linux-kernel - [PATCH 7/7] EDAC/{skx_common,i10nm}: Add RRL support for Intel Granite Rapids server

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: <20250417150724.1170168-8-qiuxu.zhuo@intel.com>
Date: Thu, 17 Apr 2025 23:07:24 +0800
From: Qiuxu Zhuo <qiuxu.zhuo@...el.com>
To: Tony Luck <tony.luck@...el.com>
Cc: Qiuxu Zhuo <qiuxu.zhuo@...el.com>,
	Feng Xu <feng.f.xu@...el.com>,
	Borislav Petkov <bp@...en8.de>,
	James Morse <james.morse@....com>,
	Mauro Carvalho Chehab <mchehab@...nel.org>,
	Robert Richter <rric@...nel.org>,
	Yi Lai <yi1.lai@...el.com>,
	Shawn Fan <shawn.fan@...el.com>,
	linux-edac@...r.kernel.org,
	linux-kernel@...r.kernel.org
Subject: [PATCH 7/7] EDAC/{skx_common,i10nm}: Add RRL support for Intel Granite Rapids server

Compared to previous generations, Granite Rapids defines the RRL control
bits {en_patspr, noover, en} in different positions, adds an extra RRL set
for the new mode of the first patrol-scrub read error, and extends the
number of CORRERRCNT registers from 4 to 8, encoding one counter per
CORRERRCNT register.

Add a Granite Rapids reg_rrl configuration table and adjust the code to
accommodate the differences mentioned above for RRL support.

Tested-by: Feng Xu <feng.f.xu@...el.com>
Signed-off-by: Qiuxu Zhuo <qiuxu.zhuo@...el.com>
---
 drivers/edac/i10nm_base.c | 37 +++++++++++++++++++++++++++++++++++--
 drivers/edac/skx_common.h |  4 ++--
 2 files changed, 37 insertions(+), 4 deletions(-)

diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c
index aefc448283d3..8863f1fb4caf 100644
--- a/drivers/edac/i10nm_base.c
+++ b/drivers/edac/i10nm_base.c
@@ -164,6 +164,29 @@ static struct reg_rrl spr_reg_rrl_hbm_pch1 = {
 	.cecnt_widths	= {4, 4, 4, 4},
 };
 
+static struct reg_rrl gnr_reg_rrl_ddr = {
+	.set_num = 4,
+	.reg_num = 6,
+	.modes = {FRE_SCRUB, FRE_DEMAND, LRE_SCRUB, LRE_DEMAND},
+	.offsets = {
+		{0x2f10, 0x2f20, 0x2f30, 0x2f50, 0x2f60, 0xba0},
+		{0x2f14, 0x2f24, 0x2f38, 0x2f54, 0x2f64, 0xba8},
+		{0x2f18, 0x2f28, 0x2f40, 0x2f58, 0x2f68, 0xbb0},
+		{0x2f1c, 0x2f2c, 0x2f48, 0x2f5c, 0x2f6c, 0xbb8},
+	},
+	.widths		= {4, 4, 8, 4, 4, 8},
+	.v_mask		= BIT(0),
+	.uc_mask	= BIT(1),
+	.over_mask	= BIT(2),
+	.en_patspr_mask	= BIT(14),
+	.noover_mask	= BIT(15),
+	.en_mask	= BIT(12),
+
+	.cecnt_num	= 8,
+	.cecnt_offsets	= {0x2c10, 0x2c14, 0x2c18, 0x2c1c, 0x2c20, 0x2c24, 0x2c28, 0x2c2c},
+	.cecnt_widths	= {4, 4, 4, 4, 4, 4, 4, 4},
+};
+
 static u64 read_imc_reg(struct skx_imc *imc, int chan, u32 offset, u8 width)
 {
 	switch (width) {
@@ -353,8 +376,17 @@ static void show_retry_rd_err_log(struct decoded_addr *res, char *msg,
 			width = rrl->cecnt_widths[i];
 			corr = read_imc_reg(imc, ch, offset, width);
 
-			n += snprintf(msg + n, len - n, "%.4llx %.4llx ",
-				      corr & 0xffff, corr >> 16);
+			/* CPUs {ICX,SPR} encode two counters per 4-byte CORRERRCNT register. */
+			if (res_cfg->type <= SPR) {
+				n += snprintf(msg + n, len - n, "%.4llx %.4llx ",
+					      corr & 0xffff, corr >> 16);
+			} else {
+			/* CPUs {GNR} encode one counter per CORRERRCNT register. */
+				if (width == 4)
+					n += snprintf(msg + n, len - n, "%.8llx ", corr);
+				else
+					n += snprintf(msg + n, len - n, "%.16llx ", corr);
+			}
 		}
 
 		/* Move back one space. */
@@ -985,6 +1017,7 @@ static struct res_config gnr_cfg = {
 	.uracu_bdf		= {0, 0, 1},
 	.ddr_mdev_bdf		= {0, 5, 1},
 	.sad_all_offset		= 0x300,
+	.reg_rrl_ddr		= &gnr_reg_rrl_ddr,
 };
 
 static const struct x86_cpu_id i10nm_cpuids[] = {
diff --git a/drivers/edac/skx_common.h b/drivers/edac/skx_common.h
index 8f0f4af2cb27..ec4966f7ea40 100644
--- a/drivers/edac/skx_common.h
+++ b/drivers/edac/skx_common.h
@@ -80,11 +80,11 @@
 #define MCACOD_EXT_MEM_ERR	0x280
 
 /* Max RRL register sets per {,sub-,pseudo-}channel. */
-#define NUM_RRL_SET		3
+#define NUM_RRL_SET		4
 /* Max RRL registers per set. */
 #define NUM_RRL_REG		6
 /* Max correctable error count registers. */
-#define NUM_CECNT_REG		4
+#define NUM_CECNT_REG		8
 
 /* Modes of RRL register set. */
 enum rrl_mode {
-- 
2.43.0