RE: [PATCH 1/2 v5] x86/kdump: always reserve the low 1MiB when the crashkernel option is specified
From: d.hatayama@xxxxxxxxxxx
Date: Thu Oct 24 2019 - 21:46:16 EST
> -----Original Message-----
> From: lijiang [mailto:lijiang@xxxxxxxxxx]
> Sent: Friday, October 25, 2019 10:31 AM
> To: Simon Horman <horms@xxxxxxxxxxxx>; Hatayama, Daisuke/çå åè
> <d.hatayama@xxxxxxxxxxx>
> Cc: linux-kernel@xxxxxxxxxxxxxxx; jgross@xxxxxxxx; Thomas.Lendacky@xxxxxxx;
> bhe@xxxxxxxxxx; x86@xxxxxxxxxx; kexec@xxxxxxxxxxxxxxxxxxx;
> dhowells@xxxxxxxxxx; mingo@xxxxxxxxxx; bp@xxxxxxxxx; ebiederm@xxxxxxxxxxxx;
> hpa@xxxxxxxxx; tglx@xxxxxxxxxxxxx; dyoung@xxxxxxxxxx; vgoyal@xxxxxxxxxx
> Subject: Re: [PATCH 1/2 v5] x86/kdump: always reserve the low 1MiB when the
> crashkernel option is specified
>
> å 2019å10æ24æ 19:33, lijiang åé:
> > å 2019å10æ24æ 18:07, Simon Horman åé:
> >> Hi Linbo,
> >>
> >> thanks for your patch.
> >>
> >> On Wed, Oct 23, 2019 at 10:19:11PM +0800, Lianbo Jiang wrote:
> >>> Kdump kernel will reuse the first 640k region because the real mode
> >>> trampoline has to work in this area. When the vmcore is dumped, the
> >>> old memory in this area may be accessed, therefore, kernel has to
> >>> copy the contents of the first 640k area to a backup region so that
> >>> kdump kernel can read the old memory from the backup area of the
> >>> first 640k area, which is done in the purgatory().
> >>>
> >>> But, the current handling of copying the first 640k area runs into
> >>> problems when SME is enabled, kernel does not properly copy these
> >>> old memory to the backup area in the purgatory(), thereby, kdump
> >>> kernel reads out the encrypted contents, because the kdump kernel
> >>> must access the first kernel's memory with the encryption bit set
> >>> when SME is enabled in the first kernel. Please refer to this link:
> >>>
> >>> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=204793
> >>>
> >>> Finally, it causes the following errors, and the crash tool gets
> >>> invalid pointers when parsing the vmcore.
> >>>
> >>> crash> kmem -s|grep -i invalid
> >>> kmem: dma-kmalloc-512: slab:ffffd77680001c00 invalid
> freepointer:a6086ac099f0c5a4
> >>> kmem: dma-kmalloc-512: slab:ffffd77680001c00 invalid
> freepointer:a6086ac099f0c5a4
> >>> crash>
> >>>
> >>> To avoid the above errors, when the crashkernel option is specified,
> >>> lets reserve the remaining low 1MiB memory(after reserving real mode
> >>> memory) so that the allocated memory does not fall into the low 1MiB
> >>> area, which makes us not to copy the first 640k content to a backup
> >>> region in purgatory(). This indicates that it does not need to be
> >>> included in crash dumps or used for anything except the processor
> >>> trampolines that must live in the low 1MiB.
> >>>
> >>> Signed-off-by: Lianbo Jiang <lijiang@xxxxxxxxxx>
> >>> ---
> >>> BTW:I also tried to fix the above problem in purgatory(), but there
> >>> are too many restricts in purgatory() context, for example: i can't
> >>> allocate new memory to create the identity mapping page table for
> >>> SME situation.
> >>>
> >>> Currently, there are two places where the first 640k area is needed,
> >>> the first one is in the find_trampoline_placement(), another one is
> >>> in the reserve_real_mode(), and their content doesn't matter.
> >>>
> >>> In addition, also need to clean all the code related to the backup
> >>> region later.
> >>>
> >>> arch/x86/realmode/init.c | 2 ++
> >>> include/linux/kexec.h | 2 ++
> >>> kernel/kexec_core.c | 13 +++++++++++++
> >>> 3 files changed, 17 insertions(+)
> >>>
> >>> diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
> >>> index 7dce39c8c034..064cc79a015d 100644
> >>> --- a/arch/x86/realmode/init.c
> >>> +++ b/arch/x86/realmode/init.c
> >>> @@ -3,6 +3,7 @@
> >>> #include <linux/slab.h>
> >>> #include <linux/memblock.h>
> >>> #include <linux/mem_encrypt.h>
> >>> +#include <linux/kexec.h>
> >>>
> >>> #include <asm/set_memory.h>
> >>> #include <asm/pgtable.h>
> >>> @@ -34,6 +35,7 @@ void __init reserve_real_mode(void)
> >>>
> >>> memblock_reserve(mem, size);
> >>> set_real_mode_mem(mem);
> >>> + kexec_reserve_low_1MiB();
> >>> }
> >>>
> >>> static void __init setup_real_mode(void)
> >>> diff --git a/include/linux/kexec.h b/include/linux/kexec.h
> >>> index 1776eb2e43a4..30acf1d738bc 100644
> >>> --- a/include/linux/kexec.h
> >>> +++ b/include/linux/kexec.h
> >>> @@ -306,6 +306,7 @@ extern void __crash_kexec(struct pt_regs *);
> >>> extern void crash_kexec(struct pt_regs *);
> >>> int kexec_should_crash(struct task_struct *);
> >>> int kexec_crash_loaded(void);
> >>> +void __init kexec_reserve_low_1MiB(void);
> >>> void crash_save_cpu(struct pt_regs *regs, int cpu);
> >>> extern int kimage_crash_copy_vmcoreinfo(struct kimage *image);
> >>>
> >>> @@ -397,6 +398,7 @@ static inline void __crash_kexec(struct pt_regs *regs)
> { }
> >>> static inline void crash_kexec(struct pt_regs *regs) { }
> >>> static inline int kexec_should_crash(struct task_struct *p) { return 0; }
> >>> static inline int kexec_crash_loaded(void) { return 0; }
> >>> +static inline void __init kexec_reserve_low_1MiB(void) { }
> >>> #define kexec_in_progress false
> >>> #endif /* CONFIG_KEXEC_CORE */
> >>>
> >>> diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
> >>> index 15d70a90b50d..5bd89f1fee42 100644
> >>> --- a/kernel/kexec_core.c
> >>> +++ b/kernel/kexec_core.c
> >>> @@ -37,6 +37,7 @@
> >>> #include <linux/compiler.h>
> >>> #include <linux/hugetlb.h>
> >>> #include <linux/frame.h>
> >>> +#include <linux/memblock.h>
> >>>
> >>> #include <asm/page.h>
> >>> #include <asm/sections.h>
> >>> @@ -70,6 +71,18 @@ struct resource crashk_low_res = {
> >>> .desc = IORES_DESC_CRASH_KERNEL
> >>> };
> >>>
> >>> +/*
> >>> + * When the crashkernel option is specified, only use the low
> >>> + * 1MiB for the real mode trampoline.
> >>> + */
> >>> +void __init kexec_reserve_low_1MiB(void)
> >>> +{
> >>> + if (strstr(boot_command_line, "crashkernel=")) {
> >>
> >> Could you comment on the issue of using strstr which
> >> was raised by Hatayama-san in response to an earlier revision
> >> of this patch?
> >>
> >
> > Thank you, Simon and Hatayama-san. Lets talk about it here.
> >
> >> strstr() matches for example,
> ANYEXTRACHARACTERScrashkernel=ANYEXTRACHARACTERS.
> >>
> >> Is it enough to use cmdline_find_option_bool()?
> >>
> >
> > The cmdline_find_option_bool() will find a boolean option, but the
> crashkernel option
> > is not a boolean option, maybe it looks odd. So, should we use the
> cmdline_find_option()
> > better?
> >
> > +#include <asm/cmdline.h>
> >
> > void __init kexec_reserve_low_1MiB(void)
> > {
> > - if (strstr(boot_command_line, "crashkernel=")) {
> > + char buffer[4];
> > +
> > + if (cmdline_find_option(boot_command_line, "crashkernel=",
> > + buffer, sizeof(buffer))) {
> Maybe it is simpler as follow:
>
> + if (cmdline_find_option(boot_command_line, "crashkernel=",
> + NULL, 0)) {
>
> Any thoughts?
I wrote a test kernel module and it works as expected.
static int __init testmod_init(void)
{
char cmdline1[] = "x y crashkernel z";
char cmdline2[] = "x y crashkernel=128M z";
printk("\"1: %d\n",
cmdline_find_option_bool(cmdline1, "crashkernel"));
printk("\"2: %d\n",
cmdline_find_option_bool(cmdline1, "crashkernel="));
printk("\"3: %d\n",
cmdline_find_option_bool(cmdline2, "crashkernel"));
printk("\"4: %d\n",
cmdline_find_option_bool(cmdline2, "crashkernel="));
printk("\"5: %d\n",
cmdline_find_option(cmdline1, "crashkernel", NULL, 0));
printk("\"6: %d\n",
cmdline_find_option(cmdline1, "crashkernel=", NULL, 0));
printk("\"7: %d\n",
cmdline_find_option(cmdline2, "crashkernel", NULL, 0));
printk("\"8: %d\n",
cmdline_find_option(cmdline2, "crashkernel=", NULL, 0));
return 0;
}
# dmesg | tail
[85335.355459] "7: 4
[85335.356923] "8: -1
[85349.763849] "1: 5
[85349.765128] "2: 0
[85349.766159] "3: 0
[85349.767145] "4: 0
[85349.768157] "5: -1
[85349.769259] "6: -1
[85349.770423] "7: 4
[85349.771512] "8: -1
>
> Thanks
> Lianbo
> > memblock_reserve(0, 1<<20);
> > pr_info("Reserving the low 1MiB of memory for
> crashkernel\n");
> > }
> >
> > And here, no need to parse the arguments of crashkernel(sometimes, which has
> a
> > complicated syntax), so the size of buffer should be enough. What's your
> opinion?
> >
> > Thanks
> > Lianbo
> >
> >> Thanks in advance!
> >>
> >>> + memblock_reserve(0, 1<<20);
> >>> + pr_info("Reserving the low 1MiB of memory for
> crashkernel\n");
> >>> + }
> >>> +}
> >>> +
> >>> int kexec_should_crash(struct task_struct *p)
> >>> {
> >>> /*
> >>> --
> >>> 2.17.1
> >>>
> >>>
> >>> _______________________________________________
> >>> kexec mailing list
> >>> kexec@xxxxxxxxxxxxxxxxxxx
> >>> http://lists.infradead.org/mailman/listinfo/kexec
> >>>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/string.h>
#include <linux/ctype.h>
#include <asm/setup.h>
MODULE_AUTHOR("FUJITSU LIMITED");
MODULE_LICENSE("GPL v2");
static inline int myisspace(u8 c)
{
return c <= ' '; /* Close enough approximation */
}
/**
* Find a boolean option (like quiet,noapic,nosmp....)
*
* @cmdline: the cmdline string
* @option: option string to look for
*
* Returns the position of that @option (starts counting with 1)
* or 0 on not found. @option will only be found if it is found
* as an entire word in @cmdline. For instance, if @option="car"
* then a cmdline which contains "cart" will not match.
*/
static int
__cmdline_find_option_bool(const char *cmdline, int max_cmdline_size,
const char *option)
{
char c;
int pos = 0, wstart = 0;
const char *opptr = NULL;
enum {
st_wordstart = 0, /* Start of word/after whitespace */
st_wordcmp, /* Comparing this word */
st_wordskip, /* Miscompare, skip */
} state = st_wordstart;
if (!cmdline)
return -1; /* No command line */
/*
* This 'pos' check ensures we do not overrun
* a non-NULL-terminated 'cmdline'
*/
while (pos < max_cmdline_size) {
c = *(char *)cmdline++;
pos++;
switch (state) {
case st_wordstart:
if (!c)
return 0;
else if (myisspace(c))
break;
state = st_wordcmp;
opptr = option;
wstart = pos;
/* fall through */
case st_wordcmp:
if (!*opptr) {
/*
* We matched all the way to the end of the
* option we were looking for. If the
* command-line has a space _or_ ends, then
* we matched!
*/
if (!c || myisspace(c))
return wstart;
/*
* We hit the end of the option, but _not_
* the end of a word on the cmdline. Not
* a match.
*/
} else if (!c) {
/*
* Hit the NULL terminator on the end of
* cmdline.
*/
return 0;
} else if (c == *opptr++) {
/*
* We are currently matching, so continue
* to the next character on the cmdline.
*/
break;
}
state = st_wordskip;
/* fall through */
case st_wordskip:
if (!c)
return 0;
else if (myisspace(c))
state = st_wordstart;
break;
}
}
return 0; /* Buffer overrun */
}
/*
* Find a non-boolean option (i.e. option=argument). In accordance with
* standard Linux practice, if this option is repeated, this returns the
* last instance on the command line.
*
* @cmdline: the cmdline string
* @max_cmdline_size: the maximum size of cmdline
* @option: option string to look for
* @buffer: memory buffer to return the option argument
* @bufsize: size of the supplied memory buffer
*
* Returns the length of the argument (regardless of if it was
* truncated to fit in the buffer), or -1 on not found.
*/
static int
__cmdline_find_option(const char *cmdline, int max_cmdline_size,
const char *option, char *buffer, int bufsize)
{
char c;
int pos = 0, len = -1;
const char *opptr = NULL;
char *bufptr = buffer;
enum {
st_wordstart = 0, /* Start of word/after whitespace */
st_wordcmp, /* Comparing this word */
st_wordskip, /* Miscompare, skip */
st_bufcpy, /* Copying this to buffer */
} state = st_wordstart;
if (!cmdline)
return -1; /* No command line */
/*
* This 'pos' check ensures we do not overrun
* a non-NULL-terminated 'cmdline'
*/
while (pos++ < max_cmdline_size) {
c = *(char *)cmdline++;
if (!c)
break;
switch (state) {
case st_wordstart:
if (myisspace(c))
break;
state = st_wordcmp;
opptr = option;
/* fall through */
case st_wordcmp:
if ((c == '=') && !*opptr) {
/*
* We matched all the way to the end of the
* option we were looking for, prepare to
* copy the argument.
*/
len = 0;
bufptr = buffer;
state = st_bufcpy;
break;
} else if (c == *opptr++) {
/*
* We are currently matching, so continue
* to the next character on the cmdline.
*/
break;
}
state = st_wordskip;
/* fall through */
case st_wordskip:
if (myisspace(c))
state = st_wordstart;
break;
case st_bufcpy:
if (myisspace(c)) {
state = st_wordstart;
} else {
/*
* Increment len, but don't overrun the
* supplied buffer and leave room for the
* NULL terminator.
*/
if (++len < bufsize)
*bufptr++ = c;
}
break;
}
}
if (bufsize)
*bufptr = '\0';
return len;
}
int cmdline_find_option_bool(const char *cmdline, const char *option)
{
return __cmdline_find_option_bool(cmdline, COMMAND_LINE_SIZE, option);
}
int cmdline_find_option(const char *cmdline, const char *option, char *buffer,
int bufsize)
{
return __cmdline_find_option(cmdline, COMMAND_LINE_SIZE, option,
buffer, bufsize);
}
static int __init testmod_init(void)
{
char cmdline1[] = "x y crashkernel z";
char cmdline2[] = "x y crashkernel=128M z";
printk("\"1: %d\n",
cmdline_find_option_bool(cmdline1, "crashkernel"));
printk("\"2: %d\n",
cmdline_find_option_bool(cmdline1, "crashkernel="));
printk("\"3: %d\n",
cmdline_find_option_bool(cmdline2, "crashkernel"));
printk("\"4: %d\n",
cmdline_find_option_bool(cmdline2, "crashkernel="));
printk("\"5: %d\n",
cmdline_find_option(cmdline1, "crashkernel", NULL, 0));
printk("\"6: %d\n",
cmdline_find_option(cmdline1, "crashkernel=", NULL, 0));
printk("\"7: %d\n",
cmdline_find_option(cmdline2, "crashkernel", NULL, 0));
printk("\"8: %d\n",
cmdline_find_option(cmdline2, "crashkernel=", NULL, 0));
return 0;
}
static void __exit testmod_exit(void)
{
}
module_init(testmod_init);
module_exit(testmod_exit);
Attachment:
Makefile
Description: Makefile