ALSA: hda: intel: Allow repeatedly probing on codec configuration errors

It seems that a few recent AMD systems show the codec configuration
errors at the early boot, while loading the driver at a later stage
works magically.  Although the root cause of the error isn't clear,
it's certainly not bad to allow retrying the codec probe in such a
case if that helps.

This patch adds the capability for retrying the probe upon codec probe
errors on the certain AMD platforms.  The probe_work is changed to a
delayed work, and at the secondary call, it'll jump to the codec
probing.

Note that, not only adding the re-probing, this includes the behavior
changes in the codec configuration function.  Namely,
snd_hda_codec_configure() won't unregister the codec at errors any
longer.  Instead, its caller, azx_codec_configure() unregisters the
codecs with the probe failures *if* any codec has been successfully
configured.  If all codec probe failed, it doesn't unregister but let
it re-probed -- which is the most case we're seeing and this patch
tries to improve.

Even if the driver doesn't re-probe or give up, it will go to the
"free-all" error path, hence the leftover codecs shall be disabled /
deleted in anyway.

BugLink: https://bugzilla.suse.com/show_bug.cgi?id=1190801
Link: https://lore.kernel.org/r/20211006141940.2897-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>

1 files changed, 23 insertions, 6 deletions

diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 47777439961c..4d22e7adeee8 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -307,7 +307,8 @@ enum {
 /* quirks for AMD SB */
 #define AZX_DCAPS_PRESET_AMD_SB \
 	(AZX_DCAPS_NO_TCSEL | AZX_DCAPS_AMD_WORKAROUND |\
-	 AZX_DCAPS_SNOOP_TYPE(ATI) | AZX_DCAPS_PM_RUNTIME)
+	 AZX_DCAPS_SNOOP_TYPE(ATI) | AZX_DCAPS_PM_RUNTIME |\
+	 AZX_DCAPS_RETRY_PROBE)
 
 /* quirks for Nvidia */
 #define AZX_DCAPS_PRESET_NVIDIA \
@@ -1723,7 +1724,7 @@ static void azx_check_snoop_available(struct azx *chip)
 
 static void azx_probe_work(struct work_struct *work)
 {
-	struct hda_intel *hda = container_of(work, struct hda_intel, probe_work);
+	struct hda_intel *hda = container_of(work, struct hda_intel, probe_work.work);
 	azx_probe_continue(&hda->chip);
 }
 
@@ -1828,7 +1829,7 @@ static int azx_create(struct snd_card *card, struct pci_dev *pci,
 	}
 
 	/* continue probing in work context as may trigger request module */
-	INIT_WORK(&hda->probe_work, azx_probe_work);
+	INIT_DELAYED_WORK(&hda->probe_work, azx_probe_work);
 
 	*rchip = chip;
 
@@ -2142,7 +2143,7 @@ static int azx_probe(struct pci_dev *pci,
 #endif
 
 	if (schedule_probe)
-		schedule_work(&hda->probe_work);
+		schedule_delayed_work(&hda->probe_work, 0);
 
 	dev++;
 	if (chip->disabled)
@@ -2228,6 +2229,11 @@ static int azx_probe_continue(struct azx *chip)
 	int dev = chip->dev_index;
 	int err;
 
+	if (chip->disabled || hda->init_failed)
+		return -EIO;
+	if (hda->probe_retry)
+		goto probe_retry;
+
 	to_hda_bus(bus)->bus_probing = 1;
 	hda->probe_continued = 1;
 
@@ -2289,10 +2295,20 @@ static int azx_probe_continue(struct azx *chip)
 #endif
 	}
 #endif
+
+ probe_retry:
 	if (bus->codec_mask && !(probe_only[dev] & 1)) {
 		err = azx_codec_configure(chip);
-		if (err < 0)
+		if (err) {
+			if ((chip->driver_caps & AZX_DCAPS_RETRY_PROBE) &&
+			    ++hda->probe_retry < 60) {
+				schedule_delayed_work(&hda->probe_work,
+						      msecs_to_jiffies(1000));
+				return 0; /* keep things up */
+			}
+			dev_err(chip->card->dev, "Cannot probe codecs, giving up\n");
 			goto out_free;
+		}
 	}
 
 	err = snd_card_register(chip->card);
@@ -2322,6 +2338,7 @@ out_free:
 		display_power(chip, false);
 	complete_all(&hda->probe_wait);
 	to_hda_bus(bus)->bus_probing = 0;
+	hda->probe_retry = 0;
 	return 0;
 }
 
@@ -2347,7 +2364,7 @@ static void azx_remove(struct pci_dev *pci)
 		 * device during cancel_work_sync() call.
 		 */
 		device_unlock(&pci->dev);
-		cancel_work_sync(&hda->probe_work);
+		cancel_delayed_work_sync(&hda->probe_work);
 		device_lock(&pci->dev);
 
 		snd_card_free(card);