aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/tools/perf/scripts/python/export-to-sqlite.py (unfollow)
AgeCommit message (Collapse)AuthorFilesLines
2022-03-07clocksource/drivers/imx-tpm: Move tpm_read_sched_clock() under CONFIG_ARMNathan Chancellor1-1/+1
When building this driver for an architecture other than ARCH=arm: drivers/clocksource/timer-imx-tpm.c:78:20: error: unused function 'tpm_read_sched_clock' [-Werror,-Wunused-function] static u64 notrace tpm_read_sched_clock(void) ^ 1 error generated. Move the function definition under the existing CONFIG_ARM section so there is no more warning. Fixes: 10720e120e2b ("clocksource/drivers/imx-tpm: Exclude sched clock for ARM64") Signed-off-by: Nathan Chancellor <nathan@kernel.org> Reviewed-by: Peng Fan <peng.fan@nxp.com> Link: https://lore.kernel.org/r/20220303184212.2356245-1-nathan@kernel.org Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
2022-03-07clocksource/drivers/arm_arch_timer: Use event stream scaling when availableMarc Zyngier2-2/+12
With FEAT_ECV and the 1GHz counter, it is pretty likely that the event stream divider doesn't fit in the field that holds the divider value (we only have 4 bits to describe counter bits [15:0] Thankfully, FEAT_ECV also provides a scaling mechanism to switch the field to cover counter bits [23:8] instead. Enable this on arm64 when ECV is available (32bit doesn't have any detection infrastructure and is unlikely to be run on an ARMv8.6 system anyway). Signed-off-by: Marc Zyngier <maz@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Acked-by: Mark Rutland <mark.rutland@arm.com> Link: https://lore.kernel.org/r/20220203170502.2694422-1-maz@kernel.org Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
2022-03-07clocksource/drivers/exynos_mct: Increase the size of name arrayAlim Akhtar1-1/+5
Variable _name_ hold mct_tick number per cpu and it is currently limited to 10. Which restrict the scalability of the MCT driver for the SoC which has more local timers interrupts (>= 12). Increase the length of it to make mct_tick printed correctly for each local timer interrupts per CPU. Signed-off-by: Alim Akhtar <alim.akhtar@samsung.com> Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> Link: https://lore.kernel.org/r/20220221174547.26176-3-alim.akhtar@samsung.com Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
2022-03-07clocksource/drivers/exynos_mct: Bump up mct max irq numberAlim Akhtar1-1/+2
Bump-up maximum number of MCT IRQ to match the binding documentation. This make driver scalable for SoC which has more than 12 timer irqs, like recently added FSD SoC. Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> Signed-off-by: Alim Akhtar <alim.akhtar@samsung.com> Link: https://lore.kernel.org/r/20220221174547.26176-2-alim.akhtar@samsung.com Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
2022-03-07clocksource/drivers/exynos_mct: Remove mct interrupt index enumAlim Akhtar1-16/+6
MCT driver define an enum which list global and local timer's irq index. Most of them are not used but MCT_G0_IRQ and MCT_L0_IRQ and these two are at a fixed offset/index. Get rid of this enum and use a #define for the used irq index. No functional changes expected. Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> Signed-off-by: Alim Akhtar <alim.akhtar@samsung.com> Link: https://lore.kernel.org/r/20220221174547.26176-1-alim.akhtar@samsung.com Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
2022-03-07clocksource/drivers/exynos_mct: Handle DTS with higher number of interruptsKrzysztof Kozlowski1-1/+9
The driver statically defines maximum number of interrupts it can handle, however it does not respect that limit when configuring them. When provided with a DTS with more interrupts than assumed, the driver will overwrite static array mct_irqs leading to silent memory corruption. Validate the interrupts coming from DTS to avoid this. This does not change the fact that such DTS might not boot at all, because it is simply incompatible, however at least some warning will be printed. Fixes: 36ba5d527e95 ("ARM: EXYNOS: add device tree support for MCT controller driver") Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> Reviewed-by: Alim Akhtar <alim.akhtar@samsung.com> Link: https://lore.kernel.org/r/20220220103815.135380-1-krzysztof.kozlowski@canonical.com Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
2022-03-07clocksource/drivers/timer-ti-dm: Fix regression from errata i940 fixDrew Fustini3-9/+8
The existing fix for errata i940 causes a conflict for IPU2 which is using timer 3 and 4. From arch/arm/boot/dts/dra7-ipu-dsp-common.dtsi: &ipu2 { mboxes = <&mailbox6 &mbox_ipu2_ipc3x>; ti,timers = <&timer3>; ti,watchdog-timers = <&timer4>, <&timer9>; }; The conflict was noticed when booting mainline on the BeagleBoard X15 which has a TI AM5728 SoC: remoteproc remoteproc1: 55020000.ipu is available remoteproc remoteproc1: powering up 55020000.ipu remoteproc remoteproc1: Booting fw image dra7-ipu2-fw.xem4 omap-rproc 55020000.ipu: could not get timer platform device omap-rproc 55020000.ipu: omap_rproc_enable_timers failed: -19 remoteproc remoteproc1: can't start rproc 55020000.ipu: -19 This change modifies the errata fix to instead use timer 15 and 16 which resolves the timer conflict. It does not appear to introduce any latency regression. Results from cyclictest with original errata fix using dmtimer 3 and 4: # cyclictest --mlockall --smp --priority=80 --interval=200 --distance=0 policy: fifo: loadavg: 0.02 0.03 0.05 T: 0 ( 1449) P:80 I:200 C: 800368 Min: 0 Act: 32 Avg: 22 Max: 128 T: 1 ( 1450) P:80 I:200 C: 800301 Min: 0 Act: 12 Avg: 23 Max: 70 The results after the change to dmtimer 15 and 16: # cyclictest --mlockall --smp --priority=80 --interval=200 --distance=0 policy: fifo: loadavg: 0.36 0.19 0.07 T: 0 ( 1711) P:80 I:200 C: 759599 Min: 0 Act: 6 Avg: 22 Max: 108 T: 1 ( 1712) P:80 I:200 C: 759539 Min: 0 Act: 19 Avg: 23 Max: 79 Fixes: 25de4ce5ed02 ("clocksource/drivers/timer-ti-dm: Handle dra7 timer wrap errata i940") Link: https://lore.kernel.org/linux-omap/YfWsG0p6to3IJuvE@x1/ Suggested-by: Suman Anna <s-anna@ti.com> Reviewed-by: Tony Lindgren <tony@atomide.com> Signed-off-by: Drew Fustini <dfustini@baylibre.com> Link: https://lore.kernel.org/r/20220204053503.1409162-1-dfustini@baylibre.com Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
2022-02-16clocksource/drivers/imx-tpm: Exclude sched clock for ARM64Peng Fan1-1/+1
For ARM64 platform such as i.MX8ULP which has ARMv8 generic timer as sched clock, which is much faster compared with tpm sched clock. Reading the tpm count register in i.MX8ULP requires about 290ns, this is slow and introduce scheduler latency. So exclude tpm sched clock for ARM64 platform. Signed-off-by: Peng Fan <peng.fan@nxp.com> Link: https://lore.kernel.org/r/20220105124304.3567629-1-peng.fan@oss.nxp.com Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
2022-01-26clocksource/drivers/imx-tpm: Update name of clkevtPeng Fan1-1/+1
The tpm driver is not only for i.MX7ULP now, i.MX8ULP also use it. It maybe also used by other i.MX variants, so update name to reflect it. Signed-off-by: Peng Fan <peng.fan@nxp.com> Link: https://lore.kernel.org/r/20211214120737.1611955-6-peng.fan@oss.nxp.com Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
2022-01-26clocksource/drivers/imx-tpm: Add CLOCK_EVT_FEAT_DYNIRQPeng Fan1-1/+1
Add CLOCK_EVT_FEAT_DYNIRQ to allow the IRQ could be runtime set affinity to the cores that needs wake up, otherwise saying core0 has to send IPI to wakeup core1. With CLOCK_EVT_FEAT_DYNIRQ set, when broadcast timer could wake up the cores, IPI is not needed. Acked-by: Jacky Bai <ping.bai@nxp.com> Signed-off-by: Peng Fan <peng.fan@nxp.com> Link: https://lore.kernel.org/r/20211214120737.1611955-5-peng.fan@oss.nxp.com Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
2022-01-26clocksource/drivers/imx-tpm: Mark two variable with __ro_after_initPeng Fan1-2/+2
counter_width and timer_base will not be updated after init, so mark as __ro_after_init. Signed-off-by: Peng Fan <peng.fan@nxp.com> Link: https://lore.kernel.org/r/20211214120737.1611955-4-peng.fan@oss.nxp.com Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
2022-01-26clocksource/drivers/imx-tpm: Drop IRQF_IRQPOLLPeng Fan1-1/+1
Per the Documentation, IRQF_IRQPOLL is used for polling (only the interrupt that is registered first in a shared interrupt is considered for performance reasons) The TPM timer is not sharing interrupt with others, and pass irqpoll not make sense for i.MX platform. Signed-off-by: Peng Fan <peng.fan@nxp.com> Link: https://lore.kernel.org/r/20211214120737.1611955-3-peng.fan@oss.nxp.com Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
2022-01-26clocksource/drivers/imx-sysctr: Drop IRQF_IRQPOLLPeng Fan1-1/+1
Per the Documentation, IRQF_IRQPOLL is used for polling (only the interrupt that is registered first in a shared interrupt is considered for performance reasons) But this timer is not sharing interrupt line with others, and actually irqpoll not work with this timer with IRQF_IRQPOLL set, so drop the flag. Signed-off-by: Peng Fan <peng.fan@nxp.com> Link: https://lore.kernel.org/r/20211214120737.1611955-2-peng.fan@oss.nxp.com Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>