[PATCH AUTOSEL 5.19 25/63] habanalabs: ignore EEPROM errors during boot

From: Sasha Levin
Date: Wed Oct 12 2022 - 20:29:51 EST


From: Ofir Bitton <obitton@xxxxxxxxx>

[ Upstream commit d155df4f628a5312a485235aa8cc5ba78e11ea65 ]

EEPROM errors reported by firmware are basically warnings and
should not fail the boot process.

Signed-off-by: Ofir Bitton <obitton@xxxxxxxxx>
Reviewed-by: Oded Gabbay <ogabbay@xxxxxxxxxx>
Signed-off-by: Oded Gabbay <ogabbay@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
drivers/misc/habanalabs/common/firmware_if.c | 9 +++++++++
drivers/misc/habanalabs/include/common/hl_boot_if.h | 5 +++++
2 files changed, 14 insertions(+)

diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
index 828a36af5b14..bb1b2d6213a5 100644
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -521,6 +521,15 @@ static bool fw_report_boot_dev0(struct hl_device *hdev, u32 err_val,
dev_dbg(hdev->dev, "Device status0 %#x\n", sts_val);

/* All warnings should go here in order not to reach the unknown error validation */
+ if (err_val & CPU_BOOT_ERR0_EEPROM_FAIL) {
+ dev_warn(hdev->dev,
+ "Device boot warning - EEPROM failure detected, default settings applied\n");
+ /* This is a warning so we don't want it to disable the
+ * device
+ */
+ err_val &= ~CPU_BOOT_ERR0_EEPROM_FAIL;
+ }
+
if (err_val & CPU_BOOT_ERR0_DRAM_SKIPPED) {
dev_warn(hdev->dev,
"Device boot warning - Skipped DRAM initialization\n");
diff --git a/drivers/misc/habanalabs/include/common/hl_boot_if.h b/drivers/misc/habanalabs/include/common/hl_boot_if.h
index 15f91ae9de6e..d4858e636fa9 100644
--- a/drivers/misc/habanalabs/include/common/hl_boot_if.h
+++ b/drivers/misc/habanalabs/include/common/hl_boot_if.h
@@ -34,6 +34,7 @@ enum cpu_boot_err {
CPU_BOOT_ERR_BINNING_FAIL = 19,
CPU_BOOT_ERR_TPM_FAIL = 20,
CPU_BOOT_ERR_TMP_THRESH_INIT_FAIL = 21,
+ CPU_BOOT_ERR_EEPROM_FAIL = 22,
CPU_BOOT_ERR_ENABLED = 31,
CPU_BOOT_ERR_SCND_EN = 63,
CPU_BOOT_ERR_LAST = 64 /* we have 2 registers of 32 bits */
@@ -115,6 +116,9 @@ enum cpu_boot_err {
* CPU_BOOT_ERR0_TMP_THRESH_INIT_FAIL Failed to set threshold for tmperature
* sensor.
*
+ * CPU_BOOT_ERR_EEPROM_FAIL Failed reading EEPROM data. Defaults
+ * are used.
+ *
* CPU_BOOT_ERR0_ENABLED Error registers enabled.
* This is a main indication that the
* running FW populates the error
@@ -139,6 +143,7 @@ enum cpu_boot_err {
#define CPU_BOOT_ERR0_BINNING_FAIL (1 << CPU_BOOT_ERR_BINNING_FAIL)
#define CPU_BOOT_ERR0_TPM_FAIL (1 << CPU_BOOT_ERR_TPM_FAIL)
#define CPU_BOOT_ERR0_TMP_THRESH_INIT_FAIL (1 << CPU_BOOT_ERR_TMP_THRESH_INIT_FAIL)
+#define CPU_BOOT_ERR0_EEPROM_FAIL (1 << CPU_BOOT_ERR_EEPROM_FAIL)
#define CPU_BOOT_ERR0_ENABLED (1 << CPU_BOOT_ERR_ENABLED)
#define CPU_BOOT_ERR1_ENABLED (1 << CPU_BOOT_ERR_ENABLED)

--
2.35.1