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@xxxxxxxxxx>
> Signed-off-by: Wang Hai <wanghai38@xxxxxxxxxx>
> ---
> 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
