| Message ID | 20211210065533.2023-8-thunder.leizhen@huawei.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | support reserving crashkernel above 4G on arm64 kdump | expand |
On 12/10/21 12:55 AM, Zhen Lei wrote: > From: Chen Zhou <chenzhou10@huawei.com> > > There are following issues in arm64 kdump: > 1. We use crashkernel=X to reserve crashkernel below 4G, which > will fail when there is no enough low memory. > 2. If reserving crashkernel above 4G, in this case, crash dump > kernel will boot failure because there is no low memory available > for allocation. > > To solve these issues, change the behavior of crashkernel=X and > introduce crashkernel=X,[high,low]. crashkernel=X tries low allocation > in DMA zone, and fall back to high allocation if it fails. > We can also use "crashkernel=X,high" to select a region above DMA zone, > which also tries to allocate at least 256M in DMA zone automatically. > "crashkernel=Y,low" can be used to allocate specified size low memory. > > Another minor change, there may be two regions reserved for crash > dump kernel, in order to distinct from the high region and make no > effect to the use of existing kexec-tools, rename the low region as > "Crash kernel (low)". > > Signed-off-by: Chen Zhou <chenzhou10@huawei.com> > Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com> > Tested-by: John Donnelly <John.p.donnelly@oracle.com> > Tested-by: Dave Kleikamp <dave.kleikamp@oracle.com> Acked-by: John Donnelly <john.p.donnelly@oracle.com> > --- > arch/arm64/Kconfig | 1 + > arch/arm64/include/asm/kexec.h | 4 ++ > arch/arm64/kernel/machine_kexec_file.c | 12 +++++- > arch/arm64/kernel/setup.c | 13 +++++- > arch/arm64/mm/init.c | 59 +++++--------------------- > 5 files changed, 38 insertions(+), 51 deletions(-) > > diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig > index c4207cf9bb17ffb..4b99efa36da3793 100644 > --- a/arch/arm64/Kconfig > +++ b/arch/arm64/Kconfig > @@ -95,6 +95,7 @@ config ARM64 > select ARCH_WANT_FRAME_POINTERS > select ARCH_WANT_HUGE_PMD_SHARE if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36) > select ARCH_WANT_LD_ORPHAN_WARN > + select ARCH_WANT_RESERVE_CRASH_KERNEL if KEXEC_CORE > select ARCH_WANTS_NO_INSTR > select ARCH_HAS_UBSAN_SANITIZE_ALL > select ARM_AMBA > diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h > index 1b9edc69f0244ca..3bde0079925d771 100644 > --- a/arch/arm64/include/asm/kexec.h > +++ b/arch/arm64/include/asm/kexec.h > @@ -96,6 +96,10 @@ static inline void crash_prepare_suspend(void) {} > static inline void crash_post_resume(void) {} > #endif > > +#ifdef CONFIG_KEXEC_CORE > +extern void __init reserve_crashkernel(void); > +#endif > + > #if defined(CONFIG_KEXEC_CORE) > void cpu_soft_restart(unsigned long el2_switch, unsigned long entry, > unsigned long arg0, unsigned long arg1, > diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c > index 63634b4d72c158f..6f3fa059ca4e816 100644 > --- a/arch/arm64/kernel/machine_kexec_file.c > +++ b/arch/arm64/kernel/machine_kexec_file.c > @@ -65,10 +65,18 @@ static int prepare_elf_headers(void **addr, unsigned long *sz) > > /* Exclude crashkernel region */ > ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); > + if (ret) > + goto out; > + > + if (crashk_low_res.end) { > + ret = crash_exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end); > + if (ret) > + goto out; > + } > > - if (!ret) > - ret = crash_prepare_elf64_headers(cmem, true, addr, sz); > + ret = crash_prepare_elf64_headers(cmem, true, addr, sz); > > +out: > kfree(cmem); > return ret; > } > diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c > index be5f85b0a24de69..4bb2e55366be64d 100644 > --- a/arch/arm64/kernel/setup.c > +++ b/arch/arm64/kernel/setup.c > @@ -248,7 +248,18 @@ static void __init request_standard_resources(void) > kernel_data.end <= res->end) > request_resource(res, &kernel_data); > #ifdef CONFIG_KEXEC_CORE > - /* Userspace will find "Crash kernel" region in /proc/iomem. */ > + /* > + * Userspace will find "Crash kernel" or "Crash kernel (low)" > + * region in /proc/iomem. > + * In order to distinct from the high region and make no effect > + * to the use of existing kexec-tools, rename the low region as > + * "Crash kernel (low)". > + */ > + if (crashk_low_res.end && crashk_low_res.start >= res->start && > + crashk_low_res.end <= res->end) { > + crashk_low_res.name = "Crash kernel (low)"; > + request_resource(res, &crashk_low_res); > + } > if (crashk_res.end && crashk_res.start >= res->start && > crashk_res.end <= res->end) > request_resource(res, &crashk_res); > diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c > index be4595dc7459115..85c83e4eff2b6c4 100644 > --- a/arch/arm64/mm/init.c > +++ b/arch/arm64/mm/init.c > @@ -36,6 +36,7 @@ > #include <asm/fixmap.h> > #include <asm/kasan.h> > #include <asm/kernel-pgtable.h> > +#include <asm/kexec.h> > #include <asm/kvm_host.h> > #include <asm/memory.h> > #include <asm/numa.h> > @@ -64,57 +65,11 @@ EXPORT_SYMBOL(memstart_addr); > */ > phys_addr_t arm64_dma_phys_limit __ro_after_init; > > -#ifdef CONFIG_KEXEC_CORE > -/* > - * reserve_crashkernel() - reserves memory for crash kernel > - * > - * This function reserves memory area given in "crashkernel=" kernel command > - * line parameter. The memory reserved is used by dump capture kernel when > - * primary kernel is crashing. > - */ > +#ifndef CONFIG_KEXEC_CORE > static void __init reserve_crashkernel(void) > { > - unsigned long long crash_base, crash_size; > - unsigned long long crash_max = CRASH_ADDR_LOW_MAX; > - int ret; > - > - ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), > - &crash_size, &crash_base); > - /* no crashkernel= or invalid value specified */ > - if (ret || !crash_size) > - return; > - > - crash_size = PAGE_ALIGN(crash_size); > - > - /* User specifies base address explicitly. */ > - if (crash_base) > - crash_max = crash_base + crash_size; > - > - /* Current arm64 boot protocol requires 2MB alignment */ > - crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, > - crash_base, crash_max); > - if (!crash_base) { > - pr_warn("cannot allocate crashkernel (size:0x%llx)\n", > - crash_size); > - return; > - } > - > - pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n", > - crash_base, crash_base + crash_size, crash_size >> 20); > - > - /* > - * The crashkernel memory will be removed from the kernel linear > - * map. Inform kmemleak so that it won't try to access it. > - */ > - kmemleak_ignore_phys(crash_base); > - crashk_res.start = crash_base; > - crashk_res.end = crash_base + crash_size - 1; > } > -#else > -static void __init reserve_crashkernel(void) > -{ > -} > -#endif /* CONFIG_KEXEC_CORE */ > +#endif > > /* > * Return the maximum physical address for a zone accessible by the given bits > @@ -362,6 +317,14 @@ void __init bootmem_init(void) > * reserved, so do it here. > */ > reserve_crashkernel(); > +#ifdef CONFIG_KEXEC_CORE > + /* > + * The low region is intended to be used for crash dump kernel devices, > + * just mark the low region as "nomap" simply. > + */ > + if (crashk_low_res.end) > + memblock_mark_nomap(crashk_low_res.start, resource_size(&crashk_low_res)); > +#endif > > memblock_dump_all(); > }
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index c4207cf9bb17ffb..4b99efa36da3793 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -95,6 +95,7 @@ config ARM64 select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_HUGE_PMD_SHARE if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36) select ARCH_WANT_LD_ORPHAN_WARN + select ARCH_WANT_RESERVE_CRASH_KERNEL if KEXEC_CORE select ARCH_WANTS_NO_INSTR select ARCH_HAS_UBSAN_SANITIZE_ALL select ARM_AMBA diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h index 1b9edc69f0244ca..3bde0079925d771 100644 --- a/arch/arm64/include/asm/kexec.h +++ b/arch/arm64/include/asm/kexec.h @@ -96,6 +96,10 @@ static inline void crash_prepare_suspend(void) {} static inline void crash_post_resume(void) {} #endif +#ifdef CONFIG_KEXEC_CORE +extern void __init reserve_crashkernel(void); +#endif + #if defined(CONFIG_KEXEC_CORE) void cpu_soft_restart(unsigned long el2_switch, unsigned long entry, unsigned long arg0, unsigned long arg1, diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index 63634b4d72c158f..6f3fa059ca4e816 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -65,10 +65,18 @@ static int prepare_elf_headers(void **addr, unsigned long *sz) /* Exclude crashkernel region */ ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); + if (ret) + goto out; + + if (crashk_low_res.end) { + ret = crash_exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end); + if (ret) + goto out; + } - if (!ret) - ret = crash_prepare_elf64_headers(cmem, true, addr, sz); + ret = crash_prepare_elf64_headers(cmem, true, addr, sz); +out: kfree(cmem); return ret; } diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index be5f85b0a24de69..4bb2e55366be64d 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -248,7 +248,18 @@ static void __init request_standard_resources(void) kernel_data.end <= res->end) request_resource(res, &kernel_data); #ifdef CONFIG_KEXEC_CORE - /* Userspace will find "Crash kernel" region in /proc/iomem. */ + /* + * Userspace will find "Crash kernel" or "Crash kernel (low)" + * region in /proc/iomem. + * In order to distinct from the high region and make no effect + * to the use of existing kexec-tools, rename the low region as + * "Crash kernel (low)". + */ + if (crashk_low_res.end && crashk_low_res.start >= res->start && + crashk_low_res.end <= res->end) { + crashk_low_res.name = "Crash kernel (low)"; + request_resource(res, &crashk_low_res); + } if (crashk_res.end && crashk_res.start >= res->start && crashk_res.end <= res->end) request_resource(res, &crashk_res); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index be4595dc7459115..85c83e4eff2b6c4 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -36,6 +36,7 @@ #include <asm/fixmap.h> #include <asm/kasan.h> #include <asm/kernel-pgtable.h> +#include <asm/kexec.h> #include <asm/kvm_host.h> #include <asm/memory.h> #include <asm/numa.h> @@ -64,57 +65,11 @@ EXPORT_SYMBOL(memstart_addr); */ phys_addr_t arm64_dma_phys_limit __ro_after_init; -#ifdef CONFIG_KEXEC_CORE -/* - * reserve_crashkernel() - reserves memory for crash kernel - * - * This function reserves memory area given in "crashkernel=" kernel command - * line parameter. The memory reserved is used by dump capture kernel when - * primary kernel is crashing. - */ +#ifndef CONFIG_KEXEC_CORE static void __init reserve_crashkernel(void) { - unsigned long long crash_base, crash_size; - unsigned long long crash_max = CRASH_ADDR_LOW_MAX; - int ret; - - ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), - &crash_size, &crash_base); - /* no crashkernel= or invalid value specified */ - if (ret || !crash_size) - return; - - crash_size = PAGE_ALIGN(crash_size); - - /* User specifies base address explicitly. */ - if (crash_base) - crash_max = crash_base + crash_size; - - /* Current arm64 boot protocol requires 2MB alignment */ - crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, - crash_base, crash_max); - if (!crash_base) { - pr_warn("cannot allocate crashkernel (size:0x%llx)\n", - crash_size); - return; - } - - pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n", - crash_base, crash_base + crash_size, crash_size >> 20); - - /* - * The crashkernel memory will be removed from the kernel linear - * map. Inform kmemleak so that it won't try to access it. - */ - kmemleak_ignore_phys(crash_base); - crashk_res.start = crash_base; - crashk_res.end = crash_base + crash_size - 1; } -#else -static void __init reserve_crashkernel(void) -{ -} -#endif /* CONFIG_KEXEC_CORE */ +#endif /* * Return the maximum physical address for a zone accessible by the given bits @@ -362,6 +317,14 @@ void __init bootmem_init(void) * reserved, so do it here. */ reserve_crashkernel(); +#ifdef CONFIG_KEXEC_CORE + /* + * The low region is intended to be used for crash dump kernel devices, + * just mark the low region as "nomap" simply. + */ + if (crashk_low_res.end) + memblock_mark_nomap(crashk_low_res.start, resource_size(&crashk_low_res)); +#endif memblock_dump_all(); }