Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S964831AbbDRBlQ (ORCPT ); Fri, 17 Apr 2015 21:41:16 -0400 Received: from mga01.intel.com ([192.55.52.88]:3819 "EHLO mga01.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754030AbbDRBjP (ORCPT ); Fri, 17 Apr 2015 21:39:15 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.11,598,1422950400"; d="scan'208";a="681970832" Subject: [PATCH 15/21] nd: pmem label sets and namespace instantiation. From: Dan Williams To: linux-nvdimm@ml01.01.org Cc: Neil Brown , Greg KH , linux-kernel@vger.kernel.org Date: Fri, 17 Apr 2015 21:36:34 -0400 Message-ID: <20150418013634.25237.91567.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: 52755 Lines: 1900 A complete label set is a PMEM-label per dimm where all the UUIDs match and the interleave set cookie matches an active interleave set. Present a sysfs ABI for manipulation of a PMEM-namespace's 'alt_name', 'uuid', and 'size' attributes. A later patch will make these settings persistent by writing back the label. Note that PMEM allocations grow forwards from the start of an interleave set (lowest dimm-physical-address (DPA)). BLK-namespaces that alias with a PMEM interleave set will grow allocations backward from the highest DPA. Cc: Greg KH Cc: Neil Brown Signed-off-by: Dan Williams --- drivers/block/nd/bus.c | 6 drivers/block/nd/core.c | 64 ++ drivers/block/nd/dimm.c | 2 drivers/block/nd/dimm_devs.c | 127 +++++ drivers/block/nd/label.c | 54 ++ drivers/block/nd/label.h | 3 drivers/block/nd/namespace_devs.c | 1020 +++++++++++++++++++++++++++++++++++++ drivers/block/nd/nd-private.h | 14 + drivers/block/nd/nd.h | 33 + drivers/block/nd/pmem.c | 22 + drivers/block/nd/region_devs.c | 147 +++++ include/linux/nd.h | 24 + include/uapi/linux/ndctl.h | 4 13 files changed, 1508 insertions(+), 12 deletions(-) diff --git a/drivers/block/nd/bus.c b/drivers/block/nd/bus.c index 944d7d7845fe..8e70098b6cb0 100644 --- a/drivers/block/nd/bus.c +++ b/drivers/block/nd/bus.c @@ -274,8 +274,10 @@ 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) +void wait_nd_bus_probe_idle(struct device *dev) { + struct nd_bus *nd_bus = walk_to_nd_bus(dev); + do { if (nd_bus->probe_active == 0) break; @@ -294,7 +296,7 @@ static int nd_cmd_clear_to_send(struct nd_dimm *nd_dimm, unsigned int cmd) return 0; nd_bus = walk_to_nd_bus(&nd_dimm->dev); - wait_nd_bus_probe_idle(nd_bus); + wait_nd_bus_probe_idle(&nd_bus->dev); if (atomic_read(&nd_dimm->busy)) return -EBUSY; diff --git a/drivers/block/nd/core.c b/drivers/block/nd/core.c index 976cd5e3ebaf..560ed5555496 100644 --- a/drivers/block/nd/core.c +++ b/drivers/block/nd/core.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -149,6 +150,69 @@ struct nd_bus *walk_to_nd_bus(struct device *nd_dev) return NULL; } +static bool is_uuid_sep(char sep) +{ + if (sep == '\n' || sep == '-' || sep == ':' || sep == '\0') + return true; + return false; +} + +static int nd_uuid_parse(struct device *dev, u8 *uuid_out, const char *buf, + size_t len) +{ + const char *str = buf; + u8 uuid[16]; + int i; + + for (i = 0; i < 16; i++) { + if (!isxdigit(str[0]) || !isxdigit(str[1])) { + dev_dbg(dev, "%s: pos: %d buf[%zd]: %c buf[%zd]: %c\n", + __func__, i, str - buf, str[0], + str + 1 - buf, str[1]); + return -EINVAL; + } + + uuid[i] = (hex_to_bin(str[0]) << 4) | hex_to_bin(str[1]); + str += 2; + if (is_uuid_sep(*str)) + str++; + } + + memcpy(uuid_out, uuid, sizeof(uuid)); + return 0; +} + +/** + * nd_uuid_store: common implementation for writing 'uuid' sysfs attributes + * @dev: container device for the uuid property + * @uuid_out: uuid buffer to replace + * @buf: raw sysfs buffer to parse + * + * Enforce that uuids can only be changed while the device is disabled + * (driver detached) + * LOCKING: expects device_lock() is held on entry + */ +int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf, + size_t len) +{ + u8 uuid[16]; + int rc; + + if (dev->driver) + return -EBUSY; + + rc = nd_uuid_parse(dev, uuid, buf, len); + if (rc) + return rc; + + kfree(*uuid_out); + *uuid_out = kmemdup(uuid, sizeof(uuid), GFP_KERNEL); + if (!(*uuid_out)) + return -ENOMEM; + + return 0; +} + static ssize_t commands_show(struct device *dev, struct device_attribute *attr, char *buf) { diff --git a/drivers/block/nd/dimm.c b/drivers/block/nd/dimm.c index ccc96d8fe2e7..eb62bc2848d3 100644 --- a/drivers/block/nd/dimm.c +++ b/drivers/block/nd/dimm.c @@ -97,7 +97,7 @@ static int nd_dimm_remove(struct device *dev) nd_bus_lock(dev); dev_set_drvdata(dev, NULL); for_each_dpa_resource_safe(ndd, res, _r) - __release_region(&ndd->dpa, res->start, resource_size(res)); + nd_dimm_free_dpa(ndd, res); nd_bus_unlock(dev); free_data(ndd); diff --git a/drivers/block/nd/dimm_devs.c b/drivers/block/nd/dimm_devs.c index 652dee210fe8..caa51d3ea6af 100644 --- a/drivers/block/nd/dimm_devs.c +++ b/drivers/block/nd/dimm_devs.c @@ -161,6 +161,14 @@ struct nd_dimm *to_nd_dimm(struct device *dev) return nd_dimm; } +struct nd_dimm_drvdata *to_ndd(struct nd_mapping *nd_mapping) +{ + struct nd_dimm *nd_dimm = nd_mapping->nd_dimm; + + return dev_get_drvdata(&nd_dimm->dev); +} +EXPORT_SYMBOL(to_ndd); + static struct nfit_mem __iomem *to_nfit_mem(struct device *dev) { struct nd_dimm *nd_dimm = to_nd_dimm(dev); @@ -408,6 +416,125 @@ static struct nd_dimm *nd_dimm_create(struct nd_bus *nd_bus, return NULL; } +/** + * nd_pmem_available_dpa - for the given dimm+region account unallocated dpa + * @nd_mapping: container of dpa-resource-root + labels + * @nd_region: constrain available space check to this reference region + * @overlap: calculate available space assuming this level of overlap + * + * Validate that a PMEM label, if present, aligns with the start of an + * interleave set and truncate the available size at the lowest BLK + * overlap point. + * + * The expectation is that this routine is called multiple times as it + * probes for the largest BLK encroachment for any single member DIMM of + * the interleave set. Once that value is determined the PMEM-limit for + * the set can be established. + */ +resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region, + struct nd_mapping *nd_mapping, resource_size_t *overlap) +{ + resource_size_t map_end, busy = 0, available, blk_start; + struct nd_dimm_drvdata *ndd = to_ndd(nd_mapping); + struct resource *res; + const char *reason; + + if (!ndd) + return 0; + + map_end = nd_mapping->start + nd_mapping->size - 1; + blk_start = max(nd_mapping->start, map_end + 1 - *overlap); + for_each_dpa_resource(ndd, res) + if (res->start >= nd_mapping->start && res->start < map_end) { + if (strncmp(res->name, "blk", 3) == 0) + blk_start = min(blk_start, res->start); + else if (res->start != nd_mapping->start) { + reason = "misaligned to iset"; + goto err; + } else { + if (busy) { + reason = "duplicate overlapping PMEM reservations?"; + goto err; + } + busy += resource_size(res); + continue; + } + } else if (res->end >= nd_mapping->start && res->end <= map_end) { + if (strncmp(res->name, "blk", 3) == 0) { + /* + * If a BLK allocation overlaps the start of + * PMEM the entire interleave set may now only + * be used for BLK. + */ + blk_start = nd_mapping->start; + } else { + reason = "misaligned to iset"; + goto err; + } + } else if (nd_mapping->start > res->start + && nd_mapping->start < res->end) { + /* total eclipse of the mapping */ + busy += nd_mapping->size; + blk_start = nd_mapping->start; + } + + *overlap = map_end + 1 - blk_start; + available = blk_start - nd_mapping->start; + if (busy < available) + return available - busy; + return 0; + + err: + /* + * Something is wrong, PMEM must align with the start of the + * interleave set, and there can only be one allocation per set. + */ + nd_dbg_dpa(nd_region, ndd, res, "%s\n", reason); + return 0; +} + +void nd_dimm_free_dpa(struct nd_dimm_drvdata *ndd, struct resource *res) +{ + WARN_ON_ONCE(!is_nd_bus_locked(ndd->dev)); + kfree(res->name); + __release_region(&ndd->dpa, res->start, resource_size(res)); +} + +struct resource *nd_dimm_allocate_dpa(struct nd_dimm_drvdata *ndd, + struct nd_label_id *label_id, resource_size_t start, + resource_size_t n) +{ + char *name = kmemdup(label_id, sizeof(*label_id), GFP_KERNEL); + struct resource *res; + + if (!name) + return NULL; + + WARN_ON_ONCE(!is_nd_bus_locked(ndd->dev)); + res = __request_region(&ndd->dpa, start, n, name, 0); + if (!res) + kfree(name); + return res; +} + +/** + * nd_dimm_allocated_dpa - sum up the dpa currently allocated to this label_id + * @nd_dimm: container of dpa-resource-root + labels + * @label_id: dpa resource name of the form {pmem|blk}- + */ +resource_size_t nd_dimm_allocated_dpa(struct nd_dimm_drvdata *ndd, + struct nd_label_id *label_id) +{ + resource_size_t allocated = 0; + struct resource *res; + + for_each_dpa_resource(ndd, res) + if (strcmp(res->name, label_id->id) == 0) + allocated += resource_size(res); + + return allocated; +} + static int count_dimms(struct device *dev, void *c) { int *count = c; diff --git a/drivers/block/nd/label.c b/drivers/block/nd/label.c index e791ea8bbdde..b55fa2a6f872 100644 --- a/drivers/block/nd/label.c +++ b/drivers/block/nd/label.c @@ -228,7 +228,7 @@ static bool preamble_current(struct nd_dimm_drvdata *ndd, return true; } -static char *nd_label_gen_id(struct nd_label_id *label_id, u8 *uuid, u32 flags) +char *nd_label_gen_id(struct nd_label_id *label_id, u8 *uuid, u32 flags) { if (!label_id || !uuid) return NULL; @@ -289,3 +289,55 @@ int nd_label_reserve_dpa(struct nd_dimm_drvdata *ndd) return 0; } + +int nd_label_active_count(struct nd_dimm_drvdata *ndd) +{ + struct nd_namespace_index __iomem *nsindex; + unsigned long *free; + u32 nslot, slot; + int count = 0; + + if (!preamble_current(ndd, &nsindex, &free, &nslot)) + return 0; + + for_each_clear_bit_le(slot, free, nslot) { + struct nd_namespace_label __iomem *nd_label; + + nd_label = nd_label_base(ndd) + slot; + + if (!slot_valid(nd_label, slot)) { + dev_dbg(ndd->dev, + "%s: slot%d invalid slot: %d dpa: %lx rawsize: %lx\n", + __func__, slot, readl(&nd_label->slot), + (unsigned long) readq(&nd_label->dpa), + (unsigned long) readq(&nd_label->rawsize)); + continue; + } + count++; + } + return count; +} + +struct nd_namespace_label __iomem *nd_label_active( + struct nd_dimm_drvdata *ndd, int n) +{ + struct nd_namespace_index __iomem *nsindex; + unsigned long *free; + u32 nslot, slot; + + if (!preamble_current(ndd, &nsindex, &free, &nslot)) + return NULL; + + for_each_clear_bit_le(slot, free, nslot) { + struct nd_namespace_label __iomem *nd_label; + + nd_label = nd_label_base(ndd) + slot; + if (slot != readl(&nd_label->slot)) + continue; + + if (n-- == 0) + return nd_label_base(ndd) + slot; + } + + return NULL; +} diff --git a/drivers/block/nd/label.h b/drivers/block/nd/label.h index 79ed885a43c0..4436624f4146 100644 --- a/drivers/block/nd/label.h +++ b/drivers/block/nd/label.h @@ -126,4 +126,7 @@ void nd_label_copy(struct nd_dimm_drvdata *ndd, struct nd_namespace_index *dst, struct nd_namespace_index *src); size_t sizeof_namespace_index(struct nd_dimm_drvdata *ndd); +int nd_label_active_count(struct nd_dimm_drvdata *ndd); +struct nd_namespace_label __iomem *nd_label_active( + struct nd_dimm_drvdata *ndd, int n); #endif /* __LABEL_H__ */ diff --git a/drivers/block/nd/namespace_devs.c b/drivers/block/nd/namespace_devs.c index 6861327f4245..386776845830 100644 --- a/drivers/block/nd/namespace_devs.c +++ b/drivers/block/nd/namespace_devs.c @@ -14,8 +14,11 @@ #include #include #include +#include "nd-private.h" #include "nd.h" +#include + static void namespace_io_release(struct device *dev) { struct nd_namespace_io *nsio = to_nd_namespace_io(dev); @@ -23,11 +26,50 @@ static void namespace_io_release(struct device *dev) kfree(nsio); } +static void namespace_pmem_release(struct device *dev) +{ + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + kfree(nspm->alt_name); + kfree(nspm->uuid); + kfree(nspm); +} + +static void namespace_blk_release(struct device *dev) +{ + /* TODO: blk namespace support */ +} + static struct device_type namespace_io_device_type = { .name = "nd_namespace_io", .release = namespace_io_release, }; +static struct device_type namespace_pmem_device_type = { + .name = "nd_namespace_pmem", + .release = namespace_pmem_release, +}; + +static struct device_type namespace_blk_device_type = { + .name = "nd_namespace_blk", + .release = namespace_blk_release, +}; + +static bool is_namespace_pmem(struct device *dev) +{ + return dev ? dev->type == &namespace_pmem_device_type : false; +} + +static bool is_namespace_blk(struct device *dev) +{ + return dev ? dev->type == &namespace_blk_device_type : false; +} + +static bool is_namespace_io(struct device *dev) +{ + return dev ? dev->type == &namespace_io_device_type : false; +} + static ssize_t type_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -37,13 +79,674 @@ static ssize_t type_show(struct device *dev, } static DEVICE_ATTR_RO(type); +static ssize_t __alt_name_store(struct device *dev, const char *buf, + const size_t len) +{ + char *input, *pos, *alt_name, **ns_altname; + ssize_t rc; + + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + ns_altname = &nspm->alt_name; + } else if (is_namespace_blk(dev)) { + /* TODO: blk namespace support */ + return -ENXIO; + } else + return -ENXIO; + + if (dev->driver) + return -EBUSY; + + input = kmemdup(buf, len + 1, GFP_KERNEL); + if (!input) + return -ENOMEM; + + input[len] = '\0'; + pos = strim(input); + if (strlen(pos) + 1 > NSLABEL_NAME_LEN) { + rc = -EINVAL; + goto out; + } + + alt_name = kzalloc(NSLABEL_NAME_LEN, GFP_KERNEL); + if (!alt_name) { + rc = -ENOMEM; + goto out; + } + kfree(*ns_altname); + *ns_altname = alt_name; + sprintf(*ns_altname, "%s", pos); + rc = len; + +out: + kfree(input); + return rc; +} + +static ssize_t alt_name_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + ssize_t rc; + + device_lock(dev); + nd_bus_lock(dev); + wait_nd_bus_probe_idle(dev); + rc = __alt_name_store(dev, buf, len); + dev_dbg(dev, "%s: %s (%zd)\n", __func__, rc < 0 ? "fail" : "success", rc); + nd_bus_unlock(dev); + device_unlock(dev); + + return rc; +} + +static ssize_t alt_name_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + char *ns_altname; + + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + ns_altname = nspm->alt_name; + } else if (is_namespace_blk(dev)) { + /* TODO: blk namespace support */ + return -ENXIO; + } else + return -ENXIO; + + return sprintf(buf, "%s\n", ns_altname ? ns_altname : ""); +} +static DEVICE_ATTR_RW(alt_name); + +static int scan_free(struct nd_region *nd_region, + struct nd_mapping *nd_mapping, struct nd_label_id *label_id, + resource_size_t n) +{ + bool is_blk = strncmp(label_id->id, "blk", 3) == 0; + struct nd_dimm_drvdata *ndd = to_ndd(nd_mapping); + int rc = 0; + + while (n) { + struct resource *res, *last; + resource_size_t new_start; + + last = NULL; + for_each_dpa_resource(ndd, res) + if (strcmp(res->name, label_id->id) == 0) + last = res; + res = last; + if (!res) + return 0; + + if (n >= resource_size(res)) { + n -= resource_size(res); + nd_dbg_dpa(nd_region, ndd, res, "delete %d\n", rc); + nd_dimm_free_dpa(ndd, res); + /* retry with last resource deleted */ + continue; + } + + /* + * Keep BLK allocations relegated to high DPA as much as + * possible + */ + if (is_blk) + new_start = res->start + n; + else + new_start = res->start; + + rc = adjust_resource(res, new_start, resource_size(res) - n); + nd_dbg_dpa(nd_region, ndd, res, "shrink %d\n", rc); + break; + } + + return rc; +} + +/** + * shrink_dpa_allocation - for each dimm in region free n bytes for label_id + * @nd_region: the set of dimms to reclaim @n bytes from + * @label_id: unique identifier for the namespace consuming this dpa range + * @n: number of bytes per-dimm to release + * + * Assumes resources are ordered. Starting from the end try to + * adjust_resource() the allocation to @n, but if @n is larger than the + * allocation delete it and find the 'new' last allocation in the label + * set. + */ +static int shrink_dpa_allocation(struct nd_region *nd_region, + struct nd_label_id *label_id, resource_size_t n) +{ + int i; + + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + int rc; + + rc = scan_free(nd_region, nd_mapping, label_id, n); + if (rc) + return rc; + } + + return 0; +} + +static resource_size_t init_dpa_allocation(struct nd_label_id *label_id, + struct nd_region *nd_region, struct nd_mapping *nd_mapping, + resource_size_t n) +{ + bool is_blk = strncmp(label_id->id, "blk", 3) == 0; + struct nd_dimm_drvdata *ndd = to_ndd(nd_mapping); + resource_size_t first_dpa; + struct resource *res; + int rc = 0; + + /* allocate blk from highest dpa first */ + if (is_blk) + first_dpa = nd_mapping->start + nd_mapping->size - n; + else + first_dpa = nd_mapping->start; + + /* first resource allocation for this label-id or dimm */ + res = nd_dimm_allocate_dpa(ndd, label_id, first_dpa, n); + if (!res) + rc = -EBUSY; + + nd_dbg_dpa(nd_region, ndd, res, "init %d\n", rc); + return rc ? n : 0; +} + +static bool space_valid(bool is_pmem, struct nd_label_id *label_id, + struct resource *res) +{ + /* + * For BLK-space any space is valid, for PMEM-space, it must be + * contiguous with an existing allocation. + */ + if (!is_pmem) + return true; + if (!res || strcmp(res->name, label_id->id) == 0) + return true; + return false; +} + +enum alloc_loc { + ALLOC_ERR = 0, ALLOC_BEFORE, ALLOC_MID, ALLOC_AFTER, +}; + +static resource_size_t scan_allocate(struct nd_region *nd_region, + struct nd_mapping *nd_mapping, struct nd_label_id *label_id, + resource_size_t n) +{ + resource_size_t mapping_end = nd_mapping->start + nd_mapping->size - 1; + bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0; + struct nd_dimm_drvdata *ndd = to_ndd(nd_mapping); + const resource_size_t to_allocate = n; + struct resource *res; + int first; + + retry: + first = 0; + for_each_dpa_resource(ndd, res) { + resource_size_t allocate, available = 0, free_start, free_end; + struct resource *next = res->sibling, *new_res = NULL; + enum alloc_loc loc = ALLOC_ERR; + const char *action; + int rc = 0; + + /* ignore resources outside this nd_mapping */ + if (res->start > mapping_end) + continue; + if (res->end < nd_mapping->start) + continue; + + /* space at the beginning of the mapping */ + if (!first++ && res->start > nd_mapping->start) { + free_start = nd_mapping->start; + available = res->start - free_start; + if (space_valid(is_pmem, label_id, NULL)) + loc = ALLOC_BEFORE; + } + + /* space between allocations */ + if (!loc && next) { + free_start = res->start + resource_size(res); + free_end = min(mapping_end, next->start - 1); + if (space_valid(is_pmem, label_id, res) + && free_start < free_end) { + available = free_end + 1 - free_start; + loc = ALLOC_MID; + } + } + + /* space at the end of the mapping */ + if (!loc && !next) { + free_start = res->start + resource_size(res); + free_end = mapping_end; + if (space_valid(is_pmem, label_id, res) + && free_start < free_end) { + available = free_end + 1 - free_start; + loc = ALLOC_AFTER; + } + } + + if (!loc || !available) + continue; + allocate = min(available, n); + switch (loc) { + case ALLOC_BEFORE: + if (strcmp(res->name, label_id->id) == 0) { + /* adjust current resource up */ + if (is_pmem) + return n; + rc = adjust_resource(res, res->start - allocate, + resource_size(res) + allocate); + action = "cur grow up"; + } else + action = "allocate"; + break; + case ALLOC_MID: + if (strcmp(next->name, label_id->id) == 0) { + /* adjust next resource up */ + if (is_pmem) + return n; + rc = adjust_resource(next, next->start + - allocate, resource_size(next) + + allocate); + new_res = next; + action = "next grow up"; + } else if (strcmp(res->name, label_id->id) == 0) { + action = "grow down"; + } else + action = "allocate"; + break; + case ALLOC_AFTER: + if (strcmp(res->name, label_id->id) == 0) + action = "grow down"; + else + action = "allocate"; + break; + default: + return n; + } + + if (strcmp(action, "allocate") == 0) { + /* BLK allocate bottom up */ + if (!is_pmem) + free_start += available - allocate; + else if (free_start != nd_mapping->start) + return n; + + new_res = nd_dimm_allocate_dpa(ndd, label_id, + free_start, allocate); + if (!new_res) + rc = -EBUSY; + } else if (strcmp(action, "grow down") == 0) { + /* adjust current resource down */ + rc = adjust_resource(res, res->start, resource_size(res) + + allocate); + } + + if (!new_res) + new_res = res; + + nd_dbg_dpa(nd_region, ndd, new_res, "%s(%d) %d\n", + action, loc, rc); + + if (rc) + return n; + + n -= allocate; + if (n) { + /* + * Retry scan with newly inserted resources. + * For example, if we did an ALLOC_BEFORE + * insertion there may also have been space + * available for an ALLOC_AFTER insertion, so we + * need to check this same resource again + */ + goto retry; + } else + return 0; + } + + if (is_pmem && n == to_allocate) + return init_dpa_allocation(label_id, nd_region, nd_mapping, n); + return n; +} + +/** + * grow_dpa_allocation - for each dimm allocate n bytes for @label_id + * @nd_region: the set of dimms to allocate @n more bytes from + * @label_id: unique identifier for the namespace consuming this dpa range + * @n: number of bytes per-dimm to add to the existing allocation + * + * Assumes resources are ordered. For BLK regions, first consume + * BLK-only available DPA free space, then consume PMEM-aliased DPA + * space starting at the highest DPA. For PMEM regions start + * allocations from the start of an interleave set and end at the first + * BLK allocation or the end of the interleave set, whichever comes + * first. + */ +static int grow_dpa_allocation(struct nd_region *nd_region, + struct nd_label_id *label_id, resource_size_t n) +{ + int i; + + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + int rc; + + rc = scan_allocate(nd_region, nd_mapping, label_id, n); + if (rc) + return rc; + } + + return 0; +} + +static void nd_namespace_pmem_set_size(struct nd_region *nd_region, + struct nd_namespace_pmem *nspm, resource_size_t size) +{ + struct resource *res = &nspm->nsio.res; + + res->start = nd_region->ndr_start; + res->end = nd_region->ndr_start + size - 1; +} + +static ssize_t __size_store(struct device *dev, unsigned long long val) +{ + resource_size_t allocated = 0, available = 0; + struct nd_region *nd_region = to_nd_region(dev->parent); + struct nd_mapping *nd_mapping; + struct nd_dimm_drvdata *ndd; + struct nd_label_id label_id; + u32 flags = 0, remainder; + u8 *uuid = NULL; + int rc, i; + + if (dev->driver) + return -EBUSY; + + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + uuid = nspm->uuid; + } else if (is_namespace_blk(dev)) { + /* TODO: blk namespace support */ + return -ENXIO; + } + + /* + * We need a uuid for the allocation-label and dimm(s) on which + * to store the label. + */ + if (!uuid || nd_region->ndr_mappings == 0) + return -ENXIO; + + div_u64_rem(val, SZ_4K * nd_region->ndr_mappings, &remainder); + if (remainder) { + dev_dbg(dev, "%llu is not %dK aligned\n", val, + (SZ_4K * nd_region->ndr_mappings) / SZ_1K); + return -EINVAL; + } + + nd_label_gen_id(&label_id, uuid, flags); + for (i = 0; i < nd_region->ndr_mappings; i++) { + nd_mapping = &nd_region->mapping[i]; + ndd = to_ndd(nd_mapping); + + /* + * All dimms in an interleave set, or the base dimm for a blk + * region, need to be enabled for the size to be changed. + */ + if (!ndd) + return -ENXIO; + + allocated += nd_dimm_allocated_dpa(ndd, &label_id); + } + available = nd_region_available_dpa(nd_region); + + if (val > available + allocated) + return -ENOSPC; + + if (val == allocated) + return 0; + + val = div_u64(val, nd_region->ndr_mappings); + allocated = div_u64(allocated, nd_region->ndr_mappings); + if (val < allocated) + rc = shrink_dpa_allocation(nd_region, &label_id, allocated - val); + else + rc = grow_dpa_allocation(nd_region, &label_id, val - allocated); + + if (rc) + return rc; + + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + nd_namespace_pmem_set_size(nd_region, nspm, + val * nd_region->ndr_mappings); + } + + return rc; +} + +static ssize_t size_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + unsigned long long val; + u8 **uuid = NULL; + int rc; + + rc = kstrtoull(buf, 0, &val); + if (rc) + return rc; + + device_lock(dev); + nd_bus_lock(dev); + wait_nd_bus_probe_idle(dev); + rc = __size_store(dev, val); + + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + uuid = &nspm->uuid; + } else if (is_namespace_blk(dev)) { + /* TODO: blk namespace support */ + rc = -ENXIO; + } + + if (rc == 0 && val == 0 && uuid) { + /* setting size zero == 'delete namespace' */ + kfree(*uuid); + *uuid = NULL; + } + + dev_dbg(dev, "%s: %llx %s (%d)\n", __func__, val, rc < 0 + ? "fail" : "success", rc); + + nd_bus_unlock(dev); + device_unlock(dev); + + return rc ? rc : len; +} + +static ssize_t size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + return sprintf(buf, "%llu\n", (unsigned long long) + resource_size(&nspm->nsio.res)); + } else if (is_namespace_blk(dev)) { + /* TODO: blk namespace support */ + return -ENXIO; + } else if (is_namespace_io(dev)) { + struct nd_namespace_io *nsio = to_nd_namespace_io(dev); + + return sprintf(buf, "%llu\n", (unsigned long long) + resource_size(&nsio->res)); + } else + return -ENXIO; +} +static DEVICE_ATTR(size, S_IRUGO, size_show, size_store); + +static ssize_t uuid_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + u8 *uuid; + + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + uuid = nspm->uuid; + } else if (is_namespace_blk(dev)) { + /* TODO: blk namespace support */ + return -ENXIO; + } else + return -ENXIO; + + if (uuid) + return sprintf(buf, "%pUb\n", uuid); + return sprintf(buf, "\n"); +} + +/** + * namespace_update_uuid - check for a unique uuid and whether we're "renaming" + * @nd_region: parent region so we can updates all dimms in the set + * @dev: namespace type for generating label_id + * @new_uuid: incoming uuid + * @old_uuid: reference to the uuid storage location in the namespace object + */ +static int namespace_update_uuid(struct nd_region *nd_region, + struct device *dev, u8 *new_uuid, u8 **old_uuid) +{ + u32 flags = is_namespace_blk(dev) ? NSLABEL_FLAG_LOCAL : 0; + struct nd_label_id old_label_id; + struct nd_label_id new_label_id; + int i, rc; + + rc = nd_is_uuid_unique(dev, new_uuid) ? 0 : -EINVAL; + if (rc) { + kfree(new_uuid); + return rc; + } + + if (*old_uuid == NULL) + goto out; + + nd_label_gen_id(&old_label_id, *old_uuid, flags); + nd_label_gen_id(&new_label_id, new_uuid, flags); + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nd_dimm_drvdata *ndd = to_ndd(nd_mapping); + struct resource *res; + + for_each_dpa_resource(ndd, res) + if (strcmp(res->name, old_label_id.id) == 0) + sprintf((void *) res->name, "%s", + new_label_id.id); + } + kfree(*old_uuid); + out: + *old_uuid = new_uuid; + return 0; +} + +static ssize_t uuid_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + struct nd_region *nd_region = to_nd_region(dev->parent); + u8 *uuid = NULL; + u8 **ns_uuid; + ssize_t rc; + + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + ns_uuid = &nspm->uuid; + } else if (is_namespace_blk(dev)) { + /* TODO: blk namespace support */ + return -ENXIO; + } else + return -ENXIO; + + device_lock(dev); + nd_bus_lock(dev); + wait_nd_bus_probe_idle(dev); + rc = nd_uuid_store(dev, &uuid, buf, len); + if (rc >= 0) + rc = namespace_update_uuid(nd_region, dev, uuid, ns_uuid); + dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__, + rc, buf, buf[len - 1] == '\n' ? "" : "\n"); + nd_bus_unlock(dev); + device_unlock(dev); + + return rc ? rc : len; +} +static DEVICE_ATTR_RW(uuid); + +static ssize_t resource_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct resource *res; + + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + res = &nspm->nsio.res; + } else if (is_namespace_io(dev)) { + struct nd_namespace_io *nsio = to_nd_namespace_io(dev); + + res = &nsio->res; + } else + return -ENXIO; + + /* no address to convey if the namespace has no allocation */ + if (resource_size(res) == 0) + return -ENXIO; + return sprintf(buf, "%#llx\n", (unsigned long long) res->start); +} +static DEVICE_ATTR_RO(resource); + static struct attribute *nd_namespace_attributes[] = { &dev_attr_type.attr, + &dev_attr_size.attr, + &dev_attr_uuid.attr, + &dev_attr_resource.attr, + &dev_attr_alt_name.attr, NULL, }; +static umode_t nd_namespace_attr_visible(struct kobject *kobj, struct attribute *a, int n) +{ + struct device *dev = container_of(kobj, struct device, kobj); + + if (a == &dev_attr_resource.attr) { + if (is_namespace_blk(dev)) + return 0; + return a->mode; + } + + if (is_namespace_pmem(dev) || is_namespace_blk(dev)) { + if (a == &dev_attr_size.attr) + return S_IWUSR; + return a->mode; + } + + if (a == &dev_attr_type.attr || a == &dev_attr_size.attr) + return a->mode; + + return 0; +} + static struct attribute_group nd_namespace_attribute_group = { .attrs = nd_namespace_attributes, + .is_visible = nd_namespace_attr_visible, }; static const struct attribute_group *nd_namespace_attribute_groups[] = { @@ -80,23 +783,322 @@ static struct device **create_namespace_io(struct nd_region *nd_region) return devs; } +static bool has_uuid_at_pos(struct nd_region *nd_region, u8 *uuid, u64 cookie, u16 pos) +{ + struct nd_namespace_label __iomem *found = NULL; + int i; + + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nd_namespace_label __iomem *nd_label; + u8 label_uuid[NSLABEL_UUID_LEN]; + u8 *found_uuid = NULL; + int l; + + for_each_label(l, nd_label, nd_mapping->labels) { + u64 isetcookie = readq(&nd_label->isetcookie); + u16 position = readw(&nd_label->position); + u16 nlabel = readw(&nd_label->nlabel); + + if (isetcookie != cookie) + continue; + + memcpy_fromio(label_uuid, nd_label->uuid, + NSLABEL_UUID_LEN); + if (memcmp(label_uuid, uuid, NSLABEL_UUID_LEN) != 0) + continue; + + if (found_uuid) { + dev_dbg(to_ndd(nd_mapping)->dev, + "%s duplicate entry for uuid\n", + __func__); + return false; + } + found_uuid = label_uuid; + if (nlabel != nd_region->ndr_mappings) + continue; + if (position != pos) + continue; + found = nd_label; + break; + } + if (found) + break; + } + return found != NULL; +} + +static int select_pmem_uuid(struct nd_region *nd_region, u8 *pmem_uuid) +{ + struct nd_namespace_label __iomem *select = NULL; + int i; + + if (!pmem_uuid) + return -ENODEV; + + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nd_namespace_label __iomem *nd_label; + u64 hw_start, hw_end, pmem_start, pmem_end; + int l; + + for_each_label(l, nd_label, nd_mapping->labels) { + u8 label_uuid[NSLABEL_UUID_LEN]; + + memcpy_fromio(label_uuid, nd_label->uuid, + NSLABEL_UUID_LEN); + if (memcmp(label_uuid, pmem_uuid, NSLABEL_UUID_LEN) == 0) + break; + } + + if (!nd_label) { + WARN_ON(1); + return -EINVAL; + } + + select = nd_label; + /* + * Check that this label is compliant with the dpa + * range published in NFIT + */ + hw_start = nd_mapping->start; + hw_end = hw_start + nd_mapping->size; + pmem_start = readq(&select->dpa); + pmem_end = pmem_start + readq(&select->rawsize); + if (pmem_start == hw_start && pmem_end <= hw_end) + /* pass */; + else + return -EINVAL; + + nd_set_label(nd_mapping->labels, select, 0); + nd_set_label(nd_mapping->labels, (void __iomem *) NULL, 1); + } + return 0; +} + +/** + * find_pmem_label_set - validate interleave set labelling, retrieve label0 + * @nd_region: region with mappings to validate + */ +static int find_pmem_label_set(struct nd_region *nd_region, + struct nd_namespace_pmem *nspm) +{ + u64 cookie = nd_region_interleave_set_cookie(nd_region); + struct nd_namespace_label __iomem *nd_label; + u8 select_uuid[NSLABEL_UUID_LEN]; + resource_size_t size = 0; + u8 *pmem_uuid = NULL; + int rc = -ENODEV, l; + u16 i; + + if (cookie == 0) + return -ENXIO; + + /* + * Find a complete set of labels by uuid. By definition we can start + * with any mapping as the reference label + */ + for_each_label(l, nd_label, nd_region->mapping[0].labels) { + u64 isetcookie = readq(&nd_label->isetcookie); + u8 label_uuid[NSLABEL_UUID_LEN]; + + if (isetcookie != cookie) + continue; + + memcpy_fromio(label_uuid, nd_label->uuid, + NSLABEL_UUID_LEN); + for (i = 0; nd_region->ndr_mappings; i++) + if (!has_uuid_at_pos(nd_region, label_uuid, cookie, i)) + break; + if (i < nd_region->ndr_mappings) { + /* + * Give up if we don't find an instance of a + * uuid at each position (from 0 to + * nd_region->ndr_mappings - 1), or if we find a + * dimm with two instances of the same uuid. + */ + rc = -EINVAL; + goto err; + } else if (pmem_uuid) { + /* + * If there is more than one valid uuid set, we + * need userspace to clean this up. + */ + rc = -EBUSY; + goto err; + } + memcpy(select_uuid, label_uuid, NSLABEL_UUID_LEN); + pmem_uuid = select_uuid; + } + + /* + * Fix up each mapping's 'labels' to have the validated pmem label for + * that position at labels[0], and NULL at labels[1]. In the process, + * check that the namespace aligns with interleave-set. We know + * that it does not overlap with any blk namespaces by virtue of + * the dimm being enabled (i.e. nd_label_reserve_dpa() + * succeeded). + */ + rc = select_pmem_uuid(nd_region, pmem_uuid); + if (rc) + goto err; + + /* Calculate total size and populate namespace properties from label0 */ + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nd_namespace_label __iomem *label0; + + label0 = nd_get_label(nd_mapping->labels, 0); + size += readq(&label0->rawsize); + if (readl(&label0->position) != 0) + continue; + WARN_ON(nspm->alt_name || nspm->uuid); + nspm->alt_name = kmemdup((void __force *) label0->name, + NSLABEL_NAME_LEN, GFP_KERNEL); + nspm->uuid = kmemdup((void __force *) label0->uuid, + NSLABEL_UUID_LEN, GFP_KERNEL); + } + + if (!nspm->alt_name || !nspm->uuid) { + rc = -ENOMEM; + goto err; + } + + nd_namespace_pmem_set_size(nd_region, nspm, size); + + return 0; + err: + switch (rc) { + case -EINVAL: + dev_dbg(&nd_region->dev, "%s: invalid label(s)\n", __func__); + break; + case -ENODEV: + dev_dbg(&nd_region->dev, "%s: label not found\n", __func__); + break; + default: + dev_dbg(&nd_region->dev, "%s: unexpected err: %d\n", __func__, rc); + break; + } + return rc; +} + +static struct device **create_namespace_pmem(struct nd_region *nd_region) +{ + struct nd_namespace_pmem *nspm; + struct device *dev, **devs; + struct resource *res; + int rc; + + nspm = kzalloc(sizeof(*nspm), GFP_KERNEL); + if (!nspm) + return NULL; + + dev = &nspm->nsio.dev; + dev->type = &namespace_pmem_device_type; + res = &nspm->nsio.res; + res->name = dev_name(&nd_region->dev); + res->flags = IORESOURCE_MEM; + rc = find_pmem_label_set(nd_region, nspm); + if (rc == -ENODEV) { + int i; + + /* Pass, try to permit namespace creation... */ + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + + kfree(nd_mapping->labels); + nd_mapping->labels = NULL; + } + + /* Publish a zero-sized namespace for userspace to configure. */ + nd_namespace_pmem_set_size(nd_region, nspm, 0); + + rc = 0; + } else if (rc) + goto err; + + devs = kcalloc(2, sizeof(struct device *), GFP_KERNEL); + if (!devs) + goto err; + + devs[0] = dev; + return devs; + + err: + namespace_pmem_release(&nspm->nsio.dev); + return NULL; +} + +static int init_active_labels(struct nd_region *nd_region) +{ + int i; + + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nd_dimm_drvdata *ndd = to_ndd(nd_mapping); + int count, j; + + /* + * If the dimm is disabled then prevent the region from + * being activated + */ + if (!ndd) { + dev_dbg(&nd_region->dev, "%s: is disabled, failing probe\n", + dev_name(&nd_mapping->nd_dimm->dev)); + return -ENXIO; + } + + count = nd_label_active_count(ndd); + dev_dbg(ndd->dev, "%s: %d\n", __func__, count); + if (!count) + continue; + nd_mapping->labels = kcalloc(count + 1, + sizeof(struct nd_namespace_label *), GFP_KERNEL); + if (!nd_mapping->labels) + return -ENOMEM; + for (j = 0; j < count; j++) { + struct nd_namespace_label __iomem *label; + + label = nd_label_active(ndd, j); + nd_set_label(nd_mapping->labels, label, j); + } + } + + return 0; +} + int nd_region_register_namespaces(struct nd_region *nd_region, int *err) { struct device **devs = NULL; - int i; + int i, rc = 0, type; *err = 0; - switch (nd_region_to_namespace_type(nd_region)) { + nd_bus_lock(&nd_region->dev); + rc = init_active_labels(nd_region); + if (rc) { + nd_bus_unlock(&nd_region->dev); + return rc; + } + + type = nd_region_to_namespace_type(nd_region); + switch (type) { case ND_DEVICE_NAMESPACE_IO: devs = create_namespace_io(nd_region); break; + case ND_DEVICE_NAMESPACE_PMEM: + devs = create_namespace_pmem(nd_region); + break; default: break; } + nd_bus_unlock(&nd_region->dev); - if (!devs) - return -ENODEV; + if (!devs) { + rc = -ENODEV; + goto err; + } + nd_region->ns_seed = devs[0]; for (i = 0; devs[i]; i++) { struct device *dev = devs[i]; @@ -108,4 +1110,14 @@ int nd_region_register_namespaces(struct nd_region *nd_region, int *err) kfree(devs); return i; + + err: + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + + kfree(nd_mapping->labels); + nd_mapping->labels = NULL; + } + + return rc; } diff --git a/drivers/block/nd/nd-private.h b/drivers/block/nd/nd-private.h index 15ca7be507ce..03b14ab8fc7d 100644 --- a/drivers/block/nd/nd-private.h +++ b/drivers/block/nd/nd-private.h @@ -123,4 +123,18 @@ 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); +struct nd_label_id; +char *nd_label_gen_id(struct nd_label_id *label_id, u8 *uuid, u32 flags); +bool nd_is_uuid_unique(struct device *dev, u8 *uuid); +struct nd_region; +struct nd_dimm_drvdata; +struct nd_mapping; +resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region, + struct nd_mapping *nd_mapping, resource_size_t *overlap); +resource_size_t nd_region_available_dpa(struct nd_region *nd_region); +struct resource *nd_dimm_allocate_dpa(struct nd_dimm_drvdata *ndd, + struct nd_label_id *label_id, resource_size_t start, + resource_size_t n); +resource_size_t nd_dimm_allocated_dpa(struct nd_dimm_drvdata *ndd, + struct nd_label_id *label_id); #endif /* __ND_PRIVATE_H__ */ diff --git a/drivers/block/nd/nd.h b/drivers/block/nd/nd.h index f8dee1df5e6a..386e17056d3c 100644 --- a/drivers/block/nd/nd.h +++ b/drivers/block/nd/nd.h @@ -15,6 +15,7 @@ #include #include #include +#include #include "label.h" struct nd_dimm_drvdata { @@ -54,6 +55,7 @@ static inline struct nd_namespace_index __iomem *to_next_namespace_index( struct nd_mapping { struct nd_dimm *nd_dimm; + struct nd_namespace_label **labels; u64 start; u64 size; }; @@ -64,6 +66,30 @@ struct nd_mapping { (unsigned long long) (res ? resource_size(res) : 0), \ (unsigned long long) (res ? res->start : 0), ##arg) +/* sparse helpers */ +static inline void nd_set_label(struct nd_namespace_label **labels, + struct nd_namespace_label __iomem *label, int idx) +{ + labels[idx] = (void __force *) label; +} + +static inline struct nd_namespace_label __iomem *nd_get_label( + struct nd_namespace_label **labels, int idx) +{ + struct nd_namespace_label __iomem *label = NULL; + + if (labels) + label = (struct nd_namespace_label __iomem *) labels[idx]; + + return label; +} + +#define for_each_label(l, label, labels) \ + for (l = 0; (label = nd_get_label(labels, l)); l++) + +#define for_each_dpa_resource(ndd, res) \ + for (res = (ndd)->dpa.child; res; res = res->sibling) + #define for_each_dpa_resource_safe(ndd, res, next) \ for (res = (ndd)->dpa.child, next = res ? res->sibling : NULL; \ res; res = next, next = next ? next->sibling : NULL) @@ -71,6 +97,7 @@ struct nd_mapping { struct nd_region { struct device dev; struct nd_spa *nd_spa; + struct device *ns_seed; u16 ndr_mappings; u64 ndr_size; u64 ndr_start; @@ -92,11 +119,15 @@ enum nd_async_mode { ND_ASYNC, }; +void wait_nd_bus_probe_idle(struct device *dev); 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); +int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf, + size_t len); extern struct attribute_group nd_device_attribute_group; struct nd_dimm; +struct nd_dimm_drvdata *to_ndd(struct nd_mapping *nd_mapping); u32 to_nfit_handle(struct nd_dimm *nd_dimm); void *nd_dimm_get_pdata(struct nd_dimm *nd_dimm); void nd_dimm_set_pdata(struct nd_dimm *nd_dimm, void *data); @@ -108,8 +139,10 @@ 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); +u64 nd_region_interleave_set_cookie(struct nd_region *nd_region); void nd_bus_lock(struct device *dev); void nd_bus_unlock(struct device *dev); bool is_nd_bus_locked(struct device *dev); int nd_label_reserve_dpa(struct nd_dimm_drvdata *ndd); +void nd_dimm_free_dpa(struct nd_dimm_drvdata *ndd, struct resource *res); #endif /* __ND_H__ */ diff --git a/drivers/block/nd/pmem.c b/drivers/block/nd/pmem.c index cd83a9a98d89..aa2b4fb1f140 100644 --- a/drivers/block/nd/pmem.c +++ b/drivers/block/nd/pmem.c @@ -24,6 +24,7 @@ #include #include #include +#include "nd.h" #define PMEM_MINORS 16 @@ -247,9 +248,27 @@ static struct platform_driver pmem_driver = { static int nd_pmem_probe(struct device *dev) { + struct nd_region *nd_region = to_nd_region(dev->parent); struct nd_namespace_io *nsio = to_nd_namespace_io(dev); struct pmem_device *pmem; + if (resource_size(&nsio->res) < ND_MIN_NAMESPACE_SIZE) { + resource_size_t size = resource_size(&nsio->res); + + dev_dbg(dev, "%s: size: %pa, too small must be at least %#x\n", + __func__, &size, ND_MIN_NAMESPACE_SIZE); + return -ENODEV; + } + + if (nd_region_to_namespace_type(nd_region) == ND_DEVICE_NAMESPACE_PMEM) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + if (!nspm->uuid) { + dev_dbg(dev, "%s: uuid not set\n", __func__); + return -ENODEV; + } + } + pmem = pmem_alloc(dev, &nsio->res); if (IS_ERR(pmem)) return PTR_ERR(pmem); @@ -269,13 +288,14 @@ static int nd_pmem_remove(struct device *dev) MODULE_ALIAS("pmem"); MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_IO); +MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_PMEM); static struct nd_device_driver nd_pmem_driver = { .probe = nd_pmem_probe, .remove = nd_pmem_remove, .drv = { .name = "pmem", }, - .type = ND_DRIVER_NAMESPACE_IO, + .type = ND_DRIVER_NAMESPACE_IO | ND_DRIVER_NAMESPACE_PMEM, }; static int __init pmem_init(void) diff --git a/drivers/block/nd/region_devs.c b/drivers/block/nd/region_devs.c index 13f45be755a5..8bcfd9b91a71 100644 --- a/drivers/block/nd/region_devs.c +++ b/drivers/block/nd/region_devs.c @@ -15,6 +15,7 @@ #include #include #include +#include #include "nd-private.h" #include "nfit.h" #include "nd.h" @@ -70,6 +71,7 @@ struct nd_region *to_nd_region(struct device *dev) WARN_ON(dev->type->release != nd_region_release); return nd_region; } +EXPORT_SYMBOL(to_nd_region); /** * nd_region_to_namespace_type() - region to an integer namespace type @@ -92,6 +94,58 @@ int nd_region_to_namespace_type(struct nd_region *nd_region) return 0; } +EXPORT_SYMBOL(nd_region_to_namespace_type); + +static int is_uuid_busy(struct device *dev, void *data) +{ + struct nd_region *nd_region = to_nd_region(dev->parent); + u8 *uuid = data; + + switch (nd_region_to_namespace_type(nd_region)) { + case ND_DEVICE_NAMESPACE_PMEM: { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + if (!nspm->uuid) + break; + if (memcmp(uuid, nspm->uuid, NSLABEL_UUID_LEN) == 0) + return -EBUSY; + break; + } + case ND_DEVICE_NAMESPACE_BLOCK: { + /* TODO: blk namespace support */ + break; + } + default: + break; + } + + return 0; +} + +static int is_namespace_uuid_busy(struct device *dev, void *data) +{ + if (is_nd_pmem(dev) || is_nd_blk(dev)) + return device_for_each_child(dev, data, is_uuid_busy); + return 0; +} + +/** + * nd_is_uuid_unique - verify that no other namespace has @uuid + * @dev: any device on a nd_bus + * @uuid: uuid to check + */ +bool nd_is_uuid_unique(struct device *dev, u8 *uuid) +{ + struct nd_bus *nd_bus = walk_to_nd_bus(dev); + + if (!nd_bus) + return false; + WARN_ON_ONCE(!is_nd_bus_locked(&nd_bus->dev)); + if (device_for_each_child(&nd_bus->dev, uuid, + is_namespace_uuid_busy) != 0) + return false; + return true; +} static ssize_t size_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -155,6 +209,60 @@ static ssize_t set_cookie_show(struct device *dev, } static DEVICE_ATTR_RO(set_cookie); +resource_size_t nd_region_available_dpa(struct nd_region *nd_region) +{ + resource_size_t blk_max_overlap = 0, available, overlap; + int i; + + WARN_ON(!is_nd_bus_locked(&nd_region->dev)); + + retry: + available = 0; + overlap = blk_max_overlap; + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nd_dimm_drvdata *ndd = to_ndd(nd_mapping); + + /* if a dimm is disabled the available capacity is zero */ + if (!ndd) + return 0; + + if (is_nd_pmem(&nd_region->dev)) { + available += nd_pmem_available_dpa(nd_region, + nd_mapping, &overlap); + if (overlap > blk_max_overlap) { + blk_max_overlap = overlap; + goto retry; + } + } else if (is_nd_blk(&nd_region->dev)) { + /* TODO: BLK Namespace support */ + } + } + + return available; +} + +static ssize_t available_size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_region *nd_region = to_nd_region(dev); + unsigned long long available = 0; + + /* + * Flush in-flight updates and grab a snapshot of the available + * size. Of course, this value is potentially invalidated the + * memory nd_bus_lock() is dropped, but that's userspace's + * problem to not race itself. + */ + nd_bus_lock(dev); + wait_nd_bus_probe_idle(dev); + available = nd_region_available_dpa(nd_region); + nd_bus_unlock(dev); + + return sprintf(buf, "%llu\n", available); +} +static DEVICE_ATTR_RO(available_size); + static ssize_t init_namespaces_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -167,12 +275,30 @@ static ssize_t init_namespaces_show(struct device *dev, } static DEVICE_ATTR_RO(init_namespaces); +static ssize_t namespace_seed_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_region *nd_region = to_nd_region(dev); + ssize_t rc; + + nd_bus_lock(dev); + if (nd_region->ns_seed) + rc = sprintf(buf, "%s\n", dev_name(nd_region->ns_seed)); + else + rc = sprintf(buf, "\n"); + nd_bus_unlock(dev); + return rc; +} +static DEVICE_ATTR_RO(namespace_seed); + static struct attribute *nd_region_attributes[] = { &dev_attr_size.attr, &dev_attr_nstype.attr, &dev_attr_mappings.attr, &dev_attr_spa_index.attr, &dev_attr_set_cookie.attr, + &dev_attr_available_size.attr, + &dev_attr_namespace_seed.attr, &dev_attr_init_namespaces.attr, NULL, }; @@ -181,13 +307,18 @@ static umode_t nd_region_visible(struct kobject *kobj, struct attribute *a, int { struct device *dev = container_of(kobj, typeof(*dev), kobj); struct nd_region *nd_region = to_nd_region(dev); + int type = nd_region_to_namespace_type(nd_region); struct nd_spa *nd_spa = nd_region->nd_spa; - if (a != &dev_attr_set_cookie.attr) + if (a != &dev_attr_set_cookie.attr && a != &dev_attr_available_size.attr) return a->mode; - if (is_nd_pmem(dev) && nd_spa->nd_set) - return a->mode; + if ((type == ND_DEVICE_NAMESPACE_PMEM + || type == ND_DEVICE_NAMESPACE_BLOCK) + && a == &dev_attr_available_size.attr) + return a->mode; + else if (is_nd_pmem(dev) && nd_spa->nd_set) + return a->mode; return 0; } @@ -330,6 +461,16 @@ int nd_bus_init_interleave_sets(struct nd_bus *nd_bus) return rc; } +u64 nd_region_interleave_set_cookie(struct nd_region *nd_region) +{ + struct nd_spa *nd_spa = nd_region->nd_spa; + struct nd_interleave_set *nd_set = nd_spa ? nd_spa->nd_set : NULL; + + if (nd_set) + return nd_set->cookie; + return 0; +} + /* * Upon successful probe/remove, take/release a reference on the * associated interleave set (if present) diff --git a/include/linux/nd.h b/include/linux/nd.h index da70e9962197..255c38a83083 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -28,16 +28,40 @@ static inline struct nd_device_driver *to_nd_device_driver( return container_of(drv, struct nd_device_driver, drv); }; +/** + * struct nd_namespace_io - infrastructure for loading an nd_pmem instance + * @dev: namespace device created by the nd region driver + * @res: struct resource conversion of a NFIT SPA table + */ struct nd_namespace_io { struct device dev; struct resource res; }; +/** + * struct nd_namespace_pmem - namespace device for dimm-backed interleaved memory + * @nsio: device and system physical address range to drive + * @alt_name: namespace name supplied in the dimm label + * @uuid: namespace name supplied in the dimm label + */ +struct nd_namespace_pmem { + struct nd_namespace_io nsio; + char *alt_name; + u8 *uuid; +}; + static inline struct nd_namespace_io *to_nd_namespace_io(struct device *dev) { return container_of(dev, struct nd_namespace_io, dev); } +static inline struct nd_namespace_pmem *to_nd_namespace_pmem(struct device *dev) +{ + struct nd_namespace_io *nsio = to_nd_namespace_io(dev); + + return container_of(nsio, struct nd_namespace_pmem, nsio); +} + #define MODULE_ALIAS_ND_DEVICE(type) \ MODULE_ALIAS("nd:t" __stringify(type) "*") #define ND_DEVICE_MODALIAS_FMT "nd:t%d" diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index 097e67a8d477..5f0cf00872e0 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -190,4 +190,8 @@ enum nd_driver_flags { ND_DRIVER_NAMESPACE_PMEM = 1 << ND_DEVICE_NAMESPACE_PMEM, ND_DRIVER_NAMESPACE_BLOCK = 1 << ND_DEVICE_NAMESPACE_BLOCK, }; + +enum { + ND_MIN_NAMESPACE_SIZE = 0x00400000, +}; #endif /* __NDCTL_H__ */ -- 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/