| Message ID | 20210601102939.16139-1-peng.fan@oss.nxp.com (mailing list archive) |
|---|---|
| State | Superseded |
| Headers | show |
| Series | remoteproc: imx_rproc: correct firmware reload | expand |
On Tue, Jun 01, 2021 at 06:29:39PM +0800, Peng Fan (OSS) wrote: > From: Peng Fan <peng.fan@nxp.com> > > ENABLE_M4 should be set to 1 when loading code to TCM, otherwise > you will not able to replace the firmware after you stop m4. > > Besides ENABLE_M4, we still need set SW_M4C_RST, because this bit > will be automatically set with SW_M4C_NON_SCLR_RST set. > > Signed-off-by: Peng Fan <peng.fan@nxp.com> > --- > > V1: > Although this is an fix, but it is not critical, patch is based on > https://patchwork.kernel.org/project/linux-remoteproc/cover/1620274123-1461-1-git-send-email-peng.fan@oss.nxp.com/ > > drivers/remoteproc/imx_rproc.c | 8 +++++--- > 1 file changed, 5 insertions(+), 3 deletions(-) > > diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c > index cd2ca96a30e5..ce2ce42bee91 100644 > --- a/drivers/remoteproc/imx_rproc.c > +++ b/drivers/remoteproc/imx_rproc.c > @@ -33,7 +33,8 @@ > > #define IMX7D_M4_START (IMX7D_ENABLE_M4 | IMX7D_SW_M4P_RST \ > | IMX7D_SW_M4C_RST) > -#define IMX7D_M4_STOP (IMX7D_ENABLE_M4 | IMX7D_SW_M4C_NON_SCLR_RST) > +#define IMX7D_M4_STOP (IMX7D_ENABLE_M4 | IMX7D_SW_M4C_RST | \ > + IMX7D_SW_M4C_NON_SCLR_RST) > > /* Address: 0x020D8000 */ > #define IMX6SX_SRC_SCR 0x00 > @@ -44,7 +45,8 @@ > > #define IMX6SX_M4_START (IMX6SX_ENABLE_M4 | IMX6SX_SW_M4P_RST \ > | IMX6SX_SW_M4C_RST) > -#define IMX6SX_M4_STOP (IMX6SX_ENABLE_M4 | IMX6SX_SW_M4C_NON_SCLR_RST) > +#define IMX6SX_M4_STOP (IMX6SX_ENABLE_M4 | IMX6SX_SW_M4C_RST | \ > + IMX6SX_SW_M4C_NON_SCLR_RST) > #define IMX6SX_M4_RST_MASK (IMX6SX_ENABLE_M4 | IMX6SX_SW_M4P_RST \ > | IMX6SX_SW_M4C_NON_SCLR_RST \ > | IMX6SX_SW_M4C_RST) > @@ -691,7 +693,7 @@ static int imx_rproc_detect_mode(struct imx_rproc *priv) > return ret; > } > > - if (!(val & dcfg->src_stop)) > + if ((val & dcfg->src_mask) != dcfg->src_stop) > priv->rproc->state = RPROC_DETACHED; Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org> Bjorn hasn't picked up this set yet so it is best to send a v7 of [1] with this change merged in it. Thanks, Mathieu [1]. https://patchwork.kernel.org/project/linux-remoteproc/cover/1620274123-1461-1-git-send-email-peng.fan@oss.nxp.com/ > > return 0; > -- > 2.30.0 >
On Tue 01 Jun 10:31 CDT 2021, Mathieu Poirier wrote: > On Tue, Jun 01, 2021 at 06:29:39PM +0800, Peng Fan (OSS) wrote: > > From: Peng Fan <peng.fan@nxp.com> > > > > ENABLE_M4 should be set to 1 when loading code to TCM, otherwise > > you will not able to replace the firmware after you stop m4. > > > > Besides ENABLE_M4, we still need set SW_M4C_RST, because this bit > > will be automatically set with SW_M4C_NON_SCLR_RST set. > > > > Signed-off-by: Peng Fan <peng.fan@nxp.com> > > --- > > > > V1: > > Although this is an fix, but it is not critical, patch is based on > > https://patchwork.kernel.org/project/linux-remoteproc/cover/1620274123-1461-1-git-send-email-peng.fan@oss.nxp.com/ > > > > drivers/remoteproc/imx_rproc.c | 8 +++++--- > > 1 file changed, 5 insertions(+), 3 deletions(-) > > > > diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c > > index cd2ca96a30e5..ce2ce42bee91 100644 > > --- a/drivers/remoteproc/imx_rproc.c > > +++ b/drivers/remoteproc/imx_rproc.c > > @@ -33,7 +33,8 @@ > > > > #define IMX7D_M4_START (IMX7D_ENABLE_M4 | IMX7D_SW_M4P_RST \ > > | IMX7D_SW_M4C_RST) > > -#define IMX7D_M4_STOP (IMX7D_ENABLE_M4 | IMX7D_SW_M4C_NON_SCLR_RST) > > +#define IMX7D_M4_STOP (IMX7D_ENABLE_M4 | IMX7D_SW_M4C_RST | \ > > + IMX7D_SW_M4C_NON_SCLR_RST) > > > > /* Address: 0x020D8000 */ > > #define IMX6SX_SRC_SCR 0x00 > > @@ -44,7 +45,8 @@ > > > > #define IMX6SX_M4_START (IMX6SX_ENABLE_M4 | IMX6SX_SW_M4P_RST \ > > | IMX6SX_SW_M4C_RST) > > -#define IMX6SX_M4_STOP (IMX6SX_ENABLE_M4 | IMX6SX_SW_M4C_NON_SCLR_RST) > > +#define IMX6SX_M4_STOP (IMX6SX_ENABLE_M4 | IMX6SX_SW_M4C_RST | \ > > + IMX6SX_SW_M4C_NON_SCLR_RST) > > #define IMX6SX_M4_RST_MASK (IMX6SX_ENABLE_M4 | IMX6SX_SW_M4P_RST \ > > | IMX6SX_SW_M4C_NON_SCLR_RST \ > > | IMX6SX_SW_M4C_RST) > > @@ -691,7 +693,7 @@ static int imx_rproc_detect_mode(struct imx_rproc *priv) > > return ret; > > } > > > > - if (!(val & dcfg->src_stop)) > > + if ((val & dcfg->src_mask) != dcfg->src_stop) > > priv->rproc->state = RPROC_DETACHED; > > Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org> > > Bjorn hasn't picked up this set yet so it is best to send a v7 of [1] with this > change merged in it. > Sorry I had missed that [1] was fully reviewed, so I figured I'll just apply the series and squash this in. But afaict this patch isn't a fix to any of the patches in [1]. More so, this patch doesn't apply on top of either v5.13-rc1, linux-next or [1] - because neither IMX7D_M4_STOP nor IMX6SX_M4_STOP has IMX6SX_ENABLE_M4 included. Peng, I've applied [1] now, please let me know what to do about this patch. Regards, Bjorn > Thanks, > Mathieu > > [1]. https://patchwork.kernel.org/project/linux-remoteproc/cover/1620274123-1461-1-git-send-email-peng.fan@oss.nxp.com/ > > > > > return 0; > > -- > > 2.30.0 > >
Bjorn, Mathieu > Subject: Re: [PATCH] remoteproc: imx_rproc: correct firmware reload > > On Tue 01 Jun 10:31 CDT 2021, Mathieu Poirier wrote: > > > On Tue, Jun 01, 2021 at 06:29:39PM +0800, Peng Fan (OSS) wrote: > > > From: Peng Fan <peng.fan@nxp.com> > > > > > > ENABLE_M4 should be set to 1 when loading code to TCM, otherwise you > > > will not able to replace the firmware after you stop m4. > > > > > > Besides ENABLE_M4, we still need set SW_M4C_RST, because this bit > > > will be automatically set with SW_M4C_NON_SCLR_RST set. > > > > > > Signed-off-by: Peng Fan <peng.fan@nxp.com> > > > --- > > > > > > V1: > > > Although this is an fix, but it is not critical, patch is based on > > > > > > https://eur01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fpa > > > > tchwork.kernel.org%2Fproject%2Flinux-remoteproc%2Fcover%2F162027412 > 3 > > > > -1461-1-git-send-email-peng.fan%40oss.nxp.com%2F&data=04%7C01% > 7C > > > > peng.fan%40nxp.com%7C471a7b81f5d44fc6f85b08d925165839%7C686ea1d > 3bc2b > > > > 4c6fa92cd99c5c301635%7C0%7C0%7C637581600173592073%7CUnknown > %7CTWFpbG > > > > Zsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6 > Mn > > > > 0%3D%7C1000&sdata=5JerdzsSmjZ%2Flowd3AXo3gmr6bdHM9DCg55kv > UmTWQw% > > > 3D&reserved=0 > > > > > > drivers/remoteproc/imx_rproc.c | 8 +++++--- > > > 1 file changed, 5 insertions(+), 3 deletions(-) > > > > > > diff --git a/drivers/remoteproc/imx_rproc.c > > > b/drivers/remoteproc/imx_rproc.c index cd2ca96a30e5..ce2ce42bee91 > > > 100644 > > > --- a/drivers/remoteproc/imx_rproc.c > > > +++ b/drivers/remoteproc/imx_rproc.c > > > @@ -33,7 +33,8 @@ > > > > > > #define IMX7D_M4_START (IMX7D_ENABLE_M4 | > IMX7D_SW_M4P_RST \ > > > | IMX7D_SW_M4C_RST) > > > -#define IMX7D_M4_STOP (IMX7D_ENABLE_M4 | > IMX7D_SW_M4C_NON_SCLR_RST) > > > +#define IMX7D_M4_STOP (IMX7D_ENABLE_M4 | > IMX7D_SW_M4C_RST | \ > > > + IMX7D_SW_M4C_NON_SCLR_RST) > > > > > > /* Address: 0x020D8000 */ > > > #define IMX6SX_SRC_SCR 0x00 > > > @@ -44,7 +45,8 @@ > > > > > > #define IMX6SX_M4_START (IMX6SX_ENABLE_M4 | > IMX6SX_SW_M4P_RST \ > > > | IMX6SX_SW_M4C_RST) > > > -#define IMX6SX_M4_STOP (IMX6SX_ENABLE_M4 | > IMX6SX_SW_M4C_NON_SCLR_RST) > > > +#define IMX6SX_M4_STOP (IMX6SX_ENABLE_M4 | > IMX6SX_SW_M4C_RST | \ > > > + IMX6SX_SW_M4C_NON_SCLR_RST) > > > #define IMX6SX_M4_RST_MASK (IMX6SX_ENABLE_M4 | > IMX6SX_SW_M4P_RST \ > > > | IMX6SX_SW_M4C_NON_SCLR_RST \ > > > | IMX6SX_SW_M4C_RST) > > > @@ -691,7 +693,7 @@ static int imx_rproc_detect_mode(struct > imx_rproc *priv) > > > return ret; > > > } > > > > > > - if (!(val & dcfg->src_stop)) > > > + if ((val & dcfg->src_mask) != dcfg->src_stop) > > > priv->rproc->state = RPROC_DETACHED; > > > > Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org> > > > > Bjorn hasn't picked up this set yet so it is best to send a v7 of [1] > > with this change merged in it. > > > > Sorry I had missed that [1] was fully reviewed, so I figured I'll just apply the > series and squash this in. But afaict this patch isn't a fix to any of the patches > in [1]. > > More so, this patch doesn't apply on top of either v5.13-rc1, linux-next or [1] - > because neither IMX7D_M4_STOP nor IMX6SX_M4_STOP has > IMX6SX_ENABLE_M4 included. I'll send v2 to avoid the conflict soon. > > > Peng, I've applied [1] now, please let me know what to do about this patch. Thanks, Peng. > > Regards, > Bjorn > > > Thanks, > > Mathieu > > > > [1]. > > https://eur01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fpatc > > > hwork.kernel.org%2Fproject%2Flinux-remoteproc%2Fcover%2F1620274123- > 146 > > > 1-1-git-send-email-peng.fan%40oss.nxp.com%2F&data=04%7C01%7Cpe > ng.f > > > an%40nxp.com%7C471a7b81f5d44fc6f85b08d925165839%7C686ea1d3bc2b > 4c6fa92c > > > d99c5c301635%7C0%7C0%7C637581600173592073%7CUnknown%7CTWFp > bGZsb3d8eyJW > > > IjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C > 1000& > > > amp;sdata=5JerdzsSmjZ%2Flowd3AXo3gmr6bdHM9DCg55kvUmTWQw%3D& > amp;reserve > > d=0 > > > > > > > > return 0; > > > -- > > > 2.30.0 > > >
diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c index cd2ca96a30e5..ce2ce42bee91 100644 --- a/drivers/remoteproc/imx_rproc.c +++ b/drivers/remoteproc/imx_rproc.c @@ -33,7 +33,8 @@ #define IMX7D_M4_START (IMX7D_ENABLE_M4 | IMX7D_SW_M4P_RST \ | IMX7D_SW_M4C_RST) -#define IMX7D_M4_STOP (IMX7D_ENABLE_M4 | IMX7D_SW_M4C_NON_SCLR_RST) +#define IMX7D_M4_STOP (IMX7D_ENABLE_M4 | IMX7D_SW_M4C_RST | \ + IMX7D_SW_M4C_NON_SCLR_RST) /* Address: 0x020D8000 */ #define IMX6SX_SRC_SCR 0x00 @@ -44,7 +45,8 @@ #define IMX6SX_M4_START (IMX6SX_ENABLE_M4 | IMX6SX_SW_M4P_RST \ | IMX6SX_SW_M4C_RST) -#define IMX6SX_M4_STOP (IMX6SX_ENABLE_M4 | IMX6SX_SW_M4C_NON_SCLR_RST) +#define IMX6SX_M4_STOP (IMX6SX_ENABLE_M4 | IMX6SX_SW_M4C_RST | \ + IMX6SX_SW_M4C_NON_SCLR_RST) #define IMX6SX_M4_RST_MASK (IMX6SX_ENABLE_M4 | IMX6SX_SW_M4P_RST \ | IMX6SX_SW_M4C_NON_SCLR_RST \ | IMX6SX_SW_M4C_RST) @@ -691,7 +693,7 @@ static int imx_rproc_detect_mode(struct imx_rproc *priv) return ret; } - if (!(val & dcfg->src_stop)) + if ((val & dcfg->src_mask) != dcfg->src_stop) priv->rproc->state = RPROC_DETACHED; return 0;