x86/CPU/AMD: Print the reason for the last reset

The following register contains bits that indicate the cause for the
previous reset.

  PMx000000C0 (FCH::PM::S5_RESET_STATUS)

This is useful for debug. The reasons for reset are broken into 6 high level
categories. Decode it by category and print during boot.

Specifics within a category are split off into debugging documentation.

The register is accessed indirectly through a "PM" port in the FCH. Use
MMIO access in order to avoid restrictions with legacy port access.

Use a late_initcall() to ensure that MMIO has been set up before trying to
access the register.

This register was introduced with AMD Family 17h, so avoid access on older
families. There is no CPUID feature bit for this register.

  [ bp: Simplify the reason dumping loop.
    - merge a fix to not access an array element after the last one:
      https://lore.kernel.org/r/20250505133609.83933-1-superm1@kernel.org
      Reported-by: James Dutton <james.dutton@gmail.com>
      ]

  [ mingo:
    - Use consistent .rst formatting
    - Fix 'Sleep' class field to 'ACPI-State'
    - Standardize pin messages around the 'tripped' verbiage
    - Remove reference to ring-buffer printing & simplify the wording
    - Use curly braces for multi-line conditional statements ]

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Co-developed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/20250422234830.2840784-6-superm1@kernel.org

1 files changed, 54 insertions, 0 deletions

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 2b36379ff675..ded4a2a38016 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -9,6 +9,7 @@
 #include <linux/sched/clock.h>
 #include <linux/random.h>
 #include <linux/topology.h>
+#include <asm/amd/fch.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
 #include <asm/cacheinfo.h>
@@ -1237,3 +1238,56 @@ void amd_check_microcode(void)
 	if (cpu_feature_enabled(X86_FEATURE_ZEN2))
 		on_each_cpu(zenbleed_check_cpu, NULL, 1);
 }
+
+static const char * const s5_reset_reason_txt[] = {
+	[0]  = "thermal pin BP_THERMTRIP_L was tripped",
+	[1]  = "power button was pressed for 4 seconds",
+	[2]  = "shutdown pin was tripped",
+	[4]  = "remote ASF power off command was received",
+	[9]  = "internal CPU thermal limit was tripped",
+	[16] = "system reset pin BP_SYS_RST_L was tripped",
+	[17] = "software issued PCI reset",
+	[18] = "software wrote 0x4 to reset control register 0xCF9",
+	[19] = "software wrote 0x6 to reset control register 0xCF9",
+	[20] = "software wrote 0xE to reset control register 0xCF9",
+	[21] = "ACPI power state transition occurred",
+	[22] = "keyboard reset pin KB_RST_L was tripped",
+	[23] = "internal CPU shutdown event occurred",
+	[24] = "system failed to boot before failed boot timer expired",
+	[25] = "hardware watchdog timer expired",
+	[26] = "remote ASF reset command was received",
+	[27] = "an uncorrected error caused a data fabric sync flood event",
+	[29] = "FCH and MP1 failed warm reset handshake",
+	[30] = "a parity error occurred",
+	[31] = "a software sync flood event occurred",
+};
+
+static __init int print_s5_reset_status_mmio(void)
+{
+	unsigned long value;
+	void __iomem *addr;
+	int i;
+
+	if (!cpu_feature_enabled(X86_FEATURE_ZEN))
+		return 0;
+
+	addr = ioremap(FCH_PM_BASE + FCH_PM_S5_RESET_STATUS, sizeof(value));
+	if (!addr)
+		return 0;
+
+	value = ioread32(addr);
+	iounmap(addr);
+
+	for (i = 0; i < ARRAY_SIZE(s5_reset_reason_txt); i++) {
+		if (!(value & BIT(i)))
+			continue;
+
+		if (s5_reset_reason_txt[i]) {
+			pr_info("x86/amd: Previous system reset reason [0x%08lx]: %s\n",
+				value, s5_reset_reason_txt[i]);
+		}
+	}
+
+	return 0;
+}
+late_initcall(print_s5_reset_status_mmio);