Skip to contentSkip to conversation

fix vt-d hard lockup when hotplug ATS capable device

RFC PATCH Superseded Ethan Zhao 1 participant 6 messages Dec 22, 2023 – Dec 23, 2023

Subsystems (3)

v5 of 14 Superseded Latest is v14 →

lore
Share & tools
lore

Ethan Zhao

author
#0 lore raw

v5 cover fix vt-d hard lockup when hotplug ATS capable device

Hi,folks

This patchset is used to fix vt-d hard lockup reported when surpprise unplug ATS capable endpoint device connects to system via PCIe switch as following topology.

     +-[0000:15]-+-00.0  Intel Corporation Ice Lake Memory Map/VT-d                 
     |           +-00.1  Intel Corporation Ice Lake Mesh 2 PCIe                     
     |           +-00.2  Intel Corporation Ice Lake RAS                             
     |           +-00.4  Intel Corporation Device 0b23                              
     |           \-01.0-[16-1b]----00.0-[17-1b]--+-00.0-[18]----00.0                
                                           NVIDIA Corporation Device 2324           
     |                                           +-01.0-[19]----00.0                
                          Mellanox Technologies MT2910 Family [ConnectX-7]          

User brought endpoint device 19:00.0's link down by flapping it's hotplug capable slot 17:01.0 link control register, as sequence DLLSC response, pciehp_ist() will unload device driver and power it off, durning device driver is unloading an iommu devTlb flush request issued to that link down device, thus a long time completion/timeout waiting in interrupt context causes continuous hard lockup warnning and system hang.

[ 4211.433662] pcieport 0000:17:01.0: pciehp: Slot(108): Link Down                  
[ 4211.433664] pcieport 0000:17:01.0: pciehp: Slot(108): Card not present           
[ 4223.822591] NMI watchdog: Watchdog detected hard LOCKUP on cpu 144               
[ 4223.822622] CPU: 144 PID: 1422 Comm: irq/57-pciehp Kdump: loaded Tainted: G S 
         OE    kernel version xxxx                                                  
[ 4223.822623] Hardware name: vendorname xxxx 666-106,                              
BIOS 01.01.02.03.01 05/15/2023                                                      
[ 4223.822623] RIP: 0010:qi_submit_sync+0x2c0/0x490                                 
[ 4223.822624] Code: 48 be 00 00 00 00 00 08 00 00 49 85 74 24 20 0f 95 c1 48 8b  
 57 10 83 c1 04 83 3c 1a 03 0f 84 a2 01 00 00 49 8b 04 24 8b 70 34 <40> f6 c6 1   
0 74 17 49 8b 04 24 8b 80 80 00 00 00 89 c2 d3 fa 41 39                             
[ 4223.822624] RSP: 0018:ffffc4f074f0bbb8 EFLAGS: 00000093                          
[ 4223.822625] RAX: ffffc4f040059000 RBX: 0000000000000014 RCX: 0000000000000005 
[ 4223.822625] RDX: ffff9f3841315800 RSI: 0000000000000000 RDI: ffff9f38401a8340 
[ 4223.822625] RBP: ffff9f38401a8340 R08: ffffc4f074f0bc00 R09: 0000000000000000 
[ 4223.822626] R10: 0000000000000010 R11: 0000000000000018 R12: ffff9f384005e200 
[ 4223.822626] R13: 0000000000000004 R14: 0000000000000046 R15: 0000000000000004 
[ 4223.822626] FS:  0000000000000000(0000) GS:ffffa237ae400000(0000)                
knlGS:0000000000000000                                                              
[ 4223.822627] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033                    
[ 4223.822627] CR2: 00007ffe86515d80 CR3: 000002fd3000a001 CR4: 0000000000770ee0 
[ 4223.822627] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 
[ 4223.822628] DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400 
[ 4223.822628] PKRU: 55555554                                                       
[ 4223.822628] Call Trace:                                                          
[ 4223.822628]  qi_flush_dev_iotlb+0xb1/0xd0                                        
[ 4223.822628]  __dmar_remove_one_dev_info+0x224/0x250                              
[ 4223.822629]  dmar_remove_one_dev_info+0x3e/0x50                                  
[ 4223.822629]  intel_iommu_release_device+0x1f/0x30                                
[ 4223.822629]  iommu_release_device+0x33/0x60                                      
[ 4223.822629]  iommu_bus_notifier+0x7f/0x90                                        
[ 4223.822630]  blocking_notifier_call_chain+0x60/0x90                              
[ 4223.822630]  device_del+0x2e5/0x420                                              
[ 4223.822630]  pci_remove_bus_device+0x70/0x110                                    
[ 4223.822630]  pciehp_unconfigure_device+0x7c/0x130                                
[ 4223.822631]  pciehp_disable_slot+0x6b/0x100                                      
[ 4223.822631]  pciehp_handle_presence_or_link_change+0xd8/0x320                    
[ 4223.822631]  pciehp_ist+0x176/0x180                                              
[ 4223.822631]  ? irq_finalize_oneshot.part.50+0x110/0x110
[ 4223.822632]  irq_thread_fn+0x19/0x50                                          
[ 4223.822632]  irq_thread+0x104/0x190                                           
[ 4223.822632]  ? irq_forced_thread_fn+0x90/0x90                                 
[ 4223.822632]  ? irq_thread_check_affinity+0xe0/0xe0                            
[ 4223.822633]  kthread+0x114/0x130                                              
[ 4223.822633]  ? __kthread_cancel_work+0x40/0x40                                
[ 4223.822633]  ret_from_fork+0x1f/0x30                                          
[ 4223.822633] Kernel panic - not syncing: Hard LOCKUP                           
[ 4223.822634] CPU: 144 PID: 1422 Comm: irq/57-pciehp Kdump: loaded Tainted: G S 
         OE     kernel version xxxx                                              
[ 4223.822634] Hardware name: vendorname xxxx 666-106,                           
BIOS 01.01.02.03.01 05/15/2023                                                   
[ 4223.822634] Call Trace:                                                       
[ 4223.822634]  <NMI>                                                            
[ 4223.822635]  dump_stack+0x6d/0x88                                             
[ 4223.822635]  panic+0x101/0x2d0                                                
[ 4223.822635]  ? ret_from_fork+0x11/0x30                                        
[ 4223.822635]  nmi_panic.cold.14+0xc/0xc                                        
[ 4223.822636]  watchdog_overflow_callback.cold.8+0x6d/0x81                      
[ 4223.822636]  __perf_event_overflow+0x4f/0xf0                                  
[ 4223.822636]  handle_pmi_common+0x1ef/0x290                                    
[ 4223.822636]  ? __set_pte_vaddr+0x28/0x40                                      
[ 4223.822637]  ? flush_tlb_one_kernel+0xa/0x20                                  
[ 4223.822637]  ? __native_set_fixmap+0x24/0x30                                  
[ 4223.822637]  ? ghes_copy_tofrom_phys+0x70/0x100                               
[ 4223.822637]  ? __ghes_peek_estatus.isra.16+0x49/0xa0                          
[ 4223.822637]  intel_pmu_handle_irq+0xba/0x2b0                                  
[ 4223.822638]  perf_event_nmi_handler+0x24/0x40                                 
[ 4223.822638]  nmi_handle+0x4d/0xf0                                             
[ 4223.822638]  default_do_nmi+0x49/0x100                                        
[ 4223.822638]  exc_nmi+0x134/0x180                                              
[ 4223.822639]  end_repeat_nmi+0x16/0x67                                         
[ 4223.822639] RIP: 0010:qi_submit_sync+0x2c0/0x490                              
[ 4223.822639] Code: 48 be 00 00 00 00 00 08 00 00 49 85 74 24 20 0f 95 c1 48 8b 
 57 10 83 c1 04 83 3c 1a 03 0f 84 a2 01 00 00 49 8b 04 24 8b 70 34 <40> f6 c6 10 
 74 17 49 8b 04 24 8b 80 80 00 00 00 89 c2 d3 fa 41 39                           
[ 4223.822640] RSP: 0018:ffffc4f074f0bbb8 EFLAGS: 00000093                       
[ 4223.822640] RAX: ffffc4f040059000 RBX: 0000000000000014 RCX: 0000000000000005 
[ 4223.822640] RDX: ffff9f3841315800 RSI: 0000000000000000 RDI: ffff9f38401a8340 
[ 4223.822641] RBP: ffff9f38401a8340 R08: ffffc4f074f0bc00 R09: 0000000000000000 
[ 4223.822641] R10: 0000000000000010 R11: 0000000000000018 R12: ffff9f384005e200 
[ 4223.822641] R13: 0000000000000004 R14: 0000000000000046 R15: 0000000000000004 
[ 4223.822641]  ? qi_submit_sync+0x2c0/0x490                                     
[ 4223.822642]  ? qi_submit_sync+0x2c0/0x490                                     
[ 4223.822642]  </NMI>                                                           
[ 4223.822642]  qi_flush_dev_iotlb+0xb1/0xd0                                     
[ 4223.822642]  __dmar_remove_one_dev_info+0x224/0x250                           
[ 4223.822643]  dmar_remove_one_dev_info+0x3e/0x50                               
[ 4223.822643]  intel_iommu_release_device+0x1f/0x30                             
[ 4223.822643]  iommu_release_device+0x33/0x60                                   
[ 4223.822643]  iommu_bus_notifier+0x7f/0x90                                     
[ 4223.822644]  blocking_notifier_call_chain+0x60/0x90                           
[ 4223.822644]  device_del+0x2e5/0x420                                           
[ 4223.822644]  pci_remove_bus_device+0x70/0x110                                 
[ 4223.822644]  pciehp_unconfigure_device+0x7c/0x130                             
[ 4223.822644]  pciehp_disable_slot+0x6b/0x100                                   
[ 4223.822645]  pciehp_handle_presence_or_link_change+0xd8/0x320                 
[ 4223.822645]  pciehp_ist+0x176/0x180                                           
[ 4223.822645]  ? irq_finalize_oneshot.part.50+0x110/0x110                       
[ 4223.822645]  irq_thread_fn+0x19/0x50                                          
[ 4223.822646]  irq_thread+0x104/0x190                                           
[ 4223.822646]  ? irq_forced_thread_fn+0x90/0x90                                 
[ 4223.822646]  ? irq_thread_check_affinity+0xe0/0xe0                            
[ 4223.822646]  kthread+0x114/0x130           
[ 4223.822647] Kernel Offset: 0x6400000 from 0xffffffff81000000 (relocation      

range: 0xffffffff80000000-0xffffffffbfffffff)

Make a quick fix by checking the device's error_state in devtlb_invalidation_with_pasid() to avoid sending meaningless devTLB flush request to link down device that is set to pci_channel_io_perm_failure and then powered off in

pciehp_ist()
pciehp_handle_presence_or_link_change()
pciehp_disable_slot()
remove_board()
pciehp_unconfigure_device()

safe_removal unplug doesn't trigger such issue.
and this fix works for all supprise_removal unplug operation.

patchset [patch 1&2] was tested by [email protected] on stable-6.7rc4. patch[3] only passed compiling on stable-6.7rc4, not test yet.

change log:
v5:
- add a patch try to fix the rare case (supprise-remove a device in safe_removal process).
v4:
- move the PCI device state checking after ATS per Baolu's suggestion. v3:
- fix commit description typo.
v2:
- revise commit[1] description part according to Lukas' suggestion.
- revise commit[2] description to clarify the issue's impact.
v1:
- https://lore.kernel.org/lkml/[email protected]/T/

Thanks,
Ethan

Ethan Zhao (3):
PCI: make pci_dev_is_disconnected() helper public for other drivers iommu/vt-d: don's issue devTLB flush request when device is
disconnected
iommu/vt-d: abort the devTLB invalidation waiting if device is removed

 drivers/iommu/intel/dmar.c  |  3 ++-
 drivers/iommu/intel/iommu.c | 37 +++++++++++++++++++++++++++++++++++++
 drivers/iommu/intel/pasid.c |  3 +++
 drivers/pci/pci.h           |  5 -----
 include/linux/pci.h         |  5 +++++
 5 files changed, 47 insertions(+), 6 deletions(-)
Signature · 1 line
2.31.1
author
#1 lore raw

RFC PATCH v5 1/3 PCI: make pci_dev_is_disconnected() helper public for other drivers

move pci_dev_is_disconnected() from driver/pci/pci.h to public include/linux/pci.h for other driver's reference.
no function change.

---
 drivers/pci/pci.h   | 5 -----
 include/linux/pci.h | 5 +++++
 2 files changed, 5 insertions(+), 5 deletions(-)
drivers/pci/pci.h +0 -5
index 5ecbcf041179..75fa2084492f 100644
@@ -366,11 +366,6 @@ static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused)
 	return 0;
 }
 
-static inline bool pci_dev_is_disconnected(const struct pci_dev *dev)
-{
-	return dev->error_state == pci_channel_io_perm_failure;
-}
-
 /* pci_dev priv_flags */
 #define PCI_DEV_ADDED 0
 #define PCI_DPC_RECOVERED 1
include/linux/pci.h +5 -0
index 60ca768bc867..869f2ec97a84 100644
@@ -2503,6 +2503,11 @@ static inline struct pci_dev *pcie_find_root_port(struct pci_dev *dev)
 	return NULL;
 }
 
+static inline bool pci_dev_is_disconnected(const struct pci_dev *dev)
+{
+	return dev->error_state == pci_channel_io_perm_failure;
+}
+
 void pci_request_acs(void);
 bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags);
 bool pci_acs_path_enabled(struct pci_dev *start,
Signature · 1 line
2.31.1
author
#2 lore raw

RFC PATCH v5 2/3 iommu/vt-d: don's issue devTLB flush request when device is disconnected

In reply to Ethan Zhao

For those endpoint devices connect to system via hotplug capable ports, users could request a warm reset to the device by flapping device's link through setting the slot's link control register, as pciehpt_ist() DLLSC interrupt sequence response, pciehp will unload the device driver and then power it off. thus cause an IOMMU devTLB flush request for device to be sent and a long time completion/timeout waiting in interrupt context.

That would cause following continuous hard lockup warning and system hang

[ 4211.433662] pcieport 0000:17:01.0: pciehp: Slot(108): Link Down
[ 4211.433664] pcieport 0000:17:01.0: pciehp: Slot(108): Card not present
[ 4223.822591] NMI watchdog: Watchdog detected hard LOCKUP on cpu 144
[ 4223.822622] CPU: 144 PID: 1422 Comm: irq/57-pciehp Kdump: loaded Tainted: G S
         OE    kernel version xxxx
[ 4223.822623] Hardware name: vendorname xxxx 666-106,
BIOS 01.01.02.03.01 05/15/2023
[ 4223.822623] RIP: 0010:qi_submit_sync+0x2c0/0x490
[ 4223.822624] Code: 48 be 00 00 00 00 00 08 00 00 49 85 74 24 20 0f 95 c1 48 8b
 57 10 83 c1 04 83 3c 1a 03 0f 84 a2 01 00 00 49 8b 04 24 8b 70 34 <40> f6 c6 1
0 74 17 49 8b 04 24 8b 80 80 00 00 00 89 c2 d3 fa 41 39
[ 4223.822624] RSP: 0018:ffffc4f074f0bbb8 EFLAGS: 00000093
[ 4223.822625] RAX: ffffc4f040059000 RBX: 0000000000000014 RCX: 0000000000000005
[ 4223.822625] RDX: ffff9f3841315800 RSI: 0000000000000000 RDI: ffff9f38401a8340
[ 4223.822625] RBP: ffff9f38401a8340 R08: ffffc4f074f0bc00 R09: 0000000000000000
[ 4223.822626] R10: 0000000000000010 R11: 0000000000000018 R12: ffff9f384005e200
[ 4223.822626] R13: 0000000000000004 R14: 0000000000000046 R15: 0000000000000004
[ 4223.822626] FS:  0000000000000000(0000) GS:ffffa237ae400000(0000)
knlGS:0000000000000000
[ 4223.822627] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 4223.822627] CR2: 00007ffe86515d80 CR3: 000002fd3000a001 CR4: 0000000000770ee0
[ 4223.822627] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 4223.822628] DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400
[ 4223.822628] PKRU: 55555554
[ 4223.822628] Call Trace:
[ 4223.822628]  qi_flush_dev_iotlb+0xb1/0xd0
[ 4223.822628]  __dmar_remove_one_dev_info+0x224/0x250
[ 4223.822629]  dmar_remove_one_dev_info+0x3e/0x50
[ 4223.822629]  intel_iommu_release_device+0x1f/0x30
[ 4223.822629]  iommu_release_device+0x33/0x60
[ 4223.822629]  iommu_bus_notifier+0x7f/0x90
[ 4223.822630]  blocking_notifier_call_chain+0x60/0x90
[ 4223.822630]  device_del+0x2e5/0x420
[ 4223.822630]  pci_remove_bus_device+0x70/0x110
[ 4223.822630]  pciehp_unconfigure_device+0x7c/0x130
[ 4223.822631]  pciehp_disable_slot+0x6b/0x100
[ 4223.822631]  pciehp_handle_presence_or_link_change+0xd8/0x320
[ 4223.822631]  pciehp_ist+0x176/0x180
[ 4223.822631]  ? irq_finalize_oneshot.part.50+0x110/0x110
[ 4223.822632]  irq_thread_fn+0x19/0x50
[ 4223.822632]  irq_thread+0x104/0x190
[ 4223.822632]  ? irq_forced_thread_fn+0x90/0x90
[ 4223.822632]  ? irq_thread_check_affinity+0xe0/0xe0
[ 4223.822633]  kthread+0x114/0x130
[ 4223.822633]  ? __kthread_cancel_work+0x40/0x40
[ 4223.822633]  ret_from_fork+0x1f/0x30
[ 4223.822633] Kernel panic - not syncing: Hard LOCKUP
[ 4223.822634] CPU: 144 PID: 1422 Comm: irq/57-pciehp Kdump: loaded Tainted: G S
         OE     kernel version xxxx
[ 4223.822634] Hardware name: vendorname xxxx 666-106,
BIOS 01.01.02.03.01 05/15/2023
[ 4223.822634] Call Trace:
[ 4223.822634]  <NMI>
[ 4223.822635]  dump_stack+0x6d/0x88
[ 4223.822635]  panic+0x101/0x2d0
[ 4223.822635]  ? ret_from_fork+0x11/0x30
[ 4223.822635]  nmi_panic.cold.14+0xc/0xc
[ 4223.822636]  watchdog_overflow_callback.cold.8+0x6d/0x81
[ 4223.822636]  __perf_event_overflow+0x4f/0xf0
[ 4223.822636]  handle_pmi_common+0x1ef/0x290
[ 4223.822636]  ? __set_pte_vaddr+0x28/0x40
[ 4223.822637]  ? flush_tlb_one_kernel+0xa/0x20
[ 4223.822637]  ? __native_set_fixmap+0x24/0x30
[ 4223.822637]  ? ghes_copy_tofrom_phys+0x70/0x100
[ 4223.822637]  ? __ghes_peek_estatus.isra.16+0x49/0xa0
[ 4223.822637]  intel_pmu_handle_irq+0xba/0x2b0
[ 4223.822638]  perf_event_nmi_handler+0x24/0x40
[ 4223.822638]  nmi_handle+0x4d/0xf0
[ 4223.822638]  default_do_nmi+0x49/0x100
[ 4223.822638]  exc_nmi+0x134/0x180
[ 4223.822639]  end_repeat_nmi+0x16/0x67
[ 4223.822639] RIP: 0010:qi_submit_sync+0x2c0/0x490
[ 4223.822639] Code: 48 be 00 00 00 00 00 08 00 00 49 85 74 24 20 0f 95 c1 48 8b
 57 10 83 c1 04 83 3c 1a 03 0f 84 a2 01 00 00 49 8b 04 24 8b 70 34 <40> f6 c6 10
 74 17 49 8b 04 24 8b 80 80 00 00 00 89 c2 d3 fa 41 39
[ 4223.822640] RSP: 0018:ffffc4f074f0bbb8 EFLAGS: 00000093
[ 4223.822640] RAX: ffffc4f040059000 RBX: 0000000000000014 RCX: 0000000000000005
[ 4223.822640] RDX: ffff9f3841315800 RSI: 0000000000000000 RDI: ffff9f38401a8340
[ 4223.822641] RBP: ffff9f38401a8340 R08: ffffc4f074f0bc00 R09: 0000000000000000
[ 4223.822641] R10: 0000000000000010 R11: 0000000000000018 R12: ffff9f384005e200
[ 4223.822641] R13: 0000000000000004 R14: 0000000000000046 R15: 0000000000000004
[ 4223.822641]  ? qi_submit_sync+0x2c0/0x490
[ 4223.822642]  ? qi_submit_sync+0x2c0/0x490
[ 4223.822642]  </NMI>
[ 4223.822642]  qi_flush_dev_iotlb+0xb1/0xd0
[ 4223.822642]  __dmar_remove_one_dev_info+0x224/0x250
[ 4223.822643]  dmar_remove_one_dev_info+0x3e/0x50
[ 4223.822643]  intel_iommu_release_device+0x1f/0x30
[ 4223.822643]  iommu_release_device+0x33/0x60
[ 4223.822643]  iommu_bus_notifier+0x7f/0x90
[ 4223.822644]  blocking_notifier_call_chain+0x60/0x90
[ 4223.822644]  device_del+0x2e5/0x420
[ 4223.822644]  pci_remove_bus_device+0x70/0x110
[ 4223.822644]  pciehp_unconfigure_device+0x7c/0x130
[ 4223.822644]  pciehp_disable_slot+0x6b/0x100
[ 4223.822645]  pciehp_handle_presence_or_link_change+0xd8/0x320
[ 4223.822645]  pciehp_ist+0x176/0x180
[ 4223.822645]  ? irq_finalize_oneshot.part.50+0x110/0x110
[ 4223.822645]  irq_thread_fn+0x19/0x50
[ 4223.822646]  irq_thread+0x104/0x190
[ 4223.822646]  ? irq_forced_thread_fn+0x90/0x90
[ 4223.822646]  ? irq_thread_check_affinity+0xe0/0xe0
[ 4223.822646]  kthread+0x114/0x130
[ 4223.822647]  ? __kthread_cancel_work+0x40/0x40
[ 4223.822647]  ret_from_fork+0x1f/0x30
[ 4223.822647] Kernel Offset: 0x6400000 from 0xffffffff81000000 (relocation

range: 0xffffffff80000000-0xffffffffbfffffff)

Fix it by checking the device's error_state in devtlb_invalidation_with_pasid() to avoid sending meaningless devTLB flush request to link down device that is set to pci_channel_io_perm_failure and then powered off in

pciehp_ist()
pciehp_handle_presence_or_link_change()
pciehp_disable_slot()
remove_board()
pciehp_unconfigure_device()

For SAVE_REMOVAL unplug, link is alive when iommu releases devcie and issues devTLB invalidate request, wouldn't trigger such issue.

This patch works for all links of SURPPRISE_REMOVAL unplug operations.

---
 drivers/iommu/intel/pasid.c | 3 +++
 1 file changed, 3 insertions(+)
drivers/iommu/intel/pasid.c +3 -0
index 74e8e4c17e81..7dbee9931eb6 100644
@@ -481,6 +481,9 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iommu,
 	if (!info || !info->ats_enabled)
 		return;
 
+	if (pci_dev_is_disconnected(to_pci_dev(dev)))
+		return;
+
 	sid = info->bus << 8 | info->devfn;
 	qdep = info->ats_qdep;
 	pfsid = info->pfsid;
Signature · 1 line
2.31.1
author
#3 lore raw

RFC PATCH v5 3/3 iommu/vt-d: abort the devTLB invalidation waiting if device is removed

In reply to Ethan Zhao

Even the devTLB invalidation request is just submitted and waiting it to be done/timeout in qi_submit_sync(), it is possible device is removed or powered-off. try to break it out in such rare but possible case.

This patch is sent for more comment. not tested, only passed compiling.

---
 drivers/iommu/intel/dmar.c  |  3 ++-
 drivers/iommu/intel/iommu.c | 36 ++++++++++++++++++++++++++++++++++++
 2 files changed, 38 insertions(+), 1 deletion(-)
drivers/iommu/intel/dmar.c +2 -1
index 23cb80d62a9a..d8637ab93387 100644
@@ -1422,7 +1422,8 @@ int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc,
 	 */
 	writel(qi->free_head << shift, iommu->reg + DMAR_IQT_REG);
 
-	while (qi->desc_status[wait_index] != QI_DONE) {
+	while (qi->desc_status[wait_index] != QI_DONE &&
+			qi->desc_status[wait_index] != QI_ABORT) {
 		/*
 		 * We will leave the interrupts disabled, to prevent interrupt
 		 * context to queue another cmd while a cmd is already submitted
drivers/iommu/intel/iommu.c +36 -0
index 897159dba47d..33075d0688bc 100644
@@ -4472,10 +4472,46 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 	return &iommu->iommu;
 }
 
+static void intel_iommu_abort_devtlib_invalidate(struct device *dev)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
+	struct q_inval *qi = iommu->qi;
+	struct qi_desc *desc, *idesc;
+	int index, offset, shift;
+	u16 sid, qdep, pfsid
+	unsigned long flags;
+
+	if (!dev_is_pci(info->dev) || !info->ats_enabled || !qi)
+		return;
+	if (!pci_dev_is_disconnected(to_pci_dev(dev)))
+		return;
+
+	sid = info->bus << 8 | info->devfn;
+	qdep = info->ats_qdep;
+	pfsid = info->pfsid;
+
+	raw_spin_lock_irqsave(&qi->q_lock, flags);
+	for (index = 1; index < QI_LENGTH; index++) {
+		offset = index << shift;
+		desc = qi->desc + offset;
+		if (desc->qw0 & QI_IWD_TYPE) {
+			offset = (index-1) << shift;
+			idesc = qi->desc + offset;
+			if (idesc->qw0 & QI_DEV_EIOTLB_SID(sid)) {
+				if (qi->desc_status[index] == QI_IN_USE)
+					qi->desc_status[index] = QI_ABORT;
+			}
+		}
+	}
+	raw_spin_unlock_irqrestore(&qi->q_lock, flags);
+
+}
 static void intel_iommu_release_device(struct device *dev)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 
+	intel_iommu_abort_devtlib_invalidate(dev);
 	dmar_remove_one_dev_info(dev);
 	intel_pasid_free_table(dev);
 	intel_iommu_debugfs_remove_dev(info);
Signature · 1 line
2.31.1
author
#4 lore raw

Re: [RFC PATCH v5 3/3] iommu/vt-d: abort the devTLB invalidation waiting if device is removed

Quoted 17 lines · Ethan Zhao

Even the devTLB invalidation request is just submitted and waiting it to be done/timeout in qi_submit_sync(), it is possible device is removed or powered-off. try to break it out in such rare but possible case.

This patch is sent for more comment. not tested, only passed compiling.

---
  drivers/iommu/intel/dmar.c  |  3 ++-
  drivers/iommu/intel/iommu.c | 36 ++++++++++++++++++++++++++++++++++++
  2 files changed, 38 insertions(+), 1 deletion(-)
drivers/iommu/intel/dmar.c +0 -0
index 23cb80d62a9a..d8637ab93387 100644

drivers/iommu/intel/dmar.c int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc, · line 1426

Quoted 6 lines
drivers/iommu/intel/dmar.c +2 -1
@@ -1422,7 +1422,8 @@ int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc,
  	 */
  	writel(qi->free_head << shift, iommu->reg + DMAR_IQT_REG);
 
-	while (qi->desc_status[wait_index] != QI_DONE) {
+	while (qi->desc_status[wait_index] != QI_DONE &&
+			qi->desc_status[wait_index] != QI_ABORT) {

Another way is checking pci_device_is_present() here and bail out,

how about it ?

Quoted 41 lines
drivers/iommu/intel/dmar.c +0 -0
  		/*
  		 * We will leave the interrupts disabled, to prevent interrupt
  		 * context to queue another cmd while a cmd is already submitted
drivers/iommu/intel/iommu.c +30 -0
index 897159dba47d..33075d0688bc 100644
@@ -4472,10 +4472,46 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
  	return &iommu->iommu;
  }
 
+static void intel_iommu_abort_devtlib_invalidate(struct device *dev)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
+	struct q_inval *qi = iommu->qi;
+	struct qi_desc *desc, *idesc;
+	int index, offset, shift;
+	u16 sid, qdep, pfsid
+	unsigned long flags;
+
+	if (!dev_is_pci(info->dev) || !info->ats_enabled || !qi)
+		return;
+	if (!pci_dev_is_disconnected(to_pci_dev(dev)))
+		return;
+
+	sid = info->bus << 8 | info->devfn;
+	qdep = info->ats_qdep;
+	pfsid = info->pfsid;
+
+	raw_spin_lock_irqsave(&qi->q_lock, flags);
+	for (index = 1; index < QI_LENGTH; index++) {
+		offset = index << shift;
+		desc = qi->desc + offset;
+		if (desc->qw0 & QI_IWD_TYPE) {
+			offset = (index-1) << shift;
+			idesc = qi->desc + offset;
+			if (idesc->qw0 & QI_DEV_EIOTLB_SID(sid)) {
+				if (qi->desc_status[index] == QI_IN_USE)
+					qi->desc_status[index] = QI_ABORT;
+			}

drivers/iommu/intel/iommu.c static struct iommu_device *intel_iommu_probe_device(struct device *dev) · line 4514

Quoted 10 lines
drivers/iommu/intel/iommu.c +6 -0
+		}
+	}
+	raw_spin_unlock_irqrestore(&qi->q_lock, flags);
+
+}
  static void intel_iommu_release_device(struct device *dev)
  {
  	struct device_domain_info *info = dev_iommu_priv_get(dev);
 
+	intel_iommu_abort_devtlib_invalidate(dev);

Wonder if there is lock something prevent pciehp_ist() supprise_removal

interrupt response re-enter to get here when another safe_removal is in process,

if so ,  see above

Quoted 3 lines
drivers/iommu/intel/iommu.c +0 -0
  	dmar_remove_one_dev_info(dev);
  	intel_pasid_free_table(dev);
  	intel_iommu_debugfs_remove_dev(info);
author
#5 lore raw

Re: [RFC PATCH v5 3/3] iommu/vt-d: abort the devTLB invalidation waiting if device is removed

Quoted 74 lines · Ethan Zhao
Quoted 17 lines · Ethan Zhao

Even the devTLB invalidation request is just submitted and waiting it to be done/timeout in qi_submit_sync(), it is possible device is removed or powered-off. try to break it out in such rare but possible case.

This patch is sent for more comment. not tested, only passed compiling.

---
  drivers/iommu/intel/dmar.c  |  3 ++- drivers/iommu/intel/iommu.c | 36 ++++++++++++++++++++++++++++++++++++

  2 files changed, 38 insertions(+), 1 deletion(-)
drivers/iommu/intel/dmar.c +0 -0
index 23cb80d62a9a..d8637ab93387 100644

drivers/iommu/intel/dmar.c int qi_submit_sync(struct intel_iommu *iommu, · line 1427

Quoted 6 lines
drivers/iommu/intel/dmar.c +2 -0
@@ -1422,7 +1422,8 @@ int qi_submit_sync(struct intel_iommu *iommu, 
 struct qi_desc *desc,
        */
       writel(qi->free_head << shift, iommu->reg + DMAR_IQT_REG);
   -    while (qi->desc_status[wait_index] != QI_DONE) {
+    while (qi->desc_status[wait_index] != QI_DONE &&
+            qi->desc_status[wait_index] != QI_ABORT) {

Another way is checking pci_device_is_present() here and bail out,

how about it ?

Quoted 44 lines
drivers/iommu/intel/dmar.c +0 -0
           /*
            * We will leave the interrupts disabled, to prevent interrupt

           * context to queue another cmd while a cmd is already submitted

drivers/iommu/intel/iommu.c +32 -0
index 897159dba47d..33075d0688bc 100644
@@ -4472,10 +4472,46 @@ static struct iommu_device 
 *intel_iommu_probe_device(struct device *dev)
       return &iommu->iommu;
   }
   +static void intel_iommu_abort_devtlib_invalidate(struct device *dev)
+{
+    struct device_domain_info *info = dev_iommu_priv_get(dev);
+    struct intel_iommu *iommu = info->iommu;
+    struct q_inval *qi = iommu->qi;
+    struct qi_desc *desc, *idesc;
+    int index, offset, shift;
+    u16 sid, qdep, pfsid
+    unsigned long flags;
+
+    if (!dev_is_pci(info->dev) || !info->ats_enabled || !qi)
+        return;
+    if (!pci_dev_is_disconnected(to_pci_dev(dev)))
+        return;
+
+    sid = info->bus << 8 | info->devfn;
+    qdep = info->ats_qdep;
+    pfsid = info->pfsid;
+
+    raw_spin_lock_irqsave(&qi->q_lock, flags);
+    for (index = 1; index < QI_LENGTH; index++) {
+        offset = index << shift;
+        desc = qi->desc + offset;
+        if (desc->qw0 & QI_IWD_TYPE) {
+            offset = (index-1) << shift;
+            idesc = qi->desc + offset;
+            if (idesc->qw0 & QI_DEV_EIOTLB_SID(sid)) {
+                if (qi->desc_status[index] == QI_IN_USE)
+                    qi->desc_status[index] = QI_ABORT;
+            }
+        }
+    }
+    raw_spin_unlock_irqrestore(&qi->q_lock, flags);
Quoted 8 lines

drivers/iommu/intel/iommu.c static struct iommu_device *intel_iommu_probe_device(struct device *dev)

Quoted 6 lines
drivers/iommu/intel/iommu.c +2 -0
+
+}
   static void intel_iommu_release_device(struct device *dev)
   {
       struct device_domain_info *info = dev_iommu_priv_get(dev);
   +    intel_iommu_abort_devtlib_invalidate(dev);

Wonder if there is lock something prevent pciehp_ist() supprise_removal

pci_lock_rescan_remove() will block another thread to re-enter the function

pci_stop_and_remove_bus_device() to get here, this patch doesn't work.

Quoted 9 lines

interrupt response re-enter to get here when another safe_removal is in process,

if so ,  see above

Quoted 3 lines
drivers/iommu/intel/iommu.c +0 -0
       dmar_remove_one_dev_info(dev);
       intel_pasid_free_table(dev);

      intel_iommu_debugfs_remove_dev(info);