Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932216AbbDRBjS (ORCPT ); Fri, 17 Apr 2015 21:39:18 -0400 Received: from mga14.intel.com ([192.55.52.115]:33633 "EHLO mga14.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753949AbbDRBjF (ORCPT ); Fri, 17 Apr 2015 21:39:05 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.11,598,1422950400"; d="scan'208";a="557972318" Subject: [PATCH 13/21] nd: add interleave-set state-tracking infrastructure From: Dan Williams To: linux-nvdimm@ml01.01.org Cc: linux-kernel@vger.kernel.org Date: Fri, 17 Apr 2015 21:36:23 -0400 Message-ID: <20150418013623.25237.94475.stgit@dwillia2-desk3.amr.corp.intel.com> In-Reply-To: <20150418013256.25237.96403.stgit@dwillia2-desk3.amr.corp.intel.com> References: <20150418013256.25237.96403.stgit@dwillia2-desk3.amr.corp.intel.com> User-Agent: StGit/0.17.1-8-g92dd MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 16061 Lines: 549 On platforms that have firmware support for reading/writing per-dimm label space, a portion of the dimm may be accessible via an interleave set PMEM mapping in addition to the dimm's BLK (block-data-window aperture(s)) interface. A label, stored in a "configuration data region" on the dimm, disambiguates which dimm addresses are accessed through which exclusive interface. Add infrastructure that allows the kernel to block modifications to a label in the set while any member dimm is active. Note that this is meant only for enforcing "no modifications of active labels" via the coarse ioctl command. Adding/deleting namespaces from an active interleave set will only be possible via sysfs. Another aspect of tracking interleave sets is tracking their integrity when DIMMs in a set are physically re-ordered. For this purpose we generate an "interleave-set cookie" that can be recorded in a label and validated against the current configuration. Signed-off-by: Dan Williams --- drivers/block/nd/bus.c | 41 +++++++++ drivers/block/nd/core.c | 51 ++++++++++++ drivers/block/nd/dimm_devs.c | 18 ++++ drivers/block/nd/nd-private.h | 17 ++++ drivers/block/nd/nd.h | 4 + drivers/block/nd/region_devs.c | 176 ++++++++++++++++++++++++++++++++++++++++ 6 files changed, 305 insertions(+), 2 deletions(-) diff --git a/drivers/block/nd/bus.c b/drivers/block/nd/bus.c index c98fe05a4c9b..944d7d7845fe 100644 --- a/drivers/block/nd/bus.c +++ b/drivers/block/nd/bus.c @@ -79,7 +79,10 @@ static int nd_bus_probe(struct device *dev) if (!try_module_get(provider)) return -ENXIO; + nd_region_probe_start(nd_bus, dev); rc = nd_drv->probe(dev); + nd_region_probe_end(nd_bus, dev, rc); + dev_dbg(&nd_bus->dev, "%s.probe(%s) = %d\n", dev->driver->name, dev_name(dev), rc); if (rc != 0) @@ -95,6 +98,8 @@ static int nd_bus_remove(struct device *dev) int rc; rc = nd_drv->remove(dev); + nd_region_notify_remove(nd_bus, dev, rc); + dev_dbg(&nd_bus->dev, "%s.remove(%s) = %d\n", dev->driver->name, dev_name(dev), rc); module_put(provider); @@ -269,6 +274,33 @@ void nd_bus_destroy_ndctl(struct nd_bus *nd_bus) device_destroy(nd_class, MKDEV(nd_bus_major, nd_bus->id)); } +static void wait_nd_bus_probe_idle(struct nd_bus *nd_bus) +{ + do { + if (nd_bus->probe_active == 0) + break; + nd_bus_unlock(&nd_bus->dev); + wait_event(nd_bus->probe_wait, nd_bus->probe_active == 0); + nd_bus_lock(&nd_bus->dev); + } while (true); +} + +/* set_config requires an idle interleave set */ +static int nd_cmd_clear_to_send(struct nd_dimm *nd_dimm, unsigned int cmd) +{ + struct nd_bus *nd_bus; + + if (!nd_dimm || cmd != NFIT_CMD_SET_CONFIG_DATA) + return 0; + + nd_bus = walk_to_nd_bus(&nd_dimm->dev); + wait_nd_bus_probe_idle(nd_bus); + + if (atomic_read(&nd_dimm->busy)) + return -EBUSY; + return 0; +} + static int __nd_ioctl(struct nd_bus *nd_bus, struct nd_dimm *nd_dimm, int read_only, unsigned int cmd, unsigned long arg) { @@ -399,11 +431,18 @@ static int __nd_ioctl(struct nd_bus *nd_bus, struct nd_dimm *nd_dimm, goto out; } + nd_bus_lock(&nd_bus->dev); + rc = nd_cmd_clear_to_send(nd_dimm, _IOC_NR(cmd)); + if (rc) + goto out_unlock; + rc = nfit_desc->nfit_ctl(nfit_desc, nd_dimm, _IOC_NR(cmd), buf, buf_len); if (rc < 0) - goto out; + goto out_unlock; if (copy_to_user(p, buf, buf_len)) rc = -EFAULT; + out_unlock: + nd_bus_unlock(&nd_bus->dev); out: if (is_vmalloc_addr(buf)) vfree(buf); diff --git a/drivers/block/nd/core.c b/drivers/block/nd/core.c index c795e8057061..976cd5e3ebaf 100644 --- a/drivers/block/nd/core.c +++ b/drivers/block/nd/core.c @@ -31,6 +31,36 @@ static bool warn_checksum; module_param(warn_checksum, bool, S_IRUGO|S_IWUSR); MODULE_PARM_DESC(warn_checksum, "Turn checksum errors into warnings"); +void nd_bus_lock(struct device *dev) +{ + struct nd_bus *nd_bus = walk_to_nd_bus(dev); + + if (!nd_bus) + return; + mutex_lock(&nd_bus->reconfig_mutex); +} +EXPORT_SYMBOL(nd_bus_lock); + +void nd_bus_unlock(struct device *dev) +{ + struct nd_bus *nd_bus = walk_to_nd_bus(dev); + + if (!nd_bus) + return; + mutex_unlock(&nd_bus->reconfig_mutex); +} +EXPORT_SYMBOL(nd_bus_unlock); + +bool is_nd_bus_locked(struct device *dev) +{ + struct nd_bus *nd_bus = walk_to_nd_bus(dev); + + if (!nd_bus) + return false; + return mutex_is_locked(&nd_bus->reconfig_mutex); +} +EXPORT_SYMBOL(is_nd_bus_locked); + /** * nd_dimm_by_handle - lookup an nd_dimm by its corresponding nfit_handle * @nd_bus: parent bus of the dimm @@ -49,6 +79,20 @@ struct nd_dimm *nd_dimm_by_handle(struct nd_bus *nd_bus, u32 nfit_handle) return nd_dimm; } +u64 nd_fletcher64(void __iomem *addr, size_t len) +{ + u32 lo32 = 0; + u64 hi32 = 0; + int i; + + for (i = 0; i < len; i += 4) { + lo32 = readl(addr + i); + hi32 += lo32; + } + + return hi32 << 32 | lo32; +} + static void nd_bus_release(struct device *dev) { struct nd_bus *nd_bus = container_of(dev, struct nd_bus, dev); @@ -60,6 +104,7 @@ static void nd_bus_release(struct device *dev) list_for_each_entry_safe(nd_spa, _spa, &nd_bus->spas, list) { list_del_init(&nd_spa->list); + kfree(nd_spa->nd_set); kfree(nd_spa); } list_for_each_entry_safe(nd_dcr, _dcr, &nd_bus->dcrs, list) { @@ -205,8 +250,10 @@ static void *nd_bus_new(struct device *parent, INIT_LIST_HEAD(&nd_bus->memdevs); INIT_LIST_HEAD(&nd_bus->dimms); INIT_LIST_HEAD(&nd_bus->list); + init_waitqueue_head(&nd_bus->probe_wait); INIT_RADIX_TREE(&nd_bus->dimm_radix, GFP_KERNEL); nd_bus->id = ida_simple_get(&nd_ida, 0, 0, GFP_KERNEL); + mutex_init(&nd_bus->reconfig_mutex); if (nd_bus->id < 0) { kfree(nd_bus); return NULL; @@ -570,6 +617,10 @@ static struct nd_bus *nd_bus_probe(struct nd_bus *nd_bus) if (rc) goto err; + rc = nd_bus_init_interleave_sets(nd_bus); + if (rc) + goto err; + rc = nd_bus_create_ndctl(nd_bus); if (rc) goto err; diff --git a/drivers/block/nd/dimm_devs.c b/drivers/block/nd/dimm_devs.c index d15ca75804ac..6192d9c82b9b 100644 --- a/drivers/block/nd/dimm_devs.c +++ b/drivers/block/nd/dimm_devs.c @@ -287,6 +287,22 @@ static ssize_t commands_show(struct device *dev, } static DEVICE_ATTR_RO(commands); +static ssize_t state_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct nd_dimm *nd_dimm = to_nd_dimm(dev); + + /* + * The state may be in the process of changing, userspace should + * quiesce probing if it wants a static answer + */ + nd_bus_lock(dev); + nd_bus_unlock(dev); + return sprintf(buf, "%s\n", atomic_read(&nd_dimm->busy) + ? "active" : "idle"); +} +static DEVICE_ATTR_RO(state); + static struct attribute *nd_dimm_attributes[] = { &dev_attr_handle.attr, &dev_attr_phys_id.attr, @@ -294,6 +310,7 @@ static struct attribute *nd_dimm_attributes[] = { &dev_attr_device.attr, &dev_attr_format.attr, &dev_attr_serial.attr, + &dev_attr_state.attr, &dev_attr_revision.attr, &dev_attr_commands.attr, NULL, @@ -364,6 +381,7 @@ static struct nd_dimm *nd_dimm_create(struct nd_bus *nd_bus, if (nd_dimm->id < 0) goto err_ida; + atomic_set(&nd_dimm->busy, 0); nd_dimm->nd_mem = nd_mem; dev = &nd_dimm->dev; dev_set_name(dev, "nmem%d", nd_dimm->id); diff --git a/drivers/block/nd/nd-private.h b/drivers/block/nd/nd-private.h index db68e013b9d0..15ca7be507ce 100644 --- a/drivers/block/nd/nd-private.h +++ b/drivers/block/nd/nd-private.h @@ -15,6 +15,9 @@ #include #include #include +#include +#include +#include "nfit.h" extern struct list_head nd_bus_list; extern struct mutex nd_bus_list_mutex; @@ -33,6 +36,7 @@ enum { struct nd_bus { struct nfit_bus_descriptor *nfit_desc; struct radix_tree_root dimm_radix; + wait_queue_head_t probe_wait; struct module *module; struct list_head memdevs; struct list_head dimms; @@ -41,7 +45,8 @@ struct nd_bus { struct list_head bdws; struct list_head list; struct device dev; - int id; + int id, probe_active; + struct mutex reconfig_mutex; }; struct nd_dimm { @@ -50,14 +55,20 @@ struct nd_dimm { struct device dev; void *provider_data; int id, nfit_status; + atomic_t busy; struct nd_dimm_delete { struct nd_bus *nd_bus; struct nd_mem *nd_mem; } *del_info; }; +struct nd_interleave_set { + u64 cookie; +}; + struct nd_spa { struct nfit_spa __iomem *nfit_spa; + struct nd_interleave_set *nd_set; struct list_head list; }; @@ -103,9 +114,13 @@ int __init nd_dimm_init(void); int __init nd_region_init(void); void nd_dimm_exit(void); int nd_region_exit(void); +void nd_region_probe_start(struct nd_bus *nd_bus, struct device *dev); +void nd_region_probe_end(struct nd_bus *nd_bus, struct device *dev, int rc); +void nd_region_notify_remove(struct nd_bus *nd_bus, struct device *dev, int rc); int nd_bus_create_ndctl(struct nd_bus *nd_bus); void nd_bus_destroy_ndctl(struct nd_bus *nd_bus); int nd_bus_register_dimms(struct nd_bus *nd_bus); int nd_bus_register_regions(struct nd_bus *nd_bus); +int nd_bus_init_interleave_sets(struct nd_bus *nd_bus); int nd_match_dimm(struct device *dev, void *data); #endif /* __ND_PRIVATE_H__ */ diff --git a/drivers/block/nd/nd.h b/drivers/block/nd/nd.h index 4ac7ff2af4c8..4deed46884c1 100644 --- a/drivers/block/nd/nd.h +++ b/drivers/block/nd/nd.h @@ -50,6 +50,7 @@ enum nd_async_mode { void nd_device_register(struct device *dev); void nd_device_unregister(struct device *dev, enum nd_async_mode mode); +u64 nd_fletcher64(void __iomem *addr, size_t len); extern struct attribute_group nd_device_attribute_group; struct nd_dimm; u32 to_nfit_handle(struct nd_dimm *nd_dimm); @@ -63,4 +64,7 @@ int nd_dimm_firmware_status(struct device *dev); struct nd_region *to_nd_region(struct device *dev); int nd_region_to_namespace_type(struct nd_region *nd_region); int nd_region_register_namespaces(struct nd_region *nd_region, int *err); +void nd_bus_lock(struct device *dev); +void nd_bus_unlock(struct device *dev); +bool is_nd_bus_locked(struct device *dev); #endif /* __ND_H__ */ diff --git a/drivers/block/nd/region_devs.c b/drivers/block/nd/region_devs.c index 03b192368e1a..13f45be755a5 100644 --- a/drivers/block/nd/region_devs.c +++ b/drivers/block/nd/region_devs.c @@ -10,7 +10,10 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * General Public License for more details. */ +#include +#include #include +#include #include #include "nd-private.h" #include "nfit.h" @@ -137,6 +140,21 @@ static ssize_t nstype_show(struct device *dev, } static DEVICE_ATTR_RO(nstype); +static ssize_t set_cookie_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_region *nd_region = to_nd_region(dev); + struct nd_spa *nd_spa = nd_region->nd_spa; + + if (is_nd_pmem(dev) && nd_spa->nd_set) + /* pass, should be precluded by nd_region_visible */; + else + return -ENXIO; + + return sprintf(buf, "%#llx\n", nd_spa->nd_set->cookie); +} +static DEVICE_ATTR_RO(set_cookie); + static ssize_t init_namespaces_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -154,12 +172,29 @@ static struct attribute *nd_region_attributes[] = { &dev_attr_nstype.attr, &dev_attr_mappings.attr, &dev_attr_spa_index.attr, + &dev_attr_set_cookie.attr, &dev_attr_init_namespaces.attr, NULL, }; +static umode_t nd_region_visible(struct kobject *kobj, struct attribute *a, int n) +{ + struct device *dev = container_of(kobj, typeof(*dev), kobj); + struct nd_region *nd_region = to_nd_region(dev); + struct nd_spa *nd_spa = nd_region->nd_spa; + + if (a != &dev_attr_set_cookie.attr) + return a->mode; + + if (is_nd_pmem(dev) && nd_spa->nd_set) + return a->mode; + + return 0; +} + static struct attribute_group nd_region_attribute_group = { .attrs = nd_region_attributes, + .is_visible = nd_region_visible, }; /* @@ -203,6 +238,147 @@ static struct nd_mem *nd_memdev_to_mem(struct nd_bus *nd_bus, return NULL; } +/* enough info to uniquely specify an interleave set */ +struct nd_set_info { + struct nd_set_info_map { + u64 region_spa_offset; + u32 serial_number; + u32 pad; + } mapping[0]; +}; + +static size_t sizeof_nd_set_info(int num_mappings) +{ + return sizeof(struct nd_set_info) + + num_mappings * sizeof(struct nd_set_info_map); +} + +static int cmp_map(const void *m0, const void *m1) +{ + const struct nd_set_info_map *map0 = m0; + const struct nd_set_info_map *map1 = m1; + + return memcmp(&map0->region_spa_offset, &map1->region_spa_offset, + sizeof(u64)); +} + +static int init_interleave_set(struct nd_bus *nd_bus, + struct nd_interleave_set *nd_set, struct nd_spa *nd_spa) +{ + u16 spa_index = readw(&nd_spa->nfit_spa->spa_index); + int num_mappings = num_nd_mem(nd_bus, spa_index); + struct nd_set_info *info; + int i; + + info = kzalloc(sizeof_nd_set_info(num_mappings), GFP_KERNEL); + if (!info) + return -ENOMEM; + for (i = 0; i < num_mappings; i++) { + struct nd_set_info_map *map = &info->mapping[i]; + struct nd_memdev *nd_memdev = nd_memdev_from_spa(nd_bus, + spa_index, i); + struct nd_mem *nd_mem = nd_memdev_to_mem(nd_bus, nd_memdev); + + if (!nd_mem) { + dev_err(&nd_bus->dev, "%s: failed to find DCR\n", + __func__); + kfree(info); + return -ENODEV; + } + + map->region_spa_offset = readl( + &nd_memdev->nfit_mem->region_spa_offset); + map->serial_number = readl(&nd_mem->nfit_dcr->serial_number); + } + + sort(&info->mapping[0], num_mappings, sizeof(struct nd_set_info_map), + cmp_map, NULL); + nd_set->cookie = nd_fletcher64(info, sizeof_nd_set_info(num_mappings)); + + kfree(info); + + return 0; +} + +int nd_bus_init_interleave_sets(struct nd_bus *nd_bus) +{ + struct nd_spa *nd_spa; + int rc = 0; + + /* PMEM interleave sets */ + list_for_each_entry(nd_spa, &nd_bus->spas, list) { + u16 spa_index = readw(&nd_spa->nfit_spa->spa_index); + int spa_type = nfit_spa_type(nd_spa->nfit_spa); + struct nd_interleave_set *nd_set; + + if (spa_type != NFIT_SPA_PM) + continue; + if (nd_memdev_from_spa(nd_bus, spa_index, 0) == NULL) + continue; + nd_set = kzalloc(sizeof(*nd_set), GFP_KERNEL); + if (!nd_set) { + rc = -ENOMEM; + break; + } + nd_spa->nd_set = nd_set; + + rc = init_interleave_set(nd_bus, nd_set, nd_spa); + if (rc) + break; + } + + return rc; +} + +/* + * Upon successful probe/remove, take/release a reference on the + * associated interleave set (if present) + */ +static void nd_region_notify_driver_action(struct nd_bus *nd_bus, + struct device *dev, int rc, bool probe) +{ + if (rc) + return; + + if (is_nd_pmem(dev) || is_nd_blk(dev)) { + struct nd_region *nd_region = to_nd_region(dev); + int i; + + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nd_dimm *nd_dimm = nd_mapping->nd_dimm; + + if (probe) + atomic_inc(&nd_dimm->busy); + else + atomic_dec(&nd_dimm->busy); + } + } +} + +void nd_region_probe_start(struct nd_bus *nd_bus, struct device *dev) +{ + nd_bus_lock(&nd_bus->dev); + nd_bus->probe_active++; + nd_bus_unlock(&nd_bus->dev); +} + +void nd_region_probe_end(struct nd_bus *nd_bus, struct device *dev, int rc) +{ + nd_bus_lock(&nd_bus->dev); + nd_region_notify_driver_action(nd_bus, dev, rc, true); + if (--nd_bus->probe_active == 0) + wake_up(&nd_bus->probe_wait); + nd_bus_unlock(&nd_bus->dev); +} + +void nd_region_notify_remove(struct nd_bus *nd_bus, struct device *dev, int rc) +{ + nd_bus_lock(dev); + nd_region_notify_driver_action(nd_bus, dev, rc, false); + nd_bus_unlock(dev); +} + static ssize_t mappingN(struct device *dev, char *buf, int n) { struct nd_region *nd_region = to_nd_region(dev); -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/