linux/arch/powerpc/kernel/machine_kexec.c

282 lines
7.2 KiB
C
Raw Normal View History

/*
* Code to handle transition of Linux booting another kernel.
*
* Copyright (C) 2002-2003 Eric Biederman <ebiederm@xmission.com>
* GameCube/ppc32 port Copyright (C) 2004 Albert Herranz
* Copyright (C) 2005 IBM Corporation.
*
* This source code is licensed under the GNU General Public License,
* Version 2. See the file COPYING for more details.
*/
#include <linux/kexec.h>
#include <linux/reboot.h>
#include <linux/threads.h>
#include <linux/memblock.h>
#include <linux/of.h>
#include <linux/irq.h>
#include <linux/ftrace.h>
#include <asm/machdep.h>
#include <asm/pgalloc.h>
#include <asm/prom.h>
#include <asm/sections.h>
void machine_kexec_mask_interrupts(void) {
unsigned int i;
struct irq_desc *desc;
for_each_irq_desc(i, desc) {
struct irq_chip *chip;
chip = irq_desc_get_chip(desc);
if (!chip)
continue;
if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data))
chip->irq_eoi(&desc->irq_data);
if (chip->irq_mask)
chip->irq_mask(&desc->irq_data);
if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
chip->irq_disable(&desc->irq_data);
}
}
void machine_crash_shutdown(struct pt_regs *regs)
{
default_machine_crash_shutdown(regs);
}
/*
* Do what every setup is needed on image and the
* reboot code buffer to allow us to avoid allocations
* later.
*/
int machine_kexec_prepare(struct kimage *image)
{
if (ppc_md.machine_kexec_prepare)
return ppc_md.machine_kexec_prepare(image);
else
return default_machine_kexec_prepare(image);
}
void machine_kexec_cleanup(struct kimage *image)
{
}
void arch_crash_save_vmcoreinfo(void)
{
#ifdef CONFIG_NEED_MULTIPLE_NODES
VMCOREINFO_SYMBOL(node_data);
VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
#endif
#ifndef CONFIG_NEED_MULTIPLE_NODES
VMCOREINFO_SYMBOL(contig_page_data);
#endif
#if defined(CONFIG_PPC64) && defined(CONFIG_SPARSEMEM_VMEMMAP)
VMCOREINFO_SYMBOL(vmemmap_list);
VMCOREINFO_SYMBOL(mmu_vmemmap_psize);
VMCOREINFO_SYMBOL(mmu_psize_defs);
VMCOREINFO_STRUCT_SIZE(vmemmap_backing);
VMCOREINFO_OFFSET(vmemmap_backing, list);
VMCOREINFO_OFFSET(vmemmap_backing, phys);
VMCOREINFO_OFFSET(vmemmap_backing, virt_addr);
VMCOREINFO_STRUCT_SIZE(mmu_psize_def);
VMCOREINFO_OFFSET(mmu_psize_def, shift);
#endif
}
/*
* Do not allocate memory (or fail in any way) in machine_kexec().
* We are past the point of no return, committed to rebooting now.
*/
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 <ying.huang@intel.com> Acked-by: Vivek Goyal <vgoyal@redhat.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Nigel Cunningham <nigel@nigel.suspend2.net> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 02:45:07 +00:00
void machine_kexec(struct kimage *image)
{
int save_ftrace_enabled;
save_ftrace_enabled = __ftrace_enabled_save();
if (ppc_md.machine_kexec)
ppc_md.machine_kexec(image);
else
default_machine_kexec(image);
__ftrace_enabled_restore(save_ftrace_enabled);
/* Fall back to normal restart if we're still alive. */
machine_restart(NULL);
for(;;);
}
void __init reserve_crashkernel(void)
{
unsigned long long crash_size, crash_base;
int ret;
/* use common parsing */
ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
&crash_size, &crash_base);
if (ret == 0 && crash_size > 0) {
crashk_res.start = crash_base;
crashk_res.end = crash_base + crash_size - 1;
}
if (crashk_res.end == crashk_res.start) {
crashk_res.start = crashk_res.end = 0;
return;
}
/* We might have got these values via the command line or the
* device tree, either way sanitise them now. */
crash_size = resource_size(&crashk_res);
#ifndef CONFIG_NONSTATIC_KERNEL
if (crashk_res.start != KDUMP_KERNELBASE)
printk("Crash kernel location must be 0x%x\n",
KDUMP_KERNELBASE);
crashk_res.start = KDUMP_KERNELBASE;
#else
if (!crashk_res.start) {
#ifdef CONFIG_PPC64
/*
* On 64bit we split the RMO in half but cap it at half of
* a small SLB (128MB) since the crash kernel needs to place
* itself and some stacks to be in the first segment.
*/
crashk_res.start = min(0x8000000ULL, (ppc64_rma_size / 2));
#else
crashk_res.start = KDUMP_KERNELBASE;
#endif
}
crash_base = PAGE_ALIGN(crashk_res.start);
if (crash_base != crashk_res.start) {
printk("Crash kernel base must be aligned to 0x%lx\n",
PAGE_SIZE);
crashk_res.start = crash_base;
}
#endif
crash_size = PAGE_ALIGN(crash_size);
crashk_res.end = crashk_res.start + crash_size - 1;
/* The crash region must not overlap the current kernel */
if (overlaps_crashkernel(__pa(_stext), _end - _stext)) {
printk(KERN_WARNING
"Crash kernel can not overlap current kernel\n");
crashk_res.start = crashk_res.end = 0;
return;
}
/* Crash kernel trumps memory limit */
if (memory_limit && memory_limit <= crashk_res.end) {
memory_limit = crashk_res.end + 1;
printk("Adjusted memory limit for crashkernel, now 0x%llx\n",
memory_limit);
}
printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
"for crashkernel (System RAM: %ldMB)\n",
(unsigned long)(crash_size >> 20),
(unsigned long)(crashk_res.start >> 20),
(unsigned long)(memblock_phys_mem_size() >> 20));
memblock_reserve(crashk_res.start, crash_size);
}
int overlaps_crashkernel(unsigned long start, unsigned long size)
{
return (start + size) > crashk_res.start && start <= crashk_res.end;
}
/* Values we need to export to the second kernel via the device tree. */
static phys_addr_t kernel_end;
static phys_addr_t crashk_base;
static phys_addr_t crashk_size;
static unsigned long long mem_limit;
static struct property kernel_end_prop = {
.name = "linux,kernel-end",
.length = sizeof(phys_addr_t),
.value = &kernel_end,
};
static struct property crashk_base_prop = {
.name = "linux,crashkernel-base",
.length = sizeof(phys_addr_t),
.value = &crashk_base
};
static struct property crashk_size_prop = {
.name = "linux,crashkernel-size",
.length = sizeof(phys_addr_t),
.value = &crashk_size,
};
static struct property memory_limit_prop = {
.name = "linux,memory-limit",
.length = sizeof(unsigned long long),
.value = &mem_limit,
};
#define cpu_to_be_ulong __PASTE(cpu_to_be, BITS_PER_LONG)
static void __init export_crashk_values(struct device_node *node)
{
struct property *prop;
/* There might be existing crash kernel properties, but we can't
* be sure what's in them, so remove them. */
prop = of_find_property(node, "linux,crashkernel-base", NULL);
if (prop)
of_remove_property(node, prop);
prop = of_find_property(node, "linux,crashkernel-size", NULL);
if (prop)
of_remove_property(node, prop);
if (crashk_res.start != 0) {
crashk_base = cpu_to_be_ulong(crashk_res.start),
of_add_property(node, &crashk_base_prop);
crashk_size = cpu_to_be_ulong(resource_size(&crashk_res));
of_add_property(node, &crashk_size_prop);
}
/*
* memory_limit is required by the kexec-tools to limit the
* crash regions to the actual memory used.
*/
mem_limit = cpu_to_be_ulong(memory_limit);
of_update_property(node, &memory_limit_prop);
}
static int __init kexec_setup(void)
{
struct device_node *node;
struct property *prop;
node = of_find_node_by_path("/chosen");
if (!node)
return -ENOENT;
/* remove any stale properties so ours can be found */
prop = of_find_property(node, kernel_end_prop.name, NULL);
if (prop)
of_remove_property(node, prop);
/* information needed by userspace when using default_machine_kexec */
kernel_end = cpu_to_be_ulong(__pa(_end));
of_add_property(node, &kernel_end_prop);
export_crashk_values(node);
of_node_put(node);
return 0;
}
late_initcall(kexec_setup);