Messages in this thread | | | Date | Tue, 30 Sep 2014 12:40:47 -0400 | From | Dave Jones <> | Subject | Re: pipe/page fault oddness. |
| |
On Tue, Sep 30, 2014 at 12:22:01PM -0400, Dave Jones wrote:
> [<ffffffff91167913>] ? trace_graph_entry+0x123/0x250 > [<ffffffff9115b7ce>] ? trace_buffer_lock_reserve+0x1e/0x60 > [<ffffffff911c3c67>] ? handle_mm_fault+0x3a7/0xcd0 > [<ffffffff910ce68d>] ? trace_hardirqs_on+0xd/0x10 > [<ffffffff911678f8>] ? trace_graph_entry+0x108/0x250 > [<ffffffff91042d14>] ? __do_page_fault+0x234/0x600 > [<ffffffff9103ad23>] ? prepare_ftrace_return+0x73/0xe0 > [<ffffffff910ca040>] ? down_write_nested+0xc0/0xc0 > [<ffffffff910ac74d>] ? get_parent_ip+0xd/0x50 > [<ffffffff91042d14>] ? __do_page_fault+0x234/0x600 > [<ffffffff9103ad23>] ? prepare_ftrace_return+0x73/0xe0 > [<ffffffff91826b3a>] ? ftrace_graph_caller+0x5a/0x85 > [<ffffffff913a5ebe>] ? trace_hardirqs_on_thunk+0x3a/0x3f > [<ffffffff9118eda7>] ? context_tracking_user_exit+0x67/0x1b0 > [<ffffffff910430fe>] ? do_page_fault+0x1e/0x70 > [<ffffffff913a5efd>] ? trace_hardirqs_off_thunk+0x3a/0x3c > [<ffffffff911bd7e3>] ? copy_page_to_iter+0x3b3/0x500 > [<ffffffff9120eddf>] ? pipe_read+0xdf/0x330 > [<ffffffff9120ed00>] ? pipe_write+0x490/0x490 > [<ffffffff912051a0>] ? do_sync_readv_writev+0xa0/0xa0 > [<ffffffff912053b8>] ? do_iter_readv_writev+0x78/0xc0 > [<ffffffff91206bbe>] ? do_readv_writev+0xce/0x280 > [<ffffffff9120ed00>] ? pipe_write+0x490/0x490 > [<ffffffff910cbbf6>] ? lock_release_holdtime.part.29+0xe6/0x160 > [<ffffffff910ac74d>] ? get_parent_ip+0xd/0x50 > [<ffffffff910ac74d>] ? get_parent_ip+0xd/0x50 > [<ffffffff910ac8ab>] ? preempt_count_sub+0x6b/0xf0 > [<ffffffff91206da9>] ? vfs_readv+0x39/0x50 > [<ffffffff91206e6c>] ? SyS_readv+0x5c/0x100 > [<ffffffff918249e4>] ? tracesys+0xdd/0xe2 > > That second one is odd, because I had disabled all the function tracing > before doing the sysrq-t, so still seeing all the ftrace stuff on the > stack suprised me.
ah, echo 0 > tracing_on isn't enough, I had to 0 out set_ftrace_pid too. Never mind. Subsequent traces all looking the same, minus the tracing junk though.
Is there some way I can figure out what address it's faulting on ? I wonder if that might give some clues.
Dave
| |