linux-toradex.git/arch/mips/oprofile, branch v4.2.7

MIPS: Add R16000 detection

2015-04-01T15:22:13+00:00

This allows the kernel to correctly detect an R16000 MIPS CPU on systems that
have those.  Otherwise, such systems will detect the CPU as an R14000, due to
similarities in the CPU PRId value.

Signed-off-by: Joshua Kinard 
Cc: Linux MIPS List 
Patchwork: https://patchwork.linux-mips.org/patch/9092/
Signed-off-by: Ralf Baechle

MIPS: OProfile: Allow sharing IRQ with timer

2015-03-31T10:04:12+00:00

When requesting the performance counter overflow interrupt, pass flags
which are compatible with the cevt-r4k driver, in particular
IRQF_SHARED so that the two handlers can share the same IRQ. This is
possible since release 2 of the architecture where there are separate
pending interrupt bits for the timer interrupt and the performance
counter interrupt.

This will be necessary since the FDC interrupt can also be arbitrarily
routed to a CPU interrupt, possibly sharing with the timer, the
performance counters, or both, and it isn't scalable to have all the
handlers able to call other handlers that may be on the same IRQ line.

Signed-off-by: James Hogan 
Cc: Robert Richter 
Cc: linux-mips@linux-mips.org
Cc: oprofile-list@lists.sf.net
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/9130/
Signed-off-by: Ralf Baechle

MIPS: Remove redundant IPTI==IPPCI logic

2015-03-31T10:04:12+00:00

The situation where the timer interrupt is on the same line as the
performance counter interrupt is handled in per_cpu_trap_init() by
setting cp0_perfcount_irq to -1, so there is no need to duplicate the
logic conditional upon cp0_perfcount_irq >= 0 in perf
(init_hw_perf_events()) and oprofile (mipsxx_init()).

Signed-off-by: James Hogan 
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/9125/
Signed-off-by: Ralf Baechle

MIPS: cevt-r4k: Use CAUSEF_TI, CAUSEF_PCI constants

2015-03-31T10:04:12+00:00

Use CAUSEF_TI and CAUSEF_PCI constants from asm/mipsregs.h rather than
the magic values (1 << 30) and (1 << 26).

Signed-off-by: James Hogan 
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/9124/
Signed-off-by: Ralf Baechle

MIPS: oprofile: Backtrace: don't fail on leaf functions

2014-11-24T06:45:31+00:00

Continue the backtrace if we cannot find SP adjustment and RA save. In
that case, just assume the current RA. This allows us to get samples of
frequent callers of e.g. GLIBC memset().

Signed-off-by: Aaro Koskinen 
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/8109/
Signed-off-by: Ralf Baechle

MIPS: oprofile: Enable backtrace on timer-based profiling

2014-11-24T06:45:31+00:00

Allow unsupported CPU types to use backtrace with timer-based profiling.
Some CPUs (notably OCTEON) lack architecture-specific oprofile driver. In
such case oprofile can fallback to timer-based mode, and arch code can
still provide the backtrace functionality. So just set up the backtrace
hook always.

Signed-off-by: Aaro Koskinen 
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/8108/
Signed-off-by: Ralf Baechle

MIPS: Loongson-3: Add oprofile support

2014-11-24T06:45:01+00:00

Loongson-3 has two groups of performance counters, they are 4 sub-
registers of CP0's REG25. This patch add oprofile support.

REG25, sel 0: Perf Control of group 0;
REG25, sel 1: Perf Counter of group 0;
REG25, sel 2: Perf Control of group 1;
REG25, sel 3: Perf Counter of group 1.

Signed-off-by: Huacai Chen 
Cc: John Crispin 
Cc: Steven J. Hill 
Cc: linux-mips@linux-mips.org
Cc: Fuxin Zhang 
Cc: Zhangjin Wu 
Patchwork: https://patchwork.linux-mips.org/patch/8328/
Signed-off-by: Ralf Baechle

MIPS: Add hook to get C0 performance counter interrupt

2014-11-24T06:44:53+00:00

The hardware perf event driver and oprofile interpret the global
cp0_perfcount_irq differently: in the hardware perf event driver
it is an offset from MIPS_CPU_IRQ_BASE and in oprofile it is the
actual IRQ number.  This still works most of the time since
MIPS_CPU_IRQ_BASE is usually 0, but is clearly wrong.  Since the
performance counter interrupt may vary from platform to platform
like the C0 timer interrupt, add the optional get_c0_perfcount_int
hook which returns the IRQ number of the performance counter.
The hook should return < 0 if the performance counter interrupt is
shared with the timer.  If the hook is not present, the CPU vector
reported in C0_IntCtl (cp0_perfcount_irq) is used.

Signed-off-by: Andrew Bresticker 
Reviewed-by: Qais Yousef 
Tested-by: Qais Yousef 
Cc: Thomas Gleixner 
Cc: Jason Cooper 
Cc: Andrew Bresticker 
Cc: Jeffrey Deans 
Cc: Markos Chandras 
Cc: Paul Burton 
Cc: Qais Yousef 
Cc: Jonas Gorski 
Cc: John Crispin 
Cc: David Daney 
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/7805/
Signed-off-by: Ralf Baechle

MIPS: oprofile: Fix backtrace on 64-bit kernel

2014-11-19T17:22:07+00:00

Fix incorrect cast that always results in wrong address for the new
frame on 64-bit kernels.

Signed-off-by: Aaro Koskinen 
Cc: stable@vger.kernel.org
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/8110/
Signed-off-by: Ralf Baechle

MIPS: Add support for the M5150 processor

2014-03-26T22:09:22+00:00

The M5150 core is a 32-bit MIPS RISC which implements the
MIPS Architecture Release-5  in a 5-stage pipeline.
In addition, it includes the MIPS Architecture Virtualization Module
that enables virtualization of operating systems,
which provides a scalable, trusted, and secure execution environment.

Signed-off-by: Leonid Yegoshin 
Signed-off-by: Markos Chandras 
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/6596/
Signed-off-by: Ralf Baechle