mptsas: add mptsas_shutdown to call pci_disable_msi

PATCH In review Yinghai Lu 4 participants 5 messages Apr 23, 2008 – May 7, 2008

Subsystems (2)

SCSI LSI Logic MPT fusion drivers (FC/SAS/SPI)

lore

Share & tools

lore

Yinghai Lu

author

2008-04-23 02:47 UTC #0 lore raw

PATCH 1/1 mptsas: add mptsas_shutdown to call pci_disable_msi

this change

| commit 23a274c8a5adafc74a66f16988776fc7dd6f6e51
| Author: Prakash, Sathya <[email protected]>
| Date:   Fri Mar 7 15:53:21 2008 +0530
|
|     [SCSI] mpt fusion: Enable MSI by default for SAS controllers
|
|     This patch modifies the driver to enable MSI by default for all SAS chips.
|

cause kexec RHEL 5.1 kernel fail.

root casue: the rhel 5.1 kernel still use INTx emulation.
and mptscsih_shutdown doesn't call pci_disable_msi to reenable INTx on kexec path

so try to call mptsas_remove in mptsas_shutdown.
then pci_disable_msi will be called via mptsas_remove==>mptscih_remove==> mpt_detach.

Signed-off-by Yinghai Lu <[email protected]>

CC Prakash, Sathya <[email protected]>

CC "Moore, Eric" <[email protected]>

drivers/message/fusion/mptsas.c +6 -1

Index: linux-2.6/drivers/message/fusion/mptsas.c
===================================================================
@@ -3327,6 +3327,11 @@ static void __devexit mptsas_remove(stru
 	mptscsih_remove(pdev);
 }
 
+static void mptsas_shutdown(struct pci_dev *pdev)
+{
+	mptsas_remove(pdev);
+}
+
 static struct pci_device_id mptsas_pci_table[] = {
 	{ PCI_VENDOR_ID_LSI_LOGIC, MPI_MANUFACTPAGE_DEVID_SAS1064,
 		PCI_ANY_ID, PCI_ANY_ID },

@@ -3348,7 +3353,7 @@ static struct pci_driver mptsas_driver =
 	.id_table	= mptsas_pci_table,
 	.probe		= mptsas_probe,
 	.remove		= __devexit_p(mptsas_remove),
-	.shutdown	= mptscsih_shutdown,
+	.shutdown	= mptsas_shutdown,
 #ifdef CONFIG_PM
 	.suspend	= mptscsih_suspend,
 	.resume		= mptscsih_resume,

Yinghai Lu

2008-04-23 03:12 UTC #1 lore raw

Quoted 47 lines · Yinghai Lu

this change
 | commit 23a274c8a5adafc74a66f16988776fc7dd6f6e51
 | Author: Prakash, Sathya <[email protected]>
 | Date:   Fri Mar 7 15:53:21 2008 +0530
 |
 |     [SCSI] mpt fusion: Enable MSI by default for SAS controllers
 |
 |     This patch modifies the driver to enable MSI by default for all SAS chips.
 |
cause kexec RHEL 5.1 kernel fail.
root casue: the rhel 5.1 kernel still use INTx emulation.
and mptscsih_shutdown doesn't call pci_disable_msi to reenable INTx on kexec path
so try to call mptsas_remove in mptsas_shutdown.
then pci_disable_msi will be called via mptsas_remove==>mptscih_remove==> mpt_detach.
Signed-off-by Yinghai Lu <[email protected]>
CC Prakash, Sathya <[email protected]>
CC "Moore, Eric" <[email protected]>
Index: linux-2.6/drivers/message/fusion/mptsas.c
===================================================================
--- linux-2.6.orig/drivers/message/fusion/mptsas.c +++ linux-2.6/drivers/message/fusion/mptsas.c
@@ -3327,6 +3327,11 @@ static void __devexit mptsas_remove(stru
        mptscsih_remove(pdev);
}
+static void mptsas_shutdown(struct pci_dev *pdev)
+{
+ mptsas_remove(pdev);
+}
+
static struct pci_device_id mptsas_pci_table[] = {
{ PCI_VENDOR_ID_LSI_LOGIC, MPI_MANUFACTPAGE_DEVID_SAS1064,
PCI_ANY_ID, PCI_ANY_ID },
@@ -3348,7 +3353,7 @@ static struct pci_driver mptsas_driver =
        .id_table       = mptsas_pci_table,
        .probe          = mptsas_probe,
        .remove         = __devexit_p(mptsas_remove),
 -       .shutdown       = mptscsih_shutdown,
 +       .shutdown       = mptsas_shutdown,

Quoted 4 lines

#ifdef CONFIG_PM
.suspend = mptscsih_suspend,
.resume = mptscsih_resume,
--

fail on one system with big sas expander...

LBSuse:~ # mkdir /xx
LBSuse:~ # mount /dev/sdl1 /xx
LBSuse:~ # cd /xx
LBSuse:/xx # sh kk_rh_5.1
LBSuse:/xx # ./kexec -e

BUG: unable to handle kernel NULL pointer dereference at 0000000000000028
IP: [<ffffffff80337af4>] sysfs_find_dirent+0x1f/0x5f
PGD 41f137067 PUD 424482067 PMD 0
Oops: 0000 [1] SMP
CPU 7
Modules linked in:
Pid: 7534, comm: kexec Not tainted
2.6.25-sched-devel.git-x86-latest.git-03823-g1508ed0-dirty #135
RIP: 0010:[<ffffffff80337af4>]  [<ffffffff80337af4>] sysfs_find_dirent+0x1f/0x5f
RSP: 0018:ffff8104238f7708  EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffffffff80cd36a5 RCX: 000000008c0f362e
RDX: ffffffff80e20ab0 RSI: ffffffff80cd36a5 RDI: 0000000000000000
RBP: ffff8104238f7728 R08: 0000000000000000 R09: 000000008c0f362e
R10: ffff8104238f77f8 R11: 000000008c0f362e R12: 0000000000000000
R13: ffff810223190358 R14: 0000000000000000 R15: 0000000000000000
FS:  00007fde8859d6f0(0000) GS:ffff810427039f00(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 0000000000000028 CR3: 00000004238b8000 CR4: 00000000000006e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process kexec (pid: 7534, threadinfo ffff8104238f6000, task ffff8104238e0000)
Stack:  0000000000000000 000000008c0f362e ffffffff80cd36a5 0000000000000000
 ffff8104238f7758 ffffffff80337b70 000000008c0f362e 000000008c0f362e
 ffff810223190268 ffffffff80e1fb20 ffff8104238f7798 ffffffff8033966e
Call Trace:
 [<ffffffff80337b70>] sysfs_get_dirent+0x3c/0x72
 [<ffffffff8033966e>] sysfs_remove_group+0x38/0xb4
 [<ffffffff80633007>] dpm_sysfs_remove+0x2f/0x45
 [<ffffffff806336d3>] device_pm_remove+0x34/0x85
 [<ffffffff8062b283>] device_del+0x30/0x1b0
 [<ffffffff8062b428>] device_unregister+0x25/0x48
 [<ffffffff80639e73>] enclosure_unregister+0x85/0xcb
 [<ffffffff807dad42>] ses_intf_remove+0x8b/0xa8
 [<ffffffff8062b2fb>] device_del+0xa8/0x1b0
 [<ffffffff8062b428>] device_unregister+0x25/0x48
 [<ffffffff80700bb4>] __scsi_remove_device+0x4c/0xaf
 [<ffffffff80700c50>] scsi_remove_device+0x39/0x5c
 [<ffffffff80700d15>] __scsi_remove_target+0xa2/0xf6
 [<ffffffff80700de0>] ? __remove_child+0x0/0x4f
 [<ffffffff80700e12>] __remove_child+0x32/0x4f
 [<ffffffff8062ab27>] ? next_device+0x21/0x45
 [<ffffffff8062ac23>] device_for_each_child+0x40/0x84
 [<ffffffff80713d8e>] ? do_sas_phy_delete+0x0/0x66
 [<ffffffff80700dbc>] scsi_remove_target+0x53/0x77
 [<ffffffff807134b0>] sas_rphy_remove+0x42/0x81
 [<ffffffff80713514>] sas_rphy_delete+0x25/0x48
 [<ffffffff80713570>] sas_port_delete+0x39/0x147
 [<ffffffff802259e0>] ? mcount_call+0x5/0x35
 [<ffffffff80713d8e>] ? do_sas_phy_delete+0x0/0x66
 [<ffffffff80713dc2>] do_sas_phy_delete+0x34/0x66
 [<ffffffff8062ac23>] device_for_each_child+0x40/0x84
 [<ffffffff80713d8e>] ? do_sas_phy_delete+0x0/0x66
 [<ffffffff8071343f>] sas_remove_children+0x2e/0x5d
 [<ffffffff807134b7>] sas_rphy_remove+0x49/0x81
 [<ffffffff80713514>] sas_rphy_delete+0x25/0x48
 [<ffffffff80713570>] sas_port_delete+0x39/0x147
 [<ffffffff802259e0>] ? mcount_call+0x5/0x35
 [<ffffffff80713d8e>] ? do_sas_phy_delete+0x0/0x66
 [<ffffffff80713dc2>] do_sas_phy_delete+0x34/0x66
 [<ffffffff8062ac23>] device_for_each_child+0x40/0x84
 [<ffffffff8071343f>] sas_remove_children+0x2e/0x5d
 [<ffffffff807136a6>] sas_remove_host+0x28/0x3e
 [<ffffffff80ab22ab>] mptsas_remove+0x46/0x107
 [<ffffffff802259e0>] ? mcount_call+0x5/0x35
 [<ffffffff8080ef6d>] mptsas_shutdown+0x21/0x37
 [<ffffffff805a6815>] pci_device_shutdown+0x37/0x4d
 [<ffffffff8062a2ad>] device_shutdown+0x64/0xa0
 [<ffffffff8027e57f>] ? blocking_notifier_call_chain+0x27/0x3d
 [<ffffffff8027131e>] kernel_restart_prepare+0x3f/0x5a
 [<ffffffff802716f7>] sys_reboot+0x172/0x1cb
 [<ffffffff802e2ac0>] ? __fput+0x158/0x17b
 [<ffffffff802efc4e>] ? vfs_ioctl+0x3e/0xa2
 [<ffffffff802e2ef0>] ? fput+0x2c/0x42
 [<ffffffff802df2d2>] ? filp_close+0x78/0x9a
 [<ffffffff802df0b4>] ? __put_unused_fd+0x33/0x60
 [<ffffffff802e0bed>] ? sys_close+0x8c/0xdf
 [<ffffffff80225b9b>] system_call_after_swapgs+0x7b/0x80


Code: e8 37 85 f2 ff 48 83 c4 18 5b c9 c3 55 48 89 e5 41 54 53 48 83

ec 10 66 66 90 66 90 65 48 8b 04 25 28 00 00 00 48 89 45 e8 31 c0 <48> 8b 5f 28 49 89 f4 eb 14 48 8b 7b 18 4c 89 e6 e8 25 e8 25 00 RIP [<ffffffff80337af4>] sysfs_find_dirent+0x1f/0x5f
RSP <ffff8104238f7708>
CR2: 0000000000000028

---[ end trace 4ca22418d73866ec ]---

may need create mptsas that only call pci_disable_msi

Andrew Morton

2008-05-07 23:32 UTC #2 lore raw

Quoted 60 lines · On Tue, 22 Apr 2008 20:12:08 -0700 "Yinghai Lu" <[email protected]> wrote:

Quoted 47 lines · Yinghai Lu
this change
 | commit 23a274c8a5adafc74a66f16988776fc7dd6f6e51
 | Author: Prakash, Sathya <[email protected]>
 | Date:   Fri Mar 7 15:53:21 2008 +0530
 |
 |     [SCSI] mpt fusion: Enable MSI by default for SAS controllers
 |
 |     This patch modifies the driver to enable MSI by default for all SAS chips.
 |
cause kexec RHEL 5.1 kernel fail.
root casue: the rhel 5.1 kernel still use INTx emulation.
and mptscsih_shutdown doesn't call pci_disable_msi to reenable INTx on kexec path
so try to call mptsas_remove in mptsas_shutdown.
then pci_disable_msi will be called via mptsas_remove==>mptscih_remove==> mpt_detach.
Signed-off-by Yinghai Lu <[email protected]>
CC Prakash, Sathya <[email protected]>
CC "Moore, Eric" <[email protected]>
Index: linux-2.6/drivers/message/fusion/mptsas.c
===================================================================
--- linux-2.6.orig/drivers/message/fusion/mptsas.c +++ linux-2.6/drivers/message/fusion/mptsas.c
@@ -3327,6 +3327,11 @@ static void __devexit mptsas_remove(stru
        mptscsih_remove(pdev);
}
+static void mptsas_shutdown(struct pci_dev *pdev)
+{
+ mptsas_remove(pdev);
+}
+
static struct pci_device_id mptsas_pci_table[] = {
{ PCI_VENDOR_ID_LSI_LOGIC, MPI_MANUFACTPAGE_DEVID_SAS1064,
PCI_ANY_ID, PCI_ANY_ID },
@@ -3348,7 +3353,7 @@ static struct pci_driver mptsas_driver =
        .id_table       = mptsas_pci_table,
        .probe          = mptsas_probe,
        .remove         = __devexit_p(mptsas_remove),
 -       .shutdown       = mptscsih_shutdown,
 +       .shutdown       = mptsas_shutdown,
Quoted 4 lines
#ifdef CONFIG_PM
.suspend = mptscsih_suspend,
.resume = mptscsih_resume,
--
fail on one system with big sas expander...
LBSuse:~ # mkdir /xx
LBSuse:~ # mount /dev/sdl1 /xx
LBSuse:~ # cd /xx
LBSuse:/xx # sh kk_rh_5.1
LBSuse:/xx # ./kexec -e

Quoted 7 lines

BUG: unable to handle kernel NULL pointer dereference at 0000000000000028
IP: [<ffffffff80337af4>] sysfs_find_dirent+0x1f/0x5f
PGD 41f137067 PUD 424482067 PMD 0
Oops: 0000 [1] SMP
CPU 7
Modules linked in:

Pid: 7534, comm: kexec Not tainted

I don't understand your email.

Are you saying that this oops is the thing which your patch fixes?

Or are you saying that this oops occurs even after your patch is applied? That we have a second regression?

Quoted 73 lines

2.6.25-sched-devel.git-x86-latest.git-03823-g1508ed0-dirty #135

RIP: 0010:[<ffffffff80337af4>]  [<ffffffff80337af4>] sysfs_find_dirent+0x1f/0x5f
RSP: 0018:ffff8104238f7708  EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffffffff80cd36a5 RCX: 000000008c0f362e
RDX: ffffffff80e20ab0 RSI: ffffffff80cd36a5 RDI: 0000000000000000
RBP: ffff8104238f7728 R08: 0000000000000000 R09: 000000008c0f362e
R10: ffff8104238f77f8 R11: 000000008c0f362e R12: 0000000000000000
R13: ffff810223190358 R14: 0000000000000000 R15: 0000000000000000
FS:  00007fde8859d6f0(0000) GS:ffff810427039f00(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 0000000000000028 CR3: 00000004238b8000 CR4: 00000000000006e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process kexec (pid: 7534, threadinfo ffff8104238f6000, task ffff8104238e0000)
Stack:  0000000000000000 000000008c0f362e ffffffff80cd36a5 0000000000000000
 ffff8104238f7758 ffffffff80337b70 000000008c0f362e 000000008c0f362e
 ffff810223190268 ffffffff80e1fb20 ffff8104238f7798 ffffffff8033966e
Call Trace:
 [<ffffffff80337b70>] sysfs_get_dirent+0x3c/0x72
 [<ffffffff8033966e>] sysfs_remove_group+0x38/0xb4
 [<ffffffff80633007>] dpm_sysfs_remove+0x2f/0x45
 [<ffffffff806336d3>] device_pm_remove+0x34/0x85
 [<ffffffff8062b283>] device_del+0x30/0x1b0
 [<ffffffff8062b428>] device_unregister+0x25/0x48
 [<ffffffff80639e73>] enclosure_unregister+0x85/0xcb
 [<ffffffff807dad42>] ses_intf_remove+0x8b/0xa8
 [<ffffffff8062b2fb>] device_del+0xa8/0x1b0
 [<ffffffff8062b428>] device_unregister+0x25/0x48
 [<ffffffff80700bb4>] __scsi_remove_device+0x4c/0xaf
 [<ffffffff80700c50>] scsi_remove_device+0x39/0x5c
 [<ffffffff80700d15>] __scsi_remove_target+0xa2/0xf6
 [<ffffffff80700de0>] ? __remove_child+0x0/0x4f
 [<ffffffff80700e12>] __remove_child+0x32/0x4f
 [<ffffffff8062ab27>] ? next_device+0x21/0x45
 [<ffffffff8062ac23>] device_for_each_child+0x40/0x84
 [<ffffffff80713d8e>] ? do_sas_phy_delete+0x0/0x66
 [<ffffffff80700dbc>] scsi_remove_target+0x53/0x77
 [<ffffffff807134b0>] sas_rphy_remove+0x42/0x81
 [<ffffffff80713514>] sas_rphy_delete+0x25/0x48
 [<ffffffff80713570>] sas_port_delete+0x39/0x147
 [<ffffffff802259e0>] ? mcount_call+0x5/0x35
 [<ffffffff80713d8e>] ? do_sas_phy_delete+0x0/0x66
 [<ffffffff80713dc2>] do_sas_phy_delete+0x34/0x66
 [<ffffffff8062ac23>] device_for_each_child+0x40/0x84
 [<ffffffff80713d8e>] ? do_sas_phy_delete+0x0/0x66
 [<ffffffff8071343f>] sas_remove_children+0x2e/0x5d
 [<ffffffff807134b7>] sas_rphy_remove+0x49/0x81
 [<ffffffff80713514>] sas_rphy_delete+0x25/0x48
 [<ffffffff80713570>] sas_port_delete+0x39/0x147
 [<ffffffff802259e0>] ? mcount_call+0x5/0x35
 [<ffffffff80713d8e>] ? do_sas_phy_delete+0x0/0x66
 [<ffffffff80713dc2>] do_sas_phy_delete+0x34/0x66
 [<ffffffff8062ac23>] device_for_each_child+0x40/0x84
 [<ffffffff8071343f>] sas_remove_children+0x2e/0x5d
 [<ffffffff807136a6>] sas_remove_host+0x28/0x3e
 [<ffffffff80ab22ab>] mptsas_remove+0x46/0x107
 [<ffffffff802259e0>] ? mcount_call+0x5/0x35
 [<ffffffff8080ef6d>] mptsas_shutdown+0x21/0x37
 [<ffffffff805a6815>] pci_device_shutdown+0x37/0x4d
 [<ffffffff8062a2ad>] device_shutdown+0x64/0xa0
 [<ffffffff8027e57f>] ? blocking_notifier_call_chain+0x27/0x3d
 [<ffffffff8027131e>] kernel_restart_prepare+0x3f/0x5a
 [<ffffffff802716f7>] sys_reboot+0x172/0x1cb
 [<ffffffff802e2ac0>] ? __fput+0x158/0x17b
 [<ffffffff802efc4e>] ? vfs_ioctl+0x3e/0xa2
 [<ffffffff802e2ef0>] ? fput+0x2c/0x42
 [<ffffffff802df2d2>] ? filp_close+0x78/0x9a
 [<ffffffff802df0b4>] ? __put_unused_fd+0x33/0x60
 [<ffffffff802e0bed>] ? sys_close+0x8c/0xdf
 [<ffffffff80225b9b>] system_call_after_swapgs+0x7b/0x80


Code: e8 37 85 f2 ff 48 83 c4 18 5b c9 c3 55 48 89 e5 41 54 53 48 83

Quoted 9 lines

ec 10 66 66 90 66 90 65 48 8b 04 25 28 00 00 00 48 89 45 e8 31 c0 <48> 8b 5f 28 49 89 f4 eb 14 48 8b 7b 18 4c 89 e6 e8 25 e8 25 00 RIP [<ffffffff80337af4>] sysfs_find_dirent+0x1f/0x5f
RSP <ffff8104238f7708>
CR2: 0000000000000028
---[ end trace 4ca22418d73866ec ]---
may need create mptsas that only call pci_disable_msi

It would be strange for an interrupt-disabling problem to cause sysfs to go oops?

Yinghai Lu

2008-05-07 23:40 UTC #3 lore raw

Quoted 161 lines · Andrew Morton

Quoted 60 lines · On Tue, 22 Apr 2008 20:12:08 -0700 "Yinghai Lu" <[email protected]> wrote:

Quoted 47 lines · Yinghai Lu
this change
 | commit 23a274c8a5adafc74a66f16988776fc7dd6f6e51
 | Author: Prakash, Sathya <[email protected]>
 | Date:   Fri Mar 7 15:53:21 2008 +0530
 |
 |     [SCSI] mpt fusion: Enable MSI by default for SAS controllers
 |
 |     This patch modifies the driver to enable MSI by default for all SAS chips.
 |
cause kexec RHEL 5.1 kernel fail.
root casue: the rhel 5.1 kernel still use INTx emulation.
and mptscsih_shutdown doesn't call pci_disable_msi to reenable INTx on kexec path
so try to call mptsas_remove in mptsas_shutdown.
then pci_disable_msi will be called via mptsas_remove==>mptscih_remove==> mpt_detach.
Signed-off-by Yinghai Lu <[email protected]>
CC Prakash, Sathya <[email protected]>
CC "Moore, Eric" <[email protected]>
Index: linux-2.6/drivers/message/fusion/mptsas.c
===================================================================
--- linux-2.6.orig/drivers/message/fusion/mptsas.c +++ linux-2.6/drivers/message/fusion/mptsas.c
@@ -3327,6 +3327,11 @@ static void __devexit mptsas_remove(stru
        mptscsih_remove(pdev);
}
+static void mptsas_shutdown(struct pci_dev *pdev)
+{
+ mptsas_remove(pdev);
+}
+
static struct pci_device_id mptsas_pci_table[] = {
{ PCI_VENDOR_ID_LSI_LOGIC, MPI_MANUFACTPAGE_DEVID_SAS1064,
PCI_ANY_ID, PCI_ANY_ID },
@@ -3348,7 +3353,7 @@ static struct pci_driver mptsas_driver =
        .id_table       = mptsas_pci_table,
        .probe          = mptsas_probe,
        .remove         = __devexit_p(mptsas_remove),
 -       .shutdown       = mptscsih_shutdown,
 +       .shutdown       = mptsas_shutdown,
Quoted 4 lines
#ifdef CONFIG_PM
.suspend = mptscsih_suspend,
.resume = mptscsih_resume,
--
fail on one system with big sas expander...
LBSuse:~ # mkdir /xx
LBSuse:~ # mount /dev/sdl1 /xx
LBSuse:~ # cd /xx
LBSuse:/xx # sh kk_rh_5.1
LBSuse:/xx # ./kexec -e

Quoted 7 lines

BUG: unable to handle kernel NULL pointer dereference at 0000000000000028
IP: [<ffffffff80337af4>] sysfs_find_dirent+0x1f/0x5f
PGD 41f137067 PUD 424482067 PMD 0
Oops: 0000 [1] SMP
CPU 7
Modules linked in:

Pid: 7534, comm: kexec Not tainted

I don't understand your email.

Are you saying that this oops is the thing which your patch fixes?

Or are you saying that this oops occurs even after your patch is applied? That we have a second regression?

Quoted 80 lines

2.6.25-sched-devel.git-x86-latest.git-03823-g1508ed0-dirty #135

RIP: 0010:[<ffffffff80337af4>]  [<ffffffff80337af4>] sysfs_find_dirent+0x1f/0x5f
RSP: 0018:ffff8104238f7708  EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffffffff80cd36a5 RCX: 000000008c0f362e
RDX: ffffffff80e20ab0 RSI: ffffffff80cd36a5 RDI: 0000000000000000
RBP: ffff8104238f7728 R08: 0000000000000000 R09: 000000008c0f362e
R10: ffff8104238f77f8 R11: 000000008c0f362e R12: 0000000000000000
R13: ffff810223190358 R14: 0000000000000000 R15: 0000000000000000
FS:  00007fde8859d6f0(0000) GS:ffff810427039f00(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 0000000000000028 CR3: 00000004238b8000 CR4: 00000000000006e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process kexec (pid: 7534, threadinfo ffff8104238f6000, task ffff8104238e0000)
Stack:  0000000000000000 000000008c0f362e ffffffff80cd36a5 0000000000000000
 ffff8104238f7758 ffffffff80337b70 000000008c0f362e 000000008c0f362e
 ffff810223190268 ffffffff80e1fb20 ffff8104238f7798 ffffffff8033966e
Call Trace:
 [<ffffffff80337b70>] sysfs_get_dirent+0x3c/0x72
 [<ffffffff8033966e>] sysfs_remove_group+0x38/0xb4
 [<ffffffff80633007>] dpm_sysfs_remove+0x2f/0x45
 [<ffffffff806336d3>] device_pm_remove+0x34/0x85
 [<ffffffff8062b283>] device_del+0x30/0x1b0
 [<ffffffff8062b428>] device_unregister+0x25/0x48
 [<ffffffff80639e73>] enclosure_unregister+0x85/0xcb
 [<ffffffff807dad42>] ses_intf_remove+0x8b/0xa8
 [<ffffffff8062b2fb>] device_del+0xa8/0x1b0
 [<ffffffff8062b428>] device_unregister+0x25/0x48
 [<ffffffff80700bb4>] __scsi_remove_device+0x4c/0xaf
 [<ffffffff80700c50>] scsi_remove_device+0x39/0x5c
 [<ffffffff80700d15>] __scsi_remove_target+0xa2/0xf6
 [<ffffffff80700de0>] ? __remove_child+0x0/0x4f
 [<ffffffff80700e12>] __remove_child+0x32/0x4f
 [<ffffffff8062ab27>] ? next_device+0x21/0x45
 [<ffffffff8062ac23>] device_for_each_child+0x40/0x84
 [<ffffffff80713d8e>] ? do_sas_phy_delete+0x0/0x66
 [<ffffffff80700dbc>] scsi_remove_target+0x53/0x77
 [<ffffffff807134b0>] sas_rphy_remove+0x42/0x81
 [<ffffffff80713514>] sas_rphy_delete+0x25/0x48
 [<ffffffff80713570>] sas_port_delete+0x39/0x147
 [<ffffffff802259e0>] ? mcount_call+0x5/0x35
 [<ffffffff80713d8e>] ? do_sas_phy_delete+0x0/0x66
 [<ffffffff80713dc2>] do_sas_phy_delete+0x34/0x66
 [<ffffffff8062ac23>] device_for_each_child+0x40/0x84
 [<ffffffff80713d8e>] ? do_sas_phy_delete+0x0/0x66
 [<ffffffff8071343f>] sas_remove_children+0x2e/0x5d
 [<ffffffff807134b7>] sas_rphy_remove+0x49/0x81
 [<ffffffff80713514>] sas_rphy_delete+0x25/0x48
 [<ffffffff80713570>] sas_port_delete+0x39/0x147
 [<ffffffff802259e0>] ? mcount_call+0x5/0x35
 [<ffffffff80713d8e>] ? do_sas_phy_delete+0x0/0x66
 [<ffffffff80713dc2>] do_sas_phy_delete+0x34/0x66
 [<ffffffff8062ac23>] device_for_each_child+0x40/0x84
 [<ffffffff8071343f>] sas_remove_children+0x2e/0x5d
 [<ffffffff807136a6>] sas_remove_host+0x28/0x3e
 [<ffffffff80ab22ab>] mptsas_remove+0x46/0x107
 [<ffffffff802259e0>] ? mcount_call+0x5/0x35
 [<ffffffff8080ef6d>] mptsas_shutdown+0x21/0x37
 [<ffffffff805a6815>] pci_device_shutdown+0x37/0x4d
 [<ffffffff8062a2ad>] device_shutdown+0x64/0xa0
 [<ffffffff8027e57f>] ? blocking_notifier_call_chain+0x27/0x3d
 [<ffffffff8027131e>] kernel_restart_prepare+0x3f/0x5a
 [<ffffffff802716f7>] sys_reboot+0x172/0x1cb
 [<ffffffff802e2ac0>] ? __fput+0x158/0x17b
 [<ffffffff802efc4e>] ? vfs_ioctl+0x3e/0xa2
 [<ffffffff802e2ef0>] ? fput+0x2c/0x42
 [<ffffffff802df2d2>] ? filp_close+0x78/0x9a
 [<ffffffff802df0b4>] ? __put_unused_fd+0x33/0x60
 [<ffffffff802e0bed>] ? sys_close+0x8c/0xdf
 [<ffffffff80225b9b>] system_call_after_swapgs+0x7b/0x80


Code: e8 37 85 f2 ff 48 83 c4 18 5b c9 c3 55 48 89 e5 41 54 53 48 83

---[ end trace 4ca22418d73866ec ]---

Quoted 5 lines

Quoted 2 lines
may need create mptsas that only call pci_disable_msi
It would be strange for an interrupt-disabling problem to cause sysfs to go oops?

andrew, updated version has been merged...

James Bottomley

maintainer

2008-05-07 23:50 UTC #4 lore raw

In reply to Andrew Morton

Quoted 71 lines · Andrew Morton

Quoted 60 lines · On Tue, 22 Apr 2008 20:12:08 -0700 "Yinghai Lu" <[email protected]> wrote:
Quoted 47 lines · Yinghai Lu
this change
 | commit 23a274c8a5adafc74a66f16988776fc7dd6f6e51
 | Author: Prakash, Sathya <[email protected]>
 | Date:   Fri Mar 7 15:53:21 2008 +0530
 |
 |     [SCSI] mpt fusion: Enable MSI by default for SAS controllers
 |
 |     This patch modifies the driver to enable MSI by default for all SAS chips.
 |
cause kexec RHEL 5.1 kernel fail.
root casue: the rhel 5.1 kernel still use INTx emulation.
and mptscsih_shutdown doesn't call pci_disable_msi to reenable INTx on kexec path
so try to call mptsas_remove in mptsas_shutdown.
then pci_disable_msi will be called via mptsas_remove==>mptscih_remove==> mpt_detach.
Signed-off-by Yinghai Lu <[email protected]>
CC Prakash, Sathya <[email protected]>
CC "Moore, Eric" <[email protected]>
Index: linux-2.6/drivers/message/fusion/mptsas.c
===================================================================
--- linux-2.6.orig/drivers/message/fusion/mptsas.c +++ linux-2.6/drivers/message/fusion/mptsas.c
@@ -3327,6 +3327,11 @@ static void __devexit mptsas_remove(stru
        mptscsih_remove(pdev);
}
+static void mptsas_shutdown(struct pci_dev *pdev)
+{
+ mptsas_remove(pdev);
+}
+
static struct pci_device_id mptsas_pci_table[] = {
{ PCI_VENDOR_ID_LSI_LOGIC, MPI_MANUFACTPAGE_DEVID_SAS1064,
PCI_ANY_ID, PCI_ANY_ID },
@@ -3348,7 +3353,7 @@ static struct pci_driver mptsas_driver =
        .id_table       = mptsas_pci_table,
        .probe          = mptsas_probe,
        .remove         = __devexit_p(mptsas_remove),
 -       .shutdown       = mptscsih_shutdown,
 +       .shutdown       = mptsas_shutdown,
Quoted 4 lines
#ifdef CONFIG_PM
.suspend = mptscsih_suspend,
.resume = mptscsih_resume,
--
fail on one system with big sas expander...
LBSuse:~ # mkdir /xx LBSuse:~ # mount /dev/sdl1 /xx LBSuse:~ # cd /xx
LBSuse:/xx # sh kk_rh_5.1 LBSuse:/xx # ./kexec -e
Quoted 7 lines
BUG: unable to handle kernel NULL pointer dereference at 0000000000000028
IP: [<ffffffff80337af4>] sysfs_find_dirent+0x1f/0x5f
PGD 41f137067 PUD 424482067 PMD 0
Oops: 0000 [1] SMP
CPU 7
Modules linked in:
Pid: 7534, comm: kexec Not tainted

Quoted 6 lines

I don't understand your email.
Are you saying that this oops is the thing which your patch fixes?
Or are you saying that this oops occurs even after your patch is applied? That we have a second regression?

The regression is actually PCI generic, not mpt specific. It was fixed by this commit:

commit d52877c7b1afb8c37ebe17e2005040b79cb618b0

Author: Yinghai Lu <[email protected]>
Date:   Wed Apr 23 14:58:09 2008 -0700

pci/irq: let pci_device_shutdown to call pci_msi_shutdown v2

James