platform/x86: amd-pmc: Add support for logging SMU metrics

SMU provides a way to dump the s0ix debug statistics in the form of a
metrics table via a of set special mailbox commands.

Add support to the driver which can send these commands to SMU and expose
the information received via debugfs. The information contains the s0ix
entry/exit, active time of each IP block etc.

As a side note, SMU subsystem logging is not supported on Picasso based
SoC's.

Signed-off-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210629084803.248498-5-Shyam-sundar.S-k@amd.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>

drivers/platform/x86/amd-pmc.c

@@ -46,6 +46,14 @@
 #define AMD_PMC_RESULT_CMD_UNKNOWN           0xFE
 #define AMD_PMC_RESULT_FAILED                0xFF
 
+/* SMU Message Definations */
+#define SMU_MSG_GETSMUVERSION		0x02
+#define SMU_MSG_LOG_GETDRAM_ADDR_HI	0x04
+#define SMU_MSG_LOG_GETDRAM_ADDR_LO	0x05
+#define SMU_MSG_LOG_START		0x06
+#define SMU_MSG_LOG_RESET		0x07
+#define SMU_MSG_LOG_DUMP_DATA		0x08
+#define SMU_MSG_GET_SUP_CONSTRAINTS	0x09
 /* List of supported CPU ids */
 #define AMD_CPU_ID_RV			0x15D0
 #define AMD_CPU_ID_RN			0x1630
@@ -55,17 +63,42 @@
 #define PMC_MSG_DELAY_MIN_US		100
 #define RESPONSE_REGISTER_LOOP_MAX	200
 
+#define SOC_SUBSYSTEM_IP_MAX	12
+#define DELAY_MIN_US		2000
+#define DELAY_MAX_US		3000
 enum amd_pmc_def {
 	MSG_TEST = 0x01,
 	MSG_OS_HINT_PCO,
 	MSG_OS_HINT_RN,
 };
 
+struct amd_pmc_bit_map {
+	const char *name;
+	u32 bit_mask;
+};
+
+static const struct amd_pmc_bit_map soc15_ip_blk[] = {
+	{"DISPLAY",	BIT(0)},
+	{"CPU",		BIT(1)},
+	{"GFX",		BIT(2)},
+	{"VDD",		BIT(3)},
+	{"ACP",		BIT(4)},
+	{"VCN",		BIT(5)},
+	{"ISP",		BIT(6)},
+	{"NBIO",	BIT(7)},
+	{"DF",		BIT(8)},
+	{"USB0",	BIT(9)},
+	{"USB1",	BIT(10)},
+	{"LAPIC",	BIT(11)},
+	{}
+};
+
 struct amd_pmc_dev {
 	void __iomem *regbase;
-	void __iomem *smu_base;
+	void __iomem *smu_virt_addr;
 	u32 base_addr;
 	u32 cpu_id;
+	u32 active_ips;
 	struct device *dev;
 	struct mutex lock; /* generic mutex lock */
 #if IS_ENABLED(CONFIG_DEBUG_FS)
@@ -74,6 +107,7 @@ struct amd_pmc_dev {
 };
 
 static struct amd_pmc_dev pmc;
+static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set, u32 *data, u8 msg, bool ret);
 
 static inline u32 amd_pmc_reg_read(struct amd_pmc_dev *dev, int reg_offset)
 {
@@ -85,9 +119,49 @@ static inline void amd_pmc_reg_write(struct amd_pmc_dev *dev, int reg_offset, u3
 	iowrite32(val, dev->regbase + reg_offset);
 }
 
+struct smu_metrics {
+	u32 table_version;
+	u32 hint_count;
+	u32 s0i3_cyclecount;
+	u32 timein_s0i2;
+	u64 timeentering_s0i3_lastcapture;
+	u64 timeentering_s0i3_totaltime;
+	u64 timeto_resume_to_os_lastcapture;
+	u64 timeto_resume_to_os_totaltime;
+	u64 timein_s0i3_lastcapture;
+	u64 timein_s0i3_totaltime;
+	u64 timein_swdrips_lastcapture;
+	u64 timein_swdrips_totaltime;
+	u64 timecondition_notmet_lastcapture[SOC_SUBSYSTEM_IP_MAX];
+	u64 timecondition_notmet_totaltime[SOC_SUBSYSTEM_IP_MAX];
+} __packed;
+
 #ifdef CONFIG_DEBUG_FS
 static int smu_fw_info_show(struct seq_file *s, void *unused)
 {
+	struct amd_pmc_dev *dev = s->private;
+	struct smu_metrics table;
+	int idx;
+
+	if (dev->cpu_id == AMD_CPU_ID_PCO)
+		return -EINVAL;
+
+	memcpy_fromio(&table, dev->smu_virt_addr, sizeof(struct smu_metrics));
+
+	seq_puts(s, "\n=== SMU Statistics ===\n");
+	seq_printf(s, "Table Version: %d\n", table.table_version);
+	seq_printf(s, "Hint Count: %d\n", table.hint_count);
+	seq_printf(s, "S0i3 Cycle Count: %d\n", table.s0i3_cyclecount);
+	seq_printf(s, "Time (in us) to S0i3: %lld\n", table.timeentering_s0i3_lastcapture);
+	seq_printf(s, "Time (in us) in S0i3: %lld\n", table.timein_s0i3_lastcapture);
+
+	seq_puts(s, "\n=== Active time (in us) ===\n");
+	for (idx = 0 ; idx < SOC_SUBSYSTEM_IP_MAX ; idx++) {
+		if (soc15_ip_blk[idx].bit_mask & dev->active_ips)
+			seq_printf(s, "%-8s : %lld\n", soc15_ip_blk[idx].name,
+				   table.timecondition_notmet_lastcapture[idx]);
+	}
+
 	return 0;
 }
 DEFINE_SHOW_ATTRIBUTE(smu_fw_info);
@@ -113,6 +187,32 @@ static inline void amd_pmc_dbgfs_unregister(struct amd_pmc_dev *dev)
 }
 #endif /* CONFIG_DEBUG_FS */
 
+static int amd_pmc_setup_smu_logging(struct amd_pmc_dev *dev)
+{
+	u32 phys_addr_low, phys_addr_hi;
+	u64 smu_phys_addr;
+
+	if (dev->cpu_id == AMD_CPU_ID_PCO)
+		return -EINVAL;
+
+	/* Get Active devices list from SMU */
+	amd_pmc_send_cmd(dev, 0, &dev->active_ips, SMU_MSG_GET_SUP_CONSTRAINTS, 1);
+
+	/* Get dram address */
+	amd_pmc_send_cmd(dev, 0, &phys_addr_low, SMU_MSG_LOG_GETDRAM_ADDR_LO, 1);
+	amd_pmc_send_cmd(dev, 0, &phys_addr_hi, SMU_MSG_LOG_GETDRAM_ADDR_HI, 1);
+	smu_phys_addr = ((u64)phys_addr_hi << 32 | phys_addr_low);
+
+	dev->smu_virt_addr = devm_ioremap(dev->dev, smu_phys_addr, sizeof(struct smu_metrics));
+	if (!dev->smu_virt_addr)
+		return -ENOMEM;
+
+	/* Start the logging */
+	amd_pmc_send_cmd(dev, 0, NULL, SMU_MSG_LOG_START, 0);
+
+	return 0;
+}
+
 static void amd_pmc_dump_registers(struct amd_pmc_dev *dev)
 {
 	u32 value;
@@ -127,10 +227,9 @@ static void amd_pmc_dump_registers(struct amd_pmc_dev *dev)
 	dev_dbg(dev->dev, "AMD_PMC_REGISTER_MESSAGE:%x\n", value);
 }
 
-static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set)
+static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set, u32 *data, u8 msg, bool ret)
 {
 	int rc;
-	u8 msg;
 	u32 val;
 
 	mutex_lock(&dev->lock);
@@ -150,8 +249,8 @@ static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set)
 	amd_pmc_reg_write(dev, AMD_PMC_REGISTER_ARGUMENT, set);
 
 	/* Write message ID to message ID register */
-	msg = (dev->cpu_id == AMD_CPU_ID_RN) ? MSG_OS_HINT_RN : MSG_OS_HINT_PCO;
 	amd_pmc_reg_write(dev, AMD_PMC_REGISTER_MESSAGE, msg);
+
 	/* Wait until we get a valid response */
 	rc = readx_poll_timeout(ioread32, dev->regbase + AMD_PMC_REGISTER_RESPONSE,
 				val, val != 0, PMC_MSG_DELAY_MIN_US,
@@ -163,6 +262,11 @@ static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set)
 
 	switch (val) {
 	case AMD_PMC_RESULT_OK:
+		if (ret) {
+			/* PMFW may take longer time to return back the data */
+			usleep_range(DELAY_MIN_US, 10 * DELAY_MAX_US);
+			*data = amd_pmc_reg_read(dev, AMD_PMC_REGISTER_ARGUMENT);
+		}
 		break;
 	case AMD_PMC_RESULT_CMD_REJECT_BUSY:
 		dev_err(dev->dev, "SMU not ready. err: 0x%x\n", val);
@@ -186,12 +290,29 @@ out_unlock:
 	return rc;
 }
 
+static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev)
+{
+	switch (dev->cpu_id) {
+	case AMD_CPU_ID_PCO:
+		return MSG_OS_HINT_PCO;
+	case AMD_CPU_ID_RN:
+		return MSG_OS_HINT_RN;
+	}
+	return -EINVAL;
+}
+
 static int __maybe_unused amd_pmc_suspend(struct device *dev)
 {
 	struct amd_pmc_dev *pdev = dev_get_drvdata(dev);
 	int rc;
+	u8 msg;
 
-	rc = amd_pmc_send_cmd(pdev, 1);
+	/* Reset and Start SMU logging - to monitor the s0i3 stats */
+	amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_RESET, 0);
+	amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_START, 0);
+
+	msg = amd_pmc_get_os_hint(pdev);
+	rc = amd_pmc_send_cmd(pdev, 1, NULL, msg, 0);
 	if (rc)
 		dev_err(pdev->dev, "suspend failed\n");
 
@@ -202,8 +323,13 @@ static int __maybe_unused amd_pmc_resume(struct device *dev)
 {
 	struct amd_pmc_dev *pdev = dev_get_drvdata(dev);
 	int rc;
+	u8 msg;
 
-	rc = amd_pmc_send_cmd(pdev, 0);
+	/* Let SMU know that we are looking for stats */
+	amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_DUMP_DATA, 0);
+
+	msg = amd_pmc_get_os_hint(pdev);
+	rc = amd_pmc_send_cmd(pdev, 0, NULL, msg, 0);
 	if (rc)
 		dev_err(pdev->dev, "resume failed\n");
 
@@ -226,8 +352,7 @@ static int amd_pmc_probe(struct platform_device *pdev)
 {
 	struct amd_pmc_dev *dev = &pmc;
 	struct pci_dev *rdev;
-	u32 base_addr_lo;
+	u32 base_addr_lo, base_addr_hi;
-	u32 base_addr_hi;
 	u64 base_addr;
 	int err;
 	u32 val;
@@ -279,6 +404,12 @@ static int amd_pmc_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	mutex_init(&dev->lock);
+
+	/* Use SMU to get the s0i3 debug stats */
+	err = amd_pmc_setup_smu_logging(dev);
+	if (err)
+		dev_err(dev->dev, "SMU debugging info not supported on this platform\n");
+
 	platform_set_drvdata(pdev, dev);
 	amd_pmc_dbgfs_register(dev);
 	return 0;