15 Jun, 2011
1 commit
-
Current oprofile's x86 callgraph support may trigger page faults
throwing the BUG_ON(in_nmi()) message below. This patch fixes this by
using the same nmi-safe copy-from-user code as in perf.------------[ cut here ]------------
kernel BUG at .../arch/x86/kernel/traps.c:436!
invalid opcode: 0000 [#1] SMP
last sysfs file: /sys/devices/pci0000:00/0000:00:0a.0/0000:07:00.0/0000:08:04.0/net/eth0/broadcast
CPU 5
Modules linked in:Pid: 8611, comm: opcontrol Not tainted 2.6.39-00007-gfe47ae7 #1 Advanced Micro Device Anaheim/Anaheim
RIP: 0010:[] [] do_nmi+0x22/0x1ee
RSP: 0000:ffff88042fd47f28 EFLAGS: 00010002
RAX: ffff88042c0a7fd8 RBX: 0000000000000001 RCX: 00000000c0000101
RDX: 00000000ffff8804 RSI: ffffffffffffffff RDI: ffff88042fd47f58
RBP: ffff88042fd47f48 R08: 0000000000000004 R09: 0000000000001484
R10: 0000000000000001 R11: 0000000000000000 R12: ffff88042fd47f58
R13: 0000000000000000 R14: ffff88042fd47d98 R15: 0000000000000020
FS: 00007fca25e56700(0000) GS:ffff88042fd40000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000074 CR3: 000000042d28b000 CR4: 00000000000006e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process opcontrol (pid: 8611, threadinfo ffff88042c0a6000, task ffff88042c532310)
Stack:
0000000000000000 0000000000000001 ffff88042c0a7fd8 0000000000000000
ffff88042fd47de8 ffffffff813e897a 0000000000000020 ffff88042fd47d98
0000000000000000 ffff88042c0a7fd8 ffff88042fd47de8 0000000000000074
Call Trace:
[] nmi+0x1a/0x20
[] ? bad_to_user+0x25/0x771
<>
Code: ff 59 5b 41 5c 41 5d c9 c3 55 65 48 8b 04 25 88 b5 00 00 48 89 e5 41 55 41 54 49 89 fc 53 48 83 ec 08 f6 80 47 e0 ff ff 04 74 04 0b eb fe 81 80 44 e0 ff ff 00 00 01 04 65 ff 04 25 c4 0f 01
RIP [] do_nmi+0x22/0x1ee
RSP
---[ end trace ed6752185092104b ]---
Kernel panic - not syncing: Fatal exception in interrupt
Pid: 8611, comm: opcontrol Tainted: G D 2.6.39-00007-gfe47ae7 #1
Call Trace:
[] panic+0x8c/0x188
[] oops_end+0x81/0x8e
[] die+0x55/0x5e
[] do_trap+0x11c/0x12b
[] do_invalid_op+0x91/0x9a
[] ? do_nmi+0x22/0x1ee
[] ? oprofile_add_sample+0x83/0x95
[] ? op_amd_check_ctrs+0x4f/0x2cf
[] invalid_op+0x15/0x20
[] ? do_nmi+0x22/0x1ee
[] ? do_nmi+0x67/0x1ee
[] nmi+0x1a/0x20
[] ? bad_to_user+0x25/0x771
<>Cc: John Lumby
Cc: Maynard Johnson
Cc: # .37+
Signed-off-by: Robert Richter
12 May, 2011
1 commit
-
Both warning and warning_symbol are nowhere used.
Let's get rid of them.Signed-off-by: Richard Weinberger
Cc: Oleg Nesterov
Cc: Andrew Morton
Cc: Huang Ying
Cc: Soeren Sandmann Pedersen
Cc: Namhyung Kim
Cc: x86
Cc: H. Peter Anvin
Cc: Thomas Gleixner
Cc: Robert Richter
Cc: Paul Mundt
Link: http://lkml.kernel.org/r/1305205872-10321-2-git-send-email-richard@nod.at
Signed-off-by: Frederic Weisbecker
18 Mar, 2011
1 commit
-
Current stack dump code scans entire stack and check each entry
contains a pointer to kernel code. If CONFIG_FRAME_POINTER=y it
could mark whether the pointer is valid or not based on value of
the frame pointer. Invalid entries could be preceded by '?' sign.However this was not going to happen because scan start point
was always higher than the frame pointer so that they could not
meet.Commit 9c0729dc8062 ("x86: Eliminate bp argument from the stack
tracing routines") delayed bp acquisition point, so the bp was
read in lower frame, thus all of the entries were marked
invalid.This patch fixes this by reverting above commit while retaining
stack_frame() helper as suggested by Frederic Weisbecker.End result looks like below:
before:
[ 3.508329] Call Trace:
[ 3.508551] [] ? panic+0x91/0x199
[ 3.508662] [] ? printk+0x68/0x6a
[ 3.508770] [] ? mount_block_root+0x257/0x26e
[ 3.508876] [] ? mount_root+0x56/0x5a
[ 3.508975] [] ? prepare_namespace+0x170/0x1a9
[ 3.509216] [] ? kernel_init+0x1d2/0x1e2
[ 3.509335] [] ? kernel_thread_helper+0x4/0x10
[ 3.509442] [] ? restore_args+0x0/0x30
[ 3.509542] [] ? kernel_init+0x0/0x1e2
[ 3.509641] [] ? kernel_thread_helper+0x0/0x10after:
[ 3.522991] Call Trace:
[ 3.523351] [] panic+0x91/0x199
[ 3.523468] [] ? printk+0x68/0x6a
[ 3.523576] [] mount_block_root+0x257/0x26e
[ 3.523681] [] mount_root+0x56/0x5a
[ 3.523780] [] prepare_namespace+0x170/0x1a9
[ 3.523885] [] kernel_init+0x1d2/0x1e2
[ 3.523987] [] kernel_thread_helper+0x4/0x10
[ 3.524228] [] ? restore_args+0x0/0x30
[ 3.524345] [] ? kernel_init+0x0/0x1e2
[ 3.524445] [] ? kernel_thread_helper+0x0/0x10-v5:
* fix build breakage with oprofile-v4:
* use 0 instead of regs->bp
* separate out printk changes-v3:
* apply comment from Frederic
* add a couple of printk fixesSigned-off-by: Namhyung Kim
Acked-by: Peter Zijlstra
Acked-by: Frederic Weisbecker
Cc: Soren Sandmann
Cc: Paul Mackerras
Cc: Arnaldo Carvalho de Melo
Cc: Robert Richter
LKML-Reference:
Signed-off-by: Ingo Molnar
18 Nov, 2010
1 commit
-
The various stack tracing routines take a 'bp' argument in which the
caller is supposed to provide the base pointer to use, or 0 if doesn't
have one. Since bp is garbage whenever CONFIG_FRAME_POINTER is not
defined, this means all callers in principle should either always pass
0, or be conditional on CONFIG_FRAME_POINTER.However, there are only really three use cases for stack tracing:
(a) Trace the current task, including IRQ stack if any
(b) Trace the current task, but skip IRQ stack
(c) Trace some other taskIn all cases, if CONFIG_FRAME_POINTER is not defined, bp should just
be 0. If it _is_ defined, then- in case (a) bp should be gotten directly from the CPU's register, so
the caller should pass NULL for regs,- in case (b) the caller should should pass the IRQ registers to
dump_trace(),- in case (c) bp should be gotten from the top of the task's stack, so
the caller should pass NULL for regs.Hence, the bp argument is not necessary because the combination of
task and regs is sufficient to determine an appropriate value for bp.This patch introduces a new inline function stack_frame(task, regs)
that computes the desired bp. This function is then called from the
two versions of dump_stack().Signed-off-by: Soren Sandmann
Acked-by: Steven Rostedt
Cc: Thomas Gleixner
Cc: Ingo Molnar
Cc: H. Peter Anvin
Cc: Peter Zijlstra
Cc: Arjan van de Ven ,
Cc: Frederic Weisbecker ,
Cc: Arnaldo Carvalho de Melo ,
LKML-Reference: >
Signed-off-by: Frederic Weisbecker
01 Oct, 2010
2 commits
-
This patch implements the oprofile backtrace generation for 32 bit
applications running in the 64bit environment (compat mode).With this change it's possible to get backtrace for 32bits applications
under the 64bits environment using oprofile's callgraph options.opcontrol --setup -c ...
opreport -l -cg ...Signed-off-by: Jiri Olsa
Signed-off-by: Robert Richter -
Removing unnecessary struct frame_head and replacing it with
struct stack_frame.The struct stack_frame is already defined and used in other places
in kernel, so there's no reason to define new structure.Signed-off-by: Jiri Olsa
Signed-off-by: Robert Richter
17 Dec, 2009
1 commit
-
The current print_context_stack helper that does the stack
walking job is good for usual stacktraces as it walks through
all the stack and reports even addresses that look unreliable,
which is nice when we don't have frame pointers for example.But we have users like perf that only require reliable
stacktraces, and those may want a more adapted stack walker, so
lets make this function a callback in stacktrace_ops that users
can tune for their needs.Signed-off-by: Frederic Weisbecker
Cc: Peter Zijlstra
Cc: Arnaldo Carvalho de Melo
Cc: Paul Mackerras
LKML-Reference:
Signed-off-by: Ingo Molnar
12 May, 2009
1 commit
-
Use ®s->sp instead of regs for getting the top of stack in kernel mode.
(on x86-64, regs->sp always points the top of stack)[ Impact: Oprofile decodes only stack for backtracing on i386 ]
Signed-off-by: Masami Hiramatsu
[ v2: rename the API to kernel_stack_pointer(), move variable inside ]
Acked-by: Linus Torvalds
Cc: systemtap@sources.redhat.com
Cc: Harvey Harrison
Cc: Jan Blunck
Cc: Christoph Hellwig
LKML-Reference:
Signed-off-by: Ingo Molnar
16 Oct, 2008
2 commits
-
Signed-off-by: Robert Richter
-
Signed-off-by: Robert Richter
30 Jan, 2008
4 commits
-
Choose a less generic name for such a special case. Add
a comment explaining the odd use in X86_32.Change the one user of stack_pointer.
Signed-off-by: Harvey Harrison
Signed-off-by: Ingo Molnar
Signed-off-by: Thomas Gleixner -
Right now, we take the stack pointer early during the backtrace path, but
only calculate bp several functions deep later, making it hard to reconcile
the stack and bp backtraces (as well as showing several internal backtrace
functions on the stack with bp based backtracing).This patch moves the bp taking to the same place we take the stack pointer;
sadly this ripples through several layers of the back tracing stack,
but it's not all that bad in the end I hope.Signed-off-by: Arjan van de Ven
Signed-off-by: Ingo Molnar
Signed-off-by: Thomas Gleixner -
For enhancing the 32 bit EBP based backtracer, I need the capability
for the backtracer to tell it's customer that an entry is either
reliable or unreliable, and the backtrace printing code then needs to
print the unreliable ones slightly different.This patch adds the basic capability, the next patch will add a user
of this capability.Signed-off-by: Arjan van de Ven
Signed-off-by: Ingo Molnar
Signed-off-by: Thomas Gleixner -
We have a lot of code which differs only by the naming of specific
members of structures that contain registers. In order to enable
additional unifications, this patch drops the e- or r- size prefix
from the register names in struct pt_regs, and drops the x- prefixes
for segment registers on the 32-bit side.This patch also performs the equivalent renames in some additional
places that might be candidates for unification in the future.Signed-off-by: H. Peter Anvin
Signed-off-by: Ingo Molnar
Signed-off-by: Thomas Gleixner
20 Oct, 2007
2 commits
-
This patch defines frame_pointer() and stack_pointer() similar to the
already defined instruction_pointer(). Thus the oprofile code can be
written in a more readable fashion.[ tglx: arch/x86 adaptation ]
Signed-off-by: Jan Blunck
Signed-off-by: Andi Kleen
Signed-off-by: Ingo Molnar
Signed-off-by: Thomas Gleixner -
This patch improves oprofile callgraphs for i386/x86_64. The old
backtracing code was unable to produce kernel backtraces if the
kernel wasn't compiled with framepointers. The code now uses
dump_trace().[ tglx: arch/x86 adaptation ]
Signed-off-by: Jan Blunck
Signed-off-by: Andi Kleen
Signed-off-by: Ingo Molnar
Signed-off-by: Thomas Gleixner
11 Oct, 2007
1 commit
-
Signed-off-by: Thomas Gleixner
Signed-off-by: Ingo Molnar
