diff mbox

[V4,5/5] arm: mvebu: Added SMP support for Armada XP

Message ID 1353357360-7242-6-git-send-email-gregory.clement@free-electrons.com (mailing list archive)
State New, archived
Headers show

Commit Message

Gregory CLEMENT Nov. 19, 2012, 8:35 p.m. UTC
From: Yehuda Yitschak <yehuday@marvell.com>

1. added smp init functions in platsmp.c
2. added secondary cpu entry point in headsmp.S
3. added hotplog initial support in hotplug.c
4. added SMP support for PJ4B cpu

Signed-off-by: Yehuda Yitschak <yehuday@marvell.com>
Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
---
 arch/arm/boot/dts/armada-xp.dtsi    |    4 ++
 arch/arm/configs/mvebu_defconfig    |    3 +
 arch/arm/mach-mvebu/Kconfig         |    1 +
 arch/arm/mach-mvebu/Makefile        |    2 +
 arch/arm/mach-mvebu/armada-370-xp.c |    3 +
 arch/arm/mach-mvebu/common.h        |    3 +
 arch/arm/mach-mvebu/headsmp.S       |   50 ++++++++++++++
 arch/arm/mach-mvebu/hotplug.c       |   30 +++++++++
 arch/arm/mach-mvebu/platsmp.c       |  124 +++++++++++++++++++++++++++++++++++
 9 files changed, 220 insertions(+)
 create mode 100644 arch/arm/mach-mvebu/headsmp.S
 create mode 100644 arch/arm/mach-mvebu/hotplug.c
 create mode 100644 arch/arm/mach-mvebu/platsmp.c

Comments

Will Deacon Nov. 20, 2012, 4:40 p.m. UTC | #1
On Mon, Nov 19, 2012 at 08:35:59PM +0000, Gregory CLEMENT wrote:
> +/*
> + * Armada XP specific entry point for secondary CPUs.
> + * We add the CPU to the coherency fabric and then jump to secondary
> + * startup
> + */
> +ENTRY(armada_xp_secondary_startup)
> +
> +	/* Read CPU id */
> + 	mrc     p15, 0, r1, c0, c0, 5
> +	and     r1, r1, #0xF
> +
> +	/* Add CPU to coherency fabric */
> +
> +	ldr     r0, = ARMADA_XP_CFB_BASE
> +	mov	lr, pc
> +	b	ll_set_cpu_coherent
> +	b	secondary_startup

adr	lr, BSYM(secondary_startup)
bl	ll_set_cpu_coherent

should let you get rid of the mov, b, b, although I think you could do
better than that by making this function a prefix of ll_set_cpu_coherent:

ENTRY(armada_xp_secondary_startup)
	ldr     r0, =ARMADA_XP_CFB_BASE
	mrc     p15, 0, r1, c0, c0, 5
	and     r1, r1, #0xF
	adr	lr, BSYM(secondary_startup)

	/* Fallthrough */

ENTRY(ll_set_cpu_coherent)
...
ENDPROC(ll_set_cpu_coherent)
ENDPROC(armada_xp_secondary_startup)

what do you think?

Will
Gregory CLEMENT Nov. 20, 2012, 4:49 p.m. UTC | #2
On 11/20/2012 05:40 PM, Will Deacon wrote:
> On Mon, Nov 19, 2012 at 08:35:59PM +0000, Gregory CLEMENT wrote:
>> +/*
>> + * Armada XP specific entry point for secondary CPUs.
>> + * We add the CPU to the coherency fabric and then jump to secondary
>> + * startup
>> + */
>> +ENTRY(armada_xp_secondary_startup)
>> +
>> +	/* Read CPU id */
>> + 	mrc     p15, 0, r1, c0, c0, 5
>> +	and     r1, r1, #0xF
>> +
>> +	/* Add CPU to coherency fabric */
>> +
>> +	ldr     r0, = ARMADA_XP_CFB_BASE
>> +	mov	lr, pc
>> +	b	ll_set_cpu_coherent
>> +	b	secondary_startup
> 
> adr	lr, BSYM(secondary_startup)
> bl	ll_set_cpu_coherent

I will try it.

> 
> should let you get rid of the mov, b, b, although I think you could do
> better than that by making this function a prefix of ll_set_cpu_coherent:
> 
> ENTRY(armada_xp_secondary_startup)
> 	ldr     r0, =ARMADA_XP_CFB_BASE
> 	mrc     p15, 0, r1, c0, c0, 5
> 	and     r1, r1, #0xF
> 	adr	lr, BSYM(secondary_startup)
> 
> 	/* Fallthrough */
> 
> ENTRY(ll_set_cpu_coherent)
> ...
> ENDPROC(ll_set_cpu_coherent)
> ENDPROC(armada_xp_secondary_startup)
> 
> what do you think?
> 

I prefer to keep them separate, as we can use coherency without SMP.
That's why I create the coherency_ll.S file instead of putting everything
in this file.


> Will
>
Will Deacon Nov. 20, 2012, 5:01 p.m. UTC | #3
On Tue, Nov 20, 2012 at 04:49:29PM +0000, Gregory CLEMENT wrote:
> On 11/20/2012 05:40 PM, Will Deacon wrote:
> > 
> > ENTRY(armada_xp_secondary_startup)
> > 	ldr     r0, =ARMADA_XP_CFB_BASE
> > 	mrc     p15, 0, r1, c0, c0, 5
> > 	and     r1, r1, #0xF
> > 	adr	lr, BSYM(secondary_startup)
> > 
> > 	/* Fallthrough */
> > 
> > ENTRY(ll_set_cpu_coherent)
> > ...
> > ENDPROC(ll_set_cpu_coherent)
> > ENDPROC(armada_xp_secondary_startup)
> > 
> > what do you think?
> > 
> 
> I prefer to keep them separate, as we can use coherency without SMP.
> That's why I create the coherency_ll.S file instead of putting everything
> in this file.

Hmm, can you elaborate a bit more on coherency without SMP please? Do these
controls also affect IO coherency?

Will
Gregory CLEMENT Nov. 20, 2012, 5:06 p.m. UTC | #4
On 11/20/2012 06:01 PM, Will Deacon wrote:
> On Tue, Nov 20, 2012 at 04:49:29PM +0000, Gregory CLEMENT wrote:
>> On 11/20/2012 05:40 PM, Will Deacon wrote:
>>>
>>> ENTRY(armada_xp_secondary_startup)
>>> 	ldr     r0, =ARMADA_XP_CFB_BASE
>>> 	mrc     p15, 0, r1, c0, c0, 5
>>> 	and     r1, r1, #0xF
>>> 	adr	lr, BSYM(secondary_startup)
>>>
>>> 	/* Fallthrough */
>>>
>>> ENTRY(ll_set_cpu_coherent)
>>> ...
>>> ENDPROC(ll_set_cpu_coherent)
>>> ENDPROC(armada_xp_secondary_startup)
>>>
>>> what do you think?
>>>
>>
>> I prefer to keep them separate, as we can use coherency without SMP.
>> That's why I create the coherency_ll.S file instead of putting everything
>> in this file.
> 
> Hmm, can you elaborate a bit more on coherency without SMP please? Do these
> controls also affect IO coherency?

I meant Hardware IO coherency which is the purpose on the other patch set:
"Add hardware I/O coherency support for Armada 370/XP"

> 
> Will
>
Thomas Petazzoni Nov. 20, 2012, 5:07 p.m. UTC | #5
Dear Will Deacon,

On Tue, 20 Nov 2012 17:01:27 +0000, Will Deacon wrote:

> > I prefer to keep them separate, as we can use coherency without SMP.
> > That's why I create the coherency_ll.S file instead of putting
> > everything in this file.
> 
> Hmm, can you elaborate a bit more on coherency without SMP please? Do
> these controls also affect IO coherency?

The coherency unit does coherency between CPUs, but also between the
CPU and the devices for DMA. So for example the MV78230 is a single-core
variant of the Armada XP, so having CONFIG_SMP for it is useless, but
you still want the CPU to join the coherency fabric in order to provide
coherency with I/O.

Thanks to the coherency unit, we have an almost DMA coherent
architecture (see the HW I/O coherency patches from Grégory for
details).

Thomas
Will Deacon Nov. 20, 2012, 5:09 p.m. UTC | #6
On Tue, Nov 20, 2012 at 05:07:59PM +0000, Thomas Petazzoni wrote:
> Dear Will Deacon,
> 
> On Tue, 20 Nov 2012 17:01:27 +0000, Will Deacon wrote:
> 
> > > I prefer to keep them separate, as we can use coherency without SMP.
> > > That's why I create the coherency_ll.S file instead of putting
> > > everything in this file.
> > 
> > Hmm, can you elaborate a bit more on coherency without SMP please? Do
> > these controls also affect IO coherency?
> 
> The coherency unit does coherency between CPUs, but also between the
> CPU and the devices for DMA. So for example the MV78230 is a single-core
> variant of the Armada XP, so having CONFIG_SMP for it is useless, but
> you still want the CPU to join the coherency fabric in order to provide
> coherency with I/O.
> 
> Thanks to the coherency unit, we have an almost DMA coherent
> architecture (see the HW I/O coherency patches from Grégory for
> details).

Ok, gotcha -- I didn't realise it was all controlled by the same register on
the CPU side.

Thanks for the explanation,

Will
diff mbox

Patch

diff --git a/arch/arm/boot/dts/armada-xp.dtsi b/arch/arm/boot/dts/armada-xp.dtsi
index 531619f..7f968dc 100644
--- a/arch/arm/boot/dts/armada-xp.dtsi
+++ b/arch/arm/boot/dts/armada-xp.dtsi
@@ -38,24 +38,28 @@ 
 	    #size-cells = <0>;
 
 	    cpu@0 {
+		device_type = "cpu";
 	       	compatible = "marvell,sheeva-v7";
 		reg = <0>;
 		clocks = <&cpuclk 0>;
 	    };
 
 	    cpu@1 {
+		device_type = "cpu";
 		compatible = "marvell,sheeva-v7";
 		reg = <1>;
 		clocks = <&cpuclk 1>;
 	    };
 
 	    cpu@2 {
+		device_type = "cpu";
 		compatible = "marvell,sheeva-v7";
 		reg = <2>;
 		clocks = <&cpuclk 2>;
 	    };
 
 	    cpu@3 {
+		device_type = "cpu";
 		compatible = "marvell,sheeva-v7";
 		reg = <3>;
 		clocks = <&cpuclk 3>;
diff --git a/arch/arm/configs/mvebu_defconfig b/arch/arm/configs/mvebu_defconfig
index 3458752..da598d3 100644
--- a/arch/arm/configs/mvebu_defconfig
+++ b/arch/arm/configs/mvebu_defconfig
@@ -12,6 +12,9 @@  CONFIG_ARCH_MVEBU=y
 CONFIG_MACH_ARMADA_370=y
 CONFIG_MACH_ARMADA_XP=y
 # CONFIG_CACHE_L2X0 is not set
+# CONFIG_SWP_EMULATE is not set
+CONFIG_SMP=y
+# CONFIG_LOCAL_TIMERS is not set
 CONFIG_AEABI=y
 CONFIG_HIGHMEM=y
 # CONFIG_COMPACTION is not set
diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig
index 9bfaa0c..d70afe3 100644
--- a/arch/arm/mach-mvebu/Kconfig
+++ b/arch/arm/mach-mvebu/Kconfig
@@ -22,6 +22,7 @@  config MVEBU_CLK_CPU
 config MACH_ARMADA_370_XP
 	bool
 	select ARMADA_370_XP_TIMER
+	select HAVE_SMP
 	select CPU_PJ4B
 
 config MACH_ARMADA_370
diff --git a/arch/arm/mach-mvebu/Makefile b/arch/arm/mach-mvebu/Makefile
index 2e3ec11..5dcb369 100644
--- a/arch/arm/mach-mvebu/Makefile
+++ b/arch/arm/mach-mvebu/Makefile
@@ -3,3 +3,5 @@  ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \
 
 obj-y += system-controller.o
 obj-$(CONFIG_MACH_ARMADA_370_XP) += armada-370-xp.o irq-armada-370-xp.o addr-map.o coherency.o coherency_ll.o pmsu.o
+obj-$(CONFIG_SMP)                += platsmp.o headsmp.o
+obj-$(CONFIG_HOTPLUG_CPU)        += hotplug.o
diff --git a/arch/arm/mach-mvebu/armada-370-xp.c b/arch/arm/mach-mvebu/armada-370-xp.c
index 2af6ce5..66befa1 100644
--- a/arch/arm/mach-mvebu/armada-370-xp.c
+++ b/arch/arm/mach-mvebu/armada-370-xp.c
@@ -22,6 +22,7 @@ 
 #include <asm/mach/time.h>
 #include "armada-370-xp.h"
 #include "common.h"
+#include "coherency.h"
 
 static struct map_desc armada_370_xp_io_desc[] __initdata = {
 	{
@@ -50,6 +51,7 @@  struct sys_timer armada_370_xp_timer = {
 static void __init armada_370_xp_dt_init(void)
 {
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+	coherency_init();
 }
 
 static const char * const armada_370_xp_dt_board_dt_compat[] = {
@@ -59,6 +61,7 @@  static const char * const armada_370_xp_dt_board_dt_compat[] = {
 };
 
 DT_MACHINE_START(ARMADA_XP_DT, "Marvell Aramada 370/XP (Device Tree)")
+	.smp		= smp_ops(armada_xp_smp_ops),
 	.init_machine	= armada_370_xp_dt_init,
 	.map_io		= armada_370_xp_map_io,
 	.init_irq	= armada_370_xp_init_irq,
diff --git a/arch/arm/mach-mvebu/common.h b/arch/arm/mach-mvebu/common.h
index 74ee0b2..86484bb 100644
--- a/arch/arm/mach-mvebu/common.h
+++ b/arch/arm/mach-mvebu/common.h
@@ -21,7 +21,10 @@  void mvebu_clocks_init(void);
 void armada_370_xp_init_irq(void);
 void armada_370_xp_handle_irq(struct pt_regs *regs);
 
+void armada_xp_cpu_die(unsigned int cpu);
 
 int armada_370_xp_coherency_init(void);
 int armada_370_xp_pmsu_init(void);
+void armada_xp_secondary_startup(void);
+extern struct smp_operations armada_xp_smp_ops;
 #endif
diff --git a/arch/arm/mach-mvebu/headsmp.S b/arch/arm/mach-mvebu/headsmp.S
new file mode 100644
index 0000000..b522de1
--- /dev/null
+++ b/arch/arm/mach-mvebu/headsmp.S
@@ -0,0 +1,50 @@ 
+/*
+ * SMP support: Entry point for secondary CPUs
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Yehuda Yitschak <yehuday@marvell.com>
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ * This file implements the assembly entry point for secondary CPUs in
+ * an SMP kernel. The only thing we need to do is to add the CPU to
+ * the coherency fabric by writing to 2 registers. Currently the base
+ * register addresses are hard coded due to the early initialisation
+ * problems.
+ */
+
+#include <linux/linkage.h>
+#include <linux/init.h>
+
+/*
+ * At this stage the secondary CPUs don't have acces yet to the MMU, so
+ * we have to provide physical addresses
+ */
+#define ARMADA_XP_CFB_BASE	     0xD0020200
+
+	__INIT
+
+/*
+ * Armada XP specific entry point for secondary CPUs.
+ * We add the CPU to the coherency fabric and then jump to secondary
+ * startup
+ */
+ENTRY(armada_xp_secondary_startup)
+
+	/* Read CPU id */
+ 	mrc     p15, 0, r1, c0, c0, 5
+	and     r1, r1, #0xF
+
+	/* Add CPU to coherency fabric */
+
+	ldr     r0, = ARMADA_XP_CFB_BASE
+	mov	lr, pc
+	b	ll_set_cpu_coherent
+	b	secondary_startup
+
+ENDPROC(armada_xp_secondary_startup)
diff --git a/arch/arm/mach-mvebu/hotplug.c b/arch/arm/mach-mvebu/hotplug.c
new file mode 100644
index 0000000..b228b6a
--- /dev/null
+++ b/arch/arm/mach-mvebu/hotplug.c
@@ -0,0 +1,30 @@ 
+/*
+ * Symmetric Multi Processing (SMP) support for Armada XP
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Lior Amsalem <alior@marvell.com>
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/smp.h>
+#include <asm/proc-fns.h>
+
+/*
+ * platform-specific code to shutdown a CPU
+ *
+ * Called with IRQs disabled
+ */
+void __ref armada_xp_cpu_die(unsigned int cpu)
+{
+	cpu_do_idle();
+
+	/* We should never return from idle */
+	panic("mvebu: cpu %d unexpectedly exit from shutdown\n", cpu);
+}
diff --git a/arch/arm/mach-mvebu/platsmp.c b/arch/arm/mach-mvebu/platsmp.c
new file mode 100644
index 0000000..1cd6c08
--- /dev/null
+++ b/arch/arm/mach-mvebu/platsmp.c
@@ -0,0 +1,124 @@ 
+/*
+ * Symmetric Multi Processing (SMP) support for Armada XP
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Lior Amsalem <alior@marvell.com>
+ * Yehuda Yitschak <yehuday@marvell.com>
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ * The Armada XP SoC has 4 ARMv7 PJ4B CPUs running in full HW coherency
+ * This file implements the routines for preparing the SMP infrastructure
+ * and waking up the secondary CPUs
+ */
+
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <asm/cacheflush.h>
+#include <asm/smp_plat.h>
+#include "common.h"
+#include "armada-370-xp.h"
+#include "pmsu.h"
+#include "coherency.h"
+
+void __init set_secondary_cpus_clock(void)
+{
+	int cpu;
+	unsigned long rate;
+	struct clk *cpu_clk = NULL;
+	struct device_node *np = NULL;
+
+	cpu = smp_processor_id();
+	np = of_find_node_by_type(np, "cpu");
+	np = NULL;
+	while ((np = of_find_node_by_type(np, "cpu"))) {
+		const u32 *reg;
+		int len;
+		reg = of_get_property(np, "reg", &len);
+		if (!reg || len != 4) {
+			pr_err("%s missing reg property\n", np->full_name);
+			continue;
+		}
+		if (be32_to_cpup(reg) == cpu) {
+			cpu_clk = of_clk_get(np, 0);
+			break;
+		}
+	}
+	WARN_ON(IS_ERR(cpu_clk));
+	clk_prepare_enable(cpu_clk);
+	rate = clk_get_rate(cpu_clk);
+
+	/* set all the other CPU clk to the same rate than the boot CPU */
+	np = NULL;
+	while ((np = of_find_node_by_type(np, "cpu"))) {
+		const u32 *reg;
+		int len;
+		reg = of_get_property(np, "reg", &len);
+		if (!reg || len != 4) {
+			pr_err("%s missing reg property\n", np->full_name);
+			continue;
+		}
+		if (be32_to_cpup(reg) != cpu) {
+			cpu_clk = of_clk_get(np, 0);
+			clk_set_rate(cpu_clk, rate);
+		}
+	}
+}
+
+static void __cpuinit armada_xp_secondary_init(unsigned int cpu)
+{
+	armada_xp_mpic_smp_cpu_init();
+}
+
+static int __cpuinit armada_xp_boot_secondary(unsigned int cpu,
+					      struct task_struct *idle)
+{
+	pr_info("Booting CPU %d\n", cpu);
+
+	armada_xp_boot_cpu(cpu, armada_xp_secondary_startup);
+
+	return 0;
+}
+
+static void __init armada_xp_smp_init_cpus(void)
+{
+	unsigned int i, ncores;
+	ncores = coherency_get_cpu_count();
+
+	/* Limit possbile CPUs to defconfig */
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %d CPUs physically present. Only %d configured.",
+			ncores, nr_cpu_ids);
+		pr_warn("Clipping CPU count to %d\n", nr_cpu_ids);
+		ncores = nr_cpu_ids;
+	}
+
+	for (i = 0; i < ncores; i++)
+		set_cpu_possible(i, true);
+
+	set_smp_cross_call(armada_mpic_send_doorbell);
+}
+
+void __init armada_xp_smp_prepare_cpus(unsigned int max_cpus)
+{
+	set_secondary_cpus_clock();
+	flush_cache_all();
+	set_cpu_coherent(cpu_logical_map(smp_processor_id()), 0);
+}
+
+struct smp_operations armada_xp_smp_ops __initdata = {
+	.smp_init_cpus		= armada_xp_smp_init_cpus,
+	.smp_prepare_cpus	= armada_xp_smp_prepare_cpus,
+	.smp_secondary_init	= armada_xp_secondary_init,
+	.smp_boot_secondary	= armada_xp_boot_secondary,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_die		= armada_xp_cpu_die,
+#endif
+};