Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
1 年多 前同步成功

通知 160
Star 36
Fork 7
cloud-kernel
cloud-kernel
切换分支/标签
  1. 17 7月, 2013 1 次提交
    • K
      x86: Make sure IDT is page aligned · 4df05f36
      由 Kees Cook 提交于 
      Since the IDT is referenced from a fixmap, make sure it is page aligned.
Merge with 32-bit one, since it was already aligned to deal with F00F
bug. Since bss is cleared before IDT setup, it can live there. This also
moves the other *_idt_table variables into common locations.

This avoids the risk of the IDT ever being moved in the bss and having
the mapping be offset, resulting in calling incorrect handlers. In the
current upstream kernel this is not a manifested bug, but heavily patched
kernels (such as those using the PaX patch series) did encounter this bug.

The tables other than idt_table technically do not need to be page
aligned, at least not at the current time, but using a common
declaration avoids mistakes.  On 64 bits the table is exactly one page
long, anyway.
Signed-off-by: NKees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/20130716183441.GA14232@www.outflux.netReported-by: NPaX Team <pageexec@gmail.com>
Signed-off-by: NH. Peter Anvin <hpa@linux.intel.com>
      4df05f36
  3. 16 7月, 2013 1 次提交
  5. 15 7月, 2013 1 次提交
    • P
      x86: delete __cpuinit usage from all x86 files · 148f9bb8
      由 Paul Gortmaker 提交于 
      The __cpuinit type of throwaway sections might have made sense
some time ago when RAM was more constrained, but now the savings
do not offset the cost and complications.  For example, the fix in
commit 5e427ec2 ("x86: Fix bit corruption at CPU resume time")
is a good example of the nasty type of bugs that can be created
with improper use of the various __init prefixes.

After a discussion on LKML[1] it was decided that cpuinit should go
the way of devinit and be phased out.  Once all the users are gone,
we can then finally remove the macros themselves from linux/init.h.

Note that some harmless section mismatch warnings may result, since
notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c)
are flagged as __cpuinit  -- so if we remove the __cpuinit from
arch specific callers, we will also get section mismatch warnings.
As an intermediate step, we intend to turn the linux/init.h cpuinit
content into no-ops as early as possible, since that will get rid
of these warnings.  In any case, they are temporary and harmless.

This removes all the arch/x86 uses of the __cpuinit macros from
all C files.  x86 only had the one __CPUINIT used in assembly files,
and it wasn't paired off with a .previous or a __FINIT, so we can
delete it directly w/o any corresponding additional change there.

[1] https://lkml.org/lkml/2013/5/20/589

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
Acked-by: NIngo Molnar <mingo@kernel.org>
Acked-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NH. Peter Anvin <hpa@linux.intel.com>
Signed-off-by: NPaul Gortmaker <paul.gortmaker@windriver.com>
      148f9bb8
  7. 12 7月, 2013 1 次提交
  9. 10 7月, 2013 9 次提交
  11. 05 7月, 2013 1 次提交
  13. 04 7月, 2013 1 次提交
  15. 02 7月, 2013 1 次提交
    • S
      x86/tracing: Add irq_enter/exit() in smp_trace_reschedule_interrupt() · 4787c368
      由 Seiji Aguchi 提交于 
      Reschedule vector tracepoints may be called in cpu idle state.
This causes lockdep check warning below.

The tracepoint requires rcu but for accuracy it also
requires irq_enter() (tracepoints record the irq context), thus,
the tracepoint interrupt handler should be calling irq_enter()
and not rcu_irq_enter() (irq_enter() calls rcu_irq_enter()).

So, add irq_enter/exit() to smp_trace_reschedule_interrupt()
with common pre/post processing functions, smp_entering_irq()
and exiting_irq() (exiting_irq() calls just irq_exit()
 in arch/x86/include/asm/apic.h),
because these can be shared among reschedule, call_function,
and call_function_single vectors.

[   50.720557] Testing event reschedule_exit:
[   50.721349]
[   50.721502] ===============================
[   50.721835] [ INFO: suspicious RCU usage. ]
[   50.722169] 3.10.0-rc6-00004-gcf910e83 #190 Not tainted
[   50.722582] -------------------------------
[   50.722915] /c/kernel-tests/src/linux/arch/x86/include/asm/trace/irq_vectors.h:50 suspicious rcu_dereference_check() usage!
[   50.723770]
[   50.723770] other info that might help us debug this:
[   50.723770]
[   50.724385]
[   50.724385] RCU used illegally from idle CPU!
[   50.724385] rcu_scheduler_active = 1, debug_locks = 0
[   50.725232] RCU used illegally from extended quiescent state!
[   50.725690] no locks held by swapper/0/0.
[   50.726010]
[   50.726010] stack backtrace:
[...]
Signed-off-by: NSeiji Aguchi <seiji.aguchi@hds.com>
Reviewed-by: NSteven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/51CDCFA3.9080101@hds.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      4787c368
  17. 28 6月, 2013 2 次提交
  19. 27 6月, 2013 3 次提交
  21. 26 6月, 2013 5 次提交
    • A
      perf/x86/intel: Support full width counting · 069e0c3c
      由 Andi Kleen 提交于 
      Recent Intel CPUs like Haswell and IvyBridge have a new
alternative MSR range for perfctrs that allows writing the full
counter width. Enable this range if the hardware reports it
using a new capability bit.

Currently the perf code queries CPUID to get the counter width,
and sign extends the counter values as needed. The traditional
PERFCTR MSRs always limit to 32bit, even though the counter
internally is larger (usually 48 bits on recent CPUs)

When the new capability is set use the alternative range which
do not have these restrictions.

This lowers the overhead of perf stat slightly because it has to
do less interrupts to accumulate the counter value. On Haswell
it also avoids some problems with TSX aborting when the end of
the counter range is reached.

( See the patch "perf/x86/intel: Avoid checkpointed counters
  causing excessive TSX aborts" for more details. )
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Reviewed-by: NStephane Eranian <eranian@google.com>
Acked-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1372173153-20215-1-git-send-email-andi@firstfloor.orgSigned-off-by: NIngo Molnar <mingo@kernel.org>
      069e0c3c
    • H
      x86, asm, cleanup: Replace open-coded control register values with symbolic · a3d7b7dd
      由 H. Peter Anvin 提交于 
      Clean up an unnecessary open-coded control register values.
Signed-off-by: NH. Peter Anvin <hpa@linux.intel.com>
Link: http://lkml.kernel.org/n/tip-um7za1nzf6brb17o0h4om6e3@git.kernel.org
      a3d7b7dd
    • H
      x86, flags: Rename X86_EFLAGS_BIT1 to X86_EFLAGS_FIXED · 1adfa76a
      由 H. Peter Anvin 提交于 
      Bit 1 in the x86 EFLAGS is always set.  Name the macro something that
actually tries to explain what it is all about, rather than being a
tautology.
Signed-off-by: NH. Peter Anvin <hpa@linux.intel.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Gleb Natapov <gleb@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Link: http://lkml.kernel.org/n/tip-f10rx5vjjm6tfnt8o1wseb3v@git.kernel.org
      1adfa76a
    • N
      mce: acpi/apei: Add comments to clarify usage of the various bitfields in the MCA subsystem · 0644414e
      由 Naveen N. Rao 提交于 
      There is some confusion about the 'mce_poll_banks' and 'mce_banks_owned'
per-cpu bitmaps.  Provide comments so that we all know exactly what these
are used for, and why.
Signed-off-by: NNaveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: NBorislav Petkov <bp@suse.de>
Signed-off-by: NTony Luck <tony.luck@intel.com>
      0644414e
    • Y
      x86: Fix /proc/mtrr with base/size more than 44bits · d5c78673
      由 Yinghai Lu 提交于 
      On one sytem that mtrr range is more then 44bits, in dmesg we have
[    0.000000] MTRR default type: write-back
[    0.000000] MTRR fixed ranges enabled:
[    0.000000]   00000-9FFFF write-back
[    0.000000]   A0000-BFFFF uncachable
[    0.000000]   C0000-DFFFF write-through
[    0.000000]   E0000-FFFFF write-protect
[    0.000000] MTRR variable ranges enabled:
[    0.000000]   0 [000080000000-0000FFFFFFFF] mask 3FFF80000000 uncachable
[    0.000000]   1 [380000000000-38FFFFFFFFFF] mask 3F0000000000 uncachable
[    0.000000]   2 [000099000000-000099FFFFFF] mask 3FFFFF000000 write-through
[    0.000000]   3 [00009A000000-00009AFFFFFF] mask 3FFFFF000000 write-through
[    0.000000]   4 [381FFA000000-381FFBFFFFFF] mask 3FFFFE000000 write-through
[    0.000000]   5 [381FFC000000-381FFC0FFFFF] mask 3FFFFFF00000 write-through
[    0.000000]   6 [0000AD000000-0000ADFFFFFF] mask 3FFFFF000000 write-through
[    0.000000]   7 [0000BD000000-0000BDFFFFFF] mask 3FFFFF000000 write-through
[    0.000000]   8 disabled
[    0.000000]   9 disabled

but /proc/mtrr report wrong:
reg00: base=0x080000000 ( 2048MB), size= 2048MB, count=1: uncachable
reg01: base=0x80000000000 (8388608MB), size=1048576MB, count=1: uncachable
reg02: base=0x099000000 ( 2448MB), size=   16MB, count=1: write-through
reg03: base=0x09a000000 ( 2464MB), size=   16MB, count=1: write-through
reg04: base=0x81ffa000000 (8519584MB), size=   32MB, count=1: write-through
reg05: base=0x81ffc000000 (8519616MB), size=    1MB, count=1: write-through
reg06: base=0x0ad000000 ( 2768MB), size=   16MB, count=1: write-through
reg07: base=0x0bd000000 ( 3024MB), size=   16MB, count=1: write-through
reg08: base=0x09b000000 ( 2480MB), size=   16MB, count=1: write-combining

so bit 44 and bit 45 get cut off.

We have problems in arch/x86/kernel/cpu/mtrr/generic.c::generic_get_mtrr().
1. for base, we miss cast base_lo to 64bit before shifting.
Fix that by adding u64 casting.

2. for size, it only can handle 44 bits aka 32bits + page_shift
Fix that with 64bit mask instead of 32bit mask_lo, then range could be
more than 44bits.
At the same time, we need to update size_or_mask for old cpus that does
support cpuid 0x80000008 to get phys_addr. Need to set high 32bits
to all 1s, otherwise will not get correct size for them.

Also fix mtrr_add_page: it should check base and (base + size - 1)
instead of base and size, as base and size could be small but
base + size could bigger enough to be out of boundary. We can
use boot_cpu_data.x86_phys_bits directly to avoid size_or_mask.

So When are we going to have size more than 44bits? that is 16TiB.

after patch we have right ouput:
reg00: base=0x080000000 ( 2048MB), size= 2048MB, count=1: uncachable
reg01: base=0x380000000000 (58720256MB), size=1048576MB, count=1: uncachable
reg02: base=0x099000000 ( 2448MB), size=   16MB, count=1: write-through
reg03: base=0x09a000000 ( 2464MB), size=   16MB, count=1: write-through
reg04: base=0x381ffa000000 (58851232MB), size=   32MB, count=1: write-through
reg05: base=0x381ffc000000 (58851264MB), size=    1MB, count=1: write-through
reg06: base=0x0ad000000 ( 2768MB), size=   16MB, count=1: write-through
reg07: base=0x0bd000000 ( 3024MB), size=   16MB, count=1: write-through
reg08: base=0x09b000000 ( 2480MB), size=   16MB, count=1: write-combining

-v2: simply checking in mtrr_add_page according to hpa.

[ hpa: This probably wants to go into -stable only after having sat in
  mainline for a bit.  It is not a regression. ]
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/1371162815-29931-1-git-send-email-yinghai@kernel.org
Cc: <stable@vger.kernel.org>
Signed-off-by: NH. Peter Anvin <hpa@linux.intel.com>
      d5c78673
  23. 24 6月, 2013 1 次提交
    • G
      irqdomain: Refactor irq_domain_associate_many() · ddaf144c
      由 Grant Likely 提交于 
      Originally, irq_domain_associate_many() was designed to unwind the
mapped irqs on a failure of any individual association. However, that
proved to be a problem with certain IRQ controllers. Some of them only
support a subset of irqs, and will fail when attempting to map a
reserved IRQ. In those cases we want to map as many IRQs as possible, so
instead it is better for irq_domain_associate_many() to make a
best-effort attempt to map irqs, but not fail if any or all of them
don't succeed. If a caller really cares about how many irqs got
associated, then it should instead go back and check that all of the
irqs is cares about were mapped.

The original design open-coded the individual association code into the
body of irq_domain_associate_many(), but with no longer needing to
unwind associations, the code becomes simpler to split out
irq_domain_associate() to contain the bulk of the logic, and
irq_domain_associate_many() to be a simple loop wrapper.

This patch also adds a new error check to the associate path to make
sure it isn't called for an irq larger than the controller can handle,
and adds locking so that the irq_domain_mutex is held while setting up a
new association.

v3: Fixup missing change to irq_domain_add_tree()
v2: Fixup x86 warning. irq_domain_associate_many() no longer returns an
    error code, but reports errors to the printk log directly. In the
    majority of cases we don't actually want to fail if there is a
    problem, but rather log it and still try to boot the system.
Signed-off-by: NGrant Likely <grant.likely@linaro.org>

irqdomain: Fix flubbed irq_domain_associate_many refactoring

commit d39046ec72, "irqdomain: Refactor irq_domain_associate_many()" was
missing the following hunk which causes a boot failure on anything using
irq_domain_add_tree() to allocate an irq domain.
Signed-off-by: NGrant Likely <grant.likely@linaro.org>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>,
Cc: Thomas Gleixner <tglx@linutronix.de>,
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
      ddaf144c
  25. 23 6月, 2013 5 次提交
    • D
      x86: Add NMI duration tracepoints · 0c4df02d
      由 Dave Hansen 提交于 
      This patch has been invaluable in my adventures finding
issues in the perf NMI handler.  I'm as big a fan of
printk() as anybody is, but using printk() in NMIs is
deadly when they're happening frequently.

Even hacking in trace_printk() ended up eating enough
CPU to throw off some of the measurements I was making.
Signed-off-by: NDave Hansen <dave.hansen@linux.intel.com>
Acked-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus@samba.org
Cc: acme@ghostprotocols.net
Cc: Dave Hansen <dave@sr71.net>
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      0c4df02d
    • D
      perf: Drop sample rate when sampling is too slow · 14c63f17
      由 Dave Hansen 提交于 
      This patch keeps track of how long perf's NMI handler is taking,
and also calculates how many samples perf can take a second.  If
the sample length times the expected max number of samples
exceeds a configurable threshold, it drops the sample rate.

This way, we don't have a runaway sampling process eating up the
CPU.

This patch can tend to drop the sample rate down to level where
perf doesn't work very well.  *BUT* the alternative is that my
system hangs because it spends all of its time handling NMIs.

I'll take a busted performance tool over an entire system that's
busted and undebuggable any day.

BTW, my suspicion is that there's still an underlying bug here.
Using the HPET instead of the TSC is definitely a contributing
factor, but I suspect there are some other things going on.
But, I can't go dig down on a bug like that with my machine
hanging all the time.
Signed-off-by: NDave Hansen <dave.hansen@linux.intel.com>
Acked-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus@samba.org
Cc: acme@ghostprotocols.net
Cc: Dave Hansen <dave@sr71.net>
[ Prettified it a bit. ]
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      14c63f17
    • D
      x86: Warn when NMI handlers take large amounts of time · 2ab00456
      由 Dave Hansen 提交于 
      I have a system which is causing all kinds of problems.  It has
8 NUMA nodes, and lots of cores that can fight over cachelines.
If things are not working _perfectly_, then NMIs can take longer
than expected.

If we get too many of them backed up to each other, we can
easily end up in a situation where we are doing nothing *but*
running NMIs.  The biggest problem, though, is that this happens
_silently_.  You might be lucky to get an hrtimer warning, but
most of the time system simply hangs.

This patch should at least give us some warning before we fall
off the cliff.  the warnings look like this:

	nmi_handle: perf_event_nmi_handler() took: 26095071 ns

The message is triggered whenever we notice the longest NMI
we've seen to date.  You can always view and reset this value
via the debugfs interface if you like.
Signed-off-by: NDave Hansen <dave.hansen@linux.intel.com>
Acked-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus@samba.org
Cc: acme@ghostprotocols.net
Cc: Dave Hansen <dave@sr71.net>
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      2ab00456
    • S
      x86/tracing: Add config option checking to the definitions of mce handlers · 33e5ff63
      由 Seiji Aguchi 提交于 
      In case CONFIG_X86_MCE_THRESHOLD and CONFIG_X86_THERMAL_VECTOR
are disabled, kernel build fails as follows.

   arch/x86/built-in.o: In function `trace_threshold_interrupt':
   (.entry.text+0x122b): undefined reference to `smp_trace_threshold_interrupt'
   arch/x86/built-in.o: In function `trace_thermal_interrupt':
   (.entry.text+0x132b): undefined reference to `smp_trace_thermal_interrupt'

In this case, trace_threshold_interrupt/trace_thermal_interrupt
are not needed to define.

So, add config option checking to their definitions in entry_64.S.
Signed-off-by: NSeiji Aguchi <seiji.aguchi@hds.com>
Cc: rostedt@goodmis.org
Link: http://lkml.kernel.org/r/51C58B8A.2080808@hds.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      33e5ff63
    • S
      trace,x86: Do not call local_irq_save() in load_current_idt() · 2b4bc789
      由 Steven Rostedt (Red Hat) 提交于 
      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:
 [<ffffffff8192822b>] dump_stack+0x19/0x1b
 [<ffffffff81035f25>] warn_slowpath_common+0x67/0x80
 [<ffffffff81035fe1>] warn_slowpath_fmt+0x46/0x48
 [<ffffffff812bfc5d>] ? __raw_spin_lock_init+0x31/0x52
 [<ffffffff810341f7>] copy_process+0x2c3/0x1398
 [<ffffffff8103539d>] do_fork+0xa8/0x260
 [<ffffffff810ca7b1>] ? trace_preempt_on+0x2a/0x2f
 [<ffffffff812afb3e>] ? trace_hardirqs_on_thunk+0x3a/0x3f
 [<ffffffff81937fe7>] ? sysret_check+0x1b/0x56
 [<ffffffff81937fe7>] ? sysret_check+0x1b/0x56
 [<ffffffff810355cf>] SyS_clone+0x16/0x18
 [<ffffffff81938369>] stub_clone+0x69/0x90
 [<ffffffff81937fc2>] ? 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 <seiji.aguchi@hds.com>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>
      2b4bc789
  27. 21 6月, 2013 8 次提交
    • S
      trace,x86: Move creation of irq tracepoints from apic.c to irq.c · 83ab8514
      由 Steven Rostedt (Red Hat) 提交于 
      Compiling without CONFIG_X86_LOCAL_APIC set, apic.c will not be
compiled, and the irq tracepoints will not be created via the
CREATE_TRACE_POINTS macro. When CONFIG_X86_LOCAL_APIC is not set,
we get the following build error:

  LD      init/built-in.o
arch/x86/built-in.o: In function `trace_x86_platform_ipi_entry':
linux-test.git/arch/x86/include/asm/trace/irq_vectors.h:66: undefined reference to `__tracepoint_x86_platform_ipi_entry'
arch/x86/built-in.o: In function `trace_x86_platform_ipi_exit':
linux-test.git/arch/x86/include/asm/trace/irq_vectors.h:66: undefined reference to `__tracepoint_x86_platform_ipi_exit'
arch/x86/built-in.o: In function `trace_irq_work_entry':
linux-test.git/arch/x86/include/asm/trace/irq_vectors.h:72: undefined reference to `__tracepoint_irq_work_entry'
arch/x86/built-in.o: In function `trace_irq_work_exit':
linux-test.git/arch/x86/include/asm/trace/irq_vectors.h:72: undefined reference to `__tracepoint_irq_work_exit'
arch/x86/built-in.o:(__jump_table+0x8): undefined reference to `__tracepoint_x86_platform_ipi_entry'
arch/x86/built-in.o:(__jump_table+0x14): undefined reference to `__tracepoint_x86_platform_ipi_exit'
arch/x86/built-in.o:(__jump_table+0x20): undefined reference to `__tracepoint_irq_work_entry'
arch/x86/built-in.o:(__jump_table+0x2c): undefined reference to `__tracepoint_irq_work_exit'
make[1]: *** [vmlinux] Error 1
make: *** [sub-make] Error 2

As irq.c is always compiled for x86, it is a more appropriate location
to create the irq tracepoints.

Cc: Seiji Aguchi <seiji.aguchi@hds.com>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>
      83ab8514
    • S
      x86, trace: Add irq vector tracepoints · cf910e83
      由 Seiji Aguchi 提交于 
      [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

<snip>
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.
<snip>

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: NSeiji Aguchi <seiji.aguchi@hds.com>
Link: http://lkml.kernel.org/r/51C323ED.5050708@hds.comSigned-off-by: NH. Peter Anvin <hpa@linux.intel.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
      cf910e83
    • S
      x86: Rename variables for debugging · 629f4f9d
      由 Seiji Aguchi 提交于 
      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: NSeiji Aguchi <seiji.aguchi@hds.com>
Link: http://lkml.kernel.org/r/51C323A8.7050905@hds.comSigned-off-by: NH. Peter Anvin <hpa@linux.intel.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
      629f4f9d
    • S
      x86, trace: Introduce entering/exiting_irq() · eddc0e92
      由 Seiji Aguchi 提交于 
      When implementing tracepoints in interrupt handers, if the tracepoints are
simply added in the performance sensitive path of interrupt handers,
it may cause potential performance problem due to the time penalty.

To solve the problem, an idea is to prepare non-trace/trace irq handers and
switch their IDTs at the enabling/disabling time.

So, let's introduce entering_irq()/exiting_irq() for pre/post-
processing of each irq handler.

A way to use them is as follows.

Non-trace irq handler:
smp_irq_handler()
{
	entering_irq();		/* pre-processing of this handler */
	__smp_irq_handler();	/*
				 * common logic between non-trace and trace handlers
				 * in a vector.
				 */
	exiting_irq();		/* post-processing of this handler */

}

Trace irq_handler:
smp_trace_irq_handler()
{
	entering_irq();		/* pre-processing of this handler */
	trace_irq_entry();	/* tracepoint for irq entry */
	__smp_irq_handler();	/*
				 * common logic between non-trace and trace handlers
				 * in a vector.
				 */
	trace_irq_exit();	/* tracepoint for irq exit */
	exiting_irq();		/* post-processing of this handler */

}

If tracepoints can place outside entering_irq()/exiting_irq() as follows,
it looks cleaner.

smp_trace_irq_handler()
{
	trace_irq_entry();
	smp_irq_handler();
	trace_irq_exit();
}

But it doesn't work.
The problem is with irq_enter/exit() being called. They must be called before
trace_irq_enter/exit(),  because of the rcu_irq_enter() must be called before
any tracepoints are used, as tracepoints use  rcu to synchronize.

As a possible alternative, we may be able to call irq_enter() first as follows
if irq_enter() can nest.

smp_trace_irq_hander()
{
	irq_entry();
	trace_irq_entry();
	smp_irq_handler();
	trace_irq_exit();
	irq_exit();
}

But it doesn't work, either.
If irq_enter() is nested, it may have a time penalty because it has to check if it
was already called or not. The time penalty is not desired in performance sensitive
paths even if it is tiny.
Signed-off-by: NSeiji Aguchi <seiji.aguchi@hds.com>
Link: http://lkml.kernel.org/r/51C3238D.9040706@hds.comSigned-off-by: NH. Peter Anvin <hpa@linux.intel.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
      eddc0e92
    • H
      x86, reloc: Use xorl instead of xorq in relocate_kernel_64.S · f037e416
      由 H. Peter Anvin 提交于 
      There is no point in using "xorq" to clear a register... use "xorl" to
clear the bottom 32 bits, and the upper 32 bits get cleared by virtue
of zero extension.
Signed-off-by: NH. Peter Anvin <hpa@linux.intel.com>
Cc: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/n/tip-b76zi1gep39c0zs8fbvkhie9@git.kernel.org
      f037e416
    • B
      x86: Add a static_cpu_has_safe variant · 4a90a99c
      由 Borislav Petkov 提交于 
      We want to use this in early code where alternatives might not have run
yet and for that case we fall back to the dynamic boot_cpu_has.

For that, force a 5-byte jump since the compiler could be generating
differently sized jumps for each label.
Signed-off-by: NBorislav Petkov <bp@suse.de>
Link: http://lkml.kernel.org/r/1370772454-6106-5-git-send-email-bp@alien8.deSigned-off-by: NH. Peter Anvin <hpa@linux.intel.com>
      4a90a99c
    • B
      x86: Sanity-check static_cpu_has usage · 5700f743
      由 Borislav Petkov 提交于 
      static_cpu_has may be used only after alternatives have run. Before that
it always returns false if constant folding with __builtin_constant_p()
doesn't happen. And you don't want that.

This patch is the result of me debugging an issue where I overzealously
put static_cpu_has in code which executed before alternatives have run
and had to spend some time with scratching head and cursing at the
monitor.

So add a jump to a warning which screams loudly when we use this
function too early. The alternatives patch that check away in
conjunction with patching the rest of the kernel image.

[ hpa: factored this into its own configuration option.  If we want to
  have an overarching option, it should be an option which selects
  other options, not as a group option in the source code. ]
Signed-off-by: NBorislav Petkov <bp@suse.de>
Link: http://lkml.kernel.org/r/1370772454-6106-4-git-send-email-bp@alien8.deSigned-off-by: NH. Peter Anvin <hpa@linux.intel.com>
      5700f743
    • B
      x86, cpu: Add a synthetic, always true, cpu feature · c3b83598
      由 Borislav Petkov 提交于 
      This will be used in alternatives later as an always-replace flag.
Signed-off-by: NBorislav Petkov <bp@suse.de>
Link: http://lkml.kernel.org/r/1370772454-6106-2-git-send-email-bp@alien8.deSigned-off-by: NH. Peter Anvin <hpa@linux.intel.com>
      c3b83598