Re: [PATCH 5.4.y] usb: dwc3: qcom: Don't leave BCR asserted

[Sasha Levin <sashal@kernel.org>]

On Mon, Jul 21, 2025 at 09:33:11PM +0530, Harshit Mogalapalli wrote:
>Hi Sasha,
>
>On 21/07/25 21:21, Sasha Levin wrote:
>>From: Krishna Kurapati <krishna.kurapati@oss.qualcomm.com>
>>
>>[ Upstream commit ef8abc0ba49ce717e6bc4124e88e59982671f3b5 ]
>>
>>Leaving the USB BCR asserted prevents the associated GDSC to turn on. This
>>blocks any subsequent attempts of probing the device, e.g. after a probe
>>deferral, with the following showing in the log:
>>
>>[    1.332226] usb30_prim_gdsc status stuck at 'off'
>>
>>Leave the BCR deasserted when exiting the driver to avoid this issue.
>>
>>Cc: stable <stable@kernel.org>
>>Fixes: a4333c3a6ba9 ("usb: dwc3: Add Qualcomm DWC3 glue driver")
>>Acked-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
>>Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
>>Signed-off-by: Krishna Kurapati <krishna.kurapati@oss.qualcomm.com>
>>Link: https://lore.kernel.org/r/20250709132900.3408752-1-krishna.kurapati@oss.qualcomm.com
>>Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
>>[ adapted to individual clock management API instead of bulk clock operations ]
>>Signed-off-by: Sasha Levin <sashal@kernel.org>
>>---
>>  drivers/usb/dwc3/dwc3-qcom.c | 8 +++-----
>>  1 file changed, 3 insertions(+), 5 deletions(-)
>>
>>diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c
>>index 742be1e07a01d..4874a6442c806 100644
>>--- a/drivers/usb/dwc3/dwc3-qcom.c
>>+++ b/drivers/usb/dwc3/dwc3-qcom.c
>>@@ -615,13 +615,13 @@ static int dwc3_qcom_probe(struct platform_device *pdev)
>>  	ret = reset_control_deassert(qcom->resets);
>>  	if (ret) {
>>  		dev_err(&pdev->dev, "failed to deassert resets, err=%d\n", ret);
>>-		goto reset_assert;
>>+		return ret;
>>  	}
>>  	ret = dwc3_qcom_clk_init(qcom, of_clk_get_parent_count(np));
>>  	if (ret) {
>>  		dev_err(dev, "failed to get clocks\n");
>>-		goto reset_assert;
>>+		return ret;
>>  	}
>>  	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
>>@@ -700,8 +700,6 @@ static int dwc3_qcom_probe(struct platform_device *pdev)
>>  		clk_disable_unprepare(qcom->clks[i]);
>>  		clk_put(qcom->clks[i]);
>>  	}
>>-reset_assert:
>>-	reset_control_assert(qcom->resets);
>>  	return ret;
>>  }
>>@@ -725,7 +723,7 @@ static int dwc3_qcom_remove(struct platform_device *pdev)
>>  	}
>>  	qcom->num_clocks = 0;
>>-	reset_control_assert(qcom->resets);
>>+	dwc3_qcom_interconnect_exit(qcom);
>
>^^ This part of diff doesn't look good to me. Can you please double 
>check the conflict resolution ? (Probably shouldn't have addition in 
>this hunk)

You're right! It came from the 5.10 backport which I've cherry picked
onto 5.4. I'll resend.

-- 
Thanks,
Sasha