diff mbox

PCI/PME: Restore pcie_pme_driver.remove

Message ID 20170215051748.3346-1-yinghai@kernel.org
State Accepted
Headers show

Commit Message

Yinghai Lu Feb. 15, 2017, 5:17 a.m. UTC
Found 4.9 and later, removing pci device for pcie port via /sys failed:
------------[ cut here ]------------
kernel BUG at drivers/pci/msi.c:370!
invalid opcode: 0000 [#1] SMP
Modules linked in:
CPU: 1 PID: 14509 Comm: sh Tainted: G    W  4.8.0-rc1-yh-00012-gd29438d
RIP: 0010:[<ffffffff9758bbf5>]  free_msi_irqs+0x65/0x190
...
Call Trace:
 [<ffffffff9758cda4>] pci_disable_msi+0x34/0x40
 [<ffffffff97583817>] cleanup_service_irqs+0x27/0x30
 [<ffffffff97583e9a>] pcie_port_device_remove+0x2a/0x40
 [<ffffffff97584250>] pcie_portdrv_remove+0x40/0x50
 [<ffffffff97576d7b>] pci_device_remove+0x4b/0xc0
 [<ffffffff9785ebe6>] __device_release_driver+0xb6/0x150
 [<ffffffff9785eca5>] device_release_driver+0x25/0x40
 [<ffffffff975702e4>] pci_stop_bus_device+0x74/0xa0
 [<ffffffff975704ea>] pci_stop_and_remove_bus_device_locked+0x1a/0x30
 [<ffffffff97578810>] remove_store+0x50/0x70
 [<ffffffff9785a378>] dev_attr_store+0x18/0x30
 [<ffffffff97260b64>] sysfs_kf_write+0x44/0x60
 [<ffffffff9725feae>] kernfs_fop_write+0x10e/0x190
 [<ffffffff971e13f8>] __vfs_write+0x28/0x110
 [<ffffffff970b0fa4>] ? percpu_down_read+0x44/0x80
 [<ffffffff971e53a7>] ? __sb_start_write+0xa7/0xe0
 [<ffffffff971e53a7>] ? __sb_start_write+0xa7/0xe0
 [<ffffffff971e1f04>] vfs_write+0xc4/0x180
 [<ffffffff971e3089>] SyS_write+0x49/0xa0
 [<ffffffff97001a46>] do_syscall_64+0xa6/0x1b0
 [<ffffffff9819201e>] entry_SYSCALL64_slow_path+0x25/0x25
...
 RIP  [<ffffffff9758bbf5>] free_msi_irqs+0x65/0x190
 RSP <ffff89ad3085bc48>
---[ end trace f4505e1dac5b95d3 ]---
Segmentation fault

Bisect to commit d7def2040077 ("PCI/PME: Make explicitly non-modular").
That commit did extra thing like remove the .remove for pcie_pme_driver.

Put back pcie_pme_remove and restore to pcie_pme_driver fix the problem.

Fixes: d7def2040077 ("PCI/PME: Make explicitly non-modular")
Cc: <stable@vger.kernel.org>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>

Comments

Rafael J. Wysocki Feb. 15, 2017, 11:25 a.m. UTC | #1
On 2/15/2017 6:17 AM, Yinghai Lu wrote:
> Found 4.9 and later, removing pci device for pcie port via /sys failed:
> ------------[ cut here ]------------
> kernel BUG at drivers/pci/msi.c:370!
> invalid opcode: 0000 [#1] SMP
> Modules linked in:
> CPU: 1 PID: 14509 Comm: sh Tainted: G    W  4.8.0-rc1-yh-00012-gd29438d
> RIP: 0010:[<ffffffff9758bbf5>]  free_msi_irqs+0x65/0x190
> ...
> Call Trace:
>   [<ffffffff9758cda4>] pci_disable_msi+0x34/0x40
>   [<ffffffff97583817>] cleanup_service_irqs+0x27/0x30
>   [<ffffffff97583e9a>] pcie_port_device_remove+0x2a/0x40
>   [<ffffffff97584250>] pcie_portdrv_remove+0x40/0x50
>   [<ffffffff97576d7b>] pci_device_remove+0x4b/0xc0
>   [<ffffffff9785ebe6>] __device_release_driver+0xb6/0x150
>   [<ffffffff9785eca5>] device_release_driver+0x25/0x40
>   [<ffffffff975702e4>] pci_stop_bus_device+0x74/0xa0
>   [<ffffffff975704ea>] pci_stop_and_remove_bus_device_locked+0x1a/0x30
>   [<ffffffff97578810>] remove_store+0x50/0x70
>   [<ffffffff9785a378>] dev_attr_store+0x18/0x30
>   [<ffffffff97260b64>] sysfs_kf_write+0x44/0x60
>   [<ffffffff9725feae>] kernfs_fop_write+0x10e/0x190
>   [<ffffffff971e13f8>] __vfs_write+0x28/0x110
>   [<ffffffff970b0fa4>] ? percpu_down_read+0x44/0x80
>   [<ffffffff971e53a7>] ? __sb_start_write+0xa7/0xe0
>   [<ffffffff971e53a7>] ? __sb_start_write+0xa7/0xe0
>   [<ffffffff971e1f04>] vfs_write+0xc4/0x180
>   [<ffffffff971e3089>] SyS_write+0x49/0xa0
>   [<ffffffff97001a46>] do_syscall_64+0xa6/0x1b0
>   [<ffffffff9819201e>] entry_SYSCALL64_slow_path+0x25/0x25
> ...
>   RIP  [<ffffffff9758bbf5>] free_msi_irqs+0x65/0x190
>   RSP <ffff89ad3085bc48>
> ---[ end trace f4505e1dac5b95d3 ]---
> Segmentation fault
>
> Bisect to commit d7def2040077 ("PCI/PME: Make explicitly non-modular").
> That commit did extra thing like remove the .remove for pcie_pme_driver.
>
> Put back pcie_pme_remove and restore to pcie_pme_driver fix the problem.
>
> Fixes: d7def2040077 ("PCI/PME: Make explicitly non-modular")
> Cc: <stable@vger.kernel.org>
> Signed-off-by: Yinghai Lu <yinghai@kernel.org>

ACK

> diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c
> index 7175293..2dd1c68 100644
> --- a/drivers/pci/pcie/pme.c
> +++ b/drivers/pci/pcie/pme.c
> @@ -433,6 +433,17 @@ static int pcie_pme_resume(struct pcie_device *srv)
>   	return 0;
>   }
>   
> +/**
> + * pcie_pme_remove - Prepare PCIe PME service device for removal.
> + * @srv - PCIe service device to remove.
> + */
> +static void pcie_pme_remove(struct pcie_device *srv)
> +{
> +	pcie_pme_suspend(srv);
> +	free_irq(srv->irq, srv);
> +	kfree(get_service_data(srv));
> +}
> +
>   static struct pcie_port_service_driver pcie_pme_driver = {
>   	.name		= "pcie_pme",
>   	.port_type	= PCI_EXP_TYPE_ROOT_PORT,
> @@ -441,6 +452,7 @@ static struct pcie_port_service_driver pcie_pme_driver = {
>   	.probe		= pcie_pme_probe,
>   	.suspend	= pcie_pme_suspend,
>   	.resume		= pcie_pme_resume,
> +	.remove		= pcie_pme_remove,
>   };
>   
>   /**

Thanks,

Rafael
Paul Gortmaker Feb. 15, 2017, 3:19 p.m. UTC | #2
[[PATCH] PCI/PME: Restore pcie_pme_driver.remove] On 14/02/2017 (Tue 21:17) Yinghai Lu wrote:

> Found 4.9 and later, removing pci device for pcie port via /sys failed:
> ------------[ cut here ]------------
> kernel BUG at drivers/pci/msi.c:370!
> 

[...]

> Bisect to commit d7def2040077 ("PCI/PME: Make explicitly non-modular").
> That commit did extra thing like remove the .remove for pcie_pme_driver.

Ah crap.  Seems I mis-interpreted the use case of the .remove.  :-/
Sorry about that.

Thanks,
Paul.
--

> 
> Put back pcie_pme_remove and restore to pcie_pme_driver fix the problem.
> 
> Fixes: d7def2040077 ("PCI/PME: Make explicitly non-modular")
> Cc: <stable@vger.kernel.org>
> Signed-off-by: Yinghai Lu <yinghai@kernel.org>
> 
> diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c
> index 7175293..2dd1c68 100644
> --- a/drivers/pci/pcie/pme.c
> +++ b/drivers/pci/pcie/pme.c
> @@ -433,6 +433,17 @@ static int pcie_pme_resume(struct pcie_device *srv)
>  	return 0;
>  }
>  
> +/**
> + * pcie_pme_remove - Prepare PCIe PME service device for removal.
> + * @srv - PCIe service device to remove.
> + */
> +static void pcie_pme_remove(struct pcie_device *srv)
> +{
> +	pcie_pme_suspend(srv);
> +	free_irq(srv->irq, srv);
> +	kfree(get_service_data(srv));
> +}
> +
>  static struct pcie_port_service_driver pcie_pme_driver = {
>  	.name		= "pcie_pme",
>  	.port_type	= PCI_EXP_TYPE_ROOT_PORT,
> @@ -441,6 +452,7 @@ static struct pcie_port_service_driver pcie_pme_driver = {
>  	.probe		= pcie_pme_probe,
>  	.suspend	= pcie_pme_suspend,
>  	.resume		= pcie_pme_resume,
> +	.remove		= pcie_pme_remove,
>  };
>  
>  /**
Bjorn Helgaas Feb. 15, 2017, 4:06 p.m. UTC | #3
On Tue, Feb 14, 2017 at 09:17:48PM -0800, Yinghai Lu wrote:
> Found 4.9 and later, removing pci device for pcie port via /sys failed:
> ------------[ cut here ]------------
> kernel BUG at drivers/pci/msi.c:370!
> invalid opcode: 0000 [#1] SMP
> Modules linked in:
> CPU: 1 PID: 14509 Comm: sh Tainted: G    W  4.8.0-rc1-yh-00012-gd29438d
> RIP: 0010:[<ffffffff9758bbf5>]  free_msi_irqs+0x65/0x190
> ...
> Call Trace:
>  [<ffffffff9758cda4>] pci_disable_msi+0x34/0x40
>  [<ffffffff97583817>] cleanup_service_irqs+0x27/0x30
>  [<ffffffff97583e9a>] pcie_port_device_remove+0x2a/0x40
>  [<ffffffff97584250>] pcie_portdrv_remove+0x40/0x50
>  [<ffffffff97576d7b>] pci_device_remove+0x4b/0xc0
>  [<ffffffff9785ebe6>] __device_release_driver+0xb6/0x150
>  [<ffffffff9785eca5>] device_release_driver+0x25/0x40
>  [<ffffffff975702e4>] pci_stop_bus_device+0x74/0xa0
>  [<ffffffff975704ea>] pci_stop_and_remove_bus_device_locked+0x1a/0x30
>  [<ffffffff97578810>] remove_store+0x50/0x70
>  [<ffffffff9785a378>] dev_attr_store+0x18/0x30
>  [<ffffffff97260b64>] sysfs_kf_write+0x44/0x60
>  [<ffffffff9725feae>] kernfs_fop_write+0x10e/0x190
>  [<ffffffff971e13f8>] __vfs_write+0x28/0x110
>  [<ffffffff970b0fa4>] ? percpu_down_read+0x44/0x80
>  [<ffffffff971e53a7>] ? __sb_start_write+0xa7/0xe0
>  [<ffffffff971e53a7>] ? __sb_start_write+0xa7/0xe0
>  [<ffffffff971e1f04>] vfs_write+0xc4/0x180
>  [<ffffffff971e3089>] SyS_write+0x49/0xa0
>  [<ffffffff97001a46>] do_syscall_64+0xa6/0x1b0
>  [<ffffffff9819201e>] entry_SYSCALL64_slow_path+0x25/0x25
> ...
>  RIP  [<ffffffff9758bbf5>] free_msi_irqs+0x65/0x190
>  RSP <ffff89ad3085bc48>
> ---[ end trace f4505e1dac5b95d3 ]---
> Segmentation fault
> 
> Bisect to commit d7def2040077 ("PCI/PME: Make explicitly non-modular").
> That commit did extra thing like remove the .remove for pcie_pme_driver.
> 
> Put back pcie_pme_remove and restore to pcie_pme_driver fix the problem.
> 
> Fixes: d7def2040077 ("PCI/PME: Make explicitly non-modular")
> Cc: <stable@vger.kernel.org>
> Signed-off-by: Yinghai Lu <yinghai@kernel.org>

Thanks, I translated Rafael's "ACK" into an Acked-by and applied this to
for-linus for v4.10.

I think the BUG_ON() in free_msi_irqs() is the same one we trip over in
https://bugzilla.kernel.org/show_bug.cgi?id=121711 .  That seems like an
excessive response to a driver that forgets to free an IRQ.

> diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c
> index 7175293..2dd1c68 100644
> --- a/drivers/pci/pcie/pme.c
> +++ b/drivers/pci/pcie/pme.c
> @@ -433,6 +433,17 @@ static int pcie_pme_resume(struct pcie_device *srv)
>  	return 0;
>  }
>  
> +/**
> + * pcie_pme_remove - Prepare PCIe PME service device for removal.
> + * @srv - PCIe service device to remove.
> + */
> +static void pcie_pme_remove(struct pcie_device *srv)
> +{
> +	pcie_pme_suspend(srv);
> +	free_irq(srv->irq, srv);
> +	kfree(get_service_data(srv));
> +}
> +
>  static struct pcie_port_service_driver pcie_pme_driver = {
>  	.name		= "pcie_pme",
>  	.port_type	= PCI_EXP_TYPE_ROOT_PORT,
> @@ -441,6 +452,7 @@ static struct pcie_port_service_driver pcie_pme_driver = {
>  	.probe		= pcie_pme_probe,
>  	.suspend	= pcie_pme_suspend,
>  	.resume		= pcie_pme_resume,
> +	.remove		= pcie_pme_remove,
>  };
>  
>  /**
diff mbox

Patch

diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c
index 7175293..2dd1c68 100644
--- a/drivers/pci/pcie/pme.c
+++ b/drivers/pci/pcie/pme.c
@@ -433,6 +433,17 @@  static int pcie_pme_resume(struct pcie_device *srv)
 	return 0;
 }
 
+/**
+ * pcie_pme_remove - Prepare PCIe PME service device for removal.
+ * @srv - PCIe service device to remove.
+ */
+static void pcie_pme_remove(struct pcie_device *srv)
+{
+	pcie_pme_suspend(srv);
+	free_irq(srv->irq, srv);
+	kfree(get_service_data(srv));
+}
+
 static struct pcie_port_service_driver pcie_pme_driver = {
 	.name		= "pcie_pme",
 	.port_type	= PCI_EXP_TYPE_ROOT_PORT,
@@ -441,6 +452,7 @@  static struct pcie_port_service_driver pcie_pme_driver = {
 	.probe		= pcie_pme_probe,
 	.suspend	= pcie_pme_suspend,
 	.resume		= pcie_pme_resume,
+	.remove		= pcie_pme_remove,
 };
 
 /**