From 7fccf0326536c1b245b98740d489abb9aab69a12 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Fri, 25 Jul 2008 19:45:02 -0700 Subject: kernel/kexec.c: make 'kimage_terminate' void Since kimage_terminate() always returns 0, make it void. Signed-off-by: WANG Cong Signed-off-by: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kexec.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'kernel/kexec.c') diff --git a/kernel/kexec.c b/kernel/kexec.c index 1c5fcacbcf3..6db42ff8d52 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -589,14 +589,12 @@ static void kimage_free_extra_pages(struct kimage *image) kimage_free_page_list(&image->unuseable_pages); } -static int kimage_terminate(struct kimage *image) +static void kimage_terminate(struct kimage *image) { if (*image->entry != 0) image->entry++; *image->entry = IND_DONE; - - return 0; } #define for_each_kimage_entry(image, ptr, entry) \ @@ -997,9 +995,7 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments, if (result) goto out; } - result = kimage_terminate(image); - if (result) - goto out; + kimage_terminate(image); } /* Install the new kernel, and Uninstall the old */ image = xchg(dest_image, image); -- cgit v1.2.3-70-g09d2 From 3ab83521378268044a448113c6aa9a9e245f4d2f Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Fri, 25 Jul 2008 19:45:07 -0700 Subject: kexec jump This patch provides an enhancement to kexec/kdump. It implements the following features: - Backup/restore memory used by the original kernel before/after kexec. - Save/restore CPU state before/after kexec. The features of this patch can be used as a general method to call program in physical mode (paging turning off). This can be used to call BIOS code under Linux. kexec-tools needs to be patched to support kexec jump. The patches and the precompiled kexec can be download from the following URL: source: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-src_git_kh10.tar.bz2 patches: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-patches_git_kh10.tar.bz2 binary: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec_git_kh10 Usage example of calling some physical mode code and return: 1. Compile and install patched kernel with following options selected: CONFIG_X86_32=y CONFIG_KEXEC=y CONFIG_PM=y CONFIG_KEXEC_JUMP=y 2. Build patched kexec-tool or download the pre-built one. 3. Build some physical mode executable named such as "phy_mode" 4. Boot kernel compiled in step 1. 5. Load physical mode executable with /sbin/kexec. The shell command line can be as follow: /sbin/kexec --load-preserve-context --args-none phy_mode 6. Call physical mode executable with following shell command line: /sbin/kexec -e Implementation point: To support jumping without reserving memory. One shadow backup page (source page) is allocated for each page used by kexeced code image (destination page). When do kexec_load, the image of kexeced code is loaded into source pages, and before executing, the destination pages and the source pages are swapped, so the contents of destination pages are backupped. Before jumping to the kexeced code image and after jumping back to the original kernel, the destination pages and the source pages are swapped too. C ABI (calling convention) is used as communication protocol between kernel and called code. A flag named KEXEC_PRESERVE_CONTEXT for sys_kexec_load is added to indicate that the loaded kernel image is used for jumping back. Now, only the i386 architecture is supported. Signed-off-by: Huang Ying Acked-by: Vivek Goyal Cc: "Eric W. Biederman" Cc: Pavel Machek Cc: Nigel Cunningham Cc: "Rafael J. Wysocki" Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/kernel/machine_kexec.c | 2 +- arch/sh/kernel/machine_kexec.c | 2 +- arch/x86/Kconfig | 7 ++ arch/x86/kernel/machine_kexec_32.c | 27 ++++-- arch/x86/kernel/machine_kexec_64.c | 2 +- arch/x86/kernel/relocate_kernel_32.S | 174 ++++++++++++++++++++++++++++++----- include/asm-x86/kexec.h | 18 ++-- include/linux/kexec.h | 17 +++- kernel/kexec.c | 57 ++++++++++++ kernel/sys.c | 31 ++----- 10 files changed, 269 insertions(+), 68 deletions(-) (limited to 'kernel/kexec.c') diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 29a0e039d43..aab76887a84 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -48,7 +48,7 @@ void machine_kexec_cleanup(struct kimage *image) * Do not allocate memory (or fail in any way) in machine_kexec(). * We are past the point of no return, committed to rebooting now. */ -NORET_TYPE void machine_kexec(struct kimage *image) +void machine_kexec(struct kimage *image) { if (ppc_md.machine_kexec) ppc_md.machine_kexec(image); diff --git a/arch/sh/kernel/machine_kexec.c b/arch/sh/kernel/machine_kexec.c index 5c17de51987..ec1eadce4aa 100644 --- a/arch/sh/kernel/machine_kexec.c +++ b/arch/sh/kernel/machine_kexec.c @@ -70,7 +70,7 @@ static void kexec_info(struct kimage *image) * Do not allocate memory (or fail in any way) in machine_kexec(). * We are past the point of no return, committed to rebooting now. */ -NORET_TYPE void machine_kexec(struct kimage *image) +void machine_kexec(struct kimage *image) { unsigned long page_list; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e3cba0b4560..7ecb679f013 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1279,6 +1279,13 @@ config CRASH_DUMP (CONFIG_RELOCATABLE=y). For more details see Documentation/kdump/kdump.txt +config KEXEC_JUMP + bool "kexec jump (EXPERIMENTAL)" + depends on EXPERIMENTAL + depends on KEXEC && PM_SLEEP && X86_32 + help + Invoke code in physical address mode via KEXEC + config PHYSICAL_START hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP) default "0x1000000" if X86_NUMAQ diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 8864230d55a..2b67609d0a1 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -22,6 +22,7 @@ #include #include #include +#include #define PAGE_ALIGNED __attribute__ ((__aligned__(PAGE_SIZE))) static u32 kexec_pgd[1024] PAGE_ALIGNED; @@ -85,10 +86,12 @@ static void load_segments(void) * reboot code buffer to allow us to avoid allocations * later. * - * Currently nothing. + * Make control page executable. */ int machine_kexec_prepare(struct kimage *image) { + if (nx_enabled) + set_pages_x(image->control_code_page, 1); return 0; } @@ -98,16 +101,24 @@ int machine_kexec_prepare(struct kimage *image) */ void machine_kexec_cleanup(struct kimage *image) { + if (nx_enabled) + set_pages_nx(image->control_code_page, 1); } /* * Do not allocate memory (or fail in any way) in machine_kexec(). * We are past the point of no return, committed to rebooting now. */ -NORET_TYPE void machine_kexec(struct kimage *image) +void machine_kexec(struct kimage *image) { unsigned long page_list[PAGES_NR]; void *control_page; + asmlinkage unsigned long + (*relocate_kernel_ptr)(unsigned long indirection_page, + unsigned long control_page, + unsigned long start_address, + unsigned int has_pae, + unsigned int preserve_context); tracer_disable(); @@ -115,10 +126,11 @@ NORET_TYPE void machine_kexec(struct kimage *image) local_irq_disable(); control_page = page_address(image->control_code_page); - memcpy(control_page, relocate_kernel, PAGE_SIZE); + memcpy(control_page, relocate_kernel, PAGE_SIZE/2); + relocate_kernel_ptr = control_page; page_list[PA_CONTROL_PAGE] = __pa(control_page); - page_list[VA_CONTROL_PAGE] = (unsigned long)relocate_kernel; + page_list[VA_CONTROL_PAGE] = (unsigned long)control_page; page_list[PA_PGD] = __pa(kexec_pgd); page_list[VA_PGD] = (unsigned long)kexec_pgd; #ifdef CONFIG_X86_PAE @@ -131,6 +143,7 @@ NORET_TYPE void machine_kexec(struct kimage *image) page_list[VA_PTE_0] = (unsigned long)kexec_pte0; page_list[PA_PTE_1] = __pa(kexec_pte1); page_list[VA_PTE_1] = (unsigned long)kexec_pte1; + page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page) << PAGE_SHIFT); /* The segment registers are funny things, they have both a * visible and an invisible part. Whenever the visible part is @@ -149,8 +162,10 @@ NORET_TYPE void machine_kexec(struct kimage *image) set_idt(phys_to_virt(0),0); /* now call it */ - relocate_kernel((unsigned long)image->head, (unsigned long)page_list, - image->start, cpu_has_pae); + image->start = relocate_kernel_ptr((unsigned long)image->head, + (unsigned long)page_list, + image->start, cpu_has_pae, + image->preserve_context); } void arch_crash_save_vmcoreinfo(void) diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 9dd9262693a..c43caa3a91f 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -181,7 +181,7 @@ void machine_kexec_cleanup(struct kimage *image) * Do not allocate memory (or fail in any way) in machine_kexec(). * We are past the point of no return, committed to rebooting now. */ -NORET_TYPE void machine_kexec(struct kimage *image) +void machine_kexec(struct kimage *image) { unsigned long page_list[PAGES_NR]; void *control_page; diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S index c30fe25d470..703310a9902 100644 --- a/arch/x86/kernel/relocate_kernel_32.S +++ b/arch/x86/kernel/relocate_kernel_32.S @@ -20,11 +20,44 @@ #define PAGE_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY) #define PAE_PGD_ATTR (_PAGE_PRESENT) +/* control_page + PAGE_SIZE/2 ~ control_page + PAGE_SIZE * 3/4 are + * used to save some data for jumping back + */ +#define DATA(offset) (PAGE_SIZE/2+(offset)) + +/* Minimal CPU state */ +#define ESP DATA(0x0) +#define CR0 DATA(0x4) +#define CR3 DATA(0x8) +#define CR4 DATA(0xc) + +/* other data */ +#define CP_VA_CONTROL_PAGE DATA(0x10) +#define CP_PA_PGD DATA(0x14) +#define CP_PA_SWAP_PAGE DATA(0x18) +#define CP_PA_BACKUP_PAGES_MAP DATA(0x1c) + .text .align PAGE_SIZE .globl relocate_kernel relocate_kernel: - movl 8(%esp), %ebp /* list of pages */ + /* Save the CPU context, used for jumping back */ + + pushl %ebx + pushl %esi + pushl %edi + pushl %ebp + pushf + + movl 20+8(%esp), %ebp /* list of pages */ + movl PTR(VA_CONTROL_PAGE)(%ebp), %edi + movl %esp, ESP(%edi) + movl %cr0, %eax + movl %eax, CR0(%edi) + movl %cr3, %eax + movl %eax, CR3(%edi) + movl %cr4, %eax + movl %eax, CR4(%edi) #ifdef CONFIG_X86_PAE /* map the control page at its virtual address */ @@ -138,15 +171,25 @@ relocate_kernel: relocate_new_kernel: /* read the arguments and say goodbye to the stack */ - movl 4(%esp), %ebx /* page_list */ - movl 8(%esp), %ebp /* list of pages */ - movl 12(%esp), %edx /* start address */ - movl 16(%esp), %ecx /* cpu_has_pae */ + movl 20+4(%esp), %ebx /* page_list */ + movl 20+8(%esp), %ebp /* list of pages */ + movl 20+12(%esp), %edx /* start address */ + movl 20+16(%esp), %ecx /* cpu_has_pae */ + movl 20+20(%esp), %esi /* preserve_context */ /* zero out flags, and disable interrupts */ pushl $0 popfl + /* save some information for jumping back */ + movl PTR(VA_CONTROL_PAGE)(%ebp), %edi + movl %edi, CP_VA_CONTROL_PAGE(%edi) + movl PTR(PA_PGD)(%ebp), %eax + movl %eax, CP_PA_PGD(%edi) + movl PTR(PA_SWAP_PAGE)(%ebp), %eax + movl %eax, CP_PA_SWAP_PAGE(%edi) + movl %ebx, CP_PA_BACKUP_PAGES_MAP(%edi) + /* get physical address of control page now */ /* this is impossible after page table switch */ movl PTR(PA_CONTROL_PAGE)(%ebp), %edi @@ -197,8 +240,90 @@ identity_mapped: xorl %eax, %eax movl %eax, %cr3 + movl CP_PA_SWAP_PAGE(%edi), %eax + pushl %eax + pushl %ebx + call swap_pages + addl $8, %esp + + /* To be certain of avoiding problems with self-modifying code + * I need to execute a serializing instruction here. + * So I flush the TLB, it's handy, and not processor dependent. + */ + xorl %eax, %eax + movl %eax, %cr3 + + /* set all of the registers to known values */ + /* leave %esp alone */ + + testl %esi, %esi + jnz 1f + xorl %edi, %edi + xorl %eax, %eax + xorl %ebx, %ebx + xorl %ecx, %ecx + xorl %edx, %edx + xorl %esi, %esi + xorl %ebp, %ebp + ret +1: + popl %edx + movl CP_PA_SWAP_PAGE(%edi), %esp + addl $PAGE_SIZE, %esp +2: + call *%edx + + /* get the re-entry point of the peer system */ + movl 0(%esp), %ebp + call 1f +1: + popl %ebx + subl $(1b - relocate_kernel), %ebx + movl CP_VA_CONTROL_PAGE(%ebx), %edi + lea PAGE_SIZE(%ebx), %esp + movl CP_PA_SWAP_PAGE(%ebx), %eax + movl CP_PA_BACKUP_PAGES_MAP(%ebx), %edx + pushl %eax + pushl %edx + call swap_pages + addl $8, %esp + movl CP_PA_PGD(%ebx), %eax + movl %eax, %cr3 + movl %cr0, %eax + orl $(1<<31), %eax + movl %eax, %cr0 + lea PAGE_SIZE(%edi), %esp + movl %edi, %eax + addl $(virtual_mapped - relocate_kernel), %eax + pushl %eax + ret + +virtual_mapped: + movl CR4(%edi), %eax + movl %eax, %cr4 + movl CR3(%edi), %eax + movl %eax, %cr3 + movl CR0(%edi), %eax + movl %eax, %cr0 + movl ESP(%edi), %esp + movl %ebp, %eax + + popf + popl %ebp + popl %edi + popl %esi + popl %ebx + ret + /* Do the copies */ - movl %ebx, %ecx +swap_pages: + movl 8(%esp), %edx + movl 4(%esp), %ecx + pushl %ebp + pushl %ebx + pushl %edi + pushl %esi + movl %ecx, %ebx jmp 1f 0: /* top, read another word from the indirection page */ @@ -226,27 +351,28 @@ identity_mapped: movl %ecx, %esi /* For every source page do a copy */ andl $0xfffff000, %esi + movl %edi, %eax + movl %esi, %ebp + + movl %edx, %edi movl $1024, %ecx rep ; movsl - jmp 0b -3: - - /* To be certain of avoiding problems with self-modifying code - * I need to execute a serializing instruction here. - * So I flush the TLB, it's handy, and not processor dependent. - */ - xorl %eax, %eax - movl %eax, %cr3 + movl %ebp, %edi + movl %eax, %esi + movl $1024, %ecx + rep ; movsl - /* set all of the registers to known values */ - /* leave %esp alone */ + movl %eax, %edi + movl %edx, %esi + movl $1024, %ecx + rep ; movsl - xorl %eax, %eax - xorl %ebx, %ebx - xorl %ecx, %ecx - xorl %edx, %edx - xorl %esi, %esi - xorl %edi, %edi - xorl %ebp, %ebp + lea PAGE_SIZE(%ebp), %esi + jmp 0b +3: + popl %esi + popl %edi + popl %ebx + popl %ebp ret diff --git a/include/asm-x86/kexec.h b/include/asm-x86/kexec.h index 8f855a15f64..c0e52a14fd4 100644 --- a/include/asm-x86/kexec.h +++ b/include/asm-x86/kexec.h @@ -10,14 +10,15 @@ # define VA_PTE_0 5 # define PA_PTE_1 6 # define VA_PTE_1 7 +# define PA_SWAP_PAGE 8 # ifdef CONFIG_X86_PAE -# define PA_PMD_0 8 -# define VA_PMD_0 9 -# define PA_PMD_1 10 -# define VA_PMD_1 11 -# define PAGES_NR 12 +# define PA_PMD_0 9 +# define VA_PMD_0 10 +# define PA_PMD_1 11 +# define VA_PMD_1 12 +# define PAGES_NR 13 # else -# define PAGES_NR 8 +# define PAGES_NR 9 # endif #else # define PA_CONTROL_PAGE 0 @@ -152,11 +153,12 @@ static inline void crash_setup_regs(struct pt_regs *newregs, } #ifdef CONFIG_X86_32 -asmlinkage NORET_TYPE void +asmlinkage unsigned long relocate_kernel(unsigned long indirection_page, unsigned long control_page, unsigned long start_address, - unsigned int has_pae) ATTRIB_NORET; + unsigned int has_pae, + unsigned int preserve_context); #else NORET_TYPE void relocate_kernel(unsigned long indirection_page, diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 3265968cd2c..82f88a8a827 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -83,6 +83,7 @@ struct kimage { unsigned long start; struct page *control_code_page; + struct page *swap_page; unsigned long nr_segments; struct kexec_segment segment[KEXEC_SEGMENT_MAX]; @@ -98,18 +99,20 @@ struct kimage { unsigned int type : 1; #define KEXEC_TYPE_DEFAULT 0 #define KEXEC_TYPE_CRASH 1 + unsigned int preserve_context : 1; }; /* kexec interface functions */ -extern NORET_TYPE void machine_kexec(struct kimage *image) ATTRIB_NORET; +extern void machine_kexec(struct kimage *image); extern int machine_kexec_prepare(struct kimage *image); extern void machine_kexec_cleanup(struct kimage *image); extern asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments, struct kexec_segment __user *segments, unsigned long flags); +extern int kernel_kexec(void); #ifdef CONFIG_COMPAT extern asmlinkage long compat_sys_kexec_load(unsigned long entry, unsigned long nr_segments, @@ -156,8 +159,9 @@ extern struct kimage *kexec_crash_image; #define kexec_flush_icache_page(page) #endif -#define KEXEC_ON_CRASH 0x00000001 -#define KEXEC_ARCH_MASK 0xffff0000 +#define KEXEC_ON_CRASH 0x00000001 +#define KEXEC_PRESERVE_CONTEXT 0x00000002 +#define KEXEC_ARCH_MASK 0xffff0000 /* These values match the ELF architecture values. * Unless there is a good reason that should continue to be the case. @@ -174,7 +178,12 @@ extern struct kimage *kexec_crash_image; #define KEXEC_ARCH_MIPS_LE (10 << 16) #define KEXEC_ARCH_MIPS ( 8 << 16) -#define KEXEC_FLAGS (KEXEC_ON_CRASH) /* List of defined/legal kexec flags */ +/* List of defined/legal kexec flags */ +#ifndef CONFIG_KEXEC_JUMP +#define KEXEC_FLAGS KEXEC_ON_CRASH +#else +#define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_PRESERVE_CONTEXT) +#endif #define VMCOREINFO_BYTES (4096) #define VMCOREINFO_NOTE_NAME "VMCOREINFO" diff --git a/kernel/kexec.c b/kernel/kexec.c index 6db42ff8d52..a0d920915b3 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -24,6 +24,8 @@ #include #include #include +#include +#include #include #include @@ -242,6 +244,12 @@ static int kimage_normal_alloc(struct kimage **rimage, unsigned long entry, goto out; } + image->swap_page = kimage_alloc_control_pages(image, 0); + if (!image->swap_page) { + printk(KERN_ERR "Could not allocate swap buffer\n"); + goto out; + } + result = 0; out: if (result == 0) @@ -986,6 +994,8 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments, if (result) goto out; + if (flags & KEXEC_PRESERVE_CONTEXT) + image->preserve_context = 1; result = machine_kexec_prepare(image); if (result) goto out; @@ -1411,3 +1421,50 @@ static int __init crash_save_vmcoreinfo_init(void) } module_init(crash_save_vmcoreinfo_init) + +/** + * kernel_kexec - reboot the system + * + * Move into place and start executing a preloaded standalone + * executable. If nothing was preloaded return an error. + */ +int kernel_kexec(void) +{ + int error = 0; + + if (xchg(&kexec_lock, 1)) + return -EBUSY; + if (!kexec_image) { + error = -EINVAL; + goto Unlock; + } + + if (kexec_image->preserve_context) { +#ifdef CONFIG_KEXEC_JUMP + local_irq_disable(); + save_processor_state(); +#endif + } else { + blocking_notifier_call_chain(&reboot_notifier_list, + SYS_RESTART, NULL); + system_state = SYSTEM_RESTART; + device_shutdown(); + sysdev_shutdown(); + printk(KERN_EMERG "Starting new kernel\n"); + machine_shutdown(); + } + + machine_kexec(kexec_image); + + if (kexec_image->preserve_context) { +#ifdef CONFIG_KEXEC_JUMP + restore_processor_state(); + local_irq_enable(); +#endif + } + + Unlock: + xchg(&kexec_lock, 0); + + return error; +} diff --git a/kernel/sys.c b/kernel/sys.c index 0c9d3fa1f5f..c01858090a9 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -301,26 +301,6 @@ void kernel_restart(char *cmd) } EXPORT_SYMBOL_GPL(kernel_restart); -/** - * kernel_kexec - reboot the system - * - * Move into place and start executing a preloaded standalone - * executable. If nothing was preloaded return an error. - */ -static void kernel_kexec(void) -{ -#ifdef CONFIG_KEXEC - struct kimage *image; - image = xchg(&kexec_image, NULL); - if (!image) - return; - kernel_restart_prepare(NULL); - printk(KERN_EMERG "Starting new kernel\n"); - machine_shutdown(); - machine_kexec(image); -#endif -} - static void kernel_shutdown_prepare(enum system_states state) { blocking_notifier_call_chain(&reboot_notifier_list, @@ -425,10 +405,15 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user kernel_restart(buffer); break; +#ifdef CONFIG_KEXEC case LINUX_REBOOT_CMD_KEXEC: - kernel_kexec(); - unlock_kernel(); - return -EINVAL; + { + int ret; + ret = kernel_kexec(); + unlock_kernel(); + return ret; + } +#endif #ifdef CONFIG_HIBERNATION case LINUX_REBOOT_CMD_SW_SUSPEND: -- cgit v1.2.3-70-g09d2 From 89081d17f7bb81d89fa1aa9b70f821c5cf4d39e9 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Fri, 25 Jul 2008 19:45:10 -0700 Subject: kexec jump: save/restore device state This patch implements devices state save/restore before after kexec. This patch together with features in kexec_jump patch can be used for following: - A simple hibernation implementation without ACPI support. You can kexec a hibernating kernel, save the memory image of original system and shutdown the system. When resuming, you restore the memory image of original system via ordinary kexec load then jump back. - Kernel/system debug through making system snapshot. You can make system snapshot, jump back, do some thing and make another system snapshot. - Cooperative multi-kernel/system. With kexec jump, you can switch between several kernels/systems quickly without boot process except the first time. This appears like swap a whole kernel/system out/in. - A general method to call program in physical mode (paging turning off). This can be used to invoke BIOS code under Linux. The following user-space tools can be used with kexec jump: - kexec-tools needs to be patched to support kexec jump. The patches and the precompiled kexec can be download from the following URL: source: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-src_git_kh10.tar.bz2 patches: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-patches_git_kh10.tar.bz2 binary: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec_git_kh10 - makedumpfile with patches are used as memory image saving tool, it can exclude free pages from original kernel memory image file. The patches and the precompiled makedumpfile can be download from the following URL: source: http://khibernation.sourceforge.net/download/release_v10/makedumpfile/makedumpfile-src_cvs_kh10.tar.bz2 patches: http://khibernation.sourceforge.net/download/release_v10/makedumpfile/makedumpfile-patches_cvs_kh10.tar.bz2 binary: http://khibernation.sourceforge.net/download/release_v10/makedumpfile/makedumpfile_cvs_kh10 - An initramfs image can be used as the root file system of kexeced kernel. An initramfs image built with "BuildRoot" can be downloaded from the following URL: initramfs image: http://khibernation.sourceforge.net/download/release_v10/initramfs/rootfs_cvs_kh10.gz All user space tools above are included in the initramfs image. Usage example of simple hibernation: 1. Compile and install patched kernel with following options selected: CONFIG_X86_32=y CONFIG_RELOCATABLE=y CONFIG_KEXEC=y CONFIG_CRASH_DUMP=y CONFIG_PM=y CONFIG_HIBERNATION=y CONFIG_KEXEC_JUMP=y 2. Build an initramfs image contains kexec-tool and makedumpfile, or download the pre-built initramfs image, called rootfs.gz in following text. 3. Prepare a partition to save memory image of original kernel, called hibernating partition in following text. 4. Boot kernel compiled in step 1 (kernel A). 5. In the kernel A, load kernel compiled in step 1 (kernel B) with /sbin/kexec. The shell command line can be as follow: /sbin/kexec --load-preserve-context /boot/bzImage --mem-min=0x100000 --mem-max=0xffffff --initrd=rootfs.gz 6. Boot the kernel B with following shell command line: /sbin/kexec -e 7. The kernel B will boot as normal kexec. In kernel B the memory image of kernel A can be saved into hibernating partition as follow: jump_back_entry=`cat /proc/cmdline | tr ' ' '\n' | grep kexec_jump_back_entry | cut -d '='` echo $jump_back_entry > kexec_jump_back_entry cp /proc/vmcore dump.elf Then you can shutdown the machine as normal. 8. Boot kernel compiled in step 1 (kernel C). Use the rootfs.gz as root file system. 9. In kernel C, load the memory image of kernel A as follow: /sbin/kexec -l --args-none --entry=`cat kexec_jump_back_entry` dump.elf 10. Jump back to the kernel A as follow: /sbin/kexec -e Then, kernel A is resumed. Implementation point: To support jumping between two kernels, before jumping to (executing) the new kernel and jumping back to the original kernel, the devices are put into quiescent state, and the state of devices and CPU is saved. After jumping back from kexeced kernel and jumping to the new kernel, the state of devices and CPU are restored accordingly. The devices/CPU state save/restore code of software suspend is called to implement corresponding function. Known issues: - Because the segment number supported by sys_kexec_load is limited, hibernation image with many segments may not be load. This is planned to be eliminated by adding a new flag to sys_kexec_load to make a image can be loaded with multiple sys_kexec_load invoking. Now, only the i386 architecture is supported. Signed-off-by: Huang Ying Acked-by: Vivek Goyal Cc: "Eric W. Biederman" Cc: Pavel Machek Cc: Nigel Cunningham Cc: "Rafael J. Wysocki" Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/Kconfig | 5 +++-- arch/x86/kernel/machine_kexec_32.c | 12 ++++++++++++ include/linux/suspend.h | 2 ++ kernel/kexec.c | 39 ++++++++++++++++++++++++++++++++++++++ kernel/power/power.h | 2 -- 5 files changed, 56 insertions(+), 4 deletions(-) (limited to 'kernel/kexec.c') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 7ecb679f013..6b2debfabdd 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1282,9 +1282,10 @@ config CRASH_DUMP config KEXEC_JUMP bool "kexec jump (EXPERIMENTAL)" depends on EXPERIMENTAL - depends on KEXEC && PM_SLEEP && X86_32 + depends on KEXEC && HIBERNATION && X86_32 help - Invoke code in physical address mode via KEXEC + Jump between original kernel and kexeced kernel and invoke + code in physical address mode via KEXEC config PHYSICAL_START hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP) diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 2b67609d0a1..9fe478d9840 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -125,6 +125,18 @@ void machine_kexec(struct kimage *image) /* Interrupts aren't acceptable while we reboot */ local_irq_disable(); + if (image->preserve_context) { +#ifdef CONFIG_X86_IO_APIC + /* We need to put APICs in legacy mode so that we can + * get timer interrupts in second kernel. kexec/kdump + * paths already have calls to disable_IO_APIC() in + * one form or other. kexec jump path also need + * one. + */ + disable_IO_APIC(); +#endif + } + control_page = page_address(image->control_code_page); memcpy(control_page, relocate_kernel, PAGE_SIZE/2); diff --git a/include/linux/suspend.h b/include/linux/suspend.h index e8e69159af7..c6343509597 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -278,4 +278,6 @@ static inline void register_nosave_region_late(unsigned long b, unsigned long e) } #endif +extern struct mutex pm_mutex; + #endif /* _LINUX_SUSPEND_H */ diff --git a/kernel/kexec.c b/kernel/kexec.c index a0d920915b3..c8a4370e2a3 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -26,6 +26,10 @@ #include #include #include +#include +#include +#include +#include #include #include @@ -1441,7 +1445,31 @@ int kernel_kexec(void) if (kexec_image->preserve_context) { #ifdef CONFIG_KEXEC_JUMP + mutex_lock(&pm_mutex); + pm_prepare_console(); + error = freeze_processes(); + if (error) { + error = -EBUSY; + goto Restore_console; + } + suspend_console(); + error = device_suspend(PMSG_FREEZE); + if (error) + goto Resume_console; + error = disable_nonboot_cpus(); + if (error) + goto Resume_devices; local_irq_disable(); + /* At this point, device_suspend() has been called, + * but *not* device_power_down(). We *must* + * device_power_down() now. Otherwise, drivers for + * some devices (e.g. interrupt controllers) become + * desynchronized with the actual state of the + * hardware at resume time, and evil weirdness ensues. + */ + error = device_power_down(PMSG_FREEZE); + if (error) + goto Enable_irqs; save_processor_state(); #endif } else { @@ -1459,7 +1487,18 @@ int kernel_kexec(void) if (kexec_image->preserve_context) { #ifdef CONFIG_KEXEC_JUMP restore_processor_state(); + device_power_up(PMSG_RESTORE); + Enable_irqs: local_irq_enable(); + enable_nonboot_cpus(); + Resume_devices: + device_resume(PMSG_RESTORE); + Resume_console: + resume_console(); + thaw_processes(); + Restore_console: + pm_restore_console(); + mutex_unlock(&pm_mutex); #endif } diff --git a/kernel/power/power.h b/kernel/power/power.h index 700f44ec840..acc0c101dbd 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -53,8 +53,6 @@ extern int hibernation_platform_enter(void); extern int pfn_is_nosave(unsigned long); -extern struct mutex pm_mutex; - #define power_attr(_name) \ static struct kobj_attribute _name##_attr = { \ .attr = { \ -- cgit v1.2.3-70-g09d2