| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20241120095923.1891-13-shiju.jose@huawei.com>
Date: Wed, 20 Nov 2024 09:59:22 +0000
From: <shiju.jose@...wei.com>
To: <linux-edac@...r.kernel.org>, <linux-cxl@...r.kernel.org>,
<mchehab@...nel.org>, <dave.jiang@...el.com>, <dan.j.williams@...el.com>,
<jonathan.cameron@...wei.com>, <alison.schofield@...el.com>,
<nifan.cxl@...il.com>, <vishal.l.verma@...el.com>, <ira.weiny@...el.com>,
<dave@...olabs.net>
CC: <linux-kernel@...r.kernel.org>, <linuxarm@...wei.com>,
<tanxiaofei@...wei.com>, <prime.zeng@...ilicon.com>, <shiju.jose@...wei.com>
Subject: [PATCH 12/13] rasdaemon: ras-mc-ctl: Update logging of CXL DRAM event data to align with CXL spec rev 3.1
From: Shiju Jose <shiju.jose@...wei.com>
CXL spec 3.1 section 8.2.9.2.1.2 Table 8-46, DRAM Event Record has updated
with following new fields and new types for Memory Event Type, Transaction
Type and Validity Flags fields.
1. Component Identifier
2. Sub-channel
3. Advanced Programmable Corrected Memory Error Threshold Event Flags
4. Corrected Volatile Memory Error Count at Event
5. Memory Event Sub-Type
This update modifies ras-mc-ctl to parse and log CXL DRAM event data
stored in the RAS SQLite database table, reflecting the specification
changes introduced in revision 3.1.
Example output,
./util/ras-mc-ctl --errors
...
CXL DRAM events:
1 2024-11-20 00:18:53 +0000 error: memdev=mem0, host=0000:0f:00.0, serial=0x3, \
log=Informational, hdr_uuid=00000000-0000-0000-0000-000000000000, \
hdr_flags=0x1, , hdr_handle=0x1, hdr_related_handle=0x0, \
hdr_timestamp=1970-01-01 00:00:58 +0000, hdr_length=128, hdr_maint_op_class=1, \
hdr_maint_op_sub_class=3, dpa=0x18680, dpa_flags: , \
descriptor_flags: 'UNCORRECTABLE EVENT' , 'THRESHOLD EVENT' , \
memory event type: Data Path Error, memory event sub type: Media Link CRC Error, \
transaction_type: Internal Media Scrub, channel=3, sub_channel=0, rank=17, \
nibble_mask=3866802, bank_group=7, bank=11, row=2, column=77, \
correction_mask:21 00 00 00 00 00 00 00 2c 00 00 00 00 00 00 00 37 00 00 \
00 00 00 00 00 42 00 00 00 00 00 00 00 hpa=0xffffffffffffffff, \
region_uuid=00000000-0000-0000-0000-000000000000, \
component_id:01 74 c5 08 9a 1a 0b fc d2 7e 2f 31 9b 3c 81 4d \
pldm_entity_id:74 c5 08 9a 1a 0b pldm_resource_id:00 00 00 00 \
cme_threshold_ev_flags: 'Corrected Memory Errors in Multiple Media Components' , \
'Exceeded Programmable Threshold' , cvme_count=0x94,
...
Signed-off-by: Shiju Jose <shiju.jose@...wei.com>
---
util/ras-mc-ctl.in | 26 +++++++++++++++++++++-----
1 file changed, 21 insertions(+), 5 deletions(-)
diff --git a/util/ras-mc-ctl.in b/util/ras-mc-ctl.in
index f8efa91..dbb1607 100755
--- a/util/ras-mc-ctl.in
+++ b/util/ras-mc-ctl.in
@@ -1402,14 +1402,17 @@ sub get_cxl_der_mem_event_type
{
my @types;
- if ($_[0] < 0 || $_[0] > 3) {
+ if ($_[0] < 0 || $_[0] > 6) {
return "unknown-type";
}
@types = ("Media ECC Error",
"Scrub Media ECC Error",
"Invalid Address",
- "Data Path Error");
+ "Data Path Error",
+ "TE State Violation",
+ "Advanced Programmable CME Counter Expiration",
+ "CKID Violation");
return $types[$_[0]];
}
@@ -1819,7 +1822,7 @@ sub errors
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, $add_status);
- my ($cme_threshold_ev_flags, $cme_count);
+ my ($sub_channel, $cme_threshold_ev_flags, $cme_count, $cvme_count);
my $dbh = DBI->connect("dbi:SQLite:dbname=$dbname", "", "", {});
@@ -2089,10 +2092,10 @@ sub errors
# CXL DRAM errors
use constant CXL_EVENT_DER_CORRECTION_MASK_SIZE => 0x20;
- $query = "select id, timestamp, memdev, host, serial, log_type, hdr_uuid, hdr_flags, hdr_handle, hdr_related_handle, hdr_ts, hdr_length, hdr_maint_op_class, dpa, dpa_flags, descriptor, type, transaction_type, channel, rank, nibble_mask, bank_group, bank, row, column, cor_mask, hpa, region, region_uuid, hdr_maint_op_sub_class from cxl_dram_event$conf{opt}{since} order by id";
+ $query = "select id, timestamp, memdev, host, serial, log_type, hdr_uuid, hdr_flags, hdr_handle, hdr_related_handle, hdr_ts, hdr_length, hdr_maint_op_class, dpa, dpa_flags, descriptor, type, transaction_type, channel, rank, nibble_mask, bank_group, bank, row, column, cor_mask, hpa, region, region_uuid, hdr_maint_op_sub_class, comp_id, pldm_entity_id, pldm_resource_id, sub_type, sub_channel, cme_threshold_ev_flags, cvme_count from cxl_dram_event$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, $dpa, $dpa_flags, $descriptor, $type, $transaction_type, $channel, $rank, $nibble_mask, $bank_group, $bank, $row, $column, $cor_mask, $hpa, $region, $region_uuid, $hdr_maint_op_sub_class));
+ $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, $dpa, $dpa_flags, $descriptor, $type, $transaction_type, $channel, $rank, $nibble_mask, $bank_group, $bank, $row, $column, $cor_mask, $hpa, $region, $region_uuid, $hdr_maint_op_sub_class, $comp_id, $pldm_entity_id, $pldm_res_id, $mem_event_sub_type, $sub_channel, $cme_threshold_ev_flags, $cvme_count));
$out = "";
while($query_handle->fetch()) {
$out .= "$id $timestamp error: ";
@@ -2112,8 +2115,10 @@ 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);
$out .= sprintf "memory event type: %s, ", get_cxl_der_mem_event_type($type) if (defined $type && length $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 "sub_channel=%u, ", $sub_channel if (defined $sub_channel && length $sub_channel);
$out .= sprintf "rank=%u, ", $rank if (defined $rank && length $rank);
$out .= sprintf "nibble_mask=%u, ", $nibble_mask if (defined $nibble_mask && length $nibble_mask);
$out .= sprintf "bank_group=%u, ", $bank_group if (defined $bank_group && length $bank_group);
@@ -2130,6 +2135,17 @@ sub errors
$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);
+ if (defined $comp_id && length $comp_id) {
+ 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);
+ }
+ $out .= sprintf "cme_threshold_ev_flags: %s, ", get_cxl_cme_threshold_ev_flags_text($cme_threshold_ev_flags) if (defined $cme_threshold_ev_flags && length $cme_threshold_ev_flags);
+ $out .= sprintf "cvme_count=0x%x, ", $cvme_count if (defined $cvme_count && length $cvme_count);
$out .= "\n";
}
if ($out ne "") {
--
2.43.0
Powered by blists - more mailing lists