diff options
Diffstat (limited to 'drivers/cxl')
| -rw-r--r-- | drivers/cxl/Kconfig | 18 | ||||
| -rw-r--r-- | drivers/cxl/Makefile | 2 | ||||
| -rw-r--r-- | drivers/cxl/acpi.c | 126 | ||||
| -rw-r--r-- | drivers/cxl/core/core.h | 8 | ||||
| -rw-r--r-- | drivers/cxl/core/mbox.c | 16 | ||||
| -rw-r--r-- | drivers/cxl/core/pci.c | 2 | ||||
| -rw-r--r-- | drivers/cxl/core/pmem.c | 109 | ||||
| -rw-r--r-- | drivers/cxl/core/port.c | 205 | ||||
| -rw-r--r-- | drivers/cxl/core/region.c | 98 | ||||
| -rw-r--r-- | drivers/cxl/core/regs.c | 70 | ||||
| -rw-r--r-- | drivers/cxl/cxl.h | 70 | ||||
| -rw-r--r-- | drivers/cxl/cxlmem.h | 56 | ||||
| -rw-r--r-- | drivers/cxl/mem.c | 74 | ||||
| -rw-r--r-- | drivers/cxl/pci.c | 18 | ||||
| -rw-r--r-- | drivers/cxl/pmem.c | 386 | ||||
| -rw-r--r-- | drivers/cxl/security.c | 163 |
16 files changed, 925 insertions, 496 deletions
diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig index 768ced3d6fe8..0ac53c422c31 100644 --- a/drivers/cxl/Kconfig +++ b/drivers/cxl/Kconfig @@ -111,4 +111,22 @@ config CXL_REGION select MEMREGION select GET_FREE_REGION +config CXL_REGION_INVALIDATION_TEST + bool "CXL: Region Cache Management Bypass (TEST)" + depends on CXL_REGION + help + CXL Region management and security operations potentially invalidate + the content of CPU caches without notifiying those caches to + invalidate the affected cachelines. The CXL Region driver attempts + to invalidate caches when those events occur. If that invalidation + fails the region will fail to enable. Reasons for cache + invalidation failure are due to the CPU not providing a cache + invalidation mechanism. For example usage of wbinvd is restricted to + bare metal x86. However, for testing purposes toggling this option + can disable that data integrity safety and proceed with enabling + regions when there might be conflicting contents in the CPU cache. + + If unsure, or if this kernel is meant for production environments, + say N. + endif diff --git a/drivers/cxl/Makefile b/drivers/cxl/Makefile index a78270794150..db321f48ba52 100644 --- a/drivers/cxl/Makefile +++ b/drivers/cxl/Makefile @@ -9,5 +9,5 @@ obj-$(CONFIG_CXL_PORT) += cxl_port.o cxl_mem-y := mem.o cxl_pci-y := pci.o cxl_acpi-y := acpi.o -cxl_pmem-y := pmem.o +cxl_pmem-y := pmem.o security.o cxl_port-y := port.o diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index fb649683dd3a..b9472fbfdefc 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -9,6 +9,8 @@ #include "cxlpci.h" #include "cxl.h" +#define CXL_RCRB_SIZE SZ_8K + static unsigned long cfmws_to_decoder_flags(int restrictions) { unsigned long flags = CXL_DECODER_F_ENABLE; @@ -70,6 +72,10 @@ static int cxl_acpi_cfmws_verify(struct device *dev, return 0; } +/* + * Note, @dev must be the first member, see 'struct cxl_chbs_context' + * and mock_acpi_table_parse_cedt() + */ struct cxl_cfmws_context { struct device *dev; struct cxl_port *root_port; @@ -193,34 +199,39 @@ static int add_host_bridge_uport(struct device *match, void *arg) { struct cxl_port *root_port = arg; struct device *host = root_port->dev.parent; - struct acpi_device *bridge = to_cxl_host_bridge(host, match); + struct acpi_device *hb = to_cxl_host_bridge(host, match); struct acpi_pci_root *pci_root; struct cxl_dport *dport; struct cxl_port *port; + struct device *bridge; int rc; - if (!bridge) + if (!hb) return 0; - dport = cxl_find_dport_by_dev(root_port, match); + pci_root = acpi_pci_find_root(hb->handle); + bridge = pci_root->bus->bridge; + dport = cxl_find_dport_by_dev(root_port, bridge); if (!dport) { dev_dbg(host, "host bridge expected and not found\n"); return 0; } - /* - * Note that this lookup already succeeded in - * to_cxl_host_bridge(), so no need to check for failure here - */ - pci_root = acpi_pci_find_root(bridge->handle); - rc = devm_cxl_register_pci_bus(host, match, pci_root->bus); + if (dport->rch) { + dev_info(bridge, "host supports CXL (restricted)\n"); + return 0; + } + + rc = devm_cxl_register_pci_bus(host, bridge, pci_root->bus); if (rc) return rc; - port = devm_cxl_add_port(host, match, dport->component_reg_phys, dport); + port = devm_cxl_add_port(host, bridge, dport->component_reg_phys, + dport); if (IS_ERR(port)) return PTR_ERR(port); - dev_dbg(host, "%s: add: %s\n", dev_name(match), dev_name(&port->dev)); + + dev_info(bridge, "host supports CXL\n"); return 0; } @@ -228,7 +239,9 @@ static int add_host_bridge_uport(struct device *match, void *arg) struct cxl_chbs_context { struct device *dev; unsigned long long uid; + resource_size_t rcrb; resource_size_t chbcr; + u32 cxl_version; }; static int cxl_get_chbcr(union acpi_subtable_headers *header, void *arg, @@ -244,51 +257,85 @@ static int cxl_get_chbcr(union acpi_subtable_headers *header, void *arg, if (ctx->uid != chbs->uid) return 0; - ctx->chbcr = chbs->base; + + ctx->cxl_version = chbs->cxl_version; + ctx->rcrb = CXL_RESOURCE_NONE; + ctx->chbcr = CXL_RESOURCE_NONE; + + if (!chbs->base) + return 0; + + if (chbs->cxl_version != ACPI_CEDT_CHBS_VERSION_CXL11) { + ctx->chbcr = chbs->base; + return 0; + } + + if (chbs->length != CXL_RCRB_SIZE) + return 0; + + ctx->rcrb = chbs->base; + ctx->chbcr = cxl_rcrb_to_component(ctx->dev, chbs->base, + CXL_RCRB_DOWNSTREAM); return 0; } static int add_host_bridge_dport(struct device *match, void *arg) { - acpi_status status; + acpi_status rc; + struct device *bridge; unsigned long long uid; struct cxl_dport *dport; struct cxl_chbs_context ctx; + struct acpi_pci_root *pci_root; struct cxl_port *root_port = arg; struct device *host = root_port->dev.parent; - struct acpi_device *bridge = to_cxl_host_bridge(host, match); + struct acpi_device *hb = to_cxl_host_bridge(host, match); - if (!bridge) + if (!hb) return 0; - status = acpi_evaluate_integer(bridge->handle, METHOD_NAME__UID, NULL, - &uid); - if (status != AE_OK) { - dev_err(host, "unable to retrieve _UID of %s\n", - dev_name(match)); + rc = acpi_evaluate_integer(hb->handle, METHOD_NAME__UID, NULL, &uid); + if (rc != AE_OK) { + dev_err(match, "unable to retrieve _UID\n"); return -ENODEV; } + dev_dbg(match, "UID found: %lld\n", uid); + ctx = (struct cxl_chbs_context) { - .dev = host, + .dev = match, .uid = uid, }; acpi_table_parse_cedt(ACPI_CEDT_TYPE_CHBS, cxl_get_chbcr, &ctx); - if (ctx.chbcr == 0) { - dev_warn(host, "No CHBS found for Host Bridge: %s\n", - dev_name(match)); + if (!ctx.chbcr) { + dev_warn(match, "No CHBS found for Host Bridge (UID %lld)\n", + uid); return 0; } - dport = devm_cxl_add_dport(root_port, match, uid, ctx.chbcr); - if (IS_ERR(dport)) { - dev_err(host, "failed to add downstream port: %s\n", - dev_name(match)); - return PTR_ERR(dport); + if (ctx.rcrb != CXL_RESOURCE_NONE) + dev_dbg(match, "RCRB found for UID %lld: %pa\n", uid, &ctx.rcrb); + + if (ctx.chbcr == CXL_RESOURCE_NONE) { + dev_warn(match, "No CHBS found for Host Bridge (UID %lld)\n", uid); + return 0; } - dev_dbg(host, "add dport%llu: %s\n", uid, dev_name(match)); + + dev_dbg(match, "CHBCR found: %pa\n", &ctx.chbcr); + + pci_root = acpi_pci_find_root(hb->handle); + bridge = pci_root->bus->bridge; + if (ctx.cxl_version == ACPI_CEDT_CHBS_VERSION_CXL11) + dport = devm_cxl_add_rch_dport(root_port, bridge, uid, + ctx.chbcr, ctx.rcrb); + else + dport = devm_cxl_add_dport(root_port, bridge, uid, + ctx.chbcr); + if (IS_ERR(dport)) + return PTR_ERR(dport); + return 0; } @@ -466,7 +513,6 @@ static int cxl_acpi_probe(struct platform_device *pdev) root_port = devm_cxl_add_port(host, host, CXL_RESOURCE_NONE, NULL); if (IS_ERR(root_port)) return PTR_ERR(root_port); - dev_dbg(host, "add: %s\n", dev_name(&root_port->dev)); rc = bus_for_each_dev(adev->dev.bus, NULL, root_port, add_host_bridge_dport); @@ -512,7 +558,8 @@ static int cxl_acpi_probe(struct platform_device *pdev) return rc; /* In case PCI is scanned before ACPI re-trigger memdev attach */ - return cxl_bus_rescan(); + cxl_bus_rescan(); + return 0; } static const struct acpi_device_id cxl_acpi_ids[] = { @@ -536,7 +583,20 @@ static struct platform_driver cxl_acpi_driver = { .id_table = cxl_test_ids, }; -module_platform_driver(cxl_acpi_driver); +static int __init cxl_acpi_init(void) +{ + return platform_driver_register(&cxl_acpi_driver); +} + +static void __exit cxl_acpi_exit(void) +{ + platform_driver_unregister(&cxl_acpi_driver); + cxl_bus_drain(); +} + +module_init(cxl_acpi_init); +module_exit(cxl_acpi_exit); MODULE_LICENSE("GPL v2"); MODULE_IMPORT_NS(CXL); MODULE_IMPORT_NS(ACPI); +MODULE_SOFTDEP("pre: cxl_pmem"); diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h index 1d8f87be283f..8c04672dca56 100644 --- a/drivers/cxl/core/core.h +++ b/drivers/cxl/core/core.h @@ -58,14 +58,6 @@ extern struct rw_semaphore cxl_dpa_rwsem; bool is_switch_decoder(struct device *dev); struct cxl_switch_decoder *to_cxl_switch_decoder(struct device *dev); -static inline struct cxl_ep *cxl_ep_load(struct cxl_port *port, - struct cxl_memdev *cxlmd) -{ - if (!port) - return NULL; - - return xa_load(&port->endpoints, (unsigned long)&cxlmd->dev); -} int cxl_memdev_init(void); void cxl_memdev_exit(void); diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 0c90f13870a4..35dd889f1d3a 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -65,6 +65,12 @@ static struct cxl_mem_command cxl_mem_commands[CXL_MEM_COMMAND_ID_MAX] = { CXL_CMD(GET_SCAN_MEDIA_CAPS, 0x10, 0x4, 0), CXL_CMD(SCAN_MEDIA, 0x11, 0, 0), CXL_CMD(GET_SCAN_MEDIA, 0, CXL_VARIABLE_PAYLOAD, 0), + CXL_CMD(GET_SECURITY_STATE, 0, 0x4, 0), + CXL_CMD(SET_PASSPHRASE, 0x60, 0, 0), + CXL_CMD(DISABLE_PASSPHRASE, 0x40, 0, 0), + CXL_CMD(FREEZE_SECURITY, 0, 0, 0), + CXL_CMD(UNLOCK, 0x20, 0, 0), + CXL_CMD(PASSPHRASE_SECURE_ERASE, 0x40, 0, 0), }; /* @@ -698,6 +704,16 @@ int cxl_enumerate_cmds(struct cxl_dev_state *cxlds) rc = 0; } + /* + * Setup permanently kernel exclusive commands, i.e. the + * mechanism is driven through sysfs, keyctl, etc... + */ + set_bit(CXL_MEM_COMMAND_ID_SET_PASSPHRASE, cxlds->exclusive_cmds); + set_bit(CXL_MEM_COMMAND_ID_DISABLE_PASSPHRASE, cxlds->exclusive_cmds); + set_bit(CXL_MEM_COMMAND_ID_UNLOCK, cxlds->exclusive_cmds); + set_bit(CXL_MEM_COMMAND_ID_PASSPHRASE_SECURE_ERASE, + cxlds->exclusive_cmds); + out: kvfree(gsl); return rc; diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index 2a8a88d38533..57764e9cd19d 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -61,8 +61,6 @@ static int match_add_dports(struct pci_dev *pdev, void *data) } ctx->count++; - dev_dbg(&port->dev, "add dport%d: %s\n", port_num, dev_name(&pdev->dev)); - return 0; } diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c index 36aa5070d902..f3d2169b6731 100644 --- a/drivers/cxl/core/pmem.c +++ b/drivers/cxl/core/pmem.c @@ -99,7 +99,6 @@ static struct cxl_nvdimm_bridge *cxl_nvdimm_bridge_alloc(struct cxl_port *port) dev = &cxl_nvb->dev; cxl_nvb->port = port; - cxl_nvb->state = CXL_NVB_NEW; device_initialize(dev); lockdep_set_class(&dev->mutex, &cxl_nvdimm_bridge_key); device_set_pm_not_required(dev); @@ -117,28 +116,7 @@ err: static void unregister_nvb(void *_cxl_nvb) { struct cxl_nvdimm_bridge *cxl_nvb = _cxl_nvb; - bool flush; - /* - * If the bridge was ever activated then there might be in-flight state - * work to flush. Once the state has been changed to 'dead' then no new - * work can be queued by user-triggered bind. - */ - device_lock(&cxl_nvb->dev); - flush = cxl_nvb->state != CXL_NVB_NEW; - cxl_nvb->state = CXL_NVB_DEAD; - device_unlock(&cxl_nvb->dev); - - /* - * Even though the device core will trigger device_release_driver() - * before the unregister, it does not know about the fact that - * cxl_nvdimm_bridge_driver defers ->remove() work. So, do the driver - * release not and flush it before tearing down the nvdimm device - * hierarchy. - */ - device_release_driver(&cxl_nvb->dev); - if (flush) - flush_work(&cxl_nvb->state_work); device_unregister(&cxl_nvb->dev); } @@ -188,7 +166,6 @@ static void cxl_nvdimm_release(struct device *dev) { struct cxl_nvdimm *cxl_nvd = to_cxl_nvdimm(dev); - xa_destroy(&cxl_nvd->pmem_regions); kfree(cxl_nvd); } @@ -220,7 +197,8 @@ EXPORT_SYMBOL_NS_GPL(to_cxl_nvdimm, CXL); static struct lock_class_key cxl_nvdimm_key; -static struct cxl_nvdimm *cxl_nvdimm_alloc(struct cxl_memdev *cxlmd) +static struct cxl_nvdimm *cxl_nvdimm_alloc(struct cxl_nvdimm_bridge *cxl_nvb, + struct cxl_memdev *cxlmd) { struct cxl_nvdimm *cxl_nvd; struct device *dev; @@ -231,38 +209,78 @@ static struct cxl_nvdimm *cxl_nvdimm_alloc(struct cxl_memdev *cxlmd) dev = &cxl_nvd->dev; cxl_nvd->cxlmd = cxlmd; - xa_init(&cxl_nvd->pmem_regions); + cxlmd->cxl_nvd = cxl_nvd; device_initialize(dev); lockdep_set_class(&dev->mutex, &cxl_nvdimm_key); device_set_pm_not_required(dev); dev->parent = &cxlmd->dev; dev->bus = &cxl_bus_type; dev->type = &cxl_nvdimm_type; + /* + * A "%llx" string is 17-bytes vs dimm_id that is max + * NVDIMM_KEY_DESC_LEN + */ + BUILD_BUG_ON(sizeof(cxl_nvd->dev_id) < 17 || + sizeof(cxl_nvd->dev_id) > NVDIMM_KEY_DESC_LEN); + sprintf(cxl_nvd->dev_id, "%llx", cxlmd->cxlds->serial); return cxl_nvd; } -static void cxl_nvd_unregister(void *dev) +static void cxl_nvd_unregister(void *_cxl_nvd) { - device_unregister(dev); + struct cxl_nvdimm *cxl_nvd = _cxl_nvd; + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_nvdimm_bridge *cxl_nvb = cxlmd->cxl_nvb; + + /* + * Either the bridge is in ->remove() context under the device_lock(), + * or cxlmd_release_nvdimm() is cancelling the bridge's release action + * for @cxl_nvd and doing it itself (while manually holding the bridge + * lock). + */ + device_lock_assert(&cxl_nvb->dev); + cxl_nvd->cxlmd = NULL; + cxlmd->cxl_nvd = NULL; + device_unregister(&cxl_nvd->dev); +} + +static void cxlmd_release_nvdimm(void *_cxlmd) +{ + struct cxl_memdev *cxlmd = _cxlmd; + struct cxl_nvdimm_bridge *cxl_nvb = cxlmd->cxl_nvb; + + device_lock(&cxl_nvb->dev); + if (cxlmd->cxl_nvd) + devm_release_action(&cxl_nvb->dev, cxl_nvd_unregister, + cxlmd->cxl_nvd); + device_unlock(&cxl_nvb->dev); + put_device(&cxl_nvb->dev); } /** * devm_cxl_add_nvdimm() - add a bridge between a cxl_memdev and an nvdimm - * @host: same host as @cxlmd * @cxlmd: cxl_memdev instance that will perform LIBNVDIMM operations * * Return: 0 on success negative error code on failure. */ -int devm_cxl_add_nvdimm(struct device *host, struct cxl_memdev *cxlmd) +int devm_cxl_add_nvdimm(struct cxl_memdev *cxlmd) { + struct cxl_nvdimm_bridge *cxl_nvb; struct cxl_nvdimm *cxl_nvd; struct device *dev; int rc; - cxl_nvd = cxl_nvdimm_alloc(cxlmd); - if (IS_ERR(cxl_nvd)) - return PTR_ERR(cxl_nvd); + cxl_nvb = cxl_find_nvdimm_bridge(&cxlmd->dev); + if (!cxl_nvb) + return -ENODEV; + + cxl_nvd = cxl_nvdimm_alloc(cxl_nvb, cxlmd); + if (IS_ERR(cxl_nvd)) { + rc = PTR_ERR(cxl_nvd); + goto err_alloc; + } + cxlmd->cxl_nvb = cxl_nvb; dev = &cxl_nvd->dev; rc = dev_set_name(dev, "pmem%d", cxlmd->id); @@ -273,13 +291,34 @@ int devm_cxl_add_nvdimm(struct device *host, struct cxl_memdev *cxlmd) if (rc) goto err; - dev_dbg(host, "%s: register %s\n", dev_name(dev->parent), - dev_name(dev)); + dev_dbg(&cxlmd->dev, "register %s\n", dev_name(dev)); + + /* + * The two actions below arrange for @cxl_nvd to be deleted when either + * the top-level PMEM bridge goes down, or the endpoint device goes + * through ->remove(). + */ + device_lock(&cxl_nvb->dev); + if (cxl_nvb->dev.driver) + rc = devm_add_action_or_reset(&cxl_nvb->dev, cxl_nvd_unregister, + cxl_nvd); + else + rc = -ENXIO; + device_unlock(&cxl_nvb->dev); - return devm_add_action_or_reset(host, cxl_nvd_unregister, dev); + if (rc) + goto err_alloc; + + /* @cxlmd carries a reference on @cxl_nvb until cxlmd_release_nvdimm */ + return devm_add_action_or_reset(&cxlmd->dev, cxlmd_release_nvdimm, cxlmd); err: put_device(dev); +err_alloc: + cxlmd->cxl_nvb = NULL; + cxlmd->cxl_nvd = NULL; + put_device(&cxl_nvb->dev); + return rc; } EXPORT_SYMBOL_NS_GPL(devm_cxl_add_nvdimm, CXL); diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 3f37b061ff26..326ffba3fb15 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -628,6 +628,8 @@ static struct cxl_port *cxl_port_alloc(struct device *uport, iter = to_cxl_port(iter->dev.parent); if (iter->host_bridge) port->host_bridge = iter->host_bridge; + else if (parent_dport->rch) + port->host_bridge = parent_dport->dport; else port->host_bridge = iter->uport; dev_dbg(uport, "host-bridge: %s\n", dev_name(port->host_bridge)); @@ -655,16 +657,10 @@ err: return ERR_PTR(rc); } -/** - * devm_cxl_add_port - register a cxl_port in CXL memory decode hierarchy - * @host: host device for devm operations - * @uport: "physical" device implementing this upstream port - * @component_reg_phys: (optional) for configurable cxl_port instances - * @parent_dport: next hop up in the CXL memory decode hierarchy - */ -struct cxl_port *devm_cxl_add_port(struct device *host, struct device *uport, - resource_size_t component_reg_phys, - struct cxl_dport *parent_dport) +static struct cxl_port *__devm_cxl_add_port(struct device *host, + struct device *uport, + resource_size_t component_reg_phys, + struct cxl_dport *parent_dport) { struct cxl_port *port; struct device *dev; @@ -702,6 +698,41 @@ err: put_device(dev); return ERR_PTR(rc); } + +/** + * devm_cxl_add_port - register a cxl_port in CXL memory decode hierarchy + * @host: host device for devm operations + * @uport: "physical" device implementing this upstream port + * @component_reg_phys: (optional) for configurable cxl_port instances + * @parent_dport: next hop up in the CXL memory decode hierarchy + */ +struct cxl_port *devm_cxl_add_port(struct device *host, struct device *uport, + resource_size_t component_reg_phys, + struct cxl_dport *parent_dport) +{ + struct cxl_port *port, *parent_port; + + port = __devm_cxl_add_port(host, uport, component_reg_phys, + parent_dport); + + parent_port = parent_dport ? parent_dport->port : NULL; + if (IS_ERR(port)) { + dev_dbg(uport, "Failed to add %s%s%s%s: %ld\n", + dev_name(&port->dev), + parent_port ? " to " : "", + parent_port ? dev_name(&parent_port->dev) : "", + parent_port ? "" : " (root port)", + PTR_ERR(port)); + } else { + dev_dbg(uport, "%s added%s%s%s\n", + dev_name(&port->dev), + parent_port ? " to " : "", + parent_port ? dev_name(&parent_port->dev) : "", + parent_port ? "" : " (root port)"); + } + + return port; +} EXPORT_SYMBOL_NS_GPL(devm_cxl_add_port, CXL); struct pci_bus *cxl_port_to_pci_bus(struct cxl_port *port) @@ -870,20 +901,10 @@ static void cxl_dport_unlink(void *data) sysfs_remove_link(&port->dev.kobj, link_name); } -/** - * devm_cxl_add_dport - append downstream port data to a cxl_port - * @port: the cxl_port that references this dport - * @dport_dev: firmware or PCI device representing the dport - * @port_id: identifier for this dport in a decoder's target list - * @component_reg_phys: optional location of CXL component registers - * - * Note that dports are appended to the devm release action's of the - * either the port's host (for root ports), or the port itself (for - * switch ports) - */ -struct cxl_dport *devm_cxl_add_dport(struct cxl_port *port, - struct device *dport_dev, int port_id, - resource_size_t component_reg_phys) +static struct cxl_dport * +__devm_cxl_add_dport(struct cxl_port *port, struct device *dport_dev, + int port_id, resource_size_t component_reg_phys, + resource_size_t rcrb) { char link_name[CXL_TARGET_STRLEN]; struct cxl_dport *dport; @@ -913,6 +934,9 @@ struct cxl_dport *devm_cxl_add_dport(struct cxl_port *port, dport->port_id = port_id; dport->component_reg_phys = component_reg_phys; dport->port = port; + if (rcrb != CXL_RESOURCE_NONE) + dport->rch = true; + dport->rcrb = rcrb; cond_cxl_root_lock(port); rc = add_dport(port, dport); @@ -935,8 +959,74 @@ struct cxl_dport *devm_cxl_add_dport(struct cxl_port *port, return dport; } + +/** + * devm_cxl_add_dport - append VH downstream port data to a cxl_port + * @port: the cxl_port that references this dport + * @dport_dev: firmware or PCI device representing the dport + * @port_id: identifier for this dport in a decoder's target list + * @component_reg_phys: optional location of CXL component registers + * + * Note that dports are appended to the devm release action's of the + * either the port's host (for root ports), or the port itself (for + * switch ports) + */ +struct cxl_dport *devm_cxl_add_dport(struct cxl_port *port, + struct device *dport_dev, int port_id, + resource_size_t component_reg_phys) +{ + struct cxl_dport *dport; + + dport = __devm_cxl_add_dport(port, dport_dev, port_id, + component_reg_phys, CXL_RESOURCE_NONE); + if (IS_ERR(dport)) { + dev_dbg(dport_dev, "failed to add dport to %s: %ld\n", + dev_name(&port->dev), PTR_ERR(dport)); + } else { + dev_dbg(dport_dev, "dport added to %s\n", + dev_name(&port->dev)); + } + + return dport; +} EXPORT_SYMBOL_NS_GPL(devm_cxl_add_dport, CXL); +/** + * devm_cxl_add_rch_dport - append RCH downstream port data to a cxl_port + * @port: the cxl_port that references this dport + * @dport_dev: firmware or PCI device representing the dport + * @port_id: identifier for this dport in a decoder's target list + * @component_reg_phys: optional location of CXL component registers + * @rcrb: mandatory location of a Root Complex Register Block + * + * See CXL 3.0 9.11.8 CXL Devices Attached to an RCH + */ +struct cxl_dport *devm_cxl_add_rch_dport(struct cxl_port *port, + struct device *dport_dev, int port_id, + resource_size_t component_reg_phys, + resource_size_t rcrb) +{ + struct cxl_dport *dport; + + if (rcrb == CXL_RESOURCE_NONE) { + dev_dbg(&port->dev, "failed to add RCH dport, missing RCRB\n"); + return ERR_PTR(-EINVAL); + } + + dport = __devm_cxl_add_dport(port, dport_dev, port_id, + component_reg_phys, rcrb); + if (IS_ERR(dport)) { + dev_dbg(dport_dev, "failed to add RCH dport to %s: %ld\n", + dev_name(&port->dev), PTR_ERR(dport)); + } else { + dev_dbg(dport_dev, "RCH dport added to %s\n", + dev_name(&port->dev)); + } + + return dport; +} +EXPORT_SYMBOL_NS_GPL(devm_cxl_add_rch_dport, CXL); + static int add_ep(struct cxl_ep *new) { struct cxl_port *port = new->dport->port; @@ -1122,47 +1212,6 @@ static void reap_dports(struct cxl_port *port) } } -int devm_cxl_add_endpoint(struct cxl_memdev *cxlmd, - struct cxl_dport *parent_dport) -{ - struct cxl_port *parent_port = parent_dport->port; - struct cxl_dev_state *cxlds = cxlmd->cxlds; - struct cxl_port *endpoint, *iter, *down; - int rc; - - /* - * Now that the path to the root is established record all the - * intervening ports in the chain. - */ - for (iter = parent_port, down = NULL; !is_cxl_root(iter); - down = iter, iter = to_cxl_port(iter->dev.parent)) { - struct cxl_ep *ep; - - ep = cxl_ep_load(iter, cxlmd); - ep->next = down; - } - - endpoint = devm_cxl_add_port(&parent_port->dev, &cxlmd->dev, - cxlds->component_reg_phys, parent_dport); - if (IS_ERR(endpoint)) - return PTR_ERR(endpoint); - - dev_dbg(&cxlmd->dev, "add: %s\n", dev_name(&endpoint->dev)); - - rc = cxl_endpoint_autoremove(cxlmd, endpoint); - if (rc) - return rc; - - if (!endpoint->dev.driver) { - dev_err(&cxlmd->dev, "%s failed probe\n", - dev_name(&endpoint->dev)); - return -ENXIO; - } - - return 0; -} -EXPORT_SYMBOL_NS_GPL(devm_cxl_add_endpoint, CXL); - static void cxl_detach_ep(void *data) { struct cxl_memdev *cxlmd = data; @@ -1320,6 +1369,13 @@ int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd) struct device *iter; int rc; + /* + * Skip intermediate port enumeration in the RCH case, there + * are no ports in between a host bridge and an endpoint. + */ + if (cxlmd->cxlds->rcd) + return 0; + rc = devm_add_action_or_reset(&cxlmd->dev, cxl_detach_ep, cxlmd); if (rc) return rc; @@ -1797,12 +1853,27 @@ static void cxl_bus_remove(struct device *dev) static struct workqueue_struct *cxl_bus_wq; -int cxl_bus_rescan(void) +static void cxl_bus_rescan_queue(struct work_struct *w) { - return bus_rescan_devices(&cxl_bus_type); + int rc = bus_rescan_devices(&cxl_bus_type); + + pr_debug("CXL bus rescan result: %d\n", rc); +} + +void cxl_bus_rescan(void) +{ + static DECLARE_WORK(rescan_work, cxl_bus_rescan_queue); + + queue_work(cxl_bus_wq, &rescan_work); } EXPORT_SYMBOL_NS_GPL(cxl_bus_rescan, CXL); +void cxl_bus_drain(void) +{ + drain_workqueue(cxl_bus_wq); +} +EXPORT_SYMBOL_NS_GPL(cxl_bus_drain, CXL); + bool schedule_cxl_memdev_detach(struct cxl_memdev *cxlmd) { return queue_work(cxl_bus_wq, &cxlmd->detach_work); diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index f9ae5ad284ff..f75df35b9d3d 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -1403,6 +1403,8 @@ static int attach_target(struct cxl_region *cxlr, const char *decoder, int pos) goto out; down_read(&cxl_dpa_rwsem); rc = cxl_region_attach(cxlr, to_cxl_endpoint_decoder(dev), pos); + if (rc == 0) + set_bit(CXL_REGION_F_INCOHERENT, &cxlr->flags); up_read(&cxl_dpa_rwsem); up_write(&cxl_region_rwsem); out: @@ -1812,6 +1814,7 @@ static struct lock_class_key cxl_pmem_region_key; static struct cxl_pmem_region *cxl_pmem_region_alloc(struct cxl_region *cxlr) { struct cxl_region_params *p = &cxlr->params; + struct cxl_nvdimm_bridge *cxl_nvb; struct cxl_pmem_region *cxlr_pmem; struct device *dev; int i; @@ -1839,6 +1842,18 @@ static struct cxl_pmem_region *cxl_pmem_region_alloc(struct cxl_region *cxlr) struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); struct cxl_pmem_region_mapping *m = &cxlr_pmem->mapping[i]; + /* + * Regions never span CXL root devices, so by definition the + * bridge for one device is the same for all. + */ + if (i == 0) { + cxl_nvb = cxl_find_nvdimm_bridge(&cxlmd->dev); + if (!cxl_nvb) { + cxlr_pmem = ERR_PTR(-ENODEV); + goto out; + } + cxlr->cxl_nvb = cxl_nvb; + } m->cxlmd = cxlmd; get_device(&cxlmd->dev); m->start = cxled->dpa_res->start; @@ -1848,6 +1863,7 @@ static struct cxl_pmem_region *cxl_pmem_region_alloc(struct cxl_region *cxlr) dev = &cxlr_pmem->dev; cxlr_pmem->cxlr = cxlr; + cxlr->cxlr_pmem = cxlr_pmem; device_initialize(dev); lockdep_set_class(&dev->mutex, &cxl_pmem_region_key); device_set_pm_not_required(dev); @@ -1860,9 +1876,36 @@ out: return cxlr_pmem; } -static void cxlr_pmem_unregister(void *dev) +static void cxlr_pmem_unregister(void *_cxlr_pmem) { - device_unregister(dev); + struct cxl_pmem_region *cxlr_pmem = _cxlr_pmem; + struct cxl_region *cxlr = cxlr_pmem->cxlr; + struct cxl_nvdimm_bridge *cxl_nvb = cxlr->cxl_nvb; + + /* + * Either the bridge is in ->remove() context under the device_lock(), + * or cxlr_release_nvdimm() is cancelling the bridge's release action + * for @cxlr_pmem and doing it itself (while manually holding the bridge + * lock). + */ + device_lock_assert(&cxl_nvb->dev); + cxlr->cxlr_pmem = NULL; + cxlr_pmem->cxlr = NULL; + device_unregister(&cxlr_pmem->dev); +} + +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); + cxlr->cxl_nvb = NULL; + put_device(&cxl_nvb->dev); } /** @@ -1874,12 +1917,14 @@ static void cxlr_pmem_unregister(void *dev) static int devm_cxl_add_pmem_region(struct cxl_region *cxlr) { struct cxl_pmem_region *cxlr_pmem; + struct cxl_nvdimm_bridge *cxl_nvb; struct device *dev; int rc; cxlr_pmem = cxl_pmem_region_alloc(cxlr); if (IS_ERR(cxlr_pmem)) return PTR_ERR(cxlr_pmem); + cxl_nvb = cxlr->cxl_nvb; dev = &cxlr_pmem->dev; rc = dev_set_name(dev, "pmem_region%d", cxlr->id); @@ -1893,13 +1938,52 @@ 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)); - return devm_add_action_or_reset(&cxlr->dev, cxlr_pmem_unregister, 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); + + if (rc) + goto err_bridge; + + /* @cxlr carries a reference on @cxl_nvb until cxlr_release_nvdimm */ + return devm_add_action_or_reset(&cxlr->dev, cxlr_release_nvdimm, cxlr); err: put_device(dev); +err_bridge: + put_device(&cxl_nvb->dev); + cxlr->cxl_nvb = NULL; return rc; } +static int cxl_region_invalidate_memregion(struct cxl_region *cxlr) +{ + if (!test_bit(CXL_REGION_F_INCOHERENT, &cxlr->flags)) + return 0; + + if (!cpu_cache_has_invalidate_memregion()) { + if (IS_ENABLED(CONFIG_CXL_REGION_INVALIDATION_TEST)) { + dev_warn( + &cxlr->dev, + "Bypassing cpu_cache_invalidate_memergion() for testing!\n"); + clear_bit(CXL_REGION_F_INCOHERENT, &cxlr->flags); + return 0; + } else { + dev_err(&cxlr->dev, + "Failed to synchronize CPU cache state\n"); + return -ENXIO; + } + } + + cpu_cache_invalidate_memregion(IORES_DESC_CXL); + clear_bit(CXL_REGION_F_INCOHERENT, &cxlr->flags); + return 0; +} + static int cxl_region_probe(struct device *dev) { struct cxl_region *cxlr = to_cxl_region(dev); @@ -1915,14 +1999,21 @@ static int cxl_region_probe(struct device *dev) if (p->state < CXL_CONFIG_COMMIT) { dev_dbg(&cxlr->dev, "config state: %d\n", p->state); rc = -ENXIO; + goto out; } + rc = cxl_region_invalidate_memregion(cxlr); + /* * From this point on any path that changes the region's state away from * CXL_CONFIG_COMMIT is also responsible for releasing the driver. */ +out: up_read(&cxl_region_rwsem); + if (rc) + return rc; + switch (cxlr->mode) { case CXL_DECODER_PMEM: return devm_cxl_add_pmem_region(cxlr); @@ -1950,4 +2041,5 @@ void cxl_region_exit(void) } MODULE_IMPORT_NS(CXL); +MODULE_IMPORT_NS(DEVMEM); MODULE_ALIAS_CXL(CXL_DEVICE_REGION); diff --git a/drivers/cxl/core/regs.c b/drivers/cxl/core/regs.c index b10f8b79ec40..dfce37d11df1 100644 --- a/drivers/cxl/core/regs.c +++ b/drivers/cxl/core/regs.c @@ -7,6 +7,8 @@ #include <cxlmem.h> #include <cxlpci.h> +#include "core.h" + /** * DOC: cxl registers * @@ -179,6 +181,9 @@ void __iomem *devm_cxl_iomap_block(struct device *dev, resource_size_t addr, void __iomem *ret_val; struct resource *res; + if (WARN_ON_ONCE(addr == CXL_RESOURCE_NONE)) + return NULL; + res = devm_request_mem_region(dev, addr, length, dev_name(dev)); if (!res) { resource_size_t end = addr + length - 1; @@ -326,3 +331,68 @@ int cxl_find_regblock(struct pci_dev *pdev, enum cxl_regloc_type type, return -ENODEV; } EXPORT_SYMBOL_NS_GPL(cxl_find_regblock, CXL); + +resource_size_t cxl_rcrb_to_component(struct device *dev, + resource_size_t rcrb, + enum cxl_rcrb which) +{ + resource_size_t component_reg_phys; + u32 bar0, bar1; + void *addr; + u16 cmd; + u32 id; + + if (which == CXL_RCRB_UPSTREAM) + rcrb += SZ_4K; + + /* + * RCRB's BAR[0..1] point to component block containing CXL + * subsystem component registers. MEMBAR extraction follows + * the PCI Base spec here, esp. 64 bit extraction and memory + * ranges alignment (6.0, 7.5.1.2.1). + */ + if (!request_mem_region(rcrb, SZ_4K, "CXL RCRB")) + return CXL_RESOURCE_NONE; + addr = ioremap(rcrb, SZ_4K); + if (!addr) { + dev_err(dev, "Failed to map region %pr\n", addr); + release_mem_region(rcrb, SZ_4K); + return CXL_RESOURCE_NONE; + } + + id = readl(addr + PCI_VENDOR_ID); + cmd = readw(addr + PCI_COMMAND); + bar0 = readl(addr + PCI_BASE_ADDRESS_0); + bar1 = readl(addr + PCI_BASE_ADDRESS_1); + iounmap(addr); + release_mem_region(rcrb, SZ_4K); + + /* + * Sanity check, see CXL 3.0 Figure 9-8 CXL Device that Does Not + * Remap Upstream Port and Component Registers + */ + if (id == U32_MAX) { + if (which == CXL_RCRB_DOWNSTREAM) + dev_err(dev, "Failed to access Downstream Port RCRB\n"); + return CXL_RESOURCE_NONE; + } + if (!(cmd & PCI_COMMAND_MEMORY)) + return CXL_RESOURCE_NONE; + /* The RCRB is a Memory Window, and the MEM_TYPE_1M bit is obsolete */ + if (bar0 & (PCI_BASE_ADDRESS_MEM_TYPE_1M | PCI_BASE_ADDRESS_SPACE_IO)) + return CXL_RESOURCE_NONE; + + component_reg_phys = bar0 & PCI_BASE_ADDRESS_MEM_MASK; + if (bar0 & PCI_BASE_ADDRESS_MEM_TYPE_64) + component_reg_phys |= ((u64)bar1) << 32; + + if (!component_reg_phys) + return CXL_RESOURCE_NONE; + + /* MEMBAR is block size (64k) aligned. */ + if (!IS_ALIGNED(component_reg_phys, CXL_COMPONENT_REG_BLOCK_SIZE)) + return CXL_RESOURCE_NONE; + + return component_reg_phys; +} +EXPORT_SYMBOL_NS_GPL(cxl_rcrb_to_component, CXL); diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 2f3951b76e2d..89847abb7e14 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -62,6 +62,10 @@ #define CXL_HDM_DECODER0_SKIP_LOW(i) CXL_HDM_DECODER0_TL_LOW(i) #define CXL_HDM_DECODER0_SKIP_HIGH(i) CXL_HDM_DECODER0_TL_HIGH(i) +/* HDM decoder control register constants CXL 3.0 8.2.5.19.7 */ +#define CXL_DECODER_MIN_GRANULARITY 256 +#define CXL_DECODER_MAX_ENCODED_IG 6 + static inline int cxl_hdm_decoder_count(u32 cap_hdr) { int val = FIELD_GET(CXL_HDM_DECODER_COUNT_MASK, cap_hdr); @@ -72,9 +76,9 @@ static inline int cxl_hdm_decoder_count(u32 cap_hdr) /* Encode defined in CXL 2.0 8.2.5.12.7 HDM Decoder Control Register */ static inline int cxl_to_granularity(u16 ig, unsigned int *val) { - if (ig > 6) + if (ig > CXL_DECODER_MAX_ENCODED_IG) return -EINVAL; - *val = 256 << ig; + *val = CXL_DECODER_MIN_GRANULARITY << ig; return 0; } @@ -97,7 +101,7 @@ static inline int cxl_to_ways(u8 eniw, unsigned int *val) static inline int granularity_to_cxl(int g, u16 *ig) { - if (g > SZ_16K || g < 256 || !is_power_of_2(g)) + if (g > SZ_16K || g < CXL_DECODER_MIN_GRANULARITY || !is_power_of_2(g)) return -EINVAL; *ig = ilog2(g) - 8; return 0; @@ -238,8 +242,14 @@ int cxl_map_device_regs(struct device *dev, struct cxl_device_regs *regs, enum cxl_regloc_type; int cxl_find_regblock(struct pci_dev *pdev, enum cxl_regloc_type type, struct cxl_register_map *map); -void __iomem *devm_cxl_iomap_block(struct device *dev, resource_size_t addr, - resource_size_t length); + +enum cxl_rcrb { + CXL_RCRB_DOWNSTREAM, + CXL_RCRB_UPSTREAM, +}; +resource_size_t cxl_rcrb_to_component(struct device *dev, + resource_size_t rcrb, + enum cxl_rcrb which); #define CXL_RESOURCE_NONE ((resource_size_t) -1) #define CXL_TARGET_STRLEN 20 @@ -268,7 +278,6 @@ enum cxl_decoder_type { */ #define CXL_DECODER_MAX_INTERLEAVE 16 -#define CXL_DECODER_MIN_GRANULARITY 256 /** * struct cxl_decoder - Common CXL HDM Decoder Attributes @@ -399,12 +408,21 @@ struct cxl_region_params { int nr_targets; }; +/* + * Flag whether this region needs to have its HPA span synchronized with + * CPU cache state at region activation time. + */ +#define CXL_REGION_F_INCOHERENT 0 + /** * struct cxl_region - CXL region * @dev: This region's device * @id: This region's id. Id is globally unique across all regions * @mode: Endpoint decoder allocation / access mode * @type: Endpoint decoder target type + * @cxl_nvb: nvdimm bridge for coordinating @cxlr_pmem setup / shutdown + * @cxlr_pmem: (for pmem regions) cached copy of the nvdimm bridge + * @flags: Region state flags * @params: active + config params for the region */ struct cxl_region { @@ -412,38 +430,26 @@ struct cxl_region { int id; enum cxl_decoder_mode mode; enum cxl_decoder_type type; + struct cxl_nvdimm_bridge *cxl_nvb; + struct cxl_pmem_region *cxlr_pmem; + unsigned long flags; struct cxl_region_params params; }; -/** - * enum cxl_nvdimm_brige_state - state machine for managing bus rescans - * @CXL_NVB_NEW: Set at bridge create and after cxl_pmem_wq is destroyed - * @CXL_NVB_DEAD: Set at brige unregistration to preclude async probing - * @CXL_NVB_ONLINE: Target state after successful ->probe() - * @CXL_NVB_OFFLINE: Target state after ->remove() or failed ->probe() - */ -enum cxl_nvdimm_brige_state { - CXL_NVB_NEW, - CXL_NVB_DEAD, - CXL_NVB_ONLINE, - CXL_NVB_OFFLINE, -}; - struct cxl_nvdimm_bridge { int id; struct device dev; struct cxl_port *port; struct nvdimm_bus *nvdimm_bus; struct nvdimm_bus_descriptor nd_desc; - struct work_struct state_work; - enum cxl_nvdimm_brige_state state; }; +#define CXL_DEV_ID_LEN 19 + struct cxl_nvdimm { struct device dev; struct cxl_memdev *cxlmd; - struct cxl_nvdimm_bridge *bridge; - struct xarray pmem_regions; + u8 dev_id[CXL_DEV_ID_LEN]; /* for nvdimm, string of 'serial' */ }; struct cxl_pmem_region_mapping { @@ -458,7 +464,6 @@ struct cxl_pmem_region { struct device dev; struct cxl_region *cxlr; struct nd_region *nd_region; - struct cxl_nvdimm_bridge *bridge; struct range hpa_range; int nr_mappings; struct cxl_pmem_region_mapping mapping[]; @@ -520,12 +525,16 @@ cxl_find_dport_by_dev(struct cxl_port *port, const struct device *dport_dev) * @dport: PCI bridge or firmware device representing the downstream link * @port_id: unique hardware identifier for dport in decoder target list * @component_reg_phys: downstream port component registers + * @rcrb: base address for the Root Complex Register Block + * @rch: Indicate whether this dport was enumerated in RCH or VH mode * @port: reference to cxl_port that contains this downstream port */ struct cxl_dport { struct device *dport; int port_id; resource_size_t component_reg_phys; + resource_size_t rcrb; + bool rch; struct cxl_port *port; }; @@ -582,11 +591,10 @@ struct pci_bus *cxl_port_to_pci_bus(struct cxl_port *port); struct cxl_port *devm_cxl_add_port(struct device *host, struct device *uport, resource_size_t component_reg_phys, struct cxl_dport *parent_dport); -int devm_cxl_add_endpoint(struct cxl_memdev *cxlmd, - struct cxl_dport *parent_dport); struct cxl_port *find_cxl_root(struct device *dev); int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd); -int cxl_bus_rescan(void); +void cxl_bus_rescan(void); +void cxl_bus_drain(void); struct cxl_port *cxl_mem_find_port(struct cxl_memdev *cxlmd, struct cxl_dport **dport); bool schedule_cxl_memdev_detach(struct cxl_memdev *cxlmd); @@ -594,6 +602,10 @@ bool schedule_cxl_memdev_detach(struct cxl_memdev *cxlmd); struct cxl_dport *devm_cxl_add_dport(struct cxl_port *port, struct device *dport, int port_id, resource_size_t component_reg_phys); +struct cxl_dport *devm_cxl_add_rch_dport(struct cxl_port *port, + struct device *dport_dev, int port_id, + resource_size_t component_reg_phys, + resource_size_t rcrb); struct cxl_decoder *to_cxl_decoder(struct device *dev); struct cxl_root_decoder *to_cxl_root_decoder(struct device *dev); @@ -657,7 +669,7 @@ struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host, struct cxl_nvdimm *to_cxl_nvdimm(struct device *dev); bool is_cxl_nvdimm(struct device *dev); bool is_cxl_nvdimm_bridge(struct device *dev); -int devm_cxl_add_nvdimm(struct device *host, struct cxl_memdev *cxlmd); +int devm_cxl_add_nvdimm(struct cxl_memdev *cxlmd); struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct device *dev); #ifdef CONFIG_CXL_REGION diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index b3117fd67f42..785c6c12515d 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -35,6 +35,8 @@ * @cdev: char dev core object for ioctl operations * @cxlds: The device state backing this device * @detach_work: active memdev lost a port in its ancestry + * @cxl_nvb: coordinate removal of @cxl_nvd if present + * @cxl_nvd: optional bridge to an nvdimm if the device supports pmem * @id: id number of this memdev instance. */ struct cxl_memdev { @@ -42,6 +44,8 @@ struct cxl_memdev { struct cdev cdev; struct cxl_dev_state *cxlds; struct work_struct detach_work; + struct cxl_nvdimm_bridge *cxl_nvb; + struct cxl_nvdimm *cxl_nvd; int id; }; @@ -76,6 +80,15 @@ static inline bool is_cxl_endpoint(struct cxl_port *port) struct cxl_memdev *devm_cxl_add_memdev(struct cxl_dev_state *cxlds); +static inline struct cxl_ep *cxl_ep_load(struct cxl_port *port, + struct cxl_memdev *cxlmd) +{ + if (!port) + return NULL; + + return xa_load(&port->endpoints, (unsigned long)&cxlmd->dev); +} + /** * struct cxl_mbox_cmd - A command to be submitted to hardware. * @opcode: (input) The command set and command submitted to hardware. @@ -189,6 +202,7 @@ struct cxl_endpoint_dvsec_info { * @cxlmd: The device representing the CXL.mem capabilities of @dev * @regs: Parsed register blocks * @cxl_dvsec: Offset to the PCIe device DVSEC + * @rcd: operating in RCD mode (CXL 3.0 9.11.8 CXL Devices Attached to an RCH) * @payload_size: Size of space for payload * (CXL 2.0 8.2.8.4.3 Mailbox Capabilities Register) * @lsa_size: Size of Label Storage Area @@ -224,6 +238,7 @@ struct cxl_dev_state { struct cxl_regs regs; int cxl_dvsec; + bool rcd; size_t payload_size; size_t lsa_size; struct mutex mbox_mutex; /* Protects device mailbox and firmware */ @@ -275,6 +290,12 @@ enum cxl_opcode { CXL_MBOX_OP_GET_SCAN_MEDIA_CAPS = 0x4303, CXL_MBOX_OP_SCAN_MEDIA = 0x4304, CXL_MBOX_OP_GET_SCAN_MEDIA = 0x4305, + CXL_MBOX_OP_GET_SECURITY_STATE = 0x4500, + CXL_MBOX_OP_SET_PASSPHRASE = 0x4501, + CXL_MBOX_OP_DISABLE_PASSPHRASE = 0x4502, + CXL_MBOX_OP_UNLOCK = 0x4503, + CXL_MBOX_OP_FREEZE_SECURITY = 0x4504, + CXL_MBOX_OP_PASSPHRASE_SECURE_ERASE = 0x4505, CXL_MBOX_OP_MAX = 0x10000 }; @@ -374,6 +395,41 @@ struct cxl_mem_command { #define CXL_CMD_FLAG_FORCE_ENABLE BIT(0) }; +#define CXL_PMEM_SEC_STATE_USER_PASS_SET 0x01 +#define CXL_PMEM_SEC_STATE_MASTER_PASS_SET 0x02 +#define CXL_PMEM_SEC_STATE_LOCKED 0x04 +#define CXL_PMEM_SEC_STATE_FROZEN 0x08 +#define CXL_PMEM_SEC_STATE_USER_PLIMIT 0x10 +#define CXL_PMEM_SEC_STATE_MASTER_PLIMIT 0x20 + +/* set passphrase input payload */ +struct cxl_set_pass { + u8 type; + u8 reserved[31]; + /* CXL field using NVDIMM define, same length */ + u8 old_pass[NVDIMM_PASSPHRASE_LEN]; + u8 new_pass[NVDIMM_PASSPHRASE_LEN]; +} __packed; + +/* disable passphrase input payload */ +struct cxl_disable_pass { + u8 type; + u8 reserved[31]; + u8 pass[NVDIMM_PASSPHRASE_LEN]; +} __packed; + +/* passphrase secure erase payload */ +struct cxl_pass_erase { + u8 type; + u8 reserved[31]; + u8 pass[NVDIMM_PASSPHRASE_LEN]; +} __packed; + +enum { + CXL_PMEM_SEC_PASS_MASTER = 0, + CXL_PMEM_SEC_PASS_USER, +}; + int cxl_mbox_send_cmd(struct cxl_dev_state *cxlds, u16 opcode, void *in, size_t in_size, void *out, size_t out_size); int cxl_dev_state_identify(struct cxl_dev_state *cxlds); diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c index 64ccf053d32c..39c4b54f0715 100644 --- a/drivers/cxl/mem.c +++ b/drivers/cxl/mem.c @@ -45,9 +45,60 @@ static int cxl_mem_dpa_show(struct seq_file *file, void *data) return 0; } +static int devm_cxl_add_endpoint(struct device *host, struct cxl_memdev *cxlmd, + struct cxl_dport *parent_dport) +{ + struct cxl_port *parent_port = parent_dport->port; + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_port *endpoint, *iter, *down; + resource_size_t component_reg_phys; + int rc; + + /* + * Now that the path to the root is established record all the + * intervening ports in the chain. + */ + for (iter = parent_port, down = NULL; !is_cxl_root(iter); + down = iter, iter = to_cxl_port(iter->dev.parent)) { + struct cxl_ep *ep; + + ep = cxl_ep_load(iter, cxlmd); + ep->next = down; + } + + /* + * The component registers for an RCD might come from the + * host-bridge RCRB if they are not already mapped via the + * typical register locator mechanism. + */ + if (parent_dport->rch && cxlds->component_reg_phys == CXL_RESOURCE_NONE) + component_reg_phys = cxl_rcrb_to_component( + &cxlmd->dev, parent_dport->rcrb, CXL_RCRB_UPSTREAM); + else + component_reg_phys = cxlds->component_reg_phys; + endpoint = devm_cxl_add_port(host, &cxlmd->dev, component_reg_phys, + parent_dport); + if (IS_ERR(endpoint)) + return PTR_ERR(endpoint); + + rc = cxl_endpoint_autoremove(cxlmd, endpoint); + if (rc) + return rc; + + if (!endpoint->dev.driver) { + dev_err(&cxlmd->dev, "%s failed probe\n", + dev_name(&endpoint->dev)); + return -ENXIO; + } + + return 0; +} + static int cxl_mem_probe(struct device *dev) { struct cxl_memdev *cxlmd = to_cxl_memdev(dev); + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct device *endpoint_parent; struct cxl_port *parent_port; struct cxl_dport *dport; struct dentry *dentry; @@ -80,21 +131,34 @@ static int cxl_mem_probe(struct device *dev) return -ENXIO; } - device_lock(&parent_port->dev); - if (!parent_port->dev.driver) { + if (dport->rch) + endpoint_parent = parent_port->uport; + else + endpoint_parent = &parent_port->dev; + + device_lock(endpoint_parent); + if (!endpoint_parent->driver) { dev_err(dev, "CXL port topology %s not enabled\n", - dev_name(&parent_port->dev)); + dev_name(endpoint_parent)); rc = -ENXIO; goto unlock; } - rc = devm_cxl_add_endpoint(cxlmd, dport); + rc = devm_cxl_add_endpoint(endpoint_parent, cxlmd, dport); unlock: - device_unlock(&parent_port->dev); + device_unlock(endpoint_parent); put_device(&parent_port->dev); if (rc) return rc; + if (resource_size(&cxlds->pmem_res) && IS_ENABLED(CONFIG_CXL_PMEM)) { + rc = devm_cxl_add_nvdimm(cxlmd); + if (rc == -ENODEV) + dev_info(dev, "PMEM disabled by platform\n"); + else + return rc; + } + /* * The kernel may be operating out of CXL memory on this device, * there is no spec defined way to determine whether this device diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 36db681f3705..6cec9fa9326c 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -390,6 +390,11 @@ static void devm_cxl_pci_create_doe(struct cxl_dev_state *cxlds) continue; } + if (!pci_request_config_region_exclusive(pdev, off, + PCI_DOE_CAP_SIZEOF, + dev_name(dev))) + pci_err(pdev, "Failed to exclude DOE registers\n"); + if (xa_insert(&cxlds->doe_mbs, off, doe_mb, GFP_KERNEL)) { dev_err(dev, "xa_insert failed to insert MB @ %x\n", off); @@ -400,6 +405,15 @@ static void devm_cxl_pci_create_doe(struct cxl_dev_state *cxlds) } } +/* + * Assume that any RCIEP that emits the CXL memory expander class code + * is an RCD + */ +static bool is_cxl_restricted(struct pci_dev *pdev) +{ + return pci_pcie_type(pdev) == PCI_EXP_TYPE_RC_END; +} + static void disable_aer(void *pdev) { pci_disable_pcie_error_reporting(pdev); @@ -428,6 +442,7 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) return PTR_ERR(cxlds); pci_set_drvdata(pdev, cxlds); + cxlds->rcd = is_cxl_restricted(pdev); cxlds->serial = pci_get_dsn(pdev); cxlds->cxl_dvsec = pci_find_dvsec_capability( pdev, PCI_DVSEC_VENDOR_ID_CXL, CXL_DVSEC_PCIE_DEVICE); @@ -489,9 +504,6 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) } pci_save_state(pdev); - if (resource_size(&cxlds->pmem_res) && IS_ENABLED(CONFIG_CXL_PMEM)) - rc = devm_cxl_add_nvdimm(&pdev->dev, cxlmd); - return rc; } diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c index 4c627d67281a..2fc8070b6a17 100644 --- a/drivers/cxl/pmem.c +++ b/drivers/cxl/pmem.c @@ -11,12 +11,7 @@ #include "cxlmem.h" #include "cxl.h" -/* - * Ordered workqueue for cxl nvdimm device arrival and departure - * to coordinate bus rescans when a bridge arrives and trigger remove - * operations when the bridge is removed. - */ -static struct workqueue_struct *cxl_pmem_wq; +extern const struct nvdimm_security_ops *cxl_security_ops; static __read_mostly DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX); @@ -27,78 +22,81 @@ static void clear_exclusive(void *cxlds) static void unregister_nvdimm(void *nvdimm) { - struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); - struct cxl_nvdimm_bridge *cxl_nvb = cxl_nvd->bridge; - struct cxl_pmem_region *cxlr_pmem; - unsigned long index; + nvdimm_delete(nvdimm); +} - device_lock(&cxl_nvb->dev); - dev_set_drvdata(&cxl_nvd->dev, NULL); - xa_for_each(&cxl_nvd->pmem_regions, index, cxlr_pmem) { - get_device(&cxlr_pmem->dev); - device_unlock(&cxl_nvb->dev); +static ssize_t provider_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct nvdimm *nvdimm = to_nvdimm(dev); + struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); - device_release_driver(&cxlr_pmem->dev); - put_device(&cxlr_pmem->dev); + return sysfs_emit(buf, "%s\n", dev_name(&cxl_nvd->dev)); +} +static DEVICE_ATTR_RO(provider); - device_lock(&cxl_nvb->dev); - } - device_unlock(&cxl_nvb->dev); +static ssize_t id_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct nvdimm *nvdimm = to_nvdimm(dev); + struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); + struct cxl_dev_state *cxlds = cxl_nvd->cxlmd->cxlds; - nvdimm_delete(nvdimm); - cxl_nvd->bridge = NULL; + return sysfs_emit(buf, "%lld\n", cxlds->serial); } +static DEVICE_ATTR_RO(id); + +static struct attribute *cxl_dimm_attributes[] = { + &dev_attr_id.attr, + &dev_attr_provider.attr, + NULL +}; + +static const struct attribute_group cxl_dimm_attribute_group = { + .name = "cxl", + .attrs = cxl_dimm_attributes, +}; + +static const struct attribute_group *cxl_dimm_attribute_groups[] = { + &cxl_dimm_attribute_group, + NULL +}; static int cxl_nvdimm_probe(struct device *dev) { struct cxl_nvdimm *cxl_nvd = to_cxl_nvdimm(dev); struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_nvdimm_bridge *cxl_nvb = cxlmd->cxl_nvb; unsigned long flags = 0, cmd_mask = 0; struct cxl_dev_state *cxlds = cxlmd->cxlds; - struct cxl_nvdimm_bridge *cxl_nvb; struct nvdimm *nvdimm; int rc; - cxl_nvb = cxl_find_nvdimm_bridge(dev); - if (!cxl_nvb) - return -ENXIO; - - device_lock(&cxl_nvb->dev); - if (!cxl_nvb->nvdimm_bus) { - rc = -ENXIO; - goto out; - } - set_exclusive_cxl_commands(cxlds, exclusive_cmds); rc = devm_add_action_or_reset(dev, clear_exclusive, cxlds); if (rc) - goto out; + return rc; set_bit(NDD_LABELING, &flags); set_bit(ND_CMD_GET_CONFIG_SIZE, &cmd_mask); set_bit(ND_CMD_GET_CONFIG_DATA, &cmd_mask); set_bit(ND_CMD_SET_CONFIG_DATA, &cmd_mask); - nvdimm = nvdimm_create(cxl_nvb->nvdimm_bus, cxl_nvd, NULL, flags, - cmd_mask, 0, NULL); - if (!nvdimm) { - rc = -ENOMEM; - goto out; - } + nvdimm = __nvdimm_create(cxl_nvb->nvdimm_bus, cxl_nvd, + cxl_dimm_attribute_groups, flags, + cmd_mask, 0, NULL, cxl_nvd->dev_id, + cxl_security_ops, NULL); + if (!nvdimm) + return -ENOMEM; dev_set_drvdata(dev, nvdimm); - cxl_nvd->bridge = cxl_nvb; - rc = devm_add_action_or_reset(dev, unregister_nvdimm, nvdimm); -out: - device_unlock(&cxl_nvb->dev); - put_device(&cxl_nvb->dev); - - return rc; + return devm_add_action_or_reset(dev, unregister_nvdimm, nvdimm); } static struct cxl_driver cxl_nvdimm_driver = { .name = "cxl_nvdimm", .probe = cxl_nvdimm_probe, .id = CXL_DEVICE_NVDIMM, + .drv = { + .suppress_bind_attrs = true, + }, }; static int cxl_pmem_get_config_size(struct cxl_dev_state *cxlds, @@ -216,204 +214,48 @@ static int cxl_pmem_ctl(struct nvdimm_bus_descriptor *nd_desc, return cxl_pmem_nvdimm_ctl(nvdimm, cmd, buf, buf_len); } -static bool online_nvdimm_bus(struct cxl_nvdimm_bridge *cxl_nvb) +static void unregister_nvdimm_bus(void *_cxl_nvb) { - if (cxl_nvb->nvdimm_bus) - return true; - cxl_nvb->nvdimm_bus = - nvdimm_bus_register(&cxl_nvb->dev, &cxl_nvb->nd_desc); - return cxl_nvb->nvdimm_bus != NULL; -} - -static int cxl_nvdimm_release_driver(struct device *dev, void *cxl_nvb) -{ - struct cxl_nvdimm *cxl_nvd; - - if (!is_cxl_nvdimm(dev)) - return 0; + struct cxl_nvdimm_bridge *cxl_nvb = _cxl_nvb; + struct nvdimm_bus *nvdimm_bus = cxl_nvb->nvdimm_bus; - cxl_nvd = to_cxl_nvdimm(dev); - if (cxl_nvd->bridge != cxl_nvb) - return 0; - - device_release_driver(dev); - return 0; -} - -static int cxl_pmem_region_release_driver(struct device *dev, void *cxl_nvb) -{ - struct cxl_pmem_region *cxlr_pmem; - - if (!is_cxl_pmem_region(dev)) - return 0; - - cxlr_pmem = to_cxl_pmem_region(dev); - if (cxlr_pmem->bridge != cxl_nvb) - return 0; - - device_release_driver(dev); - return 0; -} - -static void offline_nvdimm_bus(struct cxl_nvdimm_bridge *cxl_nvb, - struct nvdimm_bus *nvdimm_bus) -{ - if (!nvdimm_bus) - return; - - /* - * Set the state of cxl_nvdimm devices to unbound / idle before - * nvdimm_bus_unregister() rips the nvdimm objects out from - * underneath them. - */ - bus_for_each_dev(&cxl_bus_type, NULL, cxl_nvb, - cxl_pmem_region_release_driver); - bus_for_each_dev(&cxl_bus_type, NULL, cxl_nvb, - cxl_nvdimm_release_driver); + cxl_nvb->nvdimm_bus = NULL; nvdimm_bus_unregister(nvdimm_bus); } -static void cxl_nvb_update_state(struct work_struct *work) -{ - struct cxl_nvdimm_bridge *cxl_nvb = - container_of(work, typeof(*cxl_nvb), state_work); - struct nvdimm_bus *victim_bus = NULL; - bool release = false, rescan = false; - - device_lock(&cxl_nvb->dev); - switch (cxl_nvb->state) { - case CXL_NVB_ONLINE: - if (!online_nvdimm_bus(cxl_nvb)) { - dev_err(&cxl_nvb->dev, - "failed to establish nvdimm bus\n"); - release = true; - } else - rescan = true; - break; - case CXL_NVB_OFFLINE: - case CXL_NVB_DEAD: - victim_bus = cxl_nvb->nvdimm_bus; - cxl_nvb->nvdimm_bus = NULL; - break; - default: - break; - } - device_unlock(&cxl_nvb->dev); - - if (release) - device_release_driver(&cxl_nvb->dev); - if (rescan) { - int rc = bus_rescan_devices(&cxl_bus_type); - - dev_dbg(&cxl_nvb->dev, "rescan: %d\n", rc); - } - offline_nvdimm_bus(cxl_nvb, victim_bus); - - put_device(&cxl_nvb->dev); -} - -static void cxl_nvdimm_bridge_state_work(struct cxl_nvdimm_bridge *cxl_nvb) -{ - /* - * Take a reference that the workqueue will drop if new work - * gets queued. - */ - get_device(&cxl_nvb->dev); - if (!queue_work(cxl_pmem_wq, &cxl_nvb->state_work)) - put_device(&cxl_nvb->dev); -} - -static void cxl_nvdimm_bridge_remove(struct device *dev) -{ - struct cxl_nvdimm_bridge *cxl_nvb = to_cxl_nvdimm_bridge(dev); - - if (cxl_nvb->state == CXL_NVB_ONLINE) - cxl_nvb->state = CXL_NVB_OFFLINE; - cxl_nvdimm_bridge_state_work(cxl_nvb); -} - static int cxl_nvdimm_bridge_probe(struct device *dev) { struct cxl_nvdimm_bridge *cxl_nvb = to_cxl_nvdimm_bridge(dev); - if (cxl_nvb->state == CXL_NVB_DEAD) - return -ENXIO; - - if (cxl_nvb->state == CXL_NVB_NEW) { - cxl_nvb->nd_desc = (struct nvdimm_bus_descriptor) { - .provider_name = "CXL", - .module = THIS_MODULE, - .ndctl = cxl_pmem_ctl, - }; + cxl_nvb->nd_desc = (struct nvdimm_bus_descriptor) { + .provider_name = "CXL", + .module = THIS_MODULE, + .ndctl = cxl_pmem_ctl, + }; - INIT_WORK(&cxl_nvb->state_work, cxl_nvb_update_state); - } + cxl_nvb->nvdimm_bus = + nvdimm_bus_register(&cxl_nvb->dev, &cxl_nvb->nd_desc); - cxl_nvb->state = CXL_NVB_ONLINE; - cxl_nvdimm_bridge_state_work(cxl_nvb); + if (!cxl_nvb->nvdimm_bus) + return -ENOMEM; - return 0; + return devm_add_action_or_reset(dev, unregister_nvdimm_bus, cxl_nvb); } static struct cxl_driver cxl_nvdimm_bridge_driver = { .name = "cxl_nvdimm_bridge", .probe = cxl_nvdimm_bridge_probe, - .remove = cxl_nvdimm_bridge_remove, .id = CXL_DEVICE_NVDIMM_BRIDGE, + .drv = { + .suppress_bind_attrs = true, + }, }; -static int match_cxl_nvdimm(struct device *dev, void *data) -{ - return is_cxl_nvdimm(dev); -} - static void unregister_nvdimm_region(void *nd_region) { nvdimm_region_delete(nd_region); } -static int cxl_nvdimm_add_region(struct cxl_nvdimm *cxl_nvd, - struct cxl_pmem_region *cxlr_pmem) -{ - int rc; - - rc = xa_insert(&cxl_nvd->pmem_regions, (unsigned long)cxlr_pmem, - cxlr_pmem, GFP_KERNEL); - if (rc) - return rc; - - get_device(&cxlr_pmem->dev); - return 0; -} - -static void cxl_nvdimm_del_region(struct cxl_nvdimm *cxl_nvd, - struct cxl_pmem_region *cxlr_pmem) -{ - /* - * It is possible this is called without a corresponding - * cxl_nvdimm_add_region for @cxlr_pmem - */ - cxlr_pmem = xa_erase(&cxl_nvd->pmem_regions, (unsigned long)cxlr_pmem); - if (cxlr_pmem) - put_device(&cxlr_pmem->dev); -} - -static void release_mappings(void *data) -{ - int i; - struct cxl_pmem_region *cxlr_pmem = data; - struct cxl_nvdimm_bridge *cxl_nvb = cxlr_pmem->bridge; - - device_lock(&cxl_nvb->dev); - for (i = 0; i < cxlr_pmem->nr_mappings; i++) { - struct cxl_pmem_region_mapping *m = &cxlr_pmem->mapping[i]; - struct cxl_nvdimm *cxl_nvd = m->cxl_nvd; - - cxl_nvdimm_del_region(cxl_nvd, cxlr_pmem); - } - device_unlock(&cxl_nvb->dev); -} - static void cxlr_pmem_remove_resource(void *res) { remove_resource(res); @@ -429,8 +271,8 @@ static int cxl_pmem_region_probe(struct device *dev) struct nd_mapping_desc mappings[CXL_DECODER_MAX_INTERLEAVE]; struct cxl_pmem_region *cxlr_pmem = to_cxl_pmem_region(dev); struct cxl_region *cxlr = cxlr_pmem->cxlr; + struct cxl_nvdimm_bridge *cxl_nvb = cxlr->cxl_nvb; struct cxl_pmem_region_info *info = NULL; - struct cxl_nvdimm_bridge *cxl_nvb; struct nd_interleave_set *nd_set; struct nd_region_desc ndr_desc; struct cxl_nvdimm *cxl_nvd; @@ -438,28 +280,12 @@ static int cxl_pmem_region_probe(struct device *dev) struct resource *res; int rc, i = 0; - cxl_nvb = cxl_find_nvdimm_bridge(&cxlr_pmem->mapping[0].cxlmd->dev); - if (!cxl_nvb) { - dev_dbg(dev, "bridge not found\n"); - return -ENXIO; - } - cxlr_pmem->bridge = cxl_nvb; - - device_lock(&cxl_nvb->dev); - if (!cxl_nvb->nvdimm_bus) { - dev_dbg(dev, "nvdimm bus not found\n"); - rc = -ENXIO; - goto out_nvb; - } - memset(&mappings, 0, sizeof(mappings)); memset(&ndr_desc, 0, sizeof(ndr_desc)); res = devm_kzalloc(dev, sizeof(*res), GFP_KERNEL); - if (!res) { - rc = -ENOMEM; - goto out_nvb; - } + if (!res) + return -ENOMEM; res->name = "Persistent Memory"; res->start = cxlr_pmem->hpa_range.start; @@ -469,11 +295,11 @@ static int cxl_pmem_region_probe(struct device *dev) rc = insert_resource(&iomem_resource, res); if (rc) - goto out_nvb; + return rc; rc = devm_add_action_or_reset(dev, cxlr_pmem_remove_resource, res); if (rc) - goto out_nvb; + return rc; ndr_desc.res = res; ndr_desc.provider_data = cxlr_pmem; @@ -487,43 +313,23 @@ static int cxl_pmem_region_probe(struct device *dev) } nd_set = devm_kzalloc(dev, sizeof(*nd_set), GFP_KERNEL); - if (!nd_set) { - rc = -ENOMEM; - goto out_nvb; - } + if (!nd_set) + return -ENOMEM; ndr_desc.memregion = cxlr->id; set_bit(ND_REGION_CXL, &ndr_desc.flags); set_bit(ND_REGION_PERSIST_MEMCTRL, &ndr_desc.flags); info = kmalloc_array(cxlr_pmem->nr_mappings, sizeof(*info), GFP_KERNEL); - if (!info) { - rc = -ENOMEM; - goto out_nvb; - } - - rc = devm_add_action_or_reset(dev, release_mappings, cxlr_pmem); - if (rc) - goto out_nvd; + if (!info) + return -ENOMEM; for (i = 0; i < cxlr_pmem->nr_mappings; i++) { struct cxl_pmem_region_mapping *m = &cxlr_pmem->mapping[i]; struct cxl_memdev *cxlmd = m->cxlmd; struct cxl_dev_state *cxlds = cxlmd->cxlds; - struct device *d; - - d = device_find_child(&cxlmd->dev, NULL, match_cxl_nvdimm); - if (!d) { - dev_dbg(dev, "[%d]: %s: no cxl_nvdimm found\n", i, - dev_name(&cxlmd->dev)); - rc = -ENODEV; - goto out_nvd; - } - /* safe to drop ref now with bridge lock held */ - put_device(d); - - cxl_nvd = to_cxl_nvdimm(d); + cxl_nvd = cxlmd->cxl_nvd; nvdimm = dev_get_drvdata(&cxl_nvd->dev); if (!nvdimm) { dev_dbg(dev, "[%d]: %s: no nvdimm found\n", i, @@ -532,14 +338,6 @@ static int cxl_pmem_region_probe(struct device *dev) goto out_nvd; } - /* - * Pin the region per nvdimm device as those may be released - * out-of-order with respect to the region, and a single nvdimm - * maybe associated with multiple regions - */ - rc = cxl_nvdimm_add_region(cxl_nvd, cxlr_pmem); - if (rc) - goto out_nvd; m->cxl_nvd = cxl_nvd; mappings[i] = (struct nd_mapping_desc) { .nvdimm = nvdimm, @@ -572,9 +370,6 @@ static int cxl_pmem_region_probe(struct device *dev) cxlr_pmem->nd_region); out_nvd: kfree(info); -out_nvb: - device_unlock(&cxl_nvb->dev); - put_device(&cxl_nvb->dev); return rc; } @@ -583,33 +378,11 @@ static struct cxl_driver cxl_pmem_region_driver = { .name = "cxl_pmem_region", .probe = cxl_pmem_region_probe, .id = CXL_DEVICE_PMEM_REGION, + .drv = { + .suppress_bind_attrs = true, + }, }; -/* - * Return all bridges to the CXL_NVB_NEW state to invalidate any - * ->state_work referring to the now destroyed cxl_pmem_wq. - */ -static int cxl_nvdimm_bridge_reset(struct device *dev, void *data) -{ - struct cxl_nvdimm_bridge *cxl_nvb; - - if (!is_cxl_nvdimm_bridge(dev)) - return 0; - - cxl_nvb = to_cxl_nvdimm_bridge(dev); - device_lock(dev); - cxl_nvb->state = CXL_NVB_NEW; - device_unlock(dev); - - return 0; -} - -static void destroy_cxl_pmem_wq(void) -{ - destroy_workqueue(cxl_pmem_wq); - bus_for_each_dev(&cxl_bus_type, NULL, NULL, cxl_nvdimm_bridge_reset); -} - static __init int cxl_pmem_init(void) { int rc; @@ -617,13 +390,9 @@ static __init int cxl_pmem_init(void) set_bit(CXL_MEM_COMMAND_ID_SET_SHUTDOWN_STATE, exclusive_cmds); set_bit(CXL_MEM_COMMAND_ID_SET_LSA, exclusive_cmds); - cxl_pmem_wq = alloc_ordered_workqueue("cxl_pmem", 0); - if (!cxl_pmem_wq) - return -ENXIO; - rc = cxl_driver_register(&cxl_nvdimm_bridge_driver); if (rc) - goto err_bridge; + return rc; rc = cxl_driver_register(&cxl_nvdimm_driver); if (rc) @@ -639,8 +408,6 @@ err_region: cxl_driver_unregister(&cxl_nvdimm_driver); err_nvdimm: cxl_driver_unregister(&cxl_nvdimm_bridge_driver); -err_bridge: - destroy_cxl_pmem_wq(); return rc; } @@ -649,7 +416,6 @@ static __exit void cxl_pmem_exit(void) cxl_driver_unregister(&cxl_pmem_region_driver); cxl_driver_unregister(&cxl_nvdimm_driver); cxl_driver_unregister(&cxl_nvdimm_bridge_driver); - destroy_cxl_pmem_wq(); } MODULE_LICENSE("GPL v2"); diff --git a/drivers/cxl/security.c b/drivers/cxl/security.c new file mode 100644 index 000000000000..5484d4eecfd1 --- /dev/null +++ b/drivers/cxl/security.c @@ -0,0 +1,163 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2022 Intel Corporation. All rights reserved. */ +#include <linux/libnvdimm.h> +#include <asm/unaligned.h> +#include <linux/module.h> +#include <linux/async.h> +#include <linux/slab.h> +#include <linux/memregion.h> +#include "cxlmem.h" +#include "cxl.h" + +static unsigned long cxl_pmem_get_security_flags(struct nvdimm *nvdimm, + enum nvdimm_passphrase_type ptype) +{ + struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_dev_state *cxlds = cxlmd->cxlds; + unsigned long security_flags = 0; + u32 sec_out; + int rc; + + rc = cxl_mbox_send_cmd(cxlds, CXL_MBOX_OP_GET_SECURITY_STATE, NULL, 0, + &sec_out, sizeof(sec_out)); + if (rc < 0) + return 0; + + if (ptype == NVDIMM_MASTER) { + if (sec_out & CXL_PMEM_SEC_STATE_MASTER_PASS_SET) + set_bit(NVDIMM_SECURITY_UNLOCKED, &security_flags); + else + set_bit(NVDIMM_SECURITY_DISABLED, &security_flags); + if (sec_out & CXL_PMEM_SEC_STATE_MASTER_PLIMIT) + set_bit(NVDIMM_SECURITY_FROZEN, &security_flags); + return security_flags; + } + + if (sec_out & CXL_PMEM_SEC_STATE_USER_PASS_SET) { + if (sec_out & CXL_PMEM_SEC_STATE_FROZEN || + sec_out & CXL_PMEM_SEC_STATE_USER_PLIMIT) + set_bit(NVDIMM_SECURITY_FROZEN, &security_flags); + + if (sec_out & CXL_PMEM_SEC_STATE_LOCKED) + set_bit(NVDIMM_SECURITY_LOCKED, &security_flags); + else + set_bit(NVDIMM_SECURITY_UNLOCKED, &security_flags); + } else { + set_bit(NVDIMM_SECURITY_DISABLED, &security_flags); + } + + return security_flags; +} + +static int cxl_pmem_security_change_key(struct nvdimm *nvdimm, + const struct nvdimm_key_data *old_data, + const struct nvdimm_key_data *new_data, + enum nvdimm_passphrase_type ptype) +{ + struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_set_pass set_pass; + int rc; + + set_pass.type = ptype == NVDIMM_MASTER ? + CXL_PMEM_SEC_PASS_MASTER : CXL_PMEM_SEC_PASS_USER; + memcpy(set_pass.old_pass, old_data->data, NVDIMM_PASSPHRASE_LEN); + memcpy(set_pass.new_pass, new_data->data, NVDIMM_PASSPHRASE_LEN); + + rc = cxl_mbox_send_cmd(cxlds, CXL_MBOX_OP_SET_PASSPHRASE, + &set_pass, sizeof(set_pass), NULL, 0); + return rc; +} + +static int __cxl_pmem_security_disable(struct nvdimm *nvdimm, + const struct nvdimm_key_data *key_data, + enum nvdimm_passphrase_type ptype) +{ + struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_disable_pass dis_pass; + int rc; + + dis_pass.type = ptype == NVDIMM_MASTER ? + CXL_PMEM_SEC_PASS_MASTER : CXL_PMEM_SEC_PASS_USER; + memcpy(dis_pass.pass, key_data->data, NVDIMM_PASSPHRASE_LEN); + + rc = cxl_mbox_send_cmd(cxlds, CXL_MBOX_OP_DISABLE_PASSPHRASE, + &dis_pass, sizeof(dis_pass), NULL, 0); + return rc; +} + +static int cxl_pmem_security_disable(struct nvdimm *nvdimm, + const struct nvdimm_key_data *key_data) +{ + return __cxl_pmem_security_disable(nvdimm, key_data, NVDIMM_USER); +} + +static int cxl_pmem_security_disable_master(struct nvdimm *nvdimm, + const struct nvdimm_key_data *key_data) +{ + return __cxl_pmem_security_disable(nvdimm, key_data, NVDIMM_MASTER); +} + +static int cxl_pmem_security_freeze(struct nvdimm *nvdimm) +{ + struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_dev_state *cxlds = cxlmd->cxlds; + + return cxl_mbox_send_cmd(cxlds, CXL_MBOX_OP_FREEZE_SECURITY, NULL, 0, NULL, 0); +} + +static int cxl_pmem_security_unlock(struct nvdimm *nvdimm, + const struct nvdimm_key_data *key_data) +{ + struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_dev_state *cxlds = cxlmd->cxlds; + u8 pass[NVDIMM_PASSPHRASE_LEN]; + int rc; + + memcpy(pass, key_data->data, NVDIMM_PASSPHRASE_LEN); + rc = cxl_mbox_send_cmd(cxlds, CXL_MBOX_OP_UNLOCK, + pass, NVDIMM_PASSPHRASE_LEN, NULL, 0); + if (rc < 0) + return rc; + + return 0; +} + +static int cxl_pmem_security_passphrase_erase(struct nvdimm *nvdimm, + const struct nvdimm_key_data *key, + enum nvdimm_passphrase_type ptype) +{ + struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_pass_erase erase; + int rc; + + erase.type = ptype == NVDIMM_MASTER ? + CXL_PMEM_SEC_PASS_MASTER : CXL_PMEM_SEC_PASS_USER; + memcpy(erase.pass, key->data, NVDIMM_PASSPHRASE_LEN); + rc = cxl_mbox_send_cmd(cxlds, CXL_MBOX_OP_PASSPHRASE_SECURE_ERASE, + &erase, sizeof(erase), NULL, 0); + if (rc < 0) + return rc; + + return 0; +} + +static const struct nvdimm_security_ops __cxl_security_ops = { + .get_flags = cxl_pmem_get_security_flags, + .change_key = cxl_pmem_security_change_key, + .disable = cxl_pmem_security_disable, + .freeze = cxl_pmem_security_freeze, + .unlock = cxl_pmem_security_unlock, + .erase = cxl_pmem_security_passphrase_erase, + .disable_master = cxl_pmem_security_disable_master, +}; + +const struct nvdimm_security_ops *cxl_security_ops = &__cxl_security_ops; |