From 047fc8a1f9a6330eacc80374dff087e20dc2304b Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Thu, 25 Jun 2015 04:21:02 -0400 Subject: libnvdimm, nfit, nd_blk: driver for BLK-mode access persistent memory The libnvdimm implementation handles allocating dimm address space (DPA) between PMEM and BLK mode interfaces. After DPA has been allocated from a BLK-region to a BLK-namespace the nd_blk driver attaches to handle I/O as a struct bio based block device. Unlike PMEM, BLK is required to handle platform specific details like mmio register formats and memory controller interleave. For this reason the libnvdimm generic nd_blk driver calls back into the bus provider to carry out the I/O. This initial implementation handles the BLK interface defined by the ACPI 6 NFIT [1] and the NVDIMM DSM Interface Example [2] composed from DCR (dimm control region), BDW (block data window), IDT (interleave descriptor) NFIT structures and the hardware register format. [1]: http://www.uefi.org/sites/default/files/resources/ACPI_6.0.pdf [2]: http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf Cc: Andy Lutomirski Cc: Boaz Harrosh Cc: H. Peter Anvin Cc: Jens Axboe Cc: Ingo Molnar Cc: Christoph Hellwig Signed-off-by: Ross Zwisler Acked-by: Rafael J. Wysocki Signed-off-by: Dan Williams --- drivers/acpi/nfit.c | 449 ++++++++++++++++++++++++++++++++++++++-- drivers/acpi/nfit.h | 49 +++++ drivers/nvdimm/Kconfig | 13 ++ drivers/nvdimm/Makefile | 3 + drivers/nvdimm/blk.c | 245 ++++++++++++++++++++++ drivers/nvdimm/dimm_devs.c | 9 + drivers/nvdimm/namespace_devs.c | 65 +++++- drivers/nvdimm/nd-core.h | 3 +- drivers/nvdimm/nd.h | 13 +- drivers/nvdimm/region.c | 8 +- drivers/nvdimm/region_devs.c | 91 +++++++- 11 files changed, 916 insertions(+), 32 deletions(-) create mode 100644 drivers/nvdimm/blk.c (limited to 'drivers') diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index fc38b49eff7d..2aa6aa97b40c 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -13,12 +13,20 @@ #include #include #include +#include #include #include #include #include +#include #include "nfit.h" +/* + * For readq() and writeq() on 32-bit builds, the hi-lo, lo-hi order is + * irrelevant. + */ +#include + static bool force_enable_dimms; module_param(force_enable_dimms, bool, S_IRUGO|S_IWUSR); MODULE_PARM_DESC(force_enable_dimms, "Ignore _STA (ACPI DIMM device) status"); @@ -72,7 +80,7 @@ static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, if (!adev) return -ENOTTY; - dimm_name = dev_name(&adev->dev); + dimm_name = nvdimm_name(nvdimm); cmd_name = nvdimm_cmd_name(cmd); dsm_mask = nfit_mem->dsm_mask; desc = nd_cmd_dimm_desc(cmd); @@ -279,6 +287,23 @@ static bool add_bdw(struct acpi_nfit_desc *acpi_desc, return true; } +static bool add_idt(struct acpi_nfit_desc *acpi_desc, + struct acpi_nfit_interleave *idt) +{ + struct device *dev = acpi_desc->dev; + struct nfit_idt *nfit_idt = devm_kzalloc(dev, sizeof(*nfit_idt), + GFP_KERNEL); + + if (!nfit_idt) + return false; + INIT_LIST_HEAD(&nfit_idt->list); + nfit_idt->idt = idt; + list_add_tail(&nfit_idt->list, &acpi_desc->idts); + dev_dbg(dev, "%s: idt index: %d num_lines: %d\n", __func__, + idt->interleave_index, idt->line_count); + return true; +} + static void *add_table(struct acpi_nfit_desc *acpi_desc, void *table, const void *end) { @@ -307,9 +332,9 @@ static void *add_table(struct acpi_nfit_desc *acpi_desc, void *table, if (!add_bdw(acpi_desc, table)) return err; break; - /* TODO */ case ACPI_NFIT_TYPE_INTERLEAVE: - dev_dbg(dev, "%s: idt\n", __func__); + if (!add_idt(acpi_desc, table)) + return err; break; case ACPI_NFIT_TYPE_FLUSH_ADDRESS: dev_dbg(dev, "%s: flush\n", __func__); @@ -362,8 +387,11 @@ static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc, struct nfit_mem *nfit_mem, struct acpi_nfit_system_address *spa) { u16 dcr = __to_nfit_memdev(nfit_mem)->region_index; + struct nfit_memdev *nfit_memdev; struct nfit_dcr *nfit_dcr; struct nfit_bdw *nfit_bdw; + struct nfit_idt *nfit_idt; + u16 idt_idx, range_index; list_for_each_entry(nfit_dcr, &acpi_desc->dcrs, list) { if (nfit_dcr->dcr->region_index != dcr) @@ -396,6 +424,26 @@ static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc, return 0; nfit_mem_find_spa_bdw(acpi_desc, nfit_mem); + + if (!nfit_mem->spa_bdw) + return 0; + + range_index = nfit_mem->spa_bdw->range_index; + list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { + if (nfit_memdev->memdev->range_index != range_index || + nfit_memdev->memdev->region_index != dcr) + continue; + nfit_mem->memdev_bdw = nfit_memdev->memdev; + idt_idx = nfit_memdev->memdev->interleave_index; + list_for_each_entry(nfit_idt, &acpi_desc->idts, list) { + if (nfit_idt->idt->interleave_index != idt_idx) + continue; + nfit_mem->idt_bdw = nfit_idt->idt; + break; + } + break; + } + return 0; } @@ -439,9 +487,19 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, } if (type == NFIT_SPA_DCR) { + struct nfit_idt *nfit_idt; + u16 idt_idx; + /* multiple dimms may share a SPA when interleaved */ nfit_mem->spa_dcr = spa; nfit_mem->memdev_dcr = nfit_memdev->memdev; + idt_idx = nfit_memdev->memdev->interleave_index; + list_for_each_entry(nfit_idt, &acpi_desc->idts, list) { + if (nfit_idt->idt->interleave_index != idt_idx) + continue; + nfit_mem->idt_dcr = nfit_idt->idt; + break; + } } else { /* * A single dimm may belong to multiple SPA-PM @@ -871,6 +929,359 @@ static int acpi_nfit_init_interleave_set(struct acpi_nfit_desc *acpi_desc, return 0; } +static u64 to_interleave_offset(u64 offset, struct nfit_blk_mmio *mmio) +{ + struct acpi_nfit_interleave *idt = mmio->idt; + u32 sub_line_offset, line_index, line_offset; + u64 line_no, table_skip_count, table_offset; + + line_no = div_u64_rem(offset, mmio->line_size, &sub_line_offset); + table_skip_count = div_u64_rem(line_no, mmio->num_lines, &line_index); + line_offset = idt->line_offset[line_index] + * mmio->line_size; + table_offset = table_skip_count * mmio->table_size; + + return mmio->base_offset + line_offset + table_offset + sub_line_offset; +} + +static u64 read_blk_stat(struct nfit_blk *nfit_blk, unsigned int bw) +{ + struct nfit_blk_mmio *mmio = &nfit_blk->mmio[DCR]; + u64 offset = nfit_blk->stat_offset + mmio->size * bw; + + if (mmio->num_lines) + offset = to_interleave_offset(offset, mmio); + + return readq(mmio->base + offset); +} + +static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw, + resource_size_t dpa, unsigned int len, unsigned int write) +{ + u64 cmd, offset; + struct nfit_blk_mmio *mmio = &nfit_blk->mmio[DCR]; + + enum { + BCW_OFFSET_MASK = (1ULL << 48)-1, + BCW_LEN_SHIFT = 48, + BCW_LEN_MASK = (1ULL << 8) - 1, + BCW_CMD_SHIFT = 56, + }; + + cmd = (dpa >> L1_CACHE_SHIFT) & BCW_OFFSET_MASK; + len = len >> L1_CACHE_SHIFT; + cmd |= ((u64) len & BCW_LEN_MASK) << BCW_LEN_SHIFT; + cmd |= ((u64) write) << BCW_CMD_SHIFT; + + offset = nfit_blk->cmd_offset + mmio->size * bw; + if (mmio->num_lines) + offset = to_interleave_offset(offset, mmio); + + writeq(cmd, mmio->base + offset); + /* FIXME: conditionally perform read-back if mandated by firmware */ +} + +static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk, + resource_size_t dpa, void *iobuf, size_t len, int rw, + unsigned int lane) +{ + struct nfit_blk_mmio *mmio = &nfit_blk->mmio[BDW]; + unsigned int copied = 0; + u64 base_offset; + int rc; + + base_offset = nfit_blk->bdw_offset + dpa % L1_CACHE_BYTES + + lane * mmio->size; + /* TODO: non-temporal access, flush hints, cache management etc... */ + write_blk_ctl(nfit_blk, lane, dpa, len, rw); + while (len) { + unsigned int c; + u64 offset; + + if (mmio->num_lines) { + u32 line_offset; + + offset = to_interleave_offset(base_offset + copied, + mmio); + div_u64_rem(offset, mmio->line_size, &line_offset); + c = min_t(size_t, len, mmio->line_size - line_offset); + } else { + offset = base_offset + nfit_blk->bdw_offset; + c = len; + } + + if (rw) + memcpy(mmio->aperture + offset, iobuf + copied, c); + else + memcpy(iobuf + copied, mmio->aperture + offset, c); + + copied += c; + len -= c; + } + rc = read_blk_stat(nfit_blk, lane) ? -EIO : 0; + return rc; +} + +static int acpi_nfit_blk_region_do_io(struct nd_blk_region *ndbr, + resource_size_t dpa, void *iobuf, u64 len, int rw) +{ + struct nfit_blk *nfit_blk = nd_blk_region_provider_data(ndbr); + struct nfit_blk_mmio *mmio = &nfit_blk->mmio[BDW]; + struct nd_region *nd_region = nfit_blk->nd_region; + unsigned int lane, copied = 0; + int rc = 0; + + lane = nd_region_acquire_lane(nd_region); + while (len) { + u64 c = min(len, mmio->size); + + rc = acpi_nfit_blk_single_io(nfit_blk, dpa + copied, + iobuf + copied, c, rw, lane); + if (rc) + break; + + copied += c; + len -= c; + } + nd_region_release_lane(nd_region, lane); + + return rc; +} + +static void nfit_spa_mapping_release(struct kref *kref) +{ + struct nfit_spa_mapping *spa_map = to_spa_map(kref); + struct acpi_nfit_system_address *spa = spa_map->spa; + struct acpi_nfit_desc *acpi_desc = spa_map->acpi_desc; + + WARN_ON(!mutex_is_locked(&acpi_desc->spa_map_mutex)); + dev_dbg(acpi_desc->dev, "%s: SPA%d\n", __func__, spa->range_index); + iounmap(spa_map->iomem); + release_mem_region(spa->address, spa->length); + list_del(&spa_map->list); + kfree(spa_map); +} + +static struct nfit_spa_mapping *find_spa_mapping( + struct acpi_nfit_desc *acpi_desc, + struct acpi_nfit_system_address *spa) +{ + struct nfit_spa_mapping *spa_map; + + WARN_ON(!mutex_is_locked(&acpi_desc->spa_map_mutex)); + list_for_each_entry(spa_map, &acpi_desc->spa_maps, list) + if (spa_map->spa == spa) + return spa_map; + + return NULL; +} + +static void nfit_spa_unmap(struct acpi_nfit_desc *acpi_desc, + struct acpi_nfit_system_address *spa) +{ + struct nfit_spa_mapping *spa_map; + + mutex_lock(&acpi_desc->spa_map_mutex); + spa_map = find_spa_mapping(acpi_desc, spa); + + if (spa_map) + kref_put(&spa_map->kref, nfit_spa_mapping_release); + mutex_unlock(&acpi_desc->spa_map_mutex); +} + +static void __iomem *__nfit_spa_map(struct acpi_nfit_desc *acpi_desc, + struct acpi_nfit_system_address *spa) +{ + resource_size_t start = spa->address; + resource_size_t n = spa->length; + struct nfit_spa_mapping *spa_map; + struct resource *res; + + WARN_ON(!mutex_is_locked(&acpi_desc->spa_map_mutex)); + + spa_map = find_spa_mapping(acpi_desc, spa); + if (spa_map) { + kref_get(&spa_map->kref); + return spa_map->iomem; + } + + spa_map = kzalloc(sizeof(*spa_map), GFP_KERNEL); + if (!spa_map) + return NULL; + + INIT_LIST_HEAD(&spa_map->list); + spa_map->spa = spa; + kref_init(&spa_map->kref); + spa_map->acpi_desc = acpi_desc; + + res = request_mem_region(start, n, dev_name(acpi_desc->dev)); + if (!res) + goto err_mem; + + /* TODO: cacheability based on the spa type */ + spa_map->iomem = ioremap_nocache(start, n); + if (!spa_map->iomem) + goto err_map; + + list_add_tail(&spa_map->list, &acpi_desc->spa_maps); + return spa_map->iomem; + + err_map: + release_mem_region(start, n); + err_mem: + kfree(spa_map); + return NULL; +} + +/** + * nfit_spa_map - interleave-aware managed-mappings of acpi_nfit_system_address ranges + * @nvdimm_bus: NFIT-bus that provided the spa table entry + * @nfit_spa: spa table to map + * + * In the case where block-data-window apertures and + * dimm-control-regions are interleaved they will end up sharing a + * single request_mem_region() + ioremap() for the address range. In + * the style of devm nfit_spa_map() mappings are automatically dropped + * when all region devices referencing the same mapping are disabled / + * unbound. + */ +static void __iomem *nfit_spa_map(struct acpi_nfit_desc *acpi_desc, + struct acpi_nfit_system_address *spa) +{ + void __iomem *iomem; + + mutex_lock(&acpi_desc->spa_map_mutex); + iomem = __nfit_spa_map(acpi_desc, spa); + mutex_unlock(&acpi_desc->spa_map_mutex); + + return iomem; +} + +static int nfit_blk_init_interleave(struct nfit_blk_mmio *mmio, + struct acpi_nfit_interleave *idt, u16 interleave_ways) +{ + if (idt) { + mmio->num_lines = idt->line_count; + mmio->line_size = idt->line_size; + if (interleave_ways == 0) + return -ENXIO; + mmio->table_size = mmio->num_lines * interleave_ways + * mmio->line_size; + } + + return 0; +} + +static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus, + struct device *dev) +{ + struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus); + struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc); + struct nd_blk_region *ndbr = to_nd_blk_region(dev); + struct nfit_blk_mmio *mmio; + struct nfit_blk *nfit_blk; + struct nfit_mem *nfit_mem; + struct nvdimm *nvdimm; + int rc; + + nvdimm = nd_blk_region_to_dimm(ndbr); + nfit_mem = nvdimm_provider_data(nvdimm); + if (!nfit_mem || !nfit_mem->dcr || !nfit_mem->bdw) { + dev_dbg(dev, "%s: missing%s%s%s\n", __func__, + nfit_mem ? "" : " nfit_mem", + nfit_mem->dcr ? "" : " dcr", + nfit_mem->bdw ? "" : " bdw"); + return -ENXIO; + } + + nfit_blk = devm_kzalloc(dev, sizeof(*nfit_blk), GFP_KERNEL); + if (!nfit_blk) + return -ENOMEM; + nd_blk_region_set_provider_data(ndbr, nfit_blk); + nfit_blk->nd_region = to_nd_region(dev); + + /* map block aperture memory */ + nfit_blk->bdw_offset = nfit_mem->bdw->offset; + mmio = &nfit_blk->mmio[BDW]; + mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_bdw); + if (!mmio->base) { + dev_dbg(dev, "%s: %s failed to map bdw\n", __func__, + nvdimm_name(nvdimm)); + return -ENOMEM; + } + mmio->size = nfit_mem->bdw->size; + mmio->base_offset = nfit_mem->memdev_bdw->region_offset; + mmio->idt = nfit_mem->idt_bdw; + mmio->spa = nfit_mem->spa_bdw; + rc = nfit_blk_init_interleave(mmio, nfit_mem->idt_bdw, + nfit_mem->memdev_bdw->interleave_ways); + if (rc) { + dev_dbg(dev, "%s: %s failed to init bdw interleave\n", + __func__, nvdimm_name(nvdimm)); + return rc; + } + + /* map block control memory */ + nfit_blk->cmd_offset = nfit_mem->dcr->command_offset; + nfit_blk->stat_offset = nfit_mem->dcr->status_offset; + mmio = &nfit_blk->mmio[DCR]; + mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_dcr); + if (!mmio->base) { + dev_dbg(dev, "%s: %s failed to map dcr\n", __func__, + nvdimm_name(nvdimm)); + return -ENOMEM; + } + mmio->size = nfit_mem->dcr->window_size; + mmio->base_offset = nfit_mem->memdev_dcr->region_offset; + mmio->idt = nfit_mem->idt_dcr; + mmio->spa = nfit_mem->spa_dcr; + rc = nfit_blk_init_interleave(mmio, nfit_mem->idt_dcr, + nfit_mem->memdev_dcr->interleave_ways); + if (rc) { + dev_dbg(dev, "%s: %s failed to init dcr interleave\n", + __func__, nvdimm_name(nvdimm)); + return rc; + } + + if (mmio->line_size == 0) + return 0; + + if ((u32) nfit_blk->cmd_offset % mmio->line_size + + 8 > mmio->line_size) { + dev_dbg(dev, "cmd_offset crosses interleave boundary\n"); + return -ENXIO; + } else if ((u32) nfit_blk->stat_offset % mmio->line_size + + 8 > mmio->line_size) { + dev_dbg(dev, "stat_offset crosses interleave boundary\n"); + return -ENXIO; + } + + return 0; +} + +static void acpi_nfit_blk_region_disable(struct nvdimm_bus *nvdimm_bus, + struct device *dev) +{ + struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus); + struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc); + struct nd_blk_region *ndbr = to_nd_blk_region(dev); + struct nfit_blk *nfit_blk = nd_blk_region_provider_data(ndbr); + int i; + + if (!nfit_blk) + return; /* never enabled */ + + /* auto-free BLK spa mappings */ + for (i = 0; i < 2; i++) { + struct nfit_blk_mmio *mmio = &nfit_blk->mmio[i]; + + if (mmio->base) + nfit_spa_unmap(acpi_desc, mmio->spa); + } + nd_blk_region_set_provider_data(ndbr, NULL); + /* devm will free nfit_blk */ +} + static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc, struct nd_mapping *nd_mapping, struct nd_region_desc *ndr_desc, struct acpi_nfit_memory_map *memdev, @@ -878,6 +1289,7 @@ static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc, { struct nvdimm *nvdimm = acpi_nfit_dimm_by_handle(acpi_desc, memdev->device_handle); + struct nd_blk_region_desc *ndbr_desc; struct nfit_mem *nfit_mem; int blk_valid = 0; @@ -908,6 +1320,10 @@ static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc, ndr_desc->nd_mapping = nd_mapping; ndr_desc->num_mappings = blk_valid; + ndbr_desc = to_blk_region_desc(ndr_desc); + ndbr_desc->enable = acpi_nfit_blk_region_enable; + ndbr_desc->disable = acpi_nfit_blk_region_disable; + ndbr_desc->do_io = acpi_nfit_blk_region_do_io; if (!nvdimm_blk_region_create(acpi_desc->nvdimm_bus, ndr_desc)) return -ENOMEM; break; @@ -921,8 +1337,9 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, { static struct nd_mapping nd_mappings[ND_MAX_MAPPINGS]; struct acpi_nfit_system_address *spa = nfit_spa->spa; + struct nd_blk_region_desc ndbr_desc; + struct nd_region_desc *ndr_desc; struct nfit_memdev *nfit_memdev; - struct nd_region_desc ndr_desc; struct nvdimm_bus *nvdimm_bus; struct resource res; int count = 0, rc; @@ -935,12 +1352,13 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, memset(&res, 0, sizeof(res)); memset(&nd_mappings, 0, sizeof(nd_mappings)); - memset(&ndr_desc, 0, sizeof(ndr_desc)); + memset(&ndbr_desc, 0, sizeof(ndbr_desc)); res.start = spa->address; res.end = res.start + spa->length - 1; - ndr_desc.res = &res; - ndr_desc.provider_data = nfit_spa; - ndr_desc.attr_groups = acpi_nfit_region_attribute_groups; + ndr_desc = &ndbr_desc.ndr_desc; + ndr_desc->res = &res; + ndr_desc->provider_data = nfit_spa; + ndr_desc->attr_groups = acpi_nfit_region_attribute_groups; list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { struct acpi_nfit_memory_map *memdev = nfit_memdev->memdev; struct nd_mapping *nd_mapping; @@ -953,24 +1371,24 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, return -ENXIO; } nd_mapping = &nd_mappings[count++]; - rc = acpi_nfit_init_mapping(acpi_desc, nd_mapping, &ndr_desc, + rc = acpi_nfit_init_mapping(acpi_desc, nd_mapping, ndr_desc, memdev, spa); if (rc) return rc; } - ndr_desc.nd_mapping = nd_mappings; - ndr_desc.num_mappings = count; - rc = acpi_nfit_init_interleave_set(acpi_desc, &ndr_desc, spa); + ndr_desc->nd_mapping = nd_mappings; + ndr_desc->num_mappings = count; + rc = acpi_nfit_init_interleave_set(acpi_desc, ndr_desc, spa); if (rc) return rc; nvdimm_bus = acpi_desc->nvdimm_bus; if (nfit_spa_type(spa) == NFIT_SPA_PM) { - if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc)) + if (!nvdimm_pmem_region_create(nvdimm_bus, ndr_desc)) return -ENOMEM; } else if (nfit_spa_type(spa) == NFIT_SPA_VOLATILE) { - if (!nvdimm_volatile_region_create(nvdimm_bus, &ndr_desc)) + if (!nvdimm_volatile_region_create(nvdimm_bus, ndr_desc)) return -ENOMEM; } return 0; @@ -996,11 +1414,14 @@ static int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, acpi_size sz) u8 *data; int rc; + INIT_LIST_HEAD(&acpi_desc->spa_maps); INIT_LIST_HEAD(&acpi_desc->spas); INIT_LIST_HEAD(&acpi_desc->dcrs); INIT_LIST_HEAD(&acpi_desc->bdws); + INIT_LIST_HEAD(&acpi_desc->idts); INIT_LIST_HEAD(&acpi_desc->memdevs); INIT_LIST_HEAD(&acpi_desc->dimms); + mutex_init(&acpi_desc->spa_map_mutex); data = (u8 *) acpi_desc->nfit; end = data + sz; diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h index b76e33629098..7bd38b7baf39 100644 --- a/drivers/acpi/nfit.h +++ b/drivers/acpi/nfit.h @@ -52,6 +52,11 @@ struct nfit_bdw { struct list_head list; }; +struct nfit_idt { + struct acpi_nfit_interleave *idt; + struct list_head list; +}; + struct nfit_memdev { struct acpi_nfit_memory_map *memdev; struct list_head list; @@ -62,10 +67,13 @@ struct nfit_mem { struct nvdimm *nvdimm; struct acpi_nfit_memory_map *memdev_dcr; struct acpi_nfit_memory_map *memdev_pmem; + struct acpi_nfit_memory_map *memdev_bdw; struct acpi_nfit_control_region *dcr; struct acpi_nfit_data_region *bdw; struct acpi_nfit_system_address *spa_dcr; struct acpi_nfit_system_address *spa_bdw; + struct acpi_nfit_interleave *idt_dcr; + struct acpi_nfit_interleave *idt_bdw; struct list_head list; struct acpi_device *adev; unsigned long dsm_mask; @@ -74,16 +82,57 @@ struct nfit_mem { struct acpi_nfit_desc { struct nvdimm_bus_descriptor nd_desc; struct acpi_table_nfit *nfit; + struct mutex spa_map_mutex; + struct list_head spa_maps; struct list_head memdevs; struct list_head dimms; struct list_head spas; struct list_head dcrs; struct list_head bdws; + struct list_head idts; struct nvdimm_bus *nvdimm_bus; struct device *dev; unsigned long dimm_dsm_force_en; }; +enum nd_blk_mmio_selector { + BDW, + DCR, +}; + +struct nfit_blk { + struct nfit_blk_mmio { + union { + void __iomem *base; + void *aperture; + }; + u64 size; + u64 base_offset; + u32 line_size; + u32 num_lines; + u32 table_size; + struct acpi_nfit_interleave *idt; + struct acpi_nfit_system_address *spa; + } mmio[2]; + struct nd_region *nd_region; + u64 bdw_offset; /* post interleave offset */ + u64 stat_offset; + u64 cmd_offset; +}; + +struct nfit_spa_mapping { + struct acpi_nfit_desc *acpi_desc; + struct acpi_nfit_system_address *spa; + struct list_head list; + struct kref kref; + void __iomem *iomem; +}; + +static inline struct nfit_spa_mapping *to_spa_map(struct kref *kref) +{ + return container_of(kref, struct nfit_spa_mapping, kref); +} + static inline struct acpi_nfit_memory_map *__to_nfit_memdev( struct nfit_mem *nfit_mem) { diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig index 204ee0796411..72226acb5c0f 100644 --- a/drivers/nvdimm/Kconfig +++ b/drivers/nvdimm/Kconfig @@ -34,6 +34,19 @@ config BLK_DEV_PMEM Say Y if you want to use an NVDIMM +config ND_BLK + tristate "BLK: Block data window (aperture) device support" + default LIBNVDIMM + select ND_BTT if BTT + help + Support NVDIMMs, or other devices, that implement a BLK-mode + access capability. BLK-mode access uses memory-mapped-i/o + apertures to access persistent media. + + Say Y if your platform firmware emits an ACPI.NFIT table + (CONFIG_ACPI_NFIT), or otherwise exposes BLK-mode + capabilities. + config ND_BTT tristate diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile index d2aab6c58492..594bb97c867a 100644 --- a/drivers/nvdimm/Makefile +++ b/drivers/nvdimm/Makefile @@ -1,11 +1,14 @@ obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o obj-$(CONFIG_ND_BTT) += nd_btt.o +obj-$(CONFIG_ND_BLK) += nd_blk.o nd_pmem-y := pmem.o nd_btt-y := btt.o +nd_blk-y := blk.o + libnvdimm-y := core.o libnvdimm-y += bus.o libnvdimm-y += dimm_devs.o diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c new file mode 100644 index 000000000000..9ac0c266c15c --- /dev/null +++ b/drivers/nvdimm/blk.c @@ -0,0 +1,245 @@ +/* + * NVDIMM Block Window Driver + * Copyright (c) 2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include +#include +#include +#include +#include +#include +#include +#include "nd.h" + +struct nd_blk_device { + struct request_queue *queue; + struct gendisk *disk; + struct nd_namespace_blk *nsblk; + struct nd_blk_region *ndbr; + size_t disk_size; +}; + +static int nd_blk_major; + +static resource_size_t to_dev_offset(struct nd_namespace_blk *nsblk, + resource_size_t ns_offset, unsigned int len) +{ + int i; + + for (i = 0; i < nsblk->num_resources; i++) { + if (ns_offset < resource_size(nsblk->res[i])) { + if (ns_offset + len > resource_size(nsblk->res[i])) { + dev_WARN_ONCE(&nsblk->common.dev, 1, + "illegal request\n"); + return SIZE_MAX; + } + return nsblk->res[i]->start + ns_offset; + } + ns_offset -= resource_size(nsblk->res[i]); + } + + dev_WARN_ONCE(&nsblk->common.dev, 1, "request out of range\n"); + return SIZE_MAX; +} + +static void nd_blk_make_request(struct request_queue *q, struct bio *bio) +{ + struct block_device *bdev = bio->bi_bdev; + struct gendisk *disk = bdev->bd_disk; + struct nd_namespace_blk *nsblk; + struct nd_blk_device *blk_dev; + struct nd_blk_region *ndbr; + struct bvec_iter iter; + struct bio_vec bvec; + int err = 0, rw; + + blk_dev = disk->private_data; + nsblk = blk_dev->nsblk; + ndbr = blk_dev->ndbr; + rw = bio_data_dir(bio); + bio_for_each_segment(bvec, bio, iter) { + unsigned int len = bvec.bv_len; + resource_size_t dev_offset; + void *iobuf; + + BUG_ON(len > PAGE_SIZE); + + dev_offset = to_dev_offset(nsblk, + iter.bi_sector << SECTOR_SHIFT, len); + if (dev_offset == SIZE_MAX) { + err = -EIO; + goto out; + } + + iobuf = kmap_atomic(bvec.bv_page); + err = ndbr->do_io(ndbr, dev_offset, iobuf + bvec.bv_offset, + len, rw); + kunmap_atomic(iobuf); + if (err) + goto out; + } + + out: + bio_endio(bio, err); +} + +static int nd_blk_rw_bytes(struct nd_namespace_common *ndns, + resource_size_t offset, void *iobuf, size_t n, int rw) +{ + struct nd_blk_device *blk_dev = dev_get_drvdata(ndns->claim); + struct nd_namespace_blk *nsblk = blk_dev->nsblk; + struct nd_blk_region *ndbr = blk_dev->ndbr; + resource_size_t dev_offset; + + dev_offset = to_dev_offset(nsblk, offset, n); + + if (unlikely(offset + n > blk_dev->disk_size)) { + dev_WARN_ONCE(&ndns->dev, 1, "request out of range\n"); + return -EFAULT; + } + + if (dev_offset == SIZE_MAX) + return -EIO; + + return ndbr->do_io(ndbr, dev_offset, iobuf, n, rw); +} + +static const struct block_device_operations nd_blk_fops = { + .owner = THIS_MODULE, +}; + +static int nd_blk_attach_disk(struct nd_namespace_common *ndns, + struct nd_blk_device *blk_dev) +{ + struct nd_namespace_blk *nsblk = to_nd_namespace_blk(&ndns->dev); + struct gendisk *disk; + + blk_dev->queue = blk_alloc_queue(GFP_KERNEL); + if (!blk_dev->queue) + return -ENOMEM; + + blk_queue_make_request(blk_dev->queue, nd_blk_make_request); + blk_queue_max_hw_sectors(blk_dev->queue, UINT_MAX); + blk_queue_bounce_limit(blk_dev->queue, BLK_BOUNCE_ANY); + blk_queue_logical_block_size(blk_dev->queue, nsblk->lbasize); + queue_flag_set_unlocked(QUEUE_FLAG_NONROT, blk_dev->queue); + + disk = blk_dev->disk = alloc_disk(0); + if (!disk) { + blk_cleanup_queue(blk_dev->queue); + return -ENOMEM; + } + + disk->driverfs_dev = &ndns->dev; + disk->major = nd_blk_major; + disk->first_minor = 0; + disk->fops = &nd_blk_fops; + disk->private_data = blk_dev; + disk->queue = blk_dev->queue; + disk->flags = GENHD_FL_EXT_DEVT; + nvdimm_namespace_disk_name(ndns, disk->disk_name); + set_capacity(disk, blk_dev->disk_size >> SECTOR_SHIFT); + add_disk(disk); + + return 0; +} + +static int nd_blk_probe(struct device *dev) +{ + struct nd_namespace_common *ndns; + struct nd_blk_device *blk_dev; + int rc; + + ndns = nvdimm_namespace_common_probe(dev); + if (IS_ERR(ndns)) + return PTR_ERR(ndns); + + blk_dev = kzalloc(sizeof(*blk_dev), GFP_KERNEL); + if (!blk_dev) + return -ENOMEM; + + blk_dev->disk_size = nvdimm_namespace_capacity(ndns); + blk_dev->ndbr = to_nd_blk_region(dev->parent); + blk_dev->nsblk = to_nd_namespace_blk(&ndns->dev); + dev_set_drvdata(dev, blk_dev); + + ndns->rw_bytes = nd_blk_rw_bytes; + if (is_nd_btt(dev)) + rc = nvdimm_namespace_attach_btt(ndns); + else if (nd_btt_probe(ndns, blk_dev) == 0) { + /* we'll come back as btt-blk */ + rc = -ENXIO; + } else + rc = nd_blk_attach_disk(ndns, blk_dev); + if (rc) + kfree(blk_dev); + return rc; +} + +static void nd_blk_detach_disk(struct nd_blk_device *blk_dev) +{ + del_gendisk(blk_dev->disk); + put_disk(blk_dev->disk); + blk_cleanup_queue(blk_dev->queue); +} + +static int nd_blk_remove(struct device *dev) +{ + struct nd_blk_device *blk_dev = dev_get_drvdata(dev); + + if (is_nd_btt(dev)) + nvdimm_namespace_detach_btt(to_nd_btt(dev)->ndns); + else + nd_blk_detach_disk(blk_dev); + kfree(blk_dev); + + return 0; +} + +static struct nd_device_driver nd_blk_driver = { + .probe = nd_blk_probe, + .remove = nd_blk_remove, + .drv = { + .name = "nd_blk", + }, + .type = ND_DRIVER_NAMESPACE_BLK, +}; + +static int __init nd_blk_init(void) +{ + int rc; + + rc = register_blkdev(0, "nd_blk"); + if (rc < 0) + return rc; + + nd_blk_major = rc; + rc = nd_driver_register(&nd_blk_driver); + + if (rc < 0) + unregister_blkdev(nd_blk_major, "nd_blk"); + + return rc; +} + +static void __exit nd_blk_exit(void) +{ + driver_unregister(&nd_blk_driver.drv); + unregister_blkdev(nd_blk_major, "nd_blk"); +} + +MODULE_AUTHOR("Ross Zwisler "); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_BLK); +module_init(nd_blk_init); +module_exit(nd_blk_exit); diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c index 83b179ed6d61..c05eb807d674 100644 --- a/drivers/nvdimm/dimm_devs.c +++ b/drivers/nvdimm/dimm_devs.c @@ -209,6 +209,15 @@ struct nvdimm *to_nvdimm(struct device *dev) } EXPORT_SYMBOL_GPL(to_nvdimm); +struct nvdimm *nd_blk_region_to_dimm(struct nd_blk_region *ndbr) +{ + struct nd_region *nd_region = &ndbr->nd_region; + struct nd_mapping *nd_mapping = &nd_region->mapping[0]; + + return nd_mapping->nvdimm; +} +EXPORT_SYMBOL_GPL(nd_blk_region_to_dimm); + struct nvdimm_drvdata *to_ndd(struct nd_mapping *nd_mapping) { struct nvdimm *nvdimm = nd_mapping->nvdimm; diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 4aa647c8d644..1ce1e70de44a 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -173,6 +173,65 @@ static resource_size_t nd_namespace_blk_size(struct nd_namespace_blk *nsblk) return size; } +static bool __nd_namespace_blk_validate(struct nd_namespace_blk *nsblk) +{ + struct nd_region *nd_region = to_nd_region(nsblk->common.dev.parent); + struct nd_mapping *nd_mapping = &nd_region->mapping[0]; + struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); + struct nd_label_id label_id; + struct resource *res; + int count, i; + + if (!nsblk->uuid || !nsblk->lbasize || !ndd) + return false; + + count = 0; + nd_label_gen_id(&label_id, nsblk->uuid, NSLABEL_FLAG_LOCAL); + for_each_dpa_resource(ndd, res) { + if (strcmp(res->name, label_id.id) != 0) + continue; + /* + * Resources with unacknoweldged adjustments indicate a + * failure to update labels + */ + if (res->flags & DPA_RESOURCE_ADJUSTED) + return false; + count++; + } + + /* These values match after a successful label update */ + if (count != nsblk->num_resources) + return false; + + for (i = 0; i < nsblk->num_resources; i++) { + struct resource *found = NULL; + + for_each_dpa_resource(ndd, res) + if (res == nsblk->res[i]) { + found = res; + break; + } + /* stale resource */ + if (!found) + return false; + } + + return true; +} + +resource_size_t nd_namespace_blk_validate(struct nd_namespace_blk *nsblk) +{ + resource_size_t size; + + nvdimm_bus_lock(&nsblk->common.dev); + size = __nd_namespace_blk_validate(nsblk); + nvdimm_bus_unlock(&nsblk->common.dev); + + return size; +} +EXPORT_SYMBOL(nd_namespace_blk_validate); + + static int nd_namespace_label_update(struct nd_region *nd_region, struct device *dev) { @@ -1224,7 +1283,11 @@ struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev) return ERR_PTR(-ENODEV); } } else if (is_namespace_blk(&ndns->dev)) { - return ERR_PTR(-ENODEV); /* TODO */ + struct nd_namespace_blk *nsblk; + + nsblk = to_nd_namespace_blk(&ndns->dev); + if (!nd_namespace_blk_validate(nsblk)) + return ERR_PTR(-ENODEV); } return ndns; diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h index 5e6413964776..e1970c71ad1c 100644 --- a/drivers/nvdimm/nd-core.h +++ b/drivers/nvdimm/nd-core.h @@ -43,9 +43,8 @@ struct nvdimm { }; bool is_nvdimm(struct device *dev); -bool is_nd_blk(struct device *dev); bool is_nd_pmem(struct device *dev); -struct nd_btt; +bool is_nd_blk(struct device *dev); struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev); int __init nvdimm_bus_init(void); void nvdimm_bus_exit(void); diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index 1b937c235913..f153f43ca3d6 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -102,6 +102,15 @@ struct nd_region { struct nd_mapping mapping[0]; }; +struct nd_blk_region { + int (*enable)(struct nvdimm_bus *nvdimm_bus, struct device *dev); + void (*disable)(struct nvdimm_bus *nvdimm_bus, struct device *dev); + int (*do_io)(struct nd_blk_region *ndbr, resource_size_t dpa, + void *iobuf, u64 len, int rw); + void *blk_provider_data; + struct nd_region nd_region; +}; + /* * Lookup next in the repeating sequence of 01, 10, and 11. */ @@ -171,8 +180,6 @@ static inline struct device *nd_btt_create(struct nd_region *nd_region) #endif struct nd_region *to_nd_region(struct device *dev); -unsigned int nd_region_acquire_lane(struct nd_region *nd_region); -void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane); int nd_region_to_nstype(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); @@ -192,4 +199,6 @@ int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns); int nvdimm_namespace_detach_btt(struct nd_namespace_common *ndns); const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns, char *name); +int nd_blk_region_init(struct nd_region *nd_region); +resource_size_t nd_namespace_blk_validate(struct nd_namespace_blk *nsblk); #endif /* __ND_H__ */ diff --git a/drivers/nvdimm/region.c b/drivers/nvdimm/region.c index eb8aebcd4800..f28f78ccff19 100644 --- a/drivers/nvdimm/region.c +++ b/drivers/nvdimm/region.c @@ -18,11 +18,10 @@ static int nd_region_probe(struct device *dev) { - int err; + int err, rc; static unsigned long once; struct nd_region_namespaces *num_ns; struct nd_region *nd_region = to_nd_region(dev); - int rc = nd_region_register_namespaces(nd_region, &err); if (nd_region->num_lanes > num_online_cpus() && nd_region->num_lanes < num_possible_cpus() @@ -34,6 +33,11 @@ static int nd_region_probe(struct device *dev) nd_region->num_lanes); } + rc = nd_blk_region_init(nd_region); + if (rc) + return rc; + + rc = nd_region_register_namespaces(nd_region, &err); num_ns = devm_kzalloc(dev, sizeof(*num_ns), GFP_KERNEL); if (!num_ns) return -ENOMEM; diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index fe8ec21fe3d7..2cfb3f74bcbf 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -11,6 +11,7 @@ * General Public License for more details. */ #include +#include #include #include #include @@ -34,7 +35,10 @@ static void nd_region_release(struct device *dev) } free_percpu(nd_region->lane); ida_simple_remove(®ion_ida, nd_region->id); - kfree(nd_region); + if (is_nd_blk(dev)) + kfree(to_nd_blk_region(dev)); + else + kfree(nd_region); } static struct device_type nd_blk_device_type = { @@ -71,6 +75,33 @@ struct nd_region *to_nd_region(struct device *dev) } EXPORT_SYMBOL_GPL(to_nd_region); +struct nd_blk_region *to_nd_blk_region(struct device *dev) +{ + struct nd_region *nd_region = to_nd_region(dev); + + WARN_ON(!is_nd_blk(dev)); + return container_of(nd_region, struct nd_blk_region, nd_region); +} +EXPORT_SYMBOL_GPL(to_nd_blk_region); + +void *nd_region_provider_data(struct nd_region *nd_region) +{ + return nd_region->provider_data; +} +EXPORT_SYMBOL_GPL(nd_region_provider_data); + +void *nd_blk_region_provider_data(struct nd_blk_region *ndbr) +{ + return ndbr->blk_provider_data; +} +EXPORT_SYMBOL_GPL(nd_blk_region_provider_data); + +void nd_blk_region_set_provider_data(struct nd_blk_region *ndbr, void *data) +{ + ndbr->blk_provider_data = data; +} +EXPORT_SYMBOL_GPL(nd_blk_region_set_provider_data); + /** * nd_region_to_nstype() - region to an integer namespace type * @nd_region: region-device to interrogate @@ -365,7 +396,8 @@ u64 nd_region_interleave_set_cookie(struct nd_region *nd_region) /* * Upon successful probe/remove, take/release a reference on the * associated interleave set (if present), and plant new btt + namespace - * seeds. + * seeds. Also, on the removal of a BLK region, notify the provider to + * disable the region. */ static void nd_region_notify_driver_action(struct nvdimm_bus *nvdimm_bus, struct device *dev, bool probe) @@ -385,8 +417,14 @@ static void nd_region_notify_driver_action(struct nvdimm_bus *nvdimm_bus, nd_mapping->labels = NULL; put_ndd(ndd); nd_mapping->ndd = NULL; - atomic_dec(&nvdimm->busy); + if (ndd) + atomic_dec(&nvdimm->busy); } + + if (is_nd_pmem(dev)) + return; + + to_nd_blk_region(dev)->disable(nvdimm_bus, dev); } if (dev->parent && is_nd_blk(dev->parent) && probe) { nd_region = to_nd_region(dev->parent); @@ -526,11 +564,21 @@ struct attribute_group nd_mapping_attribute_group = { }; EXPORT_SYMBOL_GPL(nd_mapping_attribute_group); -void *nd_region_provider_data(struct nd_region *nd_region) +int nd_blk_region_init(struct nd_region *nd_region) { - return nd_region->provider_data; + struct device *dev = &nd_region->dev; + struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); + + if (!is_nd_blk(dev)) + return 0; + + if (nd_region->ndr_mappings < 1) { + dev_err(dev, "invalid BLK region\n"); + return -ENXIO; + } + + return to_nd_blk_region(dev)->enable(nvdimm_bus, dev); } -EXPORT_SYMBOL_GPL(nd_region_provider_data); /** * nd_region_acquire_lane - allocate and lock a lane @@ -591,6 +639,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, { struct nd_region *nd_region; struct device *dev; + void *region_buf; unsigned int i; for (i = 0; i < ndr_desc->num_mappings; i++) { @@ -605,10 +654,30 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, } } - nd_region = kzalloc(sizeof(struct nd_region) - + sizeof(struct nd_mapping) * ndr_desc->num_mappings, - GFP_KERNEL); - if (!nd_region) + if (dev_type == &nd_blk_device_type) { + struct nd_blk_region_desc *ndbr_desc; + struct nd_blk_region *ndbr; + + ndbr_desc = to_blk_region_desc(ndr_desc); + ndbr = kzalloc(sizeof(*ndbr) + sizeof(struct nd_mapping) + * ndr_desc->num_mappings, + GFP_KERNEL); + if (ndbr) { + nd_region = &ndbr->nd_region; + ndbr->enable = ndbr_desc->enable; + ndbr->disable = ndbr_desc->disable; + ndbr->do_io = ndbr_desc->do_io; + } + region_buf = ndbr; + } else { + nd_region = kzalloc(sizeof(struct nd_region) + + sizeof(struct nd_mapping) + * ndr_desc->num_mappings, + GFP_KERNEL); + region_buf = nd_region; + } + + if (!region_buf) return NULL; nd_region->id = ida_simple_get(®ion_ida, 0, 0, GFP_KERNEL); if (nd_region->id < 0) @@ -654,7 +723,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, err_percpu: ida_simple_remove(®ion_ida, nd_region->id); err_id: - kfree(nd_region); + kfree(region_buf); return NULL; } -- cgit v1.2.3