diff mbox series

[RFC,2/3] coresight: add support for debug module

Message ID 1486966298-16767-3-git-send-email-leo.yan@linaro.org
State New
Headers show
Series [RFC,1/3] coresight: binding for coresight debug driver | expand

Commit Message

Leo Yan Feb. 13, 2017, 6:11 a.m. UTC
Coresight includes debug module and usually the module connects with CPU
debug logic. ARMv8 architecture reference manual (ARMv8-ARM) has defined
the debug registers in the chapter "H9: External Debug Register
Descriptions".

After enable the debug module we can check CPU state and PC value, etc.
So this is helpful for some CPU lockup bugs, e.g. if one CPU has run
into infinite loop with IRQ disabled. So the CPU cannot switch context
and handle any interrupt, so it cannot handle SMP call for stack dump,
etc. Furthermore, now ARMv8 introduces some other runtime firmwares like
ARM trusted firmware BL31, so sometime CPU hard lock may happen in the
firmware and cannot return back to kernel.

This patch is to enable coresight debug module and register callback
notifier for panic; so when system detect the CPU lockup we can utilize
debug module registers to get to know PC value for all CPUs; so we can
quickly know the hang address for CPUs.

This is initial driver for coresight debug module and could enhance it
later according to debugging requirement.

Signed-off-by: Leo Yan <leo.yan@linaro.org>

---
 drivers/hwtracing/coresight/Kconfig           |   8 ++
 drivers/hwtracing/coresight/Makefile          |   1 +
 drivers/hwtracing/coresight/coresight-debug.c | 169 ++++++++++++++++++++++++++
 3 files changed, 178 insertions(+)
 create mode 100644 drivers/hwtracing/coresight/coresight-debug.c

-- 
2.7.4

Comments

Mark Rutland Feb. 15, 2017, 11:43 a.m. UTC | #1
On Mon, Feb 13, 2017 at 02:11:37PM +0800, Leo Yan wrote:
> Coresight includes debug module and usually the module connects with CPU

> debug logic. ARMv8 architecture reference manual (ARMv8-ARM) has defined

> the debug registers in the chapter "H9: External Debug Register

> Descriptions".


This should have been in the binding description also.

The layout of the ARM ARM can change over time, so please refer to the
full document number, which can be found at the bottom of each page
(e.g. ARM DDI 0487A.j).

> After enable the debug module we can check CPU state and PC value, etc.

> So this is helpful for some CPU lockup bugs, e.g. if one CPU has run

> into infinite loop with IRQ disabled. So the CPU cannot switch context

> and handle any interrupt, so it cannot handle SMP call for stack dump,

> etc. Furthermore, now ARMv8 introduces some other runtime firmwares like

> ARM trusted firmware BL31, so sometime CPU hard lock may happen in the

> firmware and cannot return back to kernel.


I would generally expect that the secure world would lock down
debugging, as this poses a security risk.

I take it that this is only unlocked on development firmware.

Given that cores can be powered down outside of our control, I'm not
sure that accesses to these registers is safe in general.

> This patch is to enable coresight debug module and register callback

> notifier for panic; so when system detect the CPU lockup we can utilize

> debug module registers to get to know PC value for all CPUs; so we can

> quickly know the hang address for CPUs.

>

> This is initial driver for coresight debug module and could enhance it

> later according to debugging requirement.


How does this interact with an external debugger making use of these
registers?

[...]

> +static struct debug_drvdata *debug_drvdata[NR_CPUS];


A per-cpu variable is preferred to an NR_CPUS sized array.

> +

> +static void debug_os_unlock(struct debug_drvdata *drvdata)

> +{

> +     /* Unlocks the debug registers */

> +     writel_relaxed(0x0, drvdata->base + EDOSLAR);

> +     isb();

> +}


I do not believe this barrier is correct.

[...]

> +static void debug_read_pcsr(struct debug_drvdata *drvdata)

> +{

> +     u32 pcsr_hi, pcsr_lo;

> +

> +     CS_UNLOCK(drvdata->base);

> +

> +     debug_os_unlock(drvdata);

> +

> +#ifdef CONFIG_64BIT

> +     pcsr_lo = readl_relaxed(drvdata->base + EDPCSR_LO);

> +     pcsr_hi = readl_relaxed(drvdata->base + EDPCSR_HI);

> +

> +     pr_emerg("CPU[%d]: PSCR=0x%lx\n", drvdata->cpu,

> +              ((unsigned long)pcsr_hi << 32 | (unsigned long)pcsr_lo));

> +#else

> +     pcsr_lo = readl_relaxed(drvdata->base + EDPCSR_LO);

> +

> +     pr_emerg("CPU[%d]: PSCR=0x%lx\n", drvdata->cpu, pcsr_lo);

> +#endif

> +

> +     CS_LOCK(drvdata->base);

> +}


Per ARM DDI 0487A.k_iss10775, H9.2.32, "EDPCSR, External Debug Program
Counter Sample Register":

        Implemented only if the OPTIONAL PC Sample-based Profiling
        Extension is implemented.

So even if we have access to an MMIO debug interface, we cannot
necessarily acecess this register.

[...]

> +/*

> + * Dump out memory limit information on panic.

> + */

> +static int dump_debug(struct notifier_block *self, unsigned long v, void *p)

> +{

> +     int i;

> +

> +     pr_emerg("Coresight debug module:\n");

> +

> +     for_each_possible_cpu(i) {

> +

> +             if (!debug_drvdata[i])

> +                     continue;

> +

> +             debug_read_pcsr(debug_drvdata[i]);

> +     }


Is there no potential for deadlock with a CPU reading its own debug
interface registers?

[...]

> +static struct amba_id debug_ids[] = {

> +     {       /* Debug for Cortex-A53 */

> +             .id     = 0x000bbd03,

> +             .mask   = 0x000fffff,

> +             .data   = "debug",

> +     },

> +     { 0, 0},

> +};


The DT binding said nothing about Cortex-A53.

How variable are the MMIO registers in practice? Do we need to know the
particular CPU?

Thanks,
Mark.
IMPORTANT NOTICE: The contents of this email and any attachments are confidential and may also be privileged. If you are not the intended recipient, please notify the sender immediately and do not disclose the contents to any other person, use it for any purpose, or store or copy the information in any medium. Thank you.
diff mbox series

Patch

diff --git a/drivers/hwtracing/coresight/Kconfig b/drivers/hwtracing/coresight/Kconfig
index 130cb21..dcf59cc 100644
--- a/drivers/hwtracing/coresight/Kconfig
+++ b/drivers/hwtracing/coresight/Kconfig
@@ -89,4 +89,12 @@  config CORESIGHT_STM
 	  logging useful software events or data coming from various entities
 	  in the system, possibly running different OSs
 
+config CORESIGHT_DEBUG
+	bool "CoreSight debug driver"
+	depends on ARM || ARM64
+	help
+	  This driver provides support for coresight debugging module. This
+	  is primarily used for printing out debug registers for panic and
+	  soft and hard lockup.
+
 endif
diff --git a/drivers/hwtracing/coresight/Makefile b/drivers/hwtracing/coresight/Makefile
index af480d9..d540d45 100644
--- a/drivers/hwtracing/coresight/Makefile
+++ b/drivers/hwtracing/coresight/Makefile
@@ -16,3 +16,4 @@  obj-$(CONFIG_CORESIGHT_SOURCE_ETM4X) += coresight-etm4x.o \
 					coresight-etm4x-sysfs.o
 obj-$(CONFIG_CORESIGHT_QCOM_REPLICATOR) += coresight-replicator-qcom.o
 obj-$(CONFIG_CORESIGHT_STM) += coresight-stm.o
+obj-$(CONFIG_CORESIGHT_DEBUG) += coresight-debug.o
diff --git a/drivers/hwtracing/coresight/coresight-debug.c b/drivers/hwtracing/coresight/coresight-debug.c
new file mode 100644
index 0000000..28206a83
--- /dev/null
+++ b/drivers/hwtracing/coresight/coresight-debug.c
@@ -0,0 +1,169 @@ 
+/*
+ * Copyright(C) 2017 Linaro Limited. All rights reserved.
+ * Author: Leo Yan <leo.yan@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kernel.h>
+#include <linux/moduleparam.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/smp.h>
+#include <linux/sysfs.h>
+#include <linux/stat.h>
+#include <linux/clk.h>
+#include <linux/cpu.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+#include <linux/uaccess.h>
+
+#include "coresight-priv.h"
+
+#define EDPCSR_LO	0x0A0
+#define EDPCSR_HI	0x0AC
+#define EDOSLAR		0x300
+#define EDOSLSR		0x304
+#define EDPDCR		0x310
+#define EDPDSR		0x314
+
+struct debug_drvdata {
+	void __iomem	*base;
+	struct device	*dev;
+	int		cpu;
+};
+
+static struct debug_drvdata *debug_drvdata[NR_CPUS];
+
+static void debug_os_unlock(struct debug_drvdata *drvdata)
+{
+	/* Unlocks the debug registers */
+	writel_relaxed(0x0, drvdata->base + EDOSLAR);
+	isb();
+}
+
+static void debug_read_pcsr(struct debug_drvdata *drvdata)
+{
+	u32 pcsr_hi, pcsr_lo;
+
+	CS_UNLOCK(drvdata->base);
+
+	debug_os_unlock(drvdata);
+
+#ifdef CONFIG_64BIT
+	pcsr_lo = readl_relaxed(drvdata->base + EDPCSR_LO);
+	pcsr_hi = readl_relaxed(drvdata->base + EDPCSR_HI);
+
+	pr_emerg("CPU[%d]: PSCR=0x%lx\n", drvdata->cpu,
+		 ((unsigned long)pcsr_hi << 32 | (unsigned long)pcsr_lo));
+#else
+	pcsr_lo = readl_relaxed(drvdata->base + EDPCSR_LO);
+
+	pr_emerg("CPU[%d]: PSCR=0x%lx\n", drvdata->cpu,	pcsr_lo);
+#endif
+
+	CS_LOCK(drvdata->base);
+}
+
+/*
+ * Dump out memory limit information on panic.
+ */
+static int dump_debug(struct notifier_block *self, unsigned long v, void *p)
+{
+	int i;
+
+	pr_emerg("Coresight debug module:\n");
+
+	for_each_possible_cpu(i) {
+
+		if (!debug_drvdata[i])
+			continue;
+
+		debug_read_pcsr(debug_drvdata[i]);
+	}
+
+	return 0;
+}
+
+static struct notifier_block debug_notifier = {
+	.notifier_call = dump_debug,
+};
+
+static int __init register_coresight_debug_dumper(void)
+{
+	atomic_notifier_chain_register(&panic_notifier_list,
+				       &debug_notifier);
+	return 0;
+}
+__initcall(register_coresight_debug_dumper);
+
+static int debug_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	void __iomem *base;
+	struct device *dev = &adev->dev;
+	struct coresight_platform_data *pdata = NULL;
+	struct debug_drvdata *drvdata;
+	struct resource *res = &adev->res;
+	struct device_node *np = adev->dev.of_node;
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	if (np) {
+		pdata = of_get_coresight_platform_data(dev, np);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+		adev->dev.platform_data = pdata;
+	}
+
+	drvdata->dev = &adev->dev;
+	dev_set_drvdata(dev, drvdata);
+
+	/* Validity for the resource is already checked by the AMBA core */
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	drvdata->base = base;
+	drvdata->cpu = pdata ? pdata->cpu : 0;
+	debug_drvdata[drvdata->cpu] = drvdata;
+
+	dev_info(dev, "%s initialized\n", (char *)id->data);
+	return 0;
+}
+
+static struct amba_id debug_ids[] = {
+	{       /* Debug for Cortex-A53 */
+		.id	= 0x000bbd03,
+		.mask	= 0x000fffff,
+		.data	= "debug",
+	},
+	{ 0, 0},
+};
+
+static struct amba_driver debug_driver = {
+	.drv = {
+		.name   = "coresight-debug",
+		.suppress_bind_attrs = true,
+	},
+	.probe		= debug_probe,
+	.id_table	= debug_ids,
+};
+builtin_amba_driver(debug_driver);