This is a note to let you know that I've just added the patch titled habanalabs: extend fatal messages to contain PCI info to the 6.1-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: habanalabs-extend-fatal-messages-to-contain-pci-info.patch and it can be found in the queue-6.1 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. commit a3fa8cecdebad9f79ecb8fa1b6c6459398785a05 Author: Moti Haimovski <mhaimovski@xxxxxxxxx> Date: Thu Dec 29 12:44:09 2022 +0200 habanalabs: extend fatal messages to contain PCI info [ Upstream commit 2a0a839b6a28f7c4c528bb75b740c7f38ef79a37 ] This commit attaches the PCI device address to driver fatal messages in order to ease debugging in multi-device setups. Signed-off-by: Moti Haimovski <mhaimovski@xxxxxxxxx> Reviewed-by: Oded Gabbay <ogabbay@xxxxxxxxxx> Signed-off-by: Oded Gabbay <ogabbay@xxxxxxxxxx> Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx> diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c index 233d8b46c831f..e0dca445abf14 100644 --- a/drivers/misc/habanalabs/common/device.c +++ b/drivers/misc/habanalabs/common/device.c @@ -1458,7 +1458,8 @@ int hl_device_reset(struct hl_device *hdev, u32 flags) if (rc == -EBUSY) { if (hdev->device_fini_pending) { dev_crit(hdev->dev, - "Failed to kill all open processes, stopping hard reset\n"); + "%s Failed to kill all open processes, stopping hard reset\n", + dev_name(&(hdev)->pdev->dev)); goto out_err; } @@ -1468,7 +1469,8 @@ int hl_device_reset(struct hl_device *hdev, u32 flags) if (rc) { dev_crit(hdev->dev, - "Failed to kill all open processes, stopping hard reset\n"); + "%s Failed to kill all open processes, stopping hard reset\n", + dev_name(&(hdev)->pdev->dev)); goto out_err; } @@ -1519,14 +1521,16 @@ int hl_device_reset(struct hl_device *hdev, u32 flags) * ensure driver puts the driver in a unusable state */ dev_crit(hdev->dev, - "Consecutive FW fatal errors received, stopping hard reset\n"); + "%s Consecutive FW fatal errors received, stopping hard reset\n", + dev_name(&(hdev)->pdev->dev)); rc = -EIO; goto out_err; } if (hdev->kernel_ctx) { dev_crit(hdev->dev, - "kernel ctx was alive during hard reset, something is terribly wrong\n"); + "%s kernel ctx was alive during hard reset, something is terribly wrong\n", + dev_name(&(hdev)->pdev->dev)); rc = -EBUSY; goto out_err; } @@ -1645,9 +1649,13 @@ int hl_device_reset(struct hl_device *hdev, u32 flags) hdev->reset_info.needs_reset = false; if (hard_reset) - dev_info(hdev->dev, "Successfully finished resetting the device\n"); + dev_info(hdev->dev, + "Successfully finished resetting the %s device\n", + dev_name(&(hdev)->pdev->dev)); else - dev_dbg(hdev->dev, "Successfully finished resetting the device\n"); + dev_dbg(hdev->dev, + "Successfully finished resetting the %s device\n", + dev_name(&(hdev)->pdev->dev)); if (hard_reset) { hdev->reset_info.hard_reset_cnt++; @@ -1681,7 +1689,9 @@ int hl_device_reset(struct hl_device *hdev, u32 flags) hdev->reset_info.in_compute_reset = 0; if (hard_reset) { - dev_err(hdev->dev, "Failed to reset! Device is NOT usable\n"); + dev_err(hdev->dev, + "%s Failed to reset! Device is NOT usable\n", + dev_name(&(hdev)->pdev->dev)); hdev->reset_info.hard_reset_cnt++; } else if (reset_upon_device_release) { spin_unlock(&hdev->reset_info.lock); @@ -2004,7 +2014,8 @@ int hl_device_init(struct hl_device *hdev, struct class *hclass) } dev_notice(hdev->dev, - "Successfully added device to habanalabs driver\n"); + "Successfully added device %s to habanalabs driver\n", + dev_name(&(hdev)->pdev->dev)); hdev->init_done = true; @@ -2053,11 +2064,11 @@ int hl_device_init(struct hl_device *hdev, struct class *hclass) device_cdev_sysfs_add(hdev); if (hdev->pdev) dev_err(&hdev->pdev->dev, - "Failed to initialize hl%d. Device is NOT usable !\n", - hdev->cdev_idx); + "Failed to initialize hl%d. Device %s is NOT usable !\n", + hdev->cdev_idx, dev_name(&(hdev)->pdev->dev)); else - pr_err("Failed to initialize hl%d. Device is NOT usable !\n", - hdev->cdev_idx); + pr_err("Failed to initialize hl%d. Device %s is NOT usable !\n", + hdev->cdev_idx, dev_name(&(hdev)->pdev->dev)); return rc; } @@ -2113,7 +2124,8 @@ void hl_device_fini(struct hl_device *hdev) if (ktime_compare(ktime_get(), timeout) > 0) { dev_crit(hdev->dev, - "Failed to remove device because reset function did not finish\n"); + "%s Failed to remove device because reset function did not finish\n", + dev_name(&(hdev)->pdev->dev)); return; } }