In order to detect hardlockups, it is necessary to have the ability to receive interrupts even when disabled: a non-maskable interrupt is required. Add the flag IRQF_DELIVER_AS_NMI to the arguments of request_irq() for this purpose.
Note that the timer, when programmed to deliver interrupts via the IO APIC is programmed as level-triggered. This is to have an indication that the NMI comes from HPET timer as indicated in the General Status Interrupt Register. However, NMIs are always edge-triggered, thus a GSI edge- triggered interrupt is now requested. An NMI handler is also implemented. The handler looks for hardlockups and kicks the timer. Cc: Ashok Raj <ashok....@intel.com> Cc: Andi Kleen <andi.kl...@intel.com> Cc: Tony Luck <tony.l...@intel.com> Cc: Borislav Petkov <b...@suse.de> Cc: Jacob Pan <jacob.jun....@intel.com> Cc: "Rafael J. Wysocki" <rafael.j.wyso...@intel.com> Cc: Don Zickus <dzic...@redhat.com> Cc: Nicholas Piggin <npig...@gmail.com> Cc: Michael Ellerman <m...@ellerman.id.au> Cc: Frederic Weisbecker <frede...@kernel.org> Cc: Alexei Starovoitov <a...@kernel.org> Cc: Babu Moger <babu.mo...@oracle.com> Cc: Mathieu Desnoyers <mathieu.desnoy...@efficios.com> Cc: Masami Hiramatsu <mhira...@kernel.org> Cc: Peter Zijlstra <pet...@infradead.org> Cc: Andrew Morton <a...@linux-foundation.org> Cc: Philippe Ombredanne <pombreda...@nexb.com> Cc: Colin Ian King <colin.k...@canonical.com> Cc: Byungchul Park <byungchul.p...@lge.com> Cc: "Paul E. McKenney" <paul...@linux.vnet.ibm.com> Cc: "Luis R. Rodriguez" <mcg...@kernel.org> Cc: Waiman Long <long...@redhat.com> Cc: Josh Poimboeuf <jpoim...@redhat.com> Cc: Randy Dunlap <rdun...@infradead.org> Cc: Davidlohr Bueso <d...@stgolabs.net> Cc: Christoffer Dall <cd...@linaro.org> Cc: Marc Zyngier <marc.zyng...@arm.com> Cc: Kai-Heng Feng <kai.heng.f...@canonical.com> Cc: Konrad Rzeszutek Wilk <konrad.w...@oracle.com> Cc: David Rientjes <rient...@google.com> Cc: "Ravi V. Shankar" <ravi.v.shan...@intel.com> Cc: x...@kernel.org Cc: io...@lists.linux-foundation.org Signed-off-by: Ricardo Neri <ricardo.neri-calde...@linux.intel.com> --- arch/x86/kernel/hpet.c | 2 +- kernel/watchdog_hld_hpet.c | 55 +++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 55 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index fda6e19..5ca1953 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -205,7 +205,7 @@ int hpet_hardlockup_detector_assign_legacy_irq(struct hpet_hld_data *hdata) break; } - gsi = acpi_register_gsi(NULL, hwirq, ACPI_LEVEL_SENSITIVE, + gsi = acpi_register_gsi(NULL, hwirq, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW); if (gsi > 0) break; diff --git a/kernel/watchdog_hld_hpet.c b/kernel/watchdog_hld_hpet.c index 8fa4e55..3bedffa 100644 --- a/kernel/watchdog_hld_hpet.c +++ b/kernel/watchdog_hld_hpet.c @@ -10,6 +10,7 @@ #include <linux/nmi.h> #include <linux/hpet.h> #include <asm/hpet.h> +#include <asm/irq_remapping.h> #undef pr_fmt #define pr_fmt(fmt) "NMI hpet watchdog: " fmt @@ -183,6 +184,8 @@ static irqreturn_t hardlockup_detector_irq_handler(int irq, void *data) if (!(hdata->flags & HPET_DEV_PERI_CAP)) kick_timer(hdata); + pr_err("This interrupt should not have happened. Ensure delivery mode is NMI.\n"); + /* Acknowledge interrupt if in level-triggered mode */ if (!use_fsb) hpet_writel(BIT(hdata->num), HPET_STATUS); @@ -191,6 +194,47 @@ static irqreturn_t hardlockup_detector_irq_handler(int irq, void *data) } /** + * hardlockup_detector_nmi_handler() - NMI Interrupt handler + * @val: Attribute associated with the NMI. Not used. + * @regs: Register values as seen when the NMI was asserted + * + * When an NMI is issued, look for hardlockups. If the timer is not periodic, + * kick it. The interrupt is always handled when if delivered via the + * Front-Side Bus. + * + * Returns: + * + * NMI_DONE if the HPET timer did not cause the interrupt. NMI_HANDLED + * otherwise. + */ +static int hardlockup_detector_nmi_handler(unsigned int val, + struct pt_regs *regs) +{ + struct hpet_hld_data *hdata = hld_data; + unsigned int use_fsb; + + /* + * If FSB delivery mode is used, the timer interrupt is programmed as + * edge-triggered and there is no need to check the ISR register. + */ + use_fsb = hdata->flags & HPET_DEV_FSB_CAP; + + if (!use_fsb && !is_hpet_wdt_interrupt(hdata)) + return NMI_DONE; + + inspect_for_hardlockups(regs); + + if (!(hdata->flags & HPET_DEV_PERI_CAP)) + kick_timer(hdata); + + /* Acknowledge interrupt if in level-triggered mode */ + if (!use_fsb) + hpet_writel(BIT(hdata->num), HPET_STATUS); + + return NMI_HANDLED; +} + +/** * setup_irq_msi_mode() - Configure the timer to deliver an MSI interrupt * @data: Data associated with the instance of the HPET timer to configure * @@ -282,11 +326,20 @@ static int setup_hpet_irq(struct hpet_hld_data *hdata) if (ret) return ret; + /* Register the NMI handler, which will be the actual handler we use. */ + ret = register_nmi_handler(NMI_LOCAL, hardlockup_detector_nmi_handler, + 0, "hpet_hld"); + if (ret) + return ret; + /* * Request an interrupt to activate the irq in all the needed domains. */ ret = request_irq(hwirq, hardlockup_detector_irq_handler, - IRQF_TIMER, "hpet_hld", hdata); + IRQF_TIMER | IRQF_DELIVER_AS_NMI, + "hpet_hld", hdata); + if (ret) + unregister_nmi_handler(NMI_LOCAL, "hpet_hld"); return ret; } -- 2.7.4