Hi Mikhail,
Thanks for the report. I will look into it this week and get back to you.
-Vasant
On 5/21/2024 3:09 PM, Mikhail Gavrilov wrote:
> Hi,
> Yesterday on the fresh kernel snapshot
> I spotted a new bug message with follow stacktrace:
> [ 4.307097] BUG: sleeping function called from invalid context at
> kernel/locking/mutex.c:585
> [ 4.307135] in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid:
> 1, name: swapper/0
> [ 4.307150] preempt_count: 3, expected: 0
> [ 4.307159] RCU nest depth: 0, expected: 0
> [ 4.307168] 4 locks held by swapper/0/1:
> [ 4.307176] #0: ffff8881080ba920 (&group->mutex){+.+.}-{3:3}, at:
> bus_iommu_probe+0xf6/0x4c0
> [ 4.307203] #1: ffff88811654c1b8 (&domain->lock){....}-{2:2}, at:
> amd_iommu_attach_device+0x1ad/0x1e80
> [ 4.307227] #2: ffff888113518c18 (&dev_data->lock){....}-{2:2},
> at: amd_iommu_attach_device+0x213/0x1e80
> [ 4.307243] #3: ffff888108393030 (&iommu->lock){....}-{2:2}, at:
> amd_iommu_iopf_add_device+0x69/0x140
> [ 4.307243] irq event stamp: 1021718
> [ 4.307243] hardirqs last enabled at (1021717):
> [<ffffffff9cc35f2e>] kasan_quarantine_put+0x12e/0x250
> [ 4.307243] hardirqs last disabled at (1021718):
> [<ffffffff9f46895c>] _raw_spin_lock_irqsave+0x7c/0xa0
> [ 4.307243] softirqs last enabled at (1020154):
> [<ffffffff9c2721fb>] __irq_exit_rcu+0xbb/0x1c0
> [ 4.307243] softirqs last disabled at (1020147):
> [<ffffffff9c2721fb>] __irq_exit_rcu+0xbb/0x1c0
> [ 4.307243] Preemption disabled at:
> [ 4.307243] [<0000000000000000>] 0x0
> [ 4.307243] CPU: 0 PID: 1 Comm: swapper/0 Not tainted
> 6.10.0-0.rc0.20240520giteb6a9339efeb.9.fc41.x86_64+debug #1
> [ 4.307243] Hardware name: ASUS System Product Name/ROG STRIX
> B650E-I GAMING WIFI, BIOS 2611 04/07/2024
> [ 4.307243] Call Trace:
> [ 4.307243] <TASK>
> [ 4.307243] dump_stack_lvl+0x84/0xd0
> [ 4.307243] __might_resched.cold+0x1f7/0x23d
> [ 4.307243] ? __pfx___might_resched+0x10/0x10
> [ 4.307243] __mutex_lock+0xf3/0x13f0
> [ 4.307243] ? iopf_queue_add_device+0xd2/0x5d0
> [ 4.307243] ? __pfx___mutex_lock+0x10/0x10
> [ 4.307243] ? find_held_lock+0x34/0x120
> [ 4.307243] ? __pfx_lock_acquired+0x10/0x10
> [ 4.307243] ? iopf_queue_add_device+0xd2/0x5d0
> [ 4.307243] iopf_queue_add_device+0xd2/0x5d0
> [ 4.307243] amd_iommu_iopf_add_device+0xcd/0x140
> [ 4.307243] amd_iommu_attach_device+0xdc8/0x1e80
> [ 4.307243] ? iommu_create_device_direct_mappings+0x571/0x7d0
> [ 4.307243] __iommu_attach_device+0x64/0x250
> [ 4.307243] __iommu_device_set_domain+0x122/0x1c0
> [ 4.307243] __iommu_group_set_domain_internal+0xfa/0x2d0
> [ 4.307243] iommu_setup_default_domain+0x918/0xcd0
> [ 4.307243] bus_iommu_probe+0x1ad/0x4c0
> [ 4.307243] ? __pfx_bus_iommu_probe+0x10/0x10
> [ 4.307243] iommu_device_register+0x184/0x230
> [ 4.307243] ? amd_iommu_iopf_init+0xfd/0x170
> [ 4.307243] iommu_go_to_state+0xf87/0x3890
> [ 4.307243] ? __pfx_iommu_go_to_state+0x10/0x10
> [ 4.307243] ? lockdep_hardirqs_on+0x7c/0x100
> [ 4.307243] ? _raw_spin_unlock_irqrestore+0x4f/0x80
> [ 4.307243] ? add_device_randomness+0xb8/0xf0
> [ 4.307243] ? __pfx_add_device_randomness+0x10/0x10
> [ 4.307243] ? __pfx_pci_iommu_init+0x10/0x10
> [ 4.307243] amd_iommu_init+0x21/0x60
> [ 4.307243] ? __pfx_pci_iommu_init+0x10/0x10
> [ 4.307243] pci_iommu_init+0x38/0x60
> [ 4.307243] do_one_initcall+0xd6/0x460
> [ 4.307243] ? __pfx_do_one_initcall+0x10/0x10
> [ 4.307243] ? kernel_init_freeable+0x4cb/0x750
> [ 4.307243] ? kasan_unpoison+0x44/0x70
> [ 4.307243] kernel_init_freeable+0x6b4/0x750
> [ 4.307243] ? __pfx_kernel_init_freeable+0x10/0x10
> [ 4.307243] ? __pfx_kernel_init+0x10/0x10
> [ 4.307243] ? __pfx_kernel_init+0x10/0x10
> [ 4.307243] kernel_init+0x1c/0x150
> [ 4.307243] ? __pfx_kernel_init+0x10/0x10
> [ 4.307243] ret_from_fork+0x31/0x70
> [ 4.307243] ? __pfx_kernel_init+0x10/0x10
> [ 4.307243] ret_from_fork_asm+0x1a/0x30
> [ 4.307243] </TASK>
>
> [ 4.307243] =============================
> [ 4.307243] [ BUG: Invalid wait context ]
> [ 4.307243] 6.10.0-0.rc0.20240520giteb6a9339efeb.9.fc41.x86_64+debug
> #1 Tainted: G W ------- ---
> [ 4.307243] -----------------------------
> [ 4.307243] swapper/0/1 is trying to lock:
> [ 4.307243] ffff88810de2fa88 (&queue->lock){....}-{3:3}, at:
> iopf_queue_add_device+0xd2/0x5d0
> [ 4.307243] other info that might help us debug this:
> [ 4.307243] context-{4:4}
> [ 4.307243] 4 locks held by swapper/0/1:
> [ 4.307243] #0: ffff8881080ba920 (&group->mutex){+.+.}-{3:3}, at:
> bus_iommu_probe+0xf6/0x4c0
> [ 4.307243] #1: ffff88811654c1b8 (&domain->lock){....}-{2:2}, at:
> amd_iommu_attach_device+0x1ad/0x1e80
> [ 4.307243] #2: ffff888113518c18 (&dev_data->lock){....}-{2:2},
> at: amd_iommu_attach_device+0x213/0x1e80
> [ 4.307243] #3: ffff888108393030 (&iommu->lock){....}-{2:2}, at:
> amd_iommu_iopf_add_device+0x69/0x140
> [ 4.307243] stack backtrace:
> [ 4.307243] CPU: 0 PID: 1 Comm: swapper/0 Tainted: G W
> ------- ---
> 6.10.0-0.rc0.20240520giteb6a9339efeb.9.fc41.x86_64+debug #1
> [ 4.307243] Hardware name: ASUS System Product Name/ROG STRIX
> B650E-I GAMING WIFI, BIOS 2611 04/07/2024
> [ 4.307243] Call Trace:
> [ 4.307243] <TASK>
> [ 4.307243] dump_stack_lvl+0x84/0xd0
> [ 4.307243] __lock_acquire.cold+0x1fe/0x2a0
> [ 4.307243] ? __pfx___lock_acquire+0x10/0x10
> [ 4.307243] ? ret_from_fork_asm+0x1a/0x30
> [ 4.307243] lock_acquire+0x1ae/0x540
> [ 4.307243] ? iopf_queue_add_device+0xd2/0x5d0
> [ 4.307243] ? __pfx_lock_acquire+0x10/0x10
> [ 4.307243] ? __printk_cpu_sync_put+0x35/0x60
> [ 4.307243] ? add_taint+0x2a/0x70
> [ 4.307243] ? __might_resched.cold+0x203/0x23d
> [ 4.307243] ? __pfx___might_resched+0x10/0x10
> [ 4.307243] __mutex_lock+0x189/0x13f0
> [ 4.307243] ? iopf_queue_add_device+0xd2/0x5d0
> [ 4.307243] ? iopf_queue_add_device+0xd2/0x5d0
> [ 4.307243] ? __pfx___mutex_lock+0x10/0x10
> [ 4.307243] ? find_held_lock+0x34/0x120
> [ 4.307243] ? __pfx_lock_acquired+0x10/0x10
> [ 4.307243] ? iopf_queue_add_device+0xd2/0x5d0
> [ 4.307243] iopf_queue_add_device+0xd2/0x5d0
> [ 4.307243] amd_iommu_iopf_add_device+0xcd/0x140
> [ 4.307243] amd_iommu_attach_device+0xdc8/0x1e80
> [ 4.307243] ? iommu_create_device_direct_mappings+0x571/0x7d0
> [ 4.307243] __iommu_attach_device+0x64/0x250
> [ 4.307243] __iommu_device_set_domain+0x122/0x1c0
> [ 4.307243] __iommu_group_set_domain_internal+0xfa/0x2d0
> [ 4.307243] iommu_setup_default_domain+0x918/0xcd0
> [ 4.307243] bus_iommu_probe+0x1ad/0x4c0
> [ 4.307243] ? __pfx_bus_iommu_probe+0x10/0x10
> [ 4.307243] iommu_device_register+0x184/0x230
> [ 4.307243] ? amd_iommu_iopf_init+0xfd/0x170
> [ 4.307243] iommu_go_to_state+0xf87/0x3890
> [ 4.307243] ? __pfx_iommu_go_to_state+0x10/0x10
> [ 4.307243] ? lockdep_hardirqs_on+0x7c/0x100
> [ 4.307243] ? _raw_spin_unlock_irqrestore+0x4f/0x80
> [ 4.307243] ? add_device_randomness+0xb8/0xf0
> [ 4.307243] ? __pfx_add_device_randomness+0x10/0x10
> [ 4.307243] ? __pfx_pci_iommu_init+0x10/0x10
> [ 4.307243] amd_iommu_init+0x21/0x60
> [ 4.307243] ? __pfx_pci_iommu_init+0x10/0x10
> [ 4.307243] pci_iommu_init+0x38/0x60
> [ 4.307243] do_one_initcall+0xd6/0x460
> [ 4.307243] ? __pfx_do_one_initcall+0x10/0x10
> [ 4.307243] ? kernel_init_freeable+0x4cb/0x750
> [ 4.307243] ? kasan_unpoison+0x44/0x70
> [ 4.307243] kernel_init_freeable+0x6b4/0x750
> [ 4.307243] ? __pfx_kernel_init_freeable+0x10/0x10
> [ 4.307243] ? __pfx_kernel_init+0x10/0x10
> [ 4.307243] ? __pfx_kernel_init+0x10/0x10
> [ 4.307243] kernel_init+0x1c/0x150
> [ 4.307243] ? __pfx_kernel_init+0x10/0x10
> [ 4.307243] ret_from_fork+0x31/0x70
> [ 4.307243] ? __pfx_kernel_init+0x10/0x10
> [ 4.307243] ret_from_fork_asm+0x1a/0x30
> [ 4.307243] </TASK>
> [ 4.311628] AMD-Vi: Extended features (0x246577efa2254afa, 0x0):
> PPR NX GT [5] IA GA PC GA_vAPIC
> [ 4.311639] AMD-Vi: Interrupt remapping enabled
> [ 4.366191] AMD-Vi: Virtual APIC enabled
>
> Bisect pointed to commit:
> commit c4cb23111103a841c2df30058597398443bcad5f (HEAD)
> Author: Vasant Hegde <vasant.hegde@xxxxxxx>
> Date: Thu Apr 18 10:33:57 2024 +0000
>
> iommu/amd: Add support for enable/disable IOPF
>
> Return success from enable_feature(IOPF) path as this interface is going
> away. Instead we will enable/disable IOPF support in attach/detach device
> path.
>
> In attach device path, if device is capable of PRI, then we will add it to
> per IOMMU IOPF queue and enable PPR support in IOMMU. Also it will
> attach device to domain even if it fails to enable PRI or add device to
> IOPF queue as device can continue to work without PRI support.
>
> In detach device patch it follows following sequence:
> - Flush the queue for the given device
> - Disable PPR support in DTE[devid]
> - Remove device from IOPF queue
> - Disable device PRI
>
> Also add IOMMU_IOPF as dependency to AMD_IOMMU driver.
>
> Co-developed-by: Suravee Suthikulpanit <suravee.suthikulpanit@xxxxxxx>
> Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@xxxxxxx>
> Signed-off-by: Vasant Hegde <vasant.hegde@xxxxxxx>
> Reviewed-by: Jason Gunthorpe <jgg@xxxxxxxxxx>
> Link: https://lore.kernel.org/r/20240418103400.6229-13-vasant.hegde@xxxxxxx
> Signed-off-by: Joerg Roedel <jroedel@xxxxxxx>
>
> drivers/iommu/amd/Kconfig | 1 +
> drivers/iommu/amd/amd_iommu.h | 4 ++++
> drivers/iommu/amd/iommu.c | 39 +++++++++++++++++++++++++++++++--------
> drivers/iommu/amd/ppr.c | 41 +++++++++++++++++++++++++++++++++++++++++
> 4 files changed, 77 insertions(+), 8 deletions(-)
>
>
> Unfortunately I can't check revert c4cb23111103 due to conflicts:
>> git revert -n c4cb23111103a841c2df30058597398443bcad5f
> Auto-merging drivers/iommu/amd/Kconfig
> CONFLICT (content): Merge conflict in drivers/iommu/amd/Kconfig
> Auto-merging drivers/iommu/amd/amd_iommu.h
> Auto-merging drivers/iommu/amd/iommu.c
> CONFLICT (content): Merge conflict in drivers/iommu/amd/iommu.c
> Auto-merging drivers/iommu/amd/ppr.c
> error: could not revert c4cb23111103... iommu/amd: Add support for
> enable/disable IOPF
>
>
> I also attach below a full kernel log and build config.
>
> My hardware specs: https://linux-hardware.org/?probe=ca80d0a307
>
> Vasant or anyone else from the AMD team can you look please.
>
