diff options
Diffstat (limited to 'drivers/cxl/core/region.c')
| -rw-r--r-- | drivers/cxl/core/region.c | 249 |
1 files changed, 194 insertions, 55 deletions
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index 3c2b6144be23..e701e4b04032 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -9,6 +9,7 @@ #include <linux/uuid.h> #include <linux/sort.h> #include <linux/idr.h> +#include <linux/memory-tiers.h> #include <cxlmem.h> #include <cxl.h> #include "core.h" @@ -1101,6 +1102,26 @@ static int cxl_port_attach_region(struct cxl_port *port, } cxld = cxl_rr->decoder; + /* + * the number of targets should not exceed the target_count + * of the decoder + */ + if (is_switch_decoder(&cxld->dev)) { + struct cxl_switch_decoder *cxlsd; + + cxlsd = to_cxl_switch_decoder(&cxld->dev); + if (cxl_rr->nr_targets > cxlsd->nr_targets) { + dev_dbg(&cxlr->dev, + "%s:%s %s add: %s:%s @ %d overflows targets: %d\n", + dev_name(port->uport_dev), dev_name(&port->dev), + dev_name(&cxld->dev), dev_name(&cxlmd->dev), + dev_name(&cxled->cxld.dev), pos, + cxlsd->nr_targets); + rc = -ENXIO; + goto out_erase; + } + } + rc = cxl_rr_ep_add(cxl_rr, cxled); if (rc) { dev_dbg(&cxlr->dev, @@ -1210,6 +1231,50 @@ static int check_last_peer(struct cxl_endpoint_decoder *cxled, return 0; } +static int check_interleave_cap(struct cxl_decoder *cxld, int iw, int ig) +{ + struct cxl_port *port = to_cxl_port(cxld->dev.parent); + struct cxl_hdm *cxlhdm = dev_get_drvdata(&port->dev); + unsigned int interleave_mask; + u8 eiw; + u16 eig; + int high_pos, low_pos; + + if (!test_bit(iw, &cxlhdm->iw_cap_mask)) + return -ENXIO; + /* + * Per CXL specification r3.1(8.2.4.20.13 Decoder Protection), + * if eiw < 8: + * DPAOFFSET[51: eig + 8] = HPAOFFSET[51: eig + 8 + eiw] + * DPAOFFSET[eig + 7: 0] = HPAOFFSET[eig + 7: 0] + * + * when the eiw is 0, all the bits of HPAOFFSET[51: 0] are used, the + * interleave bits are none. + * + * if eiw >= 8: + * DPAOFFSET[51: eig + 8] = HPAOFFSET[51: eig + eiw] / 3 + * DPAOFFSET[eig + 7: 0] = HPAOFFSET[eig + 7: 0] + * + * when the eiw is 8, all the bits of HPAOFFSET[51: 0] are used, the + * interleave bits are none. + */ + ways_to_eiw(iw, &eiw); + if (eiw == 0 || eiw == 8) + return 0; + + granularity_to_eig(ig, &eig); + if (eiw > 8) + high_pos = eiw + eig - 1; + else + high_pos = eiw + eig + 7; + low_pos = eig + 8; + interleave_mask = GENMASK(high_pos, low_pos); + if (interleave_mask & ~cxlhdm->interleave_mask) + return -ENXIO; + + return 0; +} + static int cxl_port_setup_targets(struct cxl_port *port, struct cxl_region *cxlr, struct cxl_endpoint_decoder *cxled) @@ -1360,6 +1425,15 @@ static int cxl_port_setup_targets(struct cxl_port *port, return -ENXIO; } } else { + rc = check_interleave_cap(cxld, iw, ig); + if (rc) { + dev_dbg(&cxlr->dev, + "%s:%s iw: %d ig: %d is not supported\n", + dev_name(port->uport_dev), + dev_name(&port->dev), iw, ig); + return rc; + } + cxld->interleave_ways = iw; cxld->interleave_granularity = ig; cxld->hpa_range = (struct range) { @@ -1559,10 +1633,13 @@ static int cxl_region_attach_position(struct cxl_region *cxlr, const struct cxl_dport *dport, int pos) { struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); + struct cxl_switch_decoder *cxlsd = &cxlrd->cxlsd; + struct cxl_decoder *cxld = &cxlsd->cxld; + int iw = cxld->interleave_ways; struct cxl_port *iter; int rc; - if (cxlrd->calc_hb(cxlrd, pos) != dport) { + if (dport != cxlrd->cxlsd.target[pos % iw]) { dev_dbg(&cxlr->dev, "%s:%s invalid target position for %s\n", dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev), dev_name(&cxlrd->cxlsd.cxld.dev)); @@ -1796,6 +1873,15 @@ static int cxl_region_attach(struct cxl_region *cxlr, struct cxl_dport *dport; int rc = -ENXIO; + rc = check_interleave_cap(&cxled->cxld, p->interleave_ways, + p->interleave_granularity); + if (rc) { + dev_dbg(&cxlr->dev, "%s iw: %d ig: %d is not supported\n", + dev_name(&cxled->cxld.dev), p->interleave_ways, + p->interleave_granularity); + return rc; + } + if (cxled->mode != cxlr->mode) { dev_dbg(&cxlr->dev, "%s region mode: %d mismatch: %d\n", dev_name(&cxled->cxld.dev), cxlr->mode, cxled->mode); @@ -1897,6 +1983,7 @@ static int cxl_region_attach(struct cxl_region *cxlr, * then the region is already committed. */ p->state = CXL_CONFIG_COMMIT; + cxl_region_shared_upstream_bandwidth_update(cxlr); return 0; } @@ -1918,6 +2005,7 @@ static int cxl_region_attach(struct cxl_region *cxlr, if (rc) return rc; p->state = CXL_CONFIG_ACTIVE; + cxl_region_shared_upstream_bandwidth_update(cxlr); } cxled->cxld.interleave_ways = p->interleave_ways; @@ -2227,7 +2315,6 @@ static void unregister_region(void *_cxlr) struct cxl_region_params *p = &cxlr->params; int i; - unregister_memory_notifier(&cxlr->memory_notifier); device_del(&cxlr->dev); /* @@ -2309,9 +2396,6 @@ static int cxl_region_perf_attrs_callback(struct notifier_block *nb, { struct cxl_region *cxlr = container_of(nb, struct cxl_region, memory_notifier); - struct cxl_region_params *p = &cxlr->params; - struct cxl_endpoint_decoder *cxled = p->targets[0]; - struct cxl_decoder *cxld = &cxled->cxld; struct memory_notify *mnb = arg; int nid = mnb->status_change_nid; int region_nid; @@ -2319,7 +2403,11 @@ static int cxl_region_perf_attrs_callback(struct notifier_block *nb, if (nid == NUMA_NO_NODE || action != MEM_ONLINE) return NOTIFY_DONE; - region_nid = phys_to_target_node(cxld->hpa_range.start); + /* + * No need to hold cxl_region_rwsem; region parameters are stable + * within the cxl_region driver. + */ + region_nid = phys_to_target_node(cxlr->params.res->start); if (nid != region_nid) return NOTIFY_DONE; @@ -2329,6 +2417,31 @@ static int cxl_region_perf_attrs_callback(struct notifier_block *nb, return NOTIFY_OK; } +static int cxl_region_calculate_adistance(struct notifier_block *nb, + unsigned long nid, void *data) +{ + struct cxl_region *cxlr = container_of(nb, struct cxl_region, + adist_notifier); + struct access_coordinate *perf; + int *adist = data; + int region_nid; + + /* + * No need to hold cxl_region_rwsem; region parameters are stable + * within the cxl_region driver. + */ + region_nid = phys_to_target_node(cxlr->params.res->start); + if (nid != region_nid) + return NOTIFY_OK; + + perf = &cxlr->coord[ACCESS_COORDINATE_CPU]; + + if (mt_perf_to_adistance(perf, adist)) + return NOTIFY_OK; + + return NOTIFY_STOP; +} + /** * devm_cxl_add_region - Adds a region to a decoder * @cxlrd: root decoder @@ -2367,10 +2480,6 @@ static struct cxl_region *devm_cxl_add_region(struct cxl_root_decoder *cxlrd, if (rc) goto err; - cxlr->memory_notifier.notifier_call = cxl_region_perf_attrs_callback; - cxlr->memory_notifier.priority = CXL_CALLBACK_PRI; - register_memory_notifier(&cxlr->memory_notifier); - rc = devm_add_action_or_reset(port->uport_dev, unregister_region, cxlr); if (rc) return ERR_PTR(rc); @@ -2688,22 +2797,33 @@ static int __cxl_dpa_to_region(struct device *dev, void *arg) { struct cxl_dpa_to_region_context *ctx = arg; struct cxl_endpoint_decoder *cxled; + struct cxl_region *cxlr; u64 dpa = ctx->dpa; if (!is_endpoint_decoder(dev)) return 0; cxled = to_cxl_endpoint_decoder(dev); - if (!cxled->dpa_res || !resource_size(cxled->dpa_res)) + if (!cxled || !cxled->dpa_res || !resource_size(cxled->dpa_res)) return 0; if (dpa > cxled->dpa_res->end || dpa < cxled->dpa_res->start) return 0; - dev_dbg(dev, "dpa:0x%llx mapped in region:%s\n", dpa, - dev_name(&cxled->cxld.region->dev)); + /* + * Stop the region search (return 1) when an endpoint mapping is + * found. The region may not be fully constructed so offering + * the cxlr in the context structure is not guaranteed. + */ + cxlr = cxled->cxld.region; + if (cxlr) + dev_dbg(dev, "dpa:0x%llx mapped in region:%s\n", dpa, + dev_name(&cxlr->dev)); + else + dev_dbg(dev, "dpa:0x%llx mapped in endpoint:%s\n", dpa, + dev_name(dev)); - ctx->cxlr = cxled->cxld.region; + ctx->cxlr = cxlr; return 1; } @@ -2723,20 +2843,13 @@ struct cxl_region *cxl_dpa_to_region(const struct cxl_memdev *cxlmd, u64 dpa) return ctx.cxlr; } -static bool cxl_is_hpa_in_range(u64 hpa, struct cxl_region *cxlr, int pos) +static bool cxl_is_hpa_in_chunk(u64 hpa, struct cxl_region *cxlr, int pos) { struct cxl_region_params *p = &cxlr->params; int gran = p->interleave_granularity; int ways = p->interleave_ways; u64 offset; - /* Is the hpa within this region at all */ - if (hpa < p->res->start || hpa > p->res->end) { - dev_dbg(&cxlr->dev, - "Addr trans fail: hpa 0x%llx not in region\n", hpa); - return false; - } - /* Is the hpa in an expected chunk for its pos(-ition) */ offset = hpa - p->res->start; offset = do_div(offset, gran * ways); @@ -2749,15 +2862,26 @@ static bool cxl_is_hpa_in_range(u64 hpa, struct cxl_region *cxlr, int pos) return false; } -static u64 cxl_dpa_to_hpa(u64 dpa, struct cxl_region *cxlr, - struct cxl_endpoint_decoder *cxled) +u64 cxl_dpa_to_hpa(struct cxl_region *cxlr, const struct cxl_memdev *cxlmd, + u64 dpa) { + struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent); u64 dpa_offset, hpa_offset, bits_upper, mask_upper, hpa; struct cxl_region_params *p = &cxlr->params; - int pos = cxled->pos; + struct cxl_endpoint_decoder *cxled = NULL; u16 eig = 0; u8 eiw = 0; + int pos; + for (int i = 0; i < p->nr_targets; i++) { + cxled = p->targets[i]; + if (cxlmd == cxled_to_memdev(cxled)) + break; + } + if (!cxled || cxlmd != cxled_to_memdev(cxled)) + return ULLONG_MAX; + + pos = cxled->pos; ways_to_eiw(p->interleave_ways, &eiw); granularity_to_eig(p->interleave_granularity, &eig); @@ -2791,27 +2915,21 @@ static u64 cxl_dpa_to_hpa(u64 dpa, struct cxl_region *cxlr, /* Apply the hpa_offset to the region base address */ hpa = hpa_offset + p->res->start; - if (!cxl_is_hpa_in_range(hpa, cxlr, cxled->pos)) - return ULLONG_MAX; - - return hpa; -} + /* Root decoder translation overrides typical modulo decode */ + if (cxlrd->hpa_to_spa) + hpa = cxlrd->hpa_to_spa(cxlrd, hpa); -u64 cxl_trace_hpa(struct cxl_region *cxlr, const struct cxl_memdev *cxlmd, - u64 dpa) -{ - struct cxl_region_params *p = &cxlr->params; - struct cxl_endpoint_decoder *cxled = NULL; - - for (int i = 0; i < p->nr_targets; i++) { - cxled = p->targets[i]; - if (cxlmd == cxled_to_memdev(cxled)) - break; + if (hpa < p->res->start || hpa > p->res->end) { + dev_dbg(&cxlr->dev, + "Addr trans fail: hpa 0x%llx not in region\n", hpa); + return ULLONG_MAX; } - if (!cxled || cxlmd != cxled_to_memdev(cxled)) + + /* Simple chunk check, by pos & gran, only applies to modulo decodes */ + if (!cxlrd->hpa_to_spa && (!cxl_is_hpa_in_chunk(hpa, cxlr, pos))) return ULLONG_MAX; - return cxl_dpa_to_hpa(dpa, cxlr, cxled); + return hpa; } static struct lock_class_key cxl_pmem_region_key; @@ -2847,7 +2965,7 @@ static int cxl_pmem_region_alloc(struct cxl_region *cxlr) * bridge for one device is the same for all. */ if (i == 0) { - cxl_nvb = cxl_find_nvdimm_bridge(cxlmd); + cxl_nvb = cxl_find_nvdimm_bridge(cxlmd->endpoint); if (!cxl_nvb) return -ENODEV; cxlr->cxl_nvb = cxl_nvb; @@ -2964,11 +3082,11 @@ static void cxlr_release_nvdimm(void *_cxlr) struct cxl_region *cxlr = _cxlr; struct cxl_nvdimm_bridge *cxl_nvb = cxlr->cxl_nvb; - device_lock(&cxl_nvb->dev); - if (cxlr->cxlr_pmem) - devm_release_action(&cxl_nvb->dev, cxlr_pmem_unregister, - cxlr->cxlr_pmem); - device_unlock(&cxl_nvb->dev); + scoped_guard(device, &cxl_nvb->dev) { + if (cxlr->cxlr_pmem) + devm_release_action(&cxl_nvb->dev, cxlr_pmem_unregister, + cxlr->cxlr_pmem); + } cxlr->cxl_nvb = NULL; put_device(&cxl_nvb->dev); } @@ -3004,13 +3122,14 @@ static int devm_cxl_add_pmem_region(struct cxl_region *cxlr) dev_dbg(&cxlr->dev, "%s: register %s\n", dev_name(dev->parent), dev_name(dev)); - device_lock(&cxl_nvb->dev); - if (cxl_nvb->dev.driver) - rc = devm_add_action_or_reset(&cxl_nvb->dev, - cxlr_pmem_unregister, cxlr_pmem); - else - rc = -ENXIO; - device_unlock(&cxl_nvb->dev); + scoped_guard(device, &cxl_nvb->dev) { + if (cxl_nvb->dev.driver) + rc = devm_add_action_or_reset(&cxl_nvb->dev, + cxlr_pmem_unregister, + cxlr_pmem); + else + rc = -ENXIO; + } if (rc) goto err_bridge; @@ -3256,6 +3375,14 @@ static int is_system_ram(struct resource *res, void *arg) return 1; } +static void shutdown_notifiers(void *_cxlr) +{ + struct cxl_region *cxlr = _cxlr; + + unregister_memory_notifier(&cxlr->memory_notifier); + unregister_mt_adistance_algorithm(&cxlr->adist_notifier); +} + static int cxl_region_probe(struct device *dev) { struct cxl_region *cxlr = to_cxl_region(dev); @@ -3291,6 +3418,18 @@ out: if (rc) return rc; + cxlr->memory_notifier.notifier_call = cxl_region_perf_attrs_callback; + cxlr->memory_notifier.priority = CXL_CALLBACK_PRI; + register_memory_notifier(&cxlr->memory_notifier); + + cxlr->adist_notifier.notifier_call = cxl_region_calculate_adistance; + cxlr->adist_notifier.priority = 100; + register_mt_adistance_algorithm(&cxlr->adist_notifier); + + rc = devm_add_action_or_reset(&cxlr->dev, shutdown_notifiers, cxlr); + if (rc) + return rc; + switch (cxlr->mode) { case CXL_DECODER_PMEM: return devm_cxl_add_pmem_region(cxlr); |