x86/nmi: remove the irqwork from long duration nmi handler
PATCH v2 1/1 x86/nmi: remove the irqwork from long duration nmi handler
First, printk is NMI context safe now since the safe printk has been implemented. The safe printk already has an irqwork to make NMI context safe.
Second, the NMI irqwork actually does not work if a NMI handler causes panic by watchdog timeout. This NMI irqwork have no chance to run in such case, while the safe printk will flush its per-cpu buffer before panic.
While at it, repurpose the IRQ work callback into a function which concentrates the NMI duration checking.
---
v2: polish commit message. (Borislav Petkov)
--- arch/x86/include/asm/nmi.h | 1 - arch/x86/kernel/nmi.c | 20 +++++++++----------- 2 files changed, 9 insertions(+), 12 deletions(-)
arch/x86/include/asm/nmi.h +0 -1
@@ -41,7 +41,6 @@ struct nmiaction {struct list_head list;nmi_handler_t handler;u64 max_duration; -struct irq_work irq_work;unsigned long flags;const char *name; };
arch/x86/kernel/nmi.c +9 -11
@@ -104,18 +104,22 @@ static int __init nmi_warning_debugfs(void) }fs_initcall (nmi_warning_debugfs); -static void nmi_max_handler (struct irq_work *w) +static void nmi_check_duration (struct nmiaction *action,u64 duration) { - struct nmiaction *a = container_of(w, struct nmiaction, irq_work);int remainder_ns, decimal_msecs; -u64 whole_msecs =READ_ONCE (a->max_duration); +u64 whole_msecs =READ_ONCE (action->max_duration); + +if (duration < nmi_longest_ns || duration < action->max_duration) +return ; + + action->max_duration = duration; remainder_ns =do_div (whole_msecs, (1000 *1000 )); decimal_msecs = remainder_ns /1000 ;printk_ratelimited (KERN_INFO "INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n" , - a->handler, whole_msecs, decimal_msecs); + action->handler, whole_msecs, decimal_msecs); }static int nmi_handle (unsigned int type,struct pt_regs *regs)
@@ -142,11 +146,7 @@ static int nmi_handle(unsigned int type, struct pt_regs *regs) delta =sched_clock () - delta;trace_nmi_handler (a->handler, (int )delta, thishandled); -if (delta < nmi_longest_ns || delta < a->max_duration) -continue ; - - a->max_duration = delta; -irq_work_queue (&a->irq_work); +nmi_check_duration (a, delta); }rcu_read_unlock ();
@@ -164,8 +164,6 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action)if (!action->handler)return -EINVAL ; -init_irq_work (&action->irq_work, nmi_max_handler); -raw_spin_lock_irqsave (&desc->lock, flags);/*
Signature · 1 line
2.24.0
[tip: x86/core] x86/nmi: Remove irq_work from the long duration NMI handler
The following commit has been merged into the x86/core branch of tip:
The following commit has been merged into the x86/core branch of tip:
Commit-ID: 248ed51048c40d36728e70914e38bffd7821da57 Gitweb: https://git.kernel.org/tip/248ed51048c40d36728e70914e38bffd7821da57 Author: Changbin Du <[email protected]> AuthorDate: Sat, 11 Jan 2020 20:54:27 +08:00 Committer: Borislav Petkov <[email protected]> CommitterDate: Sat, 11 Jan 2020 15:55:39 +01:00
x86/nmi: Remove irq_work from the long duration NMI handler
First, printk() is NMI-context safe now since the safe printk() has been implemented and it already has an irq_work to make NMI-context safe.
Second, this NMI irq_work actually does not work if a NMI handler causes panic by watchdog timeout. It has no chance to run in such case, while the safe printk() will flush its per-cpu buffers before panicking.
While at it, repurpose the irq_work callback into a function which concentrates the NMI duration checking and makes the code easier to follow.
[ bp: Massage. ]
--- arch/x86/include/asm/nmi.h | 1 - arch/x86/kernel/nmi.c | 20 +++++++++----------- 2 files changed, 9 insertions(+), 12 deletions(-)
arch/x86/include/asm/nmi.h +0 -1
@@ -41,7 +41,6 @@ struct nmiaction {struct list_head list;nmi_handler_t handler;u64 max_duration; -struct irq_work irq_work;unsigned long flags;const char *name; };
arch/x86/kernel/nmi.c +9 -11
@@ -104,18 +104,22 @@ static int __init nmi_warning_debugfs(void) }fs_initcall (nmi_warning_debugfs); -static void nmi_max_handler (struct irq_work *w) +static void nmi_check_duration (struct nmiaction *action,u64 duration) { - struct nmiaction *a = container_of(w, struct nmiaction, irq_work); +u64 whole_msecs =READ_ONCE (action->max_duration);int remainder_ns, decimal_msecs; -u64 whole_msecs =READ_ONCE (a->max_duration); + +if (duration < nmi_longest_ns || duration < action->max_duration) +return ; + + action->max_duration = duration; remainder_ns =do_div (whole_msecs, (1000 *1000 )); decimal_msecs = remainder_ns /1000 ;printk_ratelimited (KERN_INFO "INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n" , - a->handler, whole_msecs, decimal_msecs); + action->handler, whole_msecs, decimal_msecs); }static int nmi_handle (unsigned int type,struct pt_regs *regs)
@@ -142,11 +146,7 @@ static int nmi_handle(unsigned int type, struct pt_regs *regs) delta =sched_clock () - delta;trace_nmi_handler (a->handler, (int )delta, thishandled); -if (delta < nmi_longest_ns || delta < a->max_duration) -continue ; - - a->max_duration = delta; -irq_work_queue (&a->irq_work); +nmi_check_duration (a, delta); }rcu_read_unlock ();
@@ -164,8 +164,6 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action)if (!action->handler)return -EINVAL ; -init_irq_work (&action->irq_work, nmi_max_handler); -raw_spin_lock_irqsave (&desc->lock, flags);/*