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,
linux-api@vger.kernel.org, linux-doc@vger.kernel.org,
qemu-devel@nongnu.org
Cc: 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>,
Shuah Khan <shuah@kernel.org>, Mike Rapoport <rppt@kernel.org>,
Steven Price <steven.price@arm.com>,
"Maciej S . Szmigiero" <mail@maciej.szmigiero.name>,
Vlastimil Babka <vbabka@suse.cz>,
Vishal Annapurve <vannapurve@google.com>,
Yu Zhang <yu.c.zhang@linux.intel.com>,
Chao Peng <chao.p.peng@linux.intel.com>,
"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
luto@kernel.org, jun.nakajima@intel.com, dave.hansen@intel.com,
ak@linux.intel.com, david@redhat.com, aarcange@redhat.com,
ddutile@redhat.com, dhildenb@redhat.com,
Quentin Perret <qperret@google.com>,
Michael Roth <michael.roth@amd.com>,
mhocko@suse.com, Muchun Song <songmuchun@bytedance.com>,
wei.w.wang@intel.com
Subject: [PATCH v8 8/8] KVM: Enable and expose KVM_MEM_PRIVATE
Date: Thu, 15 Sep 2022 22:29:13 +0800 [thread overview]
Message-ID: <20220915142913.2213336-9-chao.p.peng@linux.intel.com> (raw)
In-Reply-To: <20220915142913.2213336-1-chao.p.peng@linux.intel.com>
Expose KVM_MEM_PRIVATE and memslot fields private_fd/offset to
userspace. KVM will register/unregister private memslot to fd-based
memory backing store and response to invalidation event from
inaccessible_notifier to zap the existing memory mappings in the
secondary page table.
Whether KVM_MEM_PRIVATE is actually exposed to userspace is determined
by architecture code which can turn on it by overriding the default
kvm_arch_has_private_mem().
A 'kvm' reference is added in memslot structure since in
inaccessible_notifier callback we can only obtain a memslot reference
but 'kvm' is needed to do the zapping.
Co-developed-by: Yu Zhang <yu.c.zhang@linux.intel.com>
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 | 116 +++++++++++++++++++++++++++++++++++++--
2 files changed, 111 insertions(+), 6 deletions(-)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index b9906cdf468b..cb4eefac709c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -589,6 +589,7 @@ struct kvm_memory_slot {
struct file *private_file;
loff_t private_offset;
struct inaccessible_notifier notifier;
+ struct kvm *kvm;
};
static inline bool kvm_slot_can_be_private(const struct kvm_memory_slot *slot)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 97d893f7482c..87e239d35b96 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -983,6 +983,57 @@ static int kvm_vm_ioctl_set_mem_attr(struct kvm *kvm, gpa_t gpa, gpa_t size,
xa_erase(&kvm->mem_attr_array, index);
return r;
}
+
+static void kvm_private_notifier_invalidate(struct inaccessible_notifier *notifier,
+ pgoff_t start, pgoff_t end)
+{
+ struct kvm_memory_slot *slot = container_of(notifier,
+ struct kvm_memory_slot,
+ notifier);
+ unsigned long base_pgoff = slot->private_offset >> PAGE_SHIFT;
+ gfn_t start_gfn = slot->base_gfn;
+ gfn_t end_gfn = slot->base_gfn + slot->npages;
+
+
+ if (start > base_pgoff)
+ start_gfn = slot->base_gfn + start - base_pgoff;
+
+ if (end < base_pgoff + slot->npages)
+ end_gfn = slot->base_gfn + end - base_pgoff;
+
+ if (start_gfn >= end_gfn)
+ return;
+
+ kvm_zap_gfn_range(slot->kvm, start_gfn, end_gfn);
+}
+
+static struct inaccessible_notifier_ops kvm_private_notifier_ops = {
+ .invalidate = kvm_private_notifier_invalidate,
+};
+
+static inline void kvm_private_mem_register(struct kvm_memory_slot *slot)
+{
+ slot->notifier.ops = &kvm_private_notifier_ops;
+ inaccessible_register_notifier(slot->private_file, &slot->notifier);
+}
+
+static inline void kvm_private_mem_unregister(struct kvm_memory_slot *slot)
+{
+ inaccessible_unregister_notifier(slot->private_file, &slot->notifier);
+}
+
+#else /* !CONFIG_HAVE_KVM_PRIVATE_MEM */
+
+static inline void kvm_private_mem_register(struct kvm_memory_slot *slot)
+{
+ WARN_ON_ONCE(1);
+}
+
+static inline void kvm_private_mem_unregister(struct kvm_memory_slot *slot)
+{
+ WARN_ON_ONCE(1);
+}
+
#endif /* CONFIG_HAVE_KVM_PRIVATE_MEM */
#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
@@ -1029,6 +1080,11 @@ 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_private_mem_unregister(slot);
+ fput(slot->private_file);
+ }
+
kvm_destroy_dirty_bitmap(slot);
kvm_arch_free_memslot(kvm, slot);
@@ -1600,10 +1656,16 @@ bool __weak kvm_arch_has_private_mem(struct kvm *kvm)
return false;
}
-static int check_memory_region_flags(const struct kvm_user_mem_region *mem)
+static int check_memory_region_flags(struct kvm *kvm,
+ const struct kvm_user_mem_region *mem)
{
u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
+#ifdef CONFIG_HAVE_KVM_PRIVATE_MEM
+ if (kvm_arch_has_private_mem(kvm))
+ valid_flags |= KVM_MEM_PRIVATE;
+#endif
+
#ifdef __KVM_HAVE_READONLY_MEM
valid_flags |= KVM_MEM_READONLY;
#endif
@@ -1679,6 +1741,9 @@ static int kvm_prepare_memory_region(struct kvm *kvm,
{
int r;
+ if (change == KVM_MR_CREATE && new->flags & KVM_MEM_PRIVATE)
+ kvm_private_mem_register(new);
+
/*
* If dirty logging is disabled, nullify the bitmap; the old bitmap
* will be freed on "commit". If logging is enabled in both old and
@@ -1707,6 +1772,9 @@ static int kvm_prepare_memory_region(struct kvm *kvm,
if (r && new && new->dirty_bitmap && (!old || !old->dirty_bitmap))
kvm_destroy_dirty_bitmap(new);
+ if (r && change == KVM_MR_CREATE && new->flags & KVM_MEM_PRIVATE)
+ kvm_private_mem_unregister(new);
+
return r;
}
@@ -2004,7 +2072,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
int as_id, id;
int r;
- r = check_memory_region_flags(mem);
+ r = check_memory_region_flags(kvm, mem);
if (r)
return r;
@@ -2023,6 +2091,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
!access_ok((void __user *)(unsigned long)mem->userspace_addr,
mem->memory_size))
return -EINVAL;
+ if (mem->flags & KVM_MEM_PRIVATE &&
+ (mem->private_offset & (PAGE_SIZE - 1) ||
+ mem->private_offset > U64_MAX - mem->memory_size))
+ return -EINVAL;
if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM)
return -EINVAL;
if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
@@ -2061,6 +2133,9 @@ int __kvm_set_memory_region(struct kvm *kvm,
if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages)
return -EINVAL;
} else { /* Modify an existing slot. */
+ /* Private memslots are immutable, they can only be deleted. */
+ if (mem->flags & KVM_MEM_PRIVATE)
+ return -EINVAL;
if ((mem->userspace_addr != old->userspace_addr) ||
(npages != old->npages) ||
((mem->flags ^ old->flags) & KVM_MEM_READONLY))
@@ -2089,10 +2164,27 @@ int __kvm_set_memory_region(struct kvm *kvm,
new->npages = npages;
new->flags = mem->flags;
new->userspace_addr = mem->userspace_addr;
+ if (mem->flags & KVM_MEM_PRIVATE) {
+ new->private_file = fget(mem->private_fd);
+ if (!new->private_file) {
+ r = -EINVAL;
+ goto out;
+ }
+ new->private_offset = mem->private_offset;
+ }
+
+ new->kvm = kvm;
r = kvm_set_memslot(kvm, old, new, change);
if (r)
- kfree(new);
+ goto out;
+
+ return 0;
+
+out:
+ if (new->private_file)
+ fput(new->private_file);
+ kfree(new);
return r;
}
EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
@@ -4747,16 +4839,28 @@ static long kvm_vm_ioctl(struct file *filp,
}
case KVM_SET_USER_MEMORY_REGION: {
struct kvm_user_mem_region mem;
- unsigned long size = sizeof(struct kvm_userspace_memory_region);
+ unsigned int flags_offset = offsetof(typeof(mem), flags);
+ unsigned long size;
+ u32 flags;
kvm_sanity_check_user_mem_region_alias();
+ memset(&mem, 0, sizeof(mem));
+
r = -EFAULT;
- if (copy_from_user(&mem, argp, size);
+ if (get_user(flags, (u32 __user *)(argp + flags_offset)))
+ goto out;
+
+ if (flags & KVM_MEM_PRIVATE)
+ size = sizeof(struct kvm_userspace_memory_region_ext);
+ else
+ size = sizeof(struct kvm_userspace_memory_region);
+
+ if (copy_from_user(&mem, argp, size))
goto out;
r = -EINVAL;
- if (mem.flags & KVM_MEM_PRIVATE)
+ if ((flags ^ mem.flags) & KVM_MEM_PRIVATE)
goto out;
r = kvm_vm_ioctl_set_memory_region(kvm, &mem);
--
2.25.1
next prev parent reply other threads:[~2022-09-15 14:37 UTC|newest]
Thread overview: 97+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-15 14:29 [PATCH v8 0/8] KVM: mm: fd-based approach for supporting KVM Chao Peng
2022-09-15 14:29 ` [PATCH v8 1/8] mm/memfd: Introduce userspace inaccessible memfd Chao Peng
2022-09-19 9:12 ` David Hildenbrand
2022-09-19 19:10 ` Sean Christopherson
2022-09-21 21:10 ` Andy Lutomirski
2022-09-22 13:23 ` Wang, Wei W
2022-09-23 15:20 ` Fuad Tabba
2022-09-23 15:19 ` Fuad Tabba
2022-09-26 14:23 ` Chao Peng
2022-09-26 15:51 ` Fuad Tabba
2022-09-27 22:47 ` Sean Christopherson
2022-09-30 16:19 ` Fuad Tabba
2022-10-13 13:34 ` Chao Peng
2022-10-17 10:31 ` Fuad Tabba
2022-10-17 14:58 ` Chao Peng
2022-10-17 19:05 ` Fuad Tabba
2022-10-19 13:30 ` Chao Peng
2022-10-18 0:33 ` Sean Christopherson
2022-10-19 15:04 ` Fuad Tabba
2022-09-23 0:58 ` Kirill A . Shutemov
2022-09-26 10:35 ` David Hildenbrand
2022-09-26 14:48 ` Kirill A. Shutemov
2022-09-26 14:53 ` David Hildenbrand
2022-09-27 23:23 ` Sean Christopherson
2022-09-28 13:36 ` Kirill A. Shutemov
2022-09-22 13:26 ` Wang, Wei W
2022-09-22 19:49 ` Sean Christopherson
2022-09-23 0:53 ` Kirill A . Shutemov
2022-09-23 15:20 ` Fuad Tabba
2022-09-30 16:14 ` Fuad Tabba
2022-09-30 16:23 ` Kirill A . Shutemov
2022-10-03 7:33 ` Fuad Tabba
2022-10-03 11:01 ` Kirill A. Shutemov
2022-10-04 15:39 ` Fuad Tabba
2022-10-06 8:50 ` Fuad Tabba
2022-10-06 13:04 ` Kirill A. Shutemov
2022-10-17 13:00 ` Vlastimil Babka
2022-10-17 16:19 ` Kirill A . Shutemov
2022-10-17 16:39 ` Gupta, Pankaj
2022-10-17 21:56 ` Kirill A . Shutemov
2022-10-18 13:42 ` Vishal Annapurve
2022-10-19 15:32 ` Kirill A . Shutemov
2022-10-20 10:50 ` Vishal Annapurve
2022-10-21 13:54 ` Chao Peng
2022-10-21 16:53 ` Sean Christopherson
2022-10-19 12:23 ` Vishal Annapurve
2022-10-21 13:47 ` Chao Peng
2022-10-21 16:18 ` Sean Christopherson
2022-10-24 14:59 ` Kirill A . Shutemov
2022-10-24 15:26 ` David Hildenbrand
2022-11-03 16:27 ` Vishal Annapurve
2022-09-15 14:29 ` [PATCH v8 2/8] KVM: Extend the memslot to support fd-based private memory Chao Peng
2022-09-16 9:14 ` Bagas Sanjaya
2022-09-16 9:53 ` Chao Peng
2022-09-26 10:26 ` Fuad Tabba
2022-09-26 14:04 ` Chao Peng
2022-09-29 22:45 ` Isaku Yamahata
2022-09-29 23:22 ` Sean Christopherson
2022-10-05 13:04 ` Jarkko Sakkinen
2022-10-05 22:05 ` Jarkko Sakkinen
2022-10-06 9:00 ` Fuad Tabba
2022-10-06 14:58 ` Jarkko Sakkinen
2022-10-06 15:07 ` Jarkko Sakkinen
2022-10-06 15:34 ` Sean Christopherson
2022-10-07 11:14 ` Jarkko Sakkinen
2022-10-07 14:58 ` Sean Christopherson
2022-10-07 21:54 ` Jarkko Sakkinen
2022-10-08 16:15 ` Jarkko Sakkinen
2022-10-08 17:35 ` Jarkko Sakkinen
2022-10-10 8:25 ` Chao Peng
2022-10-12 8:14 ` Jarkko Sakkinen
2022-09-15 14:29 ` [PATCH v8 3/8] KVM: Add KVM_EXIT_MEMORY_FAULT exit Chao Peng
2022-09-16 9:17 ` Bagas Sanjaya
2022-09-16 9:54 ` Chao Peng
2022-09-15 14:29 ` [PATCH v8 4/8] KVM: Use gfn instead of hva for mmu_notifier_retry Chao Peng
2022-09-15 14:29 ` [PATCH v8 5/8] KVM: Register/unregister the guest private memory regions Chao Peng
2022-09-26 10:36 ` Fuad Tabba
2022-09-26 14:07 ` Chao Peng
2022-10-11 9:48 ` Fuad Tabba
2022-10-12 2:35 ` Chao Peng
2022-10-17 10:15 ` Fuad Tabba
2022-10-17 22:17 ` Sean Christopherson
2022-10-19 13:23 ` Chao Peng
2022-10-19 15:02 ` Fuad Tabba
2022-10-19 16:09 ` Sean Christopherson
2022-10-19 18:32 ` Fuad Tabba
2022-09-15 14:29 ` [PATCH v8 6/8] KVM: Update lpage info when private/shared memory are mixed Chao Peng
2022-09-29 16:52 ` Isaku Yamahata
2022-09-30 8:59 ` Chao Peng
2022-09-15 14:29 ` [PATCH v8 7/8] KVM: Handle page fault for private memory Chao Peng
2022-10-14 18:57 ` Sean Christopherson
2022-10-17 14:48 ` Chao Peng
2022-09-15 14:29 ` Chao Peng [this message]
2022-10-04 14:55 ` [PATCH v8 8/8] KVM: Enable and expose KVM_MEM_PRIVATE Jarkko Sakkinen
2022-10-10 8:31 ` Chao Peng
2022-10-06 8:55 ` Fuad Tabba
2022-10-10 8:33 ` 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=20220915142913.2213336-9-chao.p.peng@linux.intel.com \
--to=chao.p.peng@linux.intel.com \
--cc=aarcange@redhat.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=ddutile@redhat.com \
--cc=dhildenb@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-doc@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=mhocko@suse.com \
--cc=michael.roth@amd.com \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=qperret@google.com \
--cc=rppt@kernel.org \
--cc=seanjc@google.com \
--cc=shuah@kernel.org \
--cc=songmuchun@bytedance.com \
--cc=steven.price@arm.com \
--cc=tglx@linutronix.de \
--cc=vannapurve@google.com \
--cc=vbabka@suse.cz \
--cc=vkuznets@redhat.com \
--cc=wanpengli@tencent.com \
--cc=wei.w.wang@intel.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).