arch_kexec_protect_crashkres() and arch_kexec_unprotect_crashkres() are meant to be called around kexec_load() in order to protect the memory allocated for crash dump kernel once after it's loaded. The protection is implemented here by unmapping the region rather than making it read-only. To make the things work correctly, we also have to - put the region in an isolated, page-level mapping initially, and - move copying kexec's control_code_page to machine_kexec_prepare() Note that page-level mapping is also required to allow for shrinking the size of memory, through /sys/kernel/kexec_crash_size, by any number of multiple pages. Signed-off-by: AKASHI Takahiro <takahiro.akashi at linaro.org> --- arch/arm64/kernel/machine_kexec.c | 65 ++++++++++++++++++++++++++------------- arch/arm64/mm/mmu.c | 35 +++++++++++++++++++++ 2 files changed, 79 insertions(+), 21 deletions(-) diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index bc96c8a7fc79..016f2dd693aa 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -14,6 +14,7 @@ #include <asm/cacheflush.h> #include <asm/cpu_ops.h> +#include <asm/mmu.h> #include <asm/mmu_context.h> #include "cpu-reset.h" @@ -22,8 +23,6 @@ extern const unsigned char arm64_relocate_new_kernel[]; extern const unsigned long arm64_relocate_new_kernel_size; -static unsigned long kimage_start; - /** * kexec_image_info - For debugging output. */ @@ -64,7 +63,7 @@ void machine_kexec_cleanup(struct kimage *kimage) */ int machine_kexec_prepare(struct kimage *kimage) { - kimage_start = kimage->start; + void *reboot_code_buffer; kexec_image_info(kimage); @@ -73,6 +72,21 @@ int machine_kexec_prepare(struct kimage *kimage) return -EBUSY; } + reboot_code_buffer = + phys_to_virt(page_to_phys(kimage->control_code_page)); + + /* + * Copy arm64_relocate_new_kernel to the reboot_code_buffer for use + * after the kernel is shut down. + */ + memcpy(reboot_code_buffer, arm64_relocate_new_kernel, + arm64_relocate_new_kernel_size); + + /* Flush the reboot_code_buffer in preparation for its execution. */ + __flush_dcache_area(reboot_code_buffer, arm64_relocate_new_kernel_size); + flush_icache_range((uintptr_t)reboot_code_buffer, + arm64_relocate_new_kernel_size); + return 0; } @@ -143,7 +157,6 @@ static void kexec_segment_flush(const struct kimage *kimage) void machine_kexec(struct kimage *kimage) { phys_addr_t reboot_code_buffer_phys; - void *reboot_code_buffer; /* * New cpus may have become stuck_in_kernel after we loaded the image. @@ -151,7 +164,6 @@ void machine_kexec(struct kimage *kimage) BUG_ON(cpus_are_stuck_in_kernel() || (num_online_cpus() > 1)); reboot_code_buffer_phys = page_to_phys(kimage->control_code_page); - reboot_code_buffer = phys_to_virt(reboot_code_buffer_phys); kexec_image_info(kimage); @@ -159,31 +171,17 @@ void machine_kexec(struct kimage *kimage) kimage->control_code_page); pr_debug("%s:%d: reboot_code_buffer_phys: %pa\n", __func__, __LINE__, &reboot_code_buffer_phys); - pr_debug("%s:%d: reboot_code_buffer: %p\n", __func__, __LINE__, - reboot_code_buffer); pr_debug("%s:%d: relocate_new_kernel: %p\n", __func__, __LINE__, arm64_relocate_new_kernel); pr_debug("%s:%d: relocate_new_kernel_size: 0x%lx(%lu) bytes\n", __func__, __LINE__, arm64_relocate_new_kernel_size, arm64_relocate_new_kernel_size); - /* - * Copy arm64_relocate_new_kernel to the reboot_code_buffer for use - * after the kernel is shut down. - */ - memcpy(reboot_code_buffer, arm64_relocate_new_kernel, - arm64_relocate_new_kernel_size); - - /* Flush the reboot_code_buffer in preparation for its execution. */ - __flush_dcache_area(reboot_code_buffer, arm64_relocate_new_kernel_size); - flush_icache_range((uintptr_t)reboot_code_buffer, - arm64_relocate_new_kernel_size); - /* Flush the kimage list and its buffers. */ kexec_list_flush(kimage); /* Flush the new image if already in place. */ - if (kimage->head & IND_DONE) + if ((kimage != kexec_crash_image) && (kimage->head & IND_DONE)) kexec_segment_flush(kimage); pr_info("Bye!\n"); @@ -201,7 +199,7 @@ void machine_kexec(struct kimage *kimage) */ cpu_soft_restart(1, reboot_code_buffer_phys, kimage->head, - kimage_start, 0); + kimage->start, 0); BUG(); /* Should never get here. */ } @@ -210,3 +208,28 @@ void machine_crash_shutdown(struct pt_regs *regs) { /* Empty routine needed to avoid build errors. */ } + +void arch_kexec_protect_crashkres(void) +{ + kexec_segment_flush(kexec_crash_image); + + remove_pgd_mapping(&init_mm, __phys_to_virt(crashk_res.start), + resource_size(&crashk_res)); + + flush_tlb_all(); +} + +void arch_kexec_unprotect_crashkres(void) +{ + /* + * We don't have to make page-level mappings here because + * the crash dump kernel memory is not allowed to be shrunk + * once the kernel is loaded. + */ + create_pgd_mapping(&init_mm, crashk_res.start, + __phys_to_virt(crashk_res.start), + resource_size(&crashk_res), PAGE_KERNEL, + debug_pagealloc_enabled()); + + flush_tlb_all(); +} diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 9d3cea1db3b4..87861e62316a 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -22,6 +22,8 @@ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/init.h> +#include <linux/ioport.h> +#include <linux/kexec.h> #include <linux/libfdt.h> #include <linux/mman.h> #include <linux/nodemask.h> @@ -538,6 +540,24 @@ static void __init map_mem(pgd_t *pgd) if (memblock_is_nomap(reg)) continue; +#ifdef CONFIG_KEXEC_CORE + /* + * While crash dump kernel memory is contained in a single + * memblock for now, it should appear in an isolated mapping + * so that we can independently unmap the region later. + */ + if (crashk_res.end && + (start <= crashk_res.start) && + ((crashk_res.end + 1) < end)) { + if (crashk_res.start != start) + __map_memblock(pgd, start, crashk_res.start); + + if ((crashk_res.end + 1) < end) + __map_memblock(pgd, crashk_res.end + 1, end); + + continue; + } +#endif __map_memblock(pgd, start, end); } } @@ -623,6 +643,21 @@ static void __init map_kernel(pgd_t *pgd) kasan_copy_shadow(pgd); } +#ifdef CONFIG_KEXEC_CORE +static int __init map_crashkernel(void) +{ + /* page-level mapping only to allow for shrinking */ + if (crashk_res.end) + create_pgd_mapping(&init_mm, crashk_res.start, + __phys_to_virt(crashk_res.start), + resource_size(&crashk_res), PAGE_KERNEL, + true); + + return 0; +} +subsys_initcall(map_crashkernel); +#endif + /* * paging_init() sets up the page tables, initialises the zone memory * maps and sets up the zero page. -- 2.11.0