linux_dsm_epyc7002/kernel/ksysfs.c
Vivek Goyal 77019967f0 kdump: fix exported size of vmcoreinfo note
Right now we seem to be exporting the max data size contained inside
vmcoreinfo note.  But this does not include the size of meta data around
vmcore info data.  Like name of the note and starting and ending elf_note.

I think user space expects total size and that size is put in PT_NOTE elf
header.  Things seem to be fine so far because we are not using vmcoreinfo
note to the maximum capacity.  But as it starts filling up, to capacity,
at some point of time, problem will be visible.

I don't think user space will be broken with this change.  So there is no
need to introduce vmcoreinfo2.  This change is safe and backward
compatible.  More explanation on why this change is safe is below.

vmcoreinfo contains information about kernel which user space needs to
know to do things like filtering.  For example, various kernel config
options or information about size or offset of some data structures etc.
All this information is commmunicated to user space with an ELF note
present in ELF /proc/vmcore file.

Currently vmcoreinfo data size is 4096.  With some elf note meta data
around it, actual size is 4132 bytes.  But we are using barely 25% of that
size.  Rest is empty.  So even if we tell user space that size of ELf note
is 4096 and not 4132, nothing will be broken becase after around 1000
bytes, everything is zero anyway.

But once we start filling up the note to the capacity, and not report the
full size of note, bad things will start happening.  Either some data will
be lost or tools will be confused that they did not fine the zero note at
the end.

So I think this change is safe and should not break existing tools.

Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Cc: Ken'ichi Ohmichi <oomichi@mxs.nes.nec.co.jp>
Cc: Dan Aloni <da-x@monatomic.org>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-23 16:37:03 -08:00

238 lines
5.5 KiB
C

/*
* kernel/ksysfs.c - sysfs attributes in /sys/kernel, which
* are not related to any other subsystem
*
* Copyright (C) 2004 Kay Sievers <kay.sievers@vrfy.org>
*
* This file is release under the GPLv2
*
*/
#include <linux/kobject.h>
#include <linux/string.h>
#include <linux/sysfs.h>
#include <linux/export.h>
#include <linux/init.h>
#include <linux/kexec.h>
#include <linux/profile.h>
#include <linux/stat.h>
#include <linux/sched.h>
#include <linux/capability.h>
#define KERNEL_ATTR_RO(_name) \
static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
#define KERNEL_ATTR_RW(_name) \
static struct kobj_attribute _name##_attr = \
__ATTR(_name, 0644, _name##_show, _name##_store)
/* current uevent sequence number */
static ssize_t uevent_seqnum_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sprintf(buf, "%llu\n", (unsigned long long)uevent_seqnum);
}
KERNEL_ATTR_RO(uevent_seqnum);
/* uevent helper program, used during early boot */
static ssize_t uevent_helper_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sprintf(buf, "%s\n", uevent_helper);
}
static ssize_t uevent_helper_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
if (count+1 > UEVENT_HELPER_PATH_LEN)
return -ENOENT;
memcpy(uevent_helper, buf, count);
uevent_helper[count] = '\0';
if (count && uevent_helper[count-1] == '\n')
uevent_helper[count-1] = '\0';
return count;
}
KERNEL_ATTR_RW(uevent_helper);
#ifdef CONFIG_PROFILING
static ssize_t profiling_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sprintf(buf, "%d\n", prof_on);
}
static ssize_t profiling_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int ret;
if (prof_on)
return -EEXIST;
/*
* This eventually calls into get_option() which
* has a ton of callers and is not const. It is
* easiest to cast it away here.
*/
profile_setup((char *)buf);
ret = profile_init();
if (ret)
return ret;
ret = create_proc_profile();
if (ret)
return ret;
return count;
}
KERNEL_ATTR_RW(profiling);
#endif
#ifdef CONFIG_KEXEC
static ssize_t kexec_loaded_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sprintf(buf, "%d\n", !!kexec_image);
}
KERNEL_ATTR_RO(kexec_loaded);
static ssize_t kexec_crash_loaded_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sprintf(buf, "%d\n", !!kexec_crash_image);
}
KERNEL_ATTR_RO(kexec_crash_loaded);
static ssize_t kexec_crash_size_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sprintf(buf, "%zu\n", crash_get_memory_size());
}
static ssize_t kexec_crash_size_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
unsigned long cnt;
int ret;
if (kstrtoul(buf, 0, &cnt))
return -EINVAL;
ret = crash_shrink_memory(cnt);
return ret < 0 ? ret : count;
}
KERNEL_ATTR_RW(kexec_crash_size);
static ssize_t vmcoreinfo_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sprintf(buf, "%lx %x\n",
paddr_vmcoreinfo_note(),
(unsigned int)sizeof(vmcoreinfo_note));
}
KERNEL_ATTR_RO(vmcoreinfo);
#endif /* CONFIG_KEXEC */
/* whether file capabilities are enabled */
static ssize_t fscaps_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sprintf(buf, "%d\n", file_caps_enabled);
}
KERNEL_ATTR_RO(fscaps);
int rcu_expedited;
static ssize_t rcu_expedited_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sprintf(buf, "%d\n", rcu_expedited);
}
static ssize_t rcu_expedited_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
if (kstrtoint(buf, 0, &rcu_expedited))
return -EINVAL;
return count;
}
KERNEL_ATTR_RW(rcu_expedited);
/*
* Make /sys/kernel/notes give the raw contents of our kernel .notes section.
*/
extern const void __start_notes __attribute__((weak));
extern const void __stop_notes __attribute__((weak));
#define notes_size (&__stop_notes - &__start_notes)
static ssize_t notes_read(struct file *filp, struct kobject *kobj,
struct bin_attribute *bin_attr,
char *buf, loff_t off, size_t count)
{
memcpy(buf, &__start_notes + off, count);
return count;
}
static struct bin_attribute notes_attr = {
.attr = {
.name = "notes",
.mode = S_IRUGO,
},
.read = &notes_read,
};
struct kobject *kernel_kobj;
EXPORT_SYMBOL_GPL(kernel_kobj);
static struct attribute * kernel_attrs[] = {
&fscaps_attr.attr,
&uevent_seqnum_attr.attr,
&uevent_helper_attr.attr,
#ifdef CONFIG_PROFILING
&profiling_attr.attr,
#endif
#ifdef CONFIG_KEXEC
&kexec_loaded_attr.attr,
&kexec_crash_loaded_attr.attr,
&kexec_crash_size_attr.attr,
&vmcoreinfo_attr.attr,
#endif
&rcu_expedited_attr.attr,
NULL
};
static struct attribute_group kernel_attr_group = {
.attrs = kernel_attrs,
};
static int __init ksysfs_init(void)
{
int error;
kernel_kobj = kobject_create_and_add("kernel", NULL);
if (!kernel_kobj) {
error = -ENOMEM;
goto exit;
}
error = sysfs_create_group(kernel_kobj, &kernel_attr_group);
if (error)
goto kset_exit;
if (notes_size > 0) {
notes_attr.size = notes_size;
error = sysfs_create_bin_file(kernel_kobj, &notes_attr);
if (error)
goto group_exit;
}
return 0;
group_exit:
sysfs_remove_group(kernel_kobj, &kernel_attr_group);
kset_exit:
kobject_put(kernel_kobj);
exit:
return error;
}
core_initcall(ksysfs_init);