { @@ -458,9 +555,12 @@ struct dev_dax *devm_create_dev_dax(stru return ERR_PTR(rc); return dev_dax; + err_alloc_dax: kfree(dev_dax->pgmap); err_pgmap: + free_dev_dax_range(dev_dax); +err_range: kfree(dev_dax); return ERR_PTR(rc); --- a/drivers/dax/bus.h~device-dax-add-an-allocation-interface-for-device-dax-instances +++ a/drivers/dax/bus.h @@ -10,8 +10,11 @@ struct resource; struct dax_device; struct dax_region; void dax_region_put(struct dax_region *dax_region); + +#define IORESOURCE_DAX_STATIC (1UL << 0) struct dax_region *alloc_dax_region(struct device *parent, int region_id, - struct resource *res, int target_node, unsigned int align); + struct resource *res, int target_node, unsigned int align, + unsigned long flags); enum dev_dax_subsys { DEV_DAX_BUS = 0, /* zeroed dev_dax_data picks this by default */ @@ -22,7 +25,7 @@ struct dev_dax_data { struct dax_region *dax_region; struct dev_pagemap *pgmap; enum dev_dax_subsys subsys; - struct range range; + resource_size_t size; int id; }; --- a/drivers/dax/dax-private.h~device-dax-add-an-allocation-interface-for-device-dax-instances +++ a/drivers/dax/dax-private.h @@ -22,7 +22,7 @@ void dax_bus_exit(void); * @kref: to pin while other agents have a need to do lookups * @dev: parent device backing this region * @align: allocation and mapping alignment for child dax devices - * @res: physical address range of the region + * @res: resource tree to track instance allocations */ struct dax_region { int id; --- a/drivers/dax/hmem/hmem.c~device-dax-add-an-allocation-interface-for-device-dax-instances +++ a/drivers/dax/hmem/hmem.c @@ -20,17 +20,14 @@ static int dax_hmem_probe(struct platfor mri = dev->platform_data; dax_region = alloc_dax_region(dev, pdev->id, res, mri->target_node, - PMD_SIZE); + PMD_SIZE, 0); if (!dax_region) return -ENOMEM; data = (struct dev_dax_data) { .dax_region = dax_region, .id = 0, - .range = { - .start = res->start, - .end = res->end, - }, + .size = resource_size(res), }; dev_dax = devm_create_dev_dax(&data); if (IS_ERR(dev_dax)) --- a/drivers/dax/pmem/core.c~device-dax-add-an-allocation-interface-for-device-dax-instances +++ a/drivers/dax/pmem/core.c @@ -54,7 +54,8 @@ struct dev_dax *__dax_pmem_probe(struct memcpy(&res, &pgmap.res, sizeof(res)); res.start += offset; dax_region = alloc_dax_region(dev, region_id, &res, - nd_region->target_node, le32_to_cpu(pfn_sb->align)); + nd_region->target_node, le32_to_cpu(pfn_sb->align), + IORESOURCE_DAX_STATIC); if (!dax_region) return ERR_PTR(-ENOMEM); @@ -63,10 +64,7 @@ struct dev_dax *__dax_pmem_probe(struct .id = id, .pgmap = &pgmap, .subsys = subsys, - .range = { - .start = res.start, - .end = res.end, - }, + .size = resource_size(&res), }; dev_dax = devm_create_dev_dax(&data); _
