| Message ID | 20201103162057.22916-3-rppt@kernel.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | arch, mm: improve robustness of direct map manipulation | expand |
On 11/3/20 5:20 PM, 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 pr_warn() 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> > Reviewed-by: David Hildenbrand <david@redhat.com> > Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> The bool param is a bit more acceptable here, being a private API. But if debug_pagealloc_map_pages() becomes split, then it might be easier to split this one too... > --- > include/linux/mm.h | 12 ------------ > kernel/power/snapshot.c | 32 ++++++++++++++++++++++++++++++-- > 2 files changed, 30 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..57d54b9d84bb 100644 > --- a/kernel/power/snapshot.c > +++ b/kernel/power/snapshot.c > @@ -76,6 +76,34 @@ 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 a warning 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 (ret) { > + pr_warn_once("Failed to remap page\n"); > + 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 +1383,9 @@ 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); > } > } > >
On Wed, Nov 04, 2020 at 06:40:28PM +0100, Vlastimil Babka wrote: > On 11/3/20 5:20 PM, 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 pr_warn() 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> > > Reviewed-by: David Hildenbrand <david@redhat.com> > > Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> > > Acked-by: Vlastimil Babka <vbabka@suse.cz> > > The bool param is a bit more acceptable here, being a private API. But if > debug_pagealloc_map_pages() becomes split, then it might be easier to split > this one too... Let's split here as well. > > --- > > include/linux/mm.h | 12 ------------ > > kernel/power/snapshot.c | 32 ++++++++++++++++++++++++++++++-- > > 2 files changed, 30 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..57d54b9d84bb 100644 > > --- a/kernel/power/snapshot.c > > +++ b/kernel/power/snapshot.c > > @@ -76,6 +76,34 @@ 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 a warning 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 (ret) { > > + pr_warn_once("Failed to remap page\n"); > > + 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 +1383,9 @@ 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); > > } > > } > > >
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..57d54b9d84bb 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -76,6 +76,34 @@ 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 a warning 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 (ret) { + pr_warn_once("Failed to remap page\n"); + 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 +1383,9 @@ 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); } }