On Tue, Jul 10, 2018 at 08:55:13PM -0600, Jason Gunthorpe wrote: > From: Jason Gunthorpe <jgg@xxxxxxxxxxxx> > > If the method fails after calling rdma_explicit_destroy (eg if > copy_to_user faults) then it will trigger a kernel oops: > > BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 > PGD 800000000548d067 P4D 800000000548d067 PUD 54a0067 PMD 0 > SMP PTI > CPU: 0 PID: 359 Comm: ibv_rc_pingpong Not tainted 4.18.0-rc1+ #28 > Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014 > RIP: 0010: (null) > Code: Bad RIP value. > RSP: 0018:ffffc900001a3bf0 EFLAGS: 00010246 > RAX: 0000000000000000 RBX: ffff88000603bd00 RCX: 0000000000000003 > RDX: 0000000000000001 RSI: 0000000000000001 RDI: ffff88000603bd00 > RBP: 0000000000000001 R08: ffffc900001a3cf8 R09: 0000000000000000 > R10: 0000000000000000 R11: 0000000000000000 R12: ffffc900001a3cf0 > R13: 0000000000000000 R14: ffffc900001a3cf0 R15: 0000000000000000 > FS: 00007fb00dda8700(0000) GS:ffff880007c00000(0000) knlGS:0000000000000000 > CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 > CR2: ffffffffffffffd6 CR3: 000000000548e004 CR4: 00000000003606b0 > DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 > Call Trace: > ? rdma_lookup_put_uobject+0x22/0x50 [ib_uverbs] > ? uverbs_finalize_object+0x3b/0x60 [ib_uverbs] > ? uverbs_finalize_attrs+0x128/0x140 [ib_uverbs] > ? ib_uverbs_cmd_verbs+0x698/0x7c0 [ib_uverbs] > ? find_held_lock+0x2d/0x90 > ? __might_fault+0x39/0x90 > ? ib_uverbs_ioctl+0x111/0x1f0 [ib_uverbs] > ? do_vfs_ioctl+0xa0/0x6d0 > ? trace_hardirqs_on_caller+0xed/0x180 > ? _raw_spin_unlock_irq+0x24/0x40 > ? syscall_trace_enter+0x138/0x1d0 > ? ksys_ioctl+0x35/0x60 > ? __x64_sys_ioctl+0x11/0x20 > ? do_syscall_64+0x5b/0x1c0 > ? entry_SYSCALL_64_after_hwframe+0x49/0xbe > > This is because the type was replaced with the null_type during explicit > destroy that cannot complete the destruction. > > One of the side effects of replacing the type is to make the object > handle totally unreachable - so no other command could attempt to use > it, even though it remains on the uboject list. > > We can get the same end result by just fully destroying the object inside > rdma_explicit_destroy and leaving the caller the residual kref for the > uobj with no attached HW object, and no presence in the ubojects list. > > Signed-off-by: Jason Gunthorpe <jgg@xxxxxxxxxxxx> > --- > drivers/infiniband/core/rdma_core.c | 41 +++++++---------------------- > 1 file changed, 9 insertions(+), 32 deletions(-) > Thanks, Reviewed-by: Leon Romanovsky <leonro@xxxxxxxxxxxx>
Attachment:
signature.asc
Description: PGP signature
