[PATCH/RFC v2] gpio: rcar: Add Runtime PM handling for interrupts

[PATCH/RFC v2] gpio: rcar: Add Runtime PM handling for interrupts

[Geert Uytterhoeven]

The R-Car GPIO driver handles Runtime PM for requested GPIOs only.

When using a GPIO purely as an interrupt source, no Runtime PM handling
is done, and the GPIO module's clock may not be enabled.

To fix this:
  - Add .irq_request_resources() and .irq_release_resources() callbacks
    to handle Runtime PM when an interrupt is requested,
  - Add irq_bus_lock() and sync_unlock() callbacks to handle Runtime PM
    when e.g. disabling/enabling an interrupt, or configuring the
    interrupt type.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
This fixes ravb Ethernet on r8a7795/Salvator-X, which was "broken" by
commit d5c3d84657db57bd ("net: phy: Avoid polling PHY with
PHY_IGNORE_INTERRUPTS").

Does it also fix the HDMI interrupt on r8a7791/Koelsch?

v2:
  - Handle Runtime PM in .irq_bus_{lock,sync_unlock}() instead of
    .irq_{dis,en}able() and .irq_set_type(),
  - Drop WARN() checks, they were just for testing.
    In case of failures, please re-add

	WARN(pm_runtime_suspended(&p->pdev->dev),
				  "%s: %s is runtime-suspended\n", __func__,
				  dev_name(&p->pdev->dev));

    to gpio_rcar_read() and gpio_rcar_write().
---
 drivers/gpio/gpio-rcar.c | 42 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index cf41440aff91971e..d9ab0cd1d2059635 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -196,6 +196,44 @@ static int gpio_rcar_irq_set_wake(struct irq_data *d, unsigned int on)
 	return 0;
 }
 
+static void gpio_rcar_irq_bus_lock(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct gpio_rcar_priv *p = gpiochip_get_data(gc);
+
+	pm_runtime_get_sync(&p->pdev->dev);
+}
+
+static void gpio_rcar_irq_bus_sync_unlock(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct gpio_rcar_priv *p = gpiochip_get_data(gc);
+
+	pm_runtime_put(&p->pdev->dev);
+}
+
+
+static int gpio_rcar_irq_request_resources(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct gpio_rcar_priv *p = gpiochip_get_data(gc);
+	int error;
+
+	error = pm_runtime_get_sync(&p->pdev->dev);
+	if (error < 0)
+		return error;
+
+	return 0;
+}
+
+static void gpio_rcar_irq_release_resources(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct gpio_rcar_priv *p = gpiochip_get_data(gc);
+
+	pm_runtime_put(&p->pdev->dev);
+}
+
 static irqreturn_t gpio_rcar_irq_handler(int irq, void *dev_id)
 {
 	struct gpio_rcar_priv *p = dev_id;
@@ -450,6 +488,10 @@ static int gpio_rcar_probe(struct platform_device *pdev)
 	irq_chip->irq_unmask = gpio_rcar_irq_enable;
 	irq_chip->irq_set_type = gpio_rcar_irq_set_type;
 	irq_chip->irq_set_wake = gpio_rcar_irq_set_wake;
+	irq_chip->irq_bus_lock = gpio_rcar_irq_bus_lock;
+	irq_chip->irq_bus_sync_unlock = gpio_rcar_irq_bus_sync_unlock;
+	irq_chip->irq_request_resources = gpio_rcar_irq_request_resources;
+	irq_chip->irq_release_resources = gpio_rcar_irq_release_resources;
 	irq_chip->flags	= IRQCHIP_SET_TYPE_MASKED | IRQCHIP_MASK_ON_SUSPEND;
 
 	ret = gpiochip_add_data(gpio_chip, p);
-- 
1.9.1

Re: [PATCH/RFC v2] gpio: rcar: Add Runtime PM handling for interrupts

[Linus Walleij]

Top-quoting so everyone on the new To:-line gets the context.

I definately need an indication from an irqchip maintainer like tglx or Marc Z
before I merge this. Also, as in reply to the previous letter, coordinate
efforts with Jon Hunters similar problem space.

Yours,
Linus Walleij

On Thu, Feb 18, 2016 at 5:06 PM, Geert Uytterhoeven
<geert+renesas@glider.be> wrote:

> The R-Car GPIO driver handles Runtime PM for requested GPIOs only.
>
> When using a GPIO purely as an interrupt source, no Runtime PM handling
> is done, and the GPIO module's clock may not be enabled.
>
> To fix this:
>   - Add .irq_request_resources() and .irq_release_resources() callbacks
>     to handle Runtime PM when an interrupt is requested,
>   - Add irq_bus_lock() and sync_unlock() callbacks to handle Runtime PM
>     when e.g. disabling/enabling an interrupt, or configuring the
>     interrupt type.
>
> Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
> ---
> This fixes ravb Ethernet on r8a7795/Salvator-X, which was "broken" by
> commit d5c3d84657db57bd ("net: phy: Avoid polling PHY with
> PHY_IGNORE_INTERRUPTS").
>
> Does it also fix the HDMI interrupt on r8a7791/Koelsch?
>
> v2:
>   - Handle Runtime PM in .irq_bus_{lock,sync_unlock}() instead of
>     .irq_{dis,en}able() and .irq_set_type(),
>   - Drop WARN() checks, they were just for testing.
>     In case of failures, please re-add
>
>         WARN(pm_runtime_suspended(&p->pdev->dev),
>                                   "%s: %s is runtime-suspended\n", __func__,
>                                   dev_name(&p->pdev->dev));
>
>     to gpio_rcar_read() and gpio_rcar_write().
> ---
>  drivers/gpio/gpio-rcar.c | 42 ++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 42 insertions(+)
>
> diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
> index cf41440aff91971e..d9ab0cd1d2059635 100644
> --- a/drivers/gpio/gpio-rcar.c
> +++ b/drivers/gpio/gpio-rcar.c
> @@ -196,6 +196,44 @@ static int gpio_rcar_irq_set_wake(struct irq_data *d, unsigned int on)
>         return 0;
>  }
>
> +static void gpio_rcar_irq_bus_lock(struct irq_data *d)
> +{
> +       struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
> +       struct gpio_rcar_priv *p = gpiochip_get_data(gc);
> +
> +       pm_runtime_get_sync(&p->pdev->dev);
> +}
> +
> +static void gpio_rcar_irq_bus_sync_unlock(struct irq_data *d)
> +{
> +       struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
> +       struct gpio_rcar_priv *p = gpiochip_get_data(gc);
> +
> +       pm_runtime_put(&p->pdev->dev);
> +}
> +
> +
> +static int gpio_rcar_irq_request_resources(struct irq_data *d)
> +{
> +       struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
> +       struct gpio_rcar_priv *p = gpiochip_get_data(gc);
> +       int error;
> +
> +       error = pm_runtime_get_sync(&p->pdev->dev);
> +       if (error < 0)
> +               return error;
> +
> +       return 0;
> +}
> +
> +static void gpio_rcar_irq_release_resources(struct irq_data *d)
> +{
> +       struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
> +       struct gpio_rcar_priv *p = gpiochip_get_data(gc);
> +
> +       pm_runtime_put(&p->pdev->dev);
> +}
> +
>  static irqreturn_t gpio_rcar_irq_handler(int irq, void *dev_id)
>  {
>         struct gpio_rcar_priv *p = dev_id;
> @@ -450,6 +488,10 @@ static int gpio_rcar_probe(struct platform_device *pdev)
>         irq_chip->irq_unmask = gpio_rcar_irq_enable;
>         irq_chip->irq_set_type = gpio_rcar_irq_set_type;
>         irq_chip->irq_set_wake = gpio_rcar_irq_set_wake;
> +       irq_chip->irq_bus_lock = gpio_rcar_irq_bus_lock;
> +       irq_chip->irq_bus_sync_unlock = gpio_rcar_irq_bus_sync_unlock;
> +       irq_chip->irq_request_resources = gpio_rcar_irq_request_resources;
> +       irq_chip->irq_release_resources = gpio_rcar_irq_release_resources;
>         irq_chip->flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_MASK_ON_SUSPEND;
>
>         ret = gpiochip_add_data(gpio_chip, p);
> --
> 1.9.1
>

Re: [PATCH/RFC v2] gpio: rcar: Add Runtime PM handling for interrupts

[Marc Zyngier]

Hi Linus,

On 19/02/16 09:18, Linus Walleij wrote:
> Top-quoting so everyone on the new To:-line gets the context.
> 
> I definately need an indication from an irqchip maintainer like tglx or Marc Z
> before I merge this. Also, as in reply to the previous letter, coordinate
> efforts with Jon Hunters similar problem space.

Seems pretty straightforward to me.

Acked-by: Marc Zyngier <marc.zyngier@arm.com>

Thanks,

	M.
-- 
Jazz is not dead. It just smells funny...

Re: [PATCH/RFC v2] gpio: rcar: Add Runtime PM handling for interrupts

[Linus Walleij]

On Thu, Feb 18, 2016 at 5:06 PM, Geert Uytterhoeven
<geert+renesas@glider.be> wrote:

> The R-Car GPIO driver handles Runtime PM for requested GPIOs only.
>
> When using a GPIO purely as an interrupt source, no Runtime PM handling
> is done, and the GPIO module's clock may not be enabled.
>
> To fix this:
>   - Add .irq_request_resources() and .irq_release_resources() callbacks
>     to handle Runtime PM when an interrupt is requested,
>   - Add irq_bus_lock() and sync_unlock() callbacks to handle Runtime PM
>     when e.g. disabling/enabling an interrupt, or configuring the
>     interrupt type.
>
> Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>

Patch applied with Marc's ACK.

Yours,
Linus Walleij

Re: [PATCH/RFC v2] gpio: rcar: Add Runtime PM handling for interrupts

[Geert Uytterhoeven]

Hi Linus,

On Thu, Feb 25, 2016 at 10:07 AM, Linus Walleij
<linus.walleij@linaro.org> wrote:
> On Thu, Feb 18, 2016 at 5:06 PM, Geert Uytterhoeven
> <geert+renesas@glider.be> wrote:
>
>> The R-Car GPIO driver handles Runtime PM for requested GPIOs only.
>>
>> When using a GPIO purely as an interrupt source, no Runtime PM handling
>> is done, and the GPIO module's clock may not be enabled.
>>
>> To fix this:
>>   - Add .irq_request_resources() and .irq_release_resources() callbacks
>>     to handle Runtime PM when an interrupt is requested,
>>   - Add irq_bus_lock() and sync_unlock() callbacks to handle Runtime PM
>>     when e.g. disabling/enabling an interrupt, or configuring the
>>     interrupt type.
>>
>> Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
>
> Patch applied with Marc's ACK.

Thanks!

Can we have it in v4.5? Else Ethernet won't work on r8a7795/salvator-x.

Gr{oetje,eeting}s,

                        Geert

--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org

In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
                                -- Linus Torvalds

Re: [PATCH/RFC v2] gpio: rcar: Add Runtime PM handling for interrupts

[Linus Walleij]

On Thu, Feb 25, 2016 at 10:37 AM, Geert Uytterhoeven
<geert@linux-m68k.org> wrote:
> On Thu, Feb 25, 2016 at 10:07 AM, Linus Walleij
> <linus.walleij@linaro.org> wrote:
>> On Thu, Feb 18, 2016 at 5:06 PM, Geert Uytterhoeven
>> <geert+renesas@glider.be> wrote:
>>
>>> The R-Car GPIO driver handles Runtime PM for requested GPIOs only.
>>>
>>> When using a GPIO purely as an interrupt source, no Runtime PM handling
>>> is done, and the GPIO module's clock may not be enabled.
>>>
>>> To fix this:
>>>   - Add .irq_request_resources() and .irq_release_resources() callbacks
>>>     to handle Runtime PM when an interrupt is requested,
>>>   - Add irq_bus_lock() and sync_unlock() callbacks to handle Runtime PM
>>>     when e.g. disabling/enabling an interrupt, or configuring the
>>>     interrupt type.
>>>
>>> Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
>>
>> Patch applied with Marc's ACK.
>
> Thanks!
>
> Can we have it in v4.5? Else Ethernet won't work on r8a7795/salvator-x.

Argh that is late. But I'll move it over to the fixes branch...

Yours,
Linus Walleij

Re: [PATCH/RFC v2] gpio: rcar: Add Runtime PM handling for interrupts

[Geert Uytterhoeven]

Hi Linus,

On Thu, Feb 25, 2016 at 3:19 PM, Linus Walleij <linus.walleij@linaro.org> wrote:
> On Thu, Feb 25, 2016 at 10:37 AM, Geert Uytterhoeven
> <geert@linux-m68k.org> wrote:
>> On Thu, Feb 25, 2016 at 10:07 AM, Linus Walleij
>> <linus.walleij@linaro.org> wrote:
>>> On Thu, Feb 18, 2016 at 5:06 PM, Geert Uytterhoeven
>>> <geert+renesas@glider.be> wrote:
>>>
>>>> The R-Car GPIO driver handles Runtime PM for requested GPIOs only.
>>>>
>>>> When using a GPIO purely as an interrupt source, no Runtime PM handling
>>>> is done, and the GPIO module's clock may not be enabled.
>>>>
>>>> To fix this:
>>>>   - Add .irq_request_resources() and .irq_release_resources() callbacks
>>>>     to handle Runtime PM when an interrupt is requested,
>>>>   - Add irq_bus_lock() and sync_unlock() callbacks to handle Runtime PM
>>>>     when e.g. disabling/enabling an interrupt, or configuring the
>>>>     interrupt type.
>>>>
>>>> Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
>>>
>>> Patch applied with Marc's ACK.
>>
>> Thanks!
>>
>> Can we have it in v4.5? Else Ethernet won't work on r8a7795/salvator-x.
>
> Argh that is late. But I'll move it over to the fixes branch...

Thanks!

The issue was exposed by commit d5c3d84657db57bd ("net: phy: Avoid polling
PHY with PHY_IGNORE_INTERRUPTS"), which went upstream only in v4.5-rc3.

Gr{oetje,eeting}s,

                        Geert

--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org

In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
                                -- Linus Torvalds

[PATCH v3 0/6] R8A7795/Salvator-X PWM support

[Ulrich Hecht]

Hi!

This revision adds the missing pwm0 node as well as Geert's endorsements.

CU
Uli

Changes since v2:
- add pwm0
- add Acked-By/Reviewed-By's

Changes since v1:
- drops the PFC driver bits that have been queued in sh-pfc-for-v4.6
- replaces ARCH_RCAR_GEN{1,2} with ARCH_RENESAS
- splits the DT patch in three
- enables only one pin group for each device
- describes what the PWM devices are used for
- adds the missing power domain entries
- adds module clock 523 to the MSSR driver


Harunobu Kurokawa (1):
  arm64: defconfig : add PWM driver support

Ryo Kodama (1):
  pwm: rcar: Use ARCH_RENESAS

Ulrich Hecht (4):
  arm64: dts: r8a7795: Add PWM device nodes
  arm64: dts: salvator-x: enable PWM
  pwm: add R-Car H3 device tree bindings
  clk: shmobile: r8a7795: add PWM clock

 .../devicetree/bindings/pwm/renesas,pwm-rcar.txt   |  1 +
 arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts | 23 ++++++++
 arch/arm64/boot/dts/renesas/r8a7795.dtsi           | 63 ++++++++++++++++++++++
 arch/arm64/configs/defconfig                       |  2 +
 drivers/clk/renesas/r8a7795-cpg-mssr.c             |  1 +
 drivers/pwm/Kconfig                                |  2 +-
 6 files changed, 91 insertions(+), 1 deletion(-)

-- 
2.7.4

[PATCH v3 1/6] pwm: rcar: Use ARCH_RENESAS

[Ulrich Hecht]

From: Ryo Kodama <ryo.kodama.vz@renesas.com>

Replace ARCH_RCAR_GEN{1,2} with ARCH_RENESAS in order to support R-Car Gen3.

Signed-off-by: Ryo Kodama <ryo.kodama.vz@renesas.com>
Signed-off-by: Harunobu Kurokawa <harunobu.kurokawa.dn@renesas.com>
Signed-off-by: Ulrich Hecht <ulrich.hecht+renesas@gmail.com>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/pwm/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pwm/Kconfig b/drivers/pwm/Kconfig
index c182efc..3a2e232 100644
--- a/drivers/pwm/Kconfig
+++ b/drivers/pwm/Kconfig
@@ -305,7 +305,7 @@ config PWM_PXA
 
 config PWM_RCAR
 	tristate "Renesas R-Car PWM support"
-	depends on ARCH_RCAR_GEN1 || ARCH_RCAR_GEN2 || COMPILE_TEST
+	depends on ARCH_RENESAS || COMPILE_TEST
 	depends on HAS_IOMEM
 	help
 	  This driver exposes the PWM Timer controller found in Renesas
-- 
2.7.4

[v3,2/6] arm64: defconfig : add PWM driver support

[Ulrich Hecht]

From: Harunobu Kurokawa <harunobu.kurokawa.dn@renesas.com>

Signed-off-by: Harunobu Kurokawa <harunobu.kurokawa.dn@renesas.com>
Signed-off-by: Ulrich Hecht <ulrich.hecht+renesas@gmail.com>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>

---
arch/arm64/configs/defconfig | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index f705051..5067137 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -252,6 +252,8 @@ CONFIG_ARCH_TEGRA_210_SOC=y
 CONFIG_HISILICON_IRQ_MBIGEN=y
 CONFIG_EXTCON_USB_GPIO=y
 CONFIG_PHY_RCAR_GEN3_USB2=y
+CONFIG_PWM=y
+CONFIG_PWM_RCAR=y
 CONFIG_PHY_XGENE=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y

[PATCH v3 2/6] arm64: defconfig : add PWM driver support

[Ulrich Hecht]

From: Harunobu Kurokawa <harunobu.kurokawa.dn@renesas.com>

Signed-off-by: Harunobu Kurokawa <harunobu.kurokawa.dn@renesas.com>
Signed-off-by: Ulrich Hecht <ulrich.hecht+renesas@gmail.com>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 arch/arm64/configs/defconfig | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index f705051..5067137 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -252,6 +252,8 @@ CONFIG_ARCH_TEGRA_210_SOC=y
 CONFIG_HISILICON_IRQ_MBIGEN=y
 CONFIG_EXTCON_USB_GPIO=y
 CONFIG_PHY_RCAR_GEN3_USB2=y
+CONFIG_PWM=y
+CONFIG_PWM_RCAR=y
 CONFIG_PHY_XGENE=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
-- 
2.7.4

[PATCH v3 3/6] arm64: dts: r8a7795: Add PWM device nodes

[Ulrich Hecht]

Signed-off-by: Ryo Kodama <ryo.kodama.vz@renesas.com>
Signed-off-by: Harunobu Kurokawa <harunobu.kurokawa.dn@renesas.com>
[uli: adapted to new MSTP clock scheme]
Signed-off-by: Ulrich Hecht <ulrich.hecht+renesas@gmail.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 arch/arm64/boot/dts/renesas/r8a7795.dtsi | 63 ++++++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)

diff --git a/arch/arm64/boot/dts/renesas/r8a7795.dtsi b/arch/arm64/boot/dts/renesas/r8a7795.dtsi
index 384cf84..fd56859 100644
--- a/arch/arm64/boot/dts/renesas/r8a7795.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a7795.dtsi
@@ -655,6 +655,69 @@
 			status = "disabled";
 		};
 
+		pwm0: pwm@e6e30000 {
+			compatible = "renesas,pwm-r8a7795", "renesas,pwm-rcar";
+			reg = <0 0xe6e30000 0 0x10>;
+			#pwm-cells = <2>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&cpg>;
+			status = "disabled";
+		};
+
+		pwm1: pwm@e6e31000 {
+			compatible = "renesas,pwm-r8a7795", "renesas,pwm-rcar";
+			reg = <0 0xe6e31000 0 0x10>;
+			#pwm-cells = <2>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&cpg>;
+			status = "disabled";
+		};
+
+		pwm2: pwm@e6e32000 {
+			compatible = "renesas,pwm-r8a7795", "renesas,pwm-rcar";
+			reg = <0 0xe6e32000 0 0x10>;
+			#pwm-cells = <2>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&cpg>;
+			status = "disabled";
+		};
+
+		pwm3: pwm@e6e33000 {
+			compatible = "renesas,pwm-r8a7795", "renesas,pwm-rcar";
+			reg = <0 0xe6e33000 0 0x10>;
+			#pwm-cells = <2>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&cpg>;
+			status = "disabled";
+		};
+
+		pwm4: pwm@e6e34000 {
+			compatible = "renesas,pwm-r8a7795", "renesas,pwm-rcar";
+			reg = <0 0xe6e34000 0 0x10>;
+			#pwm-cells = <2>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&cpg>;
+			status = "disabled";
+		};
+
+		pwm5: pwm@e6e35000 {
+			compatible = "renesas,pwm-r8a7795", "renesas,pwm-rcar";
+			reg = <0 0xe6e35000 0 0x10>;
+			#pwm-cells = <2>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&cpg>;
+			status = "disabled";
+		};
+
+		pwm6: pwm@e6e36000 {
+			compatible = "renesas,pwm-r8a7795", "renesas,pwm-rcar";
+			reg = <0 0xe6e36000 0 0x10>;
+			#pwm-cells = <2>;
+			clocks = <&cpg CPG_MOD 523>;
+			power-domains = <&cpg>;
+			status = "disabled";
+		};
+
 		scif0: serial@e6e60000 {
 			compatible = "renesas,scif-r8a7795",
 				     "renesas,rcar-gen3-scif", "renesas,scif";
-- 
2.7.4

[PATCH v3 4/6] arm64: dts: salvator-x: enable PWM

[Ulrich Hecht]

Enables PWM1 (brightness control) and PWM2 (PMIC switching frequency
synchronization).

Signed-off-by: Ulrich Hecht <ulrich.hecht+renesas@gmail.com>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts | 23 ++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts b/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts
index 507d6a4..5525637 100644
--- a/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts
+++ b/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts
@@ -189,6 +189,15 @@
 	pinctrl-0 = <&scif_clk_pins>;
 	pinctrl-names = "default";
 
+	pwm1_pins: pwm1 {
+		renesas,groups = "pwm1_a";
+		renesas,function = "pwm1";
+	};
+	pwm2_pins: pwm2 {
+		renesas,groups = "pwm2_a";
+		renesas,function = "pwm2";
+	};
+
 	scif1_pins: scif1 {
 		renesas,groups = "scif1_data_a", "scif1_ctrl";
 		renesas,function = "scif1";
@@ -299,6 +308,20 @@
 	};
 };
 
+&pwm1 {
+	/* brightness control */
+	pinctrl-0 = <&pwm1_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&pwm2 {
+	/* PMIC DC/DC switching frequency synchronization */
+	pinctrl-0 = <&pwm2_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
 &rcar_sound {
 	pinctrl-0 = <&sound_pins &sound_clk_pins>;
 	pinctrl-names = "default";
-- 
2.7.4

[PATCH v3 5/6] pwm: add R-Car H3 device tree bindings

[Ulrich Hecht]

Signed-off-by: Ulrich Hecht <ulrich.hecht+renesas@gmail.com>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt b/Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt
index 0822a08..d6de643 100644
--- a/Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt
+++ b/Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt
@@ -7,6 +7,7 @@ Required Properties:
  - "renesas,pwm-r8a7790": for R-Car H2
  - "renesas,pwm-r8a7791": for R-Car M2-W
  - "renesas,pwm-r8a7794": for R-Car E2
+ - "renesas,pwm-r8a7795": for R-Car H3
 - reg: base address and length of the registers block for the PWM.
 - #pwm-cells: should be 2. See pwm.txt in this directory for a description of
   the cells format.
-- 
2.7.4

[v3,6/6] clk: shmobile: r8a7795: add PWM clock

[Ulrich Hecht]

Signed-off-by: Ulrich Hecht <ulrich.hecht+renesas@gmail.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>

---
drivers/clk/renesas/r8a7795-cpg-mssr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/clk/renesas/r8a7795-cpg-mssr.c b/drivers/clk/renesas/r8a7795-cpg-mssr.c
index b2198aef..9de458a 100644
--- a/drivers/clk/renesas/r8a7795-cpg-mssr.c
+++ b/drivers/clk/renesas/r8a7795-cpg-mssr.c
@@ -148,6 +148,7 @@ static const struct mssr_mod_clk r8a7795_mod_clks[] __initconst = {
 	DEF_MOD("hscif2",		 518,	R8A7795_CLK_S3D1),
 	DEF_MOD("hscif1",		 519,	R8A7795_CLK_S3D1),
 	DEF_MOD("hscif0",		 520,	R8A7795_CLK_S3D1),
+	DEF_MOD("pwm",			 523,	R8A7795_CLK_S3D4),
 	DEF_MOD("fcpvd3",		 600,	R8A7795_CLK_S2D1),
 	DEF_MOD("fcpvd2",		 601,	R8A7795_CLK_S2D1),
 	DEF_MOD("fcpvd1",		 602,	R8A7795_CLK_S2D1),

[PATCH v3 6/6] clk: shmobile: r8a7795: add PWM clock

[Ulrich Hecht]

Signed-off-by: Ulrich Hecht <ulrich.hecht+renesas@gmail.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/clk/renesas/r8a7795-cpg-mssr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/clk/renesas/r8a7795-cpg-mssr.c b/drivers/clk/renesas/r8a7795-cpg-mssr.c
index b2198aef..9de458a 100644
--- a/drivers/clk/renesas/r8a7795-cpg-mssr.c
+++ b/drivers/clk/renesas/r8a7795-cpg-mssr.c
@@ -148,6 +148,7 @@ static const struct mssr_mod_clk r8a7795_mod_clks[] __initconst = {
 	DEF_MOD("hscif2",		 518,	R8A7795_CLK_S3D1),
 	DEF_MOD("hscif1",		 519,	R8A7795_CLK_S3D1),
 	DEF_MOD("hscif0",		 520,	R8A7795_CLK_S3D1),
+	DEF_MOD("pwm",			 523,	R8A7795_CLK_S3D4),
 	DEF_MOD("fcpvd3",		 600,	R8A7795_CLK_S2D1),
 	DEF_MOD("fcpvd2",		 601,	R8A7795_CLK_S2D1),
 	DEF_MOD("fcpvd1",		 602,	R8A7795_CLK_S2D1),
-- 
2.7.4

Re: [v3,1/6] pwm: rcar: Use ARCH_RENESAS

[Simon Horman]

On Thu, Mar 31, 2016 at 01:39:11PM +0200, Ulrich Hecht wrote:
> From: Ryo Kodama <ryo.kodama.vz@renesas.com>
> 
> Replace ARCH_RCAR_GEN{1,2} with ARCH_RENESAS in order to support R-Car Gen3.
> 
> Signed-off-by: Ryo Kodama <ryo.kodama.vz@renesas.com>
> Signed-off-by: Harunobu Kurokawa <harunobu.kurokawa.dn@renesas.com>
> Signed-off-by: Ulrich Hecht <ulrich.hecht+renesas@gmail.com>
> Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>

Acked-by: Simon Horman <horms+renesas@verge.net.au>

> ---
> drivers/pwm/Kconfig | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/pwm/Kconfig b/drivers/pwm/Kconfig
> index c182efc..3a2e232 100644
> --- a/drivers/pwm/Kconfig
> +++ b/drivers/pwm/Kconfig
> @@ -305,7 +305,7 @@ config PWM_PXA
>  
>  config PWM_RCAR
>  	tristate "Renesas R-Car PWM support"
> -	depends on ARCH_RCAR_GEN1 || ARCH_RCAR_GEN2 || COMPILE_TEST
> +	depends on ARCH_RENESAS || COMPILE_TEST
>  	depends on HAS_IOMEM
>  	help
>  	  This driver exposes the PWM Timer controller found in Renesas

Re: [v3,5/6] pwm: add R-Car H3 device tree bindings

[Simon Horman]

On Thu, Mar 31, 2016 at 01:39:15PM +0200, Ulrich Hecht wrote:
> Signed-off-by: Ulrich Hecht <ulrich.hecht+renesas@gmail.com>
> Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>

Acked-by: Simon Horman <horms+renesas@verge.net.au>

> ---
> Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt | 1 +
>  1 file changed, 1 insertion(+)
> 
> diff --git a/Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt b/Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt
> index 0822a08..d6de643 100644
> --- a/Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt
> +++ b/Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt
> @@ -7,6 +7,7 @@ Required Properties:
>   - "renesas,pwm-r8a7790": for R-Car H2
>   - "renesas,pwm-r8a7791": for R-Car M2-W
>   - "renesas,pwm-r8a7794": for R-Car E2
> + - "renesas,pwm-r8a7795": for R-Car H3
>  - reg: base address and length of the registers block for the PWM.
>  - #pwm-cells: should be 2. See pwm.txt in this directory for a description of
>    the cells format.

[PATCH v5 net-next 00/15] MTU/buffer reconfig changes

[Jakub Kicinski]

Hi!

I re-discussed MPLS/MTU internally, dropped it from the patch 1,
re-tested everything, found out I forgot about debugfs pointers,
fixed that as well.

v5:
 - don't reserve space in RX buffers for MPLS label stack
   (patch 1);
 - fix debugfs pointers to ring structures (patch 5).
v4:
 - cut down on unrelated patches;
 - don't "close" the device on error path.

--- v4 cover letter

Previous series included some not entirely related patches,
this one is cut down.  Main issue I'm trying to solve here
is that .ndo_change_mtu() in nfpvf driver is doing full
close/open to reallocate buffers - which if open fails
can result in device being basically closed even though
the interface is started.  As suggested by you I try to move
towards a paradigm where the resources are allocated first
and the MTU change is only done once I'm certain (almost)
nothing can fail.  Almost because I need to communicate 
with FW and that can always time out.

Patch 1 fixes small issue.  Next 10 patches reorganize things
so that I can easily allocate new rings and sets of buffers
while the device is running.  Patches 13 and 15 reshape the
.ndo_change_mtu() and ethtool's ring-resize operation into
desired form.


Jakub Kicinski (15):
  nfp: correct RX buffer length calculation
  nfp: move link state interrupt request/free calls
  nfp: break up nfp_net_{alloc|free}_rings
  nfp: make *x_ring_init do all the init
  nfp: allocate ring SW structs dynamically
  nfp: cleanup tx ring flush and rename to reset
  nfp: reorganize initial filling of RX rings
  nfp: preallocate RX buffers early in .ndo_open
  nfp: move filling ring information to FW config
  nfp: slice .ndo_open() and .ndo_stop() up
  nfp: sync ring state during FW reconfiguration
  nfp: propagate list buffer size in struct rx_ring
  nfp: convert .ndo_change_mtu() to prepare/commit paradigm
  nfp: pass ring count as function parameter
  nfp: allow ring size reconfiguration at runtime

 drivers/net/ethernet/netronome/nfp/nfp_net.h       |  10 +-
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 903 ++++++++++++++-------
 .../net/ethernet/netronome/nfp/nfp_net_debugfs.c   |  20 +-
 .../net/ethernet/netronome/nfp/nfp_net_ethtool.c   |  30 +-
 4 files changed, 627 insertions(+), 336 deletions(-)

-- 
1.9.1

[PATCH v5 net-next 01/15] nfp: correct RX buffer length calculation

[Jakub Kicinski]

When calculating the RX buffer length we need to account
for up to 2 VLAN tags.  Rounding up to 1k is an relic of
a distant past and can be removed.  While at it also remove
trivial print statement.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 43c618bafdb6..0dae81454e77 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1911,9 +1911,6 @@ static void nfp_net_set_rx_mode(struct net_device *netdev)
 static int nfp_net_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
-	u32 tmp;
-
-	nn_dbg(nn, "New MTU = %d\n", new_mtu);
 
 	if (new_mtu < 68 || new_mtu > nn->max_mtu) {
 		nn_err(nn, "New MTU (%d) is not valid\n", new_mtu);
@@ -1921,10 +1918,7 @@ static int nfp_net_change_mtu(struct net_device *netdev, int new_mtu)
 	}
 
 	netdev->mtu = new_mtu;
-
-	/* Freelist buffer size rounded up to the nearest 1K */
-	tmp = new_mtu + ETH_HLEN + VLAN_HLEN + NFP_NET_MAX_PREPEND;
-	nn->fl_bufsz = roundup(tmp, 1024);
+	nn->fl_bufsz = NFP_NET_MAX_PREPEND + ETH_HLEN + VLAN_HLEN * 2 + new_mtu;
 
 	/* restart if running */
 	if (netif_running(netdev)) {
-- 
1.9.1

[PATCH v5 net-next 02/15] nfp: move link state interrupt request/free calls

[Jakub Kicinski]

We need to be able to disable the link state interrupt when
the device is brought down.  We used to just free the IRQ
at the beginning of .ndo_stop().  As we now move towards
more ordered .ndo_open()/.ndo_stop() paths LSC allocation
should be placed in the "allocate resource" section.

Since the IRQ can't be freed early in .ndo_stop(), it is
disabled instead.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 23 +++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 0dae81454e77..5da1199e7afb 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1729,10 +1729,16 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 				      NFP_NET_IRQ_EXN_IDX, nn->exn_handler);
 	if (err)
 		return err;
+	err = nfp_net_aux_irq_request(nn, NFP_NET_CFG_LSC, "%s-lsc",
+				      nn->lsc_name, sizeof(nn->lsc_name),
+				      NFP_NET_IRQ_LSC_IDX, nn->lsc_handler);
+	if (err)
+		goto err_free_exn;
+	disable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector);
 
 	err = nfp_net_alloc_rings(nn);
 	if (err)
-		goto err_free_exn;
+		goto err_free_lsc;
 
 	err = netif_set_real_num_tx_queues(netdev, nn->num_tx_rings);
 	if (err)
@@ -1812,19 +1818,11 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 
 	netif_tx_wake_all_queues(netdev);
 
-	err = nfp_net_aux_irq_request(nn, NFP_NET_CFG_LSC, "%s-lsc",
-				      nn->lsc_name, sizeof(nn->lsc_name),
-				      NFP_NET_IRQ_LSC_IDX, nn->lsc_handler);
-	if (err)
-		goto err_stop_tx;
+	enable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector);
 	nfp_net_read_link_status(nn);
 
 	return 0;
 
-err_stop_tx:
-	netif_tx_disable(netdev);
-	for (r = 0; r < nn->num_r_vecs; r++)
-		nfp_net_tx_flush(nn->r_vecs[r].tx_ring);
 err_disable_napi:
 	while (r--) {
 		napi_disable(&nn->r_vecs[r].napi);
@@ -1834,6 +1832,8 @@ err_clear_config:
 	nfp_net_clear_config_and_disable(nn);
 err_free_rings:
 	nfp_net_free_rings(nn);
+err_free_lsc:
+	nfp_net_aux_irq_free(nn, NFP_NET_CFG_LSC, NFP_NET_IRQ_LSC_IDX);
 err_free_exn:
 	nfp_net_aux_irq_free(nn, NFP_NET_CFG_EXN, NFP_NET_IRQ_EXN_IDX);
 	return err;
@@ -1855,7 +1855,7 @@ static int nfp_net_netdev_close(struct net_device *netdev)
 
 	/* Step 1: Disable RX and TX rings from the Linux kernel perspective
 	 */
-	nfp_net_aux_irq_free(nn, NFP_NET_CFG_LSC, NFP_NET_IRQ_LSC_IDX);
+	disable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector);
 	netif_carrier_off(netdev);
 	nn->link_up = false;
 
@@ -1876,6 +1876,7 @@ static int nfp_net_netdev_close(struct net_device *netdev)
 	}
 
 	nfp_net_free_rings(nn);
+	nfp_net_aux_irq_free(nn, NFP_NET_CFG_LSC, NFP_NET_IRQ_LSC_IDX);
 	nfp_net_aux_irq_free(nn, NFP_NET_CFG_EXN, NFP_NET_IRQ_EXN_IDX);
 
 	nn_dbg(nn, "%s down", netdev->name);
-- 
1.9.1

[PATCH v5 net-next 03/15] nfp: break up nfp_net_{alloc|free}_rings

[Jakub Kicinski]

nfp_net_{alloc|free}_rings contained strange mix of allocations
and vector initialization.  Remove it, declare vector init as
a separate function and handle allocations explicitly.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 126 ++++++++-------------
 1 file changed, 47 insertions(+), 79 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 5da1199e7afb..8692587904c5 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1488,91 +1488,40 @@ err_alloc:
 	return -ENOMEM;
 }
 
-static void __nfp_net_free_rings(struct nfp_net *nn, unsigned int n_free)
+static int
+nfp_net_prepare_vector(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
+		       int idx)
 {
-	struct nfp_net_r_vector *r_vec;
-	struct msix_entry *entry;
+	struct msix_entry *entry = &nn->irq_entries[r_vec->irq_idx];
+	int err;
 
-	while (n_free--) {
-		r_vec = &nn->r_vecs[n_free];
-		entry = &nn->irq_entries[r_vec->irq_idx];
+	snprintf(r_vec->name, sizeof(r_vec->name),
+		 "%s-rxtx-%d", nn->netdev->name, idx);
+	err = request_irq(entry->vector, r_vec->handler, 0, r_vec->name, r_vec);
+	if (err) {
+		nn_err(nn, "Error requesting IRQ %d\n", entry->vector);
+		return err;
+	}
 
-		nfp_net_rx_ring_free(r_vec->rx_ring);
-		nfp_net_tx_ring_free(r_vec->tx_ring);
+	/* Setup NAPI */
+	netif_napi_add(nn->netdev, &r_vec->napi,
+		       nfp_net_poll, NAPI_POLL_WEIGHT);
 
-		irq_set_affinity_hint(entry->vector, NULL);
-		free_irq(entry->vector, r_vec);
+	irq_set_affinity_hint(entry->vector, &r_vec->affinity_mask);
 
-		netif_napi_del(&r_vec->napi);
-	}
-}
+	nn_dbg(nn, "RV%02d: irq=%03d/%03d\n", idx, entry->vector, entry->entry);
 
-/**
- * nfp_net_free_rings() - Free all ring resources
- * @nn:      NFP Net device to reconfigure
- */
-static void nfp_net_free_rings(struct nfp_net *nn)
-{
-	__nfp_net_free_rings(nn, nn->num_r_vecs);
+	return 0;
 }
 
-/**
- * nfp_net_alloc_rings() - Allocate resources for RX and TX rings
- * @nn:      NFP Net device to reconfigure
- *
- * Return: 0 on success or negative errno on error.
- */
-static int nfp_net_alloc_rings(struct nfp_net *nn)
+static void
+nfp_net_cleanup_vector(struct nfp_net *nn, struct nfp_net_r_vector *r_vec)
 {
-	struct nfp_net_r_vector *r_vec;
-	struct msix_entry *entry;
-	int err;
-	int r;
+	struct msix_entry *entry = &nn->irq_entries[r_vec->irq_idx];
 
-	for (r = 0; r < nn->num_r_vecs; r++) {
-		r_vec = &nn->r_vecs[r];
-		entry = &nn->irq_entries[r_vec->irq_idx];
-
-		/* Setup NAPI */
-		netif_napi_add(nn->netdev, &r_vec->napi,
-			       nfp_net_poll, NAPI_POLL_WEIGHT);
-
-		snprintf(r_vec->name, sizeof(r_vec->name),
-			 "%s-rxtx-%d", nn->netdev->name, r);
-		err = request_irq(entry->vector, r_vec->handler, 0,
-				  r_vec->name, r_vec);
-		if (err) {
-			nn_dbg(nn, "Error requesting IRQ %d\n", entry->vector);
-			goto err_napi_del;
-		}
-
-		irq_set_affinity_hint(entry->vector, &r_vec->affinity_mask);
-
-		nn_dbg(nn, "RV%02d: irq=%03d/%03d\n",
-		       r, entry->vector, entry->entry);
-
-		/* Allocate TX ring resources */
-		err = nfp_net_tx_ring_alloc(r_vec->tx_ring);
-		if (err)
-			goto err_free_irq;
-
-		/* Allocate RX ring resources */
-		err = nfp_net_rx_ring_alloc(r_vec->rx_ring);
-		if (err)
-			goto err_free_tx;
-	}
-
-	return 0;
-
-err_free_tx:
-	nfp_net_tx_ring_free(r_vec->tx_ring);
-err_free_irq:
 	irq_set_affinity_hint(entry->vector, NULL);
-	free_irq(entry->vector, r_vec);
-err_napi_del:
 	netif_napi_del(&r_vec->napi);
-	__nfp_net_free_rings(nn, r);
-	return err;
+	free_irq(entry->vector, r_vec);
 }
 
 /**
@@ -1736,9 +1685,19 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 		goto err_free_exn;
 	disable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector);
 
-	err = nfp_net_alloc_rings(nn);
-	if (err)
-		goto err_free_lsc;
+	for (r = 0; r < nn->num_r_vecs; r++) {
+		err = nfp_net_prepare_vector(nn, &nn->r_vecs[r], r);
+		if (err)
+			goto err_free_prev_vecs;
+
+		err = nfp_net_tx_ring_alloc(nn->r_vecs[r].tx_ring);
+		if (err)
+			goto err_cleanup_vec_p;
+
+		err = nfp_net_rx_ring_alloc(nn->r_vecs[r].rx_ring);
+		if (err)
+			goto err_free_tx_ring_p;
+	}
 
 	err = netif_set_real_num_tx_queues(netdev, nn->num_tx_rings);
 	if (err)
@@ -1831,8 +1790,15 @@ err_disable_napi:
 err_clear_config:
 	nfp_net_clear_config_and_disable(nn);
 err_free_rings:
-	nfp_net_free_rings(nn);
-err_free_lsc:
+	r = nn->num_r_vecs;
+err_free_prev_vecs:
+	while (r--) {
+		nfp_net_rx_ring_free(nn->r_vecs[r].rx_ring);
+err_free_tx_ring_p:
+		nfp_net_tx_ring_free(nn->r_vecs[r].tx_ring);
+err_cleanup_vec_p:
+		nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
+	}
 	nfp_net_aux_irq_free(nn, NFP_NET_CFG_LSC, NFP_NET_IRQ_LSC_IDX);
 err_free_exn:
 	nfp_net_aux_irq_free(nn, NFP_NET_CFG_EXN, NFP_NET_IRQ_EXN_IDX);
@@ -1873,9 +1839,11 @@ static int nfp_net_netdev_close(struct net_device *netdev)
 	for (r = 0; r < nn->num_r_vecs; r++) {
 		nfp_net_rx_flush(nn->r_vecs[r].rx_ring);
 		nfp_net_tx_flush(nn->r_vecs[r].tx_ring);
+		nfp_net_rx_ring_free(nn->r_vecs[r].rx_ring);
+		nfp_net_tx_ring_free(nn->r_vecs[r].tx_ring);
+		nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
 	}
 
-	nfp_net_free_rings(nn);
 	nfp_net_aux_irq_free(nn, NFP_NET_CFG_LSC, NFP_NET_IRQ_LSC_IDX);
 	nfp_net_aux_irq_free(nn, NFP_NET_CFG_EXN, NFP_NET_IRQ_EXN_IDX);
 
-- 
1.9.1

[PATCH v5 net-next 04/15] nfp: make *x_ring_init do all the init

[Jakub Kicinski]

nfp_net_[rt]x_ring_init functions used to be called from probe
path only and some of their functionality was spilled to the
call site.  In order to reuse them for ring reconfiguration
we need them to do all the init.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 28 ++++++++++++++--------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 8692587904c5..7cd20fcd631a 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -347,12 +347,18 @@ static irqreturn_t nfp_net_irq_exn(int irq, void *data)
 /**
  * nfp_net_tx_ring_init() - Fill in the boilerplate for a TX ring
  * @tx_ring:  TX ring structure
+ * @r_vec:    IRQ vector servicing this ring
+ * @idx:      Ring index
  */
-static void nfp_net_tx_ring_init(struct nfp_net_tx_ring *tx_ring)
+static void
+nfp_net_tx_ring_init(struct nfp_net_tx_ring *tx_ring,
+		     struct nfp_net_r_vector *r_vec, unsigned int idx)
 {
-	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
 	struct nfp_net *nn = r_vec->nfp_net;
 
+	tx_ring->idx = idx;
+	tx_ring->r_vec = r_vec;
+
 	tx_ring->qcidx = tx_ring->idx * nn->stride_tx;
 	tx_ring->qcp_q = nn->tx_bar + NFP_QCP_QUEUE_OFF(tx_ring->qcidx);
 }
@@ -360,12 +366,18 @@ static void nfp_net_tx_ring_init(struct nfp_net_tx_ring *tx_ring)
 /**
  * nfp_net_rx_ring_init() - Fill in the boilerplate for a RX ring
  * @rx_ring:  RX ring structure
+ * @r_vec:    IRQ vector servicing this ring
+ * @idx:      Ring index
  */
-static void nfp_net_rx_ring_init(struct nfp_net_rx_ring *rx_ring)
+static void
+nfp_net_rx_ring_init(struct nfp_net_rx_ring *rx_ring,
+		     struct nfp_net_r_vector *r_vec, unsigned int idx)
 {
-	struct nfp_net_r_vector *r_vec = rx_ring->r_vec;
 	struct nfp_net *nn = r_vec->nfp_net;
 
+	rx_ring->idx = idx;
+	rx_ring->r_vec = r_vec;
+
 	rx_ring->fl_qcidx = rx_ring->idx * nn->stride_rx;
 	rx_ring->rx_qcidx = rx_ring->fl_qcidx + (nn->stride_rx - 1);
 
@@ -403,14 +415,10 @@ static void nfp_net_irqs_assign(struct net_device *netdev)
 		cpumask_set_cpu(r, &r_vec->affinity_mask);
 
 		r_vec->tx_ring = &nn->tx_rings[r];
-		nn->tx_rings[r].idx = r;
-		nn->tx_rings[r].r_vec = r_vec;
-		nfp_net_tx_ring_init(r_vec->tx_ring);
+		nfp_net_tx_ring_init(r_vec->tx_ring, r_vec, r);
 
 		r_vec->rx_ring = &nn->rx_rings[r];
-		nn->rx_rings[r].idx = r;
-		nn->rx_rings[r].r_vec = r_vec;
-		nfp_net_rx_ring_init(r_vec->rx_ring);
+		nfp_net_rx_ring_init(r_vec->rx_ring, r_vec, r);
 	}
 }
 
-- 
1.9.1

[PATCH v5 net-next 05/15] nfp: allocate ring SW structs dynamically

[Jakub Kicinski]

To be able to switch rings more easily on config changes
allocate them dynamically, separately from nfp_net structure.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/ethernet/netronome/nfp/nfp_net.h       |  6 ++---
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 28 +++++++++++++++++-----
 .../net/ethernet/netronome/nfp/nfp_net_debugfs.c   | 20 +++++++++-------
 3 files changed, 37 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index 75683fb26734..fc005c982b7d 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -472,6 +472,9 @@ struct nfp_net {
 
 	u32 rx_offset;
 
+	struct nfp_net_tx_ring *tx_rings;
+	struct nfp_net_rx_ring *rx_rings;
+
 #ifdef CONFIG_PCI_IOV
 	unsigned int num_vfs;
 	struct vf_data_storage *vfinfo;
@@ -504,9 +507,6 @@ struct nfp_net {
 	int txd_cnt;
 	int rxd_cnt;
 
-	struct nfp_net_tx_ring tx_rings[NFP_NET_MAX_TX_RINGS];
-	struct nfp_net_rx_ring rx_rings[NFP_NET_MAX_RX_RINGS];
-
 	u8 num_irqs;
 	u8 num_r_vecs;
 	struct nfp_net_r_vector r_vecs[NFP_NET_MAX_TX_RINGS];
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 7cd20fcd631a..66fab7162b7c 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -413,12 +413,6 @@ static void nfp_net_irqs_assign(struct net_device *netdev)
 		r_vec->irq_idx = NFP_NET_NON_Q_VECTORS + r;
 
 		cpumask_set_cpu(r, &r_vec->affinity_mask);
-
-		r_vec->tx_ring = &nn->tx_rings[r];
-		nfp_net_tx_ring_init(r_vec->tx_ring, r_vec, r);
-
-		r_vec->rx_ring = &nn->rx_rings[r];
-		nfp_net_rx_ring_init(r_vec->rx_ring, r_vec, r);
 	}
 }
 
@@ -1503,6 +1497,12 @@ nfp_net_prepare_vector(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 	struct msix_entry *entry = &nn->irq_entries[r_vec->irq_idx];
 	int err;
 
+	r_vec->tx_ring = &nn->tx_rings[idx];
+	nfp_net_tx_ring_init(r_vec->tx_ring, r_vec, idx);
+
+	r_vec->rx_ring = &nn->rx_rings[idx];
+	nfp_net_rx_ring_init(r_vec->rx_ring, r_vec, idx);
+
 	snprintf(r_vec->name, sizeof(r_vec->name),
 		 "%s-rxtx-%d", nn->netdev->name, idx);
 	err = request_irq(entry->vector, r_vec->handler, 0, r_vec->name, r_vec);
@@ -1693,6 +1693,15 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 		goto err_free_exn;
 	disable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector);
 
+	nn->rx_rings = kcalloc(nn->num_rx_rings, sizeof(*nn->rx_rings),
+			       GFP_KERNEL);
+	if (!nn->rx_rings)
+		goto err_free_lsc;
+	nn->tx_rings = kcalloc(nn->num_tx_rings, sizeof(*nn->tx_rings),
+			       GFP_KERNEL);
+	if (!nn->tx_rings)
+		goto err_free_rx_rings;
+
 	for (r = 0; r < nn->num_r_vecs; r++) {
 		err = nfp_net_prepare_vector(nn, &nn->r_vecs[r], r);
 		if (err)
@@ -1807,6 +1816,10 @@ err_free_tx_ring_p:
 err_cleanup_vec_p:
 		nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
 	}
+	kfree(nn->tx_rings);
+err_free_rx_rings:
+	kfree(nn->rx_rings);
+err_free_lsc:
 	nfp_net_aux_irq_free(nn, NFP_NET_CFG_LSC, NFP_NET_IRQ_LSC_IDX);
 err_free_exn:
 	nfp_net_aux_irq_free(nn, NFP_NET_CFG_EXN, NFP_NET_IRQ_EXN_IDX);
@@ -1852,6 +1865,9 @@ static int nfp_net_netdev_close(struct net_device *netdev)
 		nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
 	}
 
+	kfree(nn->rx_rings);
+	kfree(nn->tx_rings);
+
 	nfp_net_aux_irq_free(nn, NFP_NET_CFG_LSC, NFP_NET_IRQ_LSC_IDX);
 	nfp_net_aux_irq_free(nn, NFP_NET_CFG_EXN, NFP_NET_IRQ_EXN_IDX);
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
index 4c97c713121c..f86a1f13d27b 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
@@ -40,8 +40,9 @@ static struct dentry *nfp_dir;
 
 static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data)
 {
-	struct nfp_net_rx_ring *rx_ring = file->private;
 	int fl_rd_p, fl_wr_p, rx_rd_p, rx_wr_p, rxd_cnt;
+	struct nfp_net_r_vector *r_vec = file->private;
+	struct nfp_net_rx_ring *rx_ring;
 	struct nfp_net_rx_desc *rxd;
 	struct sk_buff *skb;
 	struct nfp_net *nn;
@@ -49,9 +50,10 @@ static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data)
 
 	rtnl_lock();
 
-	if (!rx_ring->r_vec || !rx_ring->r_vec->nfp_net)
+	if (!r_vec->nfp_net || !r_vec->rx_ring)
 		goto out;
-	nn = rx_ring->r_vec->nfp_net;
+	nn = r_vec->nfp_net;
+	rx_ring = r_vec->rx_ring;
 	if (!netif_running(nn->netdev))
 		goto out;
 
@@ -115,7 +117,8 @@ static const struct file_operations nfp_rx_q_fops = {
 
 static int nfp_net_debugfs_tx_q_read(struct seq_file *file, void *data)
 {
-	struct nfp_net_tx_ring *tx_ring = file->private;
+	struct nfp_net_r_vector *r_vec = file->private;
+	struct nfp_net_tx_ring *tx_ring;
 	struct nfp_net_tx_desc *txd;
 	int d_rd_p, d_wr_p, txd_cnt;
 	struct sk_buff *skb;
@@ -124,9 +127,10 @@ static int nfp_net_debugfs_tx_q_read(struct seq_file *file, void *data)
 
 	rtnl_lock();
 
-	if (!tx_ring->r_vec || !tx_ring->r_vec->nfp_net)
+	if (!r_vec->nfp_net || !r_vec->tx_ring)
 		goto out;
-	nn = tx_ring->r_vec->nfp_net;
+	nn = r_vec->nfp_net;
+	tx_ring = r_vec->tx_ring;
 	if (!netif_running(nn->netdev))
 		goto out;
 
@@ -207,13 +211,13 @@ void nfp_net_debugfs_adapter_add(struct nfp_net *nn)
 	for (i = 0; i < nn->num_rx_rings; i++) {
 		sprintf(int_name, "%d", i);
 		debugfs_create_file(int_name, S_IRUSR, rx,
-				    &nn->rx_rings[i], &nfp_rx_q_fops);
+				    &nn->r_vecs[i], &nfp_rx_q_fops);
 	}
 
 	for (i = 0; i < nn->num_tx_rings; i++) {
 		sprintf(int_name, "%d", i);
 		debugfs_create_file(int_name, S_IRUSR, tx,
-				    &nn->tx_rings[i], &nfp_tx_q_fops);
+				    &nn->r_vecs[i], &nfp_tx_q_fops);
 	}
 }
 
-- 
1.9.1

[PATCH v5 net-next 06/15] nfp: cleanup tx ring flush and rename to reset

[Jakub Kicinski]

Since we never used flush without freeing the ring later
the functionality of the two operations is mixed.
Rename flush to ring reset and move there all the things
which have to be done after FW ring state is cleared.
While at it do some clean-ups.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 81 ++++++++++------------
 1 file changed, 37 insertions(+), 44 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 66fab7162b7c..61f243760ee0 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -867,61 +867,59 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 }
 
 /**
- * nfp_net_tx_flush() - Free any untransmitted buffers currently on the TX ring
- * @tx_ring:     TX ring structure
+ * nfp_net_tx_ring_reset() - Free any untransmitted buffers and reset pointers
+ * @nn:		NFP Net device
+ * @tx_ring:	TX ring structure
  *
  * Assumes that the device is stopped
  */
-static void nfp_net_tx_flush(struct nfp_net_tx_ring *tx_ring)
+static void
+nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring)
 {
-	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
-	struct nfp_net *nn = r_vec->nfp_net;
-	struct pci_dev *pdev = nn->pdev;
 	const struct skb_frag_struct *frag;
 	struct netdev_queue *nd_q;
-	struct sk_buff *skb;
-	int nr_frags;
-	int fidx;
-	int idx;
+	struct pci_dev *pdev = nn->pdev;
 
 	while (tx_ring->rd_p != tx_ring->wr_p) {
-		idx = tx_ring->rd_p % tx_ring->cnt;
+		int nr_frags, fidx, idx;
+		struct sk_buff *skb;
 
+		idx = tx_ring->rd_p % tx_ring->cnt;
 		skb = tx_ring->txbufs[idx].skb;
-		if (skb) {
-			nr_frags = skb_shinfo(skb)->nr_frags;
-			fidx = tx_ring->txbufs[idx].fidx;
-
-			if (fidx == -1) {
-				/* unmap head */
-				dma_unmap_single(&pdev->dev,
-						 tx_ring->txbufs[idx].dma_addr,
-						 skb_headlen(skb),
-						 DMA_TO_DEVICE);
-			} else {
-				/* unmap fragment */
-				frag = &skb_shinfo(skb)->frags[fidx];
-				dma_unmap_page(&pdev->dev,
-					       tx_ring->txbufs[idx].dma_addr,
-					       skb_frag_size(frag),
-					       DMA_TO_DEVICE);
-			}
-
-			/* check for last gather fragment */
-			if (fidx == nr_frags - 1)
-				dev_kfree_skb_any(skb);
-
-			tx_ring->txbufs[idx].dma_addr = 0;
-			tx_ring->txbufs[idx].skb = NULL;
-			tx_ring->txbufs[idx].fidx = -2;
+		nr_frags = skb_shinfo(skb)->nr_frags;
+		fidx = tx_ring->txbufs[idx].fidx;
+
+		if (fidx == -1) {
+			/* unmap head */
+			dma_unmap_single(&pdev->dev,
+					 tx_ring->txbufs[idx].dma_addr,
+					 skb_headlen(skb), DMA_TO_DEVICE);
+		} else {
+			/* unmap fragment */
+			frag = &skb_shinfo(skb)->frags[fidx];
+			dma_unmap_page(&pdev->dev,
+				       tx_ring->txbufs[idx].dma_addr,
+				       skb_frag_size(frag), DMA_TO_DEVICE);
 		}
 
-		memset(&tx_ring->txds[idx], 0, sizeof(tx_ring->txds[idx]));
+		/* check for last gather fragment */
+		if (fidx == nr_frags - 1)
+			dev_kfree_skb_any(skb);
+
+		tx_ring->txbufs[idx].dma_addr = 0;
+		tx_ring->txbufs[idx].skb = NULL;
+		tx_ring->txbufs[idx].fidx = -2;
 
 		tx_ring->qcp_rd_p++;
 		tx_ring->rd_p++;
 	}
 
+	memset(tx_ring->txds, 0, sizeof(*tx_ring->txds) * tx_ring->cnt);
+	tx_ring->wr_p = 0;
+	tx_ring->rd_p = 0;
+	tx_ring->qcp_rd_p = 0;
+	tx_ring->wr_ptr_add = 0;
+
 	nd_q = netdev_get_tx_queue(nn->netdev, tx_ring->idx);
 	netdev_tx_reset_queue(nd_q);
 }
@@ -1362,11 +1360,6 @@ static void nfp_net_tx_ring_free(struct nfp_net_tx_ring *tx_ring)
 				  tx_ring->txds, tx_ring->dma);
 
 	tx_ring->cnt = 0;
-	tx_ring->wr_p = 0;
-	tx_ring->rd_p = 0;
-	tx_ring->qcp_rd_p = 0;
-	tx_ring->wr_ptr_add = 0;
-
 	tx_ring->txbufs = NULL;
 	tx_ring->txds = NULL;
 	tx_ring->dma = 0;
@@ -1859,7 +1852,7 @@ static int nfp_net_netdev_close(struct net_device *netdev)
 	 */
 	for (r = 0; r < nn->num_r_vecs; r++) {
 		nfp_net_rx_flush(nn->r_vecs[r].rx_ring);
-		nfp_net_tx_flush(nn->r_vecs[r].tx_ring);
+		nfp_net_tx_ring_reset(nn, nn->r_vecs[r].tx_ring);
 		nfp_net_rx_ring_free(nn->r_vecs[r].rx_ring);
 		nfp_net_tx_ring_free(nn->r_vecs[r].tx_ring);
 		nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
-- 
1.9.1

[PATCH v5 net-next 07/15] nfp: reorganize initial filling of RX rings

[Jakub Kicinski]

Separate allocation of buffers from giving them to FW,
thanks to this it will be possible to move allocation
earlier on .ndo_open() path and reuse buffers during
runtime reconfiguration.

Similar to TX side clean up the spill of functionality
from flush to freeing the ring.  Unlike on TX side,
RX ring reset does not free buffers from the ring.
Ring reset means only that FW pointers are zeroed and
buffers on the ring must be placed in [0, cnt - 1)
positions.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 119 ++++++++++++++-------
 1 file changed, 78 insertions(+), 41 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 61f243760ee0..0c3c37ad28a4 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1020,62 +1020,100 @@ static void nfp_net_rx_give_one(struct nfp_net_rx_ring *rx_ring,
 }
 
 /**
- * nfp_net_rx_flush() - Free any buffers currently on the RX ring
- * @rx_ring:  RX ring to remove buffers from
+ * nfp_net_rx_ring_reset() - Reflect in SW state of freelist after disable
+ * @rx_ring:	RX ring structure
  *
- * Assumes that the device is stopped
+ * Warning: Do *not* call if ring buffers were never put on the FW freelist
+ *	    (i.e. device was not enabled)!
  */
-static void nfp_net_rx_flush(struct nfp_net_rx_ring *rx_ring)
+static void nfp_net_rx_ring_reset(struct nfp_net_rx_ring *rx_ring)
 {
-	struct nfp_net *nn = rx_ring->r_vec->nfp_net;
-	struct pci_dev *pdev = nn->pdev;
-	int idx;
+	unsigned int wr_idx, last_idx;
 
-	while (rx_ring->rd_p != rx_ring->wr_p) {
-		idx = rx_ring->rd_p % rx_ring->cnt;
+	/* Move the empty entry to the end of the list */
+	wr_idx = rx_ring->wr_p % rx_ring->cnt;
+	last_idx = rx_ring->cnt - 1;
+	rx_ring->rxbufs[wr_idx].dma_addr = rx_ring->rxbufs[last_idx].dma_addr;
+	rx_ring->rxbufs[wr_idx].skb = rx_ring->rxbufs[last_idx].skb;
+	rx_ring->rxbufs[last_idx].dma_addr = 0;
+	rx_ring->rxbufs[last_idx].skb = NULL;
 
-		if (rx_ring->rxbufs[idx].skb) {
-			dma_unmap_single(&pdev->dev,
-					 rx_ring->rxbufs[idx].dma_addr,
-					 nn->fl_bufsz, DMA_FROM_DEVICE);
-			dev_kfree_skb_any(rx_ring->rxbufs[idx].skb);
-			rx_ring->rxbufs[idx].dma_addr = 0;
-			rx_ring->rxbufs[idx].skb = NULL;
-		}
+	memset(rx_ring->rxds, 0, sizeof(*rx_ring->rxds) * rx_ring->cnt);
+	rx_ring->wr_p = 0;
+	rx_ring->rd_p = 0;
+	rx_ring->wr_ptr_add = 0;
+}
 
-		memset(&rx_ring->rxds[idx], 0, sizeof(rx_ring->rxds[idx]));
+/**
+ * nfp_net_rx_ring_bufs_free() - Free any buffers currently on the RX ring
+ * @nn:		NFP Net device
+ * @rx_ring:	RX ring to remove buffers from
+ *
+ * Assumes that the device is stopped and buffers are in [0, ring->cnt - 1)
+ * entries.  After device is disabled nfp_net_rx_ring_reset() must be called
+ * to restore required ring geometry.
+ */
+static void
+nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring)
+{
+	struct pci_dev *pdev = nn->pdev;
+	unsigned int i;
 
-		rx_ring->rd_p++;
+	for (i = 0; i < rx_ring->cnt - 1; i++) {
+		/* NULL skb can only happen when initial filling of the ring
+		 * fails to allocate enough buffers and calls here to free
+		 * already allocated ones.
+		 */
+		if (!rx_ring->rxbufs[i].skb)
+			continue;
+
+		dma_unmap_single(&pdev->dev, rx_ring->rxbufs[i].dma_addr,
+				 nn->fl_bufsz, DMA_FROM_DEVICE);
+		dev_kfree_skb_any(rx_ring->rxbufs[i].skb);
+		rx_ring->rxbufs[i].dma_addr = 0;
+		rx_ring->rxbufs[i].skb = NULL;
 	}
 }
 
 /**
- * nfp_net_rx_fill_freelist() - Attempt filling freelist with RX buffers
- * @rx_ring: RX ring to fill
- *
- * Try to fill as many buffers as possible into freelist.  Return
- * number of buffers added.
- *
- * Return: Number of freelist buffers added.
+ * nfp_net_rx_ring_bufs_alloc() - Fill RX ring with buffers (don't give to FW)
+ * @nn:		NFP Net device
+ * @rx_ring:	RX ring to remove buffers from
  */
-static int nfp_net_rx_fill_freelist(struct nfp_net_rx_ring *rx_ring)
+static int
+nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring)
 {
-	struct sk_buff *skb;
-	dma_addr_t dma_addr;
+	struct nfp_net_rx_buf *rxbufs;
+	unsigned int i;
+
+	rxbufs = rx_ring->rxbufs;
 
-	while (nfp_net_rx_space(rx_ring)) {
-		skb = nfp_net_rx_alloc_one(rx_ring, &dma_addr);
-		if (!skb) {
-			nfp_net_rx_flush(rx_ring);
+	for (i = 0; i < rx_ring->cnt - 1; i++) {
+		rxbufs[i].skb =
+			nfp_net_rx_alloc_one(rx_ring, &rxbufs[i].dma_addr);
+		if (!rxbufs[i].skb) {
+			nfp_net_rx_ring_bufs_free(nn, rx_ring);
 			return -ENOMEM;
 		}
-		nfp_net_rx_give_one(rx_ring, skb, dma_addr);
 	}
 
 	return 0;
 }
 
 /**
+ * nfp_net_rx_ring_fill_freelist() - Give buffers from the ring to FW
+ * @rx_ring: RX ring to fill
+ */
+static void nfp_net_rx_ring_fill_freelist(struct nfp_net_rx_ring *rx_ring)
+{
+	unsigned int i;
+
+	for (i = 0; i < rx_ring->cnt - 1; i++)
+		nfp_net_rx_give_one(rx_ring, rx_ring->rxbufs[i].skb,
+				    rx_ring->rxbufs[i].dma_addr);
+}
+
+/**
  * nfp_net_rx_csum_has_errors() - group check if rxd has any csum errors
  * @flags: RX descriptor flags field in CPU byte order
  */
@@ -1431,10 +1469,6 @@ static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring)
 				  rx_ring->rxds, rx_ring->dma);
 
 	rx_ring->cnt = 0;
-	rx_ring->wr_p = 0;
-	rx_ring->rd_p = 0;
-	rx_ring->wr_ptr_add = 0;
-
 	rx_ring->rxbufs = NULL;
 	rx_ring->rxds = NULL;
 	rx_ring->dma = 0;
@@ -1641,12 +1675,13 @@ static int nfp_net_start_vec(struct nfp_net *nn, struct nfp_net_r_vector *r_vec)
 
 	disable_irq(irq_vec);
 
-	err = nfp_net_rx_fill_freelist(r_vec->rx_ring);
+	err = nfp_net_rx_ring_bufs_alloc(r_vec->nfp_net, r_vec->rx_ring);
 	if (err) {
 		nn_err(nn, "RV%02d: couldn't allocate enough buffers\n",
 		       r_vec->irq_idx);
 		goto out;
 	}
+	nfp_net_rx_ring_fill_freelist(r_vec->rx_ring);
 
 	napi_enable(&r_vec->napi);
 out:
@@ -1795,7 +1830,8 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 err_disable_napi:
 	while (r--) {
 		napi_disable(&nn->r_vecs[r].napi);
-		nfp_net_rx_flush(nn->r_vecs[r].rx_ring);
+		nfp_net_rx_ring_reset(nn->r_vecs[r].rx_ring);
+		nfp_net_rx_ring_bufs_free(nn, nn->r_vecs[r].rx_ring);
 	}
 err_clear_config:
 	nfp_net_clear_config_and_disable(nn);
@@ -1851,7 +1887,8 @@ static int nfp_net_netdev_close(struct net_device *netdev)
 	/* Step 3: Free resources
 	 */
 	for (r = 0; r < nn->num_r_vecs; r++) {
-		nfp_net_rx_flush(nn->r_vecs[r].rx_ring);
+		nfp_net_rx_ring_reset(nn->r_vecs[r].rx_ring);
+		nfp_net_rx_ring_bufs_free(nn, nn->r_vecs[r].rx_ring);
 		nfp_net_tx_ring_reset(nn, nn->r_vecs[r].tx_ring);
 		nfp_net_rx_ring_free(nn->r_vecs[r].rx_ring);
 		nfp_net_tx_ring_free(nn->r_vecs[r].tx_ring);
-- 
1.9.1

[PATCH v5 net-next 08/15] nfp: preallocate RX buffers early in .ndo_open

[Jakub Kicinski]

We want the .ndo_open() to have following structure:
 - allocate resources;
 - configure HW/FW;
 - enable the device from stack perspective.
Therefore filling RX rings needs to be moved to the beginning
of .ndo_open().

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 34 +++++++---------------
 1 file changed, 11 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 0c3c37ad28a4..a6a917fe8e31 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1666,28 +1666,19 @@ static void nfp_net_clear_config_and_disable(struct nfp_net *nn)
  * @nn:      NFP Net device structure
  * @r_vec:   Ring vector to be started
  */
-static int nfp_net_start_vec(struct nfp_net *nn, struct nfp_net_r_vector *r_vec)
+static void
+nfp_net_start_vec(struct nfp_net *nn, struct nfp_net_r_vector *r_vec)
 {
 	unsigned int irq_vec;
-	int err = 0;
 
 	irq_vec = nn->irq_entries[r_vec->irq_idx].vector;
 
 	disable_irq(irq_vec);
 
-	err = nfp_net_rx_ring_bufs_alloc(r_vec->nfp_net, r_vec->rx_ring);
-	if (err) {
-		nn_err(nn, "RV%02d: couldn't allocate enough buffers\n",
-		       r_vec->irq_idx);
-		goto out;
-	}
 	nfp_net_rx_ring_fill_freelist(r_vec->rx_ring);
-
 	napi_enable(&r_vec->napi);
-out:
-	enable_irq(irq_vec);
 
-	return err;
+	enable_irq(irq_vec);
 }
 
 static int nfp_net_netdev_open(struct net_device *netdev)
@@ -1742,6 +1733,10 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 		err = nfp_net_rx_ring_alloc(nn->r_vecs[r].rx_ring);
 		if (err)
 			goto err_free_tx_ring_p;
+
+		err = nfp_net_rx_ring_bufs_alloc(nn, nn->r_vecs[r].rx_ring);
+		if (err)
+			goto err_flush_rx_ring_p;
 	}
 
 	err = netif_set_real_num_tx_queues(netdev, nn->num_tx_rings);
@@ -1814,11 +1809,8 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 	 * - enable all TX queues
 	 * - set link state
 	 */
-	for (r = 0; r < nn->num_r_vecs; r++) {
-		err = nfp_net_start_vec(nn, &nn->r_vecs[r]);
-		if (err)
-			goto err_disable_napi;
-	}
+	for (r = 0; r < nn->num_r_vecs; r++)
+		nfp_net_start_vec(nn, &nn->r_vecs[r]);
 
 	netif_tx_wake_all_queues(netdev);
 
@@ -1827,18 +1819,14 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 
 	return 0;
 
-err_disable_napi:
-	while (r--) {
-		napi_disable(&nn->r_vecs[r].napi);
-		nfp_net_rx_ring_reset(nn->r_vecs[r].rx_ring);
-		nfp_net_rx_ring_bufs_free(nn, nn->r_vecs[r].rx_ring);
-	}
 err_clear_config:
 	nfp_net_clear_config_and_disable(nn);
 err_free_rings:
 	r = nn->num_r_vecs;
 err_free_prev_vecs:
 	while (r--) {
+		nfp_net_rx_ring_bufs_free(nn, nn->r_vecs[r].rx_ring);
+err_flush_rx_ring_p:
 		nfp_net_rx_ring_free(nn->r_vecs[r].rx_ring);
 err_free_tx_ring_p:
 		nfp_net_tx_ring_free(nn->r_vecs[r].tx_ring);
-- 
1.9.1

[PATCH v5 net-next 09/15] nfp: move filling ring information to FW config

[Jakub Kicinski]

nfp_net_[rt]x_ring_{alloc,free} should only allocate or free
ring resources without touching the device.  Move setting
parameters in the BAR to separate functions.  This will make
it possible to reuse alloc/free functions to allocate new
rings while the device is running.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 50 ++++++++++++++--------
 1 file changed, 32 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index a6a917fe8e31..342335d09fb2 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1387,10 +1387,6 @@ static void nfp_net_tx_ring_free(struct nfp_net_tx_ring *tx_ring)
 	struct nfp_net *nn = r_vec->nfp_net;
 	struct pci_dev *pdev = nn->pdev;
 
-	nn_writeq(nn, NFP_NET_CFG_TXR_ADDR(tx_ring->idx), 0);
-	nn_writeb(nn, NFP_NET_CFG_TXR_SZ(tx_ring->idx), 0);
-	nn_writeb(nn, NFP_NET_CFG_TXR_VEC(tx_ring->idx), 0);
-
 	kfree(tx_ring->txbufs);
 
 	if (tx_ring->txds)
@@ -1430,11 +1426,6 @@ static int nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring)
 	if (!tx_ring->txbufs)
 		goto err_alloc;
 
-	/* Write the DMA address, size and MSI-X info to the device */
-	nn_writeq(nn, NFP_NET_CFG_TXR_ADDR(tx_ring->idx), tx_ring->dma);
-	nn_writeb(nn, NFP_NET_CFG_TXR_SZ(tx_ring->idx), ilog2(tx_ring->cnt));
-	nn_writeb(nn, NFP_NET_CFG_TXR_VEC(tx_ring->idx), r_vec->irq_idx);
-
 	netif_set_xps_queue(nn->netdev, &r_vec->affinity_mask, tx_ring->idx);
 
 	nn_dbg(nn, "TxQ%02d: QCidx=%02d cnt=%d dma=%#llx host=%p\n",
@@ -1458,10 +1449,6 @@ static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring)
 	struct nfp_net *nn = r_vec->nfp_net;
 	struct pci_dev *pdev = nn->pdev;
 
-	nn_writeq(nn, NFP_NET_CFG_RXR_ADDR(rx_ring->idx), 0);
-	nn_writeb(nn, NFP_NET_CFG_RXR_SZ(rx_ring->idx), 0);
-	nn_writeb(nn, NFP_NET_CFG_RXR_VEC(rx_ring->idx), 0);
-
 	kfree(rx_ring->rxbufs);
 
 	if (rx_ring->rxds)
@@ -1501,11 +1488,6 @@ static int nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring)
 	if (!rx_ring->rxbufs)
 		goto err_alloc;
 
-	/* Write the DMA address, size and MSI-X info to the device */
-	nn_writeq(nn, NFP_NET_CFG_RXR_ADDR(rx_ring->idx), rx_ring->dma);
-	nn_writeb(nn, NFP_NET_CFG_RXR_SZ(rx_ring->idx), ilog2(rx_ring->cnt));
-	nn_writeb(nn, NFP_NET_CFG_RXR_VEC(rx_ring->idx), r_vec->irq_idx);
-
 	nn_dbg(nn, "RxQ%02d: FlQCidx=%02d RxQCidx=%02d cnt=%d dma=%#llx host=%p\n",
 	       rx_ring->idx, rx_ring->fl_qcidx, rx_ring->rx_qcidx,
 	       rx_ring->cnt, (unsigned long long)rx_ring->dma, rx_ring->rxds);
@@ -1630,6 +1612,17 @@ static void nfp_net_write_mac_addr(struct nfp_net *nn, const u8 *mac)
 		  get_unaligned_be16(nn->netdev->dev_addr + 4) << 16);
 }
 
+static void nfp_net_vec_clear_ring_data(struct nfp_net *nn, unsigned int idx)
+{
+	nn_writeq(nn, NFP_NET_CFG_RXR_ADDR(idx), 0);
+	nn_writeb(nn, NFP_NET_CFG_RXR_SZ(idx), 0);
+	nn_writeb(nn, NFP_NET_CFG_RXR_VEC(idx), 0);
+
+	nn_writeq(nn, NFP_NET_CFG_TXR_ADDR(idx), 0);
+	nn_writeb(nn, NFP_NET_CFG_TXR_SZ(idx), 0);
+	nn_writeb(nn, NFP_NET_CFG_TXR_VEC(idx), 0);
+}
+
 /**
  * nfp_net_clear_config_and_disable() - Clear control BAR and disable NFP
  * @nn:      NFP Net device to reconfigure
@@ -1637,6 +1630,7 @@ static void nfp_net_write_mac_addr(struct nfp_net *nn, const u8 *mac)
 static void nfp_net_clear_config_and_disable(struct nfp_net *nn)
 {
 	u32 new_ctrl, update;
+	unsigned int r;
 	int err;
 
 	new_ctrl = nn->ctrl;
@@ -1658,9 +1652,26 @@ static void nfp_net_clear_config_and_disable(struct nfp_net *nn)
 		return;
 	}
 
+	for (r = 0; r < nn->num_r_vecs; r++)
+		nfp_net_vec_clear_ring_data(nn, r);
+
 	nn->ctrl = new_ctrl;
 }
 
+static void
+nfp_net_vec_write_ring_data(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
+			    unsigned int idx)
+{
+	/* Write the DMA address, size and MSI-X info to the device */
+	nn_writeq(nn, NFP_NET_CFG_RXR_ADDR(idx), r_vec->rx_ring->dma);
+	nn_writeb(nn, NFP_NET_CFG_RXR_SZ(idx), ilog2(r_vec->rx_ring->cnt));
+	nn_writeb(nn, NFP_NET_CFG_RXR_VEC(idx), r_vec->irq_idx);
+
+	nn_writeq(nn, NFP_NET_CFG_TXR_ADDR(idx), r_vec->tx_ring->dma);
+	nn_writeb(nn, NFP_NET_CFG_TXR_SZ(idx), ilog2(r_vec->tx_ring->cnt));
+	nn_writeb(nn, NFP_NET_CFG_TXR_VEC(idx), r_vec->irq_idx);
+}
+
 /**
  * nfp_net_start_vec() - Start ring vector
  * @nn:      NFP Net device structure
@@ -1768,6 +1779,9 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 	 * - Set the Freelist buffer size
 	 * - Enable the FW
 	 */
+	for (r = 0; r < nn->num_r_vecs; r++)
+		nfp_net_vec_write_ring_data(nn, &nn->r_vecs[r], r);
+
 	nn_writeq(nn, NFP_NET_CFG_TXRS_ENABLE, nn->num_tx_rings == 64 ?
 		  0xffffffffffffffffULL : ((u64)1 << nn->num_tx_rings) - 1);
 
-- 
1.9.1

[PATCH v5 net-next 10/15] nfp: slice .ndo_open() and .ndo_stop() up

[Jakub Kicinski]

Divide .ndo_open() and .ndo_stop() into logical, callable
chunks.  No functional changes.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 218 +++++++++++++--------
 1 file changed, 136 insertions(+), 82 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 342335d09fb2..6c1ed8914416 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1672,6 +1672,82 @@ nfp_net_vec_write_ring_data(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 	nn_writeb(nn, NFP_NET_CFG_TXR_VEC(idx), r_vec->irq_idx);
 }
 
+static int __nfp_net_set_config_and_enable(struct nfp_net *nn)
+{
+	u32 new_ctrl, update = 0;
+	unsigned int r;
+	int err;
+
+	new_ctrl = nn->ctrl;
+
+	if (nn->cap & NFP_NET_CFG_CTRL_RSS) {
+		nfp_net_rss_write_key(nn);
+		nfp_net_rss_write_itbl(nn);
+		nn_writel(nn, NFP_NET_CFG_RSS_CTRL, nn->rss_cfg);
+		update |= NFP_NET_CFG_UPDATE_RSS;
+	}
+
+	if (nn->cap & NFP_NET_CFG_CTRL_IRQMOD) {
+		nfp_net_coalesce_write_cfg(nn);
+
+		new_ctrl |= NFP_NET_CFG_CTRL_IRQMOD;
+		update |= NFP_NET_CFG_UPDATE_IRQMOD;
+	}
+
+	for (r = 0; r < nn->num_r_vecs; r++)
+		nfp_net_vec_write_ring_data(nn, &nn->r_vecs[r], r);
+
+	nn_writeq(nn, NFP_NET_CFG_TXRS_ENABLE, nn->num_tx_rings == 64 ?
+		  0xffffffffffffffffULL : ((u64)1 << nn->num_tx_rings) - 1);
+
+	nn_writeq(nn, NFP_NET_CFG_RXRS_ENABLE, nn->num_rx_rings == 64 ?
+		  0xffffffffffffffffULL : ((u64)1 << nn->num_rx_rings) - 1);
+
+	nfp_net_write_mac_addr(nn, nn->netdev->dev_addr);
+
+	nn_writel(nn, NFP_NET_CFG_MTU, nn->netdev->mtu);
+	nn_writel(nn, NFP_NET_CFG_FLBUFSZ, nn->fl_bufsz);
+
+	/* Enable device */
+	new_ctrl |= NFP_NET_CFG_CTRL_ENABLE;
+	update |= NFP_NET_CFG_UPDATE_GEN;
+	update |= NFP_NET_CFG_UPDATE_MSIX;
+	update |= NFP_NET_CFG_UPDATE_RING;
+	if (nn->cap & NFP_NET_CFG_CTRL_RINGCFG)
+		new_ctrl |= NFP_NET_CFG_CTRL_RINGCFG;
+
+	nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl);
+	err = nfp_net_reconfig(nn, update);
+
+	nn->ctrl = new_ctrl;
+
+	/* Since reconfiguration requests while NFP is down are ignored we
+	 * have to wipe the entire VXLAN configuration and reinitialize it.
+	 */
+	if (nn->ctrl & NFP_NET_CFG_CTRL_VXLAN) {
+		memset(&nn->vxlan_ports, 0, sizeof(nn->vxlan_ports));
+		memset(&nn->vxlan_usecnt, 0, sizeof(nn->vxlan_usecnt));
+		vxlan_get_rx_port(nn->netdev);
+	}
+
+	return err;
+}
+
+/**
+ * nfp_net_set_config_and_enable() - Write control BAR and enable NFP
+ * @nn:      NFP Net device to reconfigure
+ */
+static int nfp_net_set_config_and_enable(struct nfp_net *nn)
+{
+	int err;
+
+	err = __nfp_net_set_config_and_enable(nn);
+	if (err)
+		nfp_net_clear_config_and_disable(nn);
+
+	return err;
+}
+
 /**
  * nfp_net_start_vec() - Start ring vector
  * @nn:      NFP Net device structure
@@ -1692,20 +1768,33 @@ nfp_net_start_vec(struct nfp_net *nn, struct nfp_net_r_vector *r_vec)
 	enable_irq(irq_vec);
 }
 
+/**
+ * nfp_net_open_stack() - Start the device from stack's perspective
+ * @nn:      NFP Net device to reconfigure
+ */
+static void nfp_net_open_stack(struct nfp_net *nn)
+{
+	unsigned int r;
+
+	for (r = 0; r < nn->num_r_vecs; r++)
+		nfp_net_start_vec(nn, &nn->r_vecs[r]);
+
+	netif_tx_wake_all_queues(nn->netdev);
+
+	enable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector);
+	nfp_net_read_link_status(nn);
+}
+
 static int nfp_net_netdev_open(struct net_device *netdev)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 	int err, r;
-	u32 update = 0;
-	u32 new_ctrl;
 
 	if (nn->ctrl & NFP_NET_CFG_CTRL_ENABLE) {
 		nn_err(nn, "Dev is already enabled: 0x%08x\n", nn->ctrl);
 		return -EBUSY;
 	}
 
-	new_ctrl = nn->ctrl;
-
 	/* Step 1: Allocate resources for rings and the like
 	 * - Request interrupts
 	 * - Allocate RX and TX ring resources
@@ -1758,20 +1847,6 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 	if (err)
 		goto err_free_rings;
 
-	if (nn->cap & NFP_NET_CFG_CTRL_RSS) {
-		nfp_net_rss_write_key(nn);
-		nfp_net_rss_write_itbl(nn);
-		nn_writel(nn, NFP_NET_CFG_RSS_CTRL, nn->rss_cfg);
-		update |= NFP_NET_CFG_UPDATE_RSS;
-	}
-
-	if (nn->cap & NFP_NET_CFG_CTRL_IRQMOD) {
-		nfp_net_coalesce_write_cfg(nn);
-
-		new_ctrl |= NFP_NET_CFG_CTRL_IRQMOD;
-		update |= NFP_NET_CFG_UPDATE_IRQMOD;
-	}
-
 	/* Step 2: Configure the NFP
 	 * - Enable rings from 0 to tx_rings/rx_rings - 1.
 	 * - Write MAC address (in case it changed)
@@ -1779,43 +1854,9 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 	 * - Set the Freelist buffer size
 	 * - Enable the FW
 	 */
-	for (r = 0; r < nn->num_r_vecs; r++)
-		nfp_net_vec_write_ring_data(nn, &nn->r_vecs[r], r);
-
-	nn_writeq(nn, NFP_NET_CFG_TXRS_ENABLE, nn->num_tx_rings == 64 ?
-		  0xffffffffffffffffULL : ((u64)1 << nn->num_tx_rings) - 1);
-
-	nn_writeq(nn, NFP_NET_CFG_RXRS_ENABLE, nn->num_rx_rings == 64 ?
-		  0xffffffffffffffffULL : ((u64)1 << nn->num_rx_rings) - 1);
-
-	nfp_net_write_mac_addr(nn, netdev->dev_addr);
-
-	nn_writel(nn, NFP_NET_CFG_MTU, netdev->mtu);
-	nn_writel(nn, NFP_NET_CFG_FLBUFSZ, nn->fl_bufsz);
-
-	/* Enable device */
-	new_ctrl |= NFP_NET_CFG_CTRL_ENABLE;
-	update |= NFP_NET_CFG_UPDATE_GEN;
-	update |= NFP_NET_CFG_UPDATE_MSIX;
-	update |= NFP_NET_CFG_UPDATE_RING;
-	if (nn->cap & NFP_NET_CFG_CTRL_RINGCFG)
-		new_ctrl |= NFP_NET_CFG_CTRL_RINGCFG;
-
-	nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl);
-	err = nfp_net_reconfig(nn, update);
+	err = nfp_net_set_config_and_enable(nn);
 	if (err)
-		goto err_clear_config;
-
-	nn->ctrl = new_ctrl;
-
-	/* Since reconfiguration requests while NFP is down are ignored we
-	 * have to wipe the entire VXLAN configuration and reinitialize it.
-	 */
-	if (nn->ctrl & NFP_NET_CFG_CTRL_VXLAN) {
-		memset(&nn->vxlan_ports, 0, sizeof(nn->vxlan_ports));
-		memset(&nn->vxlan_usecnt, 0, sizeof(nn->vxlan_usecnt));
-		vxlan_get_rx_port(netdev);
-	}
+		goto err_free_rings;
 
 	/* Step 3: Enable for kernel
 	 * - put some freelist descriptors on each RX ring
@@ -1823,18 +1864,10 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 	 * - enable all TX queues
 	 * - set link state
 	 */
-	for (r = 0; r < nn->num_r_vecs; r++)
-		nfp_net_start_vec(nn, &nn->r_vecs[r]);
-
-	netif_tx_wake_all_queues(netdev);
-
-	enable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector);
-	nfp_net_read_link_status(nn);
+	nfp_net_open_stack(nn);
 
 	return 0;
 
-err_clear_config:
-	nfp_net_clear_config_and_disable(nn);
 err_free_rings:
 	r = nn->num_r_vecs;
 err_free_prev_vecs:
@@ -1858,36 +1891,31 @@ err_free_exn:
 }
 
 /**
- * nfp_net_netdev_close() - Called when the device is downed
- * @netdev:      netdev structure
+ * nfp_net_close_stack() - Quiescent the stack (part of close)
+ * @nn:	     NFP Net device to reconfigure
  */
-static int nfp_net_netdev_close(struct net_device *netdev)
+static void nfp_net_close_stack(struct nfp_net *nn)
 {
-	struct nfp_net *nn = netdev_priv(netdev);
-	int r;
-
-	if (!(nn->ctrl & NFP_NET_CFG_CTRL_ENABLE)) {
-		nn_err(nn, "Dev is not up: 0x%08x\n", nn->ctrl);
-		return 0;
-	}
+	unsigned int r;
 
-	/* Step 1: Disable RX and TX rings from the Linux kernel perspective
-	 */
 	disable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector);
-	netif_carrier_off(netdev);
+	netif_carrier_off(nn->netdev);
 	nn->link_up = false;
 
 	for (r = 0; r < nn->num_r_vecs; r++)
 		napi_disable(&nn->r_vecs[r].napi);
 
-	netif_tx_disable(netdev);
+	netif_tx_disable(nn->netdev);
+}
 
-	/* Step 2: Tell NFP
-	 */
-	nfp_net_clear_config_and_disable(nn);
+/**
+ * nfp_net_close_free_all() - Free all runtime resources
+ * @nn:      NFP Net device to reconfigure
+ */
+static void nfp_net_close_free_all(struct nfp_net *nn)
+{
+	unsigned int r;
 
-	/* Step 3: Free resources
-	 */
 	for (r = 0; r < nn->num_r_vecs; r++) {
 		nfp_net_rx_ring_reset(nn->r_vecs[r].rx_ring);
 		nfp_net_rx_ring_bufs_free(nn, nn->r_vecs[r].rx_ring);
@@ -1902,6 +1930,32 @@ static int nfp_net_netdev_close(struct net_device *netdev)
 
 	nfp_net_aux_irq_free(nn, NFP_NET_CFG_LSC, NFP_NET_IRQ_LSC_IDX);
 	nfp_net_aux_irq_free(nn, NFP_NET_CFG_EXN, NFP_NET_IRQ_EXN_IDX);
+}
+
+/**
+ * nfp_net_netdev_close() - Called when the device is downed
+ * @netdev:      netdev structure
+ */
+static int nfp_net_netdev_close(struct net_device *netdev)
+{
+	struct nfp_net *nn = netdev_priv(netdev);
+
+	if (!(nn->ctrl & NFP_NET_CFG_CTRL_ENABLE)) {
+		nn_err(nn, "Dev is not up: 0x%08x\n", nn->ctrl);
+		return 0;
+	}
+
+	/* Step 1: Disable RX and TX rings from the Linux kernel perspective
+	 */
+	nfp_net_close_stack(nn);
+
+	/* Step 2: Tell NFP
+	 */
+	nfp_net_clear_config_and_disable(nn);
+
+	/* Step 3: Free resources
+	 */
+	nfp_net_close_free_all(nn);
 
 	nn_dbg(nn, "%s down", netdev->name);
 	return 0;
-- 
1.9.1

[PATCH v5 net-next 11/15] nfp: sync ring state during FW reconfiguration

[Jakub Kicinski]

FW reconfiguration in .ndo_open()/.ndo_stop() should reset/
restore queue state.  Since we need IRQs to be disabled when
filling rings on RX path we have to move disable_irq() from
.ndo_open() all the way up to IRQ allocation.

nfp_net_start_vec() becomes trivial now so it's inlined.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 45 ++++++++--------------
 1 file changed, 16 insertions(+), 29 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 6c1ed8914416..ed23b9d348c3 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1519,6 +1519,7 @@ nfp_net_prepare_vector(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 		nn_err(nn, "Error requesting IRQ %d\n", entry->vector);
 		return err;
 	}
+	disable_irq(entry->vector);
 
 	/* Setup NAPI */
 	netif_napi_add(nn->netdev, &r_vec->napi,
@@ -1647,13 +1648,14 @@ static void nfp_net_clear_config_and_disable(struct nfp_net *nn)
 
 	nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl);
 	err = nfp_net_reconfig(nn, update);
-	if (err) {
+	if (err)
 		nn_err(nn, "Could not disable device: %d\n", err);
-		return;
-	}
 
-	for (r = 0; r < nn->num_r_vecs; r++)
+	for (r = 0; r < nn->num_r_vecs; r++) {
+		nfp_net_rx_ring_reset(nn->r_vecs[r].rx_ring);
+		nfp_net_tx_ring_reset(nn, nn->r_vecs[r].tx_ring);
 		nfp_net_vec_clear_ring_data(nn, r);
+	}
 
 	nn->ctrl = new_ctrl;
 }
@@ -1721,6 +1723,9 @@ static int __nfp_net_set_config_and_enable(struct nfp_net *nn)
 
 	nn->ctrl = new_ctrl;
 
+	for (r = 0; r < nn->num_r_vecs; r++)
+		nfp_net_rx_ring_fill_freelist(nn->r_vecs[r].rx_ring);
+
 	/* Since reconfiguration requests while NFP is down are ignored we
 	 * have to wipe the entire VXLAN configuration and reinitialize it.
 	 */
@@ -1749,26 +1754,6 @@ static int nfp_net_set_config_and_enable(struct nfp_net *nn)
 }
 
 /**
- * nfp_net_start_vec() - Start ring vector
- * @nn:      NFP Net device structure
- * @r_vec:   Ring vector to be started
- */
-static void
-nfp_net_start_vec(struct nfp_net *nn, struct nfp_net_r_vector *r_vec)
-{
-	unsigned int irq_vec;
-
-	irq_vec = nn->irq_entries[r_vec->irq_idx].vector;
-
-	disable_irq(irq_vec);
-
-	nfp_net_rx_ring_fill_freelist(r_vec->rx_ring);
-	napi_enable(&r_vec->napi);
-
-	enable_irq(irq_vec);
-}
-
-/**
  * nfp_net_open_stack() - Start the device from stack's perspective
  * @nn:      NFP Net device to reconfigure
  */
@@ -1776,8 +1761,10 @@ static void nfp_net_open_stack(struct nfp_net *nn)
 {
 	unsigned int r;
 
-	for (r = 0; r < nn->num_r_vecs; r++)
-		nfp_net_start_vec(nn, &nn->r_vecs[r]);
+	for (r = 0; r < nn->num_r_vecs; r++) {
+		napi_enable(&nn->r_vecs[r].napi);
+		enable_irq(nn->irq_entries[nn->r_vecs[r].irq_idx].vector);
+	}
 
 	netif_tx_wake_all_queues(nn->netdev);
 
@@ -1902,8 +1889,10 @@ static void nfp_net_close_stack(struct nfp_net *nn)
 	netif_carrier_off(nn->netdev);
 	nn->link_up = false;
 
-	for (r = 0; r < nn->num_r_vecs; r++)
+	for (r = 0; r < nn->num_r_vecs; r++) {
+		disable_irq(nn->irq_entries[nn->r_vecs[r].irq_idx].vector);
 		napi_disable(&nn->r_vecs[r].napi);
+	}
 
 	netif_tx_disable(nn->netdev);
 }
@@ -1917,9 +1906,7 @@ static void nfp_net_close_free_all(struct nfp_net *nn)
 	unsigned int r;
 
 	for (r = 0; r < nn->num_r_vecs; r++) {
-		nfp_net_rx_ring_reset(nn->r_vecs[r].rx_ring);
 		nfp_net_rx_ring_bufs_free(nn, nn->r_vecs[r].rx_ring);
-		nfp_net_tx_ring_reset(nn, nn->r_vecs[r].tx_ring);
 		nfp_net_rx_ring_free(nn->r_vecs[r].rx_ring);
 		nfp_net_tx_ring_free(nn->r_vecs[r].tx_ring);
 		nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
-- 
1.9.1

[PATCH v5 net-next 12/15] nfp: propagate list buffer size in struct rx_ring

[Jakub Kicinski]

Free list buffer size needs to be propagated to few functions
as a parameter and added to struct nfp_net_rx_ring since soon
some of the functions will be reused to manage rings with
buffers of size different than nn->fl_bufsz.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/ethernet/netronome/nfp/nfp_net.h       |  3 +++
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 24 ++++++++++++++--------
 2 files changed, 19 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index fc005c982b7d..9ab8e3967dc9 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -298,6 +298,8 @@ struct nfp_net_rx_buf {
  * @rxds:       Virtual address of FL/RX ring in host memory
  * @dma:        DMA address of the FL/RX ring
  * @size:       Size, in bytes, of the FL/RX ring (needed to free)
+ * @bufsz:	Buffer allocation size for convenience of management routines
+ *		(NOTE: this is in second cache line, do not use on fast path!)
  */
 struct nfp_net_rx_ring {
 	struct nfp_net_r_vector *r_vec;
@@ -319,6 +321,7 @@ struct nfp_net_rx_ring {
 
 	dma_addr_t dma;
 	unsigned int size;
+	unsigned int bufsz;
 } ____cacheline_aligned;
 
 /**
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index ed23b9d348c3..03c60f755de0 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -957,25 +957,27 @@ static inline int nfp_net_rx_space(struct nfp_net_rx_ring *rx_ring)
  * nfp_net_rx_alloc_one() - Allocate and map skb for RX
  * @rx_ring:	RX ring structure of the skb
  * @dma_addr:	Pointer to storage for DMA address (output param)
+ * @fl_bufsz:	size of freelist buffers
  *
  * This function will allcate a new skb, map it for DMA.
  *
  * Return: allocated skb or NULL on failure.
  */
 static struct sk_buff *
-nfp_net_rx_alloc_one(struct nfp_net_rx_ring *rx_ring, dma_addr_t *dma_addr)
+nfp_net_rx_alloc_one(struct nfp_net_rx_ring *rx_ring, dma_addr_t *dma_addr,
+		     unsigned int fl_bufsz)
 {
 	struct nfp_net *nn = rx_ring->r_vec->nfp_net;
 	struct sk_buff *skb;
 
-	skb = netdev_alloc_skb(nn->netdev, nn->fl_bufsz);
+	skb = netdev_alloc_skb(nn->netdev, fl_bufsz);
 	if (!skb) {
 		nn_warn_ratelimit(nn, "Failed to alloc receive SKB\n");
 		return NULL;
 	}
 
 	*dma_addr = dma_map_single(&nn->pdev->dev, skb->data,
-				  nn->fl_bufsz, DMA_FROM_DEVICE);
+				   fl_bufsz, DMA_FROM_DEVICE);
 	if (dma_mapping_error(&nn->pdev->dev, *dma_addr)) {
 		dev_kfree_skb_any(skb);
 		nn_warn_ratelimit(nn, "Failed to map DMA RX buffer\n");
@@ -1068,7 +1070,7 @@ nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring)
 			continue;
 
 		dma_unmap_single(&pdev->dev, rx_ring->rxbufs[i].dma_addr,
-				 nn->fl_bufsz, DMA_FROM_DEVICE);
+				 rx_ring->bufsz, DMA_FROM_DEVICE);
 		dev_kfree_skb_any(rx_ring->rxbufs[i].skb);
 		rx_ring->rxbufs[i].dma_addr = 0;
 		rx_ring->rxbufs[i].skb = NULL;
@@ -1090,7 +1092,8 @@ nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring)
 
 	for (i = 0; i < rx_ring->cnt - 1; i++) {
 		rxbufs[i].skb =
-			nfp_net_rx_alloc_one(rx_ring, &rxbufs[i].dma_addr);
+			nfp_net_rx_alloc_one(rx_ring, &rxbufs[i].dma_addr,
+					     rx_ring->bufsz);
 		if (!rxbufs[i].skb) {
 			nfp_net_rx_ring_bufs_free(nn, rx_ring);
 			return -ENOMEM;
@@ -1278,7 +1281,8 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 
 		skb = rx_ring->rxbufs[idx].skb;
 
-		new_skb = nfp_net_rx_alloc_one(rx_ring, &new_dma_addr);
+		new_skb = nfp_net_rx_alloc_one(rx_ring, &new_dma_addr,
+					       nn->fl_bufsz);
 		if (!new_skb) {
 			nfp_net_rx_give_one(rx_ring, rx_ring->rxbufs[idx].skb,
 					    rx_ring->rxbufs[idx].dma_addr);
@@ -1465,10 +1469,12 @@ static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring)
 /**
  * nfp_net_rx_ring_alloc() - Allocate resource for a RX ring
  * @rx_ring:  RX ring to allocate
+ * @fl_bufsz: Size of buffers to allocate
  *
  * Return: 0 on success, negative errno otherwise.
  */
-static int nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring)
+static int
+nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring, unsigned int fl_bufsz)
 {
 	struct nfp_net_r_vector *r_vec = rx_ring->r_vec;
 	struct nfp_net *nn = r_vec->nfp_net;
@@ -1476,6 +1482,7 @@ static int nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring)
 	int sz;
 
 	rx_ring->cnt = nn->rxd_cnt;
+	rx_ring->bufsz = fl_bufsz;
 
 	rx_ring->size = sizeof(*rx_ring->rxds) * rx_ring->cnt;
 	rx_ring->rxds = dma_zalloc_coherent(&pdev->dev, rx_ring->size,
@@ -1817,7 +1824,8 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 		if (err)
 			goto err_cleanup_vec_p;
 
-		err = nfp_net_rx_ring_alloc(nn->r_vecs[r].rx_ring);
+		err = nfp_net_rx_ring_alloc(nn->r_vecs[r].rx_ring,
+					    nn->fl_bufsz);
 		if (err)
 			goto err_free_tx_ring_p;
 
-- 
1.9.1

[PATCH v5 net-next 13/15] nfp: convert .ndo_change_mtu() to prepare/commit paradigm

[Jakub Kicinski]

When changing MTU on running device first allocate new rings
and buffers and once it succeeds proceed with changing MTU.

Allocation of new rings is not really necessary for this
operation - it's done to keep the code simple and because
size of the extra ring memory is quite small compared to
the size of buffers.

Operation can still fail midway through if FW communication
times out.  In that case we retry with old MTU (rings).

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 108 +++++++++++++++++++--
 1 file changed, 102 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 03c60f755de0..e7c420fdcb0d 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1506,6 +1506,64 @@ err_alloc:
 	return -ENOMEM;
 }
 
+static struct nfp_net_rx_ring *
+nfp_net_shadow_rx_rings_prepare(struct nfp_net *nn, unsigned int fl_bufsz)
+{
+	struct nfp_net_rx_ring *rings;
+	unsigned int r;
+
+	rings = kcalloc(nn->num_rx_rings, sizeof(*rings), GFP_KERNEL);
+	if (!rings)
+		return NULL;
+
+	for (r = 0; r < nn->num_rx_rings; r++) {
+		nfp_net_rx_ring_init(&rings[r], nn->rx_rings[r].r_vec, r);
+
+		if (nfp_net_rx_ring_alloc(&rings[r], fl_bufsz))
+			goto err_free_prev;
+
+		if (nfp_net_rx_ring_bufs_alloc(nn, &rings[r]))
+			goto err_free_ring;
+	}
+
+	return rings;
+
+err_free_prev:
+	while (r--) {
+		nfp_net_rx_ring_bufs_free(nn, &rings[r]);
+err_free_ring:
+		nfp_net_rx_ring_free(&rings[r]);
+	}
+	kfree(rings);
+	return NULL;
+}
+
+static struct nfp_net_rx_ring *
+nfp_net_shadow_rx_rings_swap(struct nfp_net *nn, struct nfp_net_rx_ring *rings)
+{
+	struct nfp_net_rx_ring *old = nn->rx_rings;
+	unsigned int r;
+
+	for (r = 0; r < nn->num_rx_rings; r++)
+		old[r].r_vec->rx_ring = &rings[r];
+
+	nn->rx_rings = rings;
+	return old;
+}
+
+static void
+nfp_net_shadow_rx_rings_free(struct nfp_net *nn, struct nfp_net_rx_ring *rings)
+{
+	unsigned int r;
+
+	for (r = 0; r < nn->num_r_vecs; r++) {
+		nfp_net_rx_ring_bufs_free(nn, &rings[r]);
+		nfp_net_rx_ring_free(&rings[r]);
+	}
+
+	kfree(rings);
+}
+
 static int
 nfp_net_prepare_vector(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 		       int idx)
@@ -1984,23 +2042,61 @@ static void nfp_net_set_rx_mode(struct net_device *netdev)
 
 static int nfp_net_change_mtu(struct net_device *netdev, int new_mtu)
 {
+	unsigned int old_mtu, old_fl_bufsz, new_fl_bufsz;
 	struct nfp_net *nn = netdev_priv(netdev);
+	struct nfp_net_rx_ring *tmp_rings;
+	int err;
 
 	if (new_mtu < 68 || new_mtu > nn->max_mtu) {
 		nn_err(nn, "New MTU (%d) is not valid\n", new_mtu);
 		return -EINVAL;
 	}
 
+	old_mtu = netdev->mtu;
+	old_fl_bufsz = nn->fl_bufsz;
+	new_fl_bufsz = NFP_NET_MAX_PREPEND + ETH_HLEN + VLAN_HLEN * 2 + new_mtu;
+
+	if (!netif_running(netdev)) {
+		netdev->mtu = new_mtu;
+		nn->fl_bufsz = new_fl_bufsz;
+		return 0;
+	}
+
+	/* Prepare new rings */
+	tmp_rings = nfp_net_shadow_rx_rings_prepare(nn, new_fl_bufsz);
+	if (!tmp_rings)
+		return -ENOMEM;
+
+	/* Stop device, swap in new rings, try to start the firmware */
+	nfp_net_close_stack(nn);
+	nfp_net_clear_config_and_disable(nn);
+
+	tmp_rings = nfp_net_shadow_rx_rings_swap(nn, tmp_rings);
+
 	netdev->mtu = new_mtu;
-	nn->fl_bufsz = NFP_NET_MAX_PREPEND + ETH_HLEN + VLAN_HLEN * 2 + new_mtu;
+	nn->fl_bufsz = new_fl_bufsz;
+
+	err = nfp_net_set_config_and_enable(nn);
+	if (err) {
+		const int err_new = err;
+
+		/* Try with old configuration and old rings */
+		tmp_rings = nfp_net_shadow_rx_rings_swap(nn, tmp_rings);
+
+		netdev->mtu = old_mtu;
+		nn->fl_bufsz = old_fl_bufsz;
 
-	/* restart if running */
-	if (netif_running(netdev)) {
-		nfp_net_netdev_close(netdev);
-		nfp_net_netdev_open(netdev);
+		err = __nfp_net_set_config_and_enable(nn);
+		if (err)
+			nn_err(nn, "Can't restore MTU - FW communication failed (%d,%d)\n",
+			       err_new, err);
 	}
 
-	return 0;
+	nfp_net_shadow_rx_rings_free(nn, tmp_rings);
+
+	nfp_net_open_stack(nn);
+
+	return err;
 }
 
 static struct rtnl_link_stats64 *nfp_net_stat64(struct net_device *netdev,
-- 
1.9.1

[PATCH v5 net-next 14/15] nfp: pass ring count as function parameter

[Jakub Kicinski]

Soon ring resize will call this functions with values
different than the current configuration we need to
explicitly pass the ring count as parameter.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 23 +++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index e7c420fdcb0d..c4f0c70e77ce 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1407,17 +1407,18 @@ static void nfp_net_tx_ring_free(struct nfp_net_tx_ring *tx_ring)
 /**
  * nfp_net_tx_ring_alloc() - Allocate resource for a TX ring
  * @tx_ring:   TX Ring structure to allocate
+ * @cnt:       Ring buffer count
  *
  * Return: 0 on success, negative errno otherwise.
  */
-static int nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring)
+static int nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt)
 {
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
 	struct nfp_net *nn = r_vec->nfp_net;
 	struct pci_dev *pdev = nn->pdev;
 	int sz;
 
-	tx_ring->cnt = nn->txd_cnt;
+	tx_ring->cnt = cnt;
 
 	tx_ring->size = sizeof(*tx_ring->txds) * tx_ring->cnt;
 	tx_ring->txds = dma_zalloc_coherent(&pdev->dev, tx_ring->size,
@@ -1470,18 +1471,20 @@ static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring)
  * nfp_net_rx_ring_alloc() - Allocate resource for a RX ring
  * @rx_ring:  RX ring to allocate
  * @fl_bufsz: Size of buffers to allocate
+ * @cnt:      Ring buffer count
  *
  * Return: 0 on success, negative errno otherwise.
  */
 static int
-nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring, unsigned int fl_bufsz)
+nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring, unsigned int fl_bufsz,
+		      u32 cnt)
 {
 	struct nfp_net_r_vector *r_vec = rx_ring->r_vec;
 	struct nfp_net *nn = r_vec->nfp_net;
 	struct pci_dev *pdev = nn->pdev;
 	int sz;
 
-	rx_ring->cnt = nn->rxd_cnt;
+	rx_ring->cnt = cnt;
 	rx_ring->bufsz = fl_bufsz;
 
 	rx_ring->size = sizeof(*rx_ring->rxds) * rx_ring->cnt;
@@ -1507,7 +1510,8 @@ err_alloc:
 }
 
 static struct nfp_net_rx_ring *
-nfp_net_shadow_rx_rings_prepare(struct nfp_net *nn, unsigned int fl_bufsz)
+nfp_net_shadow_rx_rings_prepare(struct nfp_net *nn, unsigned int fl_bufsz,
+				u32 buf_cnt)
 {
 	struct nfp_net_rx_ring *rings;
 	unsigned int r;
@@ -1519,7 +1523,7 @@ nfp_net_shadow_rx_rings_prepare(struct nfp_net *nn, unsigned int fl_bufsz)
 	for (r = 0; r < nn->num_rx_rings; r++) {
 		nfp_net_rx_ring_init(&rings[r], nn->rx_rings[r].r_vec, r);
 
-		if (nfp_net_rx_ring_alloc(&rings[r], fl_bufsz))
+		if (nfp_net_rx_ring_alloc(&rings[r], fl_bufsz, buf_cnt))
 			goto err_free_prev;
 
 		if (nfp_net_rx_ring_bufs_alloc(nn, &rings[r]))
@@ -1878,12 +1882,12 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 		if (err)
 			goto err_free_prev_vecs;
 
-		err = nfp_net_tx_ring_alloc(nn->r_vecs[r].tx_ring);
+		err = nfp_net_tx_ring_alloc(nn->r_vecs[r].tx_ring, nn->txd_cnt);
 		if (err)
 			goto err_cleanup_vec_p;
 
 		err = nfp_net_rx_ring_alloc(nn->r_vecs[r].rx_ring,
-					    nn->fl_bufsz);
+					    nn->fl_bufsz, nn->rxd_cnt);
 		if (err)
 			goto err_free_tx_ring_p;
 
@@ -2063,7 +2067,8 @@ static int nfp_net_change_mtu(struct net_device *netdev, int new_mtu)
 	}
 
 	/* Prepare new rings */
-	tmp_rings = nfp_net_shadow_rx_rings_prepare(nn, new_fl_bufsz);
+	tmp_rings = nfp_net_shadow_rx_rings_prepare(nn, new_fl_bufsz,
+						    nn->rxd_cnt);
 	if (!tmp_rings)
 		return -ENOMEM;
 
-- 
1.9.1

[PATCH v5 net-next 15/15] nfp: allow ring size reconfiguration at runtime

[Jakub Kicinski]

Since much of the required changes have already been made for
changing MTU at runtime let's use it for ring size changes as
well.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/ethernet/netronome/nfp/nfp_net.h       |   1 +
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 126 +++++++++++++++++++++
 .../net/ethernet/netronome/nfp/nfp_net_ethtool.c   |  30 ++---
 3 files changed, 136 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index 9ab8e3967dc9..3d53fcf323eb 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -724,6 +724,7 @@ void nfp_net_rss_write_key(struct nfp_net *nn);
 void nfp_net_coalesce_write_cfg(struct nfp_net *nn);
 int nfp_net_irqs_alloc(struct nfp_net *nn);
 void nfp_net_irqs_disable(struct nfp_net *nn);
+int nfp_net_set_ring_size(struct nfp_net *nn, u32 rxd_cnt, u32 txd_cnt);
 
 #ifdef CONFIG_NFP_NET_DEBUG
 void nfp_net_debugfs_create(void);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index c4f0c70e77ce..0bdff390c958 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1444,6 +1444,59 @@ err_alloc:
 	return -ENOMEM;
 }
 
+static struct nfp_net_tx_ring *
+nfp_net_shadow_tx_rings_prepare(struct nfp_net *nn, u32 buf_cnt)
+{
+	struct nfp_net_tx_ring *rings;
+	unsigned int r;
+
+	rings = kcalloc(nn->num_tx_rings, sizeof(*rings), GFP_KERNEL);
+	if (!rings)
+		return NULL;
+
+	for (r = 0; r < nn->num_tx_rings; r++) {
+		nfp_net_tx_ring_init(&rings[r], nn->tx_rings[r].r_vec, r);
+
+		if (nfp_net_tx_ring_alloc(&rings[r], buf_cnt))
+			goto err_free_prev;
+	}
+
+	return rings;
+
+err_free_prev:
+	while (r--)
+		nfp_net_tx_ring_free(&rings[r]);
+	kfree(rings);
+	return NULL;
+}
+
+static struct nfp_net_tx_ring *
+nfp_net_shadow_tx_rings_swap(struct nfp_net *nn, struct nfp_net_tx_ring *rings)
+{
+	struct nfp_net_tx_ring *old = nn->tx_rings;
+	unsigned int r;
+
+	for (r = 0; r < nn->num_tx_rings; r++)
+		old[r].r_vec->tx_ring = &rings[r];
+
+	nn->tx_rings = rings;
+	return old;
+}
+
+static void
+nfp_net_shadow_tx_rings_free(struct nfp_net *nn, struct nfp_net_tx_ring *rings)
+{
+	unsigned int r;
+
+	if (!rings)
+		return;
+
+	for (r = 0; r < nn->num_tx_rings; r++)
+		nfp_net_tx_ring_free(&rings[r]);
+
+	kfree(rings);
+}
+
 /**
  * nfp_net_rx_ring_free() - Free resources allocated to a RX ring
  * @rx_ring:  RX ring to free
@@ -1560,6 +1613,9 @@ nfp_net_shadow_rx_rings_free(struct nfp_net *nn, struct nfp_net_rx_ring *rings)
 {
 	unsigned int r;
 
+	if (!rings)
+		return;
+
 	for (r = 0; r < nn->num_r_vecs; r++) {
 		nfp_net_rx_ring_bufs_free(nn, &rings[r]);
 		nfp_net_rx_ring_free(&rings[r]);
@@ -2104,6 +2160,76 @@ static int nfp_net_change_mtu(struct net_device *netdev, int new_mtu)
 	return err;
 }
 
+int nfp_net_set_ring_size(struct nfp_net *nn, u32 rxd_cnt, u32 txd_cnt)
+{
+	struct nfp_net_tx_ring *tx_rings = NULL;
+	struct nfp_net_rx_ring *rx_rings = NULL;
+	u32 old_rxd_cnt, old_txd_cnt;
+	int err;
+
+	if (!netif_running(nn->netdev)) {
+		nn->rxd_cnt = rxd_cnt;
+		nn->txd_cnt = txd_cnt;
+		return 0;
+	}
+
+	old_rxd_cnt = nn->rxd_cnt;
+	old_txd_cnt = nn->txd_cnt;
+
+	/* Prepare new rings */
+	if (nn->rxd_cnt != rxd_cnt) {
+		rx_rings = nfp_net_shadow_rx_rings_prepare(nn, nn->fl_bufsz,
+							   rxd_cnt);
+		if (!rx_rings)
+			return -ENOMEM;
+	}
+	if (nn->txd_cnt != txd_cnt) {
+		tx_rings = nfp_net_shadow_tx_rings_prepare(nn, txd_cnt);
+		if (!tx_rings) {
+			nfp_net_shadow_rx_rings_free(nn, rx_rings);
+			return -ENOMEM;
+		}
+	}
+
+	/* Stop device, swap in new rings, try to start the firmware */
+	nfp_net_close_stack(nn);
+	nfp_net_clear_config_and_disable(nn);
+
+	if (rx_rings)
+		rx_rings = nfp_net_shadow_rx_rings_swap(nn, rx_rings);
+	if (tx_rings)
+		tx_rings = nfp_net_shadow_tx_rings_swap(nn, tx_rings);
+
+	nn->rxd_cnt = rxd_cnt;
+	nn->txd_cnt = txd_cnt;
+
+	err = nfp_net_set_config_and_enable(nn);
+	if (err) {
+		const int err_new = err;
+
+		/* Try with old configuration and old rings */
+		if (rx_rings)
+			rx_rings = nfp_net_shadow_rx_rings_swap(nn, rx_rings);
+		if (tx_rings)
+			tx_rings = nfp_net_shadow_tx_rings_swap(nn, tx_rings);
+
+		nn->rxd_cnt = old_rxd_cnt;
+		nn->txd_cnt = old_txd_cnt;
+
+		err = __nfp_net_set_config_and_enable(nn);
+		if (err)
+			nn_err(nn, "Can't restore ring config - FW communication failed (%d,%d)\n",
+			       err_new, err);
+	}
+
+	nfp_net_shadow_rx_rings_free(nn, rx_rings);
+	nfp_net_shadow_tx_rings_free(nn, tx_rings);
+
+	nfp_net_open_stack(nn);
+
+	return err;
+}
+
 static struct rtnl_link_stats64 *nfp_net_stat64(struct net_device *netdev,
 						struct rtnl_link_stats64 *stats)
 {
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index 9a4084a68db5..ccfef1f17627 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -153,37 +153,25 @@ static int nfp_net_set_ringparam(struct net_device *netdev,
 	struct nfp_net *nn = netdev_priv(netdev);
 	u32 rxd_cnt, txd_cnt;
 
-	if (netif_running(netdev)) {
-		/* Some NIC drivers allow reconfiguration on the fly,
-		 * some down the interface, change and then up it
-		 * again.  For now we don't allow changes when the
-		 * device is up.
-		 */
-		nn_warn(nn, "Can't change rings while device is up\n");
-		return -EBUSY;
-	}
-
 	/* We don't have separate queues/rings for small/large frames. */
 	if (ring->rx_mini_pending || ring->rx_jumbo_pending)
 		return -EINVAL;
 
 	/* Round up to supported values */
 	rxd_cnt = roundup_pow_of_two(ring->rx_pending);
-	rxd_cnt = max_t(u32, rxd_cnt, NFP_NET_MIN_RX_DESCS);
-	rxd_cnt = min_t(u32, rxd_cnt, NFP_NET_MAX_RX_DESCS);
-
 	txd_cnt = roundup_pow_of_two(ring->tx_pending);
-	txd_cnt = max_t(u32, txd_cnt, NFP_NET_MIN_TX_DESCS);
-	txd_cnt = min_t(u32, txd_cnt, NFP_NET_MAX_TX_DESCS);
 
-	if (nn->rxd_cnt != rxd_cnt || nn->txd_cnt != txd_cnt)
-		nn_dbg(nn, "Change ring size: RxQ %u->%u, TxQ %u->%u\n",
-		       nn->rxd_cnt, rxd_cnt, nn->txd_cnt, txd_cnt);
+	if (rxd_cnt < NFP_NET_MIN_RX_DESCS || rxd_cnt > NFP_NET_MAX_RX_DESCS ||
+	    txd_cnt < NFP_NET_MIN_TX_DESCS || txd_cnt > NFP_NET_MAX_TX_DESCS)
+		return -EINVAL;
 
-	nn->rxd_cnt = rxd_cnt;
-	nn->txd_cnt = txd_cnt;
+	if (nn->rxd_cnt == rxd_cnt && nn->txd_cnt == txd_cnt)
+		return 0;
 
-	return 0;
+	nn_dbg(nn, "Change ring size: RxQ %u->%u, TxQ %u->%u\n",
+	       nn->rxd_cnt, rxd_cnt, nn->txd_cnt, txd_cnt);
+
+	return nfp_net_set_ring_size(nn, rxd_cnt, txd_cnt);
 }
 
 static void nfp_net_get_strings(struct net_device *netdev,
-- 
1.9.1

[RFC PATCH 00/11] GSO partial and TSO FIXEDID support

[Alexander Duyck]

This patch series represents my respun version of the GSO partial work.
The major changes from the first version is that we are no longer making
the decision to mangle IP IDs transparently at the device.  Instead it is
now pushed up to the tunnel layer itself so that the tunnel is not
responsible for deciding if the IP IDs will be static or fixed for a given
TSO.

I'm a bit jammed up at the moment as I am trying to determine the best spot
to make the same change I currently am for VXLAN and GENEVE with GRE and
IPIP tunnels.  I'm assuming the correct spot would be somewhere near
iptunnel_handle_offload as I did for the other two tunnel types I have
already updated, but the flow based tunnels for GRE seem to be making it a
bit more complicated as I am not sure if a tunnel dev actually exists for
those tunnels.

This patch series is meant to apply to the dev-queue branch Jeff Kirsher's
next-queue tree at:
https://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue.git

I chose his tree as the Intel driver patches would not apply otherwise.

Patch 1 from the series is a copy of the patch recently accepted for the
net tree.  It is needed in this series to avoid merge conflicts later on as
we were making other changes in the GRO code.

---

Alexander Duyck (11):
      GRE: Disable segmentation offloads w/ CSUM and we are encapsulated via FOU
      ethtool: Add support for toggling any of the GSO offloads
      GSO: Add GSO type for fixed IPv4 ID
      GRO: Add support for TCP with fixed IPv4 ID field, limit tunnel IP ID values
      GSO: Support partial segmentation offload
      VXLAN: Add option to mangle IP IDs on inner headers when using TSO
      GENEVE: Add option to mangle IP IDs on inner headers when using TSO
      Documentation: Add documentation for TSO and GSO features
      i40e/i40evf: Add support for GSO partial with UDP_TUNNEL_CSUM and GRE_CSUM
      ixgbe/ixgbevf: Add support for GSO partial
      igb/igbvf: Add support for GSO partial


 Documentation/networking/segmentation-offloads.txt |  127 ++++++++++++++
 drivers/net/ethernet/intel/i40e/i40e_main.c        |    6 +
 drivers/net/ethernet/intel/i40e/i40e_txrx.c        |    7 +
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c      |    7 +
 drivers/net/ethernet/intel/i40evf/i40evf_main.c    |    6 +
 drivers/net/ethernet/intel/igb/igb_main.c          |  119 ++++++++++---
 drivers/net/ethernet/intel/igbvf/netdev.c          |  180 ++++++++++++--------
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c      |  115 +++++++++----
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c  |  122 +++++++++++---
 drivers/net/geneve.c                               |   24 ++-
 drivers/net/vxlan.c                                |   16 ++
 include/linux/netdev_features.h                    |    8 +
 include/linux/netdevice.h                          |   11 +
 include/linux/skbuff.h                             |   27 ++-
 include/net/udp_tunnel.h                           |    8 -
 include/net/vxlan.h                                |    1 
 include/uapi/linux/if_link.h                       |    2 
 net/core/dev.c                                     |   33 ++++
 net/core/ethtool.c                                 |    4 
 net/core/skbuff.c                                  |   29 +++
 net/ipv4/af_inet.c                                 |   70 ++++++--
 net/ipv4/fou.c                                     |    6 +
 net/ipv4/gre_offload.c                             |   35 +++-
 net/ipv4/ip_gre.c                                  |   13 +
 net/ipv4/tcp_offload.c                             |   30 +++
 net/ipv4/udp_offload.c                             |   27 ++-
 net/ipv6/ip6_offload.c                             |   21 ++
 27 files changed, 837 insertions(+), 217 deletions(-)
 create mode 100644 Documentation/networking/segmentation-offloads.txt

[RFC PATCH 01/11] GRE: Disable segmentation offloads w/ CSUM and we are encapsulated via FOU

[Alexander Duyck]

This patch fixes an issue I found in which we were dropping frames if we
had enabled checksums on GRE headers that were encapsulated by either FOU
or GUE.  Without this patch I was barely able to get 1 Gb/s of throughput.
With this patch applied I am now at least getting around 6 Gb/s.

The issue is due to the fact that with FOU or GUE applied we do not provide
a transport offset pointing to the GRE header, nor do we offload it in
software as the GRE header is completely skipped by GSO and treated like a
VXLAN or GENEVE type header.  As such we need to prevent the stack from
generating it and also prevent GRE from generating it via any interface we
create.

Fixes: c3483384ee511 ("gro: Allow tunnel stacking in the case of FOU/GUE")
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
---
 include/linux/netdevice.h |    5 ++++-
 net/core/dev.c            |    1 +
 net/ipv4/fou.c            |    6 ++++++
 net/ipv4/gre_offload.c    |    8 ++++++++
 net/ipv4/ip_gre.c         |   13 ++++++++++---
 5 files changed, 29 insertions(+), 4 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index cb0d5d09c2e4..8395308a2445 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2120,7 +2120,10 @@ struct napi_gro_cb {
 	/* Used in foo-over-udp, set in udp[46]_gro_receive */
 	u8	is_ipv6:1;
 
-	/* 7 bit hole */
+	/* Used in GRE, set in fou/gue_gro_receive */
+	u8	is_fou:1;
+
+	/* 6 bit hole */
 
 	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
 	__wsum	csum;
diff --git a/net/core/dev.c b/net/core/dev.c
index 273f10d1e306..d51343a821ed 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4439,6 +4439,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		NAPI_GRO_CB(skb)->flush = 0;
 		NAPI_GRO_CB(skb)->free = 0;
 		NAPI_GRO_CB(skb)->encap_mark = 0;
+		NAPI_GRO_CB(skb)->is_fou = 0;
 		NAPI_GRO_CB(skb)->gro_remcsum_start = 0;
 
 		/* Setup for GRO checksum validation */
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 5a94aea280d3..a39068b4a4d9 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -203,6 +203,9 @@ static struct sk_buff **fou_gro_receive(struct sk_buff **head,
 	 */
 	NAPI_GRO_CB(skb)->encap_mark = 0;
 
+	/* Flag this frame as already having an outer encap header */
+	NAPI_GRO_CB(skb)->is_fou = 1;
+
 	rcu_read_lock();
 	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
 	ops = rcu_dereference(offloads[proto]);
@@ -368,6 +371,9 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head,
 	 */
 	NAPI_GRO_CB(skb)->encap_mark = 0;
 
+	/* Flag this frame as already having an outer encap header */
+	NAPI_GRO_CB(skb)->is_fou = 1;
+
 	rcu_read_lock();
 	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
 	ops = rcu_dereference(offloads[guehdr->proto_ctype]);
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index c47539d04b88..6a5bd4317866 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -150,6 +150,14 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head,
 	if ((greh->flags & ~(GRE_KEY|GRE_CSUM)) != 0)
 		goto out;
 
+	/* We can only support GRE_CSUM if we can track the location of
+	 * the GRE header.  In the case of FOU/GUE we cannot because the
+	 * outer UDP header displaces the GRE header leaving us in a state
+	 * of limbo.
+	 */
+	if ((greh->flags & GRE_CSUM) && NAPI_GRO_CB(skb)->is_fou)
+		goto out;
+
 	type = greh->protocol;
 
 	rcu_read_lock();
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 31936d387cfd..af5d1f38217f 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -862,9 +862,16 @@ static void __gre_tunnel_init(struct net_device *dev)
 	dev->hw_features	|= GRE_FEATURES;
 
 	if (!(tunnel->parms.o_flags & TUNNEL_SEQ)) {
-		/* TCP offload with GRE SEQ is not supported. */
-		dev->features    |= NETIF_F_GSO_SOFTWARE;
-		dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+		/* TCP offload with GRE SEQ is not supported, nor
+		 * can we support 2 levels of outer headers requiring
+		 * an update.
+		 */
+		if (!(tunnel->parms.o_flags & TUNNEL_CSUM) ||
+		    (tunnel->encap.type == TUNNEL_ENCAP_NONE)) {
+			dev->features    |= NETIF_F_GSO_SOFTWARE;
+			dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+		}
+
 		/* Can use a lockless transmit, unless we generate
 		 * output sequences
 		 */

[RFC PATCH 02/11] ethtool: Add support for toggling any of the GSO offloads

[Alexander Duyck]

The strings were missing for several of the GSO offloads that are
available.  This patch provides the missing strings so that we can toggle
or query any of them via the ethtool command.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
---
 net/core/ethtool.c |    2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index f426c5ad6149..6a7f99661c2f 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -82,9 +82,11 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_TSO6_BIT] =             "tx-tcp6-segmentation",
 	[NETIF_F_FSO_BIT] =              "tx-fcoe-segmentation",
 	[NETIF_F_GSO_GRE_BIT] =		 "tx-gre-segmentation",
+	[NETIF_F_GSO_GRE_CSUM_BIT] =	 "tx-gre-csum-segmentation",
 	[NETIF_F_GSO_IPIP_BIT] =	 "tx-ipip-segmentation",
 	[NETIF_F_GSO_SIT_BIT] =		 "tx-sit-segmentation",
 	[NETIF_F_GSO_UDP_TUNNEL_BIT] =	 "tx-udp_tnl-segmentation",
+	[NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation",
 
 	[NETIF_F_FCOE_CRC_BIT] =         "tx-checksum-fcoe-crc",
 	[NETIF_F_SCTP_CRC_BIT] =        "tx-checksum-sctp",

[RFC PATCH 03/11] GSO: Add GSO type for fixed IPv4 ID

[Alexander Duyck]

This patch adds support for TSO using IPv4 headers with a fixed IP ID
field.  This is meant to allow us to do a lossless GRO in the case of TCP
flows that use a fixed IP ID such as those that convert IPv6 header to IPv4
headers.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
---
 include/linux/netdev_features.h |    3 +++
 include/linux/netdevice.h       |    1 +
 include/linux/skbuff.h          |   20 +++++++++++---------
 net/core/ethtool.c              |    1 +
 net/ipv4/af_inet.c              |   19 +++++++++++--------
 net/ipv4/gre_offload.c          |    1 +
 net/ipv4/tcp_offload.c          |    4 +++-
 net/ipv6/ip6_offload.c          |    3 ++-
 8 files changed, 33 insertions(+), 19 deletions(-)

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index a734bf43d190..5d7da1ac6df5 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -39,6 +39,7 @@ enum {
 	NETIF_F_UFO_BIT,		/* ... UDPv4 fragmentation */
 	NETIF_F_GSO_ROBUST_BIT,		/* ... ->SKB_GSO_DODGY */
 	NETIF_F_TSO_ECN_BIT,		/* ... TCP ECN support */
+	NETIF_F_TSO_FIXEDID_BIT,	/* ... IPV4 header has fixed IP ID */
 	NETIF_F_TSO6_BIT,		/* ... TCPv6 segmentation */
 	NETIF_F_FSO_BIT,		/* ... FCoE segmentation */
 	NETIF_F_GSO_GRE_BIT,		/* ... GRE with TSO */
@@ -120,6 +121,7 @@ enum {
 #define NETIF_F_GSO_SIT		__NETIF_F(GSO_SIT)
 #define NETIF_F_GSO_UDP_TUNNEL	__NETIF_F(GSO_UDP_TUNNEL)
 #define NETIF_F_GSO_UDP_TUNNEL_CSUM __NETIF_F(GSO_UDP_TUNNEL_CSUM)
+#define NETIF_F_TSO_FIXEDID	__NETIF_F(TSO_FIXEDID)
 #define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM)
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
 #define NETIF_F_HW_VLAN_STAG_RX	__NETIF_F(HW_VLAN_STAG_RX)
@@ -147,6 +149,7 @@ enum {
 
 /* List of features with software fallbacks. */
 #define NETIF_F_GSO_SOFTWARE	(NETIF_F_TSO | NETIF_F_TSO_ECN | \
+				 NETIF_F_TSO_FIXEDID | \
 				 NETIF_F_TSO6 | NETIF_F_UFO)
 
 /* List of IP checksum features. Note that NETIF_F_ HW_CSUM should not be
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 8395308a2445..38ccc01eb97d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4011,6 +4011,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	BUILD_BUG_ON(SKB_GSO_UDP     != (NETIF_F_UFO >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_DODGY   != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_FIXEDID >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_TCPV6   != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_FCOE    != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_GRE     != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT));
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 007381270ff8..5fba16658f9d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -465,23 +465,25 @@ enum {
 	/* This indicates the tcp segment has CWR set. */
 	SKB_GSO_TCP_ECN = 1 << 3,
 
-	SKB_GSO_TCPV6 = 1 << 4,
+	SKB_GSO_TCP_FIXEDID = 1 << 4,
 
-	SKB_GSO_FCOE = 1 << 5,
+	SKB_GSO_TCPV6 = 1 << 5,
 
-	SKB_GSO_GRE = 1 << 6,
+	SKB_GSO_FCOE = 1 << 6,
 
-	SKB_GSO_GRE_CSUM = 1 << 7,
+	SKB_GSO_GRE = 1 << 7,
 
-	SKB_GSO_IPIP = 1 << 8,
+	SKB_GSO_GRE_CSUM = 1 << 8,
 
-	SKB_GSO_SIT = 1 << 9,
+	SKB_GSO_IPIP = 1 << 9,
 
-	SKB_GSO_UDP_TUNNEL = 1 << 10,
+	SKB_GSO_SIT = 1 << 10,
 
-	SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11,
+	SKB_GSO_UDP_TUNNEL = 1 << 11,
 
-	SKB_GSO_TUNNEL_REMCSUM = 1 << 12,
+	SKB_GSO_UDP_TUNNEL_CSUM = 1 << 12,
+
+	SKB_GSO_TUNNEL_REMCSUM = 1 << 13,
 };
 
 #if BITS_PER_LONG > 32
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 6a7f99661c2f..5340c9dbc318 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -79,6 +79,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_UFO_BIT] =              "tx-udp-fragmentation",
 	[NETIF_F_GSO_ROBUST_BIT] =       "tx-gso-robust",
 	[NETIF_F_TSO_ECN_BIT] =          "tx-tcp-ecn-segmentation",
+	[NETIF_F_TSO_FIXEDID_BIT] =	 "tx-tcp-fixedid-segmentation",
 	[NETIF_F_TSO6_BIT] =             "tx-tcp6-segmentation",
 	[NETIF_F_FSO_BIT] =              "tx-fcoe-segmentation",
 	[NETIF_F_GSO_GRE_BIT] =		 "tx-gre-segmentation",
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index a38b9910af60..19e9a2c45d71 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1195,10 +1195,10 @@ EXPORT_SYMBOL(inet_sk_rebuild_header);
 static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 					netdev_features_t features)
 {
+	bool udpfrag = false, fixedid = false, encap;
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	const struct net_offload *ops;
 	unsigned int offset = 0;
-	bool udpfrag, encap;
 	struct iphdr *iph;
 	int proto;
 	int nhoff;
@@ -1217,6 +1217,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_TCPV6 |
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_UDP_TUNNEL_CSUM |
+		       SKB_GSO_TCP_FIXEDID |
 		       SKB_GSO_TUNNEL_REMCSUM |
 		       0)))
 		goto out;
@@ -1248,11 +1249,14 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 
 	segs = ERR_PTR(-EPROTONOSUPPORT);
 
-	if (skb->encapsulation &&
-	    skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
-		udpfrag = proto == IPPROTO_UDP && encap;
-	else
-		udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
+	if (!skb->encapsulation || encap) {
+		udpfrag = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
+		fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID);
+
+		/* fixed ID is invalid if DF bit is not set */
+		if (fixedid && !(iph->frag_off & htons(IP_DF)))
+			goto out;
+	}
 
 	ops = rcu_dereference(inet_offloads[proto]);
 	if (likely(ops && ops->callbacks.gso_segment))
@@ -1265,12 +1269,11 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 	do {
 		iph = (struct iphdr *)(skb_mac_header(skb) + nhoff);
 		if (udpfrag) {
-			iph->id = htons(id);
 			iph->frag_off = htons(offset >> 3);
 			if (skb->next)
 				iph->frag_off |= htons(IP_MF);
 			offset += skb->len - nhoff - ihl;
-		} else {
+		} else if (!fixedid) {
 			iph->id = htons(id++);
 		}
 		iph->tot_len = htons(skb->len - nhoff);
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 6a5bd4317866..6376b0cdf693 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -32,6 +32,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_UDP |
 				  SKB_GSO_DODGY |
 				  SKB_GSO_TCP_ECN |
+				  SKB_GSO_TCP_FIXEDID |
 				  SKB_GSO_GRE |
 				  SKB_GSO_GRE_CSUM |
 				  SKB_GSO_IPIP |
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 773083b7f1e9..08dd25d835af 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -89,6 +89,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 			     ~(SKB_GSO_TCPV4 |
 			       SKB_GSO_DODGY |
 			       SKB_GSO_TCP_ECN |
+			       SKB_GSO_TCP_FIXEDID |
 			       SKB_GSO_TCPV6 |
 			       SKB_GSO_GRE |
 			       SKB_GSO_GRE_CSUM |
@@ -98,7 +99,8 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 			       SKB_GSO_UDP_TUNNEL_CSUM |
 			       SKB_GSO_TUNNEL_REMCSUM |
 			       0) ||
-			     !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
+			     !(type & (SKB_GSO_TCPV4 |
+				       SKB_GSO_TCPV6))))
 			goto out;
 
 		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 82e9f3076028..d7530b9a1d63 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -73,6 +73,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_UDP |
 		       SKB_GSO_DODGY |
 		       SKB_GSO_TCP_ECN |
+		       SKB_GSO_TCP_FIXEDID |
+		       SKB_GSO_TCPV6 |
 		       SKB_GSO_GRE |
 		       SKB_GSO_GRE_CSUM |
 		       SKB_GSO_IPIP |
@@ -80,7 +82,6 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_UDP_TUNNEL_CSUM |
 		       SKB_GSO_TUNNEL_REMCSUM |
-		       SKB_GSO_TCPV6 |
 		       0)))
 		goto out;
 

[RFC PATCH 04/11] GRO: Add support for TCP with fixed IPv4 ID field, limit tunnel IP ID values

[Alexander Duyck]

This patch does two things.

First it allows TCP to aggregate TCP frames with a fixed IPv4 ID field.  As
a result we should now be able to aggregate flows that were converted from
IPv6 to IPv4.  In addition this allows us more flexibility for future
implementations of segmentation as we may be able to use a fixed IP ID when
segmenting the flow.

The second thing this addresses is that it places limitations on the outer
IPv4 ID header in the case of tunneled frames.  Specifically it forces the
IP ID to be incrementing by 1 unless the DF bit is set in the outer IPv4
header.  This way we can avoid creating overlapping series of IP IDs that
could possibly be fragmented if the frame goes through GRO and is then
resegmented via GSO.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
---
 include/linux/netdevice.h |    5 ++++-
 net/core/dev.c            |    1 +
 net/ipv4/af_inet.c        |   35 ++++++++++++++++++++++++++++-------
 net/ipv4/tcp_offload.c    |   16 +++++++++++++++-
 net/ipv6/ip6_offload.c    |    8 ++++++--
 5 files changed, 54 insertions(+), 11 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 38ccc01eb97d..abf8cc2d9bfb 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2123,7 +2123,10 @@ struct napi_gro_cb {
 	/* Used in GRE, set in fou/gue_gro_receive */
 	u8	is_fou:1;
 
-	/* 6 bit hole */
+	/* Used to determine if flush_id can be ignored */
+	u8	is_atomic:1;
+
+	/* 5 bit hole */
 
 	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
 	__wsum	csum;
diff --git a/net/core/dev.c b/net/core/dev.c
index d51343a821ed..4ed2852b3706 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4440,6 +4440,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		NAPI_GRO_CB(skb)->free = 0;
 		NAPI_GRO_CB(skb)->encap_mark = 0;
 		NAPI_GRO_CB(skb)->is_fou = 0;
+		NAPI_GRO_CB(skb)->is_atomic = 1;
 		NAPI_GRO_CB(skb)->gro_remcsum_start = 0;
 
 		/* Setup for GRO checksum validation */
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 19e9a2c45d71..98fe04b99e01 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1328,6 +1328,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 
 	for (p = *head; p; p = p->next) {
 		struct iphdr *iph2;
+		u16 flush_id;
 
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
@@ -1351,16 +1352,36 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 			(iph->tos ^ iph2->tos) |
 			((iph->frag_off ^ iph2->frag_off) & htons(IP_DF));
 
-		/* Save the IP ID check to be included later when we get to
-		 * the transport layer so only the inner most IP ID is checked.
-		 * This is because some GSO/TSO implementations do not
-		 * correctly increment the IP ID for the outer hdrs.
-		 */
-		NAPI_GRO_CB(p)->flush_id =
-			    ((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id);
 		NAPI_GRO_CB(p)->flush |= flush;
+
+		/* We need to store of the IP ID check to be included later
+		 * when we can verify that this packet does in fact belong
+		 * to a given flow.
+		 */
+		flush_id = (u16)(id - ntohs(iph2->id));
+
+		/* This bit of code makes it much easier for us to identify
+		 * the cases where we are doing atomic vs non-atomic IP ID
+		 * checks.  Specifically an atomic check can return IP ID
+		 * values 0 - 0xFFFF, while a non-atomic check can only
+		 * return 0 or 0xFFFF.
+		 */
+		if (!NAPI_GRO_CB(p)->is_atomic ||
+		    !(iph->frag_off & htons(IP_DF))) {
+			flush_id ^= NAPI_GRO_CB(p)->count;
+			flush_id = flush_id ? 0xFFFF : 0;
+		}
+
+		/* If the previous IP ID value was based on an atomic
+		 * datagram we can overwrite the value and ignore it.
+		 */
+		if (NAPI_GRO_CB(skb)->is_atomic)
+			NAPI_GRO_CB(p)->flush_id = flush_id;
+		else
+			NAPI_GRO_CB(p)->flush_id |= flush_id;
 	}
 
+	NAPI_GRO_CB(skb)->is_atomic = !!(iph->frag_off & htons(IP_DF));
 	NAPI_GRO_CB(skb)->flush |= flush;
 	skb_set_network_header(skb, off);
 	/* The above will be needed by the transport layer if there is one
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 08dd25d835af..d1ffd55289bd 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -239,7 +239,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 
 found:
 	/* Include the IP ID check below from the inner most IP hdr */
-	flush = NAPI_GRO_CB(p)->flush | NAPI_GRO_CB(p)->flush_id;
+	flush = NAPI_GRO_CB(p)->flush;
 	flush |= (__force int)(flags & TCP_FLAG_CWR);
 	flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
 		  ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH));
@@ -248,6 +248,17 @@ found:
 		flush |= *(u32 *)((u8 *)th + i) ^
 			 *(u32 *)((u8 *)th2 + i);
 
+	/* When we receive our second frame we can made a decision on if we
+	 * continue this flow as an atomic flow with a fixed ID or if we use
+	 * an incrementing ID.
+	 */
+	if (NAPI_GRO_CB(p)->flush_id != 1 ||
+	    NAPI_GRO_CB(p)->count != 1 ||
+	    !NAPI_GRO_CB(p)->is_atomic)
+		flush |= NAPI_GRO_CB(p)->flush_id;
+	else
+		NAPI_GRO_CB(p)->is_atomic = false;
+
 	mss = skb_shinfo(p)->gso_size;
 
 	flush |= (len - 1) >= mss;
@@ -316,6 +327,9 @@ static int tcp4_gro_complete(struct sk_buff *skb, int thoff)
 				  iph->daddr, 0);
 	skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4;
 
+	if (NAPI_GRO_CB(skb)->is_atomic)
+		skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_FIXEDID;
+
 	return tcp_gro_complete(skb);
 }
 
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index d7530b9a1d63..e9479499f58c 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -240,10 +240,14 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 		NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000));
 		NAPI_GRO_CB(p)->flush |= flush;
 
-		/* Clear flush_id, there's really no concept of ID in IPv6. */
-		NAPI_GRO_CB(p)->flush_id = 0;
+		/* If the previous IP ID value was based on an atomic
+		 * datagram we can overwrite the value and ignore it.
+		 */
+		if (NAPI_GRO_CB(skb)->is_atomic)
+			NAPI_GRO_CB(p)->flush_id = 0;
 	}
 
+	NAPI_GRO_CB(skb)->is_atomic = true;
 	NAPI_GRO_CB(skb)->flush |= flush;
 
 	skb_gro_postpull_rcsum(skb, iph, nlen);

[RFC PATCH 05/11] GSO: Support partial segmentation offload

[Alexander Duyck]

This patch adds support for something I am referring to as GSO partial.
The basic idea is that we can support a broader range of devices for
segmentation if we use fixed outer headers and have the hardware only
really deal with segmenting the inner header.  The idea behind the naming
is due to the fact that everything before csum_start will be fixed headers,
and everything after will be the region that is handled by hardware.

With the current implementation it allows us to add support for the
following GSO types with an inner TSO_FIXEDID or TSO6 offload:
NETIF_F_GSO_GRE
NETIF_F_GSO_GRE_CSUM
NETIF_F_GSO_IPIP
NETIF_F_GSO_SIT
NETIF_F_UDP_TUNNEL
NETIF_F_UDP_TUNNEL_CSUM

In the case of hardware that already supports tunneling we may be able to
extend this further to support TSO_TCPV4 without TSO_FIXEDID if the
hardware can support updating inner IPv4 headers.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
---
 include/linux/netdev_features.h |    5 +++++
 include/linux/netdevice.h       |    2 ++
 include/linux/skbuff.h          |    9 +++++++--
 net/core/dev.c                  |   31 ++++++++++++++++++++++++++++++-
 net/core/ethtool.c              |    1 +
 net/core/skbuff.c               |   29 ++++++++++++++++++++++++++++-
 net/ipv4/af_inet.c              |   20 ++++++++++++++++----
 net/ipv4/gre_offload.c          |   26 +++++++++++++++++++++-----
 net/ipv4/tcp_offload.c          |   10 ++++++++--
 net/ipv4/udp_offload.c          |   27 +++++++++++++++++++++------
 net/ipv6/ip6_offload.c          |   10 +++++++++-
 11 files changed, 148 insertions(+), 22 deletions(-)

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 5d7da1ac6df5..6ef549ec5b13 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -48,6 +48,10 @@ enum {
 	NETIF_F_GSO_SIT_BIT,		/* ... SIT tunnel with TSO */
 	NETIF_F_GSO_UDP_TUNNEL_BIT,	/* ... UDP TUNNEL with TSO */
 	NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT,/* ... UDP TUNNEL with TSO & CSUM */
+	NETIF_F_GSO_PARTIAL_BIT,	/* ... Only segment inner-most L4
+					 *     in hardware and all other
+					 *     headers in software.
+					 */
 	NETIF_F_GSO_TUNNEL_REMCSUM_BIT, /* ... TUNNEL with TSO & REMCSUM */
 	/**/NETIF_F_GSO_LAST =		/* last bit, see GSO_MASK */
 		NETIF_F_GSO_TUNNEL_REMCSUM_BIT,
@@ -122,6 +126,7 @@ enum {
 #define NETIF_F_GSO_UDP_TUNNEL	__NETIF_F(GSO_UDP_TUNNEL)
 #define NETIF_F_GSO_UDP_TUNNEL_CSUM __NETIF_F(GSO_UDP_TUNNEL_CSUM)
 #define NETIF_F_TSO_FIXEDID	__NETIF_F(TSO_FIXEDID)
+#define NETIF_F_GSO_PARTIAL	 __NETIF_F(GSO_PARTIAL)
 #define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM)
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
 #define NETIF_F_HW_VLAN_STAG_RX	__NETIF_F(HW_VLAN_STAG_RX)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index abf8cc2d9bfb..36a079598034 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1656,6 +1656,7 @@ struct net_device {
 	netdev_features_t	vlan_features;
 	netdev_features_t	hw_enc_features;
 	netdev_features_t	mpls_features;
+	netdev_features_t	gso_partial_features;
 
 	int			ifindex;
 	int			group;
@@ -4023,6 +4024,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	BUILD_BUG_ON(SKB_GSO_SIT     != (NETIF_F_GSO_SIT >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL != (NETIF_F_GSO_UDP_TUNNEL >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_PARTIAL != (NETIF_F_GSO_PARTIAL >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT));
 
 	return (features & feature) == feature;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 5fba16658f9d..da0ace389fec 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -483,7 +483,9 @@ enum {
 
 	SKB_GSO_UDP_TUNNEL_CSUM = 1 << 12,
 
-	SKB_GSO_TUNNEL_REMCSUM = 1 << 13,
+	SKB_GSO_PARTIAL = 1 << 13,
+
+	SKB_GSO_TUNNEL_REMCSUM = 1 << 14,
 };
 
 #if BITS_PER_LONG > 32
@@ -3591,7 +3593,10 @@ static inline struct sec_path *skb_sec_path(struct sk_buff *skb)
  * Keeps track of level of encapsulation of network headers.
  */
 struct skb_gso_cb {
-	int	mac_offset;
+	union {
+		int	mac_offset;
+		int	data_offset;
+	};
 	int	encap_level;
 	__wsum	csum;
 	__u16	csum_start;
diff --git a/net/core/dev.c b/net/core/dev.c
index 4ed2852b3706..53b216b617c3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2711,6 +2711,19 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 			return ERR_PTR(err);
 	}
 
+	/* Only report GSO partial support if it will enable us to
+	 * support segmentation on this frame without needing additional
+	 * work.
+	 */
+	if (features & NETIF_F_GSO_PARTIAL) {
+		netdev_features_t partial_features = NETIF_F_GSO_ROBUST;
+		struct net_device *dev = skb->dev;
+
+		partial_features |= dev->features & dev->gso_partial_features;
+		if (!skb_gso_ok(skb, features | partial_features))
+			features &= ~NETIF_F_GSO_PARTIAL;
+	}
+
 	BUILD_BUG_ON(SKB_SGO_CB_OFFSET +
 		     sizeof(*SKB_GSO_CB(skb)) > sizeof(skb->cb));
 
@@ -2841,6 +2854,14 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
 	if (skb->encapsulation)
 		features &= dev->hw_enc_features;
 
+	/* Support for GSO partial features requires software intervention
+	 * before we can actually process the packets so we need to strip
+	 * support for any partial features now and we can pull them back
+	 * in after we have partially segmented the frame.
+	 */
+	if (skb_is_gso(skb) && !(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL))
+		features &= ~dev->gso_partial_features;
+
 	if (skb_vlan_tagged(skb))
 		features = netdev_intersect_features(features,
 						     dev->vlan_features |
@@ -6707,6 +6728,14 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
 		}
 	}
 
+	/* GSO partial features require GSO partial be set */
+	if ((features & dev->gso_partial_features) &&
+	    !(features & NETIF_F_GSO_PARTIAL)) {
+		netdev_dbg(dev,
+			   "Dropping partially supported GSO features since no GSO partial.\n");
+		features &= ~dev->gso_partial_features;
+	}
+
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	if (dev->netdev_ops->ndo_busy_poll)
 		features |= NETIF_F_BUSY_POLL;
@@ -6987,7 +7016,7 @@ int register_netdevice(struct net_device *dev)
 
 	/* Make NETIF_F_SG inheritable to tunnel devices.
 	 */
-	dev->hw_enc_features |= NETIF_F_SG;
+	dev->hw_enc_features |= NETIF_F_SG | NETIF_F_GSO_PARTIAL;
 
 	/* Make NETIF_F_SG inheritable to MPLS.
 	 */
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 5340c9dbc318..005478851118 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -88,6 +88,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_GSO_SIT_BIT] =		 "tx-sit-segmentation",
 	[NETIF_F_GSO_UDP_TUNNEL_BIT] =	 "tx-udp_tnl-segmentation",
 	[NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation",
+	[NETIF_F_GSO_PARTIAL_BIT] =	 "tx-gso-partial",
 
 	[NETIF_F_FCOE_CRC_BIT] =         "tx-checksum-fcoe-crc",
 	[NETIF_F_SCTP_CRC_BIT] =        "tx-checksum-sctp",
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index d04c2d1c8c87..4cc594cdaada 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3076,8 +3076,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 	struct sk_buff *frag_skb = head_skb;
 	unsigned int offset = doffset;
 	unsigned int tnl_hlen = skb_tnl_header_len(head_skb);
+	unsigned int partial_segs = 0;
 	unsigned int headroom;
-	unsigned int len;
+	unsigned int len = head_skb->len;
 	__be16 proto;
 	bool csum;
 	int sg = !!(features & NETIF_F_SG);
@@ -3094,6 +3095,15 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 
 	csum = !!can_checksum_protocol(features, proto);
 
+	/* GSO partial only requires that we trim off any excess that
+	 * doesn't fit into an MSS sized block, so take care of that
+	 * now.
+	 */
+	if (features & NETIF_F_GSO_PARTIAL) {
+		partial_segs = len / mss;
+		mss *= partial_segs;
+	}
+
 	headroom = skb_headroom(head_skb);
 	pos = skb_headlen(head_skb);
 
@@ -3281,6 +3291,23 @@ perform_csum_check:
 	 */
 	segs->prev = tail;
 
+	/* Update GSO info on first skb in partial sequence. */
+	if (partial_segs) {
+		int type = skb_shinfo(head_skb)->gso_type;
+
+		/* Update type to add partial and then remove dodgy if set */
+		type |= SKB_GSO_PARTIAL;
+		type &= ~SKB_GSO_DODGY;
+
+		/* Update GSO info and prepare to start updating headers on
+		 * our way back down the stack of protocols.
+		 */
+		skb_shinfo(segs)->gso_size = skb_shinfo(head_skb)->gso_size;
+		skb_shinfo(segs)->gso_segs = partial_segs;
+		skb_shinfo(segs)->gso_type = type;
+		SKB_GSO_CB(segs)->data_offset = skb_headroom(segs) + doffset;
+	}
+
 	/* Following permits correct backpressure, for protocols
 	 * using skb_set_owner_w().
 	 * Idea is to tranfert ownership from head_skb to last segment.
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 98fe04b99e01..22b03eb07740 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1200,7 +1200,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 	const struct net_offload *ops;
 	unsigned int offset = 0;
 	struct iphdr *iph;
-	int proto;
+	int proto, tot_len;
 	int nhoff;
 	int ihl;
 	int id;
@@ -1219,6 +1219,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_UDP_TUNNEL_CSUM |
 		       SKB_GSO_TCP_FIXEDID |
 		       SKB_GSO_TUNNEL_REMCSUM |
+		       SKB_GSO_PARTIAL |
 		       0)))
 		goto out;
 
@@ -1273,10 +1274,21 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 			if (skb->next)
 				iph->frag_off |= htons(IP_MF);
 			offset += skb->len - nhoff - ihl;
-		} else if (!fixedid) {
-			iph->id = htons(id++);
+			tot_len = skb->len - nhoff;
+		} else if (skb_is_gso(skb)) {
+			if (!fixedid) {
+				iph->id = htons(id);
+				id += skb_shinfo(skb)->gso_segs;
+			}
+			tot_len = skb_shinfo(skb)->gso_size +
+				  SKB_GSO_CB(skb)->data_offset +
+				  skb->head - (unsigned char *)iph;
+		} else {
+			if (!fixedid)
+				iph->id = htons(id++);
+			tot_len = skb->len - nhoff;
 		}
-		iph->tot_len = htons(skb->len - nhoff);
+		iph->tot_len = htons(tot_len);
 		ip_send_check(iph);
 		if (encap)
 			skb_reset_inner_headers(skb);
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 6376b0cdf693..20557f211408 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -36,7 +36,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_GRE |
 				  SKB_GSO_GRE_CSUM |
 				  SKB_GSO_IPIP |
-				  SKB_GSO_SIT)))
+				  SKB_GSO_SIT |
+				  SKB_GSO_PARTIAL)))
 		goto out;
 
 	if (!skb->encapsulation)
@@ -87,7 +88,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 	skb = segs;
 	do {
 		struct gre_base_hdr *greh;
-		__be32 *pcsum;
+		__sum16 *pcsum;
 
 		/* Set up inner headers if we are offloading inner checksum */
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
@@ -107,10 +108,25 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 			continue;
 
 		greh = (struct gre_base_hdr *)skb_transport_header(skb);
-		pcsum = (__be32 *)(greh + 1);
+		pcsum = (__sum16 *)(greh + 1);
+
+		if (skb_is_gso(skb)) {
+			unsigned int partial_adj;
+
+			/* Adjust checksum to account for the fact that
+			 * the partial checksum is based on actual size
+			 * whereas headers should be based on MSS size.
+			 */
+			partial_adj = skb->len + skb_headroom(skb) -
+				      SKB_GSO_CB(skb)->data_offset -
+				      skb_shinfo(skb)->gso_size;
+			*pcsum = ~csum_fold((__force __wsum)htonl(partial_adj));
+		} else {
+			*pcsum = 0;
+		}
 
-		*pcsum = 0;
-		*(__sum16 *)pcsum = gso_make_checksum(skb, 0);
+		*(pcsum + 1) = 0;
+		*pcsum = gso_make_checksum(skb, 0);
 	} while ((skb = skb->next));
 out:
 	return segs;
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index d1ffd55289bd..02737b607aa7 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -109,6 +109,12 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 		goto out;
 	}
 
+	/* GSO partial only requires splitting the frame into an MSS
+	 * multiple and possibly a remainder.  So update the mss now.
+	 */
+	if (features & NETIF_F_GSO_PARTIAL)
+		mss = skb->len - (skb->len % mss);
+
 	copy_destructor = gso_skb->destructor == tcp_wfree;
 	ooo_okay = gso_skb->ooo_okay;
 	/* All segments but the first should have ooo_okay cleared */
@@ -133,7 +139,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	newcheck = ~csum_fold((__force __wsum)((__force u32)th->check +
 					       (__force u32)delta));
 
-	do {
+	while (skb->next) {
 		th->fin = th->psh = 0;
 		th->check = newcheck;
 
@@ -153,7 +159,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 
 		th->seq = htonl(seq);
 		th->cwr = 0;
-	} while (skb->next);
+	}
 
 	/* Following permits TCP Small Queues to work well with GSO :
 	 * The callback to TCP stack will be called at the time last frag
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 0ed2dafb7cc4..454e9e70d460 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -51,8 +51,11 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	 * 16 bit length field due to the header being added outside of an
 	 * IP or IPv6 frame that was already limited to 64K - 1.
 	 */
-	partial = csum_sub(csum_unfold(uh->check),
-			   (__force __wsum)htonl(skb->len));
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL)
+		partial = (__force __wsum)uh->len;
+	else
+		partial = (__force __wsum)htonl(skb->len);
+	partial = csum_sub(csum_unfold(uh->check), partial);
 
 	/* setup inner skb. */
 	skb->encapsulation = 0;
@@ -101,7 +104,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	udp_offset = outer_hlen - tnl_hlen;
 	skb = segs;
 	do {
-		__be16 len;
+		unsigned int len;
 
 		if (remcsum)
 			skb->ip_summed = CHECKSUM_NONE;
@@ -119,14 +122,26 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 		skb_reset_mac_header(skb);
 		skb_set_network_header(skb, mac_len);
 		skb_set_transport_header(skb, udp_offset);
-		len = htons(skb->len - udp_offset);
+		len = skb->len - udp_offset;
 		uh = udp_hdr(skb);
-		uh->len = len;
+
+		/* If we are only performing partial GSO the inner header
+		 * will be using a length value equal to only one MSS sized
+		 * segment instead of the entire frame.
+		 */
+		if (skb_is_gso(skb)) {
+			uh->len = htons(skb_shinfo(skb)->gso_size +
+					SKB_GSO_CB(skb)->data_offset +
+					skb->head - (unsigned char *)uh);
+		} else {
+			uh->len = htons(len);
+		}
 
 		if (!need_csum)
 			continue;
 
-		uh->check = ~csum_fold(csum_add(partial, (__force __wsum)len));
+		uh->check = ~csum_fold(csum_add(partial,
+				       (__force __wsum)htonl(len)));
 
 		if (skb->encapsulation || !offload_csum) {
 			uh->check = gso_make_checksum(skb, ~uh->check);
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index e9479499f58c..ad3a6bd4a7f7 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -63,6 +63,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	int proto;
 	struct frag_hdr *fptr;
 	unsigned int unfrag_ip6hlen;
+	unsigned int payload_len;
 	u8 *prevhdr;
 	int offset = 0;
 	bool encap, udpfrag;
@@ -82,6 +83,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_UDP_TUNNEL_CSUM |
 		       SKB_GSO_TUNNEL_REMCSUM |
+		       SKB_GSO_PARTIAL |
 		       0)))
 		goto out;
 
@@ -118,7 +120,13 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 
 	for (skb = segs; skb; skb = skb->next) {
 		ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
-		ipv6h->payload_len = htons(skb->len - nhoff - sizeof(*ipv6h));
+		if (skb_is_gso(skb))
+			payload_len = skb_shinfo(skb)->gso_size +
+				      SKB_GSO_CB(skb)->data_offset +
+				      skb->head - (unsigned char *)(ipv6h + 1);
+		else
+			payload_len = skb->len - nhoff - sizeof(*ipv6h);
+		ipv6h->payload_len = htons(payload_len);
 		skb->network_header = (u8 *)ipv6h - skb->head;
 
 		if (udpfrag) {

[RFC PATCH 06/11] VXLAN: Add option to mangle IP IDs on inner headers when using TSO

[Alexander Duyck]

This patch adds support for a feature I am calling IP ID mangling.  It is
basically just another way of saying the IP IDs that are transmitted by the
tunnel may not match up with what would normally be expected.  Specifically
what will happen is in the case of TSO the IP IDs on the headers will be a
fixed value so a given TSO will repeat the same inner IP ID value gso_segs
number of times.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
---
 drivers/net/vxlan.c          |   16 ++++++++++++++++
 include/net/vxlan.h          |    1 +
 include/uapi/linux/if_link.h |    1 +
 3 files changed, 18 insertions(+)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 51cccddfe403..cc903ab832c2 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1783,6 +1783,10 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst,
 			type |= SKB_GSO_TUNNEL_REMCSUM;
 	}
 
+	if ((vxflags & VXLAN_F_TCP_FIXEDID) && skb_is_gso(skb) &&
+	    (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4))
+		type |= SKB_GSO_TCP_FIXEDID;
+
 	min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len
 			+ VXLAN_HLEN + iphdr_len
 			+ (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
@@ -2635,6 +2639,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
 	[IFLA_VXLAN_GBP]	= { .type = NLA_FLAG, },
 	[IFLA_VXLAN_GPE]	= { .type = NLA_FLAG, },
 	[IFLA_VXLAN_REMCSUM_NOPARTIAL]	= { .type = NLA_FLAG },
+	[IFLA_VXLAN_IPID_MANGLE]	= { .type = NLA_FLAG },
 };
 
 static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -3092,6 +3097,9 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 	if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL])
 		conf.flags |= VXLAN_F_REMCSUM_NOPARTIAL;
 
+	if (data[IFLA_VXLAN_IPID_MANGLE])
+		conf.flags |= VXLAN_F_TCP_FIXEDID;
+
 	err = vxlan_dev_configure(src_net, dev, &conf);
 	switch (err) {
 	case -ENODEV:
@@ -3154,6 +3162,10 @@ static size_t vxlan_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_RX */
 		nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_TX */
 		nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_RX */
+		nla_total_size(0) +	       /* IFLA_VXLAN_GBP */
+		nla_total_size(0) +	       /* IFLA_VXLAN_GPE */
+		nla_total_size(0) +	       /* IFLA_VXLAN_REMCSUM_NOPARTIAL */
+		nla_total_size(0) +	       /* IFLA_VXLAN_IPID_MANGLE */
 		0;
 }
 
@@ -3244,6 +3256,10 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_flag(skb, IFLA_VXLAN_REMCSUM_NOPARTIAL))
 		goto nla_put_failure;
 
+	if (vxlan->flags & VXLAN_F_TCP_FIXEDID &&
+	    nla_put_flag(skb, IFLA_VXLAN_IPID_MANGLE))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index dcc6f4057115..5c2dc9ecea59 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -265,6 +265,7 @@ struct vxlan_dev {
 #define VXLAN_F_REMCSUM_NOPARTIAL	0x1000
 #define VXLAN_F_COLLECT_METADATA	0x2000
 #define VXLAN_F_GPE			0x4000
+#define VXLAN_F_TCP_FIXEDID		0x8000
 
 /* Flags that are used in the receive path. These flags must match in
  * order for a socket to be shareable
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 9427f17d06d6..a3bc3f2a63d3 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -489,6 +489,7 @@ enum {
 	IFLA_VXLAN_COLLECT_METADATA,
 	IFLA_VXLAN_LABEL,
 	IFLA_VXLAN_GPE,
+	IFLA_VXLAN_IPID_MANGLE,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)

[RFC PATCH 07/11] GENEVE: Add option to mangle IP IDs on inner headers when using TSO

[Alexander Duyck]

This patch adds support for a feature I am calling IP ID mangling.  It is
basically just another way of saying the IP IDs that are transmitted by the
tunnel may not match up with what would normally be expected.  Specifically
what will happen is in the case of TSO the IP IDs on the headers will be a
fixed value so a given TSO will repeat the same inner IP ID value gso_segs
number of times.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
---
 drivers/net/geneve.c         |   24 ++++++++++++++++++++++--
 include/net/udp_tunnel.h     |    8 --------
 include/uapi/linux/if_link.h |    1 +
 3 files changed, 23 insertions(+), 10 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index bc168894bda3..6352223d80c3 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -80,6 +80,7 @@ struct geneve_dev {
 #define GENEVE_F_UDP_ZERO_CSUM_TX	BIT(0)
 #define GENEVE_F_UDP_ZERO_CSUM6_TX	BIT(1)
 #define GENEVE_F_UDP_ZERO_CSUM6_RX	BIT(2)
+#define GENEVE_F_TCP_FIXEDID		BIT(3)
 
 struct geneve_sock {
 	bool			collect_md;
@@ -702,9 +703,14 @@ static int geneve_build_skb(struct rtable *rt, struct sk_buff *skb,
 	int min_headroom;
 	int err;
 	bool udp_sum = !(flags & GENEVE_F_UDP_ZERO_CSUM_TX);
+	int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
 
 	skb_scrub_packet(skb, xnet);
 
+	if ((flags & GENEVE_F_TCP_FIXEDID) && skb_is_gso(skb) &&
+	    (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4))
+		type |= SKB_GSO_TCP_FIXEDID;
+
 	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
 			+ GENEVE_BASE_HLEN + opt_len + sizeof(struct iphdr);
 	err = skb_cow_head(skb, min_headroom);
@@ -713,7 +719,7 @@ static int geneve_build_skb(struct rtable *rt, struct sk_buff *skb,
 		goto free_rt;
 	}
 
-	skb = udp_tunnel_handle_offloads(skb, udp_sum);
+	skb = iptunnel_handle_offloads(skb, type);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
 		goto free_rt;
@@ -739,9 +745,14 @@ static int geneve6_build_skb(struct dst_entry *dst, struct sk_buff *skb,
 	int min_headroom;
 	int err;
 	bool udp_sum = !(flags & GENEVE_F_UDP_ZERO_CSUM6_TX);
+	int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
 
 	skb_scrub_packet(skb, xnet);
 
+	if ((flags & GENEVE_F_TCP_FIXEDID) && skb_is_gso(skb) &&
+	    (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4))
+		type |= SKB_GSO_TCP_FIXEDID;
+
 	min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len
 			+ GENEVE_BASE_HLEN + opt_len + sizeof(struct ipv6hdr);
 	err = skb_cow_head(skb, min_headroom);
@@ -750,7 +761,7 @@ static int geneve6_build_skb(struct dst_entry *dst, struct sk_buff *skb,
 		goto free_dst;
 	}
 
-	skb = udp_tunnel_handle_offloads(skb, udp_sum);
+	skb = iptunnel_handle_offloads(skb, type);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
 		goto free_dst;
@@ -1249,6 +1260,7 @@ static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = {
 	[IFLA_GENEVE_UDP_CSUM]		= { .type = NLA_U8 },
 	[IFLA_GENEVE_UDP_ZERO_CSUM6_TX]	= { .type = NLA_U8 },
 	[IFLA_GENEVE_UDP_ZERO_CSUM6_RX]	= { .type = NLA_U8 },
+	[IFLA_GENEVE_IPID_MANGLE]	= { .type = NLA_FLAG },
 };
 
 static int geneve_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -1436,6 +1448,9 @@ static int geneve_newlink(struct net *net, struct net_device *dev,
 	    nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX]))
 		flags |= GENEVE_F_UDP_ZERO_CSUM6_RX;
 
+	if (data[IFLA_GENEVE_IPID_MANGLE])
+		flags |= GENEVE_F_TCP_FIXEDID;
+
 	return geneve_configure(net, dev, &remote, vni, ttl, tos, label,
 				dst_port, metadata, flags);
 }
@@ -1460,6 +1475,7 @@ static size_t geneve_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_CSUM */
 		nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_TX */
 		nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_RX */
+		nla_total_size(0) +	 /* IFLA_GENEVE_IPID_MANGLE */
 		0;
 }
 
@@ -1505,6 +1521,10 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 		       !!(geneve->flags & GENEVE_F_UDP_ZERO_CSUM6_RX)))
 		goto nla_put_failure;
 
+	if ((geneve->flags & GENEVE_F_TCP_FIXEDID) &&
+	    nla_put_flag(skb, IFLA_GENEVE_IPID_MANGLE))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index b83114077cee..c44d04259665 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -98,14 +98,6 @@ struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family,
 				    __be16 flags, __be64 tunnel_id,
 				    int md_size);
 
-static inline struct sk_buff *udp_tunnel_handle_offloads(struct sk_buff *skb,
-							 bool udp_csum)
-{
-	int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
-
-	return iptunnel_handle_offloads(skb, type);
-}
-
 static inline void udp_tunnel_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	struct udphdr *uh;
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index a3bc3f2a63d3..38acf49c818b 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -513,6 +513,7 @@ enum {
 	IFLA_GENEVE_UDP_ZERO_CSUM6_TX,
 	IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
 	IFLA_GENEVE_LABEL,
+	IFLA_GENEVE_IPID_MANGLE,
 	__IFLA_GENEVE_MAX
 };
 #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)

[RFC PATCH 08/11] Documentation: Add documentation for TSO and GSO features

[Alexander Duyck]

This document is a starting point for defining the TSO and GSO features.
The whole thing is starting to get a bit messy so I wanted to make sure we
have notes somwhere to start describing what does and doesn't work.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
---
 Documentation/networking/segmentation-offloads.txt |  127 ++++++++++++++++++++
 1 file changed, 127 insertions(+)
 create mode 100644 Documentation/networking/segmentation-offloads.txt

diff --git a/Documentation/networking/segmentation-offloads.txt b/Documentation/networking/segmentation-offloads.txt
new file mode 100644
index 000000000000..b06dd9b65ab3
--- /dev/null
+++ b/Documentation/networking/segmentation-offloads.txt
@@ -0,0 +1,127 @@
+Segmentation Offloads in the Linux Networking Stack
+
+Introduction
+============
+
+This document describes a set of techniques in the Linux networking stack
+to take advantage of segmentation offload capabilities of various NICs.
+
+The following technologies are described:
+ * TCP Segmentation Offload - TSO
+ * UDP Fragmentation Offload - UFO
+ * IPIP, SIT, GRE, and UDP Tunnel Offloads
+ * Generic Segmentation Offload - GSO
+ * Generic Receive Offload - GRO
+ * Partial Generic Segmentation Offload - GSO_PARTIAL
+
+TCP Segmentation Offload
+========================
+
+TCP segmentation allows a device to segment a single frame into multiple
+frames with a data payload size specified in skb_shinfo()->gso_size.
+When TCP segmentation requested the bit for either SKB_GSO_TCP or
+SKB_GSO_TCP6 should be set in skb_shinfo()->gso_type and
+skb_shinfo()->gso_size should be set to a non-zero value.
+
+TCP segmentation is dependent on support for the use of partial checksum
+offload.  For this reason TSO is normally disabled if the Tx checksum
+offload for a given device is disabled.
+
+In order to support TCP segmentation offload it is necessary to populate
+the network and transport header offsets of the skbuff so that the device
+drivers will be able determine the offsets of the IP or IPv6 header and the
+TCP header.  In addition as CHECKSUM_PARTIAL is required csum_start should
+also point to the TCP header of the packet.
+
+For IPv4 segmentation we support one of two types in terms of the IP ID.
+The default behavior is to increment the IP ID with every segment.  If the
+GSO type SKB_GSO_TCP_FIXEDID is specified then we will not increment the IP
+ID and all segments will use the same IP ID.
+
+UDP Fragmentation Offload
+=========================
+
+UDP fragmentation offload allows a device to fragment an oversized UDP
+datagram into multiple IPv4 fragments.  Many of the requirements for UDP
+fragmentation offload are the same as TSO.  However the IPv4 ID for
+fragments should not increment as a single IPv4 datagram is fragmented.
+
+IPIP, SIT, GRE, UDP Tunnel, and Remote Checksum Offloads
+========================================================
+
+In addition to the offloads described above it is possible for a frame to
+contain additional headers such as an outer tunnel.  In order to account
+for such instances an additional set of segmentation offload types were
+introduced including SKB_GSO_IPIP, SKB_GSO_SIT, SKB_GSO_GRE, and
+SKB_GSO_UDP_TUNNEL.  These extra segmentation types are used to identify
+cases where there are more than just 1 set of headers.  For example in the
+case of IPIP and SIT we should have the network and transport headers moved
+from the standard list of headers to "inner" header offsets.
+
+Currently only two levels of headers are supported.  The convention is to
+refer to the tunnel headers as the outer headers, while the encapsulated
+data is normally referred to as the inner headers.  Below is the list of
+calls to access the given headers:
+
+IPIP/SIT Tunnel:
+		Outer			Inner
+MAC		skb_mac_header
+Network		skb_network_header	skb_inner_network_header
+Transport	skb_transport_header
+
+UDP/GRE Tunnel:
+		Outer			Inner
+MAC		skb_mac_header		skb_inner_mac_header
+Network		skb_network_header	skb_inner_network_header
+Transport	skb_transport_header	skb_inner_transport_header
+
+In addition to the above tunnel types there are also SKB_GSO_GRE_CSUM and
+SKB_GSO_UDP_TUNNEL_CSUM.  These two additional tunnel types reflect the
+fact that the outer header also requests to have a non-zero checksum
+included in the outer header.
+
+Finally there is SKB_GSO_REMCSUM which indicates that a given tunnel header
+has requested a remote checksum offload.  In this case the inner headers
+will be left with a partial checksum and only the outer header checksum
+will be computed.
+
+Generic Segmentation Offload
+============================
+
+Generic segmentation offload is a pure software offload that is meant to
+deal with cases where device drivers cannot perform the offloads described
+above.  What occurs in GSO is that a given skbuff will have its data broken
+out over multiple skbuffs that have been resized to match the MSS provided
+via skb_shinfo()->gso_size.
+
+Before enabling any hardware segmentation offload a corresponding software
+offload is required in GSO.  Otherwise it becomes possible for a frame to
+be re-routed between devices and end up being unable to be transmitted.
+
+Generic Receive Offload
+=======================
+
+Generic receive offload is the complement to GSO.  Ideally any frame
+assembled by GRO should be segmented to create an identical sequence of
+frames using GSO, and any sequence of frames segmented by GSO should be
+able to be reassembled back to the original by GRO.  The only exception to
+this is IPv4 ID in the case that the DF bit is set for a given IP header.
+If the value of the IPv4 ID is not sequentially incrementing it will be
+altered so that it is when a frame assembled via GRO is segmented via GSO.
+
+Partial Generic Segmentation Offload
+====================================
+
+Partial generic segmentation offload is a hybrid between TSO and GSO.  What
+it effectively does is take advantage of certain traits of TCP and tunnels
+so that instead of having to rewrite the packet headers for each segment
+only the inner-most transport header and possibly the outer-most network
+header need to be updated.  This allows devices that do not support tunnel
+offloads or tunnel offloads with checksum to still make use of segmentation.
+
+With the partial offload what occurs is that all headers excluding the
+inner transport header are updated such that they will contain the correct
+values for if the header was simply duplicated.  The one exception to this
+is the outer IPv4 ID field.  It is up to the device drivers to guarantee
+that the IPv4 ID field is incremented in the case that a given header does
+not have the DF bit set.

[RFC PATCH 09/11] i40e/i40evf: Add support for GSO partial with UDP_TUNNEL_CSUM and GRE_CSUM

[Alexander Duyck]

This patch makes it so that i40e and i40evf can use GSO_PARTIAL to support
segmentation for frames with checksums enabled in outer headers.  As a
result we can now send data over these types of tunnels at over 20Gb/s
versus the 12Gb/s that was previously possible on my system.

The advantage with the i40e parts is that this offload is mostly
transparent as the hardware still deals with the inner and/or outer IPv4
headers so the IP ID is still incrementing for both when this offload is
performed.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c     |    6 +++++-
 drivers/net/ethernet/intel/i40e/i40e_txrx.c     |    7 ++++++-
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c   |    7 ++++++-
 drivers/net/ethernet/intel/i40evf/i40evf_main.c |    6 +++++-
 4 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 07a70c4ac49f..6c095b07ce82 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -9119,17 +9119,21 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 				   NETIF_F_TSO_ECN		|
 				   NETIF_F_TSO6			|
 				   NETIF_F_GSO_GRE		|
+				   NETIF_F_GSO_GRE_CSUM		|
 				   NETIF_F_GSO_IPIP		|
 				   NETIF_F_GSO_SIT		|
 				   NETIF_F_GSO_UDP_TUNNEL	|
 				   NETIF_F_GSO_UDP_TUNNEL_CSUM	|
+				   NETIF_F_GSO_PARTIAL		|
 				   NETIF_F_SCTP_CRC		|
 				   NETIF_F_RXHASH		|
 				   NETIF_F_RXCSUM		|
 				   0;
 
 	if (!(pf->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE))
-		netdev->hw_enc_features ^= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+		netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+
+	netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
 
 	/* record features VLANs can make use of */
 	netdev->vlan_features |= netdev->hw_enc_features;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 6e44cf118843..ede4183468b9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2300,11 +2300,15 @@ static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss)
 	}
 
 	if (skb_shinfo(skb)->gso_type & (SKB_GSO_GRE |
+					 SKB_GSO_GRE_CSUM |
 					 SKB_GSO_IPIP |
 					 SKB_GSO_SIT |
 					 SKB_GSO_UDP_TUNNEL |
 					 SKB_GSO_UDP_TUNNEL_CSUM)) {
-		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM) {
+		if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) &&
+		    (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)) {
+			l4.udp->len = 0;
+
 			/* determine offset of outer transport header */
 			l4_offset = l4.hdr - skb->data;
 
@@ -2481,6 +2485,7 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 
 		/* indicate if we need to offload outer UDP header */
 		if ((*tx_flags & I40E_TX_FLAGS_TSO) &&
+		    !(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) &&
 		    (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM))
 			tunnel |= I40E_TXD_CTX_QW0_L4T_CS_MASK;
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index f101895ecf4a..6ce00547c13e 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1565,11 +1565,15 @@ static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss)
 	}
 
 	if (skb_shinfo(skb)->gso_type & (SKB_GSO_GRE |
+					 SKB_GSO_GRE_CSUM |
 					 SKB_GSO_IPIP |
 					 SKB_GSO_SIT |
 					 SKB_GSO_UDP_TUNNEL |
 					 SKB_GSO_UDP_TUNNEL_CSUM)) {
-		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM) {
+		if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) &&
+		    (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)) {
+			l4.udp->len = 0;
+
 			/* determine offset of outer transport header */
 			l4_offset = l4.hdr - skb->data;
 
@@ -1704,6 +1708,7 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 
 		/* indicate if we need to offload outer UDP header */
 		if ((*tx_flags & I40E_TX_FLAGS_TSO) &&
+		    !(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) &&
 		    (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM))
 			tunnel |= I40E_TXD_CTX_QW0_L4T_CS_MASK;
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 806da2686623..9c78c6d6afcb 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -2346,17 +2346,21 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
 				   NETIF_F_TSO_ECN		|
 				   NETIF_F_TSO6			|
 				   NETIF_F_GSO_GRE		|
+				   NETIF_F_GSO_GRE_CSUM		|
 				   NETIF_F_GSO_IPIP		|
 				   NETIF_F_GSO_SIT		|
 				   NETIF_F_GSO_UDP_TUNNEL	|
 				   NETIF_F_GSO_UDP_TUNNEL_CSUM	|
+				   NETIF_F_GSO_PARTIAL		|
 				   NETIF_F_SCTP_CRC		|
 				   NETIF_F_RXHASH		|
 				   NETIF_F_RXCSUM		|
 				   0;
 
 	if (!(adapter->flags & I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE))
-		netdev->hw_enc_features ^= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+		netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+
+	netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
 
 	/* record features VLANs can make use of */
 	netdev->vlan_features |= netdev->hw_enc_features;

[RFC PATCH 10/11] ixgbe/ixgbevf: Add support for GSO partial

[Alexander Duyck]

This patch adds support for partial GSO segmentation in the case of
encapsulated frames.  Specifically with this change the driver can perform
segmentation as long as the type is either SKB_GSO_TCP_FIXEDID or
SKB_GSO_TCPV6.  If neither of these gso types are specified then tunnel
segmentation is not supported and we will default back to GSO.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c     |  115 +++++++++++++++-----
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c |  122 ++++++++++++++++-----
 2 files changed, 180 insertions(+), 57 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index c6bd3ae5f986..57e083f6c8a9 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -7195,9 +7195,18 @@ static int ixgbe_tso(struct ixgbe_ring *tx_ring,
 		     struct ixgbe_tx_buffer *first,
 		     u8 *hdr_len)
 {
+	u32 vlan_macip_lens, type_tucmd, mss_l4len_idx;
 	struct sk_buff *skb = first->skb;
-	u32 vlan_macip_lens, type_tucmd;
-	u32 mss_l4len_idx, l4len;
+	union {
+		struct iphdr *v4;
+		struct ipv6hdr *v6;
+		unsigned char *hdr;
+	} ip;
+	union {
+		struct tcphdr *tcp;
+		unsigned char *hdr;
+	} l4;
+	u32 paylen, l4_offset;
 	int err;
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
@@ -7210,46 +7219,52 @@ static int ixgbe_tso(struct ixgbe_ring *tx_ring,
 	if (err < 0)
 		return err;
 
+	ip.hdr = skb_network_header(skb);
+	l4.hdr = skb_checksum_start(skb);
+
 	/* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
 	type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_TCP;
 
-	if (first->protocol == htons(ETH_P_IP)) {
-		struct iphdr *iph = ip_hdr(skb);
-		iph->tot_len = 0;
-		iph->check = 0;
-		tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr,
-							 iph->daddr, 0,
-							 IPPROTO_TCP,
-							 0);
+	/* initialize outer IP header fields */
+	if (ip.v4->version == 4) {
+		/* IP header will have to cancel out any data that
+		 * is not a part of the outer IP header
+		 */
+		ip.v4->check = csum_fold(csum_add(lco_csum(skb),
+						  csum_unfold(l4.tcp->check)));
 		type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4;
+
+		ip.v4->tot_len = 0;
 		first->tx_flags |= IXGBE_TX_FLAGS_TSO |
 				   IXGBE_TX_FLAGS_CSUM |
 				   IXGBE_TX_FLAGS_IPV4;
-	} else if (skb_is_gso_v6(skb)) {
-		ipv6_hdr(skb)->payload_len = 0;
-		tcp_hdr(skb)->check =
-		    ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
-				     &ipv6_hdr(skb)->daddr,
-				     0, IPPROTO_TCP, 0);
+	} else {
+		ip.v6->payload_len = 0;
 		first->tx_flags |= IXGBE_TX_FLAGS_TSO |
 				   IXGBE_TX_FLAGS_CSUM;
 	}
 
-	/* compute header lengths */
-	l4len = tcp_hdrlen(skb);
-	*hdr_len = skb_transport_offset(skb) + l4len;
+	/* determine offset of inner transport header */
+	l4_offset = l4.hdr - skb->data;
+
+	/* compute length of segmentation header */
+	*hdr_len = (l4.tcp->doff * 4) + l4_offset;
+
+	/* remove payload length from inner checksum */
+	paylen = skb->len - l4_offset;
+	csum_replace_by_diff(&l4.tcp->check, htonl(paylen));
 
 	/* update gso size and bytecount with header size */
 	first->gso_segs = skb_shinfo(skb)->gso_segs;
 	first->bytecount += (first->gso_segs - 1) * *hdr_len;
 
 	/* mss_l4len_id: use 0 as index for TSO */
-	mss_l4len_idx = l4len << IXGBE_ADVTXD_L4LEN_SHIFT;
+	mss_l4len_idx = (*hdr_len - l4_offset) << IXGBE_ADVTXD_L4LEN_SHIFT;
 	mss_l4len_idx |= skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT;
 
 	/* vlan_macip_lens: HEADLEN, MACLEN, VLAN tag */
-	vlan_macip_lens = skb_network_header_len(skb);
-	vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT;
+	vlan_macip_lens = l4.hdr - ip.hdr;
+	vlan_macip_lens |= (ip.hdr - skb->data) << IXGBE_ADVTXD_MACLEN_SHIFT;
 	vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK;
 
 	ixgbe_tx_ctxtdesc(tx_ring, vlan_macip_lens, 0, type_tucmd,
@@ -8906,17 +8921,49 @@ static void ixgbe_fwd_del(struct net_device *pdev, void *priv)
 	kfree(fwd_adapter);
 }
 
-#define IXGBE_MAX_TUNNEL_HDR_LEN 80
+#define IXGBE_MAX_MAC_HDR_LEN		127
+#define IXGBE_MAX_NETWORK_HDR_LEN	511
+#define IXGBE_GSO_PARTIAL_FEATURES (NETIF_F_TSO_FIXEDID | \
+				    NETIF_F_GSO_GRE | \
+				    NETIF_F_GSO_GRE_CSUM | \
+				    NETIF_F_GSO_IPIP | \
+				    NETIF_F_GSO_SIT | \
+				    NETIF_F_GSO_UDP_TUNNEL | \
+				    NETIF_F_GSO_UDP_TUNNEL_CSUM)
+
 static netdev_features_t
 ixgbe_features_check(struct sk_buff *skb, struct net_device *dev,
 		     netdev_features_t features)
 {
-	if (!skb->encapsulation)
-		return features;
-
-	if (unlikely(skb_inner_mac_header(skb) - skb_transport_header(skb) >
-		     IXGBE_MAX_TUNNEL_HDR_LEN))
-		return features & ~NETIF_F_CSUM_MASK;
+	unsigned int network_hdr_len, mac_hdr_len;
+
+	/* Make certain the headers can be described by a context descriptor */
+	mac_hdr_len = skb_network_header(skb) - skb->data;
+	network_hdr_len = skb_checksum_start(skb) - skb_network_header(skb);
+	if (unlikely((mac_hdr_len > IXGBE_MAX_MAC_HDR_LEN) ||
+		     (network_hdr_len >  IXGBE_MAX_NETWORK_HDR_LEN)))
+		return features & ~(NETIF_F_HW_CSUM |
+				    NETIF_F_SCTP_CRC |
+				    NETIF_F_HW_VLAN_CTAG_TX |
+				    NETIF_F_TSO |
+				    NETIF_F_TSO_FIXEDID |
+				    NETIF_F_TSO6);
+
+	/* We can only support a fixed IPv4 ID or IPv6 header for TSO
+	 * with tunnels.  So if we aren't using a tunnel, or we aren't
+	 * performing TSO with a fixed ID we must strip the partial
+	 * features.
+	 */
+	if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_GRE |
+					   SKB_GSO_GRE_CSUM |
+					   SKB_GSO_IPIP |
+					   SKB_GSO_SIT |
+					   SKB_GSO_UDP_TUNNEL |
+					   SKB_GSO_UDP_TUNNEL_CSUM)) ||
+	    !(skb_shinfo(skb)->gso_type & (SKB_GSO_TCP_FIXEDID |
+					   SKB_GSO_TCPV6)))
+		return features & ~(NETIF_F_GSO_PARTIAL |
+				    IXGBE_GSO_PARTIAL_FEATURES);
 
 	return features;
 }
@@ -9288,6 +9335,10 @@ skip_sriov:
 			   NETIF_F_HW_VLAN_CTAG_RX |
 			   NETIF_F_HW_VLAN_CTAG_FILTER;
 
+	netdev->gso_partial_features = IXGBE_GSO_PARTIAL_FEATURES;
+	netdev->features |= NETIF_F_GSO_PARTIAL |
+			    IXGBE_GSO_PARTIAL_FEATURES;
+
 	if (hw->mac.type >= ixgbe_mac_82599EB)
 		netdev->features |= NETIF_F_SCTP_CRC;
 
@@ -9307,7 +9358,11 @@ skip_sriov:
 				 NETIF_F_SCTP_CRC;
 
 	netdev->mpls_features |= NETIF_F_HW_CSUM;
-	netdev->hw_enc_features |= NETIF_F_HW_CSUM;
+	netdev->hw_enc_features |= NETIF_F_HW_CSUM |
+				   NETIF_F_TSO |
+				   NETIF_F_TSO6 |
+				   NETIF_F_GSO_PARTIAL |
+				   IXGBE_GSO_PARTIAL_FEATURES;
 
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 	netdev->priv_flags |= IFF_SUPP_NOFCS;
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 007cbe094990..9c8ff4f69463 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -3272,9 +3272,18 @@ static int ixgbevf_tso(struct ixgbevf_ring *tx_ring,
 		       struct ixgbevf_tx_buffer *first,
 		       u8 *hdr_len)
 {
+	u32 vlan_macip_lens, type_tucmd, mss_l4len_idx;
 	struct sk_buff *skb = first->skb;
-	u32 vlan_macip_lens, type_tucmd;
-	u32 mss_l4len_idx, l4len;
+	union {
+		struct iphdr *v4;
+		struct ipv6hdr *v6;
+		unsigned char *hdr;
+	} ip;
+	union {
+		struct tcphdr *tcp;
+		unsigned char *hdr;
+	} l4;
+	u32 paylen, l4_offset;
 	int err;
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
@@ -3287,49 +3296,53 @@ static int ixgbevf_tso(struct ixgbevf_ring *tx_ring,
 	if (err < 0)
 		return err;
 
+	ip.hdr = skb_network_header(skb);
+	l4.hdr = skb_checksum_start(skb);
+
 	/* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
 	type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_TCP;
 
-	if (first->protocol == htons(ETH_P_IP)) {
-		struct iphdr *iph = ip_hdr(skb);
-
-		iph->tot_len = 0;
-		iph->check = 0;
-		tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr,
-							 iph->daddr, 0,
-							 IPPROTO_TCP,
-							 0);
+	/* initialize outer IP header fields */
+	if (ip.v4->version == 4) {
+		/* IP header will have to cancel out any data that
+		 * is not a part of the outer IP header
+		 */
+		ip.v4->check = csum_fold(csum_add(lco_csum(skb),
+						  csum_unfold(l4.tcp->check)));
 		type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4;
+
+		ip.v4->tot_len = 0;
 		first->tx_flags |= IXGBE_TX_FLAGS_TSO |
 				   IXGBE_TX_FLAGS_CSUM |
 				   IXGBE_TX_FLAGS_IPV4;
-	} else if (skb_is_gso_v6(skb)) {
-		ipv6_hdr(skb)->payload_len = 0;
-		tcp_hdr(skb)->check =
-		    ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
-				     &ipv6_hdr(skb)->daddr,
-				     0, IPPROTO_TCP, 0);
+	} else {
+		ip.v6->payload_len = 0;
 		first->tx_flags |= IXGBE_TX_FLAGS_TSO |
 				   IXGBE_TX_FLAGS_CSUM;
 	}
 
-	/* compute header lengths */
-	l4len = tcp_hdrlen(skb);
-	*hdr_len += l4len;
-	*hdr_len = skb_transport_offset(skb) + l4len;
+	/* determine offset of inner transport header */
+	l4_offset = l4.hdr - skb->data;
+
+	/* compute length of segmentation header */
+	*hdr_len = (l4.tcp->doff * 4) + l4_offset;
+
+	/* remove payload length from inner checksum */
+	paylen = skb->len - l4_offset;
+	csum_replace_by_diff(&l4.tcp->check, htonl(paylen));
 
-	/* update GSO size and bytecount with header size */
+	/* update gso size and bytecount with header size */
 	first->gso_segs = skb_shinfo(skb)->gso_segs;
 	first->bytecount += (first->gso_segs - 1) * *hdr_len;
 
 	/* mss_l4len_id: use 1 as index for TSO */
-	mss_l4len_idx = l4len << IXGBE_ADVTXD_L4LEN_SHIFT;
+	mss_l4len_idx = (*hdr_len - l4_offset) << IXGBE_ADVTXD_L4LEN_SHIFT;
 	mss_l4len_idx |= skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT;
 	mss_l4len_idx |= 1 << IXGBE_ADVTXD_IDX_SHIFT;
 
 	/* vlan_macip_lens: HEADLEN, MACLEN, VLAN tag */
-	vlan_macip_lens = skb_network_header_len(skb);
-	vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT;
+	vlan_macip_lens = l4.hdr - ip.hdr;
+	vlan_macip_lens |= (ip.hdr - skb->data) << IXGBE_ADVTXD_MACLEN_SHIFT;
 	vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK;
 
 	ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens,
@@ -3870,6 +3883,53 @@ static struct rtnl_link_stats64 *ixgbevf_get_stats(struct net_device *netdev,
 	return stats;
 }
 
+#define IXGBEVF_MAX_MAC_HDR_LEN		127
+#define IXGBEVF_MAX_NETWORK_HDR_LEN	511
+#define IXGBEVF_GSO_PARTIAL_FEATURES (NETIF_F_TSO_FIXEDID | \
+				      NETIF_F_GSO_GRE | \
+				      NETIF_F_GSO_GRE_CSUM | \
+				      NETIF_F_GSO_IPIP | \
+				      NETIF_F_GSO_SIT | \
+				      NETIF_F_GSO_UDP_TUNNEL | \
+				      NETIF_F_GSO_UDP_TUNNEL_CSUM)
+
+static netdev_features_t
+ixgbevf_features_check(struct sk_buff *skb, struct net_device *dev,
+		       netdev_features_t features)
+{
+	unsigned int network_hdr_len, mac_hdr_len;
+
+	/* Make certain the headers can be described by a context descriptor */
+	mac_hdr_len = skb_network_header(skb) - skb->data;
+	network_hdr_len = skb_checksum_start(skb) - skb_network_header(skb);
+	if (unlikely((mac_hdr_len > IXGBEVF_MAX_MAC_HDR_LEN) ||
+		     (network_hdr_len >  IXGBEVF_MAX_NETWORK_HDR_LEN)))
+		return features & ~(NETIF_F_HW_CSUM |
+				    NETIF_F_SCTP_CRC |
+				    NETIF_F_HW_VLAN_CTAG_TX |
+				    NETIF_F_TSO |
+				    NETIF_F_TSO_FIXEDID |
+				    NETIF_F_TSO6);
+
+	/* We can only support a fixed IPv4 ID or IPv6 header for TSO
+	 * with tunnels.  So if we aren't using a tunnel, or we aren't
+	 * performing TSO with a fixed ID we must strip the partial
+	 * features.
+	 */
+	if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_GRE |
+					   SKB_GSO_GRE_CSUM |
+					   SKB_GSO_IPIP |
+					   SKB_GSO_SIT |
+					   SKB_GSO_UDP_TUNNEL |
+					   SKB_GSO_UDP_TUNNEL_CSUM)) ||
+	    !(skb_shinfo(skb)->gso_type & (SKB_GSO_TCP_FIXEDID |
+					   SKB_GSO_TCPV6)))
+		return features & ~(NETIF_F_GSO_PARTIAL |
+				    IXGBEVF_GSO_PARTIAL_FEATURES);
+
+	return features;
+}
+
 static const struct net_device_ops ixgbevf_netdev_ops = {
 	.ndo_open		= ixgbevf_open,
 	.ndo_stop		= ixgbevf_close,
@@ -3888,7 +3948,7 @@ static const struct net_device_ops ixgbevf_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= ixgbevf_netpoll,
 #endif
-	.ndo_features_check	= passthru_features_check,
+	.ndo_features_check	= ixgbevf_features_check,
 };
 
 static void ixgbevf_assign_netdev_ops(struct net_device *dev)
@@ -3999,6 +4059,10 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			      NETIF_F_HW_CSUM |
 			      NETIF_F_SCTP_CRC;
 
+	netdev->gso_partial_features = IXGBEVF_GSO_PARTIAL_FEATURES;
+	netdev->hw_features |= NETIF_F_GSO_PARTIAL |
+			       IXGBEVF_GSO_PARTIAL_FEATURES;
+
 	netdev->features = netdev->hw_features |
 			   NETIF_F_HW_VLAN_CTAG_TX |
 			   NETIF_F_HW_VLAN_CTAG_RX |
@@ -4011,7 +4075,11 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 				 NETIF_F_SCTP_CRC;
 
 	netdev->mpls_features |= NETIF_F_HW_CSUM;
-	netdev->hw_enc_features |= NETIF_F_HW_CSUM;
+	netdev->hw_enc_features |= NETIF_F_HW_CSUM |
+				   NETIF_F_TSO |
+				   NETIF_F_TSO6 |
+				   NETIF_F_GSO_PARTIAL |
+				   IXGBEVF_GSO_PARTIAL_FEATURES;
 
 	if (pci_using_dac)
 		netdev->features |= NETIF_F_HIGHDMA;

[RFC PATCH 11/11] igb/igbvf: Add support for GSO partial

[Alexander Duyck]

This patch adds support for partial GSO segmentation in the case of
encapsulated frames.  Specifically with this change the driver can perform
segmentation as long as the type is either SKB_GSO_TCP_FIXEDID or
SKB_GSO_TCPV6.  If neither of these gso types are specified then tunnel
segmentation is not supported and we will default back to GSO.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
---
 drivers/net/ethernet/intel/igb/igb_main.c |  119 +++++++++++++++----
 drivers/net/ethernet/intel/igbvf/netdev.c |  180 ++++++++++++++++++-----------
 2 files changed, 205 insertions(+), 94 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 8e96c35307fb..8204ebecd2a5 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2087,6 +2087,52 @@ static int igb_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	return ndo_dflt_fdb_add(ndm, tb, dev, addr, vid, flags);
 }
 
+#define IGB_MAX_MAC_HDR_LEN	127
+#define IGB_MAX_NETWORK_HDR_LEN	511
+#define IGB_GSO_PARTIAL_FEATURES (NETIF_F_TSO_FIXEDID | \
+				  NETIF_F_GSO_GRE | \
+				  NETIF_F_GSO_GRE_CSUM | \
+				  NETIF_F_GSO_IPIP | \
+				  NETIF_F_GSO_SIT | \
+				  NETIF_F_GSO_UDP_TUNNEL | \
+				  NETIF_F_GSO_UDP_TUNNEL_CSUM)
+static netdev_features_t
+igb_features_check(struct sk_buff *skb, struct net_device *dev,
+		   netdev_features_t features)
+{
+	unsigned int network_hdr_len, mac_hdr_len;
+
+	/* Make certain the headers can be described by a context descriptor */
+	mac_hdr_len = skb_network_header(skb) - skb->data;
+	network_hdr_len = skb_checksum_start(skb) - skb_network_header(skb);
+	if (unlikely((mac_hdr_len > IGB_MAX_MAC_HDR_LEN) ||
+		     (network_hdr_len >  IGB_MAX_NETWORK_HDR_LEN)))
+		return features & ~(NETIF_F_HW_CSUM |
+				    NETIF_F_SCTP_CRC |
+				    NETIF_F_HW_VLAN_CTAG_TX |
+				    NETIF_F_TSO |
+				    NETIF_F_TSO_FIXEDID |
+				    NETIF_F_TSO6);
+
+	/* We can only support a fixed IPv4 ID or IPv6 header for TSO
+	 * with tunnels.  So if we aren't using a tunnel, or we aren't
+	 * performing TSO with a fixed ID we must strip the partial
+	 * features.
+	 */
+	if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_GRE |
+					   SKB_GSO_GRE_CSUM |
+					   SKB_GSO_IPIP |
+					   SKB_GSO_SIT |
+					   SKB_GSO_UDP_TUNNEL |
+					   SKB_GSO_UDP_TUNNEL_CSUM)) ||
+	    !(skb_shinfo(skb)->gso_type & (SKB_GSO_TCP_FIXEDID |
+					   SKB_GSO_TCPV6)))
+		return features & ~(NETIF_F_GSO_PARTIAL |
+				    IGB_GSO_PARTIAL_FEATURES);
+
+	return features;
+}
+
 static const struct net_device_ops igb_netdev_ops = {
 	.ndo_open		= igb_open,
 	.ndo_stop		= igb_close,
@@ -2111,7 +2157,7 @@ static const struct net_device_ops igb_netdev_ops = {
 	.ndo_fix_features	= igb_fix_features,
 	.ndo_set_features	= igb_set_features,
 	.ndo_fdb_add		= igb_ndo_fdb_add,
-	.ndo_features_check	= passthru_features_check,
+	.ndo_features_check	= igb_features_check,
 };
 
 /**
@@ -2384,6 +2430,9 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (hw->mac.type >= e1000_82576)
 		netdev->features |= NETIF_F_SCTP_CRC;
 
+	netdev->gso_partial_features = IGB_GSO_PARTIAL_FEATURES;
+	netdev->features |= NETIF_F_GSO_PARTIAL | IGB_GSO_PARTIAL_FEATURES;
+
 	/* copy netdev features into list of user selectable features */
 	netdev->hw_features |= netdev->features;
 	netdev->hw_features |= NETIF_F_RXALL;
@@ -2401,14 +2450,16 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 				 NETIF_F_SCTP_CRC;
 
 	netdev->mpls_features |= NETIF_F_HW_CSUM;
-	netdev->hw_enc_features |= NETIF_F_HW_CSUM;
+	netdev->hw_enc_features |= NETIF_F_HW_CSUM |
+				   NETIF_F_TSO |
+				   NETIF_F_TSO6 |
+				   NETIF_F_GSO_PARTIAL |
+				   IGB_GSO_PARTIAL_FEATURES;
 
 	netdev->priv_flags |= IFF_SUPP_NOFCS;
 
-	if (pci_using_dac) {
+	if (pci_using_dac)
 		netdev->features |= NETIF_F_HIGHDMA;
-		netdev->vlan_features |= NETIF_F_HIGHDMA;
-	}
 
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 
@@ -4842,9 +4893,18 @@ static int igb_tso(struct igb_ring *tx_ring,
 		   struct igb_tx_buffer *first,
 		   u8 *hdr_len)
 {
+	u32 vlan_macip_lens, type_tucmd, mss_l4len_idx;
 	struct sk_buff *skb = first->skb;
-	u32 vlan_macip_lens, type_tucmd;
-	u32 mss_l4len_idx, l4len;
+	union {
+		struct iphdr *v4;
+		struct ipv6hdr *v6;
+		unsigned char *hdr;
+	} ip;
+	union {
+		struct tcphdr *tcp;
+		unsigned char *hdr;
+	} l4;
+	u32 paylen, l4_offset;
 	int err;
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
@@ -4857,45 +4917,52 @@ static int igb_tso(struct igb_ring *tx_ring,
 	if (err < 0)
 		return err;
 
+	ip.hdr = skb_network_header(skb);
+	l4.hdr = skb_checksum_start(skb);
+
 	/* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
 	type_tucmd = E1000_ADVTXD_TUCMD_L4T_TCP;
 
-	if (first->protocol == htons(ETH_P_IP)) {
-		struct iphdr *iph = ip_hdr(skb);
-		iph->tot_len = 0;
-		iph->check = 0;
-		tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr,
-							 iph->daddr, 0,
-							 IPPROTO_TCP,
-							 0);
+	/* initialize outer IP header fields */
+	if (ip.v4->version == 4) {
+		/* IP header will have to cancel out any data that
+		 * is not a part of the outer IP header
+		 */
+		ip.v4->check = csum_fold(csum_add(lco_csum(skb),
+						  csum_unfold(l4.tcp->check)));
 		type_tucmd |= E1000_ADVTXD_TUCMD_IPV4;
+
+		ip.v4->tot_len = 0;
 		first->tx_flags |= IGB_TX_FLAGS_TSO |
 				   IGB_TX_FLAGS_CSUM |
 				   IGB_TX_FLAGS_IPV4;
-	} else if (skb_is_gso_v6(skb)) {
-		ipv6_hdr(skb)->payload_len = 0;
-		tcp_hdr(skb)->check = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
-						       &ipv6_hdr(skb)->daddr,
-						       0, IPPROTO_TCP, 0);
+	} else {
+		ip.v6->payload_len = 0;
 		first->tx_flags |= IGB_TX_FLAGS_TSO |
 				   IGB_TX_FLAGS_CSUM;
 	}
 
-	/* compute header lengths */
-	l4len = tcp_hdrlen(skb);
-	*hdr_len = skb_transport_offset(skb) + l4len;
+	/* determine offset of inner transport header */
+	l4_offset = l4.hdr - skb->data;
+
+	/* compute length of segmentation header */
+	*hdr_len = (l4.tcp->doff * 4) + l4_offset;
+
+	/* remove payload length from inner checksum */
+	paylen = skb->len - l4_offset;
+	csum_replace_by_diff(&l4.tcp->check, htonl(paylen));
 
 	/* update gso size and bytecount with header size */
 	first->gso_segs = skb_shinfo(skb)->gso_segs;
 	first->bytecount += (first->gso_segs - 1) * *hdr_len;
 
 	/* MSS L4LEN IDX */
-	mss_l4len_idx = l4len << E1000_ADVTXD_L4LEN_SHIFT;
+	mss_l4len_idx = (*hdr_len - l4_offset) << E1000_ADVTXD_L4LEN_SHIFT;
 	mss_l4len_idx |= skb_shinfo(skb)->gso_size << E1000_ADVTXD_MSS_SHIFT;
 
 	/* VLAN MACLEN IPLEN */
-	vlan_macip_lens = skb_network_header_len(skb);
-	vlan_macip_lens |= skb_network_offset(skb) << E1000_ADVTXD_MACLEN_SHIFT;
+	vlan_macip_lens = l4.hdr - ip.hdr;
+	vlan_macip_lens |= (ip.hdr - skb->data) << E1000_ADVTXD_MACLEN_SHIFT;
 	vlan_macip_lens |= first->tx_flags & IGB_TX_FLAGS_VLAN_MASK;
 
 	igb_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, mss_l4len_idx);
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index c12442252adb..287fb6ca7670 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -1933,83 +1933,74 @@ static void igbvf_tx_ctxtdesc(struct igbvf_ring *tx_ring, u32 vlan_macip_lens,
 	buffer_info->dma = 0;
 }
 
-static int igbvf_tso(struct igbvf_adapter *adapter,
-		     struct igbvf_ring *tx_ring,
-		     struct sk_buff *skb, u32 tx_flags, u8 *hdr_len,
-		     __be16 protocol)
-{
-	struct e1000_adv_tx_context_desc *context_desc;
-	struct igbvf_buffer *buffer_info;
-	u32 info = 0, tu_cmd = 0;
-	u32 mss_l4len_idx, l4len;
-	unsigned int i;
+static int igbvf_tso(struct igbvf_ring *tx_ring,
+		     struct sk_buff *skb, u32 tx_flags, u8 *hdr_len)
+{
+	u32 vlan_macip_lens, type_tucmd, mss_l4len_idx;
+	union {
+		struct iphdr *v4;
+		struct ipv6hdr *v6;
+		unsigned char *hdr;
+	} ip;
+	union {
+		struct tcphdr *tcp;
+		unsigned char *hdr;
+	} l4;
+	u32 paylen, l4_offset;
 	int err;
 
-	*hdr_len = 0;
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return 0;
+
+	if (!skb_is_gso(skb))
+		return 0;
 
 	err = skb_cow_head(skb, 0);
-	if (err < 0) {
-		dev_err(&adapter->pdev->dev, "igbvf_tso returning an error\n");
+	if (err < 0)
 		return err;
-	}
 
-	l4len = tcp_hdrlen(skb);
-	*hdr_len += l4len;
-
-	if (protocol == htons(ETH_P_IP)) {
-		struct iphdr *iph = ip_hdr(skb);
-
-		iph->tot_len = 0;
-		iph->check = 0;
-		tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr,
-							 iph->daddr, 0,
-							 IPPROTO_TCP,
-							 0);
-	} else if (skb_is_gso_v6(skb)) {
-		ipv6_hdr(skb)->payload_len = 0;
-		tcp_hdr(skb)->check = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
-						       &ipv6_hdr(skb)->daddr,
-						       0, IPPROTO_TCP, 0);
-	}
+	ip.hdr = skb_network_header(skb);
+	l4.hdr = skb_checksum_start(skb);
 
-	i = tx_ring->next_to_use;
+	/* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
+	type_tucmd = E1000_ADVTXD_TUCMD_L4T_TCP;
 
-	buffer_info = &tx_ring->buffer_info[i];
-	context_desc = IGBVF_TX_CTXTDESC_ADV(*tx_ring, i);
-	/* VLAN MACLEN IPLEN */
-	if (tx_flags & IGBVF_TX_FLAGS_VLAN)
-		info |= (tx_flags & IGBVF_TX_FLAGS_VLAN_MASK);
-	info |= (skb_network_offset(skb) << E1000_ADVTXD_MACLEN_SHIFT);
-	*hdr_len += skb_network_offset(skb);
-	info |= (skb_transport_header(skb) - skb_network_header(skb));
-	*hdr_len += (skb_transport_header(skb) - skb_network_header(skb));
-	context_desc->vlan_macip_lens = cpu_to_le32(info);
+	/* initialize outer IP header fields */
+	if (ip.v4->version == 4) {
+		/* IP header will have to cancel out any data that
+		 * is not a part of the outer IP header
+		 */
+		ip.v4->check = csum_fold(csum_add(lco_csum(skb),
+						  csum_unfold(l4.tcp->check)));
+		type_tucmd |= E1000_ADVTXD_TUCMD_IPV4;
 
-	/* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
-	tu_cmd |= (E1000_TXD_CMD_DEXT | E1000_ADVTXD_DTYP_CTXT);
+		ip.v4->tot_len = 0;
+	} else {
+		ip.v6->payload_len = 0;
+	}
 
-	if (protocol == htons(ETH_P_IP))
-		tu_cmd |= E1000_ADVTXD_TUCMD_IPV4;
-	tu_cmd |= E1000_ADVTXD_TUCMD_L4T_TCP;
+	/* determine offset of inner transport header */
+	l4_offset = l4.hdr - skb->data;
 
-	context_desc->type_tucmd_mlhl = cpu_to_le32(tu_cmd);
+	/* compute length of segmentation header */
+	*hdr_len = (l4.tcp->doff * 4) + l4_offset;
 
-	/* MSS L4LEN IDX */
-	mss_l4len_idx = (skb_shinfo(skb)->gso_size << E1000_ADVTXD_MSS_SHIFT);
-	mss_l4len_idx |= (l4len << E1000_ADVTXD_L4LEN_SHIFT);
+	/* remove payload length from inner checksum */
+	paylen = skb->len - l4_offset;
+	csum_replace_by_diff(&l4.tcp->check, htonl(paylen));
 
-	context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx);
-	context_desc->seqnum_seed = 0;
+	/* MSS L4LEN IDX */
+	mss_l4len_idx = (*hdr_len - l4_offset) << E1000_ADVTXD_L4LEN_SHIFT;
+	mss_l4len_idx |= skb_shinfo(skb)->gso_size << E1000_ADVTXD_MSS_SHIFT;
 
-	buffer_info->time_stamp = jiffies;
-	buffer_info->dma = 0;
-	i++;
-	if (i == tx_ring->count)
-		i = 0;
+	/* VLAN MACLEN IPLEN */
+	vlan_macip_lens = l4.hdr - ip.hdr;
+	vlan_macip_lens |= (ip.hdr - skb->data) << E1000_ADVTXD_MACLEN_SHIFT;
+	vlan_macip_lens |= tx_flags & IGBVF_TX_FLAGS_VLAN_MASK;
 
-	tx_ring->next_to_use = i;
+	igbvf_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, mss_l4len_idx);
 
-	return true;
+	return 1;
 }
 
 static inline bool igbvf_ipv6_csum_is_sctp(struct sk_buff *skb)
@@ -2271,8 +2262,7 @@ static netdev_tx_t igbvf_xmit_frame_ring_adv(struct sk_buff *skb,
 
 	first = tx_ring->next_to_use;
 
-	tso = skb_is_gso(skb) ?
-		igbvf_tso(adapter, tx_ring, skb, tx_flags, &hdr_len, protocol) : 0;
+	tso = igbvf_tso(tx_ring, skb, tx_flags, &hdr_len);
 	if (unlikely(tso < 0)) {
 		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
@@ -2615,6 +2605,52 @@ static int igbvf_set_features(struct net_device *netdev,
 	return 0;
 }
 
+#define IGBVF_MAX_MAC_HDR_LEN		127
+#define IGBVF_MAX_NETWORK_HDR_LEN	511
+#define IGBVF_GSO_PARTIAL_FEATURES (NETIF_F_TSO_FIXEDID | \
+				    NETIF_F_GSO_GRE | \
+				    NETIF_F_GSO_GRE_CSUM | \
+				    NETIF_F_GSO_IPIP | \
+				    NETIF_F_GSO_SIT | \
+				    NETIF_F_GSO_UDP_TUNNEL | \
+				    NETIF_F_GSO_UDP_TUNNEL_CSUM)
+static netdev_features_t
+igbvf_features_check(struct sk_buff *skb, struct net_device *dev,
+		     netdev_features_t features)
+{
+	unsigned int network_hdr_len, mac_hdr_len;
+
+	/* Make certain the headers can be described by a context descriptor */
+	mac_hdr_len = skb_network_header(skb) - skb->data;
+	network_hdr_len = skb_checksum_start(skb) - skb_network_header(skb);
+	if (unlikely((mac_hdr_len > IGBVF_MAX_MAC_HDR_LEN) ||
+		     (network_hdr_len >  IGBVF_MAX_NETWORK_HDR_LEN)))
+		return features & ~(NETIF_F_HW_CSUM |
+				    NETIF_F_SCTP_CRC |
+				    NETIF_F_HW_VLAN_CTAG_TX |
+				    NETIF_F_TSO |
+				    NETIF_F_TSO_FIXEDID |
+				    NETIF_F_TSO6);
+
+	/* We can only support a fixed IPv4 ID or IPv6 header for TSO
+	 * with tunnels.  So if we aren't using a tunnel, or we aren't
+	 * performing TSO with a fixed ID we must strip the partial
+	 * features.
+	 */
+	if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_GRE |
+					   SKB_GSO_GRE_CSUM |
+					   SKB_GSO_IPIP |
+					   SKB_GSO_SIT |
+					   SKB_GSO_UDP_TUNNEL |
+					   SKB_GSO_UDP_TUNNEL_CSUM)) ||
+	    !(skb_shinfo(skb)->gso_type & (SKB_GSO_TCP_FIXEDID |
+					   SKB_GSO_TCPV6)))
+		return features & ~(NETIF_F_GSO_PARTIAL |
+				    IGBVF_GSO_PARTIAL_FEATURES);
+
+	return features;
+}
+
 static const struct net_device_ops igbvf_netdev_ops = {
 	.ndo_open		= igbvf_open,
 	.ndo_stop		= igbvf_close,
@@ -2631,7 +2667,7 @@ static const struct net_device_ops igbvf_netdev_ops = {
 	.ndo_poll_controller	= igbvf_netpoll,
 #endif
 	.ndo_set_features	= igbvf_set_features,
-	.ndo_features_check	= passthru_features_check,
+	.ndo_features_check	= igbvf_features_check,
 };
 
 /**
@@ -2739,14 +2775,15 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			      NETIF_F_HW_CSUM |
 			      NETIF_F_SCTP_CRC;
 
+	netdev->gso_partial_features = IGBVF_GSO_PARTIAL_FEATURES;
+	netdev->hw_features |= NETIF_F_GSO_PARTIAL |
+			       IGBVF_GSO_PARTIAL_FEATURES;
+
 	netdev->features = netdev->hw_features |
 			   NETIF_F_HW_VLAN_CTAG_TX |
 			   NETIF_F_HW_VLAN_CTAG_RX |
 			   NETIF_F_HW_VLAN_CTAG_FILTER;
 
-	if (pci_using_dac)
-		netdev->features |= NETIF_F_HIGHDMA;
-
 	netdev->vlan_features |= NETIF_F_SG |
 				 NETIF_F_TSO |
 				 NETIF_F_TSO6 |
@@ -2754,7 +2791,14 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 				 NETIF_F_SCTP_CRC;
 
 	netdev->mpls_features |= NETIF_F_HW_CSUM;
-	netdev->hw_enc_features |= NETIF_F_HW_CSUM;
+	netdev->hw_enc_features |= NETIF_F_HW_CSUM |
+				   NETIF_F_TSO |
+				   NETIF_F_TSO6 |
+				   NETIF_F_GSO_PARTIAL |
+				   IGBVF_GSO_PARTIAL_FEATURES;
+
+	if (pci_using_dac)
+		netdev->features |= NETIF_F_HIGHDMA;
 
 	/*reset the controller to put the device in a known good state */
 	err = hw->mac.ops.reset_hw(hw);

Re: [RFC PATCH 07/11] GENEVE: Add option to mangle IP IDs on inner headers when using TSO

[Jesse Gross]

On Thu, Apr 7, 2016 at 7:32 PM, Alexander Duyck <aduyck@mirantis.com> wrote:
> This patch adds support for a feature I am calling IP ID mangling.  It is
> basically just another way of saying the IP IDs that are transmitted by the
> tunnel may not match up with what would normally be expected.  Specifically
> what will happen is in the case of TSO the IP IDs on the headers will be a
> fixed value so a given TSO will repeat the same inner IP ID value gso_segs
> number of times.
>
> Signed-off-by: Alexander Duyck <aduyck@mirantis.com>

If I'm understanding this correctly, enabling IP ID mangling will help
performance on ixgbe since it will allow it to do GSO partial instead
of plain GSO but it will hurt performance on i40e since it will drop
from TSO to plain GSO.

Assuming that's right, it seems like it will make it hard to chose the
right setting without knowledge of which hardware is in use. I guess
what we really want is "I care about nicely incrementing IP IDs" vs.
"I don't care as long as the DF bit is set". That second case is
really what this flag is trying to say but it seems like it is
enforcing too much in the i40e case - I don't think anyone wants to go
out of their way to make IP IDs jump around if incrementing is faster.

Re: [RFC PATCH 07/11] GENEVE: Add option to mangle IP IDs on inner headers when using TSO

[Alexander Duyck]

On Thu, Apr 7, 2016 at 4:22 PM, Jesse Gross <jesse@kernel.org> wrote:
> On Thu, Apr 7, 2016 at 7:32 PM, Alexander Duyck <aduyck@mirantis.com> wrote:
>> This patch adds support for a feature I am calling IP ID mangling.  It is
>> basically just another way of saying the IP IDs that are transmitted by the
>> tunnel may not match up with what would normally be expected.  Specifically
>> what will happen is in the case of TSO the IP IDs on the headers will be a
>> fixed value so a given TSO will repeat the same inner IP ID value gso_segs
>> number of times.
>>
>> Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
>
> If I'm understanding this correctly, enabling IP ID mangling will help
> performance on ixgbe since it will allow it to do GSO partial instead
> of plain GSO but it will hurt performance on i40e since it will drop
> from TSO to plain GSO.

Right.  However the option is currently defaulted to off, and can be
enabled per tunnel endpoint.  So if you had an ixgbe to i40e link you
could enable it on the end with the ixgbe and you should see good
performance in both directions.

> Assuming that's right, it seems like it will make it hard to chose the
> right setting without knowledge of which hardware is in use. I guess
> what we really want is "I care about nicely incrementing IP IDs" vs.
> "I don't care as long as the DF bit is set". That second case is
> really what this flag is trying to say but it seems like it is
> enforcing too much in the i40e case - I don't think anyone wants to go
> out of their way to make IP IDs jump around if incrementing is faster.

Right.  The problem is trying to sort out all the GRO/GSO bits.  I was
probably being a bit too conservative after the last few iterations
for the GRO fixes.

Just a thought.  What if I replaced NETIF_F_TSO_FIXEDID with something
that meant we could mange the IP ID like a NETIF_F_TSO_IPID_MANGLE
(advice for better name welcome).  Instead of the feature flag meaning
we are going to transmit packets with a fixed ID it would mean we
don't care about the ID and are free to mangle it as we see fit.  The
GSO type can retain the same meaning as far as that requiring the same
ID for all, but the feature would mean we will take fixed and convert
it to incrementing, or incrementing and convert it to fixed.

- Alex

[patch net-next 0/5] mlxsw: small driver update

[Jiri Pirko]

From: Jiri Pirko <jiri@mellanox.com>

Cosmetics, in preparation to sharedbuffer patchset.

Jiri Pirko (5):
  mlxsw: Move devlink port registration into common core code
  mlxsw: Pass mlxsw_core as a param of mlxsw_core_skb_transmit*
  mlxsw: Do not pass around driver_priv directly
  mlxsw: reg: Share direction enum between SBPR, SBCM, SBPM
  mlxsw: reg: Fix SBPM register name

 drivers/net/ethernet/mellanox/mlxsw/core.c         | 56 ++++++++++++++--------
 drivers/net/ethernet/mellanox/mlxsw/core.h         | 26 +++++++---
 drivers/net/ethernet/mellanox/mlxsw/reg.h          | 27 ++++-------
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     | 52 +++++++++-----------
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  3 +-
 .../net/ethernet/mellanox/mlxsw/spectrum_buffers.c | 20 ++++----
 drivers/net/ethernet/mellanox/mlxsw/switchx2.c     | 42 +++++++---------
 7 files changed, 114 insertions(+), 112 deletions(-)

-- 
2.5.5

[patch net-next 1/5] mlxsw: Move devlink port registration into common core code

[Jiri Pirko]

From: Jiri Pirko <jiri@mellanox.com>

Remove devlink port reg/unreg from spectrum and switchx2 code and rather
do the common work in core. That also ensures code separation where
devlink is only used in core.c.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlxsw/core.c     | 22 ++++++++++++++++++
 drivers/net/ethernet/mellanox/mlxsw/core.h     | 10 +++++++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 31 +++++++++-----------------
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h |  3 +--
 drivers/net/ethernet/mellanox/mlxsw/switchx2.c | 30 +++++++++----------------
 5 files changed, 55 insertions(+), 41 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index f69f628..004fb8b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1358,6 +1358,28 @@ void mlxsw_core_lag_mapping_clear(struct mlxsw_core *mlxsw_core,
 }
 EXPORT_SYMBOL(mlxsw_core_lag_mapping_clear);
 
+int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core,
+			 struct mlxsw_core_port *mlxsw_core_port, u8 local_port,
+			 struct net_device *dev, bool split, u32 split_group)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_core);
+	struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port;
+
+	if (split)
+		devlink_port_split_set(devlink_port, split_group);
+	devlink_port_type_eth_set(devlink_port, dev);
+	return devlink_port_register(devlink, devlink_port, local_port);
+}
+EXPORT_SYMBOL(mlxsw_core_port_init);
+
+void mlxsw_core_port_fini(struct mlxsw_core_port *mlxsw_core_port)
+{
+	struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port;
+
+	devlink_port_unregister(devlink_port);
+}
+EXPORT_SYMBOL(mlxsw_core_port_fini);
+
 int mlxsw_cmd_exec(struct mlxsw_core *mlxsw_core, u16 opcode, u8 opcode_mod,
 		   u32 in_mod, bool out_mbox_direct,
 		   char *in_mbox, size_t in_mbox_size,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index c73d1c0..06631a0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -43,6 +43,7 @@
 #include <linux/gfp.h>
 #include <linux/types.h>
 #include <linux/skbuff.h>
+#include <net/devlink.h>
 
 #include "trap.h"
 #include "reg.h"
@@ -131,6 +132,15 @@ u8 mlxsw_core_lag_mapping_get(struct mlxsw_core *mlxsw_core,
 void mlxsw_core_lag_mapping_clear(struct mlxsw_core *mlxsw_core,
 				  u16 lag_id, u8 local_port);
 
+struct mlxsw_core_port {
+	struct devlink_port devlink_port;
+};
+
+int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core,
+			 struct mlxsw_core_port *mlxsw_core_port, u8 local_port,
+			 struct net_device *dev, bool split, u32 split_group);
+void mlxsw_core_port_fini(struct mlxsw_core_port *mlxsw_core_port);
+
 #define MLXSW_CONFIG_PROFILE_SWID_COUNT 8
 
 struct mlxsw_swid_config {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 507263a..3216f2b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -50,7 +50,6 @@
 #include <linux/bitops.h>
 #include <linux/list.h>
 #include <linux/dcbnl.h>
-#include <net/devlink.h>
 #include <net/switchdev.h>
 #include <generated/utsrelease.h>
 
@@ -1685,9 +1684,7 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port)
 static int __mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				  bool split, u8 module, u8 width)
 {
-	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
 	struct mlxsw_sp_port *mlxsw_sp_port;
-	struct devlink_port *devlink_port;
 	struct net_device *dev;
 	size_t bytes;
 	int err;
@@ -1740,16 +1737,6 @@ static int __mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 	 */
 	dev->hard_header_len += MLXSW_TXHDR_LEN;
 
-	devlink_port = &mlxsw_sp_port->devlink_port;
-	if (mlxsw_sp_port->split)
-		devlink_port_split_set(devlink_port, module);
-	err = devlink_port_register(devlink, devlink_port, local_port);
-	if (err) {
-		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to register devlink port\n",
-			mlxsw_sp_port->local_port);
-		goto err_devlink_port_register;
-	}
-
 	err = mlxsw_sp_port_system_port_mapping_set(mlxsw_sp_port);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set system port mapping\n",
@@ -1812,7 +1799,14 @@ static int __mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 		goto err_register_netdev;
 	}
 
-	devlink_port_type_eth_set(devlink_port, dev);
+	err = mlxsw_core_port_init(mlxsw_sp->core, &mlxsw_sp_port->core_port,
+				   mlxsw_sp_port->local_port, dev,
+				   mlxsw_sp_port->split, module);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to init core port\n",
+			mlxsw_sp_port->local_port);
+		goto err_core_port_init;
+	}
 
 	err = mlxsw_sp_port_vlan_init(mlxsw_sp_port);
 	if (err)
@@ -1822,6 +1816,8 @@ static int __mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 	return 0;
 
 err_port_vlan_init:
+	mlxsw_core_port_fini(&mlxsw_sp_port->core_port);
+err_core_port_init:
 	unregister_netdev(dev);
 err_register_netdev:
 err_port_dcb_init:
@@ -1832,8 +1828,6 @@ err_port_mtu_set:
 err_port_speed_by_width_set:
 err_port_swid_set:
 err_port_system_port_mapping_set:
-	devlink_port_unregister(&mlxsw_sp_port->devlink_port);
-err_devlink_port_register:
 err_dev_addr_init:
 	free_percpu(mlxsw_sp_port->pcpu_stats);
 err_alloc_stats:
@@ -1887,16 +1881,13 @@ static void mlxsw_sp_port_vports_fini(struct mlxsw_sp_port *mlxsw_sp_port)
 static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp->ports[local_port];
-	struct devlink_port *devlink_port;
 
 	if (!mlxsw_sp_port)
 		return;
 	mlxsw_sp->ports[local_port] = NULL;
-	devlink_port = &mlxsw_sp_port->devlink_port;
-	devlink_port_type_clear(devlink_port);
+	mlxsw_core_port_fini(&mlxsw_sp_port->core_port);
 	unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */
 	mlxsw_sp_port_dcb_fini(mlxsw_sp_port);
-	devlink_port_unregister(devlink_port);
 	mlxsw_sp_port_vports_fini(mlxsw_sp_port);
 	mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
 	mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 47610a5..361b0c2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -44,7 +44,6 @@
 #include <linux/list.h>
 #include <linux/dcbnl.h>
 #include <net/switchdev.h>
-#include <net/devlink.h>
 
 #include "port.h"
 #include "core.h"
@@ -166,6 +165,7 @@ struct mlxsw_sp_port_pcpu_stats {
 };
 
 struct mlxsw_sp_port {
+	struct mlxsw_core_port core_port; /* must be first */
 	struct net_device *dev;
 	struct mlxsw_sp_port_pcpu_stats __percpu *pcpu_stats;
 	struct mlxsw_sp *mlxsw_sp;
@@ -198,7 +198,6 @@ struct mlxsw_sp_port {
 	unsigned long *untagged_vlans;
 	/* VLAN interfaces */
 	struct list_head vports_list;
-	struct devlink_port devlink_port;
 };
 
 static inline bool
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index c49447f..2417f09 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -43,7 +43,6 @@
 #include <linux/device.h>
 #include <linux/skbuff.h>
 #include <linux/if_vlan.h>
-#include <net/devlink.h>
 #include <net/switchdev.h>
 #include <generated/utsrelease.h>
 
@@ -75,11 +74,11 @@ struct mlxsw_sx_port_pcpu_stats {
 };
 
 struct mlxsw_sx_port {
+	struct mlxsw_core_port core_port; /* must be first */
 	struct net_device *dev;
 	struct mlxsw_sx_port_pcpu_stats __percpu *pcpu_stats;
 	struct mlxsw_sx *mlxsw_sx;
 	u8 local_port;
-	struct devlink_port devlink_port;
 };
 
 /* tx_hdr_version
@@ -956,9 +955,7 @@ mlxsw_sx_port_mac_learning_mode_set(struct mlxsw_sx_port *mlxsw_sx_port,
 
 static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port)
 {
-	struct devlink *devlink = priv_to_devlink(mlxsw_sx->core);
 	struct mlxsw_sx_port *mlxsw_sx_port;
-	struct devlink_port *devlink_port;
 	struct net_device *dev;
 	bool usable;
 	int err;
@@ -1012,14 +1009,6 @@ static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port)
 		goto port_not_usable;
 	}
 
-	devlink_port = &mlxsw_sx_port->devlink_port;
-	err = devlink_port_register(devlink, devlink_port, local_port);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to register devlink port\n",
-			mlxsw_sx_port->local_port);
-		goto err_devlink_port_register;
-	}
-
 	err = mlxsw_sx_port_system_port_mapping_set(mlxsw_sx_port);
 	if (err) {
 		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set system port mapping\n",
@@ -1077,11 +1066,19 @@ static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port)
 		goto err_register_netdev;
 	}
 
-	devlink_port_type_eth_set(devlink_port, dev);
+	err = mlxsw_core_port_init(mlxsw_sx->core, &mlxsw_sx_port->core_port,
+				   mlxsw_sx_port->local_port, dev, false, 0);
+	if (err) {
+		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to init core port\n",
+			mlxsw_sx_port->local_port);
+		goto err_core_port_init;
+	}
 
 	mlxsw_sx->ports[local_port] = mlxsw_sx_port;
 	return 0;
 
+err_core_port_init:
+	unregister_netdev(dev);
 err_register_netdev:
 err_port_mac_learning_mode_set:
 err_port_stp_state_set:
@@ -1090,8 +1087,6 @@ err_port_mtu_set:
 err_port_speed_set:
 err_port_swid_set:
 err_port_system_port_mapping_set:
-	devlink_port_unregister(&mlxsw_sx_port->devlink_port);
-err_devlink_port_register:
 port_not_usable:
 err_port_module_check:
 err_dev_addr_get:
@@ -1104,15 +1099,12 @@ err_alloc_stats:
 static void mlxsw_sx_port_remove(struct mlxsw_sx *mlxsw_sx, u8 local_port)
 {
 	struct mlxsw_sx_port *mlxsw_sx_port = mlxsw_sx->ports[local_port];
-	struct devlink_port *devlink_port;
 
 	if (!mlxsw_sx_port)
 		return;
-	devlink_port = &mlxsw_sx_port->devlink_port;
-	devlink_port_type_clear(devlink_port);
+	mlxsw_core_port_fini(&mlxsw_sx_port->core_port);
 	unregister_netdev(mlxsw_sx_port->dev); /* This calls ndo_stop */
 	mlxsw_sx_port_swid_set(mlxsw_sx_port, MLXSW_PORT_SWID_DISABLED_PORT);
-	devlink_port_unregister(devlink_port);
 	free_percpu(mlxsw_sx_port->pcpu_stats);
 	free_netdev(mlxsw_sx_port->dev);
 }
-- 
2.5.5

[patch net-next 2/5] mlxsw: Pass mlxsw_core as a param of mlxsw_core_skb_transmit*

[Jiri Pirko]

From: Jiri Pirko <jiri@mellanox.com>

Instead of passing around driver priv, pass struct mlxsw_core *
directly.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlxsw/core.c     | 15 +++------------
 drivers/net/ethernet/mellanox/mlxsw/core.h     |  5 ++---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c |  4 ++--
 drivers/net/ethernet/mellanox/mlxsw/switchx2.c |  4 ++--
 4 files changed, 9 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 004fb8b..39161fb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -381,7 +381,7 @@ static int __mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core,
 
 	mlxsw_core->emad.trans_active = true;
 
-	err = mlxsw_core_skb_transmit(mlxsw_core->driver_priv, skb, tx_info);
+	err = mlxsw_core_skb_transmit(mlxsw_core, skb, tx_info);
 	if (err) {
 		dev_err(mlxsw_core->bus_info->dev, "Failed to transmit EMAD (tid=%llx)\n",
 			mlxsw_core->emad.tid);
@@ -929,26 +929,17 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core)
 }
 EXPORT_SYMBOL(mlxsw_core_bus_device_unregister);
 
-static struct mlxsw_core *__mlxsw_core_get(void *driver_priv)
-{
-	return container_of(driver_priv, struct mlxsw_core, driver_priv);
-}
-
-bool mlxsw_core_skb_transmit_busy(void *driver_priv,
+bool mlxsw_core_skb_transmit_busy(struct mlxsw_core *mlxsw_core,
 				  const struct mlxsw_tx_info *tx_info)
 {
-	struct mlxsw_core *mlxsw_core = __mlxsw_core_get(driver_priv);
-
 	return mlxsw_core->bus->skb_transmit_busy(mlxsw_core->bus_priv,
 						  tx_info);
 }
 EXPORT_SYMBOL(mlxsw_core_skb_transmit_busy);
 
-int mlxsw_core_skb_transmit(void *driver_priv, struct sk_buff *skb,
+int mlxsw_core_skb_transmit(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
 			    const struct mlxsw_tx_info *tx_info)
 {
-	struct mlxsw_core *mlxsw_core = __mlxsw_core_get(driver_priv);
-
 	return mlxsw_core->bus->skb_transmit(mlxsw_core->bus_priv, skb,
 					     tx_info);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index 06631a0..0454212 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -75,10 +75,9 @@ struct mlxsw_tx_info {
 	bool is_emad;
 };
 
-bool mlxsw_core_skb_transmit_busy(void *driver_priv,
+bool mlxsw_core_skb_transmit_busy(struct mlxsw_core *mlxsw_core,
 				  const struct mlxsw_tx_info *tx_info);
-
-int mlxsw_core_skb_transmit(void *driver_priv, struct sk_buff *skb,
+int mlxsw_core_skb_transmit(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
 			    const struct mlxsw_tx_info *tx_info);
 
 struct mlxsw_rx_listener {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 3216f2b..8abe1a6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -390,7 +390,7 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
 	u64 len;
 	int err;
 
-	if (mlxsw_core_skb_transmit_busy(mlxsw_sp, &tx_info))
+	if (mlxsw_core_skb_transmit_busy(mlxsw_sp->core, &tx_info))
 		return NETDEV_TX_BUSY;
 
 	if (unlikely(skb_headroom(skb) < MLXSW_TXHDR_LEN)) {
@@ -414,7 +414,7 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
 	/* Due to a race we might fail here because of a full queue. In that
 	 * unlikely case we simply drop the packet.
 	 */
-	err = mlxsw_core_skb_transmit(mlxsw_sp, skb, &tx_info);
+	err = mlxsw_core_skb_transmit(mlxsw_sp->core, skb, &tx_info);
 
 	if (!err) {
 		pcpu_stats = this_cpu_ptr(mlxsw_sp_port->pcpu_stats);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index 2417f09..2518c84 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -302,7 +302,7 @@ static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb,
 	u64 len;
 	int err;
 
-	if (mlxsw_core_skb_transmit_busy(mlxsw_sx, &tx_info))
+	if (mlxsw_core_skb_transmit_busy(mlxsw_sx->core, &tx_info))
 		return NETDEV_TX_BUSY;
 
 	if (unlikely(skb_headroom(skb) < MLXSW_TXHDR_LEN)) {
@@ -320,7 +320,7 @@ static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb,
 	/* Due to a race we might fail here because of a full queue. In that
 	 * unlikely case we simply drop the packet.
 	 */
-	err = mlxsw_core_skb_transmit(mlxsw_sx, skb, &tx_info);
+	err = mlxsw_core_skb_transmit(mlxsw_sx->core, skb, &tx_info);
 
 	if (!err) {
 		pcpu_stats = this_cpu_ptr(mlxsw_sx_port->pcpu_stats);
-- 
2.5.5

[patch net-next 3/5] mlxsw: Do not pass around driver_priv directly

[Jiri Pirko]

From: Jiri Pirko <jiri@mellanox.com>

Instead of that, pass mlxsw_core and use a helper to get driver priv
from driver code. Looks much cleaner that way.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlxsw/core.c     | 19 +++++++++++--------
 drivers/net/ethernet/mellanox/mlxsw/core.h     | 11 +++++++----
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 17 +++++++++--------
 drivers/net/ethernet/mellanox/mlxsw/switchx2.c |  8 ++++----
 4 files changed, 31 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 39161fb..3958195 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -114,6 +114,12 @@ struct mlxsw_core {
 	/* driver_priv has to be always the last item */
 };
 
+void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core)
+{
+	return mlxsw_core->driver_priv;
+}
+EXPORT_SYMBOL(mlxsw_core_driver_priv);
+
 struct mlxsw_rx_listener_item {
 	struct list_head list;
 	struct mlxsw_rx_listener rxl;
@@ -795,8 +801,7 @@ static int mlxsw_devlink_port_split(struct devlink *devlink,
 		return -EINVAL;
 	if (!mlxsw_core->driver->port_split)
 		return -EOPNOTSUPP;
-	return mlxsw_core->driver->port_split(mlxsw_core->driver_priv,
-					      port_index, count);
+	return mlxsw_core->driver->port_split(mlxsw_core, port_index, count);
 }
 
 static int mlxsw_devlink_port_unsplit(struct devlink *devlink,
@@ -808,8 +813,7 @@ static int mlxsw_devlink_port_unsplit(struct devlink *devlink,
 		return -EINVAL;
 	if (!mlxsw_core->driver->port_unsplit)
 		return -EOPNOTSUPP;
-	return mlxsw_core->driver->port_unsplit(mlxsw_core->driver_priv,
-						port_index);
+	return mlxsw_core->driver->port_unsplit(mlxsw_core, port_index);
 }
 
 static const struct devlink_ops mlxsw_devlink_ops = {
@@ -880,8 +884,7 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 	if (err)
 		goto err_devlink_register;
 
-	err = mlxsw_driver->init(mlxsw_core->driver_priv, mlxsw_core,
-				 mlxsw_bus_info);
+	err = mlxsw_driver->init(mlxsw_core, mlxsw_bus_info);
 	if (err)
 		goto err_driver_init;
 
@@ -892,7 +895,7 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 	return 0;
 
 err_debugfs_init:
-	mlxsw_core->driver->fini(mlxsw_core->driver_priv);
+	mlxsw_core->driver->fini(mlxsw_core);
 err_driver_init:
 	devlink_unregister(devlink);
 err_devlink_register:
@@ -918,7 +921,7 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core)
 	struct devlink *devlink = priv_to_devlink(mlxsw_core);
 
 	mlxsw_core_debugfs_fini(mlxsw_core);
-	mlxsw_core->driver->fini(mlxsw_core->driver_priv);
+	mlxsw_core->driver->fini(mlxsw_core);
 	devlink_unregister(devlink);
 	mlxsw_emad_fini(mlxsw_core);
 	mlxsw_core->bus->fini(mlxsw_core->bus_priv);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index 0454212..f3cebef 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -62,6 +62,8 @@ struct mlxsw_driver;
 struct mlxsw_bus;
 struct mlxsw_bus_info;
 
+void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core);
+
 int mlxsw_core_driver_register(struct mlxsw_driver *mlxsw_driver);
 void mlxsw_core_driver_unregister(struct mlxsw_driver *mlxsw_driver);
 
@@ -192,11 +194,12 @@ struct mlxsw_driver {
 	const char *kind;
 	struct module *owner;
 	size_t priv_size;
-	int (*init)(void *driver_priv, struct mlxsw_core *mlxsw_core,
+	int (*init)(struct mlxsw_core *mlxsw_core,
 		    const struct mlxsw_bus_info *mlxsw_bus_info);
-	void (*fini)(void *driver_priv);
-	int (*port_split)(void *driver_priv, u8 local_port, unsigned int count);
-	int (*port_unsplit)(void *driver_priv, u8 local_port);
+	void (*fini)(struct mlxsw_core *mlxsw_core);
+	int (*port_split)(struct mlxsw_core *mlxsw_core, u8 local_port,
+			  unsigned int count);
+	int (*port_unsplit)(struct mlxsw_core *mlxsw_core, u8 local_port);
 	void (*txhdr_construct)(struct sk_buff *skb,
 				const struct mlxsw_tx_info *tx_info);
 	u8 txhdr_len;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 8abe1a6..19b3c14 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1948,9 +1948,10 @@ static u8 mlxsw_sp_cluster_base_port_get(u8 local_port)
 	return local_port - offset;
 }
 
-static int mlxsw_sp_port_split(void *priv, u8 local_port, unsigned int count)
+static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
+			       unsigned int count)
 {
-	struct mlxsw_sp *mlxsw_sp = priv;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	u8 width = MLXSW_PORT_MODULE_MAX_WIDTH / count;
 	u8 module, cur_width, base_port;
@@ -2022,9 +2023,9 @@ err_port_create:
 	return err;
 }
 
-static int mlxsw_sp_port_unsplit(void *priv, u8 local_port)
+static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port)
 {
-	struct mlxsw_sp *mlxsw_sp = priv;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	u8 module, cur_width, base_port;
 	unsigned int count;
@@ -2369,10 +2370,10 @@ static int mlxsw_sp_lag_init(struct mlxsw_sp *mlxsw_sp)
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(slcr), slcr_pl);
 }
 
-static int mlxsw_sp_init(void *priv, struct mlxsw_core *mlxsw_core,
+static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 			 const struct mlxsw_bus_info *mlxsw_bus_info)
 {
-	struct mlxsw_sp *mlxsw_sp = priv;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
 	int err;
 
 	mlxsw_sp->core = mlxsw_core;
@@ -2443,9 +2444,9 @@ err_event_register:
 	return err;
 }
 
-static void mlxsw_sp_fini(void *priv)
+static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 {
-	struct mlxsw_sp *mlxsw_sp = priv;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
 
 	mlxsw_sp_switchdev_fini(mlxsw_sp);
 	mlxsw_sp_traps_fini(mlxsw_sp);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index 2518c84..3842eab 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -1447,10 +1447,10 @@ static int mlxsw_sx_flood_init(struct mlxsw_sx *mlxsw_sx)
 	return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sgcr), sgcr_pl);
 }
 
-static int mlxsw_sx_init(void *priv, struct mlxsw_core *mlxsw_core,
+static int mlxsw_sx_init(struct mlxsw_core *mlxsw_core,
 			 const struct mlxsw_bus_info *mlxsw_bus_info)
 {
-	struct mlxsw_sx *mlxsw_sx = priv;
+	struct mlxsw_sx *mlxsw_sx = mlxsw_core_driver_priv(mlxsw_core);
 	int err;
 
 	mlxsw_sx->core = mlxsw_core;
@@ -1497,9 +1497,9 @@ err_event_register:
 	return err;
 }
 
-static void mlxsw_sx_fini(void *priv)
+static void mlxsw_sx_fini(struct mlxsw_core *mlxsw_core)
 {
-	struct mlxsw_sx *mlxsw_sx = priv;
+	struct mlxsw_sx *mlxsw_sx = mlxsw_core_driver_priv(mlxsw_core);
 
 	mlxsw_sx_traps_fini(mlxsw_sx);
 	mlxsw_sx_event_unregister(mlxsw_sx, MLXSW_TRAP_ID_PUDE);
-- 
2.5.5

[patch net-next 4/5] mlxsw: reg: Share direction enum between SBPR, SBCM, SBPM

[Jiri Pirko]

From: Jiri Pirko <jiri@mellanox.com>

Same field, same values, so share the same enum.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h          | 23 +++++++---------------
 .../net/ethernet/mellanox/mlxsw/spectrum_buffers.c | 20 +++++++++----------
 2 files changed, 17 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 28f5b99..19bdc82 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -3476,9 +3476,10 @@ static const struct mlxsw_reg_info mlxsw_reg_sbpr = {
 	.len = MLXSW_REG_SBPR_LEN,
 };
 
-enum mlxsw_reg_sbpr_dir {
-	MLXSW_REG_SBPR_DIR_INGRESS,
-	MLXSW_REG_SBPR_DIR_EGRESS,
+/* shared direstion enum for SBPR, SBCM, SBPM */
+enum mlxsw_reg_sbxx_dir {
+	MLXSW_REG_SBXX_DIR_INGRESS,
+	MLXSW_REG_SBXX_DIR_EGRESS,
 };
 
 /* reg_sbpr_dir
@@ -3511,7 +3512,7 @@ enum mlxsw_reg_sbpr_mode {
 MLXSW_ITEM32(reg, sbpr, mode, 0x08, 0, 4);
 
 static inline void mlxsw_reg_sbpr_pack(char *payload, u8 pool,
-				       enum mlxsw_reg_sbpr_dir dir,
+				       enum mlxsw_reg_sbxx_dir dir,
 				       enum mlxsw_reg_sbpr_mode mode, u32 size)
 {
 	MLXSW_REG_ZERO(sbpr, payload);
@@ -3553,11 +3554,6 @@ MLXSW_ITEM32(reg, sbcm, local_port, 0x00, 16, 8);
  */
 MLXSW_ITEM32(reg, sbcm, pg_buff, 0x00, 8, 6);
 
-enum mlxsw_reg_sbcm_dir {
-	MLXSW_REG_SBCM_DIR_INGRESS,
-	MLXSW_REG_SBCM_DIR_EGRESS,
-};
-
 /* reg_sbcm_dir
  * Direction.
  * Access: Index
@@ -3590,7 +3586,7 @@ MLXSW_ITEM32(reg, sbcm, max_buff, 0x1C, 0, 24);
 MLXSW_ITEM32(reg, sbcm, pool, 0x24, 0, 4);
 
 static inline void mlxsw_reg_sbcm_pack(char *payload, u8 local_port, u8 pg_buff,
-				       enum mlxsw_reg_sbcm_dir dir,
+				       enum mlxsw_reg_sbxx_dir dir,
 				       u32 min_buff, u32 max_buff, u8 pool)
 {
 	MLXSW_REG_ZERO(sbcm, payload);
@@ -3630,11 +3626,6 @@ MLXSW_ITEM32(reg, sbpm, local_port, 0x00, 16, 8);
  */
 MLXSW_ITEM32(reg, sbpm, pool, 0x00, 8, 4);
 
-enum mlxsw_reg_sbpm_dir {
-	MLXSW_REG_SBPM_DIR_INGRESS,
-	MLXSW_REG_SBPM_DIR_EGRESS,
-};
-
 /* reg_sbpm_dir
  * Direction.
  * Access: Index
@@ -3661,7 +3652,7 @@ MLXSW_ITEM32(reg, sbpm, min_buff, 0x18, 0, 24);
 MLXSW_ITEM32(reg, sbpm, max_buff, 0x1C, 0, 24);
 
 static inline void mlxsw_reg_sbpm_pack(char *payload, u8 local_port, u8 pool,
-				       enum mlxsw_reg_sbpm_dir dir,
+				       enum mlxsw_reg_sbxx_dir dir,
 				       u32 min_buff, u32 max_buff)
 {
 	MLXSW_REG_ZERO(sbpm, payload);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index 97c8d53..f58b1d3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -110,7 +110,7 @@ static int mlxsw_sp_port_headroom_init(struct mlxsw_sp_port *mlxsw_sp_port)
 
 struct mlxsw_sp_sb_pool {
 	u8 pool;
-	enum mlxsw_reg_sbpr_dir dir;
+	enum mlxsw_reg_sbxx_dir dir;
 	enum mlxsw_reg_sbpr_mode mode;
 	u32 size;
 };
@@ -129,11 +129,11 @@ struct mlxsw_sp_sb_pool {
 	}
 
 #define MLXSW_SP_SB_POOL_INGRESS(_pool, _size)			\
-	MLXSW_SP_SB_POOL(_pool, MLXSW_REG_SBPR_DIR_INGRESS,	\
+	MLXSW_SP_SB_POOL(_pool, MLXSW_REG_SBXX_DIR_INGRESS,	\
 			 MLXSW_REG_SBPR_MODE_DYNAMIC, _size)
 
 #define MLXSW_SP_SB_POOL_EGRESS(_pool, _size)			\
-	MLXSW_SP_SB_POOL(_pool, MLXSW_REG_SBPR_DIR_EGRESS,	\
+	MLXSW_SP_SB_POOL(_pool, MLXSW_REG_SBXX_DIR_EGRESS,	\
 			 MLXSW_REG_SBPR_MODE_DYNAMIC, _size)
 
 static const struct mlxsw_sp_sb_pool mlxsw_sp_sb_pools[] = {
@@ -173,7 +173,7 @@ struct mlxsw_sp_sb_cm {
 		u8 pg;
 		u8 tc;
 	} u;
-	enum mlxsw_reg_sbcm_dir dir;
+	enum mlxsw_reg_sbxx_dir dir;
 	u32 min_buff;
 	u32 max_buff;
 	u8 pool;
@@ -189,15 +189,15 @@ struct mlxsw_sp_sb_cm {
 	}
 
 #define MLXSW_SP_SB_CM_INGRESS(_pg, _min_buff, _max_buff)		\
-	MLXSW_SP_SB_CM(_pg, MLXSW_REG_SBCM_DIR_INGRESS,			\
+	MLXSW_SP_SB_CM(_pg, MLXSW_REG_SBXX_DIR_INGRESS,			\
 		       _min_buff, _max_buff, 0)
 
 #define MLXSW_SP_SB_CM_EGRESS(_tc, _min_buff, _max_buff)		\
-	MLXSW_SP_SB_CM(_tc, MLXSW_REG_SBCM_DIR_EGRESS,			\
+	MLXSW_SP_SB_CM(_tc, MLXSW_REG_SBXX_DIR_EGRESS,			\
 		       _min_buff, _max_buff, 0)
 
 #define MLXSW_SP_CPU_PORT_SB_CM_EGRESS(_tc)				\
-	MLXSW_SP_SB_CM(_tc, MLXSW_REG_SBCM_DIR_EGRESS, 104, 2, 3)
+	MLXSW_SP_SB_CM(_tc, MLXSW_REG_SBXX_DIR_EGRESS, 104, 2, 3)
 
 static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms[] = {
 	MLXSW_SP_SB_CM_INGRESS(0, MLXSW_SP_BYTES_TO_CELLS(10000), 8),
@@ -304,7 +304,7 @@ static int mlxsw_sp_cpu_port_sb_cms_init(struct mlxsw_sp *mlxsw_sp)
 
 struct mlxsw_sp_sb_pm {
 	u8 pool;
-	enum mlxsw_reg_sbpm_dir dir;
+	enum mlxsw_reg_sbxx_dir dir;
 	u32 min_buff;
 	u32 max_buff;
 };
@@ -318,11 +318,11 @@ struct mlxsw_sp_sb_pm {
 	}
 
 #define MLXSW_SP_SB_PM_INGRESS(_pool, _min_buff, _max_buff)	\
-	MLXSW_SP_SB_PM(_pool, MLXSW_REG_SBPM_DIR_INGRESS,	\
+	MLXSW_SP_SB_PM(_pool, MLXSW_REG_SBXX_DIR_INGRESS,	\
 		       _min_buff, _max_buff)
 
 #define MLXSW_SP_SB_PM_EGRESS(_pool, _min_buff, _max_buff)	\
-	MLXSW_SP_SB_PM(_pool, MLXSW_REG_SBPM_DIR_EGRESS,	\
+	MLXSW_SP_SB_PM(_pool, MLXSW_REG_SBXX_DIR_EGRESS,	\
 		       _min_buff, _max_buff)
 
 static const struct mlxsw_sp_sb_pm mlxsw_sp_sb_pms[] = {
-- 
2.5.5

[patch net-next 5/5] mlxsw: reg: Fix SBPM register name

[Jiri Pirko]

From: Jiri Pirko <jiri@mellanox.com>

Fix copy&paste error and state the name of SBPM register correctly.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 19bdc82..57e4a63 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -3598,8 +3598,8 @@ static inline void mlxsw_reg_sbcm_pack(char *payload, u8 local_port, u8 pg_buff,
 	mlxsw_reg_sbcm_pool_set(payload, pool);
 }
 
-/* SBPM - Shared Buffer Class Management Register
- * ----------------------------------------------
+/* SBPM - Shared Buffer Port Management Register
+ * ---------------------------------------------
  * The SBPM register configures and retrieves the shared buffer allocation
  * and configuration according to Port-Pool, including the definition
  * of the associated quota.
-- 
2.5.5

Re: [patch net-next 0/5] mlxsw: small driver update

[Jiri Pirko]

Fri, Apr 08, 2016 at 05:45:20PM CEST, jiri@resnulli.us wrote:
>From: Jiri Pirko <jiri@mellanox.com>
>
>Cosmetics, in preparation to sharedbuffer patchset.

Dave, I just realized there is dependency on:
"devlink: remove implicit type set in port register" which I sent couple
of minutes after this patchset. I can either resend in bulk, or if you
could apply in order, that would be great.

Thanks and sorry, owe you another beer :)


>
>Jiri Pirko (5):
>  mlxsw: Move devlink port registration into common core code
>  mlxsw: Pass mlxsw_core as a param of mlxsw_core_skb_transmit*
>  mlxsw: Do not pass around driver_priv directly
>  mlxsw: reg: Share direction enum between SBPR, SBCM, SBPM
>  mlxsw: reg: Fix SBPM register name
>
> drivers/net/ethernet/mellanox/mlxsw/core.c         | 56 ++++++++++++++--------
> drivers/net/ethernet/mellanox/mlxsw/core.h         | 26 +++++++---
> drivers/net/ethernet/mellanox/mlxsw/reg.h          | 27 ++++-------
> drivers/net/ethernet/mellanox/mlxsw/spectrum.c     | 52 +++++++++-----------
> drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  3 +-
> .../net/ethernet/mellanox/mlxsw/spectrum_buffers.c | 20 ++++----
> drivers/net/ethernet/mellanox/mlxsw/switchx2.c     | 42 +++++++---------
> 7 files changed, 114 insertions(+), 112 deletions(-)
>
>-- 
>2.5.5
>

Re: [patch net-next 0/5] mlxsw: small driver update

[David Miller]

From: Jiri Pirko <jiri@resnulli.us>
Date: Fri, 8 Apr 2016 17:51:55 +0200

> Fri, Apr 08, 2016 at 05:45:20PM CEST, jiri@resnulli.us wrote:
>>From: Jiri Pirko <jiri@mellanox.com>
>>
>>Cosmetics, in preparation to sharedbuffer patchset.
> 
> Dave, I just realized there is dependency on:
> "devlink: remove implicit type set in port register" which I sent couple
> of minutes after this patchset. I can either resend in bulk, or if you
> could apply in order, that would be great.

The devlink series also lacked a header posting.  Can you just sort this
all out properly and respin everything?

Thanks.

> Thanks and sorry, owe you another beer :)

:-)

Re: [patch net-next 0/5] mlxsw: small driver update

[Jiri Pirko]

Fri, Apr 08, 2016 at 07:07:37PM CEST, davem@davemloft.net wrote:
>From: Jiri Pirko <jiri@resnulli.us>
>Date: Fri, 8 Apr 2016 17:51:55 +0200
>
>> Fri, Apr 08, 2016 at 05:45:20PM CEST, jiri@resnulli.us wrote:
>>>From: Jiri Pirko <jiri@mellanox.com>
>>>
>>>Cosmetics, in preparation to sharedbuffer patchset.
>> 
>> Dave, I just realized there is dependency on:
>> "devlink: remove implicit type set in port register" which I sent couple
>> of minutes after this patchset. I can either resend in bulk, or if you
>> could apply in order, that would be great.
>
>The devlink series also lacked a header posting.  Can you just sort this
>all out properly and respin everything?

done.

>
>Thanks.
>
>> Thanks and sorry, owe you another beer :)
>
>:-)

Re: [PATCH v5 net-next 00/15] MTU/buffer reconfig changes

[David Miller]

From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu,  7 Apr 2016 19:39:33 +0100

> I re-discussed MPLS/MTU internally, dropped it from the patch 1,
> re-tested everything, found out I forgot about debugfs pointers,
> fixed that as well.
> 
> v5:
>  - don't reserve space in RX buffers for MPLS label stack
>    (patch 1);
>  - fix debugfs pointers to ring structures (patch 5).
> v4:
>  - cut down on unrelated patches;
>  - don't "close" the device on error path.
> 
> --- v4 cover letter
> 
> Previous series included some not entirely related patches,
> this one is cut down.  Main issue I'm trying to solve here
> is that .ndo_change_mtu() in nfpvf driver is doing full
> close/open to reallocate buffers - which if open fails
> can result in device being basically closed even though
> the interface is started.  As suggested by you I try to move
> towards a paradigm where the resources are allocated first
> and the MTU change is only done once I'm certain (almost)
> nothing can fail.  Almost because I need to communicate 
> with FW and that can always time out.
> 
> Patch 1 fixes small issue.  Next 10 patches reorganize things
> so that I can easily allocate new rings and sets of buffers
> while the device is running.  Patches 13 and 15 reshape the
> .ndo_change_mtu() and ethtool's ring-resize operation into
> desired form.

Looks good, series applied, thanks!

Re: [PATCH v5 net-next 00/15] MTU/buffer reconfig changes, [PATCH net-next v2 1/2] bpf, trace: add BPF_F_CURRENT_CPU flag for bpf_perf_event_output, [PATCH v2 1/5] mmc: tmio: give read32/write32 functions more descriptive names, Re: [patch net-next 0/5] mlxsw: small driver update, Re: [RFC PATCH 07/11] GENEVE: Add option to mangle IP IDs on inner headers when using TSO, Re: [PATCH/RFC v2] gpio: rcar: Add Runtime PM handling for interrupts, [v3,4/6] arm64: dts: salvator-x: enable PWM

[David Miller, Daniel Borkmann, Wolfram Sang, David Miller, Jesse Gross, Laurent Pinchart, Ulrich Hecht]

From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu,  7 Apr 2016 19:39:33 +0100

> I re-discussed MPLS/MTU internally, dropped it from the patch 1,
> re-tested everything, found out I forgot about debugfs pointers,
> fixed that as well.
> 
> v5:
>  - don't reserve space in RX buffers for MPLS label stack
>    (patch 1);
>  - fix debugfs pointers to ring structures (patch 5).
> v4:
>  - cut down on unrelated patches;
>  - don't "close" the device on error path.
> 
> --- v4 cover letter
> 
> Previous series included some not entirely related patches,
> this one is cut down.  Main issue I'm trying to solve here
> is that .ndo_change_mtu() in nfpvf driver is doing full
> close/open to reallocate buffers - which if open fails
> can result in device being basically closed even though
> the interface is started.  As suggested by you I try to move
> towards a paradigm where the resources are allocated first
> and the MTU change is only done once I'm certain (almost)
> nothing can fail.  Almost because I need to communicate 
> with FW and that can always time out.
> 
> Patch 1 fixes small issue.  Next 10 patches reorganize things
> so that I can easily allocate new rings and sets of buffers
> while the device is running.  Patches 13 and 15 reshape the
> .ndo_change_mtu() and ethtool's ring-resize operation into
> desired form.

Looks good, series applied, thanks!

Add a BPF_F_CURRENT_CPU flag to optimize the use-case where user space has
per-CPU ring buffers and the eBPF program pushes the data into the current
CPU's ring buffer which saves us an extra helper function call in eBPF.
Also, make sure to properly reserve the remaining flags which are not used.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h | 4 ++++
 kernel/trace/bpf_trace.c | 7 ++++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 70eda5a..b7b0fb1 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -347,6 +347,10 @@ enum bpf_func_id {
 #define BPF_F_ZERO_CSUM_TX		(1ULL << 1)
 #define BPF_F_DONT_FRAGMENT		(1ULL << 2)
 
+/* BPF_FUNC_perf_event_output flags. */
+#define BPF_F_INDEX_MASK		0xffffffffULL
+#define BPF_F_CURRENT_CPU		BPF_F_INDEX_MASK
+
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
  */
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 6855878..6bfe55c 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -225,11 +225,12 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
-static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
+static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
 {
 	struct pt_regs *regs = (struct pt_regs *) (long) r1;
 	struct bpf_map *map = (struct bpf_map *) (long) r2;
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	u64 index = flags & BPF_F_INDEX_MASK;
 	void *data = (void *) (long) r4;
 	struct perf_sample_data sample_data;
 	struct perf_event *event;
@@ -239,6 +240,10 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
 		.data = data,
 	};
 
+	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
+		return -EINVAL;
+	if (index == BPF_F_CURRENT_CPU)
+		index = raw_smp_processor_id();
 	if (unlikely(index >= array->map.max_entries))
 		return -E2BIG;
 
-- 
1.9.3

From: Wolfram Sang <wsa+renesas@sang-engineering.com>

Looking at the backlogs, I am not the only one who missed that the above
functions do not read u32 from one register, but create a virtual u32
from reading to adjacent u16 registers (which depending on 'bus_shift'
can be up to 8 byte apart). Because this driver supports old hardware
for which we don't have documentation, I first wrongly assumed there was
a variant which had a few u32 registers. Let's give the functions more
descriptive names to make it more obvious what is happening.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
---
 drivers/mmc/host/tmio_mmc.h     |  5 ++---
 drivers/mmc/host/tmio_mmc_pio.c | 22 +++++++++++-----------
 2 files changed, 13 insertions(+), 14 deletions(-)

diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 439fdad2bad91d..e75e5ca220bc0a 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -232,7 +232,7 @@ static inline void sd_ctrl_read16_rep(struct tmio_mmc_host *host, int addr,
 	readsw(host->ctl + (addr << host->bus_shift), buf, count);
 }
 
-static inline u32 sd_ctrl_read32(struct tmio_mmc_host *host, int addr)
+static inline u32 sd_ctrl_read16_and_16_as_32(struct tmio_mmc_host *host, int addr)
 {
 	return readw(host->ctl + (addr << host->bus_shift)) |
 	       readw(host->ctl + ((addr + 2) << host->bus_shift)) << 16;
@@ -254,11 +254,10 @@ static inline void sd_ctrl_write16_rep(struct tmio_mmc_host *host, int addr,
 	writesw(host->ctl + (addr << host->bus_shift), buf, count);
 }
 
-static inline void sd_ctrl_write32(struct tmio_mmc_host *host, int addr, u32 val)
+static inline void sd_ctrl_write32_as_16_and_16(struct tmio_mmc_host *host, int addr, u32 val)
 {
 	writew(val, host->ctl + (addr << host->bus_shift));
 	writew(val >> 16, host->ctl + ((addr + 2) << host->bus_shift));
 }
 
-
 #endif
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index 15e6f6d5a42337..dad2ebd3dc22b4 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -55,18 +55,18 @@
 void tmio_mmc_enable_mmc_irqs(struct tmio_mmc_host *host, u32 i)
 {
 	host->sdcard_irq_mask &= ~(i & TMIO_MASK_IRQ);
-	sd_ctrl_write32(host, CTL_IRQ_MASK, host->sdcard_irq_mask);
+	sd_ctrl_write32_as_16_and_16(host, CTL_IRQ_MASK, host->sdcard_irq_mask);
 }
 
 void tmio_mmc_disable_mmc_irqs(struct tmio_mmc_host *host, u32 i)
 {
 	host->sdcard_irq_mask |= (i & TMIO_MASK_IRQ);
-	sd_ctrl_write32(host, CTL_IRQ_MASK, host->sdcard_irq_mask);
+	sd_ctrl_write32_as_16_and_16(host, CTL_IRQ_MASK, host->sdcard_irq_mask);
 }
 
 static void tmio_mmc_ack_mmc_irqs(struct tmio_mmc_host *host, u32 i)
 {
-	sd_ctrl_write32(host, CTL_STATUS, ~i);
+	sd_ctrl_write32_as_16_and_16(host, CTL_STATUS, ~i);
 }
 
 static void tmio_mmc_init_sg(struct tmio_mmc_host *host, struct mmc_data *data)
@@ -381,7 +381,7 @@ static int tmio_mmc_start_command(struct tmio_mmc_host *host, struct mmc_command
 	tmio_mmc_enable_mmc_irqs(host, irq_mask);
 
 	/* Fire off the command */
-	sd_ctrl_write32(host, CTL_ARG_REG, cmd->arg);
+	sd_ctrl_write32_as_16_and_16(host, CTL_ARG_REG, cmd->arg);
 	sd_ctrl_write16(host, CTL_SD_CMD, c);
 
 	return 0;
@@ -536,7 +536,7 @@ static void tmio_mmc_data_irq(struct tmio_mmc_host *host)
 		goto out;
 
 	if (host->chan_tx && (data->flags & MMC_DATA_WRITE) && !host->force_pio) {
-		u32 status = sd_ctrl_read32(host, CTL_STATUS);
+		u32 status = sd_ctrl_read16_and_16_as_32(host, CTL_STATUS);
 		bool done = false;
 
 		/*
@@ -591,7 +591,7 @@ static void tmio_mmc_cmd_irq(struct tmio_mmc_host *host,
 	 */
 
 	for (i = 3, addr = CTL_RESPONSE ; i >= 0 ; i--, addr += 4)
-		cmd->resp[i] = sd_ctrl_read32(host, addr);
+		cmd->resp[i] = sd_ctrl_read16_and_16_as_32(host, addr);
 
 	if (cmd->flags &  MMC_RSP_136) {
 		cmd->resp[0] = (cmd->resp[0] << 8) | (cmd->resp[1] >> 24);
@@ -708,14 +708,14 @@ irqreturn_t tmio_mmc_irq(int irq, void *devid)
 	struct tmio_mmc_host *host = devid;
 	unsigned int ireg, status;
 
-	status = sd_ctrl_read32(host, CTL_STATUS);
+	status = sd_ctrl_read16_and_16_as_32(host, CTL_STATUS);
 	ireg = status & TMIO_MASK_IRQ & ~host->sdcard_irq_mask;
 
 	pr_debug_status(status);
 	pr_debug_status(ireg);
 
 	/* Clear the status except the interrupt status */
-	sd_ctrl_write32(host, CTL_STATUS, TMIO_MASK_IRQ);
+	sd_ctrl_write32_as_16_and_16(host, CTL_STATUS, TMIO_MASK_IRQ);
 
 	if (__tmio_mmc_card_detect_irq(host, ireg, status))
 		return IRQ_HANDLED;
@@ -961,7 +961,7 @@ static int tmio_mmc_get_ro(struct mmc_host *mmc)
 
 	pm_runtime_get_sync(mmc_dev(mmc));
 	ret = !((pdata->flags & TMIO_MMC_WRPROTECT_DISABLE) ||
-		(sd_ctrl_read32(host, CTL_STATUS) & TMIO_STAT_WRPROTECT));
+		(sd_ctrl_read16_and_16_as_32(host, CTL_STATUS) & TMIO_STAT_WRPROTECT));
 	pm_runtime_mark_last_busy(mmc_dev(mmc));
 	pm_runtime_put_autosuspend(mmc_dev(mmc));
 
@@ -983,7 +983,7 @@ static int tmio_mmc_card_busy(struct mmc_host *mmc)
 {
 	struct tmio_mmc_host *host = mmc_priv(mmc);
 
-	return !(sd_ctrl_read32(host, CTL_STATUS2) & TMIO_STATUS2_DAT0);
+	return !(sd_ctrl_read16_and_16_as_32(host, CTL_STATUS2) & TMIO_STATUS2_DAT0);
 }
 
 static struct mmc_host_ops tmio_mmc_ops = {
@@ -1132,7 +1132,7 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 	tmio_mmc_clk_stop(_host);
 	tmio_mmc_reset(_host);
 
-	_host->sdcard_irq_mask = sd_ctrl_read32(_host, CTL_IRQ_MASK);
+	_host->sdcard_irq_mask = sd_ctrl_read16_and_16_as_32(_host, CTL_IRQ_MASK);
 	tmio_mmc_disable_mmc_irqs(_host, TMIO_MASK_ALL);
 
 	/* Unmask the IRQs we want to know about */
-- 
2.7.0

From: Jiri Pirko <jiri@resnulli.us>
Date: Fri, 8 Apr 2016 17:51:55 +0200

> Fri, Apr 08, 2016 at 05:45:20PM CEST, jiri@resnulli.us wrote:
>>From: Jiri Pirko <jiri@mellanox.com>
>>
>>Cosmetics, in preparation to sharedbuffer patchset.
> 
> Dave, I just realized there is dependency on:
> "devlink: remove implicit type set in port register" which I sent couple
> of minutes after this patchset. I can either resend in bulk, or if you
> could apply in order, that would be great.

The devlink series also lacked a header posting.  Can you just sort this
all out properly and respin everything?

Thanks.

> Thanks and sorry, owe you another beer :)

:-)

On Thu, Apr 7, 2016 at 7:32 PM, Alexander Duyck <aduyck@mirantis.com> wrote:
> This patch adds support for a feature I am calling IP ID mangling.  It is
> basically just another way of saying the IP IDs that are transmitted by the
> tunnel may not match up with what would normally be expected.  Specifically
> what will happen is in the case of TSO the IP IDs on the headers will be a
> fixed value so a given TSO will repeat the same inner IP ID value gso_segs
> number of times.
>
> Signed-off-by: Alexander Duyck <aduyck@mirantis.com>

If I'm understanding this correctly, enabling IP ID mangling will help
performance on ixgbe since it will allow it to do GSO partial instead
of plain GSO but it will hurt performance on i40e since it will drop
from TSO to plain GSO.

Assuming that's right, it seems like it will make it hard to chose the
right setting without knowledge of which hardware is in use. I guess
what we really want is "I care about nicely incrementing IP IDs" vs.
"I don't care as long as the DF bit is set". That second case is
really what this flag is trying to say but it seems like it is
enforcing too much in the i40e case - I don't think anyone wants to go
out of their way to make IP IDs jump around if incrementing is faster.

On Friday 19 Feb 2016 11:59:40 Marc Zyngier wrote:
> On 19/02/16 09:18, Linus Walleij wrote:
> > Top-quoting so everyone on the new To:-line gets the context.
> > 
> > I definately need an indication from an irqchip maintainer like tglx or
> > Marc Z before I merge this. Also, as in reply to the previous letter,
> > coordinate efforts with Jon Hunters similar problem space.
> 
> Seems pretty straightforward to me.
>
> Acked-by: Marc Zyngier <marc.zyngier@arm.com>

Too straightforward to be correct :-/

[    6.232681] BUG: sleeping function called from invalid context at /home/laurent/src/iob/renesas/linux/drivers/base/power/runtime.c:955
[    6.244795] in_atomic(): 1, irqs_disabled(): 128, pid: 658, name: udevd
[    6.251429] CPU: 3 PID: 658 Comm: udevd Tainted: P                4.6.0-rc3 #756
[    6.258844] Hardware name: Generic R8A7790 (Flattened Device Tree)
[    6.265036] Backtrace: 
[    6.267535] [<c0014c98>] (dump_backtrace) from [<c0014fb0>] (show_stack+0x20/0x24)
[    6.275124]  r6:00000000 r5:00000000 r4:60000093 r3:00000000
[    6.280850] [<c0014f90>] (show_stack) from [<c01f614c>] (dump_stack+0x8c/0xac)
[    6.288105] [<c01f60c0>] (dump_stack) from [<c00510c8>] (___might_sleep+0x100/0x158)
[    6.295863]  r5:000003bb r4:c06ca340
[    6.299474] [<c0050fc8>] (___might_sleep) from [<c005118c>] (__might_sleep+0x6c/0xa8)
[    6.307317]  r4:c05b6a24
[    6.309880] [<c0051120>] (__might_sleep) from [<c02d971c>] (__pm_runtime_resume+0x98/0xa0)
[    6.318159]  r6:000000dc r5:00000004 r4:ea280010
[    6.322831] [<c02d9684>] (__pm_runtime_resume) from [<c02282c8>] (gpio_rcar_irq_request_resources+0x2c/0x34)
[    6.332674]  r7:00000000 r6:000000dc r5:e95b3c00 r4:e99f3c00
[    6.338397] [<c022829c>] (gpio_rcar_irq_request_resources) from [<c0077a88>] (__setup_irq+0x24c/0x5dc)
[    6.347724] [<c007783c>] (__setup_irq) from [<c0077ff4>] (request_threaded_irq+0xdc/0x180)
[    6.356004]  r10:bf0aabc8 r9:000000dc r8:e9bc3000 r7:c0075be8 r6:e99f3c00 r5:00002003
[    6.363905]  r4:e95b3c00
[    6.366466] [<c0077f18>] (request_threaded_irq) from [<c007a758>] (devm_request_threaded_irq+0x6c/0xac)
[    6.375874]  r10:ea2db810 r9:ea2db810 r8:00000000 r7:bf0aabc8 r6:000000dc r5:e9bc3000
[    6.383773]  r4:e95b3b50 r3:00002003
[    6.387410] [<c007a6ec>] (devm_request_threaded_irq) from [<bf0aab9c>] (mmc_gpiod_request_cd_irq+0xa4/0xd0 [mmc_core])
[    6.398121]  r10:ea2db800 r8:e9bc3000 r7:e9bed598 r6:000000dc r5:e9bed524 r4:e9bc3000
[    6.406065] [<bf0aaaf8>] (mmc_gpiod_request_cd_irq [mmc_core]) from [<bf09f3bc>] (mmc_start_host+0x70/0x90 [mmc_core])
[    6.416779]  r6:e9bc3300 r5:00000000 r4:e9bc3000
[    6.421476] [<bf09f34c>] (mmc_start_host [mmc_core]) from [<bf0a061c>] (mmc_add_host+0x54/0x78 [mmc_core])
[    6.431146]  r4:e9bc3000 r3:00000001
[    6.434782] [<bf0a05c8>] (mmc_add_host [mmc_core]) from [<bf134b3c>] (tmio_mmc_host_probe+0x3ac/0x450 [tmio_mmc_core])
[    6.445498]  r5:ffffffe0 r4:00000000
[    6.449119] [<bf134790>] (tmio_mmc_host_probe [tmio_mmc_core]) from [<bf1501e8>] (sh_mobile_sdhi_probe+0x198/0x414 [sh_mobile_sdhi])
[    6.461051]  r10:bf150d04 r9:e9bed598 r8:00000001 r7:ea2db810 r6:ea2db800 r5:e9bc3300
[    6.468958]  r4:e9bed590
[    6.471532] [<bf150050>] (sh_mobile_sdhi_probe [sh_mobile_sdhi]) from [<c02cf220>] (platform_drv_probe+0x60/0xc0)
[    6.481811]  r10:00000011 r9:00000000 r8:bf151464 r7:bf151464 r6:fffffdfb r5:ea2db810
[    6.489712]  r4:00000000
[    6.492271] [<c02cf1c0>] (platform_drv_probe) from [<c02ccf80>] (driver_probe_device+0x224/0x440)
[    6.501156]  r7:c06c45f8 r6:c08e2b44 r5:c08e2b3c r4:ea2db810
[    6.506878] [<c02ccd5c>] (driver_probe_device) from [<c02cd2a0>] (__driver_attach+0x104/0x128)
[    6.515508]  r10:00000000 r9:bf1514c0 r8:c06c4520 r7:00000000 r6:bf151464 r5:ea2db810
[    6.523411]  r4:ea2db844
[    6.525965] [<c02cd19c>] (__driver_attach) from [<c02cae04>] (bus_for_each_dev+0x64/0x98)
[    6.534156]  r6:c02cd19c r5:bf151464 r4:00000000 r3:00000000
[    6.539874] [<c02cada0>] (bus_for_each_dev) from [<c02cc5e4>] (driver_attach+0x2c/0x30)
[    6.547895]  r6:c06ace08 r5:ea294c80 r4:bf151464
[    6.552561] [<c02cc5b8>] (driver_attach) from [<c02cc264>] (bus_add_driver+0x18c/0x268)
[    6.560586] [<c02cc0d8>] (bus_add_driver) from [<c02cdf90>] (driver_register+0x88/0x104)
[    6.568691]  r8:bf153000 r7:00000001 r6:e9ba7a40 r5:c067cfc8 r4:bf151464
[    6.575464] [<c02cdf08>] (driver_register) from [<c02cef80>] (__platform_driver_register+0x50/0x54)
[    6.584523]  r5:c067cfc8 r4:c067cfc8
[    6.588141] [<c02cef30>] (__platform_driver_register) from [<bf153018>] (sh_mobile_sdhi_driver_init+0x18/0x24 [sh_mobile_sdhi])
[    6.599654] [<bf153000>] (sh_mobile_sdhi_driver_init [sh_mobile_sdhi]) from [<c000a884>] (do_one_initcall+0xc0/0x200)
[    6.610292] [<c000a7c4>] (do_one_initcall) from [<c00ccd28>] (do_init_module+0x70/0x1dc)
[    6.618398]  r10:000005fa r9:bf1514c0 r8:c00a1f28 r7:00000001 r6:e94f3fc0 r5:00000001
[    6.626299]  r4:bf1514c0
[    6.628860] [<c00cccb8>] (do_init_module) from [<c00a5368>] (load_module+0x19c8/0x2164)
[    6.636878]  r7:00000001 r6:e955ec00 r5:00000001 r4:e9b73f3c
[    6.642603] [<c00a39a0>] (load_module) from [<c00a5d38>] (SyS_finit_module+0xb0/0xe0)
[    6.650447]  r10:00000000 r9:e9b72000 r8:b6f75330 r7:00000009 r6:00000000 r5:00000000
[    6.658342]  r4:7fffffff
[    6.660901] [<c00a5c88>] (SyS_finit_module) from [<c0011940>] (ret_fast_syscall+0x0/0x34)
[    6.669093]  r8:c0011ae4 r7:0000017b r6:00000000 r5:00000000 r4:00020000

The .irq_request_resources() handler is called with a spinlock held, it thus
can't call the synchronous version of the PM runtime functions.

-- 
Regards,

Laurent Pinchart

Enables PWM1 (brightness control) and PWM2 (PMIC switching frequency
synchronization).

Signed-off-by: Ulrich Hecht <ulrich.hecht+renesas@gmail.com>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>

---
arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts | 23 ++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts b/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts
index 507d6a4..5525637 100644
--- a/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts
+++ b/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts
@@ -189,6 +189,15 @@
 	pinctrl-0 = <&scif_clk_pins>;
 	pinctrl-names = "default";
 
+	pwm1_pins: pwm1 {
+		renesas,groups = "pwm1_a";
+		renesas,function = "pwm1";
+	};
+	pwm2_pins: pwm2 {
+		renesas,groups = "pwm2_a";
+		renesas,function = "pwm2";
+	};
+
 	scif1_pins: scif1 {
 		renesas,groups = "scif1_data_a", "scif1_ctrl";
 		renesas,function = "scif1";
@@ -299,6 +308,20 @@
 	};
 };
 
+&pwm1 {
+	/* brightness control */
+	pinctrl-0 = <&pwm1_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&pwm2 {
+	/* PMIC DC/DC switching frequency synchronization */
+	pinctrl-0 = <&pwm2_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
 &rcar_sound {
 	pinctrl-0 = <&sound_pins &sound_clk_pins>;
 	pinctrl-names = "default";

Re: [RFC PATCH 07/11] GENEVE: Add option to mangle IP IDs on inner headers when using TSO

[Jesse Gross]

On Thu, Apr 7, 2016 at 8:52 PM, Alexander Duyck
<alexander.duyck@gmail.com> wrote:
> Just a thought.  What if I replaced NETIF_F_TSO_FIXEDID with something
> that meant we could mange the IP ID like a NETIF_F_TSO_IPID_MANGLE
> (advice for better name welcome).  Instead of the feature flag meaning
> we are going to transmit packets with a fixed ID it would mean we
> don't care about the ID and are free to mangle it as we see fit.  The
> GSO type can retain the same meaning as far as that requiring the same
> ID for all, but the feature would mean we will take fixed and convert
> it to incrementing, or incrementing and convert it to fixed.

I saw the new version of the code that you posted with this idea and
now that I understand it better, it seems like a reasonable choice to
me - it's nice that it is consistent with GRO and not tunnel specific.
It also makes behavior consistent across drivers in regards to
incrementing IDs in the default case, which was one of my concerns
from before.

Maybe I missed it but I didn't see any checks for the DF bit being set
when we transmit a packet with NETIF_F_TSO_MANGLEID. Even if I am
comfortable mangling my IDs in the DF case, I don't think this would
ever extend to non-DF packets. In the documentation you noted that it
is the driver's responsibility to do this check but I couldn't find it
in either ixgbe or igb. It would also be nice if the core stack could
enforce it somehow as well rather than each driver.

Re: [RFC PATCH 07/11] GENEVE: Add option to mangle IP IDs on inner headers when using TSO

[Alexander Duyck]

On Fri, Apr 8, 2016 at 2:40 PM, Jesse Gross <jesse@kernel.org> wrote:
> On Thu, Apr 7, 2016 at 8:52 PM, Alexander Duyck
> <alexander.duyck@gmail.com> wrote:
>> Just a thought.  What if I replaced NETIF_F_TSO_FIXEDID with something
>> that meant we could mange the IP ID like a NETIF_F_TSO_IPID_MANGLE
>> (advice for better name welcome).  Instead of the feature flag meaning
>> we are going to transmit packets with a fixed ID it would mean we
>> don't care about the ID and are free to mangle it as we see fit.  The
>> GSO type can retain the same meaning as far as that requiring the same
>> ID for all, but the feature would mean we will take fixed and convert
>> it to incrementing, or incrementing and convert it to fixed.
>
> I saw the new version of the code that you posted with this idea and
> now that I understand it better, it seems like a reasonable choice to
> me - it's nice that it is consistent with GRO and not tunnel specific.
> It also makes behavior consistent across drivers in regards to
> incrementing IDs in the default case, which was one of my concerns
> from before.
>
> Maybe I missed it but I didn't see any checks for the DF bit being set
> when we transmit a packet with NETIF_F_TSO_MANGLEID. Even if I am
> comfortable mangling my IDs in the DF case, I don't think this would
> ever extend to non-DF packets. In the documentation you noted that it
> is the driver's responsibility to do this check but I couldn't find it
> in either ixgbe or igb. It would also be nice if the core stack could
> enforce it somehow as well rather than each driver.

Yeah I had glossed over that in the igb and ixgbe patches.  A check is
only really needed for the incrementing to non-incrementing case and I
wasn't sure how common it was to have TCP with an IP header that
didn't set the DF bit.  In the case of the outer headers igb and ixgbe
will increment the IP ID always so we don't have to worry about if DF
is set of not there.  For the inner headers I had fudged it a bit and
didn't add the validation.  If needed I can see about adding that
shortly.

- Alex

Re: [RFC PATCH 07/11] GENEVE: Add option to mangle IP IDs on inner headers when using TSO

[Jesse Gross]

On Fri, Apr 8, 2016 at 7:04 PM, Alexander Duyck
<alexander.duyck@gmail.com> wrote:
> On Fri, Apr 8, 2016 at 2:40 PM, Jesse Gross <jesse@kernel.org> wrote:
>> Maybe I missed it but I didn't see any checks for the DF bit being set
>> when we transmit a packet with NETIF_F_TSO_MANGLEID. Even if I am
>> comfortable mangling my IDs in the DF case, I don't think this would
>> ever extend to non-DF packets. In the documentation you noted that it
>> is the driver's responsibility to do this check but I couldn't find it
>> in either ixgbe or igb. It would also be nice if the core stack could
>> enforce it somehow as well rather than each driver.
>
> Yeah I had glossed over that in the igb and ixgbe patches.  A check is
> only really needed for the incrementing to non-incrementing case and I
> wasn't sure how common it was to have TCP with an IP header that
> didn't set the DF bit.  In the case of the outer headers igb and ixgbe
> will increment the IP ID always so we don't have to worry about if DF
> is set of not there.  For the inner headers I had fudged it a bit and
> didn't add the validation.  If needed I can see about adding that
> shortly.

TCP without the DF bit set is not the default but it is possible (it
can be enabled by setting /proc/sys/net/ipv4/ip_no_pmtu_disc). I also
did a quick check of some Internet services and at least some of them
seem to return TCP without DF, so it's not too rare.

Re: [RFC PATCH 07/11] GENEVE: Add option to mangle IP IDs on inner headers when using TSO

[Alexander Duyck]

On Sat, Apr 9, 2016 at 8:52 AM, Jesse Gross <jesse@kernel.org> wrote:
> On Fri, Apr 8, 2016 at 7:04 PM, Alexander Duyck
> <alexander.duyck@gmail.com> wrote:
>> On Fri, Apr 8, 2016 at 2:40 PM, Jesse Gross <jesse@kernel.org> wrote:
>>> Maybe I missed it but I didn't see any checks for the DF bit being set
>>> when we transmit a packet with NETIF_F_TSO_MANGLEID. Even if I am
>>> comfortable mangling my IDs in the DF case, I don't think this would
>>> ever extend to non-DF packets. In the documentation you noted that it
>>> is the driver's responsibility to do this check but I couldn't find it
>>> in either ixgbe or igb. It would also be nice if the core stack could
>>> enforce it somehow as well rather than each driver.
>>
>> Yeah I had glossed over that in the igb and ixgbe patches.  A check is
>> only really needed for the incrementing to non-incrementing case and I
>> wasn't sure how common it was to have TCP with an IP header that
>> didn't set the DF bit.  In the case of the outer headers igb and ixgbe
>> will increment the IP ID always so we don't have to worry about if DF
>> is set of not there.  For the inner headers I had fudged it a bit and
>> didn't add the validation.  If needed I can see about adding that
>> shortly.
>
> TCP without the DF bit set is not the default but it is possible (it
> can be enabled by setting /proc/sys/net/ipv4/ip_no_pmtu_disc). I also
> did a quick check of some Internet services and at least some of them
> seem to return TCP without DF, so it's not too rare.

For next version I plan to include a check in netif_skb_features that
will clear NETIF_F_TSO_MANGLEID if the DF bit is not set.

- Alex

Re: [RFC PATCH 07/11] GENEVE: Add option to mangle IP IDs on inner headers when using TSO

[Eric Dumazet]

On Sat, 2016-04-09 at 10:36 -0700, Alexander Duyck wrote:

> For next version I plan to include a check in netif_skb_features that
> will clear NETIF_F_TSO_MANGLEID if the DF bit is not set.

So it looks like we slowly but surely make the whole stack damn slow, to
support some extra features.

How many instructions are needed nowadays for netif_skb_features()
alone ?

More than 120 if I am not mistaken, if we count fast path in
skb_network_protocol()

Note: I have a patch to remove the gso_min_segs thing, currently unused.

2 instructions saved ! Woo-hoo !

Re: [RFC PATCH 07/11] GENEVE: Add option to mangle IP IDs on inner headers when using TSO

[Alexander Duyck]

On Sat, Apr 9, 2016 at 11:02 AM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> On Sat, 2016-04-09 at 10:36 -0700, Alexander Duyck wrote:
>
>> For next version I plan to include a check in netif_skb_features that
>> will clear NETIF_F_TSO_MANGLEID if the DF bit is not set.
>
> So it looks like we slowly but surely make the whole stack damn slow, to
> support some extra features.
>
> How many instructions are needed nowadays for netif_skb_features()
> alone ?
>
> More than 120 if I am not mistaken, if we count fast path in
> skb_network_protocol()
>
> Note: I have a patch to remove the gso_min_segs thing, currently unused.
>
> 2 instructions saved ! Woo-hoo !

I was planning to drop the checks for TSO_MANGLEID and GSO_PARTIAL in
a if statment based on skb_is_gso() since I had both GSO_PARTIAL to
check for as well.

- Alex

Re: [PATCH/RFC v2] gpio: rcar: Add Runtime PM handling for interrupts

[Laurent Pinchart]

On Friday 19 Feb 2016 11:59:40 Marc Zyngier wrote:
> On 19/02/16 09:18, Linus Walleij wrote:
> > Top-quoting so everyone on the new To:-line gets the context.
> > 
> > I definately need an indication from an irqchip maintainer like tglx or
> > Marc Z before I merge this. Also, as in reply to the previous letter,
> > coordinate efforts with Jon Hunters similar problem space.
> 
> Seems pretty straightforward to me.
>
> Acked-by: Marc Zyngier <marc.zyngier@arm.com>

Too straightforward to be correct :-/

[    6.232681] BUG: sleeping function called from invalid context at /home/laurent/src/iob/renesas/linux/drivers/base/power/runtime.c:955
[    6.244795] in_atomic(): 1, irqs_disabled(): 128, pid: 658, name: udevd
[    6.251429] CPU: 3 PID: 658 Comm: udevd Tainted: P                4.6.0-rc3 #756
[    6.258844] Hardware name: Generic R8A7790 (Flattened Device Tree)
[    6.265036] Backtrace: 
[    6.267535] [<c0014c98>] (dump_backtrace) from [<c0014fb0>] (show_stack+0x20/0x24)
[    6.275124]  r6:00000000 r5:00000000 r4:60000093 r3:00000000
[    6.280850] [<c0014f90>] (show_stack) from [<c01f614c>] (dump_stack+0x8c/0xac)
[    6.288105] [<c01f60c0>] (dump_stack) from [<c00510c8>] (___might_sleep+0x100/0x158)
[    6.295863]  r5:000003bb r4:c06ca340
[    6.299474] [<c0050fc8>] (___might_sleep) from [<c005118c>] (__might_sleep+0x6c/0xa8)
[    6.307317]  r4:c05b6a24
[    6.309880] [<c0051120>] (__might_sleep) from [<c02d971c>] (__pm_runtime_resume+0x98/0xa0)
[    6.318159]  r6:000000dc r5:00000004 r4:ea280010
[    6.322831] [<c02d9684>] (__pm_runtime_resume) from [<c02282c8>] (gpio_rcar_irq_request_resources+0x2c/0x34)
[    6.332674]  r7:00000000 r6:000000dc r5:e95b3c00 r4:e99f3c00
[    6.338397] [<c022829c>] (gpio_rcar_irq_request_resources) from [<c0077a88>] (__setup_irq+0x24c/0x5dc)
[    6.347724] [<c007783c>] (__setup_irq) from [<c0077ff4>] (request_threaded_irq+0xdc/0x180)
[    6.356004]  r10:bf0aabc8 r9:000000dc r8:e9bc3000 r7:c0075be8 r6:e99f3c00 r5:00002003
[    6.363905]  r4:e95b3c00
[    6.366466] [<c0077f18>] (request_threaded_irq) from [<c007a758>] (devm_request_threaded_irq+0x6c/0xac)
[    6.375874]  r10:ea2db810 r9:ea2db810 r8:00000000 r7:bf0aabc8 r6:000000dc r5:e9bc3000
[    6.383773]  r4:e95b3b50 r3:00002003
[    6.387410] [<c007a6ec>] (devm_request_threaded_irq) from [<bf0aab9c>] (mmc_gpiod_request_cd_irq+0xa4/0xd0 [mmc_core])
[    6.398121]  r10:ea2db800 r8:e9bc3000 r7:e9bed598 r6:000000dc r5:e9bed524 r4:e9bc3000
[    6.406065] [<bf0aaaf8>] (mmc_gpiod_request_cd_irq [mmc_core]) from [<bf09f3bc>] (mmc_start_host+0x70/0x90 [mmc_core])
[    6.416779]  r6:e9bc3300 r5:00000000 r4:e9bc3000
[    6.421476] [<bf09f34c>] (mmc_start_host [mmc_core]) from [<bf0a061c>] (mmc_add_host+0x54/0x78 [mmc_core])
[    6.431146]  r4:e9bc3000 r3:00000001
[    6.434782] [<bf0a05c8>] (mmc_add_host [mmc_core]) from [<bf134b3c>] (tmio_mmc_host_probe+0x3ac/0x450 [tmio_mmc_core])
[    6.445498]  r5:ffffffe0 r4:00000000
[    6.449119] [<bf134790>] (tmio_mmc_host_probe [tmio_mmc_core]) from [<bf1501e8>] (sh_mobile_sdhi_probe+0x198/0x414 [sh_mobile_sdhi])
[    6.461051]  r10:bf150d04 r9:e9bed598 r8:00000001 r7:ea2db810 r6:ea2db800 r5:e9bc3300
[    6.468958]  r4:e9bed590
[    6.471532] [<bf150050>] (sh_mobile_sdhi_probe [sh_mobile_sdhi]) from [<c02cf220>] (platform_drv_probe+0x60/0xc0)
[    6.481811]  r10:00000011 r9:00000000 r8:bf151464 r7:bf151464 r6:fffffdfb r5:ea2db810
[    6.489712]  r4:00000000
[    6.492271] [<c02cf1c0>] (platform_drv_probe) from [<c02ccf80>] (driver_probe_device+0x224/0x440)
[    6.501156]  r7:c06c45f8 r6:c08e2b44 r5:c08e2b3c r4:ea2db810
[    6.506878] [<c02ccd5c>] (driver_probe_device) from [<c02cd2a0>] (__driver_attach+0x104/0x128)
[    6.515508]  r10:00000000 r9:bf1514c0 r8:c06c4520 r7:00000000 r6:bf151464 r5:ea2db810
[    6.523411]  r4:ea2db844
[    6.525965] [<c02cd19c>] (__driver_attach) from [<c02cae04>] (bus_for_each_dev+0x64/0x98)
[    6.534156]  r6:c02cd19c r5:bf151464 r4:00000000 r3:00000000
[    6.539874] [<c02cada0>] (bus_for_each_dev) from [<c02cc5e4>] (driver_attach+0x2c/0x30)
[    6.547895]  r6:c06ace08 r5:ea294c80 r4:bf151464
[    6.552561] [<c02cc5b8>] (driver_attach) from [<c02cc264>] (bus_add_driver+0x18c/0x268)
[    6.560586] [<c02cc0d8>] (bus_add_driver) from [<c02cdf90>] (driver_register+0x88/0x104)
[    6.568691]  r8:bf153000 r7:00000001 r6:e9ba7a40 r5:c067cfc8 r4:bf151464
[    6.575464] [<c02cdf08>] (driver_register) from [<c02cef80>] (__platform_driver_register+0x50/0x54)
[    6.584523]  r5:c067cfc8 r4:c067cfc8
[    6.588141] [<c02cef30>] (__platform_driver_register) from [<bf153018>] (sh_mobile_sdhi_driver_init+0x18/0x24 [sh_mobile_sdhi])
[    6.599654] [<bf153000>] (sh_mobile_sdhi_driver_init [sh_mobile_sdhi]) from [<c000a884>] (do_one_initcall+0xc0/0x200)
[    6.610292] [<c000a7c4>] (do_one_initcall) from [<c00ccd28>] (do_init_module+0x70/0x1dc)
[    6.618398]  r10:000005fa r9:bf1514c0 r8:c00a1f28 r7:00000001 r6:e94f3fc0 r5:00000001
[    6.626299]  r4:bf1514c0
[    6.628860] [<c00cccb8>] (do_init_module) from [<c00a5368>] (load_module+0x19c8/0x2164)
[    6.636878]  r7:00000001 r6:e955ec00 r5:00000001 r4:e9b73f3c
[    6.642603] [<c00a39a0>] (load_module) from [<c00a5d38>] (SyS_finit_module+0xb0/0xe0)
[    6.650447]  r10:00000000 r9:e9b72000 r8:b6f75330 r7:00000009 r6:00000000 r5:00000000
[    6.658342]  r4:7fffffff
[    6.660901] [<c00a5c88>] (SyS_finit_module) from [<c0011940>] (ret_fast_syscall+0x0/0x34)
[    6.669093]  r8:c0011ae4 r7:0000017b r6:00000000 r5:00000000 r4:00020000

The .irq_request_resources() handler is called with a spinlock held, it thus
can't call the synchronous version of the PM runtime functions.

-- 
Regards,

Laurent Pinchart

Re: [PATCH/RFC v2] gpio: rcar: Add Runtime PM handling for interrupts

[Marc Zyngier]

On 11/04/16 17:26, Laurent Pinchart wrote:
> On Friday 19 Feb 2016 11:59:40 Marc Zyngier wrote:
>> On 19/02/16 09:18, Linus Walleij wrote:
>>> Top-quoting so everyone on the new To:-line gets the context.
>>>
>>> I definately need an indication from an irqchip maintainer like tglx or
>>> Marc Z before I merge this. Also, as in reply to the previous letter,
>>> coordinate efforts with Jon Hunters similar problem space.
>>
>> Seems pretty straightforward to me.
>>
>> Acked-by: Marc Zyngier <marc.zyngier@arm.com>
> 
> Too straightforward to be correct :-/
> 
> [    6.232681] BUG: sleeping function called from invalid context at /home/laurent/src/iob/renesas/linux/drivers/base/power/runtime.c:955
> [    6.244795] in_atomic(): 1, irqs_disabled(): 128, pid: 658, name: udevd
> [    6.251429] CPU: 3 PID: 658 Comm: udevd Tainted: P                4.6.0-rc3 #756
> [    6.258844] Hardware name: Generic R8A7790 (Flattened Device Tree)

[...]

Ah! That will teach me a lesson.

> The .irq_request_resources() handler is called with a spinlock held, it thus
> can't call the synchronous version of the PM runtime functions.

OK, so we're back to square one. Is that just a matter of calling the
non-synchronous version? My hunch is that it is not that simple...

Geert?

	M.
-- 
Jazz is not dead. It just smells funny...

Re: [PATCH/RFC v2] gpio: rcar: Add Runtime PM handling for interrupts

[Geert Uytterhoeven]

Hi Marc,

On Mon, Apr 11, 2016 at 6:55 PM, Marc Zyngier <marc.zyngier@arm.com> wrote:
> On 11/04/16 17:26, Laurent Pinchart wrote:
>> On Friday 19 Feb 2016 11:59:40 Marc Zyngier wrote:
>>> On 19/02/16 09:18, Linus Walleij wrote:
>>>> Top-quoting so everyone on the new To:-line gets the context.
>>>>
>>>> I definately need an indication from an irqchip maintainer like tglx or
>>>> Marc Z before I merge this. Also, as in reply to the previous letter,
>>>> coordinate efforts with Jon Hunters similar problem space.
>>>
>>> Seems pretty straightforward to me.
>>>
>>> Acked-by: Marc Zyngier <marc.zyngier@arm.com>
>>
>> Too straightforward to be correct :-/
>>
>> [    6.232681] BUG: sleeping function called from invalid context at /home/laurent/src/iob/renesas/linux/drivers/base/power/runtime.c:955
>> [    6.244795] in_atomic(): 1, irqs_disabled(): 128, pid: 658, name: udevd
>> [    6.251429] CPU: 3 PID: 658 Comm: udevd Tainted: P                4.6.0-rc3 #756
>> [    6.258844] Hardware name: Generic R8A7790 (Flattened Device Tree)
>
> [...]
>
> Ah! That will teach me a lesson.
>
>> The .irq_request_resources() handler is called with a spinlock held, it thus
>> can't call the synchronous version of the PM runtime functions.
>
> OK, so we're back to square one. Is that just a matter of calling the
> non-synchronous version? My hunch is that it is not that simple...
>
> Geert?

Unfortunately it's not that simple.
The irqchip must be runtime-resumed before we can access its registers.

I'm afraid we'll have to keep gpio-rcar runtime-resumed all the time,
i.e. revert both of
b26a719bdb ("gpio: rcar: Add Runtime PM handling for interrupts")
65194cb174 ("gpio: rcar: Fine-grained Runtime PM support")
until Jon Hunter's "genirq: Add runtime power management support for IRQ chips"
(and perhaps a few more patches from his series) is applied.

Gr{oetje,eeting}s,

                        Geert

--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org

In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
                                -- Linus Torvalds

Re: [PATCH/RFC v2] gpio: rcar: Add Runtime PM handling for interrupts

[Linus Walleij]

On Mon, Apr 11, 2016 at 7:18 PM, Geert Uytterhoeven
<geert@linux-m68k.org> wrote:

> I'm afraid we'll have to keep gpio-rcar runtime-resumed all the time,
> i.e. revert both of
> b26a719bdb ("gpio: rcar: Add Runtime PM handling for interrupts")

I have reverted this for fixes.

> 65194cb174 ("gpio: rcar: Fine-grained Runtime PM support")

I reverted this too, with some manual intervention.

> until Jon Hunter's "genirq: Add runtime power management support for IRQ chips"
> (and perhaps a few more patches from his series) is applied.

Yup let's try to solve the big picture problem with Jon.

Yours,
Linus Walleij

[PATCH net-next v2 0/2] BPF updates

[Daniel Borkmann]

This minor set adds a new helper bpf_event_output() for eBPF cls/act
program types which allows to pass events to user space applications.
For details, please see individual patches.

Thanks!

v1 -> v2:
  - Address kbuild bot found compile issue in patch 2
  - Rest as is

Daniel Borkmann (2):
  bpf, trace: add BPF_F_CURRENT_CPU flag for bpf_perf_event_output
  bpf: add event output helper for notifications/sampling/logging

 include/linux/bpf.h      |  2 ++
 include/uapi/linux/bpf.h |  4 ++++
 kernel/bpf/core.c        |  7 +++++++
 kernel/trace/bpf_trace.c | 34 +++++++++++++++++++++++++++++++++-
 net/core/filter.c        |  2 ++
 5 files changed, 48 insertions(+), 1 deletion(-)

-- 
1.9.3

[PATCH net-next v2 1/2] bpf, trace: add BPF_F_CURRENT_CPU flag for bpf_perf_event_output

[Daniel Borkmann]

Add a BPF_F_CURRENT_CPU flag to optimize the use-case where user space has
per-CPU ring buffers and the eBPF program pushes the data into the current
CPU's ring buffer which saves us an extra helper function call in eBPF.
Also, make sure to properly reserve the remaining flags which are not used.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h | 4 ++++
 kernel/trace/bpf_trace.c | 7 ++++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 70eda5a..b7b0fb1 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -347,6 +347,10 @@ enum bpf_func_id {
 #define BPF_F_ZERO_CSUM_TX		(1ULL << 1)
 #define BPF_F_DONT_FRAGMENT		(1ULL << 2)
 
+/* BPF_FUNC_perf_event_output flags. */
+#define BPF_F_INDEX_MASK		0xffffffffULL
+#define BPF_F_CURRENT_CPU		BPF_F_INDEX_MASK
+
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
  */
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 6855878..6bfe55c 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -225,11 +225,12 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
-static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
+static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
 {
 	struct pt_regs *regs = (struct pt_regs *) (long) r1;
 	struct bpf_map *map = (struct bpf_map *) (long) r2;
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	u64 index = flags & BPF_F_INDEX_MASK;
 	void *data = (void *) (long) r4;
 	struct perf_sample_data sample_data;
 	struct perf_event *event;
@@ -239,6 +240,10 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
 		.data = data,
 	};
 
+	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
+		return -EINVAL;
+	if (index == BPF_F_CURRENT_CPU)
+		index = raw_smp_processor_id();
 	if (unlikely(index >= array->map.max_entries))
 		return -E2BIG;
 
-- 
1.9.3

[PATCH net-next v2 2/2] bpf: add event output helper for notifications/sampling/logging

[Daniel Borkmann]

This patch adds a new helper for cls/act programs that can push events
to user space applications. For networking, this can be f.e. for sampling,
debugging, logging purposes or pushing of arbitrary wake-up events. The
idea is similar to a43eec304259 ("bpf: introduce bpf_perf_event_output()
helper") and 39111695b1b8 ("samples: bpf: add bpf_perf_event_output example").

The eBPF program utilizes a perf event array map that user space populates
with fds from perf_event_open(), the eBPF program calls into the helper
f.e. as skb_event_output(skb, &my_map, BPF_F_CURRENT_CPU, raw, sizeof(raw))
so that the raw data is pushed into the fd f.e. at the map index of the
current CPU.

User space can poll/mmap/etc on this and has a data channel for receiving
events that can be post-processed. The nice thing is that since the eBPF
program and user space application making use of it are tightly coupled,
they can define their own arbitrary raw data format and what/when they
want to push.

While f.e. packet headers could be one part of the meta data that is being
pushed, this is not a substitute for things like packet sockets as whole
packet is not being pushed and push is only done in a single direction.
Intention is more of a generically usable, efficient event pipe to applications.
Workflow is that tc can pin the map and applications can attach themselves
e.g. after cls/act setup to one or multiple map slots, demuxing is done by
the eBPF program.

Adding this facility is with minimal effort, it reuses the helper
introduced in a43eec304259 ("bpf: introduce bpf_perf_event_output() helper")
and we get its functionality for free by overloading its BPF_FUNC_ identifier
for cls/act programs, ctx is currently unused, but will be made use of in
future. Example will be added to iproute2's BPF example files.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h      |  2 ++
 kernel/bpf/core.c        |  7 +++++++
 kernel/trace/bpf_trace.c | 27 +++++++++++++++++++++++++++
 net/core/filter.c        |  2 ++
 4 files changed, 38 insertions(+)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5fb3c61..f63afdc 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -169,7 +169,9 @@ u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5);
 u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 void bpf_fd_array_map_clear(struct bpf_map *map);
 bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
+
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
+const struct bpf_func_proto *bpf_get_event_output_proto(void);
 
 #ifdef CONFIG_BPF_SYSCALL
 DECLARE_PER_CPU(int, bpf_prog_active);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index be0abf6..e4248fe 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -764,14 +764,21 @@ const struct bpf_func_proto bpf_map_delete_elem_proto __weak;
 const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
 const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
 const struct bpf_func_proto bpf_ktime_get_ns_proto __weak;
+
 const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak;
 const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak;
 const struct bpf_func_proto bpf_get_current_comm_proto __weak;
+
 const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
 {
 	return NULL;
 }
 
+const struct bpf_func_proto * __weak bpf_get_event_output_proto(void)
+{
+	return NULL;
+}
+
 /* Always built-in helper functions. */
 const struct bpf_func_proto bpf_tail_call_proto = {
 	.func		= NULL,
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 6bfe55c..75cb154 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -277,6 +277,33 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = {
 	.arg5_type	= ARG_CONST_STACK_SIZE,
 };
 
+static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs);
+
+static u64 bpf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
+{
+	struct pt_regs *regs = this_cpu_ptr(&bpf_pt_regs);
+
+	perf_fetch_caller_regs(regs);
+
+	return bpf_perf_event_output((long)regs, r2, flags, r4, size);
+}
+
+static const struct bpf_func_proto bpf_event_output_proto = {
+	.func		= bpf_event_output,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_CONST_MAP_PTR,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_STACK,
+	.arg5_type	= ARG_CONST_STACK_SIZE,
+};
+
+const struct bpf_func_proto *bpf_get_event_output_proto(void)
+{
+	return &bpf_event_output_proto;
+}
+
 static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
diff --git a/net/core/filter.c b/net/core/filter.c
index 5d2ac2b..218e5de 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2039,6 +2039,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
 		return &bpf_redirect_proto;
 	case BPF_FUNC_get_route_realm:
 		return &bpf_get_route_realm_proto;
+	case BPF_FUNC_perf_event_output:
+		return bpf_get_event_output_proto();
 	default:
 		return sk_filter_func_proto(func_id);
 	}
-- 
1.9.3

Re: [PATCH net-next v2 0/2] BPF updates

[David Miller]

From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 18 Apr 2016 21:01:22 +0200

> This minor set adds a new helper bpf_event_output() for eBPF cls/act
> program types which allows to pass events to user space applications.
> For details, please see individual patches.
 ...
> v1 -> v2:
>   - Address kbuild bot found compile issue in patch 2
>   - Rest as is
> 

Series applied, thanks.

[PATCH v2 0/5] mmc: tmio: make CTL_STATUS handling consistent

[Wolfram Sang]

It took me a little to discover that CTL_STATUS has a different handling than
the other registers. CTL_STATUS and CTL_STATUS2, both u16, are merged into a
virtual u32. However, CTL_STATUS2 was also directly accessed.

Clean this up, make this consistent, and document this. Making the driver less
complex and easier to work with.

Tested on Renesas R-Car Gen2 and Gen3.

Changes since V1:

* rebased
* added simons review tags


Wolfram Sang (5):
  mmc: tmio: give read32/write32 functions more descriptive names
  mmc: tmio: use BIT() within defines
  mmc: tmio: use CTL_STATUS consistently
  mmc: tmio/sdhi: distinguish between SCLKDIVEN and ILL_FUNC
  mmc: tmio: document CTL_STATUS handling

 drivers/mmc/host/sh_mobile_sdhi.c |  3 ++-
 drivers/mmc/host/tmio_mmc.h       | 56 ++++++++++++++++++++-------------------
 drivers/mmc/host/tmio_mmc_pio.c   | 24 ++++++++---------
 3 files changed, 43 insertions(+), 40 deletions(-)

-- 
2.7.0

[PATCH v2 1/5] mmc: tmio: give read32/write32 functions more descriptive names

[Wolfram Sang]

From: Wolfram Sang <wsa+renesas@sang-engineering.com>

Looking at the backlogs, I am not the only one who missed that the above
functions do not read u32 from one register, but create a virtual u32
from reading to adjacent u16 registers (which depending on 'bus_shift'
can be up to 8 byte apart). Because this driver supports old hardware
for which we don't have documentation, I first wrongly assumed there was
a variant which had a few u32 registers. Let's give the functions more
descriptive names to make it more obvious what is happening.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
---
 drivers/mmc/host/tmio_mmc.h     |  5 ++---
 drivers/mmc/host/tmio_mmc_pio.c | 22 +++++++++++-----------
 2 files changed, 13 insertions(+), 14 deletions(-)

diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 439fdad2bad91d..e75e5ca220bc0a 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -232,7 +232,7 @@ static inline void sd_ctrl_read16_rep(struct tmio_mmc_host *host, int addr,
 	readsw(host->ctl + (addr << host->bus_shift), buf, count);
 }
 
-static inline u32 sd_ctrl_read32(struct tmio_mmc_host *host, int addr)
+static inline u32 sd_ctrl_read16_and_16_as_32(struct tmio_mmc_host *host, int addr)
 {
 	return readw(host->ctl + (addr << host->bus_shift)) |
 	       readw(host->ctl + ((addr + 2) << host->bus_shift)) << 16;
@@ -254,11 +254,10 @@ static inline void sd_ctrl_write16_rep(struct tmio_mmc_host *host, int addr,
 	writesw(host->ctl + (addr << host->bus_shift), buf, count);
 }
 
-static inline void sd_ctrl_write32(struct tmio_mmc_host *host, int addr, u32 val)
+static inline void sd_ctrl_write32_as_16_and_16(struct tmio_mmc_host *host, int addr, u32 val)
 {
 	writew(val, host->ctl + (addr << host->bus_shift));
 	writew(val >> 16, host->ctl + ((addr + 2) << host->bus_shift));
 }
 
-
 #endif
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index 15e6f6d5a42337..dad2ebd3dc22b4 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -55,18 +55,18 @@
 void tmio_mmc_enable_mmc_irqs(struct tmio_mmc_host *host, u32 i)
 {
 	host->sdcard_irq_mask &= ~(i & TMIO_MASK_IRQ);
-	sd_ctrl_write32(host, CTL_IRQ_MASK, host->sdcard_irq_mask);
+	sd_ctrl_write32_as_16_and_16(host, CTL_IRQ_MASK, host->sdcard_irq_mask);
 }
 
 void tmio_mmc_disable_mmc_irqs(struct tmio_mmc_host *host, u32 i)
 {
 	host->sdcard_irq_mask |= (i & TMIO_MASK_IRQ);
-	sd_ctrl_write32(host, CTL_IRQ_MASK, host->sdcard_irq_mask);
+	sd_ctrl_write32_as_16_and_16(host, CTL_IRQ_MASK, host->sdcard_irq_mask);
 }
 
 static void tmio_mmc_ack_mmc_irqs(struct tmio_mmc_host *host, u32 i)
 {
-	sd_ctrl_write32(host, CTL_STATUS, ~i);
+	sd_ctrl_write32_as_16_and_16(host, CTL_STATUS, ~i);
 }
 
 static void tmio_mmc_init_sg(struct tmio_mmc_host *host, struct mmc_data *data)
@@ -381,7 +381,7 @@ static int tmio_mmc_start_command(struct tmio_mmc_host *host, struct mmc_command
 	tmio_mmc_enable_mmc_irqs(host, irq_mask);
 
 	/* Fire off the command */
-	sd_ctrl_write32(host, CTL_ARG_REG, cmd->arg);
+	sd_ctrl_write32_as_16_and_16(host, CTL_ARG_REG, cmd->arg);
 	sd_ctrl_write16(host, CTL_SD_CMD, c);
 
 	return 0;
@@ -536,7 +536,7 @@ static void tmio_mmc_data_irq(struct tmio_mmc_host *host)
 		goto out;
 
 	if (host->chan_tx && (data->flags & MMC_DATA_WRITE) && !host->force_pio) {
-		u32 status = sd_ctrl_read32(host, CTL_STATUS);
+		u32 status = sd_ctrl_read16_and_16_as_32(host, CTL_STATUS);
 		bool done = false;
 
 		/*
@@ -591,7 +591,7 @@ static void tmio_mmc_cmd_irq(struct tmio_mmc_host *host,
 	 */
 
 	for (i = 3, addr = CTL_RESPONSE ; i >= 0 ; i--, addr += 4)
-		cmd->resp[i] = sd_ctrl_read32(host, addr);
+		cmd->resp[i] = sd_ctrl_read16_and_16_as_32(host, addr);
 
 	if (cmd->flags &  MMC_RSP_136) {
 		cmd->resp[0] = (cmd->resp[0] << 8) | (cmd->resp[1] >> 24);
@@ -708,14 +708,14 @@ irqreturn_t tmio_mmc_irq(int irq, void *devid)
 	struct tmio_mmc_host *host = devid;
 	unsigned int ireg, status;
 
-	status = sd_ctrl_read32(host, CTL_STATUS);
+	status = sd_ctrl_read16_and_16_as_32(host, CTL_STATUS);
 	ireg = status & TMIO_MASK_IRQ & ~host->sdcard_irq_mask;
 
 	pr_debug_status(status);
 	pr_debug_status(ireg);
 
 	/* Clear the status except the interrupt status */
-	sd_ctrl_write32(host, CTL_STATUS, TMIO_MASK_IRQ);
+	sd_ctrl_write32_as_16_and_16(host, CTL_STATUS, TMIO_MASK_IRQ);
 
 	if (__tmio_mmc_card_detect_irq(host, ireg, status))
 		return IRQ_HANDLED;
@@ -961,7 +961,7 @@ static int tmio_mmc_get_ro(struct mmc_host *mmc)
 
 	pm_runtime_get_sync(mmc_dev(mmc));
 	ret = !((pdata->flags & TMIO_MMC_WRPROTECT_DISABLE) ||
-		(sd_ctrl_read32(host, CTL_STATUS) & TMIO_STAT_WRPROTECT));
+		(sd_ctrl_read16_and_16_as_32(host, CTL_STATUS) & TMIO_STAT_WRPROTECT));
 	pm_runtime_mark_last_busy(mmc_dev(mmc));
 	pm_runtime_put_autosuspend(mmc_dev(mmc));
 
@@ -983,7 +983,7 @@ static int tmio_mmc_card_busy(struct mmc_host *mmc)
 {
 	struct tmio_mmc_host *host = mmc_priv(mmc);
 
-	return !(sd_ctrl_read32(host, CTL_STATUS2) & TMIO_STATUS2_DAT0);
+	return !(sd_ctrl_read16_and_16_as_32(host, CTL_STATUS2) & TMIO_STATUS2_DAT0);
 }
 
 static struct mmc_host_ops tmio_mmc_ops = {
@@ -1132,7 +1132,7 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 	tmio_mmc_clk_stop(_host);
 	tmio_mmc_reset(_host);
 
-	_host->sdcard_irq_mask = sd_ctrl_read32(_host, CTL_IRQ_MASK);
+	_host->sdcard_irq_mask = sd_ctrl_read16_and_16_as_32(_host, CTL_IRQ_MASK);
 	tmio_mmc_disable_mmc_irqs(_host, TMIO_MASK_ALL);
 
 	/* Unmask the IRQs we want to know about */
-- 
2.7.0

[PATCH v2 2/5] mmc: tmio: use BIT() within defines

[Wolfram Sang]

From: Wolfram Sang <wsa+renesas@sang-engineering.com>

BIT() makes it easier to match the bits to the datasheet. This is
especially important here, since some variants have different names in
their datasheets (like with Renesas R-Car).

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
---
 drivers/mmc/host/tmio_mmc.h | 44 +++++++++++++++++++++++---------------------
 1 file changed, 23 insertions(+), 21 deletions(-)

diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index e75e5ca220bc0a..74945c1a66ce81 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -49,27 +49,29 @@
 #define CTL_RESET_SDIO 0x1e0
 
 /* Definitions for values the CTRL_STATUS register can take. */
-#define TMIO_STAT_CMDRESPEND    0x00000001
-#define TMIO_STAT_DATAEND       0x00000004
-#define TMIO_STAT_CARD_REMOVE   0x00000008
-#define TMIO_STAT_CARD_INSERT   0x00000010
-#define TMIO_STAT_SIGSTATE      0x00000020
-#define TMIO_STAT_WRPROTECT     0x00000080
-#define TMIO_STAT_CARD_REMOVE_A 0x00000100
-#define TMIO_STAT_CARD_INSERT_A 0x00000200
-#define TMIO_STAT_SIGSTATE_A    0x00000400
-#define TMIO_STAT_CMD_IDX_ERR   0x00010000
-#define TMIO_STAT_CRCFAIL       0x00020000
-#define TMIO_STAT_STOPBIT_ERR   0x00040000
-#define TMIO_STAT_DATATIMEOUT   0x00080000
-#define TMIO_STAT_RXOVERFLOW    0x00100000
-#define TMIO_STAT_TXUNDERRUN    0x00200000
-#define TMIO_STAT_CMDTIMEOUT    0x00400000
-#define TMIO_STAT_RXRDY         0x01000000
-#define TMIO_STAT_TXRQ          0x02000000
-#define TMIO_STAT_ILL_FUNC      0x20000000
-#define TMIO_STAT_CMD_BUSY      0x40000000
-#define TMIO_STAT_ILL_ACCESS    0x80000000
+#define TMIO_STAT_CMDRESPEND    BIT(0)
+#define TMIO_STAT_DATAEND       BIT(2)
+#define TMIO_STAT_CARD_REMOVE   BIT(3)
+#define TMIO_STAT_CARD_INSERT   BIT(4)
+#define TMIO_STAT_SIGSTATE      BIT(5)
+#define TMIO_STAT_WRPROTECT     BIT(7)
+#define TMIO_STAT_CARD_REMOVE_A BIT(8)
+#define TMIO_STAT_CARD_INSERT_A BIT(9)
+#define TMIO_STAT_SIGSTATE_A    BIT(10)
+
+/* These belong technically to CTRL_STATUS2, but the driver merges them */
+#define TMIO_STAT_CMD_IDX_ERR   BIT(16)
+#define TMIO_STAT_CRCFAIL       BIT(17)
+#define TMIO_STAT_STOPBIT_ERR   BIT(18)
+#define TMIO_STAT_DATATIMEOUT   BIT(19)
+#define TMIO_STAT_RXOVERFLOW    BIT(20)
+#define TMIO_STAT_TXUNDERRUN    BIT(21)
+#define TMIO_STAT_CMDTIMEOUT    BIT(22)
+#define TMIO_STAT_RXRDY         BIT(24)
+#define TMIO_STAT_TXRQ          BIT(25)
+#define TMIO_STAT_ILL_FUNC      BIT(29)
+#define TMIO_STAT_CMD_BUSY      BIT(30)
+#define TMIO_STAT_ILL_ACCESS    BIT(31)
 
 #define TMIO_STATUS2_DAT0	BIT(7)
 
-- 
2.7.0

[PATCH v2 3/5] mmc: tmio: use CTL_STATUS consistently

[Wolfram Sang]

From: Wolfram Sang <wsa+renesas@sang-engineering.com>

To prevent confusion, use the virtual u32 CTL_STATUS in card_busy() the
same way as in other parts of this driver.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
---
 drivers/mmc/host/tmio_mmc.h     | 3 +--
 drivers/mmc/host/tmio_mmc_pio.c | 2 +-
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 74945c1a66ce81..55f251fdb78623 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -67,14 +67,13 @@
 #define TMIO_STAT_RXOVERFLOW    BIT(20)
 #define TMIO_STAT_TXUNDERRUN    BIT(21)
 #define TMIO_STAT_CMDTIMEOUT    BIT(22)
+#define TMIO_STAT_DAT0		BIT(23)	/* only known on R-Car so far */
 #define TMIO_STAT_RXRDY         BIT(24)
 #define TMIO_STAT_TXRQ          BIT(25)
 #define TMIO_STAT_ILL_FUNC      BIT(29)
 #define TMIO_STAT_CMD_BUSY      BIT(30)
 #define TMIO_STAT_ILL_ACCESS    BIT(31)
 
-#define TMIO_STATUS2_DAT0	BIT(7)
-
 #define	CLK_CTL_DIV_MASK	0xff
 #define	CLK_CTL_SCLKEN		BIT(8)
 
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index dad2ebd3dc22b4..f4d8b5a741a875 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -983,7 +983,7 @@ static int tmio_mmc_card_busy(struct mmc_host *mmc)
 {
 	struct tmio_mmc_host *host = mmc_priv(mmc);
 
-	return !(sd_ctrl_read16_and_16_as_32(host, CTL_STATUS2) & TMIO_STATUS2_DAT0);
+	return !(sd_ctrl_read16_and_16_as_32(host, CTL_STATUS) & TMIO_STAT_DAT0);
 }
 
 static struct mmc_host_ops tmio_mmc_ops = {
-- 
2.7.0

[PATCH v2 4/5] mmc: tmio/sdhi: distinguish between SCLKDIVEN and ILL_FUNC

[Wolfram Sang]

From: Wolfram Sang <wsa+renesas@sang-engineering.com>

This bit has a different meaning in SDHI and original TMIO. Document
that and use the proper naming.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
---
 drivers/mmc/host/sh_mobile_sdhi.c | 3 ++-
 drivers/mmc/host/tmio_mmc.h       | 3 ++-
 drivers/mmc/host/tmio_mmc_pio.c   | 2 +-
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index b85b87eb55009f..5923ce7e0fccb3 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -244,7 +244,8 @@ static int sh_mobile_sdhi_wait_idle(struct tmio_mmc_host *host)
 {
 	int timeout = 1000;
 
-	while (--timeout && !(sd_ctrl_read16(host, CTL_STATUS2) & (1 << 13)))
+	while (--timeout && !(sd_ctrl_read16_and_16_as_32(host, CTL_STATUS)
+			      & TMIO_STAT_SCLKDIVEN))
 		udelay(1);
 
 	if (!timeout) {
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 55f251fdb78623..8dd5ea4be0a371 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -70,7 +70,8 @@
 #define TMIO_STAT_DAT0		BIT(23)	/* only known on R-Car so far */
 #define TMIO_STAT_RXRDY         BIT(24)
 #define TMIO_STAT_TXRQ          BIT(25)
-#define TMIO_STAT_ILL_FUNC      BIT(29)
+#define TMIO_STAT_ILL_FUNC      BIT(29) /* only when !TMIO_MMC_HAS_IDLE_WAIT */
+#define TMIO_STAT_SCLKDIVEN     BIT(29) /* only when TMIO_MMC_HAS_IDLE_WAIT */
 #define TMIO_STAT_CMD_BUSY      BIT(30)
 #define TMIO_STAT_ILL_ACCESS    BIT(31)
 
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index f4d8b5a741a875..e9b0271a81742a 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -548,7 +548,7 @@ static void tmio_mmc_data_irq(struct tmio_mmc_host *host)
 		 * waiting for one more interrupt fixes the problem.
 		 */
 		if (host->pdata->flags & TMIO_MMC_HAS_IDLE_WAIT) {
-			if (status & TMIO_STAT_ILL_FUNC)
+			if (status & TMIO_STAT_SCLKDIVEN)
 				done = true;
 		} else {
 			if (!(status & TMIO_STAT_CMD_BUSY))
-- 
2.7.0

[PATCH v2 5/5] mmc: tmio: document CTL_STATUS handling

[Wolfram Sang]

From: Wolfram Sang <wsa+renesas@sang-engineering.com>

Now that reading CTL_STATUS is consistent, we can remove CTL_STATUS2 and
document how this is handled internally.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
---
 drivers/mmc/host/tmio_mmc.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 8dd5ea4be0a371..1aac2ad8edf265 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -30,8 +30,9 @@
 #define CTL_STOP_INTERNAL_ACTION 0x08
 #define CTL_XFER_BLK_COUNT 0xa
 #define CTL_RESPONSE 0x0c
+/* driver merges STATUS and following STATUS2 */
 #define CTL_STATUS 0x1c
-#define CTL_STATUS2 0x1e
+/* driver merges IRQ_MASK and following IRQ_MASK2 */
 #define CTL_IRQ_MASK 0x20
 #define CTL_SD_CARD_CLK_CTL 0x24
 #define CTL_SD_XFER_LEN 0x26
-- 
2.7.0

Re: [PATCH v2 0/5] mmc: tmio: make CTL_STATUS handling consistent

[Ulf Hansson]

On 26 April 2016 at 18:53, Wolfram Sang <wsa@the-dreams.de> wrote:
> It took me a little to discover that CTL_STATUS has a different handling than
> the other registers. CTL_STATUS and CTL_STATUS2, both u16, are merged into a
> virtual u32. However, CTL_STATUS2 was also directly accessed.
>
> Clean this up, make this consistent, and document this. Making the driver less
> complex and easier to work with.
>
> Tested on Renesas R-Car Gen2 and Gen3.
>
> Changes since V1:
>
> * rebased
> * added simons review tags
>
>
> Wolfram Sang (5):
>   mmc: tmio: give read32/write32 functions more descriptive names
>   mmc: tmio: use BIT() within defines
>   mmc: tmio: use CTL_STATUS consistently
>   mmc: tmio/sdhi: distinguish between SCLKDIVEN and ILL_FUNC
>   mmc: tmio: document CTL_STATUS handling
>
>  drivers/mmc/host/sh_mobile_sdhi.c |  3 ++-
>  drivers/mmc/host/tmio_mmc.h       | 56 ++++++++++++++++++++-------------------
>  drivers/mmc/host/tmio_mmc_pio.c   | 24 ++++++++---------
>  3 files changed, 43 insertions(+), 40 deletions(-)
>
> --
> 2.7.0
>

They still don't apply, sorry.

Are you re-basing towards my mmc tree's next branch?

Kind regards
Uffe

Re: [PATCH v3 1/6] pwm: rcar: Use ARCH_RENESAS

[Thierry Reding]

[-- Attachment #1: Type: text/plain, Size: 568 bytes --]

On Thu, Mar 31, 2016 at 01:39:11PM +0200, Ulrich Hecht wrote:
> From: Ryo Kodama <ryo.kodama.vz@renesas.com>
> 
> Replace ARCH_RCAR_GEN{1,2} with ARCH_RENESAS in order to support R-Car Gen3.
> 
> Signed-off-by: Ryo Kodama <ryo.kodama.vz@renesas.com>
> Signed-off-by: Harunobu Kurokawa <harunobu.kurokawa.dn@renesas.com>
> Signed-off-by: Ulrich Hecht <ulrich.hecht+renesas@gmail.com>
> Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
> ---
>  drivers/pwm/Kconfig | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)

Applied, thanks.

Thierry

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]

Re: [PATCH v3 5/6] pwm: add R-Car H3 device tree bindings

[Thierry Reding]

[-- Attachment #1: Type: text/plain, Size: 317 bytes --]

On Thu, Mar 31, 2016 at 01:39:15PM +0200, Ulrich Hecht wrote:
> Signed-off-by: Ulrich Hecht <ulrich.hecht+renesas@gmail.com>
> Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
> ---
>  Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt | 1 +
>  1 file changed, 1 insertion(+)

Applied, thanks.

Thierry

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]

Re: [patch net-next 0/5] mlxsw: small driver update

[David Miller]

From: Jiri Pirko <jiri@resnulli.us>
Date: Mon,  9 Jan 2017 11:25:43 +0100

> This patchset contains various small "non-net" fixes and enhancements.

Series applied, thanks Jiri.

[patch net-next 0/5] mlxsw: small driver update

[Jiri Pirko]

From: Jiri Pirko <jiri@mellanox.com>

This patchset contains various small "non-net" fixes and enhancements.

Elad Raz (2):
  mlxsw: Fix mlxsw_i2c_write return value
  mlxsw: cmd: Fix API name comments for event-queues

Yotam Gigi (3):
  mlxsw: spectrum: Make the add_matchall_tc_entry symmetric
  mlxsw: spectrum: Fix order of commands in port remove function
  mlxsw: spectrum: Change ENOTSUPP to EOPNOTSUPP

 drivers/net/ethernet/mellanox/mlxsw/cmd.h      |  10 +--
 drivers/net/ethernet/mellanox/mlxsw/i2c.c      |   2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 101 +++++++++++++------------
 3 files changed, 59 insertions(+), 54 deletions(-)

-- 
2.7.4

Re: [patch net-next 0/5] mlxsw: small driver update

[David Miller]

From: Jiri Pirko <jiri@resnulli.us>
Date: Thu, 27 Oct 2016 15:12:56 +0200

> For details, see individual patches.

Series applied, thanks.

[patch net-next 0/5] mlxsw: small driver update

[Jiri Pirko]

From: Jiri Pirko <jiri@mellanox.com>

For details, see individual patches.

Ido Schimmel (1):
  mlxsw: spectrum: Remove extra whitespace

Jiri Pirko (4):
  mlxsw: pci: Rename header with HW definitions
  mlxsw: Move PCI id table definitions into driver modules
  mlxsw: spectrum: Set physical device for port netdevice
  mlxsw: switchx2: Set physical device for port netdevice

 drivers/net/ethernet/mellanox/mlxsw/Kconfig        |   4 +-
 drivers/net/ethernet/mellanox/mlxsw/core.c         |  14 --
 drivers/net/ethernet/mellanox/mlxsw/core.h         |   8 -
 drivers/net/ethernet/mellanox/mlxsw/pci.c          |  56 ++---
 drivers/net/ethernet/mellanox/mlxsw/pci.h          | 206 ++----------------
 drivers/net/ethernet/mellanox/mlxsw/pci_hw.h       | 229 +++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     |  26 ++-
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  |   2 +-
 drivers/net/ethernet/mellanox/mlxsw/switchx2.c     |  35 +++-
 9 files changed, 323 insertions(+), 257 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlxsw/pci_hw.h

-- 
2.5.5