diff options
Diffstat (limited to 'drivers/cxl/core')
| -rw-r--r-- | drivers/cxl/core/Makefile | 3 | ||||
| -rw-r--r-- | drivers/cxl/core/core.h | 7 | ||||
| -rw-r--r-- | drivers/cxl/core/hdm.c | 144 | ||||
| -rw-r--r-- | drivers/cxl/core/mbox.c | 263 | ||||
| -rw-r--r-- | drivers/cxl/core/memdev.c | 3 | ||||
| -rw-r--r-- | drivers/cxl/core/pci.c | 316 | ||||
| -rw-r--r-- | drivers/cxl/core/port.c | 123 | ||||
| -rw-r--r-- | drivers/cxl/core/region.c | 878 | ||||
| -rw-r--r-- | drivers/cxl/core/trace.c | 5 | ||||
| -rw-r--r-- | drivers/cxl/core/trace.h | 606 |
10 files changed, 2088 insertions, 260 deletions
diff --git a/drivers/cxl/core/Makefile b/drivers/cxl/core/Makefile index 79c7257f4107..ca4ae31d8f57 100644 --- a/drivers/cxl/core/Makefile +++ b/drivers/cxl/core/Makefile @@ -3,6 +3,8 @@ obj-$(CONFIG_CXL_BUS) += cxl_core.o obj-$(CONFIG_CXL_SUSPEND) += suspend.o ccflags-y += -I$(srctree)/drivers/cxl +CFLAGS_trace.o = -DTRACE_INCLUDE_PATH=. -I$(src) + cxl_core-y := port.o cxl_core-y += pmem.o cxl_core-y += regs.o @@ -10,4 +12,5 @@ cxl_core-y += memdev.o cxl_core-y += mbox.o cxl_core-y += pci.o cxl_core-y += hdm.o +cxl_core-$(CONFIG_TRACING) += trace.o cxl_core-$(CONFIG_CXL_REGION) += region.o diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h index 8c04672dca56..cde475e13216 100644 --- a/drivers/cxl/core/core.h +++ b/drivers/cxl/core/core.h @@ -11,15 +11,18 @@ extern struct attribute_group cxl_base_attribute_group; #ifdef CONFIG_CXL_REGION extern struct device_attribute dev_attr_create_pmem_region; +extern struct device_attribute dev_attr_create_ram_region; extern struct device_attribute dev_attr_delete_region; extern struct device_attribute dev_attr_region; extern const struct device_type cxl_pmem_region_type; +extern const struct device_type cxl_dax_region_type; extern const struct device_type cxl_region_type; void cxl_decoder_kill_region(struct cxl_endpoint_decoder *cxled); #define CXL_REGION_ATTR(x) (&dev_attr_##x.attr) #define CXL_REGION_TYPE(x) (&cxl_region_type) #define SET_CXL_REGION_ATTR(x) (&dev_attr_##x.attr), #define CXL_PMEM_REGION_TYPE(x) (&cxl_pmem_region_type) +#define CXL_DAX_REGION_TYPE(x) (&cxl_dax_region_type) int cxl_region_init(void); void cxl_region_exit(void); #else @@ -37,6 +40,7 @@ static inline void cxl_region_exit(void) #define CXL_REGION_TYPE(x) NULL #define SET_CXL_REGION_ATTR(x) #define CXL_PMEM_REGION_TYPE(x) NULL +#define CXL_DAX_REGION_TYPE(x) NULL #endif struct cxl_send_command; @@ -56,9 +60,6 @@ resource_size_t cxl_dpa_size(struct cxl_endpoint_decoder *cxled); resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled); 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); - int cxl_memdev_init(void); void cxl_memdev_exit(void); void cxl_mbox_init(void); diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index dcc16d7cb8f3..45deda18ed32 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -101,11 +101,34 @@ static int map_hdm_decoder_regs(struct cxl_port *port, void __iomem *crb, BIT(CXL_CM_CAP_CAP_ID_HDM)); } +static struct cxl_hdm *devm_cxl_setup_emulated_hdm(struct cxl_port *port, + struct cxl_endpoint_dvsec_info *info) +{ + struct device *dev = &port->dev; + struct cxl_hdm *cxlhdm; + + if (!info->mem_enabled) + return ERR_PTR(-ENODEV); + + cxlhdm = devm_kzalloc(dev, sizeof(*cxlhdm), GFP_KERNEL); + if (!cxlhdm) + return ERR_PTR(-ENOMEM); + + cxlhdm->port = port; + cxlhdm->decoder_count = info->ranges; + cxlhdm->target_count = info->ranges; + dev_set_drvdata(&port->dev, cxlhdm); + + return cxlhdm; +} + /** * devm_cxl_setup_hdm - map HDM decoder component registers * @port: cxl_port to map + * @info: cached DVSEC range register info */ -struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port) +struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port, + struct cxl_endpoint_dvsec_info *info) { struct device *dev = &port->dev; struct cxl_hdm *cxlhdm; @@ -119,6 +142,9 @@ struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port) cxlhdm->port = port; crb = ioremap(port->component_reg_phys, CXL_COMPONENT_REG_BLOCK_SIZE); if (!crb) { + if (info && info->mem_enabled) + return devm_cxl_setup_emulated_hdm(port, info); + dev_err(dev, "No component registers mapped\n"); return ERR_PTR(-ENXIO); } @@ -279,7 +305,7 @@ success: return 0; } -static int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled, +int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled, resource_size_t base, resource_size_t len, resource_size_t skipped) { @@ -295,6 +321,7 @@ static int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled, return devm_add_action_or_reset(&port->dev, cxl_dpa_release, cxled); } +EXPORT_SYMBOL_NS_GPL(devm_cxl_dpa_reserve, CXL); resource_size_t cxl_dpa_size(struct cxl_endpoint_decoder *cxled) { @@ -676,12 +703,71 @@ static int cxl_decoder_reset(struct cxl_decoder *cxld) port->commit_end--; cxld->flags &= ~CXL_DECODER_F_ENABLE; + /* Userspace is now responsible for reconfiguring this decoder */ + if (is_endpoint_decoder(&cxld->dev)) { + struct cxl_endpoint_decoder *cxled; + + cxled = to_cxl_endpoint_decoder(&cxld->dev); + cxled->state = CXL_DECODER_STATE_MANUAL; + } + + return 0; +} + +static int cxl_setup_hdm_decoder_from_dvsec(struct cxl_port *port, + struct cxl_decoder *cxld, int which, + struct cxl_endpoint_dvsec_info *info) +{ + if (!is_cxl_endpoint(port)) + return -EOPNOTSUPP; + + if (!range_len(&info->dvsec_range[which])) + return -ENOENT; + + cxld->target_type = CXL_DECODER_EXPANDER; + cxld->commit = NULL; + cxld->reset = NULL; + cxld->hpa_range = info->dvsec_range[which]; + + /* + * Set the emulated decoder as locked pending additional support to + * change the range registers at run time. + */ + cxld->flags |= CXL_DECODER_F_ENABLE | CXL_DECODER_F_LOCK; + port->commit_end = cxld->id; + return 0; } +static bool should_emulate_decoders(struct cxl_port *port) +{ + struct cxl_hdm *cxlhdm = dev_get_drvdata(&port->dev); + void __iomem *hdm = cxlhdm->regs.hdm_decoder; + u32 ctrl; + int i; + + if (!is_cxl_endpoint(cxlhdm->port)) + return false; + + if (!hdm) + return true; + + /* + * If any decoders are committed already, there should not be any + * emulated DVSEC decoders. + */ + for (i = 0; i < cxlhdm->decoder_count; i++) { + ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(i)); + if (FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl)) + return false; + } + + return true; +} + static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, int *target_map, void __iomem *hdm, int which, - u64 *dpa_base) + u64 *dpa_base, struct cxl_endpoint_dvsec_info *info) { struct cxl_endpoint_decoder *cxled = NULL; u64 size, base, skip, dpa_size; @@ -694,6 +780,9 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, unsigned char target_id[8]; } target_list; + if (should_emulate_decoders(port)) + return cxl_setup_hdm_decoder_from_dvsec(port, cxld, which, info); + if (is_endpoint_decoder(&cxld->dev)) cxled = to_cxl_endpoint_decoder(&cxld->dev); @@ -717,6 +806,9 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, .end = base + size - 1, }; + if (cxled && !committed && range_len(&info->dvsec_range[which])) + return cxl_setup_hdm_decoder_from_dvsec(port, cxld, which, info); + /* decoders are enabled if committed */ if (committed) { cxld->flags |= CXL_DECODER_F_ENABLE; @@ -783,21 +875,21 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, return rc; } *dpa_base += dpa_size + skip; + + cxled->state = CXL_DECODER_STATE_AUTO; + return 0; } -/** - * devm_cxl_enumerate_decoders - add decoder objects per HDM register set - * @cxlhdm: Structure to populate with HDM capabilities - */ -int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm) +static void cxl_settle_decoders(struct cxl_hdm *cxlhdm) { void __iomem *hdm = cxlhdm->regs.hdm_decoder; - struct cxl_port *port = cxlhdm->port; - int i, committed; - u64 dpa_base = 0; + int committed, i; u32 ctrl; + if (!hdm) + return; + /* * Since the register resource was recently claimed via request_region() * be careful about trusting the "not-committed" status until the commit @@ -814,6 +906,22 @@ int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm) /* ensure that future checks of committed can be trusted */ if (committed != cxlhdm->decoder_count) msleep(20); +} + +/** + * devm_cxl_enumerate_decoders - add decoder objects per HDM register set + * @cxlhdm: Structure to populate with HDM capabilities + * @info: cached DVSEC range register info + */ +int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, + struct cxl_endpoint_dvsec_info *info) +{ + void __iomem *hdm = cxlhdm->regs.hdm_decoder; + struct cxl_port *port = cxlhdm->port; + int i; + u64 dpa_base = 0; + + cxl_settle_decoders(cxlhdm); for (i = 0; i < cxlhdm->decoder_count; i++) { int target_map[CXL_DECODER_MAX_INTERLEAVE] = { 0 }; @@ -826,7 +934,8 @@ int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm) cxled = cxl_endpoint_decoder_alloc(port); if (IS_ERR(cxled)) { dev_warn(&port->dev, - "Failed to allocate the decoder\n"); + "Failed to allocate decoder%d.%d\n", + port->id, i); return PTR_ERR(cxled); } cxld = &cxled->cxld; @@ -836,21 +945,26 @@ int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm) cxlsd = cxl_switch_decoder_alloc(port, target_count); if (IS_ERR(cxlsd)) { dev_warn(&port->dev, - "Failed to allocate the decoder\n"); + "Failed to allocate decoder%d.%d\n", + port->id, i); return PTR_ERR(cxlsd); } cxld = &cxlsd->cxld; } - rc = init_hdm_decoder(port, cxld, target_map, hdm, i, &dpa_base); + rc = init_hdm_decoder(port, cxld, target_map, hdm, i, + &dpa_base, info); if (rc) { + dev_warn(&port->dev, + "Failed to initialize decoder%d.%d\n", + port->id, i); put_device(&cxld->dev); return rc; } rc = add_hdm_decoder(port, cxld, target_map); if (rc) { dev_warn(&port->dev, - "Failed to add decoder to port\n"); + "Failed to add decoder%d.%d\n", port->id, i); return rc; } } diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index b03fba212799..f2addb457172 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -3,11 +3,13 @@ #include <linux/io-64-nonatomic-lo-hi.h> #include <linux/security.h> #include <linux/debugfs.h> +#include <linux/ktime.h> #include <linux/mutex.h> #include <cxlmem.h> #include <cxl.h> #include "core.h" +#include "trace.h" static bool cxl_raw_allow_all; @@ -170,6 +172,12 @@ int cxl_internal_send_cmd(struct cxl_dev_state *cxlds, out_size = mbox_cmd->size_out; min_out = mbox_cmd->min_out; rc = cxlds->mbox_send(cxlds, mbox_cmd); + /* + * EIO is reserved for a payload size mismatch and mbox_send() + * may not return this error. + */ + if (WARN_ONCE(rc == -EIO, "Bad return code: -EIO")) + return -ENXIO; if (rc) return rc; @@ -445,9 +453,14 @@ int cxl_query_cmd(struct cxl_memdev *cxlmd, * structures. */ cxl_for_each_cmd(cmd) { - const struct cxl_command_info *info = &cmd->info; + struct cxl_command_info info = cmd->info; - if (copy_to_user(&q->commands[j++], info, sizeof(*info))) + if (test_bit(info.id, cxlmd->cxlds->enabled_cmds)) + info.flags |= CXL_MEM_COMMAND_FLAG_ENABLED; + if (test_bit(info.id, cxlmd->cxlds->exclusive_cmds)) + info.flags |= CXL_MEM_COMMAND_FLAG_EXCLUSIVE; + + if (copy_to_user(&q->commands[j++], &info, sizeof(info))) return -EFAULT; if (j == n_commands) @@ -550,9 +563,9 @@ int cxl_send_cmd(struct cxl_memdev *cxlmd, struct cxl_send_command __user *s) return 0; } -static int cxl_xfer_log(struct cxl_dev_state *cxlds, uuid_t *uuid, u32 size, u8 *out) +static int cxl_xfer_log(struct cxl_dev_state *cxlds, uuid_t *uuid, u32 *size, u8 *out) { - u32 remaining = size; + u32 remaining = *size; u32 offset = 0; while (remaining) { @@ -576,6 +589,17 @@ static int cxl_xfer_log(struct cxl_dev_state *cxlds, uuid_t *uuid, u32 size, u8 }; rc = cxl_internal_send_cmd(cxlds, &mbox_cmd); + + /* + * The output payload length that indicates the number + * of valid bytes can be smaller than the Log buffer + * size. + */ + if (rc == -EIO && mbox_cmd.size_out < xfer_size) { + offset += mbox_cmd.size_out; + break; + } + if (rc < 0) return rc; @@ -584,6 +608,8 @@ static int cxl_xfer_log(struct cxl_dev_state *cxlds, uuid_t *uuid, u32 size, u8 offset += xfer_size; } + *size = offset; + return 0; } @@ -610,11 +636,12 @@ static void cxl_walk_cel(struct cxl_dev_state *cxlds, size_t size, u8 *cel) if (!cmd) { dev_dbg(cxlds->dev, - "Opcode 0x%04x unsupported by driver", opcode); + "Opcode 0x%04x unsupported by driver\n", opcode); continue; } set_bit(cmd->info.id, cxlds->enabled_cmds); + dev_dbg(cxlds->dev, "Opcode 0x%04x enabled\n", opcode); } } @@ -694,7 +721,7 @@ int cxl_enumerate_cmds(struct cxl_dev_state *cxlds) goto out; } - rc = cxl_xfer_log(cxlds, &uuid, size, log); + rc = cxl_xfer_log(cxlds, &uuid, &size, log); if (rc) { kvfree(log); goto out; @@ -717,6 +744,203 @@ out: } EXPORT_SYMBOL_NS_GPL(cxl_enumerate_cmds, CXL); +/* + * General Media Event Record + * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43 + */ +static const uuid_t gen_media_event_uuid = + UUID_INIT(0xfbcd0a77, 0xc260, 0x417f, + 0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6); + +/* + * DRAM Event Record + * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44 + */ +static const uuid_t dram_event_uuid = + UUID_INIT(0x601dcbb3, 0x9c06, 0x4eab, + 0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24); + +/* + * Memory Module Event Record + * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45 + */ +static const uuid_t mem_mod_event_uuid = + UUID_INIT(0xfe927475, 0xdd59, 0x4339, + 0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74); + +static void cxl_event_trace_record(const struct cxl_memdev *cxlmd, + enum cxl_event_log_type type, + struct cxl_event_record_raw *record) +{ + uuid_t *id = &record->hdr.id; + + if (uuid_equal(id, &gen_media_event_uuid)) { + struct cxl_event_gen_media *rec = + (struct cxl_event_gen_media *)record; + + trace_cxl_general_media(cxlmd, type, rec); + } else if (uuid_equal(id, &dram_event_uuid)) { + struct cxl_event_dram *rec = (struct cxl_event_dram *)record; + + trace_cxl_dram(cxlmd, type, rec); + } else if (uuid_equal(id, &mem_mod_event_uuid)) { + struct cxl_event_mem_module *rec = + (struct cxl_event_mem_module *)record; + + trace_cxl_memory_module(cxlmd, type, rec); + } else { + /* For unknown record types print just the header */ + trace_cxl_generic_event(cxlmd, type, record); + } +} + +static int cxl_clear_event_record(struct cxl_dev_state *cxlds, + enum cxl_event_log_type log, + struct cxl_get_event_payload *get_pl) +{ + struct cxl_mbox_clear_event_payload *payload; + u16 total = le16_to_cpu(get_pl->record_count); + u8 max_handles = CXL_CLEAR_EVENT_MAX_HANDLES; + size_t pl_size = struct_size(payload, handles, max_handles); + struct cxl_mbox_cmd mbox_cmd; + u16 cnt; + int rc = 0; + int i; + + /* Payload size may limit the max handles */ + if (pl_size > cxlds->payload_size) { + max_handles = (cxlds->payload_size - sizeof(*payload)) / + sizeof(__le16); + pl_size = struct_size(payload, handles, max_handles); + } + + payload = kvzalloc(pl_size, GFP_KERNEL); + if (!payload) + return -ENOMEM; + + *payload = (struct cxl_mbox_clear_event_payload) { + .event_log = log, + }; + + mbox_cmd = (struct cxl_mbox_cmd) { + .opcode = CXL_MBOX_OP_CLEAR_EVENT_RECORD, + .payload_in = payload, + .size_in = pl_size, + }; + + /* + * Clear Event Records uses u8 for the handle cnt while Get Event + * Record can return up to 0xffff records. + */ + i = 0; + for (cnt = 0; cnt < total; cnt++) { + payload->handles[i++] = get_pl->records[cnt].hdr.handle; + dev_dbg(cxlds->dev, "Event log '%d': Clearing %u\n", + log, le16_to_cpu(payload->handles[i])); + + if (i == max_handles) { + payload->nr_recs = i; + rc = cxl_internal_send_cmd(cxlds, &mbox_cmd); + if (rc) + goto free_pl; + i = 0; + } + } + + /* Clear what is left if any */ + if (i) { + payload->nr_recs = i; + mbox_cmd.size_in = struct_size(payload, handles, i); + rc = cxl_internal_send_cmd(cxlds, &mbox_cmd); + if (rc) + goto free_pl; + } + +free_pl: + kvfree(payload); + return rc; +} + +static void cxl_mem_get_records_log(struct cxl_dev_state *cxlds, + enum cxl_event_log_type type) +{ + struct cxl_get_event_payload *payload; + struct cxl_mbox_cmd mbox_cmd; + u8 log_type = type; + u16 nr_rec; + + mutex_lock(&cxlds->event.log_lock); + payload = cxlds->event.buf; + + mbox_cmd = (struct cxl_mbox_cmd) { + .opcode = CXL_MBOX_OP_GET_EVENT_RECORD, + .payload_in = &log_type, + .size_in = sizeof(log_type), + .payload_out = payload, + .size_out = cxlds->payload_size, + .min_out = struct_size(payload, records, 0), + }; + + do { + int rc, i; + + rc = cxl_internal_send_cmd(cxlds, &mbox_cmd); + if (rc) { + dev_err_ratelimited(cxlds->dev, + "Event log '%d': Failed to query event records : %d", + type, rc); + break; + } + + nr_rec = le16_to_cpu(payload->record_count); + if (!nr_rec) + break; + + for (i = 0; i < nr_rec; i++) + cxl_event_trace_record(cxlds->cxlmd, type, + &payload->records[i]); + + if (payload->flags & CXL_GET_EVENT_FLAG_OVERFLOW) + trace_cxl_overflow(cxlds->cxlmd, type, payload); + + rc = cxl_clear_event_record(cxlds, type, payload); + if (rc) { + dev_err_ratelimited(cxlds->dev, + "Event log '%d': Failed to clear events : %d", + type, rc); + break; + } + } while (nr_rec); + + mutex_unlock(&cxlds->event.log_lock); +} + +/** + * cxl_mem_get_event_records - Get Event Records from the device + * @cxlds: The device data for the operation + * @status: Event Status register value identifying which events are available. + * + * Retrieve all event records available on the device, report them as trace + * events, and clear them. + * + * See CXL rev 3.0 @8.2.9.2.2 Get Event Records + * See CXL rev 3.0 @8.2.9.2.3 Clear Event Records + */ +void cxl_mem_get_event_records(struct cxl_dev_state *cxlds, u32 status) +{ + dev_dbg(cxlds->dev, "Reading event logs: %x\n", status); + + if (status & CXLDEV_EVENT_STATUS_FATAL) + cxl_mem_get_records_log(cxlds, CXL_EVENT_TYPE_FATAL); + if (status & CXLDEV_EVENT_STATUS_FAIL) + cxl_mem_get_records_log(cxlds, CXL_EVENT_TYPE_FAIL); + if (status & CXLDEV_EVENT_STATUS_WARN) + cxl_mem_get_records_log(cxlds, CXL_EVENT_TYPE_WARN); + if (status & CXLDEV_EVENT_STATUS_INFO) + cxl_mem_get_records_log(cxlds, CXL_EVENT_TYPE_INFO); +} +EXPORT_SYMBOL_NS_GPL(cxl_mem_get_event_records, CXL); + /** * cxl_mem_get_partition_info - Get partition info * @cxlds: The device data for the operation @@ -857,6 +1081,32 @@ int cxl_mem_create_range_info(struct cxl_dev_state *cxlds) } EXPORT_SYMBOL_NS_GPL(cxl_mem_create_range_info, CXL); +int cxl_set_timestamp(struct cxl_dev_state *cxlds) +{ + struct cxl_mbox_cmd mbox_cmd; + struct cxl_mbox_set_timestamp_in pi; + int rc; + + pi.timestamp = cpu_to_le64(ktime_get_real_ns()); + mbox_cmd = (struct cxl_mbox_cmd) { + .opcode = CXL_MBOX_OP_SET_TIMESTAMP, + .size_in = sizeof(pi), + .payload_in = &pi, + }; + + rc = cxl_internal_send_cmd(cxlds, &mbox_cmd); + /* + * Command is optional. Devices may have another way of providing + * a timestamp, or may return all 0s in timestamp fields. + * Don't report an error if this command isn't supported + */ + if (rc && (mbox_cmd.return_code != CXL_MBOX_CMD_RC_UNSUPPORTED)) + return rc; + + return 0; +} +EXPORT_SYMBOL_NS_GPL(cxl_set_timestamp, CXL); + struct cxl_dev_state *cxl_dev_state_create(struct device *dev) { struct cxl_dev_state *cxlds; @@ -868,6 +1118,7 @@ struct cxl_dev_state *cxl_dev_state_create(struct device *dev) } mutex_init(&cxlds->mbox_mutex); + mutex_init(&cxlds->event.log_lock); cxlds->dev = dev; return cxlds; diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index b75dd77df7ce..28a05f2fe32d 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -242,10 +242,11 @@ static struct cxl_memdev *cxl_memdev_alloc(struct cxl_dev_state *cxlds, if (!cxlmd) return ERR_PTR(-ENOMEM); - rc = ida_alloc_range(&cxl_memdev_ida, 0, CXL_MEM_MAX_DEVS, GFP_KERNEL); + rc = ida_alloc_max(&cxl_memdev_ida, CXL_MEM_MAX_DEVS - 1, GFP_KERNEL); if (rc < 0) goto err; cxlmd->id = rc; + cxlmd->depth = -1; dev = &cxlmd->dev; device_initialize(dev); diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index 57764e9cd19d..7328a2552411 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -9,6 +9,7 @@ #include <cxlmem.h> #include <cxl.h> #include "core.h" +#include "trace.h" /** * DOC: cxl core pci @@ -141,11 +142,10 @@ int cxl_await_media_ready(struct cxl_dev_state *cxlds) } EXPORT_SYMBOL_NS_GPL(cxl_await_media_ready, CXL); -static int wait_for_valid(struct cxl_dev_state *cxlds) +static int wait_for_valid(struct pci_dev *pdev, int d) { - struct pci_dev *pdev = to_pci_dev(cxlds->dev); - int d = cxlds->cxl_dvsec, rc; u32 val; + int rc; /* * Memory_Info_Valid: When set, indicates that the CXL Range 1 Size high @@ -213,11 +213,6 @@ static int devm_cxl_enable_mem(struct device *host, struct cxl_dev_state *cxlds) return devm_add_action_or_reset(host, clear_mem_enable, cxlds); } -static bool range_contains(struct range *r1, struct range *r2) -{ - return r1->start <= r2->start && r1->end >= r2->end; -} - /* require dvsec ranges to be covered by a locked platform window */ static int dvsec_range_allowed(struct device *dev, void *arg) { @@ -229,8 +224,6 @@ static int dvsec_range_allowed(struct device *dev, void *arg) cxld = to_cxl_decoder(dev); - if (!(cxld->flags & CXL_DECODER_F_LOCK)) - return 0; if (!(cxld->flags & CXL_DECODER_F_RAM)) return 0; @@ -260,94 +253,11 @@ static int devm_cxl_enable_hdm(struct device *host, struct cxl_hdm *cxlhdm) return devm_add_action_or_reset(host, disable_hdm, cxlhdm); } -static bool __cxl_hdm_decode_init(struct cxl_dev_state *cxlds, - struct cxl_hdm *cxlhdm, - struct cxl_endpoint_dvsec_info *info) +int cxl_dvsec_rr_decode(struct device *dev, int d, + struct cxl_endpoint_dvsec_info *info) { - void __iomem *hdm = cxlhdm->regs.hdm_decoder; - struct cxl_port *port = cxlhdm->port; - struct device *dev = cxlds->dev; - struct cxl_port *root; - int i, rc, allowed; - u32 global_ctrl; - - global_ctrl = readl(hdm + CXL_HDM_DECODER_CTRL_OFFSET); - - /* - * If the HDM Decoder Capability is already enabled then assume - * that some other agent like platform firmware set it up. - */ - if (global_ctrl & CXL_HDM_DECODER_ENABLE) { - rc = devm_cxl_enable_mem(&port->dev, cxlds); - if (rc) - return false; - return true; - } - - root = to_cxl_port(port->dev.parent); - while (!is_cxl_root(root) && is_cxl_port(root->dev.parent)) - root = to_cxl_port(root->dev.parent); - if (!is_cxl_root(root)) { - dev_err(dev, "Failed to acquire root port for HDM enable\n"); - return false; - } - - for (i = 0, allowed = 0; info->mem_enabled && i < info->ranges; i++) { - struct device *cxld_dev; - - cxld_dev = device_find_child(&root->dev, &info->dvsec_range[i], - dvsec_range_allowed); - if (!cxld_dev) { - dev_dbg(dev, "DVSEC Range%d denied by platform\n", i); - continue; - } - dev_dbg(dev, "DVSEC Range%d allowed by platform\n", i); - put_device(cxld_dev); - allowed++; - } - - if (!allowed) { - cxl_set_mem_enable(cxlds, 0); - info->mem_enabled = 0; - } - - /* - * Per CXL 2.0 Section 8.1.3.8.3 and 8.1.3.8.4 DVSEC CXL Range 1 Base - * [High,Low] when HDM operation is enabled the range register values - * are ignored by the device, but the spec also recommends matching the - * DVSEC Range 1,2 to HDM Decoder Range 0,1. So, non-zero info->ranges - * are expected even though Linux does not require or maintain that - * match. If at least one DVSEC range is enabled and allowed, skip HDM - * Decoder Capability Enable. - */ - if (info->mem_enabled) - return false; - - rc = devm_cxl_enable_hdm(&port->dev, cxlhdm); - if (rc) - return false; - - rc = devm_cxl_enable_mem(&port->dev, cxlds); - if (rc) - return false; - - return true; -} - -/** - * cxl_hdm_decode_init() - Setup HDM decoding for the endpoint - * @cxlds: Device state - * @cxlhdm: Mapped HDM decoder Capability - * - * Try to enable the endpoint's HDM Decoder Capability - */ -int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm) -{ - struct pci_dev *pdev = to_pci_dev(cxlds->dev); - struct cxl_endpoint_dvsec_info info = { 0 }; + struct pci_dev *pdev = to_pci_dev(dev); int hdm_count, rc, i, ranges = 0; - struct device *dev = &pdev->dev; - int d = cxlds->cxl_dvsec; u16 cap, ctrl; if (!d) { @@ -378,7 +288,7 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm) if (!hdm_count || hdm_count > 2) return -EINVAL; - rc = wait_for_valid(cxlds); + rc = wait_for_valid(pdev, d); if (rc) { dev_dbg(dev, "Failure awaiting MEM_INFO_VALID (%d)\n", rc); return rc; @@ -389,9 +299,9 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm) * disabled, and they will remain moot after the HDM Decoder * capability is enabled. */ - info.mem_enabled = FIELD_GET(CXL_DVSEC_MEM_ENABLE, ctrl); - if (!info.mem_enabled) - goto hdm_init; + info->mem_enabled = FIELD_GET(CXL_DVSEC_MEM_ENABLE, ctrl); + if (!info->mem_enabled) + return 0; for (i = 0; i < hdm_count; i++) { u64 base, size; @@ -410,6 +320,13 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm) return rc; size |= temp & CXL_DVSEC_MEM_SIZE_LOW_MASK; + if (!size) { + info->dvsec_range[i] = (struct range) { + .start = 0, + .end = CXL_RESOURCE_NONE, + }; + continue; + } rc = pci_read_config_dword( pdev, d + CXL_DVSEC_RANGE_BASE_HIGH(i), &temp); @@ -425,29 +342,94 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm) base |= temp & CXL_DVSEC_MEM_BASE_LOW_MASK; - info.dvsec_range[i] = (struct range) { + info->dvsec_range[i] = (struct range) { .start = base, .end = base + size - 1 }; - if (size) - ranges++; + ranges++; } - info.ranges = ranges; + info->ranges = ranges; + + return 0; +} +EXPORT_SYMBOL_NS_GPL(cxl_dvsec_rr_decode, CXL); + +/** + * cxl_hdm_decode_init() - Setup HDM decoding for the endpoint + * @cxlds: Device state + * @cxlhdm: Mapped HDM decoder Capability + * @info: Cached DVSEC range registers info + * + * Try to enable the endpoint's HDM Decoder Capability + */ +int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm, + struct cxl_endpoint_dvsec_info *info) +{ + void __iomem *hdm = cxlhdm->regs.hdm_decoder; + struct cxl_port *port = cxlhdm->port; + struct device *dev = cxlds->dev; + struct cxl_port *root; + int i, rc, allowed; + u32 global_ctrl = 0; + + if (hdm) + global_ctrl = readl(hdm + CXL_HDM_DECODER_CTRL_OFFSET); /* - * If DVSEC ranges are being used instead of HDM decoder registers there - * is no use in trying to manage those. + * If the HDM Decoder Capability is already enabled then assume + * that some other agent like platform firmware set it up. */ -hdm_init: - if (!__cxl_hdm_decode_init(cxlds, cxlhdm, &info)) { - dev_err(dev, - "Legacy range registers configuration prevents HDM operation.\n"); - return -EBUSY; + if (global_ctrl & CXL_HDM_DECODER_ENABLE || (!hdm && info->mem_enabled)) + return devm_cxl_enable_mem(&port->dev, cxlds); + else if (!hdm) + return -ENODEV; + + root = to_cxl_port(port->dev.parent); + while (!is_cxl_root(root) && is_cxl_port(root->dev.parent)) + root = to_cxl_port(root->dev.parent); + if (!is_cxl_root(root)) { + dev_err(dev, "Failed to acquire root port for HDM enable\n"); + return -ENODEV; } - return 0; + for (i = 0, allowed = 0; info->mem_enabled && i < info->ranges; i++) { + struct device *cxld_dev; + + cxld_dev = device_find_child(&root->dev, &info->dvsec_range[i], + dvsec_range_allowed); + if (!cxld_dev) { + dev_dbg(dev, "DVSEC Range%d denied by platform\n", i); + continue; + } + dev_dbg(dev, "DVSEC Range%d allowed by platform\n", i); + put_device(cxld_dev); + allowed++; + } + + if (!allowed) { + cxl_set_mem_enable(cxlds, 0); + info->mem_enabled = 0; + } + + /* + * Per CXL 2.0 Section 8.1.3.8.3 and 8.1.3.8.4 DVSEC CXL Range 1 Base + * [High,Low] when HDM operation is enabled the range register values + * are ignored by the device, but the spec also recommends matching the + * DVSEC Range 1,2 to HDM Decoder Range 0,1. So, non-zero info->ranges + * are expected even though Linux does not require or maintain that + * match. If at least one DVSEC range is enabled and allowed, skip HDM + * Decoder Capability Enable. + */ + if (info->mem_enabled) + return 0; + + rc = devm_cxl_enable_hdm(&port->dev, cxlhdm); + if (rc) + return rc; + + return devm_cxl_enable_mem(&port->dev, cxlds); } EXPORT_SYMBOL_NS_GPL(cxl_hdm_decode_init, CXL); @@ -622,3 +604,113 @@ void read_cdat_data(struct cxl_port *port) } } EXPORT_SYMBOL_NS_GPL(read_cdat_data, CXL); + +void cxl_cor_error_detected(struct pci_dev *pdev) +{ + struct cxl_dev_state *cxlds = pci_get_drvdata(pdev); + void __iomem *addr; + u32 status; + + if (!cxlds->regs.ras) + return; + + addr = cxlds->regs.ras + CXL_RAS_CORRECTABLE_STATUS_OFFSET; + status = readl(addr); + if (status & CXL_RAS_CORRECTABLE_STATUS_MASK) { + writel(status & CXL_RAS_CORRECTABLE_STATUS_MASK, addr); + trace_cxl_aer_correctable_error(cxlds->cxlmd, status); + } +} +EXPORT_SYMBOL_NS_GPL(cxl_cor_error_detected, CXL); + +/* CXL spec rev3.0 8.2.4.16.1 */ +static void header_log_copy(struct cxl_dev_state *cxlds, u32 *log) +{ + void __iomem *addr; + u32 *log_addr; + int i, log_u32_size = CXL_HEADERLOG_SIZE / sizeof(u32); + + addr = cxlds->regs.ras + CXL_RAS_HEADER_LOG_OFFSET; + log_addr = log; + + for (i = 0; i < log_u32_size; i++) { + *log_addr = readl(addr); + log_addr++; + addr += sizeof(u32); + } +} + +/* + * Log the state of the RAS status registers and prepare them to log the + * next error status. Return 1 if reset needed. + */ +static bool cxl_report_and_clear(struct cxl_dev_state *cxlds) +{ + u32 hl[CXL_HEADERLOG_SIZE_U32]; + void __iomem *addr; + u32 status; + u32 fe; + + if (!cxlds->regs.ras) + return false; + + addr = cxlds->regs.ras + CXL_RAS_UNCORRECTABLE_STATUS_OFFSET; + status = readl(addr); + if (!(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK)) + return false; + + /* If multiple errors, log header points to first error from ctrl reg */ + if (hweight32(status) > 1) { + void __iomem *rcc_addr = + cxlds->regs.ras + CXL_RAS_CAP_CONTROL_OFFSET; + + fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK, + readl(rcc_addr))); + } else { + fe = status; + } + + header_log_copy(cxlds, hl); + trace_cxl_aer_uncorrectable_error(cxlds->cxlmd, status, fe, hl); + writel(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK, addr); + + return true; +} + +pci_ers_result_t cxl_error_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + struct cxl_dev_state *cxlds = pci_get_drvdata(pdev); + struct cxl_memdev *cxlmd = cxlds->cxlmd; + struct device *dev = &cxlmd->dev; + bool ue; + + /* + * A frozen channel indicates an impending reset which is fatal to + * CXL.mem operation, and will likely crash the system. On the off + * chance the situation is recoverable dump the status of the RAS + * capability registers and bounce the active state of the memdev. + */ + ue = cxl_report_and_clear(cxlds); + + switch (state) { + case pci_channel_io_normal: + if (ue) { + device_release_driver(dev); + return PCI_ERS_RESULT_NEED_RESET; + } + return PCI_ERS_RESULT_CAN_RECOVER; + case pci_channel_io_frozen: + dev_warn(&pdev->dev, + "%s: frozen state error detected, disable CXL.mem\n", + dev_name(dev)); + device_release_driver(dev); + return PCI_ERS_RESULT_NEED_RESET; + case pci_channel_io_perm_failure: + dev_warn(&pdev->dev, + "failure state error detected, request disconnect\n"); + return PCI_ERS_RESULT_DISCONNECT; + } + return PCI_ERS_RESULT_NEED_RESET; +} +EXPORT_SYMBOL_NS_GPL(cxl_error_detected, CXL); diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 3f02dc135a12..8ee6b6e2e2a4 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -46,6 +46,8 @@ static int cxl_device_id(const struct device *dev) return CXL_DEVICE_NVDIMM; if (dev->type == CXL_PMEM_REGION_TYPE()) return CXL_DEVICE_PMEM_REGION; + if (dev->type == CXL_DAX_REGION_TYPE()) + return CXL_DEVICE_DAX_REGION; if (is_cxl_port(dev)) { if (is_cxl_root(to_cxl_port(dev))) return CXL_DEVICE_ROOT; @@ -180,17 +182,7 @@ static ssize_t mode_show(struct device *dev, struct device_attribute *attr, { struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev); - switch (cxled->mode) { - case CXL_DECODER_RAM: - return sysfs_emit(buf, "ram\n"); - case CXL_DECODER_PMEM: - return sysfs_emit(buf, "pmem\n"); - case CXL_DECODER_NONE: - return sysfs_emit(buf, "none\n"); - case CXL_DECODER_MIXED: - default: - return sysfs_emit(buf, "mixed\n"); - } + return sysfs_emit(buf, "%s\n", cxl_decoder_mode_name(cxled->mode)); } static ssize_t mode_store(struct device *dev, struct device_attribute *attr, @@ -304,6 +296,7 @@ static struct attribute *cxl_decoder_root_attrs[] = { &dev_attr_cap_type3.attr, &dev_attr_target_list.attr, SET_CXL_REGION_ATTR(create_pmem_region) + SET_CXL_REGION_ATTR(create_ram_region) SET_CXL_REGION_ATTR(delete_region) NULL, }; @@ -315,6 +308,13 @@ static bool can_create_pmem(struct cxl_root_decoder *cxlrd) return (cxlrd->cxlsd.cxld.flags & flags) == flags; } +static bool can_create_ram(struct cxl_root_decoder *cxlrd) +{ + unsigned long flags = CXL_DECODER_F_TYPE3 | CXL_DECODER_F_RAM; + + return (cxlrd->cxlsd.cxld.flags & flags) == flags; +} + static umode_t cxl_root_decoder_visible(struct kobject *kobj, struct attribute *a, int n) { struct device *dev = kobj_to_dev(kobj); @@ -323,7 +323,11 @@ static umode_t cxl_root_decoder_visible(struct kobject *kobj, struct attribute * if (a == CXL_REGION_ATTR(create_pmem_region) && !can_create_pmem(cxlrd)) return 0; - if (a == CXL_REGION_ATTR(delete_region) && !can_create_pmem(cxlrd)) + if (a == CXL_REGION_ATTR(create_ram_region) && !can_create_ram(cxlrd)) + return 0; + + if (a == CXL_REGION_ATTR(delete_region) && + !(can_create_pmem(cxlrd) || can_create_ram(cxlrd))) return 0; return a->mode; @@ -444,6 +448,7 @@ bool is_endpoint_decoder(struct device *dev) { return dev->type == &cxl_decoder_endpoint_type; } +EXPORT_SYMBOL_NS_GPL(is_endpoint_decoder, CXL); bool is_root_decoder(struct device *dev) { @@ -455,6 +460,7 @@ bool is_switch_decoder(struct device *dev) { return is_root_decoder(dev) || dev->type == &cxl_decoder_switch_type; } +EXPORT_SYMBOL_NS_GPL(is_switch_decoder, CXL); struct cxl_decoder *to_cxl_decoder(struct device *dev) { @@ -482,6 +488,7 @@ struct cxl_switch_decoder *to_cxl_switch_decoder(struct device *dev) return NULL; return container_of(dev, struct cxl_switch_decoder, cxld.dev); } +EXPORT_SYMBOL_NS_GPL(to_cxl_switch_decoder, CXL); static void cxl_ep_release(struct cxl_ep *ep) { @@ -583,6 +590,29 @@ static int devm_cxl_link_uport(struct device *host, struct cxl_port *port) return devm_add_action_or_reset(host, cxl_unlink_uport, port); } +static void cxl_unlink_parent_dport(void *_port) +{ + struct cxl_port *port = _port; + + sysfs_remove_link(&port->dev.kobj, "parent_dport"); +} + +static int devm_cxl_link_parent_dport(struct device *host, + struct cxl_port *port, + struct cxl_dport *parent_dport) +{ + int rc; + + if (!parent_dport) + return 0; + + rc = sysfs_create_link(&port->dev.kobj, &parent_dport->dport->kobj, + "parent_dport"); + if (rc) + return rc; + return devm_add_action_or_reset(host, cxl_unlink_parent_dport, port); +} + static struct lock_class_key cxl_port_key; static struct cxl_port *cxl_port_alloc(struct device *uport, @@ -692,6 +722,10 @@ static struct cxl_port *__devm_cxl_add_port(struct device *host, if (rc) return ERR_PTR(rc); + rc = devm_cxl_link_parent_dport(host, port, parent_dport); + if (rc) + return ERR_PTR(rc); + return port; err: @@ -1137,7 +1171,7 @@ static struct cxl_port *find_cxl_port_at(struct cxl_port *parent_port, } /* - * All users of grandparent() are using it to walk PCIe-like swich port + * All users of grandparent() are using it to walk PCIe-like switch port * hierarchy. A PCIe switch is comprised of a bridge device representing the * upstream switch port and N bridges representing downstream switch ports. When * bridges stack the grand-parent of a downstream switch port is another @@ -1164,6 +1198,7 @@ static void delete_endpoint(void *data) device_lock(parent); if (parent->driver && !endpoint->dead) { + devm_release_action(parent, cxl_unlink_parent_dport, endpoint); devm_release_action(parent, cxl_unlink_uport, endpoint); devm_release_action(parent, unregister_port, endpoint); } @@ -1179,6 +1214,7 @@ int cxl_endpoint_autoremove(struct cxl_memdev *cxlmd, struct cxl_port *endpoint) get_device(&endpoint->dev); dev_set_drvdata(dev, endpoint); + cxlmd->depth = endpoint->depth; return devm_add_action_or_reset(dev, delete_endpoint, cxlmd); } EXPORT_SYMBOL_NS_GPL(cxl_endpoint_autoremove, CXL); @@ -1194,6 +1230,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_endpoint_autoremove, CXL); */ static void delete_switch_port(struct cxl_port *port) { + devm_release_action(port->dev.parent, cxl_unlink_parent_dport, port); devm_release_action(port->dev.parent, cxl_unlink_uport, port); devm_release_action(port->dev.parent, unregister_port, port); } @@ -1212,50 +1249,55 @@ static void reap_dports(struct cxl_port *port) } } +struct detach_ctx { + struct cxl_memdev *cxlmd; + int depth; +}; + +static int port_has_memdev(struct device *dev, const void *data) +{ + const struct detach_ctx *ctx = data; + struct cxl_port *port; + + if (!is_cxl_port(dev)) + return 0; + + port = to_cxl_port(dev); + if (port->depth != ctx->depth) + return 0; + + return !!cxl_ep_load(port, ctx->cxlmd); +} + static void cxl_detach_ep(void *data) { struct cxl_memdev *cxlmd = data; - struct device *iter; - for (iter = &cxlmd->dev; iter; iter = grandparent(iter)) { - struct device *dport_dev = grandparent(iter); + for (int i = cxlmd->depth - 1; i >= 1; i--) { struct cxl_port *port, *parent_port; + struct detach_ctx ctx = { + .cxlmd = cxlmd, + .depth = i, + }; + struct device *dev; struct cxl_ep *ep; bool died = false; - if (!dport_dev) - break; - - port = find_cxl_port(dport_dev, NULL); - if (!port) + dev = bus_find_device(&cxl_bus_type, NULL, &ctx, + port_has_memdev); + if (!dev) continue; - - if (is_cxl_root(port)) { - put_device(&port->dev); - continue; - } + port = to_cxl_port(dev); parent_port = to_cxl_port(port->dev.parent); device_lock(&parent_port->dev); - if (!parent_port->dev.driver) { - /* - * The bottom-up race to delete the port lost to a - * top-down port disable, give up here, because the - * parent_port ->remove() will have cleaned up all - * descendants. - */ - device_unlock(&parent_port->dev); - put_device(&port->dev); - continue; - } - device_lock(&port->dev); ep = cxl_ep_load(port, cxlmd); dev_dbg(&cxlmd->dev, "disconnect %s from %s\n", ep ? dev_name(ep->ep) : "", dev_name(&port->dev)); cxl_ep_remove(port, ep); if (ep && !port->dead && xa_empty(&port->endpoints) && - !is_cxl_root(parent_port)) { + !is_cxl_root(parent_port) && parent_port->dev.driver) { /* * This was the last ep attached to a dynamically * enumerated port. Block new cxl_add_ep() and garbage @@ -1591,6 +1633,7 @@ struct cxl_root_decoder *cxl_root_decoder_alloc(struct cxl_port *port, } cxlrd->calc_hb = calc_hb; + mutex_init(&cxlrd->range_lock); cxld = &cxlsd->cxld; cxld->dev.type = &cxl_decoder_root_type; @@ -1974,6 +2017,6 @@ static void cxl_core_exit(void) debugfs_remove_recursive(cxl_debugfs); } -module_init(cxl_core_init); +subsys_initcall(cxl_core_init); module_exit(cxl_core_exit); MODULE_LICENSE("GPL v2"); diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index 940f805b1534..f29028148806 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -6,6 +6,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/uuid.h> +#include <linux/sort.h> #include <linux/idr.h> #include <cxlmem.h> #include <cxl.h> @@ -45,7 +46,10 @@ static ssize_t uuid_show(struct device *dev, struct device_attribute *attr, rc = down_read_interruptible(&cxl_region_rwsem); if (rc) return rc; - rc = sysfs_emit(buf, "%pUb\n", &p->uuid); + if (cxlr->mode != CXL_DECODER_PMEM) + rc = sysfs_emit(buf, "\n"); + else + rc = sysfs_emit(buf, "%pUb\n", &p->uuid); up_read(&cxl_region_rwsem); return rc; @@ -157,6 +161,22 @@ static int cxl_region_decode_reset(struct cxl_region *cxlr, int count) return 0; } +static int commit_decoder(struct cxl_decoder *cxld) +{ + struct cxl_switch_decoder *cxlsd = NULL; + + if (cxld->commit) + return cxld->commit(cxld); + + if (is_switch_decoder(&cxld->dev)) + cxlsd = to_cxl_switch_decoder(&cxld->dev); + + if (dev_WARN_ONCE(&cxld->dev, !cxlsd || cxlsd->nr_targets > 1, + "->commit() is required\n")) + return -ENXIO; + return 0; +} + static int cxl_region_decode_commit(struct cxl_region *cxlr) { struct cxl_region_params *p = &cxlr->params; @@ -175,8 +195,7 @@ static int cxl_region_decode_commit(struct cxl_region *cxlr) iter = to_cxl_port(iter->dev.parent)) { cxl_rr = cxl_rr_load(iter, cxlr); cxld = cxl_rr->decoder; - if (cxld->commit) - rc = cxld->commit(cxld); + rc = commit_decoder(cxld); if (rc) break; } @@ -287,8 +306,12 @@ static umode_t cxl_region_visible(struct kobject *kobj, struct attribute *a, struct device *dev = kobj_to_dev(kobj); struct cxl_region *cxlr = to_cxl_region(dev); + /* + * Support tooling that expects to find a 'uuid' attribute for all + * regions regardless of mode. + */ if (a == &dev_attr_uuid.attr && cxlr->mode != CXL_DECODER_PMEM) - return 0; + return 0444; return a->mode; } @@ -401,7 +424,7 @@ static ssize_t interleave_granularity_store(struct device *dev, * When the host-bridge is interleaved, disallow region granularity != * root granularity. Regions with a granularity less than the root * interleave result in needing multiple endpoints to support a single - * slot in the interleave (possible to suport in the future). Regions + * slot in the interleave (possible to support in the future). Regions * with a granularity greater than the root interleave result in invalid * DPA translations (invalid to support). */ @@ -445,6 +468,15 @@ static ssize_t resource_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(resource); +static ssize_t mode_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct cxl_region *cxlr = to_cxl_region(dev); + + return sysfs_emit(buf, "%s\n", cxl_decoder_mode_name(cxlr->mode)); +} +static DEVICE_ATTR_RO(mode); + static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size) { struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent); @@ -495,7 +527,12 @@ static void cxl_region_iomem_release(struct cxl_region *cxlr) if (device_is_registered(&cxlr->dev)) lockdep_assert_held_write(&cxl_region_rwsem); if (p->res) { - remove_resource(p->res); + /* + * Autodiscovered regions may not have been able to insert their + * resource. + */ + if (p->res->parent) + remove_resource(p->res); kfree(p->res); p->res = NULL; } @@ -572,6 +609,7 @@ static struct attribute *cxl_region_attrs[] = { &dev_attr_interleave_granularity.attr, &dev_attr_resource.attr, &dev_attr_size.attr, + &dev_attr_mode.attr, NULL, }; @@ -1075,12 +1113,35 @@ static int cxl_port_setup_targets(struct cxl_port *port, return rc; } - cxld->interleave_ways = iw; - cxld->interleave_granularity = ig; - cxld->hpa_range = (struct range) { - .start = p->res->start, - .end = p->res->end, - }; + if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) { + if (cxld->interleave_ways != iw || + cxld->interleave_granularity != ig || + cxld->hpa_range.start != p->res->start || + cxld->hpa_range.end != p->res->end || + ((cxld->flags & CXL_DECODER_F_ENABLE) == 0)) { + dev_err(&cxlr->dev, + "%s:%s %s expected iw: %d ig: %d %pr\n", + dev_name(port->uport), dev_name(&port->dev), + __func__, iw, ig, p->res); + dev_err(&cxlr->dev, + "%s:%s %s got iw: %d ig: %d state: %s %#llx:%#llx\n", + dev_name(port->uport), dev_name(&port->dev), + __func__, cxld->interleave_ways, + cxld->interleave_granularity, + (cxld->flags & CXL_DECODER_F_ENABLE) ? + "enabled" : + "disabled", + cxld->hpa_range.start, cxld->hpa_range.end); + return -ENXIO; + } + } else { + cxld->interleave_ways = iw; + cxld->interleave_granularity = ig; + cxld->hpa_range = (struct range) { + .start = p->res->start, + .end = p->res->end, + }; + } dev_dbg(&cxlr->dev, "%s:%s iw: %d ig: %d\n", dev_name(port->uport), dev_name(&port->dev), iw, ig); add_target: @@ -1091,7 +1152,17 @@ add_target: dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev), pos); return -ENXIO; } - cxlsd->target[cxl_rr->nr_targets_set] = ep->dport; + if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) { + if (cxlsd->target[cxl_rr->nr_targets_set] != ep->dport) { + dev_dbg(&cxlr->dev, "%s:%s: %s expected %s at %d\n", + dev_name(port->uport), dev_name(&port->dev), + dev_name(&cxlsd->cxld.dev), + dev_name(ep->dport->dport), + cxl_rr->nr_targets_set); + return -ENXIO; + } + } else + cxlsd->target[cxl_rr->nr_targets_set] = ep->dport; inc = 1; out_target_set: cxl_rr->nr_targets_set += inc; @@ -1133,6 +1204,13 @@ static void cxl_region_teardown_targets(struct cxl_region *cxlr) struct cxl_ep *ep; int i; + /* + * In the auto-discovery case skip automatic teardown since the + * address space is already active + */ + if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) + return; + for (i = 0; i < p->nr_targets; i++) { cxled = p->targets[i]; cxlmd = cxled_to_memdev(cxled); @@ -1165,8 +1243,8 @@ static int cxl_region_setup_targets(struct cxl_region *cxlr) iter = to_cxl_port(iter->dev.parent); /* - * Descend the topology tree programming targets while - * looking for conflicts. + * Descend the topology tree programming / validating + * targets while looking for conflicts. */ for (ep = cxl_ep_load(iter, cxlmd); iter; iter = ep->next, ep = cxl_ep_load(iter, cxlmd)) { @@ -1181,29 +1259,13 @@ static int cxl_region_setup_targets(struct cxl_region *cxlr) return 0; } -static int cxl_region_attach(struct cxl_region *cxlr, - struct cxl_endpoint_decoder *cxled, int pos) +static int cxl_region_validate_position(struct cxl_region *cxlr, + struct cxl_endpoint_decoder *cxled, + int pos) { - struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent); struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); - struct cxl_port *ep_port, *root_port, *iter; struct cxl_region_params *p = &cxlr->params; - struct cxl_dport *dport; - int i, rc = -ENXIO; - - if (cxled->mode == CXL_DECODER_DEAD) { - dev_dbg(&cxlr->dev, "%s dead\n", dev_name(&cxled->cxld.dev)); - return -ENODEV; - } - - /* all full of members, or interleave config not established? */ - if (p->state > CXL_CONFIG_INTERLEAVE_ACTIVE) { - dev_dbg(&cxlr->dev, "region already active\n"); - return -EBUSY; - } else if (p->state < CXL_CONFIG_INTERLEAVE_ACTIVE) { - dev_dbg(&cxlr->dev, "interleave config missing\n"); - return -ENXIO; - } + int i; if (pos < 0 || pos >= p->interleave_ways) { dev_dbg(&cxlr->dev, "position %d out of range %d\n", pos, @@ -1242,6 +1304,256 @@ static int cxl_region_attach(struct cxl_region *cxlr, } } + return 0; +} + +static int cxl_region_attach_position(struct cxl_region *cxlr, + struct cxl_root_decoder *cxlrd, + struct cxl_endpoint_decoder *cxled, + const struct cxl_dport *dport, int pos) +{ + struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); + struct cxl_port *iter; + int rc; + + if (cxlrd->calc_hb(cxlrd, pos) != dport) { + dev_dbg(&cxlr->dev, "%s:%s invalid target position for %s\n", + dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev), + dev_name(&cxlrd->cxlsd.cxld.dev)); + return -ENXIO; + } + + for (iter = cxled_to_port(cxled); !is_cxl_root(iter); + iter = to_cxl_port(iter->dev.parent)) { + rc = cxl_port_attach_region(iter, cxlr, cxled, pos); + if (rc) + goto err; + } + + return 0; + +err: + for (iter = cxled_to_port(cxled); !is_cxl_root(iter); + iter = to_cxl_port(iter->dev.parent)) + cxl_port_detach_region(iter, cxlr, cxled); + return rc; +} + +static int cxl_region_attach_auto(struct cxl_region *cxlr, + struct cxl_endpoint_decoder *cxled, int pos) +{ + struct cxl_region_params *p = &cxlr->params; + + if (cxled->state != CXL_DECODER_STATE_AUTO) { + dev_err(&cxlr->dev, + "%s: unable to add decoder to autodetected region\n", + dev_name(&cxled->cxld.dev)); + return -EINVAL; + } + + if (pos >= 0) { + dev_dbg(&cxlr->dev, "%s: expected auto position, not %d\n", + dev_name(&cxled->cxld.dev), pos); + return -EINVAL; + } + + if (p->nr_targets >= p->interleave_ways) { + dev_err(&cxlr->dev, "%s: no more target slots available\n", + dev_name(&cxled->cxld.dev)); + return -ENXIO; + } + + /* + * Temporarily record the endpoint decoder into the target array. Yes, + * this means that userspace can view devices in the wrong position + * before the region activates, and must be careful to understand when + * it might be racing region autodiscovery. + */ + pos = p->nr_targets; + p->targets[pos] = cxled; + cxled->pos = pos; + p->nr_targets++; + + return 0; +} + +static struct cxl_port *next_port(struct cxl_port *port) +{ + if (!port->parent_dport) + return NULL; + return port->parent_dport->port; +} + +static int decoder_match_range(struct device *dev, void *data) +{ + struct cxl_endpoint_decoder *cxled = data; + struct cxl_switch_decoder *cxlsd; + + 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; + + 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; + } +} + +static int cmp_decode_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; + 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 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; + + /* + * 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; + + next_a = next_port(iter_a); + if (!next_a) + break; + + 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; + break; + } + + if (port) + break; + } + + if (!port) { + dev_err(cxlmd_a->dev.parent, + "failed to find shared port with %s\n", + dev_name(cxlmd_b->dev.parent)); + goto err; + } + + dev = device_find_child(&port->dev, cxled_a, decoder_match_range); + if (!dev) { + struct range *range = &cxled_a->cxld.hpa_range; + + dev_err(port->uport, + "failed to find decoder that maps %#llx-%#llx\n", + range->start, range->end); + goto err; + } + + 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)); + + put_device(dev); + + if (a_pos < 0 || b_pos < 0) { + dev_err(port->uport, + "failed to find shared decoder for %s and %s\n", + dev_name(cxlmd_a->dev.parent), + dev_name(cxlmd_b->dev.parent)); + goto err; + } + + dev_dbg(port->uport, "%s comes %s %s\n", dev_name(cxlmd_a->dev.parent), + a_pos - b_pos < 0 ? "before" : "after", + dev_name(cxlmd_b->dev.parent)); + + return a_pos - b_pos; +err: + cxled_a->pos = -1; + return 0; +} + +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]; + + /* + * 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. + */ + if (cxled->pos < 0) + rc = -ENXIO; + cxled->pos = i; + } + + dev_dbg(&cxlr->dev, "region sort %s\n", rc ? "failed" : "successful"); + return rc; +} + +static int cxl_region_attach(struct cxl_region *cxlr, + struct cxl_endpoint_decoder *cxled, int pos) +{ + struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent); + struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); + struct cxl_region_params *p = &cxlr->params; + struct cxl_port *ep_port, *root_port; + struct cxl_dport *dport; + int rc = -ENXIO; + + if (cxled->mode != cxlr->mode) { + dev_dbg(&cxlr->dev, "%s region mode: %d mismatch: %d\n", + dev_name(&cxled->cxld.dev), cxlr->mode, cxled->mode); + return -EINVAL; + } + + if (cxled->mode == CXL_DECODER_DEAD) { + dev_dbg(&cxlr->dev, "%s dead\n", dev_name(&cxled->cxld.dev)); + return -ENODEV; + } + + /* all full of members, or interleave config not established? */ + if (p->state > CXL_CONFIG_INTERLEAVE_ACTIVE) { + dev_dbg(&cxlr->dev, "region already active\n"); + return -EBUSY; + } else if (p->state < CXL_CONFIG_INTERLEAVE_ACTIVE) { + dev_dbg(&cxlr->dev, "interleave config missing\n"); + return -ENXIO; + } + ep_port = cxled_to_port(cxled); root_port = cxlrd_to_port(cxlrd); dport = cxl_find_dport_by_dev(root_port, ep_port->host_bridge); @@ -1252,13 +1564,6 @@ static int cxl_region_attach(struct cxl_region *cxlr, return -ENXIO; } - if (cxlrd->calc_hb(cxlrd, pos) != dport) { - dev_dbg(&cxlr->dev, "%s:%s invalid target position for %s\n", - dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev), - dev_name(&cxlrd->cxlsd.cxld.dev)); - return -ENXIO; - } - if (cxled->cxld.target_type != cxlr->type) { dev_dbg(&cxlr->dev, "%s:%s type mismatch: %d vs %d\n", dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev), @@ -1282,13 +1587,58 @@ static int cxl_region_attach(struct cxl_region *cxlr, return -EINVAL; } - for (iter = ep_port; !is_cxl_root(iter); - iter = to_cxl_port(iter->dev.parent)) { - rc = cxl_port_attach_region(iter, cxlr, cxled, pos); + if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) { + int i; + + rc = cxl_region_attach_auto(cxlr, cxled, pos); if (rc) - goto err; + return rc; + + /* await more targets to arrive... */ + if (p->nr_targets < p->interleave_ways) + return 0; + + /* + * All targets are here, which implies all PCI enumeration that + * affects this region has been completed. Walk the topology to + * sort the devices into their relative region decode position. + */ + rc = cxl_region_sort_targets(cxlr); + if (rc) + return rc; + + for (i = 0; i < p->nr_targets; i++) { + cxled = p->targets[i]; + ep_port = cxled_to_port(cxled); + dport = cxl_find_dport_by_dev(root_port, + ep_port->host_bridge); + rc = cxl_region_attach_position(cxlr, cxlrd, cxled, + dport, i); + if (rc) + return rc; + } + + rc = cxl_region_setup_targets(cxlr); + if (rc) + return rc; + + /* + * If target setup succeeds in the autodiscovery case + * then the region is already committed. + */ + p->state = CXL_CONFIG_COMMIT; + + return 0; } + rc = cxl_region_validate_position(cxlr, cxled, pos); + if (rc) + return rc; + + rc = cxl_region_attach_position(cxlr, cxlrd, cxled, dport, pos); + if (rc) + return rc; + p->targets[pos] = cxled; cxled->pos = pos; p->nr_targets++; @@ -1311,10 +1661,8 @@ static int cxl_region_attach(struct cxl_region *cxlr, err_decrement: p->nr_targets--; -err: - for (iter = ep_port; !is_cxl_root(iter); - iter = to_cxl_port(iter->dev.parent)) - cxl_port_detach_region(iter, cxlr, cxled); + cxled->pos = -1; + p->targets[pos] = NULL; return rc; } @@ -1386,31 +1734,25 @@ void cxl_decoder_kill_region(struct cxl_endpoint_decoder *cxled) up_write(&cxl_region_rwsem); } -static int attach_target(struct cxl_region *cxlr, const char *decoder, int pos) +static int attach_target(struct cxl_region *cxlr, + struct cxl_endpoint_decoder *cxled, int pos, + unsigned int state) { - struct device *dev; - int rc; - - dev = bus_find_device_by_name(&cxl_bus_type, NULL, decoder); - if (!dev) - return -ENODEV; - - if (!is_endpoint_decoder(dev)) { - put_device(dev); - return -EINVAL; - } + int rc = 0; - rc = down_write_killable(&cxl_region_rwsem); + if (state == TASK_INTERRUPTIBLE) + rc = down_write_killable(&cxl_region_rwsem); + else + down_write(&cxl_region_rwsem); if (rc) - goto out; + return rc; + down_read(&cxl_dpa_rwsem); - rc = cxl_region_attach(cxlr, to_cxl_endpoint_decoder(dev), pos); + rc = cxl_region_attach(cxlr, cxled, pos); if (rc == 0) set_bit(CXL_REGION_F_INCOHERENT, &cxlr->flags); up_read(&cxl_dpa_rwsem); up_write(&cxl_region_rwsem); -out: - put_device(dev); return rc; } @@ -1448,8 +1790,23 @@ static size_t store_targetN(struct cxl_region *cxlr, const char *buf, int pos, if (sysfs_streq(buf, "\n")) rc = detach_target(cxlr, pos); - else - rc = attach_target(cxlr, buf, pos); + else { + struct device *dev; + + dev = bus_find_device_by_name(&cxl_bus_type, NULL, buf); + if (!dev) + return -ENODEV; + + if (!is_endpoint_decoder(dev)) { + rc = -EINVAL; + goto out; + } + + rc = attach_target(cxlr, to_cxl_endpoint_decoder(dev), pos, + TASK_INTERRUPTIBLE); +out: + put_device(dev); + } if (rc < 0) return rc; @@ -1653,6 +2010,15 @@ static struct cxl_region *devm_cxl_add_region(struct cxl_root_decoder *cxlrd, struct device *dev; int rc; + switch (mode) { + case CXL_DECODER_RAM: + case CXL_DECODER_PMEM: + break; + default: + dev_err(&cxlrd->cxlsd.cxld.dev, "unsupported mode %d\n", mode); + return ERR_PTR(-EINVAL); + } + cxlr = cxl_region_alloc(cxlrd, id); if (IS_ERR(cxlr)) return cxlr; @@ -1681,12 +2047,38 @@ err: return ERR_PTR(rc); } +static ssize_t __create_region_show(struct cxl_root_decoder *cxlrd, char *buf) +{ + return sysfs_emit(buf, "region%u\n", atomic_read(&cxlrd->region_id)); +} + static ssize_t create_pmem_region_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(dev); + return __create_region_show(to_cxl_root_decoder(dev), buf); +} - return sysfs_emit(buf, "region%u\n", atomic_read(&cxlrd->region_id)); +static ssize_t create_ram_region_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return __create_region_show(to_cxl_root_decoder(dev), buf); +} + +static struct cxl_region *__create_region(struct cxl_root_decoder *cxlrd, + enum cxl_decoder_mode mode, int id) +{ + int rc; + + rc = memregion_alloc(GFP_KERNEL); + if (rc < 0) + return ERR_PTR(rc); + + if (atomic_cmpxchg(&cxlrd->region_id, id, rc) != id) { + memregion_free(rc); + return ERR_PTR(-EBUSY); + } + + return devm_cxl_add_region(cxlrd, id, mode, CXL_DECODER_EXPANDER); } static ssize_t create_pmem_region_store(struct device *dev, @@ -1695,29 +2087,39 @@ static ssize_t create_pmem_region_store(struct device *dev, { struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(dev); struct cxl_region *cxlr; - int id, rc; + int rc, id; rc = sscanf(buf, "region%d\n", &id); if (rc != 1) return -EINVAL; - rc = memregion_alloc(GFP_KERNEL); - if (rc < 0) - return rc; + cxlr = __create_region(cxlrd, CXL_DECODER_PMEM, id); + if (IS_ERR(cxlr)) + return PTR_ERR(cxlr); - if (atomic_cmpxchg(&cxlrd->region_id, id, rc) != id) { - memregion_free(rc); - return -EBUSY; - } + return len; +} +DEVICE_ATTR_RW(create_pmem_region); + +static ssize_t create_ram_region_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(dev); + struct cxl_region *cxlr; + int rc, id; + + rc = sscanf(buf, "region%d\n", &id); + if (rc != 1) + return -EINVAL; - cxlr = devm_cxl_add_region(cxlrd, id, CXL_DECODER_PMEM, - CXL_DECODER_EXPANDER); + cxlr = __create_region(cxlrd, CXL_DECODER_RAM, id); if (IS_ERR(cxlr)) return PTR_ERR(cxlr); return len; } -DEVICE_ATTR_RW(create_pmem_region); +DEVICE_ATTR_RW(create_ram_region); static ssize_t region_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -1878,6 +2280,75 @@ out: return cxlr_pmem; } +static void cxl_dax_region_release(struct device *dev) +{ + struct cxl_dax_region *cxlr_dax = to_cxl_dax_region(dev); + + kfree(cxlr_dax); +} + +static const struct attribute_group *cxl_dax_region_attribute_groups[] = { + &cxl_base_attribute_group, + NULL, +}; + +const struct device_type cxl_dax_region_type = { + .name = "cxl_dax_region", + .release = cxl_dax_region_release, + .groups = cxl_dax_region_attribute_groups, +}; + +static bool is_cxl_dax_region(struct device *dev) +{ + return dev->type == &cxl_dax_region_type; +} + +struct cxl_dax_region *to_cxl_dax_region(struct device *dev) +{ + if (dev_WARN_ONCE(dev, !is_cxl_dax_region(dev), + "not a cxl_dax_region device\n")) + return NULL; + return container_of(dev, struct cxl_dax_region, dev); +} +EXPORT_SYMBOL_NS_GPL(to_cxl_dax_region, CXL); + +static struct lock_class_key cxl_dax_region_key; + +static struct cxl_dax_region *cxl_dax_region_alloc(struct cxl_region *cxlr) +{ + struct cxl_region_params *p = &cxlr->params; + struct cxl_dax_region *cxlr_dax; + struct device *dev; + + down_read(&cxl_region_rwsem); + if (p->state != CXL_CONFIG_COMMIT) { + cxlr_dax = ERR_PTR(-ENXIO); + goto out; + } + + cxlr_dax = kzalloc(sizeof(*cxlr_dax), GFP_KERNEL); + if (!cxlr_dax) { + cxlr_dax = ERR_PTR(-ENOMEM); + goto out; + } + + cxlr_dax->hpa_range.start = p->res->start; + cxlr_dax->hpa_range.end = p->res->end; + + dev = &cxlr_dax->dev; + cxlr_dax->cxlr = cxlr; + device_initialize(dev); + lockdep_set_class(&dev->mutex, &cxl_dax_region_key); + device_set_pm_not_required(dev); + dev->parent = &cxlr->dev; + dev->bus = &cxl_bus_type; + dev->type = &cxl_dax_region_type; +out: + up_read(&cxl_region_rwsem); + + return cxlr_dax; +} + static void cxlr_pmem_unregister(void *_cxlr_pmem) { struct cxl_pmem_region *cxlr_pmem = _cxlr_pmem; @@ -1962,6 +2433,227 @@ err_bridge: return rc; } +static void cxlr_dax_unregister(void *_cxlr_dax) +{ + struct cxl_dax_region *cxlr_dax = _cxlr_dax; + + device_unregister(&cxlr_dax->dev); +} + +static int devm_cxl_add_dax_region(struct cxl_region *cxlr) +{ + struct cxl_dax_region *cxlr_dax; + struct device *dev; + int rc; + + cxlr_dax = cxl_dax_region_alloc(cxlr); + if (IS_ERR(cxlr_dax)) + return PTR_ERR(cxlr_dax); + + dev = &cxlr_dax->dev; + rc = dev_set_name(dev, "dax_region%d", cxlr->id); + if (rc) + goto err; + + rc = device_add(dev); + if (rc) + goto err; + + dev_dbg(&cxlr->dev, "%s: register %s\n", dev_name(dev->parent), + dev_name(dev)); + + return devm_add_action_or_reset(&cxlr->dev, cxlr_dax_unregister, + cxlr_dax); +err: + put_device(dev); + return rc; +} + +static int match_decoder_by_range(struct device *dev, void *data) +{ + struct range *r1, *r2 = data; + struct cxl_root_decoder *cxlrd; + + if (!is_root_decoder(dev)) + return 0; + + cxlrd = to_cxl_root_decoder(dev); + r1 = &cxlrd->cxlsd.cxld.hpa_range; + return range_contains(r1, r2); +} + +static int match_region_by_range(struct device *dev, void *data) +{ + struct cxl_region_params *p; + struct cxl_region *cxlr; + struct range *r = data; + int rc = 0; + + if (!is_cxl_region(dev)) + return 0; + + cxlr = to_cxl_region(dev); + p = &cxlr->params; + + down_read(&cxl_region_rwsem); + if (p->res && p->res->start == r->start && p->res->end == r->end) + rc = 1; + up_read(&cxl_region_rwsem); + + return rc; +} + +/* Establish an empty region covering the given HPA range */ +static struct cxl_region *construct_region(struct cxl_root_decoder *cxlrd, + struct cxl_endpoint_decoder *cxled) +{ + struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); + struct cxl_port *port = cxlrd_to_port(cxlrd); + struct range *hpa = &cxled->cxld.hpa_range; + struct cxl_region_params *p; + struct cxl_region *cxlr; + struct resource *res; + int rc; + + do { + cxlr = __create_region(cxlrd, cxled->mode, + atomic_read(&cxlrd->region_id)); + } while (IS_ERR(cxlr) && PTR_ERR(cxlr) == -EBUSY); + + if (IS_ERR(cxlr)) { + dev_err(cxlmd->dev.parent, + "%s:%s: %s failed assign region: %ld\n", + dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev), + __func__, PTR_ERR(cxlr)); + return cxlr; + } + + down_write(&cxl_region_rwsem); + p = &cxlr->params; + if (p->state >= CXL_CONFIG_INTERLEAVE_ACTIVE) { + dev_err(cxlmd->dev.parent, + "%s:%s: %s autodiscovery interrupted\n", + dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev), + __func__); + rc = -EBUSY; + goto err; + } + + set_bit(CXL_REGION_F_AUTO, &cxlr->flags); + + res = kmalloc(sizeof(*res), GFP_KERNEL); + if (!res) { + rc = -ENOMEM; + goto err; + } + + *res = DEFINE_RES_MEM_NAMED(hpa->start, range_len(hpa), + dev_name(&cxlr->dev)); + rc = insert_resource(cxlrd->res, res); + if (rc) { + /* + * Platform-firmware may not have split resources like "System + * RAM" on CXL window boundaries see cxl_region_iomem_release() + */ + dev_warn(cxlmd->dev.parent, + "%s:%s: %s %s cannot insert resource\n", + dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev), + __func__, dev_name(&cxlr->dev)); + } + + p->res = res; + p->interleave_ways = cxled->cxld.interleave_ways; + p->interleave_granularity = cxled->cxld.interleave_granularity; + p->state = CXL_CONFIG_INTERLEAVE_ACTIVE; + + rc = sysfs_update_group(&cxlr->dev.kobj, get_cxl_region_target_group()); + if (rc) + goto err; + + dev_dbg(cxlmd->dev.parent, "%s:%s: %s %s res: %pr iw: %d ig: %d\n", + dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev), __func__, + dev_name(&cxlr->dev), p->res, p->interleave_ways, + p->interleave_granularity); + + /* ...to match put_device() in cxl_add_to_region() */ + get_device(&cxlr->dev); + up_write(&cxl_region_rwsem); + + return cxlr; + +err: + up_write(&cxl_region_rwsem); + devm_release_action(port->uport, unregister_region, cxlr); + return ERR_PTR(rc); +} + +int cxl_add_to_region(struct cxl_port *root, struct cxl_endpoint_decoder *cxled) +{ + struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); + struct range *hpa = &cxled->cxld.hpa_range; + struct cxl_decoder *cxld = &cxled->cxld; + struct device *cxlrd_dev, *region_dev; + struct cxl_root_decoder *cxlrd; + struct cxl_region_params *p; + struct cxl_region *cxlr; + bool attach = false; + int rc; + + cxlrd_dev = device_find_child(&root->dev, &cxld->hpa_range, + match_decoder_by_range); + if (!cxlrd_dev) { + dev_err(cxlmd->dev.parent, + "%s:%s no CXL window for range %#llx:%#llx\n", + dev_name(&cxlmd->dev), dev_name(&cxld->dev), + cxld->hpa_range.start, cxld->hpa_range.end); + return -ENXIO; + } + + cxlrd = to_cxl_root_decoder(cxlrd_dev); + + /* + * Ensure that if multiple threads race to construct_region() for @hpa + * one does the construction and the others add to that. + */ + mutex_lock(&cxlrd->range_lock); + region_dev = device_find_child(&cxlrd->cxlsd.cxld.dev, hpa, + match_region_by_range); + if (!region_dev) { + cxlr = construct_region(cxlrd, cxled); + region_dev = &cxlr->dev; + } else + cxlr = to_cxl_region(region_dev); + mutex_unlock(&cxlrd->range_lock); + + rc = PTR_ERR_OR_ZERO(cxlr); + if (rc) + goto out; + + attach_target(cxlr, cxled, -1, TASK_UNINTERRUPTIBLE); + + down_read(&cxl_region_rwsem); + p = &cxlr->params; + attach = p->state == CXL_CONFIG_COMMIT; + up_read(&cxl_region_rwsem); + + if (attach) { + /* + * If device_attach() fails the range may still be active via + * the platform-firmware memory map, otherwise the driver for + * regions is local to this file, so driver matching can't fail. + */ + if (device_attach(&cxlr->dev) < 0) + dev_err(&cxlr->dev, "failed to enable, range: %pr\n", + p->res); + } + + put_device(region_dev); +out: + put_device(cxlrd_dev); + return rc; +} +EXPORT_SYMBOL_NS_GPL(cxl_add_to_region, CXL); + static int cxl_region_invalidate_memregion(struct cxl_region *cxlr) { if (!test_bit(CXL_REGION_F_INCOHERENT, &cxlr->flags)) @@ -1969,7 +2661,7 @@ static int cxl_region_invalidate_memregion(struct cxl_region *cxlr) if (!cpu_cache_has_invalidate_memregion()) { if (IS_ENABLED(CONFIG_CXL_REGION_INVALIDATION_TEST)) { - dev_warn( + dev_warn_once( &cxlr->dev, "Bypassing cpu_cache_invalidate_memregion() for testing!\n"); clear_bit(CXL_REGION_F_INCOHERENT, &cxlr->flags); @@ -1986,6 +2678,15 @@ static int cxl_region_invalidate_memregion(struct cxl_region *cxlr) return 0; } +static int is_system_ram(struct resource *res, void *arg) +{ + struct cxl_region *cxlr = arg; + struct cxl_region_params *p = &cxlr->params; + + dev_dbg(&cxlr->dev, "%pr has System RAM: %pr\n", p->res, res); + return 1; +} + static int cxl_region_probe(struct device *dev) { struct cxl_region *cxlr = to_cxl_region(dev); @@ -2019,6 +2720,17 @@ out: switch (cxlr->mode) { case CXL_DECODER_PMEM: return devm_cxl_add_pmem_region(cxlr); + case CXL_DECODER_RAM: + /* + * The region can not be manged by CXL if any portion of + * it is already online as 'System RAM' + */ + if (walk_iomem_res_desc(IORES_DESC_NONE, + IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY, + p->res->start, p->res->end, cxlr, + is_system_ram) > 0) + return 0; + return devm_cxl_add_dax_region(cxlr); default: dev_dbg(&cxlr->dev, "unsupported region mode: %d\n", cxlr->mode); diff --git a/drivers/cxl/core/trace.c b/drivers/cxl/core/trace.c new file mode 100644 index 000000000000..29ae7ce81dc5 --- /dev/null +++ b/drivers/cxl/core/trace.c @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2022 Intel Corporation. All rights reserved. */ + +#define CREATE_TRACE_POINTS +#include "trace.h" diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h new file mode 100644 index 000000000000..9b8d3d997834 --- /dev/null +++ b/drivers/cxl/core/trace.h @@ -0,0 +1,606 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2022 Intel Corporation. All rights reserved. */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM cxl + +#if !defined(_CXL_EVENTS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _CXL_EVENTS_H + +#include <linux/tracepoint.h> +#include <asm-generic/unaligned.h> + +#include <cxl.h> +#include <cxlmem.h> + +#define CXL_RAS_UC_CACHE_DATA_PARITY BIT(0) +#define CXL_RAS_UC_CACHE_ADDR_PARITY BIT(1) +#define CXL_RAS_UC_CACHE_BE_PARITY BIT(2) +#define CXL_RAS_UC_CACHE_DATA_ECC BIT(3) +#define CXL_RAS_UC_MEM_DATA_PARITY BIT(4) +#define CXL_RAS_UC_MEM_ADDR_PARITY BIT(5) +#define CXL_RAS_UC_MEM_BE_PARITY BIT(6) +#define CXL_RAS_UC_MEM_DATA_ECC BIT(7) +#define CXL_RAS_UC_REINIT_THRESH BIT(8) +#define CXL_RAS_UC_RSVD_ENCODE BIT(9) +#define CXL_RAS_UC_POISON BIT(10) +#define CXL_RAS_UC_RECV_OVERFLOW BIT(11) +#define CXL_RAS_UC_INTERNAL_ERR BIT(14) +#define CXL_RAS_UC_IDE_TX_ERR BIT(15) +#define CXL_RAS_UC_IDE_RX_ERR BIT(16) + +#define show_uc_errs(status) __print_flags(status, " | ", \ + { CXL_RAS_UC_CACHE_DATA_PARITY, "Cache Data Parity Error" }, \ + { CXL_RAS_UC_CACHE_ADDR_PARITY, "Cache Address Parity Error" }, \ + { CXL_RAS_UC_CACHE_BE_PARITY, "Cache Byte Enable Parity Error" }, \ + { CXL_RAS_UC_CACHE_DATA_ECC, "Cache Data ECC Error" }, \ + { CXL_RAS_UC_MEM_DATA_PARITY, "Memory Data Parity Error" }, \ + { CXL_RAS_UC_MEM_ADDR_PARITY, "Memory Address Parity Error" }, \ + { CXL_RAS_UC_MEM_BE_PARITY, "Memory Byte Enable Parity Error" }, \ + { CXL_RAS_UC_MEM_DATA_ECC, "Memory Data ECC Error" }, \ + { CXL_RAS_UC_REINIT_THRESH, "REINIT Threshold Hit" }, \ + { CXL_RAS_UC_RSVD_ENCODE, "Received Unrecognized Encoding" }, \ + { CXL_RAS_UC_POISON, "Received Poison From Peer" }, \ + { CXL_RAS_UC_RECV_OVERFLOW, "Receiver Overflow" }, \ + { CXL_RAS_UC_INTERNAL_ERR, "Component Specific Error" }, \ + { CXL_RAS_UC_IDE_TX_ERR, "IDE Tx Error" }, \ + { CXL_RAS_UC_IDE_RX_ERR, "IDE Rx Error" } \ +) + +TRACE_EVENT(cxl_aer_uncorrectable_error, + TP_PROTO(const struct cxl_memdev *cxlmd, u32 status, u32 fe, u32 *hl), + TP_ARGS(cxlmd, status, fe, hl), + TP_STRUCT__entry( + __string(memdev, dev_name(&cxlmd->dev)) + __string(host, dev_name(cxlmd->dev.parent)) + __field(u64, serial) + __field(u32, status) + __field(u32, first_error) + __array(u32, header_log, CXL_HEADERLOG_SIZE_U32) + ), + TP_fast_assign( + __assign_str(memdev, dev_name(&cxlmd->dev)); + __assign_str(host, dev_name(cxlmd->dev.parent)); + __entry->serial = cxlmd->cxlds->serial; + __entry->status = status; + __entry->first_error = fe; + /* + * Embed the 512B headerlog data for user app retrieval and + * parsing, but no need to print this in the trace buffer. + */ + memcpy(__entry->header_log, hl, CXL_HEADERLOG_SIZE); + ), + TP_printk("memdev=%s host=%s serial=%lld: status: '%s' first_error: '%s'", + __get_str(memdev), __get_str(host), __entry->serial, + show_uc_errs(__entry->status), + show_uc_errs(__entry->first_error) + ) +); + +#define CXL_RAS_CE_CACHE_DATA_ECC BIT(0) +#define CXL_RAS_CE_MEM_DATA_ECC BIT(1) +#define CXL_RAS_CE_CRC_THRESH BIT(2) +#define CLX_RAS_CE_RETRY_THRESH BIT(3) +#define CXL_RAS_CE_CACHE_POISON BIT(4) +#define CXL_RAS_CE_MEM_POISON BIT(5) +#define CXL_RAS_CE_PHYS_LAYER_ERR BIT(6) + +#define show_ce_errs(status) __print_flags(status, " | ", \ + { CXL_RAS_CE_CACHE_DATA_ECC, "Cache Data ECC Error" }, \ + { CXL_RAS_CE_MEM_DATA_ECC, "Memory Data ECC Error" }, \ + { CXL_RAS_CE_CRC_THRESH, "CRC Threshold Hit" }, \ + { CLX_RAS_CE_RETRY_THRESH, "Retry Threshold" }, \ + { CXL_RAS_CE_CACHE_POISON, "Received Cache Poison From Peer" }, \ + { CXL_RAS_CE_MEM_POISON, "Received Memory Poison From Peer" }, \ + { CXL_RAS_CE_PHYS_LAYER_ERR, "Received Error From Physical Layer" } \ +) + +TRACE_EVENT(cxl_aer_correctable_error, + TP_PROTO(const struct cxl_memdev *cxlmd, u32 status), + TP_ARGS(cxlmd, status), + TP_STRUCT__entry( + __string(memdev, dev_name(&cxlmd->dev)) + __string(host, dev_name(cxlmd->dev.parent)) + __field(u64, serial) + __field(u32, status) + ), + TP_fast_assign( + __assign_str(memdev, dev_name(&cxlmd->dev)); + __assign_str(host, dev_name(cxlmd->dev.parent)); + __entry->serial = cxlmd->cxlds->serial; + __entry->status = status; + ), + TP_printk("memdev=%s host=%s serial=%lld: status: '%s'", + __get_str(memdev), __get_str(host), __entry->serial, + show_ce_errs(__entry->status) + ) +); + +#define cxl_event_log_type_str(type) \ + __print_symbolic(type, \ + { CXL_EVENT_TYPE_INFO, "Informational" }, \ + { CXL_EVENT_TYPE_WARN, "Warning" }, \ + { CXL_EVENT_TYPE_FAIL, "Failure" }, \ + { CXL_EVENT_TYPE_FATAL, "Fatal" }) + +TRACE_EVENT(cxl_overflow, + + TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log, + struct cxl_get_event_payload *payload), + + TP_ARGS(cxlmd, log, payload), + + TP_STRUCT__entry( + __string(memdev, dev_name(&cxlmd->dev)) + __string(host, dev_name(cxlmd->dev.parent)) + __field(int, log) + __field(u64, serial) + __field(u64, first_ts) + __field(u64, last_ts) + __field(u16, count) + ), + + TP_fast_assign( + __assign_str(memdev, dev_name(&cxlmd->dev)); + __assign_str(host, dev_name(cxlmd->dev.parent)); + __entry->serial = cxlmd->cxlds->serial; + __entry->log = log; + __entry->count = le16_to_cpu(payload->overflow_err_count); + __entry->first_ts = le64_to_cpu(payload->first_overflow_timestamp); + __entry->last_ts = le64_to_cpu(payload->last_overflow_timestamp); + ), + + TP_printk("memdev=%s host=%s serial=%lld: log=%s : %u records from %llu to %llu", + __get_str(memdev), __get_str(host), __entry->serial, + cxl_event_log_type_str(__entry->log), __entry->count, + __entry->first_ts, __entry->last_ts) + +); + +/* + * Common Event Record Format + * CXL 3.0 section 8.2.9.2.1; Table 8-42 + */ +#define CXL_EVENT_RECORD_FLAG_PERMANENT BIT(2) +#define CXL_EVENT_RECORD_FLAG_MAINT_NEEDED BIT(3) +#define CXL_EVENT_RECORD_FLAG_PERF_DEGRADED BIT(4) +#define CXL_EVENT_RECORD_FLAG_HW_REPLACE BIT(5) +#define show_hdr_flags(flags) __print_flags(flags, " | ", \ + { CXL_EVENT_RECORD_FLAG_PERMANENT, "PERMANENT_CONDITION" }, \ + { CXL_EVENT_RECORD_FLAG_MAINT_NEEDED, "MAINTENANCE_NEEDED" }, \ + { CXL_EVENT_RECORD_FLAG_PERF_DEGRADED, "PERFORMANCE_DEGRADED" }, \ + { CXL_EVENT_RECORD_FLAG_HW_REPLACE, "HARDWARE_REPLACEMENT_NEEDED" } \ +) + +/* + * Define macros for the common header of each CXL event. + * + * Tracepoints using these macros must do 3 things: + * + * 1) Add CXL_EVT_TP_entry to TP_STRUCT__entry + * 2) Use CXL_EVT_TP_fast_assign within TP_fast_assign; + * pass the dev, log, and CXL event header + * 3) Use CXL_EVT_TP_printk() instead of TP_printk() + * + * See the generic_event tracepoint as an example. + */ +#define CXL_EVT_TP_entry \ + __string(memdev, dev_name(&cxlmd->dev)) \ + __string(host, dev_name(cxlmd->dev.parent)) \ + __field(int, log) \ + __field_struct(uuid_t, hdr_uuid) \ + __field(u64, serial) \ + __field(u32, hdr_flags) \ + __field(u16, hdr_handle) \ + __field(u16, hdr_related_handle) \ + __field(u64, hdr_timestamp) \ + __field(u8, hdr_length) \ + __field(u8, hdr_maint_op_class) + +#define CXL_EVT_TP_fast_assign(cxlmd, l, hdr) \ + __assign_str(memdev, dev_name(&(cxlmd)->dev)); \ + __assign_str(host, dev_name((cxlmd)->dev.parent)); \ + __entry->log = (l); \ + __entry->serial = (cxlmd)->cxlds->serial; \ + memcpy(&__entry->hdr_uuid, &(hdr).id, sizeof(uuid_t)); \ + __entry->hdr_length = (hdr).length; \ + __entry->hdr_flags = get_unaligned_le24((hdr).flags); \ + __entry->hdr_handle = le16_to_cpu((hdr).handle); \ + __entry->hdr_related_handle = le16_to_cpu((hdr).related_handle); \ + __entry->hdr_timestamp = le64_to_cpu((hdr).timestamp); \ + __entry->hdr_maint_op_class = (hdr).maint_op_class + +#define CXL_EVT_TP_printk(fmt, ...) \ + TP_printk("memdev=%s host=%s serial=%lld log=%s : time=%llu uuid=%pUb " \ + "len=%d flags='%s' handle=%x related_handle=%x " \ + "maint_op_class=%u : " fmt, \ + __get_str(memdev), __get_str(host), __entry->serial, \ + cxl_event_log_type_str(__entry->log), \ + __entry->hdr_timestamp, &__entry->hdr_uuid, __entry->hdr_length,\ + show_hdr_flags(__entry->hdr_flags), __entry->hdr_handle, \ + __entry->hdr_related_handle, __entry->hdr_maint_op_class, \ + ##__VA_ARGS__) + +TRACE_EVENT(cxl_generic_event, + + TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log, + struct cxl_event_record_raw *rec), + + TP_ARGS(cxlmd, log, rec), + + TP_STRUCT__entry( + CXL_EVT_TP_entry + __array(u8, data, CXL_EVENT_RECORD_DATA_LENGTH) + ), + + TP_fast_assign( + CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr); + memcpy(__entry->data, &rec->data, CXL_EVENT_RECORD_DATA_LENGTH); + ), + + CXL_EVT_TP_printk("%s", + __print_hex(__entry->data, CXL_EVENT_RECORD_DATA_LENGTH)) +); + +/* + * Physical Address field masks + * + * General Media Event Record + * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43 + * + * DRAM Event Record + * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44 + */ +#define CXL_DPA_FLAGS_MASK 0x3F +#define CXL_DPA_MASK (~CXL_DPA_FLAGS_MASK) + +#define CXL_DPA_VOLATILE BIT(0) +#define CXL_DPA_NOT_REPAIRABLE BIT(1) +#define show_dpa_flags(flags) __print_flags(flags, "|", \ + { CXL_DPA_VOLATILE, "VOLATILE" }, \ + { CXL_DPA_NOT_REPAIRABLE, "NOT_REPAIRABLE" } \ +) + +/* + * General Media Event Record - GMER + * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43 + */ +#define CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT BIT(0) +#define CXL_GMER_EVT_DESC_THRESHOLD_EVENT BIT(1) +#define CXL_GMER_EVT_DESC_POISON_LIST_OVERFLOW BIT(2) +#define show_event_desc_flags(flags) __print_flags(flags, "|", \ + { CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT, "UNCORRECTABLE_EVENT" }, \ + { CXL_GMER_EVT_DESC_THRESHOLD_EVENT, "THRESHOLD_EVENT" }, \ + { CXL_GMER_EVT_DESC_POISON_LIST_OVERFLOW, "POISON_LIST_OVERFLOW" } \ +) + +#define CXL_GMER_MEM_EVT_TYPE_ECC_ERROR 0x00 +#define CXL_GMER_MEM_EVT_TYPE_INV_ADDR 0x01 +#define CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR 0x02 +#define show_mem_event_type(type) __print_symbolic(type, \ + { CXL_GMER_MEM_EVT_TYPE_ECC_ERROR, "ECC Error" }, \ + { CXL_GMER_MEM_EVT_TYPE_INV_ADDR, "Invalid Address" }, \ + { CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR, "Data Path Error" } \ +) + +#define CXL_GMER_TRANS_UNKNOWN 0x00 +#define CXL_GMER_TRANS_HOST_READ 0x01 +#define CXL_GMER_TRANS_HOST_WRITE 0x02 +#define CXL_GMER_TRANS_HOST_SCAN_MEDIA 0x03 +#define CXL_GMER_TRANS_HOST_INJECT_POISON 0x04 +#define CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB 0x05 +#define CXL_GMER_TRANS_INTERNAL_MEDIA_MANAGEMENT 0x06 +#define show_trans_type(type) __print_symbolic(type, \ + { CXL_GMER_TRANS_UNKNOWN, "Unknown" }, \ + { CXL_GMER_TRANS_HOST_READ, "Host Read" }, \ + { CXL_GMER_TRANS_HOST_WRITE, "Host Write" }, \ + { CXL_GMER_TRANS_HOST_SCAN_MEDIA, "Host Scan Media" }, \ + { CXL_GMER_TRANS_HOST_INJECT_POISON, "Host Inject Poison" }, \ + { CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB, "Internal Media Scrub" }, \ + { CXL_GMER_TRANS_INTERNAL_MEDIA_MANAGEMENT, "Internal Media Management" } \ +) + +#define CXL_GMER_VALID_CHANNEL BIT(0) +#define CXL_GMER_VALID_RANK BIT(1) +#define CXL_GMER_VALID_DEVICE BIT(2) +#define CXL_GMER_VALID_COMPONENT BIT(3) +#define show_valid_flags(flags) __print_flags(flags, "|", \ + { CXL_GMER_VALID_CHANNEL, "CHANNEL" }, \ + { CXL_GMER_VALID_RANK, "RANK" }, \ + { CXL_GMER_VALID_DEVICE, "DEVICE" }, \ + { CXL_GMER_VALID_COMPONENT, "COMPONENT" } \ +) + +TRACE_EVENT(cxl_general_media, + + TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log, + struct cxl_event_gen_media *rec), + + TP_ARGS(cxlmd, log, rec), + + TP_STRUCT__entry( + CXL_EVT_TP_entry + /* General Media */ + __field(u64, dpa) + __field(u8, descriptor) + __field(u8, type) + __field(u8, transaction_type) + __field(u8, channel) + __field(u32, device) + __array(u8, comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE) + __field(u16, validity_flags) + /* Following are out of order to pack trace record */ + __field(u8, rank) + __field(u8, dpa_flags) + ), + + TP_fast_assign( + CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr); + + /* General Media */ + __entry->dpa = le64_to_cpu(rec->phys_addr); + __entry->dpa_flags = __entry->dpa & CXL_DPA_FLAGS_MASK; + /* Mask after flags have been parsed */ + __entry->dpa &= CXL_DPA_MASK; + __entry->descriptor = rec->descriptor; + __entry->type = rec->type; + __entry->transaction_type = rec->transaction_type; + __entry->channel = rec->channel; + __entry->rank = rec->rank; + __entry->device = get_unaligned_le24(rec->device); + memcpy(__entry->comp_id, &rec->component_id, + CXL_EVENT_GEN_MED_COMP_ID_SIZE); + __entry->validity_flags = get_unaligned_le16(&rec->validity_flags); + ), + + CXL_EVT_TP_printk("dpa=%llx dpa_flags='%s' " \ + "descriptor='%s' type='%s' transaction_type='%s' channel=%u rank=%u " \ + "device=%x comp_id=%s validity_flags='%s'", + __entry->dpa, show_dpa_flags(__entry->dpa_flags), + show_event_desc_flags(__entry->descriptor), + show_mem_event_type(__entry->type), + show_trans_type(__entry->transaction_type), + __entry->channel, __entry->rank, __entry->device, + __print_hex(__entry->comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE), + show_valid_flags(__entry->validity_flags) + ) +); + +/* + * DRAM Event Record - DER + * + * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44 + */ +/* + * DRAM Event Record defines many fields the same as the General Media Event + * Record. Reuse those definitions as appropriate. + */ +#define CXL_DER_VALID_CHANNEL BIT(0) +#define CXL_DER_VALID_RANK BIT(1) +#define CXL_DER_VALID_NIBBLE BIT(2) +#define CXL_DER_VALID_BANK_GROUP BIT(3) +#define CXL_DER_VALID_BANK BIT(4) +#define CXL_DER_VALID_ROW BIT(5) +#define CXL_DER_VALID_COLUMN BIT(6) +#define CXL_DER_VALID_CORRECTION_MASK BIT(7) +#define show_dram_valid_flags(flags) __print_flags(flags, "|", \ + { CXL_DER_VALID_CHANNEL, "CHANNEL" }, \ + { CXL_DER_VALID_RANK, "RANK" }, \ + { CXL_DER_VALID_NIBBLE, "NIBBLE" }, \ + { CXL_DER_VALID_BANK_GROUP, "BANK GROUP" }, \ + { CXL_DER_VALID_BANK, "BANK" }, \ + { CXL_DER_VALID_ROW, "ROW" }, \ + { CXL_DER_VALID_COLUMN, "COLUMN" }, \ + { CXL_DER_VALID_CORRECTION_MASK, "CORRECTION MASK" } \ +) + +TRACE_EVENT(cxl_dram, + + TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log, + struct cxl_event_dram *rec), + + TP_ARGS(cxlmd, log, rec), + + TP_STRUCT__entry( + CXL_EVT_TP_entry + /* DRAM */ + __field(u64, dpa) + __field(u8, descriptor) + __field(u8, type) + __field(u8, transaction_type) + __field(u8, channel) + __field(u16, validity_flags) + __field(u16, column) /* Out of order to pack trace record */ + __field(u32, nibble_mask) + __field(u32, row) + __array(u8, cor_mask, CXL_EVENT_DER_CORRECTION_MASK_SIZE) + __field(u8, rank) /* Out of order to pack trace record */ + __field(u8, bank_group) /* Out of order to pack trace record */ + __field(u8, bank) /* Out of order to pack trace record */ + __field(u8, dpa_flags) /* Out of order to pack trace record */ + ), + + TP_fast_assign( + CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr); + + /* DRAM */ + __entry->dpa = le64_to_cpu(rec->phys_addr); + __entry->dpa_flags = __entry->dpa & CXL_DPA_FLAGS_MASK; + __entry->dpa &= CXL_DPA_MASK; + __entry->descriptor = rec->descriptor; + __entry->type = rec->type; + __entry->transaction_type = rec->transaction_type; + __entry->validity_flags = get_unaligned_le16(rec->validity_flags); + __entry->channel = rec->channel; + __entry->rank = rec->rank; + __entry->nibble_mask = get_unaligned_le24(rec->nibble_mask); + __entry->bank_group = rec->bank_group; + __entry->bank = rec->bank; + __entry->row = get_unaligned_le24(rec->row); + __entry->column = get_unaligned_le16(rec->column); + memcpy(__entry->cor_mask, &rec->correction_mask, + CXL_EVENT_DER_CORRECTION_MASK_SIZE); + ), + + CXL_EVT_TP_printk("dpa=%llx dpa_flags='%s' descriptor='%s' type='%s' " \ + "transaction_type='%s' channel=%u rank=%u nibble_mask=%x " \ + "bank_group=%u bank=%u row=%u column=%u cor_mask=%s " \ + "validity_flags='%s'", + __entry->dpa, show_dpa_flags(__entry->dpa_flags), + show_event_desc_flags(__entry->descriptor), + show_mem_event_type(__entry->type), + show_trans_type(__entry->transaction_type), + __entry->channel, __entry->rank, __entry->nibble_mask, + __entry->bank_group, __entry->bank, + __entry->row, __entry->column, + __print_hex(__entry->cor_mask, CXL_EVENT_DER_CORRECTION_MASK_SIZE), + show_dram_valid_flags(__entry->validity_flags) + ) +); + +/* + * Memory Module Event Record - MMER + * + * CXL res 3.0 section 8.2.9.2.1.3; Table 8-45 + */ +#define CXL_MMER_HEALTH_STATUS_CHANGE 0x00 +#define CXL_MMER_MEDIA_STATUS_CHANGE 0x01 +#define CXL_MMER_LIFE_USED_CHANGE 0x02 +#define CXL_MMER_TEMP_CHANGE 0x03 +#define CXL_MMER_DATA_PATH_ERROR 0x04 +#define CXL_MMER_LSA_ERROR 0x05 +#define show_dev_evt_type(type) __print_symbolic(type, \ + { CXL_MMER_HEALTH_STATUS_CHANGE, "Health Status Change" }, \ + { CXL_MMER_MEDIA_STATUS_CHANGE, "Media Status Change" }, \ + { CXL_MMER_LIFE_USED_CHANGE, "Life Used Change" }, \ + { CXL_MMER_TEMP_CHANGE, "Temperature Change" }, \ + { CXL_MMER_DATA_PATH_ERROR, "Data Path Error" }, \ + { CXL_MMER_LSA_ERROR, "LSA Error" } \ +) + +/* + * Device Health Information - DHI + * + * CXL res 3.0 section 8.2.9.8.3.1; Table 8-100 + */ +#define CXL_DHI_HS_MAINTENANCE_NEEDED BIT(0) +#define CXL_DHI_HS_PERFORMANCE_DEGRADED BIT(1) +#define CXL_DHI_HS_HW_REPLACEMENT_NEEDED BIT(2) +#define show_health_status_flags(flags) __print_flags(flags, "|", \ + { CXL_DHI_HS_MAINTENANCE_NEEDED, "MAINTENANCE_NEEDED" }, \ + { CXL_DHI_HS_PERFORMANCE_DEGRADED, "PERFORMANCE_DEGRADED" }, \ + { CXL_DHI_HS_HW_REPLACEMENT_NEEDED, "REPLACEMENT_NEEDED" } \ +) + +#define CXL_DHI_MS_NORMAL 0x00 +#define CXL_DHI_MS_NOT_READY 0x01 +#define CXL_DHI_MS_WRITE_PERSISTENCY_LOST 0x02 +#define CXL_DHI_MS_ALL_DATA_LOST 0x03 +#define CXL_DHI_MS_WRITE_PERSISTENCY_LOSS_EVENT_POWER_LOSS 0x04 +#define CXL_DHI_MS_WRITE_PERSISTENCY_LOSS_EVENT_SHUTDOWN 0x05 +#define CXL_DHI_MS_WRITE_PERSISTENCY_LOSS_IMMINENT 0x06 +#define CXL_DHI_MS_WRITE_ALL_DATA_LOSS_EVENT_POWER_LOSS 0x07 +#define CXL_DHI_MS_WRITE_ALL_DATA_LOSS_EVENT_SHUTDOWN 0x08 +#define CXL_DHI_MS_WRITE_ALL_DATA_LOSS_IMMINENT 0x09 +#define show_media_status(ms) __print_symbolic(ms, \ + { CXL_DHI_MS_NORMAL, \ + "Normal" }, \ + { CXL_DHI_MS_NOT_READY, \ + "Not Ready" }, \ + { CXL_DHI_MS_WRITE_PERSISTENCY_LOST, \ + "Write Persistency Lost" }, \ + { CXL_DHI_MS_ALL_DATA_LOST, \ + "All Data Lost" }, \ + { CXL_DHI_MS_WRITE_PERSISTENCY_LOSS_EVENT_POWER_LOSS, \ + "Write Persistency Loss in the Event of Power Loss" }, \ + { CXL_DHI_MS_WRITE_PERSISTENCY_LOSS_EVENT_SHUTDOWN, \ + "Write Persistency Loss in Event of Shutdown" }, \ + { CXL_DHI_MS_WRITE_PERSISTENCY_LOSS_IMMINENT, \ + "Write Persistency Loss Imminent" }, \ + { CXL_DHI_MS_WRITE_ALL_DATA_LOSS_EVENT_POWER_LOSS, \ + "All Data Loss in Event of Power Loss" }, \ + { CXL_DHI_MS_WRITE_ALL_DATA_LOSS_EVENT_SHUTDOWN, \ + "All Data loss in the Event of Shutdown" }, \ + { CXL_DHI_MS_WRITE_ALL_DATA_LOSS_IMMINENT, \ + "All Data Loss Imminent" } \ +) + +#define CXL_DHI_AS_NORMAL 0x0 +#define CXL_DHI_AS_WARNING 0x1 +#define CXL_DHI_AS_CRITICAL 0x2 +#define show_two_bit_status(as) __print_symbolic(as, \ + { CXL_DHI_AS_NORMAL, "Normal" }, \ + { CXL_DHI_AS_WARNING, "Warning" }, \ + { CXL_DHI_AS_CRITICAL, "Critical" } \ +) +#define show_one_bit_status(as) __print_symbolic(as, \ + { CXL_DHI_AS_NORMAL, "Normal" }, \ + { CXL_DHI_AS_WARNING, "Warning" } \ +) + +#define CXL_DHI_AS_LIFE_USED(as) (as & 0x3) +#define CXL_DHI_AS_DEV_TEMP(as) ((as & 0xC) >> 2) +#define CXL_DHI_AS_COR_VOL_ERR_CNT(as) ((as & 0x10) >> 4) +#define CXL_DHI_AS_COR_PER_ERR_CNT(as) ((as & 0x20) >> 5) + +TRACE_EVENT(cxl_memory_module, + + TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log, + struct cxl_event_mem_module *rec), + + TP_ARGS(cxlmd, log, rec), + + TP_STRUCT__entry( + CXL_EVT_TP_entry + + /* Memory Module Event */ + __field(u8, event_type) + + /* Device Health Info */ + __field(u8, health_status) + __field(u8, media_status) + __field(u8, life_used) + __field(u32, dirty_shutdown_cnt) + __field(u32, cor_vol_err_cnt) + __field(u32, cor_per_err_cnt) + __field(s16, device_temp) + __field(u8, add_status) + ), + + TP_fast_assign( + CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr); + + /* Memory Module Event */ + __entry->event_type = rec->event_type; + + /* Device Health Info */ + __entry->health_status = rec->info.health_status; + __entry->media_status = rec->info.media_status; + __entry->life_used = rec->info.life_used; + __entry->dirty_shutdown_cnt = get_unaligned_le32(rec->info.dirty_shutdown_cnt); + __entry->cor_vol_err_cnt = get_unaligned_le32(rec->info.cor_vol_err_cnt); + __entry->cor_per_err_cnt = get_unaligned_le32(rec->info.cor_per_err_cnt); + __entry->device_temp = get_unaligned_le16(rec->info.device_temp); + __entry->add_status = rec->info.add_status; + ), + + CXL_EVT_TP_printk("event_type='%s' health_status='%s' media_status='%s' " \ + "as_life_used=%s as_dev_temp=%s as_cor_vol_err_cnt=%s " \ + "as_cor_per_err_cnt=%s life_used=%u device_temp=%d " \ + "dirty_shutdown_cnt=%u cor_vol_err_cnt=%u cor_per_err_cnt=%u", + show_dev_evt_type(__entry->event_type), + show_health_status_flags(__entry->health_status), + show_media_status(__entry->media_status), + show_two_bit_status(CXL_DHI_AS_LIFE_USED(__entry->add_status)), + show_two_bit_status(CXL_DHI_AS_DEV_TEMP(__entry->add_status)), + show_one_bit_status(CXL_DHI_AS_COR_VOL_ERR_CNT(__entry->add_status)), + show_one_bit_status(CXL_DHI_AS_COR_PER_ERR_CNT(__entry->add_status)), + __entry->life_used, __entry->device_temp, + __entry->dirty_shutdown_cnt, __entry->cor_vol_err_cnt, + __entry->cor_per_err_cnt + ) +); + +#endif /* _CXL_EVENTS_H */ + +#define TRACE_INCLUDE_FILE trace +#include <trace/define_trace.h> |