[permalink] [raw]

Subject: [PATCH v7 06/14] clk: qcom: cpu-8996: Add support to switch below 600Mhz

From: Rajendra Nayak <[email protected]>

The CPU clock controller's primary PLL operates on a single VCO range,
between 600MHz and 3GHz. However the CPUs do support OPPs with
frequencies between 300MHz and 600MHz. In order to support running the
CPUs at those frequencies we end up having to lock the PLL at twice the
rate and drive the CPU clk via the PLL/2 output and SMUX.

So for frequencies above 600MHz we follow the following path
Primary PLL --> PLL_EARLY --> PMUX(1) --> CPU clk
and for frequencies between 300MHz and 600MHz we follow
Primary PLL --> PLL/2 --> SMUX(1) --> PMUX(0) --> CPU clk

Signed-off-by: Rajendra Nayak <[email protected]>
Signed-off-by: Ilia Lin <[email protected]>

Conflicts:
drivers/clk/qcom/clk-cpu-8996.c
---
drivers/clk/qcom/clk-cpu-8996.c | 25 ++++++++++++++++++++++---
1 file changed, 22 insertions(+), 3 deletions(-)

diff --git a/drivers/clk/qcom/clk-cpu-8996.c b/drivers/clk/qcom/clk-cpu-8996.c
index 390b369..3ea0446 100644
--- a/drivers/clk/qcom/clk-cpu-8996.c
+++ b/drivers/clk/qcom/clk-cpu-8996.c
@@ -77,6 +77,8 @@ enum _pmux_input {
NUM_OF_PMUX_INPUTS
};

+#define DIV_2_THRESHOLD 600000000
+
static const u8 prim_pll_regs[PLL_OFF_MAX_REGS] = {
[PLL_OFF_L_VAL] = 0x04,
[PLL_OFF_ALPHA_VAL] = 0x08,
@@ -104,10 +106,11 @@ enum _pmux_input {

static const struct alpha_pll_config hfpll_config = {
.l = 60,
- .config_ctl_val = 0x200d4828,
+ .config_ctl_val = 0x200d4aa8,
.config_ctl_hi_val = 0x006,
.pre_div_mask = BIT(12),
.post_div_mask = 0x3 << 8,
+ .post_div_val = 0x1 << 8,
.main_output_mask = BIT(0),
.early_output_mask = BIT(3),
};
@@ -149,7 +152,7 @@ enum _pmux_input {
.vco_mask = 0x3 << 20,
.config_ctl_val = 0x4001051b,
.post_div_mask = 0x3 << 8,
- .post_div_val = 0x1,
+ .post_div_val = 0x1 << 8,
.main_output_mask = BIT(0),
.early_output_mask = BIT(3),
};
@@ -190,6 +193,7 @@ struct clk_cpu_8996_mux {
u8 width;
struct notifier_block nb;
struct clk_hw *pll;
+ struct clk_hw *pll_div_2;
struct clk_regmap clkr;
};

@@ -235,6 +239,13 @@ static int clk_cpu_8996_mux_set_parent(struct clk_hw *hw, u8 index)
struct clk_cpu_8996_mux *cpuclk = to_clk_cpu_8996_mux_hw(hw);
struct clk_hw *parent = cpuclk->pll;

+ if (cpuclk->pll_div_2 && req->rate < DIV_2_THRESHOLD) {
+ if (req->rate < (DIV_2_THRESHOLD / 2))
+ return -EINVAL;
+
+ parent = cpuclk->pll_div_2;
+ }
+
req->best_parent_rate = clk_hw_round_rate(parent, req->rate);
req->best_parent_hw = parent;

@@ -246,13 +257,19 @@ int cpu_clk_notifier_cb(struct notifier_block *nb, unsigned long event,
{
int ret;
struct clk_cpu_8996_mux *cpuclk = to_clk_cpu_8996_mux_nb(nb);
+ struct clk_notifier_data *cnd = data;

switch (event) {
case PRE_RATE_CHANGE:
ret = clk_cpu_8996_mux_set_parent(&cpuclk->clkr.hw, ALT_INDEX);
break;
case POST_RATE_CHANGE:
- ret = clk_cpu_8996_mux_set_parent(&cpuclk->clkr.hw, PLL_INDEX);
+ if (cnd->new_rate < DIV_2_THRESHOLD)
+ ret = clk_cpu_8996_mux_set_parent(&cpuclk->clkr.hw,
+ DIV_2_INDEX);
+ else
+ ret = clk_cpu_8996_mux_set_parent(&cpuclk->clkr.hw,
+ PLL_INDEX);
break;
default:
ret = 0;
@@ -304,6 +321,7 @@ int cpu_clk_notifier_cb(struct notifier_block *nb, unsigned long event,
.shift = 0,
.width = 2,
.pll = &pwrcl_pll.clkr.hw,
+ .pll_div_2 = &pwrcl_smux.clkr.hw,
.nb.notifier_call = cpu_clk_notifier_cb,
.clkr.hw.init = &(struct clk_init_data) {
.name = "pwrcl_pmux",
@@ -324,6 +342,7 @@ int cpu_clk_notifier_cb(struct notifier_block *nb, unsigned long event,
.shift = 0,
.width = 2,
.pll = &perfcl_pll.clkr.hw,
+ .pll_div_2 = &perfcl_smux.clkr.hw,
.nb.notifier_call = cpu_clk_notifier_cb,
.clkr.hw.init = &(struct clk_init_data) {
.name = "perfcl_pmux",
--
1.9.1

2018-05-15 09:20:29

by Ilia Lin

[permalink] [raw]

Subject: [PATCH v7 07/14] clk: qcom: Add ACD path to CPU clock driver for msm8996

The PMUX for each duplex allows for selection of ACD clock source.
The DVM (Dynamic Variation Monitor) will flag an error
when a voltage droop event is detected. This flagged error
enables ACD to provide a div-by-2 clock, sourced from the primary PLL.
The duplex will be provided the divided clock
until a pre-programmed delay has expired.

This change configures ACD during the probe and switches
the PMUXes to the ACD clock source.

Signed-off-by: Ilia Lin <[email protected]>
---
drivers/clk/qcom/clk-cpu-8996.c | 75 +++++++++++++++++++++++++++++++++++------
1 file changed, 65 insertions(+), 10 deletions(-)

diff --git a/drivers/clk/qcom/clk-cpu-8996.c b/drivers/clk/qcom/clk-cpu-8996.c
index 3ea0446..396285c 100644
--- a/drivers/clk/qcom/clk-cpu-8996.c
+++ b/drivers/clk/qcom/clk-cpu-8996.c
@@ -62,9 +62,11 @@
*/

#include <linux/clk.h>
+#include <linux/clk-provider.h>
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/regmap.h>
+#include <soc/qcom/kryo-l2-accessors.h>

#include "clk-alpha-pll.h"
#include "clk-regmap.h"
@@ -78,6 +80,11 @@ enum _pmux_input {
};

#define DIV_2_THRESHOLD 600000000
+#define PWRCL_REG_OFFSET 0x0
+#define PERFCL_REG_OFFSET 0x80000
+#define MUX_OFFSET 0x40
+#define ALT_PLL_OFFSET 0x100
+#define SSSCTL_OFFSET 0x160

static const u8 prim_pll_regs[PLL_OFF_MAX_REGS] = {
[PLL_OFF_L_VAL] = 0x04,
@@ -116,7 +123,7 @@ enum _pmux_input {
};

static struct clk_alpha_pll perfcl_pll = {
- .offset = 0x80000,
+ .offset = PERFCL_REG_OFFSET,
.regs = prim_pll_regs,
.flags = SUPPORTS_DYNAMIC_UPDATE | SUPPORTS_FSM_MODE,
.clkr.hw.init = &(struct clk_init_data){
@@ -128,7 +135,7 @@ enum _pmux_input {
};

static struct clk_alpha_pll pwrcl_pll = {
- .offset = 0x0,
+ .offset = PWRCL_REG_OFFSET,
.regs = prim_pll_regs,
.flags = SUPPORTS_DYNAMIC_UPDATE | SUPPORTS_FSM_MODE,
.clkr.hw.init = &(struct clk_init_data){
@@ -158,7 +165,7 @@ enum _pmux_input {
};

static struct clk_alpha_pll perfcl_alt_pll = {
- .offset = 0x80100,
+ .offset = PERFCL_REG_OFFSET + ALT_PLL_OFFSET,
.regs = alt_pll_regs,
.vco_table = alt_pll_vco_modes,
.num_vco = ARRAY_SIZE(alt_pll_vco_modes),
@@ -172,7 +179,7 @@ enum _pmux_input {
};

static struct clk_alpha_pll pwrcl_alt_pll = {
- .offset = 0x100,
+ .offset = PWRCL_REG_OFFSET + ALT_PLL_OFFSET,
.regs = alt_pll_regs,
.vco_table = alt_pll_vco_modes,
.num_vco = ARRAY_SIZE(alt_pll_vco_modes),
@@ -185,6 +192,9 @@ enum _pmux_input {
},
};

+void __iomem *base;
+static void qcom_cpu_clk_msm8996_acd_init(void __iomem *base);
+
/* Mux'es */

struct clk_cpu_8996_mux {
@@ -262,6 +272,7 @@ int cpu_clk_notifier_cb(struct notifier_block *nb, unsigned long event,
switch (event) {
case PRE_RATE_CHANGE:
ret = clk_cpu_8996_mux_set_parent(&cpuclk->clkr.hw, ALT_INDEX);
+ qcom_cpu_clk_msm8996_acd_init(base);
break;
case POST_RATE_CHANGE:
if (cnd->new_rate < DIV_2_THRESHOLD)
@@ -269,7 +280,7 @@ int cpu_clk_notifier_cb(struct notifier_block *nb, unsigned long event,
DIV_2_INDEX);
else
ret = clk_cpu_8996_mux_set_parent(&cpuclk->clkr.hw,
- PLL_INDEX);
+ ACD_INDEX);
break;
default:
ret = 0;
@@ -285,7 +296,7 @@ int cpu_clk_notifier_cb(struct notifier_block *nb, unsigned long event,
};

static struct clk_cpu_8996_mux pwrcl_smux = {
- .reg = 0x40,
+ .reg = PWRCL_REG_OFFSET + MUX_OFFSET,
.shift = 2,
.width = 2,
.clkr.hw.init = &(struct clk_init_data) {
@@ -301,7 +312,7 @@ int cpu_clk_notifier_cb(struct notifier_block *nb, unsigned long event,
};

static struct clk_cpu_8996_mux perfcl_smux = {
- .reg = 0x80040,
+ .reg = PERFCL_REG_OFFSET + MUX_OFFSET,
.shift = 2,
.width = 2,
.clkr.hw.init = &(struct clk_init_data) {
@@ -317,7 +328,7 @@ int cpu_clk_notifier_cb(struct notifier_block *nb, unsigned long event,
};

static struct clk_cpu_8996_mux pwrcl_pmux = {
- .reg = 0x40,
+ .reg = PWRCL_REG_OFFSET + MUX_OFFSET,
.shift = 0,
.width = 2,
.pll = &pwrcl_pll.clkr.hw,
@@ -338,7 +349,7 @@ int cpu_clk_notifier_cb(struct notifier_block *nb, unsigned long event,
};

static struct clk_cpu_8996_mux perfcl_pmux = {
- .reg = 0x80040,
+ .reg = PERFCL_REG_OFFSET + MUX_OFFSET,
.shift = 0,
.width = 2,
.pll = &perfcl_pll.clkr.hw,
@@ -402,6 +413,10 @@ struct clk_regmap *clks[] = {
clk_alpha_pll_configure(&perfcl_alt_pll, regmap, &altpll_config);
clk_alpha_pll_configure(&pwrcl_alt_pll, regmap, &altpll_config);

+ /* Enable alt PLLs */
+ clk_prepare_enable(pwrcl_alt_pll.clkr.hw.clk);
+ clk_prepare_enable(perfcl_alt_pll.clkr.hw.clk);
+
ret = clk_notifier_register(pwrcl_pmux.clkr.hw.clk, &pwrcl_pmux.nb);
if (ret)
return ret;
@@ -411,10 +426,48 @@ struct clk_regmap *clks[] = {
return ret;
}

+#define CPU_AFINITY_MASK 0xFFF
+#define PWRCL_CPU_REG_MASK 0x3
+#define PERFCL_CPU_REG_MASK 0x103
+
+#define L2ACDCR_REG 0x580ULL
+#define L2ACDTD_REG 0x581ULL
+#define L2ACDDVMRC_REG 0x584ULL
+#define L2ACDSSCR_REG 0x589ULL
+
+static DEFINE_SPINLOCK(acd_lock);
+
+static void qcom_cpu_clk_msm8996_acd_init(void __iomem *base)
+{
+ u64 hwid;
+ unsigned long flags;
+
+ spin_lock_irqsave(&acd_lock, flags);
+
+ hwid = read_cpuid_mpidr() & CPU_AFINITY_MASK;
+
+ kryo_l2_set_indirect_reg(L2ACDTD_REG, 0x00006A11);
+ kryo_l2_set_indirect_reg(L2ACDDVMRC_REG, 0x000E0F0F);
+ kryo_l2_set_indirect_reg(L2ACDSSCR_REG, 0x00000601);
+
+ if (PWRCL_CPU_REG_MASK == (hwid | PWRCL_CPU_REG_MASK)) {
+ writel(0xF, base + PWRCL_REG_OFFSET + SSSCTL_OFFSET);
+ wmb();
+ kryo_l2_set_indirect_reg(L2ACDCR_REG, 0x002C5FFD);
+ }
+
+ if (PERFCL_CPU_REG_MASK == (hwid | PERFCL_CPU_REG_MASK)) {
+ kryo_l2_set_indirect_reg(L2ACDCR_REG, 0x002C5FFD);
+ writel(0xF, base + PERFCL_REG_OFFSET + SSSCTL_OFFSET);
+ wmb();
+ }
+
+ spin_unlock_irqrestore(&acd_lock, flags);
+}
+
static int qcom_cpu_clk_msm8996_driver_probe(struct platform_device *pdev)
{
int ret;
- void __iomem *base;
struct resource *res;
struct regmap *regmap;
struct clk_hw_onecell_data *data;
@@ -438,6 +491,8 @@ static int qcom_cpu_clk_msm8996_driver_probe(struct platform_device *pdev)
if (ret)
return ret;

+ qcom_cpu_clk_msm8996_acd_init(base);
+
data->hws[0] = &pwrcl_pmux.clkr.hw;
data->hws[1] = &perfcl_pmux.clkr.hw;
data->num = 2;
--
1.9.1

2018-05-15 09:20:58

by Ilia Lin

[permalink] [raw]

Subject: [PATCH v7 02/14] clk: qcom: Make clk_alpha_pll_configure available to modules

From: Rajendra Nayak <[email protected]>

Allow clk_alpha_pll_configure to be called from loadable
kernel modules.

Signed-off-by: Rajendra Nayak <[email protected]>
Signed-off-by: Ilia Lin <[email protected]>
---
drivers/clk/qcom/clk-alpha-pll.c | 1 +
1 file changed, 1 insertion(+)

diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c
index 9722b70..57f2084 100644
--- a/drivers/clk/qcom/clk-alpha-pll.c
+++ b/drivers/clk/qcom/clk-alpha-pll.c
@@ -228,6 +228,7 @@ void clk_alpha_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
if (pll->flags & SUPPORTS_FSM_MODE)
qcom_pll_set_fsm_mode(regmap, PLL_MODE(pll), 6, 0);
}
+EXPORT_SYMBOL_GPL(clk_alpha_pll_configure);

static int clk_alpha_pll_hwfsm_enable(struct clk_hw *hw)
{
--
1.9.1

2018-05-15 09:21:09

by Ilia Lin

[permalink] [raw]

Subject: [PATCH v7 01/14] soc: qcom: Separate kryo l2 accessors from PMU driver

The driver provides kernel level API for other drivers
to access the MSM8996 L2 cache registers.
Separating the L2 access code from the PMU driver and
making it public to allow other drivers use it.
The accesses must be separated with a single spinlock,
maintained in this driver.

Signed-off-by: Ilia Lin <[email protected]>
---
drivers/perf/Kconfig | 1 +
drivers/perf/qcom_l2_pmu.c | 90 ++++++++++--------------------------
drivers/soc/qcom/Kconfig | 3 ++
drivers/soc/qcom/Makefile | 1 +
drivers/soc/qcom/kryo-l2-accessors.c | 65 ++++++++++++++++++++++++++
include/soc/qcom/kryo-l2-accessors.h | 21 +++++++++
6 files changed, 115 insertions(+), 66 deletions(-)
create mode 100644 drivers/soc/qcom/kryo-l2-accessors.c
create mode 100644 include/soc/qcom/kryo-l2-accessors.h

diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index 28bb5a0..561252a 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -69,6 +69,7 @@ config HISI_PMU
config QCOM_L2_PMU
bool "Qualcomm Technologies L2-cache PMU"
depends on ARCH_QCOM && ARM64 && ACPI
+ select QCOM_KRYO_L2_ACCESSORS
help
Provides support for the L2 cache performance monitor unit (PMU)
in Qualcomm Technologies processors.
diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c
index 842135c..cc31f51 100644
--- a/drivers/perf/qcom_l2_pmu.c
+++ b/drivers/perf/qcom_l2_pmu.c
@@ -31,6 +31,7 @@
#include <asm/barrier.h>
#include <asm/local64.h>
#include <asm/sysreg.h>
+#include <soc/qcom/kryo-l2-accessors.h>

#define MAX_L2_CTRS 9

@@ -87,8 +88,6 @@
#define L2_COUNTER_RELOAD BIT_ULL(31)
#define L2_CYCLE_COUNTER_RELOAD BIT_ULL(63)

-#define L2CPUSRSELR_EL1 sys_reg(3, 3, 15, 0, 6)
-#define L2CPUSRDR_EL1 sys_reg(3, 3, 15, 0, 7)

#define reg_idx(reg, i) (((i) * IA_L2_REG_OFFSET) + reg##_BASE)

@@ -107,48 +106,7 @@
#define L2_EVENT_STREX 0x421
#define L2_EVENT_CLREX 0x422

-static DEFINE_RAW_SPINLOCK(l2_access_lock);

-/**
- * set_l2_indirect_reg: write value to an L2 register
- * @reg: Address of L2 register.
- * @value: Value to be written to register.
- *
- * Use architecturally required barriers for ordering between system register
- * accesses
- */
-static void set_l2_indirect_reg(u64 reg, u64 val)
-{
- unsigned long flags;
-
- raw_spin_lock_irqsave(&l2_access_lock, flags);
- write_sysreg_s(reg, L2CPUSRSELR_EL1);
- isb();
- write_sysreg_s(val, L2CPUSRDR_EL1);
- isb();
- raw_spin_unlock_irqrestore(&l2_access_lock, flags);
-}
-
-/**
- * get_l2_indirect_reg: read an L2 register value
- * @reg: Address of L2 register.
- *
- * Use architecturally required barriers for ordering between system register
- * accesses
- */
-static u64 get_l2_indirect_reg(u64 reg)
-{
- u64 val;
- unsigned long flags;
-
- raw_spin_lock_irqsave(&l2_access_lock, flags);
- write_sysreg_s(reg, L2CPUSRSELR_EL1);
- isb();
- val = read_sysreg_s(L2CPUSRDR_EL1);
- raw_spin_unlock_irqrestore(&l2_access_lock, flags);
-
- return val;
-}

struct cluster_pmu;

@@ -219,28 +177,28 @@ static inline struct cluster_pmu *get_cluster_pmu(
static void cluster_pmu_reset(void)
{
/* Reset all counters */
- set_l2_indirect_reg(L2PMCR, L2PMCR_RESET_ALL);
- set_l2_indirect_reg(L2PMCNTENCLR, l2_counter_present_mask);
- set_l2_indirect_reg(L2PMINTENCLR, l2_counter_present_mask);
- set_l2_indirect_reg(L2PMOVSCLR, l2_counter_present_mask);
+ kryo_l2_set_indirect_reg(L2PMCR, L2PMCR_RESET_ALL);
+ kryo_l2_set_indirect_reg(L2PMCNTENCLR, l2_counter_present_mask);
+ kryo_l2_set_indirect_reg(L2PMINTENCLR, l2_counter_present_mask);
+ kryo_l2_set_indirect_reg(L2PMOVSCLR, l2_counter_present_mask);
}

static inline void cluster_pmu_enable(void)
{
- set_l2_indirect_reg(L2PMCR, L2PMCR_COUNTERS_ENABLE);
+ kryo_l2_set_indirect_reg(L2PMCR, L2PMCR_COUNTERS_ENABLE);
}

static inline void cluster_pmu_disable(void)
{
- set_l2_indirect_reg(L2PMCR, L2PMCR_COUNTERS_DISABLE);
+ kryo_l2_set_indirect_reg(L2PMCR, L2PMCR_COUNTERS_DISABLE);
}

static inline void cluster_pmu_counter_set_value(u32 idx, u64 value)
{
if (idx == l2_cycle_ctr_idx)
- set_l2_indirect_reg(L2PMCCNTR, value);
+ kryo_l2_set_indirect_reg(L2PMCCNTR, value);
else
- set_l2_indirect_reg(reg_idx(IA_L2PMXEVCNTR, idx), value);
+ kryo_l2_set_indirect_reg(reg_idx(IA_L2PMXEVCNTR, idx), value);
}

static inline u64 cluster_pmu_counter_get_value(u32 idx)
@@ -248,46 +206,46 @@ static inline u64 cluster_pmu_counter_get_value(u32 idx)
u64 value;

if (idx == l2_cycle_ctr_idx)
- value = get_l2_indirect_reg(L2PMCCNTR);
+ value = kryo_l2_get_indirect_reg(L2PMCCNTR);
else
- value = get_l2_indirect_reg(reg_idx(IA_L2PMXEVCNTR, idx));
+ value = kryo_l2_get_indirect_reg(reg_idx(IA_L2PMXEVCNTR, idx));

return value;
}

static inline void cluster_pmu_counter_enable(u32 idx)
{
- set_l2_indirect_reg(L2PMCNTENSET, idx_to_reg_bit(idx));
+ kryo_l2_set_indirect_reg(L2PMCNTENSET, idx_to_reg_bit(idx));
}

static inline void cluster_pmu_counter_disable(u32 idx)
{
- set_l2_indirect_reg(L2PMCNTENCLR, idx_to_reg_bit(idx));
+ kryo_l2_set_indirect_reg(L2PMCNTENCLR, idx_to_reg_bit(idx));
}

static inline void cluster_pmu_counter_enable_interrupt(u32 idx)
{
- set_l2_indirect_reg(L2PMINTENSET, idx_to_reg_bit(idx));
+ kryo_l2_set_indirect_reg(L2PMINTENSET, idx_to_reg_bit(idx));
}

static inline void cluster_pmu_counter_disable_interrupt(u32 idx)
{
- set_l2_indirect_reg(L2PMINTENCLR, idx_to_reg_bit(idx));
+ kryo_l2_set_indirect_reg(L2PMINTENCLR, idx_to_reg_bit(idx));
}

static inline void cluster_pmu_set_evccntcr(u32 val)
{
- set_l2_indirect_reg(L2PMCCNTCR, val);
+ kryo_l2_set_indirect_reg(L2PMCCNTCR, val);
}

static inline void cluster_pmu_set_evcntcr(u32 ctr, u32 val)
{
- set_l2_indirect_reg(reg_idx(IA_L2PMXEVCNTCR, ctr), val);
+ kryo_l2_set_indirect_reg(reg_idx(IA_L2PMXEVCNTCR, ctr), val);
}

static inline void cluster_pmu_set_evtyper(u32 ctr, u32 val)
{
- set_l2_indirect_reg(reg_idx(IA_L2PMXEVTYPER, ctr), val);
+ kryo_l2_set_indirect_reg(reg_idx(IA_L2PMXEVTYPER, ctr), val);
}

static void cluster_pmu_set_resr(struct cluster_pmu *cluster,
@@ -303,11 +261,11 @@ static void cluster_pmu_set_resr(struct cluster_pmu *cluster,

spin_lock_irqsave(&cluster->pmu_lock, flags);

- resr_val = get_l2_indirect_reg(L2PMRESR);
+ resr_val = kryo_l2_get_indirect_reg(L2PMRESR);
resr_val &= ~(L2PMRESR_GROUP_MASK << shift);
resr_val |= field;
resr_val |= L2PMRESR_EN;
- set_l2_indirect_reg(L2PMRESR, resr_val);
+ kryo_l2_set_indirect_reg(L2PMRESR, resr_val);

spin_unlock_irqrestore(&cluster->pmu_lock, flags);
}
@@ -323,14 +281,14 @@ static inline void cluster_pmu_set_evfilter_sys_mode(u32 ctr)
L2PMXEVFILTER_ORGFILTER_IDINDEP |
L2PMXEVFILTER_ORGFILTER_ALL;

- set_l2_indirect_reg(reg_idx(IA_L2PMXEVFILTER, ctr), val);
+ kryo_l2_set_indirect_reg(reg_idx(IA_L2PMXEVFILTER, ctr), val);
}

static inline u32 cluster_pmu_getreset_ovsr(void)
{
- u32 result = get_l2_indirect_reg(L2PMOVSSET);
+ u32 result = kryo_l2_get_indirect_reg(L2PMOVSSET);

- set_l2_indirect_reg(L2PMOVSCLR, result);
+ kryo_l2_set_indirect_reg(L2PMOVSCLR, result);
return result;
}

@@ -783,7 +741,7 @@ static int get_num_counters(void)
{
int val;

- val = get_l2_indirect_reg(L2PMCR);
+ val = kryo_l2_get_indirect_reg(L2PMCR);

/*
* Read number of counters from L2PMCR and add 1
diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
index 7093fe7..0567dff 100644
--- a/drivers/soc/qcom/Kconfig
+++ b/drivers/soc/qcom/Kconfig
@@ -39,6 +39,9 @@ config QCOM_GSBI
functions for connecting the underlying serial UART, SPI, and I2C
devices to the output pins.

+config QCOM_KRYO_L2_ACCESSORS
+ bool
+
config QCOM_MDT_LOADER
tristate
select QCOM_SCM
diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile
index cbf414c..e4d3f5a 100644
--- a/drivers/soc/qcom/Makefile
+++ b/drivers/soc/qcom/Makefile
@@ -14,3 +14,4 @@ obj-$(CONFIG_QCOM_SMEM_STATE) += smem_state.o
obj-$(CONFIG_QCOM_SMP2P) += smp2p.o
obj-$(CONFIG_QCOM_SMSM) += smsm.o
obj-$(CONFIG_QCOM_WCNSS_CTRL) += wcnss_ctrl.o
+obj-$(CONFIG_QCOM_KRYO_L2_ACCESSORS) += kryo-l2-accessors.o
diff --git a/drivers/soc/qcom/kryo-l2-accessors.c b/drivers/soc/qcom/kryo-l2-accessors.c
new file mode 100644
index 0000000..d35a860
--- /dev/null
+++ b/drivers/soc/qcom/kryo-l2-accessors.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2014-2015, 2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/spinlock.h>
+#include <asm/sysreg.h>
+#include <soc/qcom/kryo-l2-accessors.h>
+
+#define L2CPUSRSELR_EL1 sys_reg(3, 3, 15, 0, 6)
+#define L2CPUSRDR_EL1 sys_reg(3, 3, 15, 0, 7)
+
+static DEFINE_RAW_SPINLOCK(l2_access_lock);
+
+/**
+ * kryo_l2_set_indirect_reg() - write value to an L2 register
+ * @reg: Address of L2 register.
+ * @value: Value to be written to register.
+ *
+ * Use architecturally required barriers for ordering between system register
+ * accesses, and system registers with respect to device memory
+ */
+void kryo_l2_set_indirect_reg(u64 reg, u64 val)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&l2_access_lock, flags);
+ write_sysreg_s(reg, L2CPUSRSELR_EL1);
+ isb();
+ write_sysreg_s(val, L2CPUSRDR_EL1);
+ isb();
+ raw_spin_unlock_irqrestore(&l2_access_lock, flags);
+}
+EXPORT_SYMBOL(kryo_l2_set_indirect_reg);
+
+/**
+ * kryo_l2_get_indirect_reg() - read an L2 register value
+ * @reg: Address of L2 register.
+ *
+ * Use architecturally required barriers for ordering between system register
+ * accesses, and system registers with respect to device memory
+ */
+u64 kryo_l2_get_indirect_reg(u64 reg)
+{
+ u64 val;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&l2_access_lock, flags);
+ write_sysreg_s(reg, L2CPUSRSELR_EL1);
+ isb();
+ val = read_sysreg_s(L2CPUSRDR_EL1);
+ raw_spin_unlock_irqrestore(&l2_access_lock, flags);
+
+ return val;
+}
+EXPORT_SYMBOL(kryo_l2_get_indirect_reg);
diff --git a/include/soc/qcom/kryo-l2-accessors.h b/include/soc/qcom/kryo-l2-accessors.h
new file mode 100644
index 0000000..0840e87
--- /dev/null
+++ b/include/soc/qcom/kryo-l2-accessors.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __SOC_ARCH_QCOM_KRYO_L2_ACCESSORS_H
+#define __SOC_ARCH_QCOM_KRYO_L2_ACCESSORS_H
+
+void kryo_l2_set_indirect_reg(u64 reg, u64 val);
+u64 kryo_l2_get_indirect_reg(u64 reg);
+
+#endif
--
1.9.1

2018-05-15 09:21:21

by Ilia Lin

[permalink] [raw]

2018-05-17 07:51:34

by Ilia Lin

[permalink] [raw]

Subject: RE: [PATCH v7 12/14] cpufreq: Add Kryo CPU scaling driver

> -----Original Message-----
> From: Viresh Kumar <[email protected]>
> Sent: Wednesday, May 16, 2018 17:12
> To: Amit Kucheria <[email protected]>
> Cc: Ilia Lin <[email protected]>; Michael Turquette
> <[email protected]>; [email protected]; Rob Herring
> <[email protected]>; Mark Rutland <[email protected]>; [email protected];
> [email protected]; [email protected]; Andy Gross
> <[email protected]>; David Brown <[email protected]>;
> [email protected]; [email protected]; Rafael J. Wysocki
> <[email protected]>; [email protected];
> [email protected]; LKML <[email protected]>; Linux
> PM list <[email protected]>; [email protected]; linux-
> [email protected]; lakml <[email protected]>;
> Rajendra Nayak <[email protected]>; [email protected];
> [email protected]; [email protected]
> Subject: Re: [PATCH v7 12/14] cpufreq: Add Kryo CPU scaling driver
>
> On 16-05-18, 16:12, Amit Kucheria wrote:
> > > + ret = PTR_ERR_OR_ZERO(opp_temp =
> > > +
> dev_pm_opp_set_supported_hw(cpu_dev,&versions,1));
> > > + if (0 > ret)
> >
> > Any particular reason to prefer this over (ret < 0) that is generally
> > used? I've seen it used to avoid the == vs. = typos, but not for other
> > comparisons.
> >
> > Suggest sticking to what is commonly used i.e. ret < 0.
> >
> > > + goto free_opp;
> > > +
> > > + cpu_dev = get_cpu_device(GOLD_LEAD);
> >
> > Error check cpu_dev here?
> >
> > > + ret = PTR_ERR_OR_ZERO(opp_temp =
> > > +
> dev_pm_opp_set_supported_hw(cpu_dev,&versions,1));
> > > + if (0 > ret)
> > > + goto free_opp;
>
> The goto here is wrong

If we are here, then the first dev_pm_opp_set_supported_hw() succeeded. And
should be deallocated before exit with error.

>
> > > +
> > > +
> > > + ret =
> PTR_ERR_OR_ZERO(platform_device_register_simple("cpufreq-dt",
> > > + -1,
> > > + NULL, 0));
> > > +
> > > + if (0 == ret)
> > > + return 0;
> > > +
> > > +free_opp:
> > > + dev_pm_opp_put_supported_hw(opp_temp);
> >
> > This is not needed because dev_pm_opp_set_supported_hw will free
> > memory in case of failure. This call in only needed in case of a
> > successful get.
>
> But this is still required for the case where platform device registration
fails.
>
> --
> viresh

2018-05-17 08:22:42

by Ilia Lin

[permalink] [raw]

Subject: RE: [PATCH v7 12/14] cpufreq: Add Kryo CPU scaling driver

> -----Original Message-----
> From: [email protected] <[email protected]>
> Sent: Thursday, May 17, 2018 10:51
> To: 'Viresh Kumar' <[email protected]>; 'Amit Kucheria'
> <[email protected]>
> Cc: 'Michael Turquette' <[email protected]>; '[email protected]'
> <[email protected]>; 'Rob Herring' <[email protected]>; 'Mark Rutland'
> <[email protected]>; '[email protected]' <[email protected]>;
> '[email protected]' <[email protected]>; '[email protected]'
> <[email protected]>; 'Andy Gross' <[email protected]>; 'David Brown'
> <[email protected]>; '[email protected]'
> <[email protected]>; '[email protected]'
> <[email protected]>; 'Rafael J. Wysocki' <[email protected]>; 'linux-
> [email protected]' <[email protected]>;
> '[email protected]' <[email protected]>; 'LKML' <linux-
> [email protected]>; 'Linux PM list' <[email protected]>;
'linux-
> [email protected]' <[email protected]>; 'linux-
> [email protected]' <[email protected]>; 'lakml' <linux-arm-
> [email protected]>; 'Rajendra Nayak' <[email protected]>;
> '[email protected]' <[email protected]>;
> '[email protected]' <[email protected]>;
> '[email protected]' <[email protected]>
> Subject: RE: [PATCH v7 12/14] cpufreq: Add Kryo CPU scaling driver
>
>
>
> > -----Original Message-----
> > From: Viresh Kumar <[email protected]>
> > Sent: Wednesday, May 16, 2018 17:12
> > To: Amit Kucheria <[email protected]>
> > Cc: Ilia Lin <[email protected]>; Michael Turquette
> > <[email protected]>; [email protected]; Rob Herring
> > <[email protected]>; Mark Rutland <[email protected]>; [email protected];
> > [email protected]; [email protected]; Andy Gross
> > <[email protected]>; David Brown <[email protected]>;
> > [email protected]; [email protected]; Rafael J. Wysocki
> > <[email protected]>; [email protected];
> > [email protected]; LKML <[email protected]>; Linux
> > PM list <[email protected]>; [email protected];
> > linux- [email protected]; lakml
> > <[email protected]>;
> > Rajendra Nayak <[email protected]>; [email protected];
> > [email protected]; [email protected]
> > Subject: Re: [PATCH v7 12/14] cpufreq: Add Kryo CPU scaling driver
> >
> > On 16-05-18, 16:12, Amit Kucheria wrote:
> > > > + ret = PTR_ERR_OR_ZERO(opp_temp =
> > > > +
> > dev_pm_opp_set_supported_hw(cpu_dev,&versions,1));
> > > > + if (0 > ret)
> > >
> > > Any particular reason to prefer this over (ret < 0) that is
> > > generally used? I've seen it used to avoid the == vs. = typos, but
> > > not for other comparisons.
> > >
> > > Suggest sticking to what is commonly used i.e. ret < 0.
> > >
> > > > + goto free_opp;
> > > > +
> > > > + cpu_dev = get_cpu_device(GOLD_LEAD);
> > >
> > > Error check cpu_dev here?
> > >
> > > > + ret = PTR_ERR_OR_ZERO(opp_temp =
> > > > +
> > dev_pm_opp_set_supported_hw(cpu_dev,&versions,1));
> > > > + if (0 > ret)
> > > > + goto free_opp;
> >
> > The goto here is wrong
>
> If we are here, then the first dev_pm_opp_set_supported_hw() succeeded.
> And should be deallocated before exit with error.

My bad. Got you.

>
> >
> > > > +
> > > > +
> > > > + ret =
> > PTR_ERR_OR_ZERO(platform_device_register_simple("cpufreq-dt",
> > > > + -1,
> > > > + NULL, 0));
> > > > +
> > > > + if (0 == ret)
> > > > + return 0;
> > > > +
> > > > +free_opp:
> > > > + dev_pm_opp_put_supported_hw(opp_temp);
> > >
> > > This is not needed because dev_pm_opp_set_supported_hw will free
> > > memory in case of failure. This call in only needed in case of a
> > > successful get.
> >
> > But this is still required for the case where platform device
registration fails.
> >
> > --
> > viresh

2018-05-17 16:32:43

by kernel test robot

[permalink] [raw]

Subject: Re: [PATCH v7 03/14] clk: qcom: Add CPU clock driver for msm8996

Attachments:

(No filename) (1.45 kB)
.config.gz (51.73 kB)
Download all attachments

2018-05-17 16:52:42

by kernel test robot

[permalink] [raw]

Subject: Re: [PATCH v7 03/14] clk: qcom: Add CPU clock driver for msm8996

Hi Ilia,

Thank you for the patch! Perhaps something to improve:

[auto build test WARNING on robh/for-next]
[also build test WARNING on v4.17-rc5]
[cannot apply to clk/clk-next next-20180517]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url: https://github.com/0day-ci/linux/commits/Ilia-Lin/CPU-scaling-support-for-msm8996/20180516-064721
base: https://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git for-next
reproduce:
# apt-get install sparse
make ARCH=x86_64 allmodconfig
make C=1 CF=-D__CHECK_ENDIAN__

sparse warnings: (new ones prefixed by >>)

>> drivers/clk/qcom/clk-cpu-8996.c:142:9: sparse: constant 2150400000 is so big it is long
>> drivers/clk/qcom/clk-cpu-8996.c:239:22: sparse: symbol 'clk_cpu_8996_mux_ops' was not declared. Should it be static?
drivers/clk/qcom/clk-cpu-8996.c:324:19: sparse: symbol 'clks' was not declared. Should it be static?

vim +142 drivers/clk/qcom/clk-cpu-8996.c

137
138 static const struct pll_vco alt_pll_vco_modes[] = {
139 VCO(3, 250000000, 500000000),
140 VCO(2, 500000000, 750000000),
141 VCO(1, 750000000, 1000000000),
> 142 VCO(0, 1000000000, 2150400000),
143 };
144
145 static const struct alpha_pll_config altpll_config = {
146 .l = 16,
147 .vco_val = 0x3 << 20,
148 .vco_mask = 0x3 << 20,
149 .config_ctl_val = 0x4001051b,
150 .post_div_mask = 0x3 << 8,
151 .post_div_val = 0x1,
152 .main_output_mask = BIT(0),
153 .early_output_mask = BIT(3),
154 };
155
156 static struct clk_alpha_pll perfcl_alt_pll = {
157 .offset = 0x80100,
158 .regs = alt_pll_regs,
159 .vco_table = alt_pll_vco_modes,
160 .num_vco = ARRAY_SIZE(alt_pll_vco_modes),
161 .flags = SUPPORTS_OFFLINE_REQ | SUPPORTS_FSM_MODE,
162 .clkr.hw.init = &(struct clk_init_data) {
163 .name = "perfcl_alt_pll",
164 .parent_names = (const char *[]){ "xo" },
165 .num_parents = 1,
166 .ops = &clk_alpha_pll_hwfsm_ops,
167 },
168 };
169
170 static struct clk_alpha_pll pwrcl_alt_pll = {
171 .offset = 0x100,
172 .regs = alt_pll_regs,
173 .vco_table = alt_pll_vco_modes,
174 .num_vco = ARRAY_SIZE(alt_pll_vco_modes),
175 .flags = SUPPORTS_OFFLINE_REQ | SUPPORTS_FSM_MODE,
176 .clkr.hw.init = &(struct clk_init_data) {
177 .name = "pwrcl_alt_pll",
178 .parent_names = (const char *[]){ "xo" },
179 .num_parents = 1,
180 .ops = &clk_alpha_pll_hwfsm_ops,
181 },
182 };
183
184 /* Mux'es */
185
186 struct clk_cpu_8996_mux {
187 u32 reg;
188 u8 shift;
189 u8 width;
190 struct clk_hw *pll;
191 struct clk_regmap clkr;
192 };
193
194 static inline
195 struct clk_cpu_8996_mux *to_clk_cpu_8996_mux_hw(struct clk_hw *hw)
196 {
197 return container_of(to_clk_regmap(hw), struct clk_cpu_8996_mux, clkr);
198 }
199
200 static u8 clk_cpu_8996_mux_get_parent(struct clk_hw *hw)
201 {
202 u32 val;
203 struct clk_regmap *clkr = to_clk_regmap(hw);
204 struct clk_cpu_8996_mux *cpuclk = to_clk_cpu_8996_mux_hw(hw);
205 u32 mask = (u32)GENMASK(cpuclk->width - 1, 0);
206
207 regmap_read(clkr->regmap, cpuclk->reg, &val);
208 val >>= (u32)(cpuclk->shift);
209
210 return (u8)(val & mask);
211 }
212
213 static int clk_cpu_8996_mux_set_parent(struct clk_hw *hw, u8 index)
214 {
215 u32 val;
216 struct clk_regmap *clkr = to_clk_regmap(hw);
217 struct clk_cpu_8996_mux *cpuclk = to_clk_cpu_8996_mux_hw(hw);
218 unsigned int mask = GENMASK(cpuclk->width + cpuclk->shift - 1,
219 cpuclk->shift);
220
221 val = (u32)index;
222 val <<= (u32)(cpuclk->shift);
223
224 return regmap_update_bits(clkr->regmap, cpuclk->reg, mask, val);
225 }
226
227 static int
228 clk_cpu_8996_mux_determine_rate(struct clk_hw *hw, struct clk_rate_request *req)
229 {
230 struct clk_cpu_8996_mux *cpuclk = to_clk_cpu_8996_mux_hw(hw);
231 struct clk_hw *parent = cpuclk->pll;
232
233 req->best_parent_rate = clk_hw_round_rate(parent, req->rate);
234 req->best_parent_hw = parent;
235
236 return 0;
237 }
238
> 239 const struct clk_ops clk_cpu_8996_mux_ops = {
240 .set_parent = clk_cpu_8996_mux_set_parent,
241 .get_parent = clk_cpu_8996_mux_get_parent,
242 .determine_rate = clk_cpu_8996_mux_determine_rate,
243 };
244

---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation