diff options
Diffstat (limited to 'drivers/cxl/core/hdm.c')
| -rw-r--r-- | drivers/cxl/core/hdm.c | 745 |
1 files changed, 501 insertions, 244 deletions
diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index 4449b34a80cc..1c5d2022c87a 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -16,14 +16,16 @@ * for enumerating these registers and capabilities. */ -DECLARE_RWSEM(cxl_dpa_rwsem); +struct cxl_rwsem cxl_rwsem = { + .region = __RWSEM_INITIALIZER(cxl_rwsem.region), + .dpa = __RWSEM_INITIALIZER(cxl_rwsem.dpa), +}; -static int add_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, - int *target_map) +static int add_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld) { int rc; - rc = cxl_decoder_add_locked(cxld, target_map); + rc = cxl_decoder_add_locked(cxld); if (rc) { put_device(&cxld->dev); dev_err(&port->dev, "Failed to add decoder\n"); @@ -34,7 +36,8 @@ static int add_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, if (rc) return rc; - dev_dbg(&cxld->dev, "Added to port %s\n", dev_name(&port->dev)); + dev_dbg(port->uport_dev, "%s added to %s\n", + dev_name(&cxld->dev), dev_name(&port->dev)); return 0; } @@ -46,12 +49,17 @@ static int add_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, * are claimed and passed to the single dport. Disable the range until the first * CXL region is enumerated / activated. */ -int devm_cxl_add_passthrough_decoder(struct cxl_port *port) +static int devm_cxl_add_passthrough_decoder(struct cxl_port *port) { struct cxl_switch_decoder *cxlsd; - struct cxl_dport *dport = NULL; - int single_port_map[1]; - unsigned long index; + struct cxl_hdm *cxlhdm = dev_get_drvdata(&port->dev); + + /* + * Capability checks are moot for passthrough decoders, support + * any and all possibilities. + */ + cxlhdm->interleave_mask = ~0U; + cxlhdm->iw_cap_mask = ~0UL; cxlsd = cxl_switch_decoder_alloc(port, 1); if (IS_ERR(cxlsd)) @@ -59,13 +67,8 @@ int devm_cxl_add_passthrough_decoder(struct cxl_port *port) device_lock_assert(&port->dev); - xa_for_each(&port->dports, index, dport) - break; - single_port_map[0] = dport->port_id; - - return add_hdm_decoder(port, &cxlsd->cxld, single_port_map); + return add_hdm_decoder(port, &cxlsd->cxld); } -EXPORT_SYMBOL_NS_GPL(devm_cxl_add_passthrough_decoder, CXL); static void parse_hdm_decoder_caps(struct cxl_hdm *cxlhdm) { @@ -79,26 +82,11 @@ static void parse_hdm_decoder_caps(struct cxl_hdm *cxlhdm) cxlhdm->interleave_mask |= GENMASK(11, 8); if (FIELD_GET(CXL_HDM_DECODER_INTERLEAVE_14_12, hdm_cap)) cxlhdm->interleave_mask |= GENMASK(14, 12); -} - -static int map_hdm_decoder_regs(struct cxl_port *port, void __iomem *crb, - struct cxl_component_regs *regs) -{ - struct cxl_register_map map = { - .dev = &port->dev, - .resource = port->component_reg_phys, - .base = crb, - .max_size = CXL_COMPONENT_REG_BLOCK_SIZE, - }; - - cxl_probe_component_regs(&port->dev, crb, &map.component_map); - if (!map.component_map.hdm_decoder.valid) { - dev_dbg(&port->dev, "HDM decoder registers not implemented\n"); - /* unique error code to indicate no HDM decoder capability */ - return -ENODEV; - } - - return cxl_map_component_regs(&map, regs, BIT(CXL_CM_CAP_CAP_ID_HDM)); + cxlhdm->iw_cap_mask = BIT(1) | BIT(2) | BIT(4) | BIT(8); + if (FIELD_GET(CXL_HDM_DECODER_INTERLEAVE_3_6_12_WAY, hdm_cap)) + cxlhdm->iw_cap_mask |= BIT(3) | BIT(6) | BIT(12); + if (FIELD_GET(CXL_HDM_DECODER_INTERLEAVE_16_WAY, hdm_cap)) + cxlhdm->iw_cap_mask |= BIT(16); } static bool should_emulate_decoders(struct cxl_endpoint_dvsec_info *info) @@ -150,12 +138,12 @@ static bool should_emulate_decoders(struct cxl_endpoint_dvsec_info *info) * @port: cxl_port to map * @info: cached DVSEC range register info */ -struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port, - struct cxl_endpoint_dvsec_info *info) +static struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port, + struct cxl_endpoint_dvsec_info *info) { + struct cxl_register_map *reg_map = &port->reg_map; struct device *dev = &port->dev; struct cxl_hdm *cxlhdm; - void __iomem *crb; int rc; cxlhdm = devm_kzalloc(dev, sizeof(*cxlhdm), GFP_KERNEL); @@ -164,19 +152,29 @@ struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port, cxlhdm->port = port; dev_set_drvdata(dev, cxlhdm); - crb = ioremap(port->component_reg_phys, CXL_COMPONENT_REG_BLOCK_SIZE); - if (!crb && info && info->mem_enabled) { + /* Memory devices can configure device HDM using DVSEC range regs. */ + if (reg_map->resource == CXL_RESOURCE_NONE) { + if (!info || !info->mem_enabled) { + dev_err(dev, "No component registers mapped\n"); + return ERR_PTR(-ENXIO); + } + cxlhdm->decoder_count = info->ranges; return cxlhdm; - } else if (!crb) { - dev_err(dev, "No component registers mapped\n"); - return ERR_PTR(-ENXIO); } - rc = map_hdm_decoder_regs(port, crb, &cxlhdm->regs); - iounmap(crb); - if (rc) + if (!reg_map->component_map.hdm_decoder.valid) { + dev_dbg(&port->dev, "HDM decoder registers not implemented\n"); + /* unique error code to indicate no HDM decoder capability */ + return ERR_PTR(-ENODEV); + } + + rc = cxl_map_component_regs(reg_map, &cxlhdm->regs, + BIT(CXL_CM_CAP_CAP_ID_HDM)); + if (rc) { + dev_err(dev, "Failed to map HDM capability.\n"); return ERR_PTR(rc); + } parse_hdm_decoder_caps(cxlhdm); if (cxlhdm->decoder_count == 0) { @@ -190,13 +188,12 @@ struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port, */ if (should_emulate_decoders(info)) { dev_dbg(dev, "Fallback map %d range register%s\n", info->ranges, - info->ranges > 1 ? "s" : ""); + str_plural(info->ranges)); cxlhdm->decoder_count = info->ranges; } return cxlhdm; } -EXPORT_SYMBOL_NS_GPL(devm_cxl_setup_hdm, CXL); static void __cxl_dpa_debug(struct seq_file *file, struct resource *r, int depth) { @@ -210,15 +207,45 @@ void cxl_dpa_debug(struct seq_file *file, struct cxl_dev_state *cxlds) { struct resource *p1, *p2; - down_read(&cxl_dpa_rwsem); + guard(rwsem_read)(&cxl_rwsem.dpa); for (p1 = cxlds->dpa_res.child; p1; p1 = p1->sibling) { __cxl_dpa_debug(file, p1, 0); for (p2 = p1->child; p2; p2 = p2->sibling) __cxl_dpa_debug(file, p2, 1); } - up_read(&cxl_dpa_rwsem); } -EXPORT_SYMBOL_NS_GPL(cxl_dpa_debug, CXL); +EXPORT_SYMBOL_NS_GPL(cxl_dpa_debug, "CXL"); + +/* See request_skip() kernel-doc */ +static resource_size_t __adjust_skip(struct cxl_dev_state *cxlds, + const resource_size_t skip_base, + const resource_size_t skip_len, + const char *requester) +{ + const resource_size_t skip_end = skip_base + skip_len - 1; + + for (int i = 0; i < cxlds->nr_partitions; i++) { + const struct resource *part_res = &cxlds->part[i].res; + resource_size_t adjust_start, adjust_end, size; + + adjust_start = max(skip_base, part_res->start); + adjust_end = min(skip_end, part_res->end); + + if (adjust_end < adjust_start) + continue; + + size = adjust_end - adjust_start + 1; + + if (!requester) + __release_region(&cxlds->dpa_res, adjust_start, size); + else if (!__request_region(&cxlds->dpa_res, adjust_start, size, + requester, 0)) + return adjust_start - skip_base; + } + + return skip_len; +} +#define release_skip(c, b, l) __adjust_skip((c), (b), (l), NULL) /* * Must be called in a context that synchronizes against this decoder's @@ -232,13 +259,13 @@ static void __cxl_dpa_release(struct cxl_endpoint_decoder *cxled) struct resource *res = cxled->dpa_res; resource_size_t skip_start; - lockdep_assert_held_write(&cxl_dpa_rwsem); + lockdep_assert_held_write(&cxl_rwsem.dpa); /* save @skip_start, before @res is released */ skip_start = res->start - cxled->skip; __release_region(&cxlds->dpa_res, res->start, resource_size(res)); if (cxled->skip) - __release_region(&cxlds->dpa_res, skip_start, cxled->skip); + release_skip(cxlds, skip_start, cxled->skip); cxled->skip = 0; cxled->dpa_res = NULL; put_device(&cxled->cxld.dev); @@ -247,9 +274,8 @@ static void __cxl_dpa_release(struct cxl_endpoint_decoder *cxled) static void cxl_dpa_release(void *cxled) { - down_write(&cxl_dpa_rwsem); + guard(rwsem_write)(&cxl_rwsem.dpa); __cxl_dpa_release(cxled); - up_write(&cxl_dpa_rwsem); } /* @@ -260,11 +286,63 @@ static void devm_cxl_dpa_release(struct cxl_endpoint_decoder *cxled) { struct cxl_port *port = cxled_to_port(cxled); - lockdep_assert_held_write(&cxl_dpa_rwsem); + lockdep_assert_held_write(&cxl_rwsem.dpa); devm_remove_action(&port->dev, cxl_dpa_release, cxled); __cxl_dpa_release(cxled); } +/** + * request_skip() - Track DPA 'skip' in @cxlds->dpa_res resource tree + * @cxlds: CXL.mem device context that parents @cxled + * @cxled: Endpoint decoder establishing new allocation that skips lower DPA + * @skip_base: DPA < start of new DPA allocation (DPAnew) + * @skip_len: @skip_base + @skip_len == DPAnew + * + * DPA 'skip' arises from out-of-sequence DPA allocation events relative + * to free capacity across multiple partitions. It is a wasteful event + * as usable DPA gets thrown away, but if a deployment has, for example, + * a dual RAM+PMEM device, wants to use PMEM, and has unallocated RAM + * DPA, the free RAM DPA must be sacrificed to start allocating PMEM. + * See third "Implementation Note" in CXL 3.1 8.2.4.19.13 "Decoder + * Protection" for more details. + * + * A 'skip' always covers the last allocated DPA in a previous partition + * to the start of the current partition to allocate. Allocations never + * start in the middle of a partition, and allocations are always + * de-allocated in reverse order (see cxl_dpa_free(), or natural devm + * unwind order from forced in-order allocation). + * + * If @cxlds->nr_partitions was guaranteed to be <= 2 then the 'skip' + * would always be contained to a single partition. Given + * @cxlds->nr_partitions may be > 2 it results in cases where the 'skip' + * might span "tail capacity of partition[0], all of partition[1], ..., + * all of partition[N-1]" to support allocating from partition[N]. That + * in turn interacts with the partition 'struct resource' boundaries + * within @cxlds->dpa_res whereby 'skip' requests need to be divided by + * partition. I.e. this is a quirk of using a 'struct resource' tree to + * detect range conflicts while also tracking partition boundaries in + * @cxlds->dpa_res. + */ +static int request_skip(struct cxl_dev_state *cxlds, + struct cxl_endpoint_decoder *cxled, + const resource_size_t skip_base, + const resource_size_t skip_len) +{ + resource_size_t skipped = __adjust_skip(cxlds, skip_base, skip_len, + dev_name(&cxled->cxld.dev)); + + if (skipped == skip_len) + return 0; + + dev_dbg(cxlds->dev, + "%s: failed to reserve skipped space (%pa %pa %pa)\n", + dev_name(&cxled->cxld.dev), &skip_base, &skip_len, &skipped); + + release_skip(cxlds, skip_base, skipped); + + return -EBUSY; +} + static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled, resource_size_t base, resource_size_t len, resource_size_t skipped) @@ -274,8 +352,9 @@ static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled, struct cxl_dev_state *cxlds = cxlmd->cxlds; struct device *dev = &port->dev; struct resource *res; + int rc; - lockdep_assert_held_write(&cxl_dpa_rwsem); + lockdep_assert_held_write(&cxl_rwsem.dpa); if (!len) { dev_warn(dev, "decoder%d.%d: empty reservation attempted\n", @@ -302,14 +381,9 @@ static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled, } if (skipped) { - res = __request_region(&cxlds->dpa_res, base - skipped, skipped, - dev_name(&cxled->cxld.dev), 0); - if (!res) { - dev_dbg(dev, - "decoder%d.%d: failed to reserve skipped space\n", - port->id, cxled->cxld.id); - return -EBUSY; - } + rc = request_skip(cxlds, cxled, base - skipped, skipped); + if (rc) + return rc; } res = __request_region(&cxlds->dpa_res, base, len, dev_name(&cxled->cxld.dev), 0); @@ -317,28 +391,117 @@ static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled, dev_dbg(dev, "decoder%d.%d: failed to reserve allocation\n", port->id, cxled->cxld.id); if (skipped) - __release_region(&cxlds->dpa_res, base - skipped, - skipped); + release_skip(cxlds, base - skipped, skipped); return -EBUSY; } cxled->dpa_res = res; cxled->skip = skipped; - if (resource_contains(&cxlds->pmem_res, res)) - cxled->mode = CXL_DECODER_PMEM; - else if (resource_contains(&cxlds->ram_res, res)) - cxled->mode = CXL_DECODER_RAM; - else { - dev_dbg(dev, "decoder%d.%d: %pr mixed\n", port->id, - cxled->cxld.id, cxled->dpa_res); - cxled->mode = CXL_DECODER_MIXED; - } + /* + * When allocating new capacity, ->part is already set, when + * discovering decoder settings at initial enumeration, ->part + * is not set. + */ + if (cxled->part < 0) + for (int i = 0; cxlds->nr_partitions; i++) + if (resource_contains(&cxlds->part[i].res, res)) { + cxled->part = i; + break; + } + + if (cxled->part < 0) + dev_warn(dev, "decoder%d.%d: %pr does not map any partition\n", + port->id, cxled->cxld.id, res); port->hdm_end++; get_device(&cxled->cxld.dev); return 0; } +static int add_dpa_res(struct device *dev, struct resource *parent, + struct resource *res, resource_size_t start, + resource_size_t size, const char *type) +{ + int rc; + + *res = (struct resource) { + .name = type, + .start = start, + .end = start + size - 1, + .flags = IORESOURCE_MEM, + }; + if (resource_size(res) == 0) { + dev_dbg(dev, "DPA(%s): no capacity\n", res->name); + return 0; + } + rc = request_resource(parent, res); + if (rc) { + dev_err(dev, "DPA(%s): failed to track %pr (%d)\n", res->name, + res, rc); + return rc; + } + + dev_dbg(dev, "DPA(%s): %pr\n", res->name, res); + + return 0; +} + +static const char *cxl_mode_name(enum cxl_partition_mode mode) +{ + switch (mode) { + case CXL_PARTMODE_RAM: + return "ram"; + case CXL_PARTMODE_PMEM: + return "pmem"; + default: + return ""; + }; +} + +/* if this fails the caller must destroy @cxlds, there is no recovery */ +int cxl_dpa_setup(struct cxl_dev_state *cxlds, const struct cxl_dpa_info *info) +{ + struct device *dev = cxlds->dev; + + guard(rwsem_write)(&cxl_rwsem.dpa); + + if (cxlds->nr_partitions) + return -EBUSY; + + if (!info->size || !info->nr_partitions) { + cxlds->dpa_res = DEFINE_RES_MEM(0, 0); + cxlds->nr_partitions = 0; + return 0; + } + + cxlds->dpa_res = DEFINE_RES_MEM(0, info->size); + + for (int i = 0; i < info->nr_partitions; i++) { + const struct cxl_dpa_part_info *part = &info->part[i]; + int rc; + + cxlds->part[i].perf.qos_class = CXL_QOS_CLASS_INVALID; + cxlds->part[i].mode = part->mode; + + /* Require ordered + contiguous partitions */ + if (i) { + const struct cxl_dpa_part_info *prev = &info->part[i - 1]; + + if (prev->range.end + 1 != part->range.start) + return -EINVAL; + } + rc = add_dpa_res(dev, &cxlds->dpa_res, &cxlds->part[i].res, + part->range.start, range_len(&part->range), + cxl_mode_name(part->mode)); + if (rc) + return rc; + cxlds->nr_partitions++; + } + + return 0; +} +EXPORT_SYMBOL_GPL(cxl_dpa_setup); + int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled, resource_size_t base, resource_size_t len, resource_size_t skipped) @@ -346,200 +509,177 @@ int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled, struct cxl_port *port = cxled_to_port(cxled); int rc; - down_write(&cxl_dpa_rwsem); - rc = __cxl_dpa_reserve(cxled, base, len, skipped); - up_write(&cxl_dpa_rwsem); + scoped_guard(rwsem_write, &cxl_rwsem.dpa) + rc = __cxl_dpa_reserve(cxled, base, len, skipped); if (rc) return rc; return devm_add_action_or_reset(&port->dev, cxl_dpa_release, cxled); } -EXPORT_SYMBOL_NS_GPL(devm_cxl_dpa_reserve, CXL); +EXPORT_SYMBOL_NS_GPL(devm_cxl_dpa_reserve, "CXL"); resource_size_t cxl_dpa_size(struct cxl_endpoint_decoder *cxled) { - resource_size_t size = 0; - - down_read(&cxl_dpa_rwsem); + guard(rwsem_read)(&cxl_rwsem.dpa); if (cxled->dpa_res) - size = resource_size(cxled->dpa_res); - up_read(&cxl_dpa_rwsem); + return resource_size(cxled->dpa_res); - return size; + return 0; } resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled) { resource_size_t base = -1; - down_read(&cxl_dpa_rwsem); + lockdep_assert_held(&cxl_rwsem.dpa); if (cxled->dpa_res) base = cxled->dpa_res->start; - up_read(&cxl_dpa_rwsem); return base; } +bool cxl_resource_contains_addr(const struct resource *res, const resource_size_t addr) +{ + struct resource _addr = DEFINE_RES_MEM(addr, 1); + + return resource_contains(res, &_addr); +} + int cxl_dpa_free(struct cxl_endpoint_decoder *cxled) { struct cxl_port *port = cxled_to_port(cxled); struct device *dev = &cxled->cxld.dev; - int rc; - down_write(&cxl_dpa_rwsem); - if (!cxled->dpa_res) { - rc = 0; - goto out; - } + guard(rwsem_write)(&cxl_rwsem.dpa); + if (!cxled->dpa_res) + return 0; if (cxled->cxld.region) { dev_dbg(dev, "decoder assigned to: %s\n", dev_name(&cxled->cxld.region->dev)); - rc = -EBUSY; - goto out; + return -EBUSY; } if (cxled->cxld.flags & CXL_DECODER_F_ENABLE) { dev_dbg(dev, "decoder enabled\n"); - rc = -EBUSY; - goto out; + return -EBUSY; } if (cxled->cxld.id != port->hdm_end) { dev_dbg(dev, "expected decoder%d.%d\n", port->id, port->hdm_end); - rc = -EBUSY; - goto out; + return -EBUSY; } + devm_cxl_dpa_release(cxled); - rc = 0; -out: - up_write(&cxl_dpa_rwsem); - return rc; + return 0; } -int cxl_dpa_set_mode(struct cxl_endpoint_decoder *cxled, - enum cxl_decoder_mode mode) +int cxl_dpa_set_part(struct cxl_endpoint_decoder *cxled, + enum cxl_partition_mode mode) { struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); struct cxl_dev_state *cxlds = cxlmd->cxlds; struct device *dev = &cxled->cxld.dev; - int rc; + int part; - switch (mode) { - case CXL_DECODER_RAM: - case CXL_DECODER_PMEM: - break; - default: + guard(rwsem_write)(&cxl_rwsem.dpa); + if (cxled->cxld.flags & CXL_DECODER_F_ENABLE) + return -EBUSY; + + for (part = 0; part < cxlds->nr_partitions; part++) + if (cxlds->part[part].mode == mode) + break; + + if (part >= cxlds->nr_partitions) { dev_dbg(dev, "unsupported mode: %d\n", mode); return -EINVAL; } - down_write(&cxl_dpa_rwsem); - if (cxled->cxld.flags & CXL_DECODER_F_ENABLE) { - rc = -EBUSY; - goto out; - } - - /* - * Only allow modes that are supported by the current partition - * configuration - */ - if (mode == CXL_DECODER_PMEM && !resource_size(&cxlds->pmem_res)) { - dev_dbg(dev, "no available pmem capacity\n"); - rc = -ENXIO; - goto out; - } - if (mode == CXL_DECODER_RAM && !resource_size(&cxlds->ram_res)) { - dev_dbg(dev, "no available ram capacity\n"); - rc = -ENXIO; - goto out; + if (!resource_size(&cxlds->part[part].res)) { + dev_dbg(dev, "no available capacity for mode: %d\n", mode); + return -ENXIO; } - cxled->mode = mode; - rc = 0; -out: - up_write(&cxl_dpa_rwsem); - - return rc; + cxled->part = part; + return 0; } -int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size) +static int __cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, u64 size) { struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); - resource_size_t free_ram_start, free_pmem_start; - struct cxl_port *port = cxled_to_port(cxled); struct cxl_dev_state *cxlds = cxlmd->cxlds; struct device *dev = &cxled->cxld.dev; - resource_size_t start, avail, skip; + struct resource *res, *prev = NULL; + resource_size_t start, avail, skip, skip_start; struct resource *p, *last; - int rc; + int part; - down_write(&cxl_dpa_rwsem); + guard(rwsem_write)(&cxl_rwsem.dpa); if (cxled->cxld.region) { dev_dbg(dev, "decoder attached to %s\n", dev_name(&cxled->cxld.region->dev)); - rc = -EBUSY; - goto out; + return -EBUSY; } if (cxled->cxld.flags & CXL_DECODER_F_ENABLE) { dev_dbg(dev, "decoder enabled\n"); - rc = -EBUSY; - goto out; + return -EBUSY; } - for (p = cxlds->ram_res.child, last = NULL; p; p = p->sibling) - last = p; - if (last) - free_ram_start = last->end + 1; - else - free_ram_start = cxlds->ram_res.start; + part = cxled->part; + if (part < 0) { + dev_dbg(dev, "partition not set\n"); + return -EBUSY; + } - for (p = cxlds->pmem_res.child, last = NULL; p; p = p->sibling) + res = &cxlds->part[part].res; + for (p = res->child, last = NULL; p; p = p->sibling) last = p; if (last) - free_pmem_start = last->end + 1; + start = last->end + 1; else - free_pmem_start = cxlds->pmem_res.start; - - if (cxled->mode == CXL_DECODER_RAM) { - start = free_ram_start; - avail = cxlds->ram_res.end - start + 1; - skip = 0; - } else if (cxled->mode == CXL_DECODER_PMEM) { - resource_size_t skip_start, skip_end; + start = res->start; - start = free_pmem_start; - avail = cxlds->pmem_res.end - start + 1; - skip_start = free_ram_start; - - /* - * If some pmem is already allocated, then that allocation - * already handled the skip. - */ - if (cxlds->pmem_res.child && - skip_start == cxlds->pmem_res.child->start) - skip_end = skip_start - 1; - else - skip_end = start - 1; - skip = skip_end - skip_start + 1; - } else { - dev_dbg(dev, "mode not set\n"); - rc = -EINVAL; - goto out; + /* + * To allocate at partition N, a skip needs to be calculated for all + * unallocated space at lower partitions indices. + * + * If a partition has any allocations, the search can end because a + * previous cxl_dpa_alloc() invocation is assumed to have accounted for + * all previous partitions. + */ + skip_start = CXL_RESOURCE_NONE; + for (int i = part; i; i--) { + prev = &cxlds->part[i - 1].res; + for (p = prev->child, last = NULL; p; p = p->sibling) + last = p; + if (last) { + skip_start = last->end + 1; + break; + } + skip_start = prev->start; } + avail = res->end - start + 1; + if (skip_start == CXL_RESOURCE_NONE) + skip = 0; + else + skip = res->start - skip_start; + if (size > avail) { - dev_dbg(dev, "%pa exceeds available %s capacity: %pa\n", &size, - cxled->mode == CXL_DECODER_RAM ? "ram" : "pmem", - &avail); - rc = -ENOSPC; - goto out; + dev_dbg(dev, "%llu exceeds available %s capacity: %llu\n", size, + res->name, (u64)avail); + return -ENOSPC; } - rc = __cxl_dpa_reserve(cxled, start, size, skip); -out: - up_write(&cxl_dpa_rwsem); + return __cxl_dpa_reserve(cxled, start, size, skip); +} + +int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, u64 size) +{ + struct cxl_port *port = cxled_to_port(cxled); + int rc; + rc = __cxl_dpa_alloc(cxled, size); if (rc) return rc; @@ -575,17 +715,11 @@ static void cxld_set_type(struct cxl_decoder *cxld, u32 *ctrl) CXL_HDM_DECODER0_CTRL_HOSTONLY); } -static int cxlsd_set_targets(struct cxl_switch_decoder *cxlsd, u64 *tgt) +static void cxlsd_set_targets(struct cxl_switch_decoder *cxlsd, u64 *tgt) { struct cxl_dport **t = &cxlsd->target[0]; int ways = cxlsd->cxld.interleave_ways; - if (dev_WARN_ONCE(&cxlsd->cxld.dev, - ways > 8 || ways > cxlsd->nr_targets, - "ways: %d overflows targets: %d\n", ways, - cxlsd->nr_targets)) - return -ENXIO; - *tgt = FIELD_PREP(GENMASK(7, 0), t[0]->port_id); if (ways > 1) *tgt |= FIELD_PREP(GENMASK(15, 8), t[1]->port_id); @@ -601,8 +735,6 @@ static int cxlsd_set_targets(struct cxl_switch_decoder *cxlsd, u64 *tgt) *tgt |= FIELD_PREP(GENMASK_ULL(55, 48), t[6]->port_id); if (ways > 7) *tgt |= FIELD_PREP(GENMASK_ULL(63, 56), t[7]->port_id); - - return 0; } /* @@ -631,26 +763,12 @@ static int cxld_await_commit(void __iomem *hdm, int id) return -ETIMEDOUT; } -static int cxl_decoder_commit(struct cxl_decoder *cxld) +static void setup_hw_decoder(struct cxl_decoder *cxld, void __iomem *hdm) { - struct cxl_port *port = to_cxl_port(cxld->dev.parent); - struct cxl_hdm *cxlhdm = dev_get_drvdata(&port->dev); - void __iomem *hdm = cxlhdm->regs.hdm_decoder; - int id = cxld->id, rc; + int id = cxld->id; u64 base, size; u32 ctrl; - if (cxld->flags & CXL_DECODER_F_ENABLE) - return 0; - - if (port->commit_end + 1 != id) { - dev_dbg(&port->dev, - "%s: out of order commit, expected decoder%d.%d\n", - dev_name(&cxld->dev), port->id, port->commit_end + 1); - return -EBUSY; - } - - down_read(&cxl_dpa_rwsem); /* common decoder settings */ ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(cxld->id)); cxld_set_interleave(cxld, &ctrl); @@ -670,13 +788,7 @@ static int cxl_decoder_commit(struct cxl_decoder *cxld) void __iomem *tl_lo = hdm + CXL_HDM_DECODER0_TL_LOW(id); u64 targets; - rc = cxlsd_set_targets(cxlsd, &targets); - if (rc) { - dev_dbg(&port->dev, "%s: target configuration error\n", - dev_name(&cxld->dev)); - goto err; - } - + cxlsd_set_targets(cxlsd, &targets); writel(upper_32_bits(targets), tl_hi); writel(lower_32_bits(targets), tl_lo); } else { @@ -690,11 +802,50 @@ static int cxl_decoder_commit(struct cxl_decoder *cxld) } writel(ctrl, hdm + CXL_HDM_DECODER0_CTRL_OFFSET(id)); - up_read(&cxl_dpa_rwsem); +} + +static int cxl_decoder_commit(struct cxl_decoder *cxld) +{ + struct cxl_port *port = to_cxl_port(cxld->dev.parent); + struct cxl_hdm *cxlhdm = dev_get_drvdata(&port->dev); + void __iomem *hdm = cxlhdm->regs.hdm_decoder; + int id = cxld->id, rc; + + if (cxld->flags & CXL_DECODER_F_ENABLE) + return 0; + + if (cxl_num_decoders_committed(port) != id) { + dev_dbg(&port->dev, + "%s: out of order commit, expected decoder%d.%d\n", + dev_name(&cxld->dev), port->id, + cxl_num_decoders_committed(port)); + return -EBUSY; + } + + /* + * For endpoint decoders hosted on CXL memory devices that + * support the sanitize operation, make sure sanitize is not in-flight. + */ + if (is_endpoint_decoder(&cxld->dev)) { + struct cxl_endpoint_decoder *cxled = + to_cxl_endpoint_decoder(&cxld->dev); + struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); + struct cxl_memdev_state *mds = + to_cxl_memdev_state(cxlmd->cxlds); + + if (mds && mds->security.sanitize_active) { + dev_dbg(&cxlmd->dev, + "attempted to commit %s during sanitize\n", + dev_name(&cxld->dev)); + return -EBUSY; + } + } + + scoped_guard(rwsem_read, &cxl_rwsem.dpa) + setup_hw_decoder(cxld, hdm); port->commit_end++; rc = cxld_await_commit(hdm, cxld->id); -err: if (rc) { dev_dbg(&port->dev, "%s: error %d committing decoder\n", dev_name(&cxld->dev), rc); @@ -706,7 +857,44 @@ err: return 0; } -static int cxl_decoder_reset(struct cxl_decoder *cxld) +static int commit_reap(struct device *dev, void *data) +{ + struct cxl_port *port = to_cxl_port(dev->parent); + struct cxl_decoder *cxld; + + if (!is_switch_decoder(dev) && !is_endpoint_decoder(dev)) + return 0; + + cxld = to_cxl_decoder(dev); + if (port->commit_end == cxld->id && + ((cxld->flags & CXL_DECODER_F_ENABLE) == 0)) { + port->commit_end--; + dev_dbg(&port->dev, "reap: %s commit_end: %d\n", + dev_name(&cxld->dev), port->commit_end); + } + + return 0; +} + +void cxl_port_commit_reap(struct cxl_decoder *cxld) +{ + struct cxl_port *port = to_cxl_port(cxld->dev.parent); + + lockdep_assert_held_write(&cxl_rwsem.region); + + /* + * Once the highest committed decoder is disabled, free any other + * decoders that were pinned allocated by out-of-order release. + */ + port->commit_end--; + dev_dbg(&port->dev, "reap: %s commit_end: %d\n", dev_name(&cxld->dev), + port->commit_end); + device_for_each_child_reverse_from(&port->dev, &cxld->dev, NULL, + commit_reap); +} +EXPORT_SYMBOL_NS_GPL(cxl_port_commit_reap, "CXL"); + +static void cxl_decoder_reset(struct cxl_decoder *cxld) { struct cxl_port *port = to_cxl_port(cxld->dev.parent); struct cxl_hdm *cxlhdm = dev_get_drvdata(&port->dev); @@ -715,16 +903,18 @@ static int cxl_decoder_reset(struct cxl_decoder *cxld) u32 ctrl; if ((cxld->flags & CXL_DECODER_F_ENABLE) == 0) - return 0; + return; + + if (test_bit(CXL_DECODER_F_LOCK, &cxld->flags)) + return; - if (port->commit_end != id) { + if (port->commit_end == id) + cxl_port_commit_reap(cxld); + else dev_dbg(&port->dev, "%s: out of order reset, expected decoder%d.%d\n", dev_name(&cxld->dev), port->id, port->commit_end); - return -EBUSY; - } - down_read(&cxl_dpa_rwsem); ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(id)); ctrl &= ~CXL_HDM_DECODER0_CTRL_COMMIT; writel(ctrl, hdm + CXL_HDM_DECODER0_CTRL_OFFSET(id)); @@ -733,9 +923,7 @@ static int cxl_decoder_reset(struct cxl_decoder *cxld) writel(0, hdm + CXL_HDM_DECODER0_SIZE_LOW_OFFSET(id)); writel(0, hdm + CXL_HDM_DECODER0_BASE_HIGH_OFFSET(id)); writel(0, hdm + CXL_HDM_DECODER0_BASE_LOW_OFFSET(id)); - up_read(&cxl_dpa_rwsem); - port->commit_end--; cxld->flags &= ~CXL_DECODER_F_ENABLE; /* Userspace is now responsible for reconfiguring this decoder */ @@ -745,8 +933,6 @@ static int cxl_decoder_reset(struct cxl_decoder *cxld) cxled = to_cxl_endpoint_decoder(&cxld->dev); cxled->state = CXL_DECODER_STATE_MANUAL; } - - return 0; } static int cxl_setup_hdm_decoder_from_dvsec( @@ -791,7 +977,7 @@ static int cxl_setup_hdm_decoder_from_dvsec( } static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, - int *target_map, void __iomem *hdm, int which, + void __iomem *hdm, int which, u64 *dpa_base, struct cxl_endpoint_dvsec_info *info) { struct cxl_endpoint_decoder *cxled = NULL; @@ -844,7 +1030,9 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, cxld->target_type = CXL_DECODER_HOSTONLYMEM; else cxld->target_type = CXL_DECODER_DEVMEM; - if (cxld->id != port->commit_end + 1) { + + guard(rwsem_write)(&cxl_rwsem.region); + if (cxld->id != cxl_num_decoders_committed(port)) { dev_warn(&port->dev, "decoder%d.%d: Committed out of order\n", port->id, cxld->id); @@ -892,8 +1080,12 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, } rc = eig_to_granularity(FIELD_GET(CXL_HDM_DECODER0_CTRL_IG_MASK, ctrl), &cxld->interleave_granularity); - if (rc) + if (rc) { + dev_warn(&port->dev, + "decoder%d.%d: Invalid interleave granularity (ctrl: %#x)\n", + port->id, cxld->id, ctrl); return rc; + } dev_dbg(&port->dev, "decoder%d.%d: range: %#llx-%#llx iw: %d ig: %d\n", port->id, cxld->id, cxld->hpa_range.start, cxld->hpa_range.end, @@ -904,7 +1096,7 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, hi = readl(hdm + CXL_HDM_DECODER0_TL_HIGH(which)); target_list.value = (hi << 32) + lo; for (i = 0; i < cxld->interleave_ways; i++) - target_map[i] = target_list.target_id[i]; + cxld->target_map[i] = target_list.target_id[i]; return 0; } @@ -969,8 +1161,8 @@ static void cxl_settle_decoders(struct cxl_hdm *cxlhdm) * @cxlhdm: Structure to populate with HDM capabilities * @info: cached DVSEC range register info */ -int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, - struct cxl_endpoint_dvsec_info *info) +static int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, + struct cxl_endpoint_dvsec_info *info) { void __iomem *hdm = cxlhdm->regs.hdm_decoder; struct cxl_port *port = cxlhdm->port; @@ -980,7 +1172,6 @@ int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, cxl_settle_decoders(cxlhdm); for (i = 0; i < cxlhdm->decoder_count; i++) { - int target_map[CXL_DECODER_MAX_INTERLEAVE] = { 0 }; int rc, target_count = cxlhdm->target_count; struct cxl_decoder *cxld; @@ -1008,8 +1199,7 @@ int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, cxld = &cxlsd->cxld; } - rc = init_hdm_decoder(port, cxld, target_map, hdm, i, - &dpa_base, info); + rc = init_hdm_decoder(port, cxld, hdm, i, &dpa_base, info); if (rc) { dev_warn(&port->dev, "Failed to initialize decoder%d.%d\n", @@ -1017,7 +1207,7 @@ int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, put_device(&cxld->dev); return rc; } - rc = add_hdm_decoder(port, cxld, target_map); + rc = add_hdm_decoder(port, cxld); if (rc) { dev_warn(&port->dev, "Failed to add decoder%d.%d\n", port->id, i); @@ -1027,4 +1217,71 @@ int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, return 0; } -EXPORT_SYMBOL_NS_GPL(devm_cxl_enumerate_decoders, CXL); + +/** + * __devm_cxl_switch_port_decoders_setup - allocate and setup switch decoders + * @port: CXL port context + * + * Return 0 or -errno on error + */ +int __devm_cxl_switch_port_decoders_setup(struct cxl_port *port) +{ + struct cxl_hdm *cxlhdm; + + if (is_cxl_root(port) || is_cxl_endpoint(port)) + return -EOPNOTSUPP; + + cxlhdm = devm_cxl_setup_hdm(port, NULL); + if (!IS_ERR(cxlhdm)) + return devm_cxl_enumerate_decoders(cxlhdm, NULL); + + if (PTR_ERR(cxlhdm) != -ENODEV) { + dev_err(&port->dev, "Failed to map HDM decoder capability\n"); + return PTR_ERR(cxlhdm); + } + + if (cxl_port_get_possible_dports(port) == 1) { + dev_dbg(&port->dev, "Fallback to passthrough decoder\n"); + return devm_cxl_add_passthrough_decoder(port); + } + + dev_err(&port->dev, "HDM decoder capability not found\n"); + return -ENXIO; +} +EXPORT_SYMBOL_NS_GPL(__devm_cxl_switch_port_decoders_setup, "CXL"); + +/** + * devm_cxl_endpoint_decoders_setup - allocate and setup endpoint decoders + * @port: CXL port context + * + * Return 0 or -errno on error + */ +int devm_cxl_endpoint_decoders_setup(struct cxl_port *port) +{ + struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev); + struct cxl_endpoint_dvsec_info info = { .port = port }; + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_hdm *cxlhdm; + int rc; + + if (!is_cxl_endpoint(port)) + return -EOPNOTSUPP; + + rc = cxl_dvsec_rr_decode(cxlds, &info); + if (rc < 0) + return rc; + + cxlhdm = devm_cxl_setup_hdm(port, &info); + if (IS_ERR(cxlhdm)) { + if (PTR_ERR(cxlhdm) == -ENODEV) + dev_err(&port->dev, "HDM decoder registers not found\n"); + return PTR_ERR(cxlhdm); + } + + rc = cxl_hdm_decode_init(cxlds, cxlhdm, &info); + if (rc) + return rc; + + return devm_cxl_enumerate_decoders(cxlhdm, &info); +} +EXPORT_SYMBOL_NS_GPL(devm_cxl_endpoint_decoders_setup, "CXL"); |