From b630a04121519c0f93f9cc8994147191cc3c17b4 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Tue, 23 Jul 2024 07:02:26 -0700 Subject: [PATCH 1/5] thermal: intel: int340x: Fix kernel warning during MSI cleanup On some pre-production Lunar Lake systems, there is a kernel warning: remove_proc_entry: removing non-empty directory 'irq/172' WARNING: CPU: 0 PID: 501 at fs/proc/generic.c:717 remove_proc_entry+0x1b4/0x1e0 ... ... remove_proc_entry+0x1b4/0x1e0 report_bug+0x182/0x1b0 handle_bug+0x51/0xa0 exc_invalid_op+0x18/0x80 asm_exc_invalid_op+0x1b/0x20 remove_proc_entry+0x1b4/0x1e0 remove_proc_entry+0x1b4/0x1e0 unregister_irq_proc+0xf2/0x120 free_desc+0x41/0xe0 irq_domain_free_irqs+0x138/0x1c0 irq_free_descs+0x52/0x80 irq_domain_free_irqs+0x151/0x1c0 msi_domain_free_locked.part.0+0x17e/0x1c0 msi_domain_free_irqs_all_locked+0x74/0xc0 pci_msi_teardown_msi_irqs+0x50/0x60 pci_free_msi_irqs+0x12/0x40 pci_free_irq_vectors+0x58/0x70 On these systems, not all the MSI thermal vectors are valid. This causes devm_request_threaded_irq() to fail for some vectors. As part of the clean up on this error, pci_free_irq_vectors() is called without calling devm_free_irq(). This causes the above warning. Add a function proc_thermal_free_msi() to call devm_free_irq() for all successfully registered IRQ handlers, then call pci_free_irq_vectors(). Call this function for MSI cleanup. Fixes: 7a9a8c5faf41 ("thermal: intel: int340x: Support MSI interrupt for Lunar Lake") Reported-by: Yijun Shen Tested-by: Yijun Shen Signed-off-by: Srinivas Pandruvada Reviewed-by: Zhang Rui Link: https://patch.msgid.link/20240723140228.865919-2-srinivas.pandruvada@linux.intel.com Signed-off-by: Rafael J. Wysocki --- .../processor_thermal_device_pci.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c index 114136893a59..2c9c45eb5b4a 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c @@ -278,6 +278,18 @@ static struct thermal_zone_params tzone_params = { static bool msi_irq; +static void proc_thermal_free_msi(struct pci_dev *pdev, struct proc_thermal_pci *pci_info) +{ + int i; + + for (i = 0; i < MSI_THERMAL_MAX; i++) { + if (proc_thermal_msi_map[i]) + devm_free_irq(&pdev->dev, proc_thermal_msi_map[i], pci_info); + } + + pci_free_irq_vectors(pdev); +} + static int proc_thermal_setup_msi(struct pci_dev *pdev, struct proc_thermal_pci *pci_info) { int ret, i, irq; @@ -310,7 +322,7 @@ static int proc_thermal_setup_msi(struct pci_dev *pdev, struct proc_thermal_pci return 0; err_free_msi_vectors: - pci_free_irq_vectors(pdev); + proc_thermal_free_msi(pdev, pci_info); return ret; } @@ -397,7 +409,7 @@ static int proc_thermal_pci_probe(struct pci_dev *pdev, const struct pci_device_ err_free_vectors: if (msi_irq) - pci_free_irq_vectors(pdev); + proc_thermal_free_msi(pdev, pci_info); err_ret_tzone: thermal_zone_device_unregister(pci_info->tzone); err_del_legacy: From b85a2d300a37641456c238591a056404436675c2 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Tue, 23 Jul 2024 07:02:27 -0700 Subject: [PATCH 2/5] thermal: intel: int340x: Allow limited thermal MSI support On some Lunar Lake pre-production systems, not all the MSI thermal vectors are valid. In that case instead of failing module load, continue with partial thermal interrupt support. pci_alloc_irq_vectors() can return less than expected maximum vectors. In that case call devm_request_threaded_irq() only for current maximum vectors. Fixes: 7a9a8c5faf41 ("thermal: intel: int340x: Support MSI interrupt for Lunar Lake") Reported-by: Yijun Shen Tested-by: Yijun Shen Signed-off-by: Srinivas Pandruvada Reviewed-by: Zhang Rui Link: https://patch.msgid.link/20240723140228.865919-3-srinivas.pandruvada@linux.intel.com Signed-off-by: Rafael J. Wysocki --- .../int340x_thermal/processor_thermal_device_pci.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c index 2c9c45eb5b4a..ff296626c498 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c @@ -292,18 +292,18 @@ static void proc_thermal_free_msi(struct pci_dev *pdev, struct proc_thermal_pci static int proc_thermal_setup_msi(struct pci_dev *pdev, struct proc_thermal_pci *pci_info) { - int ret, i, irq; + int ret, i, irq, count; - ret = pci_alloc_irq_vectors(pdev, 1, MSI_THERMAL_MAX, PCI_IRQ_MSI | PCI_IRQ_MSIX); - if (ret < 0) { + count = pci_alloc_irq_vectors(pdev, 1, MSI_THERMAL_MAX, PCI_IRQ_MSI | PCI_IRQ_MSIX); + if (count < 0) { dev_err(&pdev->dev, "Failed to allocate vectors!\n"); - return ret; + return count; } dev_info(&pdev->dev, "msi enabled:%d msix enabled:%d\n", pdev->msi_enabled, pdev->msix_enabled); - for (i = 0; i < MSI_THERMAL_MAX; i++) { + for (i = 0; i < count; i++) { irq = pci_irq_vector(pdev, i); ret = devm_request_threaded_irq(&pdev->dev, irq, proc_thermal_irq_handler, From f8ce49be2743541bdc9e184fab1cfd736031ab66 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Tue, 23 Jul 2024 07:02:28 -0700 Subject: [PATCH 3/5] thermal: intel: int340x: Free MSI IRQ vectors on module exit On module exit call proc_thermal_free_msi() to free vectors allocated by pci_alloc_irq_vectors(). Fixes: 7a9a8c5faf41 ("thermal: intel: int340x: Support MSI interrupt for Lunar Lake") Signed-off-by: Srinivas Pandruvada Reviewed-by: Zhang Rui Link: https://patch.msgid.link/20240723140228.865919-4-srinivas.pandruvada@linux.intel.com Signed-off-by: Rafael J. Wysocki --- .../intel/int340x_thermal/processor_thermal_device_pci.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c index ff296626c498..006614921870 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c @@ -431,6 +431,9 @@ static void proc_thermal_pci_remove(struct pci_dev *pdev) proc_thermal_mmio_write(pci_info, PROC_THERMAL_MMIO_THRES_0, 0); proc_thermal_mmio_write(pci_info, PROC_THERMAL_MMIO_INT_ENABLE_0, 0); + if (msi_irq) + proc_thermal_free_msi(pdev, pci_info); + thermal_zone_device_unregister(pci_info->tzone); proc_thermal_mmio_remove(pdev, pci_info->proc_priv); if (!pci_info->no_legacy) From f844793f2d374ffb7f2231f4d36cd4bc52f12de0 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 30 Jul 2024 16:41:18 +0200 Subject: [PATCH 4/5] thermal: trip: Avoid skipping trips in thermal_zone_set_trips() Say there are 3 trip points A, B, C sorted in ascending temperature order with no hysteresis. If the zone temerature is exactly equal to B, thermal_zone_set_trips() will set the boundaries to A and C and the hardware will not catch any crossing of B (either way) until either A or C is crossed and the boundaries are changed. To avoid that, use non-strict inequalities when comparing the trip threshold to the zone temperature in thermal_zone_set_trips(). In the example above, it will cause both boundaries to be set to B, which is desirable because an interrupt will trigger when the zone temperature becomes different from B regardless of which way it goes. That will allow a new interval to be set depending on the direction of the zone temperature change. Fixes: 893bae92237d ("thermal: trip: Make thermal_zone_set_trips() use trip thresholds") Signed-off-by: Rafael J. Wysocki Link: https://patch.msgid.link/12509184.O9o76ZdvQC@rjwysocki.net --- drivers/thermal/thermal_trip.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/thermal/thermal_trip.c b/drivers/thermal/thermal_trip.c index c0b679b846b3..06a0554ddc38 100644 --- a/drivers/thermal/thermal_trip.c +++ b/drivers/thermal/thermal_trip.c @@ -88,10 +88,10 @@ void thermal_zone_set_trips(struct thermal_zone_device *tz) return; for_each_trip_desc(tz, td) { - if (td->threshold < tz->temperature && td->threshold > low) + if (td->threshold <= tz->temperature && td->threshold > low) low = td->threshold; - if (td->threshold > tz->temperature && td->threshold < high) + if (td->threshold >= tz->temperature && td->threshold < high) high = td->threshold; } From a09074228977c24c677c10282f506fa11f88eb93 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 1 Aug 2024 18:39:28 +0200 Subject: [PATCH 5/5] thermal: core: Update thermal zone registration documentation The thermal sysfs API document is outdated. One of the problems with it is that is still documents thermal_zone_device_register() which does not exit any more and it does not reflect the current thermal zone operations definition. Replace the thermal_zone_device_register() description in it with a thermal_zone_device_register_with_trips() description, including an update of the thermal zone operations list. Signed-off-by: Rafael J. Wysocki Reviewed-by: Lukasz Luba Link: https://patch.msgid.link/2767845.mvXUDI8C0e@rjwysocki.net --- .../driver-api/thermal/sysfs-api.rst | 65 +++++++++---------- 1 file changed, 30 insertions(+), 35 deletions(-) diff --git a/Documentation/driver-api/thermal/sysfs-api.rst b/Documentation/driver-api/thermal/sysfs-api.rst index 6c1175c6afba..978198f8a18b 100644 --- a/Documentation/driver-api/thermal/sysfs-api.rst +++ b/Documentation/driver-api/thermal/sysfs-api.rst @@ -4,8 +4,6 @@ Generic Thermal Sysfs driver How To Written by Sujith Thomas , Zhang Rui -Updated: 2 January 2008 - Copyright (c) 2008 Intel Corporation @@ -38,23 +36,23 @@ temperature) and throttle appropriate devices. :: - struct thermal_zone_device - *thermal_zone_device_register(char *type, - int trips, int mask, void *devdata, - struct thermal_zone_device_ops *ops, - const struct thermal_zone_params *tzp, - int passive_delay, int polling_delay)) + struct thermal_zone_device * + thermal_zone_device_register_with_trips(const char *type, + const struct thermal_trip *trips, + int num_trips, void *devdata, + const struct thermal_zone_device_ops *ops, + const struct thermal_zone_params *tzp, + unsigned int passive_delay, + unsigned int polling_delay) - This interface function adds a new thermal zone device (sensor) to + This interface function adds a new thermal zone device (sensor) to the /sys/class/thermal folder as `thermal_zone[0-*]`. It tries to bind all the - thermal cooling devices registered at the same time. + thermal cooling devices registered to it at the same time. type: the thermal zone type. trips: - the total number of trip points this thermal zone supports. - mask: - Bit string: If 'n'th bit is set, then trip point 'n' is writable. + the table of trip points for this thermal zone. devdata: device private data ops: @@ -67,32 +65,29 @@ temperature) and throttle appropriate devices. .get_temp: get the current temperature of the thermal zone. .set_trips: - set the trip points window. Whenever the current temperature - is updated, the trip points immediately below and above the - current temperature are found. - .get_mode: - get the current mode (enabled/disabled) of the thermal zone. - - - "enabled" means the kernel thermal management is - enabled. - - "disabled" will prevent kernel thermal driver action - upon trip points so that user applications can take - charge of thermal management. - .set_mode: - set the mode (enabled/disabled) of the thermal zone. - .get_trip_type: - get the type of certain trip point. - .get_trip_temp: - get the temperature above which the certain trip point - will be fired. + set the trip points window. Whenever the current temperature + is updated, the trip points immediately below and above the + current temperature are found. + .change_mode: + change the mode (enabled/disabled) of the thermal zone. + .set_trip_temp: + set the temperature of a given trip point. + .get_crit_temp: + get the critical temperature for this thermal zone. .set_emul_temp: - set the emulation temperature which helps in debugging - different threshold temperature points. + set the emulation temperature which helps in debugging + different threshold temperature points. + .get_trend: + get the trend of most recent zone temperature changes. + .hot: + hot trip point crossing handler. + .critical: + critical trip point crossing handler. tzp: thermal zone platform parameters. passive_delay: - number of milliseconds to wait between polls when - performing passive cooling. + number of milliseconds to wait between polls when performing passive + cooling. polling_delay: number of milliseconds to wait between polls when checking whether trip points have been crossed (0 for interrupt driven systems).