Skip to contentSkip to conversation

ata: libahci_platform: Fix regulator_get_optional() misuse

PATCH Applied Mark Brown 3 participants 3 messages Oct 16, 2019 – Oct 25, 2019

Subsystems (2)
lore
Share & tools
lore

Mark Brown

author
#0 lore raw

PATCH 1/1 ata: libahci_platform: Fix regulator_get_optional() misuse

This driver is using regulator_get_optional() to handle all the supplies that it handles, and only ever enables and disables all supplies en masse without ever doing any other configuration of the device to handle missing power. These are clear signs that the API is being misused - it should only be used for supplies that may be physically absent from the system and in these cases the hardware usually needs different configuration if the supply is missing. Instead use normal regualtor_get(), if the supply is not described in DT then the framework will substitute a dummy regulator in so no special handling is needed by the consumer driver.

In the case of the PHY regulator the handling in the driver is a hack to deal with integrated PHYs; the supplies are only optional in the sense that that there's some confusion in the code about where they're bound to. From a code point of view they function exactly as normal supplies so can be treated as such. It'd probably be better to model this by instantiating a PHY object for integrated PHYs.

---
 drivers/ata/libahci_platform.c | 38 +++++++++++++---------------------
 1 file changed, 14 insertions(+), 24 deletions(-)
drivers/ata/libahci_platform.c +14 -24
index e742780950de..8befce036af8 100644
@@ -153,17 +153,13 @@ int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv)
 {
 	int rc, i;
 
-	if (hpriv->ahci_regulator) {
-		rc = regulator_enable(hpriv->ahci_regulator);
-		if (rc)
-			return rc;
-	}
+	rc = regulator_enable(hpriv->ahci_regulator);
+	if (rc)
+		return rc;
 
-	if (hpriv->phy_regulator) {
-		rc = regulator_enable(hpriv->phy_regulator);
-		if (rc)
-			goto disable_ahci_pwrs;
-	}
+	rc = regulator_enable(hpriv->phy_regulator);
+	if (rc)
+		goto disable_ahci_pwrs;
 
 	for (i = 0; i < hpriv->nports; i++) {
 		if (!hpriv->target_pwrs[i])
@@ -181,11 +177,9 @@ int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv)
 		if (hpriv->target_pwrs[i])
 			regulator_disable(hpriv->target_pwrs[i]);
 
-	if (hpriv->phy_regulator)
-		regulator_disable(hpriv->phy_regulator);
+	regulator_disable(hpriv->phy_regulator);
 disable_ahci_pwrs:
-	if (hpriv->ahci_regulator)
-		regulator_disable(hpriv->ahci_regulator);
+	regulator_disable(hpriv->ahci_regulator);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(ahci_platform_enable_regulators);
@@ -207,10 +201,8 @@ void ahci_platform_disable_regulators(struct ahci_host_priv *hpriv)
 		regulator_disable(hpriv->target_pwrs[i]);
 	}
 
-	if (hpriv->ahci_regulator)
-		regulator_disable(hpriv->ahci_regulator);
-	if (hpriv->phy_regulator)
-		regulator_disable(hpriv->phy_regulator);
+	regulator_disable(hpriv->ahci_regulator);
+	regulator_disable(hpriv->phy_regulator);
 }
 EXPORT_SYMBOL_GPL(ahci_platform_disable_regulators);
 /**
@@ -359,7 +351,7 @@ static int ahci_platform_get_regulator(struct ahci_host_priv *hpriv, u32 port,
 	struct regulator *target_pwr;
 	int rc = 0;
 
-	target_pwr = regulator_get_optional(dev, "target");
+	target_pwr = regulator_get(dev, "target");
 
 	if (!IS_ERR(target_pwr))
 		hpriv->target_pwrs[port] = target_pwr;
@@ -436,16 +428,14 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev,
 		hpriv->clks[i] = clk;
 	}
 
-	hpriv->ahci_regulator = devm_regulator_get_optional(dev, "ahci");
+	hpriv->ahci_regulator = devm_regulator_get(dev, "ahci");
 	if (IS_ERR(hpriv->ahci_regulator)) {
 		rc = PTR_ERR(hpriv->ahci_regulator);
-		if (rc == -EPROBE_DEFER)
+		if (rc != 0)
 			goto err_out;
-		rc = 0;
-		hpriv->ahci_regulator = NULL;
 	}
 
-	hpriv->phy_regulator = devm_regulator_get_optional(dev, "phy");
+	hpriv->phy_regulator = devm_regulator_get(dev, "phy");
 	if (IS_ERR(hpriv->phy_regulator)) {
 		rc = PTR_ERR(hpriv->phy_regulator);
 		if (rc == -EPROBE_DEFER)
Signature · 1 line
2.20.1
Reviewed-by on v1 1/1
#1 lore raw

Hi,

Quoted 10 lines · Mark Brown

This driver is using regulator_get_optional() to handle all the supplies that it handles, and only ever enables and disables all supplies en masse without ever doing any other configuration of the device to handle missing power. These are clear signs that the API is being misused - it should only be used for supplies that may be physically absent from the system and in these cases the hardware usually needs different configuration if the supply is missing. Instead use normal regualtor_get(), if the supply is not described in DT then the framework will substitute a dummy regulator in so no special handling is needed by the consumer driver.

Quoted 8 lines

In the case of the PHY regulator the handling in the driver is a hack to deal with integrated PHYs; the supplies are only optional in the sense that that there's some confusion in the code about where they're bound to.
From a code point of view they function exactly as normal supplies so can
be treated as such. It'd probably be better to model this by instantiating a PHY object for integrated PHYs.

Patch looks good to me:

Regards,

Hans

Quoted 89 lines
---
  drivers/ata/libahci_platform.c | 38 +++++++++++++---------------------
  1 file changed, 14 insertions(+), 24 deletions(-)
drivers/ata/libahci_platform.c +14 -24
index e742780950de..8befce036af8 100644
@@ -153,17 +153,13 @@ int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv)
  {
  	int rc, i;
 
-	if (hpriv->ahci_regulator) {
-		rc = regulator_enable(hpriv->ahci_regulator);
-		if (rc)
-			return rc;
-	}
+	rc = regulator_enable(hpriv->ahci_regulator);
+	if (rc)
+		return rc;
 
-	if (hpriv->phy_regulator) {
-		rc = regulator_enable(hpriv->phy_regulator);
-		if (rc)
-			goto disable_ahci_pwrs;
-	}
+	rc = regulator_enable(hpriv->phy_regulator);
+	if (rc)
+		goto disable_ahci_pwrs;
 
  	for (i = 0; i < hpriv->nports; i++) {
  		if (!hpriv->target_pwrs[i])
@@ -181,11 +177,9 @@ int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv)
  		if (hpriv->target_pwrs[i])
  			regulator_disable(hpriv->target_pwrs[i]);
 
-	if (hpriv->phy_regulator)
-		regulator_disable(hpriv->phy_regulator);
+	regulator_disable(hpriv->phy_regulator);
  disable_ahci_pwrs:
-	if (hpriv->ahci_regulator)
-		regulator_disable(hpriv->ahci_regulator);
+	regulator_disable(hpriv->ahci_regulator);
  	return rc;
  }
  EXPORT_SYMBOL_GPL(ahci_platform_enable_regulators);
@@ -207,10 +201,8 @@ void ahci_platform_disable_regulators(struct ahci_host_priv *hpriv)
  		regulator_disable(hpriv->target_pwrs[i]);
  	}
 
-	if (hpriv->ahci_regulator)
-		regulator_disable(hpriv->ahci_regulator);
-	if (hpriv->phy_regulator)
-		regulator_disable(hpriv->phy_regulator);
+	regulator_disable(hpriv->ahci_regulator);
+	regulator_disable(hpriv->phy_regulator);
  }
  EXPORT_SYMBOL_GPL(ahci_platform_disable_regulators);
  /**
@@ -359,7 +351,7 @@ static int ahci_platform_get_regulator(struct ahci_host_priv *hpriv, u32 port,
  	struct regulator *target_pwr;
  	int rc = 0;
 
-	target_pwr = regulator_get_optional(dev, "target");
+	target_pwr = regulator_get(dev, "target");
 
  	if (!IS_ERR(target_pwr))
  		hpriv->target_pwrs[port] = target_pwr;
@@ -436,16 +428,14 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev,
  		hpriv->clks[i] = clk;
  	}
 
-	hpriv->ahci_regulator = devm_regulator_get_optional(dev, "ahci");
+	hpriv->ahci_regulator = devm_regulator_get(dev, "ahci");
  	if (IS_ERR(hpriv->ahci_regulator)) {
  		rc = PTR_ERR(hpriv->ahci_regulator);
-		if (rc == -EPROBE_DEFER)
+		if (rc != 0)
  			goto err_out;
-		rc = 0;
-		hpriv->ahci_regulator = NULL;
  	}
 
-	hpriv->phy_regulator = devm_regulator_get_optional(dev, "phy");
+	hpriv->phy_regulator = devm_regulator_get(dev, "phy");
  	if (IS_ERR(hpriv->phy_regulator)) {
  		rc = PTR_ERR(hpriv->phy_regulator);
  		if (rc == -EPROBE_DEFER)
Applied
#2 lore raw
In reply to Mark Brown
Quoted 10 lines · Mark Brown

This driver is using regulator_get_optional() to handle all the supplies that it handles, and only ever enables and disables all supplies en masse without ever doing any other configuration of the device to handle missing power. These are clear signs that the API is being misused - it should only be used for supplies that may be physically absent from the system and in these cases the hardware usually needs different configuration if the supply is missing. Instead use normal regualtor_get(), if the supply is not described in DT then the framework will substitute a dummy regulator in so no special handling is needed by the consumer driver.

Quoted 6 lines

In the case of the PHY regulator the handling in the driver is a hack to deal with integrated PHYs; the supplies are only optional in the sense that that there's some confusion in the code about where they're bound to.
From a code point of view they function exactly as normal supplies so can
be treated as such. It'd probably be better to model this by instantiating a PHY object for integrated PHYs.

Applied, thanks.

Signature · 1 line
Jens Axboe