On some pre-production Lunar Lake systems, there is a kernel
warning:
remove_proc_entry: removing non-empty directory 'irq/172'
WARNING: CPU: 0 PID: 501 at fs/proc/generic.c:717
remove_proc_entry+0x1b4/0x1e0
...
...
remove_proc_entry+0x1b4/0x1e0
report_bug+0x182/0x1b0
handle_bug+0x51/0xa0
exc_invalid_op+0x18/0x80
asm_exc_invalid_op+0x1b/0x20
remove_proc_entry+0x1b4/0x1e0
remove_proc_entry+0x1b4/0x1e0
unregister_irq_proc+0xf2/0x120
free_desc+0x41/0xe0
irq_domain_free_irqs+0x138/0x1c0
irq_free_descs+0x52/0x80
irq_domain_free_irqs+0x151/0x1c0
msi_domain_free_locked.part.0+0x17e/0x1c0
msi_domain_free_irqs_all_locked+0x74/0xc0
pci_msi_teardown_msi_irqs+0x50/0x60
pci_free_msi_irqs+0x12/0x40
pci_free_irq_vectors+0x58/0x70
On these systems, not all the MSI thermal vectors are valid. This causes
devm_request_threaded_irq() to fail for some vectors. As part of the
clean up on this error, pci_free_irq_vectors() is called without calling
devm_free_irq(). This causes the above warning.
Add a function proc_thermal_free_msi() to call devm_free_irq() for all
successfully registered IRQ handlers, then call pci_free_irq_vectors().
Call this function for MSI cleanup.
Fixes: 7a9a8c5faf41 ("thermal: intel: int340x: Support MSI interrupt for Lunar Lake")
Reported-by: Yijun Shen <Yijun.shen@dell.com>
Tested-by: Yijun Shen <Yijun.shen@dell.com>
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
---
.../processor_thermal_device_pci.c | 16 ++++++++++++++--
1 file changed, 14 insertions(+), 2 deletions(-)
diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c
index 114136893a59..2c9c45eb5b4a 100644
--- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c
+++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c
@@ -278,6 +278,18 @@ static struct thermal_zone_params tzone_params = {
static bool msi_irq;
+static void proc_thermal_free_msi(struct pci_dev *pdev, struct proc_thermal_pci *pci_info)
+{
+ int i;
+
+ for (i = 0; i < MSI_THERMAL_MAX; i++) {
+ if (proc_thermal_msi_map[i])
+ devm_free_irq(&pdev->dev, proc_thermal_msi_map[i], pci_info);
+ }
+
+ pci_free_irq_vectors(pdev);
+}
+
static int proc_thermal_setup_msi(struct pci_dev *pdev, struct proc_thermal_pci *pci_info)
{
int ret, i, irq;
@@ -310,7 +322,7 @@ static int proc_thermal_setup_msi(struct pci_dev *pdev, struct proc_thermal_pci
return 0;
err_free_msi_vectors:
- pci_free_irq_vectors(pdev);
+ proc_thermal_free_msi(pdev, pci_info);
return ret;
}
@@ -397,7 +409,7 @@ static int proc_thermal_pci_probe(struct pci_dev *pdev, const struct pci_device_
err_free_vectors:
if (msi_irq)
- pci_free_irq_vectors(pdev);
+ proc_thermal_free_msi(pdev, pci_info);
err_ret_tzone:
thermal_zone_device_unregister(pci_info->tzone);
err_del_legacy:
--
2.45.0
On Tue, 2024-07-23 at 07:02 -0700, Srinivas Pandruvada wrote: > On some pre-production Lunar Lake systems, there is a kernel > warning: > > remove_proc_entry: removing non-empty directory 'irq/172' > WARNING: CPU: 0 PID: 501 at fs/proc/generic.c:717 > remove_proc_entry+0x1b4/0x1e0 > ... > ... > remove_proc_entry+0x1b4/0x1e0 > report_bug+0x182/0x1b0 > handle_bug+0x51/0xa0 > exc_invalid_op+0x18/0x80 > asm_exc_invalid_op+0x1b/0x20 > remove_proc_entry+0x1b4/0x1e0 > remove_proc_entry+0x1b4/0x1e0 > unregister_irq_proc+0xf2/0x120 > free_desc+0x41/0xe0 > irq_domain_free_irqs+0x138/0x1c0 > irq_free_descs+0x52/0x80 > irq_domain_free_irqs+0x151/0x1c0 > msi_domain_free_locked.part.0+0x17e/0x1c0 > msi_domain_free_irqs_all_locked+0x74/0xc0 > pci_msi_teardown_msi_irqs+0x50/0x60 > pci_free_msi_irqs+0x12/0x40 > pci_free_irq_vectors+0x58/0x70 > > On these systems, not all the MSI thermal vectors are valid. This > causes > devm_request_threaded_irq() to fail for some vectors. As part of the > clean up on this error, pci_free_irq_vectors() is called without > calling > devm_free_irq(). This causes the above warning. > > Add a function proc_thermal_free_msi() to call devm_free_irq() for > all > successfully registered IRQ handlers, then call > pci_free_irq_vectors(). > Call this function for MSI cleanup. > > Fixes: 7a9a8c5faf41 ("thermal: intel: int340x: Support MSI interrupt > for Lunar Lake") > Reported-by: Yijun Shen <Yijun.shen@dell.com> > Tested-by: Yijun Shen <Yijun.shen@dell.com> > Signed-off-by: Srinivas Pandruvada > <srinivas.pandruvada@linux.intel.com> The whole patch set looks good to me. Reviewed-by: Zhang Rui <rui.zhang@intel.com> thanks, rui > --- > .../processor_thermal_device_pci.c | 16 > ++++++++++++++-- > 1 file changed, 14 insertions(+), 2 deletions(-) > > diff --git > a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci. > c > b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci. > c > index 114136893a59..2c9c45eb5b4a 100644 > --- > a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci. > c > +++ > b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci. > c > @@ -278,6 +278,18 @@ static struct thermal_zone_params tzone_params = > { > > static bool msi_irq; > > +static void proc_thermal_free_msi(struct pci_dev *pdev, struct > proc_thermal_pci *pci_info) > +{ > + int i; > + > + for (i = 0; i < MSI_THERMAL_MAX; i++) { > + if (proc_thermal_msi_map[i]) > + devm_free_irq(&pdev->dev, > proc_thermal_msi_map[i], pci_info); > + } > + > + pci_free_irq_vectors(pdev); > +} > + > static int proc_thermal_setup_msi(struct pci_dev *pdev, struct > proc_thermal_pci *pci_info) > { > int ret, i, irq; > @@ -310,7 +322,7 @@ static int proc_thermal_setup_msi(struct pci_dev > *pdev, struct proc_thermal_pci > return 0; > > err_free_msi_vectors: > - pci_free_irq_vectors(pdev); > + proc_thermal_free_msi(pdev, pci_info); > > return ret; > } > @@ -397,7 +409,7 @@ static int proc_thermal_pci_probe(struct pci_dev > *pdev, const struct pci_device_ > > err_free_vectors: > if (msi_irq) > - pci_free_irq_vectors(pdev); > + proc_thermal_free_msi(pdev, pci_info); > err_ret_tzone: > thermal_zone_device_unregister(pci_info->tzone); > err_del_legacy:
© 2016 - 2024 Red Hat, Inc.