| Message ID | 20220706082016.2603916-5-chao.p.peng@linux.intel.com |
|---|---|
| State | New |
| Headers | show |
| Series | KVM: mm: fd-based approach for supporting KVM guest private memory | expand |
On 7/6/2022 10:20 AM, Chao Peng wrote: > From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> > > Implement shmem as a memfile_notifier backing store. Essentially it > interacts with the memfile_notifier feature flags for userspace > access/page migration/page reclaiming and implements the necessary > memfile_backing_store callbacks. > > Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> > Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com> > --- > include/linux/shmem_fs.h | 2 + > mm/shmem.c | 109 ++++++++++++++++++++++++++++++++++++++- > 2 files changed, 110 insertions(+), 1 deletion(-) > > diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h > index a68f982f22d1..6031c0b08d26 100644 > --- a/include/linux/shmem_fs.h > +++ b/include/linux/shmem_fs.h > @@ -9,6 +9,7 @@ > #include <linux/percpu_counter.h> > #include <linux/xattr.h> > #include <linux/fs_parser.h> > +#include <linux/memfile_notifier.h> > > /* inode in-kernel data */ > > @@ -25,6 +26,7 @@ struct shmem_inode_info { > struct simple_xattrs xattrs; /* list of xattrs */ > atomic_t stop_eviction; /* hold when working on inode */ > struct timespec64 i_crtime; /* file creation time */ > + struct memfile_node memfile_node; /* memfile node */ > struct inode vfs_inode; > }; > > diff --git a/mm/shmem.c b/mm/shmem.c > index 6c8aef15a17d..627e315c3b4d 100644 > --- a/mm/shmem.c > +++ b/mm/shmem.c > @@ -905,6 +905,17 @@ static struct folio *shmem_get_partial_folio(struct inode *inode, pgoff_t index) > return page ? page_folio(page) : NULL; > } > > +static void notify_invalidate(struct inode *inode, struct folio *folio, > + pgoff_t start, pgoff_t end) > +{ > + struct shmem_inode_info *info = SHMEM_I(inode); > + > + start = max(start, folio->index); > + end = min(end, folio->index + folio_nr_pages(folio)); > + > + memfile_notifier_invalidate(&info->memfile_node, start, end); > +} > + > /* > * Remove range of pages and swap entries from page cache, and free them. > * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate. > @@ -948,6 +959,8 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, > } > index += folio_nr_pages(folio) - 1; > > + notify_invalidate(inode, folio, start, end); > + > if (!unfalloc || !folio_test_uptodate(folio)) > truncate_inode_folio(mapping, folio); > folio_unlock(folio); > @@ -1021,6 +1034,9 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, > index--; > break; > } > + > + notify_invalidate(inode, folio, start, end); > + > VM_BUG_ON_FOLIO(folio_test_writeback(folio), > folio); > truncate_inode_folio(mapping, folio); > @@ -1092,6 +1108,13 @@ static int shmem_setattr(struct user_namespace *mnt_userns, > (newsize > oldsize && (info->seals & F_SEAL_GROW))) > return -EPERM; > > + if (info->memfile_node.flags & MEMFILE_F_USER_INACCESSIBLE) { > + if (oldsize) > + return -EPERM; > + if (!PAGE_ALIGNED(newsize)) > + return -EINVAL; > + } > + > if (newsize != oldsize) { > error = shmem_reacct_size(SHMEM_I(inode)->flags, > oldsize, newsize); > @@ -1336,6 +1359,8 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) > goto redirty; > if (!total_swap_pages) > goto redirty; > + if (info->memfile_node.flags & MEMFILE_F_UNRECLAIMABLE) > + goto redirty; > > /* > * Our capabilities prevent regular writeback or sync from ever calling > @@ -2271,6 +2296,9 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) > if (ret) > return ret; > > + if (info->memfile_node.flags & MEMFILE_F_USER_INACCESSIBLE) > + return -EPERM; > + > /* arm64 - allow memory tagging on RAM-based files */ > vma->vm_flags |= VM_MTE_ALLOWED; > > @@ -2306,6 +2334,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode > info->i_crtime = inode->i_mtime; > INIT_LIST_HEAD(&info->shrinklist); > INIT_LIST_HEAD(&info->swaplist); > + memfile_node_init(&info->memfile_node); > simple_xattrs_init(&info->xattrs); > cache_no_acl(inode); > mapping_set_large_folios(inode->i_mapping); > @@ -2477,6 +2506,8 @@ shmem_write_begin(struct file *file, struct address_space *mapping, > if ((info->seals & F_SEAL_GROW) && pos + len > inode->i_size) > return -EPERM; > } > + if (unlikely(info->memfile_node.flags & MEMFILE_F_USER_INACCESSIBLE)) > + return -EPERM; > > if (unlikely(info->seals & F_SEAL_AUTO_ALLOCATE)) > sgp = SGP_NOALLOC; > @@ -2556,6 +2587,13 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) > end_index = i_size >> PAGE_SHIFT; > if (index > end_index) > break; > + > + if (SHMEM_I(inode)->memfile_node.flags & > + MEMFILE_F_USER_INACCESSIBLE) { > + error = -EPERM; > + break; > + } > + > if (index == end_index) { > nr = i_size & ~PAGE_MASK; > if (nr <= offset) > @@ -2697,6 +2735,12 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, > goto out; > } > > + if ((info->memfile_node.flags & MEMFILE_F_USER_INACCESSIBLE) && > + (!PAGE_ALIGNED(offset) || !PAGE_ALIGNED(len))) { > + error = -EINVAL; > + goto out; > + } > + > shmem_falloc.waitq = &shmem_falloc_waitq; > shmem_falloc.start = (u64)unmap_start >> PAGE_SHIFT; > shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT; > @@ -3806,6 +3850,20 @@ static int shmem_error_remove_page(struct address_space *mapping, > return 0; > } > > +#ifdef CONFIG_MIGRATION > +static int shmem_migrate_page(struct address_space *mapping, > + struct page *newpage, struct page *page, > + enum migrate_mode mode) > +{ > + struct inode *inode = mapping->host; > + struct shmem_inode_info *info = SHMEM_I(inode); > + > + if (info->memfile_node.flags & MEMFILE_F_UNMOVABLE) > + return -EOPNOTSUPP; > + return migrate_page(mapping, newpage, page, mode); Wondering how well page migrate would work for private pages on shmem memfd based backend? > +} > +#endif > + > const struct address_space_operations shmem_aops = { > .writepage = shmem_writepage, > .dirty_folio = noop_dirty_folio, > @@ -3814,7 +3872,7 @@ const struct address_space_operations shmem_aops = { > .write_end = shmem_write_end, > #endif > #ifdef CONFIG_MIGRATION > - .migratepage = migrate_page, > + .migratepage = shmem_migrate_page, > #endif > .error_remove_page = shmem_error_remove_page, > }; > @@ -3931,6 +3989,51 @@ static struct file_system_type shmem_fs_type = { > .fs_flags = FS_USERNS_MOUNT, > }; > > +#ifdef CONFIG_MEMFILE_NOTIFIER > +static struct memfile_node *shmem_lookup_memfile_node(struct file *file) > +{ > + struct inode *inode = file_inode(file); > + > + if (!shmem_mapping(inode->i_mapping)) > + return NULL; > + > + return &SHMEM_I(inode)->memfile_node; > +} > + > + > +static int shmem_get_pfn(struct file *file, pgoff_t offset, pfn_t *pfn, > + int *order) > +{ > + struct page *page; > + int ret; > + > + ret = shmem_getpage(file_inode(file), offset, &page, SGP_WRITE); > + if (ret) > + return ret; > + > + unlock_page(page); > + *pfn = page_to_pfn_t(page); > + *order = thp_order(compound_head(page)); > + return 0; > +} > + > +static void shmem_put_pfn(pfn_t pfn) > +{ > + struct page *page = pfn_t_to_page(pfn); > + > + if (!page) > + return; > + > + put_page(page); > +} > + > +static struct memfile_backing_store shmem_backing_store = { > + .lookup_memfile_node = shmem_lookup_memfile_node, > + .get_pfn = shmem_get_pfn, > + .put_pfn = shmem_put_pfn, > +}; > +#endif /* CONFIG_MEMFILE_NOTIFIER */ > + > void __init shmem_init(void) > { > int error; > @@ -3956,6 +4059,10 @@ void __init shmem_init(void) > else > shmem_huge = SHMEM_HUGE_NEVER; /* just in case it was patched */ > #endif > + > +#ifdef CONFIG_MEMFILE_NOTIFIER > + memfile_register_backing_store(&shmem_backing_store); > +#endif > return; > > out1:
On Tue, Jul 12, 2022 at 08:02:34PM +0200, Gupta, Pankaj wrote: > On 7/6/2022 10:20 AM, Chao Peng wrote: > > From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> > > > > Implement shmem as a memfile_notifier backing store. Essentially it > > interacts with the memfile_notifier feature flags for userspace > > access/page migration/page reclaiming and implements the necessary > > memfile_backing_store callbacks. > > > > Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> > > Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com> > > --- > > include/linux/shmem_fs.h | 2 + > > mm/shmem.c | 109 ++++++++++++++++++++++++++++++++++++++- > > 2 files changed, 110 insertions(+), 1 deletion(-) ... > > +#ifdef CONFIG_MIGRATION > > +static int shmem_migrate_page(struct address_space *mapping, > > + struct page *newpage, struct page *page, > > + enum migrate_mode mode) > > +{ > > + struct inode *inode = mapping->host; > > + struct shmem_inode_info *info = SHMEM_I(inode); > > + > > + if (info->memfile_node.flags & MEMFILE_F_UNMOVABLE) > > + return -EOPNOTSUPP; > > + return migrate_page(mapping, newpage, page, mode); > > Wondering how well page migrate would work for private pages > on shmem memfd based backend?
>>> +#ifdef CONFIG_MIGRATION >>> +static int shmem_migrate_page(struct address_space *mapping, >>> + struct page *newpage, struct page *page, >>> + enum migrate_mode mode) >>> +{ >>> + struct inode *inode = mapping->host; >>> + struct shmem_inode_info *info = SHMEM_I(inode); >>> + >>> + if (info->memfile_node.flags & MEMFILE_F_UNMOVABLE) >>> + return -EOPNOTSUPP; >>> + return migrate_page(mapping, newpage, page, mode); >> >> Wondering how well page migrate would work for private pages >> on shmem memfd based backend? > > From high level: > - KVM unset MEMFILE_F_UNMOVABLE bit to indicate it capable of > migrating a page. > - Introduce new 'migrate' callback(s) to memfile_notifier_ops for KVM > to register. > - The callback is hooked to migrate_page() here. > - Once page migration requested, shmem calls into the 'migrate' > callback(s) to perform additional steps for encrypted memory (For > TDX we will call TDH.MEM.PAGE.RELOCATE). Yes, that would require additional (protocol specific) handling for private pages. Was trying to find where "MEMFILE_F_UNMOVABLE" flag is set currently? Thanks, Pankaj
On Wed, Jul 13, 2022 at 12:01:13PM +0200, Gupta, Pankaj wrote: > > > > > +#ifdef CONFIG_MIGRATION > > > > +static int shmem_migrate_page(struct address_space *mapping, > > > > + struct page *newpage, struct page *page, > > > > + enum migrate_mode mode) > > > > +{ > > > > + struct inode *inode = mapping->host; > > > > + struct shmem_inode_info *info = SHMEM_I(inode); > > > > + > > > > + if (info->memfile_node.flags & MEMFILE_F_UNMOVABLE) > > > > + return -EOPNOTSUPP; > > > > + return migrate_page(mapping, newpage, page, mode); > > > > > > Wondering how well page migrate would work for private pages > > > on shmem memfd based backend? > > > > From high level: > > - KVM unset MEMFILE_F_UNMOVABLE bit to indicate it capable of > > migrating a page. > > - Introduce new 'migrate' callback(s) to memfile_notifier_ops for KVM > > to register. > > - The callback is hooked to migrate_page() here. > > - Once page migration requested, shmem calls into the 'migrate' > > callback(s) to perform additional steps for encrypted memory (For > > TDX we will call TDH.MEM.PAGE.RELOCATE). > > Yes, that would require additional (protocol specific) handling for private > pages. Was trying to find where "MEMFILE_F_UNMOVABLE" flag is set currently? It's set with memfile_register_notifier() in patch 13. > > Thanks, > Pankaj
On 06.07.22 10:20, Chao Peng wrote: > From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> > > Implement shmem as a memfile_notifier backing store. Essentially it > interacts with the memfile_notifier feature flags for userspace > access/page migration/page reclaiming and implements the necessary > memfile_backing_store callbacks. > > Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> > Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com> > --- [...] > +#ifdef CONFIG_MEMFILE_NOTIFIER > +static struct memfile_node *shmem_lookup_memfile_node(struct file *file) > +{ > + struct inode *inode = file_inode(file); > + > + if (!shmem_mapping(inode->i_mapping)) > + return NULL; > + > + return &SHMEM_I(inode)->memfile_node; > +} > + > + > +static int shmem_get_pfn(struct file *file, pgoff_t offset, pfn_t *pfn, > + int *order) > +{ > + struct page *page; > + int ret; > + > + ret = shmem_getpage(file_inode(file), offset, &page, SGP_WRITE); > + if (ret) > + return ret; > + > + unlock_page(page); > + *pfn = page_to_pfn_t(page); > + *order = thp_order(compound_head(page)); > + return 0; > +} > + > +static void shmem_put_pfn(pfn_t pfn) > +{ > + struct page *page = pfn_t_to_page(pfn); > + > + if (!page) > + return; > + > + put_page(page); Why do we export shmem_get_pfn/shmem_put_pfn and not simply get_folio() and let the caller deal with putting the folio? What's the reason to a) Operate on PFNs and not folios b) Have these get/put semantics? > +} > + > +static struct memfile_backing_store shmem_backing_store = { > + .lookup_memfile_node = shmem_lookup_memfile_node, > + .get_pfn = shmem_get_pfn, > + .put_pfn = shmem_put_pfn, > +}; > +#endif /* CONFIG_MEMFILE_NOTIFIER */ > + > void __init shmem_init(void) > { > int error; > @@ -3956,6 +4059,10 @@ void __init shmem_init(void) > else > shmem_huge = SHMEM_HUGE_NEVER; /* just in case it was patched */ > #endif > + > +#ifdef CONFIG_MEMFILE_NOTIFIER > + memfile_register_backing_store(&shmem_backing_store); Can we instead prove a dummy function that does nothing without CONFIG_MEMFILE_NOTIFIER? > +#endif > return; > > out1:
On Fri, Aug 05, 2022 at 03:26:02PM +0200, David Hildenbrand wrote: > On 06.07.22 10:20, Chao Peng wrote: > > From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> > > > > Implement shmem as a memfile_notifier backing store. Essentially it > > interacts with the memfile_notifier feature flags for userspace > > access/page migration/page reclaiming and implements the necessary > > memfile_backing_store callbacks. > > > > Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> > > Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com> > > --- > > [...] > > > +#ifdef CONFIG_MEMFILE_NOTIFIER > > +static struct memfile_node *shmem_lookup_memfile_node(struct file *file) > > +{ > > + struct inode *inode = file_inode(file); > > + > > + if (!shmem_mapping(inode->i_mapping)) > > + return NULL; > > + > > + return &SHMEM_I(inode)->memfile_node; > > +} > > + > > + > > +static int shmem_get_pfn(struct file *file, pgoff_t offset, pfn_t *pfn, > > + int *order) > > +{ > > + struct page *page; > > + int ret; > > + > > + ret = shmem_getpage(file_inode(file), offset, &page, SGP_WRITE); > > + if (ret) > > + return ret; > > + > > + unlock_page(page); > > + *pfn = page_to_pfn_t(page); > > + *order = thp_order(compound_head(page)); > > + return 0; > > +} > > + > > +static void shmem_put_pfn(pfn_t pfn) > > +{ > > + struct page *page = pfn_t_to_page(pfn); > > + > > + if (!page) > > + return; > > + > > + put_page(page); > > > Why do we export shmem_get_pfn/shmem_put_pfn and not simply > > get_folio() > > and let the caller deal with putting the folio? What's the reason to > > a) Operate on PFNs and not folios > b) Have these get/put semantics? We have a design assumption that somedays this can even support non-page based backing stores. There are some discussions: https://lkml.org/lkml/2022/3/28/1440 I should add document for this two callbacks. > > > +} > > + > > +static struct memfile_backing_store shmem_backing_store = { > > + .lookup_memfile_node = shmem_lookup_memfile_node, > > + .get_pfn = shmem_get_pfn, > > + .put_pfn = shmem_put_pfn, > > +}; > > +#endif /* CONFIG_MEMFILE_NOTIFIER */ > > + > > void __init shmem_init(void) > > { > > int error; > > @@ -3956,6 +4059,10 @@ void __init shmem_init(void) > > else > > shmem_huge = SHMEM_HUGE_NEVER; /* just in case it was patched */ > > #endif > > + > > +#ifdef CONFIG_MEMFILE_NOTIFIER > > + memfile_register_backing_store(&shmem_backing_store); > > Can we instead prove a dummy function that does nothing without > CONFIG_MEMFILE_NOTIFIER? Sounds good. Chao > > > +#endif > > return; > > > > out1: > > > -- > Thanks, > > David / dhildenb >
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index a68f982f22d1..6031c0b08d26 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -9,6 +9,7 @@ #include <linux/percpu_counter.h> #include <linux/xattr.h> #include <linux/fs_parser.h> +#include <linux/memfile_notifier.h> /* inode in-kernel data */ @@ -25,6 +26,7 @@ struct shmem_inode_info { struct simple_xattrs xattrs; /* list of xattrs */ atomic_t stop_eviction; /* hold when working on inode */ struct timespec64 i_crtime; /* file creation time */ + struct memfile_node memfile_node; /* memfile node */ struct inode vfs_inode; }; diff --git a/mm/shmem.c b/mm/shmem.c index 6c8aef15a17d..627e315c3b4d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -905,6 +905,17 @@ static struct folio *shmem_get_partial_folio(struct inode *inode, pgoff_t index) return page ? page_folio(page) : NULL; } +static void notify_invalidate(struct inode *inode, struct folio *folio, + pgoff_t start, pgoff_t end) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + + start = max(start, folio->index); + end = min(end, folio->index + folio_nr_pages(folio)); + + memfile_notifier_invalidate(&info->memfile_node, start, end); +} + /* * Remove range of pages and swap entries from page cache, and free them. * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate. @@ -948,6 +959,8 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, } index += folio_nr_pages(folio) - 1; + notify_invalidate(inode, folio, start, end); + if (!unfalloc || !folio_test_uptodate(folio)) truncate_inode_folio(mapping, folio); folio_unlock(folio); @@ -1021,6 +1034,9 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, index--; break; } + + notify_invalidate(inode, folio, start, end); + VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); truncate_inode_folio(mapping, folio); @@ -1092,6 +1108,13 @@ static int shmem_setattr(struct user_namespace *mnt_userns, (newsize > oldsize && (info->seals & F_SEAL_GROW))) return -EPERM; + if (info->memfile_node.flags & MEMFILE_F_USER_INACCESSIBLE) { + if (oldsize) + return -EPERM; + if (!PAGE_ALIGNED(newsize)) + return -EINVAL; + } + if (newsize != oldsize) { error = shmem_reacct_size(SHMEM_I(inode)->flags, oldsize, newsize); @@ -1336,6 +1359,8 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) goto redirty; if (!total_swap_pages) goto redirty; + if (info->memfile_node.flags & MEMFILE_F_UNRECLAIMABLE) + goto redirty; /* * Our capabilities prevent regular writeback or sync from ever calling @@ -2271,6 +2296,9 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) if (ret) return ret; + if (info->memfile_node.flags & MEMFILE_F_USER_INACCESSIBLE) + return -EPERM; + /* arm64 - allow memory tagging on RAM-based files */ vma->vm_flags |= VM_MTE_ALLOWED; @@ -2306,6 +2334,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode info->i_crtime = inode->i_mtime; INIT_LIST_HEAD(&info->shrinklist); INIT_LIST_HEAD(&info->swaplist); + memfile_node_init(&info->memfile_node); simple_xattrs_init(&info->xattrs); cache_no_acl(inode); mapping_set_large_folios(inode->i_mapping); @@ -2477,6 +2506,8 @@ shmem_write_begin(struct file *file, struct address_space *mapping, if ((info->seals & F_SEAL_GROW) && pos + len > inode->i_size) return -EPERM; } + if (unlikely(info->memfile_node.flags & MEMFILE_F_USER_INACCESSIBLE)) + return -EPERM; if (unlikely(info->seals & F_SEAL_AUTO_ALLOCATE)) sgp = SGP_NOALLOC; @@ -2556,6 +2587,13 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) end_index = i_size >> PAGE_SHIFT; if (index > end_index) break; + + if (SHMEM_I(inode)->memfile_node.flags & + MEMFILE_F_USER_INACCESSIBLE) { + error = -EPERM; + break; + } + if (index == end_index) { nr = i_size & ~PAGE_MASK; if (nr <= offset) @@ -2697,6 +2735,12 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, goto out; } + if ((info->memfile_node.flags & MEMFILE_F_USER_INACCESSIBLE) && + (!PAGE_ALIGNED(offset) || !PAGE_ALIGNED(len))) { + error = -EINVAL; + goto out; + } + shmem_falloc.waitq = &shmem_falloc_waitq; shmem_falloc.start = (u64)unmap_start >> PAGE_SHIFT; shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT; @@ -3806,6 +3850,20 @@ static int shmem_error_remove_page(struct address_space *mapping, return 0; } +#ifdef CONFIG_MIGRATION +static int shmem_migrate_page(struct address_space *mapping, + struct page *newpage, struct page *page, + enum migrate_mode mode) +{ + struct inode *inode = mapping->host; + struct shmem_inode_info *info = SHMEM_I(inode); + + if (info->memfile_node.flags & MEMFILE_F_UNMOVABLE) + return -EOPNOTSUPP; + return migrate_page(mapping, newpage, page, mode); +} +#endif + const struct address_space_operations shmem_aops = { .writepage = shmem_writepage, .dirty_folio = noop_dirty_folio, @@ -3814,7 +3872,7 @@ const struct address_space_operations shmem_aops = { .write_end = shmem_write_end, #endif #ifdef CONFIG_MIGRATION - .migratepage = migrate_page, + .migratepage = shmem_migrate_page, #endif .error_remove_page = shmem_error_remove_page, }; @@ -3931,6 +3989,51 @@ static struct file_system_type shmem_fs_type = { .fs_flags = FS_USERNS_MOUNT, }; +#ifdef CONFIG_MEMFILE_NOTIFIER +static struct memfile_node *shmem_lookup_memfile_node(struct file *file) +{ + struct inode *inode = file_inode(file); + + if (!shmem_mapping(inode->i_mapping)) + return NULL; + + return &SHMEM_I(inode)->memfile_node; +} + + +static int shmem_get_pfn(struct file *file, pgoff_t offset, pfn_t *pfn, + int *order) +{ + struct page *page; + int ret; + + ret = shmem_getpage(file_inode(file), offset, &page, SGP_WRITE); + if (ret) + return ret; + + unlock_page(page); + *pfn = page_to_pfn_t(page); + *order = thp_order(compound_head(page)); + return 0; +} + +static void shmem_put_pfn(pfn_t pfn) +{ + struct page *page = pfn_t_to_page(pfn); + + if (!page) + return; + + put_page(page); +} + +static struct memfile_backing_store shmem_backing_store = { + .lookup_memfile_node = shmem_lookup_memfile_node, + .get_pfn = shmem_get_pfn, + .put_pfn = shmem_put_pfn, +}; +#endif /* CONFIG_MEMFILE_NOTIFIER */ + void __init shmem_init(void) { int error; @@ -3956,6 +4059,10 @@ void __init shmem_init(void) else shmem_huge = SHMEM_HUGE_NEVER; /* just in case it was patched */ #endif + +#ifdef CONFIG_MEMFILE_NOTIFIER + memfile_register_backing_store(&shmem_backing_store); +#endif return; out1: