From: ZhuLing <zhuling8@huawei.com> hulk inclusion category: feature bugzilla: 48159 CVE: NA Register pmem in arm64: Use memmap(memmap=nn[KMG]!ss[KMG]) reserve memory and e820(driver/nvdimm/e820.c) function to register persistent memory in arm64. when the kernel restart or update, the data in PMEM will not be lost and can be loaded faster. this is a general features. driver/nvdimm/e820.c: The function of this file is scan "iomem_resource" and take advantage of nvdimm resource discovery mechanism by registering a resource named "Persistent Memory (legacy)", this function doesn't depend on architecture. We will push the feature to linux kernel community and discuss to modify the file name. because people have a mistaken notion that the e820.c is depend on x86. If you want use this features, you need do as follows: 1.Reserve memory: add memmap to reserve memory in grub.cfg memmap=nn[KMG]!ss[KMG] exp:memmap=100K!0x1a0000000. 2.Insmod nd_e820.ko: modprobe nd_e820. 3.Check pmem device in /dev exp: /dev/pmem0 Signed-off-by: ZhuLing <zhuling8@huawei.com> --- arch/arm64/Kconfig | 21 +++++++++ arch/arm64/kernel/Makefile | 1 + arch/arm64/kernel/pmem.c | 35 ++++++++++++++ arch/arm64/kernel/setup.c | 10 ++++ arch/arm64/mm/init.c | 97 ++++++++++++++++++++++++++++++++++++++ drivers/nvdimm/Kconfig | 5 ++ drivers/nvdimm/Makefile | 2 +- 7 files changed, 170 insertions(+), 1 deletion(-) create mode 100644 arch/arm64/kernel/pmem.c diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index c451137ab..326f26d40 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -360,6 +360,27 @@ config ARM64_CPU_PARK config ARCH_HAS_CPU_RELAX def_bool y +config ARM64_PMEM_RESERVE + bool "Reserve memory for persistent storage" + default n + help + Use memmap=nn[KMG]!ss[KMG](memmap=100K!0x1a0000000) reserve + memory for persistent storage. + + Say y here to enable this feature. + +config ARM64_PMEM_LEGACY_DEVICE + bool "Create persistent storage" + depends on BLK_DEV + depends on LIBNVDIMM + select ARM64_PMEM_RESERVE + help + Use reserved memory for persistent storage when the kernel + restart or update. the data in PMEM will not be lost and + can be loaded faster. + + Say y if unsure. + source "arch/arm64/Kconfig.platforms" menu "Kernel Features" diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 967cb3c6d..be996f3c1 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -67,6 +67,7 @@ obj-$(CONFIG_ARM64_PTR_AUTH) += pointer_auth.o obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o obj-$(CONFIG_ARM64_MTE) += mte.o obj-$(CONFIG_MPAM) += mpam/ +obj-$(CONFIG_ARM64_PMEM_LEGACY_DEVICE) += pmem.o obj-y += vdso/ probes/ obj-$(CONFIG_COMPAT_VDSO) += vdso32/ diff --git a/arch/arm64/kernel/pmem.c b/arch/arm64/kernel/pmem.c new file mode 100644 index 000000000..16eaf706f --- /dev/null +++ b/arch/arm64/kernel/pmem.c @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright(c) 2021 Huawei Technologies Co., Ltd + * + * Derived from x86 and arm64 implement PMEM. + */ +#include <linux/platform_device.h> +#include <linux/init.h> +#include <linux/ioport.h> +#include <linux/module.h> + +static int found(struct resource *res, void *data) +{ + return 1; +} + +static int __init register_e820_pmem(void) +{ + struct platform_device *pdev; + int rc; + + rc = walk_iomem_res_desc(IORES_DESC_PERSISTENT_MEMORY_LEGACY, + IORESOURCE_MEM, 0, -1, NULL, found); + if (rc <= 0) + return 0; + + /* + * See drivers/nvdimm/e820.c for the implementation, this is + * simply here to trigger the module to load on demand. + */ + pdev = platform_device_alloc("e820_pmem", -1); + + return platform_device_add(pdev); +} +device_initcall(register_e820_pmem); diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 5e282d31a..84c71c88d 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -57,6 +57,10 @@ static int num_standard_resources; static struct resource *standard_resources; +#ifdef CONFIG_ARM64_PMEM_RESERVE +extern struct resource pmem_res; +#endif + phys_addr_t __fdt_pointer __initdata; /* @@ -270,6 +274,12 @@ static void __init request_standard_resources(void) request_resource(res, &pin_memory_resource); #endif } + +#ifdef CONFIG_ARM64_PMEM_RESERVE + if (pmem_res.end && pmem_res.start) + request_resource(&iomem_resource, &pmem_res); +#endif + } static int __init reserve_memblock_reserved_regions(void) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index b3437440d..f22faea1a 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -66,6 +66,18 @@ EXPORT_SYMBOL(memstart_addr); phys_addr_t arm64_dma_phys_limit __ro_after_init; phys_addr_t arm64_dma32_phys_limit __ro_after_init; +static unsigned long long pmem_size, pmem_start; + +#ifdef CONFIG_ARM64_PMEM_RESERVE +struct resource pmem_res = { + .name = "Persistent Memory (legacy)", + .start = 0, + .end = 0, + .flags = IORESOURCE_MEM, + .desc = IORES_DESC_PERSISTENT_MEMORY_LEGACY +}; +#endif + #ifndef CONFIG_KEXEC_CORE static void __init reserve_crashkernel(void) { @@ -378,6 +390,87 @@ static int __init reserve_park_mem(void) } #endif +static int __init is_mem_valid(unsigned long long mem_size, unsigned long long mem_start) +{ + if (!memblock_is_region_memory(mem_start, mem_size)) { + pr_warn("cannot reserve mem: region is not memory!\n"); + return -EINVAL; + } + + if (memblock_is_region_reserved(mem_start, mem_size)) { + pr_warn("cannot reserve mem: region overlaps reserved memory!\n"); + return -EINVAL; + } + + if (!IS_ALIGNED(mem_start, SZ_2M)) { + pr_warn("cannot reserve mem: base address is not 2MB aligned!\n"); + return -EINVAL; + } + + return 0; +} + +static int __init parse_memmap_one(char *p) +{ + char *oldp; + phys_addr_t start_at, mem_size; + + if (!p) + return -EINVAL; + + oldp = p; + mem_size = memparse(p, &p); + if (p == oldp) + return -EINVAL; + + if (!mem_size) + return -EINVAL; + + mem_size = PAGE_ALIGN(mem_size); + + if (*p == '!') { + start_at = memparse(p+1, &p); + + if (is_mem_valid(mem_size, start_at) != 0) + return -EINVAL; + + pr_info("pmem reserved: 0x%016llx - 0x%016llx (%lld MB)\n", + start_at, start_at + mem_size, mem_size >> 20); + pmem_start = start_at; + pmem_size = mem_size; + } else + pr_info("Unrecognized memmap option, please check the parameter.\n"); + + return *p == '\0' ? 0 : -EINVAL; +} + +static int __init parse_memmap_opt(char *str) +{ + while (str) { + char *k = strchr(str, ','); + + if (k) + *k++ = 0; + + parse_memmap_one(str); + str = k; + } + + return 0; +} +early_param("memmap", parse_memmap_opt); + +#ifdef CONFIG_ARM64_PMEM_RESERVE +static void __init reserve_pmem(void) +{ + memblock_remove(pmem_start, pmem_size); + pr_info("pmem reserved: 0x%016llx - 0x%016llx (%lld MB)\n", + pmem_start, pmem_start + pmem_size, pmem_size >> 20); + pmem_res.start = pmem_start; + pmem_res.end = pmem_start + pmem_size - 1; +} +#endif + void __init arm64_memblock_init(void) { const s64 linear_region_size = BIT(vabits_actual - 1); @@ -511,6 +604,10 @@ void __init arm64_memblock_init(void) reserve_elfcorehdr(); +#ifdef CONFIG_ARM64_PMEM_RESERVE + reserve_pmem(); +#endif + high_memory = __va(memblock_end_of_DRAM() - 1) + 1; dma_contiguous_reserve(arm64_dma32_phys_limit); diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig index b7d1eb38b..ce4de7526 100644 --- a/drivers/nvdimm/Kconfig +++ b/drivers/nvdimm/Kconfig @@ -132,3 +132,8 @@ config NVDIMM_TEST_BUILD infrastructure. endif + +config PMEM_LEGACY + tristate "Pmem_legacy" + select X86_PMEM_LEGACY if X86 + select ARM64_PMEM_LEGACY_DEVICE if ARM64 diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile index 29203f3d3..6f8dc9242 100644 --- a/drivers/nvdimm/Makefile +++ b/drivers/nvdimm/Makefile @@ -3,7 +3,7 @@ obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o obj-$(CONFIG_ND_BTT) += nd_btt.o obj-$(CONFIG_ND_BLK) += nd_blk.o -obj-$(CONFIG_X86_PMEM_LEGACY) += nd_e820.o +obj-$(CONFIG_PMEM_LEGACY) += nd_e820.o obj-$(CONFIG_OF_PMEM) += of_pmem.o obj-$(CONFIG_VIRTIO_PMEM) += virtio_pmem.o nd_virtio.o -- 2.19.1