habanalabs: support DEVICE_UNUSABLE error indication from FW

In case of multiple ECC errors, FW will set the DEVICE_UNUSABLE bit.
On boot-up, the driver will therefore fail inserting the device.

Signed-off-by: Koby Elbaz <kelbaz@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>

diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
index 092691a..d81a8d5 100644 (file)
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -342,6 +342,9 @@ static int fw_read_errors(struct hl_device *hdev, u32 boot_err0_reg,
                dev_err(hdev->dev, "Device boot error - eFuse failure\n");
        if (err_val & CPU_BOOT_ERR0_PLL_FAIL)
                dev_err(hdev->dev, "Device boot error - PLL failure\n");
+       if (err_val & CPU_BOOT_ERR0_DEVICE_UNUSABLE_FAIL)
+               dev_err(hdev->dev,
+                       "Device boot error - device unusable failure\n");
 
        security_val = RREG32(cpu_security_boot_status_reg);
        if (security_val & CPU_BOOT_DEV_STS0_ENABLED)

diff --git a/drivers/misc/habanalabs/include/common/hl_boot_if.h b/drivers/misc/habanalabs/include/common/hl_boot_if.h
index 1717874..980b432 100644 (file)
--- a/drivers/misc/habanalabs/include/common/hl_boot_if.h
+++ b/drivers/misc/habanalabs/include/common/hl_boot_if.h
@@ -73,6 +73,9 @@
  * CPU_BOOT_ERR0_PLL_FAIL              PLL settings failed, meaning that one
  *                                     of the PLLs remains in REF_CLK
  *
+ * CPU_BOOT_ERR0_DEVICE_UNUSABLE_FAIL  Device is unusable and customer support
+ *                                     should be contacted.
+ *
  * CPU_BOOT_ERR0_ENABLED               Error registers enabled.
  *                                     This is a main indication that the
  *                                     running FW populates the error
@@ -92,6 +95,7 @@
 #define CPU_BOOT_ERR0_PRI_IMG_VER_FAIL         (1 << 10)
 #define CPU_BOOT_ERR0_SEC_IMG_VER_FAIL         (1 << 11)
 #define CPU_BOOT_ERR0_PLL_FAIL                 (1 << 12)
+#define CPU_BOOT_ERR0_DEVICE_UNUSABLE_FAIL     (1 << 13)
 #define CPU_BOOT_ERR0_ENABLED                  (1 << 31)
 
 /*