From a899418167264c7bac574b1a0f1b2c26c5b0995a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 5 Jul 2015 17:12:30 +0000 Subject: hotplug: Prevent alloc/free of irq descriptors during cpu up/down When a cpu goes up some architectures (e.g. x86) have to walk the irq space to set up the vector space for the cpu. While this needs extra protection at the architecture level we can avoid a few race conditions by preventing the concurrent allocation/free of irq descriptors and the associated data. When a cpu goes down it moves the interrupts which are targeted to this cpu away by reassigning the affinities. While this happens interrupts can be allocated and freed, which opens a can of race conditions in the code which reassignes the affinities because interrupt descriptors might be freed underneath. Example: CPU1 CPU2 cpu_up/down irq_desc = irq_to_desc(irq); remove_from_radix_tree(desc); raw_spin_lock(&desc->lock); free(desc); We could protect the irq descriptors with RCU, but that would require a full tree change of all accesses to interrupt descriptors. But fortunately these kind of race conditions are rather limited to a few things like cpu hotplug. The normal setup/teardown is very well serialized. So the simpler and obvious solution is: Prevent allocation and freeing of interrupt descriptors accross cpu hotplug. Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra Cc: xiao jin Cc: Joerg Roedel Cc: Borislav Petkov Cc: Yanmin Zhang Link: http://lkml.kernel.org/r/20150705171102.063519515@linutronix.de --- kernel/cpu.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index 9c9c9fab16cc..6a374544d495 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include "smpboot.h" @@ -392,13 +393,19 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) smpboot_park_threads(cpu); /* - * So now all preempt/rcu users must observe !cpu_active(). + * Prevent irq alloc/free while the dying cpu reorganizes the + * interrupt affinities. */ + irq_lock_sparse(); + /* + * So now all preempt/rcu users must observe !cpu_active(). + */ err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu)); if (err) { /* CPU didn't die: tell everyone. Can't complain. */ cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu); + irq_unlock_sparse(); goto out_release; } BUG_ON(cpu_online(cpu)); @@ -415,6 +422,9 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) smp_mb(); /* Read from cpu_dead_idle before __cpu_die(). */ per_cpu(cpu_dead_idle, cpu) = false; + /* Interrupts are moved away from the dying cpu, reenable alloc/free */ + irq_unlock_sparse(); + hotplug_cpu__broadcast_tick_pull(cpu); /* This actually kills the CPU. */ __cpu_die(cpu); @@ -517,8 +527,18 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen) goto out_notify; } + /* + * Some architectures have to walk the irq descriptors to + * setup the vector space for the cpu which comes online. + * Prevent irq alloc/free across the bringup. + */ + irq_lock_sparse(); + /* Arch-specific enabling code. */ ret = __cpu_up(cpu, idle); + + irq_unlock_sparse(); + if (ret != 0) goto out_notify; BUG_ON(!cpu_online(cpu)); -- cgit v1.2.3 From ce0d3c0a6fb1422101498ef378c0851dabbbf67f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 14 Jul 2015 22:03:57 +0200 Subject: genirq: Revert sparse irq locking around __cpu_up() and move it to x86 for now Boris reported that the sparse_irq protection around __cpu_up() in the generic code causes a regression on Xen. Xen allocates interrupts and some more in the xen_cpu_up() function, so it deadlocks on the sparse_irq_lock. There is no simple fix for this and we really should have the protection for all architectures, but for now the only solution is to move it to x86 where actual wreckage due to the lack of protection has been observed. Reported-and-tested-by: Boris Ostrovsky Fixes: a89941816726 'hotplug: Prevent alloc/free of irq descriptors during cpu up/down' Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: xiao jin Cc: Joerg Roedel Cc: Borislav Petkov Cc: Yanmin Zhang Cc: xen-devel --- kernel/cpu.c | 9 --------- 1 file changed, 9 deletions(-) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index 6a374544d495..5644ec5582b9 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -527,18 +527,9 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen) goto out_notify; } - /* - * Some architectures have to walk the irq descriptors to - * setup the vector space for the cpu which comes online. - * Prevent irq alloc/free across the bringup. - */ - irq_lock_sparse(); - /* Arch-specific enabling code. */ ret = __cpu_up(cpu, idle); - irq_unlock_sparse(); - if (ret != 0) goto out_notify; BUG_ON(!cpu_online(cpu)); -- cgit v1.2.3