#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/kexec.h>
-#include <linux/spinlock.h>
+#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/highmem.h>
#include <linux/syscalls.h>
#include <linux/hardirq.h>
#include <linux/elf.h>
#include <linux/elfcore.h>
-#include <linux/utsrelease.h>
+#include <generated/utsrelease.h>
#include <linux/utsname.h>
#include <linux/numa.h>
+#include <linux/suspend.h>
+#include <linux/device.h>
+#include <linux/freezer.h>
+#include <linux/pm.h>
+#include <linux/cpu.h>
+#include <linux/console.h>
+#include <linux/vmalloc.h>
+#include <linux/swap.h>
+#include <linux/kmsg_dump.h>
#include <asm/page.h>
#include <asm/uaccess.h>
#include <asm/sections.h>
/* Per cpu memory for storing cpu states in case of system crash. */
-note_buf_t* crash_notes;
+note_buf_t __percpu *crash_notes;
/* vmcoreinfo stuff */
-unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
+static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
size_t vmcoreinfo_size;
size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
*
* The code for the transition from the current kernel to the
* the new kernel is placed in the control_code_buffer, whose size
- * is given by KEXEC_CONTROL_CODE_SIZE. In the best case only a single
+ * is given by KEXEC_CONTROL_PAGE_SIZE. In the best case only a single
* page of memory is necessary, but some architectures require more.
* Because this memory must be identity mapped in the transition from
* virtual to physical addresses it must live in the range
*/
result = -ENOMEM;
image->control_code_page = kimage_alloc_control_pages(image,
- get_order(KEXEC_CONTROL_CODE_SIZE));
+ get_order(KEXEC_CONTROL_PAGE_SIZE));
if (!image->control_code_page) {
printk(KERN_ERR "Could not allocate control_code_buffer\n");
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)
*/
result = -ENOMEM;
image->control_code_page = kimage_alloc_control_pages(image,
- get_order(KEXEC_CONTROL_CODE_SIZE));
+ get_order(KEXEC_CONTROL_PAGE_SIZE));
if (!image->control_code_page) {
printk(KERN_ERR "Could not allocate control_code_buffer\n");
goto out;
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) \
*old = addr | (*old & ~PAGE_MASK);
/* The old page I have found cannot be a
- * destination page, so return it.
+ * destination page, so return it if it's
+ * gfp_flags honor the ones passed in.
*/
+ if (!(gfp_mask & __GFP_HIGHMEM) &&
+ PageHighMem(old_page)) {
+ kimage_free_pages(old_page);
+ continue;
+ }
addr = old_addr;
page = old_page;
break;
*/
struct kimage *kexec_image;
struct kimage *kexec_crash_image;
-/*
- * A home grown binary mutex.
- * Nothing can wait so this mutex is safe to use
- * in interrupt context :)
- */
-static int kexec_lock;
-asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
- struct kexec_segment __user *segments,
- unsigned long flags)
+static DEFINE_MUTEX(kexec_mutex);
+
+SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
+ struct kexec_segment __user *, segments, unsigned long, flags)
{
struct kimage **dest_image, *image;
- int locked;
int result;
/* We only trust the superuser with rebooting the system. */
*
* KISS: always take the mutex.
*/
- locked = xchg(&kexec_lock, 1);
- if (locked)
+ if (!mutex_trylock(&kexec_mutex))
return -EBUSY;
dest_image = &kexec_image;
if (result)
goto out;
+ if (flags & KEXEC_PRESERVE_CONTEXT)
+ image->preserve_context = 1;
result = machine_kexec_prepare(image);
if (result)
goto out;
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);
out:
- locked = xchg(&kexec_lock, 0); /* Release the mutex */
- BUG_ON(!locked);
+ mutex_unlock(&kexec_mutex);
kimage_free(image);
return result;
void crash_kexec(struct pt_regs *regs)
{
- int locked;
-
-
- /* Take the kexec_lock here to prevent sys_kexec_load
+ /* Take the kexec_mutex here to prevent sys_kexec_load
* running on one cpu from replacing the crash kernel
* we are using after a panic on a different cpu.
*
* of memory the xchg(&kexec_crash_image) would be
* sufficient. But since I reuse the memory...
*/
- locked = xchg(&kexec_lock, 1);
- if (!locked) {
+ if (mutex_trylock(&kexec_mutex)) {
if (kexec_crash_image) {
struct pt_regs fixed_regs;
+
+ kmsg_dump(KMSG_DUMP_KEXEC);
+
crash_setup_regs(&fixed_regs, regs);
crash_save_vmcoreinfo();
machine_crash_shutdown(&fixed_regs);
machine_kexec(kexec_crash_image);
}
- locked = xchg(&kexec_lock, 0);
- BUG_ON(!locked);
+ mutex_unlock(&kexec_mutex);
}
}
+size_t crash_get_memory_size(void)
+{
+ size_t size;
+ mutex_lock(&kexec_mutex);
+ size = crashk_res.end - crashk_res.start + 1;
+ mutex_unlock(&kexec_mutex);
+ return size;
+}
+
+static void free_reserved_phys_range(unsigned long begin, unsigned long end)
+{
+ unsigned long addr;
+
+ for (addr = begin; addr < end; addr += PAGE_SIZE) {
+ ClearPageReserved(pfn_to_page(addr >> PAGE_SHIFT));
+ init_page_count(pfn_to_page(addr >> PAGE_SHIFT));
+ free_page((unsigned long)__va(addr));
+ totalram_pages++;
+ }
+}
+
+int crash_shrink_memory(unsigned long new_size)
+{
+ int ret = 0;
+ unsigned long start, end;
+
+ mutex_lock(&kexec_mutex);
+
+ if (kexec_crash_image) {
+ ret = -ENOENT;
+ goto unlock;
+ }
+ start = crashk_res.start;
+ end = crashk_res.end;
+
+ if (new_size >= end - start + 1) {
+ ret = -EINVAL;
+ if (new_size == end - start + 1)
+ ret = 0;
+ goto unlock;
+ }
+
+ start = roundup(start, PAGE_SIZE);
+ end = roundup(start + new_size, PAGE_SIZE);
+
+ free_reserved_phys_range(end, crashk_res.end);
+
+ if (start == end)
+ release_resource(&crashk_res);
+ crashk_res.end = end - 1;
+
+unlock:
+ mutex_unlock(&kexec_mutex);
+ return ret;
+}
+
static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data,
size_t data_len)
{
struct elf_prstatus prstatus;
u32 *buf;
- if ((cpu < 0) || (cpu >= NR_CPUS))
+ if ((cpu < 0) || (cpu >= nr_cpu_ids))
return;
/* Using ELF notes here is opportunistic.
return;
memset(&prstatus, 0, sizeof(prstatus));
prstatus.pr_pid = current->pid;
- elf_core_copy_regs(&prstatus.pr_reg, regs);
+ elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
&prstatus, sizeof(prstatus));
final_note(buf);
} while (*cur++ == ',');
if (*crash_size > 0) {
- while (*cur != ' ' && *cur != '@')
+ while (*cur && *cur != ' ' && *cur != '@')
cur++;
if (*cur == '@') {
cur++;
VMCOREINFO_SYMBOL(node_online_map);
VMCOREINFO_SYMBOL(swapper_pg_dir);
VMCOREINFO_SYMBOL(_stext);
+ VMCOREINFO_SYMBOL(vmlist);
#ifndef CONFIG_NEED_MULTIPLE_NODES
VMCOREINFO_SYMBOL(mem_map);
VMCOREINFO_OFFSET(free_area, free_list);
VMCOREINFO_OFFSET(list_head, next);
VMCOREINFO_OFFSET(list_head, prev);
+ VMCOREINFO_OFFSET(vm_struct, addr);
VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
+ log_buf_kexec_setup();
VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
VMCOREINFO_NUMBER(NR_FREE_PAGES);
VMCOREINFO_NUMBER(PG_lru);
}
module_init(crash_save_vmcoreinfo_init)
+
+/*
+ * 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 (!mutex_trylock(&kexec_mutex))
+ return -EBUSY;
+ if (!kexec_image) {
+ error = -EINVAL;
+ goto Unlock;
+ }
+
+#ifdef CONFIG_KEXEC_JUMP
+ if (kexec_image->preserve_context) {
+ mutex_lock(&pm_mutex);
+ pm_prepare_console();
+ error = freeze_processes();
+ if (error) {
+ error = -EBUSY;
+ goto Restore_console;
+ }
+ suspend_console();
+ error = dpm_suspend_start(PMSG_FREEZE);
+ if (error)
+ goto Resume_console;
+ /* At this point, dpm_suspend_start() has been called,
+ * but *not* dpm_suspend_noirq(). We *must* call
+ * dpm_suspend_noirq() 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 = dpm_suspend_noirq(PMSG_FREEZE);
+ if (error)
+ goto Resume_devices;
+ error = disable_nonboot_cpus();
+ if (error)
+ goto Enable_cpus;
+ local_irq_disable();
+ /* Suspend system devices */
+ error = sysdev_suspend(PMSG_FREEZE);
+ if (error)
+ goto Enable_irqs;
+ } else
+#endif
+ {
+ kernel_restart_prepare(NULL);
+ printk(KERN_EMERG "Starting new kernel\n");
+ machine_shutdown();
+ }
+
+ machine_kexec(kexec_image);
+
+#ifdef CONFIG_KEXEC_JUMP
+ if (kexec_image->preserve_context) {
+ sysdev_resume();
+ Enable_irqs:
+ local_irq_enable();
+ Enable_cpus:
+ enable_nonboot_cpus();
+ dpm_resume_noirq(PMSG_RESTORE);
+ Resume_devices:
+ dpm_resume_end(PMSG_RESTORE);
+ Resume_console:
+ resume_console();
+ thaw_processes();
+ Restore_console:
+ pm_restore_console();
+ mutex_unlock(&pm_mutex);
+ }
+#endif
+
+ Unlock:
+ mutex_unlock(&kexec_mutex);
+ return error;
+}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff