Introduce SMP support for MIPS Creator CI20, which is
based on Ingenic JZ4780 SoC.
Forward port smp support from kernel 3.18.3 of CI20_linux
to upstream kernel 5.5.
Tested-by: H. Nikolaus Schaller <[email protected]>
Tested-by: Paul Boddie <[email protected]>
Signed-off-by: 周琰杰 (Zhou Yanjie) <[email protected]>
---
Notes:
v1->v2:
1.Remove unnecessary "plat_irq_dispatch(void)" in irq-ingenic.c.
2.Add a timeout check for "jz4780_boot_secondary()" to avoid a dead loop.
3.Replace hard code in smp.c with macro.
v2->v3:
1.Remove unnecessary "extern void (*r4k_blast_dcache)(void)" in smp.c.
2.Use "for_each_of_cpu_node" instead "for_each_compatible_node" in smp.c.
3.Use "of_cpu_node_to_id" instead "of_property_read_u32_index" in smp.c.
4.Move LCR related operations to jz4780-cgu.c.
v3->v4:
Rebase on top of kernel 5.6-rc1.
arch/mips/include/asm/mach-jz4740/jz4780-smp.h | 91 ++++++++
arch/mips/jz4740/Kconfig | 3 +
arch/mips/jz4740/Makefile | 5 +
arch/mips/jz4740/prom.c | 4 +
arch/mips/jz4740/smp-entry.S | 57 +++++
arch/mips/jz4740/smp.c | 286 +++++++++++++++++++++++++
arch/mips/kernel/idle.c | 14 +-
drivers/clk/ingenic/jz4780-cgu.c | 58 ++++-
8 files changed, 512 insertions(+), 6 deletions(-)
create mode 100644 arch/mips/include/asm/mach-jz4740/jz4780-smp.h
create mode 100644 arch/mips/jz4740/smp-entry.S
create mode 100644 arch/mips/jz4740/smp.c
diff --git a/arch/mips/include/asm/mach-jz4740/jz4780-smp.h b/arch/mips/include/asm/mach-jz4740/jz4780-smp.h
new file mode 100644
index 00000000..3f592ce
--- /dev/null
+++ b/arch/mips/include/asm/mach-jz4740/jz4780-smp.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2013, Paul Burton <[email protected]>
+ * JZ4780 SMP definitions
+ */
+
+#ifndef __MIPS_ASM_MACH_JZ4740_JZ4780_SMP_H__
+#define __MIPS_ASM_MACH_JZ4740_JZ4780_SMP_H__
+
+#define read_c0_corectrl() __read_32bit_c0_register($12, 2)
+#define write_c0_corectrl(val) __write_32bit_c0_register($12, 2, val)
+
+#define read_c0_corestatus() __read_32bit_c0_register($12, 3)
+#define write_c0_corestatus(val) __write_32bit_c0_register($12, 3, val)
+
+#define read_c0_reim() __read_32bit_c0_register($12, 4)
+#define write_c0_reim(val) __write_32bit_c0_register($12, 4, val)
+
+#define read_c0_mailbox0() __read_32bit_c0_register($20, 0)
+#define write_c0_mailbox0(val) __write_32bit_c0_register($20, 0, val)
+
+#define read_c0_mailbox1() __read_32bit_c0_register($20, 1)
+#define write_c0_mailbox1(val) __write_32bit_c0_register($20, 1, val)
+
+#define smp_clr_pending(mask) do { \
+ unsigned int stat; \
+ stat = read_c0_corestatus(); \
+ stat &= ~((mask) & 0xff); \
+ write_c0_corestatus(stat); \
+ } while (0)
+
+/*
+ * Core Control register
+ */
+#define CORECTRL_SLEEP1M_SHIFT 17
+#define CORECTRL_SLEEP1M (_ULCAST_(0x1) << CORECTRL_SLEEP1M_SHIFT)
+#define CORECTRL_SLEEP0M_SHIFT 16
+#define CORECTRL_SLEEP0M (_ULCAST_(0x1) << CORECTRL_SLEEP0M_SHIFT)
+#define CORECTRL_RPC1_SHIFT 9
+#define CORECTRL_RPC1 (_ULCAST_(0x1) << CORECTRL_RPC1_SHIFT)
+#define CORECTRL_RPC0_SHIFT 8
+#define CORECTRL_RPC0 (_ULCAST_(0x1) << CORECTRL_RPC0_SHIFT)
+#define CORECTRL_SWRST1_SHIFT 1
+#define CORECTRL_SWRST1 (_ULCAST_(0x1) << CORECTRL_SWRST1_SHIFT)
+#define CORECTRL_SWRST0_SHIFT 0
+#define CORECTRL_SWRST0 (_ULCAST_(0x1) << CORECTRL_SWRST0_SHIFT)
+
+/*
+ * Core Status register
+ */
+#define CORESTATUS_SLEEP1_SHIFT 17
+#define CORESTATUS_SLEEP1 (_ULCAST_(0x1) << CORESTATUS_SLEEP1_SHIFT)
+#define CORESTATUS_SLEEP0_SHIFT 16
+#define CORESTATUS_SLEEP0 (_ULCAST_(0x1) << CORESTATUS_SLEEP0_SHIFT)
+#define CORESTATUS_IRQ1P_SHIFT 9
+#define CORESTATUS_IRQ1P (_ULCAST_(0x1) << CORESTATUS_IRQ1P_SHIFT)
+#define CORESTATUS_IRQ0P_SHIFT 8
+#define CORESTATUS_IRQ0P (_ULCAST_(0x1) << CORESTATUS_IRQ8P_SHIFT)
+#define CORESTATUS_MIRQ1P_SHIFT 1
+#define CORESTATUS_MIRQ1P (_ULCAST_(0x1) << CORESTATUS_MIRQ1P_SHIFT)
+#define CORESTATUS_MIRQ0P_SHIFT 0
+#define CORESTATUS_MIRQ0P (_ULCAST_(0x1) << CORESTATUS_MIRQ0P_SHIFT)
+
+/*
+ * Reset Entry & IRQ Mask register
+ */
+#define REIM_ENTRY_SHIFT 16
+#define REIM_ENTRY (_ULCAST_(0xffff) << REIM_ENTRY_SHIFT)
+#define REIM_IRQ1M_SHIFT 9
+#define REIM_IRQ1M (_ULCAST_(0x1) << REIM_IRQ1M_SHIFT)
+#define REIM_IRQ0M_SHIFT 8
+#define REIM_IRQ0M (_ULCAST_(0x1) << REIM_IRQ0M_SHIFT)
+#define REIM_MBOXIRQ1M_SHIFT 1
+#define REIM_MBOXIRQ1M (_ULCAST_(0x1) << REIM_MBOXIRQ1M_SHIFT)
+#define REIM_MBOXIRQ0M_SHIFT 0
+#define REIM_MBOXIRQ0M (_ULCAST_(0x1) << REIM_MBOXIRQ0M_SHIFT)
+
+#ifdef CONFIG_SMP
+
+extern void jz4780_smp_wait_irqoff(void);
+
+extern void jz4780_smp_init(void);
+extern void jz4780_secondary_cpu_entry(void);
+
+#else /* !CONFIG_SMP */
+
+static inline void jz4780_smp_init(void) { }
+
+#endif /* !CONFIG_SMP */
+
+#endif /* __MIPS_ASM_MACH_JZ4740_JZ4780_SMP_H__ */
diff --git a/arch/mips/jz4740/Kconfig b/arch/mips/jz4740/Kconfig
index 412d2fa..0239597 100644
--- a/arch/mips/jz4740/Kconfig
+++ b/arch/mips/jz4740/Kconfig
@@ -34,9 +34,12 @@ config MACH_JZ4770
config MACH_JZ4780
bool
+ select GENERIC_CLOCKEVENTS_BROADCAST if SMP
select MIPS_CPU_SCACHE
+ select NR_CPUS_DEFAULT_2
select SYS_HAS_CPU_MIPS32_R2
select SYS_SUPPORTS_HIGHMEM
+ select SYS_SUPPORTS_SMP
config MACH_X1000
bool
diff --git a/arch/mips/jz4740/Makefile b/arch/mips/jz4740/Makefile
index 6de14c0..0a0f024 100644
--- a/arch/mips/jz4740/Makefile
+++ b/arch/mips/jz4740/Makefile
@@ -12,3 +12,8 @@ CFLAGS_setup.o = -I$(src)/../../../scripts/dtc/libfdt
# PM support
obj-$(CONFIG_PM) += pm.o
+
+# SMP support
+
+obj-$(CONFIG_SMP) += smp.o
+obj-$(CONFIG_SMP) += smp-entry.o
diff --git a/arch/mips/jz4740/prom.c b/arch/mips/jz4740/prom.c
index ff4555c..a79159e 100644
--- a/arch/mips/jz4740/prom.c
+++ b/arch/mips/jz4740/prom.c
@@ -8,10 +8,14 @@
#include <asm/bootinfo.h>
#include <asm/fw/fw.h>
+#include <asm/mach-jz4740/jz4780-smp.h>
void __init prom_init(void)
{
fw_init_cmdline();
+#if defined(CONFIG_MACH_JZ4780) && defined(CONFIG_SMP)
+ jz4780_smp_init();
+#endif
}
void __init prom_free_prom_memory(void)
diff --git a/arch/mips/jz4740/smp-entry.S b/arch/mips/jz4740/smp-entry.S
new file mode 100644
index 00000000..20049a3
--- /dev/null
+++ b/arch/mips/jz4740/smp-entry.S
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2013, Paul Burton <[email protected]>
+ * JZ4780 SMP entry point
+ */
+
+#include <asm/addrspace.h>
+#include <asm/asm.h>
+#include <asm/asmmacro.h>
+#include <asm/cacheops.h>
+#include <asm/mipsregs.h>
+
+#define CACHE_SIZE (32 * 1024)
+#define CACHE_LINESIZE 32
+
+.extern jz4780_cpu_entry_sp
+.extern jz4780_cpu_entry_gp
+
+.section .text.smp-entry
+.balign 0x10000
+.set noreorder
+LEAF(jz4780_secondary_cpu_entry)
+ mtc0 zero, CP0_CAUSE
+
+ li t0, ST0_CU0
+ mtc0 t0, CP0_STATUS
+
+ /* cache setup */
+ li t0, KSEG0
+ ori t1, t0, CACHE_SIZE
+ mtc0 zero, CP0_TAGLO, 0
+1: cache Index_Store_Tag_I, 0(t0)
+ cache Index_Store_Tag_D, 0(t0)
+ bne t0, t1, 1b
+ addiu t0, t0, CACHE_LINESIZE
+
+ /* kseg0 cache attribute */
+ mfc0 t0, CP0_CONFIG, 0
+ ori t0, t0, CONF_CM_CACHABLE_NONCOHERENT
+ mtc0 t0, CP0_CONFIG, 0
+
+ /* pagemask */
+ mtc0 zero, CP0_PAGEMASK, 0
+
+ /* retrieve sp */
+ la t0, jz4780_cpu_entry_sp
+ lw sp, 0(t0)
+
+ /* retrieve gp */
+ la t0, jz4780_cpu_entry_gp
+ lw gp, 0(t0)
+
+ /* jump to the kernel in kseg0 */
+ la t0, smp_bootstrap
+ jr t0
+ nop
+ END(jz4780_secondary_cpu_entry)
diff --git a/arch/mips/jz4740/smp.c b/arch/mips/jz4740/smp.c
new file mode 100644
index 00000000..19b75c2
--- /dev/null
+++ b/arch/mips/jz4740/smp.c
@@ -0,0 +1,286 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2013, Paul Burton <[email protected]>
+ * JZ4780 SMP
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/of.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/smp.h>
+#include <linux/tick.h>
+#include <asm/mach-jz4740/jz4780-smp.h>
+#include <asm/r4kcache.h>
+#include <asm/smp-ops.h>
+
+static struct clk *cpu_clock_gates[CONFIG_NR_CPUS] = { NULL };
+
+u32 jz4780_cpu_entry_sp;
+u32 jz4780_cpu_entry_gp;
+
+static struct cpumask cpu_running;
+
+static DEFINE_SPINLOCK(smp_lock);
+
+/*
+ * The Ingenic jz4780 SMP variant has to write back dirty cache lines before
+ * executing wait. The CPU & cache clock will be gated until we return from
+ * the wait, and if another core attempts to access data from our data cache
+ * during this time then it will lock up.
+ */
+void jz4780_smp_wait_irqoff(void)
+{
+ unsigned long pending = read_c0_cause() & read_c0_status() & CAUSEF_IP;
+
+ /*
+ * Going to idle has a significant overhead due to the cache flush so
+ * try to avoid it if we'll immediately be woken again due to an IRQ.
+ */
+ if (!need_resched() && !pending) {
+ r4k_blast_dcache();
+
+ __asm__(
+ " .set push \n"
+ " .set mips3 \n"
+ " sync \n"
+ " wait \n"
+ " .set pop \n");
+ }
+
+ local_irq_enable();
+}
+
+static irqreturn_t mbox_handler(int irq, void *dev_id)
+{
+ int cpu = smp_processor_id();
+ u32 action, status;
+
+ spin_lock(&smp_lock);
+
+ switch (cpu) {
+ case 0:
+ action = read_c0_mailbox0();
+ write_c0_mailbox0(0);
+ break;
+ case 1:
+ action = read_c0_mailbox1();
+ write_c0_mailbox1(0);
+ break;
+ default:
+ panic("unhandled cpu %d!", cpu);
+ }
+
+ /* clear pending mailbox interrupt */
+ status = read_c0_corestatus();
+ status &= ~(CORESTATUS_MIRQ0P << cpu);
+ write_c0_corestatus(status);
+
+ spin_unlock(&smp_lock);
+
+ if (action & SMP_RESCHEDULE_YOURSELF)
+ scheduler_ipi();
+ if (action & SMP_CALL_FUNCTION)
+ generic_smp_call_function_interrupt();
+
+ return IRQ_HANDLED;
+}
+
+static struct irqaction mbox_action = {
+ .handler = mbox_handler,
+ .name = "core mailbox",
+ .flags = IRQF_PERCPU | IRQF_NO_THREAD,
+};
+
+static void jz4780_smp_setup(void)
+{
+ u32 addr, reim;
+ int cpu;
+
+ reim = read_c0_reim();
+
+ for (cpu = 0; cpu < NR_CPUS; cpu++) {
+ __cpu_number_map[cpu] = cpu;
+ __cpu_logical_map[cpu] = cpu;
+ set_cpu_possible(cpu, true);
+ }
+
+ /* mask mailbox interrupts for this core */
+ reim &= ~REIM_MBOXIRQ0M;
+ write_c0_reim(reim);
+
+ /* clear mailboxes & pending mailbox IRQs */
+ write_c0_mailbox0(0);
+ write_c0_mailbox1(0);
+ write_c0_corestatus(0);
+
+ /* set reset entry point */
+ addr = KSEG1ADDR((u32)&jz4780_secondary_cpu_entry);
+ WARN_ON(addr & ~REIM_ENTRY);
+ reim &= ~REIM_ENTRY;
+ reim |= addr & REIM_ENTRY;
+
+ /* unmask mailbox interrupts for this core */
+ reim |= REIM_MBOXIRQ0M;
+ write_c0_reim(reim);
+ set_c0_status(STATUSF_IP3);
+ irq_enable_hazard();
+
+ cpumask_set_cpu(cpu, &cpu_running);
+}
+
+static void jz4780_smp_prepare_cpus(unsigned int max_cpus)
+{
+ struct device_node *cpu_node;
+ unsigned cpu, ctrl;
+ int err;
+
+ /* setup the mailbox IRQ */
+ setup_irq(MIPS_CPU_IRQ_BASE + 3, &mbox_action);
+
+ init_cpu_present(cpu_possible_mask);
+
+ ctrl = read_c0_corectrl();
+
+ for (cpu = 0; cpu < max_cpus; cpu++) {
+ /* use reset entry point from REIM register */
+ ctrl |= CORECTRL_RPC0 << cpu;
+ }
+
+ for_each_of_cpu_node(cpu_node) {
+ cpu = of_cpu_node_to_id(cpu_node);
+ if (cpu < 0) {
+ pr_err("Failed to read index of %s\n",
+ cpu_node->full_name);
+ continue;
+ }
+
+ cpu_clock_gates[cpu] = of_clk_get(cpu_node, 0);
+ if (IS_ERR(cpu_clock_gates[cpu])) {
+ cpu_clock_gates[cpu] = NULL;
+ continue;
+ }
+
+ err = clk_prepare(cpu_clock_gates[cpu]);
+ if (err)
+ pr_err("Failed to prepare CPU clock gate\n");
+ }
+
+ write_c0_corectrl(ctrl);
+}
+
+static int jz4780_boot_secondary(int cpu, struct task_struct *idle)
+{
+ unsigned long flags;
+ u32 ctrl;
+
+ spin_lock_irqsave(&smp_lock, flags);
+
+ /* ensure the core is in reset */
+ ctrl = read_c0_corectrl();
+ ctrl |= CORECTRL_SWRST0 << cpu;
+ write_c0_corectrl(ctrl);
+
+ /* ungate core clock */
+ if (cpu_clock_gates[cpu])
+ clk_enable(cpu_clock_gates[cpu]);
+
+ /* set entry sp/gp register values */
+ jz4780_cpu_entry_sp = __KSTK_TOS(idle);
+ jz4780_cpu_entry_gp = (u32)task_thread_info(idle);
+ smp_wmb();
+
+ /* take the core out of reset */
+ ctrl &= ~(CORECTRL_SWRST0 << cpu);
+ write_c0_corectrl(ctrl);
+
+ cpumask_set_cpu(cpu, &cpu_running);
+
+ spin_unlock_irqrestore(&smp_lock, flags);
+
+ return 0;
+}
+
+static void jz4780_init_secondary(void)
+{
+}
+
+static void jz4780_smp_finish(void)
+{
+ u32 reim;
+
+ spin_lock(&smp_lock);
+
+ /* unmask mailbox interrupts for this core */
+ reim = read_c0_reim();
+ reim |= REIM_MBOXIRQ0M << smp_processor_id();
+ write_c0_reim(reim);
+
+ spin_unlock(&smp_lock);
+
+ /* unmask interrupts for this core */
+ change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP2 |
+ STATUSF_IP1 | STATUSF_IP0);
+ irq_enable_hazard();
+
+ /* force broadcast timer */
+ tick_broadcast_force();
+}
+
+static void jz4780_send_ipi_single_locked(int cpu, unsigned int action)
+{
+ u32 mbox;
+
+ switch (cpu) {
+ case 0:
+ mbox = read_c0_mailbox0();
+ write_c0_mailbox0(mbox | action);
+ break;
+ case 1:
+ mbox = read_c0_mailbox1();
+ write_c0_mailbox1(mbox | action);
+ break;
+ default:
+ panic("unhandled cpu %d!", cpu);
+ }
+}
+
+static void jz4780_send_ipi_single(int cpu, unsigned int action)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&smp_lock, flags);
+ jz4780_send_ipi_single_locked(cpu, action);
+ spin_unlock_irqrestore(&smp_lock, flags);
+}
+
+static void jz4780_send_ipi_mask(const struct cpumask *mask,
+ unsigned int action)
+{
+ unsigned long flags;
+ int cpu;
+
+ spin_lock_irqsave(&smp_lock, flags);
+
+ for_each_cpu(cpu, mask)
+ jz4780_send_ipi_single_locked(cpu, action);
+
+ spin_unlock_irqrestore(&smp_lock, flags);
+}
+
+static struct plat_smp_ops jz4780_smp_ops = {
+ .send_ipi_single = jz4780_send_ipi_single,
+ .send_ipi_mask = jz4780_send_ipi_mask,
+ .init_secondary = jz4780_init_secondary,
+ .smp_finish = jz4780_smp_finish,
+ .boot_secondary = jz4780_boot_secondary,
+ .smp_setup = jz4780_smp_setup,
+ .prepare_cpus = jz4780_smp_prepare_cpus,
+};
+
+void jz4780_smp_init(void)
+{
+ register_smp_ops(&jz4780_smp_ops);
+}
diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
index 37f8e78..a406de3 100644
--- a/arch/mips/kernel/idle.c
+++ b/arch/mips/kernel/idle.c
@@ -19,6 +19,10 @@
#include <asm/idle.h>
#include <asm/mipsregs.h>
+#ifdef CONFIG_MACH_JZ4780
+# include <asm/mach-jz4740/jz4780-smp.h>
+#endif
+
/*
* Not all of the MIPS CPUs have the "wait" instruction available. Moreover,
* the implementation of the "wait" feature differs between CPU families. This
@@ -172,7 +176,6 @@ void __init check_wait(void)
case CPU_CAVIUM_OCTEON_PLUS:
case CPU_CAVIUM_OCTEON2:
case CPU_CAVIUM_OCTEON3:
- case CPU_XBURST:
case CPU_LOONGSON32:
case CPU_XLR:
case CPU_XLP:
@@ -246,6 +249,15 @@ void __init check_wait(void)
cpu_wait = r4k_wait;
*/
break;
+ case CPU_XBURST:
+#if defined(CONFIG_MACH_JZ4780) && defined(CONFIG_SMP)
+ if (NR_CPUS > 1)
+ cpu_wait = jz4780_smp_wait_irqoff;
+ else
+ cpu_wait = r4k_wait;
+#else
+ cpu_wait = r4k_wait;
+#endif
default:
break;
}
diff --git a/drivers/clk/ingenic/jz4780-cgu.c b/drivers/clk/ingenic/jz4780-cgu.c
index d07fff1..4f81819 100644
--- a/drivers/clk/ingenic/jz4780-cgu.c
+++ b/drivers/clk/ingenic/jz4780-cgu.c
@@ -16,7 +16,7 @@
/* CGU register offsets */
#define CGU_REG_CLOCKCONTROL 0x00
-#define CGU_REG_PLLCONTROL 0x0c
+#define CGU_REG_LCR 0x04
#define CGU_REG_APLL 0x10
#define CGU_REG_MPLL 0x14
#define CGU_REG_EPLL 0x18
@@ -46,8 +46,8 @@
#define CGU_REG_CLOCKSTATUS 0xd4
/* bits within the OPCR register */
-#define OPCR_SPENDN0 (1 << 7)
-#define OPCR_SPENDN1 (1 << 6)
+#define OPCR_SPENDN0 BIT(7)
+#define OPCR_SPENDN1 BIT(6)
/* bits within the USBPCR register */
#define USBPCR_USB_MODE BIT(31)
@@ -88,6 +88,13 @@
#define USBVBFIL_IDDIGFIL_MASK (0xffff << USBVBFIL_IDDIGFIL_SHIFT)
#define USBVBFIL_USBVBFIL_MASK (0xffff)
+/* bits within the LCR register */
+#define LCR_PD_SCPU BIT(31)
+#define LCR_SCPUS BIT(27)
+
+/* bits within the CLKGR1 register */
+#define CLKGR1_CORE1 BIT(15)
+
static struct ingenic_cgu *cgu;
static u8 jz4780_otg_phy_get_parent(struct clk_hw *hw)
@@ -205,6 +212,47 @@ static const struct clk_ops jz4780_otg_phy_ops = {
.set_rate = jz4780_otg_phy_set_rate,
};
+static int jz4780_core1_enable(struct clk_hw *hw)
+{
+ struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw);
+ struct ingenic_cgu *cgu = ingenic_clk->cgu;
+ const unsigned int timeout = 100;
+ unsigned long flags;
+ unsigned int i;
+ u32 lcr, clkgr1;
+
+ spin_lock_irqsave(&cgu->lock, flags);
+
+ lcr = readl(cgu->base + CGU_REG_LCR);
+ lcr &= ~LCR_PD_SCPU;
+ writel(lcr, cgu->base + CGU_REG_LCR);
+
+ clkgr1 = readl(cgu->base + CGU_REG_CLKGR1);
+ clkgr1 &= ~CLKGR1_CORE1;
+ writel(clkgr1, cgu->base + CGU_REG_CLKGR1);
+
+ spin_unlock_irqrestore(&cgu->lock, flags);
+
+ /* wait for the CPU to be powered up */
+ for (i = 0; i < timeout; i++) {
+ lcr = readl(cgu->base + CGU_REG_LCR);
+ if (!(lcr & LCR_SCPUS))
+ break;
+ mdelay(1);
+ }
+
+ if (i == timeout) {
+ pr_err("%s: Wait for power up core1 timeout\n", __func__);
+ return -EBUSY;
+ }
+
+ return 0;
+}
+
+static const struct clk_ops jz4780_core1_ops = {
+ .enable = jz4780_core1_enable,
+};
+
static const s8 pll_od_encoding[16] = {
0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf,
@@ -701,9 +749,9 @@ static const struct ingenic_cgu_clk_info jz4780_cgu_clocks[] = {
},
[JZ4780_CLK_CORE1] = {
- "core1", CGU_CLK_GATE,
+ "core1", CGU_CLK_CUSTOM,
.parents = { JZ4780_CLK_CPU, -1, -1, -1 },
- .gate = { CGU_REG_CLKGR1, 15 },
+ .custom = { &jz4780_core1_ops },
},
};
--
2.7.4
Add 'cpus' node to the jz4740.dtsi, jz4770.dtsi, jz4780.dtsi
and x1000.dtsi files.
Tested-by: H. Nikolaus Schaller <[email protected]>
Tested-by: Paul Boddie <[email protected]>
Signed-off-by: 周琰杰 (Zhou Yanjie) <[email protected]>
---
Notes:
v1->v2:
No change.
v2->v3:
No change.
v3->v4:
Rebase on top of kernel 5.6-rc1.
arch/mips/boot/dts/ingenic/jz4740.dtsi | 14 ++++++++++++++
arch/mips/boot/dts/ingenic/jz4770.dtsi | 15 ++++++++++++++-
arch/mips/boot/dts/ingenic/jz4780.dtsi | 23 +++++++++++++++++++++++
arch/mips/boot/dts/ingenic/x1000.dtsi | 14 ++++++++++++++
4 files changed, 65 insertions(+), 1 deletion(-)
diff --git a/arch/mips/boot/dts/ingenic/jz4740.dtsi b/arch/mips/boot/dts/ingenic/jz4740.dtsi
index 5accda2..9627d95 100644
--- a/arch/mips/boot/dts/ingenic/jz4740.dtsi
+++ b/arch/mips/boot/dts/ingenic/jz4740.dtsi
@@ -6,6 +6,20 @@
#size-cells = <1>;
compatible = "ingenic,jz4740";
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu0: cpu@0 {
+ device_type = "cpu";
+ compatible = "ingenic,xburst";
+ reg = <0>;
+
+ clocks = <&cgu JZ4740_CLK_CCLK>;
+ clock-names = "cpu";
+ };
+ };
+
cpuintc: interrupt-controller {
#address-cells = <0>;
#interrupt-cells = <1>;
diff --git a/arch/mips/boot/dts/ingenic/jz4770.dtsi b/arch/mips/boot/dts/ingenic/jz4770.dtsi
index 0bfb9ed..1b8114d 100644
--- a/arch/mips/boot/dts/ingenic/jz4770.dtsi
+++ b/arch/mips/boot/dts/ingenic/jz4770.dtsi
@@ -1,5 +1,4 @@
// SPDX-License-Identifier: GPL-2.0
-
#include <dt-bindings/clock/jz4770-cgu.h>
/ {
@@ -7,6 +6,20 @@
#size-cells = <1>;
compatible = "ingenic,jz4770";
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu0: cpu@0 {
+ device_type = "cpu";
+ compatible = "ingenic,xburst";
+ reg = <0>;
+
+ clocks = <&cgu JZ4770_CLK_CCLK>;
+ clock-names = "cpu";
+ };
+ };
+
cpuintc: interrupt-controller {
#address-cells = <0>;
#interrupt-cells = <1>;
diff --git a/arch/mips/boot/dts/ingenic/jz4780.dtsi b/arch/mips/boot/dts/ingenic/jz4780.dtsi
index f928329..93a0604 100644
--- a/arch/mips/boot/dts/ingenic/jz4780.dtsi
+++ b/arch/mips/boot/dts/ingenic/jz4780.dtsi
@@ -7,6 +7,29 @@
#size-cells = <1>;
compatible = "ingenic,jz4780";
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu0: cpu@0 {
+ device_type = "cpu";
+ compatible = "ingenic,xburst";
+ reg = <0>;
+
+ clocks = <&cgu JZ4780_CLK_CPU>;
+ clock-names = "cpu";
+ };
+
+ cpu1: cpu@1 {
+ device_type = "cpu";
+ compatible = "ingenic,xburst";
+ reg = <1>;
+
+ clocks = <&cgu JZ4780_CLK_CORE1>;
+ clock-names = "cpu";
+ };
+ };
+
cpuintc: interrupt-controller {
#address-cells = <0>;
#interrupt-cells = <1>;
diff --git a/arch/mips/boot/dts/ingenic/x1000.dtsi b/arch/mips/boot/dts/ingenic/x1000.dtsi
index 4994c69..376df1b 100644
--- a/arch/mips/boot/dts/ingenic/x1000.dtsi
+++ b/arch/mips/boot/dts/ingenic/x1000.dtsi
@@ -7,6 +7,20 @@
#size-cells = <1>;
compatible = "ingenic,x1000", "ingenic,x1000e";
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu0: cpu@0 {
+ device_type = "cpu";
+ compatible = "ingenic,xburst";
+ reg = <0>;
+
+ clocks = <&cgu X1000_CLK_CPU>;
+ clock-names = "cpu";
+ };
+ };
+
cpuintc: interrupt-controller {
#address-cells = <0>;
#interrupt-cells = <1>;
--
2.7.4
Add "CONFIG_SMP=y" and "CONFIG_NR_CPUS=2" to support SMP.
Tested-by: H. Nikolaus Schaller <[email protected]>
Tested-by: Paul Boddie <[email protected]>
Signed-off-by: 周琰杰 (Zhou Yanjie) <[email protected]>
---
Notes:
v1->v2:
No change.
v2->v3:
No change.
v3->v4:
Rebase on top of kernel 5.6-rc1.
arch/mips/configs/ci20_defconfig | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/mips/configs/ci20_defconfig b/arch/mips/configs/ci20_defconfig
index be41df2..3aadb2e 100644
--- a/arch/mips/configs/ci20_defconfig
+++ b/arch/mips/configs/ci20_defconfig
@@ -1,3 +1,5 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=2
# CONFIG_LOCALVERSION_AUTO is not set
CONFIG_KERNEL_XZ=y
CONFIG_SYSVIPC=y
--
2.7.4
Introduce SMP support for MIPS Creator CI20, which is
based on Ingenic JZ4780 SoC.
周琰杰 (Zhou Yanjie) (6):
MIPS: JZ4780: Introduce SMP support.
clocksource: Ingenic: Add high resolution timer support for SMP.
dt-bindings: MIPS: Document Ingenic SoCs binding.
MIPS: Ingenic: Add 'cpus' node for Ingenic SoCs.
MIPS: CI20: Modify DTS to support high resolution timer for SMP.
MIPS: CI20: Update defconfig to support SMP.
.../bindings/mips/ingenic/ingenic,cpu.yaml | 53 ++++
.../bindings/mips/ingenic/ingenic,soc.yaml | 35 +++
arch/mips/boot/dts/ingenic/ci20.dts | 11 +-
arch/mips/boot/dts/ingenic/jz4740.dtsi | 14 +
arch/mips/boot/dts/ingenic/jz4770.dtsi | 15 +-
arch/mips/boot/dts/ingenic/jz4780.dtsi | 23 ++
arch/mips/boot/dts/ingenic/x1000.dtsi | 14 +
arch/mips/configs/ci20_defconfig | 2 +
arch/mips/include/asm/mach-jz4740/jz4780-smp.h | 91 +++++++
arch/mips/jz4740/Kconfig | 3 +
arch/mips/jz4740/Makefile | 5 +
arch/mips/jz4740/prom.c | 4 +
arch/mips/jz4740/smp-entry.S | 57 ++++
arch/mips/jz4740/smp.c | 286 +++++++++++++++++++++
arch/mips/kernel/idle.c | 14 +-
drivers/clk/ingenic/jz4780-cgu.c | 58 ++++-
drivers/clocksource/ingenic-timer.c | 200 +++++++++-----
17 files changed, 810 insertions(+), 75 deletions(-)
create mode 100755 Documentation/devicetree/bindings/mips/ingenic/ingenic,cpu.yaml
create mode 100755 Documentation/devicetree/bindings/mips/ingenic/ingenic,soc.yaml
create mode 100644 arch/mips/include/asm/mach-jz4740/jz4780-smp.h
create mode 100644 arch/mips/jz4740/smp-entry.S
create mode 100644 arch/mips/jz4740/smp.c
--
2.7.4
Enable clock event handling on per CPU core basis.
Make sure that interrupts raised on the first core execute
event handlers on the correct CPU core.
Tested-by: H. Nikolaus Schaller <[email protected]>
Tested-by: Paul Boddie <[email protected]>
Signed-off-by: 周琰杰 (Zhou Yanjie) <[email protected]>
---
Notes:
v1->v2:
1.Adjust function naming to make it more reasonable.
2.Replace function smp_call_function_single() with
smp_call_function_single_async() in order to resolve
the warning below:
[ 0.350942] smp: Brought up 1 node, 2 CPUs
[ 0.365497] ------------[ cut here ]------------
[ 0.365522] WARNING: CPU: 0 PID: 1 at kernel/smp.c:300 smp_call_function_single+0x110/0x200
[ 0.365533] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.5.0-rc1+ #5
[ 0.365537] Stack : 00000000 59c73bcd 00000037 80074e80 80000000 80670000 805a0000 80620590
[ 0.365557] 8065ce38 8fc0dc8c 806d0000 00000000 80670000 00000001 8fc0dc20 59c73bcd
[ 0.365574] 00000000 00000000 806f0000 80670000 00000000 806dab00 00000000 2d302e35
[ 0.365591] 203a6d6d 806e0000 806e0000 70617773 80670000 00000000 00000000 00000009
[ 0.365610] 00000000 8fc94e20 8fc0de30 80690000 00000018 803592dc 00000000 806d0000
[ 0.365627] ...
[ 0.365634] Call Trace:
[ 0.365647] [<8001b9a0>] show_stack+0x6c/0x12c
[ 0.365663] [<804aed20>] dump_stack+0x98/0xc8
[ 0.365673] [<8003044c>] __warn+0xc4/0xe8
[ 0.365682] [<800304f4>] warn_slowpath_fmt+0x84/0xb8
[ 0.365690] [<800a886c>] smp_call_function_single+0x110/0x200
[ 0.365703] ---[ end trace 5785856ca39c79d5 ]---
[ 0.365557] 8065ce38 8fc0dc8c 806d0000 00000000 80670000 00000001 8fc0dc20 59c73bcd
[ 0.365574] 00000000 00000000 806f0000 80670000 00000000 806dab00 00000000 2d302e35
[ 0.365591] 203a6d6d 806e0000 806e0000 70617773 80670000 00000000 00000000 00000009
[ 0.365610] 00000000 8fc94e20 8fc0de30 80690000 00000018 803592dc 00000000 806d0000
[ 0.365627] ...
[ 0.365634] Call Trace:
[ 0.365647] [<8001b9a0>] show_stack+0x6c/0x12c
[ 0.365663] [<804aed20>] dump_stack+0x98/0xc8
[ 0.365673] [<8003044c>] __warn+0xc4/0xe8
[ 0.365682] [<800304f4>] warn_slowpath_fmt+0x84/0xb8
[ 0.365690] [<800a886c>] smp_call_function_single+0x110/0x200
[ 0.365703] ---[ end trace 5785856ca39c79d5 ]---
v2->v3:
No Change.
v3->v4:
Rebase on top of kernel 5.6-rc1.
drivers/clocksource/ingenic-timer.c | 200 ++++++++++++++++++++++++------------
1 file changed, 134 insertions(+), 66 deletions(-)
diff --git a/drivers/clocksource/ingenic-timer.c b/drivers/clocksource/ingenic-timer.c
index 4bbdb3d..9127c73 100644
--- a/drivers/clocksource/ingenic-timer.c
+++ b/drivers/clocksource/ingenic-timer.c
@@ -1,7 +1,8 @@
// SPDX-License-Identifier: GPL-2.0
/*
- * JZ47xx SoCs TCU IRQ driver
+ * XBurst SoCs TCU IRQ driver
* Copyright (C) 2019 Paul Cercueil <[email protected]>
+ * Copyright (C) 2020 周琰杰 (Zhou Yanjie) <[email protected]>
*/
#include <linux/bitops.h>
@@ -21,18 +22,23 @@
#include <dt-bindings/clock/ingenic,tcu.h>
+static DEFINE_PER_CPU(call_single_data_t, ingenic_cevt_csd);
+
struct ingenic_soc_info {
unsigned int num_channels;
};
struct ingenic_tcu {
struct regmap *map;
+ struct device_node *np;
struct clk *timer_clk, *cs_clk;
+ unsigned int timer_local[NR_CPUS];
unsigned int timer_channel, cs_channel;
struct clock_event_device cevt;
struct clocksource cs;
- char name[4];
+ char name[16];
unsigned long pwm_channels_mask;
+ int cpu;
};
static struct ingenic_tcu *ingenic_tcu;
@@ -81,6 +87,25 @@ static int ingenic_tcu_cevt_set_next(unsigned long next,
return 0;
}
+static void ingenic_per_cpu_event_handler(void *info)
+{
+ struct clock_event_device *cevt = (struct clock_event_device *) info;
+
+ if (cevt->event_handler)
+ cevt->event_handler(cevt);
+}
+
+static void ingenic_tcu_per_cpu_cb(struct clock_event_device *evt)
+{
+ struct ingenic_tcu *tcu = to_ingenic_tcu(evt);
+ call_single_data_t *csd;
+
+ csd = &per_cpu(ingenic_cevt_csd, tcu->cpu);
+ csd->info = (void *) evt;
+ csd->func = ingenic_per_cpu_event_handler;
+ smp_call_function_single_async(tcu->cpu, csd);
+}
+
static irqreturn_t ingenic_tcu_cevt_cb(int irq, void *dev_id)
{
struct clock_event_device *evt = dev_id;
@@ -88,8 +113,7 @@ static irqreturn_t ingenic_tcu_cevt_cb(int irq, void *dev_id)
regmap_write(tcu->map, TCU_REG_TECR, BIT(tcu->timer_channel));
- if (evt->event_handler)
- evt->event_handler(evt);
+ ingenic_tcu_per_cpu_cb(evt);
return IRQ_HANDLED;
}
@@ -105,14 +129,73 @@ static struct clk * __init ingenic_tcu_get_clock(struct device_node *np, int id)
return of_clk_get_from_provider(&args);
}
-static int __init ingenic_tcu_timer_init(struct device_node *np,
- struct ingenic_tcu *tcu)
+static int __init ingenic_tcu_clocksource_init(struct device_node *np,
+ struct ingenic_tcu *tcu)
+{
+ unsigned int channel = tcu->cs_channel;
+ struct clocksource *cs = &tcu->cs;
+ unsigned long rate;
+ int err;
+
+ tcu->cs_clk = ingenic_tcu_get_clock(np, channel);
+ if (IS_ERR(tcu->cs_clk))
+ return PTR_ERR(tcu->cs_clk);
+
+ err = clk_prepare_enable(tcu->cs_clk);
+ if (err)
+ goto err_clk_put;
+
+ rate = clk_get_rate(tcu->cs_clk);
+ if (!rate) {
+ err = -EINVAL;
+ goto err_clk_disable;
+ }
+
+ /* Reset channel */
+ regmap_update_bits(tcu->map, TCU_REG_TCSRc(channel),
+ 0xffff & ~TCU_TCSR_RESERVED_BITS, 0);
+
+ /* Reset counter */
+ regmap_write(tcu->map, TCU_REG_TDFRc(channel), 0xffff);
+ regmap_write(tcu->map, TCU_REG_TCNTc(channel), 0);
+
+ /* Enable channel */
+ regmap_write(tcu->map, TCU_REG_TESR, BIT(channel));
+
+ cs->name = "ingenic-timer";
+ cs->rating = 200;
+ cs->flags = CLOCK_SOURCE_IS_CONTINUOUS;
+ cs->mask = CLOCKSOURCE_MASK(16);
+ cs->read = ingenic_tcu_timer_cs_read;
+
+ err = clocksource_register_hz(cs, rate);
+ if (err)
+ goto err_clk_disable;
+
+ return 0;
+
+err_clk_disable:
+ clk_disable_unprepare(tcu->cs_clk);
+err_clk_put:
+ clk_put(tcu->cs_clk);
+ return err;
+}
+
+static int ingenic_tcu_setup_per_cpu_cevt(struct device_node *np,
+ unsigned int channel)
{
- unsigned int timer_virq, channel = tcu->timer_channel;
+ unsigned int timer_virq;
struct irq_domain *domain;
+ struct ingenic_tcu *tcu;
unsigned long rate;
int err;
+ tcu = kzalloc(sizeof(*tcu), GFP_KERNEL);
+ if (!tcu)
+ return -ENOMEM;
+
+ tcu->map = ingenic_tcu->map;
+
tcu->timer_clk = ingenic_tcu_get_clock(np, channel);
if (IS_ERR(tcu->timer_clk))
return PTR_ERR(tcu->timer_clk);
@@ -139,13 +222,15 @@ static int __init ingenic_tcu_timer_init(struct device_node *np,
goto err_clk_disable;
}
- snprintf(tcu->name, sizeof(tcu->name), "TCU");
+ snprintf(tcu->name, sizeof(tcu->name), "TCU channel.%u", channel);
err = request_irq(timer_virq, ingenic_tcu_cevt_cb, IRQF_TIMER,
tcu->name, &tcu->cevt);
if (err)
goto err_irq_dispose_mapping;
+ tcu->cpu = smp_processor_id();
+ tcu->timer_channel = channel;
tcu->cevt.cpumask = cpumask_of(smp_processor_id());
tcu->cevt.features = CLOCK_EVT_FEAT_ONESHOT;
tcu->cevt.name = tcu->name;
@@ -166,56 +251,23 @@ static int __init ingenic_tcu_timer_init(struct device_node *np,
return err;
}
-static int __init ingenic_tcu_clocksource_init(struct device_node *np,
- struct ingenic_tcu *tcu)
+static int ingenic_tcu_setup_cevt(unsigned int cpu)
{
- unsigned int channel = tcu->cs_channel;
- struct clocksource *cs = &tcu->cs;
- unsigned long rate;
- int err;
-
- tcu->cs_clk = ingenic_tcu_get_clock(np, channel);
- if (IS_ERR(tcu->cs_clk))
- return PTR_ERR(tcu->cs_clk);
-
- err = clk_prepare_enable(tcu->cs_clk);
- if (err)
- goto err_clk_put;
-
- rate = clk_get_rate(tcu->cs_clk);
- if (!rate) {
- err = -EINVAL;
- goto err_clk_disable;
- }
-
- /* Reset channel */
- regmap_update_bits(tcu->map, TCU_REG_TCSRc(channel),
- 0xffff & ~TCU_TCSR_RESERVED_BITS, 0);
-
- /* Reset counter */
- regmap_write(tcu->map, TCU_REG_TDFRc(channel), 0xffff);
- regmap_write(tcu->map, TCU_REG_TCNTc(channel), 0);
-
- /* Enable channel */
- regmap_write(tcu->map, TCU_REG_TESR, BIT(channel));
-
- cs->name = "ingenic-timer";
- cs->rating = 200;
- cs->flags = CLOCK_SOURCE_IS_CONTINUOUS;
- cs->mask = CLOCKSOURCE_MASK(16);
- cs->read = ingenic_tcu_timer_cs_read;
+ int ret;
- err = clocksource_register_hz(cs, rate);
- if (err)
- goto err_clk_disable;
+ ret = ingenic_tcu_setup_per_cpu_cevt(ingenic_tcu->np,
+ ingenic_tcu->timer_local[cpu]);
+ if (ret)
+ goto err_tcu_clocksource_cleanup;
return 0;
-err_clk_disable:
- clk_disable_unprepare(tcu->cs_clk);
-err_clk_put:
- clk_put(tcu->cs_clk);
- return err;
+err_tcu_clocksource_cleanup:
+ clocksource_unregister(&ingenic_tcu->cs);
+ clk_disable_unprepare(ingenic_tcu->cs_clk);
+ clk_put(ingenic_tcu->cs_clk);
+ kfree(ingenic_tcu);
+ return ret;
}
static const struct ingenic_soc_info jz4740_soc_info = {
@@ -239,6 +291,7 @@ static int __init ingenic_tcu_init(struct device_node *np)
const struct ingenic_soc_info *soc_info = id->data;
struct ingenic_tcu *tcu;
struct regmap *map;
+ unsigned cpu = 0;
long rate;
int ret;
@@ -253,12 +306,14 @@ static int __init ingenic_tcu_init(struct device_node *np)
return -ENOMEM;
/* Enable all TCU channels for PWM use by default except channels 0/1 */
- tcu->pwm_channels_mask = GENMASK(soc_info->num_channels - 1, 2);
+ tcu->pwm_channels_mask = GENMASK(soc_info->num_channels - 1,
+ NR_CPUS + 1);
of_property_read_u32(np, "ingenic,pwm-channels-mask",
(u32 *)&tcu->pwm_channels_mask);
/* Verify that we have at least two free channels */
- if (hweight8(tcu->pwm_channels_mask) > soc_info->num_channels - 2) {
+ if (hweight8(tcu->pwm_channels_mask) >
+ soc_info->num_channels - NR_CPUS + 1) {
pr_crit("%s: Invalid PWM channel mask: 0x%02lx\n", __func__,
tcu->pwm_channels_mask);
ret = -EINVAL;
@@ -266,13 +321,29 @@ static int __init ingenic_tcu_init(struct device_node *np)
}
tcu->map = map;
+ tcu->np = np;
ingenic_tcu = tcu;
- tcu->timer_channel = find_first_zero_bit(&tcu->pwm_channels_mask,
+ tcu->timer_local[cpu] = find_first_zero_bit(&tcu->pwm_channels_mask,
soc_info->num_channels);
- tcu->cs_channel = find_next_zero_bit(&tcu->pwm_channels_mask,
- soc_info->num_channels,
- tcu->timer_channel + 1);
+
+ if (NR_CPUS > 1) {
+ for (cpu = 1; cpu < NR_CPUS; cpu++)
+ tcu->timer_local[cpu] = find_next_zero_bit(
+ &tcu->pwm_channels_mask,
+ soc_info->num_channels,
+ tcu->timer_local[cpu - 1] + 1);
+
+ tcu->cs_channel = find_next_zero_bit(&tcu->pwm_channels_mask,
+ soc_info->num_channels,
+ tcu->timer_local[cpu-1] + 1);
+ } else {
+ tcu->cs_channel = find_next_zero_bit(&tcu->pwm_channels_mask,
+ soc_info->num_channels,
+ tcu->timer_local[cpu] + 1);
+ }
+
+
ret = ingenic_tcu_clocksource_init(np, tcu);
if (ret) {
@@ -280,9 +351,10 @@ static int __init ingenic_tcu_init(struct device_node *np)
goto err_free_ingenic_tcu;
}
- ret = ingenic_tcu_timer_init(np, tcu);
- if (ret)
- goto err_tcu_clocksource_cleanup;
+ /* Setup clock events on each CPU core */
+ ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "Ingenic XBurst: online",
+ ingenic_tcu_setup_cevt, NULL);
+ WARN_ON(ret < 0);
/* Register the sched_clock at the end as there's no way to undo it */
rate = clk_get_rate(tcu->cs_clk);
@@ -290,10 +362,6 @@ static int __init ingenic_tcu_init(struct device_node *np)
return 0;
-err_tcu_clocksource_cleanup:
- clocksource_unregister(&tcu->cs);
- clk_disable_unprepare(tcu->cs_clk);
- clk_put(tcu->cs_clk);
err_free_ingenic_tcu:
kfree(tcu);
return ret;
--
2.7.4
Hi Zhou,
The changes to drivers/clk/ingenic/jz4780-cgu.c look sound but they
really don't belong in this patch.
Please split them to another patch.
-Paul
Le sam., févr. 15, 2020 at 02:02, 周琰杰 (Zhou Yanjie)
<[email protected]> a écrit :
> Forward port smp support from kernel 3.18.3 of CI20_linux
> to upstream kernel 5.5.
>
> Tested-by: H. Nikolaus Schaller <[email protected]>
> Tested-by: Paul Boddie <[email protected]>
> Signed-off-by: 周琰杰 (Zhou Yanjie) <[email protected]>
> ---
>
> Notes:
> v1->v2:
> 1.Remove unnecessary "plat_irq_dispatch(void)" in irq-ingenic.c.
> 2.Add a timeout check for "jz4780_boot_secondary()" to avoid a
> dead loop.
> 3.Replace hard code in smp.c with macro.
>
> v2->v3:
> 1.Remove unnecessary "extern void (*r4k_blast_dcache)(void)" in
> smp.c.
> 2.Use "for_each_of_cpu_node" instead "for_each_compatible_node"
> in smp.c.
> 3.Use "of_cpu_node_to_id" instead "of_property_read_u32_index" in
> smp.c.
> 4.Move LCR related operations to jz4780-cgu.c.
>
> v3->v4:
> Rebase on top of kernel 5.6-rc1.
>
> arch/mips/include/asm/mach-jz4740/jz4780-smp.h | 91 ++++++++
> arch/mips/jz4740/Kconfig | 3 +
> arch/mips/jz4740/Makefile | 5 +
> arch/mips/jz4740/prom.c | 4 +
> arch/mips/jz4740/smp-entry.S | 57 +++++
> arch/mips/jz4740/smp.c | 286
> +++++++++++++++++++++++++
> arch/mips/kernel/idle.c | 14 +-
> drivers/clk/ingenic/jz4780-cgu.c | 58 ++++-
> 8 files changed, 512 insertions(+), 6 deletions(-)
> create mode 100644 arch/mips/include/asm/mach-jz4740/jz4780-smp.h
> create mode 100644 arch/mips/jz4740/smp-entry.S
> create mode 100644 arch/mips/jz4740/smp.c
>
> diff --git a/arch/mips/include/asm/mach-jz4740/jz4780-smp.h
> b/arch/mips/include/asm/mach-jz4740/jz4780-smp.h
> new file mode 100644
> index 00000000..3f592ce
> --- /dev/null
> +++ b/arch/mips/include/asm/mach-jz4740/jz4780-smp.h
> @@ -0,0 +1,91 @@
> +/* SPDX-License-Identifier: GPL-2.0-or-later */
> +/*
> + * Copyright (C) 2013, Paul Burton <[email protected]>
> + * JZ4780 SMP definitions
> + */
> +
> +#ifndef __MIPS_ASM_MACH_JZ4740_JZ4780_SMP_H__
> +#define __MIPS_ASM_MACH_JZ4740_JZ4780_SMP_H__
> +
> +#define read_c0_corectrl() __read_32bit_c0_register($12, 2)
> +#define write_c0_corectrl(val) __write_32bit_c0_register($12, 2,
> val)
> +
> +#define read_c0_corestatus() __read_32bit_c0_register($12, 3)
> +#define write_c0_corestatus(val) __write_32bit_c0_register($12, 3,
> val)
> +
> +#define read_c0_reim() __read_32bit_c0_register($12, 4)
> +#define write_c0_reim(val) __write_32bit_c0_register($12, 4, val)
> +
> +#define read_c0_mailbox0() __read_32bit_c0_register($20, 0)
> +#define write_c0_mailbox0(val) __write_32bit_c0_register($20, 0,
> val)
> +
> +#define read_c0_mailbox1() __read_32bit_c0_register($20, 1)
> +#define write_c0_mailbox1(val) __write_32bit_c0_register($20, 1,
> val)
> +
> +#define smp_clr_pending(mask) do { \
> + unsigned int stat; \
> + stat = read_c0_corestatus(); \
> + stat &= ~((mask) & 0xff); \
> + write_c0_corestatus(stat); \
> + } while (0)
> +
> +/*
> + * Core Control register
> + */
> +#define CORECTRL_SLEEP1M_SHIFT 17
> +#define CORECTRL_SLEEP1M (_ULCAST_(0x1) << CORECTRL_SLEEP1M_SHIFT)
> +#define CORECTRL_SLEEP0M_SHIFT 16
> +#define CORECTRL_SLEEP0M (_ULCAST_(0x1) << CORECTRL_SLEEP0M_SHIFT)
> +#define CORECTRL_RPC1_SHIFT 9
> +#define CORECTRL_RPC1 (_ULCAST_(0x1) << CORECTRL_RPC1_SHIFT)
> +#define CORECTRL_RPC0_SHIFT 8
> +#define CORECTRL_RPC0 (_ULCAST_(0x1) << CORECTRL_RPC0_SHIFT)
> +#define CORECTRL_SWRST1_SHIFT 1
> +#define CORECTRL_SWRST1 (_ULCAST_(0x1) << CORECTRL_SWRST1_SHIFT)
> +#define CORECTRL_SWRST0_SHIFT 0
> +#define CORECTRL_SWRST0 (_ULCAST_(0x1) << CORECTRL_SWRST0_SHIFT)
> +
> +/*
> + * Core Status register
> + */
> +#define CORESTATUS_SLEEP1_SHIFT 17
> +#define CORESTATUS_SLEEP1 (_ULCAST_(0x1) << CORESTATUS_SLEEP1_SHIFT)
> +#define CORESTATUS_SLEEP0_SHIFT 16
> +#define CORESTATUS_SLEEP0 (_ULCAST_(0x1) << CORESTATUS_SLEEP0_SHIFT)
> +#define CORESTATUS_IRQ1P_SHIFT 9
> +#define CORESTATUS_IRQ1P (_ULCAST_(0x1) << CORESTATUS_IRQ1P_SHIFT)
> +#define CORESTATUS_IRQ0P_SHIFT 8
> +#define CORESTATUS_IRQ0P (_ULCAST_(0x1) << CORESTATUS_IRQ8P_SHIFT)
> +#define CORESTATUS_MIRQ1P_SHIFT 1
> +#define CORESTATUS_MIRQ1P (_ULCAST_(0x1) << CORESTATUS_MIRQ1P_SHIFT)
> +#define CORESTATUS_MIRQ0P_SHIFT 0
> +#define CORESTATUS_MIRQ0P (_ULCAST_(0x1) << CORESTATUS_MIRQ0P_SHIFT)
> +
> +/*
> + * Reset Entry & IRQ Mask register
> + */
> +#define REIM_ENTRY_SHIFT 16
> +#define REIM_ENTRY (_ULCAST_(0xffff) << REIM_ENTRY_SHIFT)
> +#define REIM_IRQ1M_SHIFT 9
> +#define REIM_IRQ1M (_ULCAST_(0x1) << REIM_IRQ1M_SHIFT)
> +#define REIM_IRQ0M_SHIFT 8
> +#define REIM_IRQ0M (_ULCAST_(0x1) << REIM_IRQ0M_SHIFT)
> +#define REIM_MBOXIRQ1M_SHIFT 1
> +#define REIM_MBOXIRQ1M (_ULCAST_(0x1) << REIM_MBOXIRQ1M_SHIFT)
> +#define REIM_MBOXIRQ0M_SHIFT 0
> +#define REIM_MBOXIRQ0M (_ULCAST_(0x1) << REIM_MBOXIRQ0M_SHIFT)
> +
> +#ifdef CONFIG_SMP
> +
> +extern void jz4780_smp_wait_irqoff(void);
> +
> +extern void jz4780_smp_init(void);
> +extern void jz4780_secondary_cpu_entry(void);
> +
> +#else /* !CONFIG_SMP */
> +
> +static inline void jz4780_smp_init(void) { }
> +
> +#endif /* !CONFIG_SMP */
> +
> +#endif /* __MIPS_ASM_MACH_JZ4740_JZ4780_SMP_H__ */
> diff --git a/arch/mips/jz4740/Kconfig b/arch/mips/jz4740/Kconfig
> index 412d2fa..0239597 100644
> --- a/arch/mips/jz4740/Kconfig
> +++ b/arch/mips/jz4740/Kconfig
> @@ -34,9 +34,12 @@ config MACH_JZ4770
>
> config MACH_JZ4780
> bool
> + select GENERIC_CLOCKEVENTS_BROADCAST if SMP
> select MIPS_CPU_SCACHE
> + select NR_CPUS_DEFAULT_2
> select SYS_HAS_CPU_MIPS32_R2
> select SYS_SUPPORTS_HIGHMEM
> + select SYS_SUPPORTS_SMP
>
> config MACH_X1000
> bool
> diff --git a/arch/mips/jz4740/Makefile b/arch/mips/jz4740/Makefile
> index 6de14c0..0a0f024 100644
> --- a/arch/mips/jz4740/Makefile
> +++ b/arch/mips/jz4740/Makefile
> @@ -12,3 +12,8 @@ CFLAGS_setup.o =
> -I$(src)/../../../scripts/dtc/libfdt
> # PM support
>
> obj-$(CONFIG_PM) += pm.o
> +
> +# SMP support
> +
> +obj-$(CONFIG_SMP) += smp.o
> +obj-$(CONFIG_SMP) += smp-entry.o
> diff --git a/arch/mips/jz4740/prom.c b/arch/mips/jz4740/prom.c
> index ff4555c..a79159e 100644
> --- a/arch/mips/jz4740/prom.c
> +++ b/arch/mips/jz4740/prom.c
> @@ -8,10 +8,14 @@
>
> #include <asm/bootinfo.h>
> #include <asm/fw/fw.h>
> +#include <asm/mach-jz4740/jz4780-smp.h>
>
> void __init prom_init(void)
> {
> fw_init_cmdline();
> +#if defined(CONFIG_MACH_JZ4780) && defined(CONFIG_SMP)
> + jz4780_smp_init();
> +#endif
> }
>
> void __init prom_free_prom_memory(void)
> diff --git a/arch/mips/jz4740/smp-entry.S
> b/arch/mips/jz4740/smp-entry.S
> new file mode 100644
> index 00000000..20049a3
> --- /dev/null
> +++ b/arch/mips/jz4740/smp-entry.S
> @@ -0,0 +1,57 @@
> +/* SPDX-License-Identifier: GPL-2.0-or-later */
> +/*
> + * Copyright (C) 2013, Paul Burton <[email protected]>
> + * JZ4780 SMP entry point
> + */
> +
> +#include <asm/addrspace.h>
> +#include <asm/asm.h>
> +#include <asm/asmmacro.h>
> +#include <asm/cacheops.h>
> +#include <asm/mipsregs.h>
> +
> +#define CACHE_SIZE (32 * 1024)
> +#define CACHE_LINESIZE 32
> +
> +.extern jz4780_cpu_entry_sp
> +.extern jz4780_cpu_entry_gp
> +
> +.section .text.smp-entry
> +.balign 0x10000
> +.set noreorder
> +LEAF(jz4780_secondary_cpu_entry)
> + mtc0 zero, CP0_CAUSE
> +
> + li t0, ST0_CU0
> + mtc0 t0, CP0_STATUS
> +
> + /* cache setup */
> + li t0, KSEG0
> + ori t1, t0, CACHE_SIZE
> + mtc0 zero, CP0_TAGLO, 0
> +1: cache Index_Store_Tag_I, 0(t0)
> + cache Index_Store_Tag_D, 0(t0)
> + bne t0, t1, 1b
> + addiu t0, t0, CACHE_LINESIZE
> +
> + /* kseg0 cache attribute */
> + mfc0 t0, CP0_CONFIG, 0
> + ori t0, t0, CONF_CM_CACHABLE_NONCOHERENT
> + mtc0 t0, CP0_CONFIG, 0
> +
> + /* pagemask */
> + mtc0 zero, CP0_PAGEMASK, 0
> +
> + /* retrieve sp */
> + la t0, jz4780_cpu_entry_sp
> + lw sp, 0(t0)
> +
> + /* retrieve gp */
> + la t0, jz4780_cpu_entry_gp
> + lw gp, 0(t0)
> +
> + /* jump to the kernel in kseg0 */
> + la t0, smp_bootstrap
> + jr t0
> + nop
> + END(jz4780_secondary_cpu_entry)
> diff --git a/arch/mips/jz4740/smp.c b/arch/mips/jz4740/smp.c
> new file mode 100644
> index 00000000..19b75c2
> --- /dev/null
> +++ b/arch/mips/jz4740/smp.c
> @@ -0,0 +1,286 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * Copyright (C) 2013, Paul Burton <[email protected]>
> + * JZ4780 SMP
> + */
> +
> +#include <linux/clk.h>
> +#include <linux/delay.h>
> +#include <linux/interrupt.h>
> +#include <linux/of.h>
> +#include <linux/sched.h>
> +#include <linux/sched/task_stack.h>
> +#include <linux/smp.h>
> +#include <linux/tick.h>
> +#include <asm/mach-jz4740/jz4780-smp.h>
> +#include <asm/r4kcache.h>
> +#include <asm/smp-ops.h>
> +
> +static struct clk *cpu_clock_gates[CONFIG_NR_CPUS] = { NULL };
> +
> +u32 jz4780_cpu_entry_sp;
> +u32 jz4780_cpu_entry_gp;
> +
> +static struct cpumask cpu_running;
> +
> +static DEFINE_SPINLOCK(smp_lock);
> +
> +/*
> + * The Ingenic jz4780 SMP variant has to write back dirty cache
> lines before
> + * executing wait. The CPU & cache clock will be gated until we
> return from
> + * the wait, and if another core attempts to access data from our
> data cache
> + * during this time then it will lock up.
> + */
> +void jz4780_smp_wait_irqoff(void)
> +{
> + unsigned long pending = read_c0_cause() & read_c0_status() &
> CAUSEF_IP;
> +
> + /*
> + * Going to idle has a significant overhead due to the cache flush
> so
> + * try to avoid it if we'll immediately be woken again due to an
> IRQ.
> + */
> + if (!need_resched() && !pending) {
> + r4k_blast_dcache();
> +
> + __asm__(
> + " .set push \n"
> + " .set mips3 \n"
> + " sync \n"
> + " wait \n"
> + " .set pop \n");
> + }
> +
> + local_irq_enable();
> +}
> +
> +static irqreturn_t mbox_handler(int irq, void *dev_id)
> +{
> + int cpu = smp_processor_id();
> + u32 action, status;
> +
> + spin_lock(&smp_lock);
> +
> + switch (cpu) {
> + case 0:
> + action = read_c0_mailbox0();
> + write_c0_mailbox0(0);
> + break;
> + case 1:
> + action = read_c0_mailbox1();
> + write_c0_mailbox1(0);
> + break;
> + default:
> + panic("unhandled cpu %d!", cpu);
> + }
> +
> + /* clear pending mailbox interrupt */
> + status = read_c0_corestatus();
> + status &= ~(CORESTATUS_MIRQ0P << cpu);
> + write_c0_corestatus(status);
> +
> + spin_unlock(&smp_lock);
> +
> + if (action & SMP_RESCHEDULE_YOURSELF)
> + scheduler_ipi();
> + if (action & SMP_CALL_FUNCTION)
> + generic_smp_call_function_interrupt();
> +
> + return IRQ_HANDLED;
> +}
> +
> +static struct irqaction mbox_action = {
> + .handler = mbox_handler,
> + .name = "core mailbox",
> + .flags = IRQF_PERCPU | IRQF_NO_THREAD,
> +};
> +
> +static void jz4780_smp_setup(void)
> +{
> + u32 addr, reim;
> + int cpu;
> +
> + reim = read_c0_reim();
> +
> + for (cpu = 0; cpu < NR_CPUS; cpu++) {
> + __cpu_number_map[cpu] = cpu;
> + __cpu_logical_map[cpu] = cpu;
> + set_cpu_possible(cpu, true);
> + }
> +
> + /* mask mailbox interrupts for this core */
> + reim &= ~REIM_MBOXIRQ0M;
> + write_c0_reim(reim);
> +
> + /* clear mailboxes & pending mailbox IRQs */
> + write_c0_mailbox0(0);
> + write_c0_mailbox1(0);
> + write_c0_corestatus(0);
> +
> + /* set reset entry point */
> + addr = KSEG1ADDR((u32)&jz4780_secondary_cpu_entry);
> + WARN_ON(addr & ~REIM_ENTRY);
> + reim &= ~REIM_ENTRY;
> + reim |= addr & REIM_ENTRY;
> +
> + /* unmask mailbox interrupts for this core */
> + reim |= REIM_MBOXIRQ0M;
> + write_c0_reim(reim);
> + set_c0_status(STATUSF_IP3);
> + irq_enable_hazard();
> +
> + cpumask_set_cpu(cpu, &cpu_running);
> +}
> +
> +static void jz4780_smp_prepare_cpus(unsigned int max_cpus)
> +{
> + struct device_node *cpu_node;
> + unsigned cpu, ctrl;
> + int err;
> +
> + /* setup the mailbox IRQ */
> + setup_irq(MIPS_CPU_IRQ_BASE + 3, &mbox_action);
> +
> + init_cpu_present(cpu_possible_mask);
> +
> + ctrl = read_c0_corectrl();
> +
> + for (cpu = 0; cpu < max_cpus; cpu++) {
> + /* use reset entry point from REIM register */
> + ctrl |= CORECTRL_RPC0 << cpu;
> + }
> +
> + for_each_of_cpu_node(cpu_node) {
> + cpu = of_cpu_node_to_id(cpu_node);
> + if (cpu < 0) {
> + pr_err("Failed to read index of %s\n",
> + cpu_node->full_name);
> + continue;
> + }
> +
> + cpu_clock_gates[cpu] = of_clk_get(cpu_node, 0);
> + if (IS_ERR(cpu_clock_gates[cpu])) {
> + cpu_clock_gates[cpu] = NULL;
> + continue;
> + }
> +
> + err = clk_prepare(cpu_clock_gates[cpu]);
> + if (err)
> + pr_err("Failed to prepare CPU clock gate\n");
> + }
> +
> + write_c0_corectrl(ctrl);
> +}
> +
> +static int jz4780_boot_secondary(int cpu, struct task_struct *idle)
> +{
> + unsigned long flags;
> + u32 ctrl;
> +
> + spin_lock_irqsave(&smp_lock, flags);
> +
> + /* ensure the core is in reset */
> + ctrl = read_c0_corectrl();
> + ctrl |= CORECTRL_SWRST0 << cpu;
> + write_c0_corectrl(ctrl);
> +
> + /* ungate core clock */
> + if (cpu_clock_gates[cpu])
> + clk_enable(cpu_clock_gates[cpu]);
> +
> + /* set entry sp/gp register values */
> + jz4780_cpu_entry_sp = __KSTK_TOS(idle);
> + jz4780_cpu_entry_gp = (u32)task_thread_info(idle);
> + smp_wmb();
> +
> + /* take the core out of reset */
> + ctrl &= ~(CORECTRL_SWRST0 << cpu);
> + write_c0_corectrl(ctrl);
> +
> + cpumask_set_cpu(cpu, &cpu_running);
> +
> + spin_unlock_irqrestore(&smp_lock, flags);
> +
> + return 0;
> +}
> +
> +static void jz4780_init_secondary(void)
> +{
> +}
> +
> +static void jz4780_smp_finish(void)
> +{
> + u32 reim;
> +
> + spin_lock(&smp_lock);
> +
> + /* unmask mailbox interrupts for this core */
> + reim = read_c0_reim();
> + reim |= REIM_MBOXIRQ0M << smp_processor_id();
> + write_c0_reim(reim);
> +
> + spin_unlock(&smp_lock);
> +
> + /* unmask interrupts for this core */
> + change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP2 |
> + STATUSF_IP1 | STATUSF_IP0);
> + irq_enable_hazard();
> +
> + /* force broadcast timer */
> + tick_broadcast_force();
> +}
> +
> +static void jz4780_send_ipi_single_locked(int cpu, unsigned int
> action)
> +{
> + u32 mbox;
> +
> + switch (cpu) {
> + case 0:
> + mbox = read_c0_mailbox0();
> + write_c0_mailbox0(mbox | action);
> + break;
> + case 1:
> + mbox = read_c0_mailbox1();
> + write_c0_mailbox1(mbox | action);
> + break;
> + default:
> + panic("unhandled cpu %d!", cpu);
> + }
> +}
> +
> +static void jz4780_send_ipi_single(int cpu, unsigned int action)
> +{
> + unsigned long flags;
> +
> + spin_lock_irqsave(&smp_lock, flags);
> + jz4780_send_ipi_single_locked(cpu, action);
> + spin_unlock_irqrestore(&smp_lock, flags);
> +}
> +
> +static void jz4780_send_ipi_mask(const struct cpumask *mask,
> + unsigned int action)
> +{
> + unsigned long flags;
> + int cpu;
> +
> + spin_lock_irqsave(&smp_lock, flags);
> +
> + for_each_cpu(cpu, mask)
> + jz4780_send_ipi_single_locked(cpu, action);
> +
> + spin_unlock_irqrestore(&smp_lock, flags);
> +}
> +
> +static struct plat_smp_ops jz4780_smp_ops = {
> + .send_ipi_single = jz4780_send_ipi_single,
> + .send_ipi_mask = jz4780_send_ipi_mask,
> + .init_secondary = jz4780_init_secondary,
> + .smp_finish = jz4780_smp_finish,
> + .boot_secondary = jz4780_boot_secondary,
> + .smp_setup = jz4780_smp_setup,
> + .prepare_cpus = jz4780_smp_prepare_cpus,
> +};
> +
> +void jz4780_smp_init(void)
> +{
> + register_smp_ops(&jz4780_smp_ops);
> +}
> diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
> index 37f8e78..a406de3 100644
> --- a/arch/mips/kernel/idle.c
> +++ b/arch/mips/kernel/idle.c
> @@ -19,6 +19,10 @@
> #include <asm/idle.h>
> #include <asm/mipsregs.h>
>
> +#ifdef CONFIG_MACH_JZ4780
> +# include <asm/mach-jz4740/jz4780-smp.h>
> +#endif
> +
> /*
> * Not all of the MIPS CPUs have the "wait" instruction available.
> Moreover,
> * the implementation of the "wait" feature differs between CPU
> families. This
> @@ -172,7 +176,6 @@ void __init check_wait(void)
> case CPU_CAVIUM_OCTEON_PLUS:
> case CPU_CAVIUM_OCTEON2:
> case CPU_CAVIUM_OCTEON3:
> - case CPU_XBURST:
> case CPU_LOONGSON32:
> case CPU_XLR:
> case CPU_XLP:
> @@ -246,6 +249,15 @@ void __init check_wait(void)
> cpu_wait = r4k_wait;
> */
> break;
> + case CPU_XBURST:
> +#if defined(CONFIG_MACH_JZ4780) && defined(CONFIG_SMP)
> + if (NR_CPUS > 1)
> + cpu_wait = jz4780_smp_wait_irqoff;
> + else
> + cpu_wait = r4k_wait;
> +#else
> + cpu_wait = r4k_wait;
> +#endif
> default:
> break;
> }
> diff --git a/drivers/clk/ingenic/jz4780-cgu.c
> b/drivers/clk/ingenic/jz4780-cgu.c
> index d07fff1..4f81819 100644
> --- a/drivers/clk/ingenic/jz4780-cgu.c
> +++ b/drivers/clk/ingenic/jz4780-cgu.c
> @@ -16,7 +16,7 @@
>
> /* CGU register offsets */
> #define CGU_REG_CLOCKCONTROL 0x00
> -#define CGU_REG_PLLCONTROL 0x0c
> +#define CGU_REG_LCR 0x04
> #define CGU_REG_APLL 0x10
> #define CGU_REG_MPLL 0x14
> #define CGU_REG_EPLL 0x18
> @@ -46,8 +46,8 @@
> #define CGU_REG_CLOCKSTATUS 0xd4
>
> /* bits within the OPCR register */
> -#define OPCR_SPENDN0 (1 << 7)
> -#define OPCR_SPENDN1 (1 << 6)
> +#define OPCR_SPENDN0 BIT(7)
> +#define OPCR_SPENDN1 BIT(6)
>
> /* bits within the USBPCR register */
> #define USBPCR_USB_MODE BIT(31)
> @@ -88,6 +88,13 @@
> #define USBVBFIL_IDDIGFIL_MASK (0xffff << USBVBFIL_IDDIGFIL_SHIFT)
> #define USBVBFIL_USBVBFIL_MASK (0xffff)
>
> +/* bits within the LCR register */
> +#define LCR_PD_SCPU BIT(31)
> +#define LCR_SCPUS BIT(27)
> +
> +/* bits within the CLKGR1 register */
> +#define CLKGR1_CORE1 BIT(15)
> +
> static struct ingenic_cgu *cgu;
>
> static u8 jz4780_otg_phy_get_parent(struct clk_hw *hw)
> @@ -205,6 +212,47 @@ static const struct clk_ops jz4780_otg_phy_ops =
> {
> .set_rate = jz4780_otg_phy_set_rate,
> };
>
> +static int jz4780_core1_enable(struct clk_hw *hw)
> +{
> + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw);
> + struct ingenic_cgu *cgu = ingenic_clk->cgu;
> + const unsigned int timeout = 100;
> + unsigned long flags;
> + unsigned int i;
> + u32 lcr, clkgr1;
> +
> + spin_lock_irqsave(&cgu->lock, flags);
> +
> + lcr = readl(cgu->base + CGU_REG_LCR);
> + lcr &= ~LCR_PD_SCPU;
> + writel(lcr, cgu->base + CGU_REG_LCR);
> +
> + clkgr1 = readl(cgu->base + CGU_REG_CLKGR1);
> + clkgr1 &= ~CLKGR1_CORE1;
> + writel(clkgr1, cgu->base + CGU_REG_CLKGR1);
> +
> + spin_unlock_irqrestore(&cgu->lock, flags);
> +
> + /* wait for the CPU to be powered up */
> + for (i = 0; i < timeout; i++) {
> + lcr = readl(cgu->base + CGU_REG_LCR);
> + if (!(lcr & LCR_SCPUS))
> + break;
> + mdelay(1);
> + }
> +
> + if (i == timeout) {
> + pr_err("%s: Wait for power up core1 timeout\n", __func__);
> + return -EBUSY;
> + }
> +
> + return 0;
> +}
> +
> +static const struct clk_ops jz4780_core1_ops = {
> + .enable = jz4780_core1_enable,
> +};
> +
> static const s8 pll_od_encoding[16] = {
> 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
> 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf,
> @@ -701,9 +749,9 @@ static const struct ingenic_cgu_clk_info
> jz4780_cgu_clocks[] = {
> },
>
> [JZ4780_CLK_CORE1] = {
> - "core1", CGU_CLK_GATE,
> + "core1", CGU_CLK_CUSTOM,
> .parents = { JZ4780_CLK_CPU, -1, -1, -1 },
> - .gate = { CGU_REG_CLKGR1, 15 },
> + .custom = { &jz4780_core1_ops },
> },
>
> };
> --
> 2.7.4
>
Hi Zhou,
Le sam., févr. 15, 2020 at 02:02, 周琰杰 (Zhou Yanjie)
<[email protected]> a écrit :
> Enable clock event handling on per CPU core basis.
> Make sure that interrupts raised on the first core execute
> event handlers on the correct CPU core.
>
> Tested-by: H. Nikolaus Schaller <[email protected]>
> Tested-by: Paul Boddie <[email protected]>
> Signed-off-by: 周琰杰 (Zhou Yanjie) <[email protected]>
> ---
>
> Notes:
> v1->v2:
> 1.Adjust function naming to make it more reasonable.
> 2.Replace function smp_call_function_single() with
> smp_call_function_single_async() in order to resolve
> the warning below:
>
> [ 0.350942] smp: Brought up 1 node, 2 CPUs
> [ 0.365497] ------------[ cut here ]------------
> [ 0.365522] WARNING: CPU: 0 PID: 1 at kernel/smp.c:300
> smp_call_function_single+0x110/0x200
> [ 0.365533] CPU: 0 PID: 1 Comm: swapper/0 Not tainted
> 5.5.0-rc1+ #5
> [ 0.365537] Stack : 00000000 59c73bcd 00000037 80074e80
> 80000000 80670000 805a0000 80620590
> [ 0.365557] 8065ce38 8fc0dc8c 806d0000 00000000
> 80670000 00000001 8fc0dc20 59c73bcd
> [ 0.365574] 00000000 00000000 806f0000 80670000
> 00000000 806dab00 00000000 2d302e35
> [ 0.365591] 203a6d6d 806e0000 806e0000 70617773
> 80670000 00000000 00000000 00000009
> [ 0.365610] 00000000 8fc94e20 8fc0de30 80690000
> 00000018 803592dc 00000000 806d0000
> [ 0.365627] ...
> [ 0.365634] Call Trace:
> [ 0.365647] [<8001b9a0>] show_stack+0x6c/0x12c
> [ 0.365663] [<804aed20>] dump_stack+0x98/0xc8
> [ 0.365673] [<8003044c>] __warn+0xc4/0xe8
> [ 0.365682] [<800304f4>] warn_slowpath_fmt+0x84/0xb8
> [ 0.365690] [<800a886c>] smp_call_function_single+0x110/0x200
> [ 0.365703] ---[ end trace 5785856ca39c79d5 ]---
> [ 0.365557] 8065ce38 8fc0dc8c 806d0000 00000000
> 80670000 00000001 8fc0dc20 59c73bcd
> [ 0.365574] 00000000 00000000 806f0000 80670000
> 00000000 806dab00 00000000 2d302e35
> [ 0.365591] 203a6d6d 806e0000 806e0000 70617773
> 80670000 00000000 00000000 00000009
> [ 0.365610] 00000000 8fc94e20 8fc0de30 80690000
> 00000018 803592dc 00000000 806d0000
> [ 0.365627] ...
> [ 0.365634] Call Trace:
> [ 0.365647] [<8001b9a0>] show_stack+0x6c/0x12c
> [ 0.365663] [<804aed20>] dump_stack+0x98/0xc8
> [ 0.365673] [<8003044c>] __warn+0xc4/0xe8
> [ 0.365682] [<800304f4>] warn_slowpath_fmt+0x84/0xb8
> [ 0.365690] [<800a886c>] smp_call_function_single+0x110/0x200
> [ 0.365703] ---[ end trace 5785856ca39c79d5 ]---
>
> v2->v3:
> No Change.
>
> v3->v4:
> Rebase on top of kernel 5.6-rc1.
>
> drivers/clocksource/ingenic-timer.c | 200
> ++++++++++++++++++++++++------------
> 1 file changed, 134 insertions(+), 66 deletions(-)
>
> diff --git a/drivers/clocksource/ingenic-timer.c
> b/drivers/clocksource/ingenic-timer.c
> index 4bbdb3d..9127c73 100644
> --- a/drivers/clocksource/ingenic-timer.c
> +++ b/drivers/clocksource/ingenic-timer.c
> @@ -1,7 +1,8 @@
> // SPDX-License-Identifier: GPL-2.0
> /*
> - * JZ47xx SoCs TCU IRQ driver
> + * XBurst SoCs TCU IRQ driver
> * Copyright (C) 2019 Paul Cercueil <[email protected]>
> + * Copyright (C) 2020 周琰杰 (Zhou Yanjie)
> <[email protected]>
> */
>
> #include <linux/bitops.h>
> @@ -21,18 +22,23 @@
>
> #include <dt-bindings/clock/ingenic,tcu.h>
>
> +static DEFINE_PER_CPU(call_single_data_t, ingenic_cevt_csd);
> +
> struct ingenic_soc_info {
> unsigned int num_channels;
> };
>
> struct ingenic_tcu {
> struct regmap *map;
> + struct device_node *np;
> struct clk *timer_clk, *cs_clk;
> + unsigned int timer_local[NR_CPUS];
> unsigned int timer_channel, cs_channel;
> struct clock_event_device cevt;
> struct clocksource cs;
> - char name[4];
> + char name[16];
> unsigned long pwm_channels_mask;
> + int cpu;
> };
>
> static struct ingenic_tcu *ingenic_tcu;
> @@ -81,6 +87,25 @@ static int ingenic_tcu_cevt_set_next(unsigned long
> next,
> return 0;
> }
>
> +static void ingenic_per_cpu_event_handler(void *info)
> +{
> + struct clock_event_device *cevt = (struct clock_event_device *)
> info;
> +
> + if (cevt->event_handler)
> + cevt->event_handler(cevt);
> +}
> +
> +static void ingenic_tcu_per_cpu_cb(struct clock_event_device *evt)
> +{
> + struct ingenic_tcu *tcu = to_ingenic_tcu(evt);
> + call_single_data_t *csd;
> +
> + csd = &per_cpu(ingenic_cevt_csd, tcu->cpu);
> + csd->info = (void *) evt;
> + csd->func = ingenic_per_cpu_event_handler;
> + smp_call_function_single_async(tcu->cpu, csd);
> +}
> +
> static irqreturn_t ingenic_tcu_cevt_cb(int irq, void *dev_id)
> {
> struct clock_event_device *evt = dev_id;
> @@ -88,8 +113,7 @@ static irqreturn_t ingenic_tcu_cevt_cb(int irq,
> void *dev_id)
>
> regmap_write(tcu->map, TCU_REG_TECR, BIT(tcu->timer_channel));
>
> - if (evt->event_handler)
> - evt->event_handler(evt);
> + ingenic_tcu_per_cpu_cb(evt);
I guess the check for (evt->event_handler) is still valid here. There's
no point in calling ingenic_tcu_per_cpu_cb() if in the end the handler
won't do anything.
>
> return IRQ_HANDLED;
> }
> @@ -105,14 +129,73 @@ static struct clk * __init
> ingenic_tcu_get_clock(struct device_node *np, int id)
> return of_clk_get_from_provider(&args);
> }
>
> -static int __init ingenic_tcu_timer_init(struct device_node *np,
> - struct ingenic_tcu *tcu)
> +static int __init ingenic_tcu_clocksource_init(struct device_node
> *np,
> + struct ingenic_tcu *tcu)
Please - don't move functions around. It makes the patch extremely hard
to review. Just add a forward declaration for
ingenic_tcu_clocksource_init() at the top of the file.
> +{
> + unsigned int channel = tcu->cs_channel;
> + struct clocksource *cs = &tcu->cs;
> + unsigned long rate;
> + int err;
> +
> + tcu->cs_clk = ingenic_tcu_get_clock(np, channel);
> + if (IS_ERR(tcu->cs_clk))
> + return PTR_ERR(tcu->cs_clk);
> +
> + err = clk_prepare_enable(tcu->cs_clk);
> + if (err)
> + goto err_clk_put;
> +
> + rate = clk_get_rate(tcu->cs_clk);
> + if (!rate) {
> + err = -EINVAL;
> + goto err_clk_disable;
> + }
> +
> + /* Reset channel */
> + regmap_update_bits(tcu->map, TCU_REG_TCSRc(channel),
> + 0xffff & ~TCU_TCSR_RESERVED_BITS, 0);
> +
> + /* Reset counter */
> + regmap_write(tcu->map, TCU_REG_TDFRc(channel), 0xffff);
> + regmap_write(tcu->map, TCU_REG_TCNTc(channel), 0);
> +
> + /* Enable channel */
> + regmap_write(tcu->map, TCU_REG_TESR, BIT(channel));
> +
> + cs->name = "ingenic-timer";
> + cs->rating = 200;
> + cs->flags = CLOCK_SOURCE_IS_CONTINUOUS;
> + cs->mask = CLOCKSOURCE_MASK(16);
> + cs->read = ingenic_tcu_timer_cs_read;
> +
> + err = clocksource_register_hz(cs, rate);
> + if (err)
> + goto err_clk_disable;
> +
> + return 0;
> +
> +err_clk_disable:
> + clk_disable_unprepare(tcu->cs_clk);
> +err_clk_put:
> + clk_put(tcu->cs_clk);
> + return err;
> +}
> +
> +static int ingenic_tcu_setup_per_cpu_cevt(struct device_node *np,
> + unsigned int channel)
> {
> - unsigned int timer_virq, channel = tcu->timer_channel;
> + unsigned int timer_virq;
> struct irq_domain *domain;
> + struct ingenic_tcu *tcu;
> unsigned long rate;
> int err;
>
> + tcu = kzalloc(sizeof(*tcu), GFP_KERNEL);
> + if (!tcu)
> + return -ENOMEM;
> +
> + tcu->map = ingenic_tcu->map;
> +
> tcu->timer_clk = ingenic_tcu_get_clock(np, channel);
> if (IS_ERR(tcu->timer_clk))
> return PTR_ERR(tcu->timer_clk);
> @@ -139,13 +222,15 @@ static int __init ingenic_tcu_timer_init(struct
> device_node *np,
> goto err_clk_disable;
> }
>
> - snprintf(tcu->name, sizeof(tcu->name), "TCU");
> + snprintf(tcu->name, sizeof(tcu->name), "TCU channel.%u", channel);
Make it TCU%u
>
> err = request_irq(timer_virq, ingenic_tcu_cevt_cb, IRQF_TIMER,
> tcu->name, &tcu->cevt);
> if (err)
> goto err_irq_dispose_mapping;
>
> + tcu->cpu = smp_processor_id();
> + tcu->timer_channel = channel;
> tcu->cevt.cpumask = cpumask_of(smp_processor_id());
> tcu->cevt.features = CLOCK_EVT_FEAT_ONESHOT;
> tcu->cevt.name = tcu->name;
> @@ -166,56 +251,23 @@ static int __init ingenic_tcu_timer_init(struct
> device_node *np,
> return err;
> }
>
> -static int __init ingenic_tcu_clocksource_init(struct device_node
> *np,
> - struct ingenic_tcu *tcu)
> +static int ingenic_tcu_setup_cevt(unsigned int cpu)
> {
> - unsigned int channel = tcu->cs_channel;
> - struct clocksource *cs = &tcu->cs;
> - unsigned long rate;
> - int err;
> -
> - tcu->cs_clk = ingenic_tcu_get_clock(np, channel);
> - if (IS_ERR(tcu->cs_clk))
> - return PTR_ERR(tcu->cs_clk);
> -
> - err = clk_prepare_enable(tcu->cs_clk);
> - if (err)
> - goto err_clk_put;
> -
> - rate = clk_get_rate(tcu->cs_clk);
> - if (!rate) {
> - err = -EINVAL;
> - goto err_clk_disable;
> - }
> -
> - /* Reset channel */
> - regmap_update_bits(tcu->map, TCU_REG_TCSRc(channel),
> - 0xffff & ~TCU_TCSR_RESERVED_BITS, 0);
> -
> - /* Reset counter */
> - regmap_write(tcu->map, TCU_REG_TDFRc(channel), 0xffff);
> - regmap_write(tcu->map, TCU_REG_TCNTc(channel), 0);
> -
> - /* Enable channel */
> - regmap_write(tcu->map, TCU_REG_TESR, BIT(channel));
> -
> - cs->name = "ingenic-timer";
> - cs->rating = 200;
> - cs->flags = CLOCK_SOURCE_IS_CONTINUOUS;
> - cs->mask = CLOCKSOURCE_MASK(16);
> - cs->read = ingenic_tcu_timer_cs_read;
> + int ret;
>
> - err = clocksource_register_hz(cs, rate);
> - if (err)
> - goto err_clk_disable;
> + ret = ingenic_tcu_setup_per_cpu_cevt(ingenic_tcu->np,
> + ingenic_tcu->timer_local[cpu]);
> + if (ret)
> + goto err_tcu_clocksource_cleanup;
>
> return 0;
>
> -err_clk_disable:
> - clk_disable_unprepare(tcu->cs_clk);
> -err_clk_put:
> - clk_put(tcu->cs_clk);
> - return err;
> +err_tcu_clocksource_cleanup:
> + clocksource_unregister(&ingenic_tcu->cs);
> + clk_disable_unprepare(ingenic_tcu->cs_clk);
> + clk_put(ingenic_tcu->cs_clk);
> + kfree(ingenic_tcu);
> + return ret;
> }
>
> static const struct ingenic_soc_info jz4740_soc_info = {
> @@ -239,6 +291,7 @@ static int __init ingenic_tcu_init(struct
> device_node *np)
> const struct ingenic_soc_info *soc_info = id->data;
> struct ingenic_tcu *tcu;
> struct regmap *map;
> + unsigned cpu = 0;
> long rate;
> int ret;
>
> @@ -253,12 +306,14 @@ static int __init ingenic_tcu_init(struct
> device_node *np)
> return -ENOMEM;
>
> /* Enable all TCU channels for PWM use by default except channels
> 0/1 */
> - tcu->pwm_channels_mask = GENMASK(soc_info->num_channels - 1, 2);
> + tcu->pwm_channels_mask = GENMASK(soc_info->num_channels - 1,
> + NR_CPUS + 1);
> of_property_read_u32(np, "ingenic,pwm-channels-mask",
> (u32 *)&tcu->pwm_channels_mask);
>
> /* Verify that we have at least two free channels */
> - if (hweight8(tcu->pwm_channels_mask) > soc_info->num_channels - 2) {
> + if (hweight8(tcu->pwm_channels_mask) >
> + soc_info->num_channels - NR_CPUS + 1) {
> pr_crit("%s: Invalid PWM channel mask: 0x%02lx\n", __func__,
> tcu->pwm_channels_mask);
> ret = -EINVAL;
> @@ -266,13 +321,29 @@ static int __init ingenic_tcu_init(struct
> device_node *np)
> }
>
> tcu->map = map;
> + tcu->np = np;
> ingenic_tcu = tcu;
>
> - tcu->timer_channel = find_first_zero_bit(&tcu->pwm_channels_mask,
> + tcu->timer_local[cpu] = find_first_zero_bit(&tcu->pwm_channels_mask,
> soc_info->num_channels);
> - tcu->cs_channel = find_next_zero_bit(&tcu->pwm_channels_mask,
> - soc_info->num_channels,
> - tcu->timer_channel + 1);
> +
> + if (NR_CPUS > 1) {
> + for (cpu = 1; cpu < NR_CPUS; cpu++)
> + tcu->timer_local[cpu] = find_next_zero_bit(
> + &tcu->pwm_channels_mask,
> + soc_info->num_channels,
> + tcu->timer_local[cpu - 1] + 1);
> +
> + tcu->cs_channel = find_next_zero_bit(&tcu->pwm_channels_mask,
> + soc_info->num_channels,
> + tcu->timer_local[cpu-1] + 1);
> + } else {
> + tcu->cs_channel = find_next_zero_bit(&tcu->pwm_channels_mask,
> + soc_info->num_channels,
> + tcu->timer_local[cpu] + 1);
> + }
> +
> +
>
> ret = ingenic_tcu_clocksource_init(np, tcu);
> if (ret) {
> @@ -280,9 +351,10 @@ static int __init ingenic_tcu_init(struct
> device_node *np)
> goto err_free_ingenic_tcu;
> }
>
> - ret = ingenic_tcu_timer_init(np, tcu);
> - if (ret)
> - goto err_tcu_clocksource_cleanup;
> + /* Setup clock events on each CPU core */
> + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "Ingenic XBurst:
> online",
> + ingenic_tcu_setup_cevt, NULL);
> + WARN_ON(ret < 0);
>
> /* Register the sched_clock at the end as there's no way to undo it
> */
> rate = clk_get_rate(tcu->cs_clk);
> @@ -290,10 +362,6 @@ static int __init ingenic_tcu_init(struct
> device_node *np)
>
> return 0;
>
> -err_tcu_clocksource_cleanup:
> - clocksource_unregister(&tcu->cs);
> - clk_disable_unprepare(tcu->cs_clk);
> - clk_put(tcu->cs_clk);
> err_free_ingenic_tcu:
> kfree(tcu);
> return ret;
> --
> 2.7.4
>
Hi Paul,
On 2020年02月15日 02:31, Paul Cercueil wrote:
> Hi Zhou,
>
>
> Le sam., févr. 15, 2020 at 02:02, 周琰杰 (Zhou Yanjie)
> <[email protected]> a écrit :
>> Enable clock event handling on per CPU core basis.
>> Make sure that interrupts raised on the first core execute
>> event handlers on the correct CPU core.
>>
>> Tested-by: H. Nikolaus Schaller <[email protected]>
>> Tested-by: Paul Boddie <[email protected]>
>> Signed-off-by: 周琰杰 (Zhou Yanjie) <[email protected]>
>> ---
>>
>> Notes:
>> v1->v2:
>> 1.Adjust function naming to make it more reasonable.
>> 2.Replace function smp_call_function_single() with
>> smp_call_function_single_async() in order to resolve
>> the warning below:
>>
>> [ 0.350942] smp: Brought up 1 node, 2 CPUs
>> [ 0.365497] ------------[ cut here ]------------
>> [ 0.365522] WARNING: CPU: 0 PID: 1 at kernel/smp.c:300
>> smp_call_function_single+0x110/0x200
>> [ 0.365533] CPU: 0 PID: 1 Comm: swapper/0 Not tainted
>> 5.5.0-rc1+ #5
>> [ 0.365537] Stack : 00000000 59c73bcd 00000037 80074e80
>> 80000000 80670000 805a0000 80620590
>> [ 0.365557] 8065ce38 8fc0dc8c 806d0000 00000000
>> 80670000 00000001 8fc0dc20 59c73bcd
>> [ 0.365574] 00000000 00000000 806f0000 80670000
>> 00000000 806dab00 00000000 2d302e35
>> [ 0.365591] 203a6d6d 806e0000 806e0000 70617773
>> 80670000 00000000 00000000 00000009
>> [ 0.365610] 00000000 8fc94e20 8fc0de30 80690000
>> 00000018 803592dc 00000000 806d0000
>> [ 0.365627] ...
>> [ 0.365634] Call Trace:
>> [ 0.365647] [<8001b9a0>] show_stack+0x6c/0x12c
>> [ 0.365663] [<804aed20>] dump_stack+0x98/0xc8
>> [ 0.365673] [<8003044c>] __warn+0xc4/0xe8
>> [ 0.365682] [<800304f4>] warn_slowpath_fmt+0x84/0xb8
>> [ 0.365690] [<800a886c>] smp_call_function_single+0x110/0x200
>> [ 0.365703] ---[ end trace 5785856ca39c79d5 ]---
>> [ 0.365557] 8065ce38 8fc0dc8c 806d0000 00000000
>> 80670000 00000001 8fc0dc20 59c73bcd
>> [ 0.365574] 00000000 00000000 806f0000 80670000
>> 00000000 806dab00 00000000 2d302e35
>> [ 0.365591] 203a6d6d 806e0000 806e0000 70617773
>> 80670000 00000000 00000000 00000009
>> [ 0.365610] 00000000 8fc94e20 8fc0de30 80690000
>> 00000018 803592dc 00000000 806d0000
>> [ 0.365627] ...
>> [ 0.365634] Call Trace:
>> [ 0.365647] [<8001b9a0>] show_stack+0x6c/0x12c
>> [ 0.365663] [<804aed20>] dump_stack+0x98/0xc8
>> [ 0.365673] [<8003044c>] __warn+0xc4/0xe8
>> [ 0.365682] [<800304f4>] warn_slowpath_fmt+0x84/0xb8
>> [ 0.365690] [<800a886c>] smp_call_function_single+0x110/0x200
>> [ 0.365703] ---[ end trace 5785856ca39c79d5 ]---
>>
>> v2->v3:
>> No Change.
>>
>> v3->v4:
>> Rebase on top of kernel 5.6-rc1.
>>
>> drivers/clocksource/ingenic-timer.c | 200
>> ++++++++++++++++++++++++------------
>> 1 file changed, 134 insertions(+), 66 deletions(-)
>>
>> diff --git a/drivers/clocksource/ingenic-timer.c
>> b/drivers/clocksource/ingenic-timer.c
>> index 4bbdb3d..9127c73 100644
>> --- a/drivers/clocksource/ingenic-timer.c
>> +++ b/drivers/clocksource/ingenic-timer.c
>> @@ -1,7 +1,8 @@
>> // SPDX-License-Identifier: GPL-2.0
>> /*
>> - * JZ47xx SoCs TCU IRQ driver
>> + * XBurst SoCs TCU IRQ driver
>> * Copyright (C) 2019 Paul Cercueil <[email protected]>
>> + * Copyright (C) 2020 周琰杰 (Zhou Yanjie) <[email protected]>
>> */
>>
>> #include <linux/bitops.h>
>> @@ -21,18 +22,23 @@
>>
>> #include <dt-bindings/clock/ingenic,tcu.h>
>>
>> +static DEFINE_PER_CPU(call_single_data_t, ingenic_cevt_csd);
>> +
>> struct ingenic_soc_info {
>> unsigned int num_channels;
>> };
>>
>> struct ingenic_tcu {
>> struct regmap *map;
>> + struct device_node *np;
>> struct clk *timer_clk, *cs_clk;
>> + unsigned int timer_local[NR_CPUS];
>> unsigned int timer_channel, cs_channel;
>> struct clock_event_device cevt;
>> struct clocksource cs;
>> - char name[4];
>> + char name[16];
>> unsigned long pwm_channels_mask;
>> + int cpu;
>> };
>>
>> static struct ingenic_tcu *ingenic_tcu;
>> @@ -81,6 +87,25 @@ static int ingenic_tcu_cevt_set_next(unsigned long
>> next,
>> return 0;
>> }
>>
>> +static void ingenic_per_cpu_event_handler(void *info)
>> +{
>> + struct clock_event_device *cevt = (struct clock_event_device *)
>> info;
>> +
>> + if (cevt->event_handler)
>> + cevt->event_handler(cevt);
>> +}
>> +
>> +static void ingenic_tcu_per_cpu_cb(struct clock_event_device *evt)
>> +{
>> + struct ingenic_tcu *tcu = to_ingenic_tcu(evt);
>> + call_single_data_t *csd;
>> +
>> + csd = &per_cpu(ingenic_cevt_csd, tcu->cpu);
>> + csd->info = (void *) evt;
>> + csd->func = ingenic_per_cpu_event_handler;
>> + smp_call_function_single_async(tcu->cpu, csd);
>> +}
>> +
>> static irqreturn_t ingenic_tcu_cevt_cb(int irq, void *dev_id)
>> {
>> struct clock_event_device *evt = dev_id;
>> @@ -88,8 +113,7 @@ static irqreturn_t ingenic_tcu_cevt_cb(int irq,
>> void *dev_id)
>>
>> regmap_write(tcu->map, TCU_REG_TECR, BIT(tcu->timer_channel));
>>
>> - if (evt->event_handler)
>> - evt->event_handler(evt);
>> + ingenic_tcu_per_cpu_cb(evt);
>
> I guess the check for (evt->event_handler) is still valid here.
> There's no point in calling ingenic_tcu_per_cpu_cb() if in the end the
> handler won't do anything.
>
Sure, I will fix it in v5.
>>
>> return IRQ_HANDLED;
>> }
>> @@ -105,14 +129,73 @@ static struct clk * __init
>> ingenic_tcu_get_clock(struct device_node *np, int id)
>> return of_clk_get_from_provider(&args);
>> }
>>
>> -static int __init ingenic_tcu_timer_init(struct device_node *np,
>> - struct ingenic_tcu *tcu)
>> +static int __init ingenic_tcu_clocksource_init(struct device_node *np,
>> + struct ingenic_tcu *tcu)
>
> Please - don't move functions around. It makes the patch extremely
> hard to review. Just add a forward declaration for
> ingenic_tcu_clocksource_init() at the top of the file.
Sure.
>
>> +{
>> + unsigned int channel = tcu->cs_channel;
>> + struct clocksource *cs = &tcu->cs;
>> + unsigned long rate;
>> + int err;
>> +
>> + tcu->cs_clk = ingenic_tcu_get_clock(np, channel);
>> + if (IS_ERR(tcu->cs_clk))
>> + return PTR_ERR(tcu->cs_clk);
>> +
>> + err = clk_prepare_enable(tcu->cs_clk);
>> + if (err)
>> + goto err_clk_put;
>> +
>> + rate = clk_get_rate(tcu->cs_clk);
>> + if (!rate) {
>> + err = -EINVAL;
>> + goto err_clk_disable;
>> + }
>> +
>> + /* Reset channel */
>> + regmap_update_bits(tcu->map, TCU_REG_TCSRc(channel),
>> + 0xffff & ~TCU_TCSR_RESERVED_BITS, 0);
>> +
>> + /* Reset counter */
>> + regmap_write(tcu->map, TCU_REG_TDFRc(channel), 0xffff);
>> + regmap_write(tcu->map, TCU_REG_TCNTc(channel), 0);
>> +
>> + /* Enable channel */
>> + regmap_write(tcu->map, TCU_REG_TESR, BIT(channel));
>> +
>> + cs->name = "ingenic-timer";
>> + cs->rating = 200;
>> + cs->flags = CLOCK_SOURCE_IS_CONTINUOUS;
>> + cs->mask = CLOCKSOURCE_MASK(16);
>> + cs->read = ingenic_tcu_timer_cs_read;
>> +
>> + err = clocksource_register_hz(cs, rate);
>> + if (err)
>> + goto err_clk_disable;
>> +
>> + return 0;
>> +
>> +err_clk_disable:
>> + clk_disable_unprepare(tcu->cs_clk);
>> +err_clk_put:
>> + clk_put(tcu->cs_clk);
>> + return err;
>> +}
>> +
>> +static int ingenic_tcu_setup_per_cpu_cevt(struct device_node *np,
>> + unsigned int channel)
>> {
>> - unsigned int timer_virq, channel = tcu->timer_channel;
>> + unsigned int timer_virq;
>> struct irq_domain *domain;
>> + struct ingenic_tcu *tcu;
>> unsigned long rate;
>> int err;
>>
>> + tcu = kzalloc(sizeof(*tcu), GFP_KERNEL);
>> + if (!tcu)
>> + return -ENOMEM;
>> +
>> + tcu->map = ingenic_tcu->map;
>> +
>> tcu->timer_clk = ingenic_tcu_get_clock(np, channel);
>> if (IS_ERR(tcu->timer_clk))
>> return PTR_ERR(tcu->timer_clk);
>> @@ -139,13 +222,15 @@ static int __init ingenic_tcu_timer_init(struct
>> device_node *np,
>> goto err_clk_disable;
>> }
>>
>> - snprintf(tcu->name, sizeof(tcu->name), "TCU");
>> + snprintf(tcu->name, sizeof(tcu->name), "TCU channel.%u", channel);
>
> Make it TCU%u
>
OK.
>>
>> err = request_irq(timer_virq, ingenic_tcu_cevt_cb, IRQF_TIMER,
>> tcu->name, &tcu->cevt);
>> if (err)
>> goto err_irq_dispose_mapping;
>>
>> + tcu->cpu = smp_processor_id();
>> + tcu->timer_channel = channel;
>> tcu->cevt.cpumask = cpumask_of(smp_processor_id());
>> tcu->cevt.features = CLOCK_EVT_FEAT_ONESHOT;
>> tcu->cevt.name = tcu->name;
>> @@ -166,56 +251,23 @@ static int __init ingenic_tcu_timer_init(struct
>> device_node *np,
>> return err;
>> }
>>
>> -static int __init ingenic_tcu_clocksource_init(struct device_node *np,
>> - struct ingenic_tcu *tcu)
>> +static int ingenic_tcu_setup_cevt(unsigned int cpu)
>> {
>> - unsigned int channel = tcu->cs_channel;
>> - struct clocksource *cs = &tcu->cs;
>> - unsigned long rate;
>> - int err;
>> -
>> - tcu->cs_clk = ingenic_tcu_get_clock(np, channel);
>> - if (IS_ERR(tcu->cs_clk))
>> - return PTR_ERR(tcu->cs_clk);
>> -
>> - err = clk_prepare_enable(tcu->cs_clk);
>> - if (err)
>> - goto err_clk_put;
>> -
>> - rate = clk_get_rate(tcu->cs_clk);
>> - if (!rate) {
>> - err = -EINVAL;
>> - goto err_clk_disable;
>> - }
>> -
>> - /* Reset channel */
>> - regmap_update_bits(tcu->map, TCU_REG_TCSRc(channel),
>> - 0xffff & ~TCU_TCSR_RESERVED_BITS, 0);
>> -
>> - /* Reset counter */
>> - regmap_write(tcu->map, TCU_REG_TDFRc(channel), 0xffff);
>> - regmap_write(tcu->map, TCU_REG_TCNTc(channel), 0);
>> -
>> - /* Enable channel */
>> - regmap_write(tcu->map, TCU_REG_TESR, BIT(channel));
>> -
>> - cs->name = "ingenic-timer";
>> - cs->rating = 200;
>> - cs->flags = CLOCK_SOURCE_IS_CONTINUOUS;
>> - cs->mask = CLOCKSOURCE_MASK(16);
>> - cs->read = ingenic_tcu_timer_cs_read;
>> + int ret;
>>
>> - err = clocksource_register_hz(cs, rate);
>> - if (err)
>> - goto err_clk_disable;
>> + ret = ingenic_tcu_setup_per_cpu_cevt(ingenic_tcu->np,
>> + ingenic_tcu->timer_local[cpu]);
>> + if (ret)
>> + goto err_tcu_clocksource_cleanup;
>>
>> return 0;
>>
>> -err_clk_disable:
>> - clk_disable_unprepare(tcu->cs_clk);
>> -err_clk_put:
>> - clk_put(tcu->cs_clk);
>> - return err;
>> +err_tcu_clocksource_cleanup:
>> + clocksource_unregister(&ingenic_tcu->cs);
>> + clk_disable_unprepare(ingenic_tcu->cs_clk);
>> + clk_put(ingenic_tcu->cs_clk);
>> + kfree(ingenic_tcu);
>> + return ret;
>> }
>>
>> static const struct ingenic_soc_info jz4740_soc_info = {
>> @@ -239,6 +291,7 @@ static int __init ingenic_tcu_init(struct
>> device_node *np)
>> const struct ingenic_soc_info *soc_info = id->data;
>> struct ingenic_tcu *tcu;
>> struct regmap *map;
>> + unsigned cpu = 0;
>> long rate;
>> int ret;
>>
>> @@ -253,12 +306,14 @@ static int __init ingenic_tcu_init(struct
>> device_node *np)
>> return -ENOMEM;
>>
>> /* Enable all TCU channels for PWM use by default except
>> channels 0/1 */
>> - tcu->pwm_channels_mask = GENMASK(soc_info->num_channels - 1, 2);
>> + tcu->pwm_channels_mask = GENMASK(soc_info->num_channels - 1,
>> + NR_CPUS + 1);
>> of_property_read_u32(np, "ingenic,pwm-channels-mask",
>> (u32 *)&tcu->pwm_channels_mask);
>>
>> /* Verify that we have at least two free channels */
>> - if (hweight8(tcu->pwm_channels_mask) > soc_info->num_channels -
>> 2) {
>> + if (hweight8(tcu->pwm_channels_mask) >
>> + soc_info->num_channels - NR_CPUS + 1) {
>> pr_crit("%s: Invalid PWM channel mask: 0x%02lx\n", __func__,
>> tcu->pwm_channels_mask);
>> ret = -EINVAL;
>> @@ -266,13 +321,29 @@ static int __init ingenic_tcu_init(struct
>> device_node *np)
>> }
>>
>> tcu->map = map;
>> + tcu->np = np;
>> ingenic_tcu = tcu;
>>
>> - tcu->timer_channel = find_first_zero_bit(&tcu->pwm_channels_mask,
>> + tcu->timer_local[cpu] =
>> find_first_zero_bit(&tcu->pwm_channels_mask,
>> soc_info->num_channels);
>> - tcu->cs_channel = find_next_zero_bit(&tcu->pwm_channels_mask,
>> - soc_info->num_channels,
>> - tcu->timer_channel + 1);
>> +
>> + if (NR_CPUS > 1) {
>> + for (cpu = 1; cpu < NR_CPUS; cpu++)
>> + tcu->timer_local[cpu] = find_next_zero_bit(
>> + &tcu->pwm_channels_mask,
>> + soc_info->num_channels,
>> + tcu->timer_local[cpu - 1] + 1);
>> +
>> + tcu->cs_channel = find_next_zero_bit(&tcu->pwm_channels_mask,
>> + soc_info->num_channels,
>> + tcu->timer_local[cpu-1] + 1);
>> + } else {
>> + tcu->cs_channel = find_next_zero_bit(&tcu->pwm_channels_mask,
>> + soc_info->num_channels,
>> + tcu->timer_local[cpu] + 1);
>> + }
>> +
>> +
>>
>> ret = ingenic_tcu_clocksource_init(np, tcu);
>> if (ret) {
>> @@ -280,9 +351,10 @@ static int __init ingenic_tcu_init(struct
>> device_node *np)
>> goto err_free_ingenic_tcu;
>> }
>>
>> - ret = ingenic_tcu_timer_init(np, tcu);
>> - if (ret)
>> - goto err_tcu_clocksource_cleanup;
>> + /* Setup clock events on each CPU core */
>> + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "Ingenic XBurst:
>> online",
>> + ingenic_tcu_setup_cevt, NULL);
>> + WARN_ON(ret < 0);
>>
>> /* Register the sched_clock at the end as there's no way to undo
>> it */
>> rate = clk_get_rate(tcu->cs_clk);
>> @@ -290,10 +362,6 @@ static int __init ingenic_tcu_init(struct
>> device_node *np)
>>
>> return 0;
>>
>> -err_tcu_clocksource_cleanup:
>> - clocksource_unregister(&tcu->cs);
>> - clk_disable_unprepare(tcu->cs_clk);
>> - clk_put(tcu->cs_clk);
>> err_free_ingenic_tcu:
>> kfree(tcu);
>> return ret;
>> --
>> 2.7.4
>>
>
Hi Paul,
On 2020年02月15日 02:21, Paul Cercueil wrote:
> Hi Zhou,
>
> The changes to drivers/clk/ingenic/jz4780-cgu.c look sound but they
> really don't belong in this patch.
>
> Please split them to another patch.
Sure., I will split them.
>
> -Paul
>
>
> Le sam., févr. 15, 2020 at 02:02, 周琰杰 (Zhou Yanjie)
> <[email protected]> a écrit :
>> Forward port smp support from kernel 3.18.3 of CI20_linux
>> to upstream kernel 5.5.
>>
>> Tested-by: H. Nikolaus Schaller <[email protected]>
>> Tested-by: Paul Boddie <[email protected]>
>> Signed-off-by: 周琰杰 (Zhou Yanjie) <[email protected]>
>> ---
>>
>> Notes:
>> v1->v2:
>> 1.Remove unnecessary "plat_irq_dispatch(void)" in irq-ingenic.c.
>> 2.Add a timeout check for "jz4780_boot_secondary()" to avoid a
>> dead loop.
>> 3.Replace hard code in smp.c with macro.
>>
>> v2->v3:
>> 1.Remove unnecessary "extern void (*r4k_blast_dcache)(void)" in
>> smp.c.
>> 2.Use "for_each_of_cpu_node" instead "for_each_compatible_node"
>> in smp.c.
>> 3.Use "of_cpu_node_to_id" instead "of_property_read_u32_index" in
>> smp.c.
>> 4.Move LCR related operations to jz4780-cgu.c.
>>
>> v3->v4:
>> Rebase on top of kernel 5.6-rc1.
>>
>> arch/mips/include/asm/mach-jz4740/jz4780-smp.h | 91 ++++++++
>> arch/mips/jz4740/Kconfig | 3 +
>> arch/mips/jz4740/Makefile | 5 +
>> arch/mips/jz4740/prom.c | 4 +
>> arch/mips/jz4740/smp-entry.S | 57 +++++
>> arch/mips/jz4740/smp.c | 286
>> +++++++++++++++++++++++++
>> arch/mips/kernel/idle.c | 14 +-
>> drivers/clk/ingenic/jz4780-cgu.c | 58 ++++-
>> 8 files changed, 512 insertions(+), 6 deletions(-)
>> create mode 100644 arch/mips/include/asm/mach-jz4740/jz4780-smp.h
>> create mode 100644 arch/mips/jz4740/smp-entry.S
>> create mode 100644 arch/mips/jz4740/smp.c
>>
>> diff --git a/arch/mips/include/asm/mach-jz4740/jz4780-smp.h
>> b/arch/mips/include/asm/mach-jz4740/jz4780-smp.h
>> new file mode 100644
>> index 00000000..3f592ce
>> --- /dev/null
>> +++ b/arch/mips/include/asm/mach-jz4740/jz4780-smp.h
>> @@ -0,0 +1,91 @@
>> +/* SPDX-License-Identifier: GPL-2.0-or-later */
>> +/*
>> + * Copyright (C) 2013, Paul Burton <[email protected]>
>> + * JZ4780 SMP definitions
>> + */
>> +
>> +#ifndef __MIPS_ASM_MACH_JZ4740_JZ4780_SMP_H__
>> +#define __MIPS_ASM_MACH_JZ4740_JZ4780_SMP_H__
>> +
>> +#define read_c0_corectrl() __read_32bit_c0_register($12, 2)
>> +#define write_c0_corectrl(val) __write_32bit_c0_register($12, 2, val)
>> +
>> +#define read_c0_corestatus() __read_32bit_c0_register($12, 3)
>> +#define write_c0_corestatus(val) __write_32bit_c0_register($12, 3, val)
>> +
>> +#define read_c0_reim() __read_32bit_c0_register($12, 4)
>> +#define write_c0_reim(val) __write_32bit_c0_register($12, 4, val)
>> +
>> +#define read_c0_mailbox0() __read_32bit_c0_register($20, 0)
>> +#define write_c0_mailbox0(val) __write_32bit_c0_register($20, 0, val)
>> +
>> +#define read_c0_mailbox1() __read_32bit_c0_register($20, 1)
>> +#define write_c0_mailbox1(val) __write_32bit_c0_register($20, 1, val)
>> +
>> +#define smp_clr_pending(mask) do { \
>> + unsigned int stat; \
>> + stat = read_c0_corestatus(); \
>> + stat &= ~((mask) & 0xff); \
>> + write_c0_corestatus(stat); \
>> + } while (0)
>> +
>> +/*
>> + * Core Control register
>> + */
>> +#define CORECTRL_SLEEP1M_SHIFT 17
>> +#define CORECTRL_SLEEP1M (_ULCAST_(0x1) << CORECTRL_SLEEP1M_SHIFT)
>> +#define CORECTRL_SLEEP0M_SHIFT 16
>> +#define CORECTRL_SLEEP0M (_ULCAST_(0x1) << CORECTRL_SLEEP0M_SHIFT)
>> +#define CORECTRL_RPC1_SHIFT 9
>> +#define CORECTRL_RPC1 (_ULCAST_(0x1) << CORECTRL_RPC1_SHIFT)
>> +#define CORECTRL_RPC0_SHIFT 8
>> +#define CORECTRL_RPC0 (_ULCAST_(0x1) << CORECTRL_RPC0_SHIFT)
>> +#define CORECTRL_SWRST1_SHIFT 1
>> +#define CORECTRL_SWRST1 (_ULCAST_(0x1) << CORECTRL_SWRST1_SHIFT)
>> +#define CORECTRL_SWRST0_SHIFT 0
>> +#define CORECTRL_SWRST0 (_ULCAST_(0x1) << CORECTRL_SWRST0_SHIFT)
>> +
>> +/*
>> + * Core Status register
>> + */
>> +#define CORESTATUS_SLEEP1_SHIFT 17
>> +#define CORESTATUS_SLEEP1 (_ULCAST_(0x1) << CORESTATUS_SLEEP1_SHIFT)
>> +#define CORESTATUS_SLEEP0_SHIFT 16
>> +#define CORESTATUS_SLEEP0 (_ULCAST_(0x1) << CORESTATUS_SLEEP0_SHIFT)
>> +#define CORESTATUS_IRQ1P_SHIFT 9
>> +#define CORESTATUS_IRQ1P (_ULCAST_(0x1) << CORESTATUS_IRQ1P_SHIFT)
>> +#define CORESTATUS_IRQ0P_SHIFT 8
>> +#define CORESTATUS_IRQ0P (_ULCAST_(0x1) << CORESTATUS_IRQ8P_SHIFT)
>> +#define CORESTATUS_MIRQ1P_SHIFT 1
>> +#define CORESTATUS_MIRQ1P (_ULCAST_(0x1) << CORESTATUS_MIRQ1P_SHIFT)
>> +#define CORESTATUS_MIRQ0P_SHIFT 0
>> +#define CORESTATUS_MIRQ0P (_ULCAST_(0x1) << CORESTATUS_MIRQ0P_SHIFT)
>> +
>> +/*
>> + * Reset Entry & IRQ Mask register
>> + */
>> +#define REIM_ENTRY_SHIFT 16
>> +#define REIM_ENTRY (_ULCAST_(0xffff) << REIM_ENTRY_SHIFT)
>> +#define REIM_IRQ1M_SHIFT 9
>> +#define REIM_IRQ1M (_ULCAST_(0x1) << REIM_IRQ1M_SHIFT)
>> +#define REIM_IRQ0M_SHIFT 8
>> +#define REIM_IRQ0M (_ULCAST_(0x1) << REIM_IRQ0M_SHIFT)
>> +#define REIM_MBOXIRQ1M_SHIFT 1
>> +#define REIM_MBOXIRQ1M (_ULCAST_(0x1) << REIM_MBOXIRQ1M_SHIFT)
>> +#define REIM_MBOXIRQ0M_SHIFT 0
>> +#define REIM_MBOXIRQ0M (_ULCAST_(0x1) << REIM_MBOXIRQ0M_SHIFT)
>> +
>> +#ifdef CONFIG_SMP
>> +
>> +extern void jz4780_smp_wait_irqoff(void);
>> +
>> +extern void jz4780_smp_init(void);
>> +extern void jz4780_secondary_cpu_entry(void);
>> +
>> +#else /* !CONFIG_SMP */
>> +
>> +static inline void jz4780_smp_init(void) { }
>> +
>> +#endif /* !CONFIG_SMP */
>> +
>> +#endif /* __MIPS_ASM_MACH_JZ4740_JZ4780_SMP_H__ */
>> diff --git a/arch/mips/jz4740/Kconfig b/arch/mips/jz4740/Kconfig
>> index 412d2fa..0239597 100644
>> --- a/arch/mips/jz4740/Kconfig
>> +++ b/arch/mips/jz4740/Kconfig
>> @@ -34,9 +34,12 @@ config MACH_JZ4770
>>
>> config MACH_JZ4780
>> bool
>> + select GENERIC_CLOCKEVENTS_BROADCAST if SMP
>> select MIPS_CPU_SCACHE
>> + select NR_CPUS_DEFAULT_2
>> select SYS_HAS_CPU_MIPS32_R2
>> select SYS_SUPPORTS_HIGHMEM
>> + select SYS_SUPPORTS_SMP
>>
>> config MACH_X1000
>> bool
>> diff --git a/arch/mips/jz4740/Makefile b/arch/mips/jz4740/Makefile
>> index 6de14c0..0a0f024 100644
>> --- a/arch/mips/jz4740/Makefile
>> +++ b/arch/mips/jz4740/Makefile
>> @@ -12,3 +12,8 @@ CFLAGS_setup.o = -I$(src)/../../../scripts/dtc/libfdt
>> # PM support
>>
>> obj-$(CONFIG_PM) += pm.o
>> +
>> +# SMP support
>> +
>> +obj-$(CONFIG_SMP) += smp.o
>> +obj-$(CONFIG_SMP) += smp-entry.o
>> diff --git a/arch/mips/jz4740/prom.c b/arch/mips/jz4740/prom.c
>> index ff4555c..a79159e 100644
>> --- a/arch/mips/jz4740/prom.c
>> +++ b/arch/mips/jz4740/prom.c
>> @@ -8,10 +8,14 @@
>>
>> #include <asm/bootinfo.h>
>> #include <asm/fw/fw.h>
>> +#include <asm/mach-jz4740/jz4780-smp.h>
>>
>> void __init prom_init(void)
>> {
>> fw_init_cmdline();
>> +#if defined(CONFIG_MACH_JZ4780) && defined(CONFIG_SMP)
>> + jz4780_smp_init();
>> +#endif
>> }
>>
>> void __init prom_free_prom_memory(void)
>> diff --git a/arch/mips/jz4740/smp-entry.S b/arch/mips/jz4740/smp-entry.S
>> new file mode 100644
>> index 00000000..20049a3
>> --- /dev/null
>> +++ b/arch/mips/jz4740/smp-entry.S
>> @@ -0,0 +1,57 @@
>> +/* SPDX-License-Identifier: GPL-2.0-or-later */
>> +/*
>> + * Copyright (C) 2013, Paul Burton <[email protected]>
>> + * JZ4780 SMP entry point
>> + */
>> +
>> +#include <asm/addrspace.h>
>> +#include <asm/asm.h>
>> +#include <asm/asmmacro.h>
>> +#include <asm/cacheops.h>
>> +#include <asm/mipsregs.h>
>> +
>> +#define CACHE_SIZE (32 * 1024)
>> +#define CACHE_LINESIZE 32
>> +
>> +.extern jz4780_cpu_entry_sp
>> +.extern jz4780_cpu_entry_gp
>> +
>> +.section .text.smp-entry
>> +.balign 0x10000
>> +.set noreorder
>> +LEAF(jz4780_secondary_cpu_entry)
>> + mtc0 zero, CP0_CAUSE
>> +
>> + li t0, ST0_CU0
>> + mtc0 t0, CP0_STATUS
>> +
>> + /* cache setup */
>> + li t0, KSEG0
>> + ori t1, t0, CACHE_SIZE
>> + mtc0 zero, CP0_TAGLO, 0
>> +1: cache Index_Store_Tag_I, 0(t0)
>> + cache Index_Store_Tag_D, 0(t0)
>> + bne t0, t1, 1b
>> + addiu t0, t0, CACHE_LINESIZE
>> +
>> + /* kseg0 cache attribute */
>> + mfc0 t0, CP0_CONFIG, 0
>> + ori t0, t0, CONF_CM_CACHABLE_NONCOHERENT
>> + mtc0 t0, CP0_CONFIG, 0
>> +
>> + /* pagemask */
>> + mtc0 zero, CP0_PAGEMASK, 0
>> +
>> + /* retrieve sp */
>> + la t0, jz4780_cpu_entry_sp
>> + lw sp, 0(t0)
>> +
>> + /* retrieve gp */
>> + la t0, jz4780_cpu_entry_gp
>> + lw gp, 0(t0)
>> +
>> + /* jump to the kernel in kseg0 */
>> + la t0, smp_bootstrap
>> + jr t0
>> + nop
>> + END(jz4780_secondary_cpu_entry)
>> diff --git a/arch/mips/jz4740/smp.c b/arch/mips/jz4740/smp.c
>> new file mode 100644
>> index 00000000..19b75c2
>> --- /dev/null
>> +++ b/arch/mips/jz4740/smp.c
>> @@ -0,0 +1,286 @@
>> +// SPDX-License-Identifier: GPL-2.0
>> +/*
>> + * Copyright (C) 2013, Paul Burton <[email protected]>
>> + * JZ4780 SMP
>> + */
>> +
>> +#include <linux/clk.h>
>> +#include <linux/delay.h>
>> +#include <linux/interrupt.h>
>> +#include <linux/of.h>
>> +#include <linux/sched.h>
>> +#include <linux/sched/task_stack.h>
>> +#include <linux/smp.h>
>> +#include <linux/tick.h>
>> +#include <asm/mach-jz4740/jz4780-smp.h>
>> +#include <asm/r4kcache.h>
>> +#include <asm/smp-ops.h>
>> +
>> +static struct clk *cpu_clock_gates[CONFIG_NR_CPUS] = { NULL };
>> +
>> +u32 jz4780_cpu_entry_sp;
>> +u32 jz4780_cpu_entry_gp;
>> +
>> +static struct cpumask cpu_running;
>> +
>> +static DEFINE_SPINLOCK(smp_lock);
>> +
>> +/*
>> + * The Ingenic jz4780 SMP variant has to write back dirty cache
>> lines before
>> + * executing wait. The CPU & cache clock will be gated until we
>> return from
>> + * the wait, and if another core attempts to access data from our
>> data cache
>> + * during this time then it will lock up.
>> + */
>> +void jz4780_smp_wait_irqoff(void)
>> +{
>> + unsigned long pending = read_c0_cause() & read_c0_status() &
>> CAUSEF_IP;
>> +
>> + /*
>> + * Going to idle has a significant overhead due to the cache
>> flush so
>> + * try to avoid it if we'll immediately be woken again due to an
>> IRQ.
>> + */
>> + if (!need_resched() && !pending) {
>> + r4k_blast_dcache();
>> +
>> + __asm__(
>> + " .set push \n"
>> + " .set mips3 \n"
>> + " sync \n"
>> + " wait \n"
>> + " .set pop \n");
>> + }
>> +
>> + local_irq_enable();
>> +}
>> +
>> +static irqreturn_t mbox_handler(int irq, void *dev_id)
>> +{
>> + int cpu = smp_processor_id();
>> + u32 action, status;
>> +
>> + spin_lock(&smp_lock);
>> +
>> + switch (cpu) {
>> + case 0:
>> + action = read_c0_mailbox0();
>> + write_c0_mailbox0(0);
>> + break;
>> + case 1:
>> + action = read_c0_mailbox1();
>> + write_c0_mailbox1(0);
>> + break;
>> + default:
>> + panic("unhandled cpu %d!", cpu);
>> + }
>> +
>> + /* clear pending mailbox interrupt */
>> + status = read_c0_corestatus();
>> + status &= ~(CORESTATUS_MIRQ0P << cpu);
>> + write_c0_corestatus(status);
>> +
>> + spin_unlock(&smp_lock);
>> +
>> + if (action & SMP_RESCHEDULE_YOURSELF)
>> + scheduler_ipi();
>> + if (action & SMP_CALL_FUNCTION)
>> + generic_smp_call_function_interrupt();
>> +
>> + return IRQ_HANDLED;
>> +}
>> +
>> +static struct irqaction mbox_action = {
>> + .handler = mbox_handler,
>> + .name = "core mailbox",
>> + .flags = IRQF_PERCPU | IRQF_NO_THREAD,
>> +};
>> +
>> +static void jz4780_smp_setup(void)
>> +{
>> + u32 addr, reim;
>> + int cpu;
>> +
>> + reim = read_c0_reim();
>> +
>> + for (cpu = 0; cpu < NR_CPUS; cpu++) {
>> + __cpu_number_map[cpu] = cpu;
>> + __cpu_logical_map[cpu] = cpu;
>> + set_cpu_possible(cpu, true);
>> + }
>> +
>> + /* mask mailbox interrupts for this core */
>> + reim &= ~REIM_MBOXIRQ0M;
>> + write_c0_reim(reim);
>> +
>> + /* clear mailboxes & pending mailbox IRQs */
>> + write_c0_mailbox0(0);
>> + write_c0_mailbox1(0);
>> + write_c0_corestatus(0);
>> +
>> + /* set reset entry point */
>> + addr = KSEG1ADDR((u32)&jz4780_secondary_cpu_entry);
>> + WARN_ON(addr & ~REIM_ENTRY);
>> + reim &= ~REIM_ENTRY;
>> + reim |= addr & REIM_ENTRY;
>> +
>> + /* unmask mailbox interrupts for this core */
>> + reim |= REIM_MBOXIRQ0M;
>> + write_c0_reim(reim);
>> + set_c0_status(STATUSF_IP3);
>> + irq_enable_hazard();
>> +
>> + cpumask_set_cpu(cpu, &cpu_running);
>> +}
>> +
>> +static void jz4780_smp_prepare_cpus(unsigned int max_cpus)
>> +{
>> + struct device_node *cpu_node;
>> + unsigned cpu, ctrl;
>> + int err;
>> +
>> + /* setup the mailbox IRQ */
>> + setup_irq(MIPS_CPU_IRQ_BASE + 3, &mbox_action);
>> +
>> + init_cpu_present(cpu_possible_mask);
>> +
>> + ctrl = read_c0_corectrl();
>> +
>> + for (cpu = 0; cpu < max_cpus; cpu++) {
>> + /* use reset entry point from REIM register */
>> + ctrl |= CORECTRL_RPC0 << cpu;
>> + }
>> +
>> + for_each_of_cpu_node(cpu_node) {
>> + cpu = of_cpu_node_to_id(cpu_node);
>> + if (cpu < 0) {
>> + pr_err("Failed to read index of %s\n",
>> + cpu_node->full_name);
>> + continue;
>> + }
>> +
>> + cpu_clock_gates[cpu] = of_clk_get(cpu_node, 0);
>> + if (IS_ERR(cpu_clock_gates[cpu])) {
>> + cpu_clock_gates[cpu] = NULL;
>> + continue;
>> + }
>> +
>> + err = clk_prepare(cpu_clock_gates[cpu]);
>> + if (err)
>> + pr_err("Failed to prepare CPU clock gate\n");
>> + }
>> +
>> + write_c0_corectrl(ctrl);
>> +}
>> +
>> +static int jz4780_boot_secondary(int cpu, struct task_struct *idle)
>> +{
>> + unsigned long flags;
>> + u32 ctrl;
>> +
>> + spin_lock_irqsave(&smp_lock, flags);
>> +
>> + /* ensure the core is in reset */
>> + ctrl = read_c0_corectrl();
>> + ctrl |= CORECTRL_SWRST0 << cpu;
>> + write_c0_corectrl(ctrl);
>> +
>> + /* ungate core clock */
>> + if (cpu_clock_gates[cpu])
>> + clk_enable(cpu_clock_gates[cpu]);
>> +
>> + /* set entry sp/gp register values */
>> + jz4780_cpu_entry_sp = __KSTK_TOS(idle);
>> + jz4780_cpu_entry_gp = (u32)task_thread_info(idle);
>> + smp_wmb();
>> +
>> + /* take the core out of reset */
>> + ctrl &= ~(CORECTRL_SWRST0 << cpu);
>> + write_c0_corectrl(ctrl);
>> +
>> + cpumask_set_cpu(cpu, &cpu_running);
>> +
>> + spin_unlock_irqrestore(&smp_lock, flags);
>> +
>> + return 0;
>> +}
>> +
>> +static void jz4780_init_secondary(void)
>> +{
>> +}
>> +
>> +static void jz4780_smp_finish(void)
>> +{
>> + u32 reim;
>> +
>> + spin_lock(&smp_lock);
>> +
>> + /* unmask mailbox interrupts for this core */
>> + reim = read_c0_reim();
>> + reim |= REIM_MBOXIRQ0M << smp_processor_id();
>> + write_c0_reim(reim);
>> +
>> + spin_unlock(&smp_lock);
>> +
>> + /* unmask interrupts for this core */
>> + change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP2 |
>> + STATUSF_IP1 | STATUSF_IP0);
>> + irq_enable_hazard();
>> +
>> + /* force broadcast timer */
>> + tick_broadcast_force();
>> +}
>> +
>> +static void jz4780_send_ipi_single_locked(int cpu, unsigned int action)
>> +{
>> + u32 mbox;
>> +
>> + switch (cpu) {
>> + case 0:
>> + mbox = read_c0_mailbox0();
>> + write_c0_mailbox0(mbox | action);
>> + break;
>> + case 1:
>> + mbox = read_c0_mailbox1();
>> + write_c0_mailbox1(mbox | action);
>> + break;
>> + default:
>> + panic("unhandled cpu %d!", cpu);
>> + }
>> +}
>> +
>> +static void jz4780_send_ipi_single(int cpu, unsigned int action)
>> +{
>> + unsigned long flags;
>> +
>> + spin_lock_irqsave(&smp_lock, flags);
>> + jz4780_send_ipi_single_locked(cpu, action);
>> + spin_unlock_irqrestore(&smp_lock, flags);
>> +}
>> +
>> +static void jz4780_send_ipi_mask(const struct cpumask *mask,
>> + unsigned int action)
>> +{
>> + unsigned long flags;
>> + int cpu;
>> +
>> + spin_lock_irqsave(&smp_lock, flags);
>> +
>> + for_each_cpu(cpu, mask)
>> + jz4780_send_ipi_single_locked(cpu, action);
>> +
>> + spin_unlock_irqrestore(&smp_lock, flags);
>> +}
>> +
>> +static struct plat_smp_ops jz4780_smp_ops = {
>> + .send_ipi_single = jz4780_send_ipi_single,
>> + .send_ipi_mask = jz4780_send_ipi_mask,
>> + .init_secondary = jz4780_init_secondary,
>> + .smp_finish = jz4780_smp_finish,
>> + .boot_secondary = jz4780_boot_secondary,
>> + .smp_setup = jz4780_smp_setup,
>> + .prepare_cpus = jz4780_smp_prepare_cpus,
>> +};
>> +
>> +void jz4780_smp_init(void)
>> +{
>> + register_smp_ops(&jz4780_smp_ops);
>> +}
>> diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
>> index 37f8e78..a406de3 100644
>> --- a/arch/mips/kernel/idle.c
>> +++ b/arch/mips/kernel/idle.c
>> @@ -19,6 +19,10 @@
>> #include <asm/idle.h>
>> #include <asm/mipsregs.h>
>>
>> +#ifdef CONFIG_MACH_JZ4780
>> +# include <asm/mach-jz4740/jz4780-smp.h>
>> +#endif
>> +
>> /*
>> * Not all of the MIPS CPUs have the "wait" instruction available.
>> Moreover,
>> * the implementation of the "wait" feature differs between CPU
>> families. This
>> @@ -172,7 +176,6 @@ void __init check_wait(void)
>> case CPU_CAVIUM_OCTEON_PLUS:
>> case CPU_CAVIUM_OCTEON2:
>> case CPU_CAVIUM_OCTEON3:
>> - case CPU_XBURST:
>> case CPU_LOONGSON32:
>> case CPU_XLR:
>> case CPU_XLP:
>> @@ -246,6 +249,15 @@ void __init check_wait(void)
>> cpu_wait = r4k_wait;
>> */
>> break;
>> + case CPU_XBURST:
>> +#if defined(CONFIG_MACH_JZ4780) && defined(CONFIG_SMP)
>> + if (NR_CPUS > 1)
>> + cpu_wait = jz4780_smp_wait_irqoff;
>> + else
>> + cpu_wait = r4k_wait;
>> +#else
>> + cpu_wait = r4k_wait;
>> +#endif
>> default:
>> break;
>> }
>> diff --git a/drivers/clk/ingenic/jz4780-cgu.c
>> b/drivers/clk/ingenic/jz4780-cgu.c
>> index d07fff1..4f81819 100644
>> --- a/drivers/clk/ingenic/jz4780-cgu.c
>> +++ b/drivers/clk/ingenic/jz4780-cgu.c
>> @@ -16,7 +16,7 @@
>>
>> /* CGU register offsets */
>> #define CGU_REG_CLOCKCONTROL 0x00
>> -#define CGU_REG_PLLCONTROL 0x0c
>> +#define CGU_REG_LCR 0x04
>> #define CGU_REG_APLL 0x10
>> #define CGU_REG_MPLL 0x14
>> #define CGU_REG_EPLL 0x18
>> @@ -46,8 +46,8 @@
>> #define CGU_REG_CLOCKSTATUS 0xd4
>>
>> /* bits within the OPCR register */
>> -#define OPCR_SPENDN0 (1 << 7)
>> -#define OPCR_SPENDN1 (1 << 6)
>> +#define OPCR_SPENDN0 BIT(7)
>> +#define OPCR_SPENDN1 BIT(6)
>>
>> /* bits within the USBPCR register */
>> #define USBPCR_USB_MODE BIT(31)
>> @@ -88,6 +88,13 @@
>> #define USBVBFIL_IDDIGFIL_MASK (0xffff << USBVBFIL_IDDIGFIL_SHIFT)
>> #define USBVBFIL_USBVBFIL_MASK (0xffff)
>>
>> +/* bits within the LCR register */
>> +#define LCR_PD_SCPU BIT(31)
>> +#define LCR_SCPUS BIT(27)
>> +
>> +/* bits within the CLKGR1 register */
>> +#define CLKGR1_CORE1 BIT(15)
>> +
>> static struct ingenic_cgu *cgu;
>>
>> static u8 jz4780_otg_phy_get_parent(struct clk_hw *hw)
>> @@ -205,6 +212,47 @@ static const struct clk_ops jz4780_otg_phy_ops = {
>> .set_rate = jz4780_otg_phy_set_rate,
>> };
>>
>> +static int jz4780_core1_enable(struct clk_hw *hw)
>> +{
>> + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw);
>> + struct ingenic_cgu *cgu = ingenic_clk->cgu;
>> + const unsigned int timeout = 100;
>> + unsigned long flags;
>> + unsigned int i;
>> + u32 lcr, clkgr1;
>> +
>> + spin_lock_irqsave(&cgu->lock, flags);
>> +
>> + lcr = readl(cgu->base + CGU_REG_LCR);
>> + lcr &= ~LCR_PD_SCPU;
>> + writel(lcr, cgu->base + CGU_REG_LCR);
>> +
>> + clkgr1 = readl(cgu->base + CGU_REG_CLKGR1);
>> + clkgr1 &= ~CLKGR1_CORE1;
>> + writel(clkgr1, cgu->base + CGU_REG_CLKGR1);
>> +
>> + spin_unlock_irqrestore(&cgu->lock, flags);
>> +
>> + /* wait for the CPU to be powered up */
>> + for (i = 0; i < timeout; i++) {
>> + lcr = readl(cgu->base + CGU_REG_LCR);
>> + if (!(lcr & LCR_SCPUS))
>> + break;
>> + mdelay(1);
>> + }
>> +
>> + if (i == timeout) {
>> + pr_err("%s: Wait for power up core1 timeout\n", __func__);
>> + return -EBUSY;
>> + }
>> +
>> + return 0;
>> +}
>> +
>> +static const struct clk_ops jz4780_core1_ops = {
>> + .enable = jz4780_core1_enable,
>> +};
>> +
>> static const s8 pll_od_encoding[16] = {
>> 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
>> 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf,
>> @@ -701,9 +749,9 @@ static const struct ingenic_cgu_clk_info
>> jz4780_cgu_clocks[] = {
>> },
>>
>> [JZ4780_CLK_CORE1] = {
>> - "core1", CGU_CLK_GATE,
>> + "core1", CGU_CLK_CUSTOM,
>> .parents = { JZ4780_CLK_CPU, -1, -1, -1 },
>> - .gate = { CGU_REG_CLKGR1, 15 },
>> + .custom = { &jz4780_core1_ops },
>> },
>>
>> };
>> --
>> 2.7.4
>>
>
Hi,
On Sat, Feb 15, 2020 at 02:02:35AM +0800, 周琰杰 (Zhou Yanjie) wrote:
> + /* setup the mailbox IRQ */
> + setup_irq(MIPS_CPU_IRQ_BASE + 3, &mbox_action);
s/setup_irq/request_irq, see,
https://lkml.kernel.org/r/alpine.DEB.2.20.1710191609480.1971@nanos
https://lkml.kernel.org/r/[email protected]
Regards
afzal
Hi Afzal,
On 2020年02月15日 23:03, afzal mohammed wrote:
> Hi,
>
> On Sat, Feb 15, 2020 at 02:02:35AM +0800, 周琰杰 (Zhou Yanjie) wrote:
>
>> + /* setup the mailbox IRQ */
>> + setup_irq(MIPS_CPU_IRQ_BASE + 3, &mbox_action);
> s/setup_irq/request_irq, see,
>
> https://lkml.kernel.org/r/alpine.DEB.2.20.1710191609480.1971@nanos
> https://lkml.kernel.org/r/[email protected]
Thanks for your advice, will change in v5.
>
> Regards
> afzal
Thanks and best regards!