kernel/linux.git/arch/arc/boot, branch v5.4.158

ARC: build: move symlink creation to arch/arc/Makefile to avoid race

2021-01-19T17:26:14+00:00

[ Upstream commit c5e6ae563c802c4d828d42e134af64004db2e58c ] If you run 'make uImage uImage.gz' with the parallel option, uImage.gz will be created by two threads simultaneously. This is because arch/arc/Makefile does not specify the dependency between uImage and uImage.gz. Hence, GNU Make assumes they can be built in parallel. One thread descends into arch/arc/boot/ to create uImage, and another to create uImage.gz. Please notice the same log is displayed twice in the following steps: $ export CROSS_COMPILE= $ make -s ARCH=arc defconfig $ make -j$(nproc) ARCH=arc uImage uImage.gz [ snip ] LD vmlinux SORTTAB vmlinux SYSMAP System.map OBJCOPY arch/arc/boot/vmlinux.bin OBJCOPY arch/arc/boot/vmlinux.bin GZIP arch/arc/boot/vmlinux.bin.gz GZIP arch/arc/boot/vmlinux.bin.gz UIMAGE arch/arc/boot/uImage.gz UIMAGE arch/arc/boot/uImage.gz Image Name: Linux-5.10.0-rc4-00003-g62f23044 Created: Sun Nov 22 02:52:26 2020 Image Type: ARC Linux Kernel Image (gzip compressed) Data Size: 2109376 Bytes = 2059.94 KiB = 2.01 MiB Load Address: 80000000 Entry Point: 80004000 Image arch/arc/boot/uImage is ready Image Name: Linux-5.10.0-rc4-00003-g62f23044 Created: Sun Nov 22 02:52:26 2020 Image Type: ARC Linux Kernel Image (gzip compressed) Data Size: 2815455 Bytes = 2749.47 KiB = 2.69 MiB Load Address: 80000000 Entry Point: 80004000 This is a race between the two threads trying to write to the same file arch/arc/boot/uImage.gz. This is a potential problem that can generate a broken file. I fixed a similar problem for ARM by commit 3939f3345050 ("ARM: 8418/1: add boot image dependencies to not generate invalid images"). I highly recommend to avoid such build rules that cause a race condition. Move the uImage rule to arch/arc/Makefile. Another strangeness is that arch/arc/boot/Makefile compares the timestamps between $(obj)/uImage and $(obj)/uImage.*: $(obj)/uImage: $(obj)/uImage.$(suffix-y) @ln -sf $(notdir $<) $@ @echo ' Image $@ is ready' This does not work as expected since $(obj)/uImage is a symlink. The symlink should be created in a phony target rule. I used $(kecho) instead of echo to suppress the message 'Image arch/arc/boot/uImage is ready' when the -s option is given. Signed-off-by: Masahiro Yamada Signed-off-by: Vineet Gupta Signed-off-by: Sasha Levin

ARC: [dts] fix the errors detected by dtbs_check

2020-11-05T10:43:19+00:00

[ Upstream commit 05b1be68c4d6d76970025e6139bfd735c2256ee5 ] xxx/arc/boot/dts/axs101.dt.yaml: dw-apb-ictl@e0012000: $nodename:0: \ 'dw-apb-ictl@e0012000' does not match '^interrupt-controller(@[0-9a-f,]+)*$' From schema: xxx/interrupt-controller/snps,dw-apb-ictl.yaml The node name of the interrupt controller must start with "interrupt-controller" instead of "dw-apb-ictl". Signed-off-by: Zhen Lei Signed-off-by: Vineet Gupta Signed-off-by: Sasha Levin

ARC: [plat-hsdk]: Switch ethernet phy-mode to rgmii-id

2020-09-17T11:47:48+00:00

[ Upstream commit 26907eb605fbc3ba9dbf888f21d9d8d04471271d ] HSDK board has Micrel KSZ9031, recent commit bcf3440c6dd ("net: phy: micrel: add phy-mode support for the KSZ9031 PHY") caused a breakdown of Ethernet. Using 'phy-mode = "rgmii"' is not correct because accodring RGMII specification it is necessary to have delay on RX (PHY to MAX) which is not generated in case of "rgmii". Using "rgmii-id" adds necessary delay and solves the issue. Also adding name of PHY placed on HSDK board. Signed-off-by: Evgeniy Didin Cc: Eugeniy Paltsev Cc: Alexey Brodkin Signed-off-by: Vineet Gupta Signed-off-by: Sasha Levin

ARC: HSDK: wireup perf irq

2020-09-17T11:47:45+00:00

[ Upstream commit fe81d927b78c4f0557836661d32e41ebc957b024 ] Newer version of HSDK aka HSDK-4xD (with dual issue HS48x4 CPU) wired up the perf interrupt, so enable that in DT. This is OK for old HSDK where this irq is ignored because pct irq is not wired up in hardware. Signed-off-by: Vineet Gupta Signed-off-by: Sasha Levin

ARC: [plat-axs10x]: Add missing multicast filter number to GMAC node

2020-02-14T21:34:12+00:00

commit 7980dff398f86a618f502378fa27cf7e77449afa upstream. Add a missing property to GMAC node so that multicast filtering works correctly. Fixes: 556cc1c5f528 ("ARC: [axs101] Add support for AXS101 SDP (software development platform)") Acked-by: Alexey Brodkin Signed-off-by: Jose Abreu Signed-off-by: Vineet Gupta Signed-off-by: Greg Kroah-Hartman

ARC: [plat-hsdk]: Enable on-boardi SPI ADC IC

2019-10-22T16:58:29+00:00

HSDK board has adc108s102 SPI ADC IC installed, enable it. Acked-by: Alexey Brodkin Signed-off-by: Eugeniy Paltsev Signed-off-by: Vineet Gupta

ARC: [plat-hsdk]: Enable on-board SPI NOR flash IC

2019-10-22T16:58:29+00:00

HSDK board has sst26wf016b SPI NOR flash IC installed, enable it. Acked-by: Alexey Brodkin Signed-off-by: Eugeniy Paltsev Signed-off-by: Vineet Gupta

ARC: [plat-hsdk]: allow to switch between AXI DMAC port configurations

2019-08-05T13:55:57+00:00

We want to use DW AXI DMAC on HSDK board in our automated verification to test cache & dma kernel code changes. This is perfect candidate as we don't depend on any external peripherals like MMC card / USB storage / etc. To increase test coverage we want to test both options: * DW AXI DMAC is connected through IOC port & dma direct ops used * DW AXI DMAC is connected to DDR port & dma noncoherent ops used Introduce 'arc_hsdk_axi_dmac_coherent' global variable which can be modified by debugger (same way as we patch 'ioc_enable') to switch between these options without recompiling the kernel. Depend on this value we tweak memory bridge configuration and "dma-coherent" DTS property of DW AXI DMAC. Signed-off-by: Eugeniy Paltsev Acked-by: Alexey Brodkin Signed-off-by: Vineet Gupta

ARC: [plat-hsdk]: enable DW SPI controller

2019-07-08T08:24:46+00:00

HSDK SoC has DW SPI controller. Enable it in preparation of enabling on-board SPI peripherals. Acked-by: Alexey Brodkin Signed-off-by: Eugeniy Paltsev Signed-off-by: Vineet Gupta

ARC: [haps] Add Virtio support

2019-07-08T08:24:45+00:00

As a preparation for QEMU usage for ARC let's add basic Virtio-MMIO peripherals support for the platform we're going to use. For now we add 5 Virtio slots in .dts and enable block and network devices via Virtio-MMIO. Note even though typically Virtio register set fits in 0x200 bytes we "allocate" here 0x2000 so that it matches ARC's default 8KiB page size and so remapping of that area is done clearly. We also enable DEVTMPFS automount for more convenient use of external root file-stystem. Before that we used to use built-in Initramfs which didn't automount DEVTMPFS anyways so we didn't need that option, while now it starts making sense. Signed-off-by: Alexey Brodkin Cc: Rob Herring Signed-off-by: Vineet Gupta