From 70b6ebdd64accd7264c3c6235a5c60fda9f0e7a5 Mon Sep 17 00:00:00 2001 From: Shiju Jose Date: Fri, 8 Nov 2024 18:06:42 +0000 Subject: [PATCH] rasdaemon: ras-mc-ctl: Update logging of CXL general media event data to align with CXL spec rev 3.1 CXL spec rev 3.1 section 8.2.9.2.1.1 Table 8-45, General Media Event Record has updated with following new fields and new types for Memory Event Type and Transaction Type fields. 1. Advanced Programmable Corrected Memory Error Threshold Event Flags 2. Corrected Memory Error Count at Event 3. Memory Event Sub-Type The format of component identifier has changed (CXL spec 3.1 section 8.2.9.2.1 Table 8-44). This update modifies ras-mc-ctl to parse and log CXL general media event data stored in the RAS SQLite database table, reflecting the specification changes introduced in revision 3.1. Reviewed-by: Jonathan Cameron Signed-off-by: Shiju Jose Signed-off-by: Mauro Carvalho Chehab --- util/ras-mc-ctl.in | 92 ++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 80 insertions(+), 12 deletions(-) diff --git a/util/ras-mc-ctl.in b/util/ras-mc-ctl.in index 58ee916..fe21f81 100755 --- a/util/ras-mc-ctl.in +++ b/util/ras-mc-ctl.in @@ -1339,21 +1339,65 @@ sub get_cxl_descriptor_flags_text return join (", ", @out); } +#CXL rev 3.1 Section 8.2.9.2.1.1; Table 8-45 +#General Media Event Record - GMER sub get_cxl_gmer_mem_event_type { my @types; - if ($_[0] < 0 || $_[0] > 2) { + if ($_[0] < 0 || $_[0] > 6) { return "unknown-type"; } @types = ("ECC Error", "Invalid Address", - "Data Path Error"); + "Data Path Error", + "TE State Violation", + "Scrub Media ECC Error", + "Advanced Programmable CME Counter Expiration", + "CKID Violation"); return $types[$_[0]]; } +# CXL rev 3.1 Section 8.2.9.2.1.1; Table 8-45 +sub get_cxl_mem_event_sub_type +{ + my @types; + + if ($_[0] < 0 || $_[0] > 5) { + return "unknown-type"; + } + + @types = ("Not Reported", + "Internal Datapath Error", + "Media Link Command Training Error", + "Media Link Control Training Error", + "Media Link Data Training Error", + "Media Link CRC Error"); + + return $types[$_[0]]; +} + +use constant { + CXL_EVT_FLAG_CME_MULTIPLE_MEDIA => 0x0001, + CXL_EVT_FLAG_THRESHOLD_EXCEEDED => 0x0002, +}; +sub get_cxl_cme_threshold_ev_flags_text +{ + my $flags = $_[0]; + my @out; + + if ($flags & CXL_EVT_FLAG_CME_MULTIPLE_MEDIA) { + push @out, (sprintf "\'Corrected Memory Errors in Multiple Media Components\' "); + } + if ($flags & CXL_EVT_FLAG_THRESHOLD_EXCEEDED) { + push @out, (sprintf "\'Exceeded Programmable Threshold\' "); + } + + return join (", ", @out); +} + sub get_cxl_der_mem_event_type { my @types; @@ -1370,11 +1414,12 @@ sub get_cxl_der_mem_event_type return $types[$_[0]]; } +# CXL rev 3.1 Section 8.2.9.2.1.1; Table 8-45 sub get_cxl_transaction_type { my @types; - if ($_[0] < 0 || $_[0] > 6) { + if ($_[0] < 0 || $_[0] > 8) { return "unknown-type"; } @@ -1384,7 +1429,9 @@ sub get_cxl_transaction_type "Host Scan Media", "Host Inject Poison", "Internal Media Scrub", - "Internal Media Management"); + "Internal Media Management", + "Internal Media Error Check Scrub", + "Media Initialization"); return $types[$_[0]]; } @@ -1453,6 +1500,19 @@ sub get_cxl_media_status return $types[$_[0]]; } +# arg0 - name of the id +# arg1 - id +# arg2 - size(bytes) of id +# arg3 - out log buffer +sub print_cxl_dev_id +{ + $_[3] .= sprintf "%s:", $_[0]; + my @bytes = unpack "C*", $_[1]; + for (my $i = 0; $i < $_[2]; $i++) { + $_[3] .= sprintf "%02x ", $bytes[$i]; + } +} + sub summary { require DBI; @@ -1756,9 +1816,10 @@ sub errors my ($log_type, $first_ts, $last_ts); my ($trace_type, $region, $region_uuid, $hpa, $dpa, $dpa_length, $source, $flags, $overflow_ts); my ($hdr_uuid, $hdr_flags, $hdr_handle, $hdr_related_handle, $hdr_ts, $hdr_length, $hdr_maint_op_class, $hdr_maint_op_sub_class, $data); - my ($dpa_flags, $descriptor, $mem_event_type, $transaction_type, $channel, $rank, $device, $comp_id); + my ($dpa_flags, $descriptor, $mem_event_type, $mem_event_sub_type, $transaction_type, $channel, $rank, $device, $comp_id, $pldm_entity_id, $pldm_res_id); my ($nibble_mask, $bank_group, $row, $column, $cor_mask); my ($event_type, $health_status, $media_status, $life_used, $dirty_shutdown_cnt, $cor_vol_err_cnt, $cor_per_err_cnt, $device_temp, $add_status); + my ($sub_type, $cme_threshold_ev_flags, $cme_count); my $dbh = DBI->connect("dbi:SQLite:dbname=$dbname", "", "", {}); @@ -1974,10 +2035,12 @@ sub errors # CXL general media errors use constant CXL_EVENT_GEN_MED_COMP_ID_SIZE => 0x10; - $query = "select id, timestamp, memdev, host, serial, log_type, hdr_uuid, hdr_flags, hdr_handle, hdr_related_handle, hdr_ts, hdr_length, hdr_maint_op_class, hdr_maint_op_sub_class, dpa, dpa_flags, descriptor, type, transaction_type, channel, rank, device, comp_id, hpa, region, region_uuid from cxl_general_media_event$conf{opt}{since} order by id"; + $query = "select id, timestamp, memdev, host, serial, log_type, hdr_uuid, hdr_flags, hdr_handle, hdr_related_handle, hdr_ts, hdr_length, hdr_maint_op_class, hdr_maint_op_sub_class, dpa, dpa_flags, descriptor, type, transaction_type, channel, rank, device, comp_id, hpa, region, region_uuid, pldm_entity_id, pldm_resource_id, sub_type, cme_threshold_ev_flags, cme_count from cxl_general_media_event$conf{opt}{since} order by id"; $query_handle = $dbh->prepare($query); $query_handle->execute(); - $query_handle->bind_columns(\($id, $timestamp, $memdev, $host, $serial, $log_type, $hdr_uuid, $hdr_flags, $hdr_handle, $hdr_related_handle, $hdr_ts, $hdr_length, $hdr_maint_op_class, $hdr_maint_op_sub_class, $dpa, $dpa_flags, $descriptor, $mem_event_type, $transaction_type, $channel, $rank, $device, $comp_id, $hpa, $region, $region_uuid)); + use constant CXL_EVENT_GEN_PLDM_ENTITY_ID_SIZE => 0x6; + use constant CXL_EVENT_GEN_PLDM_RES_ID_SIZE => 0x4; + $query_handle->bind_columns(\($id, $timestamp, $memdev, $host, $serial, $log_type, $hdr_uuid, $hdr_flags, $hdr_handle, $hdr_related_handle, $hdr_ts, $hdr_length, $hdr_maint_op_class, $hdr_maint_op_sub_class, $dpa, $dpa_flags, $descriptor, $mem_event_type, $transaction_type, $channel, $rank, $device, $comp_id, $hpa, $region, $region_uuid, $pldm_entity_id, $pldm_res_id, $sub_type, $cme_threshold_ev_flags, $cme_count)); $out = ""; while($query_handle->fetch()) { $out .= "$id $timestamp error: "; @@ -1997,20 +2060,25 @@ sub errors $out .= sprintf "dpa_flags: %s, ", get_cxl_dpa_flags_text($dpa_flags) if (defined $dpa_flags && length $dpa_flags); $out .= sprintf "descriptor_flags: %s, ", get_cxl_descriptor_flags_text($descriptor) if (defined $descriptor && length $descriptor); $out .= sprintf "memory event type: %s, ", get_cxl_gmer_mem_event_type($mem_event_type) if (defined $mem_event_type && length $mem_event_type); + $out .= sprintf "memory event sub type: %s, ", get_cxl_mem_event_sub_type($mem_event_sub_type) if (defined $mem_event_sub_type && length $mem_event_sub_type); $out .= sprintf "transaction_type: %s, ", get_cxl_transaction_type($transaction_type) if (defined $transaction_type && length $transaction_type); $out .= sprintf "channel=%u, ", $channel if (defined $channel && length $channel); $out .= sprintf "rank=%u, ", $rank if (defined $rank && length $rank); $out .= sprintf "device=0x%x, ", $device if (defined $device && length $device); if (defined $comp_id && length $comp_id) { - $out .= sprintf "component_id:"; - my @bytes = unpack "C*", $comp_id; - for (my $i = 0; $i < CXL_EVENT_GEN_MED_COMP_ID_SIZE; $i++) { - $out .= sprintf "%02x ", $bytes[$i]; - } + print_cxl_dev_id("component_id", $comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE, $out); } + if (defined $pldm_entity_id && length $pldm_entity_id) { + print_cxl_dev_id("pldm_entity_id", $pldm_entity_id, CXL_EVENT_GEN_PLDM_ENTITY_ID_SIZE, $out); + } + if (defined $pldm_res_id && length $pldm_res_id) { + print_cxl_dev_id("pldm_resource_id", $pldm_res_id, CXL_EVENT_GEN_PLDM_RES_ID_SIZE, $out); + } $out .= sprintf "hpa=0x%llx, ", $hpa if (defined $hpa && length $hpa); $out .= "region=$region, " if (defined $region && length $region); $out .= "region_uuid=$region_uuid, " if (defined $region_uuid && length $region_uuid); + $out .= sprintf "cme_threshold_ev_flags: %s, ", get_cxl_cme_threshold_ev_flags_text($cme_threshold_ev_flags) if (defined $cme_threshold_ev_flags && length $cme_threshold_ev_flags); + $out .= sprintf "cme_count=%u, ", $cme_count if (defined $cme_count && length $cme_count); $out .= "\n"; } if ($out ne "") { -- 2.49.0