From 5882e5acf18d79d586282acfd07a8c88550e2cee Mon Sep 17 00:00:00 2001 From: Chen Jiahao Date: Wed, 26 Jul 2023 17:49:59 +0000 Subject: [PATCH 1/2] riscv: kdump: Implement crashkernel=X,[high,low] On riscv, the current crash kernel allocation logic is trying to allocate within 32bit addressible memory region by default, if failed, try to allocate without 4G restriction. In need of saving DMA zone memory while allocating a relatively large crash kernel region, allocating the reserved memory top down in high memory, without overlapping the DMA zone, is a mature solution. Here introduce the parameter option crashkernel=X,[high,low]. One can reserve the crash kernel from high memory above DMA zone range by explicitly passing "crashkernel=X,high"; or reserve a memory range below 4G with "crashkernel=X,low". Signed-off-by: Chen Jiahao Acked-by: Guo Ren Acked-by: Baoquan He Link: https://lore.kernel.org/r/20230726175000.2536220-2-chenjiahao16@huawei.com Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/setup.c | 5 +++ arch/riscv/mm/init.c | 93 ++++++++++++++++++++++++++++++++++++--- 2 files changed, 91 insertions(+), 7 deletions(-) diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 971fe776e2f8..376f5d49ce85 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -178,6 +178,11 @@ static void __init init_resources(void) if (ret < 0) goto error; } + if (crashk_low_res.start != crashk_low_res.end) { + ret = add_resource(&iomem_resource, &crashk_low_res); + if (ret < 0) + goto error; + } #endif #ifdef CONFIG_CRASH_DUMP diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 70fb31960b63..156e09a1ceee 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -1297,6 +1297,28 @@ static inline void setup_vm_final(void) } #endif /* CONFIG_MMU */ +/* Reserve 128M low memory by default for swiotlb buffer */ +#define DEFAULT_CRASH_KERNEL_LOW_SIZE (128UL << 20) + +static int __init reserve_crashkernel_low(unsigned long long low_size) +{ + unsigned long long low_base; + + low_base = memblock_phys_alloc_range(low_size, PMD_SIZE, 0, dma32_phys_limit); + if (!low_base) { + pr_err("cannot allocate crashkernel low memory (size:0x%llx).\n", low_size); + return -ENOMEM; + } + + pr_info("crashkernel low memory reserved: 0x%016llx - 0x%016llx (%lld MB)\n", + low_base, low_base + low_size, low_size >> 20); + + crashk_low_res.start = low_base; + crashk_low_res.end = low_base + low_size - 1; + + return 0; +} + /* * reserve_crashkernel() - reserves memory for crash kernel * @@ -1308,8 +1330,12 @@ static void __init reserve_crashkernel(void) { unsigned long long crash_base = 0; unsigned long long crash_size = 0; + unsigned long long crash_low_size = 0; unsigned long search_start = memblock_start_of_DRAM(); - unsigned long search_end = memblock_end_of_DRAM(); + unsigned long search_end = (unsigned long)dma32_phys_limit; + char *cmdline = boot_command_line; + bool fixed_base = false; + bool high = false; int ret = 0; @@ -1325,14 +1351,36 @@ static void __init reserve_crashkernel(void) return; } - ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), + ret = parse_crashkernel(cmdline, memblock_phys_mem_size(), &crash_size, &crash_base); - if (ret || !crash_size) + if (ret == -ENOENT) { + /* Fallback to crashkernel=X,[high,low] */ + ret = parse_crashkernel_high(cmdline, 0, &crash_size, &crash_base); + if (ret || !crash_size) + return; + + /* + * crashkernel=Y,low is valid only when crashkernel=X,high + * is passed. + */ + ret = parse_crashkernel_low(cmdline, 0, &crash_low_size, &crash_base); + if (ret == -ENOENT) + crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE; + else if (ret) + return; + + search_start = (unsigned long)dma32_phys_limit; + search_end = memblock_end_of_DRAM(); + high = true; + } else if (ret || !crash_size) { + /* Invalid argument value specified */ return; + } crash_size = PAGE_ALIGN(crash_size); if (crash_base) { + fixed_base = true; search_start = crash_base; search_end = crash_base + crash_size; } @@ -1345,12 +1393,37 @@ static void __init reserve_crashkernel(void) * swiotlb can work on the crash kernel. */ crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE, - search_start, - min(search_end, (unsigned long) SZ_4G)); + search_start, search_end); if (crash_base == 0) { - /* Try again without restricting region to 32bit addressible memory */ + /* + * For crashkernel=size[KMG]@offset[KMG], print out failure + * message if can't reserve the specified region. + */ + if (fixed_base) { + pr_warn("crashkernel: allocating failed with given size@offset\n"); + return; + } + + if (high) { + /* + * For crashkernel=size[KMG],high, if the first attempt was + * for high memory, fall back to low memory. + */ + search_start = memblock_start_of_DRAM(); + search_end = (unsigned long)dma32_phys_limit; + } else { + /* + * For crashkernel=size[KMG], if the first attempt was for + * low memory, fall back to high memory, the minimum required + * low memory will be reserved later. + */ + search_start = (unsigned long)dma32_phys_limit; + search_end = memblock_end_of_DRAM(); + crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE; + } + crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE, - search_start, search_end); + search_start, search_end); if (crash_base == 0) { pr_warn("crashkernel: couldn't allocate %lldKB\n", crash_size >> 10); @@ -1358,6 +1431,12 @@ static void __init reserve_crashkernel(void) } } + if ((crash_base >= dma32_phys_limit) && crash_low_size && + reserve_crashkernel_low(crash_low_size)) { + memblock_phys_free(crash_base, crash_size); + return; + } + pr_info("crashkernel: reserved 0x%016llx - 0x%016llx (%lld MB)\n", crash_base, crash_base + crash_size, crash_size >> 20); From 33f0dd973d4e7d3ed208b5df027490380d5876ab Mon Sep 17 00:00:00 2001 From: Chen Jiahao Date: Wed, 26 Jul 2023 17:50:00 +0000 Subject: [PATCH 2/2] docs: kdump: Update the crashkernel description for riscv Now "crashkernel=" parameter on riscv has been updated to support crashkernel=X,[high,low]. Through which we can reserve memory region above/within 32bit addressible DMA zone. Here update the parameter description accordingly. Signed-off-by: Chen Jiahao Reviewed-by: Guo Ren Reviewed-by: Simon Horman Reviewed-by: Zhen Lei Acked-by: Baoquan He Link: https://lore.kernel.org/r/20230726175000.2536220-3-chenjiahao16@huawei.com Signed-off-by: Palmer Dabbelt --- Documentation/admin-guide/kernel-parameters.txt | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a1457995fd41..bd519749968f 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -862,7 +862,7 @@ memory region [offset, offset + size] for that kernel image. If '@offset' is omitted, then a suitable offset is selected automatically. - [KNL, X86-64, ARM64] Select a region under 4G first, and + [KNL, X86-64, ARM64, RISCV] Select a region under 4G first, and fall back to reserve region above 4G when '@offset' hasn't been specified. See Documentation/admin-guide/kdump/kdump.rst for further details. @@ -875,14 +875,14 @@ Documentation/admin-guide/kdump/kdump.rst for an example. crashkernel=size[KMG],high - [KNL, X86-64, ARM64] range could be above 4G. Allow kernel - to allocate physical memory region from top, so could - be above 4G if system have more than 4G ram installed. - Otherwise memory region will be allocated below 4G, if - available. + [KNL, X86-64, ARM64, RISCV] range could be above 4G. + Allow kernel to allocate physical memory region from top, + so could be above 4G if system have more than 4G ram + installed. Otherwise memory region will be allocated + below 4G, if available. It will be ignored if crashkernel=X is specified. crashkernel=size[KMG],low - [KNL, X86-64, ARM64] range under 4G. When crashkernel=X,high + [KNL, X86-64, ARM64, RISCV] range under 4G. When crashkernel=X,high is passed, kernel could allocate physical memory region above 4G, that cause second kernel crash on system that require some amount of low memory, e.g. swiotlb @@ -893,6 +893,7 @@ size is platform dependent. --> x86: max(swiotlb_size_or_default() + 8MiB, 256MiB) --> arm64: 128MiB + --> riscv: 128MiB This one lets the user specify own low range under 4G for second kernel instead. 0: to disable low allocation.