RAS/AMD/ATL: Translate normalized to system physical addresses using PRM

JIRA: https://issues.redhat.com/browse/RHEL-22695
Tested: sanity

commit 26e43c9
Author: John Allen <[email protected]>
Date:   Tue Jul 30 15:17:31 2024 +0000

    RAS/AMD/ATL: Translate normalized to system physical addresses using PRM

    AMD Zen-based systems report memory error addresses through machine
    check banks representing Unified Memory Controllers (UMCs) in the form
    of UMC relative "normalized" addresses. A normalized address must be
    converted to a system physical address to be usable by the OS.

    Future AMD platforms will provide a UEFI PRM module that implements a
    number of address translation PRM handlers. This will provide an
    interface for the OS to call platform specific code without requiring
    the use of SMM or other heavy firmware operations.

    Add support for the normalized to system physical address translation
    PRM handler in the AMD Address Translation Library and prefer it over
    native code if available. The GUID and parameter buffer structure are
    specific to the normalized to system physical address handler provided
    by the address translation PRM module included in future AMD systems.

    The address translation PRM module is documented in chapter 22 of the
    publicly available "AMD Family 1Ah Models 00h–0Fh and Models 10h–1Fh
    ACPI v6.5 Porting Guide".

      [ bp: Massage commit message. ]

    Signed-off-by: John Allen <[email protected]>
    Signed-off-by: Borislav Petkov (AMD) <[email protected]>
    Link: https://lore.kernel.org/r/[email protected]

Signed-off-by: Aristeu Rozanski <[email protected]>

Author: aristeu

drivers/ras/amd/atl/Kconfig

@@ -19,3 +19,7 @@ config AMD_ATL
 
 	  Enable this option if using DRAM ECC on Zen-based systems
 	  and OS-based error handling.
+
+config AMD_ATL_PRM
+	depends on AMD_ATL && ACPI_PRMT
+	def_bool y

drivers/ras/amd/atl/Makefile

@@ -15,4 +15,6 @@ amd_atl-y		+= map.o
 amd_atl-y		+= system.o
 amd_atl-y		+= umc.o
 
+amd_atl-$(CONFIG_AMD_ATL_PRM) += prm.o
+
 obj-$(CONFIG_AMD_ATL)	+= amd_atl.o

drivers/ras/amd/atl/internal.h

@@ -234,6 +234,16 @@ int dehash_address(struct addr_ctx *ctx);
 unsigned long norm_to_sys_addr(u8 socket_id, u8 die_id, u8 coh_st_inst_id, unsigned long addr);
 unsigned long convert_umc_mca_addr_to_sys_addr(struct atl_err *err);
 
+#ifdef CONFIG_AMD_ATL_PRM
+unsigned long prm_umc_norm_to_sys_addr(u8 socket_id, u64 umc_bank_inst_id, unsigned long addr);
+#else
+static inline unsigned long prm_umc_norm_to_sys_addr(u8 socket_id, u64 umc_bank_inst_id,
+						     unsigned long addr)
+{
+       return -ENODEV;
+}
+#endif
+
 /*
  * Make a gap in @data that is @num_bits long starting at @bit_num.
  * e.g. data		= 11111111'b

drivers/ras/amd/atl/prm.c

@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * AMD Address Translation Library
+ *
+ * prm.c : Plumbing code for ACPI Platform Runtime Mechanism (PRM)
+ *
+ * Information on AMD PRM modules and handlers including the GUIDs and buffer
+ * structures used here are defined in the AMD ACPI Porting Guide in the
+ * chapter "Platform Runtime Mechanism Table (PRMT)"
+ *
+ * Copyright (c) 2024, Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Author: John Allen <[email protected]>
+ */
+
+#include "internal.h"
+
+#include <linux/prmt.h>
+
+/*
+ * PRM parameter buffer - normalized to system physical address, as described
+ * in the "PRM Parameter Buffer" section of the AMD ACPI Porting Guide.
+ */
+struct norm_to_sys_param_buf {
+	u64 norm_addr;
+	u8 socket;
+	u64 bank_id;
+	void *out_buf;
+} __packed;
+
+static const guid_t norm_to_sys_guid = GUID_INIT(0xE7180659, 0xA65D, 0x451D,
+						 0x92, 0xCD, 0x2B, 0x56, 0xF1,
+						 0x2B, 0xEB, 0xA6);
+
+unsigned long prm_umc_norm_to_sys_addr(u8 socket_id, u64 bank_id, unsigned long addr)
+{
+	struct norm_to_sys_param_buf p_buf;
+	unsigned long ret_addr;
+	int ret;
+
+	p_buf.norm_addr = addr;
+	p_buf.socket    = socket_id;
+	p_buf.bank_id   = bank_id;
+	p_buf.out_buf   = &ret_addr;
+
+	ret = acpi_call_prm_handler(norm_to_sys_guid, &p_buf);
+	if (!ret)
+		return ret_addr;
+
+	if (ret == -ENODEV)
+		pr_debug("PRM module/handler not available\n");
+	else
+		pr_notice_once("PRM address translation failed\n");
+
+	return ret;
+}

drivers/ras/amd/atl/umc.c

@@ -401,9 +401,14 @@ unsigned long convert_umc_mca_addr_to_sys_addr(struct atl_err *err)
 	u8 coh_st_inst_id = get_coh_st_inst_id(err);
 	unsigned long addr = get_addr(err->addr);
 	u8 die_id = get_die_id(err);
+	unsigned long ret_addr;
 
 	pr_debug("socket_id=0x%x die_id=0x%x coh_st_inst_id=0x%x addr=0x%016lx",
 		 socket_id, die_id, coh_st_inst_id, addr);
 
+	ret_addr = prm_umc_norm_to_sys_addr(socket_id, err->ipid, addr);
+	if (!IS_ERR_VALUE(ret_addr))
+		return ret_addr;
+
 	return norm_to_sys_addr(socket_id, die_id, coh_st_inst_id, addr);
 }