RAS/AMD/ATL: Add MI300 support

AMD MI300 systems include on-die HBM3 memory and a unique topology. And
they fall under Data Fabric version 4.5 in overall design.

Generally, topology information (IDs, etc.) is gathered from Data Fabric
registers. However, the unique topology for MI300 means that some
topology information is fixed in hardware and follows arbitrary
mappings. Furthermore, not all hardware instances are software-visible,
so register accesses must be adjusted.

Recognize and add helper functions for the new MI300 interleave modes.
Add lookup tables for fixed values where appropriate. Adjust how Die and
Node IDs are found and used.

Also, fix some register bitmasks that were mislabeled.

Signed-off-by: Muralidhara M K <muralidhara.mk@amd.com>
Co-developed-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20240128155950.1434067-1-yazen.ghannam@amd.com

1 files changed, 51 insertions, 0 deletions

diff --git a/drivers/ras/amd/atl/umc.c b/drivers/ras/amd/atl/umc.c
index 9d51e4954687..7bfa21a582f0 100644
--- a/drivers/ras/amd/atl/umc.c
+++ b/drivers/ras/amd/atl/umc.c
@@ -12,9 +12,57 @@
 
 #include "internal.h"
 
+/*
+ * MI300 has a fixed, model-specific mapping between a UMC instance and
+ * its related Data Fabric Coherent Station instance.
+ *
+ * The MCA_IPID_UMC[InstanceId] field holds a unique identifier for the
+ * UMC instance within a Node. Use this to find the appropriate Coherent
+ * Station ID.
+ *
+ * Redundant bits were removed from the map below.
+ */
+static const u16 umc_coh_st_map[32] = {
+	0x393, 0x293, 0x193, 0x093,
+	0x392, 0x292, 0x192, 0x092,
+	0x391, 0x291, 0x191, 0x091,
+	0x390, 0x290, 0x190, 0x090,
+	0x793, 0x693, 0x593, 0x493,
+	0x792, 0x692, 0x592, 0x492,
+	0x791, 0x691, 0x591, 0x491,
+	0x790, 0x690, 0x590, 0x490,
+};
+
+#define UMC_ID_MI300 GENMASK(23, 12)
+static u8 get_coh_st_inst_id_mi300(struct atl_err *err)
+{
+	u16 umc_id = FIELD_GET(UMC_ID_MI300, err->ipid);
+	u8 i;
+
+	for (i = 0; i < ARRAY_SIZE(umc_coh_st_map); i++) {
+		if (umc_id == umc_coh_st_map[i])
+			break;
+	}
+
+	WARN_ON_ONCE(i >= ARRAY_SIZE(umc_coh_st_map));
+
+	return i;
+}
+
+#define MCA_IPID_INST_ID_HI	GENMASK_ULL(47, 44)
 static u8 get_die_id(struct atl_err *err)
 {
 	/*
+	 * AMD Node ID is provided in MCA_IPID[InstanceIdHi], and this
+	 * needs to be divided by 4 to get the internal Die ID.
+	 */
+	if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous) {
+		u8 node_id = FIELD_GET(MCA_IPID_INST_ID_HI, err->ipid);
+
+		return node_id >> 2;
+	}
+
+	/*
 	 * For CPUs, this is the AMD Node ID modulo the number
 	 * of AMD Nodes per socket.
 	 */
@@ -24,6 +72,9 @@ static u8 get_die_id(struct atl_err *err)
 #define UMC_CHANNEL_NUM	GENMASK(31, 20)
 static u8 get_coh_st_inst_id(struct atl_err *err)
 {
+	if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous)
+		return get_coh_st_inst_id_mi300(err);
+
 	return FIELD_GET(UMC_CHANNEL_NUM, err->ipid);
 }