mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-23 20:37:36 +07:00
473291b3ea
With IRQF_SHARED flag set and CONFIG_DEBUG_SHIRQ enabled module removal may result in panic in sdma_interrupt() routine if associated sdma context was released before pci_free_irq(); [ 9198.939885] BUG: unable to handle kernel NULL pointer dereference at (null) [ 9198.940514] IP: sdma_make_progress+0xa5/0x450 [hfi1] [ 9198.941114] PGD 170bdc0067 P4D 170bdc0067 PUD 172063e067 PMD 0 [ 9198.941783] Oops: 0000 [#1] SMP ..... [ 9198.958877] CPU: 132 PID: 64173 Comm: rmmod Tainted: G OE 4.14.0-rc4+ #1 [ 9198.961032] Hardware name: Intel Corporation S7200AP/S7200AP, BIOS S72C610.86B.01.02.0118.080620171935 08/06/2017 [ 9198.963323] task: ffff9681397f0000 task.stack: ffffae1647c40000 [ 9198.965695] RIP: 0010:sdma_make_progress+0xa5/0x450 [hfi1] [ 9198.968082] RSP: 0018:ffffae1647c43be8 EFLAGS: 00010046 [ 9198.970503] RAX: 0000000000000000 RBX: ffff9680ce8b5ca8 RCX: 0000000000000000 [ 9198.973006] RDX: 0000000000000000 RSI: 0000000001a00d28 RDI: ffff9680ce8b5ca0 [ 9198.975546] RBP: ffffae1647c43c40 R08: ffff96814325ec00 R09: 00000000ffffffff [ 9198.978142] R10: 000000004325e501 R11: ffff96814325ec00 R12: ffff9680ce8b5c44 [ 9198.980779] R13: ffff9680ce8b5ca0 R14: 0000000000000000 R15: ffff9680ce8b5b00 [ 9198.983462] FS: 00007f31196ba740(0000) GS:ffff96819df00000(0000) knlGS:0000000000000000 [ 9198.986231] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 9198.989036] CR2: 0000000000000000 CR3: 000000170833f000 CR4: 00000000001406e0 [ 9198.991911] Call Trace: [ 9198.994847] sdma_engine_interrupt+0x82/0x100 [hfi1] [ 9198.997852] sdma_interrupt+0x61/0xc0 [hfi1] [ 9199.000852] __free_irq+0x1b3/0x2d0 [ 9199.003873] free_irq+0x35/0x70 [ 9199.006909] pci_free_irq+0x1c/0x30 [ 9199.009999] clean_up_interrupts+0x53/0xf0 [hfi1] [ 9199.013137] hfi1_start_cleanup+0x117/0x190 [hfi1] [ 9199.016315] postinit_cleanup+0x1d/0x270 [hfi1] [ 9199.019529] remove_one+0x1f3/0x210 [hfi1] [ 9199.022738] pci_device_remove+0x39/0xc0 [ 9199.025974] device_release_driver_internal+0x141/0x210 [ 9199.029268] driver_detach+0x3f/0x80 [ 9199.032580] bus_remove_driver+0x55/0xd0 [ 9199.035931] driver_unregister+0x2c/0x50 [ 9199.039321] pci_unregister_driver+0x2a/0xa0 [ 9199.042755] hfi1_mod_cleanup+0x10/0xb50 [hfi1] [ 9199.046196] SyS_delete_module+0x171/0x250 ... Fix by exporting sdma_clean() and removing from sdma_exit(). sdma_exit() now just manipulates the engine state, leaving the memory free to sdma_clean() which is now called just before the dd is freed. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Reviewed-by: Michael J Ruhl <michael.j.ruhl@intel.com> Signed-off-by: Alex Estrin <alex.estrin@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com> |
||
|---|---|---|
| .. | ||
| affinity.c | ||
| affinity.h | ||
| aspm.h | ||
| chip_registers.h | ||
| chip.c | ||
| chip.h | ||
| common.h | ||
| debugfs.c | ||
| debugfs.h | ||
| device.c | ||
| device.h | ||
| driver.c | ||
| efivar.c | ||
| efivar.h | ||
| eprom.c | ||
| eprom.h | ||
| exp_rcv.c | ||
| exp_rcv.h | ||
| file_ops.c | ||
| firmware.c | ||
| hfi.h | ||
| init.c | ||
| intr.c | ||
| iowait.h | ||
| Kconfig | ||
| mad.c | ||
| mad.h | ||
| Makefile | ||
| mmu_rb.c | ||
| mmu_rb.h | ||
| opa_compat.h | ||
| pcie.c | ||
| pio_copy.c | ||
| pio.c | ||
| pio.h | ||
| platform.c | ||
| platform.h | ||
| qp.c | ||
| qp.h | ||
| qsfp.c | ||
| qsfp.h | ||
| rc.c | ||
| ruc.c | ||
| sdma_txreq.h | ||
| sdma.c | ||
| sdma.h | ||
| sysfs.c | ||
| trace_ctxts.h | ||
| trace_dbg.h | ||
| trace_ibhdrs.h | ||
| trace_misc.h | ||
| trace_mmu.h | ||
| trace_rc.h | ||
| trace_rx.h | ||
| trace_tx.h | ||
| trace.c | ||
| trace.h | ||
| uc.c | ||
| ud.c | ||
| user_exp_rcv.c | ||
| user_exp_rcv.h | ||
| user_pages.c | ||
| user_sdma.c | ||
| user_sdma.h | ||
| verbs_txreq.c | ||
| verbs_txreq.h | ||
| verbs.c | ||
| verbs.h | ||
| vnic_main.c | ||
| vnic_sdma.c | ||
| vnic.h | ||