All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH] x86/mm: Skip the hypervisor range when walking PGD
@ 2015-11-05 18:56 Boris Ostrovsky
  0 siblings, 0 replies; 6+ messages in thread
From: Boris Ostrovsky @ 2015-11-05 18:56 UTC (permalink / raw)
  To: tglx, mingo, hpa; +Cc: linux, boris.ostrovsky, x86, linux-kernel, xen-devel

The range between 0xffff800000000000 and 0xffff87ffffffffff is reserved
for hypervisor and therefore we should not try to follow PGD's indexes
corresponding to those addresses.

While this has alsways been a problem, with commit e1a58320a38d ("x86/mm:
Warn on W^X mappings") ptdump_walk_pgd_level_core() can now be called
during boot, causing a PV Xen guest to crash.

Reported-by: Sander Eikelenboom <linux@eikelenboom.it>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/x86/mm/dump_pagetables.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 1bf417e..756c921 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -362,8 +362,13 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
 				       bool checkwx)
 {
 #ifdef CONFIG_X86_64
+/* ffff800000000000 - ffff87ffffffffff is reserved for hypervisor */
+#define is_hypervisor_range(idx) (paravirt_enabled() && \
+				  (((idx) >= pgd_index(__PAGE_OFFSET) - 16) && \
+				   ((idx) < pgd_index(__PAGE_OFFSET))))
 	pgd_t *start = (pgd_t *) &init_level4_pgt;
 #else
+#define is_hypervisor_range(idx)   0
 	pgd_t *start = swapper_pg_dir;
 #endif
 	pgprotval_t prot;
@@ -381,7 +386,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
 
 	for (i = 0; i < PTRS_PER_PGD; i++) {
 		st.current_address = normalize_addr(i * PGD_LEVEL_MULT);
-		if (!pgd_none(*start)) {
+		if (!pgd_none(*start) && !is_hypervisor_range(i)) {
 			if (pgd_large(*start) || !pgd_present(*start)) {
 				prot = pgd_flags(*start);
 				note_page(m, &st, __pgprot(prot), 1);
-- 
1.9.3

^ permalink raw reply related	[flat|nested] 6+ messages in thread
* Re: [PATCH] x86/mm: Skip the hypervisor range when walking PGD
  2015-11-05 22:31 ` H. Peter Anvin
@ 2015-11-06  3:38   ` Boris Ostrovsky
  2015-11-06  3:38   ` Boris Ostrovsky
  1 sibling, 0 replies; 6+ messages in thread
From: Boris Ostrovsky @ 2015-11-06  3:38 UTC (permalink / raw)
  To: H. Peter Anvin, tglx, mingo; +Cc: x86, linux-kernel, linux, xen-devel



On 11/05/2015 05:31 PM, H. Peter Anvin wrote:
> On 11/05/15 10:56, Boris Ostrovsky wrote:
>> The range between 0xffff800000000000 and 0xffff87ffffffffff is reserved
>> for hypervisor and therefore we should not try to follow PGD's indexes
>> corresponding to those addresses.
>>
>> While this has alsways been a problem, with commit e1a58320a38d ("x86/mm:
>> Warn on W^X mappings") ptdump_walk_pgd_level_core() can now be called
>> during boot, causing a PV Xen guest to crash.
>>
>> Reported-by: Sander Eikelenboom <linux@eikelenboom.it>
>> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
>> ---
>>   arch/x86/mm/dump_pagetables.c | 7 ++++++-
>>   1 file changed, 6 insertions(+), 1 deletion(-)
>>
>> diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
>> index 1bf417e..756c921 100644
>> --- a/arch/x86/mm/dump_pagetables.c
>> +++ b/arch/x86/mm/dump_pagetables.c
>> @@ -362,8 +362,13 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
>>   				       bool checkwx)
>>   {
>>   #ifdef CONFIG_X86_64
>> +/* ffff800000000000 - ffff87ffffffffff is reserved for hypervisor */
>> +#define is_hypervisor_range(idx) (paravirt_enabled() && \
>> +				  (((idx) >= pgd_index(__PAGE_OFFSET) - 16) && \
>> +				   ((idx) < pgd_index(__PAGE_OFFSET))))
>>   	pgd_t *start = (pgd_t *) &init_level4_pgt;
>>   #else
>> +#define is_hypervisor_range(idx)   0
>>   	pgd_t *start = swapper_pg_dir;
>>   #endif
>>   	pgprotval_t prot;
>> @@ -381,7 +386,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
>>   
>>   	for (i = 0; i < PTRS_PER_PGD; i++) {
>>   		st.current_address = normalize_addr(i * PGD_LEVEL_MULT);
>> -		if (!pgd_none(*start)) {
>> +		if (!pgd_none(*start) && !is_hypervisor_range(i)) {
>>   			if (pgd_large(*start) || !pgd_present(*start)) {
>>   				prot = pgd_flags(*start);
>>   				note_page(m, &st, __pgprot(prot), 1);
>>
> Maybe we could use the max_lines field in the address_markers[] array?
> We really shouldn't be mapping anything in the hypervisor space even on
> native.

You mean overload max_lines with a value indicating that the range needs 
to be skipped?

That would require checking the range on each loop iteration since we 
update st.marker *after* we've walked a particular index. (And I think 
it would need to be done on each level to be generic).

I could just drop paravirt_enabled() in is_hypervisor_range() but you 
are thinking about avoiding the macro altogether, right?

(I do need to add hypervisor range to address_markers[])

-boris


^ permalink raw reply	[flat|nested] 6+ messages in thread
* Re: [PATCH] x86/mm: Skip the hypervisor range when walking PGD
  2015-11-05 22:31 ` H. Peter Anvin
  2015-11-06  3:38   ` Boris Ostrovsky
@ 2015-11-06  3:38   ` Boris Ostrovsky
  1 sibling, 0 replies; 6+ messages in thread
From: Boris Ostrovsky @ 2015-11-06  3:38 UTC (permalink / raw)
  To: H. Peter Anvin, tglx, mingo; +Cc: linux, x86, linux-kernel, xen-devel



On 11/05/2015 05:31 PM, H. Peter Anvin wrote:
> On 11/05/15 10:56, Boris Ostrovsky wrote:
>> The range between 0xffff800000000000 and 0xffff87ffffffffff is reserved
>> for hypervisor and therefore we should not try to follow PGD's indexes
>> corresponding to those addresses.
>>
>> While this has alsways been a problem, with commit e1a58320a38d ("x86/mm:
>> Warn on W^X mappings") ptdump_walk_pgd_level_core() can now be called
>> during boot, causing a PV Xen guest to crash.
>>
>> Reported-by: Sander Eikelenboom <linux@eikelenboom.it>
>> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
>> ---
>>   arch/x86/mm/dump_pagetables.c | 7 ++++++-
>>   1 file changed, 6 insertions(+), 1 deletion(-)
>>
>> diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
>> index 1bf417e..756c921 100644
>> --- a/arch/x86/mm/dump_pagetables.c
>> +++ b/arch/x86/mm/dump_pagetables.c
>> @@ -362,8 +362,13 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
>>   				       bool checkwx)
>>   {
>>   #ifdef CONFIG_X86_64
>> +/* ffff800000000000 - ffff87ffffffffff is reserved for hypervisor */
>> +#define is_hypervisor_range(idx) (paravirt_enabled() && \
>> +				  (((idx) >= pgd_index(__PAGE_OFFSET) - 16) && \
>> +				   ((idx) < pgd_index(__PAGE_OFFSET))))
>>   	pgd_t *start = (pgd_t *) &init_level4_pgt;
>>   #else
>> +#define is_hypervisor_range(idx)   0
>>   	pgd_t *start = swapper_pg_dir;
>>   #endif
>>   	pgprotval_t prot;
>> @@ -381,7 +386,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
>>   
>>   	for (i = 0; i < PTRS_PER_PGD; i++) {
>>   		st.current_address = normalize_addr(i * PGD_LEVEL_MULT);
>> -		if (!pgd_none(*start)) {
>> +		if (!pgd_none(*start) && !is_hypervisor_range(i)) {
>>   			if (pgd_large(*start) || !pgd_present(*start)) {
>>   				prot = pgd_flags(*start);
>>   				note_page(m, &st, __pgprot(prot), 1);
>>
> Maybe we could use the max_lines field in the address_markers[] array?
> We really shouldn't be mapping anything in the hypervisor space even on
> native.

You mean overload max_lines with a value indicating that the range needs 
to be skipped?

That would require checking the range on each loop iteration since we 
update st.marker *after* we've walked a particular index. (And I think 
it would need to be done on each level to be generic).

I could just drop paravirt_enabled() in is_hypervisor_range() but you 
are thinking about avoiding the macro altogether, right?

(I do need to add hypervisor range to address_markers[])

-boris

^ permalink raw reply	[flat|nested] 6+ messages in thread
* Re: [PATCH] x86/mm: Skip the hypervisor range when walking PGD
  2015-11-05 18:56 Boris Ostrovsky
  2015-11-05 22:31 ` H. Peter Anvin
@ 2015-11-05 22:31 ` H. Peter Anvin
  2015-11-06  3:38   ` Boris Ostrovsky
  2015-11-06  3:38   ` Boris Ostrovsky
  1 sibling, 2 replies; 6+ messages in thread
From: H. Peter Anvin @ 2015-11-05 22:31 UTC (permalink / raw)
  To: Boris Ostrovsky, tglx, mingo; +Cc: x86, linux-kernel, linux, xen-devel

On 11/05/15 10:56, Boris Ostrovsky wrote:
> The range between 0xffff800000000000 and 0xffff87ffffffffff is reserved
> for hypervisor and therefore we should not try to follow PGD's indexes
> corresponding to those addresses.
> 
> While this has alsways been a problem, with commit e1a58320a38d ("x86/mm:
> Warn on W^X mappings") ptdump_walk_pgd_level_core() can now be called
> during boot, causing a PV Xen guest to crash.
> 
> Reported-by: Sander Eikelenboom <linux@eikelenboom.it>
> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
> ---
>  arch/x86/mm/dump_pagetables.c | 7 ++++++-
>  1 file changed, 6 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
> index 1bf417e..756c921 100644
> --- a/arch/x86/mm/dump_pagetables.c
> +++ b/arch/x86/mm/dump_pagetables.c
> @@ -362,8 +362,13 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
>  				       bool checkwx)
>  {
>  #ifdef CONFIG_X86_64
> +/* ffff800000000000 - ffff87ffffffffff is reserved for hypervisor */
> +#define is_hypervisor_range(idx) (paravirt_enabled() && \
> +				  (((idx) >= pgd_index(__PAGE_OFFSET) - 16) && \
> +				   ((idx) < pgd_index(__PAGE_OFFSET))))
>  	pgd_t *start = (pgd_t *) &init_level4_pgt;
>  #else
> +#define is_hypervisor_range(idx)   0
>  	pgd_t *start = swapper_pg_dir;
>  #endif
>  	pgprotval_t prot;
> @@ -381,7 +386,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
>  
>  	for (i = 0; i < PTRS_PER_PGD; i++) {
>  		st.current_address = normalize_addr(i * PGD_LEVEL_MULT);
> -		if (!pgd_none(*start)) {
> +		if (!pgd_none(*start) && !is_hypervisor_range(i)) {
>  			if (pgd_large(*start) || !pgd_present(*start)) {
>  				prot = pgd_flags(*start);
>  				note_page(m, &st, __pgprot(prot), 1);
> 

Maybe we could use the max_lines field in the address_markers[] array?
We really shouldn't be mapping anything in the hypervisor space even on
native.

	-hpa


^ permalink raw reply	[flat|nested] 6+ messages in thread
* Re: [PATCH] x86/mm: Skip the hypervisor range when walking PGD
  2015-11-05 18:56 Boris Ostrovsky
@ 2015-11-05 22:31 ` H. Peter Anvin
  2015-11-05 22:31 ` H. Peter Anvin
  1 sibling, 0 replies; 6+ messages in thread
From: H. Peter Anvin @ 2015-11-05 22:31 UTC (permalink / raw)
  To: Boris Ostrovsky, tglx, mingo; +Cc: linux, x86, linux-kernel, xen-devel

On 11/05/15 10:56, Boris Ostrovsky wrote:
> The range between 0xffff800000000000 and 0xffff87ffffffffff is reserved
> for hypervisor and therefore we should not try to follow PGD's indexes
> corresponding to those addresses.
> 
> While this has alsways been a problem, with commit e1a58320a38d ("x86/mm:
> Warn on W^X mappings") ptdump_walk_pgd_level_core() can now be called
> during boot, causing a PV Xen guest to crash.
> 
> Reported-by: Sander Eikelenboom <linux@eikelenboom.it>
> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
> ---
>  arch/x86/mm/dump_pagetables.c | 7 ++++++-
>  1 file changed, 6 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
> index 1bf417e..756c921 100644
> --- a/arch/x86/mm/dump_pagetables.c
> +++ b/arch/x86/mm/dump_pagetables.c
> @@ -362,8 +362,13 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
>  				       bool checkwx)
>  {
>  #ifdef CONFIG_X86_64
> +/* ffff800000000000 - ffff87ffffffffff is reserved for hypervisor */
> +#define is_hypervisor_range(idx) (paravirt_enabled() && \
> +				  (((idx) >= pgd_index(__PAGE_OFFSET) - 16) && \
> +				   ((idx) < pgd_index(__PAGE_OFFSET))))
>  	pgd_t *start = (pgd_t *) &init_level4_pgt;
>  #else
> +#define is_hypervisor_range(idx)   0
>  	pgd_t *start = swapper_pg_dir;
>  #endif
>  	pgprotval_t prot;
> @@ -381,7 +386,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
>  
>  	for (i = 0; i < PTRS_PER_PGD; i++) {
>  		st.current_address = normalize_addr(i * PGD_LEVEL_MULT);
> -		if (!pgd_none(*start)) {
> +		if (!pgd_none(*start) && !is_hypervisor_range(i)) {
>  			if (pgd_large(*start) || !pgd_present(*start)) {
>  				prot = pgd_flags(*start);
>  				note_page(m, &st, __pgprot(prot), 1);
> 

Maybe we could use the max_lines field in the address_markers[] array?
We really shouldn't be mapping anything in the hypervisor space even on
native.

	-hpa

^ permalink raw reply	[flat|nested] 6+ messages in thread
* [PATCH] x86/mm: Skip the hypervisor range when walking PGD
@ 2015-11-05 18:56 Boris Ostrovsky
  2015-11-05 22:31 ` H. Peter Anvin
  2015-11-05 22:31 ` H. Peter Anvin
  0 siblings, 2 replies; 6+ messages in thread
From: Boris Ostrovsky @ 2015-11-05 18:56 UTC (permalink / raw)
  To: tglx, mingo, hpa; +Cc: x86, linux-kernel, linux, xen-devel, boris.ostrovsky

The range between 0xffff800000000000 and 0xffff87ffffffffff is reserved
for hypervisor and therefore we should not try to follow PGD's indexes
corresponding to those addresses.

While this has alsways been a problem, with commit e1a58320a38d ("x86/mm:
Warn on W^X mappings") ptdump_walk_pgd_level_core() can now be called
during boot, causing a PV Xen guest to crash.

Reported-by: Sander Eikelenboom <linux@eikelenboom.it>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/x86/mm/dump_pagetables.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 1bf417e..756c921 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -362,8 +362,13 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
 				       bool checkwx)
 {
 #ifdef CONFIG_X86_64
+/* ffff800000000000 - ffff87ffffffffff is reserved for hypervisor */
+#define is_hypervisor_range(idx) (paravirt_enabled() && \
+				  (((idx) >= pgd_index(__PAGE_OFFSET) - 16) && \
+				   ((idx) < pgd_index(__PAGE_OFFSET))))
 	pgd_t *start = (pgd_t *) &init_level4_pgt;
 #else
+#define is_hypervisor_range(idx)   0
 	pgd_t *start = swapper_pg_dir;
 #endif
 	pgprotval_t prot;
@@ -381,7 +386,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
 
 	for (i = 0; i < PTRS_PER_PGD; i++) {
 		st.current_address = normalize_addr(i * PGD_LEVEL_MULT);
-		if (!pgd_none(*start)) {
+		if (!pgd_none(*start) && !is_hypervisor_range(i)) {
 			if (pgd_large(*start) || !pgd_present(*start)) {
 				prot = pgd_flags(*start);
 				note_page(m, &st, __pgprot(prot), 1);
-- 
1.9.3


^ permalink raw reply related	[flat|nested] 6+ messages in thread
end of thread, other threads:[~2015-11-06  3:39 UTC | newest]

Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2015-11-05 18:56 [PATCH] x86/mm: Skip the hypervisor range when walking PGD Boris Ostrovsky
  -- strict thread matches above, loose matches on Subject: below --
2015-11-05 18:56 Boris Ostrovsky
2015-11-05 22:31 ` H. Peter Anvin
2015-11-05 22:31 ` H. Peter Anvin
2015-11-06  3:38   ` Boris Ostrovsky
2015-11-06  3:38   ` Boris Ostrovsky

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.