linux-toradex.git/arch/x86/include/asm/desc.h, branch v3.14

x86, trace: Delete __trace_alloc_intr_gate()

2013-11-08T22:15:47+00:00

Currently irq vector handlers for tracing are registered in both set_intr_gate()
 and __trace_alloc_intr_gate() in alloc_intr_gate().
But, we don't need to do that twice.
So, let's delete __trace_alloc_intr_gate().

Signed-off-by: Seiji Aguchi 
Link: http://lkml.kernel.org/r/52716E1B.7090205@hds.com
Signed-off-by: H. Peter Anvin

x86, trace: Register exception handler to trace IDT

2013-11-08T22:15:45+00:00

This patch registers exception handlers for tracing to a trace IDT.

To implemented it in set_intr_gate(), this patch does followings.
 - Register the exception handlers to
   the trace IDT by prepending "trace_" to the handler's names.
 - Also, newly introduce trace_page_fault() to add tracepoints
   in a subsequent patch.

Signed-off-by: Seiji Aguchi 
Link: http://lkml.kernel.org/r/52716DEC.5050204@hds.com
Signed-off-by: H. Peter Anvin

x86, trace: Remove __alloc_intr_gate()

2013-11-08T22:15:44+00:00

Prepare to move set_intr_gate() into a macro by removing
__alloc_intr_gate().

The purpose is to avoid failing a kernel build after applying a
subsequent patch which changes set_intr_gate() into a macro.

Signed-off-by: Seiji Aguchi 
Link: http://lkml.kernel.org/r/52716DB8.1080702@hds.com
Signed-off-by: H. Peter Anvin

trace,x86: Do not call local_irq_save() in load_current_idt()

2013-06-22T17:16:19+00:00

As load_current_idt() is now what is used to update the IDT for the
switches needed for NMI, lockdep debug, and for tracing, it must not
call local_irq_save(). This is because one of the users of this is
lockdep, which does tracing of local_irq_save() and when the debug
trap is hit, we need to update the IDT before tracing interrupts
being disabled. As load_current_idt() is used to do this, calling
local_irq_save() which lockdep traces, defeats the point of calling
load_current_idt().

As interrupts are already disabled when used by lockdep and NMI, the
only other user is tracing that can disable interrupts itself. Simply
have the tracing update disable interrupts before calling load_current_idt()
instead of breaking the other users.

Here's the dump that happened:

------------[ cut here ]------------
WARNING: at /work/autotest/nobackup/linux-test.git/kernel/fork.c:1196 copy_process+0x2c3/0x1398()
DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled)
Modules linked in:
CPU: 1 PID: 4570 Comm: gdm-simple-gree Not tainted 3.10.0-rc3-test+ #5
Hardware name:                  /DG965MQ, BIOS MQ96510J.86A.0372.2006.0605.1717 06/05/2006
 ffffffff81d2a7a5 ffff88006ed13d50 ffffffff8192822b ffff88006ed13d90
 ffffffff81035f25 ffff8800721c6000 ffff88006ed13da0 0000000001200011
 0000000000000000 ffff88006ed5e000 ffff8800721c6000 ffff88006ed13df0
Call Trace:
 [] dump_stack+0x19/0x1b
 [] warn_slowpath_common+0x67/0x80
 [] warn_slowpath_fmt+0x46/0x48
 [] ? __raw_spin_lock_init+0x31/0x52
 [] copy_process+0x2c3/0x1398
 [] do_fork+0xa8/0x260
 [] ? trace_preempt_on+0x2a/0x2f
 [] ? trace_hardirqs_on_thunk+0x3a/0x3f
 [] ? sysret_check+0x1b/0x56
 [] ? sysret_check+0x1b/0x56
 [] SyS_clone+0x16/0x18
 [] stub_clone+0x69/0x90
 [] ? system_call_fastpath+0x16/0x1b
---[ end trace 8b157a9d20ca1aa2 ]---

in fork.c:

 #ifdef CONFIG_PROVE_LOCKING
	DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled); <-- bug here
	DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
 #endif

Cc: Seiji Aguchi 
Signed-off-by: Steven Rostedt

x86, trace: Add irq vector tracepoints

2013-06-21T05:25:34+00:00

[Purpose of this patch]

As Vaibhav explained in the thread below, tracepoints for irq vectors
are useful.

http://www.spinics.net/lists/mm-commits/msg85707.html


The current interrupt traces from irq_handler_entry and irq_handler_exit
provide when an interrupt is handled.  They provide good data about when
the system has switched to kernel space and how it affects the currently
running processes.

There are some IRQ vectors which trigger the system into kernel space,
which are not handled in generic IRQ handlers.  Tracing such events gives
us the information about IRQ interaction with other system events.

The trace also tells where the system is spending its time.  We want to
know which cores are handling interrupts and how they are affecting other
processes in the system.  Also, the trace provides information about when
the cores are idle and which interrupts are changing that state.


On the other hand, my usecase is tracing just local timer event and
getting a value of instruction pointer.

I suggested to add an argument local timer event to get instruction pointer before.
But there is another way to get it with external module like systemtap.
So, I don't need to add any argument to irq vector tracepoints now.

[Patch Description]

Vaibhav's patch shared a trace point ,irq_vector_entry/irq_vector_exit, in all events.
But there is an above use case to trace specific irq_vector rather than tracing all events.
In this case, we are concerned about overhead due to unwanted events.

So, add following tracepoints instead of introducing irq_vector_entry/exit.
so that we can enable them independently.
   - local_timer_vector
   - reschedule_vector
   - call_function_vector
   - call_function_single_vector
   - irq_work_entry_vector
   - error_apic_vector
   - thermal_apic_vector
   - threshold_apic_vector
   - spurious_apic_vector
   - x86_platform_ipi_vector

Also, introduce a logic switching IDT at enabling/disabling time so that a time penalty
makes a zero when tracepoints are disabled. Detailed explanations are as follows.
 - Create trace irq handlers with entering_irq()/exiting_irq().
 - Create a new IDT, trace_idt_table, at boot time by adding a logic to
   _set_gate(). It is just a copy of original idt table.
 - Register the new handlers for tracpoints to the new IDT by introducing
   macros to alloc_intr_gate() called at registering time of irq_vector handlers.
 - Add checking, whether irq vector tracing is on/off, into load_current_idt().
   This has to be done below debug checking for these reasons.
   - Switching to debug IDT may be kicked while tracing is enabled.
   - On the other hands, switching to trace IDT is kicked only when debugging
     is disabled.

In addition, the new IDT is created only when CONFIG_TRACING is enabled to avoid being
used for other purposes.

Signed-off-by: Seiji Aguchi 
Link: http://lkml.kernel.org/r/51C323ED.5050708@hds.com
Signed-off-by: H. Peter Anvin 
Cc: Steven Rostedt

x86: Rename variables for debugging

2013-06-21T05:25:13+00:00

Rename variables for debugging to describe meaning of them precisely.

Also, introduce a generic way to switch IDT by checking a current state,
debug on/off.

Signed-off-by: Seiji Aguchi 
Link: http://lkml.kernel.org/r/51C323A8.7050905@hds.com
Signed-off-by: H. Peter Anvin 
Cc: Steven Rostedt

x86: replace percpu_xxx funcs with this_cpu_xxx

2012-05-14T21:15:31+00:00

Since percpu_xxx() serial functions are duplicated with this_cpu_xxx().
Removing percpu_xxx() definition and replacing them by this_cpu_xxx()
in code. There is no function change in this patch, just preparation for
later percpu_xxx serial function removing.

On x86 machine the this_cpu_xxx() serial functions are same as
__this_cpu_xxx() without no unnecessary premmpt enable/disable.

Thanks for Stephen Rothwell, he found and fixed a i386 build error in
the patch.

Also thanks for Andrew Morton, he kept updating the patchset in Linus'
tree.

Signed-off-by: Alex Shi 
Acked-by: Christoph Lameter 
Acked-by: Tejun Heo 
Acked-by: "H. Peter Anvin" 
Cc: Ingo Molnar 
Cc: Thomas Gleixner 
Signed-off-by: Stephen Rothwell 
Signed-off-by: Andrew Morton 
Signed-off-by: Tejun Heo

x86: Keep current stack in NMI breakpoints

2011-12-21T20:38:55+00:00

We want to allow NMI handlers to have breakpoints to be able to
remove stop_machine from ftrace, kprobes and jump_labels. But if
an NMI interrupts a current breakpoint, and then it triggers a
breakpoint itself, it will switch to the breakpoint stack and
corrupt the data on it for the breakpoint processing that it
interrupted.

Instead, have the NMI check if it interrupted breakpoint processing
by checking if the stack that is currently used is a breakpoint
stack. If it is, then load a special IDT that changes the IST
for the debug exception to keep the same stack in kernel context.
When the NMI is done, it puts it back.

This way, if the NMI does trigger a breakpoint, it will keep
using the same stack and not stomp on the breakpoint data for
the breakpoint it interrupted.

Suggested-by: Peter Zijlstra 
Signed-off-by: Steven Rostedt

x86-64: Add user_64bit_mode paravirt op

2011-08-04T23:13:49+00:00

Three places in the kernel assume that the only long mode CPL 3
selector is __USER_CS.  This is not true on Xen -- Xen's sysretq
changes cs to the magic value 0xe033.

Two of the places are corner cases, but as of "x86-64: Improve
vsyscall emulation CS and RIP handling"
(c9712944b2a12373cb6ff8059afcfb7e826a6c54), vsyscalls will segfault
if called with Xen's extra CS selector.  This causes a panic when
older init builds die.

It seems impossible to make Xen use __USER_CS reliably without
taking a performance hit on every system call, so this fixes the
tests instead with a new paravirt op.  It's a little ugly because
ptrace.h can't include paravirt.h.

Signed-off-by: Andy Lutomirski 
Link: http://lkml.kernel.org/r/f4fcb3947340d9e96ce1054a432f183f9da9db83.1312378163.git.luto@mit.edu
Reported-by: Konrad Rzeszutek Wilk 
Signed-off-by: H. Peter Anvin

x86, asm: Clean up desc.h a bit

2011-05-27T07:30:50+00:00

I have looked at this file and found it rather ugly - improve
readability a bit. No change in functionality.

Link: http://lkml.kernel.org/n/tip-incpt6y26yd8586idx65t9ll@git.kernel.org
Signed-off-by: Ingo Molnar