From 025af39b87dc4dc78de4e861ca8b88a1d5ba89f6 Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Tue, 5 Nov 2019 15:08:54 +0100 Subject: genirq: Show irq name in non-oneshot error message Requesting a threaded IRQ with handler=NULL and !ONESHOT fails, but the error message does not include the IRQ line name, which makes it harder to find the offending driver. Print the IRQ line name to clarify where the error comes from. Use the same format as the other pr_err() above in the same function. Signed-off-by: Luca Ceresoli Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20191105140854.27893-1-luca@lucaceresoli.net --- kernel/irq/manage.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/irq/manage.c') diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 1753486b440c..b6c53ab053d2 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1500,8 +1500,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) * has. The type flags are unreliable as the * underlying chip implementation can override them. */ - pr_err("Threaded irq requested with handler=NULL and !ONESHOT for irq %d\n", - irq); + pr_err("Threaded irq requested with handler=NULL and !ONESHOT for %s (irq %d)\n", + new->name, irq); ret = -EINVAL; goto out_unlock; } -- cgit From 11ea68f553e244851d15793a7fa33a97c46d8271 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 20 Jan 2020 17:16:25 +0800 Subject: genirq, sched/isolation: Isolate from handling managed interrupts The affinity of managed interrupts is completely handled in the kernel and cannot be changed via the /proc/irq/* interfaces from user space. As the kernel tries to spread out interrupts evenly accross CPUs on x86 to prevent vector exhaustion, it can happen that a managed interrupt whose affinity mask contains both isolated and housekeeping CPUs is routed to an isolated CPU. As a consequence IO submitted on a housekeeping CPU causes interrupts on the isolated CPU. Add a new sub-parameter 'managed_irq' for 'isolcpus' and the corresponding logic in the interrupt affinity selection code. The subparameter indicates to the interrupt affinity selection logic that it should try to avoid the above scenario. This isolation is best effort and only effective if the automatically assigned interrupt mask of a device queue contains isolated and housekeeping CPUs. If housekeeping CPUs are online then such interrupts are directed to the housekeeping CPU so that IO submitted on the housekeeping CPU cannot disturb the isolated CPU. If a queue's affinity mask contains only isolated CPUs then this parameter has no effect on the interrupt routing decision, though interrupts are only happening when tasks running on those isolated CPUs submit IO. IO submitted on housekeeping CPUs has no influence on those queues. If the affinity mask contains both housekeeping and isolated CPUs, but none of the contained housekeeping CPUs is online, then the interrupt is also routed to an isolated CPU. Interrupts are only delivered when one of the isolated CPUs in the affinity mask submits IO. If one of the contained housekeeping CPUs comes online, the CPU hotplug logic migrates the interrupt automatically back to the upcoming housekeeping CPU. Depending on the type of interrupt controller, this can require that at least one interrupt is delivered to the isolated CPU in order to complete the migration. [ tglx: Removed unused parameter, added and edited comments/documentation and rephrased the changelog so it contains more details. ] Signed-off-by: Ming Lei Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20200120091625.17912-1-ming.lei@redhat.com --- Documentation/admin-guide/kernel-parameters.txt | 26 ++++++++++++++-- include/linux/sched/isolation.h | 1 + kernel/irq/cpuhotplug.c | 21 +++++++++++-- kernel/irq/manage.c | 41 ++++++++++++++++++++++++- kernel/sched/isolation.c | 6 ++++ 5 files changed, 90 insertions(+), 5 deletions(-) (limited to 'kernel/irq/manage.c') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index ade4e6ec23e0..765e4274ba71 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1933,9 +1933,31 @@ begins at 0 and the maximum value is "number of CPUs in system - 1". - The format of is described above. - + managed_irq + + Isolate from being targeted by managed interrupts + which have an interrupt mask containing isolated + CPUs. The affinity of managed interrupts is + handled by the kernel and cannot be changed via + the /proc/irq/* interfaces. + + This isolation is best effort and only effective + if the automatically assigned interrupt mask of a + device queue contains isolated and housekeeping + CPUs. If housekeeping CPUs are online then such + interrupts are directed to the housekeeping CPU + so that IO submitted on the housekeeping CPU + cannot disturb the isolated CPU. + + If a queue's affinity mask contains only isolated + CPUs then this parameter has no effect on the + interrupt routing decision, though interrupts are + only delivered when tasks running on those + isolated CPUs submit IO. IO submitted on + housekeeping CPUs has no influence on those + queues. + The format of is described above. iucv= [HW,NET] diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 6c8512d3be88..0fbcbacd1b29 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -13,6 +13,7 @@ enum hk_flags { HK_FLAG_TICK = (1 << 4), HK_FLAG_DOMAIN = (1 << 5), HK_FLAG_WQ = (1 << 6), + HK_FLAG_MANAGED_IRQ = (1 << 7), }; #ifdef CONFIG_CPU_ISOLATION diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c index 6c7ca2e983a5..02236b13b359 100644 --- a/kernel/irq/cpuhotplug.c +++ b/kernel/irq/cpuhotplug.c @@ -12,6 +12,7 @@ #include #include #include +#include #include "internals.h" @@ -171,6 +172,20 @@ void irq_migrate_all_off_this_cpu(void) } } +static bool hk_should_isolate(struct irq_data *data, unsigned int cpu) +{ + const struct cpumask *hk_mask; + + if (!housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) + return false; + + hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ); + if (cpumask_subset(irq_data_get_effective_affinity_mask(data), hk_mask)) + return false; + + return cpumask_test_cpu(cpu, hk_mask); +} + static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu) { struct irq_data *data = irq_desc_get_irq_data(desc); @@ -188,9 +203,11 @@ static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu) /* * If the interrupt can only be directed to a single target * CPU then it is already assigned to a CPU in the affinity - * mask. No point in trying to move it around. + * mask. No point in trying to move it around unless the + * isolation mechanism requests to move it to an upcoming + * housekeeping CPU. */ - if (!irqd_is_single_target(data)) + if (!irqd_is_single_target(data) || hk_should_isolate(data, cpu)) irq_set_affinity_locked(data, affinity, false); } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index b6c53ab053d2..818b2802d3e7 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -217,7 +218,45 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, if (!chip || !chip->irq_set_affinity) return -EINVAL; - ret = chip->irq_set_affinity(data, mask, force); + /* + * If this is a managed interrupt and housekeeping is enabled on + * it check whether the requested affinity mask intersects with + * a housekeeping CPU. If so, then remove the isolated CPUs from + * the mask and just keep the housekeeping CPU(s). This prevents + * the affinity setter from routing the interrupt to an isolated + * CPU to avoid that I/O submitted from a housekeeping CPU causes + * interrupts on an isolated one. + * + * If the masks do not intersect or include online CPU(s) then + * keep the requested mask. The isolated target CPUs are only + * receiving interrupts when the I/O operation was submitted + * directly from them. + * + * If all housekeeping CPUs in the affinity mask are offline, the + * interrupt will be migrated by the CPU hotplug code once a + * housekeeping CPU which belongs to the affinity mask comes + * online. + */ + if (irqd_affinity_is_managed(data) && + housekeeping_enabled(HK_FLAG_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); + + 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); + } switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 9fcb2a695a41..008d6ac2342b 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -163,6 +163,12 @@ static int __init housekeeping_isolcpus_setup(char *str) continue; } + if (!strncmp(str, "managed_irq,", 12)) { + str += 12; + flags |= HK_FLAG_MANAGED_IRQ; + continue; + } + pr_warn("isolcpus: Error, unknown flag\n"); return 0; } -- cgit From f9f21cea311340f38074ff93a8d89b4a9cae6bcc Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Thu, 6 Feb 2020 11:15:21 -0800 Subject: genirq: Clarify that irq wake state is orthogonal to enable/disable There's some confusion around if an irq that's disabled with disable_irq() can still wake the system from sleep states such as "suspend to RAM". Clarify this in the kernel documentation for irq_set_irq_wake() so that it's clear that an irq can be disabled and still wake the system if it has been marked for wakeup. Signed-off-by: Stephen Boyd Signed-off-by: Thomas Gleixner Reviewed-by: Douglas Anderson Link: https://lkml.kernel.org/r/20200206191521.94559-1-swboyd@chromium.org --- kernel/irq/manage.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'kernel/irq/manage.c') diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 818b2802d3e7..3089a60ea8f9 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -731,6 +731,13 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on) * * Wakeup mode lets this IRQ wake the system from sleep * states like "suspend to RAM". + * + * Note: irq enable/disable state is completely orthogonal + * to the enable/disable state of irq wake. An irq can be + * disabled with disable_irq() and still wake the system as + * long as the irq has wake enabled. If this does not hold, + * then the underlying irq chip and the related driver need + * to be investigated. */ int irq_set_irq_wake(unsigned int irq, unsigned int on) { -- cgit From cba6437a1854fde5934098ec3bd0ee83af3129f5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 12 Feb 2020 12:19:41 +0100 Subject: genirq/proc: Reject invalid affinity masks (again) Qian Cai reported that the WARN_ON() in the x86/msi affinity setting code, which catches cases where the affinity setting is not done on the CPU which is the current target of the interrupt, triggers during CPU hotplug stress testing. It turns out that the warning which was added with the commit addressing the MSI affinity race unearthed yet another long standing bug. If user space writes a bogus affinity mask, i.e. it contains no online CPUs, then it calls irq_select_affinity_usr(). This was introduced for ALPHA in eee45269b0f5 ("[PATCH] Alpha: convert to generic irq framework (generic part)") and subsequently made available for all architectures in 18404756765c ("genirq: Expose default irq affinity mask (take 3)") which introduced the circumvention of the affinity setting restrictions for interrupt which cannot be moved in process context. The whole exercise is bogus in various aspects: 1) If the interrupt is already started up then there is absolutely no point to honour a bogus interrupt affinity setting from user space. The interrupt is already assigned to an online CPU and it does not make any sense to reassign it to some other randomly chosen online CPU. 2) If the interupt is not yet started up then there is no point either. A subsequent startup of the interrupt will invoke irq_setup_affinity() anyway which will chose a valid target CPU. So the only correct solution is to just return -EINVAL in case user space wrote an affinity mask which does not contain any online CPUs, except for ALPHA which has it's own magic sauce for this. Fixes: 18404756765c ("genirq: Expose default irq affinity mask (take 3)") Reported-by: Qian Cai Signed-off-by: Thomas Gleixner Tested-by: Qian Cai Link: https://lkml.kernel.org/r/878sl8xdbm.fsf@nanos.tec.linutronix.de --- kernel/irq/internals.h | 2 -- kernel/irq/manage.c | 18 ++---------------- kernel/irq/proc.c | 22 ++++++++++++++++++++++ 3 files changed, 24 insertions(+), 18 deletions(-) (limited to 'kernel/irq/manage.c') diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 3924fbe829d4..c9d8eb7f5c02 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -128,8 +128,6 @@ static inline void unregister_handler_proc(unsigned int irq, extern bool irq_can_set_affinity_usr(unsigned int irq); -extern int irq_select_affinity_usr(unsigned int irq); - extern void irq_set_thread_affinity(struct irq_desc *desc); extern int irq_do_set_affinity(struct irq_data *data, diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 3089a60ea8f9..7eee98c38f25 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -481,23 +481,9 @@ int irq_setup_affinity(struct irq_desc *desc) { return irq_select_affinity(irq_desc_get_irq(desc)); } -#endif +#endif /* CONFIG_AUTO_IRQ_AFFINITY */ +#endif /* CONFIG_SMP */ -/* - * Called when a bogus affinity is set via /proc/irq - */ -int irq_select_affinity_usr(unsigned int irq) -{ - struct irq_desc *desc = irq_to_desc(irq); - unsigned long flags; - int ret; - - raw_spin_lock_irqsave(&desc->lock, flags); - ret = irq_setup_affinity(desc); - raw_spin_unlock_irqrestore(&desc->lock, flags); - return ret; -} -#endif /** * irq_set_vcpu_affinity - Set vcpu affinity for the interrupt diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 9e5783d98033..32c071d7bc03 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -111,6 +111,28 @@ static int irq_affinity_list_proc_show(struct seq_file *m, void *v) return show_irq_affinity(AFFINITY_LIST, m); } +#ifndef CONFIG_AUTO_IRQ_AFFINITY +static inline int irq_select_affinity_usr(unsigned int irq) +{ + /* + * If the interrupt is started up already then this fails. The + * interrupt is assigned to an online CPU already. There is no + * point to move it around randomly. Tell user space that the + * selected mask is bogus. + * + * If not then any change to the affinity is pointless because the + * startup code invokes irq_setup_affinity() which will select + * a online CPU anyway. + */ + return -EINVAL; +} +#else +/* ALPHA magic affinity auto selector. Keep it for historical reasons. */ +static inline int irq_select_affinity_usr(unsigned int irq) +{ + return irq_select_affinity(irq); +} +#endif static ssize_t write_irq_affinity(int type, struct file *file, const char __user *buffer, size_t count, loff_t *pos) -- cgit