| Message ID | 20201101170815.9795-3-rppt@kernel.org |
|---|---|
| State | New |
| Headers | show |
| Series | arch, mm: improve robustness of direct map manipulation | expand |
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> -- Thanks, David / dhildenb
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 > -- Sincerely yours, Mike.
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 *); -- Kirill A. Shutemov
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 -- Sincerely yours, Mike.
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 -- Kirill A. Shutemov
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 :) -- Sincerely yours, Mike.
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); } }