From mboxrd@z Thu Jan 1 00:00:00 1970 From: Maurice Petallo Subject: [PATCH] thermal: Don't call thermal_zone_device_update inside spinlock Date: Thu, 13 Nov 2014 18:47:04 +0800 Message-ID: <1415875624-587-1-git-send-email-mauricex.r.petallo@intel.com> Return-path: Received: from mga11.intel.com ([192.55.52.93]:19710 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932338AbaKMKtc (ORCPT ); Thu, 13 Nov 2014 05:49:32 -0500 Sender: linux-pm-owner@vger.kernel.org List-Id: linux-pm@vger.kernel.org To: Zhang Rui Cc: Srinivas Pandruvada , linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org, Maurice Petallo The driver calls spin_lock_irqsave during DTS interrupt. The interrupt handle then calls thermal_zone_device_update which implicitly calls a sleep function and produce the following bug: BUG: sleeping function called from invalid context at kernel/locking/mutex.c:97 in_atomic(): 1, irqs_disabled(): 1, pid: 920, name: irq/86-soc_dts CPU: 0 PID: 920 Comm: irq/86-soc_dts Tainted: G E 3.17.0-rc2+ #1 Hardware name: Intel Corp. VALLEYVIEW B3 PLATFORM/NOTEBOOK, BIOS BYTICRB1.86C.0092.R31.1408290850 08/29/2014 00000000 00000000 c25dbe74 c1818cfd f3cc488c c25dbe9c c1059305 c1b4063b 00000001 00000001 00000398 f3cc488c f6817644 f6817644 f3ecc6c0 c25dbea8 c18208f2 f6817400 c25dbebc c159b0bb c25dbedc f6817400 f32a2300 c25dbee8 Call Trace: [] dump_stack+0x48/0x60 [] __might_sleep+0xec/0xf4 [] mutex_lock+0x1c/0x34 [] thermal_zone_get_temp+0x34/0x59 [] thermal_zone_device_update+0x2d/0xcb [] ? iosf_mbi_write+0x6c/0x74 [iosf_mbi] [] soc_irq_thread_fn+0x10c/0x163 [intel_soc_dts_thermal] [] irq_thread_fn+0x18/0x2a [] irq_thread+0x81/0x11f [] ? irq_finalize_oneshot+0x7c/0x7c [] ? irq_thread+0x11f/0x11f [] ? wake_threads_waitq+0x31/0x31 [] kthread+0x87/0x8c [] ret_from_kernel_thread+0x21/0x30 [] ? __kthread_parkme+0x55/0x55 Signed-off-by: Maurice Petallo Acked-by: Srinivas Pandruvada --- drivers/thermal/intel_soc_dts_thermal.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/thermal/intel_soc_dts_thermal.c b/drivers/thermal/intel_soc_dts_thermal.c index a6a0a18..5580f5b 100644 --- a/drivers/thermal/intel_soc_dts_thermal.c +++ b/drivers/thermal/intel_soc_dts_thermal.c @@ -360,6 +360,9 @@ static void proc_thermal_interrupt(void) u32 sticky_out; int status; u32 ptmc_out; + unsigned long flags; + + spin_lock_irqsave(&intr_notify_lock, flags); /* Clear APIC interrupt */ status = iosf_mbi_read(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_READ, @@ -378,21 +381,20 @@ static void proc_thermal_interrupt(void) /* reset sticky bit */ status = iosf_mbi_write(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_WRITE, SOC_DTS_OFFSET_PTTSS, sticky_out); + spin_unlock_irqrestore(&intr_notify_lock, flags); + for (i = 0; i < SOC_MAX_DTS_SENSORS; ++i) { pr_debug("TZD update for zone %d\n", i); thermal_zone_device_update(soc_dts[i]->tzone); } - } + } else + spin_unlock_irqrestore(&intr_notify_lock, flags); } static irqreturn_t soc_irq_thread_fn(int irq, void *dev_data) { - unsigned long flags; - - spin_lock_irqsave(&intr_notify_lock, flags); proc_thermal_interrupt(); - spin_unlock_irqrestore(&intr_notify_lock, flags); pr_debug("proc_thermal_interrupt\n"); return IRQ_HANDLED; -- 1.7.9.5