[PATCH] espfix/xen: Fix allocation of pages for paravirt page tables

[PATCH] espfix/xen: Fix allocation of pages for paravirt page tables

[Boris Ostrovsky]

init_espfix_ap() is currently off by one level when informing hypervisor
that allocated pages will be used for ministacks' page tables.

The most immediate effect of this on a PV guest is that if
'stack_page = __get_free_page()' returns a non-zeroed-out page the hypervisor
will refuse to use it for a page table (which it shouldn't be anyway). This will
result in warnings by both Xen and Linux.

More importantly, a subsequent write to that page (again, by a PV guest) is
likely to result in fatal page fault.

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/x86/kernel/espfix_64.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index 6afbb16..94d857f 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -175,7 +175,7 @@ void init_espfix_ap(void)
 	if (!pud_present(pud)) {
 		pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
 		pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
-		paravirt_alloc_pud(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
+		paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
 		for (n = 0; n < ESPFIX_PUD_CLONES; n++)
 			set_pud(&pud_p[n], pud);
 	}
@@ -185,7 +185,7 @@ void init_espfix_ap(void)
 	if (!pmd_present(pmd)) {
 		pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
 		pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
-		paravirt_alloc_pmd(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
+		paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
 		for (n = 0; n < ESPFIX_PMD_CLONES; n++)
 			set_pmd(&pmd_p[n], pmd);
 	}
@@ -193,7 +193,6 @@ void init_espfix_ap(void)
 	pte_p = pte_offset_kernel(&pmd, addr);
 	stack_page = (void *)__get_free_page(GFP_KERNEL);
 	pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
-	paravirt_alloc_pte(&init_mm, __pa(stack_page) >> PAGE_SHIFT);
 	for (n = 0; n < ESPFIX_PTE_CLONES; n++)
 		set_pte(&pte_p[n*PTE_STRIDE], pte);
 
-- 
1.8.1.4

Re: [PATCH] espfix/xen: Fix allocation of pages for paravirt page tables

[Konrad Rzeszutek Wilk]

On Wed, Jul 09, 2014 at 01:18:18PM -0400, Boris Ostrovsky wrote:
> init_espfix_ap() is currently off by one level when informing hypervisor
> that allocated pages will be used for ministacks' page tables.
> 
> The most immediate effect of this on a PV guest is that if
> 'stack_page = __get_free_page()' returns a non-zeroed-out page the hypervisor
> will refuse to use it for a page table (which it shouldn't be anyway). This will
> result in warnings by both Xen and Linux.
> 
> More importantly, a subsequent write to that page (again, by a PV guest) is
> likely to result in fatal page fault.
> 
> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>

Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

<sigh>
> ---
>  arch/x86/kernel/espfix_64.c | 5 ++---
>  1 file changed, 2 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
> index 6afbb16..94d857f 100644
> --- a/arch/x86/kernel/espfix_64.c
> +++ b/arch/x86/kernel/espfix_64.c
> @@ -175,7 +175,7 @@ void init_espfix_ap(void)
>  	if (!pud_present(pud)) {
>  		pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
>  		pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
> -		paravirt_alloc_pud(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
> +		paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
>  		for (n = 0; n < ESPFIX_PUD_CLONES; n++)
>  			set_pud(&pud_p[n], pud);
>  	}
> @@ -185,7 +185,7 @@ void init_espfix_ap(void)
>  	if (!pmd_present(pmd)) {
>  		pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
>  		pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
> -		paravirt_alloc_pmd(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
> +		paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
>  		for (n = 0; n < ESPFIX_PMD_CLONES; n++)
>  			set_pmd(&pmd_p[n], pmd);
>  	}
> @@ -193,7 +193,6 @@ void init_espfix_ap(void)
>  	pte_p = pte_offset_kernel(&pmd, addr);
>  	stack_page = (void *)__get_free_page(GFP_KERNEL);
>  	pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
> -	paravirt_alloc_pte(&init_mm, __pa(stack_page) >> PAGE_SHIFT);
>  	for (n = 0; n < ESPFIX_PTE_CLONES; n++)
>  		set_pte(&pte_p[n*PTE_STRIDE], pte);
>  
> -- 
> 1.8.1.4
> 

[tip:x86/urgent] x86/espfix/xen: Fix allocation of pages for paravirt page tables

[tip-bot for Boris Ostrovsky]

Commit-ID:  8762e5092828c4dc0f49da5a47a644c670df77f3
Gitweb:     http://git.kernel.org/tip/8762e5092828c4dc0f49da5a47a644c670df77f3
Author:     Boris Ostrovsky <boris.ostrovsky@oracle.com>
AuthorDate: Wed, 9 Jul 2014 13:18:18 -0400
Committer:  H. Peter Anvin <hpa@linux.intel.com>
CommitDate: Mon, 14 Jul 2014 13:47:32 -0700

x86/espfix/xen: Fix allocation of pages for paravirt page tables

init_espfix_ap() is currently off by one level when informing hypervisor
that allocated pages will be used for ministacks' page tables.

The most immediate effect of this on a PV guest is that if
'stack_page = __get_free_page()' returns a non-zeroed-out page the hypervisor
will refuse to use it for a page table (which it shouldn't be anyway). This will
result in warnings by both Xen and Linux.

More importantly, a subsequent write to that page (again, by a PV guest) is
likely to result in fatal page fault.

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Link: http://lkml.kernel.org/r/1404926298-5565-1-git-send-email-boris.ostrovsky@oracle.com
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: <stable@vger.kernel.org>
---
 arch/x86/kernel/espfix_64.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index 6afbb16..94d857f 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -175,7 +175,7 @@ void init_espfix_ap(void)
 	if (!pud_present(pud)) {
 		pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
 		pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
-		paravirt_alloc_pud(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
+		paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
 		for (n = 0; n < ESPFIX_PUD_CLONES; n++)
 			set_pud(&pud_p[n], pud);
 	}
@@ -185,7 +185,7 @@ void init_espfix_ap(void)
 	if (!pmd_present(pmd)) {
 		pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
 		pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
-		paravirt_alloc_pmd(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
+		paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
 		for (n = 0; n < ESPFIX_PMD_CLONES; n++)
 			set_pmd(&pmd_p[n], pmd);
 	}
@@ -193,7 +193,6 @@ void init_espfix_ap(void)
 	pte_p = pte_offset_kernel(&pmd, addr);
 	stack_page = (void *)__get_free_page(GFP_KERNEL);
 	pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
-	paravirt_alloc_pte(&init_mm, __pa(stack_page) >> PAGE_SHIFT);
 	for (n = 0; n < ESPFIX_PTE_CLONES; n++)
 		set_pte(&pte_p[n*PTE_STRIDE], pte);