Re: [PATCH V1 1/7] accel/amdxdna: Add device status for aie2 devices

[Lizhi Hou <lizhi.hou@xxxxxxx>]

On 12/4/24 14:26, Mario Limonciello wrote:
> On 12/4/2024 15:37, Lizhi Hou wrote:
> > Add device status to track if aie2_hw_start() or aie2_hw_stop() is
> > re-entered. In aie2_hw_stop(), call drmm_kfree to free mbox.
> >
> > Signed-off-by: Lizhi Hou <lizhi.hou@xxxxxxx>
> > ---
> >   drivers/accel/amdxdna/aie2_pci.c        | 17 +++++++++++++++++
> >   drivers/accel/amdxdna/aie2_pci.h        |  7 +++++++
> >   drivers/accel/amdxdna/amdxdna_mailbox.c |  6 ------
> >   3 files changed, 24 insertions(+), 6 deletions(-)
> >
> > diff --git a/drivers/accel/amdxdna/aie2_pci.c 
> > b/drivers/accel/amdxdna/aie2_pci.c
> > index 349ada697e48..19c76b2b204b 100644
> > --- a/drivers/accel/amdxdna/aie2_pci.c
> > +++ b/drivers/accel/amdxdna/aie2_pci.c
> > @@ -267,12 +267,22 @@ static void aie2_hw_stop(struct amdxdna_dev *xdna)
> >       struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev);
> >       struct amdxdna_dev_hdl *ndev = xdna->dev_handle;
> >   +    if (ndev->dev_status <= AIE2_DEV_INIT) {
> > +        XDNA_ERR(xdna, "device is already stopped");
> > +        return;
> > +    }
> > +
> >       aie2_mgmt_fw_fini(ndev);
> >       xdna_mailbox_stop_channel(ndev->mgmt_chann);
> >       xdna_mailbox_destroy_channel(ndev->mgmt_chann);
> > +    ndev->mgmt_chann = NULL;
> > +    drmm_kfree(&xdna->ddev, ndev->mbox);
> > +    ndev->mbox = NULL;
> >       aie2_psp_stop(ndev->psp_hdl);
> >       aie2_smu_fini(ndev);
> >       pci_disable_device(pdev);
> > +
> > +    ndev->dev_status = AIE2_DEV_INIT;
> >   }
> >     static int aie2_hw_start(struct amdxdna_dev *xdna)
> > @@ -283,6 +293,11 @@ static int aie2_hw_start(struct amdxdna_dev *xdna)
> >       u32 xdna_mailbox_intr_reg;
> >       int mgmt_mb_irq, ret;
> >   +    if (ndev->dev_status >= AIE2_DEV_START) {
> > +        XDNA_INFO(xdna, "device is already started");
> > +        return 0;
> > +    }
> > +
> >       ret = pci_enable_device(pdev);
> >       if (ret) {
> >           XDNA_ERR(xdna, "failed to enable device, ret %d", ret);
> > @@ -345,6 +360,8 @@ static int aie2_hw_start(struct amdxdna_dev *xdna)
> >           goto destroy_mgmt_chann;
> >       }
> >   +    ndev->dev_status = AIE2_DEV_START;
> > +
> >       return 0;
> >     destroy_mgmt_chann:
> > diff --git a/drivers/accel/amdxdna/aie2_pci.h 
> > b/drivers/accel/amdxdna/aie2_pci.h
> > index 6a2686255c9c..5d262ae5c9bb 100644
> > --- a/drivers/accel/amdxdna/aie2_pci.h
> > +++ b/drivers/accel/amdxdna/aie2_pci.h
> > @@ -149,6 +149,11 @@ struct amdxdna_hwctx_priv {
> >       struct drm_syncobj        *syncobj;
> >   };
> >   +enum aie2_dev_status {
> > +    AIE2_DEV_INIT,
> > +    AIE2_DEV_START,
> > +};
> > +
> >   struct amdxdna_dev_hdl {
> >       struct amdxdna_dev        *xdna;
> >       const struct amdxdna_dev_priv    *priv;
> > @@ -171,6 +176,8 @@ struct amdxdna_dev_hdl {
> >       struct mailbox            *mbox;
> >       struct mailbox_channel        *mgmt_chann;
> >       struct async_events        *async_events;
> > +
> > +    u32                dev_status;
>
> Shouldn't this be "enum aie2_dev_status" not "u32"?

You are right. I will fix it.


Thanks,

Lizhi

> >   };
> >     #define DEFINE_BAR_OFFSET(reg_name, bar, reg_addr) \
> > diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.c 
> > b/drivers/accel/amdxdna/amdxdna_mailbox.c
> > index 415d99abaaa3..eab79dbb8b25 100644
> > --- a/drivers/accel/amdxdna/amdxdna_mailbox.c
> > +++ b/drivers/accel/amdxdna/amdxdna_mailbox.c
> > @@ -530,9 +530,6 @@ xdna_mailbox_create_channel(struct mailbox *mb,
> >     int xdna_mailbox_destroy_channel(struct mailbox_channel *mb_chann)
> >   {
> > -    if (!mb_chann)
> > -        return 0;
> > -
> >       MB_DBG(mb_chann, "IRQ disabled and RX work cancelled");
> >       free_irq(mb_chann->msix_irq, mb_chann);
> >       destroy_workqueue(mb_chann->work_q);
> > @@ -548,9 +545,6 @@ int xdna_mailbox_destroy_channel(struct 
> > mailbox_channel *mb_chann)
> >     void xdna_mailbox_stop_channel(struct mailbox_channel *mb_chann)
> >   {
> > -    if (!mb_chann)
> > -        return;
> > -
> >       /* Disable an irq and wait. This might sleep. */
> >       disable_irq(mb_chann->msix_irq);