The MCT has a nice 64-bit counter. That means that we _can_ register as a 64-bit clocksource and sched_clock. ...but that doesn't mean we should. The 64-bit counter is read by reading two 32-bit registers. That means reading needs to be something like: - Read upper half - Read lower half - Read upper half and confirm that it hasn't changed. That wouldn't be terrible, but: - THe MCT isn't very fast to access (hundreds of nanoseconds). - The clocksource is queried _all the time_. In total system profiles of real workloads on ChromeOS, we've seen exynos_frc_read() taking 2% or more of CPU time even after optimizing the 3 reads above to 2 (see below). The MCT is clocked at ~24MHz on all known systems. That means that the 32-bit half of the counter rolls over every ~178 seconds. This inspired an optimization in ChromeOS to cache the upper half between calls, moving 3 reads to 2. ...but we can do better! Having a 32-bit timer that flips every 178 seconds is more than sufficient for Linux. Let's just use the lower half of the MCT. Times on 5420 to do 1000000 gettimeofday() calls from userspace: * Original code: 1323852 us * ChromeOS cache upper half: 1173084 us * ChromeOS + ldmia to optimize: 1045674 us * Use lower 32-bit only (this code): 1014429 us As you can see, the time used doesn't increase linearly with the number of reads and we can make 64-bit work almost as fast as 32-bit with a bit of assembly code. But since there's no real gain for 64-bit, let's go with the simplest and fastest implementation. Note: with this change roughly half the time for gettimeofday() is spent in exynos_frc_read(). The rest is timer / system call overhead. Also note: this patch disables the use of the MCT on ARM64 systems until we've sorted out how to make "cycles_t" always 32-bit. Really ARM64 systems should be using arch timers anyway. Signed-off-by: Doug Anderson <dianders@chromium.org> Acked-by Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Kukjin Kim <kgene.kim@samsung.com> Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
In 'em_sti.c', it will call devm_ioremap_resource() which need HAS_IOMEM. So need let EM_TIMER_STI depend on HAS_IOMEM, too. The related error (with allmodconfig under score): LD init/built-in.o em_sti.c:(.text.em_sti_probe+0x84): undefined reference to `devm_ioremap_resource' make: *** [vmlinux] Error 1 Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com> Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
This patch adds a clock source and clock event for the timer found on the Mediatek SoCs. The Mediatek General Purpose Timer block provides five 32 bit timers and one 64 bit timer. Two 32 bit timers are used by this driver: TIMER1: clock events supporting periodic and oneshot events TIMER2: clock source configured as a free running counter The General Purpose Timer block can be run with two clocks. A 13 MHz system clock and the RTC clock running at 32 KHz. This implementation uses the system clock with no clock source divider. The interrupts are shared between the different timers and have to be read back from a register. We just enable one interrupt for the clock event. The clock event timer is used by all cores. Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
It should be "MTU2" instead of "TMU2" Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Acked-by: Wolfram Sang <wsa@sang-engineering.com> Acked-by: Simon Horman <horms+renesas@verge.net.au> Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Move the clocksource Kconfig entries into their own menu, so that they don't pollute the main device driver menu. Signed-off-by: Jean Delvare <jdelvare@suse.de> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Link: http://lkml.kernel.org/r/20140616114845.343e9960@endymion.delvare Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Pull timer core updates from Thomas Gleixner: "This time you get nothing really exciting: - A huge update to the sh* clocksource drivers - Support for two more ARM SoCs - Removal of the deprecated setup_sched_clock() API - The usual pile of fixlets all over the place" * 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits) clocksource: Add Freescale FlexTimer Module (FTM) timer support ARM: dts: vf610: Add Freescale FlexTimer Module timer node. clocksource: ftm: Add FlexTimer Module (FTM) Timer devicetree Documentation clocksource: sh_tmu: Remove unnecessary OOM messages clocksource: sh_mtu2: Remove unnecessary OOM messages clocksource: sh_cmt: Remove unnecessary OOM messages clocksource: em_sti: Remove unnecessary OOM messages clocksource: dw_apb_timer_of: Do not trace read_sched_clock clocksource: Fix clocksource_mmio_readX_down clocksource: Fix type confusion for clocksource_mmio_readX_Y clocksource: sh_tmu: Fix channel IRQ retrieval in legacy case clocksource: qcom: Implement read_current_timer for udelay ntp: Make is_error_status() use its argument ntp: Convert simple_strtol to kstrtol timer_stats/doc: Fix /proc/timer_stats documentation sched_clock: Remove deprecated setup_sched_clock() API ARM: sun6i: a31: Add support for the High Speed Timers clocksource: sun5i: Add support for reset controller clocksource: efm32: use $vendor,$device scheme for compatible string KConfig: Vexpress: build the ARM_GLOBAL_TIMER with vexpress platform ...
The versatile express changes for 3.16 introduced a number of build regressions for randconfig kernels by not tracking dependencies between the components right. This patch tries to rectify that: * the mach-vexpress code cannot link without the syscfg driver, which in turn needs MFD_VEXPRESS_SYSREG * various drivers call devm_regmap_init_vexpress_config(), which has to be exported so it can be used by loadable modules * the configuration bus uses OF DT helper functions that are not available to platforms disable CONFIG_OF * The sysreg driver exports GPIOs through gpiolib, which can be disabled on some platforms. * The clocksource code cannot be built on platforms that don't use modern timekeeping but rely on gettimeoffset. Signed-off-by: Arnd Bergmann <arnd@arndb.de>
The Freescale FlexTimer Module time reference is a 16-bit counter that can be used as an unsigned or signed increase counter. CNTIN defines the starting value of the count and MOD defines the final value of the count. The value of CNTIN is loaded into the FTM counter, and the counter increments until the value of MOD is reached, at which point the counter is reloaded with the value of CNTIN. That's also when an overflow interrupt will be generated. Here using the 'evt' prefix or postfix as clock event device and the 'src' as clock source device. Signed-off-by: Xiubo Li <Li.Xiubo@freescale.com> Cc: Shawn Guo <shawn.guo@linaro.org> Cc: Jingchang Lu <b35083@freescale.com> Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
This patch adds a trival sched clock source using free running, 24MHz clocked counter present in the ARM Ltd. reference platforms (Versatile, RealView, Versatile Express) System Registers block. This code replaces the call in the VE machine code. Signed-off-by: Pawel Moll <pawel.moll@arm.com> Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Pull ARM SoC cleanups from Arnd Bergmann:
"These cleanup patches are mainly move stuff around and should all be
harmless. They are mainly split out so that other branches can be
based on top to avoid conflicts.
Notable changes are:
- We finally remove all mach/timex.h, after CLOCK_TICK_RATE is no
longer used (Uwe Kleine-König)
- The Qualcomm MSM platform is split out into legacy mach-msm and
new-style mach-qcom, to allow easier maintainance of the new
hardware support without regressions (Kumar Gala)
- A rework of some of the Kconfig logic to simplify multiplatform
support (Rob Herring)
- Samsung Exynos gets closer to supporting multiplatform (Sachin
Kamat and others)
- mach-bcm3528 gets merged into mach-bcm (Stephen Warren)
- at91 gains some common clock framework support (Alexandre Belloni,
Jean-Jacques Hiblot and other French people)"
* tag 'cleanup-3.15' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc: (89 commits)
ARM: hisi: select HAVE_ARM_SCU only for SMP
ARM: efm32: allow uncompress debug output
ARM: prima2: build reset code standalone
ARM: at91: add PWM clock
ARM: at91: move sam9261 SoC to common clk
ARM: at91: prepare common clk transition for sam9261 SoC
ARM: at91: updated the at91_dt_defconfig with support for the ADS7846
ARM: at91: dt: sam9261: Device Tree support for the at91sam9261ek
ARM: at91: dt: defconfig: Added the sam9261 to the list of DT-enabled SOCs
ARM: at91: dt: Add at91sam9261 dt SoC support
ARM: at91: switch sam9rl to common clock framework
ARM: at91/dt: define main clk frequency of at91sam9rlek
ARM: at91/dt: define at91sam9rl clocks
ARM: at91: prepare common clk transition for sam9rl SoCs
ARM: at91: prepare sam9 dt boards transition to common clk
ARM: at91: dt: sam9rl: Device Tree for the at91sam9rlek
ARM: at91/defconfig: Add the sam9rl to the list of DT-enabled SOCs
ARM: at91: Add at91sam9rl DT SoC support
ARM: at91: prepare at91sam9rl DT transition
ARM: at91/defconfig: refresh at91sam9260_9g20_defconfig
...