[V1] mmc: sdhci-pci-gli: GL975[05]: Mask the replay timer timeout of AER

Commit Message

Victor Shih Sept. 18, 2023, 10:30 a.m. UTC

From: Victor Shih <[e-mail]>

Due to a flaw in the hardware design, the GL975x replay timer frequently
times out when ASPM is enabled. As a result, the system will resume
immediately when it enters suspend. Therefore, the replay timer
timeout must be masked.

Signed-off-by: Victor Shih <[e-mail]>
---
 drivers/mmc/host/sdhci-pci-gli.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

Comments

Kai-Heng Feng Sept. 19, 2023, 4:24 a.m. UTC | #1

Hi Victor,

On Mon, Sep 18, 2023 at 6:31 PM Victor Shih <[e-mail]> wrote:
>
> From: Victor Shih <[e-mail]>
>
> Due to a flaw in the hardware design, the GL975x replay timer frequently
> times out when ASPM is enabled. As a result, the system will resume
> immediately when it enters suspend. Therefore, the replay timer
> timeout must be masked.

This patch solves AER error when its PCI config gets accessed, but the
AER still happens at system suspend:

[ 1100.103603] ACPI: EC: interrupt blocked
[ 1100.268244] ACPI: EC: interrupt unblocked
[ 1100.326960] pcieport 0000:00:1c.0: AER: Corrected error received:
0000:00:1c.0
[ 1100.326991] pcieport 0000:00:1c.0: PCIe Bus Error:
severity=Corrected, type=Data Link Layer, (Transmitter ID)
[ 1100.326993] pcieport 0000:00:1c.0:   device [8086:7ab9] error
status/mask=00001000/00002000
[ 1100.326996] pcieport 0000:00:1c.0:    [12] Timeout

Kai-Heng

>
> Signed-off-by: Victor Shih <[e-mail]>
> ---
>  drivers/mmc/host/sdhci-pci-gli.c | 16 ++++++++++++++++
>  1 file changed, 16 insertions(+)
>
> diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c
> index d83261e857a5..d8a991b349a8 100644
> --- a/drivers/mmc/host/sdhci-pci-gli.c
> +++ b/drivers/mmc/host/sdhci-pci-gli.c
> @@ -28,6 +28,9 @@
>  #define PCI_GLI_9750_PM_CTRL   0xFC
>  #define   PCI_GLI_9750_PM_STATE          GENMASK(1, 0)
>
> +#define PCI_GLI_9750_CORRERR_MASK                              0x214
> +#define   PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> +
>  #define SDHCI_GLI_9750_CFG2          0x848
>  #define   SDHCI_GLI_9750_CFG2_L1DLY    GENMASK(28, 24)
>  #define   GLI_9750_CFG2_L1DLY_VALUE    0x1F
> @@ -152,6 +155,9 @@
>  #define PCI_GLI_9755_PM_CTRL     0xFC
>  #define   PCI_GLI_9755_PM_STATE    GENMASK(1, 0)
>
> +#define PCI_GLI_9755_CORRERR_MASK                              0x214
> +#define   PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> +
>  #define SDHCI_GLI_9767_GM_BURST_SIZE                   0x510
>  #define   SDHCI_GLI_9767_GM_BURST_SIZE_AXI_ALWAYS_SET    BIT(8)
>
> @@ -561,6 +567,11 @@ static void gl9750_hw_setting(struct sdhci_host *host)
>         value &= ~PCI_GLI_9750_PM_STATE;
>         pci_write_config_dword(pdev, PCI_GLI_9750_PM_CTRL, value);
>
> +       /* mask the replay timer timeout of AER */
> +       pci_read_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, &value);
> +       value |= PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> +       pci_write_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, value);
> +
>         gl9750_wt_off(host);
>  }
>
> @@ -770,6 +781,11 @@ static void gl9755_hw_setting(struct sdhci_pci_slot *slot)
>         value &= ~PCI_GLI_9755_PM_STATE;
>         pci_write_config_dword(pdev, PCI_GLI_9755_PM_CTRL, value);
>
> +       /* mask the replay timer timeout of AER */
> +       pci_read_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, &value);
> +       value |= PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> +       pci_write_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, value);
> +
>         gl9755_wt_off(pdev);
>  }
>
> --
> 2.25.1
>

Victor Shih Sept. 19, 2023, 7:10 a.m. UTC | #2

On Tue, Sep 19, 2023 at 12:24 PM Kai-Heng Feng
<[e-mail]> wrote:
>
> Hi Victor,
>
> On Mon, Sep 18, 2023 at 6:31 PM Victor Shih <[e-mail]> wrote:
> >
> > From: Victor Shih <[e-mail]>
> >
> > Due to a flaw in the hardware design, the GL975x replay timer frequently
> > times out when ASPM is enabled. As a result, the system will resume
> > immediately when it enters suspend. Therefore, the replay timer
> > timeout must be masked.
>
> This patch solves AER error when its PCI config gets accessed, but the
> AER still happens at system suspend:
>
> [ 1100.103603] ACPI: EC: interrupt blocked
> [ 1100.268244] ACPI: EC: interrupt unblocked
> [ 1100.326960] pcieport 0000:00:1c.0: AER: Corrected error received:
> 0000:00:1c.0
> [ 1100.326991] pcieport 0000:00:1c.0: PCIe Bus Error:
> severity=Corrected, type=Data Link Layer, (Transmitter ID)
> [ 1100.326993] pcieport 0000:00:1c.0:   device [8086:7ab9] error
> status/mask=00001000/00002000
> [ 1100.326996] pcieport 0000:00:1c.0:    [12] Timeout
>
> Kai-Heng
>

Hi, Kai-Heng

Could you try applying the patch and re-testing again after restarting
the system?
Because I applied the patch and restarted the system and it didn't happen.
The system can enter suspend normally.

If you still have the issue after following the above instructions,
please provide me with your environment and I will verify it again.

Thanks, Victor Shih

> >
> > Signed-off-by: Victor Shih <[e-mail]>
> > ---
> >  drivers/mmc/host/sdhci-pci-gli.c | 16 ++++++++++++++++
> >  1 file changed, 16 insertions(+)
> >
> > diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c
> > index d83261e857a5..d8a991b349a8 100644
> > --- a/drivers/mmc/host/sdhci-pci-gli.c
> > +++ b/drivers/mmc/host/sdhci-pci-gli.c
> > @@ -28,6 +28,9 @@
> >  #define PCI_GLI_9750_PM_CTRL   0xFC
> >  #define   PCI_GLI_9750_PM_STATE          GENMASK(1, 0)
> >
> > +#define PCI_GLI_9750_CORRERR_MASK                              0x214
> > +#define   PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> > +
> >  #define SDHCI_GLI_9750_CFG2          0x848
> >  #define   SDHCI_GLI_9750_CFG2_L1DLY    GENMASK(28, 24)
> >  #define   GLI_9750_CFG2_L1DLY_VALUE    0x1F
> > @@ -152,6 +155,9 @@
> >  #define PCI_GLI_9755_PM_CTRL     0xFC
> >  #define   PCI_GLI_9755_PM_STATE    GENMASK(1, 0)
> >
> > +#define PCI_GLI_9755_CORRERR_MASK                              0x214
> > +#define   PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> > +
> >  #define SDHCI_GLI_9767_GM_BURST_SIZE                   0x510
> >  #define   SDHCI_GLI_9767_GM_BURST_SIZE_AXI_ALWAYS_SET    BIT(8)
> >
> > @@ -561,6 +567,11 @@ static void gl9750_hw_setting(struct sdhci_host *host)
> >         value &= ~PCI_GLI_9750_PM_STATE;
> >         pci_write_config_dword(pdev, PCI_GLI_9750_PM_CTRL, value);
> >
> > +       /* mask the replay timer timeout of AER */
> > +       pci_read_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, &value);
> > +       value |= PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> > +       pci_write_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, value);
> > +
> >         gl9750_wt_off(host);
> >  }
> >
> > @@ -770,6 +781,11 @@ static void gl9755_hw_setting(struct sdhci_pci_slot *slot)
> >         value &= ~PCI_GLI_9755_PM_STATE;
> >         pci_write_config_dword(pdev, PCI_GLI_9755_PM_CTRL, value);
> >
> > +       /* mask the replay timer timeout of AER */
> > +       pci_read_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, &value);
> > +       value |= PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> > +       pci_write_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, value);
> > +
> >         gl9755_wt_off(pdev);
> >  }
> >
> > --
> > 2.25.1
> >

Kai-Heng Feng Sept. 19, 2023, 7:31 a.m. UTC | #3

Hi Victor,

On Tue, Sep 19, 2023 at 3:10 PM Victor Shih <[e-mail]> wrote:
>
> On Tue, Sep 19, 2023 at 12:24 PM Kai-Heng Feng
> <[e-mail]> wrote:
> >
> > Hi Victor,
> >
> > On Mon, Sep 18, 2023 at 6:31 PM Victor Shih <[e-mail]> wrote:
> > >
> > > From: Victor Shih <[e-mail]>
> > >
> > > Due to a flaw in the hardware design, the GL975x replay timer frequently
> > > times out when ASPM is enabled. As a result, the system will resume
> > > immediately when it enters suspend. Therefore, the replay timer
> > > timeout must be masked.
> >
> > This patch solves AER error when its PCI config gets accessed, but the
> > AER still happens at system suspend:
> >
> > [ 1100.103603] ACPI: EC: interrupt blocked
> > [ 1100.268244] ACPI: EC: interrupt unblocked
> > [ 1100.326960] pcieport 0000:00:1c.0: AER: Corrected error received:
> > 0000:00:1c.0
> > [ 1100.326991] pcieport 0000:00:1c.0: PCIe Bus Error:
> > severity=Corrected, type=Data Link Layer, (Transmitter ID)
> > [ 1100.326993] pcieport 0000:00:1c.0:   device [8086:7ab9] error
> > status/mask=00001000/00002000
> > [ 1100.326996] pcieport 0000:00:1c.0:    [12] Timeout
> >
> > Kai-Heng
> >
>
> Hi, Kai-Heng
>
> Could you try applying the patch and re-testing again after restarting
> the system?

Same issue happens after coldboot.

> Because I applied the patch and restarted the system and it didn't happen.
> The system can enter suspend normally.
>
> If you still have the issue after following the above instructions,
> please provide me with your environment and I will verify it again.

The patch gets applied on top of next-20230918. Please let me know
what else you want to know.

Kai-Heng

>
> Thanks, Victor Shih
>
> > >
> > > Signed-off-by: Victor Shih <[e-mail]>
> > > ---
> > >  drivers/mmc/host/sdhci-pci-gli.c | 16 ++++++++++++++++
> > >  1 file changed, 16 insertions(+)
> > >
> > > diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c
> > > index d83261e857a5..d8a991b349a8 100644
> > > --- a/drivers/mmc/host/sdhci-pci-gli.c
> > > +++ b/drivers/mmc/host/sdhci-pci-gli.c
> > > @@ -28,6 +28,9 @@
> > >  #define PCI_GLI_9750_PM_CTRL   0xFC
> > >  #define   PCI_GLI_9750_PM_STATE          GENMASK(1, 0)
> > >
> > > +#define PCI_GLI_9750_CORRERR_MASK                              0x214
> > > +#define   PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> > > +
> > >  #define SDHCI_GLI_9750_CFG2          0x848
> > >  #define   SDHCI_GLI_9750_CFG2_L1DLY    GENMASK(28, 24)
> > >  #define   GLI_9750_CFG2_L1DLY_VALUE    0x1F
> > > @@ -152,6 +155,9 @@
> > >  #define PCI_GLI_9755_PM_CTRL     0xFC
> > >  #define   PCI_GLI_9755_PM_STATE    GENMASK(1, 0)
> > >
> > > +#define PCI_GLI_9755_CORRERR_MASK                              0x214
> > > +#define   PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> > > +
> > >  #define SDHCI_GLI_9767_GM_BURST_SIZE                   0x510
> > >  #define   SDHCI_GLI_9767_GM_BURST_SIZE_AXI_ALWAYS_SET    BIT(8)
> > >
> > > @@ -561,6 +567,11 @@ static void gl9750_hw_setting(struct sdhci_host *host)
> > >         value &= ~PCI_GLI_9750_PM_STATE;
> > >         pci_write_config_dword(pdev, PCI_GLI_9750_PM_CTRL, value);
> > >
> > > +       /* mask the replay timer timeout of AER */
> > > +       pci_read_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, &value);
> > > +       value |= PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> > > +       pci_write_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, value);
> > > +
> > >         gl9750_wt_off(host);
> > >  }
> > >
> > > @@ -770,6 +781,11 @@ static void gl9755_hw_setting(struct sdhci_pci_slot *slot)
> > >         value &= ~PCI_GLI_9755_PM_STATE;
> > >         pci_write_config_dword(pdev, PCI_GLI_9755_PM_CTRL, value);
> > >
> > > +       /* mask the replay timer timeout of AER */
> > > +       pci_read_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, &value);
> > > +       value |= PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> > > +       pci_write_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, value);
> > > +
> > >         gl9755_wt_off(pdev);
> > >  }
> > >
> > > --
> > > 2.25.1
> > >

Victor Shih Sept. 20, 2023, 8:53 a.m. UTC | #4

On Tue, Sep 19, 2023 at 3:31 PM Kai-Heng Feng
<[e-mail]> wrote:
>
> Hi Victor,
>
> On Tue, Sep 19, 2023 at 3:10 PM Victor Shih <[e-mail]> wrote:
> >
> > On Tue, Sep 19, 2023 at 12:24 PM Kai-Heng Feng
> > <[e-mail]> wrote:
> > >
> > > Hi Victor,
> > >
> > > On Mon, Sep 18, 2023 at 6:31 PM Victor Shih <[e-mail]> wrote:
> > > >
> > > > From: Victor Shih <[e-mail]>
> > > >
> > > > Due to a flaw in the hardware design, the GL975x replay timer frequently
> > > > times out when ASPM is enabled. As a result, the system will resume
> > > > immediately when it enters suspend. Therefore, the replay timer
> > > > timeout must be masked.
> > >
> > > This patch solves AER error when its PCI config gets accessed, but the
> > > AER still happens at system suspend:
> > >
> > > [ 1100.103603] ACPI: EC: interrupt blocked
> > > [ 1100.268244] ACPI: EC: interrupt unblocked
> > > [ 1100.326960] pcieport 0000:00:1c.0: AER: Corrected error received:
> > > 0000:00:1c.0
> > > [ 1100.326991] pcieport 0000:00:1c.0: PCIe Bus Error:
> > > severity=Corrected, type=Data Link Layer, (Transmitter ID)
> > > [ 1100.326993] pcieport 0000:00:1c.0:   device [8086:7ab9] error
> > > status/mask=00001000/00002000
> > > [ 1100.326996] pcieport 0000:00:1c.0:    [12] Timeout
> > >
> > > Kai-Heng
> > >
> >
> > Hi, Kai-Heng
> >
> > Could you try applying the patch and re-testing again after restarting
> > the system?
>
> Same issue happens after coldboot.
>
> > Because I applied the patch and restarted the system and it didn't happen.
> > The system can enter suspend normally.
> >
> > If you still have the issue after following the above instructions,
> > please provide me with your environment and I will verify it again.
>
> The patch gets applied on top of next-20230918. Please let me know
> what else you want to know.
>
> Kai-Heng
>

Hi, Kai-Heng

If I want to mask the replay timer timeout AER of the upper layer root port,
could you give me some suggestions?
Or could you provide sample code for my reference?

Thanks, Victor Shih

> >
> > Thanks, Victor Shih
> >
> > > >
> > > > Signed-off-by: Victor Shih <[e-mail]>
> > > > ---
> > > >  drivers/mmc/host/sdhci-pci-gli.c | 16 ++++++++++++++++
> > > >  1 file changed, 16 insertions(+)
> > > >
> > > > diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c
> > > > index d83261e857a5..d8a991b349a8 100644
> > > > --- a/drivers/mmc/host/sdhci-pci-gli.c
> > > > +++ b/drivers/mmc/host/sdhci-pci-gli.c
> > > > @@ -28,6 +28,9 @@
> > > >  #define PCI_GLI_9750_PM_CTRL   0xFC
> > > >  #define   PCI_GLI_9750_PM_STATE          GENMASK(1, 0)
> > > >
> > > > +#define PCI_GLI_9750_CORRERR_MASK                              0x214
> > > > +#define   PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> > > > +
> > > >  #define SDHCI_GLI_9750_CFG2          0x848
> > > >  #define   SDHCI_GLI_9750_CFG2_L1DLY    GENMASK(28, 24)
> > > >  #define   GLI_9750_CFG2_L1DLY_VALUE    0x1F
> > > > @@ -152,6 +155,9 @@
> > > >  #define PCI_GLI_9755_PM_CTRL     0xFC
> > > >  #define   PCI_GLI_9755_PM_STATE    GENMASK(1, 0)
> > > >
> > > > +#define PCI_GLI_9755_CORRERR_MASK                              0x214
> > > > +#define   PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> > > > +
> > > >  #define SDHCI_GLI_9767_GM_BURST_SIZE                   0x510
> > > >  #define   SDHCI_GLI_9767_GM_BURST_SIZE_AXI_ALWAYS_SET    BIT(8)
> > > >
> > > > @@ -561,6 +567,11 @@ static void gl9750_hw_setting(struct sdhci_host *host)
> > > >         value &= ~PCI_GLI_9750_PM_STATE;
> > > >         pci_write_config_dword(pdev, PCI_GLI_9750_PM_CTRL, value);
> > > >
> > > > +       /* mask the replay timer timeout of AER */
> > > > +       pci_read_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, &value);
> > > > +       value |= PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> > > > +       pci_write_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, value);
> > > > +
> > > >         gl9750_wt_off(host);
> > > >  }
> > > >
> > > > @@ -770,6 +781,11 @@ static void gl9755_hw_setting(struct sdhci_pci_slot *slot)
> > > >         value &= ~PCI_GLI_9755_PM_STATE;
> > > >         pci_write_config_dword(pdev, PCI_GLI_9755_PM_CTRL, value);
> > > >
> > > > +       /* mask the replay timer timeout of AER */
> > > > +       pci_read_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, &value);
> > > > +       value |= PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> > > > +       pci_write_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, value);
> > > > +
> > > >         gl9755_wt_off(pdev);
> > > >  }
> > > >
> > > > --
> > > > 2.25.1
> > > >

Kai-Heng Feng Sept. 22, 2023, 7:10 a.m. UTC | #5

Hi Victor,

On Wed, Sep 20, 2023 at 4:54 PM Victor Shih <[e-mail]> wrote:
>
> On Tue, Sep 19, 2023 at 3:31 PM Kai-Heng Feng
> <[e-mail]> wrote:
> >
> > Hi Victor,
> >
> > On Tue, Sep 19, 2023 at 3:10 PM Victor Shih <[e-mail]> wrote:
> > >
> > > On Tue, Sep 19, 2023 at 12:24 PM Kai-Heng Feng
> > > <[e-mail]> wrote:
> > > >
> > > > Hi Victor,
> > > >
> > > > On Mon, Sep 18, 2023 at 6:31 PM Victor Shih <[e-mail]> wrote:
> > > > >
> > > > > From: Victor Shih <[e-mail]>
> > > > >
> > > > > Due to a flaw in the hardware design, the GL975x replay timer frequently
> > > > > times out when ASPM is enabled. As a result, the system will resume
> > > > > immediately when it enters suspend. Therefore, the replay timer
> > > > > timeout must be masked.
> > > >
> > > > This patch solves AER error when its PCI config gets accessed, but the
> > > > AER still happens at system suspend:
> > > >
> > > > [ 1100.103603] ACPI: EC: interrupt blocked
> > > > [ 1100.268244] ACPI: EC: interrupt unblocked
> > > > [ 1100.326960] pcieport 0000:00:1c.0: AER: Corrected error received:
> > > > 0000:00:1c.0
> > > > [ 1100.326991] pcieport 0000:00:1c.0: PCIe Bus Error:
> > > > severity=Corrected, type=Data Link Layer, (Transmitter ID)
> > > > [ 1100.326993] pcieport 0000:00:1c.0:   device [8086:7ab9] error
> > > > status/mask=00001000/00002000
> > > > [ 1100.326996] pcieport 0000:00:1c.0:    [12] Timeout
> > > >
> > > > Kai-Heng
> > > >
> > >
> > > Hi, Kai-Heng
> > >
> > > Could you try applying the patch and re-testing again after restarting
> > > the system?
> >
> > Same issue happens after coldboot.
> >
> > > Because I applied the patch and restarted the system and it didn't happen.
> > > The system can enter suspend normally.
> > >
> > > If you still have the issue after following the above instructions,
> > > please provide me with your environment and I will verify it again.
> >
> > The patch gets applied on top of next-20230918. Please let me know
> > what else you want to know.
> >
> > Kai-Heng
> >
>
> Hi, Kai-Heng
>
> If I want to mask the replay timer timeout AER of the upper layer root port,
> could you give me some suggestions?
> Or could you provide sample code for my reference?

I am not aware of anyway to mask "replay timer timeout" from root port.
I wonder if the device supoprt D3hot? Or should it stay at D0 when
ASPM L1.2 is enabled?

Kai-Heng

>
> Thanks, Victor Shih
>
> > >
> > > Thanks, Victor Shih
> > >
> > > > >
> > > > > Signed-off-by: Victor Shih <[e-mail]>
> > > > > ---
> > > > >  drivers/mmc/host/sdhci-pci-gli.c | 16 ++++++++++++++++
> > > > >  1 file changed, 16 insertions(+)
> > > > >
> > > > > diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c
> > > > > index d83261e857a5..d8a991b349a8 100644
> > > > > --- a/drivers/mmc/host/sdhci-pci-gli.c
> > > > > +++ b/drivers/mmc/host/sdhci-pci-gli.c
> > > > > @@ -28,6 +28,9 @@
> > > > >  #define PCI_GLI_9750_PM_CTRL   0xFC
> > > > >  #define   PCI_GLI_9750_PM_STATE          GENMASK(1, 0)
> > > > >
> > > > > +#define PCI_GLI_9750_CORRERR_MASK                              0x214
> > > > > +#define   PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> > > > > +
> > > > >  #define SDHCI_GLI_9750_CFG2          0x848
> > > > >  #define   SDHCI_GLI_9750_CFG2_L1DLY    GENMASK(28, 24)
> > > > >  #define   GLI_9750_CFG2_L1DLY_VALUE    0x1F
> > > > > @@ -152,6 +155,9 @@
> > > > >  #define PCI_GLI_9755_PM_CTRL     0xFC
> > > > >  #define   PCI_GLI_9755_PM_STATE    GENMASK(1, 0)
> > > > >
> > > > > +#define PCI_GLI_9755_CORRERR_MASK                              0x214
> > > > > +#define   PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> > > > > +
> > > > >  #define SDHCI_GLI_9767_GM_BURST_SIZE                   0x510
> > > > >  #define   SDHCI_GLI_9767_GM_BURST_SIZE_AXI_ALWAYS_SET    BIT(8)
> > > > >
> > > > > @@ -561,6 +567,11 @@ static void gl9750_hw_setting(struct sdhci_host *host)
> > > > >         value &= ~PCI_GLI_9750_PM_STATE;
> > > > >         pci_write_config_dword(pdev, PCI_GLI_9750_PM_CTRL, value);
> > > > >
> > > > > +       /* mask the replay timer timeout of AER */
> > > > > +       pci_read_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, &value);
> > > > > +       value |= PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> > > > > +       pci_write_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, value);
> > > > > +
> > > > >         gl9750_wt_off(host);
> > > > >  }
> > > > >
> > > > > @@ -770,6 +781,11 @@ static void gl9755_hw_setting(struct sdhci_pci_slot *slot)
> > > > >         value &= ~PCI_GLI_9755_PM_STATE;
> > > > >         pci_write_config_dword(pdev, PCI_GLI_9755_PM_CTRL, value);
> > > > >
> > > > > +       /* mask the replay timer timeout of AER */
> > > > > +       pci_read_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, &value);
> > > > > +       value |= PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> > > > > +       pci_write_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, value);
> > > > > +
> > > > >         gl9755_wt_off(pdev);
> > > > >  }
> > > > >
> > > > > --
> > > > > 2.25.1
> > > > >

Victor Shih Sept. 26, 2023, 8:21 a.m. UTC | #6

On Fri, Sep 22, 2023 at 3:11 PM Kai-Heng Feng
<[e-mail]> wrote:
>
> Hi Victor,
>
> On Wed, Sep 20, 2023 at 4:54 PM Victor Shih <[e-mail]> wrote:
> >
> > On Tue, Sep 19, 2023 at 3:31 PM Kai-Heng Feng
> > <[e-mail]> wrote:
> > >
> > > Hi Victor,
> > >
> > > On Tue, Sep 19, 2023 at 3:10 PM Victor Shih <[e-mail]> wrote:
> > > >
> > > > On Tue, Sep 19, 2023 at 12:24 PM Kai-Heng Feng
> > > > <[e-mail]> wrote:
> > > > >
> > > > > Hi Victor,
> > > > >
> > > > > On Mon, Sep 18, 2023 at 6:31 PM Victor Shih <[e-mail]> wrote:
> > > > > >
> > > > > > From: Victor Shih <[e-mail]>
> > > > > >
> > > > > > Due to a flaw in the hardware design, the GL975x replay timer frequently
> > > > > > times out when ASPM is enabled. As a result, the system will resume
> > > > > > immediately when it enters suspend. Therefore, the replay timer
> > > > > > timeout must be masked.
> > > > >
> > > > > This patch solves AER error when its PCI config gets accessed, but the
> > > > > AER still happens at system suspend:
> > > > >
> > > > > [ 1100.103603] ACPI: EC: interrupt blocked
> > > > > [ 1100.268244] ACPI: EC: interrupt unblocked
> > > > > [ 1100.326960] pcieport 0000:00:1c.0: AER: Corrected error received:
> > > > > 0000:00:1c.0
> > > > > [ 1100.326991] pcieport 0000:00:1c.0: PCIe Bus Error:
> > > > > severity=Corrected, type=Data Link Layer, (Transmitter ID)
> > > > > [ 1100.326993] pcieport 0000:00:1c.0:   device [8086:7ab9] error
> > > > > status/mask=00001000/00002000
> > > > > [ 1100.326996] pcieport 0000:00:1c.0:    [12] Timeout
> > > > >
> > > > > Kai-Heng
> > > > >
> > > >
> > > > Hi, Kai-Heng
> > > >
> > > > Could you try applying the patch and re-testing again after restarting
> > > > the system?
> > >
> > > Same issue happens after coldboot.
> > >
> > > > Because I applied the patch and restarted the system and it didn't happen.
> > > > The system can enter suspend normally.
> > > >
> > > > If you still have the issue after following the above instructions,
> > > > please provide me with your environment and I will verify it again.
> > >
> > > The patch gets applied on top of next-20230918. Please let me know
> > > what else you want to know.
> > >
> > > Kai-Heng
> > >
> >
> > Hi, Kai-Heng
> >
> > If I want to mask the replay timer timeout AER of the upper layer root port,
> > could you give me some suggestions?
> > Or could you provide sample code for my reference?
>
> I am not aware of anyway to mask "replay timer timeout" from root port.
> I wonder if the device supoprt D3hot? Or should it stay at D0 when
> ASPM L1.2 is enabled?
>
> Kai-Heng
>

Hi, Kai-Heng

Do you know any way to mask the replay timer timeout AER of the
upstream port from the device?
The device supports D3hot.

Thanks, Victor Shih

> >
> > Thanks, Victor Shih
> >
> > > >
> > > > Thanks, Victor Shih
> > > >
> > > > > >
> > > > > > Signed-off-by: Victor Shih <[e-mail]>
> > > > > > ---
> > > > > >  drivers/mmc/host/sdhci-pci-gli.c | 16 ++++++++++++++++
> > > > > >  1 file changed, 16 insertions(+)
> > > > > >
> > > > > > diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c
> > > > > > index d83261e857a5..d8a991b349a8 100644
> > > > > > --- a/drivers/mmc/host/sdhci-pci-gli.c
> > > > > > +++ b/drivers/mmc/host/sdhci-pci-gli.c
> > > > > > @@ -28,6 +28,9 @@
> > > > > >  #define PCI_GLI_9750_PM_CTRL   0xFC
> > > > > >  #define   PCI_GLI_9750_PM_STATE          GENMASK(1, 0)
> > > > > >
> > > > > > +#define PCI_GLI_9750_CORRERR_MASK                              0x214
> > > > > > +#define   PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> > > > > > +
> > > > > >  #define SDHCI_GLI_9750_CFG2          0x848
> > > > > >  #define   SDHCI_GLI_9750_CFG2_L1DLY    GENMASK(28, 24)
> > > > > >  #define   GLI_9750_CFG2_L1DLY_VALUE    0x1F
> > > > > > @@ -152,6 +155,9 @@
> > > > > >  #define PCI_GLI_9755_PM_CTRL     0xFC
> > > > > >  #define   PCI_GLI_9755_PM_STATE    GENMASK(1, 0)
> > > > > >
> > > > > > +#define PCI_GLI_9755_CORRERR_MASK                              0x214
> > > > > > +#define   PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> > > > > > +
> > > > > >  #define SDHCI_GLI_9767_GM_BURST_SIZE                   0x510
> > > > > >  #define   SDHCI_GLI_9767_GM_BURST_SIZE_AXI_ALWAYS_SET    BIT(8)
> > > > > >
> > > > > > @@ -561,6 +567,11 @@ static void gl9750_hw_setting(struct sdhci_host *host)
> > > > > >         value &= ~PCI_GLI_9750_PM_STATE;
> > > > > >         pci_write_config_dword(pdev, PCI_GLI_9750_PM_CTRL, value);
> > > > > >
> > > > > > +       /* mask the replay timer timeout of AER */
> > > > > > +       pci_read_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, &value);
> > > > > > +       value |= PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> > > > > > +       pci_write_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, value);
> > > > > > +
> > > > > >         gl9750_wt_off(host);
> > > > > >  }
> > > > > >
> > > > > > @@ -770,6 +781,11 @@ static void gl9755_hw_setting(struct sdhci_pci_slot *slot)
> > > > > >         value &= ~PCI_GLI_9755_PM_STATE;
> > > > > >         pci_write_config_dword(pdev, PCI_GLI_9755_PM_CTRL, value);
> > > > > >
> > > > > > +       /* mask the replay timer timeout of AER */
> > > > > > +       pci_read_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, &value);
> > > > > > +       value |= PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> > > > > > +       pci_write_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, value);
> > > > > > +
> > > > > >         gl9755_wt_off(pdev);
> > > > > >  }
> > > > > >
> > > > > > --
> > > > > > 2.25.1
> > > > > >

Kai-Heng Feng Oct. 2, 2023, 2:18 a.m. UTC | #7

Hi Victor,

On Tue, Sep 26, 2023 at 4:21 PM Victor Shih <[e-mail]> wrote:
>
> On Fri, Sep 22, 2023 at 3:11 PM Kai-Heng Feng
> <[e-mail]> wrote:
> >
> > Hi Victor,
> >
> > On Wed, Sep 20, 2023 at 4:54 PM Victor Shih <[e-mail]> wrote:
> > >
> > > On Tue, Sep 19, 2023 at 3:31 PM Kai-Heng Feng
> > > <[e-mail]> wrote:
> > > >
> > > > Hi Victor,
> > > >
> > > > On Tue, Sep 19, 2023 at 3:10 PM Victor Shih <[e-mail]> wrote:
> > > > >
> > > > > On Tue, Sep 19, 2023 at 12:24 PM Kai-Heng Feng
> > > > > <[e-mail]> wrote:
> > > > > >
> > > > > > Hi Victor,
> > > > > >
> > > > > > On Mon, Sep 18, 2023 at 6:31 PM Victor Shih <[e-mail]> wrote:
> > > > > > >
> > > > > > > From: Victor Shih <[e-mail]>
> > > > > > >
> > > > > > > Due to a flaw in the hardware design, the GL975x replay timer frequently
> > > > > > > times out when ASPM is enabled. As a result, the system will resume
> > > > > > > immediately when it enters suspend. Therefore, the replay timer
> > > > > > > timeout must be masked.
> > > > > >
> > > > > > This patch solves AER error when its PCI config gets accessed, but the
> > > > > > AER still happens at system suspend:
> > > > > >
> > > > > > [ 1100.103603] ACPI: EC: interrupt blocked
> > > > > > [ 1100.268244] ACPI: EC: interrupt unblocked
> > > > > > [ 1100.326960] pcieport 0000:00:1c.0: AER: Corrected error received:
> > > > > > 0000:00:1c.0
> > > > > > [ 1100.326991] pcieport 0000:00:1c.0: PCIe Bus Error:
> > > > > > severity=Corrected, type=Data Link Layer, (Transmitter ID)
> > > > > > [ 1100.326993] pcieport 0000:00:1c.0:   device [8086:7ab9] error
> > > > > > status/mask=00001000/00002000
> > > > > > [ 1100.326996] pcieport 0000:00:1c.0:    [12] Timeout
> > > > > >
> > > > > > Kai-Heng
> > > > > >
> > > > >
> > > > > Hi, Kai-Heng
> > > > >
> > > > > Could you try applying the patch and re-testing again after restarting
> > > > > the system?
> > > >
> > > > Same issue happens after coldboot.
> > > >
> > > > > Because I applied the patch and restarted the system and it didn't happen.
> > > > > The system can enter suspend normally.
> > > > >
> > > > > If you still have the issue after following the above instructions,
> > > > > please provide me with your environment and I will verify it again.
> > > >
> > > > The patch gets applied on top of next-20230918. Please let me know
> > > > what else you want to know.
> > > >
> > > > Kai-Heng
> > > >
> > >
> > > Hi, Kai-Heng
> > >
> > > If I want to mask the replay timer timeout AER of the upper layer root port,
> > > could you give me some suggestions?
> > > Or could you provide sample code for my reference?
> >
> > I am not aware of anyway to mask "replay timer timeout" from root port.
> > I wonder if the device supoprt D3hot? Or should it stay at D0 when
> > ASPM L1.2 is enabled?
> >
> > Kai-Heng
> >
>
> Hi, Kai-Heng
>
> Do you know any way to mask the replay timer timeout AER of the
> upstream port from the device?

Per PCIe Spec, I don't think it's possible to only mask 'replay timer timeout'.

> The device supports D3hot.

Do you think such error plays any crucial rule? Otherwise disable
'correctable' errors may be plausible.

Kai-Heng

>
> Thanks, Victor Shih
>
> > >
> > > Thanks, Victor Shih
> > >
> > > > >
> > > > > Thanks, Victor Shih
> > > > >
> > > > > > >
> > > > > > > Signed-off-by: Victor Shih <[e-mail]>
> > > > > > > ---
> > > > > > >  drivers/mmc/host/sdhci-pci-gli.c | 16 ++++++++++++++++
> > > > > > >  1 file changed, 16 insertions(+)
> > > > > > >
> > > > > > > diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c
> > > > > > > index d83261e857a5..d8a991b349a8 100644
> > > > > > > --- a/drivers/mmc/host/sdhci-pci-gli.c
> > > > > > > +++ b/drivers/mmc/host/sdhci-pci-gli.c
> > > > > > > @@ -28,6 +28,9 @@
> > > > > > >  #define PCI_GLI_9750_PM_CTRL   0xFC
> > > > > > >  #define   PCI_GLI_9750_PM_STATE          GENMASK(1, 0)
> > > > > > >
> > > > > > > +#define PCI_GLI_9750_CORRERR_MASK                              0x214
> > > > > > > +#define   PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> > > > > > > +
> > > > > > >  #define SDHCI_GLI_9750_CFG2          0x848
> > > > > > >  #define   SDHCI_GLI_9750_CFG2_L1DLY    GENMASK(28, 24)
> > > > > > >  #define   GLI_9750_CFG2_L1DLY_VALUE    0x1F
> > > > > > > @@ -152,6 +155,9 @@
> > > > > > >  #define PCI_GLI_9755_PM_CTRL     0xFC
> > > > > > >  #define   PCI_GLI_9755_PM_STATE    GENMASK(1, 0)
> > > > > > >
> > > > > > > +#define PCI_GLI_9755_CORRERR_MASK                              0x214
> > > > > > > +#define   PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> > > > > > > +
> > > > > > >  #define SDHCI_GLI_9767_GM_BURST_SIZE                   0x510
> > > > > > >  #define   SDHCI_GLI_9767_GM_BURST_SIZE_AXI_ALWAYS_SET    BIT(8)
> > > > > > >
> > > > > > > @@ -561,6 +567,11 @@ static void gl9750_hw_setting(struct sdhci_host *host)
> > > > > > >         value &= ~PCI_GLI_9750_PM_STATE;
> > > > > > >         pci_write_config_dword(pdev, PCI_GLI_9750_PM_CTRL, value);
> > > > > > >
> > > > > > > +       /* mask the replay timer timeout of AER */
> > > > > > > +       pci_read_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, &value);
> > > > > > > +       value |= PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> > > > > > > +       pci_write_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, value);
> > > > > > > +
> > > > > > >         gl9750_wt_off(host);
> > > > > > >  }
> > > > > > >
> > > > > > > @@ -770,6 +781,11 @@ static void gl9755_hw_setting(struct sdhci_pci_slot *slot)
> > > > > > >         value &= ~PCI_GLI_9755_PM_STATE;
> > > > > > >         pci_write_config_dword(pdev, PCI_GLI_9755_PM_CTRL, value);
> > > > > > >
> > > > > > > +       /* mask the replay timer timeout of AER */
> > > > > > > +       pci_read_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, &value);
> > > > > > > +       value |= PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> > > > > > > +       pci_write_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, value);
> > > > > > > +
> > > > > > >         gl9755_wt_off(pdev);
> > > > > > >  }
> > > > > > >
> > > > > > > --
> > > > > > > 2.25.1
> > > > > > >

Victor Shih Oct. 6, 2023, 10:30 a.m. UTC | #8

On Mon, Oct 2, 2023 at 10:18 AM Kai-Heng Feng
<[e-mail]> wrote:
>
> Hi Victor,
>
> On Tue, Sep 26, 2023 at 4:21 PM Victor Shih <[e-mail]> wrote:
> >
> > On Fri, Sep 22, 2023 at 3:11 PM Kai-Heng Feng
> > <[e-mail]> wrote:
> > >
> > > Hi Victor,
> > >
> > > On Wed, Sep 20, 2023 at 4:54 PM Victor Shih <[e-mail]> wrote:
> > > >
> > > > On Tue, Sep 19, 2023 at 3:31 PM Kai-Heng Feng
> > > > <[e-mail]> wrote:
> > > > >
> > > > > Hi Victor,
> > > > >
> > > > > On Tue, Sep 19, 2023 at 3:10 PM Victor Shih <[e-mail]> wrote:
> > > > > >
> > > > > > On Tue, Sep 19, 2023 at 12:24 PM Kai-Heng Feng
> > > > > > <[e-mail]> wrote:
> > > > > > >
> > > > > > > Hi Victor,
> > > > > > >
> > > > > > > On Mon, Sep 18, 2023 at 6:31 PM Victor Shih <[e-mail]> wrote:
> > > > > > > >
> > > > > > > > From: Victor Shih <[e-mail]>
> > > > > > > >
> > > > > > > > Due to a flaw in the hardware design, the GL975x replay timer frequently
> > > > > > > > times out when ASPM is enabled. As a result, the system will resume
> > > > > > > > immediately when it enters suspend. Therefore, the replay timer
> > > > > > > > timeout must be masked.
> > > > > > >
> > > > > > > This patch solves AER error when its PCI config gets accessed, but the
> > > > > > > AER still happens at system suspend:
> > > > > > >
> > > > > > > [ 1100.103603] ACPI: EC: interrupt blocked
> > > > > > > [ 1100.268244] ACPI: EC: interrupt unblocked
> > > > > > > [ 1100.326960] pcieport 0000:00:1c.0: AER: Corrected error received:
> > > > > > > 0000:00:1c.0
> > > > > > > [ 1100.326991] pcieport 0000:00:1c.0: PCIe Bus Error:
> > > > > > > severity=Corrected, type=Data Link Layer, (Transmitter ID)
> > > > > > > [ 1100.326993] pcieport 0000:00:1c.0:   device [8086:7ab9] error
> > > > > > > status/mask=00001000/00002000
> > > > > > > [ 1100.326996] pcieport 0000:00:1c.0:    [12] Timeout
> > > > > > >
> > > > > > > Kai-Heng
> > > > > > >
> > > > > >
> > > > > > Hi, Kai-Heng
> > > > > >
> > > > > > Could you try applying the patch and re-testing again after restarting
> > > > > > the system?
> > > > >
> > > > > Same issue happens after coldboot.
> > > > >
> > > > > > Because I applied the patch and restarted the system and it didn't happen.
> > > > > > The system can enter suspend normally.
> > > > > >
> > > > > > If you still have the issue after following the above instructions,
> > > > > > please provide me with your environment and I will verify it again.
> > > > >
> > > > > The patch gets applied on top of next-20230918. Please let me know
> > > > > what else you want to know.
> > > > >
> > > > > Kai-Heng
> > > > >
> > > >
> > > > Hi, Kai-Heng
> > > >
> > > > If I want to mask the replay timer timeout AER of the upper layer root port,
> > > > could you give me some suggestions?
> > > > Or could you provide sample code for my reference?
> > >
> > > I am not aware of anyway to mask "replay timer timeout" from root port.
> > > I wonder if the device supoprt D3hot? Or should it stay at D0 when
> > > ASPM L1.2 is enabled?
> > >
> > > Kai-Heng
> > >
> >
> > Hi, Kai-Heng
> >
> > Do you know any way to mask the replay timer timeout AER of the
> > upstream port from the device?
>
> Per PCIe Spec, I don't think it's possible to only mask 'replay timer timeout'.
>
> > The device supports D3hot.
>
> Do you think such error plays any crucial rule? Otherwise disable
> 'correctable' errors may be plausible.
>
> Kai-Heng
>

Hi, Kai-Heng

Due to a flaw in the hardware design, the GL975x replay timer frequently
times out when ASPM is enabled.
This patch solves the AER error of the replay timer timeout for GL975x.
We have not encountered any other errors so far.
Does your 'correctable' errors mean the AER error of the replay timer timeout?
May I ask if you have any other comments on this patch?

Thanks, Victor Shih

> >
> > Thanks, Victor Shih
> >
> > > >
> > > > Thanks, Victor Shih
> > > >
> > > > > >
> > > > > > Thanks, Victor Shih
> > > > > >
> > > > > > > >
> > > > > > > > Signed-off-by: Victor Shih <[e-mail]>
> > > > > > > > ---
> > > > > > > >  drivers/mmc/host/sdhci-pci-gli.c | 16 ++++++++++++++++
> > > > > > > >  1 file changed, 16 insertions(+)
> > > > > > > >
> > > > > > > > diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c
> > > > > > > > index d83261e857a5..d8a991b349a8 100644
> > > > > > > > --- a/drivers/mmc/host/sdhci-pci-gli.c
> > > > > > > > +++ b/drivers/mmc/host/sdhci-pci-gli.c
> > > > > > > > @@ -28,6 +28,9 @@
> > > > > > > >  #define PCI_GLI_9750_PM_CTRL   0xFC
> > > > > > > >  #define   PCI_GLI_9750_PM_STATE          GENMASK(1, 0)
> > > > > > > >
> > > > > > > > +#define PCI_GLI_9750_CORRERR_MASK                              0x214
> > > > > > > > +#define   PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> > > > > > > > +
> > > > > > > >  #define SDHCI_GLI_9750_CFG2          0x848
> > > > > > > >  #define   SDHCI_GLI_9750_CFG2_L1DLY    GENMASK(28, 24)
> > > > > > > >  #define   GLI_9750_CFG2_L1DLY_VALUE    0x1F
> > > > > > > > @@ -152,6 +155,9 @@
> > > > > > > >  #define PCI_GLI_9755_PM_CTRL     0xFC
> > > > > > > >  #define   PCI_GLI_9755_PM_STATE    GENMASK(1, 0)
> > > > > > > >
> > > > > > > > +#define PCI_GLI_9755_CORRERR_MASK                              0x214
> > > > > > > > +#define   PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> > > > > > > > +
> > > > > > > >  #define SDHCI_GLI_9767_GM_BURST_SIZE                   0x510
> > > > > > > >  #define   SDHCI_GLI_9767_GM_BURST_SIZE_AXI_ALWAYS_SET    BIT(8)
> > > > > > > >
> > > > > > > > @@ -561,6 +567,11 @@ static void gl9750_hw_setting(struct sdhci_host *host)
> > > > > > > >         value &= ~PCI_GLI_9750_PM_STATE;
> > > > > > > >         pci_write_config_dword(pdev, PCI_GLI_9750_PM_CTRL, value);
> > > > > > > >
> > > > > > > > +       /* mask the replay timer timeout of AER */
> > > > > > > > +       pci_read_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, &value);
> > > > > > > > +       value |= PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> > > > > > > > +       pci_write_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, value);
> > > > > > > > +
> > > > > > > >         gl9750_wt_off(host);
> > > > > > > >  }
> > > > > > > >
> > > > > > > > @@ -770,6 +781,11 @@ static void gl9755_hw_setting(struct sdhci_pci_slot *slot)
> > > > > > > >         value &= ~PCI_GLI_9755_PM_STATE;
> > > > > > > >         pci_write_config_dword(pdev, PCI_GLI_9755_PM_CTRL, value);
> > > > > > > >
> > > > > > > > +       /* mask the replay timer timeout of AER */
> > > > > > > > +       pci_read_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, &value);
> > > > > > > > +       value |= PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> > > > > > > > +       pci_write_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, value);
> > > > > > > > +
> > > > > > > >         gl9755_wt_off(pdev);
> > > > > > > >  }
> > > > > > > >
> > > > > > > > --
> > > > > > > > 2.25.1
> > > > > > > >

Kai-Heng Feng Oct. 11, 2023, 6:34 a.m. UTC | #9

On Fri, Oct 6, 2023 at 6:30 PM Victor Shih <[e-mail]> wrote:
>
> On Mon, Oct 2, 2023 at 10:18 AM Kai-Heng Feng
> <[e-mail]> wrote:
> >
> > Hi Victor,
> >
> > On Tue, Sep 26, 2023 at 4:21 PM Victor Shih <[e-mail]> wrote:
> > >
> > > On Fri, Sep 22, 2023 at 3:11 PM Kai-Heng Feng
> > > <[e-mail]> wrote:
> > > >
> > > > Hi Victor,
> > > >
> > > > On Wed, Sep 20, 2023 at 4:54 PM Victor Shih <[e-mail]> wrote:
> > > > >
> > > > > On Tue, Sep 19, 2023 at 3:31 PM Kai-Heng Feng
> > > > > <[e-mail]> wrote:
> > > > > >
> > > > > > Hi Victor,
> > > > > >
> > > > > > On Tue, Sep 19, 2023 at 3:10 PM Victor Shih <[e-mail]> wrote:
> > > > > > >
> > > > > > > On Tue, Sep 19, 2023 at 12:24 PM Kai-Heng Feng
> > > > > > > <[e-mail]> wrote:
> > > > > > > >
> > > > > > > > Hi Victor,
> > > > > > > >
> > > > > > > > On Mon, Sep 18, 2023 at 6:31 PM Victor Shih <[e-mail]> wrote:
> > > > > > > > >
> > > > > > > > > From: Victor Shih <[e-mail]>
> > > > > > > > >
> > > > > > > > > Due to a flaw in the hardware design, the GL975x replay timer frequently
> > > > > > > > > times out when ASPM is enabled. As a result, the system will resume
> > > > > > > > > immediately when it enters suspend. Therefore, the replay timer
> > > > > > > > > timeout must be masked.
> > > > > > > >
> > > > > > > > This patch solves AER error when its PCI config gets accessed, but the
> > > > > > > > AER still happens at system suspend:
> > > > > > > >
> > > > > > > > [ 1100.103603] ACPI: EC: interrupt blocked
> > > > > > > > [ 1100.268244] ACPI: EC: interrupt unblocked
> > > > > > > > [ 1100.326960] pcieport 0000:00:1c.0: AER: Corrected error received:
> > > > > > > > 0000:00:1c.0
> > > > > > > > [ 1100.326991] pcieport 0000:00:1c.0: PCIe Bus Error:
> > > > > > > > severity=Corrected, type=Data Link Layer, (Transmitter ID)
> > > > > > > > [ 1100.326993] pcieport 0000:00:1c.0:   device [8086:7ab9] error
> > > > > > > > status/mask=00001000/00002000
> > > > > > > > [ 1100.326996] pcieport 0000:00:1c.0:    [12] Timeout
> > > > > > > >
> > > > > > > > Kai-Heng
> > > > > > > >
> > > > > > >
> > > > > > > Hi, Kai-Heng
> > > > > > >
> > > > > > > Could you try applying the patch and re-testing again after restarting
> > > > > > > the system?
> > > > > >
> > > > > > Same issue happens after coldboot.
> > > > > >
> > > > > > > Because I applied the patch and restarted the system and it didn't happen.
> > > > > > > The system can enter suspend normally.
> > > > > > >
> > > > > > > If you still have the issue after following the above instructions,
> > > > > > > please provide me with your environment and I will verify it again.
> > > > > >
> > > > > > The patch gets applied on top of next-20230918. Please let me know
> > > > > > what else you want to know.
> > > > > >
> > > > > > Kai-Heng
> > > > > >
> > > > >
> > > > > Hi, Kai-Heng
> > > > >
> > > > > If I want to mask the replay timer timeout AER of the upper layer root port,
> > > > > could you give me some suggestions?
> > > > > Or could you provide sample code for my reference?
> > > >
> > > > I am not aware of anyway to mask "replay timer timeout" from root port.
> > > > I wonder if the device supoprt D3hot? Or should it stay at D0 when
> > > > ASPM L1.2 is enabled?
> > > >
> > > > Kai-Heng
> > > >
> > >
> > > Hi, Kai-Heng
> > >
> > > Do you know any way to mask the replay timer timeout AER of the
> > > upstream port from the device?
> >
> > Per PCIe Spec, I don't think it's possible to only mask 'replay timer timeout'.
> >
> > > The device supports D3hot.
> >
> > Do you think such error plays any crucial rule? Otherwise disable
> > 'correctable' errors may be plausible.
> >
> > Kai-Heng
> >
>
> Hi, Kai-Heng
>
> Due to a flaw in the hardware design, the GL975x replay timer frequently
> times out when ASPM is enabled.
> This patch solves the AER error of the replay timer timeout for GL975x.
> We have not encountered any other errors so far.

On the system I tested, this patch reduces the occurrence of the
error, but not completely eliminated.

> Does your 'correctable' errors mean the AER error of the replay timer timeout?
> May I ask if you have any other comments on this patch?

Spamming `lspci -vv -s` on the device can still observe the AER error.

I think the "correctable" mask should be optional, let me send a patch
to PCI for comment.

Kai-Heng

>
> Thanks, Victor Shih
>
> > >
> > > Thanks, Victor Shih
> > >
> > > > >
> > > > > Thanks, Victor Shih
> > > > >
> > > > > > >
> > > > > > > Thanks, Victor Shih
> > > > > > >
> > > > > > > > >
> > > > > > > > > Signed-off-by: Victor Shih <[e-mail]>
> > > > > > > > > ---
> > > > > > > > >  drivers/mmc/host/sdhci-pci-gli.c | 16 ++++++++++++++++
> > > > > > > > >  1 file changed, 16 insertions(+)
> > > > > > > > >
> > > > > > > > > diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c
> > > > > > > > > index d83261e857a5..d8a991b349a8 100644
> > > > > > > > > --- a/drivers/mmc/host/sdhci-pci-gli.c
> > > > > > > > > +++ b/drivers/mmc/host/sdhci-pci-gli.c
> > > > > > > > > @@ -28,6 +28,9 @@
> > > > > > > > >  #define PCI_GLI_9750_PM_CTRL   0xFC
> > > > > > > > >  #define   PCI_GLI_9750_PM_STATE          GENMASK(1, 0)
> > > > > > > > >
> > > > > > > > > +#define PCI_GLI_9750_CORRERR_MASK                              0x214
> > > > > > > > > +#define   PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> > > > > > > > > +
> > > > > > > > >  #define SDHCI_GLI_9750_CFG2          0x848
> > > > > > > > >  #define   SDHCI_GLI_9750_CFG2_L1DLY    GENMASK(28, 24)
> > > > > > > > >  #define   GLI_9750_CFG2_L1DLY_VALUE    0x1F
> > > > > > > > > @@ -152,6 +155,9 @@
> > > > > > > > >  #define PCI_GLI_9755_PM_CTRL     0xFC
> > > > > > > > >  #define   PCI_GLI_9755_PM_STATE    GENMASK(1, 0)
> > > > > > > > >
> > > > > > > > > +#define PCI_GLI_9755_CORRERR_MASK                              0x214
> > > > > > > > > +#define   PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> > > > > > > > > +
> > > > > > > > >  #define SDHCI_GLI_9767_GM_BURST_SIZE                   0x510
> > > > > > > > >  #define   SDHCI_GLI_9767_GM_BURST_SIZE_AXI_ALWAYS_SET    BIT(8)
> > > > > > > > >
> > > > > > > > > @@ -561,6 +567,11 @@ static void gl9750_hw_setting(struct sdhci_host *host)
> > > > > > > > >         value &= ~PCI_GLI_9750_PM_STATE;
> > > > > > > > >         pci_write_config_dword(pdev, PCI_GLI_9750_PM_CTRL, value);
> > > > > > > > >
> > > > > > > > > +       /* mask the replay timer timeout of AER */
> > > > > > > > > +       pci_read_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, &value);
> > > > > > > > > +       value |= PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> > > > > > > > > +       pci_write_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, value);
> > > > > > > > > +
> > > > > > > > >         gl9750_wt_off(host);
> > > > > > > > >  }
> > > > > > > > >
> > > > > > > > > @@ -770,6 +781,11 @@ static void gl9755_hw_setting(struct sdhci_pci_slot *slot)
> > > > > > > > >         value &= ~PCI_GLI_9755_PM_STATE;
> > > > > > > > >         pci_write_config_dword(pdev, PCI_GLI_9755_PM_CTRL, value);
> > > > > > > > >
> > > > > > > > > +       /* mask the replay timer timeout of AER */
> > > > > > > > > +       pci_read_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, &value);
> > > > > > > > > +       value |= PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> > > > > > > > > +       pci_write_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, value);
> > > > > > > > > +
> > > > > > > > >         gl9755_wt_off(pdev);
> > > > > > > > >  }
> > > > > > > > >
> > > > > > > > > --
> > > > > > > > > 2.25.1
> > > > > > > > >

Victor Shih Oct. 18, 2023, 10:05 a.m. UTC | #10

On Wed, Oct 11, 2023 at 2:35 PM Kai-Heng Feng
<[e-mail]> wrote:
>
> On Fri, Oct 6, 2023 at 6:30 PM Victor Shih <[e-mail]> wrote:
> >
> > On Mon, Oct 2, 2023 at 10:18 AM Kai-Heng Feng
> > <[e-mail]> wrote:
> > >
> > > Hi Victor,
> > >
> > > On Tue, Sep 26, 2023 at 4:21 PM Victor Shih <[e-mail]> wrote:
> > > >
> > > > On Fri, Sep 22, 2023 at 3:11 PM Kai-Heng Feng
> > > > <[e-mail]> wrote:
> > > > >
> > > > > Hi Victor,
> > > > >
> > > > > On Wed, Sep 20, 2023 at 4:54 PM Victor Shih <[e-mail]> wrote:
> > > > > >
> > > > > > On Tue, Sep 19, 2023 at 3:31 PM Kai-Heng Feng
> > > > > > <[e-mail]> wrote:
> > > > > > >
> > > > > > > Hi Victor,
> > > > > > >
> > > > > > > On Tue, Sep 19, 2023 at 3:10 PM Victor Shih <[e-mail]> wrote:
> > > > > > > >
> > > > > > > > On Tue, Sep 19, 2023 at 12:24 PM Kai-Heng Feng
> > > > > > > > <[e-mail]> wrote:
> > > > > > > > >
> > > > > > > > > Hi Victor,
> > > > > > > > >
> > > > > > > > > On Mon, Sep 18, 2023 at 6:31 PM Victor Shih <[e-mail]> wrote:
> > > > > > > > > >
> > > > > > > > > > From: Victor Shih <[e-mail]>
> > > > > > > > > >
> > > > > > > > > > Due to a flaw in the hardware design, the GL975x replay timer frequently
> > > > > > > > > > times out when ASPM is enabled. As a result, the system will resume
> > > > > > > > > > immediately when it enters suspend. Therefore, the replay timer
> > > > > > > > > > timeout must be masked.
> > > > > > > > >
> > > > > > > > > This patch solves AER error when its PCI config gets accessed, but the
> > > > > > > > > AER still happens at system suspend:
> > > > > > > > >
> > > > > > > > > [ 1100.103603] ACPI: EC: interrupt blocked
> > > > > > > > > [ 1100.268244] ACPI: EC: interrupt unblocked
> > > > > > > > > [ 1100.326960] pcieport 0000:00:1c.0: AER: Corrected error received:
> > > > > > > > > 0000:00:1c.0
> > > > > > > > > [ 1100.326991] pcieport 0000:00:1c.0: PCIe Bus Error:
> > > > > > > > > severity=Corrected, type=Data Link Layer, (Transmitter ID)
> > > > > > > > > [ 1100.326993] pcieport 0000:00:1c.0:   device [8086:7ab9] error
> > > > > > > > > status/mask=00001000/00002000
> > > > > > > > > [ 1100.326996] pcieport 0000:00:1c.0:    [12] Timeout
> > > > > > > > >
> > > > > > > > > Kai-Heng
> > > > > > > > >
> > > > > > > >
> > > > > > > > Hi, Kai-Heng
> > > > > > > >
> > > > > > > > Could you try applying the patch and re-testing again after restarting
> > > > > > > > the system?
> > > > > > >
> > > > > > > Same issue happens after coldboot.
> > > > > > >
> > > > > > > > Because I applied the patch and restarted the system and it didn't happen.
> > > > > > > > The system can enter suspend normally.
> > > > > > > >
> > > > > > > > If you still have the issue after following the above instructions,
> > > > > > > > please provide me with your environment and I will verify it again.
> > > > > > >
> > > > > > > The patch gets applied on top of next-20230918. Please let me know
> > > > > > > what else you want to know.
> > > > > > >
> > > > > > > Kai-Heng
> > > > > > >
> > > > > >
> > > > > > Hi, Kai-Heng
> > > > > >
> > > > > > If I want to mask the replay timer timeout AER of the upper layer root port,
> > > > > > could you give me some suggestions?
> > > > > > Or could you provide sample code for my reference?
> > > > >
> > > > > I am not aware of anyway to mask "replay timer timeout" from root port.
> > > > > I wonder if the device supoprt D3hot? Or should it stay at D0 when
> > > > > ASPM L1.2 is enabled?
> > > > >
> > > > > Kai-Heng
> > > > >
> > > >
> > > > Hi, Kai-Heng
> > > >
> > > > Do you know any way to mask the replay timer timeout AER of the
> > > > upstream port from the device?
> > >
> > > Per PCIe Spec, I don't think it's possible to only mask 'replay timer timeout'.
> > >
> > > > The device supports D3hot.
> > >
> > > Do you think such error plays any crucial rule? Otherwise disable
> > > 'correctable' errors may be plausible.
> > >
> > > Kai-Heng
> > >
> >
> > Hi, Kai-Heng
> >
> > Due to a flaw in the hardware design, the GL975x replay timer frequently
> > times out when ASPM is enabled.
> > This patch solves the AER error of the replay timer timeout for GL975x.
> > We have not encountered any other errors so far.
>
> On the system I tested, this patch reduces the occurrence of the
> error, but not completely eliminated.
>
> > Does your 'correctable' errors mean the AER error of the replay timer timeout?
> > May I ask if you have any other comments on this patch?
>
> Spamming `lspci -vv -s` on the device can still observe the AER error.
>
> I think the "correctable" mask should be optional, let me send a patch
> to PCI for comment.
>
> Kai-Heng
>

Hi, Kai-Heng

As we discussed in another email, if you want to solve the issue of suspension,
you only need masking the replay timer timeout on its root port.
I haven't seen the PCI patch you submitted yet.
If you provide me with the PCI patch, I can help you test it.

This patch only solves the warning messages that will often appear in
the system log
when the system accesses the GL975x PCI config.
Therefore, I will revise the commit message and submit the V2 version.

Thanks, Victor Shih

> >
> > Thanks, Victor Shih
> >
> > > >
> > > > Thanks, Victor Shih
> > > >
> > > > > >
> > > > > > Thanks, Victor Shih
> > > > > >
> > > > > > > >
> > > > > > > > Thanks, Victor Shih
> > > > > > > >
> > > > > > > > > >
> > > > > > > > > > Signed-off-by: Victor Shih <[e-mail]>
> > > > > > > > > > ---
> > > > > > > > > >  drivers/mmc/host/sdhci-pci-gli.c | 16 ++++++++++++++++
> > > > > > > > > >  1 file changed, 16 insertions(+)
> > > > > > > > > >
> > > > > > > > > > diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c
> > > > > > > > > > index d83261e857a5..d8a991b349a8 100644
> > > > > > > > > > --- a/drivers/mmc/host/sdhci-pci-gli.c
> > > > > > > > > > +++ b/drivers/mmc/host/sdhci-pci-gli.c
> > > > > > > > > > @@ -28,6 +28,9 @@
> > > > > > > > > >  #define PCI_GLI_9750_PM_CTRL   0xFC
> > > > > > > > > >  #define   PCI_GLI_9750_PM_STATE          GENMASK(1, 0)
> > > > > > > > > >
> > > > > > > > > > +#define PCI_GLI_9750_CORRERR_MASK                              0x214
> > > > > > > > > > +#define   PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> > > > > > > > > > +
> > > > > > > > > >  #define SDHCI_GLI_9750_CFG2          0x848
> > > > > > > > > >  #define   SDHCI_GLI_9750_CFG2_L1DLY    GENMASK(28, 24)
> > > > > > > > > >  #define   GLI_9750_CFG2_L1DLY_VALUE    0x1F
> > > > > > > > > > @@ -152,6 +155,9 @@
> > > > > > > > > >  #define PCI_GLI_9755_PM_CTRL     0xFC
> > > > > > > > > >  #define   PCI_GLI_9755_PM_STATE    GENMASK(1, 0)
> > > > > > > > > >
> > > > > > > > > > +#define PCI_GLI_9755_CORRERR_MASK                              0x214
> > > > > > > > > > +#define   PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT         BIT(12)
> > > > > > > > > > +
> > > > > > > > > >  #define SDHCI_GLI_9767_GM_BURST_SIZE                   0x510
> > > > > > > > > >  #define   SDHCI_GLI_9767_GM_BURST_SIZE_AXI_ALWAYS_SET    BIT(8)
> > > > > > > > > >
> > > > > > > > > > @@ -561,6 +567,11 @@ static void gl9750_hw_setting(struct sdhci_host *host)
> > > > > > > > > >         value &= ~PCI_GLI_9750_PM_STATE;
> > > > > > > > > >         pci_write_config_dword(pdev, PCI_GLI_9750_PM_CTRL, value);
> > > > > > > > > >
> > > > > > > > > > +       /* mask the replay timer timeout of AER */
> > > > > > > > > > +       pci_read_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, &value);
> > > > > > > > > > +       value |= PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> > > > > > > > > > +       pci_write_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, value);
> > > > > > > > > > +
> > > > > > > > > >         gl9750_wt_off(host);
> > > > > > > > > >  }
> > > > > > > > > >
> > > > > > > > > > @@ -770,6 +781,11 @@ static void gl9755_hw_setting(struct sdhci_pci_slot *slot)
> > > > > > > > > >         value &= ~PCI_GLI_9755_PM_STATE;
> > > > > > > > > >         pci_write_config_dword(pdev, PCI_GLI_9755_PM_CTRL, value);
> > > > > > > > > >
> > > > > > > > > > +       /* mask the replay timer timeout of AER */
> > > > > > > > > > +       pci_read_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, &value);
> > > > > > > > > > +       value |= PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
> > > > > > > > > > +       pci_write_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, value);
> > > > > > > > > > +
> > > > > > > > > >         gl9755_wt_off(pdev);
> > > > > > > > > >  }
> > > > > > > > > >
> > > > > > > > > > --
> > > > > > > > > > 2.25.1
> > > > > > > > > >

Patch

diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c
index d83261e857a5..d8a991b349a8 100644
--- a/drivers/mmc/host/sdhci-pci-gli.c
+++ b/drivers/mmc/host/sdhci-pci-gli.c
@@ -28,6 +28,9 @@ 
 #define PCI_GLI_9750_PM_CTRL	0xFC
 #define   PCI_GLI_9750_PM_STATE	  GENMASK(1, 0)
 
+#define PCI_GLI_9750_CORRERR_MASK				0x214
+#define   PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT	  BIT(12)
+
 #define SDHCI_GLI_9750_CFG2          0x848
 #define   SDHCI_GLI_9750_CFG2_L1DLY    GENMASK(28, 24)
 #define   GLI_9750_CFG2_L1DLY_VALUE    0x1F
@@ -152,6 +155,9 @@ 
 #define PCI_GLI_9755_PM_CTRL     0xFC
 #define   PCI_GLI_9755_PM_STATE    GENMASK(1, 0)
 
+#define PCI_GLI_9755_CORRERR_MASK				0x214
+#define   PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT	  BIT(12)
+
 #define SDHCI_GLI_9767_GM_BURST_SIZE			0x510
 #define   SDHCI_GLI_9767_GM_BURST_SIZE_AXI_ALWAYS_SET	  BIT(8)
 
@@ -561,6 +567,11 @@  static void gl9750_hw_setting(struct sdhci_host *host)
 	value &= ~PCI_GLI_9750_PM_STATE;
 	pci_write_config_dword(pdev, PCI_GLI_9750_PM_CTRL, value);
 
+	/* mask the replay timer timeout of AER */
+	pci_read_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, &value);
+	value |= PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
+	pci_write_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, value);
+
 	gl9750_wt_off(host);
 }
 
@@ -770,6 +781,11 @@  static void gl9755_hw_setting(struct sdhci_pci_slot *slot)
 	value &= ~PCI_GLI_9755_PM_STATE;
 	pci_write_config_dword(pdev, PCI_GLI_9755_PM_CTRL, value);
 
+	/* mask the replay timer timeout of AER */
+	pci_read_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, &value);
+	value |= PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
+	pci_write_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, value);
+
 	gl9755_wt_off(pdev);
 }