coresight: etm4x: Save/restore state across CPU low power states

Some hardware will ignore bit TRCPDCR.PU which is used to signal
to hardware that power should not be removed from the trace unit.
Let's mitigate against this by conditionally saving and restoring
the trace unit state when the CPU enters low power states.

This patchset introduces a firmware property named
'arm,coresight-loses-context-with-cpu' - when this is present the
hardware state will be conditionally saved and restored.

A module parameter 'pm_save_enable' is also introduced which can
be configured to override the firmware property. This can be set
to never allow save/restore or to conditionally allow it (only for
self-hosted). The default value is determined by firmware.

We avoid saving the hardware state when self-hosted coresight isn't
in use to reduce PM latency - we can't determine this by reading the
claim tags (TRCCLAIMCLR) as these are 'trace' registers which need
power and clocking, something we can't easily provide in the PM
context. Therefore we rely on the existing drvdata->mode internal
state that is set when self-hosted coresight is used (and powered).

Signed-off-by: Andrew Murray <andrew.murray@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Link: https://lore.kernel.org/r/20191104181251.26732-2-mathieu.poirier@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Author: Andrew Murray

drivers/hwtracing/coresight/coresight-etm4x.c

@@ -18,6 +18,7 @@
 #include <linux/stat.h>
 #include <linux/clk.h>
 #include <linux/cpu.h>
+#include <linux/cpu_pm.h>
 #include <linux/coresight.h>
 #include <linux/coresight-pmu.h>
 #include <linux/pm_wakeup.h>
@@ -26,6 +27,7 @@
 #include <linux/uaccess.h>
 #include <linux/perf_event.h>
 #include <linux/pm_runtime.h>
+#include <linux/property.h>
 #include <asm/sections.h>
 #include <asm/local.h>
 #include <asm/virt.h>
@@ -37,6 +39,15 @@ static int boot_enable;
 module_param(boot_enable, int, 0444);
 MODULE_PARM_DESC(boot_enable, "Enable tracing on boot");
 
+#define PARAM_PM_SAVE_FIRMWARE	  0 /* save self-hosted state as per firmware */
+#define PARAM_PM_SAVE_NEVER	  1 /* never save any state */
+#define PARAM_PM_SAVE_SELF_HOSTED 2 /* save self-hosted state only */
+
+static int pm_save_enable = PARAM_PM_SAVE_FIRMWARE;
+module_param(pm_save_enable, int, 0444);
+MODULE_PARM_DESC(pm_save_enable,
+	"Save/restore state on power down: 1 = never, 2 = self-hosted");
+
 /* The number of ETMv4 currently registered */
 static int etm4_count;
 static struct etmv4_drvdata *etmdrvdata[NR_CPUS];
@@ -54,6 +65,14 @@ static void etm4_os_unlock(struct etmv4_drvdata *drvdata)
 	isb();
 }
 
+static void etm4_os_lock(struct etmv4_drvdata *drvdata)
+{
+	/* Writing 0x1 to TRCOSLAR locks the trace registers */
+	writel_relaxed(0x1, drvdata->base + TRCOSLAR);
+	drvdata->os_unlock = false;
+	isb();
+}
+
 static bool etm4_arch_supported(u8 arch)
 {
 	/* Mask out the minor version number */
@@ -1085,6 +1104,288 @@ static void etm4_init_trace_id(struct etmv4_drvdata *drvdata)
 	drvdata->trcid = coresight_get_trace_id(drvdata->cpu);
 }
 
+#ifdef CONFIG_CPU_PM
+static int etm4_cpu_save(struct etmv4_drvdata *drvdata)
+{
+	int i, ret = 0;
+	struct etmv4_save_state *state;
+	struct device *etm_dev = &drvdata->csdev->dev;
+
+	/*
+	 * As recommended by 3.4.1 ("The procedure when powering down the PE")
+	 * of ARM IHI 0064D
+	 */
+	dsb(sy);
+	isb();
+
+	CS_UNLOCK(drvdata->base);
+
+	/* Lock the OS lock to disable trace and external debugger access */
+	etm4_os_lock(drvdata);
+
+	/* wait for TRCSTATR.PMSTABLE to go up */
+	if (coresight_timeout(drvdata->base, TRCSTATR,
+			      TRCSTATR_PMSTABLE_BIT, 1)) {
+		dev_err(etm_dev,
+			"timeout while waiting for PM Stable Status\n");
+		etm4_os_unlock(drvdata);
+		ret = -EBUSY;
+		goto out;
+	}
+
+	state = drvdata->save_state;
+
+	state->trcprgctlr = readl(drvdata->base + TRCPRGCTLR);
+	state->trcprocselr = readl(drvdata->base + TRCPROCSELR);
+	state->trcconfigr = readl(drvdata->base + TRCCONFIGR);
+	state->trcauxctlr = readl(drvdata->base + TRCAUXCTLR);
+	state->trceventctl0r = readl(drvdata->base + TRCEVENTCTL0R);
+	state->trceventctl1r = readl(drvdata->base + TRCEVENTCTL1R);
+	state->trcstallctlr = readl(drvdata->base + TRCSTALLCTLR);
+	state->trctsctlr = readl(drvdata->base + TRCTSCTLR);
+	state->trcsyncpr = readl(drvdata->base + TRCSYNCPR);
+	state->trcccctlr = readl(drvdata->base + TRCCCCTLR);
+	state->trcbbctlr = readl(drvdata->base + TRCBBCTLR);
+	state->trctraceidr = readl(drvdata->base + TRCTRACEIDR);
+	state->trcqctlr = readl(drvdata->base + TRCQCTLR);
+
+	state->trcvictlr = readl(drvdata->base + TRCVICTLR);
+	state->trcviiectlr = readl(drvdata->base + TRCVIIECTLR);
+	state->trcvissctlr = readl(drvdata->base + TRCVISSCTLR);
+	state->trcvipcssctlr = readl(drvdata->base + TRCVIPCSSCTLR);
+	state->trcvdctlr = readl(drvdata->base + TRCVDCTLR);
+	state->trcvdsacctlr = readl(drvdata->base + TRCVDSACCTLR);
+	state->trcvdarcctlr = readl(drvdata->base + TRCVDARCCTLR);
+
+	for (i = 0; i < drvdata->nrseqstate; i++)
+		state->trcseqevr[i] = readl(drvdata->base + TRCSEQEVRn(i));
+
+	state->trcseqrstevr = readl(drvdata->base + TRCSEQRSTEVR);
+	state->trcseqstr = readl(drvdata->base + TRCSEQSTR);
+	state->trcextinselr = readl(drvdata->base + TRCEXTINSELR);
+
+	for (i = 0; i < drvdata->nr_cntr; i++) {
+		state->trccntrldvr[i] = readl(drvdata->base + TRCCNTRLDVRn(i));
+		state->trccntctlr[i] = readl(drvdata->base + TRCCNTCTLRn(i));
+		state->trccntvr[i] = readl(drvdata->base + TRCCNTVRn(i));
+	}
+
+	for (i = 0; i < drvdata->nr_resource * 2; i++)
+		state->trcrsctlr[i] = readl(drvdata->base + TRCRSCTLRn(i));
+
+	for (i = 0; i < drvdata->nr_ss_cmp; i++) {
+		state->trcssccr[i] = readl(drvdata->base + TRCSSCCRn(i));
+		state->trcsscsr[i] = readl(drvdata->base + TRCSSCSRn(i));
+		state->trcsspcicr[i] = readl(drvdata->base + TRCSSPCICRn(i));
+	}
+
+	for (i = 0; i < drvdata->nr_addr_cmp * 2; i++) {
+		state->trcacvr[i] = readl(drvdata->base + TRCACVRn(i));
+		state->trcacatr[i] = readl(drvdata->base + TRCACATRn(i));
+	}
+
+	/*
+	 * Data trace stream is architecturally prohibited for A profile cores
+	 * so we don't save (or later restore) trcdvcvr and trcdvcmr - As per
+	 * section 1.3.4 ("Possible functional configurations of an ETMv4 trace
+	 * unit") of ARM IHI 0064D.
+	 */
+
+	for (i = 0; i < drvdata->numcidc; i++)
+		state->trccidcvr[i] = readl(drvdata->base + TRCCIDCVRn(i));
+
+	for (i = 0; i < drvdata->numvmidc; i++)
+		state->trcvmidcvr[i] = readl(drvdata->base + TRCVMIDCVRn(i));
+
+	state->trccidcctlr0 = readl(drvdata->base + TRCCIDCCTLR0);
+	state->trccidcctlr1 = readl(drvdata->base + TRCCIDCCTLR1);
+
+	state->trcvmidcctlr0 = readl(drvdata->base + TRCVMIDCCTLR0);
+	state->trcvmidcctlr0 = readl(drvdata->base + TRCVMIDCCTLR1);
+
+	state->trcclaimset = readl(drvdata->base + TRCCLAIMCLR);
+
+	state->trcpdcr = readl(drvdata->base + TRCPDCR);
+
+	/* wait for TRCSTATR.IDLE to go up */
+	if (coresight_timeout(drvdata->base, TRCSTATR, TRCSTATR_IDLE_BIT, 1)) {
+		dev_err(etm_dev,
+			"timeout while waiting for Idle Trace Status\n");
+		etm4_os_unlock(drvdata);
+		ret = -EBUSY;
+		goto out;
+	}
+
+	drvdata->state_needs_restore = true;
+
+	/*
+	 * Power can be removed from the trace unit now. We do this to
+	 * potentially save power on systems that respect the TRCPDCR_PU
+	 * despite requesting software to save/restore state.
+	 */
+	writel_relaxed((state->trcpdcr & ~TRCPDCR_PU),
+			drvdata->base + TRCPDCR);
+
+out:
+	CS_LOCK(drvdata->base);
+	return ret;
+}
+
+static void etm4_cpu_restore(struct etmv4_drvdata *drvdata)
+{
+	int i;
+	struct etmv4_save_state *state = drvdata->save_state;
+
+	CS_UNLOCK(drvdata->base);
+
+	writel_relaxed(state->trcclaimset, drvdata->base + TRCCLAIMSET);
+
+	writel_relaxed(state->trcprgctlr, drvdata->base + TRCPRGCTLR);
+	writel_relaxed(state->trcprocselr, drvdata->base + TRCPROCSELR);
+	writel_relaxed(state->trcconfigr, drvdata->base + TRCCONFIGR);
+	writel_relaxed(state->trcauxctlr, drvdata->base + TRCAUXCTLR);
+	writel_relaxed(state->trceventctl0r, drvdata->base + TRCEVENTCTL0R);
+	writel_relaxed(state->trceventctl1r, drvdata->base + TRCEVENTCTL1R);
+	writel_relaxed(state->trcstallctlr, drvdata->base + TRCSTALLCTLR);
+	writel_relaxed(state->trctsctlr, drvdata->base + TRCTSCTLR);
+	writel_relaxed(state->trcsyncpr, drvdata->base + TRCSYNCPR);
+	writel_relaxed(state->trcccctlr, drvdata->base + TRCCCCTLR);
+	writel_relaxed(state->trcbbctlr, drvdata->base + TRCBBCTLR);
+	writel_relaxed(state->trctraceidr, drvdata->base + TRCTRACEIDR);
+	writel_relaxed(state->trcqctlr, drvdata->base + TRCQCTLR);
+
+	writel_relaxed(state->trcvictlr, drvdata->base + TRCVICTLR);
+	writel_relaxed(state->trcviiectlr, drvdata->base + TRCVIIECTLR);
+	writel_relaxed(state->trcvissctlr, drvdata->base + TRCVISSCTLR);
+	writel_relaxed(state->trcvipcssctlr, drvdata->base + TRCVIPCSSCTLR);
+	writel_relaxed(state->trcvdctlr, drvdata->base + TRCVDCTLR);
+	writel_relaxed(state->trcvdsacctlr, drvdata->base + TRCVDSACCTLR);
+	writel_relaxed(state->trcvdarcctlr, drvdata->base + TRCVDARCCTLR);
+
+	for (i = 0; i < drvdata->nrseqstate; i++)
+		writel_relaxed(state->trcseqevr[i],
+			       drvdata->base + TRCSEQEVRn(i));
+
+	writel_relaxed(state->trcseqrstevr, drvdata->base + TRCSEQRSTEVR);
+	writel_relaxed(state->trcseqstr, drvdata->base + TRCSEQSTR);
+	writel_relaxed(state->trcextinselr, drvdata->base + TRCEXTINSELR);
+
+	for (i = 0; i < drvdata->nr_cntr; i++) {
+		writel_relaxed(state->trccntrldvr[i],
+			       drvdata->base + TRCCNTRLDVRn(i));
+		writel_relaxed(state->trccntctlr[i],
+			       drvdata->base + TRCCNTCTLRn(i));
+		writel_relaxed(state->trccntvr[i],
+			       drvdata->base + TRCCNTVRn(i));
+	}
+
+	for (i = 0; i < drvdata->nr_resource * 2; i++)
+		writel_relaxed(state->trcrsctlr[i],
+			       drvdata->base + TRCRSCTLRn(i));
+
+	for (i = 0; i < drvdata->nr_ss_cmp; i++) {
+		writel_relaxed(state->trcssccr[i],
+			       drvdata->base + TRCSSCCRn(i));
+		writel_relaxed(state->trcsscsr[i],
+			       drvdata->base + TRCSSCSRn(i));
+		writel_relaxed(state->trcsspcicr[i],
+			       drvdata->base + TRCSSPCICRn(i));
+	}
+
+	for (i = 0; i < drvdata->nr_addr_cmp * 2; i++) {
+		writel_relaxed(state->trcacvr[i],
+			       drvdata->base + TRCACVRn(i));
+		writel_relaxed(state->trcacatr[i],
+			       drvdata->base + TRCACATRn(i));
+	}
+
+	for (i = 0; i < drvdata->numcidc; i++)
+		writel_relaxed(state->trccidcvr[i],
+			       drvdata->base + TRCCIDCVRn(i));
+
+	for (i = 0; i < drvdata->numvmidc; i++)
+		writel_relaxed(state->trcvmidcvr[i],
+			       drvdata->base + TRCVMIDCVRn(i));
+
+	writel_relaxed(state->trccidcctlr0, drvdata->base + TRCCIDCCTLR0);
+	writel_relaxed(state->trccidcctlr1, drvdata->base + TRCCIDCCTLR1);
+
+	writel_relaxed(state->trcvmidcctlr0, drvdata->base + TRCVMIDCCTLR0);
+	writel_relaxed(state->trcvmidcctlr0, drvdata->base + TRCVMIDCCTLR1);
+
+	writel_relaxed(state->trcclaimset, drvdata->base + TRCCLAIMSET);
+
+	writel_relaxed(state->trcpdcr, drvdata->base + TRCPDCR);
+
+	drvdata->state_needs_restore = false;
+
+	/*
+	 * As recommended by section 4.3.7 ("Synchronization when using the
+	 * memory-mapped interface") of ARM IHI 0064D
+	 */
+	dsb(sy);
+	isb();
+
+	/* Unlock the OS lock to re-enable trace and external debug access */
+	etm4_os_unlock(drvdata);
+	CS_LOCK(drvdata->base);
+}
+
+static int etm4_cpu_pm_notify(struct notifier_block *nb, unsigned long cmd,
+			      void *v)
+{
+	struct etmv4_drvdata *drvdata;
+	unsigned int cpu = smp_processor_id();
+
+	if (!etmdrvdata[cpu])
+		return NOTIFY_OK;
+
+	drvdata = etmdrvdata[cpu];
+
+	if (!drvdata->save_state)
+		return NOTIFY_OK;
+
+	if (WARN_ON_ONCE(drvdata->cpu != cpu))
+		return NOTIFY_BAD;
+
+	switch (cmd) {
+	case CPU_PM_ENTER:
+		/* save the state if self-hosted coresight is in use */
+		if (local_read(&drvdata->mode))
+			if (etm4_cpu_save(drvdata))
+				return NOTIFY_BAD;
+		break;
+	case CPU_PM_EXIT:
+		/* fallthrough */
+	case CPU_PM_ENTER_FAILED:
+		if (drvdata->state_needs_restore)
+			etm4_cpu_restore(drvdata);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block etm4_cpu_pm_nb = {
+	.notifier_call = etm4_cpu_pm_notify,
+};
+
+static int etm4_cpu_pm_register(void)
+{
+	return cpu_pm_register_notifier(&etm4_cpu_pm_nb);
+}
+
+static void etm4_cpu_pm_unregister(void)
+{
+	cpu_pm_unregister_notifier(&etm4_cpu_pm_nb);
+}
+#else
+static int etm4_cpu_pm_register(void) { return 0; }
+static void etm4_cpu_pm_unregister(void) { }
+#endif
+
 static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 {
 	int ret;
@@ -1101,6 +1402,17 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 
 	dev_set_drvdata(dev, drvdata);
 
+	if (pm_save_enable == PARAM_PM_SAVE_FIRMWARE)
+		pm_save_enable = coresight_loses_context_with_cpu(dev) ?
+			       PARAM_PM_SAVE_SELF_HOSTED : PARAM_PM_SAVE_NEVER;
+
+	if (pm_save_enable != PARAM_PM_SAVE_NEVER) {
+		drvdata->save_state = devm_kmalloc(dev,
+				sizeof(struct etmv4_save_state), GFP_KERNEL);
+		if (!drvdata->save_state)
+			return -ENOMEM;
+	}
+
 	/* Validity for the resource is already checked by the AMBA core */
 	base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(base))
@@ -1135,6 +1447,10 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 		if (ret < 0)
 			goto err_arch_supported;
 		hp_online = ret;
+
+		ret = etm4_cpu_pm_register();
+		if (ret)
+			goto err_arch_supported;
 	}
 
 	cpus_read_unlock();
@@ -1185,6 +1501,8 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 
 err_arch_supported:
 	if (--etm4_count == 0) {
+		etm4_cpu_pm_unregister();
+
 		cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING);
 		if (hp_online)
 			cpuhp_remove_state_nocalls(hp_online);