* [PATCH 1/1] arm64: Correcting format specifier for printing 64 bit addresses
From: Maninder Singh @ 2016-12-05 8:09 UTC (permalink / raw)
To: linux-arm-kernel
This patch corrects format specifier for printing 64 bit addresses.
Signed-off-by: Maninder Singh <maninder1.s@samsung.com>
Signed-off-by: Vaneet Narang <v.narang@samsung.com>
---
arch/arm64/kernel/signal.c | 2 +-
arch/arm64/kvm/sys_regs.c | 8 ++++++--
arch/arm64/mm/fault.c | 15 ++++++++++-----
arch/arm64/mm/mmu.c | 4 ++--
4 files changed, 19 insertions(+), 10 deletions(-)
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index c7b6de6..c89d5fd 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -155,7 +155,7 @@ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
badframe:
if (show_unhandled_signals)
- pr_info_ratelimited("%s[%d]: bad frame in %s: pc=%08llx sp=%08llx\n",
+ pr_info_ratelimited("%s[%d]: bad frame in %s: pc=%016llx sp=%016llx\n",
current->comm, task_pid_nr(current), __func__,
regs->pc, regs->sp);
force_sig(SIGSEGV, current);
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 87e7e66..89bf5c1 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1554,8 +1554,12 @@ static void unhandled_cp_access(struct kvm_vcpu *vcpu,
WARN_ON(1);
}
- kvm_err("Unsupported guest CP%d access at: %08lx\n",
- cp, *vcpu_pc(vcpu));
+ if (params->is_32bit)
+ kvm_err("Unsupported guest CP%d access at: %08lx\n",
+ cp, *vcpu_pc(vcpu));
+ else
+ kvm_err("Unsupported guest CP%d access at: %016lx\n",
+ cp, *vcpu_pc(vcpu));
print_sys_reg_instr(params);
kvm_inject_undefined(vcpu);
}
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index a78a5c4..d96a42a 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -77,7 +77,7 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
pr_alert("pgd = %p\n", mm->pgd);
pgd = pgd_offset(mm, addr);
- pr_alert("[%08lx] *pgd=%016llx", addr, pgd_val(*pgd));
+ pr_alert("[%016lx] *pgd=%016llx", addr, pgd_val(*pgd));
do {
pud_t *pud;
@@ -177,7 +177,7 @@ static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr,
* No handler, we'll have to terminate things with extreme prejudice.
*/
bust_spinlocks(1);
- pr_alert("Unable to handle kernel %s at virtual address %08lx\n",
+ pr_alert("Unable to handle kernel %s at virtual address %016lx\n",
(addr < PAGE_SIZE) ? "NULL pointer dereference" :
"paging request", addr);
@@ -198,9 +198,14 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
struct siginfo si;
if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) {
- pr_info("%s[%d]: unhandled %s (%d)@0x%08lx, esr 0x%03x\n",
- tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
- addr, esr);
+ if (compat_user_mode(regs))
+ pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
+ tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
+ addr, esr);
+ else
+ pr_info("%s[%d]: unhandled %s (%d) at 0x%016lx, esr 0x%03x\n",
+ tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
+ addr, esr);
show_pte(tsk->mm, addr);
show_regs(regs);
}
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 17243e4..cbf444c 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -683,9 +683,9 @@ void __init early_fixmap_init(void)
pr_warn("pmd %p != %p, %p\n",
pmd, fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)),
fixmap_pmd(fix_to_virt(FIX_BTMAP_END)));
- pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n",
+ pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %016lx\n",
fix_to_virt(FIX_BTMAP_BEGIN));
- pr_warn("fix_to_virt(FIX_BTMAP_END): %08lx\n",
+ pr_warn("fix_to_virt(FIX_BTMAP_END): %016lx\n",
fix_to_virt(FIX_BTMAP_END));
pr_warn("FIX_BTMAP_END: %d\n", FIX_BTMAP_END);
--
1.9.1
^ permalink raw reply related
* [PATCH 1/2] ARM: dts: sun8i: Specify memblock for Nano Pi M1
From: Maxime Ripard @ 2016-12-05 8:09 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <20161205020032.26586-1-woogyom.kim@gmail.com>
On Mon, Dec 05, 2016 at 11:00:31AM +0900, Milo Kim wrote:
> The board has DDR3 512MB. This patch helps scanning the memory and
> adding memblock through the DT.
>
> Signed-off-by: Milo Kim <woogyom.kim@gmail.com>
> ---
> arch/arm/boot/dts/sun8i-h3-nanopi-m1.dts | 5 +++++
> 1 file changed, 5 insertions(+)
>
> diff --git a/arch/arm/boot/dts/sun8i-h3-nanopi-m1.dts b/arch/arm/boot/dts/sun8i-h3-nanopi-m1.dts
> index ec63d10..be3668f 100644
> --- a/arch/arm/boot/dts/sun8i-h3-nanopi-m1.dts
> +++ b/arch/arm/boot/dts/sun8i-h3-nanopi-m1.dts
> @@ -45,6 +45,11 @@
> / {
> model = "FriendlyArm NanoPi M1";
> compatible = "friendlyarm,nanopi-m1", "allwinner,sun8i-h3";
> +
> + memory at 40000000 {
> + device_type = "memory";
> + reg = <0x40000000 0x20000000>;
> + };
U-boot will fill that up, so there's no need to put it there.
Maxime
--
Maxime Ripard, Free Electrons
Embedded Linux and Kernel engineering
http://free-electrons.com
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 801 bytes
Desc: not available
URL: <http://lists.infradead.org/pipermail/linux-arm-kernel/attachments/20161205/a219cc4b/attachment.sig>
^ permalink raw reply
* [PATCH 1/1] arm64: Correcting format specifier for printing 64 bit addresses
From: Maninder Singh @ 2016-12-05 8:06 UTC (permalink / raw)
To: linux-arm-kernel
This patch corrects format specifier for printing 64 bit addresses.
Signed-off-by: Maninder Singh <maninder1.s@samsung.com>
Signed-off-by: Vaneet Narang <v.narang@samsung.com>
---
arch/arm64/kernel/signal.c | 2 +-
arch/arm64/kvm/sys_regs.c | 8 ++++++--
arch/arm64/mm/fault.c | 15 ++++++++++-----
arch/arm64/mm/mmu.c | 4 ++--
4 files changed, 19 insertions(+), 10 deletions(-)
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index c7b6de6..c89d5fd 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -155,7 +155,7 @@ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
badframe:
if (show_unhandled_signals)
- pr_info_ratelimited("%s[%d]: bad frame in %s: pc=%08llx sp=%08llx\n",
+ pr_info_ratelimited("%s[%d]: bad frame in %s: pc=%016llx sp=%016llx\n",
current->comm, task_pid_nr(current), __func__,
regs->pc, regs->sp);
force_sig(SIGSEGV, current);
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 87e7e66..89bf5c1 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1554,8 +1554,12 @@ static void unhandled_cp_access(struct kvm_vcpu *vcpu,
WARN_ON(1);
}
- kvm_err("Unsupported guest CP%d access at: %08lx\n",
- cp, *vcpu_pc(vcpu));
+ if (params->is_32bit)
+ kvm_err("Unsupported guest CP%d access at: %08lx\n",
+ cp, *vcpu_pc(vcpu));
+ else
+ kvm_err("Unsupported guest CP%d access at: %016lx\n",
+ cp, *vcpu_pc(vcpu));
print_sys_reg_instr(params);
kvm_inject_undefined(vcpu);
}
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index a78a5c4..d96a42a 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -77,7 +77,7 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
pr_alert("pgd = %p\n", mm->pgd);
pgd = pgd_offset(mm, addr);
- pr_alert("[%08lx] *pgd=%016llx", addr, pgd_val(*pgd));
+ pr_alert("[%016lx] *pgd=%016llx", addr, pgd_val(*pgd));
do {
pud_t *pud;
@@ -177,7 +177,7 @@ static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr,
* No handler, we'll have to terminate things with extreme prejudice.
*/
bust_spinlocks(1);
- pr_alert("Unable to handle kernel %s at virtual address %08lx\n",
+ pr_alert("Unable to handle kernel %s at virtual address %016lx\n",
(addr < PAGE_SIZE) ? "NULL pointer dereference" :
"paging request", addr);
@@ -198,9 +198,14 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
struct siginfo si;
if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) {
- pr_info("%s[%d]: unhandled %s (%d)@0x%08lx, esr 0x%03x\n",
- tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
- addr, esr);
+ if (compat_user_mode(regs))
+ pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
+ tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
+ addr, esr);
+ else
+ pr_info("%s[%d]: unhandled %s (%d) at 0x%016lx, esr 0x%03x\n",
+ tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
+ addr, esr);
show_pte(tsk->mm, addr);
show_regs(regs);
}
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 17243e4..cbf444c 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -683,9 +683,9 @@ void __init early_fixmap_init(void)
pr_warn("pmd %p != %p, %p\n",
pmd, fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)),
fixmap_pmd(fix_to_virt(FIX_BTMAP_END)));
- pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n",
+ pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %016lx\n",
fix_to_virt(FIX_BTMAP_BEGIN));
- pr_warn("fix_to_virt(FIX_BTMAP_END): %08lx\n",
+ pr_warn("fix_to_virt(FIX_BTMAP_END): %016lx\n",
fix_to_virt(FIX_BTMAP_END));
pr_warn("FIX_BTMAP_END: %d\n", FIX_BTMAP_END);
--
1.9.1
^ permalink raw reply related
* [PATCH] i2c: rk3x: keep i2c irq ON in suspend
From: David Wu @ 2016-12-05 8:02 UTC (permalink / raw)
To: linux-arm-kernel
During suspend there may still be some i2c access happening.
And if we don't keep i2c irq ON, there may be i2c access timeout if
i2c is in irq mode of operation.
Signed-off-by: David Wu <david.wu@rock-chips.com>
---
drivers/i2c/busses/i2c-rk3x.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c
index df22066..67af32a 100644
--- a/drivers/i2c/busses/i2c-rk3x.c
+++ b/drivers/i2c/busses/i2c-rk3x.c
@@ -1261,7 +1261,7 @@ static int rk3x_i2c_probe(struct platform_device *pdev)
}
ret = devm_request_irq(&pdev->dev, irq, rk3x_i2c_irq,
- 0, dev_name(&pdev->dev), i2c);
+ IRQF_NO_SUSPEND, dev_name(&pdev->dev), i2c);
if (ret < 0) {
dev_err(&pdev->dev, "cannot request IRQ\n");
return ret;
--
1.9.1
^ permalink raw reply related
* [PATCH v3 4/7] PWM: add pwm driver for stm32 plaftorm
From: Thierry Reding @ 2016-12-05 7:23 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <1480673842-20804-5-git-send-email-benjamin.gaignard@st.com>
On Fri, Dec 02, 2016 at 11:17:19AM +0100, Benjamin Gaignard wrote:
> This driver add support for pwm driver on stm32 platform.
"adds". Also please use PWM in prose because it's an abbreviation.
> The SoC have multiple instances of the hardware IP and each
> of them could have small differences: number of channels,
> complementary output, counter register size...
> Use DT parameters to handle those differentes configuration
"different configurations"
>
> version 2:
> - only keep one comptatible
> - use DT paramaters to discover hardware block configuration
"parameters"
>
> Signed-off-by: Benjamin Gaignard <benjamin.gaignard@st.com>
> ---
> drivers/pwm/Kconfig | 8 ++
> drivers/pwm/Makefile | 1 +
> drivers/pwm/pwm-stm32.c | 285 ++++++++++++++++++++++++++++++++++++++++++++++++
> 3 files changed, 294 insertions(+)
> create mode 100644 drivers/pwm/pwm-stm32.c
>
> diff --git a/drivers/pwm/Kconfig b/drivers/pwm/Kconfig
> index bf01288..a89fdba 100644
> --- a/drivers/pwm/Kconfig
> +++ b/drivers/pwm/Kconfig
> @@ -388,6 +388,14 @@ config PWM_STI
> To compile this driver as a module, choose M here: the module
> will be called pwm-sti.
>
> +config PWM_STM32
> + bool "STMicroelectronics STM32 PWM"
> + depends on ARCH_STM32
> + depends on OF
> + select MFD_STM32_GP_TIMER
Should that be a "depends on"?
> + help
> + Generic PWM framework driver for STM32 SoCs.
> +
> config PWM_STMPE
> bool "STMPE expander PWM export"
> depends on MFD_STMPE
> diff --git a/drivers/pwm/Makefile b/drivers/pwm/Makefile
> index 1194c54..5aa9308 100644
> --- a/drivers/pwm/Makefile
> +++ b/drivers/pwm/Makefile
> @@ -37,6 +37,7 @@ obj-$(CONFIG_PWM_ROCKCHIP) += pwm-rockchip.o
> obj-$(CONFIG_PWM_SAMSUNG) += pwm-samsung.o
> obj-$(CONFIG_PWM_SPEAR) += pwm-spear.o
> obj-$(CONFIG_PWM_STI) += pwm-sti.o
> +obj-$(CONFIG_PWM_STM32) += pwm-stm32.o
> obj-$(CONFIG_PWM_STMPE) += pwm-stmpe.o
> obj-$(CONFIG_PWM_SUN4I) += pwm-sun4i.o
> obj-$(CONFIG_PWM_TEGRA) += pwm-tegra.o
> diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c
> new file mode 100644
> index 0000000..a362f63
> --- /dev/null
> +++ b/drivers/pwm/pwm-stm32.c
> @@ -0,0 +1,285 @@
> +/*
> + * Copyright (C) STMicroelectronics 2016
> + * Author: Gerald Baeza <gerald.baeza@st.com>
Could use a blank line between the above. Also, please use a single
space after : for consistency.
> + * License terms: GNU General Public License (GPL), version 2
Here too.
> + *
> + * Inspired by timer-stm32.c from Maxime Coquelin
> + * pwm-atmel.c from Bo Shen
> + */
> +
> +#include <linux/of.h>
> +#include <linux/module.h>
> +#include <linux/platform_device.h>
> +#include <linux/pwm.h>
Please sort these alphabetically.
> +
> +#include <linux/mfd/stm32-gptimer.h>
> +
> +#define DRIVER_NAME "stm32-pwm"
> +
> +#define CAP_COMPLEMENTARY BIT(0)
> +#define CAP_32BITS_COUNTER BIT(1)
> +#define CAP_BREAKINPUT BIT(2)
> +#define CAP_BREAKINPUT_POLARITY BIT(3)
Just make these boolean. Makes the conditionals a lot simpler to read.
> +
> +struct stm32_pwm_dev {
No need for the _dev suffix.
> + struct device *dev;
> + struct clk *clk;
> + struct regmap *regmap;
> + struct pwm_chip chip;
It's slightly more efficient to put this as first field because then
to_stm32_pwm() becomes a no-op.
> + int caps;
> + int npwm;
unsigned int, please.
> + u32 polarity;
Maybe use a prefix here to stress that it is the polarity of the
complementary output. Otherwise one might take it for the PWM signal's
polarity that's already part of the PWM state.
> +};
> +
> +#define to_stm32_pwm_dev(x) container_of(chip, struct stm32_pwm_dev, chip)
Please turn this into a static inline.
> +
> +static u32 __active_channels(struct stm32_pwm_dev *pwm_dev)
No need for a __ prefix.
> +{
> + u32 ccer;
> +
> + regmap_read(pwm_dev->regmap, TIM_CCER, &ccer);
> +
> + return ccer & TIM_CCER_CCXE;
> +}
> +
> +static int write_ccrx(struct stm32_pwm_dev *dev, struct pwm_device *pwm,
> + u32 ccr)
u32 value, perhaps? I first mistook this to be a register offset.
> +{
> + switch (pwm->hwpwm) {
> + case 0:
> + return regmap_write(dev->regmap, TIM_CCR1, ccr);
> + case 1:
> + return regmap_write(dev->regmap, TIM_CCR2, ccr);
> + case 2:
> + return regmap_write(dev->regmap, TIM_CCR3, ccr);
> + case 3:
> + return regmap_write(dev->regmap, TIM_CCR4, ccr);
> + }
> + return -EINVAL;
> +}
> +
> +static int stm32_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
> + int duty_ns, int period_ns)
Please implement this as an atomic PWM driver, I don't want new drivers
to use the legacy callbacks.
> +{
> + struct stm32_pwm_dev *dev = to_stm32_pwm_dev(chip);
I think something like "stm", or "priv" would be more appropriate here.
If you ever need access to a struct device, you'll be hard-pressed to
find a good name for it.
> + unsigned long long prd, div, dty;
> + int prescaler = 0;
If this can never be negative, please make it unsigned int.
> + u32 max_arr = 0xFFFF, ccmr, mask, shift, bdtr;
> +
> + if (dev->caps & CAP_32BITS_COUNTER)
> + max_arr = 0xFFFFFFFF;
I prefer lower-case hexadecimal digits.
> +
> + /* Period and prescaler values depends of clock rate */
"depend on"
> + div = (unsigned long long)clk_get_rate(dev->clk) * period_ns;
> +
> + do_div(div, NSEC_PER_SEC);
> + prd = div;
> +
> + while (div > max_arr) {
> + prescaler++;
> + div = prd;
> + do_div(div, (prescaler + 1));
> + }
> + prd = div;
Blank line after blocks, please.
> +
> + if (prescaler > MAX_TIM_PSC) {
> + dev_err(chip->dev, "prescaler exceeds the maximum value\n");
> + return -EINVAL;
> + }
> +
> + /* All channels share the same prescaler and counter so
> + * when two channels are active at the same we can't change them
> + */
This isn't proper block comment style. Also, please use all of the
columns at your disposal.
> + if (__active_channels(dev) & ~(1 << pwm->hwpwm * 4)) {
> + u32 psc, arr;
> +
> + regmap_read(dev->regmap, TIM_PSC, &psc);
> + regmap_read(dev->regmap, TIM_ARR, &arr);
> +
> + if ((psc != prescaler) || (arr != prd - 1))
> + return -EINVAL;
Maybe -EBUSY to differentiate from other error cases?
> + }
> +
> + regmap_write(dev->regmap, TIM_PSC, prescaler);
> + regmap_write(dev->regmap, TIM_ARR, prd - 1);
> + regmap_update_bits(dev->regmap, TIM_CR1, TIM_CR1_ARPE, TIM_CR1_ARPE);
> +
> + /* Calculate the duty cycles */
> + dty = prd * duty_ns;
> + do_div(dty, period_ns);
> +
> + write_ccrx(dev, pwm, dty);
> +
> + /* Configure output mode */
> + shift = (pwm->hwpwm & 0x1) * 8;
> + ccmr = (TIM_CCMR_PE | TIM_CCMR_M1) << shift;
> + mask = 0xFF << shift;
> +
> + if (pwm->hwpwm & 0x2)
This looks as though TIM_CCMR1 is used for channels 0 and 1, while
TIM_CCMR2 is used for channels 2 and 3. Wouldn't it be more natural to
make the conditional above:
if (pwm->hwpwm >= 2)
? Or perhaps better yet:
if (pwm->hwpwm < 2)
/* update TIM_CCMR1 */
else
/* update TIM_CCMR2 */
The other alternative, which might make the code slightly more readable,
would be to get rid of all these conditionals by parameterizing the
offsets per PWM channel. The PWM subsystem has a means of storing per-
channel chip-specific data (see pwm_{set,get}_chip_data()). It might be
a little overkill for this particular driver, given that the number of
conditionals is fairly small.
> + regmap_update_bits(dev->regmap, TIM_CCMR2, mask, ccmr);
> + else
> + regmap_update_bits(dev->regmap, TIM_CCMR1, mask, ccmr);
> +
> + if (!(dev->caps & CAP_BREAKINPUT))
> + return 0;
If you make these capabilities boolean, it becomes much more readable,
especially for negations:
if (!dev->has_breakinput)
> +
> + bdtr = TIM_BDTR_MOE | TIM_BDTR_AOE;
> +
> + if (dev->caps & CAP_BREAKINPUT_POLARITY)
> + bdtr |= TIM_BDTR_BKE;
> +
> + if (dev->polarity)
> + bdtr |= TIM_BDTR_BKP;
> +
> + regmap_update_bits(dev->regmap, TIM_BDTR,
> + TIM_BDTR_MOE | TIM_BDTR_AOE |
> + TIM_BDTR_BKP | TIM_BDTR_BKE,
> + bdtr);
> +
> + return 0;
> +}
> +
> +static int stm32_pwm_set_polarity(struct pwm_chip *chip, struct pwm_device *pwm,
> + enum pwm_polarity polarity)
> +{
> + u32 mask;
> + struct stm32_pwm_dev *dev = to_stm32_pwm_dev(chip);
> +
> + mask = TIM_CCER_CC1P << (pwm->hwpwm * 4);
> + if (dev->caps & CAP_COMPLEMENTARY)
> + mask |= TIM_CCER_CC1NP << (pwm->hwpwm * 4);
> +
> + regmap_update_bits(dev->regmap, TIM_CCER, mask,
> + polarity == PWM_POLARITY_NORMAL ? 0 : mask);
> +
> + return 0;
> +}
> +
> +static int stm32_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
> +{
> + u32 mask;
> + struct stm32_pwm_dev *dev = to_stm32_pwm_dev(chip);
> +
> + clk_enable(dev->clk);
> +
> + /* Enable channel */
> + mask = TIM_CCER_CC1E << (pwm->hwpwm * 4);
> + if (dev->caps & CAP_COMPLEMENTARY)
> + mask |= TIM_CCER_CC1NE << (pwm->hwpwm * 4);
> +
> + regmap_update_bits(dev->regmap, TIM_CCER, mask, mask);
> +
> + /* Make sure that registers are updated */
> + regmap_update_bits(dev->regmap, TIM_EGR, TIM_EGR_UG, TIM_EGR_UG);
> +
> + /* Enable controller */
> + regmap_update_bits(dev->regmap, TIM_CR1, TIM_CR1_CEN, TIM_CR1_CEN);
> +
> + return 0;
> +}
> +
> +static void stm32_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
> +{
> + u32 mask;
> + struct stm32_pwm_dev *dev = to_stm32_pwm_dev(chip);
> +
> + /* Disable channel */
> + mask = TIM_CCER_CC1E << (pwm->hwpwm * 4);
> + if (dev->caps & CAP_COMPLEMENTARY)
> + mask |= TIM_CCER_CC1NE << (pwm->hwpwm * 4);
> +
> + regmap_update_bits(dev->regmap, TIM_CCER, mask, 0);
> +
> + /* When all channels are disabled, we can disable the controller */
> + if (!__active_channels(dev))
> + regmap_update_bits(dev->regmap, TIM_CR1, TIM_CR1_CEN, 0);
> +
> + clk_disable(dev->clk);
> +}
All of the above can be folded into the ->apply() hook for atomic PWM
support.
Also, in the above you use clk_enable() in the ->enable() callback and
clk_disable() in ->disable(). If you need the clock to access registers
you'll have to enabled it in the others as well because there are no
guarantees that configuration will only happen between ->enable() and
->disable(). Atomic PWM simplifies this a bit, but you still need to be
careful about when to enable the clock in your ->apply() hook.
> +
> +static const struct pwm_ops stm32pwm_ops = {
> + .config = stm32_pwm_config,
> + .set_polarity = stm32_pwm_set_polarity,
> + .enable = stm32_pwm_enable,
> + .disable = stm32_pwm_disable,
> +};
You need to set the .owner field as well.
> +
> +static int stm32_pwm_probe(struct platform_device *pdev)
> +{
> + struct device *dev = &pdev->dev;
> + struct device_node *np = dev->of_node;
> + struct stm32_gptimer_dev *mfd = dev_get_drvdata(pdev->dev.parent);
> + struct stm32_pwm_dev *pwm;
> + int ret;
> +
> + pwm = devm_kzalloc(dev, sizeof(*pwm), GFP_KERNEL);
> + if (!pwm)
> + return -ENOMEM;
> +
> + pwm->regmap = mfd->regmap;
> + pwm->clk = mfd->clk;
> +
> + if (!pwm->regmap || !pwm->clk)
> + return -EINVAL;
> +
> + if (of_property_read_bool(np, "st,complementary"))
> + pwm->caps |= CAP_COMPLEMENTARY;
> +
> + if (of_property_read_bool(np, "st,32bits-counter"))
> + pwm->caps |= CAP_32BITS_COUNTER;
> +
> + if (of_property_read_bool(np, "st,breakinput"))
> + pwm->caps |= CAP_BREAKINPUT;
> +
> + if (!of_property_read_u32(np, "st,breakinput-polarity", &pwm->polarity))
> + pwm->caps |= CAP_BREAKINPUT_POLARITY;
> +
> + of_property_read_u32(np, "st,pwm-num-chan", &pwm->npwm);
> +
> + pwm->chip.base = -1;
> + pwm->chip.dev = dev;
> + pwm->chip.ops = &stm32pwm_ops;
> + pwm->chip.npwm = pwm->npwm;
> +
> + ret = pwmchip_add(&pwm->chip);
> + if (ret < 0)
> + return ret;
> +
> + platform_set_drvdata(pdev, pwm);
> +
> + return 0;
> +}
> +
> +static int stm32_pwm_remove(struct platform_device *pdev)
> +{
> + struct stm32_pwm_dev *pwm = platform_get_drvdata(pdev);
> + int i;
unsigned int, please.
> +
> + for (i = 0; i < pwm->npwm; i++)
> + pwm_disable(&pwm->chip.pwms[i]);
> +
> + pwmchip_remove(&pwm->chip);
> +
> + return 0;
> +}
> +
> +static const struct of_device_id stm32_pwm_of_match[] = {
> + {
> + .compatible = "st,stm32-pwm",
> + },
The above can be collapsed into a single line.
> +};
> +MODULE_DEVICE_TABLE(of, stm32_pwm_of_match);
> +
> +static struct platform_driver stm32_pwm_driver = {
> + .probe = stm32_pwm_probe,
> + .remove = stm32_pwm_remove,
> + .driver = {
> + .name = DRIVER_NAME,
> + .of_match_table = stm32_pwm_of_match,
> + },
> +};
Please don't use tabs for padding within the structure definition since
it doesn't align properly anyway.
> +module_platform_driver(stm32_pwm_driver);
> +
> +MODULE_ALIAS("platform:" DRIVER_NAME);
> +MODULE_DESCRIPTION("STMicroelectronics STM32 PWM driver");
> +MODULE_LICENSE("GPL");
According to the header comment this should be "GPL v2".
Thanks,
Thierry
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 801 bytes
Desc: not available
URL: <http://lists.infradead.org/pipermail/linux-arm-kernel/attachments/20161205/a32f069c/attachment.sig>
^ permalink raw reply
* [PATCH] ARM: dts: imx7d: fix LCDIF clock assignment
From: Uwe Kleine-König @ 2016-12-05 7:06 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <7e4829f484f6c4425fc9d01bea1a094f@agner.ch>
Hello Stefan,
On Sun, Dec 04, 2016 at 05:26:58PM -0800, Stefan Agner wrote:
> Since this fixes a kernel freeze, is there a chance to get this still in
> 4.9?
a Fixes:-Line would be nice then.
Best regards
Uwe
--
Pengutronix e.K. | Uwe Kleine-K?nig |
Industrial Linux Solutions | http://www.pengutronix.de/ |
^ permalink raw reply
* [LINUX RFC v4 3/4] mtd: spi-nor: add stripe support
From: Naga Sureshkumar Relli @ 2016-12-05 7:02 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <504cd632-022b-3e6b-8c50-563a585e1a08@atmel.com>
Hi Cyrille,
> > Hi Cyrille,
> >
> >> I have not finished to review the whole series yet but here some
> >> first
> >> comments:
> >
> > Thanks for reviewing these patch series.
> >
> >>
> >> Le 27/11/2016 ? 09:33, Naga Sureshkumar Relli a ?crit :
> >>> This patch adds stripe support and it is needed for GQSPI parallel
> >>> configuration mode by:
> >>>
> >>> - Adding required parameters like stripe and shift to spi_nor
> >>> structure.
> >>> - Initializing all added parameters in spi_nor_scan()
> >>> - Updating read_sr() and read_fsr() for getting status from both
> >>> flashes
> >>> - Increasing page_size, sector_size, erase_size and toatal flash
> >>> size as and when required.
> >>> - Dividing address by 2
> >>> - Updating spi->master->flags for qspi driver to change CS
> >>>
> >>> Signed-off-by: Naga Sureshkumar Relli <nagasure@xilinx.com>
> >>> ---
> >>> Changes for v4:
> >>> - rename isparallel to stripe
> >>> Changes for v3:
> >>> - No change
> >>> Changes for v2:
> >>> - Splitted to separate MTD layer changes from SPI core changes
> >>> ---
> >>> drivers/mtd/spi-nor/spi-nor.c | 130
> >> ++++++++++++++++++++++++++++++++----------
> >>> include/linux/mtd/spi-nor.h | 2 +
> >>> 2 files changed, 103 insertions(+), 29 deletions(-)
> >>>
> >>> diff --git a/drivers/mtd/spi-nor/spi-nor.c
> >>> b/drivers/mtd/spi-nor/spi-nor.c index d0fc165..4252239 100644
> >>> --- a/drivers/mtd/spi-nor/spi-nor.c
> >>> +++ b/drivers/mtd/spi-nor/spi-nor.c
> >>> @@ -22,6 +22,7 @@
> >>> #include <linux/of_platform.h>
> >>> #include <linux/spi/flash.h>
> >>> #include <linux/mtd/spi-nor.h>
> >>> +#include <linux/spi/spi.h>
> >>>
> >>> /* Define max times to check status register before we give up. */
> >>>
> >>> @@ -89,15 +90,24 @@ static const struct flash_info
> >>> *spi_nor_match_id(const char *name); static int read_sr(struct
> >>> spi_nor *nor) {
> >>> int ret;
> >>> - u8 val;
> >>> + u8 val[2];
> >>>
> >>> - ret = nor->read_reg(nor, SPINOR_OP_RDSR, &val, 1);
> >>> - if (ret < 0) {
> >>> - pr_err("error %d reading SR\n", (int) ret);
> >>> - return ret;
> >>> + if (nor->stripe) {
> >>> + ret = nor->read_reg(nor, SPINOR_OP_RDSR, &val[0], 2);
> >>> + if (ret < 0) {
> >>> + pr_err("error %d reading SR\n", (int) ret);
> >>> + return ret;
> >>> + }
> >>> + val[0] |= val[1];
> >> Why '|' rather than '&' ?
> >> I guess because of the 'Write In Progress/Busy' bit: when called by
> >> spi_nor_sr_ready(), you want to be sure that this 'BUSY' bit is
> >> cleared on both memories.
> >>
> >> But what about when the Status Register is read for purpose other
> >> than checking the state of the 'BUSY' bit?
> >>
> > Yes you are correct, I will change this.
> >
> >> What about SPI controllers supporting more than 2 memories in parallel?
> >>
> >> This solution might fit the ZynqMP controller but doesn't look so generic.
> >>
> >>> + } else {
> >>> + ret = nor->read_reg(nor, SPINOR_OP_RDSR, &val[0], 1);
> >>> + if (ret < 0) {
> >>> + pr_err("error %d reading SR\n", (int) ret);
> >>> + return ret;
> >>> + }
> >>> }
> >>>
> >>> - return val;
> >>> + return val[0];
> >>> }
> >>>
> >>> /*
> >>> @@ -108,15 +118,24 @@ static int read_sr(struct spi_nor *nor)
> >>> static int read_fsr(struct spi_nor *nor) {
> >>> int ret;
> >>> - u8 val;
> >>> + u8 val[2];
> >>>
> >>> - ret = nor->read_reg(nor, SPINOR_OP_RDFSR, &val, 1);
> >>> - if (ret < 0) {
> >>> - pr_err("error %d reading FSR\n", ret);
> >>> - return ret;
> >>> + if (nor->stripe) {
> >>> + ret = nor->read_reg(nor, SPINOR_OP_RDFSR, &val[0], 2);
> >>> + if (ret < 0) {
> >>> + pr_err("error %d reading FSR\n", ret);
> >>> + return ret;
> >>> + }
> >>> + val[0] &= val[1];
> >> Same comment here: why '&' rather than '|'?
> >> Surely because of the the 'READY' bit which should be set for both
> memories.
> > I will update this also.
> >>
> >>> + } else {
> >>> + ret = nor->read_reg(nor, SPINOR_OP_RDFSR, &val[0], 1);
> >>> + if (ret < 0) {
> >>> + pr_err("error %d reading FSR\n", ret);
> >>> + return ret;
> >>> + }
> >>> }
> >>>
> >>> - return val;
> >>> + return val[0];
> >>> }
> >>>
> >>> /*
> >>> @@ -290,9 +309,16 @@ static int spi_nor_wait_till_ready(struct
> >>> spi_nor
> >> *nor)
> >>> */
> >>> static int erase_chip(struct spi_nor *nor) {
> >>> + u32 ret;
> >>> +
> >>> dev_dbg(nor->dev, " %lldKiB\n", (long long)(nor->mtd.size >> 10));
> >>>
> >>> - return nor->write_reg(nor, SPINOR_OP_CHIP_ERASE, NULL, 0);
> >>> + ret = nor->write_reg(nor, SPINOR_OP_CHIP_ERASE, NULL, 0);
> >>> + if (ret)
> >>> + return ret;
> >>> +
> >>> + return ret;
> >>> +
> >>
> >> if (ret)
> >> return ret;
> >> else
> >> return ret;
> >>
> >> This chunk should be removed, it doesn't ease the patch review ;)
> > Ok, I will remove.
> >>
> >>> }
> >>>
> >>> static int spi_nor_lock_and_prep(struct spi_nor *nor, enum
> >>> spi_nor_ops ops) @@ -349,7 +375,7 @@ static int
> >>> spi_nor_erase_sector(struct spi_nor *nor, u32 addr) static int
> >>> spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr) {
> >>> struct spi_nor *nor = mtd_to_spi_nor(mtd);
> >>> - u32 addr, len;
> >>> + u32 addr, len, offset;
> >>> uint32_t rem;
> >>> int ret;
> >>>
> >>> @@ -399,9 +425,13 @@ static int spi_nor_erase(struct mtd_info *mtd,
> >> struct erase_info *instr)
> >>> /* "sector"-at-a-time erase */
> >>> } else {
> >>> while (len) {
> >>> +
> >>> write_enable(nor);
> >>> + offset = addr;
> >>> + if (nor->stripe)
> >>> + offset /= 2;
> >>
> >> I guess this should be /= 4 for controllers supporting 4 memories in
> parallel.
> >> Shouldn't you use nor->shift and define shift as an unsigned int
> >> instead of a bool?
> >> offset >>= nor->shift;
> >>
> > Yes we can use this shift, I will update
> >
> >> Anyway, by tuning the address here in spi-nor.c rather than in the
> >> SPI controller driver, you impose a model to support parallel
> >> memories that might not be suited to other controllers.
> >
> > For this ZynqMP GQSPI controller parallel configuration, globally
> > spi-nor should know about this stripe feature And based on that address
> has to change.
> > As I mentioned in cover letter, this controller in parallel configuration will
> work with even addresses only.
> > i.e. Before creating address format(m25p_addr2cmd) in mtd layer, spi-nor
> should change that address based on stripe option.
> >
> > I am updating this offset based on stripe option, and stripe option will
> update by reading dt property in nor_scan().
> > So the controller which doesn't support, then the stripe will be zero.
> > Or Can you please suggest any other way?
> >
> >>
> >>>
> >>> - ret = spi_nor_erase_sector(nor, addr);
> >>> + ret = spi_nor_erase_sector(nor, offset);
> >>> if (ret)
> >>> goto erase_err;
> >>>
> >>> @@ -525,6 +555,8 @@ static int stm_lock(struct spi_nor *nor, loff_t
> >>> ofs,
> >> uint64_t len)
> >>> bool use_top;
> >>> int ret;
> >>>
> >>> + ofs = ofs >> nor->shift;
> >>> +
> >>> status_old = read_sr(nor);
> >>> if (status_old < 0)
> >>> return status_old;
> >>> @@ -610,6 +642,8 @@ static int stm_unlock(struct spi_nor *nor,
> >>> loff_t ofs,
> >> uint64_t len)
> >>> bool use_top;
> >>> int ret;
> >>>
> >>> + ofs = ofs >> nor->shift;
> >>> +
> >>> status_old = read_sr(nor);
> >>> if (status_old < 0)
> >>> return status_old;
> >>> @@ -709,6 +743,8 @@ static int spi_nor_lock(struct mtd_info *mtd,
> >>> loff_t
> >> ofs, uint64_t len)
> >>> if (ret)
> >>> return ret;
> >>>
> >>> + ofs = ofs >> nor->shift;
> >>> +
> >>> ret = nor->flash_lock(nor, ofs, len);
> >>>
> >>> spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_UNLOCK); @@ -
> >> 724,6 +760,8
> >>> @@ static int spi_nor_unlock(struct mtd_info *mtd, loff_t ofs,
> >>> uint64_t
> >> len)
> >>> if (ret)
> >>> return ret;
> >>>
> >>> + ofs = ofs >> nor->shift;
> >>> +
> >>> ret = nor->flash_unlock(nor, ofs, len);
> >>>
> >>> spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_LOCK); @@ -
> >> 1018,6 +1056,9
> >>> @@ static const struct flash_info *spi_nor_read_id(struct spi_nor *nor)
> >>> u8 id[SPI_NOR_MAX_ID_LEN];
> >>> const struct flash_info *info;
> >>>
> >>> + nor->spi->master->flags &= ~(SPI_MASTER_BOTH_CS |
> >>> + SPI_MASTER_DATA_STRIPE);
> >>> +
> >>> tmp = nor->read_reg(nor, SPINOR_OP_RDID, id,
> >> SPI_NOR_MAX_ID_LEN);
> >>> if (tmp < 0) {
> >>> dev_dbg(nor->dev, "error %d reading JEDEC ID\n", tmp);
> >> @@ -1041,6
> >>> +1082,7 @@ static int spi_nor_read(struct mtd_info *mtd, loff_t
> >>> +from,
> >>> size_t len, {
> >>> struct spi_nor *nor = mtd_to_spi_nor(mtd);
> >>> int ret;
> >>> + u32 offset = from;
> >>>
> >>> dev_dbg(nor->dev, "from 0x%08x, len %zd\n", (u32)from, len);
> >>>
> >>> @@ -1049,7 +1091,13 @@ static int spi_nor_read(struct mtd_info *mtd,
> >> loff_t from, size_t len,
> >>> return ret;
> >>>
> >>> while (len) {
> >>> - ret = nor->read(nor, from, len, buf);
> >>> +
> >>> + offset = from;
> >>> +
> >>> + if (nor->stripe)
> >>> + offset /= 2;
> >>> +
> >>> + ret = nor->read(nor, offset, len, buf);
> >>> if (ret == 0) {
> >>> /* We shouldn't see 0-length reads */
> >>> ret = -EIO;
> >>> @@ -1161,6 +1209,7 @@ static int spi_nor_write(struct mtd_info *mtd,
> >> loff_t to, size_t len,
> >>> struct spi_nor *nor = mtd_to_spi_nor(mtd);
> >>> size_t page_offset, page_remain, i;
> >>> ssize_t ret;
> >>> + u32 offset;
> >>>
> >>> dev_dbg(nor->dev, "to 0x%08x, len %zd\n", (u32)to, len);
> >>>
> >>> @@ -1178,9 +1227,13 @@ static int spi_nor_write(struct mtd_info
> >>> *mtd,
> >> loff_t to, size_t len,
> >>> /* the size of data remaining on the first page */
> >>> page_remain = min_t(size_t,
> >>> nor->page_size - page_offset, len - i);
> >>> + offset = (to + i);
> >>> +
> >>> + if (nor->stripe)
> >>> + offset /= 2;
> >>>
> >>> write_enable(nor);
> >>> - ret = nor->write(nor, to + i, page_remain, buf + i);
> >>> + ret = nor->write(nor, (offset), page_remain, buf + i);
> >>> if (ret < 0)
> >>> goto write_err;
> >>> written = ret;
> >>> @@ -1302,22 +1355,22 @@ static int spi_nor_check(struct spi_nor
> >>> *nor)
> >>>
> >>> int spi_nor_scan(struct spi_nor *nor, const char *name, enum
> >>> read_mode mode) {
> >>> - const struct flash_info *info = NULL;
> >>> + struct flash_info *info = NULL;
> >>
> >> You should not remove the const and should not try to modify members
> >> of *info.
> >>
> >>> struct device *dev = nor->dev;
> >>> struct mtd_info *mtd = &nor->mtd;
> >>> struct device_node *np = spi_nor_get_flash_node(nor);
> >>> - int ret;
> >>> - int i;
> >>> + struct device_node *np_spi;
> >>> + int ret, i, xlnx_qspi_mode;
> >>>
> >>> ret = spi_nor_check(nor);
> >>> if (ret)
> >>> return ret;
> >>>
> >>> if (name)
> >>> - info = spi_nor_match_id(name);
> >>> + info = (struct flash_info *)spi_nor_match_id(name);
> >>> /* Try to auto-detect if chip name wasn't specified or not found */
> >>> if (!info)
> >>> - info = spi_nor_read_id(nor);
> >>> + info = (struct flash_info *)spi_nor_read_id(nor);
> >>> if (IS_ERR_OR_NULL(info))
> >>> return -ENOENT;
> >>>
> >> Both spi_nor_match_id() and spi_nor_read_id(), when they succeed,
> >> return a pointer to an entry of the spi_nor_ids[] array, which is
> >> located in a read- only memory area.
> >>
> >> Since your patch doesn't remove the const attribute of the
> >> spi_nor_ids[], I wonder whether it has been tested. I expect it not
> >> to work on most architecture.
> >>
> >> Anyway spi_nor_ids[] should remain const. Let's take the case of
> >> eXecution In Place (XIP) from an external memory: if spi_nor_ids[] is
> >> const, it can be read directly from this external (read-only) memory
> >> and we never need to copy the array in RAM, so we save some KB of
> RAM.
> >> This is just an example but I guess we can find other reasons to keep
> >> this array const.
> >>
> >>> @@ -1341,7 +1394,7 @@ int spi_nor_scan(struct spi_nor *nor, const
> >>> char
> >> *name, enum read_mode mode)
> >>> */
> >>> dev_warn(dev, "found %s, expected %s\n",
> >>> jinfo->name, info->name);
> >>> - info = jinfo;
> >>> + info = (struct flash_info *)jinfo;
> >>> }
> >>> }
> >>>
> >>> @@ -1370,6 +1423,27 @@ int spi_nor_scan(struct spi_nor *nor, const
> >>> char
> >> *name, enum read_mode mode)
> >>> mtd->size = info->sector_size * info->n_sectors;
> >>> mtd->_erase = spi_nor_erase;
> >>> mtd->_read = spi_nor_read;
> >>> +#ifdef CONFIG_OF
> >>> + np_spi = of_get_next_parent(np);
> >>> +
> >>> + if (of_property_read_u32(np_spi, "xlnx,qspi-mode",
> >>> + &xlnx_qspi_mode) < 0) {
> >> This really looks controller specific so should not be placed in the
> >> generic spi- nor.c file.
> >
> > Const is removed in info struct, because to update info members based
> parallel configuration.
> > As I mentioned above, for this parallel configuration, mtd and
> > spi-nor should know the details like
> > mtd->size, info->sectors, sector_size and page_size.
>
> You can tune the values of nor->mtd.size, nor->mtd.erasesize, nor-
> >page_size or whatever member of nor/nor.mtd as needed without ever
> modifying members of *info.
>
> If you modify *info then spi_nor_scan() is called a 2nd time to probe and
> configure SPI memories of the same part but connected to another
> controller, the values of the modified members in this *info would not be
> those expected.
> So *info and the spi_nor_ids[] array must remain const.
>
> The *info structure is not used outside spi_nor_scan(); none of
> spi_nor_read(),
> spi_nor_write() and spi_nor_erase() refers to *info hence every relevant
> value can be set only nor or nor->mtd members.
>
>
> Anyway, I think OR'ing or AND'ing values of memory registers depending on
> the relevant bit we want to check is not the right solution.
> If done in spi-nor.c, there would be a specific case for each memory register
> we read, each register bit would have to be handled differently.
>
> spi-nor.c tries to support as much memory parts as possible, it deals with
> many registers and bits: Status/Control registers, Quad Enable bits...
>
> If we start to OR or AND each of these register values to support the
> stripping mode, spi-nor will become really hard to maintain.
>
> I don't know whether it could be done with the xilinx controller but I thought
> about first configuring the two memories independently calling
> spi_nor_scan() twice; one call for each memory.
>
> Then the xilinx driver could register only one struct mtd_info, overriding
> mtd->_read() [and likely mtd->_write() and mtd->_erase() too] set by
> spi_nor_scan() with a xilinx driver custom implementation so this driver
> supports its controller stripping mode as it wants.
>
> Of course, this solution assumes that the SPI controller has one dedicated
> chip-select line for each memory and not a single chip-select line shared by
> both memories. The memories should be configured independently: you
> can't assume multiple instances of the very same memory part always return
> the exact same value when reading one of their register. Logical AND/OR is
> not a generic solution, IMHO.
>
> If the xilinx controller has only one shared chip-select line then let's see
> whether 2 GPIO lines could be used as independent chip-select lines.
>
>
In parallel configuration, Physically we have two flashes but mtd will see as single flash memory (sum of both memories)
If we call spi_nor_scan(), twice then read/write will override but nor->mtd.size, nor->mtd.erasesize, nor->page_size will remain same, I,e they will also override, they won't append.
I tried calling spi_nor_scan() twice by some hacks but nor->mtd.size, nor->mtd.erasesize, nor->page_size are not changing
Also the same issue we are getting for flash address, need to shift the address to work in this configuration.
Also to tune nor->mtd.size, nor->mtd.erasesize, nor->page_size, we need to touch this spi-nor.c
Please kindly suggest, if I am wrong.
Thanks,
Naga Sureshkumar Relli
> Best regards,
>
> Cyrille
This email and any attachments are intended for the sole use of the named recipient(s) and contain(s) confidential information that may be proprietary, privileged or copyrighted under applicable law. If you are not the intended recipient, do not read, copy, or forward this email message or any attachments. Delete this email message and any attachments immediately.
^ permalink raw reply
* [PATCH v1 2/2] crypto: mediatek - add DT bindings documentation
From: Ryder Lee @ 2016-12-05 7:01 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <1480921284-45827-1-git-send-email-ryder.lee@mediatek.com>
Add DT bindings documentation for the crypto driver
Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
---
.../devicetree/bindings/crypto/mediatek-crypto.txt | 32 ++++++++++++++++++++++
1 file changed, 32 insertions(+)
create mode 100644 Documentation/devicetree/bindings/crypto/mediatek-crypto.txt
diff --git a/Documentation/devicetree/bindings/crypto/mediatek-crypto.txt b/Documentation/devicetree/bindings/crypto/mediatek-crypto.txt
new file mode 100644
index 0000000..8b1db08
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/mediatek-crypto.txt
@@ -0,0 +1,32 @@
+MediaTek cryptographic accelerators
+
+Required properties:
+- compatible: Should be "mediatek,mt7623-crypto"
+- reg: Address and length of the register set for the device
+- interrupts: Should contain the five crypto engines interrupts in numeric
+ order. These are global system and four descriptor rings.
+- clocks: the clock used by the core
+- clock-names: the names of the clock listed in the clocks property. These are
+ "ethif", "cryp"
+- power-domains: Must contain a reference to the PM domain.
+
+
+Optional properties:
+- interrupt-parent: Should be the phandle for the interrupt controller
+ that services interrupts for this device
+
+
+Example:
+ crypto: crypto at 1b240000 {
+ compatible = "mediatek,mt7623-crypto";
+ reg = <0 0x1b240000 0 0x20000>;
+ interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_LOW>,
+ <GIC_SPI 83 IRQ_TYPE_LEVEL_LOW>,
+ <GIC_SPI 84 IRQ_TYPE_LEVEL_LOW>,
+ <GIC_SPI 91 IRQ_TYPE_LEVEL_LOW>,
+ <GIC_SPI 97 IRQ_TYPE_LEVEL_LOW>;
+ clocks = <&topckgen CLK_TOP_ETHIF_SEL>,
+ <ðsys CLK_ETHSYS_CRYPTO>;
+ clock-names = "ethif","cryp";
+ power-domains = <&scpsys MT2701_POWER_DOMAIN_ETH>;
+ };
--
1.9.1
^ permalink raw reply related
* [PATCH v1 1/2] Add crypto driver support for some MediaTek chips
From: Ryder Lee @ 2016-12-05 7:01 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <1480921284-45827-1-git-send-email-ryder.lee@mediatek.com>
This adds support for the MediaTek hardware accelerator on
mt7623/mt2701/mt8521p SoC.
This driver currently implement:
- SHA1 and SHA2 family(HMAC) hash alogrithms.
- AES block cipher in CBC/ECB mode with 128/196/256 bits keys.
Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
---
drivers/crypto/Kconfig | 17 +
drivers/crypto/Makefile | 1 +
drivers/crypto/mediatek/Makefile | 2 +
drivers/crypto/mediatek/mtk-aes.c | 763 +++++++++++++++++
drivers/crypto/mediatek/mtk-platform.c | 580 +++++++++++++
drivers/crypto/mediatek/mtk-platform.h | 235 ++++++
drivers/crypto/mediatek/mtk-regs.h | 194 +++++
drivers/crypto/mediatek/mtk-sha.c | 1423 ++++++++++++++++++++++++++++++++
8 files changed, 3215 insertions(+)
create mode 100644 drivers/crypto/mediatek/Makefile
create mode 100644 drivers/crypto/mediatek/mtk-aes.c
create mode 100644 drivers/crypto/mediatek/mtk-platform.c
create mode 100644 drivers/crypto/mediatek/mtk-platform.h
create mode 100644 drivers/crypto/mediatek/mtk-regs.h
create mode 100644 drivers/crypto/mediatek/mtk-sha.c
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 4d2b81f..ad0a00b 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -553,6 +553,23 @@ config CRYPTO_DEV_ROCKCHIP
This driver interfaces with the hardware crypto accelerator.
Supporting cbc/ecb chainmode, and aes/des/des3_ede cipher mode.
+config CRYPTO_DEV_MEDIATEK
+ tristate "MediaTek's Cryptographic Engine driver"
+ depends on ARM && (ARCH_MEDIATEK || COMPILE_TEST)
+ select NEON
+ select KERNEL_MODE_NEON
+ select ARM_CRYPTO
+ select CRYPTO_AES
+ select CRYPTO_BLKCIPHER
+ select CRYPTO_SHA1_ARM_NEON
+ select CRYPTO_SHA256_ARM
+ select CRYPTO_SHA512_ARM
+ select CRYPTO_HMAC
+ help
+ This driver allows you to utilize the hardware crypto accelerator
+ which can be found on the MT7623 MT2701, MT8521p, etc ....
+ Select this if you want to use it for AES/SHA1/SHA2 algorithms.
+
source "drivers/crypto/chelsio/Kconfig"
endif # CRYPTO_HW
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index ad7250f..272b51a 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_CRYPTO_DEV_IMGTEC_HASH) += img-hash.o
obj-$(CONFIG_CRYPTO_DEV_IXP4XX) += ixp4xx_crypto.o
obj-$(CONFIG_CRYPTO_DEV_MV_CESA) += mv_cesa.o
obj-$(CONFIG_CRYPTO_DEV_MARVELL_CESA) += marvell/
+obj-$(CONFIG_CRYPTO_DEV_MEDIATEK) += mediatek/
obj-$(CONFIG_CRYPTO_DEV_MXS_DCP) += mxs-dcp.o
obj-$(CONFIG_CRYPTO_DEV_NIAGARA2) += n2_crypto.o
n2_crypto-y := n2_core.o n2_asm.o
diff --git a/drivers/crypto/mediatek/Makefile b/drivers/crypto/mediatek/Makefile
new file mode 100644
index 0000000..187be79
--- /dev/null
+++ b/drivers/crypto/mediatek/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_CRYPTO_DEV_MEDIATEK) += mtk-crypto.o
+mtk-crypto-objs:= mtk-platform.o mtk-aes.o mtk-sha.o
diff --git a/drivers/crypto/mediatek/mtk-aes.c b/drivers/crypto/mediatek/mtk-aes.c
new file mode 100644
index 0000000..0208981
--- /dev/null
+++ b/drivers/crypto/mediatek/mtk-aes.c
@@ -0,0 +1,763 @@
+/*
+ * Cryptographic API.
+ *
+ * Support for MediaTek AES hardware accelerator.
+ *
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Ryder Lee <ryder.lee@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Some ideas are from atmel-aes.c drivers.
+ */
+
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <crypto/scatterwalk.h>
+#include <linux/dma-mapping.h>
+#include <linux/scatterlist.h>
+#include "mtk-platform.h"
+#include "mtk-regs.h"
+
+#define AES_QUEUE_LENGTH 512
+#define AES_BUFFER_ORDER 2
+#define AES_BUFFER_SIZE ((PAGE_SIZE << AES_BUFFER_ORDER) \
+ & ~(AES_BLOCK_SIZE - 1))
+
+/* AES command token */
+#define AES_CT_SIZE_ECB 2
+#define AES_CT_SIZE_CBC 3
+#define AES_CT_CTRL_HDR 0x00220000
+#define AES_COMMAND0 0x05000000
+#define AES_COMMAND1 0x2d060000
+#define AES_COMMAND2 0xe4a63806
+
+/* AES transform information */
+#define AES_TFM_ECB (0x0 << 0)
+#define AES_TFM_CBC (0x1 << 0)
+#define AES_TFM_DECRYPT (0x5 << 0)
+#define AES_TFM_ENCRYPT (0x4 << 0)
+#define AES_TFM_SIZE(x) ((x) << 8)
+#define AES_TFM_128BITS (0xb << 16)
+#define AES_TFM_192BITS (0xd << 16)
+#define AES_TFM_256BITS (0xf << 16)
+#define AES_TFM_FULL_IV (0xf << 5)
+
+/* AES flags */
+#define AES_FLAGS_MODE_MSK GENMASK(2, 0)
+#define AES_FLAGS_ECB BIT(0)
+#define AES_FLAGS_CBC BIT(1)
+#define AES_FLAGS_ENCRYPT BIT(2)
+#define AES_FLAGS_BUSY BIT(3)
+
+/**
+ * AES command token(CT) is a set of hardware instructions that
+ * are used to control crypto engine AES processing flow.
+ */
+struct mtk_aes_ct {
+ u32 ct_ctrl0;
+ u32 ct_ctrl1;
+ u32 ct_ctrl2;
+};
+
+/**
+ * AES transform state(tfm) is use to define AES transform state
+ * and contains all keys and initial vectors.
+ */
+struct mtk_aes_tfm {
+ u32 tfm_ctrl0;
+ u32 tfm_ctrl1;
+ /* store keys and IVs */
+ u8 state[AES_KEYSIZE_256 + AES_BLOCK_SIZE] __aligned(sizeof(u32));
+};
+
+/**
+ * mtk_aes_info consists of command token and transform state of AES,
+ * which should be encapsulated in command and result descriptors.
+ * The packet processing engine requires these information to do:
+ *
+ * - Commands decoding and control of the crypto engine?s data path.
+ * - Coordinating hardware data fetch and store operations.
+ * - Result token construction and output.
+ */
+struct mtk_aes_info {
+ struct mtk_aes_ct ct;
+ struct mtk_aes_tfm tfm;
+};
+
+struct mtk_aes_reqctx {
+ u64 mode;
+};
+
+struct mtk_aes_ctx {
+ struct mtk_cryp *cryp;
+ struct mtk_aes_info info;
+ u32 keylen;
+
+ unsigned long flags;
+};
+
+struct mtk_aes_drv {
+ struct list_head dev_list;
+ /* device list lock */
+ spinlock_t lock;
+};
+
+static struct mtk_aes_drv mtk_aes = {
+ .dev_list = LIST_HEAD_INIT(mtk_aes.dev_list),
+ .lock = __SPIN_LOCK_UNLOCKED(mtk_aes.lock),
+};
+
+static inline u32 mtk_aes_read(struct mtk_cryp *cryp, u32 offset)
+{
+ return readl_relaxed(cryp->base + offset);
+}
+
+static inline void mtk_aes_write(struct mtk_cryp *cryp,
+ u32 offset, u32 value)
+{
+ writel_relaxed(value, cryp->base + offset);
+}
+
+static struct mtk_cryp *mtk_aes_find_dev(struct mtk_aes_ctx *ctx)
+{
+ struct mtk_cryp *cryp = NULL;
+ struct mtk_cryp *tmp;
+
+ spin_lock_bh(&mtk_aes.lock);
+ if (!ctx->cryp) {
+ list_for_each_entry(tmp, &mtk_aes.dev_list, aes_list) {
+ cryp = tmp;
+ break;
+ }
+ ctx->cryp = cryp;
+ } else {
+ cryp = ctx->cryp;
+ }
+ spin_unlock_bh(&mtk_aes.lock);
+
+ return cryp;
+}
+
+static inline size_t mtk_aes_padlen(size_t len)
+{
+ len &= AES_BLOCK_SIZE - 1;
+ return len ? AES_BLOCK_SIZE - len : 0;
+}
+
+static bool mtk_aes_check_aligned(struct scatterlist *sg,
+ size_t len, struct mtk_aes_dma *dma)
+{
+ int nents;
+
+ if (!IS_ALIGNED(len, AES_BLOCK_SIZE))
+ return false;
+
+ for (nents = 0; sg; sg = sg_next(sg), ++nents) {
+ if (!IS_ALIGNED(sg->offset, sizeof(u32)))
+ return false;
+
+ if (len <= sg->length) {
+ if (!IS_ALIGNED(len, AES_BLOCK_SIZE))
+ return false;
+
+ dma->nents = nents + 1;
+ dma->remainder = sg->length - len;
+ sg->length = len;
+ return true;
+ }
+
+ if (!IS_ALIGNED(sg->length, AES_BLOCK_SIZE))
+ return false;
+
+ len -= sg->length;
+ }
+
+ return false;
+}
+
+/* Initialize and map transform information of AES */
+static int mtk_aes_info_map(struct mtk_cryp *cryp,
+ struct mtk_aes *aes, size_t len)
+{
+ struct mtk_aes_ctx *ctx = crypto_ablkcipher_ctx(
+ crypto_ablkcipher_reqtfm(aes->req));
+ struct mtk_aes_info *info = aes->info;
+ struct mtk_aes_ct *ct = &info->ct;
+ struct mtk_aes_tfm *tfm = &info->tfm;
+ u32 keylen = ctx->keylen;
+
+ aes->ct_hdr = AES_CT_CTRL_HDR | len;
+ ct->ct_ctrl0 = AES_COMMAND0 | len;
+ ct->ct_ctrl1 = AES_COMMAND1;
+
+ if (aes->flags & AES_FLAGS_ENCRYPT)
+ tfm->tfm_ctrl0 = AES_TFM_ENCRYPT;
+ else
+ tfm->tfm_ctrl0 = AES_TFM_DECRYPT;
+
+ if (aes->flags & AES_FLAGS_CBC) {
+ aes->ct_size = AES_CT_SIZE_CBC;
+ ct->ct_ctrl2 = AES_COMMAND2;
+
+ tfm->tfm_ctrl0 |=
+ AES_TFM_SIZE(SIZE_IN_WORDS(keylen + AES_BLOCK_SIZE));
+ tfm->tfm_ctrl1 = AES_TFM_CBC;
+ tfm->tfm_ctrl1 |= AES_TFM_FULL_IV;
+
+ memcpy(tfm->state + keylen, aes->req->info, AES_BLOCK_SIZE);
+ } else if (aes->flags & AES_FLAGS_ECB) {
+ aes->ct_size = AES_CT_SIZE_ECB;
+ tfm->tfm_ctrl0 |= AES_TFM_SIZE(SIZE_IN_WORDS(keylen));
+ tfm->tfm_ctrl1 = AES_TFM_ECB;
+ }
+
+ if (keylen == AES_KEYSIZE_128)
+ tfm->tfm_ctrl0 |= AES_TFM_128BITS;
+ else if (keylen == AES_KEYSIZE_256)
+ tfm->tfm_ctrl0 |= AES_TFM_256BITS;
+ else if (keylen == AES_KEYSIZE_192)
+ tfm->tfm_ctrl0 |= AES_TFM_192BITS;
+
+ aes->ct_dma = dma_map_single(cryp->dev, info, sizeof(*info),
+ DMA_TO_DEVICE);
+ if (unlikely(dma_mapping_error(cryp->dev, aes->ct_dma))) {
+ dev_err(cryp->dev, "dma %d bytes error\n", sizeof(*info));
+ return -EINVAL;
+ }
+ aes->tfm_dma = aes->ct_dma + sizeof(*ct);
+
+ return 0;
+}
+
+static int mtk_aes_xmit(struct mtk_cryp *cryp, struct mtk_aes *aes)
+{
+ struct mtk_ring *ring = cryp->ring[aes->id];
+ struct mtk_desc *cmd = NULL, *res = NULL;
+ struct scatterlist *ssg, *dsg;
+ u32 len = aes->src.sg_len;
+ int nents;
+
+ /* Fill command and result descriptors */
+ for (nents = 0; nents < len; ++nents) {
+ ssg = &aes->src.sg[nents];
+ dsg = &aes->dst.sg[nents];
+
+ cmd = ring->cmd_base + ring->pos;
+ res = ring->res_base + ring->pos;
+
+ res->hdr = MTK_DESC_BUF_LEN(dsg->length);
+ res->buf = sg_dma_address(dsg);
+
+ cmd->hdr = MTK_DESC_BUF_LEN(ssg->length);
+ cmd->buf = sg_dma_address(ssg);
+
+ if (nents == 0) {
+ res->hdr |= MTK_DESC_FIRST;
+ cmd->hdr |= MTK_DESC_FIRST;
+ cmd->hdr |= MTK_DESC_CT_LEN(aes->ct_size);
+ cmd->ct = aes->ct_dma;
+ cmd->ct_hdr = aes->ct_hdr;
+ cmd->tfm = aes->tfm_dma;
+ }
+
+ if (++ring->pos == MTK_MAX_DESC_NUM)
+ ring->pos = 0;
+ }
+
+ cmd->hdr |= MTK_DESC_LAST;
+ res->hdr |= MTK_DESC_LAST;
+
+ /*
+ * make sure that all changes to the dma ring are done before we
+ * start engine.
+ */
+ wmb();
+ /* Start DMA transfer */
+ mtk_aes_write(cryp, RDR_PREP_COUNT(aes->id), MTK_DESC_CNT(len));
+ mtk_aes_write(cryp, CDR_PREP_COUNT(aes->id), MTK_DESC_CNT(len));
+
+ return -EINPROGRESS;
+}
+
+static inline void mtk_aes_restore_sg(const struct mtk_aes_dma *dma)
+{
+ struct scatterlist *sg = dma->sg;
+ int nents = dma->nents;
+
+ if (!dma->remainder)
+ return;
+
+ while (--nents > 0 && sg)
+ sg = sg_next(sg);
+
+ if (!sg)
+ return;
+
+ sg->length += dma->remainder;
+}
+
+static int mtk_aes_map(struct mtk_cryp *cryp, struct mtk_aes *aes)
+{
+ struct scatterlist *src = aes->req->src;
+ struct scatterlist *dst = aes->req->dst;
+ size_t len = aes->req->nbytes;
+ size_t padlen = 0;
+ bool src_aligned, dst_aligned;
+
+ aes->total = len;
+ aes->src.sg = src;
+ aes->dst.sg = dst;
+ aes->real_dst = dst;
+
+ src_aligned = mtk_aes_check_aligned(src, len, &aes->src);
+ if (src == dst)
+ dst_aligned = src_aligned;
+ else
+ dst_aligned = mtk_aes_check_aligned(dst, len, &aes->dst);
+
+ if (!src_aligned || !dst_aligned) {
+ padlen = mtk_aes_padlen(len);
+
+ if (len + padlen > AES_BUFFER_SIZE)
+ return -ENOMEM;
+
+ if (!src_aligned) {
+ sg_copy_to_buffer(src, sg_nents(src), aes->buf, len);
+ aes->src.sg = &aes->aligned_sg;
+ aes->src.nents = 1;
+ aes->src.remainder = 0;
+ }
+
+ if (!dst_aligned) {
+ aes->dst.sg = &aes->aligned_sg;
+ aes->dst.nents = 1;
+ aes->dst.remainder = 0;
+ }
+
+ sg_init_table(&aes->aligned_sg, 1);
+ sg_set_buf(&aes->aligned_sg, aes->buf, len + padlen);
+ }
+
+ if (aes->src.sg == aes->dst.sg) {
+ aes->src.sg_len = dma_map_sg(cryp->dev, aes->src.sg,
+ aes->src.nents, DMA_BIDIRECTIONAL);
+ aes->dst.sg_len = aes->src.sg_len;
+ if (unlikely(!aes->src.sg_len))
+ return -EFAULT;
+ } else {
+ aes->src.sg_len = dma_map_sg(cryp->dev, aes->src.sg,
+ aes->src.nents, DMA_TO_DEVICE);
+ if (unlikely(!aes->src.sg_len))
+ return -EFAULT;
+
+ aes->dst.sg_len = dma_map_sg(cryp->dev, aes->dst.sg,
+ aes->dst.nents, DMA_FROM_DEVICE);
+ if (unlikely(!aes->dst.sg_len)) {
+ dma_unmap_sg(cryp->dev, aes->src.sg,
+ aes->src.nents, DMA_TO_DEVICE);
+ return -EFAULT;
+ }
+ }
+
+ return mtk_aes_info_map(cryp, aes, len + padlen);
+}
+
+static int mtk_aes_handle_queue(struct mtk_cryp *cryp, u8 id,
+ struct ablkcipher_request *req)
+{
+ struct mtk_aes *aes = cryp->aes[id];
+ struct crypto_async_request *areq, *backlog;
+ struct mtk_aes_reqctx *rctx;
+ struct mtk_aes_ctx *ctx;
+ unsigned long flags;
+ int err, ret = 0;
+
+ spin_lock_irqsave(&aes->lock, flags);
+ if (req)
+ ret = ablkcipher_enqueue_request(&aes->queue, req);
+ if (aes->flags & AES_FLAGS_BUSY) {
+ spin_unlock_irqrestore(&aes->lock, flags);
+ return ret;
+ }
+ backlog = crypto_get_backlog(&aes->queue);
+ areq = crypto_dequeue_request(&aes->queue);
+ if (areq)
+ aes->flags |= AES_FLAGS_BUSY;
+ spin_unlock_irqrestore(&aes->lock, flags);
+
+ if (!areq)
+ return ret;
+
+ if (backlog)
+ backlog->complete(backlog, -EINPROGRESS);
+
+ req = ablkcipher_request_cast(areq);
+ ctx = crypto_ablkcipher_ctx(crypto_ablkcipher_reqtfm(req));
+ rctx = ablkcipher_request_ctx(req);
+ rctx->mode &= AES_FLAGS_MODE_MSK;
+ /* assign new request to device */
+ aes->req = req;
+ aes->info = &ctx->info;
+ aes->flags = (aes->flags & ~AES_FLAGS_MODE_MSK) | rctx->mode;
+
+ err = mtk_aes_map(cryp, aes);
+ if (err)
+ return err;
+
+ return mtk_aes_xmit(cryp, aes);
+}
+
+static void mtk_aes_unmap(struct mtk_cryp *cryp, struct mtk_aes *aes)
+{
+ dma_unmap_single(cryp->dev, aes->ct_dma,
+ sizeof(struct mtk_aes_info), DMA_TO_DEVICE);
+
+ if (aes->src.sg == aes->dst.sg) {
+ dma_unmap_sg(cryp->dev, aes->src.sg,
+ aes->src.nents, DMA_BIDIRECTIONAL);
+
+ if (aes->src.sg != &aes->aligned_sg)
+ mtk_aes_restore_sg(&aes->src);
+ } else {
+ dma_unmap_sg(cryp->dev, aes->dst.sg,
+ aes->dst.nents, DMA_FROM_DEVICE);
+
+ if (aes->dst.sg != &aes->aligned_sg)
+ mtk_aes_restore_sg(&aes->dst);
+
+ dma_unmap_sg(cryp->dev, aes->src.sg,
+ aes->src.nents, DMA_TO_DEVICE);
+
+ if (aes->src.sg != &aes->aligned_sg)
+ mtk_aes_restore_sg(&aes->src);
+ }
+
+ if (aes->dst.sg == &aes->aligned_sg)
+ sg_copy_from_buffer(aes->real_dst,
+ sg_nents(aes->real_dst),
+ aes->buf, aes->total);
+}
+
+static inline void mtk_aes_complete(struct mtk_cryp *cryp,
+ struct mtk_aes *aes)
+{
+ aes->flags &= ~AES_FLAGS_BUSY;
+
+ aes->req->base.complete(&aes->req->base, 0);
+
+ /* handle new request */
+ mtk_aes_handle_queue(cryp, aes->id, NULL);
+}
+
+/* Check and set the AES key to transform state's buffer */
+static int mtk_aes_setkey(struct crypto_ablkcipher *tfm,
+ const u8 *key, u32 keylen)
+{
+ struct mtk_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+ u8 *state = ctx->info.tfm.state;
+
+ if (keylen != AES_KEYSIZE_128 &&
+ keylen != AES_KEYSIZE_192 &&
+ keylen != AES_KEYSIZE_256) {
+ crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+ return -EINVAL;
+ }
+
+ ctx->keylen = keylen;
+ memcpy(state, key, keylen);
+
+ return 0;
+}
+
+static int mtk_aes_crypt(struct ablkcipher_request *req, u64 mode)
+{
+ struct mtk_aes_ctx *ctx = crypto_ablkcipher_ctx(
+ crypto_ablkcipher_reqtfm(req));
+ struct mtk_aes_reqctx *rctx = ablkcipher_request_ctx(req);
+
+ rctx->mode = mode;
+
+ return mtk_aes_handle_queue(ctx->cryp,
+ !(mode & AES_FLAGS_ENCRYPT), req);
+}
+
+static int mtk_ecb_encrypt(struct ablkcipher_request *req)
+{
+ return mtk_aes_crypt(req, AES_FLAGS_ENCRYPT | AES_FLAGS_ECB);
+}
+
+static int mtk_ecb_decrypt(struct ablkcipher_request *req)
+{
+ return mtk_aes_crypt(req, AES_FLAGS_ECB);
+}
+
+static int mtk_cbc_encrypt(struct ablkcipher_request *req)
+{
+ return mtk_aes_crypt(req, AES_FLAGS_ENCRYPT | AES_FLAGS_CBC);
+}
+
+static int mtk_cbc_decrypt(struct ablkcipher_request *req)
+{
+ return mtk_aes_crypt(req, AES_FLAGS_CBC);
+}
+
+static int mtk_aes_cra_init(struct crypto_tfm *tfm)
+{
+ struct mtk_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+ struct mtk_cryp *cryp = NULL;
+
+ tfm->crt_ablkcipher.reqsize = sizeof(struct mtk_aes_reqctx);
+
+ cryp = mtk_aes_find_dev(ctx);
+ if (!cryp) {
+ pr_err("can't find crypto device\n");
+ return -ENODEV;
+ }
+
+ return 0;
+}
+
+static struct crypto_alg aes_algs[] = {
+{
+ .cra_name = "cbc(aes)",
+ .cra_driver_name = "cbc-aes-mtk",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+ CRYPTO_ALG_ASYNC,
+ .cra_init = mtk_aes_cra_init,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct mtk_aes_ctx),
+ .cra_alignmask = 15,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_u.ablkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .setkey = mtk_aes_setkey,
+ .encrypt = mtk_cbc_encrypt,
+ .decrypt = mtk_cbc_decrypt,
+ .ivsize = AES_BLOCK_SIZE,
+ }
+},
+{
+ .cra_name = "ecb(aes)",
+ .cra_driver_name = "ecb-aes-mtk",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+ CRYPTO_ALG_ASYNC,
+ .cra_init = mtk_aes_cra_init,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct mtk_aes_ctx),
+ .cra_alignmask = 15,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_u.ablkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .setkey = mtk_aes_setkey,
+ .encrypt = mtk_ecb_encrypt,
+ .decrypt = mtk_ecb_decrypt,
+ }
+},
+};
+
+static void mtk_aes_enc_task(unsigned long data)
+{
+ struct mtk_cryp *cryp = (struct mtk_cryp *)data;
+ struct mtk_aes *aes = cryp->aes[0];
+
+ mtk_aes_unmap(cryp, aes);
+ mtk_aes_complete(cryp, aes);
+}
+
+static void mtk_aes_dec_task(unsigned long data)
+{
+ struct mtk_cryp *cryp = (struct mtk_cryp *)data;
+ struct mtk_aes *aes = cryp->aes[1];
+
+ mtk_aes_unmap(cryp, aes);
+ mtk_aes_complete(cryp, aes);
+}
+
+static irqreturn_t mtk_aes_enc_irq(int irq, void *dev_id)
+{
+ struct mtk_cryp *cryp = (struct mtk_cryp *)dev_id;
+ struct mtk_aes *aes = cryp->aes[0];
+ u32 val = mtk_aes_read(cryp, RDR_STAT(RING0));
+
+ mtk_aes_write(cryp, RDR_STAT(RING0), val);
+
+ if (likely(AES_FLAGS_BUSY & aes->flags)) {
+ mtk_aes_write(cryp, RDR_PROC_COUNT(RING0), MTK_DESC_CNT_CLR);
+ mtk_aes_write(cryp, RDR_THRESH(RING0), MTK_RDR_THRESH_DEF);
+
+ tasklet_schedule(&aes->task);
+ } else {
+ dev_warn(cryp->dev, "AES interrupt when no active requests.\n");
+ }
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t mtk_aes_dec_irq(int irq, void *dev_id)
+{
+ struct mtk_cryp *cryp = (struct mtk_cryp *)dev_id;
+ struct mtk_aes *aes = cryp->aes[1];
+ u32 val = mtk_aes_read(cryp, RDR_STAT(RING1));
+
+ mtk_aes_write(cryp, RDR_STAT(RING1), val);
+
+ if (likely(AES_FLAGS_BUSY & aes->flags)) {
+ mtk_aes_write(cryp, RDR_PROC_COUNT(RING1), MTK_DESC_CNT_CLR);
+ mtk_aes_write(cryp, RDR_THRESH(RING1), MTK_RDR_THRESH_DEF);
+
+ tasklet_schedule(&aes->task);
+ } else {
+ dev_warn(cryp->dev, "AES interrupt when no active requests.\n");
+ }
+ return IRQ_HANDLED;
+}
+
+/*
+ * The purpose of creating encryption and decryption records is
+ * to process outbound/inbound data in parallel, it can improve
+ * performance in most use cases, such as IPSec VPN, especially
+ * under heavy network traffic.
+ */
+static int mtk_aes_record_init(struct mtk_cryp *cryp)
+{
+ struct mtk_aes **aes = cryp->aes;
+ int i, err = -ENOMEM;
+
+ for (i = 0; i < RECORD_NUM; i++) {
+ aes[i] = kzalloc(sizeof(**aes), GFP_KERNEL);
+ if (!aes[i])
+ goto err_cleanup;
+
+ aes[i]->buf = (void *)__get_free_pages(GFP_KERNEL,
+ AES_BUFFER_ORDER);
+ if (!aes[i]->buf)
+ goto err_cleanup;
+
+ aes[i]->id = i;
+
+ spin_lock_init(&aes[i]->lock);
+ crypto_init_queue(&aes[i]->queue, AES_QUEUE_LENGTH);
+ }
+
+ tasklet_init(&aes[0]->task, mtk_aes_enc_task, (unsigned long)cryp);
+ tasklet_init(&aes[1]->task, mtk_aes_dec_task, (unsigned long)cryp);
+
+ return 0;
+
+err_cleanup:
+ for (; i--; ) {
+ free_page((unsigned long)aes[i]->buf);
+ kfree(aes[i]);
+ }
+
+ return err;
+}
+
+static void mtk_aes_record_free(struct mtk_cryp *cryp)
+{
+ int i;
+
+ for (i = 0; i < RECORD_NUM; i++) {
+ tasklet_kill(&cryp->aes[i]->task);
+ free_page((unsigned long)cryp->aes[i]->buf);
+ kfree(cryp->aes[i]);
+ }
+}
+
+static void mtk_aes_unregister_algs(void)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(aes_algs); i++)
+ crypto_unregister_alg(&aes_algs[i]);
+}
+
+static int mtk_aes_register_algs(void)
+{
+ int err, i, j;
+
+ for (i = 0; i < ARRAY_SIZE(aes_algs); i++) {
+ err = crypto_register_alg(&aes_algs[i]);
+ if (err)
+ goto err_aes_algs;
+ }
+
+ return 0;
+
+err_aes_algs:
+ for (j = 0; j < i; j++)
+ crypto_unregister_alg(&aes_algs[j]);
+
+ return err;
+}
+
+int mtk_cipher_alg_register(struct mtk_cryp *cryp)
+{
+ int ret;
+
+ INIT_LIST_HEAD(&cryp->aes_list);
+
+ /* Initialize two cipher records */
+ ret = mtk_aes_record_init(cryp);
+ if (ret)
+ goto err_record;
+
+ /* Ring0 irq is use by encryption record */
+ ret = devm_request_irq(cryp->dev, cryp->irq[RING0], mtk_aes_enc_irq,
+ IRQF_TRIGGER_LOW, "mtk-aes", cryp);
+ if (ret) {
+ dev_err(cryp->dev, "unable to request AES encryption irq.\n");
+ goto err_res;
+ }
+
+ /* Ring1 irq is use by decryption record */
+ ret = devm_request_irq(cryp->dev, cryp->irq[RING1], mtk_aes_dec_irq,
+ IRQF_TRIGGER_LOW, "mtk-aes", cryp);
+ if (ret) {
+ dev_err(cryp->dev, "unable to request AES decryption irq.\n");
+ goto err_res;
+ }
+
+ /* Enable ring0 and ring1 interrupt */
+ mtk_aes_write(cryp, AIC_ENABLE_SET(RING0), MTK_IRQ_RDR0);
+ mtk_aes_write(cryp, AIC_ENABLE_SET(RING1), MTK_IRQ_RDR1);
+
+ spin_lock(&mtk_aes.lock);
+ list_add_tail(&cryp->aes_list, &mtk_aes.dev_list);
+ spin_unlock(&mtk_aes.lock);
+
+ ret = mtk_aes_register_algs();
+ if (ret)
+ goto err_algs;
+
+ return 0;
+
+err_algs:
+ spin_lock(&mtk_aes.lock);
+ list_del(&cryp->aes_list);
+ spin_unlock(&mtk_aes.lock);
+err_res:
+ mtk_aes_record_free(cryp);
+err_record:
+
+ dev_err(cryp->dev, "mtk-aes initialization failed.\n");
+ return ret;
+}
+
+void mtk_cipher_alg_release(struct mtk_cryp *cryp)
+{
+ spin_lock(&mtk_aes.lock);
+ list_del(&cryp->aes_list);
+ spin_unlock(&mtk_aes.lock);
+
+ mtk_aes_unregister_algs();
+ mtk_aes_record_free(cryp);
+}
diff --git a/drivers/crypto/mediatek/mtk-platform.c b/drivers/crypto/mediatek/mtk-platform.c
new file mode 100644
index 0000000..25025fe
--- /dev/null
+++ b/drivers/crypto/mediatek/mtk-platform.c
@@ -0,0 +1,580 @@
+/*
+ * Support for MediaTek cryptographic accelerator.
+ *
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Ryder Lee <ryder.lee@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License.
+ *
+ */
+
+#include <linux/clk.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include "mtk-platform.h"
+#include "mtk-regs.h"
+
+#define MTK_BURST_SIZE(x, y) (((x) & ~0xf0) | ((y) << 4))
+#define MTK_DESC_SIZE_SET(x) ((x) << 0)
+#define MTK_DESC_OFFSET_SET(x) ((x) << 16)
+#define MTK_DFSE_RING_ID(x) (((x) >> 12) & 0xf)
+#define MTK_DSE_MIN_DATA(x) ((x) << 0)
+#define MTK_DSE_MAX_DATA(x) ((x) << 8)
+#define MTK_DFE_MIN_DATA(x) ((x) << 0)
+#define MTK_DFE_MAX_DATA(x) ((x) << 8)
+#define MTK_DFE_MIN_CTRL(x) ((x) << 16)
+#define MTK_DFE_MAX_CTRL(x) ((x) << 24)
+#define MTK_FETCH_SIZE_SET(x) ((x) << 0)
+#define MTK_FETCH_THRESH_SET(x) ((x) << 16)
+#define MTK_IN_BUF_MIN_THRESH(x) ((x) << 8)
+#define MTK_IN_BUF_MAX_THRESH(x) ((x) << 12)
+#define MTK_OUT_BUF_MIN_THRESH(x) ((x) << 0)
+#define MTK_OUT_BUF_MAX_THRESH(x) ((x) << 4)
+#define MTK_CMD_FIFO_SIZE(x) (((x) >> 8) & 0xf)
+#define MTK_RES_FIFO_SIZE(x) (((x) >> 12) & 0xf)
+#define MTK_HIA_DATA_WIDTH(x) (((x) >> 25) & 0x3)
+#define MTK_HIA_DMA_LENGTH(x) (((x) >> 20) & 0x1f)
+#define MTK_IN_TBUF_SIZE(x) (((x) >> 4) & 0xf)
+#define MTK_IN_DBUF_SIZE(x) (((x) >> 8) & 0xf)
+#define MTK_OUT_DBUF_SIZE(x) (((x) >> 16) & 0xf)
+#define MTK_AIC_INT_NUM(x) ((x) & 0x3f)
+#define MTK_AIC_VER_GET(x) ((x) & 0x0ff0ffff)
+#define MTK_PE_TOKEN_CTRL_DEF 0x00014004
+#define MTK_PE_INT_CTRL_DEF 0xc00f400f
+#define MTK_PRNG_CTRL_EN BIT(0)
+#define MTK_PRNG_CTRL_AUTO BIT(1)
+#define MTK_TOKEN_TIMEOUT_EN BIT(22)
+#define MTK_OVL_IRQ_EN BIT(25)
+#define MTK_ATP_PRESENT BIT(30)
+#define MTK_DFSE_THR_CTRL_EN BIT(30)
+#define MTK_DFSE_THR_CTRL_RESET BIT(31)
+#define MTK_HIA_SIGNATURE ((u16)0x35ca)
+#define MTK_CDR_STAT_CLR 0x1f
+#define MTK_RDR_STAT_CLR 0xff
+#define MTK_AIC_VER11 0x011036C9
+#define MTK_AIC_VER12 0x012036C9
+#define MTK_AIC_GLOBAL_CLR 0x7FF00000
+#define MTK_DFSE_IDLE 0xf
+
+/**
+ * This engine is an integrated security subsystem to accelerate
+ * cryptographic functions and protocols to off-load the host processor.
+ *
+ * Hardware modules are briefly introduced below:
+ *
+ * Host Interface Adapter(HIA) - the main interface between the host
+ * system and the hardware subsystem. It is responsible for attaching
+ * processing engine to the specific host bus interface and provides a
+ * standardized software view for off loading tasks to the engine.
+ *
+ * Command Descriptor Ring Manager(CDR Manager) - keeps track of how many
+ * CD the host has prepared in the CDR. It monitors the fill level of its
+ * CD-FIFO and if there's sufficient space for the next block of descriptors,
+ * then it fires off a DMA request to fetch a block of CDs.
+ *
+ * Data fetch engine(DFE) - It is responsible for parsing the CD and
+ * setting up the required control and packet data DMA transfers from
+ * system memory to the processing engine.
+ *
+ * Result Descriptor Ring Manager(RDR Manager) - same as CDR Manager,
+ * but target is result descriptors, Moreover, it also handles the RD
+ * updates under control of the DSE. For each packet data segment
+ * processed, the DSE triggers the RDR Manager to write the updated RD.
+ * If triggered to update, the RDR Manager sets up a DMA operation to
+ * copy the RD from the DSE to the correct location in the RDR.
+ *
+ * Data Store Engine(DSE) - It is responsible for parsing the prepared RD
+ * and setting up the required control and packet data DMA transfers from
+ * the processing engine to system memory.
+ *
+ * Advanced Interrupt Controllers(AICs) - receive interrupt request signals
+ * from various sources and combine them into one interrupt output. The AICs
+ * are use by:
+ * - One for the HIA global and processing engine interrupts.
+ * - The others for the descriptor ring interrupts.
+ */
+
+/* Cryptographic engine capabilities */
+struct mtk_sys_cap {
+ /* host interface adapter */
+ u32 hia_ver;
+ u32 hia_opt;
+ /* packet engine */
+ u32 pkt_eng_opt;
+ /* global hardware */
+ u32 hw_opt;
+};
+
+static void mtk_desc_ring_link(struct mtk_cryp *cryp, u32 mask)
+{
+ /* Assign rings to DFE/DSE thread and enable it */
+ writel(MTK_DFSE_THR_CTRL_EN | mask, cryp->base + DFE_THR_CTRL);
+ writel(MTK_DFSE_THR_CTRL_EN | mask, cryp->base + DSE_THR_CTRL);
+}
+
+static void mtk_dfe_dse_buf_setup(struct mtk_cryp *cryp,
+ struct mtk_sys_cap *cap)
+{
+ u32 width = MTK_HIA_DATA_WIDTH(cap->hia_opt) + 2;
+ u32 len = MTK_HIA_DMA_LENGTH(cap->hia_opt) - 1;
+ u32 ipbuf = min(MTK_IN_DBUF_SIZE(cap->hw_opt) + width, len);
+ u32 opbuf = min(MTK_OUT_DBUF_SIZE(cap->hw_opt) + width, len);
+ u32 itbuf = min(MTK_IN_TBUF_SIZE(cap->hw_opt) + width, len);
+ u32 val;
+
+ val = MTK_DFE_MIN_DATA(ipbuf - 1) | MTK_DFE_MAX_DATA(ipbuf) |
+ MTK_DFE_MIN_CTRL(itbuf - 1) | MTK_DFE_MAX_CTRL(itbuf);
+ writel(val, cryp->base + DFE_CFG);
+
+ val = MTK_DFE_MIN_DATA(opbuf - 1) | MTK_DFE_MAX_DATA(opbuf);
+ writel(val, cryp->base + DSE_CFG);
+
+ val = MTK_IN_BUF_MIN_THRESH(ipbuf - 1) | MTK_IN_BUF_MAX_THRESH(ipbuf);
+ writel(val, cryp->base + PE_IN_DBUF_THRESH);
+
+ val = MTK_IN_BUF_MIN_THRESH(itbuf - 1) | MTK_IN_BUF_MAX_THRESH(itbuf);
+ writel(val, cryp->base + PE_IN_TBUF_THRESH);
+
+ val = MTK_OUT_BUF_MIN_THRESH(opbuf - 1) | MTK_OUT_BUF_MAX_THRESH(opbuf);
+ writel(val, cryp->base + PE_OUT_DBUF_THRESH);
+
+ writel(0, cryp->base + PE_OUT_TBUF_THRESH);
+ writel(0, cryp->base + PE_OUT_BUF_CTRL);
+}
+
+static int mtk_dfe_dse_state_check(struct mtk_cryp *cryp)
+{
+ int ret = -EINVAL;
+ u32 val;
+
+ /* Check for completion of all DMA transfers */
+ val = readl(cryp->base + DFE_THR_STAT);
+ if (MTK_DFSE_RING_ID(val) == MTK_DFSE_IDLE) {
+ val = readl(cryp->base + DSE_THR_STAT);
+ if (MTK_DFSE_RING_ID(val) == MTK_DFSE_IDLE)
+ ret = 0;
+ }
+
+ if (!ret) {
+ /* Take DFE/DSE thread out of reset */
+ writel(0, cryp->base + DFE_THR_CTRL);
+ writel(0, cryp->base + DSE_THR_CTRL);
+ } else {
+ return -EBUSY;
+ }
+
+ return 0;
+}
+
+static int mtk_dfe_dse_reset(struct mtk_cryp *cryp)
+{
+ int err;
+
+ /* Reset DSE/DFE and correct system priorities for all rings. */
+ writel(MTK_DFSE_THR_CTRL_RESET, cryp->base + DFE_THR_CTRL);
+ writel(0, cryp->base + DFE_PRIO_0);
+ writel(0, cryp->base + DFE_PRIO_1);
+ writel(0, cryp->base + DFE_PRIO_2);
+ writel(0, cryp->base + DFE_PRIO_3);
+
+ writel(MTK_DFSE_THR_CTRL_RESET, cryp->base + DSE_THR_CTRL);
+ writel(0, cryp->base + DSE_PRIO_0);
+ writel(0, cryp->base + DSE_PRIO_1);
+ writel(0, cryp->base + DSE_PRIO_2);
+ writel(0, cryp->base + DSE_PRIO_3);
+
+ err = mtk_dfe_dse_state_check(cryp);
+ if (err)
+ return err;
+
+ return 0;
+}
+
+static void mtk_cmd_desc_ring_setup(struct mtk_cryp *cryp,
+ int i, struct mtk_sys_cap *cap)
+{
+ /* Full descriptor that fits FIFO minus one */
+ u32 count =
+ ((1 << MTK_CMD_FIFO_SIZE(cap->hia_opt)) / MTK_DESC_SIZE) - 1;
+ u32 size = count * MTK_DESC_OFFSET;
+ u32 thresh = count * MTK_DESC_SIZE;
+ u32 val;
+
+ /* Temporarily disable external triggering */
+ writel(0, cryp->base + CDR_CFG(i));
+
+ /* Clear CDR count */
+ writel(MTK_DESC_CNT_CLR, cryp->base + CDR_PREP_COUNT(i));
+ writel(MTK_DESC_CNT_CLR, cryp->base + CDR_PROC_COUNT(i));
+
+ writel(0, cryp->base + CDR_PREP_PNTR(i));
+ writel(0, cryp->base + CDR_PROC_PNTR(i));
+ writel(0, cryp->base + CDR_DMA_CFG(i));
+
+ /* Configure command ring host address space */
+ writel(0, cryp->base + CDR_BASE_ADDR_HI(i));
+ writel(cryp->ring[i]->cmd_dma, cryp->base + CDR_BASE_ADDR_LO(i));
+
+ writel(MTK_MAX_RING_SIZE, cryp->base + CDR_RING_SIZE(i));
+
+ /* Clear and disable all CDR interrupts */
+ writel(MTK_CDR_STAT_CLR, cryp->base + CDR_STAT(i));
+
+ /*
+ * Set command descriptor offset and enable additional
+ * token present in descriptor.
+ */
+ val = MTK_DESC_SIZE_SET(MTK_DESC_SIZE) |
+ MTK_DESC_OFFSET_SET(MTK_DESC_OFFSET) |
+ MTK_ATP_PRESENT;
+ writel(val, cryp->base + CDR_DESC_SIZE(i));
+
+ val = MTK_FETCH_SIZE_SET(size) | MTK_FETCH_THRESH_SET(thresh);
+ writel(val, cryp->base + CDR_CFG(i));
+}
+
+static void mtk_res_desc_ring_setup(struct mtk_cryp *cryp,
+ int i, struct mtk_sys_cap *cap)
+{
+ u32 rndup = 2;
+ u32 count = ((1 << MTK_RES_FIFO_SIZE(cap->hia_opt)) / rndup) - 1;
+ u32 size = count * MTK_DESC_OFFSET;
+ u32 thresh = count * rndup;
+ u32 val;
+
+ writel(0, cryp->base + RDR_CFG(i));
+
+ writel(MTK_DESC_CNT_CLR, cryp->base + RDR_PREP_COUNT(i));
+ writel(MTK_DESC_CNT_CLR, cryp->base + RDR_PROC_COUNT(i));
+
+ writel(0, cryp->base + RDR_PREP_PNTR(i));
+ writel(0, cryp->base + RDR_PROC_PNTR(i));
+ writel(0, cryp->base + RDR_DMA_CFG(i));
+
+ writel(0, cryp->base + RDR_BASE_ADDR_HI(i));
+ writel(cryp->ring[i]->res_dma, cryp->base + RDR_BASE_ADDR_LO(i));
+
+ writel(MTK_MAX_RING_SIZE, cryp->base + RDR_RING_SIZE(i));
+ writel(MTK_RDR_STAT_CLR, cryp->base + RDR_STAT(i));
+
+ /*
+ * RDR manager generates update interrupts on a per-completed-packet,
+ * and the rd_proc_thresh_irq interrupt is fired when proc_pkt_count
+ * for the RDR exceeds the number of packets.
+ */
+ writel(MTK_RDR_THRESH_DEF, cryp->base + RDR_THRESH(i));
+
+ /*
+ * Configure a threshold and time-out value for the processed
+ * result descriptors (or complete packets) that are written to
+ * the RDR.
+ */
+ val = MTK_DESC_SIZE_SET(MTK_DESC_SIZE) |
+ MTK_DESC_OFFSET_SET(MTK_DESC_OFFSET);
+ writel(val, cryp->base + RDR_DESC_SIZE(i));
+
+ /*
+ * Configure HIA fetch size and fetch threshold that are used to
+ * fetch blocks of multiple descriptors.
+ */
+ val = MTK_FETCH_SIZE_SET(size) |
+ MTK_FETCH_THRESH_SET(thresh) |
+ MTK_OVL_IRQ_EN;
+ writel(val, cryp->base + RDR_CFG(i));
+}
+
+static int mtk_packet_engine_setup(struct mtk_cryp *cryp)
+{
+ struct mtk_sys_cap cap;
+ int i, err;
+ u32 val;
+
+ cap.hia_ver = readl(cryp->base + HIA_VERSION);
+ cap.hia_opt = readl(cryp->base + HIA_OPTIONS);
+ cap.hw_opt = readl(cryp->base + EIP97_OPTIONS);
+
+ if (!(((u16)cap.hia_ver) == MTK_HIA_SIGNATURE))
+ return -EINVAL;
+
+ /* Configure endianness conversion method for master (DMA) interface */
+ writel(0, cryp->base + EIP97_MST_CTRL);
+
+ /* Set HIA burst size */
+ val = readl(cryp->base + HIA_MST_CTRL);
+ writel(MTK_BURST_SIZE(val, 5), cryp->base + HIA_MST_CTRL);
+
+ err = mtk_dfe_dse_reset(cryp);
+ if (err) {
+ dev_err(cryp->dev, "Failed to reset DFE and DSE.\n");
+ return err;
+ }
+
+ mtk_dfe_dse_buf_setup(cryp, &cap);
+
+ /* Enable the 4 rings for the packet engines. */
+ mtk_desc_ring_link(cryp, 0xf);
+
+ for (i = 0; i < RING_MAX; i++) {
+ mtk_cmd_desc_ring_setup(cryp, i, &cap);
+ mtk_res_desc_ring_setup(cryp, i, &cap);
+ }
+
+ val = MTK_PE_TOKEN_CTRL_DEF | MTK_TOKEN_TIMEOUT_EN;
+ writel(val, cryp->base + PE_TOKEN_CTRL_STAT);
+
+ /* Clear all pending interrupts */
+ writel(MTK_AIC_GLOBAL_CLR, cryp->base + AIC_G_ACK);
+ writel(MTK_PE_INT_CTRL_DEF, cryp->base + PE_INTERRUPT_CTRL_STAT);
+
+ return 0;
+}
+
+static int mtk_aic_cap_check(struct mtk_cryp *cryp, int hw)
+{
+ u32 val;
+
+ if (hw == RING_MAX)
+ val = readl(cryp->base + AIC_G_VERSION);
+ else
+ val = readl(cryp->base + AIC_VERSION(hw));
+
+ val = MTK_AIC_VER_GET(val);
+ if (val != MTK_AIC_VER11 && val != MTK_AIC_VER12)
+ return -ENXIO;
+
+ if (hw == RING_MAX)
+ val = readl(cryp->base + AIC_G_OPTIONS);
+ else
+ val = readl(cryp->base + AIC_OPTIONS(hw));
+
+ val = MTK_AIC_INT_NUM(val);
+ if (!val || val > 32)
+ return -ENXIO;
+
+ return 0;
+}
+
+static int mtk_aic_init(struct mtk_cryp *cryp, int hw)
+{
+ int err;
+
+ err = mtk_aic_cap_check(cryp, hw);
+ if (err)
+ return err;
+
+ /* Disable all interrupts and set initial configuration */
+ if (hw == RING_MAX) {
+ writel(0, cryp->base + AIC_G_ENABLE_CTRL);
+ writel(0, cryp->base + AIC_G_POL_CTRL);
+ writel(0, cryp->base + AIC_G_TYPE_CTRL);
+ writel(0, cryp->base + AIC_G_ENABLE_SET);
+ } else {
+ writel(0, cryp->base + AIC_ENABLE_CTRL(hw));
+ writel(0, cryp->base + AIC_POL_CTRL(hw));
+ writel(0, cryp->base + AIC_TYPE_CTRL(hw));
+ writel(0, cryp->base + AIC_ENABLE_SET(hw));
+ }
+
+ return 0;
+}
+
+static int mtk_accelerator_init(struct mtk_cryp *cryp)
+{
+ int i, err;
+
+ /* Initialize advanced interrupt controller(AIC) */
+ for (i = 0; i < IRQ_NUM; i++) {
+ err = mtk_aic_init(cryp, i);
+ if (err) {
+ dev_err(cryp->dev, "Failed to initialize AIC.\n");
+ return err;
+ }
+ }
+
+ /* Initialize packet engine */
+ err = mtk_packet_engine_setup(cryp);
+ if (err) {
+ dev_err(cryp->dev, "Failed to configure packet engine.\n");
+ return err;
+ }
+
+ return 0;
+}
+
+static void mtk_desc_dma_free(struct mtk_cryp *cryp)
+{
+ int i;
+
+ for (i = 0; i < RING_MAX; i++) {
+ dma_free_coherent(cryp->dev, MTK_MAX_RING_SIZE,
+ cryp->ring[i]->res_base,
+ cryp->ring[i]->res_dma);
+ dma_free_coherent(cryp->dev, MTK_MAX_RING_SIZE,
+ cryp->ring[i]->cmd_base,
+ cryp->ring[i]->cmd_dma);
+ kfree(cryp->ring[i]);
+ }
+}
+
+static int mtk_desc_ring_alloc(struct mtk_cryp *cryp)
+{
+ struct mtk_ring **ring = cryp->ring;
+ int i, err = ENOMEM;
+
+ for (i = 0; i < RING_MAX; i++) {
+ ring[i] = kzalloc(sizeof(**ring), GFP_KERNEL);
+ if (!ring[i])
+ goto err_cleanup;
+
+ ring[i]->cmd_base = dma_zalloc_coherent(cryp->dev,
+ MTK_MAX_RING_SIZE, &ring[i]->cmd_dma,
+ GFP_KERNEL);
+ if (!ring[i]->cmd_base)
+ goto err_cleanup;
+
+ ring[i]->res_base = dma_zalloc_coherent(cryp->dev,
+ MTK_MAX_RING_SIZE, &ring[i]->res_dma,
+ GFP_KERNEL);
+ if (!ring[i]->res_base)
+ goto err_cleanup;
+ }
+ return 0;
+
+err_cleanup:
+ for (; i--; ) {
+ dma_free_coherent(cryp->dev, MTK_MAX_RING_SIZE,
+ ring[i]->res_base, ring[i]->res_dma);
+ dma_free_coherent(cryp->dev, MTK_MAX_RING_SIZE,
+ ring[i]->cmd_base, ring[i]->cmd_dma);
+ kfree(ring[i]);
+ }
+ return err;
+}
+
+static int mtk_crypto_probe(struct platform_device *pdev)
+{
+ struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ struct mtk_cryp *cryp;
+ int i, err;
+
+ cryp = devm_kzalloc(&pdev->dev, sizeof(*cryp), GFP_KERNEL);
+ if (!cryp)
+ return -ENOMEM;
+
+ cryp->base = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(cryp->base))
+ return PTR_ERR(cryp->base);
+
+ for (i = 0; i < IRQ_NUM; i++) {
+ cryp->irq[i] = platform_get_irq(pdev, i);
+ if (cryp->irq[i] < 0) {
+ dev_err(cryp->dev, "no IRQ:%d resource info\n", i);
+ return -ENXIO;
+ }
+ }
+
+ cryp->clk_ethif = devm_clk_get(&pdev->dev, "ethif");
+ cryp->clk_cryp = devm_clk_get(&pdev->dev, "cryp");
+ if (IS_ERR(cryp->clk_ethif) || IS_ERR(cryp->clk_cryp))
+ return -EPROBE_DEFER;
+
+ cryp->dev = &pdev->dev;
+ pm_runtime_enable(cryp->dev);
+ pm_runtime_get_sync(cryp->dev);
+
+ err = clk_prepare_enable(cryp->clk_ethif);
+ if (err)
+ goto err_clk_ethif;
+
+ err = clk_prepare_enable(cryp->clk_cryp);
+ if (err)
+ goto err_clk_cryp;
+
+ err = mtk_desc_ring_alloc(cryp);
+ if (err) {
+ dev_err(cryp->dev, "Unable to allocate descriptor rings.\n");
+ goto err_resource;
+ }
+
+ err = mtk_accelerator_init(cryp);
+ if (err) {
+ dev_err(cryp->dev, "Failed to initialize cryptographic engine.\n");
+ goto err_engine;
+ }
+
+ err = mtk_cipher_alg_register(cryp);
+ if (err) {
+ dev_err(cryp->dev, "Unable to register MTK-AES.\n");
+ goto err_cipher;
+ }
+
+ err = mtk_hash_alg_register(cryp);
+ if (err) {
+ dev_err(cryp->dev, "Unable to register MTK-SHA.\n");
+ goto err_hash;
+ }
+
+ platform_set_drvdata(pdev, cryp);
+ return 0;
+
+err_hash:
+ mtk_cipher_alg_release(cryp);
+err_cipher:
+ mtk_dfe_dse_reset(cryp);
+err_engine:
+ mtk_desc_dma_free(cryp);
+err_resource:
+ clk_disable_unprepare(cryp->clk_cryp);
+err_clk_cryp:
+ clk_disable_unprepare(cryp->clk_ethif);
+err_clk_ethif:
+ pm_runtime_put_sync(cryp->dev);
+ pm_runtime_disable(cryp->dev);
+
+ return err;
+}
+
+static int mtk_crypto_remove(struct platform_device *pdev)
+{
+ struct mtk_cryp *cryp = platform_get_drvdata(pdev);
+
+ mtk_hash_alg_release(cryp);
+ mtk_cipher_alg_release(cryp);
+ mtk_desc_dma_free(cryp);
+
+ clk_disable_unprepare(cryp->clk_cryp);
+ clk_disable_unprepare(cryp->clk_ethif);
+
+ pm_runtime_put_sync(cryp->dev);
+ pm_runtime_disable(cryp->dev);
+ platform_set_drvdata(pdev, NULL);
+
+ return 0;
+}
+
+const struct of_device_id of_crypto_id[] = {
+ { .compatible = "mediatek,mt7623-crypto" },
+ {},
+};
+MODULE_DEVICE_TABLE(of, of_crypto_id);
+
+static struct platform_driver mtk_crypto_driver = {
+ .probe = mtk_crypto_probe,
+ .remove = mtk_crypto_remove,
+ .driver = {
+ .name = "mtk-crypto",
+ .owner = THIS_MODULE,
+ .of_match_table = of_crypto_id,
+ },
+};
+module_platform_driver(mtk_crypto_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ryder Lee <ryder.lee@mediatek.com>");
+MODULE_DESCRIPTION("Cryptographic accelerator driver for MediaTek SoC");
diff --git a/drivers/crypto/mediatek/mtk-platform.h b/drivers/crypto/mediatek/mtk-platform.h
new file mode 100644
index 0000000..e9651f1
--- /dev/null
+++ b/drivers/crypto/mediatek/mtk-platform.h
@@ -0,0 +1,235 @@
+/*
+ * Support for MediaTek cryptographic accelerator.
+ *
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Ryder Lee <ryder.lee@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License.
+ *
+ */
+
+#ifndef __MTK_PLATFORM_H_
+#define __MTK_PLATFORM_H_
+
+#include <crypto/internal/hash.h>
+#include <linux/crypto.h>
+#include <linux/interrupt.h>
+
+#define MTK_RDR_THRESH_DEF 0x800001
+
+#define MTK_IRQ_RDR0 BIT(1)
+#define MTK_IRQ_RDR1 BIT(3)
+#define MTK_IRQ_RDR2 BIT(5)
+#define MTK_IRQ_RDR3 BIT(7)
+
+#define MTK_DESC_CNT_CLR BIT(31)
+#define MTK_DESC_LAST BIT(22)
+#define MTK_DESC_FIRST BIT(23)
+#define MTK_DESC_BUF_LEN(x) ((x) & 0x1ffff)
+#define MTK_DESC_CT_LEN(x) (((x) & 0xff) << 24)
+
+#define SIZE_IN_WORDS(x) ((x) >> 2)
+
+/**
+ * Ring 0/1 are used by AES encrypt and decrypt.
+ * Ring 2/3 are used by SHA.
+ */
+enum {
+ RING0 = 0,
+ RING1,
+ RING2,
+ RING3,
+ RING_MAX,
+};
+
+#define RECORD_NUM (RING_MAX / 2)
+#define IRQ_NUM 5
+
+/**
+ * struct mtk_desc - DMA descriptor
+ * @hdr: the descriptor control header
+ * @buf: DMA address of input buffer segment
+ * @ct: DMA address of command token that control operation flow
+ * @ct_hdr: the command token control header
+ * @tag: the user-defined field
+ * @tfm: DMA address of transform state
+ * @bound: align descriptors offset boundary
+ *
+ * Structure passed to the crypto engine to describe where source
+ * data needs to be fetched and how it needs to be processed.
+ */
+struct mtk_desc {
+ u32 hdr;
+ u32 buf;
+ u32 ct;
+ u32 ct_hdr;
+ u32 tag;
+ u32 tfm;
+ u32 bound[2];
+};
+
+/**
+ * struct mtk_ring - Descriptor ring
+ * @cmd_base: pointer to command descriptor ring base
+ * @cmd_dma: DMA address of command descriptor ring
+ * @res_base: pointer to result descriptor ring base
+ * @res_dma: DMA address of result descriptor ring
+ * @pos: current position in the ring
+ *
+ * A descriptor ring is a circular buffer that is used to manage
+ * one or more descriptors. There are two type of descriptor rings;
+ * the command descriptor ring and result descriptor ring.
+ */
+struct mtk_ring {
+ struct mtk_desc *cmd_base;
+ dma_addr_t cmd_dma;
+ struct mtk_desc *res_base;
+ dma_addr_t res_dma;
+ u32 pos;
+};
+
+#define MTK_MAX_DESC_NUM 512
+#define MTK_DESC_OFFSET SIZE_IN_WORDS(sizeof(struct mtk_desc))
+#define MTK_DESC_SIZE (MTK_DESC_OFFSET - 2)
+#define MTK_MAX_RING_SIZE ((sizeof(struct mtk_desc) * MTK_MAX_DESC_NUM))
+#define MTK_DESC_CNT(x) ((MTK_DESC_OFFSET * (x)) << 2)
+
+/**
+ * struct mtk_aes_dma - Structure that holds sg list info
+ * @sg: pointer to scatter-gather list
+ * @nents: number of entries in the sg list
+ * @remainder: remainder of sg list
+ * @sg_len: number of entries in the sg mapped list
+ */
+struct mtk_aes_dma {
+ struct scatterlist *sg;
+ int nents;
+ u32 remainder;
+ u32 sg_len;
+};
+
+/**
+ * struct mtk_aes - AES operation record
+ * @queue: crypto request queue
+ * @req: pointer to ablkcipher request
+ * @task: the tasklet is use in AES interrupt
+ * @src: the structure that holds source sg list info
+ * @dst: the structure that holds destination sg list info
+ * @aligned_sg: the scatter list is use to alignment
+ * @real_dst: pointer to the destination sg list
+ * @total: request buffer length
+ * @buf: pointer to page buffer
+ * @info: pointer to AES transform state and command token
+ * @ct_hdr: AES command token control field
+ * @ct_size: size of AES command token
+ * @ct_dma: DMA address of AES command token
+ * @tfm_dma: DMA address of AES transform state
+ * @id: record identification
+ * @flags: it's describing AES operation state
+ * @lock: the ablkcipher queue lock
+ *
+ * Structure used to record AES execution state.
+ */
+struct mtk_aes {
+ struct crypto_queue queue;
+ struct ablkcipher_request *req;
+ struct tasklet_struct task;
+ struct mtk_aes_dma src;
+ struct mtk_aes_dma dst;
+
+ struct scatterlist aligned_sg;
+ struct scatterlist *real_dst;
+
+ size_t total;
+ void *buf;
+
+ void *info;
+ u32 ct_hdr;
+ u32 ct_size;
+ dma_addr_t ct_dma;
+ dma_addr_t tfm_dma;
+
+ u8 id;
+ unsigned long flags;
+ /* queue lock */
+ spinlock_t lock;
+};
+
+/**
+ * struct mtk_sha - SHA operation record
+ * @queue: crypto request queue
+ * @req: pointer to ahash request
+ * @task: the tasklet is use in SHA interrupt
+ * @info: pointer to SHA transform state and command token
+ * @ct_hdr: SHA command token control field
+ * @ct_size: size of SHA command token
+ * @ct_dma: DMA address of SHA command token
+ * @tfm_dma: DMA address of SHA transform state
+ * @id: record identification
+ * @flags: it's describing SHA operation state
+ * @lock: the ablkcipher queue lock
+ *
+ * Structure used to record SHA execution state.
+ */
+struct mtk_sha {
+ struct crypto_queue queue;
+ struct ahash_request *req;
+ struct tasklet_struct task;
+
+ void *info;
+ u32 ct_hdr;
+ u32 ct_size;
+ dma_addr_t ct_dma;
+ dma_addr_t tfm_dma;
+
+ u8 id;
+ unsigned long flags;
+ /* queue lock */
+ spinlock_t lock;
+};
+
+/**
+ * struct mtk_cryp - Cryptographic device
+ * @base: pointer to mapped register I/O base
+ * @dev: pointer to device
+ * @clk_ethif: pointer to ethif clock
+ * @clk_cryp: pointer to crypto clock
+ * @irq: global system and rings IRQ
+ * @ring: pointer to execution state of AES
+ * @aes: pointer to execution state of SHA
+ * @sha: each execution record map to a ring
+ * @aes_list: device list of AES
+ * @sha_list: device list of SHA
+ * @tmp: pointer to temporary buffer for internal use
+ * @tmp_dma: DMA address of temporary buffer
+ * @rec: it's used to select SHA record for tfm
+ *
+ * Structure storing cryptographic device information.
+ */
+struct mtk_cryp {
+ void __iomem *base;
+ struct device *dev;
+ struct clk *clk_ethif;
+ struct clk *clk_cryp;
+ int irq[IRQ_NUM];
+
+ struct mtk_ring *ring[RING_MAX];
+ struct mtk_aes *aes[RECORD_NUM];
+ struct mtk_sha *sha[RECORD_NUM];
+
+ struct list_head aes_list;
+ struct list_head sha_list;
+
+ void *tmp;
+ dma_addr_t tmp_dma;
+ bool rec;
+};
+
+int mtk_cipher_alg_register(struct mtk_cryp *cryp);
+void mtk_cipher_alg_release(struct mtk_cryp *cryp);
+int mtk_hash_alg_register(struct mtk_cryp *cryp);
+void mtk_hash_alg_release(struct mtk_cryp *cryp);
+
+#endif /* __MTK_PLATFORM_H_ */
diff --git a/drivers/crypto/mediatek/mtk-regs.h b/drivers/crypto/mediatek/mtk-regs.h
new file mode 100644
index 0000000..94f4eb8
--- /dev/null
+++ b/drivers/crypto/mediatek/mtk-regs.h
@@ -0,0 +1,194 @@
+/*
+ * Support for MediaTek cryptographic accelerator.
+ *
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Ryder Lee <ryder.lee@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License.
+ *
+ */
+
+#ifndef __MTK_REGS_H__
+#define __MTK_REGS_H__
+
+/* HIA, Command Descriptor Ring Manager */
+#define CDR_BASE_ADDR_LO(x) (0x0 + ((x) << 12))
+#define CDR_BASE_ADDR_HI(x) (0x4 + ((x) << 12))
+#define CDR_DATA_BASE_ADDR_LO(x) (0x8 + ((x) << 12))
+#define CDR_DATA_BASE_ADDR_HI(x) (0xC + ((x) << 12))
+#define CDR_ACD_BASE_ADDR_LO(x) (0x10 + ((x) << 12))
+#define CDR_ACD_BASE_ADDR_HI(x) (0x14 + ((x) << 12))
+#define CDR_RING_SIZE(x) (0x18 + ((x) << 12))
+#define CDR_DESC_SIZE(x) (0x1C + ((x) << 12))
+#define CDR_CFG(x) (0x20 + ((x) << 12))
+#define CDR_DMA_CFG(x) (0x24 + ((x) << 12))
+#define CDR_THRESH(x) (0x28 + ((x) << 12))
+#define CDR_PREP_COUNT(x) (0x2C + ((x) << 12))
+#define CDR_PROC_COUNT(x) (0x30 + ((x) << 12))
+#define CDR_PREP_PNTR(x) (0x34 + ((x) << 12))
+#define CDR_PROC_PNTR(x) (0x38 + ((x) << 12))
+#define CDR_STAT(x) (0x3C + ((x) << 12))
+
+/* HIA, Result Descriptor Ring Manager */
+#define RDR_BASE_ADDR_LO(x) (0x800 + ((x) << 12))
+#define RDR_BASE_ADDR_HI(x) (0x804 + ((x) << 12))
+#define RDR_DATA_BASE_ADDR_LO(x) (0x808 + ((x) << 12))
+#define RDR_DATA_BASE_ADDR_HI(x) (0x80C + ((x) << 12))
+#define RDR_ACD_BASE_ADDR_LO(x) (0x810 + ((x) << 12))
+#define RDR_ACD_BASE_ADDR_HI(x) (0x814 + ((x) << 12))
+#define RDR_RING_SIZE(x) (0x818 + ((x) << 12))
+#define RDR_DESC_SIZE(x) (0x81C + ((x) << 12))
+#define RDR_CFG(x) (0x820 + ((x) << 12))
+#define RDR_DMA_CFG(x) (0x824 + ((x) << 12))
+#define RDR_THRESH(x) (0x828 + ((x) << 12))
+#define RDR_PREP_COUNT(x) (0x82C + ((x) << 12))
+#define RDR_PROC_COUNT(x) (0x830 + ((x) << 12))
+#define RDR_PREP_PNTR(x) (0x834 + ((x) << 12))
+#define RDR_PROC_PNTR(x) (0x838 + ((x) << 12))
+#define RDR_STAT(x) (0x83C + ((x) << 12))
+
+/* HIA, Ring AIC */
+#define AIC_POL_CTRL(x) (0xE000 - ((x) << 12))
+#define AIC_TYPE_CTRL(x) (0xE004 - ((x) << 12))
+#define AIC_ENABLE_CTRL(x) (0xE008 - ((x) << 12))
+#define AIC_RAW_STAL(x) (0xE00C - ((x) << 12))
+#define AIC_ENABLE_SET(x) (0xE00C - ((x) << 12))
+#define AIC_ENABLED_STAT(x) (0xE010 - ((x) << 12))
+#define AIC_ACK(x) (0xE010 - ((x) << 12))
+#define AIC_ENABLE_CLR(x) (0xE014 - ((x) << 12))
+#define AIC_OPTIONS(x) (0xE018 - ((x) << 12))
+#define AIC_VERSION(x) (0xE01C - ((x) << 12))
+
+/* HIA, Global AIC */
+#define AIC_G_POL_CTRL 0xF800
+#define AIC_G_TYPE_CTRL 0xF804
+#define AIC_G_ENABLE_CTRL 0xF808
+#define AIC_G_RAW_STAT 0xF80C
+#define AIC_G_ENABLE_SET 0xF80C
+#define AIC_G_ENABLED_STAT 0xF810
+#define AIC_G_ACK 0xF810
+#define AIC_G_ENABLE_CLR 0xF814
+#define AIC_G_OPTIONS 0xF818
+#define AIC_G_VERSION 0xF81C
+
+/* HIA, Data Fetch Engine */
+#define DFE_CFG 0xF000
+#define DFE_PRIO_0 0xF010
+#define DFE_PRIO_1 0xF014
+#define DFE_PRIO_2 0xF018
+#define DFE_PRIO_3 0xF01C
+
+/* HIA, Data Fetch Engine access monitoring for CDR */
+#define DFE_RING_REGION_LO(x) (0xF080 + ((x) << 3))
+#define DFE_RING_REGION_HI(x) (0xF084 + ((x) << 3))
+
+/* HIA, Data Fetch Engine thread control and status for thread */
+#define DFE_THR_CTRL 0xF200
+#define DFE_THR_STAT 0xF204
+#define DFE_THR_DESC_CTRL 0xF208
+#define DFE_THR_DESC_DPTR_LO 0xF210
+#define DFE_THR_DESC_DPTR_HI 0xF214
+#define DFE_THR_DESC_ACDPTR_LO 0xF218
+#define DFE_THR_DESC_ACDPTR_HI 0xF21C
+
+/* HIA, Data Store Engine */
+#define DSE_CFG 0xF400
+#define DSE_PRIO_0 0xF410
+#define DSE_PRIO_1 0xF414
+#define DSE_PRIO_2 0xF418
+#define DSE_PRIO_3 0xF41C
+
+/* HIA, Data Store Engine access monitoring for RDR */
+#define DSE_RING_REGION_LO(x) (0xF480 + ((x) << 3))
+#define DSE_RING_REGION_HI(x) (0xF484 + ((x) << 3))
+
+/* HIA, Data Store Engine thread control and status for thread */
+#define DSE_THR_CTRL 0xF600
+#define DSE_THR_STAT 0xF604
+#define DSE_THR_DESC_CTRL 0xF608
+#define DSE_THR_DESC_DPTR_LO 0xF610
+#define DSE_THR_DESC_DPTR_HI 0xF614
+#define DSE_THR_DESC_S_DPTR_LO 0xF618
+#define DSE_THR_DESC_S_DPTR_HI 0xF61C
+#define DSE_THR_ERROR_STAT 0xF620
+
+/* HIA Global */
+#define HIA_MST_CTRL 0xFFF4
+#define HIA_OPTIONS 0xFFF8
+#define HIA_VERSION 0xFFFC
+
+/* Processing Engine Input Side, Processing Engine */
+#define PE_IN_DBUF_THRESH 0x10000
+#define PE_IN_TBUF_THRESH 0x10100
+
+/* Packet Engine Configuration / Status Registers */
+#define PE_TOKEN_CTRL_STAT 0x11000
+#define PE_FUNCTION_EN 0x11004
+#define PE_CONTEXT_CTRL 0x11008
+#define PE_INTERRUPT_CTRL_STAT 0x11010
+#define PE_CONTEXT_STAT 0x1100C
+#define PE_OUT_TRANS_CTRL_STAT 0x11018
+#define PE_OUT_BUF_CTRL 0x1101C
+
+/* Packet Engine PRNG Registers */
+#define PE_PRNG_STAT 0x11040
+#define PE_PRNG_CTRL 0x11044
+#define PE_PRNG_SEED_L 0x11048
+#define PE_PRNG_SEED_H 0x1104C
+#define PE_PRNG_KEY_0_L 0x11050
+#define PE_PRNG_KEY_0_H 0x11054
+#define PE_PRNG_KEY_1_L 0x11058
+#define PE_PRNG_KEY_1_H 0x1105C
+#define PE_PRNG_RES_0 0x11060
+#define PE_PRNG_RES_1 0x11064
+#define PE_PRNG_RES_2 0x11068
+#define PE_PRNG_RES_3 0x1106C
+#define PE_PRNG_LFSR_L 0x11070
+#define PE_PRNG_LFSR_H 0x11074
+
+/* Packet Engine AIC */
+#define PE_EIP96_AIC_POL_CTRL 0x113C0
+#define PE_EIP96_AIC_TYPE_CTRL 0x113C4
+#define PE_EIP96_AIC_ENABLE_CTRL 0x113C8
+#define PE_EIP96_AIC_RAW_STAT 0x113CC
+#define PE_EIP96_AIC_ENABLE_SET 0x113CC
+#define PE_EIP96_AIC_ENABLED_STAT 0x113D0
+#define PE_EIP96_AIC_ACK 0x113D0
+#define PE_EIP96_AIC_ENABLE_CLR 0x113D4
+#define PE_EIP96_AIC_OPTIONS 0x113D8
+#define PE_EIP96_AIC_VERSION 0x113DC
+
+/* Packet Engine Options & Version Registers */
+#define PE_EIP96_OPTIONS 0x113F8
+#define PE_EIP96_VERSION 0x113FC
+
+/* Processing Engine Output Side */
+#define PE_OUT_DBUF_THRESH 0x11C00
+#define PE_OUT_TBUF_THRESH 0x11D00
+
+/* Processing Engine Local AIC */
+#define PE_AIC_POL_CTRL 0x11F00
+#define PE_AIC_TYPE_CTRL 0x11F04
+#define PE_AIC_ENABLE_CTRL 0x11F08
+#define PE_AIC_RAW_STAT 0x11F0C
+#define PE_AIC_ENABLE_SET 0x11F0C
+#define PE_AIC_ENABLED_STAT 0x11F10
+#define PE_AIC_ENABLE_CLR 0x11F14
+#define PE_AIC_OPTIONS 0x11F18
+#define PE_AIC_VERSION 0x11F1C
+
+/* Processing Engine General Configuration and Version */
+#define PE_IN_FLIGHT 0x11FF0
+#define PE_OPTIONS 0x11FF8
+#define PE_VERSION 0x11FFC
+
+/* EIP-97 - Global */
+#define EIP97_CLOCK_STATE 0x1FFE4
+#define EIP97_FORCE_CLOCK_ON 0x1FFE8
+#define EIP97_FORCE_CLOCK_OFF 0x1FFEC
+#define EIP97_MST_CTRL 0x1FFF4
+#define EIP97_OPTIONS 0x1FFF8
+#define EIP97_VERSION 0x1FFFC
+#endif /* __MTK_REGS_H__ */
diff --git a/drivers/crypto/mediatek/mtk-sha.c b/drivers/crypto/mediatek/mtk-sha.c
new file mode 100644
index 0000000..191dee2
--- /dev/null
+++ b/drivers/crypto/mediatek/mtk-sha.c
@@ -0,0 +1,1423 @@
+/*
+ * Cryptographic API.
+ *
+ * Support for MediaTek SHA1/SHA2 hardware accelerator.
+ *
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Ryder Lee <ryder.lee@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Some ideas are from atmel-sha.c and omap-sham.c drivers.
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/internal/hash.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/sha.h>
+#include <linux/crypto.h>
+#include <linux/dma-mapping.h>
+#include <linux/scatterlist.h>
+#include "mtk-platform.h"
+#include "mtk-regs.h"
+
+#define SHA_ALIGN_MSK (sizeof(u32) - 1)
+#define SHA_QUEUE_SIZE 512
+#define SHA_TMP_STATE_SIZE 512
+
+#define SHA_DATA_LEN_MSK GENMASK(16, 0)
+#define SHA_BUFFER_LEN ((u32)PAGE_SIZE)
+
+#define SHA_OP_UPDATE 1
+#define SHA_OP_FINAL 2
+
+/* SHA command token */
+#define SHA_CT_SIZE 5
+#define SHA_CT_CTRL_HDR 0x02220000
+#define SHA_COMMAND0 0x03020000
+#define SHA_COMMAND1 0x21060000
+#define SHA_COMMAND2 0xe0e63802
+
+/* SHA transform information */
+#define SHA_TFM_HASH (0x2 << 0)
+#define SHA_TFM_DIG_TYPE (0x1 << 21)
+#define SHA_TFM_SIZE(x) ((x) << 8)
+#define SHA_TFM_START (0x1 << 4)
+#define SHA_TFM_CONTINUE (0x1 << 5)
+#define SHA_TFM_HASH_STORE (0x1 << 19)
+#define SHA_TFM_SHA1 (0x2 << 23)
+#define SHA_TFM_SHA256 (0x3 << 23)
+#define SHA_TFM_SHA224 (0x4 << 23)
+#define SHA_TFM_SHA512 (0x5 << 23)
+#define SHA_TFM_SHA384 (0x6 << 23)
+#define SHA_TFM_DIGEST(x) (((x) & 0xf) << 24)
+
+/* SHA flags */
+#define SHA_FLAGS_BUSY BIT(0)
+#define SHA_FLAGS_FINAL BIT(1)
+#define SHA_FLAGS_FINUP BIT(2)
+#define SHA_FLAGS_SG BIT(3)
+#define SHA_FLAGS_ALGO_MASK GENMASK(8, 4)
+#define SHA_FLAGS_SHA1 BIT(4)
+#define SHA_FLAGS_SHA224 BIT(5)
+#define SHA_FLAGS_SHA256 BIT(6)
+#define SHA_FLAGS_SHA384 BIT(7)
+#define SHA_FLAGS_SHA512 BIT(8)
+#define SHA_FLAGS_HMAC BIT(9)
+#define SHA_FLAGS_PAD BIT(10)
+
+/**
+ * SHA command token(CT) is a set of hardware instructions that
+ * are used to control engine's processing flow of sha, and it
+ * contains the first two words of transform state.
+ */
+struct mtk_sha_ct {
+ u32 tfm_ctrl0;
+ u32 tfm_ctrl1;
+ u32 ct_ctrl0;
+ u32 ct_ctrl1;
+ u32 ct_ctrl2;
+};
+
+/**
+ * SHA transform state(tfm) is used to define SHA transform state
+ * and store the result digest that produce by crypto engine.
+ */
+struct mtk_sha_tfm {
+ u32 tfm_ctrl0;
+ u32 tfm_ctrl1;
+ /* store result digests */
+ u8 digest[SHA512_DIGEST_SIZE] __aligned(sizeof(u32));
+};
+
+/**
+ * mtk_sha_info consists of command token and transform state
+ * of SHA, its role is similar to mtk_aes_info.
+ */
+struct mtk_sha_info {
+ struct mtk_sha_ct ct;
+ struct mtk_sha_tfm tfm;
+};
+
+struct mtk_sha_reqctx {
+ struct mtk_sha_info info;
+ unsigned long flags;
+ unsigned long op;
+
+ u64 digcnt;
+ bool start;
+ size_t bufcnt;
+ dma_addr_t dma_addr;
+
+ /* walk state */
+ struct scatterlist *sg;
+ u32 offset; /* offset in current sg */
+ u32 total; /* total request */
+ size_t ds;
+ size_t bs;
+
+ u8 *buffer;
+};
+
+struct mtk_sha_hmac_ctx {
+ struct crypto_shash *shash;
+ u8 ipad[SHA512_BLOCK_SIZE] __aligned(sizeof(u32));
+ u8 opad[SHA512_BLOCK_SIZE] __aligned(sizeof(u32));
+};
+
+struct mtk_sha_ctx {
+ struct mtk_cryp *cryp;
+ unsigned long flags;
+ u8 id;
+ u8 buf[SHA_BUFFER_LEN] __aligned(sizeof(u32));
+
+ struct mtk_sha_hmac_ctx base[0];
+};
+
+struct mtk_sha_drv {
+ struct list_head dev_list;
+ /* device list lock */
+ spinlock_t lock;
+};
+
+static struct mtk_sha_drv mtk_sha = {
+ .dev_list = LIST_HEAD_INIT(mtk_sha.dev_list),
+ .lock = __SPIN_LOCK_UNLOCKED(mtk_sha.lock),
+};
+
+static int mtk_sha_handle_queue(struct mtk_cryp *cryp, u8 id,
+ struct ahash_request *req);
+
+static inline u32 mtk_sha_read(struct mtk_cryp *cryp, u32 offset)
+{
+ return readl_relaxed(cryp->base + offset);
+}
+
+static inline void mtk_sha_write(struct mtk_cryp *cryp,
+ u32 offset, u32 value)
+{
+ writel_relaxed(value, cryp->base + offset);
+}
+
+static struct mtk_cryp *mtk_sha_find_dev(struct mtk_sha_ctx *tctx)
+{
+ struct mtk_cryp *cryp = NULL;
+ struct mtk_cryp *tmp;
+
+ spin_lock_bh(&mtk_sha.lock);
+ if (!tctx->cryp) {
+ list_for_each_entry(tmp, &mtk_sha.dev_list, sha_list) {
+ cryp = tmp;
+ break;
+ }
+ tctx->cryp = cryp;
+ } else {
+ cryp = tctx->cryp;
+ }
+
+ /*
+ * Assign record id to tfm in round-robin fashion, and this
+ * will help tfm to bind to corresponding descriptor rings.
+ */
+ tctx->id = cryp->rec;
+ cryp->rec = !cryp->rec;
+
+ spin_unlock_bh(&mtk_sha.lock);
+
+ return cryp;
+}
+
+static int mtk_sha_append_sg(struct mtk_sha_reqctx *ctx)
+{
+ size_t count;
+
+ while ((ctx->bufcnt < SHA_BUFFER_LEN) && ctx->total) {
+ count = min(ctx->sg->length - ctx->offset, ctx->total);
+ count = min(count, SHA_BUFFER_LEN - ctx->bufcnt);
+
+ if (count <= 0) {
+ /*
+ * Check if count <= 0 because the buffer is full or
+ * because the sg length is 0. In the latest case,
+ * check if there is another sg in the list, a 0 length
+ * sg doesn't necessarily mean the end of the sg list.
+ */
+ if ((ctx->sg->length == 0) && !sg_is_last(ctx->sg)) {
+ ctx->sg = sg_next(ctx->sg);
+ continue;
+ } else {
+ break;
+ }
+ }
+
+ scatterwalk_map_and_copy(ctx->buffer + ctx->bufcnt, ctx->sg,
+ ctx->offset, count, 0);
+
+ ctx->bufcnt += count;
+ ctx->offset += count;
+ ctx->total -= count;
+
+ if (ctx->offset == ctx->sg->length) {
+ ctx->sg = sg_next(ctx->sg);
+ if (ctx->sg)
+ ctx->offset = 0;
+ else
+ ctx->total = 0;
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * The purpose of this padding is to ensure that the padded message is a
+ * multiple of 512 bits (SHA1/SHA224/SHA256) or 1024 bits (SHA384/SHA512).
+ * The bit "1" is appended at the end of the message followed by
+ * "padlen-1" zero bits. Then a 64 bits block (SHA1/SHA224/SHA256) or
+ * 128 bits block (SHA384/SHA512) equals to the message length in bits
+ * is appended.
+ *
+ * For SHA1/SHA224/SHA256, padlen is calculated as followed:
+ * - if message length < 56 bytes then padlen = 56 - message length
+ * - else padlen = 64 + 56 - message length
+ *
+ * For SHA384/SHA512, padlen is calculated as followed:
+ * - if message length < 112 bytes then padlen = 112 - message length
+ * - else padlen = 128 + 112 - message length
+ */
+static void mtk_sha_fill_padding(struct mtk_sha_reqctx *ctx, u32 len)
+{
+ u32 index, padlen;
+ u64 bits[2];
+ u64 size = ctx->digcnt;
+
+ size += ctx->bufcnt;
+ size += len;
+
+ bits[1] = cpu_to_be64(size << 3);
+ bits[0] = cpu_to_be64(size >> 61);
+
+ if (ctx->flags & (SHA_FLAGS_SHA384 | SHA_FLAGS_SHA512)) {
+ index = ctx->bufcnt & 0x7f;
+ padlen = (index < 112) ? (112 - index) : ((128 + 112) - index);
+ *(ctx->buffer + ctx->bufcnt) = 0x80;
+ memset(ctx->buffer + ctx->bufcnt + 1, 0, padlen - 1);
+ memcpy(ctx->buffer + ctx->bufcnt + padlen, bits, 16);
+ ctx->bufcnt += padlen + 16;
+ ctx->flags |= SHA_FLAGS_PAD;
+ } else {
+ index = ctx->bufcnt & 0x3f;
+ padlen = (index < 56) ? (56 - index) : ((64 + 56) - index);
+ *(ctx->buffer + ctx->bufcnt) = 0x80;
+ memset(ctx->buffer + ctx->bufcnt + 1, 0, padlen - 1);
+ memcpy(ctx->buffer + ctx->bufcnt + padlen, &bits[1], 8);
+ ctx->bufcnt += padlen + 8;
+ ctx->flags |= SHA_FLAGS_PAD;
+ }
+}
+
+/* Initialize basic transform information of SHA */
+static void mtk_sha_info_init(struct mtk_sha *sha,
+ struct mtk_sha_reqctx *ctx)
+{
+ struct mtk_sha_info *info = sha->info;
+ struct mtk_sha_ct *ct = &info->ct;
+ struct mtk_sha_tfm *tfm = &info->tfm;
+
+ sha->ct_hdr = SHA_CT_CTRL_HDR;
+ sha->ct_size = SHA_CT_SIZE;
+
+ tfm->tfm_ctrl0 = SHA_TFM_HASH | SHA_TFM_DIG_TYPE |
+ SHA_TFM_SIZE(SIZE_IN_WORDS(ctx->ds));
+
+ switch (ctx->flags & SHA_FLAGS_ALGO_MASK) {
+ case SHA_FLAGS_SHA1:
+ tfm->tfm_ctrl0 |= SHA_TFM_SHA1;
+ break;
+ case SHA_FLAGS_SHA224:
+ tfm->tfm_ctrl0 |= SHA_TFM_SHA224;
+ break;
+ case SHA_FLAGS_SHA256:
+ tfm->tfm_ctrl0 |= SHA_TFM_SHA256;
+ break;
+ case SHA_FLAGS_SHA384:
+ tfm->tfm_ctrl0 |= SHA_TFM_SHA384;
+ break;
+ case SHA_FLAGS_SHA512:
+ tfm->tfm_ctrl0 |= SHA_TFM_SHA512;
+ break;
+
+ default:
+ /* Should not happen... */
+ return;
+ }
+
+ tfm->tfm_ctrl1 = SHA_TFM_HASH_STORE;
+ ct->tfm_ctrl0 = tfm->tfm_ctrl0 | SHA_TFM_CONTINUE | SHA_TFM_START;
+ ct->tfm_ctrl1 = tfm->tfm_ctrl1;
+
+ ct->ct_ctrl0 = SHA_COMMAND0;
+ ct->ct_ctrl1 = SHA_COMMAND1;
+ ct->ct_ctrl2 = SHA_COMMAND2 | SHA_TFM_DIGEST(SIZE_IN_WORDS(ctx->ds));
+}
+
+/* Update input data length of transform information and map it. */
+static int mtk_sha_info_map(struct mtk_cryp *cryp,
+ struct mtk_sha *sha, size_t len)
+{
+ struct mtk_sha_reqctx *ctx = ahash_request_ctx(sha->req);
+ struct mtk_sha_info *info = sha->info;
+ struct mtk_sha_ct *ct = &info->ct;
+
+ if (ctx->start)
+ ctx->start = false;
+ else
+ ct->tfm_ctrl0 &= ~SHA_TFM_START;
+
+ sha->ct_hdr = (sha->ct_hdr & ~SHA_DATA_LEN_MSK) | len;
+ ct->ct_ctrl0 = (ct->ct_ctrl0 & ~SHA_DATA_LEN_MSK) | len;
+
+ ctx->digcnt += len;
+
+ sha->ct_dma = dma_map_single(cryp->dev, info, sizeof(*info),
+ DMA_BIDIRECTIONAL);
+ if (unlikely(dma_mapping_error(cryp->dev, sha->ct_dma))) {
+ dev_err(cryp->dev, "dma %d bytes error\n", sizeof(*info));
+ return -EINVAL;
+ }
+ sha->tfm_dma = sha->ct_dma + sizeof(*ct);
+
+ return 0;
+}
+
+/*
+ * Because of hardware limitation, we must pre-calculate the inner
+ * and outer digest that need to be processed firstly by engine, then
+ * apply the result digest to the input message. These complex hashing
+ * procedures limits HMAC performance, so we use fallback SW encoding.
+ */
+static int mtk_sha_finish_hmac(struct ahash_request *req)
+{
+ struct mtk_sha_ctx *tctx = crypto_tfm_ctx(req->base.tfm);
+ struct mtk_sha_hmac_ctx *bctx = tctx->base;
+ struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
+
+ SHASH_DESC_ON_STACK(shash, bctx->shash);
+
+ shash->tfm = bctx->shash;
+ shash->flags = 0; /* not CRYPTO_TFM_REQ_MAY_SLEEP */
+
+ return crypto_shash_init(shash) ?:
+ crypto_shash_update(shash, bctx->opad, ctx->bs) ?:
+ crypto_shash_finup(shash, req->result, ctx->ds, req->result);
+}
+
+/* Initialize request context */
+static int mtk_sha_init(struct ahash_request *req)
+{
+ struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+ struct mtk_sha_ctx *tctx = crypto_ahash_ctx(tfm);
+ struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
+
+ ctx->flags = 0;
+ ctx->ds = crypto_ahash_digestsize(tfm);
+
+ switch (ctx->ds) {
+ case SHA1_DIGEST_SIZE:
+ ctx->flags |= SHA_FLAGS_SHA1;
+ ctx->bs = SHA1_BLOCK_SIZE;
+ break;
+ case SHA224_DIGEST_SIZE:
+ ctx->flags |= SHA_FLAGS_SHA224;
+ ctx->bs = SHA224_BLOCK_SIZE;
+ break;
+ case SHA256_DIGEST_SIZE:
+ ctx->flags |= SHA_FLAGS_SHA256;
+ ctx->bs = SHA256_BLOCK_SIZE;
+ break;
+ case SHA384_DIGEST_SIZE:
+ ctx->flags |= SHA_FLAGS_SHA384;
+ ctx->bs = SHA384_BLOCK_SIZE;
+ break;
+ case SHA512_DIGEST_SIZE:
+ ctx->flags |= SHA_FLAGS_SHA512;
+ ctx->bs = SHA512_BLOCK_SIZE;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ ctx->bufcnt = 0;
+ ctx->digcnt = 0;
+ ctx->buffer = tctx->buf;
+ ctx->start = true;
+
+ if (tctx->flags & SHA_FLAGS_HMAC) {
+ struct mtk_sha_hmac_ctx *bctx = tctx->base;
+
+ memcpy(ctx->buffer, bctx->ipad, ctx->bs);
+ ctx->bufcnt = ctx->bs;
+ ctx->flags |= SHA_FLAGS_HMAC;
+ }
+
+ return 0;
+}
+
+static int mtk_sha_xmit(struct mtk_cryp *cryp, struct mtk_sha *sha,
+ dma_addr_t addr, size_t len)
+{
+ struct mtk_ring *ring = cryp->ring[sha->id];
+ struct mtk_desc *cmd = ring->cmd_base + ring->pos;
+ struct mtk_desc *res = ring->res_base + ring->pos;
+ int err;
+
+ err = mtk_sha_info_map(cryp, sha, len);
+ if (err)
+ return err;
+
+ /* Fill command and result descriptors */
+ res->hdr = MTK_DESC_FIRST | MTK_DESC_LAST |
+ MTK_DESC_BUF_LEN(len);
+
+ res->buf = cryp->tmp_dma;
+
+ cmd->hdr = MTK_DESC_FIRST | MTK_DESC_LAST |
+ MTK_DESC_BUF_LEN(len) |
+ MTK_DESC_CT_LEN(sha->ct_size);
+
+ cmd->buf = addr;
+ cmd->ct = sha->ct_dma;
+ cmd->ct_hdr = sha->ct_hdr;
+ cmd->tfm = sha->tfm_dma;
+
+ if (++ring->pos == MTK_MAX_DESC_NUM)
+ ring->pos = 0;
+
+ /*
+ * make sure that all changes to the dma ring are done before we
+ * start engine.
+ */
+ wmb();
+ /* Start DMA transfer */
+ mtk_sha_write(cryp, RDR_PREP_COUNT(sha->id), MTK_DESC_CNT(1));
+ mtk_sha_write(cryp, CDR_PREP_COUNT(sha->id), MTK_DESC_CNT(1));
+
+ return -EINPROGRESS;
+}
+
+static int mtk_sha_xmit2(struct mtk_cryp *cryp, struct mtk_sha *sha,
+ struct mtk_sha_reqctx *ctx, size_t len1, size_t len2)
+{
+ struct mtk_ring *ring = cryp->ring[sha->id];
+ struct mtk_desc *cmd = ring->cmd_base + ring->pos;
+ struct mtk_desc *res = ring->res_base + ring->pos;
+ int err;
+
+ err = mtk_sha_info_map(cryp, sha, len1 + len2);
+ if (err)
+ return err;
+
+ /* Fill command and result descriptors */
+ res->hdr = MTK_DESC_BUF_LEN(len1) | MTK_DESC_FIRST;
+ res->buf = cryp->tmp_dma;
+
+ cmd->hdr = MTK_DESC_BUF_LEN(len1) | MTK_DESC_FIRST |
+ MTK_DESC_CT_LEN(sha->ct_size);
+ cmd->buf = sg_dma_address(ctx->sg);
+ cmd->ct = sha->ct_dma;
+ cmd->ct_hdr = sha->ct_hdr;
+ cmd->tfm = sha->tfm_dma;
+
+ if (++ring->pos == MTK_MAX_DESC_NUM)
+ ring->pos = 0;
+
+ cmd = ring->cmd_base + ring->pos;
+ res = ring->res_base + ring->pos;
+
+ res->hdr = MTK_DESC_BUF_LEN(len2) | MTK_DESC_LAST;
+ res->buf = cryp->tmp_dma;
+
+ cmd->hdr = MTK_DESC_BUF_LEN(len2) | MTK_DESC_LAST;
+ cmd->buf = ctx->dma_addr;
+
+ if (++ring->pos == MTK_MAX_DESC_NUM)
+ ring->pos = 0;
+
+ /*
+ * make sure that all changes to the dma ring are done before we
+ * start engine.
+ */
+ wmb();
+ /* Start DMA transfer */
+ mtk_sha_write(cryp, RDR_PREP_COUNT(sha->id), MTK_DESC_CNT(2));
+ mtk_sha_write(cryp, CDR_PREP_COUNT(sha->id), MTK_DESC_CNT(2));
+
+ return -EINPROGRESS;
+}
+
+static int mtk_sha_dma_map(struct mtk_cryp *cryp, struct mtk_sha *sha,
+ struct mtk_sha_reqctx *ctx, size_t count)
+{
+ ctx->dma_addr = dma_map_single(cryp->dev, ctx->buffer,
+ SHA_BUFFER_LEN, DMA_TO_DEVICE);
+ if (unlikely(dma_mapping_error(cryp->dev, ctx->dma_addr))) {
+ dev_err(cryp->dev, "dma map error\n");
+ return -EINVAL;
+ }
+
+ ctx->flags &= ~SHA_FLAGS_SG;
+
+ return mtk_sha_xmit(cryp, sha, ctx->dma_addr, count);
+}
+
+static int mtk_sha_update_slow(struct mtk_cryp *cryp, struct mtk_sha *sha)
+{
+ struct mtk_sha_reqctx *ctx = ahash_request_ctx(sha->req);
+ size_t count;
+ u32 final;
+
+ mtk_sha_append_sg(ctx);
+
+ final = (ctx->flags & SHA_FLAGS_FINUP) && !ctx->total;
+
+ dev_dbg(cryp->dev, "slow: bufcnt: %u\n", ctx->bufcnt);
+
+ if (final) {
+ sha->flags |= SHA_FLAGS_FINAL;
+ mtk_sha_fill_padding(ctx, 0);
+ }
+
+ if (final || (ctx->bufcnt == SHA_BUFFER_LEN && ctx->total)) {
+ count = ctx->bufcnt;
+ ctx->bufcnt = 0;
+
+ return mtk_sha_dma_map(cryp, sha, ctx, count);
+ }
+ return 0;
+}
+
+static int mtk_sha_update_start(struct mtk_cryp *cryp, struct mtk_sha *sha)
+{
+ struct mtk_sha_reqctx *ctx = ahash_request_ctx(sha->req);
+ u32 len, final, tail;
+ struct scatterlist *sg;
+
+ if (!ctx->total)
+ return 0;
+
+ if (ctx->bufcnt || ctx->offset)
+ return mtk_sha_update_slow(cryp, sha);
+
+ sg = ctx->sg;
+
+ if (!IS_ALIGNED(sg->offset, sizeof(u32)))
+ return mtk_sha_update_slow(cryp, sha);
+
+ if (!sg_is_last(sg) && !IS_ALIGNED(sg->length, ctx->bs))
+ /* size is not ctx->bs aligned */
+ return mtk_sha_update_slow(cryp, sha);
+
+ len = min(ctx->total, sg->length);
+
+ if (sg_is_last(sg)) {
+ if (!(ctx->flags & SHA_FLAGS_FINUP)) {
+ /* not last sg must be ctx->bs aligned */
+ tail = len & (ctx->bs - 1);
+ len -= tail;
+ }
+ }
+
+ ctx->total -= len;
+ ctx->offset = len; /* offset where to start slow */
+
+ final = (ctx->flags & SHA_FLAGS_FINUP) && !ctx->total;
+
+ /* Add padding */
+ if (final) {
+ size_t count;
+
+ tail = len & (ctx->bs - 1);
+ len -= tail;
+ ctx->total += tail;
+ ctx->offset = len; /* offset where to start slow */
+
+ sg = ctx->sg;
+ mtk_sha_append_sg(ctx);
+ mtk_sha_fill_padding(ctx, len);
+
+ ctx->dma_addr = dma_map_single(cryp->dev, ctx->buffer,
+ SHA_BUFFER_LEN, DMA_TO_DEVICE);
+ if (unlikely(dma_mapping_error(cryp->dev, ctx->dma_addr))) {
+ dev_err(cryp->dev, "dma map bytes error\n");
+ return -EINVAL;
+ }
+
+ sha->flags |= SHA_FLAGS_FINAL;
+ count = ctx->bufcnt;
+ ctx->bufcnt = 0;
+
+ if (len == 0) {
+ ctx->flags &= ~SHA_FLAGS_SG;
+ return mtk_sha_xmit(cryp, sha, ctx->dma_addr, count);
+
+ } else {
+ ctx->sg = sg;
+ if (!dma_map_sg(cryp->dev, ctx->sg, 1, DMA_TO_DEVICE)) {
+ dev_err(cryp->dev, "dma_map_sg error\n");
+ return -EINVAL;
+ }
+
+ ctx->flags |= SHA_FLAGS_SG;
+ return mtk_sha_xmit2(cryp, sha, ctx, len, count);
+ }
+ }
+
+ if (!dma_map_sg(cryp->dev, ctx->sg, 1, DMA_TO_DEVICE)) {
+ dev_err(cryp->dev, "dma_map_sg error\n");
+ return -EINVAL;
+ }
+
+ ctx->flags |= SHA_FLAGS_SG;
+
+ return mtk_sha_xmit(cryp, sha, sg_dma_address(ctx->sg), len);
+}
+
+static int mtk_sha_final_req(struct mtk_cryp *cryp, struct mtk_sha *sha)
+{
+ struct ahash_request *req = sha->req;
+ struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
+ size_t count;
+
+ mtk_sha_fill_padding(ctx, 0);
+
+ sha->flags |= SHA_FLAGS_FINAL;
+ count = ctx->bufcnt;
+ ctx->bufcnt = 0;
+
+ return mtk_sha_dma_map(cryp, sha, ctx, count);
+}
+
+/* copy ready hash (+ finalize hmac) */
+static int mtk_sha_finish(struct ahash_request *req)
+{
+ struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
+ u8 *digest = ctx->info.tfm.digest;
+
+ memcpy(req->result, digest, ctx->ds);
+
+ if (ctx->flags & SHA_FLAGS_HMAC)
+ return mtk_sha_finish_hmac(req);
+
+ return 0;
+}
+
+static void mtk_sha_finish_req(struct mtk_cryp *cryp,
+ struct mtk_sha *sha, int err)
+{
+ if (likely(!err && (SHA_FLAGS_FINAL & sha->flags)))
+ err = mtk_sha_finish(sha->req);
+
+ sha->flags &= ~(SHA_FLAGS_BUSY | SHA_FLAGS_FINAL);
+
+ sha->req->base.complete(&sha->req->base, err);
+
+ /* handle new request */
+ mtk_sha_handle_queue(cryp, sha->id - RING2, NULL);
+}
+
+static int mtk_sha_handle_queue(struct mtk_cryp *cryp, u8 id,
+ struct ahash_request *req)
+{
+ struct mtk_sha *sha = cryp->sha[id];
+ struct crypto_async_request *async_req, *backlog;
+ struct mtk_sha_reqctx *ctx;
+ unsigned long flags;
+ int err = 0, ret = 0;
+
+ spin_lock_irqsave(&sha->lock, flags);
+ if (req)
+ ret = ahash_enqueue_request(&sha->queue, req);
+
+ if (SHA_FLAGS_BUSY & sha->flags) {
+ spin_unlock_irqrestore(&sha->lock, flags);
+ return ret;
+ }
+
+ backlog = crypto_get_backlog(&sha->queue);
+ async_req = crypto_dequeue_request(&sha->queue);
+ if (async_req)
+ sha->flags |= SHA_FLAGS_BUSY;
+ spin_unlock_irqrestore(&sha->lock, flags);
+
+ if (!async_req)
+ return ret;
+
+ if (backlog)
+ backlog->complete(backlog, -EINPROGRESS);
+
+ req = ahash_request_cast(async_req);
+ ctx = ahash_request_ctx(req);
+
+ sha->req = req;
+ sha->info = &ctx->info;
+
+ mtk_sha_info_init(sha, ctx);
+
+ if (ctx->op == SHA_OP_UPDATE) {
+ err = mtk_sha_update_start(cryp, sha);
+ if (err != -EINPROGRESS && (ctx->flags & SHA_FLAGS_FINUP))
+ /* no final() after finup() */
+ err = mtk_sha_final_req(cryp, sha);
+ } else if (ctx->op == SHA_OP_FINAL) {
+ err = mtk_sha_final_req(cryp, sha);
+ }
+
+ if (unlikely(err != -EINPROGRESS))
+ /* task will not finish it, so do it here */
+ mtk_sha_finish_req(cryp, sha, err);
+
+ return ret;
+}
+
+static int mtk_sha_enqueue(struct ahash_request *req, u32 op)
+{
+ struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
+ struct mtk_sha_ctx *tctx = crypto_tfm_ctx(req->base.tfm);
+
+ ctx->op = op;
+
+ return mtk_sha_handle_queue(tctx->cryp, tctx->id, req);
+}
+
+static void mtk_sha_unmap(struct mtk_cryp *cryp, struct mtk_sha *sha)
+{
+ struct mtk_sha_reqctx *ctx = ahash_request_ctx(sha->req);
+
+ dma_unmap_single(cryp->dev, sha->ct_dma,
+ sizeof(struct mtk_sha_info), DMA_BIDIRECTIONAL);
+
+ if (ctx->flags & SHA_FLAGS_SG) {
+ dma_unmap_sg(cryp->dev, ctx->sg, 1, DMA_TO_DEVICE);
+ if (ctx->sg->length == ctx->offset) {
+ ctx->sg = sg_next(ctx->sg);
+ if (ctx->sg)
+ ctx->offset = 0;
+ }
+ if (ctx->flags & SHA_FLAGS_PAD) {
+ dma_unmap_single(cryp->dev, ctx->dma_addr,
+ SHA_BUFFER_LEN, DMA_TO_DEVICE);
+ }
+ } else
+ dma_unmap_single(cryp->dev, ctx->dma_addr,
+ SHA_BUFFER_LEN, DMA_TO_DEVICE);
+}
+
+static void mtk_sha_complete(struct mtk_cryp *cryp, struct mtk_sha *sha)
+{
+ int err = 0;
+
+ err = mtk_sha_update_start(cryp, sha);
+ if (err != -EINPROGRESS)
+ mtk_sha_finish_req(cryp, sha, err);
+}
+
+static int mtk_sha_update(struct ahash_request *req)
+{
+ struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
+
+ ctx->total = req->nbytes;
+ ctx->sg = req->src;
+ ctx->offset = 0;
+
+ if ((ctx->bufcnt + ctx->total < SHA_BUFFER_LEN) &&
+ !(ctx->flags & SHA_FLAGS_FINUP))
+ return mtk_sha_append_sg(ctx);
+
+ return mtk_sha_enqueue(req, SHA_OP_UPDATE);
+}
+
+static int mtk_sha_final(struct ahash_request *req)
+{
+ struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
+
+ ctx->flags |= SHA_FLAGS_FINUP;
+
+ if (ctx->flags & SHA_FLAGS_PAD)
+ return mtk_sha_finish(req);
+
+ return mtk_sha_enqueue(req, SHA_OP_FINAL);
+}
+
+static int mtk_sha_finup(struct ahash_request *req)
+{
+ struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
+ int err1, err2;
+
+ ctx->flags |= SHA_FLAGS_FINUP;
+
+ err1 = mtk_sha_update(req);
+ if (err1 == -EINPROGRESS || err1 == -EBUSY)
+ return err1;
+ /*
+ * final() has to be always called to cleanup resources
+ * even if update() failed
+ */
+ err2 = mtk_sha_final(req);
+
+ return err1 ?: err2;
+}
+
+static int mtk_sha_digest(struct ahash_request *req)
+{
+ return mtk_sha_init(req) ?: mtk_sha_finup(req);
+}
+
+static int mtk_sha_setkey(struct crypto_ahash *tfm,
+ const unsigned char *key, u32 keylen)
+{
+ struct mtk_sha_ctx *tctx = crypto_ahash_ctx(tfm);
+ struct mtk_sha_hmac_ctx *bctx = tctx->base;
+ size_t bs = crypto_shash_blocksize(bctx->shash);
+ size_t ds = crypto_shash_digestsize(bctx->shash);
+ int err, i;
+
+ SHASH_DESC_ON_STACK(shash, bctx->shash);
+
+ shash->tfm = bctx->shash;
+ shash->flags = crypto_shash_get_flags(bctx->shash) &
+ CRYPTO_TFM_REQ_MAY_SLEEP;
+
+ if (keylen > bs) {
+ err = crypto_shash_digest(shash, key, keylen, bctx->ipad);
+ if (err)
+ return err;
+ keylen = ds;
+ } else {
+ memcpy(bctx->ipad, key, keylen);
+ }
+
+ memset(bctx->ipad + keylen, 0, bs - keylen);
+ memcpy(bctx->opad, bctx->ipad, bs);
+
+ for (i = 0; i < bs; i++) {
+ bctx->ipad[i] ^= 0x36;
+ bctx->opad[i] ^= 0x5c;
+ }
+
+ return err;
+}
+
+static int mtk_sha_export(struct ahash_request *req, void *out)
+{
+ const struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
+
+ memcpy(out, ctx, sizeof(*ctx));
+ return 0;
+}
+
+static int mtk_sha_import(struct ahash_request *req, const void *in)
+{
+ struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
+
+ memcpy(ctx, in, sizeof(*ctx));
+ return 0;
+}
+
+static int mtk_sha_cra_init_alg(struct crypto_tfm *tfm,
+ const char *alg_base)
+{
+ struct mtk_sha_ctx *tctx = crypto_tfm_ctx(tfm);
+ struct mtk_cryp *cryp = NULL;
+
+ cryp = mtk_sha_find_dev(tctx);
+ if (!cryp)
+ return -ENODEV;
+
+ crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+ sizeof(struct mtk_sha_reqctx));
+
+ if (alg_base) {
+ struct mtk_sha_hmac_ctx *bctx = tctx->base;
+
+ tctx->flags |= SHA_FLAGS_HMAC;
+ bctx->shash = crypto_alloc_shash(alg_base, 0,
+ CRYPTO_ALG_NEED_FALLBACK);
+ if (IS_ERR(bctx->shash)) {
+ pr_err("base driver %s could not be loaded.\n",
+ alg_base);
+
+ return PTR_ERR(bctx->shash);
+ }
+ }
+ return 0;
+}
+
+static int mtk_sha_cra_init(struct crypto_tfm *tfm)
+{
+ return mtk_sha_cra_init_alg(tfm, NULL);
+}
+
+static int mtk_sha_cra_sha1_init(struct crypto_tfm *tfm)
+{
+ return mtk_sha_cra_init_alg(tfm, "sha1");
+}
+
+static int mtk_sha_cra_sha224_init(struct crypto_tfm *tfm)
+{
+ return mtk_sha_cra_init_alg(tfm, "sha224");
+}
+
+static int mtk_sha_cra_sha256_init(struct crypto_tfm *tfm)
+{
+ return mtk_sha_cra_init_alg(tfm, "sha256");
+}
+
+static int mtk_sha_cra_sha384_init(struct crypto_tfm *tfm)
+{
+ return mtk_sha_cra_init_alg(tfm, "sha384");
+}
+
+static int mtk_sha_cra_sha512_init(struct crypto_tfm *tfm)
+{
+ return mtk_sha_cra_init_alg(tfm, "sha512");
+}
+
+static void mtk_sha_cra_exit(struct crypto_tfm *tfm)
+{
+ struct mtk_sha_ctx *tctx = crypto_tfm_ctx(tfm);
+
+ if (tctx->flags & SHA_FLAGS_HMAC) {
+ struct mtk_sha_hmac_ctx *bctx = tctx->base;
+
+ crypto_free_shash(bctx->shash);
+ }
+}
+
+static struct ahash_alg algs_sha1_sha224_sha256[] = {
+{
+ .init = mtk_sha_init,
+ .update = mtk_sha_update,
+ .final = mtk_sha_final,
+ .finup = mtk_sha_finup,
+ .digest = mtk_sha_digest,
+ .export = mtk_sha_export,
+ .import = mtk_sha_import,
+ .halg.digestsize = SHA1_DIGEST_SIZE,
+ .halg.statesize = sizeof(struct mtk_sha_reqctx),
+ .halg.base = {
+ .cra_name = "sha1",
+ .cra_driver_name = "mtk-sha1",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_ASYNC,
+ .cra_blocksize = SHA1_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct mtk_sha_ctx),
+ .cra_alignmask = SHA_ALIGN_MSK,
+ .cra_module = THIS_MODULE,
+ .cra_init = mtk_sha_cra_init,
+ .cra_exit = mtk_sha_cra_exit,
+ }
+},
+{
+ .init = mtk_sha_init,
+ .update = mtk_sha_update,
+ .final = mtk_sha_final,
+ .finup = mtk_sha_finup,
+ .digest = mtk_sha_digest,
+ .export = mtk_sha_export,
+ .import = mtk_sha_import,
+ .halg.digestsize = SHA224_DIGEST_SIZE,
+ .halg.statesize = sizeof(struct mtk_sha_reqctx),
+ .halg.base = {
+ .cra_name = "sha224",
+ .cra_driver_name = "mtk-sha224",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_ASYNC,
+ .cra_blocksize = SHA224_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct mtk_sha_ctx),
+ .cra_alignmask = SHA_ALIGN_MSK,
+ .cra_module = THIS_MODULE,
+ .cra_init = mtk_sha_cra_init,
+ .cra_exit = mtk_sha_cra_exit,
+ }
+},
+{
+ .init = mtk_sha_init,
+ .update = mtk_sha_update,
+ .final = mtk_sha_final,
+ .finup = mtk_sha_finup,
+ .digest = mtk_sha_digest,
+ .export = mtk_sha_export,
+ .import = mtk_sha_import,
+ .halg.digestsize = SHA256_DIGEST_SIZE,
+ .halg.statesize = sizeof(struct mtk_sha_reqctx),
+ .halg.base = {
+ .cra_name = "sha256",
+ .cra_driver_name = "mtk-sha256",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_ASYNC,
+ .cra_blocksize = SHA256_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct mtk_sha_ctx),
+ .cra_alignmask = SHA_ALIGN_MSK,
+ .cra_module = THIS_MODULE,
+ .cra_init = mtk_sha_cra_init,
+ .cra_exit = mtk_sha_cra_exit,
+ }
+},
+{
+ .init = mtk_sha_init,
+ .update = mtk_sha_update,
+ .final = mtk_sha_final,
+ .finup = mtk_sha_finup,
+ .digest = mtk_sha_digest,
+ .export = mtk_sha_export,
+ .import = mtk_sha_import,
+ .setkey = mtk_sha_setkey,
+ .halg.digestsize = SHA1_DIGEST_SIZE,
+ .halg.statesize = sizeof(struct mtk_sha_reqctx),
+ .halg.base = {
+ .cra_name = "hmac(sha1)",
+ .cra_driver_name = "mtk-hmac-sha1",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_ASYNC |
+ CRYPTO_ALG_NEED_FALLBACK,
+ .cra_blocksize = SHA1_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct mtk_sha_ctx) +
+ sizeof(struct mtk_sha_hmac_ctx),
+ .cra_alignmask = SHA_ALIGN_MSK,
+ .cra_module = THIS_MODULE,
+ .cra_init = mtk_sha_cra_sha1_init,
+ .cra_exit = mtk_sha_cra_exit,
+ }
+},
+{
+ .init = mtk_sha_init,
+ .update = mtk_sha_update,
+ .final = mtk_sha_final,
+ .finup = mtk_sha_finup,
+ .digest = mtk_sha_digest,
+ .export = mtk_sha_export,
+ .import = mtk_sha_import,
+ .setkey = mtk_sha_setkey,
+ .halg.digestsize = SHA224_DIGEST_SIZE,
+ .halg.statesize = sizeof(struct mtk_sha_reqctx),
+ .halg.base = {
+ .cra_name = "hmac(sha224)",
+ .cra_driver_name = "mtk-hmac-sha224",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_ASYNC |
+ CRYPTO_ALG_NEED_FALLBACK,
+ .cra_blocksize = SHA224_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct mtk_sha_ctx) +
+ sizeof(struct mtk_sha_hmac_ctx),
+ .cra_alignmask = SHA_ALIGN_MSK,
+ .cra_module = THIS_MODULE,
+ .cra_init = mtk_sha_cra_sha224_init,
+ .cra_exit = mtk_sha_cra_exit,
+ }
+},
+{
+ .init = mtk_sha_init,
+ .update = mtk_sha_update,
+ .final = mtk_sha_final,
+ .finup = mtk_sha_finup,
+ .digest = mtk_sha_digest,
+ .export = mtk_sha_export,
+ .import = mtk_sha_import,
+ .setkey = mtk_sha_setkey,
+ .halg.digestsize = SHA256_DIGEST_SIZE,
+ .halg.statesize = sizeof(struct mtk_sha_reqctx),
+ .halg.base = {
+ .cra_name = "hmac(sha256)",
+ .cra_driver_name = "mtk-hmac-sha256",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_ASYNC |
+ CRYPTO_ALG_NEED_FALLBACK,
+ .cra_blocksize = SHA256_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct mtk_sha_ctx) +
+ sizeof(struct mtk_sha_hmac_ctx),
+ .cra_alignmask = SHA_ALIGN_MSK,
+ .cra_module = THIS_MODULE,
+ .cra_init = mtk_sha_cra_sha256_init,
+ .cra_exit = mtk_sha_cra_exit,
+ }
+},
+};
+
+static struct ahash_alg algs_sha384_sha512[] = {
+{
+ .init = mtk_sha_init,
+ .update = mtk_sha_update,
+ .final = mtk_sha_final,
+ .finup = mtk_sha_finup,
+ .digest = mtk_sha_digest,
+ .export = mtk_sha_export,
+ .import = mtk_sha_import,
+ .halg.digestsize = SHA384_DIGEST_SIZE,
+ .halg.statesize = sizeof(struct mtk_sha_reqctx),
+ .halg.base = {
+ .cra_name = "sha384",
+ .cra_driver_name = "mtk-sha384",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_ASYNC,
+ .cra_blocksize = SHA384_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct mtk_sha_ctx),
+ .cra_alignmask = SHA_ALIGN_MSK,
+ .cra_module = THIS_MODULE,
+ .cra_init = mtk_sha_cra_init,
+ .cra_exit = mtk_sha_cra_exit,
+ }
+},
+{
+ .init = mtk_sha_init,
+ .update = mtk_sha_update,
+ .final = mtk_sha_final,
+ .finup = mtk_sha_finup,
+ .digest = mtk_sha_digest,
+ .export = mtk_sha_export,
+ .import = mtk_sha_import,
+ .halg.digestsize = SHA512_DIGEST_SIZE,
+ .halg.statesize = sizeof(struct mtk_sha_reqctx),
+ .halg.base = {
+ .cra_name = "sha512",
+ .cra_driver_name = "mtk-sha512",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_ASYNC,
+ .cra_blocksize = SHA512_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct mtk_sha_ctx),
+ .cra_alignmask = SHA_ALIGN_MSK,
+ .cra_module = THIS_MODULE,
+ .cra_init = mtk_sha_cra_init,
+ .cra_exit = mtk_sha_cra_exit,
+ }
+},
+{
+ .init = mtk_sha_init,
+ .update = mtk_sha_update,
+ .final = mtk_sha_final,
+ .finup = mtk_sha_finup,
+ .digest = mtk_sha_digest,
+ .export = mtk_sha_export,
+ .import = mtk_sha_import,
+ .setkey = mtk_sha_setkey,
+ .halg.digestsize = SHA384_DIGEST_SIZE,
+ .halg.statesize = sizeof(struct mtk_sha_reqctx),
+ .halg.base = {
+ .cra_name = "hmac(sha384)",
+ .cra_driver_name = "mtk-hmac-sha384",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_ASYNC |
+ CRYPTO_ALG_NEED_FALLBACK,
+ .cra_blocksize = SHA384_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct mtk_sha_ctx) +
+ sizeof(struct mtk_sha_hmac_ctx),
+ .cra_alignmask = SHA_ALIGN_MSK,
+ .cra_module = THIS_MODULE,
+ .cra_init = mtk_sha_cra_sha384_init,
+ .cra_exit = mtk_sha_cra_exit,
+ }
+},
+{
+ .init = mtk_sha_init,
+ .update = mtk_sha_update,
+ .final = mtk_sha_final,
+ .finup = mtk_sha_finup,
+ .digest = mtk_sha_digest,
+ .export = mtk_sha_export,
+ .import = mtk_sha_import,
+ .setkey = mtk_sha_setkey,
+ .halg.digestsize = SHA512_DIGEST_SIZE,
+ .halg.statesize = sizeof(struct mtk_sha_reqctx),
+ .halg.base = {
+ .cra_name = "hmac(sha512)",
+ .cra_driver_name = "mtk-hmac-sha512",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_ASYNC |
+ CRYPTO_ALG_NEED_FALLBACK,
+ .cra_blocksize = SHA512_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct mtk_sha_ctx) +
+ sizeof(struct mtk_sha_hmac_ctx),
+ .cra_alignmask = SHA_ALIGN_MSK,
+ .cra_module = THIS_MODULE,
+ .cra_init = mtk_sha_cra_sha512_init,
+ .cra_exit = mtk_sha_cra_exit,
+ }
+},
+};
+
+static void mtk_sha_task0(unsigned long data)
+{
+ struct mtk_cryp *cryp = (struct mtk_cryp *)data;
+ struct mtk_sha *sha = cryp->sha[0];
+
+ mtk_sha_unmap(cryp, sha);
+ mtk_sha_complete(cryp, sha);
+}
+
+static void mtk_sha_task1(unsigned long data)
+{
+ struct mtk_cryp *cryp = (struct mtk_cryp *)data;
+ struct mtk_sha *sha = cryp->sha[1];
+
+ mtk_sha_unmap(cryp, sha);
+ mtk_sha_complete(cryp, sha);
+}
+
+static irqreturn_t mtk_sha_ring2_irq(int irq, void *dev_id)
+{
+ struct mtk_cryp *cryp = (struct mtk_cryp *)dev_id;
+ struct mtk_sha *sha = cryp->sha[0];
+ u32 val = mtk_sha_read(cryp, RDR_STAT(RING2));
+
+ mtk_sha_write(cryp, RDR_STAT(RING2), val);
+
+ if (likely((SHA_FLAGS_BUSY & sha->flags))) {
+ mtk_sha_write(cryp, RDR_PROC_COUNT(RING2), MTK_DESC_CNT_CLR);
+ mtk_sha_write(cryp, RDR_THRESH(RING2), MTK_RDR_THRESH_DEF);
+
+ tasklet_schedule(&sha->task);
+ } else {
+ dev_warn(cryp->dev, "AES interrupt when no active requests.\n");
+ }
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t mtk_sha_ring3_irq(int irq, void *dev_id)
+{
+ struct mtk_cryp *cryp = (struct mtk_cryp *)dev_id;
+ struct mtk_sha *sha = cryp->sha[1];
+ u32 val = mtk_sha_read(cryp, RDR_STAT(RING3));
+
+ mtk_sha_write(cryp, RDR_STAT(RING3), val);
+
+ if (likely((SHA_FLAGS_BUSY & sha->flags))) {
+ mtk_sha_write(cryp, RDR_PROC_COUNT(RING3), MTK_DESC_CNT_CLR);
+ mtk_sha_write(cryp, RDR_THRESH(RING3), MTK_RDR_THRESH_DEF);
+
+ tasklet_schedule(&sha->task);
+ } else {
+ dev_warn(cryp->dev, "AES interrupt when no active requests.\n");
+ }
+ return IRQ_HANDLED;
+}
+
+/*
+ * The purpose of two SHA records is used to get extra performance.
+ * It is similar to mtk_aes_record_init().
+ */
+static int mtk_sha_record_init(struct mtk_cryp *cryp)
+{
+ struct mtk_sha **sha = cryp->sha;
+ int i, err = -ENOMEM;
+
+ for (i = 0; i < RECORD_NUM; i++) {
+ sha[i] = kzalloc(sizeof(**sha), GFP_KERNEL);
+ if (!sha[i])
+ goto err_cleanup;
+
+ sha[i]->id = i + RING2;
+
+ spin_lock_init(&sha[i]->lock);
+ crypto_init_queue(&sha[i]->queue, SHA_QUEUE_SIZE);
+ }
+
+ tasklet_init(&sha[0]->task, mtk_sha_task0, (unsigned long)cryp);
+ tasklet_init(&sha[1]->task, mtk_sha_task1, (unsigned long)cryp);
+
+ cryp->rec = 1;
+
+ return 0;
+
+err_cleanup:
+ for (; i--; )
+ kfree(sha[i]);
+ return err;
+}
+
+static void mtk_sha_record_free(struct mtk_cryp *cryp)
+{
+ int i;
+
+ for (i = 0; i < RECORD_NUM; i++) {
+ tasklet_kill(&cryp->sha[i]->task);
+ kfree(cryp->sha[i]);
+ }
+}
+
+static void mtk_sha_unregister_algs(void)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(algs_sha1_sha224_sha256); i++)
+ crypto_unregister_ahash(&algs_sha1_sha224_sha256[i]);
+
+ for (i = 0; i < ARRAY_SIZE(algs_sha384_sha512); i++)
+ crypto_unregister_ahash(&algs_sha384_sha512[i]);
+}
+
+static int mtk_sha_register_algs(void)
+{
+ int err, i;
+
+ for (i = 0; i < ARRAY_SIZE(algs_sha1_sha224_sha256); i++) {
+ err = crypto_register_ahash(&algs_sha1_sha224_sha256[i]);
+ if (err)
+ goto err_sha_224_256_algs;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(algs_sha384_sha512); i++) {
+ err = crypto_register_ahash(&algs_sha384_sha512[i]);
+ if (err)
+ goto err_sha_384_512_algs;
+ }
+
+ return 0;
+
+err_sha_384_512_algs:
+ for (; i--; )
+ crypto_unregister_ahash(&algs_sha384_sha512[i]);
+ i = ARRAY_SIZE(algs_sha1_sha224_sha256);
+err_sha_224_256_algs:
+ for (; i--; )
+ crypto_unregister_ahash(&algs_sha1_sha224_sha256[i]);
+
+ return err;
+}
+
+int mtk_hash_alg_register(struct mtk_cryp *cryp)
+{
+ int err;
+
+ INIT_LIST_HEAD(&cryp->sha_list);
+
+ /* Initialize two hash records */
+ err = mtk_sha_record_init(cryp);
+ if (err)
+ goto err_record;
+
+ /* Ring2 irq is use by SHA record0 */
+ err = devm_request_irq(cryp->dev, cryp->irq[RING2],
+ mtk_sha_ring2_irq, IRQF_TRIGGER_LOW,
+ "mtk-sha", cryp);
+ if (err) {
+ dev_err(cryp->dev, "unable to request sha irq0.\n");
+ goto err_res;
+ }
+
+ /* Ring3 irq is use by SHA record1 */
+ err = devm_request_irq(cryp->dev, cryp->irq[RING3],
+ mtk_sha_ring3_irq, IRQF_TRIGGER_LOW,
+ "mtk-sha", cryp);
+ if (err) {
+ dev_err(cryp->dev, "unable to request sha irq1.\n");
+ goto err_res;
+ }
+
+ /* enable ring2 and ring3 interrupt for hash */
+ mtk_sha_write(cryp, AIC_ENABLE_SET(RING2), MTK_IRQ_RDR2);
+ mtk_sha_write(cryp, AIC_ENABLE_SET(RING3), MTK_IRQ_RDR3);
+
+ cryp->tmp = dma_alloc_coherent(cryp->dev, SHA_TMP_STATE_SIZE,
+ &cryp->tmp_dma, GFP_KERNEL);
+ if (!cryp->tmp) {
+ dev_err(cryp->dev, "unable to allocate tmp buffer.\n");
+ err = -EINVAL;
+ goto err_res;
+ }
+
+ spin_lock(&mtk_sha.lock);
+ list_add_tail(&cryp->sha_list, &mtk_sha.dev_list);
+ spin_unlock(&mtk_sha.lock);
+
+ err = mtk_sha_register_algs();
+ if (err)
+ goto err_algs;
+
+ return 0;
+
+err_algs:
+ spin_lock(&mtk_sha.lock);
+ list_del(&cryp->sha_list);
+ spin_unlock(&mtk_sha.lock);
+ dma_free_coherent(cryp->dev, SHA_TMP_STATE_SIZE,
+ cryp->tmp, cryp->tmp_dma);
+err_res:
+ mtk_sha_record_free(cryp);
+err_record:
+
+ dev_err(cryp->dev, "mtk-sha initialization failed.\n");
+ return err;
+}
+
+void mtk_hash_alg_release(struct mtk_cryp *cryp)
+{
+ spin_lock(&mtk_sha.lock);
+ list_del(&cryp->sha_list);
+ spin_unlock(&mtk_sha.lock);
+
+ mtk_sha_unregister_algs();
+ dma_free_coherent(cryp->dev, SHA_TMP_STATE_SIZE,
+ cryp->tmp, cryp->tmp_dma);
+ mtk_sha_record_free(cryp);
+}
--
1.9.1
^ permalink raw reply related
* [PATCH v1 0/2] Add MediaTek crypto acclelrator driver
From: Ryder Lee @ 2016-12-05 7:01 UTC (permalink / raw)
To: linux-arm-kernel
Hello,
This adds support for the MediaTek hardware accelerator on
mt7623 SoC.
This driver currently implement:
- SHA1 and SHA2 family(HMAC) hash alogrithms.
- AES block cipher in CBC/ECB mode with 128/196/256 bits keys.
Changes since v1:
- remove EXPORT_SYMBOL
- remove unused PRNG setting
- sort headers in alphabetical order
- add a definition for IRQ unmber
- replace ambiguous definition
- add more annotation and function comment
- add COMPILE_TEST in Kconfig
Ryder Lee (2):
Add crypto driver support for some MediaTek chips
crypto: mediatek - add DT bindings documentation
.../devicetree/bindings/crypto/mediatek-crypto.txt | 32 +
drivers/crypto/Kconfig | 17 +
drivers/crypto/Makefile | 1 +
drivers/crypto/mediatek/Makefile | 2 +
drivers/crypto/mediatek/mtk-aes.c | 763 +++++++++++
drivers/crypto/mediatek/mtk-platform.c | 580 ++++++++
drivers/crypto/mediatek/mtk-platform.h | 235 ++++
drivers/crypto/mediatek/mtk-regs.h | 194 +++
drivers/crypto/mediatek/mtk-sha.c | 1423 ++++++++++++++++++++
9 files changed, 3247 insertions(+)
create mode 100644 Documentation/devicetree/bindings/crypto/mediatek-crypto.txt
create mode 100644 drivers/crypto/mediatek/Makefile
create mode 100644 drivers/crypto/mediatek/mtk-aes.c
create mode 100644 drivers/crypto/mediatek/mtk-platform.c
create mode 100644 drivers/crypto/mediatek/mtk-platform.h
create mode 100644 drivers/crypto/mediatek/mtk-regs.h
create mode 100644 drivers/crypto/mediatek/mtk-sha.c
--
1.9.1
^ permalink raw reply
* [PATCH v3 3/7] PWM: add pwm-stm32 DT bindings
From: Thierry Reding @ 2016-12-05 6:53 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <1480673842-20804-4-git-send-email-benjamin.gaignard@st.com>
On Fri, Dec 02, 2016 at 11:17:18AM +0100, Benjamin Gaignard wrote:
> Define bindings for pwm-stm32
>
> version 2:
> - use parameters instead of compatible of handle the hardware configuration
>
> Signed-off-by: Benjamin Gaignard <benjamin.gaignard@st.com>
> ---
> .../devicetree/bindings/pwm/pwm-stm32.txt | 38 ++++++++++++++++++++++
> 1 file changed, 38 insertions(+)
> create mode 100644 Documentation/devicetree/bindings/pwm/pwm-stm32.txt
>
> diff --git a/Documentation/devicetree/bindings/pwm/pwm-stm32.txt b/Documentation/devicetree/bindings/pwm/pwm-stm32.txt
> new file mode 100644
> index 0000000..575b9fb
> --- /dev/null
> +++ b/Documentation/devicetree/bindings/pwm/pwm-stm32.txt
> @@ -0,0 +1,38 @@
> +STMicroelectronics PWM driver bindings for STM32
Technically this bindings describe devices, so "driver binding" is a
somewhat odd wording. Perhaps:
STMicroelectronics STM32 General Purpose Timer PWM bindings
?
> +
> +Must be a sub-node of STM32 general purpose timer driver
> +Parent node properties are describe in ../mfd/stm32-general-purpose-timer.txt
Again, "driver parent node" is odd. Perhaps:
Must be a sub-node of an STM32 General Purpose Timer device tree
node. See ../mfd/stm32-general-purpose-timer.txt for details about
the parent node.
?
> +Required parameters:
> +- compatible: Must be "st,stm32-pwm"
> +- pinctrl-names: Set to "default".
> +- pinctrl-0: List of phandles pointing to pin configuration nodes
> + for PWM module.
> + For Pinctrl properties, please refer to [1].
Your indentation and capitalization are inconsistent. Also, please refer
to the pinctrl bindings by relative path and inline, rather than as a
footnote reference.
> +
> +Optional parameters:
> +- st,breakinput: Set if the hardware have break input capabilities
> +- st,breakinput-polarity: Set break input polarity. Default is 0
> + The value define the active polarity:
> + - 0 (active LOW)
> + - 1 (active HIGH)
Could we fold these into a single property? If st,breakinput-polarity is
not present it could simply mean that there is no break input, and if it
is present you don't have to rely on a default.
> +- st,pwm-num-chan: Number of available PWM channels. Default is 0.
The pwm- prefix is rather redundant since the node is already named pwm.
Why not simply st,channels? Or simply channels, since it's not really
anything specific to this hardware.
Come to think of it, might be worth having a discussion with our DT
gurus about what their stance is on using the # as prefix for numbers
(such as in #address-cells or #size-cells). This could be #channels to
mark it more explicitly as representing a count.
> +- st,32bits-counter: Set if the hardware have a 32 bits counter
> +- st,complementary: Set if the hardware have complementary output channels
"hardware has" and also maybe mention explicitly that this is a boolean
property. Otherwise people might be left wondering what it should be set
to. Or maybe word this differently to imply that it's boolean:
- st,32bits-counter: if present, the hardware has a 32 bit counter
- st,complementary: if present, the hardware has a complementary
output channel
Thierry
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 801 bytes
Desc: not available
URL: <http://lists.infradead.org/pipermail/linux-arm-kernel/attachments/20161205/23d337b3/attachment.sig>
^ permalink raw reply
* [PATCH v4] ARM: davinci: da8xx: Fix sleeping function called from invalid context
From: Sekhar Nori @ 2016-12-05 6:32 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <907a3c22-534f-80ce-daff-be84dd5e5cf8@lechnology.com>
Hi David,
On Monday 05 December 2016 09:14 AM, David Lechner wrote:
> I have just tried this patch with a bunch of kernel hacking options
> enabled. I am getting the message show at the end of this email. We
> still have the problem of nested spin locks due to nested calls to
> clk_enable(). So, really, we need to use __clk_enable() and
> __clk_disable() from arch/arm/mach-davinci/clock.c in
> usb20_phy_clk_enable() above.
Good catch. I noticed that common clock framework uses a more elaborate
mechanism to allow nested clock API calls (see clk_prepare_lock()), but
we don't (yet) have that issue in mach-davinci since the recursive calls
are still in mach-davinci and dont need the exported API to be
recursively callable.
> Applying the following patch on top of your patch fixed the recursive
> lock message.
The patch looks okay to me, except couple of minor adjustments.
>
> ---
>
> diff --git a/arch/arm/mach-davinci/clock.c b/arch/arm/mach-davinci/clock.c
> index df42c93..4fba579 100644
> --- a/arch/arm/mach-davinci/clock.c
> +++ b/arch/arm/mach-davinci/clock.c
> @@ -31,7 +31,7 @@ static LIST_HEAD(clocks);
> static DEFINE_MUTEX(clocks_mutex);
> static DEFINE_SPINLOCK(clockfw_lock);
>
> -static void __clk_enable(struct clk *clk)
> +void __clk_enable(struct clk *clk)
Now that this function is going to be used outside of this file, lets
drop the __ naming convention and call this davinci_clk_enable() in line
with how other davinci-local clock APIs are named. Same thing for the
disable counterpart.
Also, the making these function non-static should be a patch of its own.
Thanks,
Sekhar
^ permalink raw reply
* [PATCH v3] mach-omap2: fixing wrong strcat for Non-NULL terminated string
From: Maninder Singh @ 2016-12-05 5:27 UTC (permalink / raw)
To: linux-arm-kernel
Issue caught with static analysis tool:
"Dangerous usage of 'name' (strncpy doesn't always 0-terminate it)"
Use strlcpy _includes_ the NUL terminator, and strlcat() which ensures
that it won't overflow the buffer.
Reported-by: Maninder Singh <maninder1.s@samsung.com>
Signed-off-by: Vaneet Narang <v.narang@samsung.com>
Signed-off-by: Russell King <linux@armlinux.org.uk>
---
v1 -> v2: changed strncpy to strlcpy
v2 -> v3: use of strlcat as suggested by Russell to
make change clearer and simpler.
arch/arm/mach-omap2/omap_hwmod.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 759e1d4..e8b9887 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -741,14 +741,14 @@ static int _init_main_clk(struct omap_hwmod *oh)
int ret = 0;
char name[MOD_CLK_MAX_NAME_LEN];
struct clk *clk;
+ static const char modck[] = "_mod_ck";
- /* +7 magic comes from '_mod_ck' suffix */
- if (strlen(oh->name) + 7 > MOD_CLK_MAX_NAME_LEN)
+ if (strlen(oh->name) >= MOD_CLK_MAX_NAME_LEN - strlen(modck))
pr_warn("%s: warning: cropping name for %s\n", __func__,
oh->name);
- strncpy(name, oh->name, MOD_CLK_MAX_NAME_LEN - 7);
- strcat(name, "_mod_ck");
+ strlcpy(name, oh->name, MOD_CLK_MAX_NAME_LEN - strlen(modck));
+ strlcat(name, modck, MOD_CLK_MAX_NAME_LEN);
clk = clk_get(NULL, name);
if (!IS_ERR(clk)) {
--
1.9.1
^ permalink raw reply related
* [PATCH 3/3] ASoC: simple-card-utils: enable clocks/clock-names/clock-ranges
From: Kuninori Morimoto @ 2016-12-05 5:23 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <874m2jvtmw.wl%kuninori.morimoto.gx@renesas.com>
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Current simple-card is supporting this style for clocks
sound {
...
simple-audio-card,cpu {
sound-dai = <&xxx>;
clocks = <&cpu_clock>;
};
simple-audio-card,codec {
sound-dai = <&xxx>;
clocks = <&codec_clock>;
};
};
Now, it can support this style too, because we can use
devm_get_clk_from_child() now.
sound {
...
clocks = <&cpu_clock>, <&codec_clock>;
clock-names = "cpu", "codec";
clock-ranges;
...
simple-audio-card,cpu {
sound-dai = <&xxx>;
};
simple-audio-card,codec {
sound-dai = <&xxx>;
};
};
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
---
.../devicetree/bindings/sound/simple-card.txt | 32 ++++++++++++++++++
sound/soc/generic/simple-card-utils.c | 39 +++++++++++++++++++++-
2 files changed, 70 insertions(+), 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/sound/simple-card.txt b/Documentation/devicetree/bindings/sound/simple-card.txt
index c7a9393..43a710b 100644
--- a/Documentation/devicetree/bindings/sound/simple-card.txt
+++ b/Documentation/devicetree/bindings/sound/simple-card.txt
@@ -86,6 +86,7 @@ Optional CPU/CODEC subnodes properties:
in dai startup() and disabled with
clk_disable_unprepare() in dai
shutdown().
+ see Clock Example.
Example 1 - single DAI link:
@@ -199,3 +200,34 @@ sound {
clocks = ...
};
};
+
+
+Clock Example 1 - clock settings on each subnode
+
+sound {
+ ...
+ simple-audio-card,cpu {
+ sound-dai = <&xxx>;
+ clocks = <&cpu_clock>;
+ };
+ simple-audio-card,codec {
+ sound-dai = <&xxx>;
+ clocks = <&codec_clock>;
+ };
+};
+
+Clock Example 2 - clock settings by clocks
+
+sound {
+ ...
+ clocks = <&cpu_clock>, <&codec_clock>;
+ clock-names = "cpu", "codec";
+ clock-ranges;
+ ...
+ simple-audio-card,cpu {
+ sound-dai = <&xxx>;
+ };
+ simple-audio-card,codec {
+ sound-dai = <&xxx>;
+ };
+};
diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c
index 4924575..c3031a5 100644
--- a/sound/soc/generic/simple-card-utils.c
+++ b/sound/soc/generic/simple-card-utils.c
@@ -104,15 +104,52 @@ int asoc_simple_card_parse_clk(struct device *dev,
struct asoc_simple_dai *simple_dai)
{
struct clk *clk;
+ const char *con_id = NULL;
+ const char *port_name[] = {
+ "cpu", "codec"
+ };
u32 val;
/*
+ * We can use this style if "con_id" is not NULL
+ *
+ * sound {
+ * ...
+ * clocks = <&xxx>, <&xxx>;
+ * clock-names = "cpu", "codec";
+ * clock-ranges;
+ *
+ * simple-audio-card,cpu {
+ * sound-dai = <&xxx>;
+ * };
+ * simple-audio-card,codec {
+ * sound-dai = <&xxx>;
+ * };
+ * };
+ */
+ if (of_find_property(dev->of_node, "clock-names", NULL)) {
+ int i;
+ int port_len, node_len;
+
+ for (i = 0; i < ARRAY_SIZE(port_name); i++) {
+ node_len = strlen(node->name);
+ port_len = strlen(port_name[i]);
+
+ if (0 == strncmp(node->name + node_len - port_len,
+ port_name[i], port_len)) {
+ con_id = port_name[i];
+ break;
+ }
+ }
+ }
+
+ /*
* Parse dai->sysclk come from "clocks = <&xxx>"
* (if system has common clock)
* or "system-clock-frequency = <xxx>"
* or device's module clock.
*/
- clk = devm_get_clk_from_child(dev, node, NULL);
+ clk = devm_get_clk_from_child(dev, node, con_id);
if (!IS_ERR(clk)) {
simple_dai->sysclk = clk_get_rate(clk);
} else if (!of_property_read_u32(node, "system-clock-frequency", &val)) {
--
1.9.1
^ permalink raw reply related
* [PATCH 2/3] ASoC: simple-card: use devm_get_clk_from_child()
From: Kuninori Morimoto @ 2016-12-05 5:23 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <874m2jvtmw.wl%kuninori.morimoto.gx@renesas.com>
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Current simple-card-utils is getting clk by of_clk_get(), but didn't call
clk_free(). Now we can use devm_get_clk_from_child() for this purpose.
Let's use it.
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
---
include/sound/simple_card_utils.h | 11 ++++++-----
sound/soc/generic/simple-card-utils.c | 8 ++++----
sound/soc/generic/simple-card.c | 4 ++--
sound/soc/generic/simple-scu-card.c | 4 ++--
4 files changed, 14 insertions(+), 13 deletions(-)
diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h
index 64e90ca..af58d23 100644
--- a/include/sound/simple_card_utils.h
+++ b/include/sound/simple_card_utils.h
@@ -34,11 +34,12 @@ int asoc_simple_card_set_dailink_name(struct device *dev,
int asoc_simple_card_parse_card_name(struct snd_soc_card *card,
char *prefix);
-#define asoc_simple_card_parse_clk_cpu(node, dai_link, simple_dai) \
- asoc_simple_card_parse_clk(node, dai_link->cpu_of_node, simple_dai)
-#define asoc_simple_card_parse_clk_codec(node, dai_link, simple_dai) \
- asoc_simple_card_parse_clk(node, dai_link->codec_of_node, simple_dai)
-int asoc_simple_card_parse_clk(struct device_node *node,
+#define asoc_simple_card_parse_clk_cpu(dev, node, dai_link, simple_dai) \
+ asoc_simple_card_parse_clk(dev, node, dai_link->cpu_of_node, simple_dai)
+#define asoc_simple_card_parse_clk_codec(dev, node, dai_link, simple_dai) \
+ asoc_simple_card_parse_clk(dev, node, dai_link->codec_of_node, simple_dai)
+int asoc_simple_card_parse_clk(struct device *dev,
+ struct device_node *node,
struct device_node *dai_of_node,
struct asoc_simple_dai *simple_dai);
diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c
index cf02625..4924575 100644
--- a/sound/soc/generic/simple-card-utils.c
+++ b/sound/soc/generic/simple-card-utils.c
@@ -98,7 +98,8 @@ int asoc_simple_card_parse_card_name(struct snd_soc_card *card,
}
EXPORT_SYMBOL_GPL(asoc_simple_card_parse_card_name);
-int asoc_simple_card_parse_clk(struct device_node *node,
+int asoc_simple_card_parse_clk(struct device *dev,
+ struct device_node *node,
struct device_node *dai_of_node,
struct asoc_simple_dai *simple_dai)
{
@@ -111,14 +112,13 @@ int asoc_simple_card_parse_clk(struct device_node *node,
* or "system-clock-frequency = <xxx>"
* or device's module clock.
*/
- clk = of_clk_get(node, 0);
+ clk = devm_get_clk_from_child(dev, node, NULL);
if (!IS_ERR(clk)) {
simple_dai->sysclk = clk_get_rate(clk);
- simple_dai->clk = clk;
} else if (!of_property_read_u32(node, "system-clock-frequency", &val)) {
simple_dai->sysclk = val;
} else {
- clk = of_clk_get(dai_of_node, 0);
+ clk = devm_get_clk_from_child(dev, dai_of_node, NULL);
if (!IS_ERR(clk))
simple_dai->sysclk = clk_get_rate(clk);
}
diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index a385ff6..85b4f18 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -278,11 +278,11 @@ static int asoc_simple_card_dai_link_of(struct device_node *node,
if (ret < 0)
goto dai_link_of_err;
- ret = asoc_simple_card_parse_clk_cpu(cpu, dai_link, cpu_dai);
+ ret = asoc_simple_card_parse_clk_cpu(dev, cpu, dai_link, cpu_dai);
if (ret < 0)
goto dai_link_of_err;
- ret = asoc_simple_card_parse_clk_codec(codec, dai_link, codec_dai);
+ ret = asoc_simple_card_parse_clk_codec(dev, codec, dai_link, codec_dai);
if (ret < 0)
goto dai_link_of_err;
diff --git a/sound/soc/generic/simple-scu-card.c b/sound/soc/generic/simple-scu-card.c
index bb86ee0..308ff4c 100644
--- a/sound/soc/generic/simple-scu-card.c
+++ b/sound/soc/generic/simple-scu-card.c
@@ -128,7 +128,7 @@ static int asoc_simple_card_dai_link_of(struct device_node *np,
if (ret)
return ret;
- ret = asoc_simple_card_parse_clk_cpu(np, dai_link, dai_props);
+ ret = asoc_simple_card_parse_clk_cpu(dev, np, dai_link, dai_props);
if (ret < 0)
return ret;
@@ -153,7 +153,7 @@ static int asoc_simple_card_dai_link_of(struct device_node *np,
if (ret < 0)
return ret;
- ret = asoc_simple_card_parse_clk_codec(np, dai_link, dai_props);
+ ret = asoc_simple_card_parse_clk_codec(dev, np, dai_link, dai_props);
if (ret < 0)
return ret;
--
1.9.1
^ permalink raw reply related
* [PATCH 1/3] clkdev: add devm_get_clk_from_child()
From: Kuninori Morimoto @ 2016-12-05 5:23 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <874m2jvtmw.wl%kuninori.morimoto.gx@renesas.com>
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Some driver is using this type of DT bindings for clock (more detail,
see ${LINUX}/Documentation/devicetree/bindings/sound/simple-card.txt).
sound_soc {
...
cpu {
clocks = <&xxx>;
...
};
codec {
clocks = <&xxx>;
...
};
};
Current driver in this case uses of_clk_get() for each node, but there
is no devm_of_clk_get() today.
OTOH, the problem of having devm_of_clk_get() is that it encourages the
use of of_clk_get() when clk_get() is more desirable.
Thus, this patch adds new devm_get_clk_from_chile() which explicitly
reads as get a clock from a child node of this device.
By this function, we can also use this type of DT bindings
sound_soc {
clocks = <&xxx>, <&xxx>;
clock-names = "cpu", "codec";
...
cpu {
...
};
codec {
...
};
};
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
---
drivers/clk/clk-devres.c | 21 +++++++++++++++++++++
include/linux/clk.h | 29 +++++++++++++++++++++++++----
2 files changed, 46 insertions(+), 4 deletions(-)
diff --git a/drivers/clk/clk-devres.c b/drivers/clk/clk-devres.c
index 8f57154..3a218c3 100644
--- a/drivers/clk/clk-devres.c
+++ b/drivers/clk/clk-devres.c
@@ -53,3 +53,24 @@ void devm_clk_put(struct device *dev, struct clk *clk)
WARN_ON(ret);
}
EXPORT_SYMBOL(devm_clk_put);
+
+struct clk *devm_get_clk_from_child(struct device *dev,
+ struct device_node *np, const char *con_id)
+{
+ struct clk **ptr, *clk;
+
+ ptr = devres_alloc(devm_clk_release, sizeof(*ptr), GFP_KERNEL);
+ if (!ptr)
+ return ERR_PTR(-ENOMEM);
+
+ clk = of_clk_get_by_name(np, con_id);
+ if (!IS_ERR(clk)) {
+ *ptr = clk;
+ devres_add(dev, ptr);
+ } else {
+ devres_free(ptr);
+ }
+
+ return clk;
+}
+EXPORT_SYMBOL(devm_get_clk_from_child);
diff --git a/include/linux/clk.h b/include/linux/clk.h
index 123c027..e9d36b3 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -17,8 +17,9 @@
#include <linux/notifier.h>
struct device;
-
struct clk;
+struct device_node;
+struct of_phandle_args;
/**
* DOC: clk notifier callback types
@@ -249,6 +250,23 @@ static inline void clk_unprepare(struct clk *clk)
struct clk *devm_clk_get(struct device *dev, const char *id);
/**
+ * devm_get_clk_from_child - lookup and obtain a managed reference to a
+ * clock producer from child node.
+ * @dev: device for clock "consumer"
+ * @np: pointer to clock consumer node
+ * @con_id: clock consumer ID
+ *
+ * This function parses the clocks, and uses them to look up the
+ * struct clk from the registered list of clock providers by using
+ * @np and @con_id
+ *
+ * The clock will automatically be freed when the device is unbound
+ * from the bus.
+ */
+struct clk *devm_get_clk_from_child(struct device *dev,
+ struct device_node *np, const char *con_id);
+
+/**
* clk_enable - inform the system when the clock source should be running.
* @clk: clock source
*
@@ -432,6 +450,12 @@ static inline struct clk *devm_clk_get(struct device *dev, const char *id)
return NULL;
}
+static inline struct clk *devm_get_clk_from_child(struct device *dev,
+ struct device_node *np, const char *con_id)
+{
+ return NULL;
+}
+
static inline void clk_put(struct clk *clk) {}
static inline void devm_clk_put(struct device *dev, struct clk *clk) {}
@@ -501,9 +525,6 @@ static inline void clk_disable_unprepare(struct clk *clk)
clk_unprepare(clk);
}
-struct device_node;
-struct of_phandle_args;
-
#if defined(CONFIG_OF) && defined(CONFIG_COMMON_CLK)
struct clk *of_clk_get(struct device_node *np, int index);
struct clk *of_clk_get_by_name(struct device_node *np, const char *name);
--
1.9.1
^ permalink raw reply related
* [PATCH 0/3] clkdev: add devm_get_clk_from_child()
From: Kuninori Morimoto @ 2016-12-05 5:22 UTC (permalink / raw)
To: linux-arm-kernel
Hi Stephen
This is v5 of "clkdev: add devm_of_clk_get()", but new series.
I hope my understanding was correct with your idea.
Kuninori Morimoto (3):
1) clkdev: add devm_get_clk_from_child()
2) ASoC: simple-card: use devm_get_clk_from_child()
3) ASoC: simple-card-utils: enable clocks/clock-names/clock-ranges
.../devicetree/bindings/sound/simple-card.txt | 32 +++++++++++++++
drivers/clk/clk-devres.c | 21 ++++++++++
include/linux/clk.h | 29 ++++++++++++--
include/sound/simple_card_utils.h | 11 +++---
sound/soc/generic/simple-card-utils.c | 45 ++++++++++++++++++++--
sound/soc/generic/simple-card.c | 4 +-
sound/soc/generic/simple-scu-card.c | 4 +-
7 files changed, 129 insertions(+), 17 deletions(-)
--
1.9.1
^ permalink raw reply
* [PATCH 2/2] ARM: omap: timers: reduce rating of gp_timer clocksource
From: Keerthy @ 2016-12-05 4:12 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <20161202183139.GF4705@atomide.com>
On Saturday 03 December 2016 12:01 AM, Tony Lindgren wrote:
> * Grygorii Strashko <grygorii.strashko@ti.com> [161202 10:02]:
>>
>>
>> On 12/02/2016 10:47 AM, Tony Lindgren wrote:
>>> * Grygorii Strashko <grygorii.strashko@ti.com> [161129 08:43]:
>>>>
>>>>
>>>> On 11/24/2016 12:19 AM, Keerthy wrote:
>>>>> From: Grygorii Strashko <grygorii.strashko@ti.com>
>>>>>
>>>>> Now ARM Global timer (rating 300) will not be selected as clocksource,
>>>>> because it's initialized after OMAP GP Timer (rating 300) and
>>>>> Timekeeping core will not allow to replace clocksource with new one if
>>>>> both of them have the same rating.
>>>>>
>>>>> Reduce rating of OMAP GP Timer (300->290) when it's used as
>>>>> clocksource device - this will allow to select ARM Global timer (300)
>>>>> as clocksource when enabled.
>>>>>
>>>>> Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
>>>>> Signed-off-by: Dave Gerlach <d-gerlach@ti.com>
>>>>> Signed-off-by: Keerthy <j-keerthy@ti.com>
>>>>
>>>> Unfortunately, this patch has dependency [1] and can't be used alone as
>>>> it will cause ARM Global timer to be selected as clocksource
>>>> always on am437x and this will kill cpuidle, because ARM Global timer
>>>> is not in always_on domain.
>>>>
>>>> The intention of enabling ARM Global timer is only for non-pm aware use
>>>> cases for RT-kernel latency improvement - where deep cpuidle states are not
>>>> enabled.
>>>
>>> Yeah we need to fix up things to be able to change the clocksource
>>> in addition to clockevent. However, currently only cpuidle_coupled
>>> knows when the whole system is idle, so quite a bit of work is
>>> needed to do that in a sane way.
>>
>> Also sched_clock and timer_delay ;)
>
> Yeah sched_clock would need something to save and restore it..
> Not nice :)
>
>>> What about the first patch in this series?
>>>
>>
>> Fist one is ok. It was originally posted long time ago.
>
> OK so can you please resend that one more time with proper
> Fixes tag on it?
Tony,
I have posted a v2 with the proper Fixes tag.
- Keerthy
>
> Regards,
>
> Tony
>
^ permalink raw reply
* [PATCH v2] ARM: omap2: am437x: rollback to use omap3_gptimer_timer_init()
From: Keerthy @ 2016-12-05 3:57 UTC (permalink / raw)
To: linux-arm-kernel
From: Grygorii Strashko <grygorii.strashko@ti.com>
The commit 55ee7017ee31 ("arm: omap2: board-generic: use
omap4_local_timer_init for AM437x") unintentionally changes the
clocksource devices for AM437x from OMAP GP Timer to SyncTimer32K.
Unfortunately, the SyncTimer32K is starving from frequency deviation
as mentioned in commit 5b5c01359152 ("ARM: OMAP2+: AM43x: Use gptimer
as clocksource") and, as reported by Franklin [1], even its monotonic
nature is under question (most probably there is a HW issue, but it's
still under investigation).
Taking into account above facts It's reasonable to rollback to the use
of omap3_gptimer_timer_init().
[1] http://www.spinics.net/lists/linux-omap/msg127425.html
Fixes: 55ee7017ee31 ("arm: omap2: board-generic: use
omap4_local_timer_init for AM437x")
Reported-by: Cooper Jr., Franklin <fcooper@ti.com>
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Lokesh Vutla <lokeshvutla@ti.com>
Signed-off-by: Keerthy <j-keerthy@ti.com>
---
Changes in v2:
* Added a proper Fixes tag with the commit ID.
arch/arm/mach-omap2/board-generic.c | 2 +-
arch/arm/mach-omap2/timer.c | 9 +++++----
2 files changed, 6 insertions(+), 5 deletions(-)
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index 36d9943..dc9e34e 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -304,7 +304,7 @@ static void __init rx51_reserve(void)
.init_late = am43xx_init_late,
.init_irq = omap_gic_of_init,
.init_machine = omap_generic_init,
- .init_time = omap4_local_timer_init,
+ .init_time = omap3_gptimer_timer_init,
.dt_compat = am43_boards_compat,
.restart = omap44xx_restart,
MACHINE_END
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index 5e2e221..b2f2448 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -510,18 +510,19 @@ void __init omap3_secure_sync32k_timer_init(void)
}
#endif /* CONFIG_ARCH_OMAP3 */
-#if defined(CONFIG_ARCH_OMAP3) || defined(CONFIG_SOC_AM33XX)
+#if defined(CONFIG_ARCH_OMAP3) || defined(CONFIG_SOC_AM33XX) || \
+ defined(CONFIG_SOC_AM43XX)
void __init omap3_gptimer_timer_init(void)
{
__omap_sync32k_timer_init(2, "timer_sys_ck", NULL,
1, "timer_sys_ck", "ti,timer-alwon", true);
-
- clocksource_probe();
+ if (of_have_populated_dt())
+ clocksource_probe();
}
#endif
#if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5) || \
- defined(CONFIG_SOC_DRA7XX) || defined(CONFIG_SOC_AM43XX)
+ defined(CONFIG_SOC_DRA7XX)
static void __init omap4_sync32k_timer_init(void)
{
__omap_sync32k_timer_init(1, "timer_32k_ck", "ti,timer-alwon",
--
1.9.1
^ permalink raw reply related
* [PATCH v4] ARM: davinci: da8xx: Fix sleeping function called from invalid context
From: David Lechner @ 2016-12-05 3:44 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <1480690380-13216-1-git-send-email-abailon@baylibre.com>
On 12/02/2016 08:53 AM, Alexandre Bailon wrote:
> Everytime the usb20 phy is enabled, there is a
> "sleeping function called from invalid context" BUG.
>
> clk_enable() from arch/arm/mach-davinci/clock.c uses spin_lock_irqsave()
> before to invoke the callback usb20_phy_clk_enable().
> usb20_phy_clk_enable() uses clk_get() and clk_enable_prepapre()
> which may sleep.
> Move clk_get() to da8xx_register_usb20_phy_clk() and
> replace clk_prepare_enable() by clk_enable().
>
> Signed-off-by: Alexandre Bailon <abailon@baylibre.com>
> ---
> arch/arm/mach-davinci/usb-da8xx.c | 28 +++++++++++++++-------------
> 1 file changed, 15 insertions(+), 13 deletions(-)
>
> diff --git a/arch/arm/mach-davinci/usb-da8xx.c b/arch/arm/mach-davinci/usb-da8xx.c
> index b010e5f..704f506 100644
> --- a/arch/arm/mach-davinci/usb-da8xx.c
> +++ b/arch/arm/mach-davinci/usb-da8xx.c
> @@ -22,6 +22,8 @@
> #define DA8XX_USB0_BASE 0x01e00000
> #define DA8XX_USB1_BASE 0x01e25000
>
> +static struct clk *usb20_clk;
> +
> static struct platform_device da8xx_usb_phy = {
> .name = "da8xx-usb-phy",
> .id = -1,
> @@ -158,21 +160,14 @@ int __init da8xx_register_usb_refclkin(int rate)
>
> static void usb20_phy_clk_enable(struct clk *clk)
> {
> - struct clk *usb20_clk;
> int err;
> u32 val;
> u32 timeout = 500000; /* 500 msec */
>
> val = readl(DA8XX_SYSCFG0_VIRT(DA8XX_CFGCHIP2_REG));
>
> - usb20_clk = clk_get(&da8xx_usb20_dev.dev, "usb20");
> - if (IS_ERR(usb20_clk)) {
> - pr_err("could not get usb20 clk: %ld\n", PTR_ERR(usb20_clk));
> - return;
> - }
> -
> /* The USB 2.O PLL requires that the USB 2.O PSC is enabled as well. */
> - err = clk_prepare_enable(usb20_clk);
> + err = clk_enable(usb20_clk);
> if (err) {
> pr_err("failed to enable usb20 clk: %d\n", err);
> clk_put(usb20_clk);
Need to remove clk_put() here.
> @@ -197,8 +192,7 @@ static void usb20_phy_clk_enable(struct clk *clk)
>
> pr_err("Timeout waiting for USB 2.0 PHY clock good\n");
> done:
> - clk_disable_unprepare(usb20_clk);
> - clk_put(usb20_clk);
> + clk_disable(usb20_clk);
> }
>
> static void usb20_phy_clk_disable(struct clk *clk)
> @@ -285,11 +279,19 @@ static struct clk_lookup usb20_phy_clk_lookup =
> int __init da8xx_register_usb20_phy_clk(bool use_usb_refclkin)
> {
> struct clk *parent;
> - int ret = 0;
> + int ret;
> +
> + usb20_clk = clk_get(&da8xx_usb20_dev.dev, "usb20");
> + ret = PTR_ERR_OR_ZERO(usb20_clk);
> + if (ret)
> + return ret;
>
> parent = clk_get(NULL, use_usb_refclkin ? "usb_refclkin" : "pll0_aux");
> - if (IS_ERR(parent))
> - return PTR_ERR(parent);
> + ret = PTR_ERR_OR_ZERO(parent);
> + if (ret) {
> + clk_put(usb20_clk);
> + return ret;
> + }
>
> usb20_phy_clk.parent = parent;
> ret = clk_register(&usb20_phy_clk);
>
I have just tried this patch with a bunch of kernel hacking options
enabled. I am getting the message show at the end of this email. We
still have the problem of nested spin locks due to nested calls to
clk_enable(). So, really, we need to use __clk_enable() and
__clk_disable() from arch/arm/mach-davinci/clock.c in
usb20_phy_clk_enable() above.
Applying the following patch on top of your patch fixed the recursive
lock message.
---
diff --git a/arch/arm/mach-davinci/clock.c b/arch/arm/mach-davinci/clock.c
index df42c93..4fba579 100644
--- a/arch/arm/mach-davinci/clock.c
+++ b/arch/arm/mach-davinci/clock.c
@@ -31,7 +31,7 @@ static LIST_HEAD(clocks);
static DEFINE_MUTEX(clocks_mutex);
static DEFINE_SPINLOCK(clockfw_lock);
-static void __clk_enable(struct clk *clk)
+void __clk_enable(struct clk *clk)
{
if (clk->parent)
__clk_enable(clk->parent);
@@ -44,7 +44,7 @@ static void __clk_enable(struct clk *clk)
}
}
-static void __clk_disable(struct clk *clk)
+void __clk_disable(struct clk *clk)
{
if (WARN_ON(clk->usecount == 0))
return;
diff --git a/arch/arm/mach-davinci/clock.h b/arch/arm/mach-davinci/clock.h
index e2a5437..8493242 100644
--- a/arch/arm/mach-davinci/clock.h
+++ b/arch/arm/mach-davinci/clock.h
@@ -136,6 +136,9 @@ int davinci_clk_reset(struct clk *clk, bool reset);
extern struct platform_device davinci_wdt_device;
extern void davinci_watchdog_reset(struct platform_device *);
+void __clk_enable(struct clk *clk);
+void __clk_disable(struct clk *clk);
+
#endif
#endif
diff --git a/arch/arm/mach-davinci/usb-da8xx.c
b/arch/arm/mach-davinci/usb-da8xx
.c
index 896d014..80ba0df 100644
--- a/arch/arm/mach-davinci/usb-da8xx.c
+++ b/arch/arm/mach-davinci/usb-da8xx.c
@@ -160,19 +160,13 @@ int __init da8xx_register_usb_refclkin(int rate)
static void usb20_phy_clk_enable(struct clk *clk)
{
- int err;
u32 val;
u32 timeout = 500000; /* 500 msec */
val = readl(DA8XX_SYSCFG0_VIRT(DA8XX_CFGCHIP2_REG));
/* The USB 2.O PLL requires that the USB 2.O PSC is enabled as
well. */
- err = clk_enable(usb20_clk);
- if (err) {
- pr_err("failed to enable usb20 clk: %d\n", err);
- clk_put(usb20_clk);
- return;
- }
+ __clk_enable(usb20_clk);
/*
* Turn on the USB 2.0 PHY, but just the PLL, and not OTG. The
USB 1.1
@@ -192,7 +186,7 @@ static void usb20_phy_clk_enable(struct clk *clk)
pr_err("Timeout waiting for USB 2.0 PHY clock good\n");
done:
- clk_disable(usb20_clk);
+ __clk_disable(usb20_clk);
}
static void usb20_phy_clk_disable(struct clk *clk)
---
=============================================
[ INFO: possible recursive locking detected ]
4.9.0-rc8-dlech-ev3-lms2012+ #22 Not tainted
---------------------------------------------
swapper/1 is trying to acquire lock:
(
clockfw_lock
){......}
, at:
[<c0014884>] clk_enable+0x24/0x50
k:
(
clockfw_lock
){......}
, at:
[<c0014884>] clk_enable+0x24/0x50
ebug this:
Possible unsafe locking scenario:
CPU0
----
lock(
clockfw_lock
);
lock(
clockfw_lock
);
May be due to missing lock nesting notation
4 locks held by swapper/1:
#0:
(
&dev->mutex
){......}
, at:
[<c02bd60c>] __driver_attach+0x68/0xb4
#1:
(
&dev->mutex
){......}
, at:
[<c02bd61c>] __driver_attach+0x78/0xb4
#2:
(
&phy->mutex
){+.+...}
, at:
[<c025ee18>] phy_power_on+0x5c/0xe4
#3:
(
clockfw_lock
){......}
, at:
[<c0014884>] clk_enable+0x24/0x50
CPU: 0 PID: 1 Comm: swapper Not tainted 4.9.0-rc8-dlech-ev3-lms2012+ #22
Hardware name: Generic DA850/OMAP-L138/AM18x
Backtrace:
[<c000d824>] (dump_backtrace) from [<c000dac4>] (show_stack+0x18/0x1c)
r7:c0e998a4 r6:c0820750 r5:c0820750 r4:c3838000
[<c000daac>] (show_stack) from [<c02393dc>] (dump_stack+0x20/0x28)
[<c02393bc>] (dump_stack) from [<c004bd7c>] (__lock_acquire+0x10f4/0x167c)
[<c004ac88>] (__lock_acquire) from [<c004c6ac>] (lock_acquire+0x78/0x98)
r10:00000000 r9:c06a5ed4 r8:00000000 r7:00000001 r6:60000093 r5:00000000
r4:ffffe000
[<c004c634>] (lock_acquire) from [<c04d8fac>]
(_raw_spin_lock_irqsave+0x60/0x74)
r7:0000003b r6:c0014884 r5:80000093 r4:c06b09a0
[<c04d8f4c>] (_raw_spin_lock_irqsave) from [<c0014884>]
(clk_enable+0x24/0x50)
r6:c06f69f4 r5:0001ef02 r4:c06b3398
[<c0014860>] (clk_enable) from [<c0015c74>] (usb20_phy_clk_enable+0x24/0xb8)
r5:0001ef02 r4:c06f69f0
[<c0015c50>] (usb20_phy_clk_enable) from [<c0014858>]
(__clk_enable+0x74/0x7c)
r9:c06a5ed4 r8:00000000 r7:0000003b r6:c3a6ca00 r5:80000013 r4:c06b7ee8
[<c00147e4>] (__clk_enable) from [<c0014808>] (__clk_enable+0x24/0x7c)
r4:c06b8648
[<c00147e4>] (__clk_enable) from [<c0014890>] (clk_enable+0x30/0x50)
r4:c06b8648
[<c0014860>] (clk_enable) from [<c025f43c>]
(da8xx_usb11_phy_power_on+0x30/0x80)
r5:c3a54050 r4:c06b8648
[<c025f40c>] (da8xx_usb11_phy_power_on) from [<c025ee3c>]
(phy_power_on+0x80/0xe4)
r5:c3a6c800 r4:fffffdf4
[<c025edbc>] (phy_power_on) from [<c032243c>] (ohci_da8xx_enable+0x4c/0x80)
r7:0000003b r6:c3af6000 r5:c3af6000 r4:00000000
[<c03223f0>] (ohci_da8xx_enable) from [<c03224f0>]
(ohci_da8xx_reset+0x1c/0xd8)
r5:00000000 r4:c3af6000
[<c03224d4>] (ohci_da8xx_reset) from [<c0309118>] (usb_add_hcd+0x314/0x834)
r7:0000003b r6:ffffffed r5:00000000 r4:c3af6000
[<c0308e04>] (usb_add_hcd) from [<c032200c>] (ohci_da8xx_probe+0x14c/0x21c)
r9:c06a5ed4 r8:00000000 r7:c38bd010 r6:c38bd000 r5:c3af6000 r4:c38af900
[<c0321ec0>] (ohci_da8xx_probe) from [<c02bec44>]
(platform_drv_probe+0x40/0x8c)
r7:c06e610c r6:c06e610c r5:c38bd010 r4:c0321ec0
[<c02bec04>] (platform_drv_probe) from [<c02bd438>]
(driver_probe_device+0x138/0x2a4)
r7:c06e610c r6:c0e9db10 r5:00000000 r4:c38bd010
[<c02bd300>] (driver_probe_device) from [<c02bd634>]
(__driver_attach+0x90/0xb4)
r9:c06a5ed4 r8:c06f66e0 r7:c06e1250 r6:c06e610c r5:c38bd044 r4:c38bd010
[<c02bd5a4>] (__driver_attach) from [<c02bba5c>]
(bus_for_each_dev+0x74/0x98)
r7:c06e1250 r6:c02bd5a4 r5:c06e610c r4:00000000
[<c02bb9e8>] (bus_for_each_dev) from [<c02bcf2c>] (driver_attach+0x20/0x28)
r6:c39a2300 r5:00000000 r4:c06e610c
[<c02bcf0c>] (driver_attach) from [<c02bca80>] (bus_add_driver+0xd4/0x1f0)
[<c02bc9ac>] (bus_add_driver) from [<c02bdcec>] (driver_register+0xa4/0xe8)
r7:c0698850 r6:00000000 r5:00000000 r4:c06e610c
[<c02bdc48>] (driver_register) from [<c02bebac>]
(__platform_driver_register+0x38/0x4c)
r5:00000000 r4:c06acce4
[<c02beb74>] (__platform_driver_register) from [<c068da20>]
(ohci_da8xx_init+0x64/0x90)
[<c068d9bc>] (ohci_da8xx_init) from [<c00096c0>]
(do_one_initcall+0xb0/0x168)
r5:c068d9bc r4:ffffe000
[<c0009610>] (do_one_initcall) from [<c0676e14>]
(kernel_init_freeable+0x110/0x1cc)
r9:c06a5ed4 r8:c06f66e0 r7:c0698850 r6:000000c1 r5:c06f66e0 r4:00000007
[<c0676d04>] (kernel_init_freeable) from [<c04d37e4>]
(kernel_init+0x10/0xf8)
r9:00000000 r8:00000000 r7:00000000 r6:00000000 r5:c04d37d4 r4:00000000
[<c04d37d4>] (kernel_init) from [<c000a2ac>] (ret_from_fork+0x14/0x28)
r5:c04d37d4 r4:00000000
BUG: spinlock lockup suspected on CPU#0, swapper/1
lock: clockfw_lock+0x0/0x20, .magic: dead4ead, .owner: swapper/1,
.owner_cpu: 0
CPU: 0 PID: 1 Comm: swapper Not tainted 4.9.0-rc8-dlech-ev3-lms2012+ #22
Hardware name: Generic DA850/OMAP-L138/AM18x
Backtrace:
[<c000d824>] (dump_backtrace) from [<c000dac4>] (show_stack+0x18/0x1c)
r7:00000000 r6:04605000 r5:c06b09a0 r4:c3838000
[<c000daac>] (show_stack) from [<c02393dc>] (dump_stack+0x20/0x28)
[<c02393bc>] (dump_stack) from [<c004f140>] (spin_dump+0x80/0x94)
[<c004f0c0>] (spin_dump) from [<c004f2c4>] (do_raw_spin_lock+0xdc/0x11c)
r5:00000000 r4:c06b09a0
[<c004f1e8>] (do_raw_spin_lock) from [<c04d8fb4>]
(_raw_spin_lock_irqsave+0x68/0x74)
r10:00000000 r9:c06a5ed4 r8:00000000 r7:0000003b r6:c0014884 r5:80000093
r4:c06b09a0 r3:c3838000
[<c04d8f4c>] (_raw_spin_lock_irqsave) from [<c0014884>]
(clk_enable+0x24/0x50)
r6:c06f69f4 r5:0001ef02 r4:c06b3398
[<c0014860>] (clk_enable) from [<c0015c74>] (usb20_phy_clk_enable+0x24/0xb8)
r5:0001ef02 r4:c06f69f0
[<c0015c50>] (usb20_phy_clk_enable) from [<c0014858>]
(__clk_enable+0x74/0x7c)
r9:c06a5ed4 r8:00000000 r7:0000003b r6:c3a6ca00 r5:80000013 r4:c06b7ee8
[<c00147e4>] (__clk_enable) from [<c0014808>] (__clk_enable+0x24/0x7c)
r4:c06b8648
[<c00147e4>] (__clk_enable) from [<c0014890>] (clk_enable+0x30/0x50)
r4:c06b8648
[<c0014860>] (clk_enable) from [<c025f43c>]
(da8xx_usb11_phy_power_on+0x30/0x80)
r5:c3a54050 r4:c06b8648
[<c025f40c>] (da8xx_usb11_phy_power_on) from [<c025ee3c>]
(phy_power_on+0x80/0xe4)
r5:c3a6c800 r4:fffffdf4
[<c025edbc>] (phy_power_on) from [<c032243c>] (ohci_da8xx_enable+0x4c/0x80)
r7:0000003b r6:c3af6000 r5:c3af6000 r4:00000000
[<c03223f0>] (ohci_da8xx_enable) from [<c03224f0>]
(ohci_da8xx_reset+0x1c/0xd8)
r5:00000000 r4:c3af6000
[<c03224d4>] (ohci_da8xx_reset) from [<c0309118>] (usb_add_hcd+0x314/0x834)
r7:0000003b r6:ffffffed r5:00000000 r4:c3af6000
[<c0308e04>] (usb_add_hcd) from [<c032200c>] (ohci_da8xx_probe+0x14c/0x21c)
r9:c06a5ed4 r8:00000000 r7:c38bd010 r6:c38bd000 r5:c3af6000 r4:c38af900
[<c0321ec0>] (ohci_da8xx_probe) from [<c02bec44>]
(platform_drv_probe+0x40/0x8c)
r7:c06e610c r6:c06e610c r5:c38bd010 r4:c0321ec0
[<c02bec04>] (platform_drv_probe) from [<c02bd438>]
(driver_probe_device+0x138/0x2a4)
r7:c06e610c r6:c0e9db10 r5:00000000 r4:c38bd010
[<c02bd300>] (driver_probe_device) from [<c02bd634>]
(__driver_attach+0x90/0xb4)
r9:c06a5ed4 r8:c06f66e0 r7:c06e1250 r6:c06e610c r5:c38bd044 r4:c38bd010
[<c02bd5a4>] (__driver_attach) from [<c02bba5c>]
(bus_for_each_dev+0x74/0x98)
r7:c06e1250 r6:c02bd5a4 r5:c06e610c r4:00000000
[<c02bb9e8>] (bus_for_each_dev) from [<c02bcf2c>] (driver_attach+0x20/0x28)
r6:c39a2300 r5:00000000 r4:c06e610c
[<c02bcf0c>] (driver_attach) from [<c02bca80>] (bus_add_driver+0xd4/0x1f0)
[<c02bc9ac>] (bus_add_driver) from [<c02bdcec>] (driver_register+0xa4/0xe8)
r7:c0698850 r6:00000000 r5:00000000 r4:c06e610c
[<c02bdc48>] (driver_register) from [<c02bebac>]
(__platform_driver_register+0x38/0x4c)
r5:00000000 r4:c06acce4
[<c02beb74>] (__platform_driver_register) from [<c068da20>]
(ohci_da8xx_init+0x64/0x90)
[<c068d9bc>] (ohci_da8xx_init) from [<c00096c0>]
(do_one_initcall+0xb0/0x168)
r5:c068d9bc r4:ffffe000
[<c0009610>] (do_one_initcall) from [<c0676e14>]
(kernel_init_freeable+0x110/0x1cc)
r9:c06a5ed4 r8:c06f66e0 r7:c0698850 r6:000000c1 r5:c06f66e0 r4:00000007
[<c0676d04>] (kernel_init_freeable) from [<c04d37e4>]
(kernel_init+0x10/0xf8)
r9:00000000 r8:00000000 r7:00000000 r6:00000000 r5:c04d37d4 r4:00000000
[<c04d37d4>] (kernel_init) from [<c000a2ac>] (ret_from_fork+0x14/0x28)
r5:c04d37d4 r4:00000000
^ permalink raw reply related
* [PATCH v2 3/3] ARM: da850: fix da850_set_pll0rate()
From: Viresh Kumar @ 2016-12-05 3:34 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <1480693134-31324-4-git-send-email-bgolaszewski@baylibre.com>
Good to see you again Bartosz :)
On 02-12-16, 16:38, Bartosz Golaszewski wrote:
> This function is broken - its second argument is an index to the freq
> table, not the requested clock rate in Hz. It leads to an oops when
> called from clk_set_rate() since this argument isn't bounds checked
> either.
>
> Fix it by iterating over the array of supported frequencies and
> selecting a one that matches or returning -EINVAL for unsupported
> rates.
>
> Also: update the davinci cpufreq driver. It's the only user of this
> clock and currently it passes the cpufreq table index to
> clk_set_rate(), which is confusing. Make it pass the requested clock
> rate in Hz.
>
> Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
> ---
> arch/arm/mach-davinci/da850.c | 22 ++++++++++++++++++----
> drivers/cpufreq/davinci-cpufreq.c | 2 +-
> 2 files changed, 19 insertions(+), 5 deletions(-)
>
> diff --git a/arch/arm/mach-davinci/da850.c b/arch/arm/mach-davinci/da850.c
> index a55101c..92e3303 100644
> --- a/arch/arm/mach-davinci/da850.c
> +++ b/arch/arm/mach-davinci/da850.c
> @@ -1179,14 +1179,28 @@ static int da850_set_armrate(struct clk *clk, unsigned long index)
> return clk_set_rate(pllclk, index);
> }
>
> -static int da850_set_pll0rate(struct clk *clk, unsigned long index)
> +static int da850_set_pll0rate(struct clk *clk, unsigned long rate)
> {
> - unsigned int prediv, mult, postdiv;
> - struct da850_opp *opp;
> struct pll_data *pll = clk->pll_data;
> + struct cpufreq_frequency_table *freq;
> + unsigned int prediv, mult, postdiv;
> + struct da850_opp *opp = NULL;
> int ret;
>
> - opp = (struct da850_opp *) cpufreq_info.freq_table[index].driver_data;
> + for (freq = da850_freq_table;
> + freq->frequency != CPUFREQ_TABLE_END; freq++) {
> + /* requested_rate is in Hz, freq->frequency is in KHz */
> + unsigned long freq_rate = freq->frequency * 1000;
> +
> + if (freq_rate == rate) {
> + opp = (struct da850_opp *)freq->driver_data;
> + break;
> + }
> + }
> +
> + if (opp == NULL)
> + return -EINVAL;
> +
> prediv = opp->prediv;
> mult = opp->mult;
> postdiv = opp->postdiv;
> diff --git a/drivers/cpufreq/davinci-cpufreq.c b/drivers/cpufreq/davinci-cpufreq.c
> index b95a872..d54a27c 100644
> --- a/drivers/cpufreq/davinci-cpufreq.c
> +++ b/drivers/cpufreq/davinci-cpufreq.c
> @@ -55,7 +55,7 @@ static int davinci_target(struct cpufreq_policy *policy, unsigned int idx)
> return ret;
> }
>
> - ret = clk_set_rate(armclk, idx);
> + ret = clk_set_rate(armclk, new_freq * 1000);
> if (ret)
> return ret;
I haven't checked the internal of davinci or the way rate is changed now, but
from cpufreq's perspective, fee free to add my:
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
--
viresh
^ permalink raw reply
* [PATCH 2/2] soc: zte: pm_domains: Add support for zx296718 driver
From: Jun Nie @ 2016-12-05 3:27 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <1480774291-6211-2-git-send-email-baoyou.xie@linaro.org>
2016-12-03 22:11 GMT+08:00 Baoyou Xie <baoyou.xie@linaro.org>:
> This patch introduces the power domain driver of zx296718
> which belongs to zte's 2967 family.
>
> Signed-off-by: Baoyou Xie <baoyou.xie@linaro.org>
> ---
> drivers/soc/zte/Makefile | 3 +
> drivers/soc/zte/zx296718_pm_domains.c | 162 ++++++++++++++++++++++++++++++++++
> 2 files changed, 165 insertions(+)
> create mode 100644 drivers/soc/zte/zx296718_pm_domains.c
>
> diff --git a/drivers/soc/zte/Makefile b/drivers/soc/zte/Makefile
> index 97ac8ea..a6e7bfe 100644
> --- a/drivers/soc/zte/Makefile
> +++ b/drivers/soc/zte/Makefile
> @@ -2,3 +2,6 @@
> # zx SOC drivers
> #
> obj-$(CONFIG_ZX_PM_DOMAINS) += pm_domains.o
> +ifeq ($(CONFIG_ZX_PM_DOMAINS), y)
> + obj-y += zx296718_pm_domains.o
> +endif
Follow unified style for Makefile:
obj-$(CONFIG_ZX_PM_DOMAINS) += zx296718_pm_domains.o
> diff --git a/drivers/soc/zte/zx296718_pm_domains.c b/drivers/soc/zte/zx296718_pm_domains.c
> new file mode 100644
> index 0000000..fc16dfd
> --- /dev/null
> +++ b/drivers/soc/zte/zx296718_pm_domains.c
> @@ -0,0 +1,162 @@
> +/*
> + * Copyright (C) 2015 ZTE Ltd.
> + *
> + * Author: Baoyou Xie <baoyou.xie@linaro.org>
> + * License terms: GNU General Public License (GPL) version 2
> + */
> +#include "pm_domains.h"
> +
> +enum {
> + PCU_DM_VOU = 0,
> + PCU_DM_SAPPU,
> + PCU_DM_VDE,
> + PCU_DM_VCE,
> + PCU_DM_HDE,
> + PCU_DM_VIU,
> + PCU_DM_USB20,
> + PCU_DM_USB21,
> + PCU_DM_USB30,
> + PCU_DM_HSIC,
> + PCU_DM_GMAC,
> + PCU_DM_TS,
> +};
> +
> +static struct zx_pm_domain vou_domain = {
> + .dm = {
> + .name = "vou_domain",
> + .power_off = zx_normal_power_off,
> + .power_on = zx_normal_power_on,
> + },
> + .bit = PCU_DM_VOU,
> +};
> +static struct zx_pm_domain sappu_domain = {
> + .dm = {
> + .name = "sappu_domain",
> + .power_off = zx_normal_power_off,
> + .power_on = zx_normal_power_on,
> + },
> + .bit = PCU_DM_SAPPU,
> +};
> +static struct zx_pm_domain vde_domain = {
> + .dm = {
> + .name = "vde_domain",
> + .power_off = zx_normal_power_off,
> + .power_on = zx_normal_power_on,
> + },
> + .bit = PCU_DM_VDE,
> +};
> +static struct zx_pm_domain vce_domain = {
> + .dm = {
> + .name = "vce_domain",
> + .power_off = zx_normal_power_off,
> + .power_on = zx_normal_power_on,
> + },
> + .bit = PCU_DM_VCE,
> +};
> +static struct zx_pm_domain hde_domain = {
> + .dm = {
> + .name = "hde_domain",
> + .power_off = zx_normal_power_off,
> + .power_on = zx_normal_power_on,
> + },
> + .bit = PCU_DM_HDE,
> +};
> +
> +static struct zx_pm_domain viu_domain = {
> + .dm = {
> + .name = "viu_domain",
> + .power_off = zx_normal_power_off,
> + .power_on = zx_normal_power_on,
> + },
> + .bit = PCU_DM_VIU,
> +};
> +static struct zx_pm_domain usb20_domain = {
> + .dm = {
> + .name = "usb20_domain",
> + .power_off = zx_normal_power_off,
> + .power_on = zx_normal_power_on,
> + },
> + .bit = PCU_DM_USB20,
> +};
> +static struct zx_pm_domain usb21_domain = {
> + .dm = {
> + .name = "usb21_domain",
> + .power_off = zx_normal_power_off,
> + .power_on = zx_normal_power_on,
> + },
> + .bit = PCU_DM_USB21,
> +};
> +static struct zx_pm_domain usb30_domain = {
> + .dm = {
> + .name = "usb30_domain",
> + .power_off = zx_normal_power_off,
> + .power_on = zx_normal_power_on,
> + },
> + .bit = PCU_DM_USB30,
> +};
> +static struct zx_pm_domain hsic_domain = {
> + .dm = {
> + .name = "hsic_domain",
> + .power_off = zx_normal_power_off,
> + .power_on = zx_normal_power_on,
> + },
> + .bit = PCU_DM_HSIC,
> +};
> +static struct zx_pm_domain gmac_domain = {
> + .dm = {
> + .name = "gmac_domain",
> + .power_off = zx_normal_power_off,
> + .power_on = zx_normal_power_on,
> + },
> + .bit = PCU_DM_GMAC,
> +};
> +static struct zx_pm_domain ts_domain = {
> + .dm = {
> + .name = "ts_domain",
> + .power_off = zx_normal_power_off,
> + .power_on = zx_normal_power_on,
> + },
> + .bit = PCU_DM_TS,
> +};
> +struct generic_pm_domain *zx296718_pm_domains[] = {
> + //&vou_domain.dm,
Remove this line.
> + &sappu_domain.dm,
If you can add an index and add the index definition in devicetree
header file, it will be more convenient when binding power domain to
device in DT file. such as
[ZX296718_PM_VDE] = &vde_domain.dm,
> + &vde_domain.dm,
> + &vce_domain.dm,
> + &hde_domain.dm,
> + &viu_domain.dm,
> + &usb20_domain.dm,
> + &usb21_domain.dm,
> + &usb30_domain.dm,
> + &hsic_domain.dm,
> + &gmac_domain.dm,
> + &ts_domain.dm,
> + &vou_domain.dm,
> +};
> +
> +static int zx296718_pd_probe(struct platform_device *pdev)
> +{
> + return zx_pd_probe(pdev,
> + zx296718_pm_domains,
> + ARRAY_SIZE(zx296718_pm_domains));
> +}
> +
> +static const struct of_device_id zx296718_pm_domain_matches[] = {
> + { .compatible = "zte,zx296718-pcu", },
Suggest to rename probe function and of_device_id to a generic zx
name, then add compatible data so that probe function can be shared.
Probe function can find SoC specific data via comparing compatible
string and initialize device accordingly.
> + { },
> +};
> +
> +static struct platform_driver zx296718_pd_driver = {
> + .driver = {
> + .name = "zx-powerdomain",
> + .owner = THIS_MODULE,
> + .of_match_table = zx296718_pm_domain_matches,
> + },
> + .probe = zx296718_pd_probe,
> +};
> +
> +static int __init zx296718_pd_init(void)
> +{
> + return platform_driver_register(&zx296718_pd_driver);
> +}
> +subsys_initcall(zx296718_pd_init);
> --
> 2.7.4
>
^ permalink raw reply
* [PATCH] arm64: dts: zx: add pcu_domain node for zx296718
From: Shawn Guo @ 2016-12-05 3:16 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <1480766354-25168-1-git-send-email-baoyou.xie@linaro.org>
On Sat, Dec 03, 2016 at 07:59:14PM +0800, Baoyou Xie wrote:
> This patch adds the pcu_domain node, so it can be used
> by zte-soc's power domain driver.
>
> Furthermore, it adds the document of the node.
>
> Signed-off-by: Baoyou Xie <baoyou.xie@linaro.org>
> ---
> Documentation/devicetree/bindings/arm/zte.txt | 11 +++++++++++
DT bindings doc should be a separate patch, and goes together with
driver changes using the bindings through subsystem maintainers, rather
than dts patches.
> arch/arm64/boot/dts/zte/zx296718.dtsi | 7 +++++++
> 2 files changed, 18 insertions(+)
>
> diff --git a/Documentation/devicetree/bindings/arm/zte.txt b/Documentation/devicetree/bindings/arm/zte.txt
> index 83369785..19a7e1b 100644
> --- a/Documentation/devicetree/bindings/arm/zte.txt
> +++ b/Documentation/devicetree/bindings/arm/zte.txt
> @@ -27,6 +27,9 @@ System management required properties:
> - compatible = "zte,zx296718-aon-sysctrl"
> - compatible = "zte,zx296718-sysctrl"
>
> +Low power management required properties:
> + - compatible = "zte,zx296718-pcu"
> +
> Example:
> aon_sysctrl: aon-sysctrl at 116000 {
> compatible = "zte,zx296718-aon-sysctrl", "syscon";
> @@ -37,3 +40,11 @@ sysctrl: sysctrl at 1463000 {
> compatible = "zte,zx296718-sysctrl", "syscon";
> reg = <0x1463000 0x1000>;
> };
> +
> +pcu_domain: pcu at 0x00117000 {
> + compatible = "zte,zx296718-pcu";
> + reg = <0x00117000 0x1000>;
> + #power-domain-cells = <1>;
> + status = "ok";
> +};
> +
I think we should have a separate bindings doc for PCU power domain
block in Documentation/devicetree/bindings/soc/zte.
> diff --git a/arch/arm64/boot/dts/zte/zx296718.dtsi b/arch/arm64/boot/dts/zte/zx296718.dtsi
> index b44d1d1..39e70c7 100644
> --- a/arch/arm64/boot/dts/zte/zx296718.dtsi
> +++ b/arch/arm64/boot/dts/zte/zx296718.dtsi
> @@ -351,5 +351,12 @@
> reg = <0x01480000 0x1000>;
> #clock-cells = <1>;
> };
> +
> + pcu_domain: pcu at 0x00117000 {
Please drop the 0x and leading zeros in unit-address after node name.
That said, the node name should be written like below:
pcu at 117000 {
Also, please sort the node with unit-address in order of the address.
That means that pcu node should be put after aon-sysctrl at 116000.
> + compatible = "zte,zx296718-pcu";
> + reg = <0x00117000 0x1000>;
> + #power-domain-cells = <1>;
> + status = "ok";
The property 'status' is generally used to enable devices that have
board-level pin-out or configuration in board dts. It's not really
necessary for pcu here.
Shawn
> + };
> };
> };
> --
> 2.7.4
>
^ permalink raw reply
* [PATCH 1/2] soc: zte: pm_domains: Prepare for supporting ARMv8 2967 family
From: Jun Nie @ 2016-12-05 3:15 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <1480774291-6211-1-git-send-email-baoyou.xie@linaro.org>
2016-12-03 22:11 GMT+08:00 Baoyou Xie <baoyou.xie@linaro.org>:
> The ARMv8 2967 family (296718, 296716 etc) uses different value
> for controlling the power domain on/off registers, Choose the
> value depending on the compatible.
>
> Multiple domains are prepared for the family, it's privated by
> the drivers of boards.
>
> This patch prepares the common functions.
>
> Signed-off-by: Baoyou Xie <baoyou.xie@linaro.org>
> ---
> MAINTAINERS | 1 +
> drivers/soc/Kconfig | 1 +
> drivers/soc/Makefile | 1 +
> drivers/soc/zte/Kconfig | 13 ++++
> drivers/soc/zte/Makefile | 4 ++
> drivers/soc/zte/pm_domains.c | 138 +++++++++++++++++++++++++++++++++++++++++++
> drivers/soc/zte/pm_domains.h | 29 +++++++++
> 7 files changed, 187 insertions(+)
> create mode 100644 drivers/soc/zte/Kconfig
> create mode 100644 drivers/soc/zte/Makefile
> create mode 100644 drivers/soc/zte/pm_domains.c
> create mode 100644 drivers/soc/zte/pm_domains.h
>
> diff --git a/MAINTAINERS b/MAINTAINERS
> index ad199da..8198389 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -1979,6 +1979,7 @@ L: linux-arm-kernel at lists.infradead.org (moderated for non-subscribers)
> S: Maintained
> F: arch/arm/mach-zx/
> F: drivers/clk/zte/
> +F: drivers/soc/zte/
> F: Documentation/devicetree/bindings/arm/zte.txt
> F: Documentation/devicetree/bindings/clock/zx296702-clk.txt
>
> diff --git a/drivers/soc/Kconfig b/drivers/soc/Kconfig
> index f31bceb..f09023f 100644
> --- a/drivers/soc/Kconfig
> +++ b/drivers/soc/Kconfig
> @@ -11,5 +11,6 @@ source "drivers/soc/tegra/Kconfig"
> source "drivers/soc/ti/Kconfig"
> source "drivers/soc/ux500/Kconfig"
> source "drivers/soc/versatile/Kconfig"
> +source "drivers/soc/zte/Kconfig"
>
> endmenu
> diff --git a/drivers/soc/Makefile b/drivers/soc/Makefile
> index 50c23d0..05eae52 100644
> --- a/drivers/soc/Makefile
> +++ b/drivers/soc/Makefile
> @@ -16,3 +16,4 @@ obj-$(CONFIG_ARCH_TEGRA) += tegra/
> obj-$(CONFIG_SOC_TI) += ti/
> obj-$(CONFIG_ARCH_U8500) += ux500/
> obj-$(CONFIG_PLAT_VERSATILE) += versatile/
> +obj-$(CONFIG_ARCH_ZX) += zte/
> diff --git a/drivers/soc/zte/Kconfig b/drivers/soc/zte/Kconfig
> new file mode 100644
> index 0000000..4953c3fa
> --- /dev/null
> +++ b/drivers/soc/zte/Kconfig
> @@ -0,0 +1,13 @@
> +#
> +# zx SoC drivers
> +#
> +menuconfig SOC_ZX
> + bool "zx SoC driver support"
Why not reuse ARCH_ZX ?
> +
> +if SOC_ZX
> +
> +config ZX_PM_DOMAINS
> + bool "zx PM domains"
> + depends on PM_GENERIC_DOMAINS
> +
> +endif
> diff --git a/drivers/soc/zte/Makefile b/drivers/soc/zte/Makefile
> new file mode 100644
> index 0000000..97ac8ea
> --- /dev/null
> +++ b/drivers/soc/zte/Makefile
> @@ -0,0 +1,4 @@
> +#
> +# zx SOC drivers
> +#
> +obj-$(CONFIG_ZX_PM_DOMAINS) += pm_domains.o
> diff --git a/drivers/soc/zte/pm_domains.c b/drivers/soc/zte/pm_domains.c
> new file mode 100644
> index 0000000..5792f21
> --- /dev/null
> +++ b/drivers/soc/zte/pm_domains.c
> @@ -0,0 +1,138 @@
> +/*
> + * Copyright (C) 2015 ZTE Ltd.
> + *
> + * Author: Baoyou Xie <baoyou.xie@linaro.org>
> + * License terms: GNU General Public License (GPL) version 2
> + */
> +#include <linux/delay.h>
> +#include <linux/err.h>
> +#include <linux/io.h>
> +#include <linux/of.h>
> +#include "pm_domains.h"
> +
> +#define PCU_DM_CLKEN 0x18
> +#define PCU_DM_RSTEN 0x20
> +#define PCU_DM_ISOEN 0x1c
List registers with ascending sequence.
I find these registers offset is different with existing 296702
register offset. So I suggest to use offset table to resolve the
conflict so that this driver is extendable for more SoC with different
register offset if you want. You can reference
drivers/tty/serial/amba-pl011.c for register offset handling.
> +#define PCU_DM_PWREN 0x24
> +#define PCU_DM_ACK_SYNC 0x28
> +
> +static void __iomem *pcubase;
> +
> +int zx_normal_power_on(struct generic_pm_domain *domain)
> +{
> + struct zx_pm_domain *zpd = (struct zx_pm_domain *)domain;
> + unsigned long loop = 20000;
> + u32 val;
> +
> + loop = 1000;
> + do {
> + val = readl_relaxed(pcubase + PCU_DM_PWREN);
> + val |= BIT(zpd->bit);
bit polarity can also be configurable if you want support more SoCs
with different polarity setting.
> + writel_relaxed(val, pcubase + PCU_DM_PWREN);
> +
> + udelay(1);
> + val = readl_relaxed(pcubase + PCU_DM_ACK_SYNC) & BIT(zpd->bit);
> + } while (--loop && !val);
> +
> + if (!loop) {
> + pr_err("Error: %s %s fail\n", __func__, domain->name);
> + return -EIO;
> + }
> +
> + val = readl_relaxed(pcubase + PCU_DM_RSTEN);
> + val &= ~BIT(zpd->bit);
> + writel_relaxed(val | BIT(zpd->bit), pcubase + PCU_DM_RSTEN);
> + udelay(5);
> +
> + val = readl_relaxed(pcubase + PCU_DM_ISOEN);
> + val &= ~BIT(zpd->bit);
> + writel_relaxed(val, pcubase + PCU_DM_ISOEN);
> + udelay(5);
> +
> + val = readl_relaxed(pcubase + PCU_DM_CLKEN);
> + val &= ~BIT(zpd->bit);
> + writel_relaxed(val | BIT(zpd->bit), pcubase + PCU_DM_CLKEN);
> + udelay(5);
> +
> + pr_info("normal poweron %s\n", domain->name);
> +
> + return 0;
> +}
> +
> +int zx_normal_power_off(struct generic_pm_domain *domain)
> +{
> + struct zx_pm_domain *zpd = (struct zx_pm_domain *)domain;
> + unsigned long loop = 1000;
> + u32 val;
> +
> + val = readl_relaxed(pcubase + PCU_DM_CLKEN);
> + val &= ~BIT(zpd->bit);
> + writel_relaxed(val, pcubase + PCU_DM_CLKEN);
> + udelay(5);
> +
> + val = readl_relaxed(pcubase + PCU_DM_ISOEN);
> + val &= ~BIT(zpd->bit);
> + writel_relaxed(val | BIT(zpd->bit), pcubase + PCU_DM_ISOEN);
> + udelay(5);
> +
> + val = readl_relaxed(pcubase + PCU_DM_RSTEN);
> + val &= ~BIT(zpd->bit);
> + writel_relaxed(val, pcubase + PCU_DM_RSTEN);
> + udelay(5);
> +
> + loop = 1000;
> + do {
> + val = readl_relaxed(pcubase + PCU_DM_PWREN);
> + val &= ~BIT(zpd->bit);
> + writel_relaxed(val, pcubase + PCU_DM_PWREN);
> +
> + udelay(1);
> +
> + val = readl_relaxed(pcubase + PCU_DM_ACK_SYNC) & BIT(zpd->bit);
> + } while (--loop && val);
> +
> + if (!loop) {
> + pr_err("Error: %s %s fail\n", __func__, domain->name);
> + return -EIO;
> + }
> +
> + pr_info("normal poweroff %s\n", domain->name);
> +
> + return 0;
> +}
> +
> +int
> +zx_pd_probe(struct platform_device *pdev,
> + struct generic_pm_domain **zx_pm_domains,
> + int domain_num)
> +{
> + struct genpd_onecell_data *genpd_data;
> + struct resource *res;
> + int i;
> +
> + genpd_data = devm_kzalloc(&pdev->dev, sizeof(*genpd_data), GFP_KERNEL);
> + if (!genpd_data)
> + return -ENOMEM;
> +
> + genpd_data->domains = zx_pm_domains;
> + genpd_data->num_domains = domain_num;
> +
> + res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
> + if (!res) {
> + dev_err(&pdev->dev, "no memory resource defined\n");
> + return -ENODEV;
> + }
> +
> + pcubase = devm_ioremap_resource(&pdev->dev, res);
> + if (!pcubase) {
> + dev_err(&pdev->dev, "ioremap fail.\n");
> + return -EIO;
> + }
> +
> + for (i = 0; i < domain_num; ++i)
> + pm_genpd_init(zx_pm_domains[i], NULL, false);
> +
> + of_genpd_add_provider_onecell(pdev->dev.of_node, genpd_data);
> + dev_info(&pdev->dev, "powerdomain init ok\n");
> + return 0;
> +}
> diff --git a/drivers/soc/zte/pm_domains.h b/drivers/soc/zte/pm_domains.h
> new file mode 100644
> index 0000000..613e0be
> --- /dev/null
> +++ b/drivers/soc/zte/pm_domains.h
> @@ -0,0 +1,29 @@
> +/*
> + * Copyright (c) 2015 ZTE Co., Ltd.
> + * http://www.zte.com.cn
> + *
> + * Header for ZTE's Power Domain Driver support
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License version 2 as
> + * published by the Free Software Foundation.
> + */
> +
> +#ifndef __ZTE_PM_DOMAIN_H
> +#define __ZTE_PM_DOMAIN_H
> +
> +#include <linux/platform_device.h>
> +#include <linux/pm_domain.h>
> +
> +struct zx_pm_domain {
> + struct generic_pm_domain dm;
> + unsigned int bit;
> +};
> +
> +extern int zx_normal_power_on(struct generic_pm_domain *domain);
> +extern int zx_normal_power_off(struct generic_pm_domain *domain);
> +extern int
> +zx_pd_probe(struct platform_device *pdev,
> + struct generic_pm_domain **zx_pm_domains,
> + int domain_num);
> +#endif /* __ZTE_PM_DOMAIN_H */
> --
> 2.7.4
>
^ permalink raw reply
* [PATCH V2 fix 5/6] mm: hugetlb: add a new function to allocate a new gigantic page
From: Huang Shijie @ 2016-12-05 3:15 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <20161202140325.GM6830@dhcp22.suse.cz>
On Fri, Dec 02, 2016 at 03:03:30PM +0100, Michal Hocko wrote:
> On Wed 16-11-16 14:55:04, Huang Shijie wrote:
> > There are three ways we can allocate a new gigantic page:
> >
> > 1. When the NUMA is not enabled, use alloc_gigantic_page() to get
> > the gigantic page.
> >
> > 2. The NUMA is enabled, but the vma is NULL.
> > There is no memory policy we can refer to.
> > So create a @nodes_allowed, initialize it with init_nodemask_of_mempolicy()
> > or init_nodemask_of_node(). Then use alloc_fresh_gigantic_page() to get
> > the gigantic page.
> >
> > 3. The NUMA is enabled, and the vma is valid.
> > We can follow the memory policy of the @vma.
> >
> > Get @nodes_allowed by huge_nodemask(), and use alloc_fresh_gigantic_page()
> > to get the gigantic page.
>
> Again __hugetlb_alloc_gigantic_page is not used and it is hard to deduce
> its usage from this commit. The above shouldn't be really much different from
Okay, I will merge it into the later patch.
> what we do in alloc_pages_vma so please make sure to check it before
> coming up with something hugetlb specific.
No problem. Thanks for the hint.
Thanks
Huang Shijie
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox