linux-kernel - [PATCH 12/21] EDAC, ghes: Add support for legacy API counters

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20190529084344.28562-13-rrichter@marvell.com>
Date:   Wed, 29 May 2019 08:44:30 +0000
From:   Robert Richter <rrichter@...vell.com>
To:     Borislav Petkov <bp@...en8.de>, Tony Luck <tony.luck@...el.com>,
        "James Morse" <james.morse@....com>,
        Mauro Carvalho Chehab <mchehab@...nel.org>
CC:     "linux-edac@...r.kernel.org" <linux-edac@...r.kernel.org>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        Robert Richter <rrichter@...vell.com>
Subject: [PATCH 12/21] EDAC, ghes: Add support for legacy API counters

The ghes driver is not able yet to count legacy API counters in sysfs,
e.g.:

 /sys/devices/system/edac/mc/mc0/csrow2/ce_count
 /sys/devices/system/edac/mc/mc0/csrow2/ch0_ce_count
 /sys/devices/system/edac/mc/mc0/csrow2/ch1_ce_count

Make counting csrows/channels generic so that the ghes driver can use
it too.

Signed-off-by: Robert Richter <rrichter@...vell.com>
---
 drivers/edac/edac_mc.c   | 39 ++++++++++++++++++++++-----------------
 drivers/edac/edac_mc.h   |  7 ++++++-
 drivers/edac/ghes_edac.c |  2 +-
 3 files changed, 29 insertions(+), 19 deletions(-)

diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 8613a31dc86c..f7e6a751f309 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -1007,7 +1007,8 @@ static void edac_ue_error(struct mem_ctl_info *mci,
 void edac_raw_mc_handle_error(const enum hw_event_mc_err_type type,
 			      struct mem_ctl_info *mci,
 			      struct dimm_info *dimm,
-			      struct edac_raw_error_desc *e)
+			      struct edac_raw_error_desc *e,
+			      int row, int chan)
 {
 	char detail[80];
 	u8 grain_bits;
@@ -1040,7 +1041,23 @@ void edac_raw_mc_handle_error(const enum hw_event_mc_err_type type,
 			      e->label, detail, e->other_detail);
 	}
 
+	/* old API's counters */
+	if (dimm) {
+		row = dimm->csrow;
+		chan = dimm->cschannel;
+	}
+
+	if (row >= 0) {
+		if (type == HW_EVENT_ERR_CORRECTED) {
+			mci->csrows[row]->ce_count += e->error_count;
+			if (chan >= 0)
+				mci->csrows[row]->channels[chan]->ce_count += e->error_count;
+		} else {
+			mci->csrows[row]->ue_count += e->error_count;
+		}
+	}
 
+	edac_dbg(4, "csrow/channel to increment: (%d,%d)\n", row, chan);
 }
 EXPORT_SYMBOL_GPL(edac_raw_mc_handle_error);
 
@@ -1171,22 +1188,10 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type,
 		}
 	}
 
-	if (!per_layer_report) {
+	if (!per_layer_report)
 		strcpy(e->label, "any memory");
-	} else {
-		edac_dbg(4, "csrow/channel to increment: (%d,%d)\n", row, chan);
-		if (p == e->label)
-			strcpy(e->label, "unknown memory");
-		if (type == HW_EVENT_ERR_CORRECTED) {
-			if (row >= 0) {
-				mci->csrows[row]->ce_count += error_count;
-				if (chan >= 0)
-					mci->csrows[row]->channels[chan]->ce_count += error_count;
-			}
-		} else
-			if (row >= 0)
-				mci->csrows[row]->ue_count += error_count;
-	}
+	else if (!*e->label)
+		strcpy(e->label, "unknown memory");
 
 	/* Fill the RAM location data */
 	p = e->location;
@@ -1204,6 +1209,6 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type,
 
 	dimm = edac_get_dimm(mci, top_layer, mid_layer, low_layer);
 
-	edac_raw_mc_handle_error(type, mci, dimm, e);
+	edac_raw_mc_handle_error(type, mci, dimm, e, row, chan);
 }
 EXPORT_SYMBOL_GPL(edac_mc_handle_error);
diff --git a/drivers/edac/edac_mc.h b/drivers/edac/edac_mc.h
index b816cf3caaee..c4ddd5c1e24c 100644
--- a/drivers/edac/edac_mc.h
+++ b/drivers/edac/edac_mc.h
@@ -216,6 +216,10 @@ extern int edac_mc_find_csrow_by_page(struct mem_ctl_info *mci,
  * @mci:		a struct mem_ctl_info pointer
  * @dimm:		a struct dimm_info pointer
  * @e:			error description
+ * @row:		csrow hint if there is no dimm info (<0 if
+ *			unknown)
+ * @chan:		cschannel hint if there is no dimm info (<0 if
+ *			unknown)
  *
  * This raw function is used internally by edac_mc_handle_error(). It should
  * only be called directly when the hardware error come directly from BIOS,
@@ -224,7 +228,8 @@ extern int edac_mc_find_csrow_by_page(struct mem_ctl_info *mci,
 void edac_raw_mc_handle_error(const enum hw_event_mc_err_type type,
 			      struct mem_ctl_info *mci,
 			      struct dimm_info *dimm,
-			      struct edac_raw_error_desc *e);
+			      struct edac_raw_error_desc *e,
+			      int row, int chan);
 
 /**
  * edac_mc_handle_error() - Reports a memory event to userspace.
diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index f6ea4b070bfe..ea4d53043199 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -435,7 +435,7 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 
 	dimm_info = edac_get_dimm_by_index(mci, e->top_layer);
 
-	edac_raw_mc_handle_error(type, mci, dimm_info, e);
+	edac_raw_mc_handle_error(type, mci, dimm_info, e, -1, -1);
 
 	spin_unlock_irqrestore(&ghes_lock, flags);
 }
-- 
2.20.1