| Message ID | 8b02b030a4a081816f35e49b210b41d9f6e2d961.1448403503.git.geoff@infradead.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On Tue, Nov 24, 2015 at 10:25:34PM +0000, Geoff Levand wrote: > From: AKASHI Takahiro <takahiro.akashi@linaro.org> > > On crash dump kernel, all the information about primary kernel's core > image is available in elf core header specified by "elfcorehdr=" boot > parameter. reserve_elfcorehdr() will set aside the region to avoid any > corruption by crash dump kernel. > > Crash dump kernel will access the system memory of primary kernel via > copy_oldmem_page(), which reads one page by ioremap'ing it since it does > not reside in linear mapping on crash dump kernel. > Please note that we should add "mem=X[MG]" boot parameter to limit the > memory size and avoid the following assertion at ioremap(): > if (WARN_ON(pfn_valid(__phys_to_pfn(phys_addr)))) > return NULL; > when accessing any pages beyond the usable memories of crash dump kernel. > > We also need our own elfcorehdr_read() here since the weak definition of > elfcorehdr_read() utilizes copy_oldmem_page() and will hit the assertion > above on arm64. > > Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org> > --- > arch/arm64/Kconfig | 12 +++++++ > arch/arm64/kernel/Makefile | 1 + > arch/arm64/kernel/crash_dump.c | 71 ++++++++++++++++++++++++++++++++++++++++++ > arch/arm64/mm/init.c | 29 +++++++++++++++++ > 4 files changed, 113 insertions(+) > create mode 100644 arch/arm64/kernel/crash_dump.c > > diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig > index c23fd77..4bac7dc 100644 > --- a/arch/arm64/Kconfig > +++ b/arch/arm64/Kconfig > @@ -545,6 +545,18 @@ config KEXEC > but it is independent of the system firmware. And like a reboot > you can start any kernel with it, not just Linux. > > +config CRASH_DUMP > + bool "Build kdump crash kernel" > + help > + Generate crash dump after being started by kexec. This should > + be normally only set in special crash dump kernels which are > + loaded in the main kernel with kexec-tools into a specially > + reserved region and then later executed after a crash by > + kdump/kexec. The crash dump kernel must be compiled to a > + memory address not used by the main kernel. What does this even mean? How do I "compile to a memory address not used by the main kernel"? > diff --git a/arch/arm64/kernel/crash_dump.c b/arch/arm64/kernel/crash_dump.c > new file mode 100644 > index 0000000..3d86c0a > --- /dev/null > +++ b/arch/arm64/kernel/crash_dump.c > @@ -0,0 +1,71 @@ > +/* > + * Routines for doing kexec-based kdump > + * > + * Copyright (C) 2014 Linaro Limited > + * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> > + * > + * This program is free software; you can redistribute it and/or modify > + * it under the terms of the GNU General Public License version 2 as > + * published by the Free Software Foundation. > + */ > + > +#include <linux/crash_dump.h> > +#include <linux/errno.h> > +#include <linux/io.h> > +#include <linux/memblock.h> > +#include <linux/uaccess.h> > +#include <asm/memory.h> > + > +/** > + * copy_oldmem_page() - copy one page from old kernel memory > + * @pfn: page frame number to be copied > + * @buf: buffer where the copied page is placed > + * @csize: number of bytes to copy > + * @offset: offset in bytes into the page > + * @userbuf: if set, @buf is in a user address space > + * > + * This function copies one page from old kernel memory into buffer pointed by > + * @buf. If @buf is in userspace, set @userbuf to %1. Returns number of bytes > + * copied or negative error in case of failure. > + */ > +ssize_t copy_oldmem_page(unsigned long pfn, char *buf, > + size_t csize, unsigned long offset, > + int userbuf) > +{ > + void *vaddr; > + > + if (!csize) > + return 0; > + > + vaddr = ioremap_cache(pfn << PAGE_SHIFT, PAGE_SIZE); pfn_to_page > + if (!vaddr) > + return -ENOMEM; > + > + if (userbuf) { > + if (copy_to_user(buf, vaddr + offset, csize)) { > + iounmap(vaddr); > + return -EFAULT; > + } > + } else { > + memcpy(buf, vaddr + offset, csize); > + } > + > + iounmap(vaddr); > + > + return csize; > +} > + > +/** > + * elfcorehdr_read - read from ELF core header > + * @buf: buffer where the data is placed > + * @csize: number of bytes to read > + * @ppos: address in the memory > + * > + * This function reads @count bytes from elf core header which exists > + * on crash dump kernel's memory. > + */ > +ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos) > +{ > + memcpy(buf, phys_to_virt((phys_addr_t)*ppos), count); > + return count; > +} I know you say that we have to override this function so that we don't hit the pfn_valid warning in ioremap, but what guarantees that the ELF header of the crashed kernel is actually mapped in our linear mapping? > diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c > index 24f0a1c..52a1469 100644 > --- a/arch/arm64/mm/init.c > +++ b/arch/arm64/mm/init.c > @@ -35,6 +35,7 @@ > #include <linux/efi.h> > #include <linux/swiotlb.h> > #include <linux/kexec.h> > +#include <linux/crash_dump.h> > > #include <asm/fixmap.h> > #include <asm/memory.h> > @@ -116,6 +117,31 @@ static void __init reserve_crashkernel(void) > } > #endif /* CONFIG_KEXEC */ > > +#ifdef CONFIG_CRASH_DUMP > +/* > + * reserve_elfcorehdr() - reserves memory for elf core header > + * > + * This function reserves elf core header given in "elfcorehdr=" kernel > + * command line parameter. This region contains all the information about > + * primary kernel's core image and is used by a dump capture kernel to > + * access the system memory on primary kernel. > + */ > +static void __init reserve_elfcorehdr(void) > +{ > + if (!elfcorehdr_size) > + return; > + > + if (memblock_is_region_reserved(elfcorehdr_addr, elfcorehdr_size)) { > + pr_warn("elfcorehdr is overlapped\n"); > + return; > + } > + > + memblock_reserve(elfcorehdr_addr, elfcorehdr_size); > + > + pr_info("Reserving %lldKB of memory at %lldMB for elfcorehdr\n", > + elfcorehdr_size >> 10, elfcorehdr_addr >> 20); I'd have thought it would be more useful to print the address as an address rather than a size. > +} Similar #else trick here. Will
On 12/16/2015 02:45 AM, Will Deacon wrote: > On Tue, Nov 24, 2015 at 10:25:34PM +0000, Geoff Levand wrote: >> From: AKASHI Takahiro <takahiro.akashi@linaro.org> >> >> On crash dump kernel, all the information about primary kernel's core >> image is available in elf core header specified by "elfcorehdr=" boot >> parameter. reserve_elfcorehdr() will set aside the region to avoid any >> corruption by crash dump kernel. >> >> Crash dump kernel will access the system memory of primary kernel via >> copy_oldmem_page(), which reads one page by ioremap'ing it since it does >> not reside in linear mapping on crash dump kernel. >> Please note that we should add "mem=X[MG]" boot parameter to limit the >> memory size and avoid the following assertion at ioremap(): >> if (WARN_ON(pfn_valid(__phys_to_pfn(phys_addr)))) >> return NULL; >> when accessing any pages beyond the usable memories of crash dump kernel. >> >> We also need our own elfcorehdr_read() here since the weak definition of >> elfcorehdr_read() utilizes copy_oldmem_page() and will hit the assertion >> above on arm64. >> >> Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org> >> --- >> arch/arm64/Kconfig | 12 +++++++ >> arch/arm64/kernel/Makefile | 1 + >> arch/arm64/kernel/crash_dump.c | 71 ++++++++++++++++++++++++++++++++++++++++++ >> arch/arm64/mm/init.c | 29 +++++++++++++++++ >> 4 files changed, 113 insertions(+) >> create mode 100644 arch/arm64/kernel/crash_dump.c >> >> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig >> index c23fd77..4bac7dc 100644 >> --- a/arch/arm64/Kconfig >> +++ b/arch/arm64/Kconfig >> @@ -545,6 +545,18 @@ config KEXEC >> but it is independent of the system firmware. And like a reboot >> you can start any kernel with it, not just Linux. >> >> +config CRASH_DUMP >> + bool "Build kdump crash kernel" >> + help >> + Generate crash dump after being started by kexec. This should >> + be normally only set in special crash dump kernels which are >> + loaded in the main kernel with kexec-tools into a specially >> + reserved region and then later executed after a crash by >> + kdump/kexec. The crash dump kernel must be compiled to a >> + memory address not used by the main kernel. > > What does this even mean? How do I "compile to a memory address not used > by the main kernel"? Well, it's just a copy from arm, but right, it's ambiguous. I will remove that text. >> diff --git a/arch/arm64/kernel/crash_dump.c b/arch/arm64/kernel/crash_dump.c >> new file mode 100644 >> index 0000000..3d86c0a >> --- /dev/null >> +++ b/arch/arm64/kernel/crash_dump.c >> @@ -0,0 +1,71 @@ >> +/* >> + * Routines for doing kexec-based kdump >> + * >> + * Copyright (C) 2014 Linaro Limited >> + * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> >> + * >> + * This program is free software; you can redistribute it and/or modify >> + * it under the terms of the GNU General Public License version 2 as >> + * published by the Free Software Foundation. >> + */ >> + >> +#include <linux/crash_dump.h> >> +#include <linux/errno.h> >> +#include <linux/io.h> >> +#include <linux/memblock.h> >> +#include <linux/uaccess.h> >> +#include <asm/memory.h> >> + >> +/** >> + * copy_oldmem_page() - copy one page from old kernel memory >> + * @pfn: page frame number to be copied >> + * @buf: buffer where the copied page is placed >> + * @csize: number of bytes to copy >> + * @offset: offset in bytes into the page >> + * @userbuf: if set, @buf is in a user address space >> + * >> + * This function copies one page from old kernel memory into buffer pointed by >> + * @buf. If @buf is in userspace, set @userbuf to %1. Returns number of bytes >> + * copied or negative error in case of failure. >> + */ >> +ssize_t copy_oldmem_page(unsigned long pfn, char *buf, >> + size_t csize, unsigned long offset, >> + int userbuf) >> +{ >> + void *vaddr; >> + >> + if (!csize) >> + return 0; >> + >> + vaddr = ioremap_cache(pfn << PAGE_SHIFT, PAGE_SIZE); > > pfn_to_page Maybe __pfn_to_phsy()? >> + if (!vaddr) >> + return -ENOMEM; >> + >> + if (userbuf) { >> + if (copy_to_user(buf, vaddr + offset, csize)) { >> + iounmap(vaddr); >> + return -EFAULT; >> + } >> + } else { >> + memcpy(buf, vaddr + offset, csize); >> + } >> + >> + iounmap(vaddr); >> + >> + return csize; >> +} >> + >> +/** >> + * elfcorehdr_read - read from ELF core header >> + * @buf: buffer where the data is placed >> + * @csize: number of bytes to read >> + * @ppos: address in the memory >> + * >> + * This function reads @count bytes from elf core header which exists >> + * on crash dump kernel's memory. >> + */ >> +ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos) >> +{ >> + memcpy(buf, phys_to_virt((phys_addr_t)*ppos), count); >> + return count; >> +} > > I know you say that we have to override this function so that we don't > hit the pfn_valid warning in ioremap, but what guarantees that the ELF > header of the crashed kernel is actually mapped in our linear mapping? Well, in fact, it depends on kexec-tools. In the current implementation for arm64, the elf core header is allocated within the usable memory of crash dump kernel. Should we add some check here? >> diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c >> index 24f0a1c..52a1469 100644 >> --- a/arch/arm64/mm/init.c >> +++ b/arch/arm64/mm/init.c >> @@ -35,6 +35,7 @@ >> #include <linux/efi.h> >> #include <linux/swiotlb.h> >> #include <linux/kexec.h> >> +#include <linux/crash_dump.h> >> >> #include <asm/fixmap.h> >> #include <asm/memory.h> >> @@ -116,6 +117,31 @@ static void __init reserve_crashkernel(void) >> } >> #endif /* CONFIG_KEXEC */ >> >> +#ifdef CONFIG_CRASH_DUMP >> +/* >> + * reserve_elfcorehdr() - reserves memory for elf core header >> + * >> + * This function reserves elf core header given in "elfcorehdr=" kernel >> + * command line parameter. This region contains all the information about >> + * primary kernel's core image and is used by a dump capture kernel to >> + * access the system memory on primary kernel. >> + */ >> +static void __init reserve_elfcorehdr(void) >> +{ >> + if (!elfcorehdr_size) >> + return; >> + >> + if (memblock_is_region_reserved(elfcorehdr_addr, elfcorehdr_size)) { >> + pr_warn("elfcorehdr is overlapped\n"); >> + return; >> + } >> + >> + memblock_reserve(elfcorehdr_addr, elfcorehdr_size); >> + >> + pr_info("Reserving %lldKB of memory at %lldMB for elfcorehdr\n", >> + elfcorehdr_size >> 10, elfcorehdr_addr >> 20); > > I'd have thought it would be more useful to print the address as an > address rather than a size. Yeah, I totally agree, but all the other archs, including x86 and arm, print the address in "%lldMB" format. If you like, I can fix it. >> +} > > Similar #else trick here. Sure. Thanks, -Takahiro AKASHI > Will >
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index c23fd77..4bac7dc 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -545,6 +545,18 @@ config KEXEC but it is independent of the system firmware. And like a reboot you can start any kernel with it, not just Linux. +config CRASH_DUMP + bool "Build kdump crash kernel" + help + Generate crash dump after being started by kexec. This should + be normally only set in special crash dump kernels which are + loaded in the main kernel with kexec-tools into a specially + reserved region and then later executed after a crash by + kdump/kexec. The crash dump kernel must be compiled to a + memory address not used by the main kernel. + + For more details see Documentation/kdump/kdump.txt + config XEN_DOM0 def_bool y depends on XEN diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index f68420d..a08b054 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -43,6 +43,7 @@ arm64-obj-$(CONFIG_ARMV8_DEPRECATED) += armv8_deprecated.o arm64-obj-$(CONFIG_ACPI) += acpi.o arm64-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o \ cpu-reset.o +arm64-obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-y += $(arm64-obj-y) vdso/ obj-m += $(arm64-obj-m) diff --git a/arch/arm64/kernel/crash_dump.c b/arch/arm64/kernel/crash_dump.c new file mode 100644 index 0000000..3d86c0a --- /dev/null +++ b/arch/arm64/kernel/crash_dump.c @@ -0,0 +1,71 @@ +/* + * Routines for doing kexec-based kdump + * + * Copyright (C) 2014 Linaro Limited + * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/crash_dump.h> +#include <linux/errno.h> +#include <linux/io.h> +#include <linux/memblock.h> +#include <linux/uaccess.h> +#include <asm/memory.h> + +/** + * copy_oldmem_page() - copy one page from old kernel memory + * @pfn: page frame number to be copied + * @buf: buffer where the copied page is placed + * @csize: number of bytes to copy + * @offset: offset in bytes into the page + * @userbuf: if set, @buf is in a user address space + * + * This function copies one page from old kernel memory into buffer pointed by + * @buf. If @buf is in userspace, set @userbuf to %1. Returns number of bytes + * copied or negative error in case of failure. + */ +ssize_t copy_oldmem_page(unsigned long pfn, char *buf, + size_t csize, unsigned long offset, + int userbuf) +{ + void *vaddr; + + if (!csize) + return 0; + + vaddr = ioremap_cache(pfn << PAGE_SHIFT, PAGE_SIZE); + if (!vaddr) + return -ENOMEM; + + if (userbuf) { + if (copy_to_user(buf, vaddr + offset, csize)) { + iounmap(vaddr); + return -EFAULT; + } + } else { + memcpy(buf, vaddr + offset, csize); + } + + iounmap(vaddr); + + return csize; +} + +/** + * elfcorehdr_read - read from ELF core header + * @buf: buffer where the data is placed + * @csize: number of bytes to read + * @ppos: address in the memory + * + * This function reads @count bytes from elf core header which exists + * on crash dump kernel's memory. + */ +ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos) +{ + memcpy(buf, phys_to_virt((phys_addr_t)*ppos), count); + return count; +} diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 24f0a1c..52a1469 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -35,6 +35,7 @@ #include <linux/efi.h> #include <linux/swiotlb.h> #include <linux/kexec.h> +#include <linux/crash_dump.h> #include <asm/fixmap.h> #include <asm/memory.h> @@ -116,6 +117,31 @@ static void __init reserve_crashkernel(void) } #endif /* CONFIG_KEXEC */ +#ifdef CONFIG_CRASH_DUMP +/* + * reserve_elfcorehdr() - reserves memory for elf core header + * + * This function reserves elf core header given in "elfcorehdr=" kernel + * command line parameter. This region contains all the information about + * primary kernel's core image and is used by a dump capture kernel to + * access the system memory on primary kernel. + */ +static void __init reserve_elfcorehdr(void) +{ + if (!elfcorehdr_size) + return; + + if (memblock_is_region_reserved(elfcorehdr_addr, elfcorehdr_size)) { + pr_warn("elfcorehdr is overlapped\n"); + return; + } + + memblock_reserve(elfcorehdr_addr, elfcorehdr_size); + + pr_info("Reserving %lldKB of memory at %lldMB for elfcorehdr\n", + elfcorehdr_size >> 10, elfcorehdr_addr >> 20); +} +#endif /* CONFIG_CRASH_DUMP */ /* * Return the maximum physical address for ZONE_DMA (DMA_BIT_MASK(32)). It * currently assumes that for memory starting above 4G, 32-bit devices will @@ -224,6 +250,9 @@ void __init arm64_memblock_init(void) #ifdef CONFIG_KEXEC reserve_crashkernel(); #endif +#ifdef CONFIG_CRASH_DUMP + reserve_elfcorehdr(); +#endif early_init_fdt_scan_reserved_mem();