Commit Graph

30 Commits (7cf79d59ea650ae82868a99cc2954871d2a239bf)

Author SHA1 Message Date
Paul Mundt 6ba653830c sh: Fix up the FPU emulation build.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2009-11-25 12:07:31 +09:00
Stuart Menefy d3ea9fa0a5 sh: Minor optimisations to FPU handling
A number of small optimisations to FPU handling, in particular:

 - move the task USEDFPU flag from the thread_info flags field (which
   is accessed asynchronously to the thread) to a new status field,
   which is only accessed by the thread itself. This allows locking to
   be removed in most cases, or can be reduced to a preempt_lock().
   This mimics the i386 behaviour.

 - move the modification of regs->sr and thread_info->status flags out
   of save_fpu() to __unlazy_fpu(). This gives the compiler a better
   chance to optimise things, as well as making save_fpu() symmetrical
   with restore_fpu() and init_fpu().

 - implement prepare_to_copy(), so that when creating a thread, we can
   unlazy the FPU prior to copying the thread data structures.

Also make sure that the FPU is disabled while in the kernel, in
particular while booting, and for newly created kernel threads,

In a very artificial benchmark, the execution time for 2500000
context switches was reduced from 50 to 45 seconds.

Signed-off-by: Stuart Menefy <stuart.menefy@st.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2009-11-24 17:45:38 +09:00
Paul Mundt 49fb2cd257 Merge branch 'master' into sh/st-integration 2009-11-24 16:32:11 +09:00
Giuseppe CAVALLARO a0458b07c1 sh: add sleazy FPU optimization
sh port of the sLeAZY-fpu feature currently implemented for some architectures
such us i386.

Right now the SH kernel has a 100% lazy fpu behaviour.
This is of course great for applications that have very sporadic or no FPU use.
However for very frequent FPU users...  you take an extra trap every context
switch.
The patch below adds a simple heuristic to this code: after 5 consecutive
context switches of FPU use, the lazy behavior is disabled and the context
gets restored every context switch.
After 256 switches, this is reset and the 100% lazy behavior is returned.

Tests with LMbench showed no regression.
I saw a little improvement due to the prefetching (~2%).

The tests below also show that, with this sLeazy patch, indeed,
the number of FPU exceptions is reduced.
To test this. I hacked the lat_ctx LMBench to use the FPU a little more.

   sLeasy implementation
   ===========================================
   switch_to calls            |  79326
   sleasy   calls             |  42577
   do_fpu_state_restore  calls|  59232
   restore_fpu   calls        |  59032

   Exceptions:  0x800 (FPU disabled  ): 16604

   100% Leazy (default implementation)
   ===========================================
   switch_to  calls            |  79690
   do_fpu_state_restore calls  |  53299
   restore_fpu  calls          |   53101

   Exceptions: 0x800 (FPU disabled  ):  53273

Signed-off-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: Stuart Menefy <stuart.menefy@st.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2009-11-24 16:23:38 +09:00
Paul Mundt 4c978ca319 sh: Clean up more superfluous symbol exports.
Many of these symbols went away completely, or we just never cared about
them in the first place. Trim the exports down to the essential set.

Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2009-10-27 11:51:19 +09:00
Jon Frosdick b46373e0d4 sh: Use internal watchdog timer to perform reset
This patches will trigger a reboot using the watchdog
timer instead of double fault.  Unlike the previous
method, this one actually works in 32 bit mode.

Reset should also be cleaner.

Signed-off-by: Jon Frosdick <jon.frosdick@st.com>
Signed-off-by: Carl Shaw <carl.shaw@st.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2009-08-24 16:20:44 +09:00
Matt Fleming 7816fecd03 sh: Mark __switch_to() as __notrace_funcgraph
Annotate __switch_to() so that the function graph tracer does not try to
trace it. Use __notrace_funcgraph, as opposed to notrace, so that other
tracers can continue to trace __switch_to().

The reason that we don't want to trace __switch_to() with the function
graph tracer is because of how the return address stack in task_struct
is implemented. When we enter __switch_to we store the real return
address on prev's ret_stack. When we return from __switch_to() we've
patched the return address on the kernel stack to be
return_to_handler. Calling return_to_handler we do,

       -> ftrace_return_to_handler()
       	  -> ftrace_pop_return_ftrace()

Which tries to pop the real return address from current->ret_stack. The
problem being that we stored the return address on prev->ret_stack, but
current now points to next, and next->ret_stack doesn't contain the
correct return address (and is possibly even empty).

Signed-off-by: Matt Fleming <matt@console-pimps.org>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2009-07-11 10:08:06 +09:00
Linus Torvalds 15fc204afc Merge git://git.kernel.org/pub/scm/linux/kernel/git/lethal/sh-2.6
* git://git.kernel.org/pub/scm/linux/kernel/git/lethal/sh-2.6: (56 commits)
  sh: Fix declaration of __kernel_sigreturn and __kernel_rt_sigreturn
  sh: Enable soc-camera in ap325rxa/migor/se7724 defconfigs.
  sh: remove stray markers.
  sh: defconfig updates.
  sh: pci: Initial PCI-Express support for SH7786 Urquell board.
  sh: Generic HAVE_PERF_COUNTER support.
  SH: convert migor to soc-camera as platform-device
  SH: convert ap325rxa to soc-camera as platform-device
  soc-camera: unify i2c camera device platform data
  sh: add platform data for r8a66597-hcd in setup-sh7723
  sh: add platform data for r8a66597-hcd in setup-sh7366
  sh: x3proto: add platform data for r8a66597-hcd
  sh: highlander: add platform data for r8a66597-hcd
  sh: sh7785lcr: add platform data for r8a66597-hcd
  sh: turn off irqs when disabling CMT/TMU timers
  sh: use kzalloc() for cpg clocks
  sh: unbreak WARN_ON()
  sh: Use generic atomic64_t implementation.
  sh: Revised clock function in highlander
  sh: Update r7780mp defconfig
  ...
2009-06-18 14:07:35 -07:00
Oleg Nesterov bba7fc0a21 ptrace: remove PT_DTRACE from avr32, mn10300, parisc, s390, sh, xtensa
avr32, mn10300, parisc, s390, sh, xtensa:

They never set PT_DTRACE, but clear it after do_execve().

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Acked-by: Kyle McMartin <kyle@mcmartin.ca>
Cc: Grant Grundler <grundler@parisc-linux.org>
Cc: Matthew Wilcox <matthew@wil.cx>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Acked-by: Paul Mundt <lethal@linux-sh.org>
Acked-by: Chris Zankel <chris@zankel.net>
Acked-by: Roland McGrath <roland@redhat.com>
Acked-by: Haavard Skinnemoen <haavard.skinnemoen@atmel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18 13:03:48 -07:00
Christoph Hellwig 4505ffda54 sh: remove stray markers.
arch/sh has a couple of stray markers without any users introduced
in commit 3d58695edb.  Remove them in
preparation of removing the markers in favour of the TRACE_EVENT
macro (and also because we don't keep dead code around).

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2009-06-18 13:38:26 +09:00
Kieran Bingham e73173dbe5 sh: Fix UBC setup and registers for SH2A
Signed-off-by: Kieran Bingham <kieranbingham@gmail.com>
Signed-off-by: Peter Griffin <pgriffin@mpc-data.co.uk>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2009-05-09 00:09:21 +09:00
Linus Torvalds 45e36c1666 Merge git://git.kernel.org/pub/scm/linux/kernel/git/lethal/sh-2.6
* git://git.kernel.org/pub/scm/linux/kernel/git/lethal/sh-2.6: (23 commits)
  sh: sh7785lcr: Map whole PCI address space.
  sh: Fix up DSP context save/restore.
  sh: Fix up number of on-chip DMA channels on SH7091.
  sh: update defconfigs.
  sh: Kill off broken direct-mapped cache mode.
  sh: Wire up ARCH_HAS_DEFAULT_IDLE for cpuidle.
  sh: Add a command line option for disabling I/O trapping.
  sh: Select ARCH_HIBERNATION_POSSIBLE.
  sh: migor: Fix up CEU use flags.
  input: migor_ts: add wakeup support
  rtc: rtc-sh: use set_irq_wake()
  input: sh_keysc: use enable/disable_irq_wake()
  sh: intc: set_irq_wake() support
  sh: intc: install enable, disable and shutdown callbacks
  clocksource: sh_cmt: use remove_irq() and remove clockevent workaround
  sh: ap325 and Migo-R use new sh_mobile_ceu_info flags
  sh: Fix up -Wformat-security whining.
  sh: ap325rxa: Add ov772x support, again.
  sh: Sanitize asm/mmu.h for assembly use.
  sh: Tidy up sh7786 pinmux table.
  ...
2009-04-05 11:15:54 -07:00
Michael Trimarchi 01ab10393c sh: Fix up DSP context save/restore.
There were a number of issues with the DSP context save/restore code,
mostly left-over relics from when it was introduced on SH3-DSP with
little follow-up testing, resulting in things like task_pt_dspregs()
referencing incorrect state on the stack.

This follows the MIPS convention of tracking the DSP state in the
thread_struct and handling the state save/restore in switch_to() and
finish_arch_switch() respectively. The regset interface is also updated,
which allows us to finally be rid of task_pt_dspregs() and the special
cased task_pt_regs().

Signed-off-by: Michael Trimarchi <michael@evidence.eu.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2009-04-04 11:48:11 -04:00
Alexey Dobriyan 6f2c55b843 Simplify copy_thread()
First argument unused since 2.3.11.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-02 19:04:51 -07:00
Paul Mundt 43f8f9b95b sh: Simplify kernel_thread_helper() for sh32.
This can use the same implementation as sh64, the generated assembly is
the same between the new and old version, so there is not much point in
leaving it open coded in inline assembly.

This is preparatory work for future consolidation of the _32/_64
variants.

Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2008-12-22 18:44:44 +09:00
Paul Mundt 1da1180c6e sh: Split out the idle loop for reuse between _32/_64 variants.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2008-12-22 18:43:50 +09:00
Paul Mundt f74c034d52 sh: do not latency trace idle.
Description snipped from Steven Rostedt's PPC patch:

    When idle is called, interrupts are blocked, but the idle
    function will still wake up on an interrupt. The problem is
    that the interrupt disabled latency tracer will take this call
    to idle as a latency.

    This patch disables the latency tracing when going into idle.

Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2008-12-22 18:43:49 +09:00
Paul Mundt 75fd24c107 sh: Tidy up backtrace formatting with kallsyms disabled.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2008-12-22 18:43:49 +09:00
Paul Mundt 9cfc9a9b6f sh: Add a simple code dumper for SUPERH32 show_regs().
This implements a simple show_code() that is in turn plugged in to
show_regs() to provide minimal code dumping at the end of the trace.

Built on top of a simple instruction disassembler derived from the
binutils opcode table.

Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2008-12-22 18:43:49 +09:00
Paul Mundt e7ab3cd251 sh: Add FPU registers to regset interface.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2008-09-21 19:04:55 +09:00
Paul Mundt 3d58695edb sh: Trivial trace_mark() instrumentation for core events.
This implements a few trace points across events that are deemed
interesting. This implements a number of trace points:

	- The page fault handler / TLB miss
	- IPC calls
	- Kernel thread creation

The original LTTng patch had the slow-path instrumented, which
fails to account for the vast majority of events. In general
placing this in the fast-path is not a huge performance hit, as
we don't take page faults for kernel addresses.

The other bits of interest are some of the other trap handlers, as
well as the syscall entry/exit (which is better off being handled
through the tracehook API). Most of the other trap handlers are corner
cases where alternate means of notification exist, so there is little
value in placing extra trace points in these locations.

Based on top of the points provided both by the LTTng instrumentation
patch as well as the patch shipping in the ST-Linux tree, albeit in a
stripped down form.

Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2008-09-21 13:56:39 +09:00
Paul Mundt fa43972fab sh: fixup many sparse errors.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2008-09-08 10:35:04 +09:00
Paul Mundt 7d96169cb7 sh: Display CPU information in show_regs().
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2008-09-08 10:35:03 +09:00
Adrian Bunk 4c1cfab1e0 sh/kernel/ cleanups
This patch contains the following cleanups:
- make the following needlessly global code static:
  - cf-enabler.c: cf_init()
  - cpu/clock.c: __clk_enable()
  - cpu/clock.c: __clk_disable()
  - process_32.c: default_idle()
  - time_32.c: struct clocksource_sh
  - timers/timer-tmu.c: struct tmu_timer_ops
- remove the following unused functions (no CONFIG_BLK_DEV_FD on sh):
  - process_{32,64}.c: disable_hlt()
  - process_{32,64}.c: enable_hlt()

Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2008-07-28 18:10:30 +09:00
Thomas Gleixner b8f8c3cf0a nohz: prevent tick stop outside of the idle loop
Jack Ren and Eric Miao tracked down the following long standing
problem in the NOHZ code:

	scheduler switch to idle task
	enable interrupts

Window starts here

	----> interrupt happens (does not set NEED_RESCHED)
	      	irq_exit() stops the tick

	----> interrupt happens (does set NEED_RESCHED)

	return from schedule()
	
	cpu_idle(): preempt_disable();

Window ends here

The interrupts can happen at any point inside the race window. The
first interrupt stops the tick, the second one causes the scheduler to
rerun and switch away from idle again and we end up with the tick
disabled.

The fact that it needs two interrupts where the first one does not set
NEED_RESCHED and the second one does made the bug obscure and extremly
hard to reproduce and analyse. Kudos to Jack and Eric.

Solution: Limit the NOHZ functionality to the idle loop to make sure
that we can not run into such a situation ever again.

cpu_idle()
{
	preempt_disable();

	while(1) {
		 tick_nohz_stop_sched_tick(1); <- tell NOHZ code that we
		 			          are in the idle loop

		 while (!need_resched())
		       halt();

		 tick_nohz_restart_sched_tick(); <- disables NOHZ mode
		 preempt_enable_no_resched();
		 schedule();
		 preempt_disable();
	}
}

In hindsight we should have done this forever, but ... 

/me grabs a large brown paperbag.

Debugged-by: Jack Ren <jack.ren@marvell.com>, 
Debugged-by: eric miao <eric.y.miao@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-07-18 18:10:28 +02:00
Paul Mundt 9bbafce2ee sh: Fix occasional FPU register corruption under preempt.
Presently with preempt enabled there's the possibility to be preempted
after the TIF_USEDFPU test and the register save, leading to bogus
state post-__switch_to(). Use an explicit preempt_disable()/enable()
pair around unlazy_fpu()/clear_fpu() to avoid this. Follows the x86
change.

Reported-by: Takuo Koguchi <takuo.koguchi.sw@hitachi.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2008-03-26 19:02:47 +09:00
Stuart Menefy 1efe4ce3ca sh: GUSA atomic rollback support.
This implements kernel-level atomic rollback built on top of gUSA,
as an alternative non-IRQ based atomicity method. This is generally
a faster method for platforms that are lacking the LL/SC pairs that
SH-4A and later use, and is only supportable on legacy cores.

Signed-off-by: Stuart Menefy <stuart.menefy@st.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2008-01-28 13:18:58 +09:00
Paul Mundt 5a4f7c66be sh: Share bug/debug traps across _32 and _64.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2008-01-28 13:18:50 +09:00
Paul Mundt e7e0a4b54a sh: Share the ELF dump_task interfaces.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2008-01-28 13:18:49 +09:00
Paul Mundt fe51bc9eaf sh: Split out arch/sh/kernel/process.c for _32 and _64 variants.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2008-01-28 13:18:42 +09:00