From cba6437a1854fde5934098ec3bd0ee83af3129f5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 12 Feb 2020 12:19:41 +0100 Subject: [PATCH 1/2] 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(-) 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) From 2546287c5fb363a0165933ae2181c92f03e701d0 Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Fri, 21 Feb 2020 10:07:25 +0800 Subject: [PATCH 2/2] genirq/irqdomain: Make sure all irq domain flags are distinct This was noticed when printing debugfs for MSIs on my ARM64 server. The new dstate IRQD_MSI_NOMASK_QUIRK came out surprisingly while it should only be the x86 stuff for the time being... The new MSI quirk flag uses the same bit as IRQ_DOMAIN_NAME_ALLOCATED which is oddly defined as bit 6 for no good reason. Switch it to the non used bit 1. Fixes: 6f1a4891a592 ("x86/apic/msi: Plug non-maskable MSI affinity race") Signed-off-by: Zenghui Yu Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20200221020725.2038-1-yuzenghui@huawei.com --- include/linux/irqdomain.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index b2d47571ab67..8d062e86d954 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -192,7 +192,7 @@ enum { IRQ_DOMAIN_FLAG_HIERARCHY = (1 << 0), /* Irq domain name was allocated in __irq_domain_add() */ - IRQ_DOMAIN_NAME_ALLOCATED = (1 << 6), + IRQ_DOMAIN_NAME_ALLOCATED = (1 << 1), /* Irq domain is an IPI domain with virq per cpu */ IRQ_DOMAIN_FLAG_IPI_PER_CPU = (1 << 2),