It is possible that something may go wrong with the secondary CPU, in that case it is much nicer to get a dump of the flow-controller state before hanging machine.
Signed-off-by: Dmitry Osipenko <[email protected]> --- arch/arm/mach-tegra/cpuidle-tegra20.c | 46 +++++++++++++++++++++++++-- 1 file changed, 44 insertions(+), 2 deletions(-) diff --git a/arch/arm/mach-tegra/cpuidle-tegra20.c b/arch/arm/mach-tegra/cpuidle-tegra20.c index 77702dd42479..bc5873e92af5 100644 --- a/arch/arm/mach-tegra/cpuidle-tegra20.c +++ b/arch/arm/mach-tegra/cpuidle-tegra20.c @@ -83,14 +83,56 @@ static inline void tegra20_wake_cpu1_from_reset(void) } #endif +static void tegra20_report_cpus_state(void) +{ + unsigned int cpu, lcpu; + + pr_err("secondary CPU taking too long to park\n"); + + for_each_cpu(lcpu, cpu_possible_mask) { + cpu = cpu_logical_map(lcpu); + + pr_err("cpu%u: online=%d flowctrl_csr=0x%08x\n", + cpu, cpu_online(lcpu), flowctrl_read_cpu_csr(cpu)); + } +} + +static int tegra20_wait_for_secondary_cpu_parking(void) +{ + unsigned int retries = 3; + + while (retries--) { + ktime_t timeout = ktime_add_ms(ktime_get(), 500); + + /* + * The primary CPU0 core shall wait for the secondaries + * shutdown in order to power-off CPU's cluster safely. + * The timeout value depends on the current CPU frequency, + * it takes about 40-150us in average and over 1000us in + * a worst case scenario. + */ + do { + if (tegra_cpu_rail_off_ready()) + return 0; + + } while (ktime_before(ktime_get(), timeout)); + + tegra20_report_cpus_state(); + } + + pr_err("timed out waiting secondaries to park\n"); + + return -ETIMEDOUT; +} + static bool tegra20_cpu_cluster_power_down(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index) { bool ret; - while (!tegra_cpu_rail_off_ready()) - cpu_relax(); + if (tegra20_wait_for_secondary_cpu_parking()) + return false; ret = !tegra_pm_enter_lp2(); -- 2.23.0
