From 336e51283ae376835b30b9edfcddd8e7b7615798 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 26 May 2022 17:21:19 +0530 Subject: [PATCH 01/27] cpufreq: Optimize cpufreq_show_cpus() Instead of specially adding a space for each CPU, except the first one, lets add space for each of them and remove it at the end. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 2cad42774164..e24aa5d4bca5 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -843,12 +843,14 @@ ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf) unsigned int cpu; for_each_cpu(cpu, mask) { - if (i) - i += scnprintf(&buf[i], (PAGE_SIZE - i - 2), " "); - i += scnprintf(&buf[i], (PAGE_SIZE - i - 2), "%u", cpu); + i += scnprintf(&buf[i], (PAGE_SIZE - i - 2), "%u ", cpu); if (i >= (PAGE_SIZE - 5)) break; } + + /* Remove the extra space at the end */ + i--; + i += sprintf(&buf[i], "\n"); return i; } From 9ab9b9d3fb9231cdcfda8e0fb3d9c24a2f95ed26 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 26 May 2022 17:21:21 +0530 Subject: [PATCH 02/27] cpufreq: Drop unnecessary cpus locking from store() This change was introduced long back by commit 4f750c930822 ("cpufreq: Synchronize the cpufreq store_*() routines with CPU hotplug"). Since then, both cpufreq and hotplug core have been reworked and have much better locking in place. The race mentioned in commit 4f750c930822 isn't possible anymore. Drop the unnecessary locking. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq.c | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index e24aa5d4bca5..73432360e6e9 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -973,21 +973,10 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, if (!fattr->store) return -EIO; - /* - * cpus_read_trylock() is used here to work around a circular lock - * dependency problem with respect to the cpufreq_register_driver(). - */ - if (!cpus_read_trylock()) - return -EBUSY; - - if (cpu_online(policy->cpu)) { - down_write(&policy->rwsem); - if (likely(!policy_is_inactive(policy))) - ret = fattr->store(policy, buf, count); - up_write(&policy->rwsem); - } - - cpus_read_unlock(); + down_write(&policy->rwsem); + if (likely(!policy_is_inactive(policy))) + ret = fattr->store(policy, buf, count); + up_write(&policy->rwsem); return ret; } From 0da11bf0cab9029db8b85e48d962ff05c00a4faa Mon Sep 17 00:00:00 2001 From: Eiichi Tsukata Date: Fri, 27 May 2022 00:53:45 +0000 Subject: [PATCH 03/27] cpuidle: haltpoll: Add trace points for guest_halt_poll_ns grow/shrink Add trace points as are implemented in KVM host halt polling. This helps tune guest halt polling params. Signed-off-by: Eiichi Tsukata Acked-by: Marcelo Tosatti Signed-off-by: Rafael J. Wysocki --- drivers/cpuidle/governors/haltpoll.c | 3 +++ include/trace/events/power.h | 29 ++++++++++++++++++++++++++++ 2 files changed, 32 insertions(+) diff --git a/drivers/cpuidle/governors/haltpoll.c b/drivers/cpuidle/governors/haltpoll.c index cb2a96eafc02..1dff3a52917d 100644 --- a/drivers/cpuidle/governors/haltpoll.c +++ b/drivers/cpuidle/governors/haltpoll.c @@ -19,6 +19,7 @@ #include #include #include +#include static unsigned int guest_halt_poll_ns __read_mostly = 200000; module_param(guest_halt_poll_ns, uint, 0644); @@ -90,6 +91,7 @@ static void adjust_poll_limit(struct cpuidle_device *dev, u64 block_ns) if (val > guest_halt_poll_ns) val = guest_halt_poll_ns; + trace_guest_halt_poll_ns_grow(val, dev->poll_limit_ns); dev->poll_limit_ns = val; } else if (block_ns > guest_halt_poll_ns && guest_halt_poll_allow_shrink) { @@ -100,6 +102,7 @@ static void adjust_poll_limit(struct cpuidle_device *dev, u64 block_ns) val = 0; else val /= shrink; + trace_guest_halt_poll_ns_shrink(val, dev->poll_limit_ns); dev->poll_limit_ns = val; } } diff --git a/include/trace/events/power.h b/include/trace/events/power.h index af5018aa9517..c708521e4ed5 100644 --- a/include/trace/events/power.h +++ b/include/trace/events/power.h @@ -500,6 +500,35 @@ DEFINE_EVENT(dev_pm_qos_request, dev_pm_qos_remove_request, TP_ARGS(name, type, new_value) ); + +TRACE_EVENT(guest_halt_poll_ns, + + TP_PROTO(bool grow, unsigned int new, unsigned int old), + + TP_ARGS(grow, new, old), + + TP_STRUCT__entry( + __field(bool, grow) + __field(unsigned int, new) + __field(unsigned int, old) + ), + + TP_fast_assign( + __entry->grow = grow; + __entry->new = new; + __entry->old = old; + ), + + TP_printk("halt_poll_ns %u (%s %u)", + __entry->new, + __entry->grow ? "grow" : "shrink", + __entry->old) +); + +#define trace_guest_halt_poll_ns_grow(new, old) \ + trace_guest_halt_poll_ns(true, new, old) +#define trace_guest_halt_poll_ns_shrink(new, old) \ + trace_guest_halt_poll_ns(false, new, old) #endif /* _TRACE_POWER_H */ /* This part must be outside protection */ From d6f895965592d5cd2771860639219964df85d555 Mon Sep 17 00:00:00 2001 From: Tony W Wang-oc Date: Thu, 23 Jun 2022 09:21:26 +0800 Subject: [PATCH 04/27] cpufreq: ACPI: Add Zhaoxin/Centaur turbo boost control interface support Recent Zhaoxin/Centaur CPUs support X86_FEATURE_IDA and the turbo boost can be dynamically enabled or disabled through MSR 0x1a0[38] in the same way as Intel. So add turbo boost control support for these CPUs too. Signed-off-by: Tony W Wang-oc Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/acpi-cpufreq.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 3d514b82d055..1bb2b90ebb21 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -78,6 +78,8 @@ static bool boost_state(unsigned int cpu) switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_INTEL: + case X86_VENDOR_CENTAUR: + case X86_VENDOR_ZHAOXIN: rdmsr_on_cpu(cpu, MSR_IA32_MISC_ENABLE, &lo, &hi); msr = lo | ((u64)hi << 32); return !(msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE); @@ -97,6 +99,8 @@ static int boost_set_msr(bool enable) switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_INTEL: + case X86_VENDOR_CENTAUR: + case X86_VENDOR_ZHAOXIN: msr_addr = MSR_IA32_MISC_ENABLE; msr_mask = MSR_IA32_MISC_ENABLE_TURBO_DISABLE; break; From 09d3154a6f0f0bb5b604832095804780f3684b96 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Mon, 6 Jun 2022 22:51:58 -0500 Subject: [PATCH 05/27] PM: wakeup: Unify device_init_wakeup() for PM_SLEEP and !PM_SLEEP Previously the CONFIG_PM_SLEEP and !CONFIG_PM_SLEEP device_init_wakeup() implementations differed in confusing ways: - The PM_SLEEP version checked for a NULL device pointer and returned -EINVAL, while the !PM_SLEEP version did not and would simply dereference a NULL pointer. - When called with "false", the !PM_SLEEP version cleared "capable" and "enable" in the opposite order of the PM_SLEEP version. That was harmless because for !PM_SLEEP they're simple assignments, but it's unnecessary confusion. Use a simplified version of the PM_SLEEP implementation for both cases. Signed-off-by: Bjorn Helgaas Signed-off-by: Rafael J. Wysocki --- drivers/base/power/wakeup.c | 30 ------------------------------ include/linux/pm_wakeup.h | 31 +++++++++++++++++++++++-------- 2 files changed, 23 insertions(+), 38 deletions(-) diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index 11a4ffe91367..e3befa2c1b66 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -500,36 +500,6 @@ void device_set_wakeup_capable(struct device *dev, bool capable) } EXPORT_SYMBOL_GPL(device_set_wakeup_capable); -/** - * device_init_wakeup - Device wakeup initialization. - * @dev: Device to handle. - * @enable: Whether or not to enable @dev as a wakeup device. - * - * By default, most devices should leave wakeup disabled. The exceptions are - * devices that everyone expects to be wakeup sources: keyboards, power buttons, - * possibly network interfaces, etc. Also, devices that don't generate their - * own wakeup requests but merely forward requests from one bus to another - * (like PCI bridges) should have wakeup enabled by default. - */ -int device_init_wakeup(struct device *dev, bool enable) -{ - int ret = 0; - - if (!dev) - return -EINVAL; - - if (enable) { - device_set_wakeup_capable(dev, true); - ret = device_wakeup_enable(dev); - } else { - device_wakeup_disable(dev); - device_set_wakeup_capable(dev, false); - } - - return ret; -} -EXPORT_SYMBOL_GPL(device_init_wakeup); - /** * device_set_wakeup_enable - Enable or disable a device to wake up the system. * @dev: Device to handle. diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h index 196a157456aa..77f4849e3418 100644 --- a/include/linux/pm_wakeup.h +++ b/include/linux/pm_wakeup.h @@ -109,7 +109,6 @@ extern struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws); extern int device_wakeup_enable(struct device *dev); extern int device_wakeup_disable(struct device *dev); extern void device_set_wakeup_capable(struct device *dev, bool capable); -extern int device_init_wakeup(struct device *dev, bool val); extern int device_set_wakeup_enable(struct device *dev, bool enable); extern void __pm_stay_awake(struct wakeup_source *ws); extern void pm_stay_awake(struct device *dev); @@ -167,13 +166,6 @@ static inline int device_set_wakeup_enable(struct device *dev, bool enable) return 0; } -static inline int device_init_wakeup(struct device *dev, bool val) -{ - device_set_wakeup_capable(dev, val); - device_set_wakeup_enable(dev, val); - return 0; -} - static inline bool device_may_wakeup(struct device *dev) { return dev->power.can_wakeup && dev->power.should_wakeup; @@ -217,4 +209,27 @@ static inline void pm_wakeup_hard_event(struct device *dev) return pm_wakeup_dev_event(dev, 0, true); } +/** + * device_init_wakeup - Device wakeup initialization. + * @dev: Device to handle. + * @enable: Whether or not to enable @dev as a wakeup device. + * + * By default, most devices should leave wakeup disabled. The exceptions are + * devices that everyone expects to be wakeup sources: keyboards, power buttons, + * possibly network interfaces, etc. Also, devices that don't generate their + * own wakeup requests but merely forward requests from one bus to another + * (like PCI bridges) should have wakeup enabled by default. + */ +static inline int device_init_wakeup(struct device *dev, bool enable) +{ + if (enable) { + device_set_wakeup_capable(dev, true); + return device_wakeup_enable(dev); + } else { + device_wakeup_disable(dev); + device_set_wakeup_capable(dev, false); + return 0; + } +} + #endif /* _LINUX_PM_WAKEUP_H */ From 2755714656d0f2f41adfe231f3865e72da2cbe39 Mon Sep 17 00:00:00 2001 From: George D Sworo Date: Wed, 1 Jun 2022 12:22:16 -0700 Subject: [PATCH 06/27] powercap: intel_rapl: Add support for RAPTORLAKE_P Add RAPTORLAKE_P to the list of supported processor models in the Intel RAPL power capping driver. Signed-off-by: George D Sworo Acked-by: Zhang Rui Tested-by: Sumeet Pawnikar [ rjw: Minor changelog edits ] Signed-off-by: Rafael J. Wysocki --- drivers/powercap/intel_rapl_common.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index a9c99d9e8b42..21d624f9f5fb 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -1109,6 +1109,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &rapl_defaults_core), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &rapl_defaults_core), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &rapl_defaults_core), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &rapl_defaults_core), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &rapl_defaults_spr_server), X86_MATCH_INTEL_FAM6_MODEL(LAKEFIELD, &rapl_defaults_core), From 7c4300eb05fbf5513924b970aaa86774af9b2832 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Thu, 2 Jun 2022 11:33:30 -0500 Subject: [PATCH 07/27] Documentation: PM: Drop pme_interrupt reference `pme_interrupt` was dropped from `struct pci_dev` as part of commit 8370c2dc4c7b ("PCI / PM: Drop pme_interrupt flag from struct pci_dev"), but the Documentation still includes this member. Remove it from the documentation as well and update it to have the missing `pme_poll` member instead. Fixes: 8370c2dc4c7b ("PCI / PM: Drop pme_interrupt flag from struct pci_dev") Signed-off-by: Mario Limonciello Reviewed-by: Mika Westerberg Signed-off-by: Rafael J. Wysocki --- Documentation/power/pci.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/power/pci.rst b/Documentation/power/pci.rst index b04fb18cc4e2..a125544b4cb6 100644 --- a/Documentation/power/pci.rst +++ b/Documentation/power/pci.rst @@ -315,7 +315,7 @@ that these callbacks operate on:: configuration space */ unsigned int pme_support:5; /* Bitmask of states from which PME# can be generated */ - unsigned int pme_interrupt:1;/* Is native PCIe PME signaling used? */ + unsigned int pme_poll:1; /* Poll device's PME status bit */ unsigned int d1_support:1; /* Low power state D1 is supported */ unsigned int d2_support:1; /* Low power state D2 is supported */ unsigned int no_d1d2:1; /* D1 and D2 are forbidden */ From c46a0d5ae4f93800d2d90f3a3290e58a2f4b6bdf Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 8 Jun 2022 17:31:20 +0200 Subject: [PATCH 08/27] PM: runtime: Extend support for wakeirq for force_suspend|resume A driver that makes use of pm_runtime_force_suspend|resume() to support system suspend/resume, currently needs to manage the wakeirq support itself. To avoid the boilerplate code in the driver's system suspend/resume callbacks in particular, let's extend pm_runtime_force_suspend|resume() to deal with the wakeirq. Signed-off-by: Ulf Hansson Reviewed-by: Tony Lindgren Signed-off-by: Rafael J. Wysocki --- drivers/base/power/runtime.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 949907e2e242..997be3ac20a7 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -1862,10 +1862,13 @@ int pm_runtime_force_suspend(struct device *dev) callback = RPM_GET_CALLBACK(dev, runtime_suspend); + dev_pm_enable_wake_irq_check(dev, true); ret = callback ? callback(dev) : 0; if (ret) goto err; + dev_pm_enable_wake_irq_complete(dev); + /* * If the device can stay in suspend after the system-wide transition * to the working state that will follow, drop the children counter of @@ -1882,6 +1885,7 @@ int pm_runtime_force_suspend(struct device *dev) return 0; err: + dev_pm_disable_wake_irq_check(dev, true); pm_runtime_enable(dev); return ret; } @@ -1915,9 +1919,11 @@ int pm_runtime_force_resume(struct device *dev) callback = RPM_GET_CALLBACK(dev, runtime_resume); + dev_pm_disable_wake_irq_check(dev, false); ret = callback ? callback(dev) : 0; if (ret) { pm_runtime_set_suspended(dev); + dev_pm_enable_wake_irq_check(dev, false); goto out; } From 37101d3c719386040ded735a5ec06974f1d94d1f Mon Sep 17 00:00:00 2001 From: Hsin-Yi Wang Date: Wed, 6 Jul 2022 01:16:49 +0800 Subject: [PATCH 09/27] PM: domains: Ensure genpd_debugfs_dir exists before remove Both genpd_debug_add() and genpd_debug_remove() may be called indirectly by other drivers while genpd_debugfs_dir is not yet set. For example, drivers can call pm_genpd_init() in probe or pm_genpd_init() in probe fail/cleanup path: pm_genpd_init() --> genpd_debug_add() pm_genpd_remove() --> genpd_remove() --> genpd_debug_remove() At this time, genpd_debug_init() may not yet be called. genpd_debug_add() checks that if genpd_debugfs_dir is NULL, it will return directly. Make sure this is also checked in pm_genpd_remove(), otherwise components under debugfs root which has the same name as other components under pm_genpd may be accidentally removed, since NULL represents debugfs root. Fixes: 718072ceb211 ("PM: domains: create debugfs nodes when adding power domains") Signed-off-by: Hsin-Yi Wang Reviewed-by: Greg Kroah-Hartman Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 739e52cd4aba..55a10e6d4e2a 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -222,6 +222,9 @@ static void genpd_debug_remove(struct generic_pm_domain *genpd) { struct dentry *d; + if (!genpd_debugfs_dir) + return; + d = debugfs_lookup(genpd->name, genpd_debugfs_dir); debugfs_remove(d); } From 3be51a3b1980347da7d51f66b1e8e8c538961f17 Mon Sep 17 00:00:00 2001 From: Johnson Wang Date: Tue, 7 Jun 2022 22:05:55 +0800 Subject: [PATCH 10/27] dt-bindings: interconnect: Add MediaTek CCI dt-bindings Add devicetree binding of MediaTek CCI on MT8183 and MT8186. Signed-off-by: Jia-Wei Chang Signed-off-by: Johnson Wang Reviewed-by: Krzysztof Kozlowski Acked-by: Chanwoo Choi Reviewed-by: Chen-Yu Tsai Reviewed-by: AngeloGioacchino Del Regno Acked-by: Georgi Djakov Tested-by: Kevin Hilman Signed-off-by: Chanwoo Choi --- .../bindings/interconnect/mediatek,cci.yaml | 141 ++++++++++++++++++ MAINTAINERS | 1 + 2 files changed, 142 insertions(+) create mode 100644 Documentation/devicetree/bindings/interconnect/mediatek,cci.yaml diff --git a/Documentation/devicetree/bindings/interconnect/mediatek,cci.yaml b/Documentation/devicetree/bindings/interconnect/mediatek,cci.yaml new file mode 100644 index 000000000000..449c7c988229 --- /dev/null +++ b/Documentation/devicetree/bindings/interconnect/mediatek,cci.yaml @@ -0,0 +1,141 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/interconnect/mediatek,cci.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: MediaTek Cache Coherent Interconnect (CCI) frequency and voltage scaling + +maintainers: + - Jia-Wei Chang + - Johnson Wang + +description: | + MediaTek Cache Coherent Interconnect (CCI) is a hardware engine used by + MT8183 and MT8186 SoCs to scale the frequency and adjust the voltage in + hardware. It can also optimize the voltage to reduce the power consumption. + +properties: + compatible: + enum: + - mediatek,mt8183-cci + - mediatek,mt8186-cci + + clocks: + items: + - description: + The multiplexer for clock input of the bus. + - description: + A parent of "bus" clock which is used as an intermediate clock source + when the original clock source (PLL) is under transition and not + stable yet. + + clock-names: + items: + - const: cci + - const: intermediate + + operating-points-v2: true + opp-table: true + + proc-supply: + description: + Phandle of the regulator for CCI that provides the supply voltage. + + sram-supply: + description: + Phandle of the regulator for sram of CCI that provides the supply + voltage. When it is present, the implementation needs to do + "voltage tracking" to step by step scale up/down Vproc and Vsram to fit + SoC specific needs. When absent, the voltage scaling flow is handled by + hardware, hence no software "voltage tracking" is needed. + +required: + - compatible + - clocks + - clock-names + - operating-points-v2 + - proc-supply + +additionalProperties: false + +examples: + - | + #include + cci: cci { + compatible = "mediatek,mt8183-cci"; + clocks = <&mcucfg CLK_MCU_BUS_SEL>, + <&topckgen CLK_TOP_ARMPLL_DIV_PLL1>; + clock-names = "cci", "intermediate"; + operating-points-v2 = <&cci_opp>; + proc-supply = <&mt6358_vproc12_reg>; + }; + + cci_opp: opp-table-cci { + compatible = "operating-points-v2"; + opp-shared; + opp2_00: opp-273000000 { + opp-hz = /bits/ 64 <273000000>; + opp-microvolt = <650000>; + }; + opp2_01: opp-338000000 { + opp-hz = /bits/ 64 <338000000>; + opp-microvolt = <687500>; + }; + opp2_02: opp-403000000 { + opp-hz = /bits/ 64 <403000000>; + opp-microvolt = <718750>; + }; + opp2_03: opp-463000000 { + opp-hz = /bits/ 64 <463000000>; + opp-microvolt = <756250>; + }; + opp2_04: opp-546000000 { + opp-hz = /bits/ 64 <546000000>; + opp-microvolt = <800000>; + }; + opp2_05: opp-624000000 { + opp-hz = /bits/ 64 <624000000>; + opp-microvolt = <818750>; + }; + opp2_06: opp-689000000 { + opp-hz = /bits/ 64 <689000000>; + opp-microvolt = <850000>; + }; + opp2_07: opp-767000000 { + opp-hz = /bits/ 64 <767000000>; + opp-microvolt = <868750>; + }; + opp2_08: opp-845000000 { + opp-hz = /bits/ 64 <845000000>; + opp-microvolt = <893750>; + }; + opp2_09: opp-871000000 { + opp-hz = /bits/ 64 <871000000>; + opp-microvolt = <906250>; + }; + opp2_10: opp-923000000 { + opp-hz = /bits/ 64 <923000000>; + opp-microvolt = <931250>; + }; + opp2_11: opp-962000000 { + opp-hz = /bits/ 64 <962000000>; + opp-microvolt = <943750>; + }; + opp2_12: opp-1027000000 { + opp-hz = /bits/ 64 <1027000000>; + opp-microvolt = <975000>; + }; + opp2_13: opp-1092000000 { + opp-hz = /bits/ 64 <1092000000>; + opp-microvolt = <1000000>; + }; + opp2_14: opp-1144000000 { + opp-hz = /bits/ 64 <1144000000>; + opp-microvolt = <1025000>; + }; + opp2_15: opp-1196000000 { + opp-hz = /bits/ 64 <1196000000>; + opp-microvolt = <1050000>; + }; + }; diff --git a/MAINTAINERS b/MAINTAINERS index f679152bdbad..29790c536587 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5856,6 +5856,7 @@ L: linux-pm@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/linux.git F: Documentation/devicetree/bindings/devfreq/ +F: Documentation/devicetree/bindings/interconnect/mediatek,cci.yaml F: drivers/devfreq/ F: include/linux/devfreq.h F: include/trace/events/devfreq.h From 86d231b1db1be0666c2fc607f5025d63d7afc5f3 Mon Sep 17 00:00:00 2001 From: Johnson Wang Date: Tue, 7 Jun 2022 22:05:56 +0800 Subject: [PATCH 11/27] PM / devfreq: mediatek: Introduce MediaTek CCI devfreq driver We introduce a devfreq driver for the MediaTek Cache Coherent Interconnect (CCI) used by some MediaTek SoCs. In this driver, we use the passive devfreq driver to get target frequencies and adjust voltages accordingly. In MT8183 and MT8186, the MediaTek CCI is supplied by the same regulators with the little core CPUs. Signed-off-by: Jia-Wei Chang Signed-off-by: Johnson Wang Acked-by: Chanwoo Choi Tested-by: Kevin Hilman Signed-off-by: Chanwoo Choi --- drivers/devfreq/Kconfig | 10 + drivers/devfreq/Makefile | 1 + drivers/devfreq/mtk-cci-devfreq.c | 440 ++++++++++++++++++++++++++++++ 3 files changed, 451 insertions(+) create mode 100644 drivers/devfreq/mtk-cci-devfreq.c diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig index 87eb2b837e68..9754d8b31621 100644 --- a/drivers/devfreq/Kconfig +++ b/drivers/devfreq/Kconfig @@ -120,6 +120,16 @@ config ARM_TEGRA_DEVFREQ It reads ACTMON counters of memory controllers and adjusts the operating frequencies and voltages with OPP support. +config ARM_MEDIATEK_CCI_DEVFREQ + tristate "MEDIATEK CCI DEVFREQ Driver" + depends on ARM_MEDIATEK_CPUFREQ || COMPILE_TEST + select DEVFREQ_GOV_PASSIVE + help + This adds a devfreq driver for MediaTek Cache Coherent Interconnect + which is shared the same regulators with the cpu cluster. It can track + buck voltages and update a proper CCI frequency. Use the notification + to get the regulator status. + config ARM_RK3399_DMC_DEVFREQ tristate "ARM RK3399 DMC DEVFREQ Driver" depends on (ARCH_ROCKCHIP && HAVE_ARM_SMCCC) || \ diff --git a/drivers/devfreq/Makefile b/drivers/devfreq/Makefile index 0b6be92a25d9..bf40d04928d0 100644 --- a/drivers/devfreq/Makefile +++ b/drivers/devfreq/Makefile @@ -11,6 +11,7 @@ obj-$(CONFIG_DEVFREQ_GOV_PASSIVE) += governor_passive.o obj-$(CONFIG_ARM_EXYNOS_BUS_DEVFREQ) += exynos-bus.o obj-$(CONFIG_ARM_IMX_BUS_DEVFREQ) += imx-bus.o obj-$(CONFIG_ARM_IMX8M_DDRC_DEVFREQ) += imx8m-ddrc.o +obj-$(CONFIG_ARM_MEDIATEK_CCI_DEVFREQ) += mtk-cci-devfreq.o obj-$(CONFIG_ARM_RK3399_DMC_DEVFREQ) += rk3399_dmc.o obj-$(CONFIG_ARM_SUN8I_A33_MBUS_DEVFREQ) += sun8i-a33-mbus.o obj-$(CONFIG_ARM_TEGRA_DEVFREQ) += tegra30-devfreq.o diff --git a/drivers/devfreq/mtk-cci-devfreq.c b/drivers/devfreq/mtk-cci-devfreq.c new file mode 100644 index 000000000000..71abb3fbd042 --- /dev/null +++ b/drivers/devfreq/mtk-cci-devfreq.c @@ -0,0 +1,440 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2022 MediaTek Inc. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct mtk_ccifreq_platform_data { + int min_volt_shift; + int max_volt_shift; + int proc_max_volt; + int sram_min_volt; + int sram_max_volt; +}; + +struct mtk_ccifreq_drv { + struct device *dev; + struct devfreq *devfreq; + struct regulator *proc_reg; + struct regulator *sram_reg; + struct clk *cci_clk; + struct clk *inter_clk; + int inter_voltage; + unsigned long pre_freq; + /* Avoid race condition for regulators between notify and policy */ + struct mutex reg_lock; + struct notifier_block opp_nb; + const struct mtk_ccifreq_platform_data *soc_data; + int vtrack_max; +}; + +static int mtk_ccifreq_set_voltage(struct mtk_ccifreq_drv *drv, int new_voltage) +{ + const struct mtk_ccifreq_platform_data *soc_data = drv->soc_data; + struct device *dev = drv->dev; + int pre_voltage, pre_vsram, new_vsram, vsram, voltage, ret; + int retry_max = drv->vtrack_max; + + if (!drv->sram_reg) { + ret = regulator_set_voltage(drv->proc_reg, new_voltage, + drv->soc_data->proc_max_volt); + return ret; + } + + pre_voltage = regulator_get_voltage(drv->proc_reg); + if (pre_voltage < 0) { + dev_err(dev, "invalid vproc value: %d\n", pre_voltage); + return pre_voltage; + } + + pre_vsram = regulator_get_voltage(drv->sram_reg); + if (pre_vsram < 0) { + dev_err(dev, "invalid vsram value: %d\n", pre_vsram); + return pre_vsram; + } + + new_vsram = clamp(new_voltage + soc_data->min_volt_shift, + soc_data->sram_min_volt, soc_data->sram_max_volt); + + do { + if (pre_voltage <= new_voltage) { + vsram = clamp(pre_voltage + soc_data->max_volt_shift, + soc_data->sram_min_volt, new_vsram); + ret = regulator_set_voltage(drv->sram_reg, vsram, + soc_data->sram_max_volt); + if (ret) + return ret; + + if (vsram == soc_data->sram_max_volt || + new_vsram == soc_data->sram_min_volt) + voltage = new_voltage; + else + voltage = vsram - soc_data->min_volt_shift; + + ret = regulator_set_voltage(drv->proc_reg, voltage, + soc_data->proc_max_volt); + if (ret) { + regulator_set_voltage(drv->sram_reg, pre_vsram, + soc_data->sram_max_volt); + return ret; + } + } else if (pre_voltage > new_voltage) { + voltage = max(new_voltage, + pre_vsram - soc_data->max_volt_shift); + ret = regulator_set_voltage(drv->proc_reg, voltage, + soc_data->proc_max_volt); + if (ret) + return ret; + + if (voltage == new_voltage) + vsram = new_vsram; + else + vsram = max(new_vsram, + voltage + soc_data->min_volt_shift); + + ret = regulator_set_voltage(drv->sram_reg, vsram, + soc_data->sram_max_volt); + if (ret) { + regulator_set_voltage(drv->proc_reg, pre_voltage, + soc_data->proc_max_volt); + return ret; + } + } + + pre_voltage = voltage; + pre_vsram = vsram; + + if (--retry_max < 0) { + dev_err(dev, + "over loop count, failed to set voltage\n"); + return -EINVAL; + } + } while (voltage != new_voltage || vsram != new_vsram); + + return 0; +} + +static int mtk_ccifreq_target(struct device *dev, unsigned long *freq, + u32 flags) +{ + struct mtk_ccifreq_drv *drv = dev_get_drvdata(dev); + struct clk *cci_pll = clk_get_parent(drv->cci_clk); + struct dev_pm_opp *opp; + unsigned long opp_rate; + int voltage, pre_voltage, inter_voltage, target_voltage, ret; + + if (!drv) + return -EINVAL; + + if (drv->pre_freq == *freq) + return 0; + + inter_voltage = drv->inter_voltage; + + opp_rate = *freq; + opp = devfreq_recommended_opp(dev, &opp_rate, 1); + if (IS_ERR(opp)) { + dev_err(dev, "failed to find opp for freq: %ld\n", opp_rate); + return PTR_ERR(opp); + } + + mutex_lock(&drv->reg_lock); + + voltage = dev_pm_opp_get_voltage(opp); + dev_pm_opp_put(opp); + + pre_voltage = regulator_get_voltage(drv->proc_reg); + if (pre_voltage < 0) { + dev_err(dev, "invalid vproc value: %d\n", pre_voltage); + ret = pre_voltage; + goto out_unlock; + } + + /* scale up: set voltage first then freq. */ + target_voltage = max(inter_voltage, voltage); + if (pre_voltage <= target_voltage) { + ret = mtk_ccifreq_set_voltage(drv, target_voltage); + if (ret) { + dev_err(dev, "failed to scale up voltage\n"); + goto out_restore_voltage; + } + } + + /* switch the cci clock to intermediate clock source. */ + ret = clk_set_parent(drv->cci_clk, drv->inter_clk); + if (ret) { + dev_err(dev, "failed to re-parent cci clock\n"); + goto out_restore_voltage; + } + + /* set the original clock to target rate. */ + ret = clk_set_rate(cci_pll, *freq); + if (ret) { + dev_err(dev, "failed to set cci pll rate: %d\n", ret); + clk_set_parent(drv->cci_clk, cci_pll); + goto out_restore_voltage; + } + + /* switch the cci clock back to the original clock source. */ + ret = clk_set_parent(drv->cci_clk, cci_pll); + if (ret) { + dev_err(dev, "failed to re-parent cci clock\n"); + mtk_ccifreq_set_voltage(drv, inter_voltage); + goto out_unlock; + } + + /* + * If the new voltage is lower than the intermediate voltage or the + * original voltage, scale down to the new voltage. + */ + if (voltage < inter_voltage || voltage < pre_voltage) { + ret = mtk_ccifreq_set_voltage(drv, voltage); + if (ret) { + dev_err(dev, "failed to scale down voltage\n"); + goto out_unlock; + } + } + + drv->pre_freq = *freq; + mutex_unlock(&drv->reg_lock); + + return 0; + +out_restore_voltage: + mtk_ccifreq_set_voltage(drv, pre_voltage); + +out_unlock: + mutex_unlock(&drv->reg_lock); + return ret; +} + +static int mtk_ccifreq_opp_notifier(struct notifier_block *nb, + unsigned long event, void *data) +{ + struct dev_pm_opp *opp = data; + struct mtk_ccifreq_drv *drv; + unsigned long freq, volt; + + drv = container_of(nb, struct mtk_ccifreq_drv, opp_nb); + + if (event == OPP_EVENT_ADJUST_VOLTAGE) { + freq = dev_pm_opp_get_freq(opp); + + mutex_lock(&drv->reg_lock); + /* current opp item is changed */ + if (freq == drv->pre_freq) { + volt = dev_pm_opp_get_voltage(opp); + mtk_ccifreq_set_voltage(drv, volt); + } + mutex_unlock(&drv->reg_lock); + } + + return 0; +} + +static struct devfreq_dev_profile mtk_ccifreq_profile = { + .target = mtk_ccifreq_target, +}; + +static int mtk_ccifreq_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct mtk_ccifreq_drv *drv; + struct devfreq_passive_data *passive_data; + struct dev_pm_opp *opp; + unsigned long rate, opp_volt; + int ret; + + drv = devm_kzalloc(dev, sizeof(*drv), GFP_KERNEL); + if (!drv) + return -ENOMEM; + + drv->dev = dev; + drv->soc_data = (const struct mtk_ccifreq_platform_data *) + of_device_get_match_data(&pdev->dev); + mutex_init(&drv->reg_lock); + platform_set_drvdata(pdev, drv); + + drv->cci_clk = devm_clk_get(dev, "cci"); + if (IS_ERR(drv->cci_clk)) { + ret = PTR_ERR(drv->cci_clk); + return dev_err_probe(dev, ret, "failed to get cci clk\n"); + } + + drv->inter_clk = devm_clk_get(dev, "intermediate"); + if (IS_ERR(drv->inter_clk)) { + ret = PTR_ERR(drv->inter_clk); + return dev_err_probe(dev, ret, + "failed to get intermediate clk\n"); + } + + drv->proc_reg = devm_regulator_get_optional(dev, "proc"); + if (IS_ERR(drv->proc_reg)) { + ret = PTR_ERR(drv->proc_reg); + return dev_err_probe(dev, ret, + "failed to get proc regulator\n"); + } + + ret = regulator_enable(drv->proc_reg); + if (ret) { + dev_err(dev, "failed to enable proc regulator\n"); + return ret; + } + + drv->sram_reg = devm_regulator_get_optional(dev, "sram"); + if (IS_ERR(drv->sram_reg)) + drv->sram_reg = NULL; + else { + ret = regulator_enable(drv->sram_reg); + if (ret) { + dev_err(dev, "failed to enable sram regulator\n"); + goto out_free_resources; + } + } + + /* + * We assume min voltage is 0 and tracking target voltage using + * min_volt_shift for each iteration. + * The retry_max is 3 times of expected iteration count. + */ + drv->vtrack_max = 3 * DIV_ROUND_UP(max(drv->soc_data->sram_max_volt, + drv->soc_data->proc_max_volt), + drv->soc_data->min_volt_shift); + + ret = clk_prepare_enable(drv->cci_clk); + if (ret) + goto out_free_resources; + + ret = dev_pm_opp_of_add_table(dev); + if (ret) { + dev_err(dev, "failed to add opp table: %d\n", ret); + goto out_disable_cci_clk; + } + + rate = clk_get_rate(drv->inter_clk); + opp = dev_pm_opp_find_freq_ceil(dev, &rate); + if (IS_ERR(opp)) { + ret = PTR_ERR(opp); + dev_err(dev, "failed to get intermediate opp: %d\n", ret); + goto out_remove_opp_table; + } + drv->inter_voltage = dev_pm_opp_get_voltage(opp); + dev_pm_opp_put(opp); + + rate = U32_MAX; + opp = dev_pm_opp_find_freq_floor(drv->dev, &rate); + if (IS_ERR(opp)) { + dev_err(dev, "failed to get opp\n"); + ret = PTR_ERR(opp); + goto out_remove_opp_table; + } + + opp_volt = dev_pm_opp_get_voltage(opp); + dev_pm_opp_put(opp); + ret = mtk_ccifreq_set_voltage(drv, opp_volt); + if (ret) { + dev_err(dev, "failed to scale to highest voltage %lu in proc_reg\n", + opp_volt); + goto out_remove_opp_table; + } + + passive_data = devm_kzalloc(dev, sizeof(*passive_data), GFP_KERNEL); + if (!passive_data) { + ret = -ENOMEM; + goto out_remove_opp_table; + } + + passive_data->parent_type = CPUFREQ_PARENT_DEV; + drv->devfreq = devm_devfreq_add_device(dev, &mtk_ccifreq_profile, + DEVFREQ_GOV_PASSIVE, + passive_data); + if (IS_ERR(drv->devfreq)) { + ret = -EPROBE_DEFER; + dev_err(dev, "failed to add devfreq device: %ld\n", + PTR_ERR(drv->devfreq)); + goto out_remove_opp_table; + } + + drv->opp_nb.notifier_call = mtk_ccifreq_opp_notifier; + ret = dev_pm_opp_register_notifier(dev, &drv->opp_nb); + if (ret) { + dev_err(dev, "failed to register opp notifier: %d\n", ret); + goto out_remove_opp_table; + } + return 0; + +out_remove_opp_table: + dev_pm_opp_of_remove_table(dev); + +out_disable_cci_clk: + clk_disable_unprepare(drv->cci_clk); + +out_free_resources: + if (regulator_is_enabled(drv->proc_reg)) + regulator_disable(drv->proc_reg); + if (drv->sram_reg && regulator_is_enabled(drv->sram_reg)) + regulator_disable(drv->sram_reg); + + return ret; +} + +static int mtk_ccifreq_remove(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct mtk_ccifreq_drv *drv; + + drv = platform_get_drvdata(pdev); + + dev_pm_opp_unregister_notifier(dev, &drv->opp_nb); + dev_pm_opp_of_remove_table(dev); + clk_disable_unprepare(drv->cci_clk); + regulator_disable(drv->proc_reg); + if (drv->sram_reg) + regulator_disable(drv->sram_reg); + + return 0; +} + +static const struct mtk_ccifreq_platform_data mt8183_platform_data = { + .min_volt_shift = 100000, + .max_volt_shift = 200000, + .proc_max_volt = 1150000, +}; + +static const struct mtk_ccifreq_platform_data mt8186_platform_data = { + .min_volt_shift = 100000, + .max_volt_shift = 250000, + .proc_max_volt = 1118750, + .sram_min_volt = 850000, + .sram_max_volt = 1118750, +}; + +static const struct of_device_id mtk_ccifreq_machines[] = { + { .compatible = "mediatek,mt8183-cci", .data = &mt8183_platform_data }, + { .compatible = "mediatek,mt8186-cci", .data = &mt8186_platform_data }, + { }, +}; +MODULE_DEVICE_TABLE(of, mtk_ccifreq_machines); + +static struct platform_driver mtk_ccifreq_platdrv = { + .probe = mtk_ccifreq_probe, + .remove = mtk_ccifreq_remove, + .driver = { + .name = "mtk-ccifreq", + .of_match_table = mtk_ccifreq_machines, + }, +}; +module_platform_driver(mtk_ccifreq_platdrv); + +MODULE_DESCRIPTION("MediaTek CCI devfreq driver"); +MODULE_AUTHOR("Jia-Wei Chang "); +MODULE_LICENSE("GPL v2"); From e7fd2e6b9772e19f4da2a7c0c7c813758aee7a88 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 26 Jun 2022 14:52:38 +0200 Subject: [PATCH 12/27] dt-bindings: interconnect: samsung,exynos-bus: convert to dtschema Convert the Samsung Exynos SoC Bus and Interconnect bindings to DT schema. Vast parts of descritpion and example were copied, so keep license as GPL-2.0-only. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Chanwoo Choi --- .../bindings/devfreq/exynos-bus.txt | 488 ------------------ .../interconnect/samsung,exynos-bus.yaml | 290 +++++++++++ MAINTAINERS | 2 +- 3 files changed, 291 insertions(+), 489 deletions(-) delete mode 100644 Documentation/devicetree/bindings/devfreq/exynos-bus.txt create mode 100644 Documentation/devicetree/bindings/interconnect/samsung,exynos-bus.yaml diff --git a/Documentation/devicetree/bindings/devfreq/exynos-bus.txt b/Documentation/devicetree/bindings/devfreq/exynos-bus.txt deleted file mode 100644 index bcaa2c08ac11..000000000000 --- a/Documentation/devicetree/bindings/devfreq/exynos-bus.txt +++ /dev/null @@ -1,488 +0,0 @@ -* Generic Exynos Bus frequency device - -The Samsung Exynos SoC has many buses for data transfer between DRAM -and sub-blocks in SoC. Most Exynos SoCs share the common architecture -for buses. Generally, each bus of Exynos SoC includes a source clock -and a power line, which are able to change the clock frequency -of the bus in runtime. To monitor the usage of each bus in runtime, -the driver uses the PPMU (Platform Performance Monitoring Unit), which -is able to measure the current load of sub-blocks. - -The Exynos SoC includes the various sub-blocks which have the each AXI bus. -The each AXI bus has the owned source clock but, has not the only owned -power line. The power line might be shared among one more sub-blocks. -So, we can divide into two type of device as the role of each sub-block. -There are two type of bus devices as following: -- parent bus device -- passive bus device - -Basically, parent and passive bus device share the same power line. -The parent bus device can only change the voltage of shared power line -and the rest bus devices (passive bus device) depend on the decision of -the parent bus device. If there are three blocks which share the VDD_xxx -power line, Only one block should be parent device and then the rest blocks -should depend on the parent device as passive device. - - VDD_xxx |--- A block (parent) - |--- B block (passive) - |--- C block (passive) - -There are a little different composition among Exynos SoC because each Exynos -SoC has different sub-blocks. Therefore, such difference should be specified -in devicetree file instead of each device driver. In result, this driver -is able to support the bus frequency for all Exynos SoCs. - -Required properties for all bus devices: -- compatible: Should be "samsung,exynos-bus". -- clock-names : the name of clock used by the bus, "bus". -- clocks : phandles for clock specified in "clock-names" property. -- operating-points-v2: the OPP table including frequency/voltage information - to support DVFS (Dynamic Voltage/Frequency Scaling) feature. - -Required properties only for parent bus device: -- vdd-supply: the regulator to provide the buses with the voltage. -- devfreq-events: the devfreq-event device to monitor the current utilization - of buses. - -Required properties only for passive bus device: -- devfreq: the parent bus device. - -Optional properties only for parent bus device: -- exynos,saturation-ratio: the percentage value which is used to calibrate - the performance count against total cycle count. - -Optional properties for the interconnect functionality (QoS frequency -constraints): -- #interconnect-cells: should be 0. -- interconnects: as documented in ../interconnect.txt, describes a path at the - higher level interconnects used by this interconnect provider. - If this interconnect provider is directly linked to a top level interconnect - provider the property contains only one phandle. The provider extends - the interconnect graph by linking its node to a node registered by provider - pointed to by first phandle in the 'interconnects' property. - -- samsung,data-clock-ratio: ratio of the data throughput in B/s to minimum data - clock frequency in Hz, default value is 8 when this property is missing. - -Detailed correlation between sub-blocks and power line according to Exynos SoC: -- In case of Exynos3250, there are two power line as following: - VDD_MIF |--- DMC - - VDD_INT |--- LEFTBUS (parent device) - |--- PERIL - |--- MFC - |--- G3D - |--- RIGHTBUS - |--- PERIR - |--- FSYS - |--- LCD0 - |--- PERIR - |--- ISP - |--- CAM - -- In case of Exynos4210, there is one power line as following: - VDD_INT |--- DMC (parent device) - |--- LEFTBUS - |--- PERIL - |--- MFC(L) - |--- G3D - |--- TV - |--- LCD0 - |--- RIGHTBUS - |--- PERIR - |--- MFC(R) - |--- CAM - |--- FSYS - |--- GPS - |--- LCD0 - |--- LCD1 - -- In case of Exynos4x12, there are two power line as following: - VDD_MIF |--- DMC - - VDD_INT |--- LEFTBUS (parent device) - |--- PERIL - |--- MFC(L) - |--- G3D - |--- TV - |--- IMAGE - |--- RIGHTBUS - |--- PERIR - |--- MFC(R) - |--- CAM - |--- FSYS - |--- GPS - |--- LCD0 - |--- ISP - -- In case of Exynos5422, there are two power line as following: - VDD_MIF |--- DREX 0 (parent device, DRAM EXpress controller) - |--- DREX 1 - - VDD_INT |--- NoC_Core (parent device) - |--- G2D - |--- G3D - |--- DISP1 - |--- NoC_WCORE - |--- GSCL - |--- MSCL - |--- ISP - |--- MFC - |--- GEN - |--- PERIS - |--- PERIC - |--- FSYS - |--- FSYS2 - -- In case of Exynos5433, there is VDD_INT power line as following: - VDD_INT |--- G2D (parent device) - |--- MSCL - |--- GSCL - |--- JPEG - |--- MFC - |--- HEVC - |--- BUS0 - |--- BUS1 - |--- BUS2 - |--- PERIS (Fixed clock rate) - |--- PERIC (Fixed clock rate) - |--- FSYS (Fixed clock rate) - -Example 1: - Show the AXI buses of Exynos3250 SoC. Exynos3250 divides the buses to - power line (regulator). The MIF (Memory Interface) AXI bus is used to - transfer data between DRAM and CPU and uses the VDD_MIF regulator. - - - MIF (Memory Interface) block - : VDD_MIF |--- DMC (Dynamic Memory Controller) - - - INT (Internal) block - : VDD_INT |--- LEFTBUS (parent device) - |--- PERIL - |--- MFC - |--- G3D - |--- RIGHTBUS - |--- FSYS - |--- LCD0 - |--- PERIR - |--- ISP - |--- CAM - - - MIF bus's frequency/voltage table - ----------------------- - |Lv| Freq | Voltage | - ----------------------- - |L1| 50000 |800000 | - |L2| 100000 |800000 | - |L3| 134000 |800000 | - |L4| 200000 |825000 | - |L5| 400000 |875000 | - ----------------------- - - - INT bus's frequency/voltage table - ---------------------------------------------------------- - |Block|LEFTBUS|RIGHTBUS|MCUISP |ISP |PERIL ||VDD_INT | - | name| |LCD0 | | | || | - | | |FSYS | | | || | - | | |MFC | | | || | - ---------------------------------------------------------- - |Mode |*parent|passive |passive|passive|passive|| | - ---------------------------------------------------------- - |Lv |Frequency ||Voltage | - ---------------------------------------------------------- - |L1 |50000 |50000 |50000 |50000 |50000 ||900000 | - |L2 |80000 |80000 |80000 |80000 |80000 ||900000 | - |L3 |100000 |100000 |100000 |100000 |100000 ||1000000 | - |L4 |134000 |134000 |200000 |200000 | ||1000000 | - |L5 |200000 |200000 |400000 |300000 | ||1000000 | - ---------------------------------------------------------- - -Example 2: - The bus of DMC (Dynamic Memory Controller) block in exynos3250.dtsi - is listed below: - - bus_dmc: bus_dmc { - compatible = "samsung,exynos-bus"; - clocks = <&cmu_dmc CLK_DIV_DMC>; - clock-names = "bus"; - operating-points-v2 = <&bus_dmc_opp_table>; - status = "disabled"; - }; - - bus_dmc_opp_table: opp_table1 { - compatible = "operating-points-v2"; - opp-shared; - - opp-50000000 { - opp-hz = /bits/ 64 <50000000>; - opp-microvolt = <800000>; - }; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <800000>; - }; - opp-134000000 { - opp-hz = /bits/ 64 <134000000>; - opp-microvolt = <800000>; - }; - opp-200000000 { - opp-hz = /bits/ 64 <200000000>; - opp-microvolt = <825000>; - }; - opp-400000000 { - opp-hz = /bits/ 64 <400000000>; - opp-microvolt = <875000>; - }; - }; - - bus_leftbus: bus_leftbus { - compatible = "samsung,exynos-bus"; - clocks = <&cmu CLK_DIV_GDL>; - clock-names = "bus"; - operating-points-v2 = <&bus_leftbus_opp_table>; - status = "disabled"; - }; - - bus_rightbus: bus_rightbus { - compatible = "samsung,exynos-bus"; - clocks = <&cmu CLK_DIV_GDR>; - clock-names = "bus"; - operating-points-v2 = <&bus_leftbus_opp_table>; - status = "disabled"; - }; - - bus_lcd0: bus_lcd0 { - compatible = "samsung,exynos-bus"; - clocks = <&cmu CLK_DIV_ACLK_160>; - clock-names = "bus"; - operating-points-v2 = <&bus_leftbus_opp_table>; - status = "disabled"; - }; - - bus_fsys: bus_fsys { - compatible = "samsung,exynos-bus"; - clocks = <&cmu CLK_DIV_ACLK_200>; - clock-names = "bus"; - operating-points-v2 = <&bus_leftbus_opp_table>; - status = "disabled"; - }; - - bus_mcuisp: bus_mcuisp { - compatible = "samsung,exynos-bus"; - clocks = <&cmu CLK_DIV_ACLK_400_MCUISP>; - clock-names = "bus"; - operating-points-v2 = <&bus_mcuisp_opp_table>; - status = "disabled"; - }; - - bus_isp: bus_isp { - compatible = "samsung,exynos-bus"; - clocks = <&cmu CLK_DIV_ACLK_266>; - clock-names = "bus"; - operating-points-v2 = <&bus_isp_opp_table>; - status = "disabled"; - }; - - bus_peril: bus_peril { - compatible = "samsung,exynos-bus"; - clocks = <&cmu CLK_DIV_ACLK_100>; - clock-names = "bus"; - operating-points-v2 = <&bus_peril_opp_table>; - status = "disabled"; - }; - - bus_mfc: bus_mfc { - compatible = "samsung,exynos-bus"; - clocks = <&cmu CLK_SCLK_MFC>; - clock-names = "bus"; - operating-points-v2 = <&bus_leftbus_opp_table>; - status = "disabled"; - }; - - bus_leftbus_opp_table: opp_table1 { - compatible = "operating-points-v2"; - opp-shared; - - opp-50000000 { - opp-hz = /bits/ 64 <50000000>; - opp-microvolt = <900000>; - }; - opp-80000000 { - opp-hz = /bits/ 64 <80000000>; - opp-microvolt = <900000>; - }; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <1000000>; - }; - opp-134000000 { - opp-hz = /bits/ 64 <134000000>; - opp-microvolt = <1000000>; - }; - opp-200000000 { - opp-hz = /bits/ 64 <200000000>; - opp-microvolt = <1000000>; - }; - }; - - bus_mcuisp_opp_table: opp_table2 { - compatible = "operating-points-v2"; - opp-shared; - - opp-50000000 { - opp-hz = /bits/ 64 <50000000>; - }; - opp-80000000 { - opp-hz = /bits/ 64 <80000000>; - }; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - }; - opp-200000000 { - opp-hz = /bits/ 64 <200000000>; - }; - opp-400000000 { - opp-hz = /bits/ 64 <400000000>; - }; - }; - - bus_isp_opp_table: opp_table3 { - compatible = "operating-points-v2"; - opp-shared; - - opp-50000000 { - opp-hz = /bits/ 64 <50000000>; - }; - opp-80000000 { - opp-hz = /bits/ 64 <80000000>; - }; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - }; - opp-200000000 { - opp-hz = /bits/ 64 <200000000>; - }; - opp-300000000 { - opp-hz = /bits/ 64 <300000000>; - }; - }; - - bus_peril_opp_table: opp_table4 { - compatible = "operating-points-v2"; - opp-shared; - - opp-50000000 { - opp-hz = /bits/ 64 <50000000>; - }; - opp-80000000 { - opp-hz = /bits/ 64 <80000000>; - }; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - }; - }; - - - Usage case to handle the frequency and voltage of bus on runtime - in exynos3250-rinato.dts is listed below: - - &bus_dmc { - devfreq-events = <&ppmu_dmc0_3>, <&ppmu_dmc1_3>; - vdd-supply = <&buck1_reg>; /* VDD_MIF */ - status = "okay"; - }; - - &bus_leftbus { - devfreq-events = <&ppmu_leftbus_3>, <&ppmu_rightbus_3>; - vdd-supply = <&buck3_reg>; - status = "okay"; - }; - - &bus_rightbus { - devfreq = <&bus_leftbus>; - status = "okay"; - }; - - &bus_lcd0 { - devfreq = <&bus_leftbus>; - status = "okay"; - }; - - &bus_fsys { - devfreq = <&bus_leftbus>; - status = "okay"; - }; - - &bus_mcuisp { - devfreq = <&bus_leftbus>; - status = "okay"; - }; - - &bus_isp { - devfreq = <&bus_leftbus>; - status = "okay"; - }; - - &bus_peril { - devfreq = <&bus_leftbus>; - status = "okay"; - }; - - &bus_mfc { - devfreq = <&bus_leftbus>; - status = "okay"; - }; - -Example 3: - An interconnect path "bus_display -- bus_leftbus -- bus_dmc" on - Exynos4412 SoC with video mixer as an interconnect consumer device. - - soc { - bus_dmc: bus_dmc { - compatible = "samsung,exynos-bus"; - clocks = <&clock CLK_DIV_DMC>; - clock-names = "bus"; - operating-points-v2 = <&bus_dmc_opp_table>; - samsung,data-clock-ratio = <4>; - #interconnect-cells = <0>; - }; - - bus_leftbus: bus_leftbus { - compatible = "samsung,exynos-bus"; - clocks = <&clock CLK_DIV_GDL>; - clock-names = "bus"; - operating-points-v2 = <&bus_leftbus_opp_table>; - #interconnect-cells = <0>; - interconnects = <&bus_dmc>; - }; - - bus_display: bus_display { - compatible = "samsung,exynos-bus"; - clocks = <&clock CLK_ACLK160>; - clock-names = "bus"; - operating-points-v2 = <&bus_display_opp_table>; - #interconnect-cells = <0>; - interconnects = <&bus_leftbus &bus_dmc>; - }; - - bus_dmc_opp_table: opp_table1 { - compatible = "operating-points-v2"; - /* ... */ - } - - bus_leftbus_opp_table: opp_table3 { - compatible = "operating-points-v2"; - /* ... */ - }; - - bus_display_opp_table: opp_table4 { - compatible = "operating-points-v2"; - /* .. */ - }; - - &mixer { - compatible = "samsung,exynos4212-mixer"; - interconnects = <&bus_display &bus_dmc>; - /* ... */ - }; - }; diff --git a/Documentation/devicetree/bindings/interconnect/samsung,exynos-bus.yaml b/Documentation/devicetree/bindings/interconnect/samsung,exynos-bus.yaml new file mode 100644 index 000000000000..ad9ed596dfef --- /dev/null +++ b/Documentation/devicetree/bindings/interconnect/samsung,exynos-bus.yaml @@ -0,0 +1,290 @@ +# SPDX-License-Identifier: GPL-2.0 +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/interconnect/samsung,exynos-bus.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Samsung Exynos SoC Bus and Interconnect + +maintainers: + - Chanwoo Choi + - Krzysztof Kozlowski + +description: | + The Samsung Exynos SoC has many buses for data transfer between DRAM and + sub-blocks in SoC. Most Exynos SoCs share the common architecture for buses. + Generally, each bus of Exynos SoC includes a source clock and a power line, + which are able to change the clock frequency of the bus in runtime. To + monitor the usage of each bus in runtime, the driver uses the PPMU (Platform + Performance Monitoring Unit), which is able to measure the current load of + sub-blocks. + + The Exynos SoC includes the various sub-blocks which have the each AXI bus. + The each AXI bus has the owned source clock but, has not the only owned power + line. The power line might be shared among one more sub-blocks. So, we can + divide into two type of device as the role of each sub-block. There are two + type of bus devices as following:: + - parent bus device + - passive bus device + + Basically, parent and passive bus device share the same power line. The + parent bus device can only change the voltage of shared power line and the + rest bus devices (passive bus device) depend on the decision of the parent + bus device. If there are three blocks which share the VDD_xxx power line, + Only one block should be parent device and then the rest blocks should depend + on the parent device as passive device. + + VDD_xxx |--- A block (parent) + |--- B block (passive) + |--- C block (passive) + + There are a little different composition among Exynos SoC because each Exynos + SoC has different sub-blocks. Therefore, such difference should be specified + in devicetree file instead of each device driver. In result, this driver is + able to support the bus frequency for all Exynos SoCs. + + Detailed correlation between sub-blocks and power line according + to Exynos SoC:: + - In case of Exynos3250, there are two power line as following:: + VDD_MIF |--- DMC (Dynamic Memory Controller) + + VDD_INT |--- LEFTBUS (parent device) + |--- PERIL + |--- MFC + |--- G3D + |--- RIGHTBUS + |--- PERIR + |--- FSYS + |--- LCD0 + |--- PERIR + |--- ISP + |--- CAM + + - MIF bus's frequency/voltage table + ----------------------- + |Lv| Freq | Voltage | + ----------------------- + |L1| 50000 |800000 | + |L2| 100000 |800000 | + |L3| 134000 |800000 | + |L4| 200000 |825000 | + |L5| 400000 |875000 | + ----------------------- + + - INT bus's frequency/voltage table + ---------------------------------------------------------- + |Block|LEFTBUS|RIGHTBUS|MCUISP |ISP |PERIL ||VDD_INT | + | name| |LCD0 | | | || | + | | |FSYS | | | || | + | | |MFC | | | || | + ---------------------------------------------------------- + |Mode |*parent|passive |passive|passive|passive|| | + ---------------------------------------------------------- + |Lv |Frequency ||Voltage | + ---------------------------------------------------------- + |L1 |50000 |50000 |50000 |50000 |50000 ||900000 | + |L2 |80000 |80000 |80000 |80000 |80000 ||900000 | + |L3 |100000 |100000 |100000 |100000 |100000 ||1000000 | + |L4 |134000 |134000 |200000 |200000 | ||1000000 | + |L5 |200000 |200000 |400000 |300000 | ||1000000 | + ---------------------------------------------------------- + + - In case of Exynos4210, there is one power line as following:: + VDD_INT |--- DMC (parent device, Dynamic Memory Controller) + |--- LEFTBUS + |--- PERIL + |--- MFC(L) + |--- G3D + |--- TV + |--- LCD0 + |--- RIGHTBUS + |--- PERIR + |--- MFC(R) + |--- CAM + |--- FSYS + |--- GPS + |--- LCD0 + |--- LCD1 + + - In case of Exynos4x12, there are two power line as following:: + VDD_MIF |--- DMC (Dynamic Memory Controller) + + VDD_INT |--- LEFTBUS (parent device) + |--- PERIL + |--- MFC(L) + |--- G3D + |--- TV + |--- IMAGE + |--- RIGHTBUS + |--- PERIR + |--- MFC(R) + |--- CAM + |--- FSYS + |--- GPS + |--- LCD0 + |--- ISP + + - In case of Exynos5422, there are two power line as following:: + VDD_MIF |--- DREX 0 (parent device, DRAM EXpress controller) + |--- DREX 1 + + VDD_INT |--- NoC_Core (parent device) + |--- G2D + |--- G3D + |--- DISP1 + |--- NoC_WCORE + |--- GSCL + |--- MSCL + |--- ISP + |--- MFC + |--- GEN + |--- PERIS + |--- PERIC + |--- FSYS + |--- FSYS2 + + - In case of Exynos5433, there is VDD_INT power line as following:: + VDD_INT |--- G2D (parent device) + |--- MSCL + |--- GSCL + |--- JPEG + |--- MFC + |--- HEVC + |--- BUS0 + |--- BUS1 + |--- BUS2 + |--- PERIS (Fixed clock rate) + |--- PERIC (Fixed clock rate) + |--- FSYS (Fixed clock rate) + +properties: + compatible: + enum: + - samsung,exynos-bus + + clocks: + maxItems: 1 + + clock-names: + items: + - const: bus + + devfreq: + $ref: /schemas/types.yaml#/definitions/phandle + description: + Parent bus device. Valid and required only for the passive bus devices. + + devfreq-events: + $ref: /schemas/types.yaml#/definitions/phandle-array + minItems: 1 + maxItems: 4 + description: + Devfreq-event device to monitor the current utilization of buses. Valid + and required only for the parent bus devices. + + exynos,saturation-ratio: + $ref: /schemas/types.yaml#/definitions/uint32 + description: + Percentage value which is used to calibrate the performance count against + total cycle count. Valid only for the parent bus devices. + + '#interconnect-cells': + const: 0 + + interconnects: + minItems: 1 + maxItems: 2 + + operating-points-v2: true + + samsung,data-clock-ratio: + $ref: /schemas/types.yaml#/definitions/uint32 + default: 8 + description: + Ratio of the data throughput in B/s to minimum data clock frequency in + Hz. + + vdd-supply: + description: + Main bus power rail. Valid and required only for the parent bus devices. + +required: + - compatible + - clocks + - clock-names + - operating-points-v2 + +additionalProperties: false + +examples: + - | + #include + + bus-dmc { + compatible = "samsung,exynos-bus"; + clocks = <&cmu_dmc CLK_DIV_DMC>; + clock-names = "bus"; + operating-points-v2 = <&bus_dmc_opp_table>; + devfreq-events = <&ppmu_dmc0_3>, <&ppmu_dmc1_3>; + vdd-supply = <&buck1_reg>; + }; + + ppmu_dmc0: ppmu@106a0000 { + compatible = "samsung,exynos-ppmu"; + reg = <0x106a0000 0x2000>; + events { + ppmu_dmc0_3: ppmu-event3-dmc0 { + event-name = "ppmu-event3-dmc0"; + }; + }; + }; + + bus_leftbus: bus-leftbus { + compatible = "samsung,exynos-bus"; + clocks = <&cmu CLK_DIV_GDL>; + clock-names = "bus"; + operating-points-v2 = <&bus_leftbus_opp_table>; + devfreq-events = <&ppmu_leftbus_3>, <&ppmu_rightbus_3>; + vdd-supply = <&buck3_reg>; + }; + + bus-rightbus { + compatible = "samsung,exynos-bus"; + clocks = <&cmu CLK_DIV_GDR>; + clock-names = "bus"; + operating-points-v2 = <&bus_leftbus_opp_table>; + devfreq = <&bus_leftbus>; + }; + + - | + dmc: bus-dmc { + compatible = "samsung,exynos-bus"; + clocks = <&clock CLK_DIV_DMC>; + clock-names = "bus"; + operating-points-v2 = <&bus_dmc_opp_table>; + samsung,data-clock-ratio = <4>; + #interconnect-cells = <0>; + devfreq-events = <&ppmu_dmc0_3>, <&ppmu_dmc1_3>; + vdd-supply = <&buck1_reg>; + }; + + leftbus: bus-leftbus { + compatible = "samsung,exynos-bus"; + clocks = <&clock CLK_DIV_GDL>; + clock-names = "bus"; + operating-points-v2 = <&bus_leftbus_opp_table>; + interconnects = <&dmc>; + #interconnect-cells = <0>; + devfreq-events = <&ppmu_leftbus_3>, <&ppmu_rightbus_3>; + vdd-supply = <&buck3_reg>; + }; + + display: bus-display { + compatible = "samsung,exynos-bus"; + clocks = <&clock CLK_DIV_ACLK_266>; + clock-names = "bus"; + operating-points-v2 = <&bus_display_opp_table>; + interconnects = <&leftbus &dmc>; + #interconnect-cells = <0>; + devfreq = <&leftbus>; + }; diff --git a/MAINTAINERS b/MAINTAINERS index 29790c536587..900082568cfa 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4374,7 +4374,7 @@ L: linux-pm@vger.kernel.org L: linux-samsung-soc@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/linux.git -F: Documentation/devicetree/bindings/devfreq/exynos-bus.txt +F: Documentation/devicetree/bindings/interconnect/samsung,exynos-bus.yaml F: drivers/devfreq/exynos-bus.c BUSLOGIC SCSI DRIVER From c9deb748683851737c5e4df623c3283c185cd8f0 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 28 Jun 2022 10:46:12 +0100 Subject: [PATCH 13/27] PM / devfreq: shut up kernel-doc warnings There are 4 warnings there: drivers/devfreq/devfreq.c:707: warning: Function parameter or member 'val' not described in 'qos_min_notifier_call' drivers/devfreq/devfreq.c:707: warning: Function parameter or member 'ptr' not described in 'qos_min_notifier_call' drivers/devfreq/devfreq.c:717: warning: Function parameter or member 'val' not described in 'qos_max_notifier_call' drivers/devfreq/devfreq.c:717: warning: Function parameter or member 'ptr' not described in 'qos_max_notifier_call' It turns that neither val nor ptr are actually used on those function, so document as such. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Chanwoo Choi --- drivers/devfreq/devfreq.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 9602141bb8ec..63347a5ae599 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -696,6 +696,8 @@ static int qos_notifier_call(struct devfreq *devfreq) /** * qos_min_notifier_call() - Callback for QoS min_freq changes. * @nb: Should be devfreq->nb_min + * @val: not used + * @ptr: not used */ static int qos_min_notifier_call(struct notifier_block *nb, unsigned long val, void *ptr) @@ -706,6 +708,8 @@ static int qos_min_notifier_call(struct notifier_block *nb, /** * qos_max_notifier_call() - Callback for QoS max_freq changes. * @nb: Should be devfreq->nb_max + * @val: not used + * @ptr: not used */ static int qos_max_notifier_call(struct notifier_block *nb, unsigned long val, void *ptr) From 2472934e36b51bbdf0a7cdd5e351910d9002c6ac Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 23 Jun 2022 19:00:54 +0100 Subject: [PATCH 14/27] PM / devfreq: imx-bus: use NULL to pass a null pointer rather than zero The 3rd argument to the function of_get_property is a pointer and it is being passed using 0. Use NULL instead. Cleans up sparse warning: warning: Using plain integer as NULL pointer Signed-off-by: Colin Ian King Signed-off-by: Chanwoo Choi --- drivers/devfreq/imx-bus.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/devfreq/imx-bus.c b/drivers/devfreq/imx-bus.c index f3f6e25053ed..f87067fc574d 100644 --- a/drivers/devfreq/imx-bus.c +++ b/drivers/devfreq/imx-bus.c @@ -59,7 +59,7 @@ static int imx_bus_init_icc(struct device *dev) struct imx_bus *priv = dev_get_drvdata(dev); const char *icc_driver_name; - if (!of_get_property(dev->of_node, "#interconnect-cells", 0)) + if (!of_get_property(dev->of_node, "#interconnect-cells", NULL)) return 0; if (!IS_ENABLED(CONFIG_INTERCONNECT_IMX)) { dev_warn(dev, "imx interconnect drivers disabled\n"); From 53f853d55e312a639eaa910154248ce06eb754ac Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Thu, 30 Jun 2022 10:57:51 +0300 Subject: [PATCH 15/27] PM / devfreq: tegra30: Add error message for devm_devfreq_add_device() It's difficult to notice that driver failed to probe by looking at KMSG when devm_devfreq_add_device() fails. Add explicit error message for this case. Signed-off-by: Dmitry Osipenko Signed-off-by: Chanwoo Choi --- drivers/devfreq/tegra30-devfreq.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/devfreq/tegra30-devfreq.c b/drivers/devfreq/tegra30-devfreq.c index 65ecf17a36f4..585a95fe2bd6 100644 --- a/drivers/devfreq/tegra30-devfreq.c +++ b/drivers/devfreq/tegra30-devfreq.c @@ -922,8 +922,10 @@ static int tegra_devfreq_probe(struct platform_device *pdev) devfreq = devm_devfreq_add_device(&pdev->dev, &tegra_devfreq_profile, "tegra_actmon", NULL); - if (IS_ERR(devfreq)) + if (IS_ERR(devfreq)) { + dev_err(&pdev->dev, "Failed to add device: %pe\n", devfreq); return PTR_ERR(devfreq); + } return 0; } From ae6ccaa650380d243cf43d31c864c5ced2fd4612 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 7 Jul 2022 08:15:52 +0100 Subject: [PATCH 16/27] PM: EM: convert power field to micro-Watts precision and align drivers The milli-Watts precision causes rounding errors while calculating efficiency cost for each OPP. This is especially visible in the 'simple' Energy Model (EM), where the power for each OPP is provided from OPP framework. This can cause some OPPs to be marked inefficient, while using micro-Watts precision that might not happen. Update all EM users which access 'power' field and assume the value is in milli-Watts. Solve also an issue with potential overflow in calculation of energy estimation on 32bit machine. It's needed now since the power value (thus the 'cost' as well) are higher. Example calculation which shows the rounding error and impact: power = 'dyn-power-coeff' * volt_mV * volt_mV * freq_MHz power_a_uW = (100 * 600mW * 600mW * 500MHz) / 10^6 = 18000 power_a_mW = (100 * 600mW * 600mW * 500MHz) / 10^9 = 18 power_b_uW = (100 * 605mW * 605mW * 600MHz) / 10^6 = 21961 power_b_mW = (100 * 605mW * 605mW * 600MHz) / 10^9 = 21 max_freq = 2000MHz cost_a_mW = 18 * 2000MHz/500MHz = 72 cost_a_uW = 18000 * 2000MHz/500MHz = 72000 cost_b_mW = 21 * 2000MHz/600MHz = 70 // <- artificially better cost_b_uW = 21961 * 2000MHz/600MHz = 73203 The 'cost_b_mW' (which is based on old milli-Watts) is misleadingly better that the 'cost_b_uW' (this patch uses micro-Watts) and such would have impact on the 'inefficient OPPs' information in the Cpufreq framework. This patch set removes the rounding issue. Signed-off-by: Lukasz Luba Acked-by: Daniel Lezcano Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/mediatek-cpufreq-hw.c | 7 ++-- drivers/cpufreq/scmi-cpufreq.c | 6 +++ drivers/opp/of.c | 15 +++---- drivers/powercap/dtpm_cpu.c | 5 +-- drivers/thermal/cpufreq_cooling.c | 13 ++++++- drivers/thermal/devfreq_cooling.c | 19 +++++++-- include/linux/energy_model.h | 56 +++++++++++++++++++-------- kernel/power/energy_model.c | 24 ++++++++---- 8 files changed, 101 insertions(+), 44 deletions(-) diff --git a/drivers/cpufreq/mediatek-cpufreq-hw.c b/drivers/cpufreq/mediatek-cpufreq-hw.c index 813cccbfe934..f0e0a35c7f21 100644 --- a/drivers/cpufreq/mediatek-cpufreq-hw.c +++ b/drivers/cpufreq/mediatek-cpufreq-hw.c @@ -51,7 +51,7 @@ static const u16 cpufreq_mtk_offsets[REG_ARRAY_SIZE] = { }; static int __maybe_unused -mtk_cpufreq_get_cpu_power(struct device *cpu_dev, unsigned long *mW, +mtk_cpufreq_get_cpu_power(struct device *cpu_dev, unsigned long *uW, unsigned long *KHz) { struct mtk_cpufreq_data *data; @@ -71,8 +71,9 @@ mtk_cpufreq_get_cpu_power(struct device *cpu_dev, unsigned long *mW, i--; *KHz = data->table[i].frequency; - *mW = readl_relaxed(data->reg_bases[REG_EM_POWER_TBL] + - i * LUT_ROW_SIZE) / 1000; + /* Provide micro-Watts value to the Energy Model */ + *uW = readl_relaxed(data->reg_bases[REG_EM_POWER_TBL] + + i * LUT_ROW_SIZE); return 0; } diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index 6d2a4cf46db7..bfd35583d653 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -19,6 +19,7 @@ #include #include #include +#include struct scmi_data { int domain_id; @@ -99,6 +100,7 @@ static int __maybe_unused scmi_get_cpu_power(struct device *cpu_dev, unsigned long *power, unsigned long *KHz) { + bool power_scale_mw = perf_ops->power_scale_mw_get(ph); unsigned long Hz; int ret, domain; @@ -112,6 +114,10 @@ scmi_get_cpu_power(struct device *cpu_dev, unsigned long *power, if (ret) return ret; + /* Provide bigger resolution power to the Energy Model */ + if (power_scale_mw) + *power *= MICROWATT_PER_MILLIWATT; + /* The EM framework specifies the frequency in KHz. */ *KHz = Hz / 1000; diff --git a/drivers/opp/of.c b/drivers/opp/of.c index 30394929d700..eb89c9a75985 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -1443,12 +1443,12 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_of_node); * It provides the power used by @dev at @kHz if it is the frequency of an * existing OPP, or at the frequency of the first OPP above @kHz otherwise * (see dev_pm_opp_find_freq_ceil()). This function updates @kHz to the ceiled - * frequency and @mW to the associated power. + * frequency and @uW to the associated power. * * Returns 0 on success or a proper -EINVAL value in case of error. */ static int __maybe_unused -_get_dt_power(struct device *dev, unsigned long *mW, unsigned long *kHz) +_get_dt_power(struct device *dev, unsigned long *uW, unsigned long *kHz) { struct dev_pm_opp *opp; unsigned long opp_freq, opp_power; @@ -1465,7 +1465,7 @@ _get_dt_power(struct device *dev, unsigned long *mW, unsigned long *kHz) return -EINVAL; *kHz = opp_freq / 1000; - *mW = opp_power / 1000; + *uW = opp_power; return 0; } @@ -1475,14 +1475,14 @@ _get_dt_power(struct device *dev, unsigned long *mW, unsigned long *kHz) * This computes the power estimated by @dev at @kHz if it is the frequency * of an existing OPP, or at the frequency of the first OPP above @kHz otherwise * (see dev_pm_opp_find_freq_ceil()). This function updates @kHz to the ceiled - * frequency and @mW to the associated power. The power is estimated as + * frequency and @uW to the associated power. The power is estimated as * P = C * V^2 * f with C being the device's capacitance and V and f * respectively the voltage and frequency of the OPP. * * Returns -EINVAL if the power calculation failed because of missing * parameters, 0 otherwise. */ -static int __maybe_unused _get_power(struct device *dev, unsigned long *mW, +static int __maybe_unused _get_power(struct device *dev, unsigned long *uW, unsigned long *kHz) { struct dev_pm_opp *opp; @@ -1512,9 +1512,10 @@ static int __maybe_unused _get_power(struct device *dev, unsigned long *mW, return -EINVAL; tmp = (u64)cap * mV * mV * (Hz / 1000000); - do_div(tmp, 1000000000); + /* Provide power in micro-Watts */ + do_div(tmp, 1000000); - *mW = (unsigned long)tmp; + *uW = (unsigned long)tmp; *kHz = Hz / 1000; return 0; diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c index f5eced0842b3..61c5ff80bd30 100644 --- a/drivers/powercap/dtpm_cpu.c +++ b/drivers/powercap/dtpm_cpu.c @@ -53,7 +53,7 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit) for (i = 0; i < pd->nr_perf_states; i++) { - power = pd->table[i].power * MICROWATT_PER_MILLIWATT * nr_cpus; + power = pd->table[i].power * nr_cpus; if (power > power_limit) break; @@ -63,8 +63,7 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit) freq_qos_update_request(&dtpm_cpu->qos_req, freq); - power_limit = pd->table[i - 1].power * - MICROWATT_PER_MILLIWATT * nr_cpus; + power_limit = pd->table[i - 1].power * nr_cpus; return power_limit; } diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c index b8151d95a806..dc19e7c80751 100644 --- a/drivers/thermal/cpufreq_cooling.c +++ b/drivers/thermal/cpufreq_cooling.c @@ -21,6 +21,7 @@ #include #include #include +#include #include @@ -101,6 +102,7 @@ static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_cdev, static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_cdev, u32 freq) { + unsigned long power_mw; int i; for (i = cpufreq_cdev->max_level - 1; i >= 0; i--) { @@ -108,16 +110,23 @@ static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_cdev, break; } - return cpufreq_cdev->em->table[i + 1].power; + power_mw = cpufreq_cdev->em->table[i + 1].power; + power_mw /= MICROWATT_PER_MILLIWATT; + + return power_mw; } static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_cdev, u32 power) { + unsigned long em_power_mw; int i; for (i = cpufreq_cdev->max_level; i > 0; i--) { - if (power >= cpufreq_cdev->em->table[i].power) + /* Convert EM power to milli-Watts to make safe comparison */ + em_power_mw = cpufreq_cdev->em->table[i].power; + em_power_mw /= MICROWATT_PER_MILLIWATT; + if (power >= em_power_mw) break; } diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c index 8c76f9655e57..8d1260f65061 100644 --- a/drivers/thermal/devfreq_cooling.c +++ b/drivers/thermal/devfreq_cooling.c @@ -200,7 +200,11 @@ static int devfreq_cooling_get_requested_power(struct thermal_cooling_device *cd res = dfc->power_ops->get_real_power(df, power, freq, voltage); if (!res) { state = dfc->capped_state; + + /* Convert EM power into milli-Watts first */ dfc->res_util = dfc->em_pd->table[state].power; + dfc->res_util /= MICROWATT_PER_MILLIWATT; + dfc->res_util *= SCALE_ERROR_MITIGATION; if (*power > 1) @@ -218,8 +222,10 @@ static int devfreq_cooling_get_requested_power(struct thermal_cooling_device *cd _normalize_load(&status); - /* Scale power for utilization */ + /* Convert EM power into milli-Watts first */ *power = dfc->em_pd->table[perf_idx].power; + *power /= MICROWATT_PER_MILLIWATT; + /* Scale power for utilization */ *power *= status.busy_time; *power >>= 10; } @@ -244,6 +250,7 @@ static int devfreq_cooling_state2power(struct thermal_cooling_device *cdev, perf_idx = dfc->max_state - state; *power = dfc->em_pd->table[perf_idx].power; + *power /= MICROWATT_PER_MILLIWATT; return 0; } @@ -254,7 +261,7 @@ static int devfreq_cooling_power2state(struct thermal_cooling_device *cdev, struct devfreq_cooling_device *dfc = cdev->devdata; struct devfreq *df = dfc->devfreq; struct devfreq_dev_status status; - unsigned long freq; + unsigned long freq, em_power_mw; s32 est_power; int i; @@ -279,9 +286,13 @@ static int devfreq_cooling_power2state(struct thermal_cooling_device *cdev, * Find the first cooling state that is within the power * budget. The EM power table is sorted ascending. */ - for (i = dfc->max_state; i > 0; i--) - if (est_power >= dfc->em_pd->table[i].power) + for (i = dfc->max_state; i > 0; i--) { + /* Convert EM power to milli-Watts to make safe comparison */ + em_power_mw = dfc->em_pd->table[i].power; + em_power_mw /= MICROWATT_PER_MILLIWATT; + if (est_power >= em_power_mw) break; + } *state = dfc->max_state - i; dfc->capped_state = *state; diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 8419bffb4398..b9caa01dfac4 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -62,7 +62,7 @@ struct em_perf_domain { /* * em_perf_domain flags: * - * EM_PERF_DOMAIN_MILLIWATTS: The power values are in milli-Watts or some + * EM_PERF_DOMAIN_MICROWATTS: The power values are in micro-Watts or some * other scale. * * EM_PERF_DOMAIN_SKIP_INEFFICIENCIES: Skip inefficient states when estimating @@ -71,7 +71,7 @@ struct em_perf_domain { * EM_PERF_DOMAIN_ARTIFICIAL: The power values are artificial and might be * created by platform missing real power information */ -#define EM_PERF_DOMAIN_MILLIWATTS BIT(0) +#define EM_PERF_DOMAIN_MICROWATTS BIT(0) #define EM_PERF_DOMAIN_SKIP_INEFFICIENCIES BIT(1) #define EM_PERF_DOMAIN_ARTIFICIAL BIT(2) @@ -79,22 +79,44 @@ struct em_perf_domain { #define em_is_artificial(em) ((em)->flags & EM_PERF_DOMAIN_ARTIFICIAL) #ifdef CONFIG_ENERGY_MODEL -#define EM_MAX_POWER 0xFFFF +/* + * The max power value in micro-Watts. The limit of 64 Watts is set as + * a safety net to not overflow multiplications on 32bit platforms. The + * 32bit value limit for total Perf Domain power implies a limit of + * maximum CPUs in such domain to 64. + */ +#define EM_MAX_POWER (64000000) /* 64 Watts */ /* - * Increase resolution of energy estimation calculations for 64-bit - * architectures. The extra resolution improves decision made by EAS for the - * task placement when two Performance Domains might provide similar energy - * estimation values (w/o better resolution the values could be equal). - * - * We increase resolution only if we have enough bits to allow this increased - * resolution (i.e. 64-bit). The costs for increasing resolution when 32-bit - * are pretty high and the returns do not justify the increased costs. + * To avoid possible energy estimation overflow on 32bit machines add + * limits to number of CPUs in the Perf. Domain. + * We are safe on 64bit machine, thus some big number. */ #ifdef CONFIG_64BIT -#define em_scale_power(p) ((p) * 1000) +#define EM_MAX_NUM_CPUS 4096 #else -#define em_scale_power(p) (p) +#define EM_MAX_NUM_CPUS 16 +#endif + +/* + * To avoid an overflow on 32bit machines while calculating the energy + * use a different order in the operation. First divide by the 'cpu_scale' + * which would reduce big value stored in the 'cost' field, then multiply by + * the 'sum_util'. This would allow to handle existing platforms, which have + * e.g. power ~1.3 Watt at max freq, so the 'cost' value > 1mln micro-Watts. + * In such scenario, where there are 4 CPUs in the Perf. Domain the 'sum_util' + * could be 4096, then multiplication: 'cost' * 'sum_util' would overflow. + * This reordering of operations has some limitations, we lose small + * precision in the estimation (comparing to 64bit platform w/o reordering). + * + * We are safe on 64bit machine. + */ +#ifdef CONFIG_64BIT +#define em_estimate_energy(cost, sum_util, scale_cpu) \ + (((cost) * (sum_util)) / (scale_cpu)) +#else +#define em_estimate_energy(cost, sum_util, scale_cpu) \ + (((cost) / (scale_cpu)) * (sum_util)) #endif struct em_data_callback { @@ -112,7 +134,7 @@ struct em_data_callback { * and frequency. * * In case of CPUs, the power is the one of a single CPU in the domain, - * expressed in milli-Watts or an abstract scale. It is expected to + * expressed in micro-Watts or an abstract scale. It is expected to * fit in the [0, EM_MAX_POWER] range. * * Return 0 on success. @@ -148,7 +170,7 @@ struct em_perf_domain *em_cpu_get(int cpu); struct em_perf_domain *em_pd_get(struct device *dev); int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, struct em_data_callback *cb, cpumask_t *span, - bool milliwatts); + bool microwatts); void em_dev_unregister_perf_domain(struct device *dev); /** @@ -273,7 +295,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, * pd_nrg = ------------------------ (4) * scale_cpu */ - return ps->cost * sum_util / scale_cpu; + return em_estimate_energy(ps->cost, sum_util, scale_cpu); } /** @@ -297,7 +319,7 @@ struct em_data_callback {}; static inline int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, struct em_data_callback *cb, cpumask_t *span, - bool milliwatts) + bool microwatts) { return -EINVAL; } diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 6c373f2960e7..f82111837b8d 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -145,7 +145,7 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, /* * The power returned by active_state() is expected to be - * positive and to fit into 16 bits. + * positive and be in range. */ if (!power || power > EM_MAX_POWER) { dev_err(dev, "EM: invalid power: %lu\n", @@ -170,7 +170,7 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, goto free_ps_table; } } else { - power_res = em_scale_power(table[i].power); + power_res = table[i].power; cost = div64_u64(fmax * power_res, table[i].frequency); } @@ -201,9 +201,17 @@ static int em_create_pd(struct device *dev, int nr_states, { struct em_perf_domain *pd; struct device *cpu_dev; - int cpu, ret; + int cpu, ret, num_cpus; if (_is_cpu_device(dev)) { + num_cpus = cpumask_weight(cpus); + + /* Prevent max possible energy calculation to not overflow */ + if (num_cpus > EM_MAX_NUM_CPUS) { + dev_err(dev, "EM: too many CPUs, overflow possible\n"); + return -EINVAL; + } + pd = kzalloc(sizeof(*pd) + cpumask_size(), GFP_KERNEL); if (!pd) return -ENOMEM; @@ -314,13 +322,13 @@ EXPORT_SYMBOL_GPL(em_cpu_get); * @cpus : Pointer to cpumask_t, which in case of a CPU device is * obligatory. It can be taken from i.e. 'policy->cpus'. For other * type of devices this should be set to NULL. - * @milliwatts : Flag indicating that the power values are in milliWatts or + * @microwatts : Flag indicating that the power values are in micro-Watts or * in some other scale. It must be set properly. * * Create Energy Model tables for a performance domain using the callbacks * defined in cb. * - * The @milliwatts is important to set with correct value. Some kernel + * The @microwatts is important to set with correct value. Some kernel * sub-systems might rely on this flag and check if all devices in the EM are * using the same scale. * @@ -331,7 +339,7 @@ EXPORT_SYMBOL_GPL(em_cpu_get); */ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, struct em_data_callback *cb, cpumask_t *cpus, - bool milliwatts) + bool microwatts) { unsigned long cap, prev_cap = 0; unsigned long flags = 0; @@ -381,8 +389,8 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, } } - if (milliwatts) - flags |= EM_PERF_DOMAIN_MILLIWATTS; + if (microwatts) + flags |= EM_PERF_DOMAIN_MICROWATTS; else if (cb->get_cost) flags |= EM_PERF_DOMAIN_ARTIFICIAL; From c5d39fae8992cfca6d57e09dadf7aaaf7e64224f Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 7 Jul 2022 08:15:53 +0100 Subject: [PATCH 17/27] Documentation: EM: Switch to micro-Watts scale The EM now uses the micro-Watts scale for the power values. Update related documentation to reflect that fact. Fix also a problematic sentence in the doc "to:" which triggers test scripts complaining about wrong email address. Reviewed-by: Daniel Lezcano Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- Documentation/power/energy-model.rst | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/Documentation/power/energy-model.rst b/Documentation/power/energy-model.rst index feb257b7f350..ef341be2882b 100644 --- a/Documentation/power/energy-model.rst +++ b/Documentation/power/energy-model.rst @@ -20,20 +20,20 @@ possible source of information on its own, the EM framework intervenes as an abstraction layer which standardizes the format of power cost tables in the kernel, hence enabling to avoid redundant work. -The power values might be expressed in milli-Watts or in an 'abstract scale'. +The power values might be expressed in micro-Watts or in an 'abstract scale'. Multiple subsystems might use the EM and it is up to the system integrator to check that the requirements for the power value scale types are met. An example can be found in the Energy-Aware Scheduler documentation Documentation/scheduler/sched-energy.rst. For some subsystems like thermal or powercap power values expressed in an 'abstract scale' might cause issues. These subsystems are more interested in estimation of power used in the past, -thus the real milli-Watts might be needed. An example of these requirements can +thus the real micro-Watts might be needed. An example of these requirements can be found in the Intelligent Power Allocation in Documentation/driver-api/thermal/power_allocator.rst. Kernel subsystems might implement automatic detection to check whether EM registered devices have inconsistent scale (based on EM internal flag). Important thing to keep in mind is that when the power values are expressed in -an 'abstract scale' deriving real energy in milli-Joules would not be possible. +an 'abstract scale' deriving real energy in micro-Joules would not be possible. The figure below depicts an example of drivers (Arm-specific here, but the approach is applicable to any architecture) providing power costs to the EM @@ -98,7 +98,7 @@ Drivers are expected to register performance domains into the EM framework by calling the following API:: int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, - struct em_data_callback *cb, cpumask_t *cpus, bool milliwatts); + struct em_data_callback *cb, cpumask_t *cpus, bool microwatts); Drivers must provide a callback function returning tuples for each performance state. The callback function provided by the driver is free @@ -106,10 +106,10 @@ to fetch data from any relevant location (DT, firmware, ...), and by any mean deemed necessary. Only for CPU devices, drivers must specify the CPUs of the performance domains using cpumask. For other devices than CPUs the last argument must be set to NULL. -The last argument 'milliwatts' is important to set with correct value. Kernel +The last argument 'microwatts' is important to set with correct value. Kernel subsystems which use EM might rely on this flag to check if all EM devices use the same scale. If there are different scales, these subsystems might decide -to: return warning/error, stop working or panic. +to return warning/error, stop working or panic. See Section 3. for an example of driver implementing this callback, or Section 2.4 for further documentation on this API @@ -137,7 +137,7 @@ The .get_cost() allows to provide the 'cost' values which reflect the efficiency of the CPUs. This would allow to provide EAS information which has different relation than what would be forced by the EM internal formulas calculating 'cost' values. To register an EM for such platform, the -driver must set the flag 'milliwatts' to 0, provide .get_power() callback +driver must set the flag 'microwatts' to 0, provide .get_power() callback and provide .get_cost() callback. The EM framework would handle such platform properly during registration. A flag EM_PERF_DOMAIN_ARTIFICIAL is set for such platform. Special care should be taken by other frameworks which are using EM From 5e0fd2026cdd474a85b3135c312912321e60f47a Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 7 Jul 2022 08:15:54 +0100 Subject: [PATCH 18/27] firmware: arm_scmi: Get detailed power scale from perf In SCMI v3.1 the power scale can be in micro-Watts. The upper layers, e.g. cpufreq and EM should handle received power values properly (upscale when needed). Thus, provide an interface which allows to check what is the scale for power values. The old interface allowed to distinguish between bogo-Watts and milli-Watts only (which was good for older SCMI spec). Acked-by: Sudeep Holla Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- drivers/firmware/arm_scmi/perf.c | 18 +++++++++++------- include/linux/scmi_protocol.h | 8 +++++++- 2 files changed, 18 insertions(+), 8 deletions(-) diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c index bbb0331801ff..92414e53f908 100644 --- a/drivers/firmware/arm_scmi/perf.c +++ b/drivers/firmware/arm_scmi/perf.c @@ -170,8 +170,7 @@ struct perf_dom_info { struct scmi_perf_info { u32 version; int num_domains; - bool power_scale_mw; - bool power_scale_uw; + enum scmi_power_scale power_scale; u64 stats_addr; u32 stats_size; struct perf_dom_info *dom_info; @@ -201,9 +200,13 @@ static int scmi_perf_attributes_get(const struct scmi_protocol_handle *ph, u16 flags = le16_to_cpu(attr->flags); pi->num_domains = le16_to_cpu(attr->num_domains); - pi->power_scale_mw = POWER_SCALE_IN_MILLIWATT(flags); + + if (POWER_SCALE_IN_MILLIWATT(flags)) + pi->power_scale = SCMI_POWER_MILLIWATTS; if (PROTOCOL_REV_MAJOR(pi->version) >= 0x3) - pi->power_scale_uw = POWER_SCALE_IN_MICROWATT(flags); + if (POWER_SCALE_IN_MICROWATT(flags)) + pi->power_scale = SCMI_POWER_MICROWATTS; + pi->stats_addr = le32_to_cpu(attr->stats_addr_low) | (u64)le32_to_cpu(attr->stats_addr_high) << 32; pi->stats_size = le32_to_cpu(attr->stats_size); @@ -792,11 +795,12 @@ static bool scmi_fast_switch_possible(const struct scmi_protocol_handle *ph, return dom->fc_info && dom->fc_info->level_set_addr; } -static bool scmi_power_scale_mw_get(const struct scmi_protocol_handle *ph) +static enum scmi_power_scale +scmi_power_scale_get(const struct scmi_protocol_handle *ph) { struct scmi_perf_info *pi = ph->get_priv(ph); - return pi->power_scale_mw; + return pi->power_scale; } static const struct scmi_perf_proto_ops perf_proto_ops = { @@ -811,7 +815,7 @@ static const struct scmi_perf_proto_ops perf_proto_ops = { .freq_get = scmi_dvfs_freq_get, .est_power_get = scmi_dvfs_est_power_get, .fast_switch_possible = scmi_fast_switch_possible, - .power_scale_mw_get = scmi_power_scale_mw_get, + .power_scale_get = scmi_power_scale_get, }; static int scmi_perf_set_notify_enabled(const struct scmi_protocol_handle *ph, diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 704111f63993..a0a246310ba1 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -60,6 +60,12 @@ struct scmi_clock_info { }; }; +enum scmi_power_scale { + SCMI_POWER_BOGOWATTS, + SCMI_POWER_MILLIWATTS, + SCMI_POWER_MICROWATTS +}; + struct scmi_handle; struct scmi_device; struct scmi_protocol_handle; @@ -135,7 +141,7 @@ struct scmi_perf_proto_ops { unsigned long *rate, unsigned long *power); bool (*fast_switch_possible)(const struct scmi_protocol_handle *ph, struct device *dev); - bool (*power_scale_mw_get)(const struct scmi_protocol_handle *ph); + enum scmi_power_scale (*power_scale_get)(const struct scmi_protocol_handle *ph); }; /** From f3ac888fc5fbdeeec1e084327de06a2765542d56 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 7 Jul 2022 08:15:55 +0100 Subject: [PATCH 19/27] cpufreq: scmi: Support the power scale in micro-Watts in SCMI v3.1 The SCMI v3.1 adds support for power values in micro-Watts. They are not always in milli-Watts anymore (ignoring the bogo-Watts). Thus, the power must be converted conditionally before sending to Energy Model. Add the logic which handles the needed checks and conversions. Acked-by: Sudeep Holla Signed-off-by: Lukasz Luba Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/scmi-cpufreq.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index bfd35583d653..513a071845c2 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -100,7 +100,7 @@ static int __maybe_unused scmi_get_cpu_power(struct device *cpu_dev, unsigned long *power, unsigned long *KHz) { - bool power_scale_mw = perf_ops->power_scale_mw_get(ph); + enum scmi_power_scale power_scale = perf_ops->power_scale_get(ph); unsigned long Hz; int ret, domain; @@ -114,8 +114,8 @@ scmi_get_cpu_power(struct device *cpu_dev, unsigned long *power, if (ret) return ret; - /* Provide bigger resolution power to the Energy Model */ - if (power_scale_mw) + /* Convert the power to uW if it is mW (ignore bogoW) */ + if (power_scale == SCMI_POWER_MILLIWATTS) *power *= MICROWATT_PER_MILLIWATT; /* The EM framework specifies the frequency in KHz. */ @@ -255,8 +255,9 @@ static int scmi_cpufreq_exit(struct cpufreq_policy *policy) static void scmi_cpufreq_register_em(struct cpufreq_policy *policy) { struct em_data_callback em_cb = EM_DATA_CB(scmi_get_cpu_power); - bool power_scale_mw = perf_ops->power_scale_mw_get(ph); + enum scmi_power_scale power_scale = perf_ops->power_scale_get(ph); struct scmi_data *priv = policy->driver_data; + bool em_power_scale = false; /* * This callback will be called for each policy, but we don't need to @@ -268,9 +269,13 @@ static void scmi_cpufreq_register_em(struct cpufreq_policy *policy) if (!priv->nr_opp) return; + if (power_scale == SCMI_POWER_MILLIWATTS + || power_scale == SCMI_POWER_MICROWATTS) + em_power_scale = true; + em_dev_register_perf_domain(get_cpu_device(policy->cpu), priv->nr_opp, &em_cb, priv->opp_shared_cpus, - power_scale_mw); + em_power_scale); } static struct cpufreq_driver scmi_cpufreq_driver = { From a2f6a7ac60e234810a386aaa6aad106927c39c4f Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 7 Jul 2022 15:28:31 +0530 Subject: [PATCH 20/27] cpufreq: Warn users while freeing active policy With the new design in place, the show() and store() callbacks check if the policy is active or not before proceeding any further to avoid potential races. And in order to guarantee that cpufreq_policy_free() must be called after clearing the policy->cpus mask, i.e. by marking the policy inactive. In order to avoid introducing a bug around this later, print a warning message if we end up freeing an active policy. Also update cpufreq_online() a bit to make sure we clear the cpus mask for each error case before calling cpufreq_policy_free(). Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 73432360e6e9..954eef26685f 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1273,6 +1273,13 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy) unsigned long flags; int cpu; + /* + * The callers must ensure the policy is inactive by now, to avoid any + * races with show()/store() callbacks. + */ + if (unlikely(!policy_is_inactive(policy))) + pr_warn("%s: Freeing active policy\n", __func__); + /* Remove policy from list */ write_lock_irqsave(&cpufreq_driver_lock, flags); list_del(&policy->policy_list); @@ -1527,8 +1534,6 @@ out_destroy_policy: for_each_cpu(j, policy->real_cpus) remove_cpu_dev_symlink(policy, j, get_cpu_device(j)); - cpumask_clear(policy->cpus); - out_offline_policy: if (cpufreq_driver->offline) cpufreq_driver->offline(policy); @@ -1538,6 +1543,7 @@ out_exit_policy: cpufreq_driver->exit(policy); out_free_policy: + cpumask_clear(policy->cpus); up_write(&policy->rwsem); cpufreq_policy_free(policy); From b3f6c43d008c5ab103e00361671c456d45012547 Mon Sep 17 00:00:00 2001 From: Todd Brandt Date: Thu, 7 Jul 2022 15:54:51 -0700 Subject: [PATCH 21/27] pm-graph v5.9 bootgraph: - fix parsing of /proc/version to be much more flexible - check kernel version to disallow ftrace on anything older than 4.10 sleepgraph: - include fix to bugzilla 212761 in case it regresses - fix for -proc bug: https://github.com/intel/pm-graph/pull/20 - add -debugtiming arg to get timestamps on prints - allow use of the netfix tool hosted in the github repo - read s0ix data from pmc_core for better debug - include more system data in the output log - Do a better job testing input files useability - flag more error data from dmesg in the timeline - pre-parse the trace log to fix any ordering issues - add new parser to process dmesg only timelines - remove superflous sleep(5) in multitest mode config/custom-timeline-functions.cfg: - change some names to keep up to date README: - new version, small wording changes Signed-off-by: Todd Brandt Signed-off-by: Rafael J. Wysocki --- tools/power/pm-graph/README | 6 +- tools/power/pm-graph/bootgraph.py | 20 +- .../config/custom-timeline-functions.cfg | 2 +- tools/power/pm-graph/sleepgraph.py | 518 ++++++++++++------ 4 files changed, 360 insertions(+), 186 deletions(-) diff --git a/tools/power/pm-graph/README b/tools/power/pm-graph/README index da468bd510ca..e6020c0d59ec 100644 --- a/tools/power/pm-graph/README +++ b/tools/power/pm-graph/README @@ -6,7 +6,7 @@ |_| |___/ |_| pm-graph: suspend/resume/boot timing analysis tools - Version: 5.8 + Version: 5.9 Author: Todd Brandt Home Page: https://01.org/pm-graph @@ -97,8 +97,8 @@ (kernel/pre-3.15/enable_trace_events_suspend_resume.patch) (kernel/pre-3.15/enable_trace_events_device_pm_callback.patch) - If you're using a kernel older than 3.15.0, the following - additional kernel parameters are required: + If you're using bootgraph, or sleepgraph with a kernel older than 3.15.0, + the following additional kernel parameters are required: (e.g. in file /etc/default/grub) GRUB_CMDLINE_LINUX_DEFAULT="... initcall_debug log_buf_len=32M ..." diff --git a/tools/power/pm-graph/bootgraph.py b/tools/power/pm-graph/bootgraph.py index 2823cd3122f7..f96f50e0c336 100755 --- a/tools/power/pm-graph/bootgraph.py +++ b/tools/power/pm-graph/bootgraph.py @@ -69,22 +69,24 @@ class SystemValues(aslib.SystemValues): bootloader = 'grub' blexec = [] def __init__(self): - self.hostname = platform.node() + self.kernel, self.hostname = 'unknown', platform.node() self.testtime = datetime.now().strftime('%Y-%m-%d_%H:%M:%S') if os.path.exists('/proc/version'): fp = open('/proc/version', 'r') - val = fp.read().strip() + self.kernel = self.kernelVersion(fp.read().strip()) fp.close() - self.kernel = self.kernelVersion(val) - else: - self.kernel = 'unknown' self.testdir = datetime.now().strftime('boot-%y%m%d-%H%M%S') def kernelVersion(self, msg): - return msg.split()[2] + m = re.match('^[Ll]inux *[Vv]ersion *(?P\S*) .*', msg) + if m: + return m.group('v') + return 'unknown' def checkFtraceKernelVersion(self): - val = tuple(map(int, self.kernel.split('-')[0].split('.'))) - if val >= (4, 10, 0): - return True + m = re.match('^(?P[0-9]*)\.(?P[0-9]*)\.(?P[0-9]*).*', self.kernel) + if m: + val = tuple(map(int, m.groups())) + if val >= (4, 10, 0): + return True return False def kernelParams(self): cmdline = 'initcall_debug log_buf_len=32M' diff --git a/tools/power/pm-graph/config/custom-timeline-functions.cfg b/tools/power/pm-graph/config/custom-timeline-functions.cfg index 962e5768681c..4f80ad7d7275 100644 --- a/tools/power/pm-graph/config/custom-timeline-functions.cfg +++ b/tools/power/pm-graph/config/custom-timeline-functions.cfg @@ -125,7 +125,7 @@ acpi_suspend_begin: suspend_console: acpi_pm_prepare: syscore_suspend: -arch_thaw_secondary_cpus_end: +arch_enable_nonboot_cpus_end: syscore_resume: acpi_pm_finish: resume_console: diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py index ffd50953a024..33981adcdd68 100755 --- a/tools/power/pm-graph/sleepgraph.py +++ b/tools/power/pm-graph/sleepgraph.py @@ -66,8 +66,13 @@ from threading import Thread from subprocess import call, Popen, PIPE import base64 +debugtiming = False +mystarttime = time.time() def pprint(msg): - print(msg) + if debugtiming: + print('[%09.3f] %s' % (time.time()-mystarttime, msg)) + else: + print(msg) sys.stdout.flush() def ascii(text): @@ -81,13 +86,14 @@ def ascii(text): # store system values and test parameters class SystemValues: title = 'SleepGraph' - version = '5.8' + version = '5.9' ansi = False rs = 0 display = '' gzip = False sync = False wifi = False + netfix = False verbose = False testlog = True dmesglog = True @@ -108,6 +114,7 @@ class SystemValues: cpucount = 0 memtotal = 204800 memfree = 204800 + osversion = '' srgap = 0 cgexp = False testdir = '' @@ -116,6 +123,7 @@ class SystemValues: fpdtpath = '/sys/firmware/acpi/tables/FPDT' epath = '/sys/kernel/debug/tracing/events/power/' pmdpath = '/sys/power/pm_debug_messages' + s0ixpath = '/sys/module/intel_pmc_core/parameters/warn_on_s0ix_failures' acpipath='/sys/module/acpi/parameters/debug_level' traceevents = [ 'suspend_resume', @@ -156,6 +164,7 @@ class SystemValues: ftop = False usetraceevents = False usetracemarkers = True + useftrace = True usekprobes = True usedevsrc = False useprocmon = False @@ -279,10 +288,16 @@ class SystemValues: 'intel_fbdev_set_suspend': {}, } infocmds = [ + [0, 'sysinfo', 'uname', '-a'], + [0, 'cpuinfo', 'head', '-7', '/proc/cpuinfo'], [0, 'kparams', 'cat', '/proc/cmdline'], [0, 'mcelog', 'mcelog'], [0, 'pcidevices', 'lspci', '-tv'], - [0, 'usbdevices', 'lsusb', '-t'], + [0, 'usbdevices', 'lsusb', '-tv'], + [0, 'acpidevices', 'sh', '-c', 'ls -l /sys/bus/acpi/devices/*/physical_node'], + [0, 's0ix_require', 'cat', '/sys/kernel/debug/pmc_core/substate_requirements'], + [0, 's0ix_debug', 'cat', '/sys/kernel/debug/pmc_core/slp_s0_debug_status'], + [1, 's0ix_residency', 'cat', '/sys/kernel/debug/pmc_core/slp_s0_residency_usec'], [1, 'interrupts', 'cat', '/proc/interrupts'], [1, 'wakeups', 'cat', '/sys/kernel/debug/wakeup_sources'], [2, 'gpecounts', 'sh', '-c', 'grep -v invalid /sys/firmware/acpi/interrupts/*'], @@ -358,8 +373,19 @@ class SystemValues: self.outputResult({'error':msg}) sys.exit(1) return False - def usable(self, file): - return (os.path.exists(file) and os.path.getsize(file) > 0) + def usable(self, file, ishtml=False): + if not os.path.exists(file) or os.path.getsize(file) < 1: + return False + if ishtml: + try: + fp = open(file, 'r') + res = fp.read(1000) + fp.close() + except: + return False + if '' not in res: + return False + return True def getExec(self, cmd): try: fp = Popen(['which', cmd], stdout=PIPE, stderr=PIPE).stdout @@ -413,12 +439,16 @@ class SystemValues: r = info['bios-release-date'] if 'bios-release-date' in info else '' self.sysstamp = '# sysinfo | man:%s | plat:%s | cpu:%s | bios:%s | biosdate:%s | numcpu:%d | memsz:%d | memfr:%d' % \ (m, p, c, b, r, self.cpucount, self.memtotal, self.memfree) + if self.osversion: + self.sysstamp += ' | os:%s' % self.osversion def printSystemInfo(self, fatal=False): self.rootCheck(True) out = dmidecode(self.mempath, fatal) if len(out) < 1: return fmt = '%-24s: %s' + if self.osversion: + print(fmt % ('os-version', self.osversion)) for name in sorted(out): print(fmt % (name, out[name])) print(fmt % ('cpucount', ('%d' % self.cpucount))) @@ -426,20 +456,25 @@ class SystemValues: print(fmt % ('memfree', ('%d kB' % self.memfree))) def cpuInfo(self): self.cpucount = 0 - fp = open('/proc/cpuinfo', 'r') - for line in fp: - if re.match('^processor[ \t]*:[ \t]*[0-9]*', line): - self.cpucount += 1 - fp.close() - fp = open('/proc/meminfo', 'r') - for line in fp: - m = re.match('^MemTotal:[ \t]*(?P[0-9]*) *kB', line) - if m: - self.memtotal = int(m.group('sz')) - m = re.match('^MemFree:[ \t]*(?P[0-9]*) *kB', line) - if m: - self.memfree = int(m.group('sz')) - fp.close() + if os.path.exists('/proc/cpuinfo'): + with open('/proc/cpuinfo', 'r') as fp: + for line in fp: + if re.match('^processor[ \t]*:[ \t]*[0-9]*', line): + self.cpucount += 1 + if os.path.exists('/proc/meminfo'): + with open('/proc/meminfo', 'r') as fp: + for line in fp: + m = re.match('^MemTotal:[ \t]*(?P[0-9]*) *kB', line) + if m: + self.memtotal = int(m.group('sz')) + m = re.match('^MemFree:[ \t]*(?P[0-9]*) *kB', line) + if m: + self.memfree = int(m.group('sz')) + if os.path.exists('/etc/os-release'): + with open('/etc/os-release', 'r') as fp: + for line in fp: + if line.startswith('PRETTY_NAME='): + self.osversion = line[12:].strip().replace('"', '') def initTestOutput(self, name): self.prefix = self.hostname v = open('/proc/version', 'r').read().strip() @@ -698,6 +733,8 @@ class SystemValues: return False return True def fsetVal(self, val, path): + if not self.useftrace: + return False return self.setVal(val, self.tpath+path) def getVal(self, file): res = '' @@ -711,9 +748,11 @@ class SystemValues: pass return res def fgetVal(self, path): + if not self.useftrace: + return '' return self.getVal(self.tpath+path) def cleanupFtrace(self): - if(self.usecallgraph or self.usetraceevents or self.usedevsrc): + if self.useftrace: self.fsetVal('0', 'events/kprobes/enable') self.fsetVal('', 'kprobe_events') self.fsetVal('1024', 'buffer_size_kb') @@ -734,13 +773,14 @@ class SystemValues: return True return False def initFtrace(self, quiet=False): + if not self.useftrace: + return if not quiet: sysvals.printSystemInfo(False) pprint('INITIALIZING FTRACE...') # turn trace off self.fsetVal('0', 'tracing_on') self.cleanupFtrace() - self.testVal(self.pmdpath, 'basic', '1') # set the trace clock to global self.fsetVal('global', 'trace_clock') self.fsetVal('nop', 'current_tracer') @@ -766,6 +806,10 @@ class SystemValues: # set trace type self.fsetVal('function_graph', 'current_tracer') self.fsetVal('', 'set_ftrace_filter') + # temporary hack to fix https://bugzilla.kernel.org/show_bug.cgi?id=212761 + fp = open(self.tpath+'set_ftrace_notrace', 'w') + fp.write('native_queued_spin_lock_slowpath\ndev_driver_string') + fp.close() # set trace format options self.fsetVal('print-parent', 'trace_options') self.fsetVal('funcgraph-abstime', 'trace_options') @@ -846,6 +890,8 @@ class SystemValues: fp.write('# turbostat %s\n' % test['turbo']) if 'wifi' in test: fp.write('# wifi %s\n' % test['wifi']) + if 'netfix' in test: + fp.write('# netfix %s\n' % test['netfix']) if test['error'] or len(testdata) > 1: fp.write('# enter_sleep_error %s\n' % test['error']) return fp @@ -865,6 +911,8 @@ class SystemValues: fp.write('error%s: %s\n' % (n, testdata['error'])) else: fp.write('result%s: pass\n' % n) + if 'mode' in testdata: + fp.write('mode%s: %s\n' % (n, testdata['mode'])) for v in ['suspend', 'resume', 'boot', 'lastinit']: if v in testdata: fp.write('%s%s: %.3f\n' % (v, n, testdata[v])) @@ -901,6 +949,8 @@ class SystemValues: fp.write(text) fp.close() def dlog(self, text): + if not self.dmesgfile: + return self.putlog(self.dmesgfile, '# %s\n' % text) def flog(self, text): self.putlog(self.ftracefile, text) @@ -954,34 +1004,31 @@ class SystemValues: dirname = props[dev].syspath if not dirname or not os.path.exists(dirname): continue - with open(dirname+'/power/async') as fp: - text = fp.read() - props[dev].isasync = False - if 'enabled' in text: + props[dev].isasync = False + if os.path.exists(dirname+'/power/async'): + fp = open(dirname+'/power/async') + if 'enabled' in fp.read(): props[dev].isasync = True + fp.close() fields = os.listdir(dirname) - if 'product' in fields: - with open(dirname+'/product', 'rb') as fp: - props[dev].altname = ascii(fp.read()) - elif 'name' in fields: - with open(dirname+'/name', 'rb') as fp: - props[dev].altname = ascii(fp.read()) - elif 'model' in fields: - with open(dirname+'/model', 'rb') as fp: - props[dev].altname = ascii(fp.read()) - elif 'description' in fields: - with open(dirname+'/description', 'rb') as fp: - props[dev].altname = ascii(fp.read()) - elif 'id' in fields: - with open(dirname+'/id', 'rb') as fp: - props[dev].altname = ascii(fp.read()) - elif 'idVendor' in fields and 'idProduct' in fields: - idv, idp = '', '' - with open(dirname+'/idVendor', 'rb') as fp: - idv = ascii(fp.read()).strip() - with open(dirname+'/idProduct', 'rb') as fp: - idp = ascii(fp.read()).strip() - props[dev].altname = '%s:%s' % (idv, idp) + for file in ['product', 'name', 'model', 'description', 'id', 'idVendor']: + if file not in fields: + continue + try: + with open(os.path.join(dirname, file), 'rb') as fp: + props[dev].altname = ascii(fp.read()) + except: + continue + if file == 'idVendor': + idv, idp = props[dev].altname.strip(), '' + try: + with open(os.path.join(dirname, 'idProduct'), 'rb') as fp: + idp = ascii(fp.read()).strip() + except: + props[dev].altname = '' + break + props[dev].altname = '%s:%s' % (idv, idp) + break if props[dev].altname: out = props[dev].altname.strip().replace('\n', ' ')\ .replace(',', ' ').replace(';', ' ') @@ -1047,7 +1094,7 @@ class SystemValues: self.cmd1[name] = self.dictify(info, delta) elif not debug and delta and name in self.cmd1: before, after = self.cmd1[name], self.dictify(info, delta) - dinfo = ('\t%s\n' % before['@']) if '@' in before else '' + dinfo = ('\t%s\n' % before['@']) if '@' in before and len(before) > 1 else '' prefix = self.commonPrefix(list(before.keys())) for key in sorted(before): if key in after and before[key] != after[key]: @@ -1128,6 +1175,22 @@ class SystemValues: val = valline[idx] out.append('%s=%s' % (key, val)) return '|'.join(out) + def netfixon(self, net='both'): + cmd = self.getExec('netfix') + if not cmd: + return '' + fp = Popen([cmd, '-s', net, 'on'], stdout=PIPE, stderr=PIPE).stdout + out = ascii(fp.read()).strip() + fp.close() + return out + def wifiRepair(self): + out = self.netfixon('wifi') + if not out or 'error' in out.lower(): + return '' + m = re.match('WIFI \S* ONLINE (?P\S*)', out) + if not m: + return 'dead' + return m.group('action') def wifiDetails(self, dev): try: info = open('/sys/class/net/%s/device/uevent' % dev, 'r').read().strip() @@ -1144,12 +1207,12 @@ class SystemValues: except: return '' for line in reversed(w.split('\n')): - m = re.match(' *(?P.*): (?P[0-9a-f]*) .*', w.split('\n')[-1]) + m = re.match(' *(?P.*): (?P[0-9a-f]*) .*', line) if not m or (dev and dev != m.group('dev')): continue return m.group('dev') return '' - def pollWifi(self, dev, timeout=60): + def pollWifi(self, dev, timeout=10): start = time.time() while (time.time() - start) < timeout: w = self.checkWifi(dev) @@ -1157,6 +1220,11 @@ class SystemValues: return '%s reconnected %.2f' % \ (self.wifiDetails(dev), max(0, time.time() - start)) time.sleep(0.01) + if self.netfix: + res = self.wifiRepair() + if res: + timeout = max(0, time.time() - start) + return '%s %s %d' % (self.wifiDetails(dev), res, timeout) return '%s timeout %d' % (self.wifiDetails(dev), timeout) def errorSummary(self, errinfo, msg): found = False @@ -1283,10 +1351,10 @@ sysvals = SystemValues() switchvalues = ['enable', 'disable', 'on', 'off', 'true', 'false', '1', '0'] switchoff = ['disable', 'off', 'false', '0'] suspendmodename = { - 'freeze': 'Freeze (S0)', - 'standby': 'Standby (S1)', - 'mem': 'Suspend (S3)', - 'disk': 'Hibernate (S4)' + 'standby': 'standby (S1)', + 'freeze': 'freeze (S2idle)', + 'mem': 'suspend (S3)', + 'disk': 'hibernate (S4)' } # Class: DevProps @@ -1376,6 +1444,7 @@ class Data: 'INVALID' : r'(?i).*\bINVALID\b.*', 'CRASH' : r'(?i).*\bCRASHED\b.*', 'TIMEOUT' : r'(?i).*\bTIMEOUT\b.*', + 'ABORT' : r'(?i).*\bABORT\b.*', 'IRQ' : r'.*\bgenirq: .*', 'TASKFAIL': r'.*Freezing of tasks *.*', 'ACPI' : r'.*\bACPI *(?P[A-Za-z]*) *Error[: ].*', @@ -1724,9 +1793,9 @@ class Data: if 'waking' in self.dmesg[lp]: tCnt = self.dmesg[lp]['waking'][0] if self.dmesg[lp]['waking'][1] >= 0.001: - tTry = '-%.0f' % (round(self.dmesg[lp]['waking'][1] * 1000)) + tTry = '%.0f' % (round(self.dmesg[lp]['waking'][1] * 1000)) else: - tTry = '-%.3f' % (self.dmesg[lp]['waking'][1] * 1000) + tTry = '%.3f' % (self.dmesg[lp]['waking'][1] * 1000) text = '%.0f (%s ms waking %d times)' % (tL * 1000, tTry, tCnt) else: text = '%.0f' % (tL * 1000) @@ -2107,6 +2176,30 @@ class Data: # set resume complete to end at end marker if 'resume_complete' in dm: dm['resume_complete']['end'] = time + def initcall_debug_call(self, line, quick=False): + m = re.match('.*(\[ *)(?P[0-9\.]*)(\]) .* (?P.*)\: '+\ + 'PM: *calling .* @ (?P.*), parent: (?P

.*)', line) + if not m: + m = re.match('.*(\[ *)(?P[0-9\.]*)(\]) .* (?P.*)\: '+\ + 'calling .* @ (?P.*), parent: (?P

.*)', line) + if not m: + m = re.match('.*(\[ *)(?P[0-9\.]*)(\]) calling '+\ + '(?P.*)\+ @ (?P.*), parent: (?P

.*)', line) + if m: + return True if quick else m.group('t', 'f', 'n', 'p') + return False if quick else ('', '', '', '') + def initcall_debug_return(self, line, quick=False): + m = re.match('.*(\[ *)(?P[0-9\.]*)(\]) .* (?P.*)\: PM: '+\ + '.* returned (?P[0-9]*) after (?P

[0-9]*) usecs', line) + if not m: + m = re.match('.*(\[ *)(?P[0-9\.]*)(\]) .* (?P.*)\: '+\ + '.* returned (?P[0-9]*) after (?P
[0-9]*) usecs', line) + if not m: + m = re.match('.*(\[ *)(?P[0-9\.]*)(\]) call '+\ + '(?P.*)\+ returned .* after (?P
.*) usecs', line) + if m: + return True if quick else m.group('t', 'f', 'dt') + return False if quick else ('', '', '') def debugPrint(self): for p in self.sortedPhases(): list = self.dmesg[p]['list'] @@ -2880,10 +2973,11 @@ class TestProps: cmdlinefmt = '^# command \| (?P.*)' kparamsfmt = '^# kparams \| (?P.*)' devpropfmt = '# Device Properties: .*' - pinfofmt = '# platform-(?P[a-z,A-Z,0-9]*): (?P.*)' + pinfofmt = '# platform-(?P[a-z,A-Z,0-9,_]*): (?P.*)' tracertypefmt = '# tracer: (?P.*)' firmwarefmt = '# fwsuspend (?P[0-9]*) fwresume (?P[0-9]*)$' procexecfmt = 'ps - (?P.*)$' + procmultifmt = '@(?P[0-9]*)\|(?P.*)$' ftrace_line_fmt_fg = \ '^ *(?P
.*) usecs', last) - if(mc and mr and (mc.group('t') == mr.group('t')) and - (mc.group('f') == mr.group('f'))): + ct, cf, n, p = data.initcall_debug_call(line) + rt, rf, l = data.initcall_debug_return(last) + if ct and rt and ct == rt and cf == rf: i = data.dmesgtext.index(last) j = data.dmesgtext.index(line) data.dmesgtext[i] = line @@ -3777,7 +3935,6 @@ def loadKernelLog(): # Function: parseKernelLog # Description: -# [deprecated for kernel 3.15.0 or newer] # Analyse a dmesg log output file generated from this app during # the execution phase. Create a set of device structures in memory # for subsequent formatting in the html output file @@ -3796,30 +3953,30 @@ def parseKernelLog(data): # dmesg phase match table dm = { - 'suspend_prepare': ['PM: Syncing filesystems.*'], - 'suspend': ['PM: Entering [a-z]* sleep.*', 'Suspending console.*'], - 'suspend_late': ['PM: suspend of devices complete after.*'], - 'suspend_noirq': ['PM: late suspend of devices complete after.*'], - 'suspend_machine': ['PM: noirq suspend of devices complete after.*'], - 'resume_machine': ['ACPI: Low-level resume complete.*'], - 'resume_noirq': ['ACPI: Waking up from system sleep state.*'], - 'resume_early': ['PM: noirq resume of devices complete after.*'], - 'resume': ['PM: early resume of devices complete after.*'], - 'resume_complete': ['PM: resume of devices complete after.*'], + 'suspend_prepare': ['PM: Syncing filesystems.*', 'PM: suspend entry.*'], + 'suspend': ['PM: Entering [a-z]* sleep.*', 'Suspending console.*', + 'PM: Suspending system .*'], + 'suspend_late': ['PM: suspend of devices complete after.*', + 'PM: freeze of devices complete after.*'], + 'suspend_noirq': ['PM: late suspend of devices complete after.*', + 'PM: late freeze of devices complete after.*'], + 'suspend_machine': ['PM: suspend-to-idle', + 'PM: noirq suspend of devices complete after.*', + 'PM: noirq freeze of devices complete after.*'], + 'resume_machine': ['PM: Timekeeping suspended for.*', + 'ACPI: Low-level resume complete.*', + 'ACPI: resume from mwait', + 'Suspended for [0-9\.]* seconds'], + 'resume_noirq': ['PM: resume from suspend-to-idle', + 'ACPI: Waking up from system sleep state.*'], + 'resume_early': ['PM: noirq resume of devices complete after.*', + 'PM: noirq restore of devices complete after.*'], + 'resume': ['PM: early resume of devices complete after.*', + 'PM: early restore of devices complete after.*'], + 'resume_complete': ['PM: resume of devices complete after.*', + 'PM: restore of devices complete after.*'], 'post_resume': ['.*Restarting tasks \.\.\..*'], } - if(sysvals.suspendmode == 'standby'): - dm['resume_machine'] = ['PM: Restoring platform NVS memory'] - elif(sysvals.suspendmode == 'disk'): - dm['suspend_late'] = ['PM: freeze of devices complete after.*'] - dm['suspend_noirq'] = ['PM: late freeze of devices complete after.*'] - dm['suspend_machine'] = ['PM: noirq freeze of devices complete after.*'] - dm['resume_machine'] = ['PM: Restoring platform NVS memory'] - dm['resume_early'] = ['PM: noirq restore of devices complete after.*'] - dm['resume'] = ['PM: early restore of devices complete after.*'] - dm['resume_complete'] = ['PM: restore of devices complete after.*'] - elif(sysvals.suspendmode == 'freeze'): - dm['resume_machine'] = ['ACPI: resume from mwait'] # action table (expected events that occur and show up in dmesg) at = { @@ -3867,12 +4024,13 @@ def parseKernelLog(data): for s in dm[p]: if(re.match(s, msg)): phasechange, phase = True, p + dm[p] = [s] break # hack for determining resume_machine end for freeze if(not sysvals.usetraceevents and sysvals.suspendmode == 'freeze' \ and phase == 'resume_machine' and \ - re.match('calling (?P.*)\+ @ .*, parent: .*', msg)): + data.initcall_debug_call(line, True)): data.setPhase(phase, ktime, False) phase = 'resume_noirq' data.setPhase(phase, ktime, True) @@ -3945,26 +4103,18 @@ def parseKernelLog(data): # -- device callbacks -- if(phase in data.sortedPhases()): # device init call - if(re.match('calling (?P.*)\+ @ .*, parent: .*', msg)): - sm = re.match('calling (?P.*)\+ @ '+\ - '(?P.*), parent: (?P

.*)', msg); - f = sm.group('f') - n = sm.group('n') - p = sm.group('p') - if(f and n and p): - data.newAction(phase, f, int(n), p, ktime, -1, '') - # device init return - elif(re.match('call (?P.*)\+ returned .* after '+\ - '(?P.*) usecs', msg)): - sm = re.match('call (?P.*)\+ returned .* after '+\ - '(?P.*) usecs(?P.*)', msg); - f = sm.group('f') - t = sm.group('t') - list = data.dmesg[phase]['list'] - if(f in list): - dev = list[f] - dev['length'] = int(t) - dev['end'] = ktime + t, f, n, p = data.initcall_debug_call(line) + if t and f and n and p: + data.newAction(phase, f, int(n), p, ktime, -1, '') + else: + # device init return + t, f, l = data.initcall_debug_return(line) + if t and f and l: + list = data.dmesg[phase]['list'] + if(f in list): + dev = list[f] + dev['length'] = int(l) + dev['end'] = ktime # if trace events are not available, these are better than nothing if(not sysvals.usetraceevents): @@ -4006,6 +4156,8 @@ def parseKernelLog(data): # fill in any missing phases phasedef = data.phasedef terr, lp = '', 'suspend_prepare' + if lp not in data.dmesg: + doError('dmesg log format has changed, could not find start of suspend') for p in sorted(phasedef, key=lambda k:phasedef[k]['order']): if p not in data.dmesg: if not terr: @@ -5302,7 +5454,7 @@ def executeSuspend(quiet=False): sv.dlog('read dmesg') sv.initdmesg() # start ftrace - if(sv.usecallgraph or sv.usetraceevents): + if sv.useftrace: if not quiet: pprint('START TRACING') sv.dlog('start ftrace tracing') @@ -5334,8 +5486,7 @@ def executeSuspend(quiet=False): sv.dlog('enable RTC wake alarm') sv.rtcWakeAlarmOn() # start of suspend trace marker - if(sv.usecallgraph or sv.usetraceevents): - sv.fsetVal(datetime.now().strftime(sv.tmstart), 'trace_marker') + sv.fsetVal(datetime.now().strftime(sv.tmstart), 'trace_marker') # predelay delay if(count == 1 and sv.predelay > 0): sv.fsetVal('WAIT %d' % sv.predelay, 'trace_marker') @@ -5384,11 +5535,17 @@ def executeSuspend(quiet=False): sv.fsetVal('WAIT END', 'trace_marker') # return from suspend pprint('RESUME COMPLETE') - if(sv.usecallgraph or sv.usetraceevents): - sv.fsetVal(datetime.now().strftime(sv.tmend), 'trace_marker') + sv.fsetVal(datetime.now().strftime(sv.tmend), 'trace_marker') if sv.wifi and wifi: tdata['wifi'] = sv.pollWifi(wifi) sv.dlog('wifi check, %s' % tdata['wifi']) + if sv.netfix: + netfixout = sv.netfixon('wired') + elif sv.netfix: + netfixout = sv.netfixon() + if sv.netfix and netfixout: + tdata['netfix'] = netfixout + sv.dlog('netfix, %s' % tdata['netfix']) if(sv.suspendmode == 'mem' or sv.suspendmode == 'command'): sv.dlog('read the ACPI FPDT') tdata['fw'] = getFPDT(False) @@ -5396,7 +5553,7 @@ def executeSuspend(quiet=False): sv.dlog('run the cmdinfo list after') cmdafter = sv.cmdinfo(False) # stop ftrace - if(sv.usecallgraph or sv.usetraceevents): + if sv.useftrace: if sv.useprocmon: sv.dlog('stop the process monitor') pm.stop() @@ -5407,7 +5564,7 @@ def executeSuspend(quiet=False): sysvals.dlog('EXECUTION TRACE END') sv.getdmesg(testdata) # grab a copy of the ftrace output - if(sv.usecallgraph or sv.usetraceevents): + if sv.useftrace: if not quiet: pprint('CAPTURING TRACE') op = sv.writeDatafileHeader(sv.ftracefile, testdata) @@ -5838,13 +5995,19 @@ def statusCheck(probecheck=False): pprint(' please choose one with -m') # check if ftrace is available - res = sysvals.colorText('NO') - ftgood = sysvals.verifyFtrace() - if(ftgood): - res = 'YES' - elif(sysvals.usecallgraph): - status = 'ftrace is not properly supported' - pprint(' is ftrace supported: %s' % res) + if sysvals.useftrace: + res = sysvals.colorText('NO') + sysvals.useftrace = sysvals.verifyFtrace() + efmt = '"{0}" uses ftrace, and it is not properly supported' + if sysvals.useftrace: + res = 'YES' + elif sysvals.usecallgraph: + status = efmt.format('-f') + elif sysvals.usedevsrc: + status = efmt.format('-dev') + elif sysvals.useprocmon: + status = efmt.format('-proc') + pprint(' is ftrace supported: %s' % res) # check if kprobes are available if sysvals.usekprobes: @@ -5857,8 +6020,8 @@ def statusCheck(probecheck=False): pprint(' are kprobes supported: %s' % res) # what data source are we using - res = 'DMESG' - if(ftgood): + res = 'DMESG (very limited, ftrace is preferred)' + if sysvals.useftrace: sysvals.usetraceevents = True for e in sysvals.traceevents: if not os.path.exists(sysvals.epath+e): @@ -5879,7 +6042,7 @@ def statusCheck(probecheck=False): pprint(' optional commands this tool may use for info:') no = sysvals.colorText('MISSING') yes = sysvals.colorText('FOUND', 32) - for c in ['turbostat', 'mcelog', 'lspci', 'lsusb']: + for c in ['turbostat', 'mcelog', 'lspci', 'lsusb', 'netfix']: if c == 'turbostat': res = yes if sysvals.haveTurbostat() else no else: @@ -5971,7 +6134,7 @@ def processData(live=False, quiet=False): if not sysvals.stamp: pprint('ERROR: data does not include the expected stamp') return (testruns, {'error': 'timeline generation failed'}) - shown = ['bios', 'biosdate', 'cpu', 'host', 'kernel', 'man', 'memfr', + shown = ['os', 'bios', 'biosdate', 'cpu', 'host', 'kernel', 'man', 'memfr', 'memsz', 'mode', 'numcpu', 'plat', 'time', 'wifi'] sysvals.vprint('System Info:') for key in sorted(sysvals.stamp): @@ -6052,6 +6215,8 @@ def runTest(n=0, quiet=False): if sysvals.display: ret = sysvals.displayControl('init') sysvals.dlog('xset display init, ret = %d' % ret) + sysvals.testVal(sysvals.pmdpath, 'basic', '1') + sysvals.testVal(sysvals.s0ixpath, 'basic', 'Y') sysvals.dlog('initialize ftrace') sysvals.initFtrace(quiet) @@ -6145,9 +6310,12 @@ def data_from_html(file, outpath, issues, fulldetail=False): elist[err[0]] += 1 for i in elist: ilist.append('%sx%d' % (i, elist[i]) if elist[i] > 1 else i) - wifi = find_in_html(html, 'Wifi Resume: ', '') - if wifi: - extra['wifi'] = wifi + line = find_in_html(log, '# wifi ', '\n') + if line: + extra['wifi'] = line + line = find_in_html(log, '# netfix ', '\n') + if line: + extra['netfix'] = line low = find_in_html(html, 'freeze time: ', ' ms') for lowstr in ['waking', '+']: if not low: @@ -6243,7 +6411,7 @@ def genHtml(subdir, force=False): sysvals.ftracefile = file sysvals.setOutputFile() if (sysvals.dmesgfile or sysvals.ftracefile) and sysvals.htmlfile and \ - (force or not sysvals.usable(sysvals.htmlfile)): + (force or not sysvals.usable(sysvals.htmlfile, True)): pprint('FTRACE: %s' % sysvals.ftracefile) if sysvals.dmesgfile: pprint('DMESG : %s' % sysvals.dmesgfile) @@ -6533,6 +6701,7 @@ def printHelp(): ' -skiphtml Run the test and capture the trace logs, but skip the timeline (default: disabled)\n'\ ' -result fn Export a results table to a text file for parsing.\n'\ ' -wifi If a wifi connection is available, check that it reconnects after resume.\n'\ + ' -netfix Use netfix to reset the network in the event it fails to resume.\n'\ ' [testprep]\n'\ ' -sync Sync the filesystems before starting the test\n'\ ' -rs on/off Enable/disable runtime suspend for all devices, restore all after test\n'\ @@ -6615,6 +6784,8 @@ if __name__ == '__main__': elif(arg == '-v'): pprint("Version %s" % sysvals.version) sys.exit(0) + elif(arg == '-debugtiming'): + debugtiming = True elif(arg == '-x2'): sysvals.execcount = 2 elif(arg == '-x2delay'): @@ -6657,6 +6828,8 @@ if __name__ == '__main__': sysvals.sync = True elif(arg == '-wifi'): sysvals.wifi = True + elif(arg == '-netfix'): + sysvals.netfix = True elif(arg == '-gzip'): sysvals.gzip = True elif(arg == '-info'): @@ -6819,7 +6992,7 @@ if __name__ == '__main__': sysvals.outdir = val sysvals.notestrun = True if(os.path.isdir(val) == False): - doError('%s is not accessible' % val) + doError('%s is not accesible' % val) elif(arg == '-filter'): try: val = next(args) @@ -6942,12 +7115,11 @@ if __name__ == '__main__': time.sleep(sysvals.multitest['delay']) fmt = 'suspend-%y%m%d-%H%M%S' sysvals.testdir = os.path.join(sysvals.outdir, datetime.now().strftime(fmt)) - ret = runTest(i+1, True) + ret = runTest(i+1, not sysvals.verbose) failcnt = 0 if not ret else failcnt + 1 if sysvals.maxfail > 0 and failcnt >= sysvals.maxfail: pprint('Maximum fail count of %d reached, aborting multitest' % (sysvals.maxfail)) break - time.sleep(5) sysvals.resetlog() sysvals.multistat(False, i, finish) if 'time' in sysvals.multitest and datetime.now() >= finish: From 9d822ccf337299d08cf5121929013f3ac21932c9 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 14 Jul 2022 18:59:03 -0700 Subject: [PATCH 22/27] cpufreq: loongson2: fix Kconfig "its" grammar Use the possessive "its" instead of the contraction "it's" where appropriate. Signed-off-by: Randy Dunlap Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index c3038cdc6865..2a84fc63371e 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -268,7 +268,7 @@ config LOONGSON2_CPUFREQ This option adds a CPUFreq driver for loongson processors which support software configurable cpu frequency. - Loongson2F and it's successors support this feature. + Loongson2F and its successors support this feature. If in doubt, say N. From 3e5c04f97c87f5061a37edad11a7b37c3fee2466 Mon Sep 17 00:00:00 2001 From: Zhao Liu Date: Fri, 22 Jul 2022 10:50:24 +0800 Subject: [PATCH 23/27] cpufreq: ondemand: Use cpumask_var_t for on-stack cpu mask A cpumask structure on the stack can cause a warning with CONFIG_NR_CPUS=8192 (e.g. Ubuntu 22.04 uses this): drivers/cpufreq/cpufreq_ondemand.c: In function 'od_set_powersave_bias': drivers/cpufreq/cpufreq_ondemand.c:449:1: warning: the frame size of 1032 bytes is larger than 1024 bytes [-Wframe-larger-than=] 449 | } | ^ CONFIG_CPUMASK_OFFSTACK=y is enabled by default for most distros, and hence we can work around the warning by using cpumask_var_t. Signed-off-by: Zhao Liu Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq_ondemand.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index e8fbf970ff07..c52d19d67557 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -416,10 +416,13 @@ static struct dbs_governor od_dbs_gov = { static void od_set_powersave_bias(unsigned int powersave_bias) { unsigned int cpu; - cpumask_t done; + cpumask_var_t done; + + if (!alloc_cpumask_var(&done, GFP_KERNEL)) + return; default_powersave_bias = powersave_bias; - cpumask_clear(&done); + cpumask_clear(done); cpus_read_lock(); for_each_online_cpu(cpu) { @@ -428,7 +431,7 @@ static void od_set_powersave_bias(unsigned int powersave_bias) struct dbs_data *dbs_data; struct od_dbs_tuners *od_tuners; - if (cpumask_test_cpu(cpu, &done)) + if (cpumask_test_cpu(cpu, done)) continue; policy = cpufreq_cpu_get_raw(cpu); @@ -439,13 +442,15 @@ static void od_set_powersave_bias(unsigned int powersave_bias) if (!policy_dbs) continue; - cpumask_or(&done, &done, policy->cpus); + cpumask_or(done, done, policy->cpus); dbs_data = policy_dbs->dbs_data; od_tuners = dbs_data->tuners; od_tuners->powersave_bias = default_powersave_bias; } cpus_read_unlock(); + + free_cpumask_var(done); } void od_register_powersave_bias_handler(unsigned int (*f) From 1548fac47a114b42063def551eb152a536ed9697 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Sat, 16 Jul 2022 09:26:55 +0300 Subject: [PATCH 24/27] intel_idle: make SPR C1 and C1E be independent This patch partially reverts the changes made by the following commit: da0e58c038e6 intel_idle: add 'preferred_cstates' module argument As that commit describes, on early Sapphire Rapids Xeon platforms the C1 and C1E states were mutually exclusive, so that users could only have either C1 and C6, or C1E and C6. However, Intel firmware engineers managed to remove this limitation and make C1 and C1E to be completely independent, just like on previous Xeon platforms. Therefore, this patch: * Removes commentary describing the old, and now non-existing SPR C1E limitation. * Marks SPR C1E as available by default. * Removes the 'preferred_cstates' parameter handling for SPR. Both C1 and C1E will be available regardless of 'preferred_cstates' value. We expect that all SPR systems are shipping with new firmware, which includes the C1/C1E improvement. Cc: v5.18+ # v5.18+ Signed-off-by: Artem Bityutskiy Signed-off-by: Rafael J. Wysocki --- drivers/idle/intel_idle.c | 24 +----------------------- 1 file changed, 1 insertion(+), 23 deletions(-) diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 424ef470223d..ba2b485a03ed 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -879,16 +879,6 @@ static struct cpuidle_state adl_l_cstates[] __initdata = { .enter = NULL } }; -/* - * On Sapphire Rapids Xeon C1 has to be disabled if C1E is enabled, and vice - * versa. On SPR C1E is enabled only if "C1E promotion" bit is set in - * MSR_IA32_POWER_CTL. But in this case there effectively no C1, because C1 - * requests are promoted to C1E. If the "C1E promotion" bit is cleared, then - * both C1 and C1E requests end up with C1, so there is effectively no C1E. - * - * By default we enable C1 and disable C1E by marking it with - * 'CPUIDLE_FLAG_UNUSABLE'. - */ static struct cpuidle_state spr_cstates[] __initdata = { { .name = "C1", @@ -901,8 +891,7 @@ static struct cpuidle_state spr_cstates[] __initdata = { { .name = "C1E", .desc = "MWAIT 0x01", - .flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE | - CPUIDLE_FLAG_UNUSABLE, + .flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE, .exit_latency = 2, .target_residency = 4, .enter = &intel_idle, @@ -1724,17 +1713,6 @@ static void __init spr_idle_state_table_update(void) { unsigned long long msr; - /* Check if user prefers C1E over C1. */ - if ((preferred_states_mask & BIT(2)) && - !(preferred_states_mask & BIT(1))) { - /* Disable C1 and enable C1E. */ - spr_cstates[0].flags |= CPUIDLE_FLAG_UNUSABLE; - spr_cstates[1].flags &= ~CPUIDLE_FLAG_UNUSABLE; - - /* Enable C1E using the "C1E promotion" bit. */ - c1e_promotion = C1E_PROMOTION_ENABLE; - } - /* * By default, the C6 state assumes the worst-case scenario of package * C6. However, if PC6 is disabled, we update the numbers to match From 8386c414e27caba8501119948e9551e52b527f59 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Fri, 15 Jul 2022 14:49:58 +0900 Subject: [PATCH 25/27] PM: hibernate: defer device probing when resuming from hibernation syzbot is reporting hung task at misc_open() [1], for there is a race window of AB-BA deadlock which involves probe_count variable. Currently wait_for_device_probe() from snapshot_open() from misc_open() can sleep forever with misc_mtx held if probe_count cannot become 0. When a device is probed by hub_event() work function, probe_count is incremented before the probe function starts, and probe_count is decremented after the probe function completed. There are three cases that can prevent probe_count from dropping to 0. (a) A device being probed stopped responding (i.e. broken/malicious hardware). (b) A process emulating a USB device using /dev/raw-gadget interface stopped responding for some reason. (c) New device probe requests keeps coming in before existing device probe requests complete. The phenomenon syzbot is reporting is (b). A process which is holding system_transition_mutex and misc_mtx is waiting for probe_count to become 0 inside wait_for_device_probe(), but the probe function which is called from hub_event() work function is waiting for the processes which are blocked at mutex_lock(&misc_mtx) to respond via /dev/raw-gadget interface. This patch mitigates (b) by deferring wait_for_device_probe() from snapshot_open() to snapshot_write() and snapshot_ioctl(). Please note that the possibility of (b) remains as long as any thread which is emulating a USB device via /dev/raw-gadget interface can be blocked by uninterruptible blocking operations (e.g. mutex_lock()). Please also note that (a) and (c) are not addressed. Regarding (c), we should change the code to wait for only one device which contains the image for resuming from hibernation. I don't know how to address (a), for use of timeout for wait_for_device_probe() might result in loss of user data in the image. Maybe we should require the userland to wait for the image device before opening /dev/snapshot interface. Link: https://syzkaller.appspot.com/bug?extid=358c9ab4c93da7b7238c [1] Reported-by: syzbot Signed-off-by: Tetsuo Handa Tested-by: syzbot Signed-off-by: Rafael J. Wysocki --- kernel/power/user.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/kernel/power/user.c b/kernel/power/user.c index ad241b4ff64c..d43c2aa583b2 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -26,6 +26,7 @@ #include "power.h" +static bool need_wait; static struct snapshot_data { struct snapshot_handle handle; @@ -78,7 +79,7 @@ static int snapshot_open(struct inode *inode, struct file *filp) * Resuming. We may need to wait for the image device to * appear. */ - wait_for_device_probe(); + need_wait = true; data->swap = -1; data->mode = O_WRONLY; @@ -168,6 +169,11 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf, ssize_t res; loff_t pg_offp = *offp & ~PAGE_MASK; + if (need_wait) { + wait_for_device_probe(); + need_wait = false; + } + lock_system_sleep(); data = filp->private_data; @@ -244,6 +250,11 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, loff_t size; sector_t offset; + if (need_wait) { + wait_for_device_probe(); + need_wait = false; + } + if (_IOC_TYPE(cmd) != SNAPSHOT_IOC_MAGIC) return -ENOTTY; if (_IOC_NR(cmd) > SNAPSHOT_IOC_MAXNR) From 8d36694245f2aec17f03a5e0b2797953d2e36704 Mon Sep 17 00:00:00 2001 From: Shivnandan Kumar Date: Fri, 15 Jul 2022 17:55:39 +0530 Subject: [PATCH 26/27] PM: QoS: Add check to make sure CPU freq is non-negative CPU frequency should never be negative. If some client driver calls freq_qos_update_request with a negative value which will be very high in absolute terms, then frequency QoS sets max CPU freq at fmax as it considers it's absolute value but it will add plist node with negative priority. plist node has priority from INT_MIN (highest) to INT_MAX(lowest). Once priority is set as negative, another client will not be able to reduce CPU frequency. Adding check to make sure CPU freq is non-negative will fix this problem. Signed-off-by: Shivnandan Kumar [ rjw: Changelog edits ] Signed-off-by: Rafael J. Wysocki --- kernel/power/qos.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/power/qos.c b/kernel/power/qos.c index ec7e1e85923e..af51ed6d45ef 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -531,7 +531,7 @@ int freq_qos_add_request(struct freq_constraints *qos, { int ret; - if (IS_ERR_OR_NULL(qos) || !req) + if (IS_ERR_OR_NULL(qos) || !req || value < 0) return -EINVAL; if (WARN(freq_qos_request_active(req), @@ -563,7 +563,7 @@ EXPORT_SYMBOL_GPL(freq_qos_add_request); */ int freq_qos_update_request(struct freq_qos_request *req, s32 new_value) { - if (!req) + if (!req || new_value < 0) return -EINVAL; if (WARN(!freq_qos_request_active(req), From b08b95cf30f53b674bdef510d4cfd0623199b036 Mon Sep 17 00:00:00 2001 From: Sumeet Pawnikar Date: Tue, 26 Jul 2022 18:32:29 +0530 Subject: [PATCH 27/27] powercap: RAPL: Add Power Limit4 support for Alder Lake-N and Raptor Lake-P Add Alder Lake-N and Raptor Lake-P to the list of processor models for which Power Limit4 is supported by the Intel RAPL driver. Signed-off-by: Sumeet Pawnikar Reviewed-by: Srinivas Pandruvada Reviewed-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- drivers/powercap/intel_rapl_msr.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/powercap/intel_rapl_msr.c b/drivers/powercap/intel_rapl_msr.c index 9d23984d8931..bc6adda58883 100644 --- a/drivers/powercap/intel_rapl_msr.c +++ b/drivers/powercap/intel_rapl_msr.c @@ -140,7 +140,9 @@ static const struct x86_cpu_id pl4_support_ids[] = { { X86_VENDOR_INTEL, 6, INTEL_FAM6_TIGERLAKE_L, X86_FEATURE_ANY }, { X86_VENDOR_INTEL, 6, INTEL_FAM6_ALDERLAKE, X86_FEATURE_ANY }, { X86_VENDOR_INTEL, 6, INTEL_FAM6_ALDERLAKE_L, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ALDERLAKE_N, X86_FEATURE_ANY }, { X86_VENDOR_INTEL, 6, INTEL_FAM6_RAPTORLAKE, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_RAPTORLAKE_P, X86_FEATURE_ANY }, {} };