habanalabs: add "in device creation" status

On init, the disabled state is cleared right before hw_init and that
causes the device to report on "Operational" state before the device
initialization is finished. Although the char device is not yet exposed
to the user at this stage, the sysfs entries are exposed.

This can cause errors in monitoring applications that use the sysfs
entries.

In order to avoid this, a new state "in device creation" is introduced
to ne reported when the device is not disabled but is still in init
flow.

Signed-off-by: Omer Shpigelman <oshpigelman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>

diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c
index 3751c915f731d0fdaf3cc72f40ff7b6d3eb765a5..c2641030d9ffb3fca191286783d6229fa03ab744 100644 (file)
--- a/drivers/misc/habanalabs/common/device.c
+++ b/drivers/misc/habanalabs/common/device.c
@@ -23,6 +23,8 @@ enum hl_device_status hl_device_status(struct hl_device *hdev)
                status = HL_DEVICE_STATUS_NEEDS_RESET;
        else if (hdev->disabled)
                status = HL_DEVICE_STATUS_MALFUNCTION;
+       else if (!hdev->init_done)
+               status = HL_DEVICE_STATUS_IN_DEVICE_CREATION;
        else
                status = HL_DEVICE_STATUS_OPERATIONAL;
 
@@ -44,6 +46,7 @@ bool hl_device_operational(struct hl_device *hdev,
        case HL_DEVICE_STATUS_NEEDS_RESET:
                return false;
        case HL_DEVICE_STATUS_OPERATIONAL:
+       case HL_DEVICE_STATUS_IN_DEVICE_CREATION:
        default:
                return true;
        }

diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 1ca3a920ea6d05557151849e93a87b49e9bfdf86..7f4548f1d7e175e121a6a7b93615c06999fe38a8 100644 (file)
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -1990,7 +1990,7 @@ struct hl_state_dump_specs {
 
 #define HL_STR_MAX     32
 
-#define HL_DEV_STS_MAX (HL_DEVICE_STATUS_NEEDS_RESET + 1)
+#define HL_DEV_STS_MAX (HL_DEVICE_STATUS_LAST + 1)
 
 /* Theoretical limit only. A single host can only contain up to 4 or 8 PCIe
  * x16 cards. In extreme cases, there are hosts that can accommodate 16 cards.

diff --git a/drivers/misc/habanalabs/common/habanalabs_drv.c b/drivers/misc/habanalabs/common/habanalabs_drv.c
index 3df4313d72cd280c47dab30f57c6462c1703c111..2ef59fd465ba9265a69261dd24ed32e9b5a3f616 100644 (file)
--- a/drivers/misc/habanalabs/common/habanalabs_drv.c
+++ b/drivers/misc/habanalabs/common/habanalabs_drv.c
@@ -317,12 +317,16 @@ int create_hdev(struct hl_device **dev, struct pci_dev *pdev,
                hdev->asic_prop.fw_security_enabled = false;
 
        /* Assign status description string */
-       strncpy(hdev->status[HL_DEVICE_STATUS_MALFUNCTION],
-                                       "disabled", HL_STR_MAX);
+       strncpy(hdev->status[HL_DEVICE_STATUS_OPERATIONAL],
+                                       "operational", HL_STR_MAX);
        strncpy(hdev->status[HL_DEVICE_STATUS_IN_RESET],
                                        "in reset", HL_STR_MAX);
+       strncpy(hdev->status[HL_DEVICE_STATUS_MALFUNCTION],
+                                       "disabled", HL_STR_MAX);
        strncpy(hdev->status[HL_DEVICE_STATUS_NEEDS_RESET],
                                        "needs reset", HL_STR_MAX);
+       strncpy(hdev->status[HL_DEVICE_STATUS_IN_DEVICE_CREATION],
+                                       "in device creation", HL_STR_MAX);
 
        hdev->major = hl_major;
        hdev->reset_on_lockup = reset_on_lockup;

diff --git a/drivers/misc/habanalabs/common/sysfs.c b/drivers/misc/habanalabs/common/sysfs.c
index db72df282ef8dc2b51c893cae3923a82f3d45a6f..34f9f2779962a15a0c62142bc47719a1cb7e3c62 100644 (file)
--- a/drivers/misc/habanalabs/common/sysfs.c
+++ b/drivers/misc/habanalabs/common/sysfs.c
@@ -9,8 +9,7 @@
 
 #include <linux/pci.h>
 
-long hl_get_frequency(struct hl_device *hdev, u32 pll_index,
-                                                               bool curr)
+long hl_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr)
 {
        struct cpucp_packet pkt;
        u32 used_pll_idx;
@@ -44,8 +43,7 @@ long hl_get_frequency(struct hl_device *hdev, u32 pll_index,
        return (long) result;
 }
 
-void hl_set_frequency(struct hl_device *hdev, u32 pll_index,
-                                                               u64 freq)
+void hl_set_frequency(struct hl_device *hdev, u32 pll_index, u64 freq)
 {
        struct cpucp_packet pkt;
        u32 used_pll_idx;
@@ -285,16 +283,12 @@ static ssize_t status_show(struct device *dev, struct device_attribute *attr,
                                char *buf)
 {
        struct hl_device *hdev = dev_get_drvdata(dev);
-       char *str;
+       char str[HL_STR_MAX];
 
-       if (atomic_read(&hdev->in_reset))
-               str = "In reset";
-       else if (hdev->disabled)
-               str = "Malfunction";
-       else if (hdev->needs_reset)
-               str = "Needs Reset";
-       else
-               str = "Operational";
+       strscpy(str, hdev->status[hl_device_status(hdev)], HL_STR_MAX);
+
+       /* use uppercase for backward compatibility */
+       str[0] = 'A' + (str[0] - 'a');
 
        return sprintf(buf, "%s\n", str);
 }

diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index 6686b73a083491598c9174b16eef1ffff3da6ed0..7cc2a0f3f2f56e462bc2cef69aa73eb5c459bb49 100644 (file)
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -276,7 +276,9 @@ enum hl_device_status {
        HL_DEVICE_STATUS_OPERATIONAL,
        HL_DEVICE_STATUS_IN_RESET,
        HL_DEVICE_STATUS_MALFUNCTION,
-       HL_DEVICE_STATUS_NEEDS_RESET
+       HL_DEVICE_STATUS_NEEDS_RESET,
+       HL_DEVICE_STATUS_IN_DEVICE_CREATION,
+       HL_DEVICE_STATUS_LAST = HL_DEVICE_STATUS_IN_DEVICE_CREATION
 };
 
 enum hl_server_type {