Received-SPF: Pass (protection.outlook.com: domain of amd.com designates
 165.204.84.17 as permitted sender) receiver=protection.outlook.com;
 client-ip=165.204.84.17; helo=SATLEXMB03.amd.com;
From:   Yazen Ghannam <yazen.ghannam@amd.com>
To:     <linux-edac@vger.kernel.org>
CC:     <linux-kernel@vger.kernel.org>, <tony.luck@intel.com>,
        <x86@kernel.org>, <Smita.KoralahalliChannabasappa@amd.com>,
        <mukul.joshi@amd.com>, <alexander.deucher@amd.com>,
        <william.roche@oracle.com>, Yazen Ghannam <yazen.ghannam@amd.com>
Subject: [PATCH 2/3] x86/MCE/AMD, EDAC/mce_amd: Add new SMCA Bank Types
Date:   Fri, 3 Dec 2021 02:00:16 +0000
Message-ID: <20211203020017.728440-3-yazen.ghannam@amd.com>
In-Reply-To: <20211203020017.728440-1-yazen.ghannam@amd.com>
References: <20211203020017.728440-1-yazen.ghannam@amd.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 03 Dec 2021 02:00:39.6653
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: b9cf2408-3558-44b2-99a4-08d9b600b4bd
X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=3dd8961f-e488-4e60-8e11-a82d994e183d;Ip=[165.204.84.17];Helo=[SATLEXMB03.amd.com]
X-MS-Exchange-CrossTenant-AuthSource: CO1NAM11FT035.eop-nam11.prod.protection.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: BL1PR12MB5045
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

Add HWID and McaType values for new SMCA bank types, and add their error
descriptions to edac_mce_amd.

The "PHY" bank types all have the same error descriptions, and the NBIF
and SHUB bank types have the same error descriptions. So reuse the same
arrays where appropriate.

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
---
 arch/x86/include/asm/mce.h    |   7 ++
 arch/x86/kernel/cpu/mce/amd.c |  28 +++++++
 drivers/edac/mce_amd.c        | 133 ++++++++++++++++++++++++++++++++--
 3 files changed, 162 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 7c1c35909946..d6834e8fbb6a 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -313,12 +313,19 @@ enum smca_bank_types {
 	SMCA_SMU,	/* System Management Unit */
 	SMCA_SMU_V2,
 	SMCA_MP5,	/* Microprocessor 5 Unit */
+	SMCA_MPDMA,	/* MPDMA Unit */
 	SMCA_NBIO,	/* Northbridge IO Unit */
 	SMCA_PCIE,	/* PCI Express Unit */
 	SMCA_PCIE_V2,
 	SMCA_XGMI_PCS,	/* xGMI PCS Unit */
+	SMCA_NBIF,	/* NBIF Unit */
+	SMCA_SHUB,	/* System HUB Unit */
+	SMCA_SATA,	/* SATA Unit */
+	SMCA_USB,	/* USB Unit */
+	SMCA_GMI_PCS,	/* GMI PCS Unit */
 	SMCA_XGMI_PHY,	/* xGMI PHY Unit */
 	SMCA_WAFL_PHY,	/* WAFL PHY Unit */
+	SMCA_GMI_PHY,	/* GMI PHY Unit */
 	SMCA_UNKNOWN,	/* Unknown type */
 	N_SMCA_BANK_TYPES
 };
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index b9a5a94914a9..e12a8f3414f5 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -95,11 +95,18 @@ static struct smca_bank_name smca_names[] = {
 	[SMCA_PSP ... SMCA_PSP_V2]	= { "psp",		"Platform Security Processor" },
 	[SMCA_SMU ... SMCA_SMU_V2]	= { "smu",		"System Management Unit" },
 	[SMCA_MP5]			= { "mp5",		"Microprocessor 5 Unit" },
+	[SMCA_MPDMA]			= { "mpdma",		"MPDMA Unit" },
 	[SMCA_NBIO]			= { "nbio",		"Northbridge IO Unit" },
 	[SMCA_PCIE ... SMCA_PCIE_V2]	= { "pcie",		"PCI Express Unit" },
 	[SMCA_XGMI_PCS]			= { "xgmi_pcs",		"Ext Global Memory Interconnect PCS Unit" },
+	[SMCA_NBIF]			= { "nbif",		"NBIF Unit" },
+	[SMCA_SHUB]			= { "shub",		"System Hub Unit" },
+	[SMCA_SATA]			= { "sata",		"SATA Unit" },
+	[SMCA_USB]			= { "usb",		"USB Unit" },
+	[SMCA_GMI_PCS]			= { "gmi_pcs",		"Global Memory Interconnect PCS Unit" },
 	[SMCA_XGMI_PHY]			= { "xgmi_phy",		"Ext Global Memory Interconnect PHY Unit" },
 	[SMCA_WAFL_PHY]			= { "wafl_phy",		"WAFL PHY Unit" },
+	[SMCA_GMI_PHY]			= { "gmi_phy",		"Global Memory Interconnect PHY Unit" },
 	[SMCA_UNKNOWN]			= { "unknown",		"Unrecognized Bank Type" },
 };
 
@@ -175,6 +182,9 @@ static struct smca_hwid smca_hwid_mcatypes[] = {
 	/* Microprocessor 5 Unit MCA type */
 	{ SMCA_MP5,	 HWID_MCATYPE(0x01, 0x2)	},
 
+	/* MPDMA MCA type */
+	{ SMCA_MPDMA,	 HWID_MCATYPE(0x01, 0x3)	},
+
 	/* Northbridge IO Unit MCA type */
 	{ SMCA_NBIO,	 HWID_MCATYPE(0x18, 0x0)	},
 
@@ -185,12 +195,30 @@ static struct smca_hwid smca_hwid_mcatypes[] = {
 	/* xGMI PCS MCA type */
 	{ SMCA_XGMI_PCS, HWID_MCATYPE(0x50, 0x0)	},
 
+	/* NBIF MCA type */
+	{ SMCA_NBIF,	 HWID_MCATYPE(0x6C, 0x0)	},
+
+	/* SHUB MCA type */
+	{ SMCA_SHUB,	 HWID_MCATYPE(0x80, 0x0)	},
+
+	/* SATA MCA type */
+	{ SMCA_SATA,	 HWID_MCATYPE(0xA8, 0x0)	},
+
+	/* USB MCA type */
+	{ SMCA_USB,	 HWID_MCATYPE(0xAA, 0x0)	},
+
+	/* GMI PCS MCA type */
+	{ SMCA_GMI_PCS,  HWID_MCATYPE(0x241, 0x0)	},
+
 	/* xGMI PHY MCA type */
 	{ SMCA_XGMI_PHY, HWID_MCATYPE(0x259, 0x0)	},
 
 	/* WAFL PHY MCA type */
 	{ SMCA_WAFL_PHY, HWID_MCATYPE(0x267, 0x0)	},
 
+	/* GMI PHY MCA type */
+	{ SMCA_GMI_PHY,	 HWID_MCATYPE(0x269, 0x0)	},
+
 	/* Unknown type - this must be last in the list */
 	{ SMCA_UNKNOWN,  HWID_MCATYPE(0xFFF, 0xFFFF)	},
 };
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 5ccc09db0a51..720df7b4d6ab 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -399,6 +399,63 @@ static const char * const smca_mp5_mce_desc[] = {
 	"Instruction Tag Cache Bank B ECC or parity error",
 };
 
+static const char * const smca_mpdma_mce_desc[] = {
+	"Main SRAM [31:0] bank ECC or parity error",
+	"Main SRAM [63:32] bank ECC or parity error",
+	"Main SRAM [95:64] bank ECC or parity error",
+	"Main SRAM [127:96] bank ECC or parity error",
+	"Data Cache Bank A ECC or parity error",
+	"Data Cache Bank B ECC or parity error",
+	"Data Tag Cache Bank A ECC or parity error",
+	"Data Tag Cache Bank B ECC or parity error",
+	"Instruction Cache Bank A ECC or parity error",
+	"Instruction Cache Bank B ECC or parity error",
+	"Instruction Tag Cache Bank A ECC or parity error",
+	"Instruction Tag Cache Bank B ECC or parity error",
+	"Data Cache Bank A ECC or parity error",
+	"Data Cache Bank B ECC or parity error",
+	"Data Tag Cache Bank A ECC or parity error",
+	"Data Tag Cache Bank B ECC or parity error",
+	"Instruction Cache Bank A ECC or parity error",
+	"Instruction Cache Bank B ECC or parity error",
+	"Instruction Tag Cache Bank A ECC or parity error",
+	"Instruction Tag Cache Bank B ECC or parity error",
+	"Data Cache Bank A ECC or parity error",
+	"Data Cache Bank B ECC or parity error",
+	"Data Tag Cache Bank A ECC or parity error",
+	"Data Tag Cache Bank B ECC or parity error",
+	"Instruction Cache Bank A ECC or parity error",
+	"Instruction Cache Bank B ECC or parity error",
+	"Instruction Tag Cache Bank A ECC or parity error",
+	"Instruction Tag Cache Bank B ECC or parity error",
+	"System Hub Read Buffer ECC or parity error",
+	"MPDMA TVF DVSEC Memory ECC or parity error",
+	"MPDMA TVF MMIO Mailbox0 ECC or parity error",
+	"MPDMA TVF MMIO Mailbox1 ECC or parity error",
+	"MPDMA TVF Doorbell Memory ECC or parity error",
+	"MPDMA TVF SDP Slave Memory 0 ECC or parity error",
+	"MPDMA TVF SDP Slave Memory 1 ECC or parity error",
+	"MPDMA TVF SDP Slave Memory 2 ECC or parity error",
+	"MPDMA TVF SDP Master Memory 0 ECC or parity error",
+	"MPDMA TVF SDP Master Memory 1 ECC or parity error",
+	"MPDMA TVF SDP Master Memory 2 ECC or parity error",
+	"MPDMA TVF SDP Master Memory 3 ECC or parity error",
+	"MPDMA TVF SDP Master Memory 4 ECC or parity error",
+	"MPDMA TVF SDP Master Memory 5 ECC or parity error",
+	"MPDMA TVF SDP Master Memory 6 ECC or parity error",
+	"MPDMA PTE Command FIFO ECC or parity error",
+	"MPDMA PTE Hub Data FIFO ECC or parity error",
+	"MPDMA PTE Internal Data FIFO ECC or parity error",
+	"MPDMA PTE Command Memory DMA ECC or parity error",
+	"MPDMA PTE Command Memory Internal ECC or parity error",
+	"MPDMA PTE DMA Completion FIFO ECC or parity error",
+	"MPDMA PTE Tablewalk Completion FIFO ECC or parity error",
+	"MPDMA PTE Descriptor Completion FIFO ECC or parity error",
+	"MPDMA PTE ReadOnly Completion FIFO ECC or parity error",
+	"MPDMA PTE DirectWrite Completion FIFO ECC or parity error",
+	"SDP Watchdog Timer expired",
+};
+
 static const char * const smca_nbio_mce_desc[] = {
 	"ECC or Parity error",
 	"PCIE error",
@@ -458,11 +515,66 @@ static const char * const smca_xgmiphy_mce_desc[] = {
 	"PHY APB error",
 };
 
-static const char * const smca_waflphy_mce_desc[] = {
-	"RAM ECC Error",
-	"ARC instruction buffer parity error",
-	"ARC data buffer parity error",
-	"PHY APB error",
+static const char * const smca_nbif_mce_desc[] = {
+	"Timeout error from GMI",
+	"SRAM ECC error",
+	"NTB Error Event",
+	"SDP Parity error",
+};
+
+static const char * const smca_sata_mce_desc[] = {
+	"Parity error for port 0",
+	"Parity error for port 1",
+	"Parity error for port 2",
+	"Parity error for port 3",
+	"Parity error for port 4",
+	"Parity error for port 5",
+	"Parity error for port 6",
+	"Parity error for port 7",
+};
+
+static const char * const smca_usb_mce_desc[] = {
+	"Parity error or ECC error for S0 RAM0",
+	"Parity error or ECC error for S0 RAM1",
+	"Parity error or ECC error for S0 RAM2",
+	"Parity error for PHY RAM0",
+	"Parity error for PHY RAM1",
+	"AXI Slave Response error",
+};
+
+static const char * const smca_gmipcs_mce_desc[] = {
+	"Data Loss Error",
+	"Training Error",
+	"Replay Parity Error",
+	"Rx Fifo Underflow Error",
+	"Rx Fifo Overflow Error",
+	"CRC Error",
+	"BER Exceeded Error",
+	"Tx Fifo Underflow Error",
+	"Replay Buffer Parity Error",
+	"Tx Overflow Error",
+	"Replay Fifo Overflow Error",
+	"Replay Fifo Underflow Error",
+	"Elastic Fifo Overflow Error",
+	"Deskew Error",
+	"Offline Error",
+	"Data Startup Limit Error",
+	"FC Init Timeout Error",
+	"Recovery Timeout Error",
+	"Ready Serial Timeout Error",
+	"Ready Serial Attempt Error",
+	"Recovery Attempt Error",
+	"Recovery Relock Attempt Error",
+	"Deskew Abort Error",
+	"Rx Buffer Error",
+	"Rx LFDS Fifo Overflow Error",
+	"Rx LFDS Fifo Underflow Error",
+	"LinkSub Tx Timeout Error",
+	"LinkSub Rx Timeout Error",
+	"Rx CMD Pocket Error",
+	"LFDS Training Timeout Error",
+	"LFDS FC Init Timeout Error",
+	"Data Loss Error",
 };
 
 struct smca_mce_desc {
@@ -490,12 +602,21 @@ static struct smca_mce_desc smca_mce_descs[] = {
 	[SMCA_SMU]	= { smca_smu_mce_desc,	ARRAY_SIZE(smca_smu_mce_desc)	},
 	[SMCA_SMU_V2]	= { smca_smu2_mce_desc,	ARRAY_SIZE(smca_smu2_mce_desc)	},
 	[SMCA_MP5]	= { smca_mp5_mce_desc,	ARRAY_SIZE(smca_mp5_mce_desc)	},
+	[SMCA_MPDMA]	= { smca_mpdma_mce_desc,	ARRAY_SIZE(smca_mpdma_mce_desc)	},
 	[SMCA_NBIO]	= { smca_nbio_mce_desc,	ARRAY_SIZE(smca_nbio_mce_desc)	},
 	[SMCA_PCIE]	= { smca_pcie_mce_desc,	ARRAY_SIZE(smca_pcie_mce_desc)	},
 	[SMCA_PCIE_V2]	= { smca_pcie2_mce_desc,   ARRAY_SIZE(smca_pcie2_mce_desc)	},
 	[SMCA_XGMI_PCS]	= { smca_xgmipcs_mce_desc, ARRAY_SIZE(smca_xgmipcs_mce_desc)	},
+	/* NBIF and SHUB have the same error descriptions, for now. */
+	[SMCA_NBIF]	= { smca_nbif_mce_desc, ARRAY_SIZE(smca_nbif_mce_desc)	},
+	[SMCA_SHUB]	= { smca_nbif_mce_desc, ARRAY_SIZE(smca_nbif_mce_desc)	},
+	[SMCA_SATA]	= { smca_sata_mce_desc, ARRAY_SIZE(smca_sata_mce_desc)	},
+	[SMCA_USB]	= { smca_usb_mce_desc,	ARRAY_SIZE(smca_usb_mce_desc)	},
+	[SMCA_GMI_PCS]	= { smca_gmipcs_mce_desc,  ARRAY_SIZE(smca_gmipcs_mce_desc)	},
+	/* All the PHY bank types have the same error descriptions, for now. */
 	[SMCA_XGMI_PHY]	= { smca_xgmiphy_mce_desc, ARRAY_SIZE(smca_xgmiphy_mce_desc)	},
-	[SMCA_WAFL_PHY]	= { smca_waflphy_mce_desc, ARRAY_SIZE(smca_waflphy_mce_desc)	},
+	[SMCA_WAFL_PHY]	= { smca_xgmiphy_mce_desc, ARRAY_SIZE(smca_xgmiphy_mce_desc)	},
+	[SMCA_GMI_PHY]	= { smca_xgmiphy_mce_desc, ARRAY_SIZE(smca_xgmiphy_mce_desc)	},
 };
 
 static bool f12h_mc0_mce(u16 ec, u8 xec)
-- 
2.25.1