qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Chao Peng <chao.p.peng@linux.intel.com>
To: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
	qemu-devel@nongnu.org
Cc: Wanpeng Li <wanpengli@tencent.com>,
	luto@kernel.org, david@redhat.com,
	"J . Bruce Fields" <bfields@fieldses.org>,
	dave.hansen@intel.com, "H . Peter Anvin" <hpa@zytor.com>,
	Chao Peng <chao.p.peng@linux.intel.com>,
	ak@linux.intel.com, Jonathan Corbet <corbet@lwn.net>,
	Joerg Roedel <joro@8bytes.org>,
	x86@kernel.org, Hugh Dickins <hughd@google.com>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	jun.nakajima@intel.com, Thomas Gleixner <tglx@linutronix.de>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Jim Mattson <jmattson@google.com>,
	Sean Christopherson <seanjc@google.com>,
	Jeff Layton <jlayton@kernel.org>,
	Yu Zhang <yu.c.zhang@linux.intel.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [PATCH v4 10/12] KVM: Register private memslot to memory backing store
Date: Tue, 18 Jan 2022 21:21:19 +0800	[thread overview]
Message-ID: <20220118132121.31388-11-chao.p.peng@linux.intel.com> (raw)
In-Reply-To: <20220118132121.31388-1-chao.p.peng@linux.intel.com>

Add 'notifier' to memslot to make it a memfile_notifier node and then
register it to memory backing store via memfile_register_notifier() when
memslot gets created. When memslot is deleted, do the reverse with
memfile_unregister_notifier(). Note each KVM memslot can be registered
to different memory backing stores (or the same backing store but at
different offset) independently.

Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
---
 include/linux/kvm_host.h |  1 +
 virt/kvm/kvm_main.c      | 75 ++++++++++++++++++++++++++++++++++++----
 2 files changed, 70 insertions(+), 6 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 927e7f44a02a..667efe839767 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -462,6 +462,7 @@ struct kvm_memory_slot {
 	struct file *private_file;
 	loff_t private_offset;
 	struct memfile_pfn_ops *pfn_ops;
+	struct memfile_notifier notifier;
 };
 
 static inline bool kvm_slot_is_private(const struct kvm_memory_slot *slot)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index ecf94e2548f7..6b78ddef7880 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -846,6 +846,37 @@ static int kvm_init_mmu_notifier(struct kvm *kvm)
 
 #endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */
 
+#ifdef CONFIG_MEMFILE_NOTIFIER
+static inline int kvm_memfile_register(struct kvm_memory_slot *slot)
+{
+	return memfile_register_notifier(file_inode(slot->private_file),
+					 &slot->notifier,
+					 &slot->pfn_ops);
+}
+
+static inline void kvm_memfile_unregister(struct kvm_memory_slot *slot)
+{
+	if (slot->private_file) {
+		memfile_unregister_notifier(file_inode(slot->private_file),
+					    &slot->notifier);
+		fput(slot->private_file);
+		slot->private_file = NULL;
+	}
+}
+
+#else /* !CONFIG_MEMFILE_NOTIFIER */
+
+static inline int kvm_memfile_register(struct kvm_memory_slot *slot)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void kvm_memfile_unregister(struct kvm_memory_slot *slot)
+{
+}
+
+#endif /* CONFIG_MEMFILE_NOTIFIER */
+
 #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
 static int kvm_pm_notifier_call(struct notifier_block *bl,
 				unsigned long state,
@@ -890,6 +921,9 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
 /* This does not remove the slot from struct kvm_memslots data structures */
 static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
 {
+	if (slot->flags & KVM_MEM_PRIVATE)
+		kvm_memfile_unregister(slot);
+
 	kvm_destroy_dirty_bitmap(slot);
 
 	kvm_arch_free_memslot(kvm, slot);
@@ -1744,6 +1778,12 @@ static int kvm_set_memslot(struct kvm *kvm,
 		kvm_invalidate_memslot(kvm, old, invalid_slot);
 	}
 
+	if (new->flags & KVM_MEM_PRIVATE && change == KVM_MR_CREATE) {
+		r = kvm_memfile_register(new);
+		if (r)
+			return r;
+	}
+
 	r = kvm_prepare_memory_region(kvm, old, new, change);
 	if (r) {
 		/*
@@ -1758,6 +1798,10 @@ static int kvm_set_memslot(struct kvm *kvm,
 		} else {
 			mutex_unlock(&kvm->slots_arch_lock);
 		}
+
+		if (new->flags & KVM_MEM_PRIVATE && change == KVM_MR_CREATE)
+			kvm_memfile_unregister(new);
+
 		return r;
 	}
 
@@ -1823,6 +1867,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	enum kvm_mr_change change;
 	unsigned long npages;
 	gfn_t base_gfn;
+	struct file *file = NULL;
 	int as_id, id;
 	int r;
 
@@ -1896,14 +1941,24 @@ int __kvm_set_memory_region(struct kvm *kvm,
 			return 0;
 	}
 
+	if (mem->flags & KVM_MEM_PRIVATE) {
+		file = fdget(region_ext->private_fd).file;
+		if (!file)
+			return -EINVAL;
+	}
+
 	if ((change == KVM_MR_CREATE || change == KVM_MR_MOVE) &&
-	    kvm_check_memslot_overlap(slots, id, base_gfn, base_gfn + npages))
-		return -EEXIST;
+	    kvm_check_memslot_overlap(slots, id, base_gfn, base_gfn + npages)) {
+		r = -EEXIST;
+		goto out;
+	}
 
 	/* Allocate a slot that will persist in the memslot. */
 	new = kzalloc(sizeof(*new), GFP_KERNEL_ACCOUNT);
-	if (!new)
-		return -ENOMEM;
+	if (!new) {
+		r = -ENOMEM;
+		goto out;
+	}
 
 	new->as_id = as_id;
 	new->id = id;
@@ -1911,10 +1966,18 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	new->npages = npages;
 	new->flags = mem->flags;
 	new->userspace_addr = mem->userspace_addr;
+	new->private_file = file;
+	new->private_offset = mem->flags & KVM_MEM_PRIVATE ?
+			      region_ext->private_offset : 0;
 
 	r = kvm_set_memslot(kvm, old, new, change);
-	if (r)
-		kfree(new);
+	if (!r)
+		return r;
+
+	kfree(new);
+out:
+	if (file)
+		fput(file);
 	return r;
 }
 EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
-- 
2.17.1



  parent reply	other threads:[~2022-01-18 15:12 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-01-18 13:21 [PATCH v4 00/12] KVM: mm: fd-based approach for supporting KVM guest private memory Chao Peng
2022-01-18 13:21 ` [PATCH v4 01/12] mm/shmem: Introduce F_SEAL_INACCESSIBLE Chao Peng
2022-02-07 12:24   ` Vlastimil Babka
2022-02-17 12:56     ` Chao Peng
2022-02-11 23:33   ` Andy Lutomirski
2022-02-17 13:06     ` Chao Peng
2022-02-17 19:09       ` Andy Lutomirski
2022-02-23 11:49         ` Chao Peng
2022-02-23 12:05           ` Steven Price
2022-03-04 19:24             ` Andy Lutomirski
2022-03-07 13:26               ` Chao Peng
2022-03-08 12:17                 ` Paolo Bonzini
2022-01-18 13:21 ` [PATCH v4 02/12] mm/memfd: Introduce MFD_INACCESSIBLE flag Chao Peng
2022-01-21 15:50   ` Steven Price
2022-01-24 13:29     ` Chao Peng
2022-02-07 18:51   ` Vlastimil Babka
2022-02-08  8:49     ` David Hildenbrand
2022-02-08 18:22       ` Mike Rapoport
2022-01-18 13:21 ` [PATCH v4 03/12] mm: Introduce memfile_notifier Chao Peng
2022-03-07 15:42   ` Vlastimil Babka
2022-03-08  1:45     ` Chao Peng
2022-01-18 13:21 ` [PATCH v4 04/12] mm/shmem: Support memfile_notifier Chao Peng
2022-02-08 18:29   ` Mike Rapoport
2022-02-17 13:10     ` Chao Peng
2022-02-11 23:40   ` Andy Lutomirski
2022-02-17 13:23     ` Chao Peng
2022-01-18 13:21 ` [PATCH v4 05/12] KVM: Extend the memslot to support fd-based private memory Chao Peng
2022-01-18 13:21 ` [PATCH v4 06/12] KVM: Use kvm_userspace_memory_region_ext Chao Peng
2022-01-18 13:21 ` [PATCH v4 07/12] KVM: Add KVM_EXIT_MEMORY_ERROR exit Chao Peng
2022-01-18 13:21 ` [PATCH v4 08/12] KVM: Use memfile_pfn_ops to obtain pfn for private pages Chao Peng
2022-01-18 13:21 ` [PATCH v4 09/12] KVM: Handle page fault for private memory Chao Peng
2022-01-18 13:21 ` Chao Peng [this message]
2022-01-18 13:21 ` [PATCH v4 11/12] KVM: Zap existing KVM mappings when pages changed in the private fd Chao Peng
2022-01-18 13:21 ` [PATCH v4 12/12] KVM: Expose KVM_MEM_PRIVATE Chao Peng
2022-01-25 20:20   ` Maciej S. Szmigiero
2022-02-17 13:45     ` Chao Peng
2022-02-22  1:16       ` Maciej S. Szmigiero
2022-02-23 12:00         ` Chao Peng
2022-02-23 18:32           ` Maciej S. Szmigiero
2022-02-24  8:07             ` Chao Peng
2022-01-28 16:47 ` [PATCH v4 00/12] KVM: mm: fd-based approach for supporting KVM guest private memory Steven Price
2022-02-02  2:28   ` Nakajima, Jun
2022-02-02  9:23     ` Steven Price
2022-02-02 20:47       ` Nakajima, Jun
2022-02-08 18:33 ` Mike Rapoport
2022-02-17 13:47   ` Chao Peng

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=20220118132121.31388-11-chao.p.peng@linux.intel.com \
    --to=chao.p.peng@linux.intel.com \
    --cc=ak@linux.intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=bfields@fieldses.org \
    --cc=bp@alien8.de \
    --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-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=mingo@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=seanjc@google.com \
    --cc=tglx@linutronix.de \
    --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).