diff options
Diffstat (limited to 'drivers/cxl')
| -rw-r--r-- | drivers/cxl/core/core.h | 1 | ||||
| -rw-r--r-- | drivers/cxl/core/hdm.c | 19 | ||||
| -rw-r--r-- | drivers/cxl/core/mbox.c | 55 | ||||
| -rw-r--r-- | drivers/cxl/core/memdev.c | 157 | ||||
| -rw-r--r-- | drivers/cxl/core/port.c | 6 | ||||
| -rw-r--r-- | drivers/cxl/core/region.c | 256 | ||||
| -rw-r--r-- | drivers/cxl/cxlmem.h | 13 | ||||
| -rw-r--r-- | drivers/cxl/pci.c | 88 |
8 files changed, 330 insertions, 265 deletions
diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h index f470ef5c0a6a..86d7ba23235e 100644 --- a/drivers/cxl/core/core.h +++ b/drivers/cxl/core/core.h @@ -76,6 +76,7 @@ resource_size_t __rcrb_to_component(struct device *dev, u16 cxl_rcrb_to_aer(struct device *dev, resource_size_t rcrb); extern struct rw_semaphore cxl_dpa_rwsem; +extern struct rw_semaphore cxl_region_rwsem; int cxl_memdev_init(void); void cxl_memdev_exit(void); diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index 0a294e8c77a9..d3d338509d96 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -640,6 +640,25 @@ static int cxl_decoder_commit(struct cxl_decoder *cxld) 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; + } + } + down_read(&cxl_dpa_rwsem); /* common decoder settings */ ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(cxld->id)); diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 7e1c4d6f2e39..72ee522e747d 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -1125,20 +1125,7 @@ int cxl_dev_state_identify(struct cxl_memdev_state *mds) } EXPORT_SYMBOL_NS_GPL(cxl_dev_state_identify, CXL); -/** - * cxl_mem_sanitize() - Send a sanitization command to the device. - * @mds: The device data for the operation - * @cmd: The specific sanitization command opcode - * - * Return: 0 if the command was executed successfully, regardless of - * whether or not the actual security operation is done in the background, - * such as for the Sanitize case. - * Error return values can be the result of the mailbox command, -EINVAL - * when security requirements are not met or invalid contexts. - * - * See CXL 3.0 @8.2.9.8.5.1 Sanitize and @8.2.9.8.5.2 Secure Erase. - */ -int cxl_mem_sanitize(struct cxl_memdev_state *mds, u16 cmd) +static int __cxl_mem_sanitize(struct cxl_memdev_state *mds, u16 cmd) { int rc; u32 sec_out = 0; @@ -1183,7 +1170,45 @@ int cxl_mem_sanitize(struct cxl_memdev_state *mds, u16 cmd) return 0; } -EXPORT_SYMBOL_NS_GPL(cxl_mem_sanitize, CXL); + + +/** + * cxl_mem_sanitize() - Send a sanitization command to the device. + * @cxlmd: The device for the operation + * @cmd: The specific sanitization command opcode + * + * Return: 0 if the command was executed successfully, regardless of + * whether or not the actual security operation is done in the background, + * such as for the Sanitize case. + * Error return values can be the result of the mailbox command, -EINVAL + * when security requirements are not met or invalid contexts, or -EBUSY + * if the sanitize operation is already in flight. + * + * See CXL 3.0 @8.2.9.8.5.1 Sanitize and @8.2.9.8.5.2 Secure Erase. + */ +int cxl_mem_sanitize(struct cxl_memdev *cxlmd, u16 cmd) +{ + struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + struct cxl_port *endpoint; + int rc; + + /* synchronize with cxl_mem_probe() and decoder write operations */ + device_lock(&cxlmd->dev); + endpoint = cxlmd->endpoint; + down_read(&cxl_region_rwsem); + /* + * Require an endpoint to be safe otherwise the driver can not + * be sure that the device is unmapped. + */ + if (endpoint && endpoint->commit_end == -1) + rc = __cxl_mem_sanitize(mds, cmd); + else + rc = -EBUSY; + up_read(&cxl_region_rwsem); + device_unlock(&cxlmd->dev); + + return rc; +} static int add_dpa_res(struct device *dev, struct resource *parent, struct resource *res, resource_size_t start, diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index 14b547c07f54..fed9573cf355 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -125,13 +125,16 @@ static ssize_t security_state_show(struct device *dev, struct cxl_memdev *cxlmd = to_cxl_memdev(dev); struct cxl_dev_state *cxlds = cxlmd->cxlds; struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); - u64 reg = readq(cxlds->regs.mbox + CXLDEV_MBOX_BG_CMD_STATUS_OFFSET); - u32 pct = FIELD_GET(CXLDEV_MBOX_BG_CMD_COMMAND_PCT_MASK, reg); - u16 cmd = FIELD_GET(CXLDEV_MBOX_BG_CMD_COMMAND_OPCODE_MASK, reg); unsigned long state = mds->security.state; + int rc = 0; - if (cmd == CXL_MBOX_OP_SANITIZE && pct != 100) - return sysfs_emit(buf, "sanitize\n"); + /* sync with latest submission state */ + mutex_lock(&mds->mbox_mutex); + if (mds->security.sanitize_active) + rc = sysfs_emit(buf, "sanitize\n"); + mutex_unlock(&mds->mbox_mutex); + if (rc) + return rc; if (!(state & CXL_PMEM_SEC_STATE_USER_PASS_SET)) return sysfs_emit(buf, "disabled\n"); @@ -152,24 +155,17 @@ static ssize_t security_sanitize_store(struct device *dev, const char *buf, size_t len) { struct cxl_memdev *cxlmd = to_cxl_memdev(dev); - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); - struct cxl_port *port = cxlmd->endpoint; bool sanitize; ssize_t rc; if (kstrtobool(buf, &sanitize) || !sanitize) return -EINVAL; - if (!port || !is_cxl_endpoint(port)) - return -EINVAL; - - /* ensure no regions are mapped to this memdev */ - if (port->commit_end != -1) - return -EBUSY; - - rc = cxl_mem_sanitize(mds, CXL_MBOX_OP_SANITIZE); + rc = cxl_mem_sanitize(cxlmd, CXL_MBOX_OP_SANITIZE); + if (rc) + return rc; - return rc ? rc : len; + return len; } static struct device_attribute dev_attr_security_sanitize = __ATTR(sanitize, 0200, NULL, security_sanitize_store); @@ -179,24 +175,17 @@ static ssize_t security_erase_store(struct device *dev, const char *buf, size_t len) { struct cxl_memdev *cxlmd = to_cxl_memdev(dev); - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); - struct cxl_port *port = cxlmd->endpoint; ssize_t rc; bool erase; if (kstrtobool(buf, &erase) || !erase) return -EINVAL; - if (!port || !is_cxl_endpoint(port)) - return -EINVAL; - - /* ensure no regions are mapped to this memdev */ - if (port->commit_end != -1) - return -EBUSY; - - rc = cxl_mem_sanitize(mds, CXL_MBOX_OP_SECURE_ERASE); + rc = cxl_mem_sanitize(cxlmd, CXL_MBOX_OP_SECURE_ERASE); + if (rc) + return rc; - return rc ? rc : len; + return len; } static struct device_attribute dev_attr_security_erase = __ATTR(erase, 0200, NULL, security_erase_store); @@ -556,21 +545,11 @@ void clear_exclusive_cxl_commands(struct cxl_memdev_state *mds, } EXPORT_SYMBOL_NS_GPL(clear_exclusive_cxl_commands, CXL); -static void cxl_memdev_security_shutdown(struct device *dev) -{ - struct cxl_memdev *cxlmd = to_cxl_memdev(dev); - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); - - if (mds->security.poll) - cancel_delayed_work_sync(&mds->security.poll_dwork); -} - static void cxl_memdev_shutdown(struct device *dev) { struct cxl_memdev *cxlmd = to_cxl_memdev(dev); down_write(&cxl_memdev_rwsem); - cxl_memdev_security_shutdown(dev); cxlmd->cxlds = NULL; up_write(&cxl_memdev_rwsem); } @@ -580,8 +559,8 @@ static void cxl_memdev_unregister(void *_cxlmd) struct cxl_memdev *cxlmd = _cxlmd; struct device *dev = &cxlmd->dev; - cxl_memdev_shutdown(dev); cdev_device_del(&cxlmd->cdev, dev); + cxl_memdev_shutdown(dev); put_device(dev); } @@ -961,17 +940,16 @@ static const struct fw_upload_ops cxl_memdev_fw_ops = { .cleanup = cxl_fw_cleanup, }; -static void devm_cxl_remove_fw_upload(void *fwl) +static void cxl_remove_fw_upload(void *fwl) { firmware_upload_unregister(fwl); } -int cxl_memdev_setup_fw_upload(struct cxl_memdev_state *mds) +int devm_cxl_setup_fw_upload(struct device *host, struct cxl_memdev_state *mds) { struct cxl_dev_state *cxlds = &mds->cxlds; struct device *dev = &cxlds->cxlmd->dev; struct fw_upload *fwl; - int rc; if (!test_bit(CXL_MEM_COMMAND_ID_GET_FW_INFO, mds->enabled_cmds)) return 0; @@ -979,19 +957,10 @@ int cxl_memdev_setup_fw_upload(struct cxl_memdev_state *mds) fwl = firmware_upload_register(THIS_MODULE, dev, dev_name(dev), &cxl_memdev_fw_ops, mds); if (IS_ERR(fwl)) - return dev_err_probe(dev, PTR_ERR(fwl), - "Failed to register firmware loader\n"); - - rc = devm_add_action_or_reset(cxlds->dev, devm_cxl_remove_fw_upload, - fwl); - if (rc) - dev_err(dev, - "Failed to add firmware loader remove action: %d\n", - rc); - - return rc; + return PTR_ERR(fwl); + return devm_add_action_or_reset(host, cxl_remove_fw_upload, fwl); } -EXPORT_SYMBOL_NS_GPL(cxl_memdev_setup_fw_upload, CXL); +EXPORT_SYMBOL_NS_GPL(devm_cxl_setup_fw_upload, CXL); static const struct file_operations cxl_memdev_fops = { .owner = THIS_MODULE, @@ -1002,36 +971,8 @@ static const struct file_operations cxl_memdev_fops = { .llseek = noop_llseek, }; -static void put_sanitize(void *data) -{ - struct cxl_memdev_state *mds = data; - - sysfs_put(mds->security.sanitize_node); -} - -static int cxl_memdev_security_init(struct cxl_memdev *cxlmd) -{ - struct cxl_dev_state *cxlds = cxlmd->cxlds; - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); - struct device *dev = &cxlmd->dev; - struct kernfs_node *sec; - - sec = sysfs_get_dirent(dev->kobj.sd, "security"); - if (!sec) { - dev_err(dev, "sysfs_get_dirent 'security' failed\n"); - return -ENODEV; - } - mds->security.sanitize_node = sysfs_get_dirent(sec, "state"); - sysfs_put(sec); - if (!mds->security.sanitize_node) { - dev_err(dev, "sysfs_get_dirent 'state' failed\n"); - return -ENODEV; - } - - return devm_add_action_or_reset(cxlds->dev, put_sanitize, mds); - } - -struct cxl_memdev *devm_cxl_add_memdev(struct cxl_dev_state *cxlds) +struct cxl_memdev *devm_cxl_add_memdev(struct device *host, + struct cxl_dev_state *cxlds) { struct cxl_memdev *cxlmd; struct device *dev; @@ -1059,11 +1000,7 @@ struct cxl_memdev *devm_cxl_add_memdev(struct cxl_dev_state *cxlds) if (rc) goto err; - rc = cxl_memdev_security_init(cxlmd); - if (rc) - goto err; - - rc = devm_add_action_or_reset(cxlds->dev, cxl_memdev_unregister, cxlmd); + rc = devm_add_action_or_reset(host, cxl_memdev_unregister, cxlmd); if (rc) return ERR_PTR(rc); return cxlmd; @@ -1079,6 +1016,50 @@ err: } EXPORT_SYMBOL_NS_GPL(devm_cxl_add_memdev, CXL); +static void sanitize_teardown_notifier(void *data) +{ + struct cxl_memdev_state *mds = data; + struct kernfs_node *state; + + /* + * Prevent new irq triggered invocations of the workqueue and + * flush inflight invocations. + */ + mutex_lock(&mds->mbox_mutex); + state = mds->security.sanitize_node; + mds->security.sanitize_node = NULL; + mutex_unlock(&mds->mbox_mutex); + + cancel_delayed_work_sync(&mds->security.poll_dwork); + sysfs_put(state); +} + +int devm_cxl_sanitize_setup_notifier(struct device *host, + struct cxl_memdev *cxlmd) +{ + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); + struct kernfs_node *sec; + + if (!test_bit(CXL_SEC_ENABLED_SANITIZE, mds->security.enabled_cmds)) + return 0; + + /* + * Note, the expectation is that @cxlmd would have failed to be + * created if these sysfs_get_dirent calls fail. + */ + sec = sysfs_get_dirent(cxlmd->dev.kobj.sd, "security"); + if (!sec) + return -ENOENT; + mds->security.sanitize_node = sysfs_get_dirent(sec, "state"); + sysfs_put(sec); + if (!mds->security.sanitize_node) + return -ENOENT; + + return devm_add_action_or_reset(host, sanitize_teardown_notifier, mds); +} +EXPORT_SYMBOL_NS_GPL(devm_cxl_sanitize_setup_notifier, CXL); + __init int cxl_memdev_init(void) { dev_t devt; diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 002c820cfd83..e2f888224362 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -28,6 +28,12 @@ * instantiated by the core. */ +/* + * All changes to the interleave configuration occur with this lock held + * for write. + */ +DECLARE_RWSEM(cxl_region_rwsem); + static DEFINE_IDA(cxl_port_ida); static DEFINE_XARRAY(cxl_root_buses); diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index 6d63b8798c29..a1eac592c66a 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -28,12 +28,6 @@ * 3. Decoder targets */ -/* - * All changes to the interleave configuration occur with this lock held - * for write. - */ -static DECLARE_RWSEM(cxl_region_rwsem); - static struct cxl_region *to_cxl_region(struct device *dev); static ssize_t uuid_show(struct device *dev, struct device_attribute *attr, @@ -294,7 +288,7 @@ static ssize_t commit_store(struct device *dev, struct device_attribute *attr, */ rc = cxl_region_invalidate_memregion(cxlr); if (rc) - return rc; + goto out; if (commit) { rc = cxl_region_decode_commit(cxlr); @@ -1133,7 +1127,14 @@ static int cxl_port_setup_targets(struct cxl_port *port, } if (is_cxl_root(parent_port)) { - parent_ig = cxlrd->cxlsd.cxld.interleave_granularity; + /* + * Root decoder IG is always set to value in CFMWS which + * may be different than this region's IG. We can use the + * region's IG here since interleave_granularity_store() + * does not allow interleaved host-bridges with + * root IG != region IG. + */ + parent_ig = p->interleave_granularity; parent_iw = cxlrd->cxlsd.cxld.interleave_ways; /* * For purposes of address bit routing, use power-of-2 math for @@ -1480,6 +1481,14 @@ static int cxl_region_attach_auto(struct cxl_region *cxlr, return 0; } +static int cmp_interleave_pos(const void *a, const void *b) +{ + struct cxl_endpoint_decoder *cxled_a = *(typeof(cxled_a) *)a; + struct cxl_endpoint_decoder *cxled_b = *(typeof(cxled_b) *)b; + + return cxled_a->pos - cxled_b->pos; +} + static struct cxl_port *next_port(struct cxl_port *port) { if (!port->parent_dport) @@ -1487,119 +1496,127 @@ static struct cxl_port *next_port(struct cxl_port *port) return port->parent_dport->port; } -static int decoder_match_range(struct device *dev, void *data) +static int match_switch_decoder_by_range(struct device *dev, void *data) { - struct cxl_endpoint_decoder *cxled = data; struct cxl_switch_decoder *cxlsd; + struct range *r1, *r2 = data; if (!is_switch_decoder(dev)) return 0; cxlsd = to_cxl_switch_decoder(dev); - return range_contains(&cxlsd->cxld.hpa_range, &cxled->cxld.hpa_range); -} - -static void find_positions(const struct cxl_switch_decoder *cxlsd, - const struct cxl_port *iter_a, - const struct cxl_port *iter_b, int *a_pos, - int *b_pos) -{ - int i; + r1 = &cxlsd->cxld.hpa_range; - for (i = 0, *a_pos = -1, *b_pos = -1; i < cxlsd->nr_targets; i++) { - if (cxlsd->target[i] == iter_a->parent_dport) - *a_pos = i; - else if (cxlsd->target[i] == iter_b->parent_dport) - *b_pos = i; - if (*a_pos >= 0 && *b_pos >= 0) - break; - } + if (is_root_decoder(dev)) + return range_contains(r1, r2); + return (r1->start == r2->start && r1->end == r2->end); } -static int cmp_decode_pos(const void *a, const void *b) +static int find_pos_and_ways(struct cxl_port *port, struct range *range, + int *pos, int *ways) { - struct cxl_endpoint_decoder *cxled_a = *(typeof(cxled_a) *)a; - struct cxl_endpoint_decoder *cxled_b = *(typeof(cxled_b) *)b; - struct cxl_memdev *cxlmd_a = cxled_to_memdev(cxled_a); - struct cxl_memdev *cxlmd_b = cxled_to_memdev(cxled_b); - struct cxl_port *port_a = cxled_to_port(cxled_a); - struct cxl_port *port_b = cxled_to_port(cxled_b); - struct cxl_port *iter_a, *iter_b, *port = NULL; struct cxl_switch_decoder *cxlsd; + struct cxl_port *parent; struct device *dev; - int a_pos, b_pos; - unsigned int seq; - - /* Exit early if any prior sorting failed */ - if (cxled_a->pos < 0 || cxled_b->pos < 0) - return 0; + int rc = -ENXIO; - /* - * Walk up the hierarchy to find a shared port, find the decoder that - * maps the range, compare the relative position of those dport - * mappings. - */ - for (iter_a = port_a; iter_a; iter_a = next_port(iter_a)) { - struct cxl_port *next_a, *next_b; + parent = next_port(port); + if (!parent) + return rc; - next_a = next_port(iter_a); - if (!next_a) - break; + dev = device_find_child(&parent->dev, range, + match_switch_decoder_by_range); + if (!dev) { + dev_err(port->uport_dev, + "failed to find decoder mapping %#llx-%#llx\n", + range->start, range->end); + return rc; + } + cxlsd = to_cxl_switch_decoder(dev); + *ways = cxlsd->cxld.interleave_ways; - for (iter_b = port_b; iter_b; iter_b = next_port(iter_b)) { - next_b = next_port(iter_b); - if (next_a != next_b) - continue; - port = next_a; + for (int i = 0; i < *ways; i++) { + if (cxlsd->target[i] == port->parent_dport) { + *pos = i; + rc = 0; break; } - - if (port) - break; } + put_device(dev); - if (!port) { - dev_err(cxlmd_a->dev.parent, - "failed to find shared port with %s\n", - dev_name(cxlmd_b->dev.parent)); - goto err; - } + return rc; +} - dev = device_find_child(&port->dev, cxled_a, decoder_match_range); - if (!dev) { - struct range *range = &cxled_a->cxld.hpa_range; +/** + * cxl_calc_interleave_pos() - calculate an endpoint position in a region + * @cxled: endpoint decoder member of given region + * + * The endpoint position is calculated by traversing the topology from + * the endpoint to the root decoder and iteratively applying this + * calculation: + * + * position = position * parent_ways + parent_pos; + * + * ...where @position is inferred from switch and root decoder target lists. + * + * Return: position >= 0 on success + * -ENXIO on failure + */ +static int cxl_calc_interleave_pos(struct cxl_endpoint_decoder *cxled) +{ + struct cxl_port *iter, *port = cxled_to_port(cxled); + struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); + struct range *range = &cxled->cxld.hpa_range; + int parent_ways = 0, parent_pos = 0, pos = 0; + int rc; - dev_err(port->uport_dev, - "failed to find decoder that maps %#llx-%#llx\n", - range->start, range->end); - goto err; - } + /* + * Example: the expected interleave order of the 4-way region shown + * below is: mem0, mem2, mem1, mem3 + * + * root_port + * / \ + * host_bridge_0 host_bridge_1 + * | | | | + * mem0 mem1 mem2 mem3 + * + * In the example the calculator will iterate twice. The first iteration + * uses the mem position in the host-bridge and the ways of the host- + * bridge to generate the first, or local, position. The second + * iteration uses the host-bridge position in the root_port and the ways + * of the root_port to refine the position. + * + * A trace of the calculation per endpoint looks like this: + * mem0: pos = 0 * 2 + 0 mem2: pos = 0 * 2 + 0 + * pos = 0 * 2 + 0 pos = 0 * 2 + 1 + * pos: 0 pos: 1 + * + * mem1: pos = 0 * 2 + 1 mem3: pos = 0 * 2 + 1 + * pos = 1 * 2 + 0 pos = 1 * 2 + 1 + * pos: 2 pos = 3 + * + * Note that while this example is simple, the method applies to more + * complex topologies, including those with switches. + */ - cxlsd = to_cxl_switch_decoder(dev); - do { - seq = read_seqbegin(&cxlsd->target_lock); - find_positions(cxlsd, iter_a, iter_b, &a_pos, &b_pos); - } while (read_seqretry(&cxlsd->target_lock, seq)); + /* Iterate from endpoint to root_port refining the position */ + for (iter = port; iter; iter = next_port(iter)) { + if (is_cxl_root(iter)) + break; - put_device(dev); + rc = find_pos_and_ways(iter, range, &parent_pos, &parent_ways); + if (rc) + return rc; - if (a_pos < 0 || b_pos < 0) { - dev_err(port->uport_dev, - "failed to find shared decoder for %s and %s\n", - dev_name(cxlmd_a->dev.parent), - dev_name(cxlmd_b->dev.parent)); - goto err; + pos = pos * parent_ways + parent_pos; } - dev_dbg(port->uport_dev, "%s comes %s %s\n", - dev_name(cxlmd_a->dev.parent), - a_pos - b_pos < 0 ? "before" : "after", - dev_name(cxlmd_b->dev.parent)); + dev_dbg(&cxlmd->dev, + "decoder:%s parent:%s port:%s range:%#llx-%#llx pos:%d\n", + dev_name(&cxled->cxld.dev), dev_name(cxlmd->dev.parent), + dev_name(&port->dev), range->start, range->end, pos); - return a_pos - b_pos; -err: - cxled_a->pos = -1; - return 0; + return pos; } static int cxl_region_sort_targets(struct cxl_region *cxlr) @@ -1607,22 +1624,21 @@ static int cxl_region_sort_targets(struct cxl_region *cxlr) struct cxl_region_params *p = &cxlr->params; int i, rc = 0; - sort(p->targets, p->nr_targets, sizeof(p->targets[0]), cmp_decode_pos, - NULL); - for (i = 0; i < p->nr_targets; i++) { struct cxl_endpoint_decoder *cxled = p->targets[i]; + cxled->pos = cxl_calc_interleave_pos(cxled); /* - * Record that sorting failed, but still continue to restore - * cxled->pos with its ->targets[] position so that follow-on - * code paths can reliably do p->targets[cxled->pos] to - * self-reference their entry. + * Record that sorting failed, but still continue to calc + * cxled->pos so that follow-on code paths can reliably + * do p->targets[cxled->pos] to self-reference their entry. */ if (cxled->pos < 0) rc = -ENXIO; - cxled->pos = i; } + /* Keep the cxlr target list in interleave position order */ + sort(p->targets, p->nr_targets, sizeof(p->targets[0]), + cmp_interleave_pos, NULL); dev_dbg(&cxlr->dev, "region sort %s\n", rc ? "failed" : "successful"); return rc; @@ -1658,6 +1674,12 @@ static int cxl_region_attach(struct cxl_region *cxlr, return -ENXIO; } + if (p->nr_targets >= p->interleave_ways) { + dev_dbg(&cxlr->dev, "region already has %d endpoints\n", + p->nr_targets); + return -EINVAL; + } + ep_port = cxled_to_port(cxled); root_port = cxlrd_to_port(cxlrd); dport = cxl_find_dport_by_dev(root_port, ep_port->host_bridge); @@ -1750,7 +1772,7 @@ static int cxl_region_attach(struct cxl_region *cxlr, if (p->nr_targets == p->interleave_ways) { rc = cxl_region_setup_targets(cxlr); if (rc) - goto err_decrement; + return rc; p->state = CXL_CONFIG_ACTIVE; } @@ -1761,13 +1783,27 @@ static int cxl_region_attach(struct cxl_region *cxlr, .end = p->res->end, }; - return 0; + if (p->nr_targets != p->interleave_ways) + return 0; -err_decrement: - p->nr_targets--; - cxled->pos = -1; - p->targets[pos] = NULL; - return rc; + /* + * Test the auto-discovery position calculator function + * against this successfully created user-defined region. + * A fail message here means that this interleave config + * will fail when presented as CXL_REGION_F_AUTO. + */ + for (int i = 0; i < p->nr_targets; i++) { + struct cxl_endpoint_decoder *cxled = p->targets[i]; + int test_pos; + + test_pos = cxl_calc_interleave_pos(cxled); + dev_dbg(&cxled->cxld.dev, + "Test cxl_calc_interleave_pos(): %s test_pos:%d cxled->pos:%d\n", + (test_pos == cxled->pos) ? "success" : "fail", + test_pos, cxled->pos); + } + + return 0; } static int cxl_region_detach(struct cxl_endpoint_decoder *cxled) @@ -2696,7 +2732,7 @@ err: return rc; } -static int match_decoder_by_range(struct device *dev, void *data) +static int match_root_decoder_by_range(struct device *dev, void *data) { struct range *r1, *r2 = data; struct cxl_root_decoder *cxlrd; @@ -2827,7 +2863,7 @@ int cxl_add_to_region(struct cxl_port *root, struct cxl_endpoint_decoder *cxled) int rc; cxlrd_dev = device_find_child(&root->dev, &cxld->hpa_range, - match_decoder_by_range); + match_root_decoder_by_range); if (!cxlrd_dev) { dev_err(cxlmd->dev.parent, "%s:%s no CXL window for range %#llx:%#llx\n", diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index cfd287466fa8..a2fcbca253f3 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -84,9 +84,12 @@ static inline bool is_cxl_endpoint(struct cxl_port *port) return is_cxl_memdev(port->uport_dev); } -struct cxl_memdev *devm_cxl_add_memdev(struct cxl_dev_state *cxlds); +struct cxl_memdev *devm_cxl_add_memdev(struct device *host, + struct cxl_dev_state *cxlds); +int devm_cxl_sanitize_setup_notifier(struct device *host, + struct cxl_memdev *cxlmd); struct cxl_memdev_state; -int cxl_memdev_setup_fw_upload(struct cxl_memdev_state *mds); +int devm_cxl_setup_fw_upload(struct device *host, struct cxl_memdev_state *mds); int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled, resource_size_t base, resource_size_t len, resource_size_t skipped); @@ -360,16 +363,16 @@ struct cxl_fw_state { * * @state: state of last security operation * @enabled_cmds: All security commands enabled in the CEL - * @poll: polling for sanitization is enabled, device has no mbox irq support * @poll_tmo_secs: polling timeout + * @sanitize_active: sanitize completion pending * @poll_dwork: polling work item * @sanitize_node: sanitation sysfs file to notify */ struct cxl_security_state { unsigned long state; DECLARE_BITMAP(enabled_cmds, CXL_SEC_ENABLED_MAX); - bool poll; int poll_tmo_secs; + bool sanitize_active; struct delayed_work poll_dwork; struct kernfs_node *sanitize_node; }; @@ -883,7 +886,7 @@ static inline void cxl_mem_active_dec(void) } #endif -int cxl_mem_sanitize(struct cxl_memdev_state *mds, u16 cmd); +int cxl_mem_sanitize(struct cxl_memdev *cxlmd, u16 cmd); struct cxl_hdm { struct cxl_component_regs regs; diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index fa94bc61af25..4067afca6389 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -90,7 +90,7 @@ struct cxl_dev_id { }; static int cxl_request_irq(struct cxl_dev_state *cxlds, int irq, - irq_handler_t handler, irq_handler_t thread_fn) + irq_handler_t thread_fn) { struct device *dev = cxlds->dev; struct cxl_dev_id *dev_id; @@ -101,9 +101,9 @@ static int cxl_request_irq(struct cxl_dev_state *cxlds, int irq, return -ENOMEM; dev_id->cxlds = cxlds; - return devm_request_threaded_irq(dev, irq, handler, thread_fn, - IRQF_SHARED | IRQF_ONESHOT, - NULL, dev_id); + return devm_request_threaded_irq(dev, irq, NULL, thread_fn, + IRQF_SHARED | IRQF_ONESHOT, NULL, + dev_id); } static bool cxl_mbox_background_complete(struct cxl_dev_state *cxlds) @@ -128,10 +128,10 @@ static irqreturn_t cxl_pci_mbox_irq(int irq, void *id) reg = readq(cxlds->regs.mbox + CXLDEV_MBOX_BG_CMD_STATUS_OFFSET); opcode = FIELD_GET(CXLDEV_MBOX_BG_CMD_COMMAND_OPCODE_MASK, reg); if (opcode == CXL_MBOX_OP_SANITIZE) { + mutex_lock(&mds->mbox_mutex); if (mds->security.sanitize_node) - sysfs_notify_dirent(mds->security.sanitize_node); - - dev_dbg(cxlds->dev, "Sanitization operation ended\n"); + mod_delayed_work(system_wq, &mds->security.poll_dwork, 0); + mutex_unlock(&mds->mbox_mutex); } else { /* short-circuit the wait in __cxl_pci_mbox_send_cmd() */ rcuwait_wake_up(&mds->mbox_wait); @@ -152,18 +152,16 @@ static void cxl_mbox_sanitize_work(struct work_struct *work) mutex_lock(&mds->mbox_mutex); if (cxl_mbox_background_complete(cxlds)) { mds->security.poll_tmo_secs = 0; - put_device(cxlds->dev); - if (mds->security.sanitize_node) sysfs_notify_dirent(mds->security.sanitize_node); + mds->security.sanitize_active = false; dev_dbg(cxlds->dev, "Sanitization operation ended\n"); } else { int timeout = mds->security.poll_tmo_secs + 10; mds->security.poll_tmo_secs = min(15 * 60, timeout); - queue_delayed_work(system_wq, &mds->security.poll_dwork, - timeout * HZ); + schedule_delayed_work(&mds->security.poll_dwork, timeout * HZ); } mutex_unlock(&mds->mbox_mutex); } @@ -295,18 +293,15 @@ static int __cxl_pci_mbox_send_cmd(struct cxl_memdev_state *mds, * and allow userspace to poll(2) for completion. */ if (mbox_cmd->opcode == CXL_MBOX_OP_SANITIZE) { - if (mds->security.poll) { - /* hold the device throughout */ - get_device(cxlds->dev); - - /* give first timeout a second */ - timeout = 1; - mds->security.poll_tmo_secs = timeout; - queue_delayed_work(system_wq, - &mds->security.poll_dwork, - timeout * HZ); - } - + if (mds->security.sanitize_active) + return -EBUSY; + + /* give first timeout a second */ + timeout = 1; + mds->security.poll_tmo_secs = timeout; + mds->security.sanitize_active = true; + schedule_delayed_work(&mds->security.poll_dwork, + timeout * HZ); dev_dbg(dev, "Sanitization operation started\n"); goto success; } @@ -389,7 +384,9 @@ static int cxl_pci_setup_mailbox(struct cxl_memdev_state *mds) const int cap = readl(cxlds->regs.mbox + CXLDEV_MBOX_CAPS_OFFSET); struct device *dev = cxlds->dev; unsigned long timeout; + int irq, msgnum; u64 md_status; + u32 ctrl; timeout = jiffies + mbox_ready_timeout * HZ; do { @@ -437,33 +434,26 @@ static int cxl_pci_setup_mailbox(struct cxl_memdev_state *mds) dev_dbg(dev, "Mailbox payload sized %zu", mds->payload_size); rcuwait_init(&mds->mbox_wait); + INIT_DELAYED_WORK(&mds->security.poll_dwork, cxl_mbox_sanitize_work); - if (cap & CXLDEV_MBOX_CAP_BG_CMD_IRQ) { - u32 ctrl; - int irq, msgnum; - struct pci_dev *pdev = to_pci_dev(cxlds->dev); - - msgnum = FIELD_GET(CXLDEV_MBOX_CAP_IRQ_MSGNUM_MASK, cap); - irq = pci_irq_vector(pdev, msgnum); - if (irq < 0) - goto mbox_poll; - - if (cxl_request_irq(cxlds, irq, cxl_pci_mbox_irq, NULL)) - goto mbox_poll; + /* background command interrupts are optional */ + if (!(cap & CXLDEV_MBOX_CAP_BG_CMD_IRQ)) + return 0; - /* enable background command mbox irq support */ - ctrl = readl(cxlds->regs.mbox + CXLDEV_MBOX_CTRL_OFFSET); - ctrl |= CXLDEV_MBOX_CTRL_BG_CMD_IRQ; - writel(ctrl, cxlds->regs.mbox + CXLDEV_MBOX_CTRL_OFFSET); + msgnum = FIELD_GET(CXLDEV_MBOX_CAP_IRQ_MSGNUM_MASK, cap); + irq = pci_irq_vector(to_pci_dev(cxlds->dev), msgnum); + if (irq < 0) + return 0; + if (cxl_request_irq(cxlds, irq, cxl_pci_mbox_irq)) return 0; - } -mbox_poll: - mds->security.poll = true; - INIT_DELAYED_WORK(&mds->security.poll_dwork, cxl_mbox_sanitize_work); + dev_dbg(cxlds->dev, "Mailbox interrupts enabled\n"); + /* enable background command mbox irq support */ + ctrl = readl(cxlds->regs.mbox + CXLDEV_MBOX_CTRL_OFFSET); + ctrl |= CXLDEV_MBOX_CTRL_BG_CMD_IRQ; + writel(ctrl, cxlds->regs.mbox + CXLDEV_MBOX_CTRL_OFFSET); - dev_dbg(cxlds->dev, "Mailbox interrupts are unsupported"); return 0; } @@ -653,7 +643,7 @@ static int cxl_event_req_irq(struct cxl_dev_state *cxlds, u8 setting) if (irq < 0) return irq; - return cxl_request_irq(cxlds, irq, NULL, cxl_event_thread); + return cxl_request_irq(cxlds, irq, cxl_event_thread); } static int cxl_event_get_int_policy(struct cxl_memdev_state *mds, @@ -880,11 +870,15 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (rc) return rc; - cxlmd = devm_cxl_add_memdev(cxlds); + cxlmd = devm_cxl_add_memdev(&pdev->dev, cxlds); if (IS_ERR(cxlmd)) return PTR_ERR(cxlmd); - rc = cxl_memdev_setup_fw_upload(mds); + rc = devm_cxl_setup_fw_upload(&pdev->dev, mds); + if (rc) + return rc; + + rc = devm_cxl_sanitize_setup_notifier(&pdev->dev, cxlmd); if (rc) return rc; |