| Message ID | 1602673931-28782-6-git-send-email-sumit.garg@linaro.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | arm64: Add framework to turn an IPI as NMI | expand |
On Wed, Oct 14, 2020 at 04:42:11PM +0530, Sumit Garg wrote: > Enable NMI backtrace support on arm64 using IPI turned as an NMI > leveraging pseudo NMIs support. It is now possible for users to get a > backtrace of a CPU stuck in hard-lockup using magic SYSRQ. > > Signed-off-by: Sumit Garg <sumit.garg@linaro.org> > --- > arch/arm64/include/asm/irq.h | 6 ++++++ > arch/arm64/kernel/ipi_nmi.c | 12 +++++++++++- > 2 files changed, 17 insertions(+), 1 deletion(-) > > diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h > index b2b0c64..e840bf1 100644 > --- a/arch/arm64/include/asm/irq.h > +++ b/arch/arm64/include/asm/irq.h > @@ -6,6 +6,12 @@ > > #include <asm-generic/irq.h> > > +#ifdef CONFIG_SMP > +extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, > + bool exclude_self); > +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace > +#endif > + > struct pt_regs; > > static inline int nr_legacy_irqs(void) > diff --git a/arch/arm64/kernel/ipi_nmi.c b/arch/arm64/kernel/ipi_nmi.c > index e0a9e03..e1dc19d 100644 > --- a/arch/arm64/kernel/ipi_nmi.c > +++ b/arch/arm64/kernel/ipi_nmi.c > @@ -9,6 +9,7 @@ > #include <linux/interrupt.h> > #include <linux/irq.h> > #include <linux/kgdb.h> > +#include <linux/nmi.h> > #include <linux/smp.h> > > #include <asm/nmi.h> > @@ -25,12 +26,21 @@ void arch_send_call_nmi_func_ipi_mask(cpumask_t *mask) > __ipi_send_mask(ipi_desc, mask); > } > > +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) > +{ > + nmi_trigger_cpumask_backtrace(mask, exclude_self, > + arch_send_call_nmi_func_ipi_mask); > +} > + > static irqreturn_t ipi_nmi_handler(int irq, void *data) > { > unsigned int cpu = smp_processor_id(); > > - ipi_kgdb_nmicallback(cpu, get_irq_regs()); > + if (nmi_cpu_backtrace(get_irq_regs())) > + goto out; > > + ipi_kgdb_nmicallback(cpu, get_irq_regs()); > +out: > return IRQ_HANDLED; > } > > -- It works well. Please feel free to add: Tested-by: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com> Thanks! Masa
On 2020-10-14 12:12, Sumit Garg wrote: > Enable NMI backtrace support on arm64 using IPI turned as an NMI > leveraging pseudo NMIs support. It is now possible for users to get a > backtrace of a CPU stuck in hard-lockup using magic SYSRQ. > > Signed-off-by: Sumit Garg <sumit.garg@linaro.org> > --- > arch/arm64/include/asm/irq.h | 6 ++++++ > arch/arm64/kernel/ipi_nmi.c | 12 +++++++++++- > 2 files changed, 17 insertions(+), 1 deletion(-) > > diff --git a/arch/arm64/include/asm/irq.h > b/arch/arm64/include/asm/irq.h > index b2b0c64..e840bf1 100644 > --- a/arch/arm64/include/asm/irq.h > +++ b/arch/arm64/include/asm/irq.h > @@ -6,6 +6,12 @@ > > #include <asm-generic/irq.h> > > +#ifdef CONFIG_SMP > +extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, > + bool exclude_self); > +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace > +#endif > + > struct pt_regs; > > static inline int nr_legacy_irqs(void) > diff --git a/arch/arm64/kernel/ipi_nmi.c b/arch/arm64/kernel/ipi_nmi.c > index e0a9e03..e1dc19d 100644 > --- a/arch/arm64/kernel/ipi_nmi.c > +++ b/arch/arm64/kernel/ipi_nmi.c > @@ -9,6 +9,7 @@ > #include <linux/interrupt.h> > #include <linux/irq.h> > #include <linux/kgdb.h> > +#include <linux/nmi.h> > #include <linux/smp.h> > > #include <asm/nmi.h> > @@ -25,12 +26,21 @@ void arch_send_call_nmi_func_ipi_mask(cpumask_t > *mask) > __ipi_send_mask(ipi_desc, mask); > } > > +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool > exclude_self) > +{ > + nmi_trigger_cpumask_backtrace(mask, exclude_self, > + arch_send_call_nmi_func_ipi_mask); > +} > + > static irqreturn_t ipi_nmi_handler(int irq, void *data) > { > unsigned int cpu = smp_processor_id(); > > - ipi_kgdb_nmicallback(cpu, get_irq_regs()); > + if (nmi_cpu_backtrace(get_irq_regs())) > + goto out; > > + ipi_kgdb_nmicallback(cpu, get_irq_regs()); > +out: > return IRQ_HANDLED; > } Can't you have *both* a request for a backtrace and a KGDB call? It really shouldn't be either/or. It also outlines how well shared interrupts work with edge triggered signalling... M.
On Mon, 19 Oct 2020 at 17:50, Marc Zyngier <maz@kernel.org> wrote: > > On 2020-10-14 12:12, Sumit Garg wrote: > > Enable NMI backtrace support on arm64 using IPI turned as an NMI > > leveraging pseudo NMIs support. It is now possible for users to get a > > backtrace of a CPU stuck in hard-lockup using magic SYSRQ. > > > > Signed-off-by: Sumit Garg <sumit.garg@linaro.org> > > --- > > arch/arm64/include/asm/irq.h | 6 ++++++ > > arch/arm64/kernel/ipi_nmi.c | 12 +++++++++++- > > 2 files changed, 17 insertions(+), 1 deletion(-) > > > > diff --git a/arch/arm64/include/asm/irq.h > > b/arch/arm64/include/asm/irq.h > > index b2b0c64..e840bf1 100644 > > --- a/arch/arm64/include/asm/irq.h > > +++ b/arch/arm64/include/asm/irq.h > > @@ -6,6 +6,12 @@ > > > > #include <asm-generic/irq.h> > > > > +#ifdef CONFIG_SMP > > +extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, > > + bool exclude_self); > > +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace > > +#endif > > + > > struct pt_regs; > > > > static inline int nr_legacy_irqs(void) > > diff --git a/arch/arm64/kernel/ipi_nmi.c b/arch/arm64/kernel/ipi_nmi.c > > index e0a9e03..e1dc19d 100644 > > --- a/arch/arm64/kernel/ipi_nmi.c > > +++ b/arch/arm64/kernel/ipi_nmi.c > > @@ -9,6 +9,7 @@ > > #include <linux/interrupt.h> > > #include <linux/irq.h> > > #include <linux/kgdb.h> > > +#include <linux/nmi.h> > > #include <linux/smp.h> > > > > #include <asm/nmi.h> > > @@ -25,12 +26,21 @@ void arch_send_call_nmi_func_ipi_mask(cpumask_t > > *mask) > > __ipi_send_mask(ipi_desc, mask); > > } > > > > +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool > > exclude_self) > > +{ > > + nmi_trigger_cpumask_backtrace(mask, exclude_self, > > + arch_send_call_nmi_func_ipi_mask); > > +} > > + > > static irqreturn_t ipi_nmi_handler(int irq, void *data) > > { > > unsigned int cpu = smp_processor_id(); > > > > - ipi_kgdb_nmicallback(cpu, get_irq_regs()); > > + if (nmi_cpu_backtrace(get_irq_regs())) > > + goto out; > > > > + ipi_kgdb_nmicallback(cpu, get_irq_regs()); > > +out: > > return IRQ_HANDLED; > > } > > Can't you have *both* a request for a backtrace and a KGDB call? > It really shouldn't be either/or. It also outlines how well shared > interrupts work with edge triggered signalling... Unfortunately, NMIs doesn't seem to support shared mode [1]. [1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/kernel/irq/manage.c#n1480 -Sumit > > M. > -- > Jazz is not dead. It just smells funny...
On 2020-10-20 10:13, Sumit Garg wrote: > On Mon, 19 Oct 2020 at 17:50, Marc Zyngier <maz@kernel.org> wrote: >> >> On 2020-10-14 12:12, Sumit Garg wrote: >> > Enable NMI backtrace support on arm64 using IPI turned as an NMI >> > leveraging pseudo NMIs support. It is now possible for users to get a >> > backtrace of a CPU stuck in hard-lockup using magic SYSRQ. >> > >> > Signed-off-by: Sumit Garg <sumit.garg@linaro.org> >> > --- >> > arch/arm64/include/asm/irq.h | 6 ++++++ >> > arch/arm64/kernel/ipi_nmi.c | 12 +++++++++++- >> > 2 files changed, 17 insertions(+), 1 deletion(-) >> > >> > diff --git a/arch/arm64/include/asm/irq.h >> > b/arch/arm64/include/asm/irq.h >> > index b2b0c64..e840bf1 100644 >> > --- a/arch/arm64/include/asm/irq.h >> > +++ b/arch/arm64/include/asm/irq.h >> > @@ -6,6 +6,12 @@ >> > >> > #include <asm-generic/irq.h> >> > >> > +#ifdef CONFIG_SMP >> > +extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, >> > + bool exclude_self); >> > +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace >> > +#endif >> > + >> > struct pt_regs; >> > >> > static inline int nr_legacy_irqs(void) >> > diff --git a/arch/arm64/kernel/ipi_nmi.c b/arch/arm64/kernel/ipi_nmi.c >> > index e0a9e03..e1dc19d 100644 >> > --- a/arch/arm64/kernel/ipi_nmi.c >> > +++ b/arch/arm64/kernel/ipi_nmi.c >> > @@ -9,6 +9,7 @@ >> > #include <linux/interrupt.h> >> > #include <linux/irq.h> >> > #include <linux/kgdb.h> >> > +#include <linux/nmi.h> >> > #include <linux/smp.h> >> > >> > #include <asm/nmi.h> >> > @@ -25,12 +26,21 @@ void arch_send_call_nmi_func_ipi_mask(cpumask_t >> > *mask) >> > __ipi_send_mask(ipi_desc, mask); >> > } >> > >> > +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool >> > exclude_self) >> > +{ >> > + nmi_trigger_cpumask_backtrace(mask, exclude_self, >> > + arch_send_call_nmi_func_ipi_mask); >> > +} >> > + >> > static irqreturn_t ipi_nmi_handler(int irq, void *data) >> > { >> > unsigned int cpu = smp_processor_id(); >> > >> > - ipi_kgdb_nmicallback(cpu, get_irq_regs()); >> > + if (nmi_cpu_backtrace(get_irq_regs())) >> > + goto out; >> > >> > + ipi_kgdb_nmicallback(cpu, get_irq_regs()); >> > +out: >> > return IRQ_HANDLED; >> > } >> >> Can't you have *both* a request for a backtrace and a KGDB call? >> It really shouldn't be either/or. It also outlines how well shared >> interrupts work with edge triggered signalling... > > Unfortunately, NMIs doesn't seem to support shared mode [1]. You are totally missing the point: shared interrupts *cannot* work reliably with edge signalling. What I am saying here is that you need implement the sharing yourself in this function. M.
On Wed, 21 Oct 2020 at 16:02, Marc Zyngier <maz@kernel.org> wrote: > > On 2020-10-20 10:13, Sumit Garg wrote: > > On Mon, 19 Oct 2020 at 17:50, Marc Zyngier <maz@kernel.org> wrote: > >> > >> On 2020-10-14 12:12, Sumit Garg wrote: > >> > Enable NMI backtrace support on arm64 using IPI turned as an NMI > >> > leveraging pseudo NMIs support. It is now possible for users to get a > >> > backtrace of a CPU stuck in hard-lockup using magic SYSRQ. > >> > > >> > Signed-off-by: Sumit Garg <sumit.garg@linaro.org> > >> > --- > >> > arch/arm64/include/asm/irq.h | 6 ++++++ > >> > arch/arm64/kernel/ipi_nmi.c | 12 +++++++++++- > >> > 2 files changed, 17 insertions(+), 1 deletion(-) > >> > > >> > diff --git a/arch/arm64/include/asm/irq.h > >> > b/arch/arm64/include/asm/irq.h > >> > index b2b0c64..e840bf1 100644 > >> > --- a/arch/arm64/include/asm/irq.h > >> > +++ b/arch/arm64/include/asm/irq.h > >> > @@ -6,6 +6,12 @@ > >> > > >> > #include <asm-generic/irq.h> > >> > > >> > +#ifdef CONFIG_SMP > >> > +extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, > >> > + bool exclude_self); > >> > +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace > >> > +#endif > >> > + > >> > struct pt_regs; > >> > > >> > static inline int nr_legacy_irqs(void) > >> > diff --git a/arch/arm64/kernel/ipi_nmi.c b/arch/arm64/kernel/ipi_nmi.c > >> > index e0a9e03..e1dc19d 100644 > >> > --- a/arch/arm64/kernel/ipi_nmi.c > >> > +++ b/arch/arm64/kernel/ipi_nmi.c > >> > @@ -9,6 +9,7 @@ > >> > #include <linux/interrupt.h> > >> > #include <linux/irq.h> > >> > #include <linux/kgdb.h> > >> > +#include <linux/nmi.h> > >> > #include <linux/smp.h> > >> > > >> > #include <asm/nmi.h> > >> > @@ -25,12 +26,21 @@ void arch_send_call_nmi_func_ipi_mask(cpumask_t > >> > *mask) > >> > __ipi_send_mask(ipi_desc, mask); > >> > } > >> > > >> > +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool > >> > exclude_self) > >> > +{ > >> > + nmi_trigger_cpumask_backtrace(mask, exclude_self, > >> > + arch_send_call_nmi_func_ipi_mask); > >> > +} > >> > + > >> > static irqreturn_t ipi_nmi_handler(int irq, void *data) > >> > { > >> > unsigned int cpu = smp_processor_id(); > >> > > >> > - ipi_kgdb_nmicallback(cpu, get_irq_regs()); > >> > + if (nmi_cpu_backtrace(get_irq_regs())) > >> > + goto out; > >> > > >> > + ipi_kgdb_nmicallback(cpu, get_irq_regs()); > >> > +out: > >> > return IRQ_HANDLED; > >> > } > >> > >> Can't you have *both* a request for a backtrace and a KGDB call? > >> It really shouldn't be either/or. It also outlines how well shared > >> interrupts work with edge triggered signalling... > > > > Unfortunately, NMIs doesn't seem to support shared mode [1]. > > You are totally missing the point: shared interrupts *cannot* work > reliably with edge signalling. What I am saying here is that you need > implement the sharing yourself in this function. Ah, I see your point now. Will instead share this IPI among both handlers. -Sumit > > M. > -- > Jazz is not dead. It just smells funny...
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h index b2b0c64..e840bf1 100644 --- a/arch/arm64/include/asm/irq.h +++ b/arch/arm64/include/asm/irq.h @@ -6,6 +6,12 @@ #include <asm-generic/irq.h> +#ifdef CONFIG_SMP +extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, + bool exclude_self); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace +#endif + struct pt_regs; static inline int nr_legacy_irqs(void) diff --git a/arch/arm64/kernel/ipi_nmi.c b/arch/arm64/kernel/ipi_nmi.c index e0a9e03..e1dc19d 100644 --- a/arch/arm64/kernel/ipi_nmi.c +++ b/arch/arm64/kernel/ipi_nmi.c @@ -9,6 +9,7 @@ #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/kgdb.h> +#include <linux/nmi.h> #include <linux/smp.h> #include <asm/nmi.h> @@ -25,12 +26,21 @@ void arch_send_call_nmi_func_ipi_mask(cpumask_t *mask) __ipi_send_mask(ipi_desc, mask); } +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) +{ + nmi_trigger_cpumask_backtrace(mask, exclude_self, + arch_send_call_nmi_func_ipi_mask); +} + static irqreturn_t ipi_nmi_handler(int irq, void *data) { unsigned int cpu = smp_processor_id(); - ipi_kgdb_nmicallback(cpu, get_irq_regs()); + if (nmi_cpu_backtrace(get_irq_regs())) + goto out; + ipi_kgdb_nmicallback(cpu, get_irq_regs()); +out: return IRQ_HANDLED; }
Enable NMI backtrace support on arm64 using IPI turned as an NMI leveraging pseudo NMIs support. It is now possible for users to get a backtrace of a CPU stuck in hard-lockup using magic SYSRQ. Signed-off-by: Sumit Garg <sumit.garg@linaro.org> --- arch/arm64/include/asm/irq.h | 6 ++++++ arch/arm64/kernel/ipi_nmi.c | 12 +++++++++++- 2 files changed, 17 insertions(+), 1 deletion(-)