* [PATCH] arm64: dts: ti: k3-am65: mark dss as dma-coherent @ 2020-10-29 14:11 ` Tomi Valkeinen 0 siblings, 0 replies; 14+ messages in thread From: Tomi Valkeinen @ 2020-10-29 14:11 UTC (permalink / raw) To: Tero Kristo, Nishanth Menon, Nikhil Devshatwar Cc: devicetree, Tomi Valkeinen, linux-arm-kernel DSS is IO coherent on AM65, so we can mark it as such with 'dma-coherent' property in the DT file. Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> --- Sending separately as requested. arch/arm64/boot/dts/ti/k3-am65-main.dtsi | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi index 533525229a8d..a0b4a421026f 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi @@ -867,6 +867,8 @@ dss: dss@04a00000 { status = "disabled"; + dma-coherent; + dss_ports: ports { #address-cells = <1>; #size-cells = <0>; -- Texas Instruments Finland Oy, Porkkalankatu 22, 00180 Helsinki. Y-tunnus/Business ID: 0615521-4. Kotipaikka/Domicile: Helsinki _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel ^ permalink raw reply related [flat|nested] 14+ messages in thread
* [PATCH] arm64: dts: ti: k3-am65: mark dss as dma-coherent @ 2020-10-29 14:11 ` Tomi Valkeinen 0 siblings, 0 replies; 14+ messages in thread From: Tomi Valkeinen @ 2020-10-29 14:11 UTC (permalink / raw) To: Tero Kristo, Nishanth Menon, Nikhil Devshatwar Cc: devicetree, linux-arm-kernel, Tomi Valkeinen DSS is IO coherent on AM65, so we can mark it as such with 'dma-coherent' property in the DT file. Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> --- Sending separately as requested. arch/arm64/boot/dts/ti/k3-am65-main.dtsi | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi index 533525229a8d..a0b4a421026f 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi @@ -867,6 +867,8 @@ dss: dss@04a00000 { status = "disabled"; + dma-coherent; + dss_ports: ports { #address-cells = <1>; #size-cells = <0>; -- Texas Instruments Finland Oy, Porkkalankatu 22, 00180 Helsinki. Y-tunnus/Business ID: 0615521-4. Kotipaikka/Domicile: Helsinki ^ permalink raw reply related [flat|nested] 14+ messages in thread
* Re: [PATCH] arm64: dts: ti: k3-am65: mark dss as dma-coherent 2020-10-29 14:11 ` Tomi Valkeinen @ 2020-10-29 14:41 ` Nikhil Devshatwar -1 siblings, 0 replies; 14+ messages in thread From: Nikhil Devshatwar @ 2020-10-29 14:41 UTC (permalink / raw) To: Tomi Valkeinen; +Cc: Tero Kristo, Nishanth Menon, linux-arm-kernel, devicetree On 16:11-20201029, Tomi Valkeinen wrote: > DSS is IO coherent on AM65, so we can mark it as such with > 'dma-coherent' property in the DT file. > > Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> Acked-by: Nikhil Devshatwar <nikhil.nd@ti.com> Nikhil D > --- > > Sending separately as requested. > > arch/arm64/boot/dts/ti/k3-am65-main.dtsi | 2 ++ > 1 file changed, 2 insertions(+) > > diff --git a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi > index 533525229a8d..a0b4a421026f 100644 > --- a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi > +++ b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi > @@ -867,6 +867,8 @@ dss: dss@04a00000 { > > status = "disabled"; > > + dma-coherent; > + > dss_ports: ports { > #address-cells = <1>; > #size-cells = <0>; > -- > Texas Instruments Finland Oy, Porkkalankatu 22, 00180 Helsinki. > Y-tunnus/Business ID: 0615521-4. Kotipaikka/Domicile: Helsinki > _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH] arm64: dts: ti: k3-am65: mark dss as dma-coherent @ 2020-10-29 14:41 ` Nikhil Devshatwar 0 siblings, 0 replies; 14+ messages in thread From: Nikhil Devshatwar @ 2020-10-29 14:41 UTC (permalink / raw) To: Tomi Valkeinen; +Cc: Tero Kristo, Nishanth Menon, devicetree, linux-arm-kernel On 16:11-20201029, Tomi Valkeinen wrote: > DSS is IO coherent on AM65, so we can mark it as such with > 'dma-coherent' property in the DT file. > > Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> Acked-by: Nikhil Devshatwar <nikhil.nd@ti.com> Nikhil D > --- > > Sending separately as requested. > > arch/arm64/boot/dts/ti/k3-am65-main.dtsi | 2 ++ > 1 file changed, 2 insertions(+) > > diff --git a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi > index 533525229a8d..a0b4a421026f 100644 > --- a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi > +++ b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi > @@ -867,6 +867,8 @@ dss: dss@04a00000 { > > status = "disabled"; > > + dma-coherent; > + > dss_ports: ports { > #address-cells = <1>; > #size-cells = <0>; > -- > Texas Instruments Finland Oy, Porkkalankatu 22, 00180 Helsinki. > Y-tunnus/Business ID: 0615521-4. Kotipaikka/Domicile: Helsinki > ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH] arm64: dts: ti: k3-am65: mark dss as dma-coherent 2020-10-29 14:41 ` Nikhil Devshatwar @ 2020-10-29 14:52 ` Nishanth Menon -1 siblings, 0 replies; 14+ messages in thread From: Nishanth Menon @ 2020-10-29 14:52 UTC (permalink / raw) To: Nikhil Devshatwar Cc: Tero Kristo, devicetree, Tomi Valkeinen, linux-arm-kernel On 20:11-20201029, Nikhil Devshatwar wrote: > On 16:11-20201029, Tomi Valkeinen wrote: > > DSS is IO coherent on AM65, so we can mark it as such with > > 'dma-coherent' property in the DT file. > > > > Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> > Acked-by: Nikhil Devshatwar <nikhil.nd@ti.com> > Tomi: Do you need to add Fixes: tag to percolate this to stable? if yes, please comment, makes it easier for me to queue for 5.10 if possible -- Regards, Nishanth Menon Key (0xDDB5849D1736249D) / Fingerprint: F8A2 8693 54EB 8232 17A3 1A34 DDB5 849D 1736 249D _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH] arm64: dts: ti: k3-am65: mark dss as dma-coherent @ 2020-10-29 14:52 ` Nishanth Menon 0 siblings, 0 replies; 14+ messages in thread From: Nishanth Menon @ 2020-10-29 14:52 UTC (permalink / raw) To: Nikhil Devshatwar Cc: Tomi Valkeinen, Tero Kristo, devicetree, linux-arm-kernel On 20:11-20201029, Nikhil Devshatwar wrote: > On 16:11-20201029, Tomi Valkeinen wrote: > > DSS is IO coherent on AM65, so we can mark it as such with > > 'dma-coherent' property in the DT file. > > > > Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> > Acked-by: Nikhil Devshatwar <nikhil.nd@ti.com> > Tomi: Do you need to add Fixes: tag to percolate this to stable? if yes, please comment, makes it easier for me to queue for 5.10 if possible -- Regards, Nishanth Menon Key (0xDDB5849D1736249D) / Fingerprint: F8A2 8693 54EB 8232 17A3 1A34 DDB5 849D 1736 249D ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH] arm64: dts: ti: k3-am65: mark dss as dma-coherent 2020-10-29 14:52 ` Nishanth Menon @ 2020-10-30 14:08 ` Tomi Valkeinen -1 siblings, 0 replies; 14+ messages in thread From: Tomi Valkeinen @ 2020-10-30 14:08 UTC (permalink / raw) To: Nishanth Menon, Nikhil Devshatwar Cc: Tero Kristo, devicetree, linux-arm-kernel On 29/10/2020 16:52, Nishanth Menon wrote: > On 20:11-20201029, Nikhil Devshatwar wrote: >> On 16:11-20201029, Tomi Valkeinen wrote: >>> DSS is IO coherent on AM65, so we can mark it as such with >>> 'dma-coherent' property in the DT file. >>> >>> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> >> Acked-by: Nikhil Devshatwar <nikhil.nd@ti.com> >> > > Tomi: Do you need to add Fixes: tag to percolate this to stable? if > yes, please comment, makes it easier for me to queue for 5.10 if > possible I don't see this as a fix, but an optimization. Nothing is broken without this. Tomi -- Texas Instruments Finland Oy, Porkkalankatu 22, 00180 Helsinki. Y-tunnus/Business ID: 0615521-4. Kotipaikka/Domicile: Helsinki _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH] arm64: dts: ti: k3-am65: mark dss as dma-coherent @ 2020-10-30 14:08 ` Tomi Valkeinen 0 siblings, 0 replies; 14+ messages in thread From: Tomi Valkeinen @ 2020-10-30 14:08 UTC (permalink / raw) To: Nishanth Menon, Nikhil Devshatwar Cc: Tero Kristo, devicetree, linux-arm-kernel On 29/10/2020 16:52, Nishanth Menon wrote: > On 20:11-20201029, Nikhil Devshatwar wrote: >> On 16:11-20201029, Tomi Valkeinen wrote: >>> DSS is IO coherent on AM65, so we can mark it as such with >>> 'dma-coherent' property in the DT file. >>> >>> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> >> Acked-by: Nikhil Devshatwar <nikhil.nd@ti.com> >> > > Tomi: Do you need to add Fixes: tag to percolate this to stable? if > yes, please comment, makes it easier for me to queue for 5.10 if > possible I don't see this as a fix, but an optimization. Nothing is broken without this. Tomi -- Texas Instruments Finland Oy, Porkkalankatu 22, 00180 Helsinki. Y-tunnus/Business ID: 0615521-4. Kotipaikka/Domicile: Helsinki ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH] arm64: dts: ti: k3-am65: mark dss as dma-coherent 2020-10-30 14:08 ` Tomi Valkeinen @ 2020-11-02 13:01 ` Robin Murphy -1 siblings, 0 replies; 14+ messages in thread From: Robin Murphy @ 2020-11-02 13:01 UTC (permalink / raw) To: Tomi Valkeinen, Nishanth Menon, Nikhil Devshatwar Cc: Tero Kristo, devicetree, linux-arm-kernel On 2020-10-30 14:08, Tomi Valkeinen wrote: > On 29/10/2020 16:52, Nishanth Menon wrote: >> On 20:11-20201029, Nikhil Devshatwar wrote: >>> On 16:11-20201029, Tomi Valkeinen wrote: >>>> DSS is IO coherent on AM65, so we can mark it as such with >>>> 'dma-coherent' property in the DT file. >>>> >>>> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> >>> Acked-by: Nikhil Devshatwar <nikhil.nd@ti.com> >>> >> >> Tomi: Do you need to add Fixes: tag to percolate this to stable? if >> yes, please comment, makes it easier for me to queue for 5.10 if >> possible > > I don't see this as a fix, but an optimization. Nothing is broken without this. Note that if the driver doesn't have explicit control over what type of memory access the device makes, that's not necessarily true. If coherent DMA buffers are allocated from regular kernel memory, there's still a cacheable alias kicking around that can be speculatively fetched into a cache somewhere. If the device is genuinely non-coherent, or configured to make non-snooping accesses, then that's not an issue, but it it's hard-wired to make snooping accesses it can start hitting that cached alias and not see subsequent updates to the buffer, since those are written straight to RAM via the non-cacheable mapping. At that point it becomes an actual problem (and it's not just theoretical - we've hit a real-world example of this recently with GPUs on certain Amlogic devices). Robin. _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH] arm64: dts: ti: k3-am65: mark dss as dma-coherent @ 2020-11-02 13:01 ` Robin Murphy 0 siblings, 0 replies; 14+ messages in thread From: Robin Murphy @ 2020-11-02 13:01 UTC (permalink / raw) To: Tomi Valkeinen, Nishanth Menon, Nikhil Devshatwar Cc: Tero Kristo, devicetree, linux-arm-kernel On 2020-10-30 14:08, Tomi Valkeinen wrote: > On 29/10/2020 16:52, Nishanth Menon wrote: >> On 20:11-20201029, Nikhil Devshatwar wrote: >>> On 16:11-20201029, Tomi Valkeinen wrote: >>>> DSS is IO coherent on AM65, so we can mark it as such with >>>> 'dma-coherent' property in the DT file. >>>> >>>> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> >>> Acked-by: Nikhil Devshatwar <nikhil.nd@ti.com> >>> >> >> Tomi: Do you need to add Fixes: tag to percolate this to stable? if >> yes, please comment, makes it easier for me to queue for 5.10 if >> possible > > I don't see this as a fix, but an optimization. Nothing is broken without this. Note that if the driver doesn't have explicit control over what type of memory access the device makes, that's not necessarily true. If coherent DMA buffers are allocated from regular kernel memory, there's still a cacheable alias kicking around that can be speculatively fetched into a cache somewhere. If the device is genuinely non-coherent, or configured to make non-snooping accesses, then that's not an issue, but it it's hard-wired to make snooping accesses it can start hitting that cached alias and not see subsequent updates to the buffer, since those are written straight to RAM via the non-cacheable mapping. At that point it becomes an actual problem (and it's not just theoretical - we've hit a real-world example of this recently with GPUs on certain Amlogic devices). Robin. ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH] arm64: dts: ti: k3-am65: mark dss as dma-coherent 2020-11-02 13:01 ` Robin Murphy @ 2020-11-02 13:42 ` Tomi Valkeinen -1 siblings, 0 replies; 14+ messages in thread From: Tomi Valkeinen @ 2020-11-02 13:42 UTC (permalink / raw) To: Robin Murphy, Nishanth Menon, Nikhil Devshatwar Cc: Tero Kristo, devicetree, linux-arm-kernel Hi, On 02/11/2020 15:01, Robin Murphy wrote: > On 2020-10-30 14:08, Tomi Valkeinen wrote: >> On 29/10/2020 16:52, Nishanth Menon wrote: >>> On 20:11-20201029, Nikhil Devshatwar wrote: >>>> On 16:11-20201029, Tomi Valkeinen wrote: >>>>> DSS is IO coherent on AM65, so we can mark it as such with >>>>> 'dma-coherent' property in the DT file. >>>>> >>>>> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> >>>> Acked-by: Nikhil Devshatwar <nikhil.nd@ti.com> >>>> >>> >>> Tomi: Do you need to add Fixes: tag to percolate this to stable? if >>> yes, please comment, makes it easier for me to queue for 5.10 if >>> possible >> >> I don't see this as a fix, but an optimization. Nothing is broken without this. > > Note that if the driver doesn't have explicit control over what type of memory access the device > makes, that's not necessarily true. > > If coherent DMA buffers are allocated from regular kernel memory, there's still a cacheable alias > kicking around that can be speculatively fetched into a cache somewhere. If the device is genuinely > non-coherent, or configured to make non-snooping accesses, then that's not an issue, but it it's > hard-wired to make snooping accesses it can start hitting that cached alias and not see subsequent > updates to the buffer, since those are written straight to RAM via the non-cacheable mapping. At > that point it becomes an actual problem (and it's not just theoretical - we've hit a real-world > example of this recently with GPUs on certain Amlogic devices). Ok, thanks. I don't know if that the case here, but better safe than sorry. I'll send a new one with appropriate tags. Tomi -- Texas Instruments Finland Oy, Porkkalankatu 22, 00180 Helsinki. Y-tunnus/Business ID: 0615521-4. Kotipaikka/Domicile: Helsinki _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH] arm64: dts: ti: k3-am65: mark dss as dma-coherent @ 2020-11-02 13:42 ` Tomi Valkeinen 0 siblings, 0 replies; 14+ messages in thread From: Tomi Valkeinen @ 2020-11-02 13:42 UTC (permalink / raw) To: Robin Murphy, Nishanth Menon, Nikhil Devshatwar Cc: Tero Kristo, devicetree, linux-arm-kernel Hi, On 02/11/2020 15:01, Robin Murphy wrote: > On 2020-10-30 14:08, Tomi Valkeinen wrote: >> On 29/10/2020 16:52, Nishanth Menon wrote: >>> On 20:11-20201029, Nikhil Devshatwar wrote: >>>> On 16:11-20201029, Tomi Valkeinen wrote: >>>>> DSS is IO coherent on AM65, so we can mark it as such with >>>>> 'dma-coherent' property in the DT file. >>>>> >>>>> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> >>>> Acked-by: Nikhil Devshatwar <nikhil.nd@ti.com> >>>> >>> >>> Tomi: Do you need to add Fixes: tag to percolate this to stable? if >>> yes, please comment, makes it easier for me to queue for 5.10 if >>> possible >> >> I don't see this as a fix, but an optimization. Nothing is broken without this. > > Note that if the driver doesn't have explicit control over what type of memory access the device > makes, that's not necessarily true. > > If coherent DMA buffers are allocated from regular kernel memory, there's still a cacheable alias > kicking around that can be speculatively fetched into a cache somewhere. If the device is genuinely > non-coherent, or configured to make non-snooping accesses, then that's not an issue, but it it's > hard-wired to make snooping accesses it can start hitting that cached alias and not see subsequent > updates to the buffer, since those are written straight to RAM via the non-cacheable mapping. At > that point it becomes an actual problem (and it's not just theoretical - we've hit a real-world > example of this recently with GPUs on certain Amlogic devices). Ok, thanks. I don't know if that the case here, but better safe than sorry. I'll send a new one with appropriate tags. Tomi -- Texas Instruments Finland Oy, Porkkalankatu 22, 00180 Helsinki. Y-tunnus/Business ID: 0615521-4. Kotipaikka/Domicile: Helsinki ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH] arm64: dts: ti: k3-am65: mark dss as dma-coherent 2020-11-02 13:42 ` Tomi Valkeinen @ 2020-11-02 16:46 ` Nishanth Menon -1 siblings, 0 replies; 14+ messages in thread From: Nishanth Menon @ 2020-11-02 16:46 UTC (permalink / raw) To: Tomi Valkeinen Cc: Tero Kristo, devicetree, Robin Murphy, Nikhil Devshatwar, linux-arm-kernel On 15:42-20201102, Tomi Valkeinen wrote: > Hi, > > On 02/11/2020 15:01, Robin Murphy wrote: > > On 2020-10-30 14:08, Tomi Valkeinen wrote: > >> On 29/10/2020 16:52, Nishanth Menon wrote: > >>> On 20:11-20201029, Nikhil Devshatwar wrote: > >>>> On 16:11-20201029, Tomi Valkeinen wrote: > >>>>> DSS is IO coherent on AM65, so we can mark it as such with > >>>>> 'dma-coherent' property in the DT file. > >>>>> > >>>>> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> > >>>> Acked-by: Nikhil Devshatwar <nikhil.nd@ti.com> > >>>> > >>> > >>> Tomi: Do you need to add Fixes: tag to percolate this to stable? if > >>> yes, please comment, makes it easier for me to queue for 5.10 if > >>> possible > >> > >> I don't see this as a fix, but an optimization. Nothing is broken without this. > > > > Note that if the driver doesn't have explicit control over what type of memory access the device > > makes, that's not necessarily true. > > > > If coherent DMA buffers are allocated from regular kernel memory, there's still a cacheable alias > > kicking around that can be speculatively fetched into a cache somewhere. If the device is genuinely > > non-coherent, or configured to make non-snooping accesses, then that's not an issue, but it it's > > hard-wired to make snooping accesses it can start hitting that cached alias and not see subsequent > > updates to the buffer, since those are written straight to RAM via the non-cacheable mapping. At > > that point it becomes an actual problem (and it's not just theoretical - we've hit a real-world > > example of this recently with GPUs on certain Amlogic devices). > > Ok, thanks. I don't know if that the case here, but better safe than sorry. I'll send a new one with > appropriate tags. Yes - the default AM65 MAT tables do force a snoop into the clusters when using DDR based buffers. Deal with display is when you dont get to see the artifacts unless you are closely monitoring frame by frame and transitions.. which in the middle of all other automatic backend cache operations tends to be rather something easy to miss.. Will let the next rev cook for a few days unless folks have some additional comments.. -- Regards, Nishanth Menon Key (0xDDB5849D1736249D) / Fingerprint: F8A2 8693 54EB 8232 17A3 1A34 DDB5 849D 1736 249D _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH] arm64: dts: ti: k3-am65: mark dss as dma-coherent @ 2020-11-02 16:46 ` Nishanth Menon 0 siblings, 0 replies; 14+ messages in thread From: Nishanth Menon @ 2020-11-02 16:46 UTC (permalink / raw) To: Tomi Valkeinen Cc: Robin Murphy, Nikhil Devshatwar, Tero Kristo, devicetree, linux-arm-kernel On 15:42-20201102, Tomi Valkeinen wrote: > Hi, > > On 02/11/2020 15:01, Robin Murphy wrote: > > On 2020-10-30 14:08, Tomi Valkeinen wrote: > >> On 29/10/2020 16:52, Nishanth Menon wrote: > >>> On 20:11-20201029, Nikhil Devshatwar wrote: > >>>> On 16:11-20201029, Tomi Valkeinen wrote: > >>>>> DSS is IO coherent on AM65, so we can mark it as such with > >>>>> 'dma-coherent' property in the DT file. > >>>>> > >>>>> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> > >>>> Acked-by: Nikhil Devshatwar <nikhil.nd@ti.com> > >>>> > >>> > >>> Tomi: Do you need to add Fixes: tag to percolate this to stable? if > >>> yes, please comment, makes it easier for me to queue for 5.10 if > >>> possible > >> > >> I don't see this as a fix, but an optimization. Nothing is broken without this. > > > > Note that if the driver doesn't have explicit control over what type of memory access the device > > makes, that's not necessarily true. > > > > If coherent DMA buffers are allocated from regular kernel memory, there's still a cacheable alias > > kicking around that can be speculatively fetched into a cache somewhere. If the device is genuinely > > non-coherent, or configured to make non-snooping accesses, then that's not an issue, but it it's > > hard-wired to make snooping accesses it can start hitting that cached alias and not see subsequent > > updates to the buffer, since those are written straight to RAM via the non-cacheable mapping. At > > that point it becomes an actual problem (and it's not just theoretical - we've hit a real-world > > example of this recently with GPUs on certain Amlogic devices). > > Ok, thanks. I don't know if that the case here, but better safe than sorry. I'll send a new one with > appropriate tags. Yes - the default AM65 MAT tables do force a snoop into the clusters when using DDR based buffers. Deal with display is when you dont get to see the artifacts unless you are closely monitoring frame by frame and transitions.. which in the middle of all other automatic backend cache operations tends to be rather something easy to miss.. Will let the next rev cook for a few days unless folks have some additional comments.. -- Regards, Nishanth Menon Key (0xDDB5849D1736249D) / Fingerprint: F8A2 8693 54EB 8232 17A3 1A34 DDB5 849D 1736 249D ^ permalink raw reply [flat|nested] 14+ messages in thread
end of thread, other threads:[~2020-11-02 16:47 UTC | newest] Thread overview: 14+ messages (download: mbox.gz follow: Atom feed -- links below jump to the message on this page -- 2020-10-29 14:11 [PATCH] arm64: dts: ti: k3-am65: mark dss as dma-coherent Tomi Valkeinen 2020-10-29 14:11 ` Tomi Valkeinen 2020-10-29 14:41 ` Nikhil Devshatwar 2020-10-29 14:41 ` Nikhil Devshatwar 2020-10-29 14:52 ` Nishanth Menon 2020-10-29 14:52 ` Nishanth Menon 2020-10-30 14:08 ` Tomi Valkeinen 2020-10-30 14:08 ` Tomi Valkeinen 2020-11-02 13:01 ` Robin Murphy 2020-11-02 13:01 ` Robin Murphy 2020-11-02 13:42 ` Tomi Valkeinen 2020-11-02 13:42 ` Tomi Valkeinen 2020-11-02 16:46 ` Nishanth Menon 2020-11-02 16:46 ` Nishanth Menon
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.