diff mbox series

[v3,2/4] PM: hibernate: make direct map manipulations more explicit

Message ID 20201101170815.9795-3-rppt@kernel.org (mailing list archive)
State Not Applicable
Headers show
Series arch, mm: improve robustness of direct map manipulation | expand

Checks

Context Check Description
snowpatch_ozlabs/apply_patch success Successfully applied on branch powerpc/merge (8cb17737940b156329cb5210669b9c9b23f4dd56)
snowpatch_ozlabs/checkpatch success
snowpatch_ozlabs/needsstable success Patch has no Fixes tags

Commit Message

Mike Rapoport Nov. 1, 2020, 5:08 p.m. UTC 
From: Mike Rapoport <rppt@linux.ibm.com>

When DEBUG_PAGEALLOC or ARCH_HAS_SET_DIRECT_MAP is enabled a page may be
not present in the direct map and has to be explicitly mapped before it
could be copied.

Introduce hibernate_map_page() that will explicitly use
set_direct_map_{default,invalid}_noflush() for ARCH_HAS_SET_DIRECT_MAP case
and debug_pagealloc_map_pages() for DEBUG_PAGEALLOC case.

The remapping of the pages in safe_copy_page() presumes that it only
changes protection bits in an existing PTE and so it is safe to ignore
return value of set_direct_map_{default,invalid}_noflush().

Still, add a WARN_ON() so that future changes in set_memory APIs will not
silently break hibernation.

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/mm.h      | 12 ------------
 kernel/power/snapshot.c | 30 ++++++++++++++++++++++++++++--
 2 files changed, 28 insertions(+), 14 deletions(-)

Comments

David Hildenbrand Nov. 2, 2020, 9:19 a.m. UTC | #1 
On 01.11.20 18:08, Mike Rapoport wrote:
> From: Mike Rapoport <rppt@linux.ibm.com>
> 
> When DEBUG_PAGEALLOC or ARCH_HAS_SET_DIRECT_MAP is enabled a page may be
> not present in the direct map and has to be explicitly mapped before it
> could be copied.
> 
> Introduce hibernate_map_page() that will explicitly use
> set_direct_map_{default,invalid}_noflush() for ARCH_HAS_SET_DIRECT_MAP case
> and debug_pagealloc_map_pages() for DEBUG_PAGEALLOC case.
> 
> The remapping of the pages in safe_copy_page() presumes that it only
> changes protection bits in an existing PTE and so it is safe to ignore
> return value of set_direct_map_{default,invalid}_noflush().
> 
> Still, add a WARN_ON() so that future changes in set_memory APIs will not
> silently break hibernation.
> 
> Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
> Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
> ---
>   include/linux/mm.h      | 12 ------------
>   kernel/power/snapshot.c | 30 ++++++++++++++++++++++++++++--
>   2 files changed, 28 insertions(+), 14 deletions(-)
> 
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 1fc0609056dc..14e397f3752c 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -2927,16 +2927,6 @@ static inline bool debug_pagealloc_enabled_static(void)
>   #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP)
>   extern void __kernel_map_pages(struct page *page, int numpages, int enable);
>   
> -/*
> - * When called in DEBUG_PAGEALLOC context, the call should most likely be
> - * guarded by debug_pagealloc_enabled() or debug_pagealloc_enabled_static()
> - */
> -static inline void
> -kernel_map_pages(struct page *page, int numpages, int enable)
> -{
> -	__kernel_map_pages(page, numpages, enable);
> -}
> -
>   static inline void debug_pagealloc_map_pages(struct page *page,
>   					     int numpages, int enable)
>   {
> @@ -2948,8 +2938,6 @@ static inline void debug_pagealloc_map_pages(struct page *page,
>   extern bool kernel_page_present(struct page *page);
>   #endif	/* CONFIG_HIBERNATION */
>   #else	/* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */
> -static inline void
> -kernel_map_pages(struct page *page, int numpages, int enable) {}
>   static inline void debug_pagealloc_map_pages(struct page *page,
>   					     int numpages, int enable) {}
>   #ifdef CONFIG_HIBERNATION
> diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
> index 46b1804c1ddf..054c8cce4236 100644
> --- a/kernel/power/snapshot.c
> +++ b/kernel/power/snapshot.c
> @@ -76,6 +76,32 @@ static inline void hibernate_restore_protect_page(void *page_address) {}
>   static inline void hibernate_restore_unprotect_page(void *page_address) {}
>   #endif /* CONFIG_STRICT_KERNEL_RWX  && CONFIG_ARCH_HAS_SET_MEMORY */
>   
> +static inline void hibernate_map_page(struct page *page, int enable)
> +{
> +	if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
> +		unsigned long addr = (unsigned long)page_address(page);
> +		int ret;
> +
> +		/*
> +		 * This should not fail because remapping a page here means
> +		 * that we only update protection bits in an existing PTE.
> +		 * It is still worth to have WARN_ON() here if something
> +		 * changes and this will no longer be the case.
> +		 */
> +		if (enable)
> +			ret = set_direct_map_default_noflush(page);
> +		else
> +			ret = set_direct_map_invalid_noflush(page);
> +
> +		if (WARN_ON(ret))
> +			return;

People seem to prefer pr_warn() now that production kernels have panic 
on warn enabled. It's weird.

> +
> +		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
> +	} else {
> +		debug_pagealloc_map_pages(page, 1, enable);

Reviewed-by: David Hildenbrand <david@redhat.com>
Mike Rapoport Nov. 2, 2020, 3:12 p.m. UTC | #2 
On Mon, Nov 02, 2020 at 10:19:36AM +0100, David Hildenbrand wrote:
> On 01.11.20 18:08, Mike Rapoport wrote:
> > From: Mike Rapoport <rppt@linux.ibm.com>
> > 
> > When DEBUG_PAGEALLOC or ARCH_HAS_SET_DIRECT_MAP is enabled a page may be
> > not present in the direct map and has to be explicitly mapped before it
> > could be copied.
> > 
> > Introduce hibernate_map_page() that will explicitly use
> > set_direct_map_{default,invalid}_noflush() for ARCH_HAS_SET_DIRECT_MAP case
> > and debug_pagealloc_map_pages() for DEBUG_PAGEALLOC case.
> > 
> > The remapping of the pages in safe_copy_page() presumes that it only
> > changes protection bits in an existing PTE and so it is safe to ignore
> > return value of set_direct_map_{default,invalid}_noflush().
> > 
> > Still, add a WARN_ON() so that future changes in set_memory APIs will not
> > silently break hibernation.
> > 
> > Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
> > Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
> > ---
> >   include/linux/mm.h      | 12 ------------
> >   kernel/power/snapshot.c | 30 ++++++++++++++++++++++++++++--
> >   2 files changed, 28 insertions(+), 14 deletions(-)
> > 
> > diff --git a/include/linux/mm.h b/include/linux/mm.h
> > index 1fc0609056dc..14e397f3752c 100644
> > --- a/include/linux/mm.h
> > +++ b/include/linux/mm.h
> > @@ -2927,16 +2927,6 @@ static inline bool debug_pagealloc_enabled_static(void)
> >   #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP)
> >   extern void __kernel_map_pages(struct page *page, int numpages, int enable);
> > -/*
> > - * When called in DEBUG_PAGEALLOC context, the call should most likely be
> > - * guarded by debug_pagealloc_enabled() or debug_pagealloc_enabled_static()
> > - */
> > -static inline void
> > -kernel_map_pages(struct page *page, int numpages, int enable)
> > -{
> > -	__kernel_map_pages(page, numpages, enable);
> > -}
> > -
> >   static inline void debug_pagealloc_map_pages(struct page *page,
> >   					     int numpages, int enable)
> >   {
> > @@ -2948,8 +2938,6 @@ static inline void debug_pagealloc_map_pages(struct page *page,
> >   extern bool kernel_page_present(struct page *page);
> >   #endif	/* CONFIG_HIBERNATION */
> >   #else	/* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */
> > -static inline void
> > -kernel_map_pages(struct page *page, int numpages, int enable) {}
> >   static inline void debug_pagealloc_map_pages(struct page *page,
> >   					     int numpages, int enable) {}
> >   #ifdef CONFIG_HIBERNATION
> > diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
> > index 46b1804c1ddf..054c8cce4236 100644
> > --- a/kernel/power/snapshot.c
> > +++ b/kernel/power/snapshot.c
> > @@ -76,6 +76,32 @@ static inline void hibernate_restore_protect_page(void *page_address) {}
> >   static inline void hibernate_restore_unprotect_page(void *page_address) {}
> >   #endif /* CONFIG_STRICT_KERNEL_RWX  && CONFIG_ARCH_HAS_SET_MEMORY */
> > +static inline void hibernate_map_page(struct page *page, int enable)
> > +{
> > +	if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
> > +		unsigned long addr = (unsigned long)page_address(page);
> > +		int ret;
> > +
> > +		/*
> > +		 * This should not fail because remapping a page here means
> > +		 * that we only update protection bits in an existing PTE.
> > +		 * It is still worth to have WARN_ON() here if something
> > +		 * changes and this will no longer be the case.
> > +		 */
> > +		if (enable)
> > +			ret = set_direct_map_default_noflush(page);
> > +		else
> > +			ret = set_direct_map_invalid_noflush(page);
> > +
> > +		if (WARN_ON(ret))
> > +			return;
> 
> People seem to prefer pr_warn() now that production kernels have panic on
> warn enabled. It's weird.

Weird indeed as the whole point of WARN to yell without causing a
crash...
I can change to pr_warn though...

> > +
> > +		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
> > +	} else {
> > +		debug_pagealloc_map_pages(page, 1, enable);
> 
> Reviewed-by: David Hildenbrand <david@redhat.com>

Thanks!

> -- 
> Thanks,
> 
> David / dhildenb
>
Kirill A . Shutemov Nov. 3, 2020, 11:08 a.m. UTC | #3 
On Sun, Nov 01, 2020 at 07:08:13PM +0200, Mike Rapoport wrote:
> diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
> index 46b1804c1ddf..054c8cce4236 100644
> --- a/kernel/power/snapshot.c
> +++ b/kernel/power/snapshot.c
> @@ -76,6 +76,32 @@ static inline void hibernate_restore_protect_page(void *page_address) {}
>  static inline void hibernate_restore_unprotect_page(void *page_address) {}
>  #endif /* CONFIG_STRICT_KERNEL_RWX  && CONFIG_ARCH_HAS_SET_MEMORY */
>  
> +static inline void hibernate_map_page(struct page *page, int enable)
> +{
> +	if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
> +		unsigned long addr = (unsigned long)page_address(page);
> +		int ret;
> +
> +		/*
> +		 * This should not fail because remapping a page here means
> +		 * that we only update protection bits in an existing PTE.
> +		 * It is still worth to have WARN_ON() here if something
> +		 * changes and this will no longer be the case.
> +		 */
> +		if (enable)
> +			ret = set_direct_map_default_noflush(page);
> +		else
> +			ret = set_direct_map_invalid_noflush(page);
> +
> +		if (WARN_ON(ret))

_ONCE?
> +			return;
> +
> +		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
> +	} else {
> +		debug_pagealloc_map_pages(page, 1, enable);
> +	}
> +}
> +
>  static int swsusp_page_is_free(struct page *);
>  static void swsusp_set_page_forbidden(struct page *);
>  static void swsusp_unset_page_forbidden(struct page *);
Mike Rapoport Nov. 3, 2020, 12:13 p.m. UTC | #4 
On Tue, Nov 03, 2020 at 02:08:16PM +0300, Kirill A. Shutemov wrote:
> On Sun, Nov 01, 2020 at 07:08:13PM +0200, Mike Rapoport wrote:
> > diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
> > index 46b1804c1ddf..054c8cce4236 100644
> > --- a/kernel/power/snapshot.c
> > +++ b/kernel/power/snapshot.c
> > @@ -76,6 +76,32 @@ static inline void hibernate_restore_protect_page(void *page_address) {}
> >  static inline void hibernate_restore_unprotect_page(void *page_address) {}
> >  #endif /* CONFIG_STRICT_KERNEL_RWX  && CONFIG_ARCH_HAS_SET_MEMORY */
> >  
> > +static inline void hibernate_map_page(struct page *page, int enable)
> > +{
> > +	if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
> > +		unsigned long addr = (unsigned long)page_address(page);
> > +		int ret;
> > +
> > +		/*
> > +		 * This should not fail because remapping a page here means
> > +		 * that we only update protection bits in an existing PTE.
> > +		 * It is still worth to have WARN_ON() here if something
> > +		 * changes and this will no longer be the case.
> > +		 */
> > +		if (enable)
> > +			ret = set_direct_map_default_noflush(page);
> > +		else
> > +			ret = set_direct_map_invalid_noflush(page);
> > +
> > +		if (WARN_ON(ret))
> 
> _ONCE?

I've changed it to pr_warn() after David said people enable panic on
warn in production kernels.

> > +			return;
> > +
> > +		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
> > +	} else {
> > +		debug_pagealloc_map_pages(page, 1, enable);
> > +	}
> > +}
> > +
> >  static int swsusp_page_is_free(struct page *);
> >  static void swsusp_set_page_forbidden(struct page *);
> >  static void swsusp_unset_page_forbidden(struct page *);
> 
> -- 
>  Kirill A. Shutemov
Kirill A . Shutemov Nov. 3, 2020, 2:39 p.m. UTC | #5 
On Tue, Nov 03, 2020 at 02:13:50PM +0200, Mike Rapoport wrote:
> On Tue, Nov 03, 2020 at 02:08:16PM +0300, Kirill A. Shutemov wrote:
> > On Sun, Nov 01, 2020 at 07:08:13PM +0200, Mike Rapoport wrote:
> > > diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
> > > index 46b1804c1ddf..054c8cce4236 100644
> > > --- a/kernel/power/snapshot.c
> > > +++ b/kernel/power/snapshot.c
> > > @@ -76,6 +76,32 @@ static inline void hibernate_restore_protect_page(void *page_address) {}
> > >  static inline void hibernate_restore_unprotect_page(void *page_address) {}
> > >  #endif /* CONFIG_STRICT_KERNEL_RWX  && CONFIG_ARCH_HAS_SET_MEMORY */
> > >  
> > > +static inline void hibernate_map_page(struct page *page, int enable)
> > > +{
> > > +	if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
> > > +		unsigned long addr = (unsigned long)page_address(page);
> > > +		int ret;
> > > +
> > > +		/*
> > > +		 * This should not fail because remapping a page here means
> > > +		 * that we only update protection bits in an existing PTE.
> > > +		 * It is still worth to have WARN_ON() here if something
> > > +		 * changes and this will no longer be the case.
> > > +		 */
> > > +		if (enable)
> > > +			ret = set_direct_map_default_noflush(page);
> > > +		else
> > > +			ret = set_direct_map_invalid_noflush(page);
> > > +
> > > +		if (WARN_ON(ret))
> > 
> > _ONCE?
> 
> I've changed it to pr_warn() after David said people enable panic on
> warn in production kernels.

pr_warn_once()? :P
Mike Rapoport Nov. 3, 2020, 3:56 p.m. UTC | #6 
On Tue, Nov 03, 2020 at 05:39:16PM +0300, Kirill A. Shutemov wrote:
> On Tue, Nov 03, 2020 at 02:13:50PM +0200, Mike Rapoport wrote:
> > > > +
> > > > +		if (WARN_ON(ret))
> > > 
> > > _ONCE?
> > 
> > I've changed it to pr_warn() after David said people enable panic on
> > warn in production kernels.
> 
> pr_warn_once()? :P

Sure :)
diff mbox series

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1fc0609056dc..14e397f3752c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2927,16 +2927,6 @@  static inline bool debug_pagealloc_enabled_static(void)
 #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP)
 extern void __kernel_map_pages(struct page *page, int numpages, int enable);
 
-/*
- * When called in DEBUG_PAGEALLOC context, the call should most likely be
- * guarded by debug_pagealloc_enabled() or debug_pagealloc_enabled_static()
- */
-static inline void
-kernel_map_pages(struct page *page, int numpages, int enable)
-{
-	__kernel_map_pages(page, numpages, enable);
-}
-
 static inline void debug_pagealloc_map_pages(struct page *page,
 					     int numpages, int enable)
 {
@@ -2948,8 +2938,6 @@  static inline void debug_pagealloc_map_pages(struct page *page,
 extern bool kernel_page_present(struct page *page);
 #endif	/* CONFIG_HIBERNATION */
 #else	/* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */
-static inline void
-kernel_map_pages(struct page *page, int numpages, int enable) {}
 static inline void debug_pagealloc_map_pages(struct page *page,
 					     int numpages, int enable) {}
 #ifdef CONFIG_HIBERNATION
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 46b1804c1ddf..054c8cce4236 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -76,6 +76,32 @@  static inline void hibernate_restore_protect_page(void *page_address) {}
 static inline void hibernate_restore_unprotect_page(void *page_address) {}
 #endif /* CONFIG_STRICT_KERNEL_RWX  && CONFIG_ARCH_HAS_SET_MEMORY */
 
+static inline void hibernate_map_page(struct page *page, int enable)
+{
+	if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
+		unsigned long addr = (unsigned long)page_address(page);
+		int ret;
+
+		/*
+		 * This should not fail because remapping a page here means
+		 * that we only update protection bits in an existing PTE.
+		 * It is still worth to have WARN_ON() here if something
+		 * changes and this will no longer be the case.
+		 */
+		if (enable)
+			ret = set_direct_map_default_noflush(page);
+		else
+			ret = set_direct_map_invalid_noflush(page);
+
+		if (WARN_ON(ret))
+			return;
+
+		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+	} else {
+		debug_pagealloc_map_pages(page, 1, enable);
+	}
+}
+
 static int swsusp_page_is_free(struct page *);
 static void swsusp_set_page_forbidden(struct page *);
 static void swsusp_unset_page_forbidden(struct page *);
@@ -1355,9 +1381,9 @@  static void safe_copy_page(void *dst, struct page *s_page)
 	if (kernel_page_present(s_page)) {
 		do_copy_page(dst, page_address(s_page));
 	} else {
-		kernel_map_pages(s_page, 1, 1);
+		hibernate_map_page(s_page, 1);
 		do_copy_page(dst, page_address(s_page));
-		kernel_map_pages(s_page, 1, 0);
+		hibernate_map_page(s_page, 0);
 	}
 }