From patchwork Wed Jan 16 08:11:13 2013 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Joseph Lo X-Patchwork-Id: 1986871 Return-Path: X-Original-To: patchwork-linux-arm@patchwork.kernel.org Delivered-To: patchwork-process-083081@patchwork1.kernel.org Received: from merlin.infradead.org (merlin.infradead.org [205.233.59.134]) by patchwork1.kernel.org (Postfix) with ESMTP id 288863FDD1 for ; Wed, 16 Jan 2013 08:15:11 +0000 (UTC) Received: from localhost ([::1] helo=merlin.infradead.org) by merlin.infradead.org with esmtp (Exim 4.76 #1 (Red Hat Linux)) id 1TvO6G-0000mI-JI; Wed, 16 Jan 2013 08:11:56 +0000 Received: from hqemgate03.nvidia.com ([216.228.121.140]) by merlin.infradead.org with esmtps (Exim 4.76 #1 (Red Hat Linux)) id 1TvO5x-0000fR-7G for linux-arm-kernel@lists.infradead.org; Wed, 16 Jan 2013 08:11:39 +0000 Received: from hqnvupgp06.nvidia.com (Not Verified[216.228.121.13]) by hqemgate03.nvidia.com id ; Wed, 16 Jan 2013 00:15:42 -0800 Received: from hqemhub01.nvidia.com ([172.17.108.22]) by hqnvupgp06.nvidia.com (PGP Universal service); Wed, 16 Jan 2013 00:10:26 -0800 X-PGP-Universal: processed; by hqnvupgp06.nvidia.com on Wed, 16 Jan 2013 00:10:26 -0800 Received: from jlo-ubuntu-64.nvidia.com (172.20.144.16) by hqemhub01.nvidia.com (172.20.150.30) with Microsoft SMTP Server (TLS) id 8.3.279.1; Wed, 16 Jan 2013 00:11:34 -0800 From: Joseph Lo To: Stephen Warren Subject: [PATCH V4 5/5] ARM: tegra20: cpuidle: apply coupled cpuidle for powered-down mode Date: Wed, 16 Jan 2013 16:11:13 +0800 Message-ID: <1358323873-30525-1-git-send-email-josephl@nvidia.com> X-Mailer: git-send-email 1.8.0.3 X-NVConfidentiality: public MIME-Version: 1.0 X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20130116_031137_678115_A4759DE7 X-CRM114-Status: GOOD ( 23.44 ) X-Spam-Score: -7.6 (-------) X-Spam-Report: SpamAssassin version 3.3.2 on merlin.infradead.org summary: Content analysis details: (-7.6 points) pts rule name description ---- ---------------------- -------------------------------------------------- -5.0 RCVD_IN_DNSWL_HI RBL: Sender listed at http://www.dnswl.org/, high trust [216.228.121.140 listed in list.dnswl.org] -0.0 SPF_HELO_PASS SPF: HELO matches SPF record -0.0 SPF_PASS SPF: sender matches SPF record -0.7 RP_MATCHES_RCVD Envelope sender domain matches handover relay domain -1.9 BAYES_00 BODY: Bayes spam probability is 0 to 1% [score: 0.0000] Cc: linux-tegra@vger.kernel.org, Peter De Schrijver , Joseph Lo , linux-arm-kernel@lists.infradead.org, Colin Cross X-BeenThere: linux-arm-kernel@lists.infradead.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: linux-arm-kernel-bounces@lists.infradead.org Errors-To: linux-arm-kernel-bounces+patchwork-linux-arm=patchwork.kernel.org@lists.infradead.org The "powered-down" cpuidle mode of Tegra20 needs the CPU0 be the last one core to go into this mode before other core. The coupled cpuidle framework can help to sync the MPCore to coupled state then go into "powered-down" idle mode together. The driver can just assume the MPCore come into "powered-down" mode at the same time. No need to take care if the CPU_0 goes into this mode along and only can put it into safe idle mode (WFI). The powered-down state of Tegra20 requires power gating both CPU cores. When the secondary CPU requests to enter powered-down state, it saves its own contexts and then enters WFI for waiting CPU0 in the same state. When the CPU0 requests powered-down state, it attempts to put the secondary CPU into reset to prevent it from waking up. Then power down both CPUs together and power off the cpu rail. Be aware of that, you may see the legacy power state "LP2" in the code which is exactly the same meaning of "CPU power down". Based on the work by: Colin Cross Gary King Signed-off-by: Joseph Lo Acked-by: Colin Cross --- V4: * rename the function to "tegra20_wake_cpu1_from_reset" * make the coupled cpuidle can be disabled if SMP is disabled V3: * sqash last two patch in previous version to support coupled cpuidle directly V2: * refine the cpu control function that dedicate for CPU_1 * rename "tegra_cpu_pllp" to "tegra_switch_cpu_to_pllp" --- arch/arm/mach-tegra/Kconfig | 1 + arch/arm/mach-tegra/cpuidle-tegra20.c | 125 +++++++++++++++++++++++++++++++--- arch/arm/mach-tegra/sleep-tegra20.S | 53 ++++++++++++++ arch/arm/mach-tegra/sleep.S | 19 ++++++ arch/arm/mach-tegra/sleep.h | 3 + 5 files changed, 192 insertions(+), 9 deletions(-) diff --git a/arch/arm/mach-tegra/Kconfig b/arch/arm/mach-tegra/Kconfig index 1ec7f80..abc688f 100644 --- a/arch/arm/mach-tegra/Kconfig +++ b/arch/arm/mach-tegra/Kconfig @@ -4,6 +4,7 @@ comment "NVIDIA Tegra options" config ARCH_TEGRA_2x_SOC bool "Enable support for Tegra20 family" + select ARCH_NEEDS_CPU_IDLE_COUPLED if SMP select ARCH_REQUIRE_GPIOLIB select ARM_ERRATA_720789 select ARM_ERRATA_742230 if SMP diff --git a/arch/arm/mach-tegra/cpuidle-tegra20.c b/arch/arm/mach-tegra/cpuidle-tegra20.c index 50f984d..63ab9c2 100644 --- a/arch/arm/mach-tegra/cpuidle-tegra20.c +++ b/arch/arm/mach-tegra/cpuidle-tegra20.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -32,22 +33,28 @@ #include "pm.h" #include "sleep.h" +#include "iomap.h" +#include "irq.h" +#include "flowctrl.h" #ifdef CONFIG_PM_SLEEP -static int tegra20_idle_lp2(struct cpuidle_device *dev, - struct cpuidle_driver *drv, - int index); +static atomic_t abort_flag; +static atomic_t abort_barrier; +static int tegra20_idle_lp2_coupled(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index); #endif static struct cpuidle_state tegra_idle_states[] = { [0] = ARM_CPUIDLE_WFI_STATE_PWR(600), #ifdef CONFIG_PM_SLEEP [1] = { - .enter = tegra20_idle_lp2, + .enter = tegra20_idle_lp2_coupled, .exit_latency = 5000, .target_residency = 10000, .power_usage = 0, - .flags = CPUIDLE_FLAG_TIME_VALID, + .flags = CPUIDLE_FLAG_TIME_VALID | + CPUIDLE_FLAG_COUPLED, .name = "powered-down", .desc = "CPU power gated", }, @@ -64,6 +71,88 @@ static DEFINE_PER_CPU(struct cpuidle_device, tegra_idle_device); #ifdef CONFIG_PM_SLEEP #ifdef CONFIG_SMP +static void __iomem *pmc = IO_ADDRESS(TEGRA_PMC_BASE); + +static int tegra20_reset_sleeping_cpu_1(void) +{ + int ret = 0; + + tegra_pen_lock(); + + if (readl(pmc + PMC_SCRATCH41) == CPU_RESETTABLE) + tegra20_cpu_shutdown(1); + else + ret = -EINVAL; + + tegra_pen_unlock(); + + return ret; +} + +static void tegra20_wake_cpu1_from_reset(void) +{ + tegra_pen_lock(); + + tegra20_cpu_clear_resettable(); + + /* enable cpu clock on cpu */ + tegra_enable_cpu_clock(1); + + /* take the CPU out of reset */ + tegra_cpu_out_of_reset(1); + + /* unhalt the cpu */ + flowctrl_write_cpu_halt(1, 0); + + tegra_pen_unlock(); +} + +static int tegra20_reset_cpu_1(void) +{ + if (!cpu_online(1) || !tegra20_reset_sleeping_cpu_1()) + return 0; + + tegra20_wake_cpu1_from_reset(); + return -EBUSY; +} +#else +static inline void tegra20_wake_cpu1_from_reset(void) +{ +} + +static inline int tegra20_reset_cpu_1(void) +{ + return 0; +} +#endif + +static bool tegra20_cpu_cluster_power_down(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + struct cpuidle_state *state = &drv->states[index]; + u32 cpu_on_time = state->exit_latency; + u32 cpu_off_time = state->target_residency - state->exit_latency; + + while (tegra20_cpu_is_resettable_soon()) + cpu_relax(); + + if (tegra20_reset_cpu_1() || !tegra_cpu_rail_off_ready()) + return false; + + clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu); + + tegra_idle_lp2_last(cpu_on_time, cpu_off_time); + + clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu); + + if (cpu_online(1)) + tegra20_wake_cpu1_from_reset(); + + return true; +} + +#ifdef CONFIG_SMP static bool tegra20_idle_enter_lp2_cpu_1(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index) @@ -87,20 +176,31 @@ static inline bool tegra20_idle_enter_lp2_cpu_1(struct cpuidle_device *dev, } #endif -static int tegra20_idle_lp2(struct cpuidle_device *dev, - struct cpuidle_driver *drv, - int index) +static int tegra20_idle_lp2_coupled(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) { u32 cpu = is_smp() ? cpu_logical_map(dev->cpu) : dev->cpu; bool entered_lp2 = false; + if (tegra_pending_sgi()) + atomic_inc(&abort_flag); + + cpuidle_coupled_parallel_barrier(dev, &abort_barrier); + + if (atomic_read(&abort_flag) > 0) { + cpuidle_coupled_parallel_barrier(dev, &abort_barrier); + atomic_set(&abort_flag, 0); /* clean flag for next coming */ + return -EINTR; + } + local_fiq_disable(); tegra_set_cpu_in_lp2(cpu); cpu_pm_enter(); if (cpu == 0) - cpu_do_idle(); + entered_lp2 = tegra20_cpu_cluster_power_down(dev, drv, index); else entered_lp2 = tegra20_idle_enter_lp2_cpu_1(dev, drv, index); @@ -122,6 +222,10 @@ int __init tegra20_cpuidle_init(void) struct cpuidle_device *dev; struct cpuidle_driver *drv = &tegra_idle_driver; +#ifdef CONFIG_PM_SLEEP + tegra_tear_down_cpu = tegra20_tear_down_cpu; +#endif + drv->state_count = ARRAY_SIZE(tegra_idle_states); memcpy(drv->states, tegra_idle_states, drv->state_count * sizeof(drv->states[0])); @@ -135,6 +239,9 @@ int __init tegra20_cpuidle_init(void) for_each_possible_cpu(cpu) { dev = &per_cpu(tegra_idle_device, cpu); dev->cpu = cpu; +#ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED + dev->coupled_cpus = *cpu_online_mask; +#endif dev->state_count = drv->state_count; ret = cpuidle_register_device(dev); diff --git a/arch/arm/mach-tegra/sleep-tegra20.S b/arch/arm/mach-tegra/sleep-tegra20.S index 1074364..9f6bfaf 100644 --- a/arch/arm/mach-tegra/sleep-tegra20.S +++ b/arch/arm/mach-tegra/sleep-tegra20.S @@ -57,6 +57,9 @@ ENDPROC(tegra20_hotplug_shutdown) ENTRY(tegra20_cpu_shutdown) cmp r0, #0 moveq pc, lr @ must not be called for CPU 0 + mov32 r1, TEGRA_PMC_VIRT + PMC_SCRATCH41 + mov r12, #CPU_RESETTABLE + str r12, [r1] cpu_to_halt_reg r1, r0 ldr r3, =TEGRA_FLOW_CTRL_VIRT @@ -163,6 +166,21 @@ ENTRY(tegra20_cpu_set_resettable_soon) ENDPROC(tegra20_cpu_set_resettable_soon) /* + * tegra20_cpu_is_resettable_soon(void) + * + * Returns true if the "resettable soon" flag in PMC_SCRATCH41 has been + * set because it is expected that the secondary CPU will be idle soon. + */ +ENTRY(tegra20_cpu_is_resettable_soon) + mov32 r1, TEGRA_PMC_VIRT + PMC_SCRATCH41 + ldr r12, [r1] + cmp r12, #CPU_RESETTABLE_SOON + moveq r0, #1 + movne r0, #0 + mov pc, lr +ENDPROC(tegra20_cpu_is_resettable_soon) + +/* * tegra20_sleep_cpu_secondary_finish(unsigned long v2p) * * Enters WFI on secondary CPU by exiting coherency. @@ -221,4 +239,39 @@ ENTRY(tegra20_sleep_cpu_secondary_finish) ldmfd sp!, {r4 - r11, pc} ENDPROC(tegra20_sleep_cpu_secondary_finish) + +/* + * tegra20_tear_down_cpu + * + * Switches the CPU cluster to PLL-P and enters sleep. + */ +ENTRY(tegra20_tear_down_cpu) + bl tegra_switch_cpu_to_pllp + b tegra20_enter_sleep +ENDPROC(tegra20_tear_down_cpu) + +/* + * tegra20_enter_sleep + * + * uses flow controller to enter sleep state + * executes from IRAM with SDRAM in selfrefresh when target state is LP0 or LP1 + * executes from SDRAM with target state is LP2 + */ +tegra20_enter_sleep: + mov32 r6, TEGRA_FLOW_CTRL_BASE + + mov r0, #FLOW_CTRL_WAIT_FOR_INTERRUPT + orr r0, r0, #FLOW_CTRL_HALT_CPU_IRQ | FLOW_CTRL_HALT_CPU_FIQ + cpu_id r1 + cpu_to_halt_reg r1, r1 + str r0, [r6, r1] + dsb + ldr r0, [r6, r1] /* memory barrier */ + +halted: + dsb + wfe /* CPU should be power gated here */ + isb + b halted + #endif diff --git a/arch/arm/mach-tegra/sleep.S b/arch/arm/mach-tegra/sleep.S index addae35..364d845 100644 --- a/arch/arm/mach-tegra/sleep.S +++ b/arch/arm/mach-tegra/sleep.S @@ -34,6 +34,9 @@ #include "flowctrl.h" #include "sleep.h" +#define CLK_RESET_CCLK_BURST 0x20 +#define CLK_RESET_CCLK_DIVIDER 0x24 + #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PM_SLEEP) /* * tegra_disable_clean_inv_dcache @@ -110,4 +113,20 @@ ENTRY(tegra_shut_off_mmu) mov pc, r0 ENDPROC(tegra_shut_off_mmu) .popsection + +/* + * tegra_switch_cpu_to_pllp + * + * In LP2 the normal cpu clock pllx will be turned off. Switch the CPU to pllp + */ +ENTRY(tegra_switch_cpu_to_pllp) + /* in LP2 idle (SDRAM active), set the CPU burst policy to PLLP */ + mov32 r5, TEGRA_CLK_RESET_BASE + mov r0, #(2 << 28) @ burst policy = run mode + orr r0, r0, #(4 << 4) @ use PLLP in run mode burst + str r0, [r5, #CLK_RESET_CCLK_BURST] + mov r0, #0 + str r0, [r5, #CLK_RESET_CCLK_DIVIDER] + mov pc, lr +ENDPROC(tegra_switch_cpu_to_pllp) #endif diff --git a/arch/arm/mach-tegra/sleep.h b/arch/arm/mach-tegra/sleep.h index e39a56b..4ffae54 100644 --- a/arch/arm/mach-tegra/sleep.h +++ b/arch/arm/mach-tegra/sleep.h @@ -131,6 +131,8 @@ static inline void tegra20_hotplug_init(void) {} static inline void tegra30_hotplug_init(void) {} #endif +void tegra20_cpu_shutdown(int cpu); +int tegra20_cpu_is_resettable_soon(void); void tegra20_cpu_clear_resettable(void); #ifdef CONFIG_ARCH_TEGRA_2x_SOC void tegra20_cpu_set_resettable_soon(void); @@ -139,6 +141,7 @@ static inline void tegra20_cpu_set_resettable_soon(void) {} #endif int tegra20_sleep_cpu_secondary_finish(unsigned long); +void tegra20_tear_down_cpu(void); int tegra30_sleep_cpu_secondary_finish(unsigned long); void tegra30_tear_down_cpu(void);