linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Vishal Annapurve <vannapurve@google.com>
To: Chao Peng <chao.p.peng@linux.intel.com>
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
	linux-api@vger.kernel.org, qemu-devel@nongnu.org,
	Paolo Bonzini <pbonzini@redhat.com>,
	Jonathan Corbet <corbet@lwn.net>,
	Sean Christopherson <seanjc@google.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Wanpeng Li <wanpengli@tencent.com>,
	Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	x86@kernel.org, "H . Peter Anvin" <hpa@zytor.com>,
	Hugh Dickins <hughd@google.com>, Jeff Layton <jlayton@kernel.org>,
	"J . Bruce Fields" <bfields@fieldses.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Mike Rapoport <rppt@kernel.org>,
	Steven Price <steven.price@arm.com>,
	"Maciej S . Szmigiero" <mail@maciej.szmigiero.name>,
	Vlastimil Babka <vbabka@suse.cz>,
	Yu Zhang <yu.c.zhang@linux.intel.com>,
	"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
	Andy Lutomirski <luto@kernel.org>,
	Jun Nakajima <jun.nakajima@intel.com>,
	dave.hansen@intel.com, ak@linux.intel.com, david@redhat.com
Subject: Re: [PATCH v5 03/13] mm/shmem: Support memfile_notifier
Date: Tue, 19 Apr 2022 15:40:09 -0700	[thread overview]
Message-ID: <CAGtprH9X-v-R+UiAvdvKgqAqoc4MBJAWTnoEtP+Y2nip_y8Heg@mail.gmail.com> (raw)
In-Reply-To: <20220310140911.50924-4-chao.p.peng@linux.intel.com>

On Thu, Mar 10, 2022 at 6:10 AM Chao Peng <chao.p.peng@linux.intel.com> wrote:
>
> From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
>
> It maintains a memfile_notifier list in shmem_inode_info structure and
> implements memfile_pfn_ops callbacks defined by memfile_notifier. It
> then exposes them to memfile_notifier via
> shmem_get_memfile_notifier_info.
>
> We use SGP_NOALLOC in shmem_get_lock_pfn since the pages should be
> allocated by userspace for private memory. If there is no pages
> allocated at the offset then error should be returned so KVM knows that
> the memory is not private memory.
>
> 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 |  4 +++
>  mm/shmem.c               | 76 ++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 80 insertions(+)
>
> diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
> index 2dde843f28ef..7bb16f2d2825 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 */
>
> @@ -28,6 +29,9 @@ struct shmem_inode_info {
>         struct simple_xattrs    xattrs;         /* list of xattrs */
>         atomic_t                stop_eviction;  /* hold when working on inode */
>         unsigned int            xflags;         /* shmem extended flags */
> +#ifdef CONFIG_MEMFILE_NOTIFIER
> +       struct memfile_notifier_list memfile_notifiers;
> +#endif
>         struct inode            vfs_inode;
>  };
>
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 9b31a7056009..7b43e274c9a2 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -903,6 +903,28 @@ static struct folio *shmem_get_partial_folio(struct inode *inode, pgoff_t index)
>         return page ? page_folio(page) : NULL;
>  }
>
> +static void notify_fallocate(struct inode *inode, pgoff_t start, pgoff_t end)
> +{
> +#ifdef CONFIG_MEMFILE_NOTIFIER
> +       struct shmem_inode_info *info = SHMEM_I(inode);
> +
> +       memfile_notifier_fallocate(&info->memfile_notifiers, start, end);
> +#endif
> +}
> +
> +static void notify_invalidate_page(struct inode *inode, struct folio *folio,
> +                                  pgoff_t start, pgoff_t end)
> +{
> +#ifdef CONFIG_MEMFILE_NOTIFIER
> +       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_notifiers, start, end);
> +#endif
> +}
> +
>  /*
>   * Remove range of pages and swap entries from page cache, and free them.
>   * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate.
> @@ -946,6 +968,8 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
>                         }
>                         index += folio_nr_pages(folio) - 1;
>
> +                       notify_invalidate_page(inode, folio, start, end);
> +
>                         if (!unfalloc || !folio_test_uptodate(folio))
>                                 truncate_inode_folio(mapping, folio);
>                         folio_unlock(folio);
> @@ -1019,6 +1043,9 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
>                                         index--;
>                                         break;
>                                 }
> +
> +                               notify_invalidate_page(inode, folio, start, end);
> +

Should this be done in batches or done once for all of range [start, end)?

>                                 VM_BUG_ON_FOLIO(folio_test_writeback(folio),
>                                                 folio);
>                                 truncate_inode_folio(mapping, folio);
> @@ -2279,6 +2306,9 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
>                 info->flags = flags & VM_NORESERVE;
>                 INIT_LIST_HEAD(&info->shrinklist);
>                 INIT_LIST_HEAD(&info->swaplist);
> +#ifdef CONFIG_MEMFILE_NOTIFIER
> +               memfile_notifier_list_init(&info->memfile_notifiers);
> +#endif
>                 simple_xattrs_init(&info->xattrs);
>                 cache_no_acl(inode);
>                 mapping_set_large_folios(inode->i_mapping);
> @@ -2802,6 +2832,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
>         if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size)
>                 i_size_write(inode, offset + len);
>         inode->i_ctime = current_time(inode);
> +       notify_fallocate(inode, start, end);
>  undone:
>         spin_lock(&inode->i_lock);
>         inode->i_private = NULL;
> @@ -3909,6 +3940,47 @@ static struct file_system_type shmem_fs_type = {
>         .fs_flags       = FS_USERNS_MOUNT,
>  };
>
> +#ifdef CONFIG_MEMFILE_NOTIFIER
> +static long shmem_get_lock_pfn(struct inode *inode, pgoff_t offset, int *order)
> +{
> +       struct page *page;
> +       int ret;
> +
> +       ret = shmem_getpage(inode, offset, &page, SGP_NOALLOC);
> +       if (ret)
> +               return ret;
> +
> +       *order = thp_order(compound_head(page));
> +
> +       return page_to_pfn(page);
> +}
> +
> +static void shmem_put_unlock_pfn(unsigned long pfn)
> +{
> +       struct page *page = pfn_to_page(pfn);
> +
> +       VM_BUG_ON_PAGE(!PageLocked(page), page);
> +
> +       set_page_dirty(page);
> +       unlock_page(page);
> +       put_page(page);
> +}
> +
> +static struct memfile_notifier_list* shmem_get_notifier_list(struct inode *inode)
> +{
> +       if (!shmem_mapping(inode->i_mapping))
> +               return NULL;
> +
> +       return  &SHMEM_I(inode)->memfile_notifiers;
> +}
> +
> +static struct memfile_backing_store shmem_backing_store = {
> +       .pfn_ops.get_lock_pfn = shmem_get_lock_pfn,
> +       .pfn_ops.put_unlock_pfn = shmem_put_unlock_pfn,
> +       .get_notifier_list = shmem_get_notifier_list,
> +};
> +#endif /* CONFIG_MEMFILE_NOTIFIER */
> +
>  int __init shmem_init(void)
>  {
>         int error;
> @@ -3934,6 +4006,10 @@ int __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 0;
>
>  out1:
> --
> 2.17.1
>

  parent reply	other threads:[~2022-04-19 22:40 UTC|newest]

Thread overview: 117+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-03-10 14:08 [PATCH v5 00/13] KVM: mm: fd-based approach for supporting KVM guest private memory Chao Peng
2022-03-10 14:08 ` [PATCH v5 01/13] mm/memfd: Introduce MFD_INACCESSIBLE flag Chao Peng
2022-04-11 15:10   ` Kirill A. Shutemov
2022-04-12 13:11     ` Chao Peng
2022-04-23  5:43   ` Vishal Annapurve
2022-04-24  8:15     ` Chao Peng
2022-03-10 14:09 ` [PATCH v5 02/13] mm: Introduce memfile_notifier Chao Peng
2022-03-29 18:45   ` Sean Christopherson
2022-04-08 12:54     ` Chao Peng
     [not found]   ` <20220412143654.6313-1-hdanton@sina.com>
2022-04-13  6:47     ` Chao Peng
2022-03-10 14:09 ` [PATCH v5 03/13] mm/shmem: Support memfile_notifier Chao Peng
2022-03-10 23:08   ` Dave Chinner
2022-03-11  8:42     ` Chao Peng
2022-04-11 15:26   ` Kirill A. Shutemov
2022-04-12 13:12     ` Chao Peng
2022-04-19 22:40   ` Vishal Annapurve [this message]
2022-04-20  3:24     ` Chao Peng
2022-03-10 14:09 ` [PATCH v5 04/13] mm/shmem: Restrict MFD_INACCESSIBLE memory against RLIMIT_MEMLOCK Chao Peng
2022-04-07 16:05   ` Sean Christopherson
2022-04-07 17:09     ` Andy Lutomirski
2022-04-08 17:56       ` Sean Christopherson
2022-04-08 18:54         ` David Hildenbrand
2022-04-12 14:36           ` Jason Gunthorpe
2022-04-12 21:27             ` Andy Lutomirski
2022-04-13 16:30               ` David Hildenbrand
2022-04-13 16:24             ` David Hildenbrand
2022-04-13 17:52               ` Jason Gunthorpe
2022-04-25 14:07                 ` David Hildenbrand
2022-04-08 13:02     ` Chao Peng
2022-04-11 15:34       ` Kirill A. Shutemov
2022-04-12  5:14         ` Hugh Dickins
2022-04-11 15:32     ` Kirill A. Shutemov
2022-04-12 13:39       ` Chao Peng
2022-04-12 19:28         ` Kirill A. Shutemov
2022-04-13  9:15           ` Chao Peng
2022-03-10 14:09 ` [PATCH v5 05/13] KVM: Extend the memslot to support fd-based private memory Chao Peng
2022-03-28 21:27   ` Sean Christopherson
2022-04-08 13:21     ` Chao Peng
2022-03-28 21:56   ` Sean Christopherson
2022-04-08 13:46     ` Chao Peng
2022-04-08 17:45       ` Sean Christopherson
2022-03-10 14:09 ` [PATCH v5 06/13] KVM: Use kvm_userspace_memory_region_ext Chao Peng
2022-03-28 22:26   ` Sean Christopherson
2022-04-08 13:58     ` Chao Peng
2022-03-10 14:09 ` [PATCH v5 07/13] KVM: Add KVM_EXIT_MEMORY_ERROR exit Chao Peng
2022-03-28 22:33   ` Sean Christopherson
2022-04-08 13:59     ` Chao Peng
2022-03-10 14:09 ` [PATCH v5 08/13] KVM: Use memfile_pfn_ops to obtain pfn for private pages Chao Peng
2022-03-28 23:56   ` Sean Christopherson
2022-04-08 14:07     ` Chao Peng
2022-04-28 12:37     ` Chao Peng
2022-03-10 14:09 ` [PATCH v5 09/13] KVM: Handle page fault for private memory Chao Peng
2022-03-29  1:07   ` Sean Christopherson
2022-04-12 12:10     ` Chao Peng
2022-03-10 14:09 ` [PATCH v5 10/13] KVM: Register private memslot to memory backing store Chao Peng
2022-03-29 19:01   ` Sean Christopherson
2022-04-12 12:40     ` Chao Peng
2022-03-10 14:09 ` [PATCH v5 11/13] KVM: Zap existing KVM mappings when pages changed in the private fd Chao Peng
2022-03-29 19:23   ` Sean Christopherson
2022-04-12 12:43     ` Chao Peng
2022-04-05 23:45   ` Michael Roth
2022-04-08  3:06     ` Sean Christopherson
2022-04-19 22:43   ` Vishal Annapurve
2022-04-20  3:17     ` Chao Peng
2022-03-10 14:09 ` [PATCH v5 12/13] KVM: Expose KVM_MEM_PRIVATE Chao Peng
2022-03-29 19:13   ` Sean Christopherson
2022-04-12 12:56     ` Chao Peng
2022-03-10 14:09 ` [PATCH v5 13/13] memfd_create.2: Describe MFD_INACCESSIBLE flag Chao Peng
2022-03-24 15:51 ` [PATCH v5 00/13] KVM: mm: fd-based approach for supporting KVM guest private memory Quentin Perret
2022-03-28 17:13   ` Sean Christopherson
2022-03-28 18:00     ` Quentin Perret
2022-03-28 18:58       ` Sean Christopherson
2022-03-29 17:01         ` Quentin Perret
2022-03-30  8:58           ` Steven Price
2022-03-30 10:39             ` Quentin Perret
2022-03-30 17:58               ` Sean Christopherson
2022-03-31 16:04                 ` Andy Lutomirski
2022-04-01 14:59                   ` Quentin Perret
2022-04-01 17:14                     ` Sean Christopherson
2022-04-01 18:03                       ` Quentin Perret
2022-04-01 18:24                         ` Sean Christopherson
2022-04-01 19:56                     ` Andy Lutomirski
2022-04-04 15:01                       ` Quentin Perret
2022-04-04 17:06                         ` Sean Christopherson
2022-04-04 22:04                           ` Andy Lutomirski
2022-04-05 10:36                             ` Quentin Perret
2022-04-05 17:51                               ` Andy Lutomirski
2022-04-05 18:30                                 ` Sean Christopherson
2022-04-06 18:42                                   ` Andy Lutomirski
2022-04-06 13:05                                 ` Quentin Perret
2022-04-05 18:03                               ` Sean Christopherson
2022-04-06 10:34                                 ` Quentin Perret
2022-04-22 10:56                                 ` Chao Peng
2022-04-22 11:06                                   ` Paolo Bonzini
2022-04-24  8:07                                     ` Chao Peng
2022-04-24 16:59                                   ` Andy Lutomirski
2022-04-25 13:40                                     ` Chao Peng
2022-04-25 14:52                                       ` Andy Lutomirski
2022-04-25 20:30                                         ` Sean Christopherson
2022-06-10 19:18                                           ` Andy Lutomirski
2022-06-10 19:27                                             ` Sean Christopherson
2022-04-28 12:29                                         ` Chao Peng
2022-05-03 11:12                                           ` Quentin Perret
2022-05-09 22:30                                   ` Michael Roth
2022-05-09 23:29                                     ` Sean Christopherson
2022-07-21 20:05                                       ` Gupta, Pankaj
2022-07-21 21:19                                         ` Sean Christopherson
2022-07-21 21:36                                           ` Gupta, Pankaj
2022-07-23  3:09                                           ` Andy Lutomirski
2022-07-25  9:19                                             ` Gupta, Pankaj
2022-03-30 16:18             ` Sean Christopherson
2022-03-28 20:16 ` Andy Lutomirski
2022-03-28 22:48   ` Nakajima, Jun
2022-03-29  0:04     ` Sean Christopherson
2022-04-08 21:35   ` Vishal Annapurve
2022-04-12 13:00     ` Chao Peng
2022-04-12 19:58   ` Kirill A. Shutemov

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=CAGtprH9X-v-R+UiAvdvKgqAqoc4MBJAWTnoEtP+Y2nip_y8Heg@mail.gmail.com \
    --to=vannapurve@google.com \
    --cc=ak@linux.intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=bfields@fieldses.org \
    --cc=bp@alien8.de \
    --cc=chao.p.peng@linux.intel.com \
    --cc=corbet@lwn.net \
    --cc=dave.hansen@intel.com \
    --cc=david@redhat.com \
    --cc=hpa@zytor.com \
    --cc=hughd@google.com \
    --cc=jlayton@kernel.org \
    --cc=jmattson@google.com \
    --cc=joro@8bytes.org \
    --cc=jun.nakajima@intel.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=mail@maciej.szmigiero.name \
    --cc=mingo@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=rppt@kernel.org \
    --cc=seanjc@google.com \
    --cc=steven.price@arm.com \
    --cc=tglx@linutronix.de \
    --cc=vbabka@suse.cz \
    --cc=vkuznets@redhat.com \
    --cc=wanpengli@tencent.com \
    --cc=x86@kernel.org \
    --cc=yu.c.zhang@linux.intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).