Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1031060AbbD1S2Q (ORCPT ); Tue, 28 Apr 2015 14:28:16 -0400 Received: from mga02.intel.com ([134.134.136.20]:17434 "EHLO mga02.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1030593AbbD1S2E (ORCPT ); Tue, 28 Apr 2015 14:28:04 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.11,665,1422950400"; d="scan'208";a="720623242" Subject: [PATCH v2 12/20] libnd, nd_acpi: add interleave-set state-tracking infrastructure From: Dan Williams To: linux-nvdimm@ml01.01.org Cc: Neil Brown , Greg KH , "Rafael J. Wysocki" , Robert Moore , linux-kernel@vger.kernel.org, linux-acpi@vger.kernel.org Date: Tue, 28 Apr 2015 14:25:19 -0400 Message-ID: <20150428182519.35812.16187.stgit@dwillia2-desk3.amr.corp.intel.com> In-Reply-To: <20150428181203.35812.60474.stgit@dwillia2-desk3.amr.corp.intel.com> References: <20150428181203.35812.60474.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: 17400 Lines: 571 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. It is the bus provider implementation's responsibility to calculate the interleave set cookie and attach it to a given region. Cc: Neil Brown Cc: Cc: Greg KH Cc: Robert Moore Cc: Rafael J. Wysocki Signed-off-by: Dan Williams --- drivers/block/nd/acpi.c | 90 ++++++++++++++++++++++++++++++++++++++++ drivers/block/nd/bus.c | 41 ++++++++++++++++++ drivers/block/nd/core.c | 47 +++++++++++++++++++++ drivers/block/nd/dimm_devs.c | 19 ++++++++ drivers/block/nd/libnd.h | 6 +++ drivers/block/nd/nd-private.h | 11 ++++- drivers/block/nd/nd.h | 4 ++ drivers/block/nd/region_devs.c | 85 ++++++++++++++++++++++++++++++++++++++ 8 files changed, 299 insertions(+), 4 deletions(-) diff --git a/drivers/block/nd/acpi.c b/drivers/block/nd/acpi.c index c3dda74f73d7..d34cefe38e2f 100644 --- a/drivers/block/nd/acpi.c +++ b/drivers/block/nd/acpi.c @@ -15,6 +15,7 @@ #include #include #include +#include #include "acpi_nfit.h" #include "libnd.h" @@ -779,6 +780,90 @@ static const struct attribute_group *nd_acpi_region_attribute_groups[] = { NULL, }; +/* enough info to uniquely specify an interleave set */ +struct nfit_set_info { + struct nfit_set_info_map { + u64 region_spa_offset; + u32 serial_number; + u32 pad; + } mapping[0]; +}; + +static size_t sizeof_nfit_set_info(int num_mappings) +{ + return sizeof(struct nfit_set_info) + + num_mappings * sizeof(struct nfit_set_info_map); +} + +static int cmp_map(const void *m0, const void *m1) +{ + const struct nfit_set_info_map *map0 = m0; + const struct nfit_set_info_map *map1 = m1; + + return memcmp(&map0->region_spa_offset, &map1->region_spa_offset, + sizeof(u64)); +} + +/* Retrieve the nth entry referencing this spa */ +static struct acpi_nfit_memdev *memdev_from_spa( + struct acpi_nfit_desc *acpi_desc, u16 spa_index, int n) +{ + struct nfit_memdev *nfit_memdev; + + list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) + if (nfit_memdev->memdev->spa_index == spa_index) + if (n-- == 0) + return nfit_memdev->memdev; + return NULL; +} + +static int nd_acpi_init_interleave_set(struct acpi_nfit_desc *acpi_desc, + struct nd_region_desc *ndr_desc, struct acpi_nfit_spa *spa) +{ + u16 num_mappings = ndr_desc->num_mappings; + int i, spa_type = nfit_spa_type(spa); + struct device *dev = acpi_desc->dev; + struct nd_interleave_set *nd_set; + struct nfit_set_info *info; + + if (spa_type == NFIT_SPA_PM || spa_type == NFIT_SPA_VOLATILE) + /* pass */; + else + return 0; + + nd_set = devm_kzalloc(dev, sizeof(*nd_set), GFP_KERNEL); + if (!nd_set) + return -ENOMEM; + + info = devm_kzalloc(dev, sizeof_nfit_set_info(num_mappings), GFP_KERNEL); + if (!info) + return -ENOMEM; + for (i = 0; i < num_mappings; i++) { + struct nd_mapping *nd_mapping = &ndr_desc->nd_mapping[i]; + struct nfit_set_info_map *map = &info->mapping[i]; + struct nd_dimm *nd_dimm = nd_mapping->nd_dimm; + struct nfit_mem *nfit_mem = nd_dimm_provider_data(nd_dimm); + struct acpi_nfit_memdev *memdev = memdev_from_spa(acpi_desc, + spa->spa_index, i); + + if (!memdev || !nfit_mem->dcr) { + dev_err(dev, "%s: failed to find DCR\n", __func__); + return -ENODEV; + } + + map->region_spa_offset = memdev->region_spa_offset; + map->serial_number = nfit_mem->dcr->serial_number; + } + + sort(&info->mapping[0], num_mappings, sizeof(struct nfit_set_info_map), + cmp_map, NULL); + nd_set->cookie = nd_fletcher64(info, sizeof_nfit_set_info(num_mappings)); + ndr_desc->nd_set = nd_set; + devm_kfree(dev, info); + + return 0; +} + static int nd_acpi_register_region(struct acpi_nfit_desc *acpi_desc, struct nfit_spa *nfit_spa) { @@ -786,7 +871,7 @@ static int nd_acpi_register_region(struct acpi_nfit_desc *acpi_desc, struct acpi_nfit_spa *spa = nfit_spa->spa; struct nfit_memdev *nfit_memdev; struct nd_region_desc ndr_desc; - int spa_type, count = 0; + int spa_type, count = 0, rc; struct resource res; u16 spa_index; @@ -852,6 +937,9 @@ static int nd_acpi_register_region(struct acpi_nfit_desc *acpi_desc, ndr_desc.nd_mapping = nd_mappings; ndr_desc.num_mappings = count; + rc = nd_acpi_init_interleave_set(acpi_desc, &ndr_desc, spa); + if (rc) + return rc; if (spa_type == NFIT_SPA_PM) { if (!nd_pmem_region_create(acpi_desc->nd_bus, &ndr_desc)) return -ENOMEM; diff --git a/drivers/block/nd/bus.c b/drivers/block/nd/bus.c index 46568d182559..8afb8d4a7e81 100644 --- a/drivers/block/nd/bus.c +++ b/drivers/block/nd/bus.c @@ -78,7 +78,10 @@ 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) @@ -94,6 +97,8 @@ 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); @@ -359,6 +364,33 @@ u32 nd_cmd_out_size(struct nd_dimm *nd_dimm, int cmd, } EXPORT_SYMBOL_GPL(nd_cmd_out_size); +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 != ND_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 ioctl_cmd, unsigned long arg) { @@ -469,11 +501,18 @@ 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, cmd); + if (rc) + goto out_unlock; + rc = nd_desc->ndctl(nd_desc, nd_dimm, 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: vfree(buf); return rc; diff --git a/drivers/block/nd/core.c b/drivers/block/nd/core.c index 646e424ae36c..603970d0ef3a 100644 --- a/drivers/block/nd/core.c +++ b/drivers/block/nd/core.c @@ -24,6 +24,51 @@ LIST_HEAD(nd_bus_list); DEFINE_MUTEX(nd_bus_list_mutex); static DEFINE_IDA(nd_ida); +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); + +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; +} +EXPORT_SYMBOL_GPL(nd_fletcher64); + static void nd_bus_release(struct device *dev) { struct nd_bus *nd_bus = container_of(dev, struct nd_bus, dev); @@ -142,7 +187,9 @@ struct nd_bus *__nd_bus_register(struct device *parent, if (!nd_bus) return NULL; INIT_LIST_HEAD(&nd_bus->list); + init_waitqueue_head(&nd_bus->probe_wait); 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; diff --git a/drivers/block/nd/dimm_devs.c b/drivers/block/nd/dimm_devs.c index 33b6d5336096..8981adc59ba4 100644 --- a/drivers/block/nd/dimm_devs.c +++ b/drivers/block/nd/dimm_devs.c @@ -185,7 +185,24 @@ 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_state.attr, &dev_attr_commands.attr, NULL, }; @@ -213,7 +230,7 @@ struct nd_dimm *nd_dimm_create(struct nd_bus *nd_bus, void *provider_data, nd_dimm->provider_data = provider_data; nd_dimm->flags = flags; nd_dimm->dsm_mask = dsm_mask; - + atomic_set(&nd_dimm->busy, 0); dev = &nd_dimm->dev; dev_set_name(dev, "nmem%d", nd_dimm->id); dev->parent = &nd_bus->dev; diff --git a/drivers/block/nd/libnd.h b/drivers/block/nd/libnd.h index 8c6f07696f30..deb29eff5b61 100644 --- a/drivers/block/nd/libnd.h +++ b/drivers/block/nd/libnd.h @@ -60,11 +60,16 @@ struct nd_cmd_desc { int out_sizes[ND_CMD_MAX_ELEM]; }; +struct nd_interleave_set { + u64 cookie; +}; + struct nd_region_desc { struct resource *res; struct nd_mapping *nd_mapping; u16 num_mappings; const struct attribute_group **attr_groups; + struct nd_interleave_set *nd_set; void *provider_data; }; @@ -98,4 +103,5 @@ struct nd_region *nd_blk_region_create(struct nd_bus *nd_bus, struct nd_region_desc *ndr_desc); struct nd_region *nd_volatile_region_create(struct nd_bus *nd_bus, struct nd_region_desc *ndr_desc); +u64 nd_fletcher64(void __iomem *addr, size_t len); #endif /* __LIBND_H__ */ diff --git a/drivers/block/nd/nd-private.h b/drivers/block/nd/nd-private.h index 131fc66ce7ab..5d8249be3415 100644 --- a/drivers/block/nd/nd-private.h +++ b/drivers/block/nd/nd-private.h @@ -13,6 +13,8 @@ #ifndef __ND_PRIVATE_H__ #define __ND_PRIVATE_H__ #include +#include +#include #include "libnd.h" extern struct list_head nd_bus_list; @@ -21,10 +23,12 @@ extern int nd_dimm_major; struct nd_bus { struct nd_bus_descriptor *nd_desc; + wait_queue_head_t probe_wait; struct module *module; struct list_head list; struct device dev; - int id; + int id, probe_active; + struct mutex reconfig_mutex; }; struct nd_dimm { @@ -32,6 +36,7 @@ struct nd_dimm { void *provider_data; unsigned long *dsm_mask; struct device dev; + atomic_t busy; int id; }; @@ -45,10 +50,14 @@ 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); void nd_synchronize(void); 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 23469513f4c0..c69707dbd272 100644 --- a/drivers/block/nd/nd.h +++ b/drivers/block/nd/nd.h @@ -35,6 +35,7 @@ struct nd_region { u64 ndr_start; int id; void *provider_data; + struct nd_interleave_set *nd_set; struct nd_mapping mapping[0]; }; @@ -50,4 +51,7 @@ int nd_dimm_init_config_data(struct nd_dimm_drvdata *ndd); 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 49ebce0c97be..c1cea42d0473 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 "nd.h" @@ -133,6 +136,21 @@ 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_interleave_set *nd_set = nd_region->nd_set; + + if (is_nd_pmem(dev) && nd_set) + /* pass, should be precluded by nd_region_visible */; + else + return -ENXIO; + + return sprintf(buf, "%#llx\n", nd_set->cookie); +} +static DEVICE_ATTR_RO(set_cookie); + static ssize_t init_namespaces_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -149,15 +167,81 @@ static struct attribute *nd_region_attributes[] = { &dev_attr_size.attr, &dev_attr_nstype.attr, &dev_attr_mappings.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_interleave_set *nd_set = nd_region->nd_set; + + if (a != &dev_attr_set_cookie.attr) + return a->mode; + + if (is_nd_pmem(dev) && nd_set) + return a->mode; + + return 0; +} + struct attribute_group nd_region_attribute_group = { .attrs = nd_region_attributes, + .is_visible = nd_region_visible, }; EXPORT_SYMBOL_GPL(nd_region_attribute_group); +/* + * 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); @@ -317,6 +401,7 @@ static noinline struct nd_region *nd_region_create(struct nd_bus *nd_bus, } nd_region->ndr_mappings = ndr_desc->num_mappings; nd_region->provider_data = ndr_desc->provider_data; + nd_region->nd_set = ndr_desc->nd_set; dev = &nd_region->dev; dev_set_name(dev, "region%d", nd_region->id); dev->parent = &nd_bus->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/