Anders

@Pali Awesome. Adding a fan has kept my device from crashing: $ uptime -p up 7 hours, 42 minutes $ cpufreq-info [...] analyzing CPU 0: current CPU frequency is 1.20 GHz (asserted by call to hardware). cpufreq stats: 200 MHz:0.72%, 300 MHz:0.05%, 600 MHz:0.06%, 1.20 GHz:99.16% (2626) [...] analyzing CPU 1: current CPU frequency is 1.20 GHz (asserted by call to hardware). cpufreq stats: 200 MHz:0.72%, 300 MHz:0.05%, 600 MHz:0.06%, 1.20 GHz:99.16% (2628) [...] AFAIK that means that everything now works on my Espressobin v7 1GB board. The bootloader is stable, the CPU frequency is correctly reported and you can even clock the CPU at the advertised 1.2Ghz. Thanks @Pali! Where should direct my frustrations on why this has taken so long? Is it the fault of GlobalScale who failed to deliver on their mainline Linux support promise? Or is it Marvell who should have been more active in upstreaming their patches, instead of just providing an old kernel + a set of patches?

Can an External Abort trigger because of temps? I should already be on v3 of the a3720 cpufreq patches. Here's the output after fixing printf: TIM-1.0 mv_ddr-devel-g7c35173 DDR4 16b 1GB 1CS WTMI-devel-18.12.1-c444aeb-dirty WTMI: system early-init DDR topology parameters: ======================== ddr type DDR4 ddr speedbin 11 bus width 16-bits cs num 1 cs[0] - group num 0 cs[0] - bank num 8 cs[0] - capacity 1024MiB SVC REV: 5, CPU VDD voltage is invalid, using default value: 1.202V DRAM windows: ============= WIN[0] - base addr 0x60000000 WIN[0] - size 0x40000000 memory test region: =================== CS[0] 0x60000000 - 0x9fffffff SELF-REFRESH TEST PASSSetting clocks: CPU 1200 MHz, DDR 750 MHz VREF READ TRAINING PASSED VREF WRITE TRAINING PASSED DLL TUNING PASSED SELF-REFRESH TEST PASSNOTICE: Booting Trusted Firmware NOTICE: BL1: v2.4(debug):v2.4-556-g8078b5c5a (Marvell-devel-18.12.2) NOTICE: BL1: Built : 15:18:32, Apr 11 2021 NOTICE: BL1: Booting BL2 NOTICE: BL2: v2.4(debug):v2.4-556-g8078b5c5a (Marvell-devel-18.12.2) NOTICE: BL2: Built : 15:18:32, Apr 11 2021 NOTICE: BL1: Booting BL31 NOTICE: BL31: v2.4(debug):v2.4-556-g8078b5c5a (Marvell-devel-18.12.2) NOTICE: BL31: Built : 15:18:32, Apr 11 2021 U-Boot 2021.04-00640-g3f2e3c7845 (Apr 10 2021 - 15:27:13 +0200) DRAM: 1 GiB WDT: Not starting Comphy-0: USB3_HOST0 5 Gbps Comphy-1: PEX0 2.5 Gbps Comphy-2: SATA0 5 Gbps SATA link 0 timeout. AHCI 0001.0300 32 slots 1 ports 6 Gbps 0x1 impl SATA mode flags: ncq led only pmp fbss pio slum part sxs PCIE-0: Link down MMC: sdhci@d0000: 0, sdhci@d8000: 1 Loading Environment from SPIFlash... SF: Detected mx25u3235f with page size 256 Bytes, erase size 4 KiB, total 4 MiB OK Model: Globalscale Marvell ESPRESSOBin Board Card did not respond to voltage select! : -110 Net: eth0: neta@30000 [PRIME] Hit any key to stop autoboot: 0 I added a fan to my Espressobin, and I'm currently testing to see if that keeps it from crashing (running `stress --cpu 2` on the device. I've had it running for about 30 min so far).

Entering a low power state would be nice. I just got a crash on 1200Mhz. It may be due to temperature. I'm trying to reproduce it now to get a crashlog. Got something: TIM-1.0 mv_ddr-devel-g7c35173 DDR4 16b 1GB 1CS WTMI-devel-18.12.1-c444aeb-dirty WTMI: system early-init DDR topology parameters: ======================== ddr type DDR4 ddr speedbin 11 bus width 16-bits cs num 1 cs[0] - group num 0 cs[0] - bank num 8 cs[0] - capacity 1024MiB SVC REV: 536817928, CPU VDD voltage is invalid, using default value: DRAM windows: ============= WIN[0] - base addr 0x60000000 WIN[0] - size 0x40000000 memory test region: =================== CS[0] 0x60000000 - 0x9fffffff SELF-REFRESH TEST PASSSetting clocks: CPU 1200 MHz, DDR 750 MHz VREF READ TRAINING PASSED VREF WRITE TRAINING PASSED DLL TUNING PASSED SELF-REFRESH TEST PASSNOTICE: Booting Trusted Firmware NOTICE: BL1: v2.4(debug):v2.4-556-g8078b5c5a (Marvell-devel-18.12.2) NOTICE: BL1: Built : 15:37:24, Apr 10 2021 NOTICE: BL1: Booting BL2 NOTICE: BL2: v2.4(debug):v2.4-556-g8078b5c5a (Marvell-devel-18.12.2) NOTICE: BL2: Built : 15:37:24, Apr 10 2021 NOTICE: BL1: Booting BL31 NOTICE: BL31: v2.4(debug):v2.4-556-g8078b5c5a (Marvell-devel-18.12.2) NOTICE: BL31: Built : 15:37:24, Apr 10 2021 U-Boot 2021.04-00640-g3f2e3c7845 (Apr 10 2021 - 15:27:13 +0200) DRAM: 1 GiB WDT: Not starting Comphy-0: USB3_HOST0 5 Gbps Comphy-1: PEX0 2.5 Gbps Comphy-2: SATA0 5 Gbps SATA link 0 timeout. AHCI 0001.0300 32 slots 1 ports 6 Gbps 0x1 impl SATA mode flags: ncq led only pmp fbss pio slum part sxs PCIE-0: Link down MMC: sdhci@d0000: 0, sdhci@d8000: 1 Loading Environment from SPIFlash... SF: Detected mx25u3235f with page size 256 Bytes, erase size 4 KiB, total 4 MiB OK Model: Globalscale Marvell ESPRESSOBin Board Card did not respond to voltage select! : -110 Net: eth0: neta@30000 [PRIME] Hit any key to stop autoboot: 0 starting USB... Bus usb@58000: Register 2000104 NbrPorts 2 Starting the controller USB XHCI 1.00 Bus usb@5e000: USB EHCI 1.00 scanning bus usb@58000 for devices... 1 USB Device(s) found scanning bus usb@5e000 for devices... 1 USB Device(s) found scanning usb for storage devices... 0 Storage Device(s) found / Can't set block device ## Executing script at 06d00000 Wrong image format for "source" command /boot/ Can't set block device ## Executing script at 06d00000 Wrong image format for "source" command scanning bus for devices... Device 0: unknown device / Can't set block device ## Executing script at 06d00000 Wrong image format for "source" command /boot/ Can't set block device ## Executing script at 06d00000 Wrong image format for "source" command / Can't set block device ## Executing script at 06d00000 Wrong image format for "source" command /boot/ Can't set block device ## Executing script at 06d00000 Wrong image format for "source" command / Failed to load '/boot.scr' ## Executing script at 06d00000 Wrong image format for "source" command /boot/ 1119 bytes read in 17 ms (63.5 KiB/s) ## Executing script at 06d00000 237 bytes read in 14 ms (15.6 KiB/s) 21432832 bytes read in 910 ms (22.5 MiB/s) 12287307 bytes read in 533 ms (22 MiB/s) Failed to load '/boot/dtb/marvell/armada-3720-community.dtb' 11459 bytes read in 35 ms (319.3 KiB/s) ## Loading init Ramdisk from Legacy Image at 01100000 ... Image Name: uInitrd Image Type: AArch64 Linux RAMDisk Image (gzip compressed) Data Size: 12287243 Bytes = 11.7 MiB Load Address: 00000000 Entry Point: 00000000 Verifying Checksum ... OK ## Flattened Device Tree blob at 06000000 Booting using the fdt blob at 0x6000000 Loading Ramdisk to 3ef51000, end 3fb08d0b ... OK Using Device Tree in place at 0000000006000000, end 0000000006005cc2 Starting kernel ... [ 0.000000] Booting Linux on physical CPU 0x0000000000 [0x410fd034] [ 0.000000] Linux version 5.11.0+ (anders@ubuntu-desktop) (aarch64-linux-gnu-gcc (Ubuntu 9.3.0-17ubuntu1~20.04) 9.3.0, GNU ld (GNU Binutils for Ubuntu) 2.34) #1 SMP PREEMPT Wed Mar 3 11:51:48 CET 2021 [ 0.000000] Machine model: Globalscale Marvell ESPRESSOBin Board [ 0.000000] earlycon: ar3700_uart0 at MMIO 0x00000000d0012000 (options '') [ 0.000000] printk: bootconsole [ar3700_uart0] enabled Loading, please wait... starting version 237 Begin: Loading essential drivers ... done. Begin: Running /scripts/init-premount ... done. Begin: Mounting root file system ... Begin: Running /scripts/local-top ... done. Begin: Running /scripts/local-premount ... done. Begin: Will now check root file system ... fsck from util-linux 2.31.1 [/sbin/fsck.ext4 (1) -- /dev/mmcblk0p1] fsck.ext4 -a -C0 /dev/mmcblk0p1 /dev/mmcblk0p1 was not cleanly unmounted, check forced. ERROR: Unhandled External Abort received on 0x80000000 at EL3! / 7.0% ERROR: exception reason=0 syndrome=0xbf000001 BACKTRACE: START: plat_ea_handler 0: EL3: 0x4024d34 1: EL3: 0x4028438 2: EL3: 0x402416c BACKTRACE: END: plat_ea_handler Unhandled Exception from EL0 x0 = 0x00000055a51c5f60 x1 = 0x00000055a51add20 x2 = 0x00000000000008b0 x3 = 0x00000055a51c6620 x4 = 0x00000055a51ae620 x5 = 0x00000055a51c6f60 x6 = 0x432e6d6574737953 x7 = 0x746e656e6f706d6f x8 = 0x6f432e6c65646f4d x9 = 0x6f697469736f706d x10 = 0x70642e6c6c642e6e x11 = 0x000077656e2d676b x12 = 0x0132003c000580ea x13 = 0x432e6d6574737953 x14 = 0x0000000000000000 x15 = 0x0000000000000000 x16 = 0x0000007faf405bd8 x17 = 0x0000007faf241f90 x18 = 0x0000007faf312a70 x19 = 0x00000055a51a8098 x20 = 0x0000000000000000 x21 = 0x00000055a51c5f60 x22 = 0x00000055a51a7f60 x23 = 0x00000055a51a8030 x24 = 0x0000000000000001 x25 = 0x0000000000181e01 x26 = 0x0000007fdba04d08 x27 = 0x0000000000000040 x28 = 0x00000055a51c5f60 x29 = 0x0000007fdba04ca0 x30 = 0x0000007faf3eaf28 scr_el3 = 0x0000000000000739 sctlr_el3 = 0x0000000030cd183f cptr_el3 = 0x0000000000000000 tcr_el3 = 0x0000000080803520 daif = 0x00000000000002c0 mair_el3 = 0x00000000004404ff spsr_el3 = 0x0000000020000000 elr_el3 = 0x0000007faf2420c4 ttbr0_el3 = 0x0000000004031c80 esr_el3 = 0x00000000bf000001 far_el3 = 0x0000000000000000 spsr_el1 = 0x0000000020001000 elr_el1 = 0x0000007faf27ff9c spsr_abt = 0x0000000000000000 spsr_und = 0x0000000000000000 spsr_irq = 0x0000000000000000 spsr_fiq = 0x0000000000000000 sctlr_el1 = 0x0000000034d4d91d actlr_el1 = 0x0000000000000000 cpacr_el1 = 0x0000000000300000 csselr_el1 = 0x0000000000000000 sp_el1 = 0xffffffc011704000 esr_el1 = 0x0000000056000000 ttbr0_el1 = 0x000000003f1e0000 ttbr1_el1 = 0x01040000080ec000 mair_el1 = 0x000c0400bb44ffff amair_el1 = 0x0000000000000000 tcr_el1 = 0x00000032b5593519 tpidr_el1 = 0xffffffc02ec2f000 tpidr_el0 = 0x0000007faf42a700 tpidrro_el0 = 0x0000000000000000 par_el1 = 0xff00000004024980 mpidr_el1 = 0x0000000080000000 afsr0_el1 = 0x0000000000000000 afsr1_el1 = 0x0000000000000000 contextidr_el1 = 0x00000000000000f1 vbar_el1 = 0xffffffc010010800 cntp_ctl_el0 = 0x0000000000000005 cntp_cval_el0 = 0x000000000e45c556 cntv_ctl_el0 = 0x0000000000000000 cntv_cval_el0 = 0x0080000000000030 cntkctl_el1 = 0x0000000000000096 sp_el0 = 0x0000000004030e50 isr_el1 = 0x0000000000000040 dacr32_el2 = 0x0000000000000000 ifsr32_el2 = 0x0000000000000000 cpuectlr_el1 = 0x0000000000000040 cpumerrsr_el1 = 0x00000000001c00f2 l2merrsr_el1 = 0x80000100911820b0 cpuactlr_el1 = 0x00000000090ca000 icc_hppir0_el1 = 0x00000000000003fd icc_hppir1_el1 = 0x000000000000001e icc_ctlr_el3 = 0x0000000000000410 gicd_ispendr regs (Offsets 0x200 - 0x278) 0000000000000200: 0x0000000000000002 0000000000000208: 0x0000000000000000 0000000000000210: 0x0000000000000000 0000000000000218: 0x0000000000000000 0000000000000220: 0x0000000f00000024 0000000000000228: 0x0000000000000000 0000000000000230: 0x0000000000000000 0000000000000238: 0x0000002400000000 0000000000000240: 0x00000000000000c0 0000000000000248: 0x0000000000000000 0000000000000250: 0x0000000000000000 0000000000000258: 0x0000000000000000 0000000000000260: 0x0000000000000000 0000000000000268: 0x0000000000000000 0000000000000270: 0x0000000000000000 0000000000000278: 0x0000000000000000 Unhandled Exception in EL3. [...] It may just need something better than the standard heat sink. Even if it is not stable, the patch is still nice to have since it lets you flash a new bootloader without moving jumpers around and doing recovery using UART.

Another nice-to-have is proper powerdown handling: anders@espressobin:~$ sudo shutdown -hP now [...] [ 921.950348] reboot: Power down ERROR: a3700_system_off needs to be implemented BACKTRACE: START: a3700_system_off 0: EL3: 0x4024d34 1: EL3: 0x4023834 2: EL3: 0x4029c2c 3: EL3: 0x4029b34 4: EL3: 0x402a43c 5: EL3: 0x4024ba0 BACKTRACE: END: a3700_system_off Unhandled Exception from EL1 x0 = 0x0000000084000008 [...]

@Pali That actually seems to work: TIM-1.0 mv_ddr-devel-g7c35173 DDR4 16b 1GB 1CS WTMI-devel-18.12.1-c444aeb-dirty WTMI: system early-init DDR topology parameters: ======================== ddr type DDR4 ddr speedbin 11 bus width 16-bits cs num 1 cs[0] - group num 0 cs[0] - bank num 8 cs[0] - capacity 1024MiB SVC REV: 536817928, CPU VDD voltage is invalid, using default value: DRAM windows: ============= WIN[0] - base addr 0x60000000 WIN[0] - size 0x40000000 memory test region: =================== CS[0] 0x60000000 - 0x9fffffff SELF-REFRESH TEST PASSSetting clocks: CPU 1200 MHz, DDR 750 MHz VREF READ TRAINING PASSED VREF WRITE TRAINING PASSED DLL TUNING PASSED SELF-REFRESH TEST PASSNOTICE: Booting Trusted Firmware NOTICE: BL1: v2.4(debug):v2.4-556-g8078b5c5a (Marvell-devel-18.12.2) NOTICE: BL1: Built : 15:37:24, Apr 10 2021 NOTICE: BL1: Booting BL2 NOTICE: BL2: v2.4(debug):v2.4-556-g8078b5c5a (Marvell-devel-18.12.2) NOTICE: BL2: Built : 15:37:24, Apr 10 2021 NOTICE: BL1: Booting BL31 NOTICE: BL31: v2.4(debug):v2.4-556-g8078b5c5a (Marvell-devel-18.12.2) NOTICE: BL31: Built : 15:37:24, Apr 10 2021 U-Boot 2021.04-00640-g3f2e3c7845 (Apr 10 2021 - 15:27:13 +0200) DRAM: 1 GiB WDT: Not starting Comphy-0: USB3_HOST0 5 Gbps Comphy-1: PEX0 2.5 Gbps Comphy-2: SATA0 5 Gbps SATA link 0 timeout. AHCI 0001.0300 32 slots 1 ports 6 Gbps 0x1 impl SATA mode flags: ncq led only pmp fbss pio slum part sxs PCIE-0: Link down MMC: sdhci@d0000: 0, sdhci@d8000: 1 Loading Environment from SPIFlash... SF: Detected mx25u3235f with page size 256 Bytes, erase size 4 KiB, total 4 MiB OK Model: Globalscale Marvell ESPRESSOBin Board Card did not respond to voltage select! : -110 Net: eth0: neta@30000 [PRIME] Hit any key to stop autoboot: 0 anders@espressobin:~$ uname -a Linux espressobin 5.11.0+ #1 SMP PREEMPT Wed Mar 3 11:51:48 CET 2021 aarch64 aarch64 aarch64 GNU/Linux anders@espressobin:~$ cpufreq-info cpufrequtils 008: cpufreq-info (C) Dominik Brodowski 2004-2009 Report errors and bugs to cpufreq@vger.kernel.org, please. analyzing CPU 0: driver: cpufreq-dt CPUs which run at the same hardware frequency: 0 1 CPUs which need to have their frequency coordinated by software: 0 1 maximum transition latency: 0.97 ms. hardware limits: 200 MHz - 1.20 GHz available frequency steps: 200 MHz, 300 MHz, 600 MHz, 1.20 GHz available cpufreq governors: conservative, ondemand, userspace, powersave, performance, schedutil current policy: frequency should be within 200 MHz and 1.20 GHz. The governor "ondemand" may decide which speed to use within this range. current CPU frequency is 600 MHz (asserted by call to hardware). cpufreq stats: 200 MHz:79.25%, 300 MHz:5.20%, 600 MHz:1.47%, 1.20 GHz:14.08% (1095) analyzing CPU 1: driver: cpufreq-dt CPUs which run at the same hardware frequency: 0 1 CPUs which need to have their frequency coordinated by software: 0 1 maximum transition latency: 0.97 ms. hardware limits: 200 MHz - 1.20 GHz available frequency steps: 200 MHz, 300 MHz, 600 MHz, 1.20 GHz available cpufreq governors: conservative, ondemand, userspace, powersave, performance, schedutil current policy: frequency should be within 200 MHz and 1.20 GHz. The governor "ondemand" may decide which speed to use within this range. current CPU frequency is 600 MHz (asserted by call to hardware). cpufreq stats: 200 MHz:79.25%, 300 MHz:5.20%, 600 MHz:1.47%, 1.20 GHz:14.08% (1095) anders@espressobin:~$ 7za b 7-Zip (a) [64] 16.02 : Copyright (c) 1999-2016 Igor Pavlov : 2016-05-21 p7zip Version 16.02 (locale=en_US.UTF-8,Utf16=on,HugeFiles=on,64 bits,2 CPUs LE) LE CPU Freq: 1195 1197 1197 1197 1197 1197 1197 1197 1196 RAM size: 983 MB, # CPU hardware threads: 2 RAM usage: 441 MB, # Benchmark threads: 2 Compressing | Decompressing Dict Speed Usage R/U Rating | Speed Usage R/U Rating KiB/s % MIPS MIPS | KiB/s % MIPS MIPS 22: 1013 159 621 986 | 26035 199 1115 2223 23: 994 158 640 1013 | 25584 199 1110 2215 24: 989 159 667 1064 | 24925 198 1103 2188 25: 982 160 703 1122 | 24618 199 1099 2191 ---------------------------------- | ------------------------------ Avr: 159 658 1046 | 199 1107 2204 Tot: 179 882 1625 For reference, this is how I built the bootloader (cpu_vdd_fallback.patch contains the patch you posted for wtmi/sys_init/avs.c): $ git clone https://source.denx.de/u-boot/u-boot.git $ git clone https://git.trustedfirmware.org/TF-A/trusted-firmware-a.git $ git clone https://github.com/weidai11/cryptopp.git $ git clone https://github.com/MarvellEmbeddedProcessors/A3700-utils-marvell.git $ git clone https://github.com/MarvellEmbeddedProcessors/mv-ddr-marvell.git $ cd u-boot $ export CROSS_COMPILE=aarch64-linux-gnu- $ make mvebu_espressobin-88f3720_defconfig $ make DEVICE_TREE=armada-3720-espressobin -j$(nproc) $ cd ../A3700-utils-marvell/ $ git apply cpu_vdd_fallback.patch $ cd ../trusted-firmware-a/ $ export BL33=../u-boot/u-boot.bin $ make DEBUG=1 USE_COHERENT_MEM=0 LOG_LEVEL=20 SECURE=0 CLOCKSPRESET=CPU_1200_DDR_750 DDR_TOPOLOGY=5 WTP="$(realpath ../A3700-utils-marvell/)" MV_DDR_PATH=../mv-ddr-marvell/ CRYPTOPP_PATH="$(realpath ../cryptopp/)" PLAT=a3700 mrvl_flash -j$(nproc) I'll let you know if I get a crash. Should I be concerned about temperatures? How can I read the CPU temperature?

@Pali This is how I attempted to build an image (inspired by http://wiki.espressobin.net/tiki-index.php?page=Build+From+Source+-+Bootloader): $ mkdir espressobin-bootloader && cd espressobin-bootloader $ git clone https://github.com/MarvellEmbeddedProcessors/u-boot-marvell.git -b u-boot-2017.03-armada-17.10 $ git clone https://github.com/MarvellEmbeddedProcessors/atf-marvell.git -b atf-v1.3-armada-17.10 $ git clone https://github.com/MarvellEmbeddedProcessors/A3700-utils-marvell.git -b master $ git clone https://github.com/MarvellEmbeddedProcessors/mv-ddr-marvell.git -b master $ cd u-boot-marvell $ export CROSS_COMPILE=aarch64-linux-gnu- $ make mvebu_espressobin-88f3720_defconfig $ sed -i 's/-Werror //' Makefile $ make DEVICE_TREE=armada-3720-espressobin $ cd .. $ mkdir -p A3700-utils-marvell/ddr/tim_ddr $ ln -sr A3700-utils-marvell/script/ A3700-utils-marvell/ddr/tim_ddr/script $ ln -sr A3700-utils-marvell/wtmi/ A3700-utils-marvell/ddr/tim_ddr/wtmi $ ln -sr A3700-utils-marvell/tim/ A3700-utils-marvell/ddr/tim_ddr/tim $ ln -sr A3700-utils-marvell/wtptp/linux/tbb_linux A3700-utils-marvell/wtptp/linux/TBB_linux $ cd atf-marvell $ export BL33=../u-boot-marvell/u-boot.bin $ make DEBUG=1 USE_COHERENT_MEM=0 LOG_LEVEL=20 SECURE=0 CLOCKSPRESET=CPU_1000_DDR_800 DDR_TOPOLOGY=5 BOOTDEV=SPINOR PARTNUM=0 WTP=../A3700-utils-marvell/ MV_DDR_PATH=../mv-ddr-marvell/ PLAT=a3700 all fip // Now copy build/a3700/debug/flash-image.bin to a FAT32 USB, and flash it on the device: Marvell>> bubt flash-image.bin spi usb This is what I got trying to boot this 1000Mhz image: TIM-1.0 mv_ddr-devel-g7c35173 DDR4 16b 1GB 1CS WTMI-devel-18.12.1-c444aeb WTMI: system early-init DDR topology parameters: ======================== ddr type DDR4 ddr speedbin 11 bus width 16-bits cs num 1 cs[0] - group num 0 cs[0] - bank num 8 cs[0] - capacity 1024MiB SVC REV: 5, CPU VDD voltage: 1.155V DRAM windows: ============= WIN[0] - base addr 0x60000000 WIN[0] - size 0x40000000 memory test region: =================== CS[0] 0x60000000 - 0x9fffffff SELF-REFRESH TEST PASSSetting clocks: CPU 1000 MHz, DDR 800 MHz VREF READ TRAINING PASSED VREF WRITE TRAINING PASSED DLL TUNING PASSED ASSERT: mmap_add_region <96> : IS_PAGE_ALIGNED(base_va) And with the new patch applied, and configured to 1200mhz: $ cd ../A3700-utils-marvell/ $ make clean $ git apply cpu_vdd_fallback.patch $ cd ../atf-marvell $ make distclean $ make DEBUG=1 USE_COHERENT_MEM=0 LOG_LEVEL=20 SECURE=0 CLOCKSPRESET=CPU_1200_DDR_750 DDR_TOPOLOGY=5 BOOTDEV=SPINOR PARTNUM=0 WTP=../A3700-utils-marvell/ MV_DDR_PATH=../mv-ddr-marvell/ PLAT=a3700 all fip This results in: TIM-1.0 mv_ddr-devel-g7c35173 DDR4 16b 1GB 1CS WTMI-devel-18.12.1-c444aeb-dirty WTMI: system early-init DDR topology parameters: ======================== ddr type DDR4 ddr speedbin 11 bus width 16-bits cs num 1 cs[0] - group num 0 cs[0] - bank num 8 cs[0] - capacity 1024MiB SVC REV: 536817928, CPU VDD voltage is invalid, using default value: DRAM windows: ============= WIN[0] - base addr 0x60000000 WIN[0] - size 0x40000000 memory test region: =================== CS[0] 0x60000000 - 0x9fffffff SELF-REFRESH TEST PASSSetting clocks: CPU 1200 MHz, DDR 750 MHz VREF READ TRAINING PASSED VREF WRITE TRAINING PASSED DLL TUNING PASSED ASSERT: mmap_add_region <96> : IS_PAGE_ALIGNED(base_va) I think this is what is causing me problems: "No input file for TIMN is supplied". I'll continue working on it tomorrow night! [...] TBB Version : 3.3.12.1 TBB Date : 2017-03-17 Start time: 04/08/21 23:49:06 CommandLineOptions: -r ../A3700-utils-marvell//atf-ntim.txt -v -D Verifying Descriptor Integrity... Parsing non trusted TIM... Parsing Instruction Labels.... Finished Parsing Instruction Labels.... Parsing Instruction Labels.... Finished Parsing Instruction Labels.... Parsing Instruction Labels.... Finished Parsing Instruction Labels.... Success: Non-trusted Tim Descriptor file parsing has completed successfully! Processing non trusted TIM... Prepending ImageTag <0x57544d49> to image file: <../A3700-utils-marvell//wtmi/build/wtmi_h.bin>. Prepending ImageTag <0x4F424d49> to image file: <./build/a3700/debug/boot-image_h.bin>. 'TIM_ATF.bin' size in bytes: 3064 Tim size to hash read from file: 3064 TIM Hash size (in bits) 256 0xEED27F4D 0xC1E7B5BF 0x93AC3F05 0x4440324F 0x10AB1D38 0x4536F14F 0x42199E01 0x2F67F28B Success: NTIM Processing has completed successfully! Finish time: 04/08/21 23:49:06 TBB Exiting...! Building flash image ../A3700-utils-marvell//script/buildtim.sh 0 SPINOR ../A3700-utils-marvell//tim/untrusted ../A3700-utils-marvell//ddr/tim_ddr CPU_1000_DDR_800 5 0 1 ../A3700-utils-marvell//atf-ntim.txt 1 sed -i 's|WTMI_IMG|../A3700-utils-marvell//wtmi/build/wtmi.bin|1' ../A3700-utils-marvell//atf-ntim.txt sed -i 's|BOOT_IMAGE|./build/a3700/debug/boot-image.bin|1' ../A3700-utils-marvell//atf-ntim.txt ../A3700-utils-marvell//wtptp/linux/TBB_linux -r ../A3700-utils-marvell//atf-ntim.txt -v -D TBB Version : 3.3.12.1 TBB Date : 2017-03-17 Start time: 04/08/21 23:49:06 CommandLineOptions: -r ../A3700-utils-marvell//atf-ntim.txt -v -D Verifying Descriptor Integrity... Parsing non trusted TIM... Parsing Instruction Labels.... Finished Parsing Instruction Labels.... Parsing Instruction Labels.... Finished Parsing Instruction Labels.... Parsing Instruction Labels.... Finished Parsing Instruction Labels.... Success: Non-trusted Tim Descriptor file parsing has completed successfully! Processing non trusted TIM... Prepending ImageTag <0x57544d49> to image file: <../A3700-utils-marvell//wtmi/build/wtmi_h.bin>. Prepending ImageTag <0x4F424d49> to image file: <./build/a3700/debug/boot-image_h.bin>. 'TIM_ATF.bin' size in bytes: 3780 Tim size to hash read from file: 3780 TIM Hash size (in bits) 256 0xD38D2762 0xBA346897 0x6BB1D740 0xD44AB2CF 0x2C52F87B 0x92A99738 0x515873A2 0xD6648666 Success: NTIM Processing has completed successfully! Finish time: 04/08/21 23:49:06 TBB Exiting...! ../A3700-utils-marvell//script/tim2img.pl -i ../A3700-utils-marvell//atf-ntim.txt -o ./build/a3700/debug/flash-image.bin No input file for TIMN is supplied Total number of images to process in file[0] - 3 0 Image at offset 00000000 is TIM_ATF.bin 1 Image at offset 00004000 is ../A3700-utils-marvell//wtmi/build/wtmi.bin 2 Image at offset 00015000 is ./build/a3700/debug/boot-image.bin Total number of images 3

With a Espressobin board? @all Are there anyone who's been able to boot using flash-image-ddr4-1g-1cs-1200_750.bin or flash-image-ddr4-2g-2cs-1200_750.bin, or should they be warned against on https://www.armbian.com/espressobin/ since they just soft brick your board? It would also be nice if someone with a chip with readable labels could take a picture and share. You'll need to wriggle the heat-sink quite a bit (maybe easier if the board is warm). I'm my case, I could just put it back on the chip with the glue still working.

@Paul Interesting. All marketing on espressobin.net and from Globalscale claims that this chip is 1.2Ghz capable. I'm going to need some help interpreting the labels on the chip: https://drive.google.com/file/d/1dqvT6HzcH9VCEb4dPryXie61xP3WwY0B/view?usp=sharing https://drive.google.com/file/d/1rldOzYHm3nWbHMIr08oCoLps1hM9dq_R/view?usp=sharing

@Pali Normal boot: TIM-1.0 WTMI-devel-18.12.1-0967979 WTMI: system early-init SVC REV: 5, CPU VDD voltage: 1.155V NOTICE: Booting Trusted Firmware NOTICE: BL1: v1.5(release):1f8ca7e0 (Marvell-devel-18.12.2) NOTICE: BL1: Built : 10:12:00, Sep 18 2020 NOTICE: BL1: Booting BL2 NOTICE: BL2: v1.5(release):1f8ca7e0 (Marvell-devel-18.12.2) NOTICE: BL2: Built : 10:12:01, Sep 18 2020 NOTICE: BL1: Booting BL31 NOTICE: BL31: v1.5(release):1f8ca7e0 (Marvell-devel-18.12.2) NOTICE: BL31: Built : 10:1 U-Boot 2018.03-devel-18.12.3-gc9aa92ce70-armbian (Sep 18 2020 - 10:07:21 +0200) Model: Marvell Armada 3720 Community Board ESPRESSOBin CPU 1000 [MHz] L2 800 [MHz] TClock 200 [MHz] DDR 800 [MHz] DRAM: 1 GiB Comphy chip #0: Comphy-0: USB3 5 Gbps Comphy-1: PEX0 2.5 Gbps Comphy-2: SATA0 6 Gbps SATA link 0 timeout. AHCI 0001.0300 32 slots 1 ports 6 Gbps 0x1 impl SATA mode flags: ncq led only pmp fbss pio slum part sxs PCIE-0: Link down MMC: sdhci@d0000: 0 Loading Environment from SPI Flash... SF: Detected mx25u3235f with page size 256 Bytes, erase size 64 KiBB OK Model: Marvell Armada 3720 Community Board ESPRESSOBin Net: eth0: neta@30000 [PRIME] Hit any key to stop autoboot: 0 Marvell>> md d0012604 1; md d0012604 1; md d0012604 1 d0012604: 00000000 .... d0012604: 27236501 .e#' d0012604: 0000f580 .... With flash-image-ddr4-1g-1cs-1200_750.bin (md5sum 1c25222cd3cb9162547afa80eb280a26) from https://minio.k-space.ee/minio/armbian/dl/espressobin/u-boot/ I managed to get this output once: TIM-1.0 WTMI-devel-18.12.1-0967979 WTMI: system early-init SVC REV: 5, CPU VDD voltage: 0.898V That voltage seems low, right? Do you still need me to pull the heat sink to get the lables / indentifiers printed on SoC chip?

Nice work. I'm unable to test it on my V7 1gb board though. Every time I fash it with a 1200mhz image, it bricks, and I can't even get to the uboot prompt. Are there anyone who's been able to boot the Espressobin V7 at 1.2 Ghz? By the way, who's sponsoring your work on this chip?

Done! https://lore.kernel.org/linux-arm-kernel/cf766197-666f-3d7d-3b9e-ba512619004e@gmail.com/

Hi @Pali Thank you for looking at this problem! I updated my u-boot to flash-image-ddr4-1g-1cs-1000_800-2021-01-03.bin (sha256: e3a9d9605d5a9ad1ff848985c18b1ce41c2dddfffcc8f8364f2d57d833e652bb), and built your kernel like this: $ git clone git://git.kernel.org/pub/scm/linux/kernel/git/pali/linux.git --depth 1 -b a3720-cpufreq-issues $ export ARCH=arm64 $ export CROSS_COMPILE=aarch64-linux-gnu- $ curl https://raw.githubusercontent.com/armbian/build/master/config/kernel/linux-mvebu64-current.config > .config $ make oldconfig (picked default for all new) $ make -j $(nproc) $ cp arch/arm64/boot/Image /mnt/sdcard/boot/ $ cp arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtb /mnt/sdcard/boot/dtb/marvell/ $ make modules_install INSTALL_MOD_PATH=/mnt/sdcard/ This is the result: root@espressobin:~# uname -a Linux espressobin 5.11.0-rc1+ #1 SMP PREEMPT Sun Jan 31 23:35:17 CET 2021 aarch64 aarch64 aarch64 GNU/Linux root@espressobin:~# cpufreq-info cpufrequtils 008: cpufreq-info (C) Dominik Brodowski 2004-2009 Report errors and bugs to cpufreq@vger.kernel.org, please. analyzing CPU 0: driver: cpufreq-dt CPUs which run at the same hardware frequency: 0 1 CPUs which need to have their frequency coordinated by software: 0 1 maximum transition latency: 0.97 ms. hardware limits: 200 MHz - 1000 MHz available frequency steps: 200 MHz, 250 MHz, 500 MHz, 1000 MHz available cpufreq governors: conservative, ondemand, userspace, powersave, performance, schedutil current policy: frequency should be within 200 MHz and 1000 MHz. The governor "ondemand" may decide which speed to use within this range. current CPU frequency is 1000 MHz (asserted by call to hardware). cpufreq stats: 200 MHz:34.71%, 250 MHz:13.20%, 500 MHz:6.26%, 1000 MHz:45.83% (2015) analyzing CPU 1: driver: cpufreq-dt CPUs which run at the same hardware frequency: 0 1 CPUs which need to have their frequency coordinated by software: 0 1 maximum transition latency: 0.97 ms. hardware limits: 200 MHz - 1000 MHz available frequency steps: 200 MHz, 250 MHz, 500 MHz, 1000 MHz available cpufreq governors: conservative, ondemand, userspace, powersave, performance, schedutil current policy: frequency should be within 200 MHz and 1000 MHz. The governor "ondemand" may decide which speed to use within this range. current CPU frequency is 500 MHz (asserted by call to hardware). cpufreq stats: 200 MHz:34.71%, 250 MHz:13.20%, 500 MHz:6.26%, 1000 MHz:45.83% (2015) root@espressobin:~# 7za b 7-Zip (a) [64] 16.02 : Copyright (c) 1999-2016 Igor Pavlov : 2016-05-21 p7zip Version 16.02 (locale=en_US.UTF-8,Utf16=on,HugeFiles=on,64 bits,2 CPUs LE) LE CPU Freq: 974 997 993 996 997 997 996 997 RAM size: 983 MB, # CPU hardware threads: 2 RAM usage: 441 MB, # Benchmark threads: 2 Compressing | Decompressing Dict Speed Usage R/U Rating | Speed Usage R/U Rating KiB/s % MIPS MIPS | KiB/s % MIPS MIPS 22: 879 153 560 856 | 21904 199 941 1870 23: 871 154 576 888 | 21518 199 938 1863 24: 863 154 603 928 | 21147 199 935 1857 25: 857 154 634 979 | 20885 199 934 1859 ---------------------------------- | ------------------------------ Avr: 154 593 913 | 199 937 1862 Tot: 176 765 1387 Yay! 1Ghz is finally working and is stable on Espressobin v7! And the new u-boot seems to boot every time! This is great - thanks! Time to push to mainline Linux, or do you want me to run more tests?

I'm getting tired of Globalscale deleting my post from the Espressobin forums, instead of either fixing or acknowledging the problem. So I'll repost this here for future reference. This is the URL to the original thread: http://espressobin.net/forums/topic/mainline-linux-not-running-at-1ghz/ Hi All That the Espressobin aims to support mainline is awesome – a lot of the benefits are described here http://espressobin.net/mainline-linux/. But I’m unable to get my v7 board running at more than 800MHz using the mainline kernel (for some reason cpufreq-info insists on reporting 1GHz with actual benchmarking only showing 800MHz). For the sake of this post, I tried pulling the most recent linux-next kernel. I’m using the config file from armbian. export ARCH=arm64 export CROSS_COMPILE=aarch64-linux-gnu- git checkout next-20190614 curl https://raw.githubusercontent.com/armbian/build/master/config/kernel/linux-mvebu64-next.config > .config make oldconfig # Just picked the defaults for new options make -j7 Image dtbs modules cp arch/arm64/boot/Image /mnt/sdcard/boot/ cp arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtb /mnt/sdcard/boot/dtb/marvell/ make modules_install INSTALL_MOD_PATH=/mnt/sdcard/ Here are the results. Notice the performance numbers and CPU Freq reported by 7-Zip: root@espressobin:~# uname -a Linux espressobin 5.2.0-rc4-next-20190614 #7 SMP PREEMPT Sun Jun 16 10:27:52 CEST 2019 aarch64 GNU/Linux root@espressobin:~# cpufreq-info cpufrequtils 008: cpufreq-info (C) Dominik Brodowski 2004-2009 Report errors and bugs to cpufreq@vger.kernel.org, please. analyzing CPU 0: driver: cpufreq-dt CPUs which run at the same hardware frequency: 0 1 CPUs which need to have their frequency coordinated by software: 0 1 maximum transition latency: 0.97 ms. hardware limits: 200 MHz - 1000 MHz available frequency steps: 200 MHz, 250 MHz, 500 MHz, 1000 MHz available cpufreq governors: conservative, userspace, powersave, ondemand, performance, schedutil current policy: frequency should be within 250 MHz and 1000 MHz. The governor "performance" may decide which speed to use within this range. current CPU frequency is 1000 MHz (asserted by call to hardware). cpufreq stats: 200 MHz:0.09%, 250 MHz:3.60%, 500 MHz:0.16%, 1000 MHz:96.15% (152) analyzing CPU 1: driver: cpufreq-dt CPUs which run at the same hardware frequency: 0 1 CPUs which need to have their frequency coordinated by software: 0 1 maximum transition latency: 0.97 ms. hardware limits: 200 MHz - 1000 MHz available frequency steps: 200 MHz, 250 MHz, 500 MHz, 1000 MHz available cpufreq governors: conservative, userspace, powersave, ondemand, performance, schedutil current policy: frequency should be within 250 MHz and 1000 MHz. The governor "performance" may decide which speed to use within this range. current CPU frequency is 1000 MHz (asserted by call to hardware). cpufreq stats: 200 MHz:0.09%, 250 MHz:3.60%, 500 MHz:0.16%, 1000 MHz:96.15% (152) root@espressobin:~# lscpu Architecture: aarch64 Byte Order: Little Endian CPU(s): 2 On-line CPU(s) list: 0,1 Thread(s) per core: 1 Core(s) per socket: 2 Socket(s): 1 NUMA node(s): 1 Model: 4 CPU max MHz: 1000.0000 CPU min MHz: 200.0000 BogoMIPS: 25.00 NUMA node0 CPU(s): 0,1 Flags: fp asimd evtstrm aes pmull sha1 sha2 crc32 cpuid root@espressobin:~# 7za b 7-Zip (a) [64] 16.02 : Copyright (c) 1999-2016 Igor Pavlov : 2016-05-21 p7zip Version 16.02 (locale=en_US.UTF-8,Utf16=on,HugeFiles=on,64 bits,2 CPUs LE) LE CPU Freq: 794 794 794 794 794 794 794 794 RAM size: 986 MB, # CPU hardware threads: 2 RAM usage: 441 MB, # Benchmark threads: 2 Compressing | Decompressing Dict Speed Usage R/U Rating | Speed Usage R/U Rating KiB/s % MIPS MIPS | KiB/s % MIPS MIPS 22: 709 148 467 690 | 17938 199 771 1532 23: 701 149 480 715 | 17737 199 770 1535 24: 696 149 503 749 | 17395 199 768 1527 25: 688 149 528 786 | 17149 198 769 1526 ---------------------------------- | ------------------------------ Avr: 149 494 735 | 199 770 1530 Tot: 174 632 1133 The following are the performance numbers I’m looking for, achieved using 4.4.8-armada-17.02-espressobin kernel downloaded from http://espressobin.net/tech-spec/. That one, and 4.4.52-armada-17.10.4-g719fc86-dirty are the only kernels I have been able to actually get 1GHz performance with: root@espressobin:~# uname -a Linux espressobin 4.4.52-armada-17.10.4-g719fc86-dirty #7 SMP PREEMPT Tue Jul 3 10:59:53 UTC 2018 aarch64 GNU/Linux root@espressobin:~# 7za b 7-Zip (a) [64] 16.02 : Copyright (c) 1999-2016 Igor Pavlov : 2016-05-21 p7zip Version 16.02 (locale=en_US.UTF-8,Utf16=on,HugeFiles=on,64 bits,2 CPUs LE) LE CPU Freq: 734 997 998 998 998 992 996 996 RAM size: 927 MB, # CPU hardware threads: 2 RAM usage: 441 MB, # Benchmark threads: 2 Compressing | Decompressing Dict Speed Usage R/U Rating | Speed Usage R/U Rating KiB/s % MIPS MIPS | KiB/s % MIPS MIPS 22: 870 150 563 847 | 22431 198 969 1915 23: 860 151 582 876 | 22154 198 968 1918 24: 854 151 607 918 | 21735 198 963 1908 25: 848 152 639 969 | 21341 198 960 1900 ---------------------------------- | ------------------------------ Avr: 151 598 903 | 198 965 1910 Tot: 174 781 1406 Following http://wiki.espressobin.net/tiki-index.php?page=Build+From+Source+-+Kernel to build 4.4.52-armada-17.10.4-g719fc86-dirty also works fine at 1GHz. I’ve tried a bunch of different U-boots, all with the same result, so I really think the bug is in Linux. (FYI this is not the only problem I have been having with the v7, but lets focus on one bug at a time. Not to mention that Globalscale claims 1.2 GHz for v7 which seems entirely out of reach as any 1200 u-boot bricks my board).

@FlashBurn I'm having the same problem - only getting 800MHz. It's frustrating, since I bought this board because it claimed to deliver 1.2GHz. I think this is a problem in Linux, but I'm not sure where to report it, so I made a post in the espressobin.net forums. Now I just discovered that they deleted my thread, but here's a repost:

Here's an update: I've been running Armbian with nightly kernels, (currently on 4.19.50-mvebu64) and flash-image-ddr4-1g-1cs-800_800-2019-05-21.bin uboot entirely stable for some time now. The only two remaining problems being: 1) U-boot sometimes get stuck. I just reset the board until it boots. 2) With flash-image-ddr4-1g-1cs-1000_800-2019-05-21.bin I'm not getting 1GHz. (Also tested with 5.2.0-rc4-next-20190614). To help address the last problem, I just posted in the Espressobin forums: http://espressobin.net/forums/topic/mainline-linux-not-running-at-1ghz/ UPDATE: wtf - espressobin deleted that thread from their forum. Here's a repost. Hopefully someone is able to reach out to Marvell and make them fix the bug. Thanks for all the help so far