Re: [PATCH 3/3] x86/mm, tracing: Fix CR2 corruption

2019-07-04 Thread Peter Zijlstra
On Thu, Jul 04, 2019 at 12:05:22AM +0200, Peter Zijlstra wrote: > On Wed, Jul 03, 2019 at 04:47:01PM -0400, Steven Rostedt wrote: > > Yeah, looks like we might be missing a TRACE_IRQS_OFF from the > > from_usermode_stack_switch path. > > Oh bugger, there's a second error_entry call. --- Subject:

Re: [PATCH 3/3] x86/mm, tracing: Fix CR2 corruption

2019-07-04 Thread Peter Zijlstra
On Thu, Jul 04, 2019 at 12:00:57AM +0200, Peter Zijlstra wrote: > On Wed, Jul 03, 2019 at 01:27:09PM -0700, Andy Lutomirski wrote: > > On Wed, Jul 3, 2019 at 3:28 AM root wrote: > > > > @@ -1338,18 +1347,9 @@ ENTRY(error_entry) > > > movq%rax, %rsp /* switch stack

Re: [PATCH 3/3] x86/mm, tracing: Fix CR2 corruption

2019-07-03 Thread Andy Lutomirski
On Wed, Jul 3, 2019 at 3:01 PM Peter Zijlstra wrote: > > On Wed, Jul 03, 2019 at 01:27:09PM -0700, Andy Lutomirski wrote: > > On Wed, Jul 3, 2019 at 3:28 AM root wrote: > > > > @@ -1338,18 +1347,9 @@ ENTRY(error_entry) > > > movq%rax, %rsp /* switch stack */ > > >

Re: [PATCH 3/3] x86/mm, tracing: Fix CR2 corruption

2019-07-03 Thread Peter Zijlstra
On Wed, Jul 03, 2019 at 04:47:01PM -0400, Steven Rostedt wrote: > On Wed, 3 Jul 2019 13:27:09 -0700 > Andy Lutomirski wrote: > > > > > @@ -1180,10 +1189,10 @@ idtentry xenint3do_int3 > > > has_error_co > > > #endif > > > > > > idtentry general_protectiondo_

Re: [PATCH 3/3] x86/mm, tracing: Fix CR2 corruption

2019-07-03 Thread Peter Zijlstra
On Wed, Jul 03, 2019 at 01:27:09PM -0700, Andy Lutomirski wrote: > On Wed, Jul 3, 2019 at 3:28 AM root wrote: > > @@ -1338,18 +1347,9 @@ ENTRY(error_entry) > > movq%rax, %rsp /* switch stack */ > > ENCODE_FRAME_POINTER > > pushq %r12 > > - > > -

Re: [PATCH 3/3] x86/mm, tracing: Fix CR2 corruption

2019-07-03 Thread Peter Zijlstra
On Wed, Jul 03, 2019 at 04:29:42PM -0400, Steven Rostedt wrote: > On Wed, 3 Jul 2019 22:22:31 +0200 > Peter Zijlstra wrote: > > > On Wed, Jul 03, 2019 at 12:27:34PM +0200, root wrote: > > > Despire the current efforts to read CR2 before tracing happens there > > > still exist a number of possible

Re: [PATCH 3/3] x86/mm, tracing: Fix CR2 corruption

2019-07-03 Thread Steven Rostedt
On Wed, 3 Jul 2019 13:27:09 -0700 Andy Lutomirski wrote: > > @@ -1180,10 +1189,10 @@ idtentry xenint3do_int3 > > has_error_co > > #endif > > > > idtentry general_protectiondo_general_protection has_error_code=1 > > -idtentry page_faultdo_page_

Re: [PATCH 3/3] x86/mm, tracing: Fix CR2 corruption

2019-07-03 Thread Steven Rostedt
On Wed, 3 Jul 2019 22:22:31 +0200 Peter Zijlstra wrote: > On Wed, Jul 03, 2019 at 12:27:34PM +0200, root wrote: > > Despire the current efforts to read CR2 before tracing happens there > > still exist a number of possible holes: > > > > idtentry page_fault do_page_fault h

Re: [PATCH 3/3] x86/mm, tracing: Fix CR2 corruption

2019-07-03 Thread Andy Lutomirski
On Wed, Jul 3, 2019 at 3:28 AM root wrote: > > Despire the current efforts to read CR2 before tracing happens there > still exist a number of possible holes: > > idtentry page_fault do_page_fault has_error_code=1 > call error_entry > TRACE_IRQS_OFF > call

Re: [PATCH 3/3] x86/mm, tracing: Fix CR2 corruption

2019-07-03 Thread Peter Zijlstra
On Wed, Jul 03, 2019 at 12:27:34PM +0200, root wrote: > Despire the current efforts to read CR2 before tracing happens there > still exist a number of possible holes: > > idtentry page_fault do_page_fault has_error_code=1 > call error_entry > TRACE_IRQS_OFF >