(no subject)

(no subject)

[Jason Gunthorpe]

Bcc: 
Subject: Re: [PATCH 2/2 v3] tpm: Add TPM 2.0 support to the Nuvoton i2c
 driver (NPCT6xx family)
Reply-To: 
In-Reply-To: <1467174493-4190-3-git-send-email-andrew.zamansky-KrzQf0k3Iz9BDgjK7y7TUQ@public.gmane.org>

On Wed, Jun 29, 2016 at 07:28:13AM +0300, andrew zamansky wrote:
> -	chip->flags |= TPM_CHIP_FLAG_IRQ;
> +	if (client->irq)
> +		chip->flags |= TPM_CHIP_FLAG_IRQ;
> +

Oh.. this should be a seperate patch, it is a bug fix for the stuff
Jarkko just sent a pull request for:

commit 570a36097f302c0bae4fb5478f1287b9b3626155
Author: Christophe Ricard <christophe.ricard-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Date:   Thu Mar 31 22:56:56 2016 +0200

    tpm: drop 'irq' from struct tpm_vendor_specific

Jason

------------------------------------------------------------------------------
Attend Shape: An AT&T Tech Expo July 15-16. Meet us at AT&T Park in San
Francisco, CA to explore cutting-edge tech and listen to tech luminaries
present their vision of the future. This family event has something for
everyone, including kids. Get more information and register today.
http://sdm.link/attshape

[No Subject]

[Gardner, Tim]

We are now providing business & personal loans: 
-Rate starting at: 2.05%. 
-Flexible repayment: up to 30 years. 
For more information and application, please reply. 

> To unsubscribe please reply with "unsubscribe" as subject. 

(No Subject)

[Yassine Oudjana]

Date: Tue, 22 Jun 2021 20:08:25 +0400
Subject: [PATCH] media: dt-bindings: media: venus: Add firmware-name

Support for parsing the firmware-name property was added a while ago [1],
but the dt-bindings were never updated with the new property. This patch
adds it to all venus dt-bindings.

Signed-off-by: Yassine Oudjana <y.oudjana@protonmail.com>

[1]: https://lore.kernel.org/linux-arm-msm/20210126084252.238078-1-stanimir.varbanov@linaro.org/
---
 .../devicetree/bindings/media/qcom,msm8916-venus.yaml        | 5 +++++
 .../devicetree/bindings/media/qcom,msm8996-venus.yaml        | 5 +++++
 .../devicetree/bindings/media/qcom,sc7180-venus.yaml         | 5 +++++
 .../devicetree/bindings/media/qcom,sdm845-venus-v2.yaml      | 5 +++++
 .../devicetree/bindings/media/qcom,sdm845-venus.yaml         | 5 +++++
 5 files changed, 25 insertions(+)

diff --git a/Documentation/devicetree/bindings/media/qcom,msm8916-venus.yaml b/Documentation/devicetree/bindings/media/qcom,msm8916-venus.yaml
index 59ab16ad12f1..cb1b866d9c37 100644
--- a/Documentation/devicetree/bindings/media/qcom,msm8916-venus.yaml
+++ b/Documentation/devicetree/bindings/media/qcom,msm8916-venus.yaml
@@ -80,6 +80,11 @@ properties:
     required:
       - iommus
 
+  firmware-name:
+    maxItems: 1
+    description: |
+      Relative firmware image path for venus.
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/media/qcom,msm8996-venus.yaml b/Documentation/devicetree/bindings/media/qcom,msm8996-venus.yaml
index 199f45217b4a..b8809325138f 100644
--- a/Documentation/devicetree/bindings/media/qcom,msm8996-venus.yaml
+++ b/Documentation/devicetree/bindings/media/qcom,msm8996-venus.yaml
@@ -107,6 +107,11 @@ properties:
     required:
       - iommus
 
+  firmware-name:
+    maxItems: 1
+    description: |
+      Relative firmware image path for venus.
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/media/qcom,sc7180-venus.yaml b/Documentation/devicetree/bindings/media/qcom,sc7180-venus.yaml
index 04013e5dd044..ffd3e2850366 100644
--- a/Documentation/devicetree/bindings/media/qcom,sc7180-venus.yaml
+++ b/Documentation/devicetree/bindings/media/qcom,sc7180-venus.yaml
@@ -99,6 +99,11 @@ properties:
     required:
       - iommus
 
+  firmware-name:
+    maxItems: 1
+    description: |
+      Relative firmware image path for venus.
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/media/qcom,sdm845-venus-v2.yaml b/Documentation/devicetree/bindings/media/qcom,sdm845-venus-v2.yaml
index 04b9af4db191..cd7a5e1374ce 100644
--- a/Documentation/devicetree/bindings/media/qcom,sdm845-venus-v2.yaml
+++ b/Documentation/devicetree/bindings/media/qcom,sdm845-venus-v2.yaml
@@ -94,6 +94,11 @@ properties:
     required:
       - iommus
 
+  firmware-name:
+    maxItems: 1
+    description: |
+      Relative firmware image path for venus.
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/media/qcom,sdm845-venus.yaml b/Documentation/devicetree/bindings/media/qcom,sdm845-venus.yaml
index 680f37726fdf..ae256238a637 100644
--- a/Documentation/devicetree/bindings/media/qcom,sdm845-venus.yaml
+++ b/Documentation/devicetree/bindings/media/qcom,sdm845-venus.yaml
@@ -108,6 +108,11 @@ properties:
     required:
       - iommus
 
+  firmware-name:
+    maxItems: 1
+    description: |
+      Relative firmware image path for venus.
+
 required:
   - compatible
   - reg
-- 
2.32.0

Re: (No Subject)

[Rob Herring]

On Tue, Jun 22, 2021 at 04:20:24PM +0000, Yassine Oudjana wrote:
> Date: Tue, 22 Jun 2021 20:08:25 +0400
> Subject: [PATCH] media: dt-bindings: media: venus: Add firmware-name
> 
> Support for parsing the firmware-name property was added a while ago [1],
> but the dt-bindings were never updated with the new property. This patch
> adds it to all venus dt-bindings.
> 
> Signed-off-by: Yassine Oudjana <y.oudjana@protonmail.com>
> 
> [1]: https://lore.kernel.org/linux-arm-msm/20210126084252.238078-1-stanimir.varbanov@linaro.org/
> ---
>  .../devicetree/bindings/media/qcom,msm8916-venus.yaml        | 5 +++++
>  .../devicetree/bindings/media/qcom,msm8996-venus.yaml        | 5 +++++
>  .../devicetree/bindings/media/qcom,sc7180-venus.yaml         | 5 +++++
>  .../devicetree/bindings/media/qcom,sdm845-venus-v2.yaml      | 5 +++++
>  .../devicetree/bindings/media/qcom,sdm845-venus.yaml         | 5 +++++
>  5 files changed, 25 insertions(+)
> 
> diff --git a/Documentation/devicetree/bindings/media/qcom,msm8916-venus.yaml b/Documentation/devicetree/bindings/media/qcom,msm8916-venus.yaml
> index 59ab16ad12f1..cb1b866d9c37 100644
> --- a/Documentation/devicetree/bindings/media/qcom,msm8916-venus.yaml
> +++ b/Documentation/devicetree/bindings/media/qcom,msm8916-venus.yaml
> @@ -80,6 +80,11 @@ properties:
>      required:
>        - iommus
>  
> +  firmware-name:
> +    maxItems: 1

Not an array.

Is there a specific pattern and/or default name you can specify?

> +    description: |
> +      Relative firmware image path for venus.
> +
>  required:
>    - compatible
>    - reg
> diff --git a/Documentation/devicetree/bindings/media/qcom,msm8996-venus.yaml b/Documentation/devicetree/bindings/media/qcom,msm8996-venus.yaml
> index 199f45217b4a..b8809325138f 100644
> --- a/Documentation/devicetree/bindings/media/qcom,msm8996-venus.yaml
> +++ b/Documentation/devicetree/bindings/media/qcom,msm8996-venus.yaml
> @@ -107,6 +107,11 @@ properties:
>      required:
>        - iommus
>  
> +  firmware-name:
> +    maxItems: 1
> +    description: |
> +      Relative firmware image path for venus.
> +
>  required:
>    - compatible
>    - reg
> diff --git a/Documentation/devicetree/bindings/media/qcom,sc7180-venus.yaml b/Documentation/devicetree/bindings/media/qcom,sc7180-venus.yaml
> index 04013e5dd044..ffd3e2850366 100644
> --- a/Documentation/devicetree/bindings/media/qcom,sc7180-venus.yaml
> +++ b/Documentation/devicetree/bindings/media/qcom,sc7180-venus.yaml
> @@ -99,6 +99,11 @@ properties:
>      required:
>        - iommus
>  
> +  firmware-name:
> +    maxItems: 1
> +    description: |
> +      Relative firmware image path for venus.
> +
>  required:
>    - compatible
>    - reg
> diff --git a/Documentation/devicetree/bindings/media/qcom,sdm845-venus-v2.yaml b/Documentation/devicetree/bindings/media/qcom,sdm845-venus-v2.yaml
> index 04b9af4db191..cd7a5e1374ce 100644
> --- a/Documentation/devicetree/bindings/media/qcom,sdm845-venus-v2.yaml
> +++ b/Documentation/devicetree/bindings/media/qcom,sdm845-venus-v2.yaml
> @@ -94,6 +94,11 @@ properties:
>      required:
>        - iommus
>  
> +  firmware-name:
> +    maxItems: 1
> +    description: |
> +      Relative firmware image path for venus.
> +
>  required:
>    - compatible
>    - reg
> diff --git a/Documentation/devicetree/bindings/media/qcom,sdm845-venus.yaml b/Documentation/devicetree/bindings/media/qcom,sdm845-venus.yaml
> index 680f37726fdf..ae256238a637 100644
> --- a/Documentation/devicetree/bindings/media/qcom,sdm845-venus.yaml
> +++ b/Documentation/devicetree/bindings/media/qcom,sdm845-venus.yaml
> @@ -108,6 +108,11 @@ properties:
>      required:
>        - iommus
>  
> +  firmware-name:
> +    maxItems: 1
> +    description: |
> +      Relative firmware image path for venus.
> +
>  required:
>    - compatible
>    - reg
> -- 
> 2.32.0
> 
> 
> 

(no subject)

[Daniel Palmer]

From 1a75d7c1077cf785b479cb975e42e09fff2839cd Mon Sep 17 00:00:00 2001
From: Daniel Palmer <daniel@thingy.jp>
Date: Fri, 18 Apr 2025 18:28:26 +0900
Subject: [PATCH] of/address: Drop ISA parts when !CONFIG_ISA

The PCI parts are already wrapped in #ifdef CONFIG_PCI
so it seems sensible to add #ifdef CONFIG_ISA around the ISA
parts.

This reduces the code/data size a bit on configs with !CONFIG_ISA.

Signed-off-by: Daniel Palmer <daniel@thingy.jp>
---

I thought about making this RFC as I'm a bit unsure if machines
that need this ISA stuff actually select CONFIG_ISA or not.

The only in-kernel devicetrees that seem to use this are 4 old powerpc
ones and I couldn't work out if those boards do end up with CONFIG_ISA.

But then again it seems odd for everyone to get this code for 4 old
boards.

 drivers/of/address.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/of/address.c b/drivers/of/address.c
index cf4aab11e9b1..9b2f0d462fb5 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -277,6 +277,7 @@ int of_range_to_resource(struct device_node *np, int index, struct resource *res
 }
 EXPORT_SYMBOL(of_range_to_resource);
 
+#ifdef CONFIG_ISA
 /*
  * ISA bus specific translator
  */
@@ -316,6 +317,7 @@ static unsigned int of_bus_isa_get_flags(const __be32 *addr)
 		flags |= IORESOURCE_MEM;
 	return flags;
 }
+#endif
 
 static int of_bus_default_flags_match(struct device_node *np)
 {
@@ -349,6 +351,7 @@ static const struct of_bus of_busses[] = {
 		.get_flags = of_bus_pci_get_flags,
 	},
 #endif /* CONFIG_PCI */
+#ifdef CONFIG_ISA
 	/* ISA */
 	{
 		.name = "isa",
@@ -360,6 +363,7 @@ static const struct of_bus of_busses[] = {
 		.flag_cells = 1,
 		.get_flags = of_bus_isa_get_flags,
 	},
+#endif /* CONFIG_ISA */
 	/* Default with flags cell */
 	{
 		.name = "default-flags",
-- 
2.53.0

Re: (no subject)

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Conditionally compiling the OF 'isa' bus translator based on `CONFIG_ISA` breaks device tree address translation for non-ISA architectures (e.g., ARM64) that use 'isa' nodes for LPC or legacy I/O bridges.
--

commit 3f535ae9ca6c863a12c1d6dbcfcb4358a6f6ed4b
Author: Daniel Palmer <daniel@thingy.jp>

of/address: Drop ISA parts when !CONFIG_ISA

This patch conditionally compiles the ISA parts of the Open Firmware address
translator based on CONFIG_ISA to reduce code size.

> diff --git a/drivers/of/address.c b/drivers/of/address.c
> index cf4aab11e9b1f..9b2f0d462fb59 100644
> --- a/drivers/of/address.c
> +++ b/drivers/of/address.c
[ ... ]
> @@ -349,6 +351,7 @@ static const struct of_bus of_busses[] = {
>  		.get_flags = of_bus_pci_get_flags,
>  	},
>  #endif /* CONFIG_PCI */
> +#ifdef CONFIG_ISA
>  	/* ISA */
>  	{
>  		.name = "isa",
> @@ -360,6 +363,7 @@ static const struct of_bus of_busses[] = {
>  		.flag_cells = 1,
>  		.get_flags = of_bus_isa_get_flags,
>  	},
> +#endif /* CONFIG_ISA */

[Severity: High]
Does this break device tree address translation for non-ISA architectures (like
ARM64) that use 'isa' nodes for LPC or legacy I/O bridges?

Platforms like Hisilicon hip06/hip07 don't have CONFIG_ISA defined but still
use 'isa' nodes. If this bus entry is compiled out, they will fall back to the
'default' OF bus translator.

The 'default' bus translator's get_flags method (of_bus_default_get_flags)
unconditionally returns IORESOURCE_MEM. This causes __of_address_to_resource()
to misclassify the I/O port and call of_translate_address() instead of
of_translate_ioport().

Because Hisilicon LPC registers an indirect I/O host, of_translate_address()
then fails with OF_BAD_ADDR (-EINVAL), causing probe failures for devices like
UART and IPMI.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260626171747.202269-1-daniel@thingy.jp?part=1