Commit 78a509fba9c9 ("x86/boot: Ignore NMIs during very early boot") added
empty handler in early boot stage to avoid boot failure by spurious NMIs.
Add a diagnostic message in case we need to know whether early NMIs have
occurred and/or what happened to them.
Signed-off-by: Jun'ichi Nomura <[email protected]>
Suggested-by: Borislav Petkov <[email protected]>
Suggested-by: H. Peter Anvin <[email protected]>
Link: https://lore.kernel.org/lkml/20231130103339.GCZWhlA196uRklTMNF@fat_crate.local/
diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c
--- a/arch/x86/boot/compressed/ident_map_64.c
+++ b/arch/x86/boot/compressed/ident_map_64.c
@@ -387,7 +387,10 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code)
kernel_add_identity_map(address, end);
}
+extern int spurious_nmi_count;
+
void do_boot_nmi_trap(struct pt_regs *regs, unsigned long error_code)
{
/* Empty handler to ignore NMI during early boot */
+ spurious_nmi_count++;
}
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -357,6 +357,8 @@ unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr,
return entry;
}
+int spurious_nmi_count;
+
/*
* The compressed kernel image (ZO), has been moved so that its position
* is against the end of the buffer used to hold the uncompressed kernel
@@ -493,6 +495,12 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output)
/* Disable exception handling before booting the kernel */
cleanup_exception_handling();
+ if (spurious_nmi_count) {
+ error_putstr("Spurious early NMI ignored. Number of NMIs: 0x");
+ error_puthex(spurious_nmi_count);
+ error_putstr("\n");
+ }
+
return output + entry_offset;
}
On Fri, Jan 12, 2024 at 11:13:53AM +0000, NOMURA JUNICHI(野村 淳一) wrote:
> Commit 78a509fba9c9 ("x86/boot: Ignore NMIs during very early boot") added
> empty handler in early boot stage to avoid boot failure by spurious NMIs.
>
> Add a diagnostic message in case we need to know whether early NMIs have
> occurred and/or what happened to them.
>
> Signed-off-by: Jun'ichi Nomura <[email protected]>
> Suggested-by: Borislav Petkov <[email protected]>
> Suggested-by: H. Peter Anvin <[email protected]>
> Link: https://lore.kernel.org/lkml/20231130103339.GCZWhlA196uRklTMNF@fat_crate.local/
>
> diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c
> --- a/arch/x86/boot/compressed/ident_map_64.c
> +++ b/arch/x86/boot/compressed/ident_map_64.c
> @@ -387,7 +387,10 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code)
> kernel_add_identity_map(address, end);
> }
>
> +extern int spurious_nmi_count;
> +
It has to be in a header file.
> void do_boot_nmi_trap(struct pt_regs *regs, unsigned long error_code)
> {
> /* Empty handler to ignore NMI during early boot */
> + spurious_nmi_count++;
> }
> diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
> --- a/arch/x86/boot/compressed/misc.c
> +++ b/arch/x86/boot/compressed/misc.c
> @@ -357,6 +357,8 @@ unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr,
> return entry;
> }
>
> +int spurious_nmi_count;
> +
It is not a right place to define a variable. Do it next to rest of
variables at the beginning of the file.
> /*
> * The compressed kernel image (ZO), has been moved so that its position
> * is against the end of the buffer used to hold the uncompressed kernel
> @@ -493,6 +495,12 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output)
> /* Disable exception handling before booting the kernel */
> cleanup_exception_handling();
>
> + if (spurious_nmi_count) {
> + error_putstr("Spurious early NMI ignored. Number of NMIs: 0x");
> + error_puthex(spurious_nmi_count);
> + error_putstr("\n");
> + }
> +
> return output + entry_offset;
> }
>
--
Kiryl Shutsemau / Kirill A. Shutemov
Commit 78a509fba9c9 ("x86/boot: Ignore NMIs during very early boot") added
empty handler in early boot stage to avoid boot failure by spurious NMIs.
Add a diagnostic message in case we need to know whether early NMIs have
occurred and/or what happened to them.
Signed-off-by: Jun'ichi Nomura <[email protected]>
Suggested-by: Borislav Petkov <[email protected]>
Suggested-by: H. Peter Anvin <[email protected]>
Link: https://lore.kernel.org/lkml/20231130103339.GCZWhlA196uRklTMNF@fat_crate.local/
--
v2
* Moved variable declaration and definition to the right place
based on comments from Kirill.
No functional changes.
diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c
--- a/arch/x86/boot/compressed/ident_map_64.c
+++ b/arch/x86/boot/compressed/ident_map_64.c
@@ -390,4 +390,5 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code)
void do_boot_nmi_trap(struct pt_regs *regs, unsigned long error_code)
{
/* Empty handler to ignore NMI during early boot */
+ spurious_nmi_count++;
}
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -52,6 +52,7 @@ struct port_io_ops pio_ops;
memptr free_mem_ptr;
memptr free_mem_end_ptr;
+int spurious_nmi_count;
static char *vidmem;
static int vidport;
@@ -493,6 +494,12 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output)
/* Disable exception handling before booting the kernel */
cleanup_exception_handling();
+ if (spurious_nmi_count) {
+ error_putstr("Spurious early NMI ignored. Number of NMIs: 0x");
+ error_puthex(spurious_nmi_count);
+ error_putstr("\n");
+ }
+
return output + entry_offset;
}
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -59,6 +59,7 @@ extern char _head[], _end[];
/* misc.c */
extern memptr free_mem_ptr;
extern memptr free_mem_end_ptr;
+extern int spurious_nmi_count;
void *malloc(int size);
void free(void *where);
void __putstr(const char *s);
On Mon, Jan 15, 2024 at 08:57:45AM +0000, NOMURA JUNICHI(野村 淳一) wrote:
> Commit 78a509fba9c9 ("x86/boot: Ignore NMIs during very early boot") added
> empty handler in early boot stage to avoid boot failure by spurious NMIs.
>
> Add a diagnostic message in case we need to know whether early NMIs have
> occurred and/or what happened to them.
>
> Signed-off-by: Jun'ichi Nomura <[email protected]>
> Suggested-by: Borislav Petkov <[email protected]>
> Suggested-by: H. Peter Anvin <[email protected]>
Acked-by: Kirill A. Shutemov <[email protected]>
--
Kiryl Shutsemau / Kirill A. Shutemov
On Mon, Jan 15, 2024 at 08:57:45AM +0000, NOMURA JUNICHI(野村 淳一) wrote:
> + if (spurious_nmi_count) {
> + error_putstr("Spurious early NMI ignored. Number of NMIs: 0x");
> + error_puthex(spurious_nmi_count);
> + error_putstr("\n");
Uff, that's just silly:
Spurious early NMIs ignored: 0x0000000000000017
Would you like to add a error_putnum() or so in a prepatch which would
make this output
Spurious early NMIs ignored: 23.
?
So that it is human readable and doesn't make me wonder what that hex
value is supposed to mean?
Thx.
Btw, please use this version when sending next time:
---
From: =?UTF-8?q?NOMURA=20JUNICHI=28=E9=87=8E=E6=9D=91=20=E6=B7=B3=E4=B8=80?=
=?UTF-8?q?=29?= <[email protected]>
Date: Mon, 15 Jan 2024 08:57:45 +0000
Subject: [PATCH] x86/boot: Add a message about ignored early NMIs
Commit
78a509fba9c9 ("x86/boot: Ignore NMIs during very early boot")
added an empty handler in early boot stage to avoid boot failure due to
spurious NMIs.
Add a diagnostic message to show when early NMIs have occurred and/or
what happened to them.
[ bp: Touchups. ]
Suggested-by: Borislav Petkov <[email protected]>
Suggested-by: H. Peter Anvin <[email protected]>
Signed-off-by: Jun'ichi Nomura <[email protected]>
Signed-off-by: Borislav Petkov (AMD) <[email protected]>
Acked-by: Kirill A. Shutemov <[email protected]>
Link: https://lore.kernel.org/lkml/20231130103339.GCZWhlA196uRklTMNF@fat_crate.local
---
arch/x86/boot/compressed/ident_map_64.c | 2 +-
arch/x86/boot/compressed/misc.c | 7 +++++++
arch/x86/boot/compressed/misc.h | 1 +
3 files changed, 9 insertions(+), 1 deletion(-)
diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c
index ff09ca6dbb87..909f2a35b60c 100644
--- a/arch/x86/boot/compressed/ident_map_64.c
+++ b/arch/x86/boot/compressed/ident_map_64.c
@@ -389,5 +389,5 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code)
void do_boot_nmi_trap(struct pt_regs *regs, unsigned long error_code)
{
- /* Empty handler to ignore NMI during early boot */
+ spurious_nmi_count++;
}
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index b99e08e6815b..e7f4eb24a9a4 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -52,6 +52,7 @@ struct port_io_ops pio_ops;
memptr free_mem_ptr;
memptr free_mem_end_ptr;
+int spurious_nmi_count;
static char *vidmem;
static int vidport;
@@ -493,6 +494,12 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output)
/* Disable exception handling before booting the kernel */
cleanup_exception_handling();
+ if (spurious_nmi_count) {
+ error_putstr("Spurious early NMIs ignored: 0x");
+ error_puthex(spurious_nmi_count);
+ error_putstr("\n");
+ }
+
return output + entry_offset;
}
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index bc2f0f17fb90..b858d6aa648c 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -59,6 +59,7 @@ extern char _head[], _end[];
/* misc.c */
extern memptr free_mem_ptr;
extern memptr free_mem_end_ptr;
+extern int spurious_nmi_count;
void *malloc(int size);
void free(void *where);
void __putstr(const char *s);
--
2.43.0
--
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquette
> From: Borislav Petkov <[email protected]>
> On Mon, Jan 15, 2024 at 08:57:45AM +0000, NOMURA JUNICHI(野村 淳一) wrote:
> > + if (spurious_nmi_count) {
> > + error_putstr("Spurious early NMI ignored. Number of NMIs: 0x");
> > + error_puthex(spurious_nmi_count);
> > + error_putstr("\n");
>
> Uff, that's just silly:
>
> Spurious early NMIs ignored: 0x0000000000000017
>
> Would you like to add a error_putnum() or so in a prepatch which would
> make this output
>
> Spurious early NMIs ignored: 23.
>
> ?
>
> So that it is human readable and doesn't make me wonder what that hex
> value is supposed to mean?
Yes, it would be nicer to print that way. I used the existing error_puthex() just
to keep the patch minimal. I will try to add error_putnum().
> Btw, please use this version when sending next time:
Thank you.
--
Jun'ichi Nomura, NEC Corporation / NEC Solution Innovators, Ltd.
On 1/24/24 03:44, NOMURA JUNICHI(野村 淳一) wrote:
>> From: Borislav Petkov <[email protected]>
>> On Mon, Jan 15, 2024 at 08:57:45AM +0000, NOMURA JUNICHI(野村 淳一) wrote:
>>> + if (spurious_nmi_count) {
>>> + error_putstr("Spurious early NMI ignored. Number of NMIs: 0x");
>>> + error_puthex(spurious_nmi_count);
>>> + error_putstr("\n");
>>
>> Uff, that's just silly:
>>
>> Spurious early NMIs ignored: 0x0000000000000017
>>
>> Would you like to add a error_putnum() or so in a prepatch which would
>> make this output
>>
>> Spurious early NMIs ignored: 23.
>>
>> ?
>>
>> So that it is human readable and doesn't make me wonder what that hex
>> value is supposed to mean?
>
> Yes, it would be nicer to print that way. I used the existing error_puthex() just
> to keep the patch minimal. I will try to add error_putnum().
>
>> Btw, please use this version when sending next time:
>
Here is a *completely* untested patch for you...
-hpa
> From: H. Peter Anvin <[email protected]>
> On 1/24/24 03:44, NOMURA JUNICHI(野村 淳一) wrote:
> >> From: Borislav Petkov <[email protected]>
> >> On Mon, Jan 15, 2024 at 08:57:45AM +0000, NOMURA JUNICHI(野村 淳一) wrote:
> >>> + if (spurious_nmi_count) {
> >>> + error_putstr("Spurious early NMI ignored. Number of NMIs: 0x");
> >>> + error_puthex(spurious_nmi_count);
> >>> + error_putstr("\n");
> >>
> >> Uff, that's just silly:
> >>
> >> Spurious early NMIs ignored: 0x0000000000000017
> >>
> >> Would you like to add a error_putnum() or so in a prepatch which would
> >> make this output
> >>
> >> Spurious early NMIs ignored: 23.
> >>
> >> ?
> >>
> >> So that it is human readable and doesn't make me wonder what that hex
> >> value is supposed to mean?
> >
> > Yes, it would be nicer to print that way. I used the existing error_puthex() just
> > to keep the patch minimal. I will try to add error_putnum().
> >
> >> Btw, please use this version when sending next time:
>
> Here is a *completely* untested patch for you...
Ah, I was preparing decimal only version but yours is much better.
I tested and it just works.
I would like to use yours as a prepatch. May I have your signed-off-by?
--
Jun'ichi Nomura, NEC Corporation / NEC Solution Innovators, Ltd.
On January 25, 2024 6:15:15 PM PST, "NOMURA JUNICHI(野村 淳一)" <[email protected]> wrote:
>> From: H. Peter Anvin <[email protected]>
>> On 1/24/24 03:44, NOMURA JUNICHI(野村 淳一) wrote:
>> >> From: Borislav Petkov <[email protected]>
>> >> On Mon, Jan 15, 2024 at 08:57:45AM +0000, NOMURA JUNICHI(野村 淳一) wrote:
>> >>> + if (spurious_nmi_count) {
>> >>> + error_putstr("Spurious early NMI ignored. Number of NMIs: 0x");
>> >>> + error_puthex(spurious_nmi_count);
>> >>> + error_putstr("\n");
>> >>
>> >> Uff, that's just silly:
>> >>
>> >> Spurious early NMIs ignored: 0x0000000000000017
>> >>
>> >> Would you like to add a error_putnum() or so in a prepatch which would
>> >> make this output
>> >>
>> >> Spurious early NMIs ignored: 23.
>> >>
>> >> ?
>> >>
>> >> So that it is human readable and doesn't make me wonder what that hex
>> >> value is supposed to mean?
>> >
>> > Yes, it would be nicer to print that way. I used the existing error_puthex() just
>> > to keep the patch minimal. I will try to add error_putnum().
>> >
>> >> Btw, please use this version when sending next time:
>>
>> Here is a *completely* untested patch for you...
>
>Ah, I was preparing decimal only version but yours is much better.
>I tested and it just works.
>
>I would like to use yours as a prepatch. May I have your signed-off-by?
>
>--
>Jun'ichi Nomura, NEC Corporation / NEC Solution Innovators, Ltd.
Signed-off-by: H. Peter Anvin (Intel) <[email protected]>