Merge branch 'v4.4/topic/kexec-kdump' into linux-linaro-lsk-v4.4

This commit is contained in:
Alex Shi 2017-10-25 13:27:31 +08:00
commit fb596ec8d3
7 changed files with 180 additions and 119 deletions

View File

@ -15,15 +15,16 @@
define bttnobp
set $tasks_off=((size_t)&((struct task_struct *)0)->tasks)
set $pid_off=((size_t)&((struct task_struct *)0)->pids[1].pid_list.next)
set $pid_off=((size_t)&((struct task_struct *)0)->thread_group.next)
set $init_t=&init_task
set $next_t=(((char *)($init_t->tasks).next) - $tasks_off)
set var $stacksize = sizeof(union thread_union)
while ($next_t != $init_t)
set $next_t=(struct task_struct *)$next_t
printf "\npid %d; comm %s:\n", $next_t.pid, $next_t.comm
printf "===================\n"
set var $stackp = $next_t.thread.esp
set var $stack_top = ($stackp & ~4095) + 4096
set var $stackp = $next_t.thread.sp
set var $stack_top = ($stackp & ~($stacksize - 1)) + $stacksize
while ($stackp < $stack_top)
if (*($stackp) > _stext && *($stackp) < _sinittext)
@ -31,13 +32,13 @@ define bttnobp
end
set $stackp += 4
end
set $next_th=(((char *)$next_t->pids[1].pid_list.next) - $pid_off)
set $next_th=(((char *)$next_t->thread_group.next) - $pid_off)
while ($next_th != $next_t)
set $next_th=(struct task_struct *)$next_th
printf "\npid %d; comm %s:\n", $next_t.pid, $next_t.comm
printf "===================\n"
set var $stackp = $next_t.thread.esp
set var $stack_top = ($stackp & ~4095) + 4096
set var $stackp = $next_t.thread.sp
set var $stack_top = ($stackp & ~($stacksize - 1)) + stacksize
while ($stackp < $stack_top)
if (*($stackp) > _stext && *($stackp) < _sinittext)
@ -45,7 +46,7 @@ define bttnobp
end
set $stackp += 4
end
set $next_th=(((char *)$next_th->pids[1].pid_list.next) - $pid_off)
set $next_th=(((char *)$next_th->thread_group.next) - $pid_off)
end
set $next_t=(char *)($next_t->tasks.next) - $tasks_off
end
@ -54,42 +55,44 @@ document bttnobp
dump all thread stack traces on a kernel compiled with !CONFIG_FRAME_POINTER
end
define btthreadstack
set var $pid_task = $arg0
printf "\npid %d; comm %s:\n", $pid_task.pid, $pid_task.comm
printf "task struct: "
print $pid_task
printf "===================\n"
set var $stackp = $pid_task.thread.sp
set var $stacksize = sizeof(union thread_union)
set var $stack_top = ($stackp & ~($stacksize - 1)) + $stacksize
set var $stack_bot = ($stackp & ~($stacksize - 1))
set $stackp = *((unsigned long *) $stackp)
while (($stackp < $stack_top) && ($stackp > $stack_bot))
set var $addr = *(((unsigned long *) $stackp) + 1)
info symbol $addr
set $stackp = *((unsigned long *) $stackp)
end
end
document btthreadstack
dump a thread stack using the given task structure pointer
end
define btt
set $tasks_off=((size_t)&((struct task_struct *)0)->tasks)
set $pid_off=((size_t)&((struct task_struct *)0)->pids[1].pid_list.next)
set $pid_off=((size_t)&((struct task_struct *)0)->thread_group.next)
set $init_t=&init_task
set $next_t=(((char *)($init_t->tasks).next) - $tasks_off)
while ($next_t != $init_t)
set $next_t=(struct task_struct *)$next_t
printf "\npid %d; comm %s:\n", $next_t.pid, $next_t.comm
printf "===================\n"
set var $stackp = $next_t.thread.esp
set var $stack_top = ($stackp & ~4095) + 4096
set var $stack_bot = ($stackp & ~4095)
btthreadstack $next_t
set $stackp = *($stackp)
while (($stackp < $stack_top) && ($stackp > $stack_bot))
set var $addr = *($stackp + 4)
info symbol $addr
set $stackp = *($stackp)
end
set $next_th=(((char *)$next_t->pids[1].pid_list.next) - $pid_off)
set $next_th=(((char *)$next_t->thread_group.next) - $pid_off)
while ($next_th != $next_t)
set $next_th=(struct task_struct *)$next_th
printf "\npid %d; comm %s:\n", $next_t.pid, $next_t.comm
printf "===================\n"
set var $stackp = $next_t.thread.esp
set var $stack_top = ($stackp & ~4095) + 4096
set var $stack_bot = ($stackp & ~4095)
set $stackp = *($stackp)
while (($stackp < $stack_top) && ($stackp > $stack_bot))
set var $addr = *($stackp + 4)
info symbol $addr
set $stackp = *($stackp)
end
set $next_th=(((char *)$next_th->pids[1].pid_list.next) - $pid_off)
btthreadstack $next_th
set $next_th=(((char *)$next_th->thread_group.next) - $pid_off)
end
set $next_t=(char *)($next_t->tasks.next) - $tasks_off
end
@ -101,7 +104,7 @@ end
define btpid
set var $pid = $arg0
set $tasks_off=((size_t)&((struct task_struct *)0)->tasks)
set $pid_off=((size_t)&((struct task_struct *)0)->pids[1].pid_list.next)
set $pid_off=((size_t)&((struct task_struct *)0)->thread_group.next)
set $init_t=&init_task
set $next_t=(((char *)($init_t->tasks).next) - $tasks_off)
set var $pid_task = 0
@ -113,29 +116,18 @@ define btpid
set $pid_task = $next_t
end
set $next_th=(((char *)$next_t->pids[1].pid_list.next) - $pid_off)
set $next_th=(((char *)$next_t->thread_group.next) - $pid_off)
while ($next_th != $next_t)
set $next_th=(struct task_struct *)$next_th
if ($next_th.pid == $pid)
set $pid_task = $next_th
end
set $next_th=(((char *)$next_th->pids[1].pid_list.next) - $pid_off)
set $next_th=(((char *)$next_th->thread_group.next) - $pid_off)
end
set $next_t=(char *)($next_t->tasks.next) - $tasks_off
end
printf "\npid %d; comm %s:\n", $pid_task.pid, $pid_task.comm
printf "===================\n"
set var $stackp = $pid_task.thread.esp
set var $stack_top = ($stackp & ~4095) + 4096
set var $stack_bot = ($stackp & ~4095)
set $stackp = *($stackp)
while (($stackp < $stack_top) && ($stackp > $stack_bot))
set var $addr = *($stackp + 4)
info symbol $addr
set $stackp = *($stackp)
end
btthreadstack $pid_task
end
document btpid
backtrace of pid
@ -145,7 +137,7 @@ end
define trapinfo
set var $pid = $arg0
set $tasks_off=((size_t)&((struct task_struct *)0)->tasks)
set $pid_off=((size_t)&((struct task_struct *)0)->pids[1].pid_list.next)
set $pid_off=((size_t)&((struct task_struct *)0)->thread_group.next)
set $init_t=&init_task
set $next_t=(((char *)($init_t->tasks).next) - $tasks_off)
set var $pid_task = 0
@ -157,13 +149,13 @@ define trapinfo
set $pid_task = $next_t
end
set $next_th=(((char *)$next_t->pids[1].pid_list.next) - $pid_off)
set $next_th=(((char *)$next_t->thread_group.next) - $pid_off)
while ($next_th != $next_t)
set $next_th=(struct task_struct *)$next_th
if ($next_th.pid == $pid)
set $pid_task = $next_th
end
set $next_th=(((char *)$next_th->pids[1].pid_list.next) - $pid_off)
set $next_th=(((char *)$next_th->thread_group.next) - $pid_off)
end
set $next_t=(char *)($next_t->tasks.next) - $tasks_off
end

View File

@ -83,13 +83,13 @@ static int machine_kdump_pm_cb(struct notifier_block *nb, unsigned long action,
switch (action) {
case PM_SUSPEND_PREPARE:
case PM_HIBERNATION_PREPARE:
if (crashk_res.start)
crash_map_reserved_pages();
if (kexec_crash_image)
arch_kexec_unprotect_crashkres();
break;
case PM_POST_SUSPEND:
case PM_POST_HIBERNATION:
if (crashk_res.start)
crash_unmap_reserved_pages();
if (kexec_crash_image)
arch_kexec_protect_crashkres();
break;
default:
return NOTIFY_DONE;
@ -100,6 +100,8 @@ static int machine_kdump_pm_cb(struct notifier_block *nb, unsigned long action,
static int __init machine_kdump_pm_init(void)
{
pm_notifier(machine_kdump_pm_cb, 0);
/* Create initial mapping for crashkernel memory */
arch_kexec_unprotect_crashkres();
return 0;
}
arch_initcall(machine_kdump_pm_init);
@ -134,6 +136,8 @@ static int kdump_csum_valid(struct kimage *image)
#endif
}
#ifdef CONFIG_CRASH_DUMP
/*
* Map or unmap crashkernel memory
*/
@ -155,21 +159,25 @@ static void crash_map_pages(int enable)
}
/*
* Map crashkernel memory
* Unmap crashkernel memory
*/
void crash_map_reserved_pages(void)
void arch_kexec_protect_crashkres(void)
{
crash_map_pages(1);
if (crashk_res.end)
crash_map_pages(0);
}
/*
* Unmap crashkernel memory
* Map crashkernel memory
*/
void crash_unmap_reserved_pages(void)
void arch_kexec_unprotect_crashkres(void)
{
crash_map_pages(0);
if (crashk_res.end)
crash_map_pages(1);
}
#endif
/*
* Give back memory to hypervisor before new kdump is loaded
*/

View File

@ -536,3 +536,48 @@ int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr,
return -ENOEXEC;
}
#endif /* CONFIG_KEXEC_FILE */
static int
kexec_mark_range(unsigned long start, unsigned long end, bool protect)
{
struct page *page;
unsigned int nr_pages;
/*
* For physical range: [start, end]. We must skip the unassigned
* crashk resource with zero-valued "end" member.
*/
if (!end || start > end)
return 0;
page = pfn_to_page(start >> PAGE_SHIFT);
nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1;
if (protect)
return set_pages_ro(page, nr_pages);
else
return set_pages_rw(page, nr_pages);
}
static void kexec_mark_crashkres(bool protect)
{
unsigned long control;
kexec_mark_range(crashk_low_res.start, crashk_low_res.end, protect);
/* Don't touch the control code page used in crash_kexec().*/
control = PFN_PHYS(page_to_pfn(kexec_crash_image->control_code_page));
/* Control code page is located in the 2nd page. */
kexec_mark_range(crashk_res.start, control + PAGE_SIZE - 1, protect);
control += KEXEC_CONTROL_PAGE_SIZE;
kexec_mark_range(control, crashk_res.end, protect);
}
void arch_kexec_protect_crashkres(void)
{
kexec_mark_crashkres(true);
}
void arch_kexec_unprotect_crashkres(void)
{
kexec_mark_crashkres(false);
}

View File

@ -241,8 +241,6 @@ extern void crash_kexec(struct pt_regs *);
int kexec_should_crash(struct task_struct *);
void crash_save_cpu(struct pt_regs *regs, int cpu);
void crash_save_vmcoreinfo(void);
void crash_map_reserved_pages(void);
void crash_unmap_reserved_pages(void);
void arch_crash_save_vmcoreinfo(void);
__printf(1, 2)
void vmcoreinfo_append_str(const char *fmt, ...);
@ -328,6 +326,8 @@ int __weak arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr,
Elf_Shdr *sechdrs, unsigned int relsec);
int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
unsigned int relsec);
void arch_kexec_protect_crashkres(void);
void arch_kexec_unprotect_crashkres(void);
#else /* !CONFIG_KEXEC_CORE */
struct pt_regs;

View File

@ -103,6 +103,65 @@ static int kimage_alloc_init(struct kimage **rimage, unsigned long entry,
return ret;
}
static int do_kexec_load(unsigned long entry, unsigned long nr_segments,
struct kexec_segment __user *segments, unsigned long flags)
{
struct kimage **dest_image, *image;
unsigned long i;
int ret;
if (flags & KEXEC_ON_CRASH) {
dest_image = &kexec_crash_image;
if (kexec_crash_image)
arch_kexec_unprotect_crashkres();
} else {
dest_image = &kexec_image;
}
if (nr_segments == 0) {
/* Uninstall image */
kimage_free(xchg(dest_image, NULL));
return 0;
}
if (flags & KEXEC_ON_CRASH) {
/*
* Loading another kernel to switch to if this one
* crashes. Free any current crash dump kernel before
* we corrupt it.
*/
kimage_free(xchg(&kexec_crash_image, NULL));
}
ret = kimage_alloc_init(&image, entry, nr_segments, segments, flags);
if (ret)
return ret;
if (flags & KEXEC_PRESERVE_CONTEXT)
image->preserve_context = 1;
ret = machine_kexec_prepare(image);
if (ret)
goto out;
for (i = 0; i < nr_segments; i++) {
ret = kimage_load_segment(image, &image->segment[i]);
if (ret)
goto out;
}
kimage_terminate(image);
/* Install the new kernel and uninstall the old */
image = xchg(dest_image, image);
out:
if ((flags & KEXEC_ON_CRASH) && kexec_crash_image)
arch_kexec_protect_crashkres();
kimage_free(image);
return ret;
}
/*
* Exec Kernel system call: for obvious reasons only root may call it.
*
@ -127,7 +186,6 @@ static int kimage_alloc_init(struct kimage **rimage, unsigned long entry,
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 result;
/* We only trust the superuser with rebooting the system. */
@ -152,9 +210,6 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
if (nr_segments > KEXEC_SEGMENT_MAX)
return -EINVAL;
image = NULL;
result = 0;
/* Because we write directly to the reserved memory
* region when loading crash kernels we need a mutex here to
* prevent multiple crash kernels from attempting to load
@ -166,53 +221,9 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
if (!mutex_trylock(&kexec_mutex))
return -EBUSY;
dest_image = &kexec_image;
if (flags & KEXEC_ON_CRASH)
dest_image = &kexec_crash_image;
if (nr_segments > 0) {
unsigned long i;
result = do_kexec_load(entry, nr_segments, segments, flags);
if (flags & KEXEC_ON_CRASH) {
/*
* Loading another kernel to switch to if this one
* crashes. Free any current crash dump kernel before
* we corrupt it.
*/
kimage_free(xchg(&kexec_crash_image, NULL));
result = kimage_alloc_init(&image, entry, nr_segments,
segments, flags);
crash_map_reserved_pages();
} else {
/* Loading another kernel to reboot into. */
result = kimage_alloc_init(&image, entry, nr_segments,
segments, flags);
}
if (result)
goto out;
if (flags & KEXEC_PRESERVE_CONTEXT)
image->preserve_context = 1;
result = machine_kexec_prepare(image);
if (result)
goto out;
for (i = 0; i < nr_segments; i++) {
result = kimage_load_segment(image, &image->segment[i]);
if (result)
goto out;
}
kimage_terminate(image);
if (flags & KEXEC_ON_CRASH)
crash_unmap_reserved_pages();
}
/* Install the new kernel, and Uninstall the old */
image = xchg(dest_image, image);
out:
mutex_unlock(&kexec_mutex);
kimage_free(image);
return result;
}

View File

@ -926,7 +926,6 @@ int crash_shrink_memory(unsigned long new_size)
start = roundup(start, KEXEC_CRASH_MEM_ALIGN);
end = roundup(start + new_size, KEXEC_CRASH_MEM_ALIGN);
crash_map_reserved_pages();
crash_free_reserved_phys_range(end, crashk_res.end);
if ((start == end) && (crashk_res.parent != NULL))
@ -940,7 +939,6 @@ int crash_shrink_memory(unsigned long new_size)
crashk_res.end = end - 1;
insert_resource(&iomem_resource, ram_res);
crash_unmap_reserved_pages();
unlock:
mutex_unlock(&kexec_mutex);
@ -1522,13 +1520,14 @@ int kernel_kexec(void)
}
/*
* Add and remove page tables for crashkernel memory
* Protection mechanism for crashkernel reserved memory after
* the kdump kernel is loaded.
*
* Provide an empty default implementation here -- architecture
* code may override this
*/
void __weak crash_map_reserved_pages(void)
void __weak arch_kexec_protect_crashkres(void)
{}
void __weak crash_unmap_reserved_pages(void)
void __weak arch_kexec_unprotect_crashkres(void)
{}

View File

@ -327,8 +327,11 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
return -EBUSY;
dest_image = &kexec_image;
if (flags & KEXEC_FILE_ON_CRASH)
if (flags & KEXEC_FILE_ON_CRASH) {
dest_image = &kexec_crash_image;
if (kexec_crash_image)
arch_kexec_unprotect_crashkres();
}
if (flags & KEXEC_FILE_UNLOAD)
goto exchange;
@ -377,6 +380,9 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
exchange:
image = xchg(dest_image, image);
out:
if ((flags & KEXEC_FILE_ON_CRASH) && kexec_crash_image)
arch_kexec_protect_crashkres();
mutex_unlock(&kexec_mutex);
kimage_free(image);
return ret;