From fe13889c390e14205e064d7e159e61eb5da4b1c3 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Fri, 28 Jan 2022 19:07:27 +0800 Subject: genirq, softirq: Use in_hardirq() instead of in_irq() Replace the obsolete and ambiguos macro in_irq() with the new macro in_hardirq(). Signed-off-by: Changbin Du Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220128110727.5110-1-changbin.du@gmail.com --- kernel/irq/irqdesc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 2267e6527db3..6167d32e27da 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -640,7 +640,7 @@ int handle_irq_desc(struct irq_desc *desc) return -EINVAL; data = irq_desc_get_irq_data(desc); - if (WARN_ON_ONCE(!in_irq() && handle_enforce_irqctx(data))) + if (WARN_ON_ONCE(!in_hardirq() && handle_enforce_irqctx(data))) return -EPERM; generic_handle_irq_desc(desc); @@ -676,7 +676,7 @@ EXPORT_SYMBOL_GPL(generic_handle_irq); */ int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq) { - WARN_ON_ONCE(!in_irq()); + WARN_ON_ONCE(!in_hardirq()); return handle_irq_desc(irq_resolve_mapping(domain, hwirq)); } EXPORT_SYMBOL_GPL(generic_handle_domain_irq); -- cgit v1.2.3 From 1f8863bfb5ca500ea1c7669b16b1931ba27fce20 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 1 Feb 2022 12:02:59 +0000 Subject: genirq: Allow the PM device to originate from irq domain As a preparation to moving the reference to the device used for runtime power management, add a new 'dev' field to the irqdomain structure for that exact purpose. The irq_chip_pm_{get,put}() helpers are made aware of the dual location via a new private helper. No functional change intended. Signed-off-by: Marc Zyngier Reviewed-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Tested-by: Tony Lindgren Acked-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20220201120310.878267-2-maz@kernel.org --- kernel/irq/chip.c | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index c09324663088..a2a12cdbe872 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1558,6 +1558,17 @@ int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) return 0; } +static struct device *irq_get_parent_device(struct irq_data *data) +{ + if (data->chip->parent_device) + return data->chip->parent_device; + + if (data->domain) + return data->domain->dev; + + return NULL; +} + /** * irq_chip_pm_get - Enable power for an IRQ chip * @data: Pointer to interrupt specific data @@ -1567,12 +1578,13 @@ int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) */ int irq_chip_pm_get(struct irq_data *data) { + struct device *dev = irq_get_parent_device(data); int retval; - if (IS_ENABLED(CONFIG_PM) && data->chip->parent_device) { - retval = pm_runtime_get_sync(data->chip->parent_device); + if (IS_ENABLED(CONFIG_PM) && dev) { + retval = pm_runtime_get_sync(dev); if (retval < 0) { - pm_runtime_put_noidle(data->chip->parent_device); + pm_runtime_put_noidle(dev); return retval; } } @@ -1590,10 +1602,11 @@ int irq_chip_pm_get(struct irq_data *data) */ int irq_chip_pm_put(struct irq_data *data) { + struct device *dev = irq_get_parent_device(data); int retval = 0; - if (IS_ENABLED(CONFIG_PM) && data->chip->parent_device) - retval = pm_runtime_put(data->chip->parent_device); + if (IS_ENABLED(CONFIG_PM) && dev) + retval = pm_runtime_put(dev); return (retval < 0) ? retval : 0; } -- cgit v1.2.3 From beb0622138cd2848dec06b0651a988c39d099574 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 1 Feb 2022 12:03:10 +0000 Subject: genirq: Kill irq_chip::parent_device Now that noone is using irq_chip::parent_device in the tree, get rid of it. Signed-off-by: Marc Zyngier Acked-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20220201120310.878267-13-maz@kernel.org --- kernel/irq/chip.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index a2a12cdbe872..24b6f2b40e5e 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1560,9 +1560,6 @@ int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) static struct device *irq_get_parent_device(struct irq_data *data) { - if (data->chip->parent_device) - return data->chip->parent_device; - if (data->domain) return data->domain->dev; -- cgit v1.2.3 From 45ec846c1cd11835a29c85645065115dd791aa45 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 9 Feb 2022 16:25:58 +0000 Subject: irqdomain: Let irq_domain_set_{info,hwirq_and_chip} take a const irq_chip In order to let a const irqchip be fed to the irqchip layer, adjust the various prototypes. An extra cast in irq_domain_set_hwirq_and_chip() is required to avoid a warning. Signed-off-by: Marc Zyngier Acked-by: Linus Walleij Link: https://lore.kernel.org/r/20220209162607.1118325-2-maz@kernel.org --- kernel/irq/irqdomain.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index bf38c546aa25..d5ce96510549 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -1319,7 +1319,8 @@ EXPORT_SYMBOL_GPL(irq_domain_get_irq_data); * @chip_data: The associated chip data */ int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq, struct irq_chip *chip, + irq_hw_number_t hwirq, + const struct irq_chip *chip, void *chip_data) { struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq); @@ -1328,7 +1329,7 @@ int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq, return -ENOENT; irq_data->hwirq = hwirq; - irq_data->chip = chip ? chip : &no_irq_chip; + irq_data->chip = (struct irq_chip *)(chip ? chip : &no_irq_chip); irq_data->chip_data = chip_data; return 0; @@ -1347,7 +1348,7 @@ EXPORT_SYMBOL_GPL(irq_domain_set_hwirq_and_chip); * @handler_name: The interrupt handler name */ void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq, struct irq_chip *chip, + irq_hw_number_t hwirq, const struct irq_chip *chip, void *chip_data, irq_flow_handler_t handler, void *handler_data, const char *handler_name) { @@ -1853,7 +1854,7 @@ EXPORT_SYMBOL_GPL(irq_domain_get_irq_data); * @handler_name: The interrupt handler name */ void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq, struct irq_chip *chip, + irq_hw_number_t hwirq, const struct irq_chip *chip, void *chip_data, irq_flow_handler_t handler, void *handler_data, const char *handler_name) { -- cgit v1.2.3 From 393e1280f765661cf39785e967676a4e57324126 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 9 Feb 2022 16:25:59 +0000 Subject: genirq: Allow irq_chip registration functions to take a const irq_chip In order to let a const irqchip be fed to the irqchip layer, adjust the various prototypes. An extra cast in irq_set_chip()() is required to avoid a warning. Signed-off-by: Marc Zyngier Acked-by: Linus Walleij Link: https://lore.kernel.org/r/20220209162607.1118325-3-maz@kernel.org --- kernel/irq/chip.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 24b6f2b40e5e..54af0deb239b 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -38,7 +38,7 @@ struct irqaction chained_action = { * @irq: irq number * @chip: pointer to irq chip description structure */ -int irq_set_chip(unsigned int irq, struct irq_chip *chip) +int irq_set_chip(unsigned int irq, const struct irq_chip *chip) { unsigned long flags; struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); @@ -46,10 +46,7 @@ int irq_set_chip(unsigned int irq, struct irq_chip *chip) if (!desc) return -EINVAL; - if (!chip) - chip = &no_irq_chip; - - desc->irq_data.chip = chip; + desc->irq_data.chip = (struct irq_chip *)(chip ?: &no_irq_chip); irq_put_desc_unlock(desc, flags); /* * For !CONFIG_SPARSE_IRQ make the irq show up in @@ -1073,7 +1070,7 @@ irq_set_chained_handler_and_data(unsigned int irq, irq_flow_handler_t handle, EXPORT_SYMBOL_GPL(irq_set_chained_handler_and_data); void -irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip, +irq_set_chip_and_handler_name(unsigned int irq, const struct irq_chip *chip, irq_flow_handler_t handle, const char *name) { irq_set_chip(irq, chip); -- cgit v1.2.3 From 0a25cb5544f4f01d2e7c06164555fd9cd6eb64fd Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 10 Feb 2022 09:27:21 +0000 Subject: genirq/debugfs: Use irq_print_chip() when provided by irqchip Since irqchips have the option to implement irq_print_chip, use this when available to output the irqchip name in debugfs. Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220215112154.1360040-1-maz@kernel.org --- kernel/irq/debugfs.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index e4cff358b437..2b43f5f5033d 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -69,8 +69,12 @@ irq_debug_show_chip(struct seq_file *m, struct irq_data *data, int ind) seq_printf(m, "chip: None\n"); return; } - seq_printf(m, "%*schip: %s\n", ind, "", chip->name); - seq_printf(m, "%*sflags: 0x%lx\n", ind + 1, "", chip->flags); + seq_printf(m, "%*schip: ", ind, ""); + if (chip->irq_print_chip) + chip->irq_print_chip(data, m); + else + seq_printf(m, "%s", chip->name); + seq_printf(m, "\n%*sflags: 0x%lx\n", ind + 1, "", chip->flags); irq_debug_show_bits(m, ind, chip->flags, irqchip_flags, ARRAY_SIZE(irqchip_flags)); } -- cgit v1.2.3 From 04d4e665a60902cf36e7ad39af1179cb5df542ad Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 7 Feb 2022 16:59:06 +0100 Subject: sched/isolation: Use single feature type while referring to housekeeping cpumask Refer to housekeeping APIs using single feature types instead of flags. This prevents from passing multiple isolation features at once to housekeeping interfaces, which soon won't be possible anymore as each isolation features will have their own cpumask. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Juri Lelli Reviewed-by: Phil Auld Link: https://lore.kernel.org/r/20220207155910.527133-5-frederic@kernel.org --- kernel/irq/cpuhotplug.c | 4 ++-- kernel/irq/manage.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c index 39a41c56ad4f..1ed2b1739363 100644 --- a/kernel/irq/cpuhotplug.c +++ b/kernel/irq/cpuhotplug.c @@ -176,10 +176,10 @@ static bool hk_should_isolate(struct irq_data *data, unsigned int cpu) { const struct cpumask *hk_mask; - if (!housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) + if (!housekeeping_enabled(HK_TYPE_MANAGED_IRQ)) return false; - hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ); + hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ); if (cpumask_subset(irq_data_get_effective_affinity_mask(data), hk_mask)) return false; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index f23ffd30385b..c03f71d5ec10 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -247,13 +247,13 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, * online. */ if (irqd_affinity_is_managed(data) && - housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) { + housekeeping_enabled(HK_TYPE_MANAGED_IRQ)) { const struct cpumask *hk_mask, *prog_mask; static DEFINE_RAW_SPINLOCK(tmp_mask_lock); static struct cpumask tmp_mask; - hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ); + hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ); raw_spin_lock(&tmp_mask_lock); cpumask_and(&tmp_mask, mask, hk_mask); -- cgit v1.2.3 From 509853f9e1e7b1490dc79f735a5dbafc9298f40d Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 11 Feb 2022 19:14:54 +0100 Subject: genirq: Provide generic_handle_irq_safe() Provide generic_handle_irq_safe() which can used from any context. Suggested-by: Thomas Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Reviewed-by: Hans de Goede Reviewed-by: Oleksandr Natalenko Reviewed-by: Wolfram Sang Link: https://lore.kernel.org/r/20220211181500.1856198-2-bigeasy@linutronix.de --- kernel/irq/irqdesc.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'kernel/irq') diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 2267e6527db3..346d283d2da1 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -662,6 +662,29 @@ int generic_handle_irq(unsigned int irq) } EXPORT_SYMBOL_GPL(generic_handle_irq); +/** + * generic_handle_irq_safe - Invoke the handler for a particular irq from any + * context. + * @irq: The irq number to handle + * + * Returns: 0 on success, a negative value on error. + * + * This function can be called from any context (IRQ or process context). It + * will report an error if not invoked from IRQ context and the irq has been + * marked to enforce IRQ-context only. + */ +int generic_handle_irq_safe(unsigned int irq) +{ + unsigned long flags; + int ret; + + local_irq_save(flags); + ret = handle_irq_desc(irq_to_desc(irq)); + local_irq_restore(flags); + return ret; +} +EXPORT_SYMBOL_GPL(generic_handle_irq_safe); + #ifdef CONFIG_IRQ_DOMAIN /** * generic_handle_domain_irq - Invoke the handler for a HW irq belonging -- cgit v1.2.3 From d802057c7c553ad426520a053da9f9fe08e2c35a Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 5 Apr 2022 19:50:38 +0100 Subject: genirq/msi: Shutdown managed interrupts with unsatifiable affinities When booting with maxcpus=, interrupt controllers such as the GICv3 ITS may not be able to satisfy the affinity of some managed interrupts, as some of the HW resources are simply not available. The same thing happens when loading a driver using managed interrupts while CPUs are offline. In order to deal with this, do not try to activate such interrupt if there is no online CPU capable of handling it. Instead, place it in shutdown state. Once a capable CPU shows up, it will be activated. Reported-by: John Garry Reported-by: David Decotigny Signed-off-by: Marc Zyngier Signed-off-by: Thomas Gleixner Tested-by: John Garry Link: https://lore.kernel.org/r/20220405185040.206297-2-maz@kernel.org --- kernel/irq/msi.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'kernel/irq') diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 2bdfce5edafd..a9ee535293eb 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -818,6 +818,21 @@ static int msi_init_virq(struct irq_domain *domain, int virq, unsigned int vflag irqd_clr_can_reserve(irqd); if (vflags & VIRQ_NOMASK_QUIRK) irqd_set_msi_nomask_quirk(irqd); + + /* + * If the interrupt is managed but no CPU is available to + * service it, shut it down until better times. Note that + * we only do this on the !RESERVE path as x86 (the only + * architecture using this flag) deals with this in a + * different way by using a catch-all vector. + */ + if ((vflags & VIRQ_ACTIVATE) && + irqd_affinity_is_managed(irqd) && + !cpumask_intersects(irq_data_get_affinity_mask(irqd), + cpu_online_mask)) { + irqd_set_managed_shutdown(irqd); + return 0; + } } if (!(vflags & VIRQ_ACTIVATE)) -- cgit v1.2.3 From 33de0aa4bae982ed6f7c777f86b5af3e627ac937 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 5 Apr 2022 19:50:39 +0100 Subject: genirq: Always limit the affinity to online CPUs When booting with maxcpus= (or even loading a driver while most CPUs are offline), it is pretty easy to observe managed affinities containing a mix of online and offline CPUs being passed to the irqchip driver. This means that the irqchip cannot trust the affinity passed down from the core code, which is a bit annoying and requires (at least in theory) all drivers to implement some sort of affinity narrowing. In order to address this, always limit the cpumask to the set of online CPUs. Signed-off-by: Marc Zyngier Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220405185040.206297-3-maz@kernel.org --- kernel/irq/manage.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index c03f71d5ec10..f71ecc100545 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -222,11 +222,16 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, { struct irq_desc *desc = irq_data_to_desc(data); struct irq_chip *chip = irq_data_get_irq_chip(data); + const struct cpumask *prog_mask; int ret; + static DEFINE_RAW_SPINLOCK(tmp_mask_lock); + static struct cpumask tmp_mask; + if (!chip || !chip->irq_set_affinity) return -EINVAL; + raw_spin_lock(&tmp_mask_lock); /* * If this is a managed interrupt and housekeeping is enabled on * it check whether the requested affinity mask intersects with @@ -248,24 +253,28 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, */ if (irqd_affinity_is_managed(data) && housekeeping_enabled(HK_TYPE_MANAGED_IRQ)) { - const struct cpumask *hk_mask, *prog_mask; - - static DEFINE_RAW_SPINLOCK(tmp_mask_lock); - static struct cpumask tmp_mask; + const struct cpumask *hk_mask; hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ); - raw_spin_lock(&tmp_mask_lock); cpumask_and(&tmp_mask, mask, hk_mask); if (!cpumask_intersects(&tmp_mask, cpu_online_mask)) prog_mask = mask; else prog_mask = &tmp_mask; - ret = chip->irq_set_affinity(data, prog_mask, force); - raw_spin_unlock(&tmp_mask_lock); } else { - ret = chip->irq_set_affinity(data, mask, force); + prog_mask = mask; } + + /* Make sure we only provide online CPUs to the irqchip */ + cpumask_and(&tmp_mask, prog_mask, cpu_online_mask); + if (!cpumask_empty(&tmp_mask)) + ret = chip->irq_set_affinity(data, &tmp_mask, force); + else + ret = -EINVAL; + + raw_spin_unlock(&tmp_mask_lock); + switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: -- cgit v1.2.3 From 911488de0565f1d53bd36174d20917ebc4b44c0e Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 10 Feb 2022 14:49:05 -0800 Subject: genirq/affinity: Replace cpumask_weight() with cpumask_empty() where appropriate __irq_build_affinity_masks() calls cpumask_weight() to check if any bit of a given cpumask is set. This can be done more efficiently with cpumask_empty() because cpumask_empty() stops traversing the cpumask as soon as it finds first set bit, while cpumask_weight() counts all bits unconditionally. Signed-off-by: Yury Norov Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220210224933.379149-22-yury.norov@gmail.com --- kernel/irq/affinity.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/irq') diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index f7ff8919dc9b..18740faf0eb1 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -258,7 +258,7 @@ static int __irq_build_affinity_masks(unsigned int startvec, nodemask_t nodemsk = NODE_MASK_NONE; struct node_vectors *node_vectors; - if (!cpumask_weight(cpu_mask)) + if (cpumask_empty(cpu_mask)) return 0; nodes = get_nodes_in_cpumask(node_to_cpumask, cpu_mask, &nodemsk); -- cgit v1.2.3 From 08d835dff916bfe8f45acc7b92c7af6c4081c8a7 Mon Sep 17 00:00:00 2001 From: Rei Yamamoto Date: Thu, 31 Mar 2022 09:33:09 +0900 Subject: genirq/affinity: Consider that CPUs on nodes can be unbalanced If CPUs on a node are offline at boot time, the number of nodes is different when building affinity masks for present cpus and when building affinity masks for possible cpus. This causes the following problem: In the case that the number of vectors is less than the number of nodes there are cases where bits of masks for present cpus are overwritten when building masks for possible cpus. Fix this by excluding CPUs, which are not part of the current build mask (present/possible). [ tglx: Massaged changelog and added comment ] Fixes: b82592199032 ("genirq/affinity: Spread IRQs to all available NUMA nodes") Signed-off-by: Rei Yamamoto Signed-off-by: Thomas Gleixner Reviewed-by: Ming Lei Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220331003309.10891-1-yamamoto.rei@jp.fujitsu.com --- kernel/irq/affinity.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index f7ff8919dc9b..fdf170404650 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -269,8 +269,9 @@ static int __irq_build_affinity_masks(unsigned int startvec, */ if (numvecs <= nodes) { for_each_node_mask(n, nodemsk) { - cpumask_or(&masks[curvec].mask, &masks[curvec].mask, - node_to_cpumask[n]); + /* Ensure that only CPUs which are in both masks are set */ + cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]); + cpumask_or(&masks[curvec].mask, &masks[curvec].mask, nmsk); if (++curvec == last_affv) curvec = firstvec; } -- cgit v1.2.3 From c48c8b829d2b966a6649827426bcdba082ccf922 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 14 Apr 2022 15:00:11 +0100 Subject: genirq: Take the proposed affinity at face value if force==true Although setting the affinity of an interrupt to a set of CPUs that doesn't have any online CPU is generally frowned apon, there are a few limited cases where such affinity is set from a CPUHP notifier, setting the affinity to a CPU that isn't online yet. The saving grace is that this is always done using the 'force' attribute, which gives a hint that the affinity setting can be outside of the online CPU mask and the callsite set this flag with the knowledge that the underlying interrupt controller knows to handle it. This restores the expected behaviour on Marek's system. Fixes: 33de0aa4bae9 ("genirq: Always limit the affinity to online CPUs") Reported-by: Marek Szyprowski Signed-off-by: Marc Zyngier Signed-off-by: Thomas Gleixner Tested-by: Marek Szyprowski Link: https://lore.kernel.org/r/4b7fc13c-887b-a664-26e8-45aed13f048a@samsung.com Link: https://lore.kernel.org/r/20220414140011.541725-1-maz@kernel.org --- kernel/irq/manage.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index f71ecc100545..f1d5a94c6c9f 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -266,10 +266,16 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, prog_mask = mask; } - /* Make sure we only provide online CPUs to the irqchip */ + /* + * Make sure we only provide online CPUs to the irqchip, + * unless we are being asked to force the affinity (in which + * case we do as we are told). + */ cpumask_and(&tmp_mask, prog_mask, cpu_online_mask); - if (!cpumask_empty(&tmp_mask)) + if (!force && !cpumask_empty(&tmp_mask)) ret = chip->irq_set_affinity(data, &tmp_mask, force); + else if (force) + ret = chip->irq_set_affinity(data, mask, force); else ret = -EINVAL; -- cgit v1.2.3 From 6c846d026d490b2383d395bc8e7b06336219667b Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 19 Apr 2022 15:18:37 +0100 Subject: gpio: Don't fiddle with irqchips marked as immutable In order to move away from gpiolib messing with the internals of unsuspecting irqchips, add a flag by which irqchips advertise that they are not to be messed with, and do solemnly swear that they correctly call into the gpiolib helpers when required. Also nudge the users into converting their drivers to the new model. Reviewed-by: Andy Shevchenko Reviewed-by: Bartosz Golaszewski Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220419141846.598305-2-maz@kernel.org --- kernel/irq/debugfs.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/irq') diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index 2b43f5f5033d..bc8e40cf2b65 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -58,6 +58,7 @@ static const struct irq_bit_descr irqchip_flags[] = { BIT_MASK_DESCR(IRQCHIP_SUPPORTS_LEVEL_MSI), BIT_MASK_DESCR(IRQCHIP_SUPPORTS_NMI), BIT_MASK_DESCR(IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND), + BIT_MASK_DESCR(IRQCHIP_IMMUTABLE), }; static void -- cgit v1.2.3 From 1adb4d7ad3a585b451f5cf6b0a90c5917af3eac5 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 22 Apr 2022 12:04:18 +0100 Subject: genirq/matrix: Remove redundant assignment to variable 'end' Variable end is being initialized with a value that is never read, it is being re-assigned later with the same value. The initialization is redundant and can be removed. Cleans up clang scan build warning: kernel/irq/matrix.c:289:25: warning: Value stored to 'end' during its initialization is never read [deadcode.DeadStores] Signed-off-by: Colin Ian King Signed-off-by: Thomas Gleixner Reviewed-by: Tom Rix Link: https://lore.kernel.org/r/20220422110418.1264778-1-colin.i.king@gmail.com --- kernel/irq/matrix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/irq') diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c index bbfb26489aa1..1698e77645ac 100644 --- a/kernel/irq/matrix.c +++ b/kernel/irq/matrix.c @@ -286,7 +286,7 @@ void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk) int irq_matrix_alloc_managed(struct irq_matrix *m, const struct cpumask *msk, unsigned int *mapped_cpu) { - unsigned int bit, cpu, end = m->alloc_end; + unsigned int bit, cpu, end; struct cpumap *cm; if (cpumask_empty(msk)) -- cgit v1.2.3 From ce4818957fdc5bca57fc2c92b0dfe109d26bcc47 Mon Sep 17 00:00:00 2001 From: Minghao Chi Date: Mon, 18 Apr 2022 11:07:16 +0000 Subject: genirq: Use pm_runtime_resume_and_get() instead of pm_runtime_get_sync() pm_runtime_resume_and_get() achieves the same and simplifies the code. [ tglx: Simplify it further by presetting retval ] Reported-by: Zeal Robot Signed-off-by: Minghao Chi Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220418110716.2559453-1-chi.minghao@zte.com.cn --- kernel/irq/chip.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 54af0deb239b..e6b8e564b37f 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1573,17 +1573,12 @@ static struct device *irq_get_parent_device(struct irq_data *data) int irq_chip_pm_get(struct irq_data *data) { struct device *dev = irq_get_parent_device(data); - int retval; + int retval = 0; - if (IS_ENABLED(CONFIG_PM) && dev) { - retval = pm_runtime_get_sync(dev); - if (retval < 0) { - pm_runtime_put_noidle(dev); - return retval; - } - } + if (IS_ENABLED(CONFIG_PM) && dev) + retval = pm_runtime_resume_and_get(dev); - return 0; + return retval; } /** -- cgit v1.2.3 From 8707898e22fd665bc1d7b18b809be4b56ce25bdd Mon Sep 17 00:00:00 2001 From: Thomas Pfaff Date: Mon, 2 May 2022 13:28:29 +0200 Subject: genirq: Synchronize interrupt thread startup A kernel hang can be observed when running setserial in a loop on a kernel with force threaded interrupts. The sequence of events is: setserial open("/dev/ttyXXX") request_irq() do_stuff() -> serial interrupt -> wake(irq_thread) desc->threads_active++; close() free_irq() kthread_stop(irq_thread) synchronize_irq() <- hangs because desc->threads_active != 0 The thread is created in request_irq() and woken up, but does not get on a CPU to reach the actual thread function, which would handle the pending wake-up. kthread_stop() sets the should stop condition which makes the thread immediately exit, which in turn leaves the stale threads_active count around. This problem was introduced with commit 519cc8652b3a, which addressed a interrupt sharing issue in the PCIe code. Before that commit free_irq() invoked synchronize_irq(), which waits for the hard interrupt handler and also for associated threads to complete. To address the PCIe issue synchronize_irq() was replaced with __synchronize_hardirq(), which only waits for the hard interrupt handler to complete, but not for threaded handlers. This was done under the assumption, that the interrupt thread already reached the thread function and waits for a wake-up, which is guaranteed to be handled before acting on the stop condition. The problematic case, that the thread would not reach the thread function, was obviously overlooked. Make sure that the interrupt thread is really started and reaches thread_fn() before returning from __setup_irq(). This utilizes the existing wait queue in the interrupt descriptor. The wait queue is unused for non-shared interrupts. For shared interrupts the usage might cause a spurious wake-up of a waiter in synchronize_irq() or the completion of a threaded handler might cause a spurious wake-up of the waiter for the ready flag. Both are harmless and have no functional impact. [ tglx: Amended changelog ] Fixes: 519cc8652b3a ("genirq: Synchronize only with single thread on free_irq()") Signed-off-by: Thomas Pfaff Signed-off-by: Thomas Gleixner Reviewed-by: Marc Zyngier Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/552fe7b4-9224-b183-bb87-a8f36d335690@pcs.com --- kernel/irq/internals.h | 2 ++ kernel/irq/irqdesc.c | 2 ++ kernel/irq/manage.c | 39 +++++++++++++++++++++++++++++---------- 3 files changed, 33 insertions(+), 10 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 99cbdf55a8bd..f09c60393e55 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -29,12 +29,14 @@ extern struct irqaction chained_action; * IRQTF_WARNED - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed * IRQTF_AFFINITY - irq thread is requested to adjust affinity * IRQTF_FORCED_THREAD - irq action is force threaded + * IRQTF_READY - signals that irq thread is ready */ enum { IRQTF_RUNTHREAD, IRQTF_WARNED, IRQTF_AFFINITY, IRQTF_FORCED_THREAD, + IRQTF_READY, }; /* diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 939d21cd55c3..0099b87dd853 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -407,6 +407,7 @@ static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags, lockdep_set_class(&desc->lock, &irq_desc_lock_class); mutex_init(&desc->request_mutex); init_rcu_head(&desc->rcu); + init_waitqueue_head(&desc->wait_for_threads); desc_set_defaults(irq, desc, node, affinity, owner); irqd_set(&desc->irq_data, flags); @@ -575,6 +576,7 @@ int __init early_irq_init(void) raw_spin_lock_init(&desc[i].lock); lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); mutex_init(&desc[i].request_mutex); + init_waitqueue_head(&desc[i].wait_for_threads); desc_set_defaults(i, &desc[i], node, NULL, NULL); } return arch_early_irq_init(); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index c03f71d5ec10..e3e245a4fd70 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1248,6 +1248,31 @@ static void irq_wake_secondary(struct irq_desc *desc, struct irqaction *action) raw_spin_unlock_irq(&desc->lock); } +/* + * Internal function to notify that a interrupt thread is ready. + */ +static void irq_thread_set_ready(struct irq_desc *desc, + struct irqaction *action) +{ + set_bit(IRQTF_READY, &action->thread_flags); + wake_up(&desc->wait_for_threads); +} + +/* + * Internal function to wake up a interrupt thread and wait until it is + * ready. + */ +static void wake_up_and_wait_for_irq_thread_ready(struct irq_desc *desc, + struct irqaction *action) +{ + if (!action || !action->thread) + return; + + wake_up_process(action->thread); + wait_event(desc->wait_for_threads, + test_bit(IRQTF_READY, &action->thread_flags)); +} + /* * Interrupt handler thread */ @@ -1259,6 +1284,8 @@ static int irq_thread(void *data) irqreturn_t (*handler_fn)(struct irq_desc *desc, struct irqaction *action); + irq_thread_set_ready(desc, action); + sched_set_fifo(current); if (force_irqthreads() && test_bit(IRQTF_FORCED_THREAD, @@ -1683,8 +1710,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } if (!shared) { - init_waitqueue_head(&desc->wait_for_threads); - /* Setup the type (level, edge polarity) if configured: */ if (new->flags & IRQF_TRIGGER_MASK) { ret = __irq_set_trigger(desc, @@ -1780,14 +1805,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) irq_setup_timings(desc, new); - /* - * Strictly no need to wake it up, but hung_task complains - * when no hard interrupt wakes the thread up. - */ - if (new->thread) - wake_up_process(new->thread); - if (new->secondary) - wake_up_process(new->secondary->thread); + wake_up_and_wait_for_irq_thread_ready(desc, new); + wake_up_and_wait_for_irq_thread_ready(desc, new->secondary); register_irq_proc(irq, desc); new->dir = NULL; -- cgit v1.2.3 From 792ea6a074ae7ea5ab6f1b8b31f76bb0297de66c Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Tue, 10 May 2022 09:56:05 +0200 Subject: genirq: Remove WARN_ON_ONCE() in generic_handle_domain_irq() Since commit 0953fb263714 ("irq: remove handle_domain_{irq,nmi}()"), generic_handle_domain_irq() warns if called outside hardirq context, even though the function calls down to handle_irq_desc(), which warns about the same, but conditionally on handle_enforce_irqctx(). The newly added warning is a false positive if the interrupt originates from any other irqchip than x86 APIC or ARM GIC/GICv3. Those are the only ones for which handle_enforce_irqctx() returns true. Per commit c16816acd086 ("genirq: Add protection against unsafe usage of generic_handle_irq()"): "In general calling generic_handle_irq() with interrupts disabled from non interrupt context is harmless. For some interrupt controllers like the x86 trainwrecks this is outright dangerous as it might corrupt state if an interrupt affinity change is pending." Examples for interrupt chips where the warning is a false positive are USB-attached GPIO controllers such as drivers/gpio/gpio-dln2.c: USB gadgets are incapable of directly signaling an interrupt because they cannot initiate a bus transaction by themselves. All communication on the bus is initiated by the host controller, which polls a gadget's Interrupt Endpoint in regular intervals. If an interrupt is pending, that information is passed up the stack in softirq context, from which a hardirq is synthesized via generic_handle_domain_irq(). Remove the warning to eliminate such false positives. Fixes: 0953fb263714 ("irq: remove handle_domain_{irq,nmi}()") Signed-off-by: Lukas Wunner Signed-off-by: Thomas Gleixner Cc: Marc Zyngier Cc: Mark Rutland Cc: Jakub Kicinski CC: Linus Walleij Cc: Bartosz Golaszewski Cc: Octavian Purdila Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220505113207.487861b2@kernel.org Link: https://lore.kernel.org/r/20220506203242.GA1855@wunner.de Link: https://lore.kernel.org/r/c3caf60bfa78e5fdbdf483096b7174da65d1813a.1652168866.git.lukas@wunner.de --- kernel/irq/irqdesc.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel/irq') diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 0099b87dd853..d323b180b0f3 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -701,7 +701,6 @@ EXPORT_SYMBOL_GPL(generic_handle_irq_safe); */ int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq) { - WARN_ON_ONCE(!in_hardirq()); return handle_irq_desc(irq_resolve_mapping(domain, hwirq)); } EXPORT_SYMBOL_GPL(generic_handle_domain_irq); -- cgit v1.2.3 From 21673fcb2532dcd189905ff5a5389eb7dcd0e57a Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 11 May 2022 13:07:50 +0200 Subject: genirq/irq_sim: Make the irq_work always run in hard irq context The IRQ simulator uses irq_work to trigger an interrupt. Without the IRQ_WORK_HARD_IRQ flag the irq_work will be performed in thread context on PREEMPT_RT. This causes locking errors later in handle_simple_irq() which expects to be invoked with disabled interrupts. Triggering individual interrupts in hardirq context should not lead to unexpected high latencies since this is also what the hardware controller does. Also it is used as a simulator so... Use IRQ_WORK_INIT_HARD() to carry out the irq_work in hardirq context on PREEMPT_RT. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/YnuZBoEVMGwKkLm+@linutronix.de --- kernel/irq/irq_sim.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/irq') diff --git a/kernel/irq/irq_sim.c b/kernel/irq/irq_sim.c index 0cd02efa3a74..dd76323ea3fd 100644 --- a/kernel/irq/irq_sim.c +++ b/kernel/irq/irq_sim.c @@ -181,7 +181,7 @@ struct irq_domain *irq_domain_create_sim(struct fwnode_handle *fwnode, goto err_free_bitmap; work_ctx->irq_count = num_irqs; - init_irq_work(&work_ctx->work, irq_sim_handle_irq); + work_ctx->work = IRQ_WORK_INIT_HARD(irq_sim_handle_irq); return work_ctx->domain; -- cgit v1.2.3 From 668a9fe5c6a1bcac6b65d5e9b91a9eca86f782a3 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 8 Jun 2022 14:45:35 +0100 Subject: genirq: PM: Use runtime PM for chained interrupts When requesting an interrupt, we correctly call into the runtime PM framework to guarantee that the underlying interrupt controller is up and running. However, we fail to do so for chained interrupt controllers, as the mux interrupt is not requested along the same path. Augment __irq_do_set_handler() to call into the runtime PM code in this case, making sure the PM flow is the same for all interrupts. Reported-by: Lucas Stach Tested-by: Liu Ying Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/26973cddee5f527ea17184c0f3fccb70bc8969a0.camel@pengutronix.de --- kernel/irq/chip.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel/irq') diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index e6b8e564b37f..886789dcee43 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1006,8 +1006,10 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, if (desc->irq_data.chip != &no_irq_chip) mask_ack_irq(desc); irq_state_set_disabled(desc); - if (is_chained) + if (is_chained) { desc->action = NULL; + WARN_ON(irq_chip_pm_put(irq_desc_get_irq_data(desc))); + } desc->depth = 1; } desc->handle_irq = handle; @@ -1033,6 +1035,7 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, irq_settings_set_norequest(desc); irq_settings_set_nothread(desc); desc->action = &chained_action; + WARN_ON(irq_chip_pm_get(irq_desc_get_irq_data(desc))); irq_activate_and_startup(desc, IRQ_RESEND); } } -- cgit v1.2.3