Message-ID: <c4112b84-9359-d4c8-1852-0057c074607c@amd.com>
Date:   Tue, 12 Jul 2022 20:02:34 +0200
From:   "Gupta, Pankaj" <pankaj.gupta@....com>
To:     Chao Peng <chao.p.peng@...ux.intel.com>, kvm@...r.kernel.org,
        linux-kernel@...r.kernel.org, linux-mm@...ck.org,
        linux-fsdevel@...r.kernel.org, linux-api@...r.kernel.org,
        linux-doc@...r.kernel.org, qemu-devel@...gnu.org,
        linux-kselftest@...r.kernel.org
Cc:     Paolo Bonzini <pbonzini@...hat.com>,
        Jonathan Corbet <corbet@....net>,
        Sean Christopherson <seanjc@...gle.com>,
        Vitaly Kuznetsov <vkuznets@...hat.com>,
        Wanpeng Li <wanpengli@...cent.com>,
        Jim Mattson <jmattson@...gle.com>,
        Joerg Roedel <joro@...tes.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
        x86@...nel.org, "H . Peter Anvin" <hpa@...or.com>,
        Hugh Dickins <hughd@...gle.com>,
        Jeff Layton <jlayton@...nel.org>,
        "J . Bruce Fields" <bfields@...ldses.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Shuah Khan <shuah@...nel.org>, Mike Rapoport <rppt@...nel.org>,
        Steven Price <steven.price@....com>,
        "Maciej S . Szmigiero" <mail@...iej.szmigiero.name>,
        Vlastimil Babka <vbabka@...e.cz>,
        Vishal Annapurve <vannapurve@...gle.com>,
        Yu Zhang <yu.c.zhang@...ux.intel.com>,
        "Kirill A . Shutemov" <kirill.shutemov@...ux.intel.com>,
        luto@...nel.org, jun.nakajima@...el.com, dave.hansen@...el.com,
        ak@...ux.intel.com, david@...hat.com, aarcange@...hat.com,
        ddutile@...hat.com, dhildenb@...hat.com,
        Quentin Perret <qperret@...gle.com>,
        Michael Roth <michael.roth@....com>, mhocko@...e.com,
        Muchun Song <songmuchun@...edance.com>
Subject: Re: [PATCH v7 04/14] mm/shmem: Support memfile_notifier

On 7/6/2022 10:20 AM, Chao Peng wrote:
> From: "Kirill A. Shutemov" <kirill.shutemov@...ux.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@...ux.intel.com>
> Signed-off-by: Chao Peng <chao.p.peng@...ux.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:

Powered by blists - more mailing lists