Re: [PATCH] ata: ahci_platform: fix null-ptr-deref in ahci_platform_enable_regulators()

[Damien Le Moal <damien.lemoal@opensource.wdc.com>]

On 10/13/21 15:16, Wang Hai wrote:
> I got a null-ptr-deref report:
> 
> KASAN: null-ptr-deref in range [0x0000000000000090-0x0000000000000097]
> ...
> RIP: 0010:regulator_enable+0x84/0x260
> ...
> Call Trace:
>  ahci_platform_enable_regulators+0xae/0x320
>  ahci_platform_enable_resources+0x1a/0x120
>  ahci_probe+0x4f/0x1b9
>  platform_probe+0x10b/0x280
> ...
>  entry_SYSCALL_64_after_hwframe+0x44/0xae
> 
> If devm_regulator_get() in ahci_platform_get_resources() fails,
> hpriv->phy_regulator will point to NULL, when enabling or disabling it,
> null-ptr-deref will occur.
> 
> ahci_probe()
> 	ahci_platform_get_resources()
> 		devm_regulator_get(, "phy") // failed, let phy_regulator = NULL
> 	ahci_platform_enable_resources()
> 		ahci_platform_enable_regulators()
> 			regulator_enable(hpriv->phy_regulator) // null-ptr-deref
> 
> commit 962399bb7fbf ("ata: libahci_platform: Fix regulator_get_optional()
> misuse") replaces devm_regulator_get_optional() with devm_regulator_get(),
> but PHY regulator omits to delete "hpriv->phy_regulator = NULL;" like AHCI.
> Delete it like AHCI regulator to fix this bug.
> 
> Fixes: commit 962399bb7fbf ("ata: libahci_platform: Fix regulator_get_optional() misuse")
> Reported-by: Hulk Robot <hulkci@huawei.com>
> Signed-off-by: Wang Hai <wanghai38@huawei.com>
> ---
>  drivers/ata/libahci_platform.c | 5 +----
>  1 file changed, 1 insertion(+), 4 deletions(-)
> 
> diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c
> index b2f552088291..0910441321f7 100644
> --- a/drivers/ata/libahci_platform.c
> +++ b/drivers/ata/libahci_platform.c
> @@ -440,10 +440,7 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev,
>  	hpriv->phy_regulator = devm_regulator_get(dev, "phy");
>  	if (IS_ERR(hpriv->phy_regulator)) {
>  		rc = PTR_ERR(hpriv->phy_regulator);
> -		if (rc == -EPROBE_DEFER)
> -			goto err_out;
> -		rc = 0;
> -		hpriv->phy_regulator = NULL;
> +		goto err_out;
>  	}
>  
>  	if (flags & AHCI_PLATFORM_GET_RESETS) {
> 

I applied this to for-5.15-fixes.

Note that the code right before the hunk you fixed looks like this:

        hpriv->ahci_regulator = devm_regulator_get(dev, "ahci");
        if (IS_ERR(hpriv->ahci_regulator)) {
                rc = PTR_ERR(hpriv->ahci_regulator);
                if (rc != 0)
                        goto err_out;
        }

This looks very strange to me. The "if (rc != 0)" seems bogus since if
IS_ERR() is true, then hpriv->ahci_regulator is not NULL, it is an error
pointer. Some cleanup seems necessary to me.


-- 
Damien Le Moal
Western Digital Research