wireguard-linux/arch/arm64/mm/init.c, branch jd/unified-crypt-queue

mm: hugetlb: optionally allocate gigantic hugepages using cma

2020-04-10T22:36:21Z

Commit 944d9fec8d7a ("hugetlb: add support for gigantic page allocation at runtime") has added the run-time allocation of gigantic pages. However it actually works only at early stages of the system loading, when the majority of memory is free. After some time the memory gets fragmented by non-movable pages, so the chances to find a contiguous 1GB block are getting close to zero. Even dropping caches manually doesn't help a lot. At large scale rebooting servers in order to allocate gigantic hugepages is quite expensive and complex. At the same time keeping some constant percentage of memory in reserved hugepages even if the workload isn't using it is a big waste: not all workloads can benefit from using 1 GB pages. The following solution can solve the problem: 1) On boot time a dedicated cma area* is reserved. The size is passed as a kernel argument. 2) Run-time allocations of gigantic hugepages are performed using the cma allocator and the dedicated cma area In this case gigantic hugepages can be allocated successfully with a high probability, however the memory isn't completely wasted if nobody is using 1GB hugepages: it can be used for pagecache, anon memory, THPs, etc. * On a multi-node machine a per-node cma area is allocated on each node. Following gigantic hugetlb allocation are using the first available numa node if the mask isn't specified by a user. Usage: 1) configure the kernel to allocate a cma area for hugetlb allocations: pass hugetlb_cma=10G as a kernel argument 2) allocate hugetlb pages as usual, e.g. echo 10 > /sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages If the option isn't enabled or the allocation of the cma area failed, the current behavior of the system is preserved. x86 and arm-64 are covered by this patch, other architectures can be trivially added later. The patch contains clean-ups and fixes proposed and implemented by Aslan Bakirov and Randy Dunlap. It also contains ideas and suggestions proposed by Rik van Riel, Michal Hocko and Mike Kravetz. Thanks! Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Tested-by: Andreas Schaufler Acked-by: Mike Kravetz Acked-by: Michal Hocko Cc: Aslan Bakirov Cc: Randy Dunlap Cc: Rik van Riel Cc: Joonsoo Kim Link: http://lkml.kernel.org/r/20200407163840.92263-3-guro@fb.com Signed-off-by: Linus Torvalds

arm64: mm: Fix initialisation of DMA zones on non-NUMA systems

2019-12-04T11:25:20Z

John reports that the recently merged commit 1a8e1cef7603 ("arm64: use both ZONE_DMA and ZONE_DMA32") breaks the boot on his DB845C board: | Booting Linux on physical CPU 0x0000000000 [0x517f803c] | Linux version 5.4.0-mainline-10675-g957a03b9e38f | Machine model: Thundercomm Dragonboard 845c | [...] | Built 1 zonelists, mobility grouping on. Total pages: -188245 | Kernel command line: earlycon | firmware_class.path=/vendor/firmware/ androidboot.hardware=db845c | init=/init androidboot.boot_devices=soc/1d84000.ufshc | printk.devkmsg=on buildvariant=userdebug root=/dev/sda2 | androidboot.bootdevice=1d84000.ufshc androidboot.serialno=c4e1189c | androidboot.baseband=sda | msm_drm.dsi_display0=dsi_lt9611_1080_video_display: | androidboot.slot_suffix=_a skip_initramfs rootwait ro init=/init | | This is because, when CONFIG_NUMA=n, zone_sizes_init() fails to handle memblocks that fall entirely within the ZONE_DMA region and erroneously ends up trying to add a negatively-sized region into the following ZONE_DMA32, which is later interpreted as a large unsigned region by the core MM code. Rework the non-NUMA implementation of zone_sizes_init() so that the start address of the memblock being processed is adjusted according to the end of the previous zone, which is then range-checked before updating the hole information of subsequent zones. Cc: Nicolas Saenz Julienne Cc: Christoph Hellwig Cc: Bjorn Andersson Link: https://lore.kernel.org/lkml/CALAqxLVVcsmFrDKLRGRq7GewcW405yTOxG=KR3csVzQ6bXutkA@mail.gmail.com Fixes: 1a8e1cef7603 ("arm64: use both ZONE_DMA and ZONE_DMA32") Reported-by: John Stultz Tested-by: John Stultz Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas

Merge branches 'for-next/elf-hwcap-docs', 'for-next/smccc-conduit-cleanup', 'for-next/zone-dma', 'for-next/relax-icc_pmr_el1-sync', 'for-next/double-page-fault', 'for-next/misc', 'for-next/kselftest-arm64-signal' and 'for-next/kaslr-diagnostics' into for-next/core

2019-11-08T17:46:11Z

* for-next/elf-hwcap-docs: : Update the arm64 ELF HWCAP documentation docs/arm64: cpu-feature-registers: Rewrite bitfields that don't follow [e, s] docs/arm64: cpu-feature-registers: Documents missing visible fields docs/arm64: elf_hwcaps: Document HWCAP_SB docs/arm64: elf_hwcaps: sort the HWCAP{, 2} documentation by ascending value * for-next/smccc-conduit-cleanup: : SMC calling convention conduit clean-up firmware: arm_sdei: use common SMCCC_CONDUIT_* firmware/psci: use common SMCCC_CONDUIT_* arm: spectre-v2: use arm_smccc_1_1_get_conduit() arm64: errata: use arm_smccc_1_1_get_conduit() arm/arm64: smccc/psci: add arm_smccc_1_1_get_conduit() * for-next/zone-dma: : Reintroduction of ZONE_DMA for Raspberry Pi 4 support arm64: mm: reserve CMA and crashkernel in ZONE_DMA32 dma/direct: turn ARCH_ZONE_DMA_BITS into a variable arm64: Make arm64_dma32_phys_limit static arm64: mm: Fix unused variable warning in zone_sizes_init mm: refresh ZONE_DMA and ZONE_DMA32 comments in 'enum zone_type' arm64: use both ZONE_DMA and ZONE_DMA32 arm64: rename variables used to calculate ZONE_DMA32's size arm64: mm: use arm64_dma_phys_limit instead of calling max_zone_dma_phys() * for-next/relax-icc_pmr_el1-sync: : Relax ICC_PMR_EL1 (GICv3) accesses when ICC_CTLR_EL1.PMHE is clear arm64: Document ICC_CTLR_EL3.PMHE setting requirements arm64: Relax ICC_PMR_EL1 accesses when ICC_CTLR_EL1.PMHE is clear * for-next/double-page-fault: : Avoid a double page fault in __copy_from_user_inatomic() if hw does not support auto Access Flag mm: fix double page fault on arm64 if PTE_AF is cleared x86/mm: implement arch_faults_on_old_pte() stub on x86 arm64: mm: implement arch_faults_on_old_pte() on arm64 arm64: cpufeature: introduce helper cpu_has_hw_af() * for-next/misc: : Various fixes and clean-ups arm64: kpti: Add NVIDIA's Carmel core to the KPTI whitelist arm64: mm: Remove MAX_USER_VA_BITS definition arm64: mm: simplify the page end calculation in __create_pgd_mapping() arm64: print additional fault message when executing non-exec memory arm64: psci: Reduce the waiting time for cpu_psci_cpu_kill() arm64: pgtable: Correct typo in comment arm64: docs: cpu-feature-registers: Document ID_AA64PFR1_EL1 arm64: cpufeature: Fix typos in comment arm64/mm: Poison initmem while freeing with free_reserved_area() arm64: use generic free_initrd_mem() arm64: simplify syscall wrapper ifdeffery * for-next/kselftest-arm64-signal: : arm64-specific kselftest support with signal-related test-cases kselftest: arm64: fake_sigreturn_misaligned_sp kselftest: arm64: fake_sigreturn_bad_size kselftest: arm64: fake_sigreturn_duplicated_fpsimd kselftest: arm64: fake_sigreturn_missing_fpsimd kselftest: arm64: fake_sigreturn_bad_size_for_magic0 kselftest: arm64: fake_sigreturn_bad_magic kselftest: arm64: add helper get_current_context kselftest: arm64: extend test_init functionalities kselftest: arm64: mangle_pstate_invalid_mode_el[123][ht] kselftest: arm64: mangle_pstate_invalid_daif_bits kselftest: arm64: mangle_pstate_invalid_compat_toggle and common utils kselftest: arm64: extend toplevel skeleton Makefile * for-next/kaslr-diagnostics: : Provide diagnostics on boot for KASLR arm64: kaslr: Check command line before looking for a seed arm64: kaslr: Announce KASLR status on boot

arm64: mm: reserve CMA and crashkernel in ZONE_DMA32

2019-11-07T11:22:20Z

With the introduction of ZONE_DMA in arm64 we moved the default CMA and crashkernel reservation into that area. This caused a regression on big machines that need big CMA and crashkernel reservations. Note that ZONE_DMA is only 1GB big. Restore the previous behavior as the wide majority of devices are OK with reserving these in ZONE_DMA32. The ones that need them in ZONE_DMA will configure it explicitly. Fixes: 1a8e1cef7603 ("arm64: use both ZONE_DMA and ZONE_DMA32") Reported-by: Qian Cai Signed-off-by: Nicolas Saenz Julienne Signed-off-by: Catalin Marinas

dma/direct: turn ARCH_ZONE_DMA_BITS into a variable

2019-11-01T09:41:18Z

Some architectures, notably ARM, are interested in tweaking this depending on their runtime DMA addressing limitations. Acked-by: Christoph Hellwig Signed-off-by: Nicolas Saenz Julienne Signed-off-by: Catalin Marinas

arm64: Make arm64_dma32_phys_limit static

2019-10-28T16:46:43Z

This variable is only used in the arch/arm64/mm/init.c file for ZONE_DMA32 initialisation, no need to expose it. Reported-by: Will Deacon Signed-off-by: Catalin Marinas

arm64: mm: Fix unused variable warning in zone_sizes_init

2019-10-16T15:06:27Z

When building arm64 allnoconfig, CONFIG_ZONE_DMA and CONFIG_ZONE_DMA32 get disabled so there is a warning about max_dma being unused. ../arch/arm64/mm/init.c:215:16: warning: unused variable 'max_dma' [-Wunused-variable] unsigned long max_dma = min; ^ 1 warning generated. Add __maybe_unused to make this clear to the compiler. Fixes: 1a8e1cef7603 ("arm64: use both ZONE_DMA and ZONE_DMA32") Reviewed-by: Nicolas Saenz Julienne Signed-off-by: Nathan Chancellor Signed-off-by: Catalin Marinas

arm64/mm: Poison initmem while freeing with free_reserved_area()

2019-10-16T12:56:30Z

Platform implementation for free_initmem() should poison the memory while freeing it up. Hence pass across POISON_FREE_INITMEM while calling into free_reserved_area(). The same is being followed in the generic fallback for free_initmem() and some other platforms overriding it. Cc: Mark Rutland Cc: linux-kernel@vger.kernel.org Reviewed-by: Steven Price Acked-by: Will Deacon Signed-off-by: Anshuman Khandual Signed-off-by: Catalin Marinas

arm64: use generic free_initrd_mem()

2019-10-16T12:55:25Z

arm64 calls memblock_free() for the initrd area in its implementation of free_initrd_mem(), but this call has no actual effect that late in the boot process. By the time initrd is freed, all the reserved memory is managed by the page allocator and the memblock.reserved is unused, so the only purpose of the memblock_free() call is to keep track of initrd memory for debugging and accounting. Without the memblock_free() call the only difference between arm64 and the generic versions of free_initrd_mem() is the memory poisoning. Move memblock_free() call to the generic code, enable it there for the architectures that define ARCH_KEEP_MEMBLOCK and use the generic implementation of free_initrd_mem() on arm64. Tested-by: Anshuman Khandual #arm64 Reviewed-by: Anshuman Khandual Acked-by: Will Deacon Signed-off-by: Mike Rapoport Signed-off-by: Catalin Marinas

arm64: use both ZONE_DMA and ZONE_DMA32

2019-10-14T09:56:28Z

So far all arm64 devices have supported 32 bit DMA masks for their peripherals. This is not true anymore for the Raspberry Pi 4 as most of it's peripherals can only address the first GB of memory on a total of up to 4 GB. This goes against ZONE_DMA32's intent, as it's expected for ZONE_DMA32 to be addressable with a 32 bit mask. So it was decided to re-introduce ZONE_DMA in arm64. ZONE_DMA will contain the lower 1G of memory, which is currently the memory area addressable by any peripheral on an arm64 device. ZONE_DMA32 will contain the rest of the 32 bit addressable memory. Signed-off-by: Nicolas Saenz Julienne Reviewed-by: Catalin Marinas Signed-off-by: Catalin Marinas