From: Ackerley Tng <ackerleytng@google.com>
To: aik@amd.com, andrew.jones@linux.dev, binbin.wu@linux.intel.com,
brauner@kernel.org, chao.p.peng@linux.intel.com,
david@kernel.org, ira.weiny@intel.com, jmattson@google.com,
jroedel@suse.de, jthoughton@google.com, michael.roth@amd.com,
oupton@kernel.org, pankaj.gupta@amd.com, qperret@google.com,
rick.p.edgecombe@intel.com, rientjes@google.com,
shivankg@amd.com, steven.price@arm.com, tabba@google.com,
willy@infradead.org, wyihan@google.com, yan.y.zhao@intel.com,
forkloop@google.com, pratyush@kernel.org,
suzuki.poulose@arm.com, aneesh.kumar@kernel.org,
Paolo Bonzini <pbonzini@redhat.com>,
Sean Christopherson <seanjc@google.com>,
Thomas Gleixner <tglx@kernel.org>, Ingo Molnar <mingo@redhat.com>,
Borislav Petkov <bp@alien8.de>,
Dave Hansen <dave.hansen@linux.intel.com>,
x86@kernel.org, "H. Peter Anvin" <hpa@zytor.com>,
Steven Rostedt <rostedt@goodmis.org>,
Masami Hiramatsu <mhiramat@kernel.org>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
Jonathan Corbet <corbet@lwn.net>,
Shuah Khan <skhan@linuxfoundation.org>,
Shuah Khan <shuah@kernel.org>,
Vishal Annapurve <vannapurve@google.com>,
Andrew Morton <akpm@linux-foundation.org>,
Chris Li <chrisl@kernel.org>, Kairui Song <kasong@tencent.com>,
Kemeng Shi <shikemeng@huaweicloud.com>,
Nhat Pham <nphamcs@gmail.com>, Baoquan He <bhe@redhat.com>,
Barry Song <baohua@kernel.org>,
Axel Rasmussen <axelrasmussen@google.com>,
Yuanchu Xie <yuanchu@google.com>, Wei Xu <weixugc@google.com>,
Jason Gunthorpe <jgg@ziepe.ca>,
Vlastimil Babka <vbabka@kernel.org>
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-trace-kernel@vger.kernel.org, linux-doc@vger.kernel.org,
linux-kselftest@vger.kernel.org, linux-mm@kvack.org,
Ackerley Tng <ackerleytng@google.com>
Subject: [PATCH RFC v4 01/44] KVM: guest_memfd: Introduce per-gmem attributes, use to guard user mappings
Date: Thu, 26 Mar 2026 15:24:10 -0700 [thread overview]
Message-ID: <20260326-gmem-inplace-conversion-v4-1-e202fe950ffd@google.com> (raw)
In-Reply-To: <20260326-gmem-inplace-conversion-v4-0-e202fe950ffd@google.com>
From: Sean Christopherson <seanjc@google.com>
Start plumbing in guest_memfd support for in-place private<=>shared
conversions by tracking attributes via a maple tree. KVM currently tracks
private vs. shared attributes on a per-VM basis, which made sense when a
guest_memfd _only_ supported private memory, but tracking per-VM simply
can't work for in-place conversions as the shareability of a given page
needs to be per-gmem_inode, not per-VM.
Use the filemap invalidation lock to protect the maple tree, as taking the
lock for read when faulting in memory (for userspace or the guest) isn't
expected to result in meaningful contention, and using a separate lock
would add significant complexity (avoid deadlock is quite difficult).
Signed-off-by: Sean Christopherson <seanjc@google.com>
Co-developed-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Vishal Annapurve <vannapurve@google.com>
Signed-off-by: Vishal Annapurve <vannapurve@google.com>
Co-developed-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Fuad Tabba <tabba@google.com>
---
virt/kvm/guest_memfd.c | 139 +++++++++++++++++++++++++++++++++++++++++++------
1 file changed, 123 insertions(+), 16 deletions(-)
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 017d84a7adf37..aa2caf5114da2 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -4,6 +4,7 @@
#include <linux/falloc.h>
#include <linux/fs.h>
#include <linux/kvm_host.h>
+#include <linux/maple_tree.h>
#include <linux/mempolicy.h>
#include <linux/pseudo_fs.h>
#include <linux/pagemap.h>
@@ -32,6 +33,12 @@ struct gmem_inode {
struct inode vfs_inode;
u64 flags;
+ /*
+ * Every index in this inode, whether memory is populated or
+ * not, is tracked in attributes. There are no gaps in this
+ * maple tree.
+ */
+ struct maple_tree attributes;
};
static __always_inline struct gmem_inode *GMEM_I(struct inode *inode)
@@ -59,6 +66,31 @@ static pgoff_t kvm_gmem_get_index(struct kvm_memory_slot *slot, gfn_t gfn)
return gfn - slot->base_gfn + slot->gmem.pgoff;
}
+static u64 kvm_gmem_get_attributes(struct inode *inode, pgoff_t index)
+{
+ struct maple_tree *mt = &GMEM_I(inode)->attributes;
+ void *entry = mtree_load(mt, index);
+
+ /*
+ * The lock _must_ be held for lookups, as some maple tree operations,
+ * e.g. append, are unsafe (return inaccurate information) with respect
+ * to concurrent RCU-protected lookups.
+ */
+ lockdep_assert(mt_lock_is_held(mt));
+
+ return WARN_ON_ONCE(!entry) ? 0 : xa_to_value(entry);
+}
+
+static bool kvm_gmem_is_private_mem(struct inode *inode, pgoff_t index)
+{
+ return kvm_gmem_get_attributes(inode, index) & KVM_MEMORY_ATTRIBUTE_PRIVATE;
+}
+
+static bool kvm_gmem_is_shared_mem(struct inode *inode, pgoff_t index)
+{
+ return !kvm_gmem_is_private_mem(inode, index);
+}
+
static int __kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot,
pgoff_t index, struct folio *folio)
{
@@ -397,10 +429,13 @@ static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf)
if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode))
return VM_FAULT_SIGBUS;
- if (!(GMEM_I(inode)->flags & GUEST_MEMFD_FLAG_INIT_SHARED))
- return VM_FAULT_SIGBUS;
+ filemap_invalidate_lock_shared(inode->i_mapping);
+ if (kvm_gmem_is_shared_mem(inode, vmf->pgoff))
+ folio = kvm_gmem_get_folio(inode, vmf->pgoff);
+ else
+ folio = ERR_PTR(-EACCES);
+ filemap_invalidate_unlock_shared(inode->i_mapping);
- folio = kvm_gmem_get_folio(inode, vmf->pgoff);
if (IS_ERR(folio)) {
if (PTR_ERR(folio) == -EAGAIN)
return VM_FAULT_RETRY;
@@ -556,6 +591,51 @@ bool __weak kvm_arch_supports_gmem_init_shared(struct kvm *kvm)
return true;
}
+static int kvm_gmem_init_inode(struct inode *inode, loff_t size, u64 flags)
+{
+ struct gmem_inode *gi = GMEM_I(inode);
+ MA_STATE(mas, &gi->attributes, 0, (size >> PAGE_SHIFT) - 1);
+ u64 attrs;
+ int r;
+
+ inode->i_op = &kvm_gmem_iops;
+ inode->i_mapping->a_ops = &kvm_gmem_aops;
+ inode->i_mode |= S_IFREG;
+ inode->i_size = size;
+ mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
+
+ /*
+ * guest_memfd memory is neither migratable nor swappable: set
+ * inaccessible to gate off both.
+ */
+ mapping_set_inaccessible(inode->i_mapping);
+ WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping));
+
+ gi->flags = flags;
+
+ mt_set_external_lock(&gi->attributes,
+ &inode->i_mapping->invalidate_lock);
+
+ /*
+ * Store default attributes for the entire gmem instance. Ensuring every
+ * index is represented in the maple tree at all times simplifies the
+ * conversion and merging logic.
+ */
+ attrs = gi->flags & GUEST_MEMFD_FLAG_INIT_SHARED ? 0 : KVM_MEMORY_ATTRIBUTE_PRIVATE;
+
+ /*
+ * Acquire the invalidation lock purely to make lockdep happy. The
+ * maple tree library expects all stores to be protected via the lock,
+ * and the library can't know when the tree is reachable only by the
+ * caller, as is the case here.
+ */
+ filemap_invalidate_lock(inode->i_mapping);
+ r = mas_store_gfp(&mas, xa_mk_value(attrs), GFP_KERNEL);
+ filemap_invalidate_unlock(inode->i_mapping);
+
+ return r;
+}
+
static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
{
static const char *name = "[kvm-gmem]";
@@ -586,16 +666,9 @@ static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
goto err_fops;
}
- inode->i_op = &kvm_gmem_iops;
- inode->i_mapping->a_ops = &kvm_gmem_aops;
- inode->i_mode |= S_IFREG;
- inode->i_size = size;
- mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
- mapping_set_inaccessible(inode->i_mapping);
- /* Unmovable mappings are supposed to be marked unevictable as well. */
- WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping));
-
- GMEM_I(inode)->flags = flags;
+ err = kvm_gmem_init_inode(inode, size, flags);
+ if (err)
+ goto err_inode;
file = alloc_file_pseudo(inode, kvm_gmem_mnt, name, O_RDWR, &kvm_gmem_fops);
if (IS_ERR(file)) {
@@ -797,9 +870,13 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
if (!file)
return -EFAULT;
+ filemap_invalidate_lock_shared(file_inode(file)->i_mapping);
+
folio = __kvm_gmem_get_pfn(file, slot, index, pfn, max_order);
- if (IS_ERR(folio))
- return PTR_ERR(folio);
+ if (IS_ERR(folio)) {
+ r = PTR_ERR(folio);
+ goto out;
+ }
if (!folio_test_uptodate(folio)) {
clear_highpage(folio_page(folio, 0));
@@ -815,6 +892,8 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
else
folio_put(folio);
+out:
+ filemap_invalidate_unlock_shared(file_inode(file)->i_mapping);
return r;
}
EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_pfn);
@@ -944,13 +1023,41 @@ static struct inode *kvm_gmem_alloc_inode(struct super_block *sb)
mpol_shared_policy_init(&gi->policy, NULL);
+ /*
+ * Memory attributes are protected by the filemap invalidation lock, but
+ * the lock structure isn't available at this time. Immediately mark
+ * maple tree as using external locking so that accessing the tree
+ * before it's fully initialized results in NULL pointer dereferences
+ * and not more subtle bugs.
+ */
+ mt_init_flags(&gi->attributes, MT_FLAGS_LOCK_EXTERN);
+
gi->flags = 0;
return &gi->vfs_inode;
}
static void kvm_gmem_destroy_inode(struct inode *inode)
{
- mpol_free_shared_policy(&GMEM_I(inode)->policy);
+ struct gmem_inode *gi = GMEM_I(inode);
+
+ mpol_free_shared_policy(&gi->policy);
+
+ /*
+ * Note! Checking for an empty tree is functionally necessary
+ * to avoid explosions if the tree hasn't been fully
+ * initialized, i.e. if the inode is being destroyed before
+ * guest_memfd can set the external lock, lockdep would find
+ * that the tree's internal ma_lock was not held.
+ */
+ if (!mtree_empty(&gi->attributes)) {
+ /*
+ * Acquire the invalidation lock purely to make lockdep happy,
+ * the inode is unreachable at this point.
+ */
+ filemap_invalidate_lock(inode->i_mapping);
+ __mt_destroy(&gi->attributes);
+ filemap_invalidate_unlock(inode->i_mapping);
+ }
}
static void kvm_gmem_free_inode(struct inode *inode)
--
2.53.0.1018.g2bb0e51243-goog
next prev parent reply other threads:[~2026-03-26 22:24 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-26 22:24 [PATCH RFC v4 00/44] guest_memfd: In-place conversion support Ackerley Tng
2026-03-26 22:24 ` Ackerley Tng [this message]
2026-03-26 22:24 ` [PATCH RFC v4 02/44] KVM: Rename KVM_GENERIC_MEMORY_ATTRIBUTES to KVM_VM_MEMORY_ATTRIBUTES Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 03/44] KVM: Enumerate support for PRIVATE memory iff kvm_arch_has_private_mem is defined Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 04/44] KVM: Stub in ability to disable per-VM memory attribute tracking Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 05/44] KVM: guest_memfd: Wire up kvm_get_memory_attributes() to per-gmem attributes Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 06/44] KVM: guest_memfd: Update kvm_gmem_populate() to use gmem attributes Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 07/44] KVM: guest_memfd: Only prepare folios for private pages Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 08/44] KVM: Introduce KVM_SET_MEMORY_ATTRIBUTES2 Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 09/44] KVM: guest_memfd: Enable INIT_SHARED on guest_memfd for x86 Coco VMs Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 10/44] KVM: guest_memfd: Add support for KVM_SET_MEMORY_ATTRIBUTES2 Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 11/44] KVM: guest_memfd: Handle lru_add fbatch refcounts during conversion safety check Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 12/44] KVM: guest_memfd: Introduce default handlers for content modes Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 13/44] KVM: guest_memfd: Apply content modes while setting memory attributes Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 14/44] KVM: x86: Add support for applying content modes Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 15/44] KVM: Add CAP to enumerate supported SET_MEMORY_ATTRIBUTES2 flags Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 16/44] KVM: Move KVM_VM_MEMORY_ATTRIBUTES config definition to x86 Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 17/44] KVM: Let userspace disable per-VM mem attributes, enable per-gmem attributes Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 18/44] KVM: selftests: Create gmem fd before "regular" fd when adding memslot Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 19/44] KVM: selftests: Rename guest_memfd{,_offset} to gmem_{fd,offset} Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 20/44] KVM: selftests: Add support for mmap() on guest_memfd in core library Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 21/44] KVM: selftests: Add selftests global for guest memory attributes capability Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 22/44] KVM: selftests: Update framework to use KVM_SET_MEMORY_ATTRIBUTES2 Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 23/44] KVM: selftests: Add helpers for calling ioctls on guest_memfd Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 24/44] KVM: selftests: Test using guest_memfd for guest private memory Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 25/44] KVM: selftests: Test basic single-page conversion flow Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 26/44] KVM: selftests: Test conversion flow when INIT_SHARED Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 27/44] KVM: selftests: Test conversion precision in guest_memfd Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 28/44] KVM: selftests: Test conversion before allocation Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 29/44] KVM: selftests: Convert with allocated folios in different layouts Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 30/44] KVM: selftests: Test that truncation does not change shared/private status Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 31/44] KVM: selftests: Test that shared/private status is consistent across processes Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 32/44] KVM: selftests: Test conversion with elevated page refcount Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 33/44] KVM: selftests: Test that conversion to private does not support ZERO Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 34/44] KVM: selftests: Support checking that data not equal expected Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 35/44] KVM: selftests: Test that not specifying a conversion flag scrambles memory contents Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 36/44] KVM: selftests: Reset shared memory after hole-punching Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 37/44] KVM: selftests: Provide function to look up guest_memfd details from gpa Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 38/44] KVM: selftests: Provide common function to set memory attributes Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 39/44] KVM: selftests: Check fd/flags provided to mmap() when setting up memslot Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 40/44] KVM: selftests: Make TEST_EXPECT_SIGBUS thread-safe Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 41/44] KVM: selftests: Update private_mem_conversions_test to mmap() guest_memfd Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 42/44] KVM: selftests: Add script to exercise private_mem_conversions_test Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 43/44] KVM: selftests: Update pre-fault test to work with per-guest_memfd attributes Ackerley Tng
2026-03-26 22:24 ` [PATCH RFC v4 44/44] KVM: selftests: Update private memory exits test to work with per-gmem attributes Ackerley Tng
2026-03-26 23:36 ` [POC PATCH 0/6] guest_memfd in-place conversion selftests for SNP Ackerley Tng
2026-03-26 23:36 ` [POC PATCH 1/6] KVM: selftests: Initialize guest_memfd with INIT_SHARED Ackerley Tng
2026-03-26 23:36 ` [POC PATCH 2/6] KVM: selftests: Call snp_launch_update_data() providing copy of memory Ackerley Tng
2026-03-26 23:36 ` [POC PATCH 3/6] KVM: selftests: Make guest_code_xsave more friendly Ackerley Tng
2026-03-26 23:36 ` [POC PATCH 4/6] KVM: selftests: Allow specifying CoCo-privateness while mapping a page Ackerley Tng
2026-03-26 23:36 ` [POC PATCH 5/6] KVM: selftests: Test conversions for SNP Ackerley Tng
2026-03-26 23:36 ` [POC PATCH 6/6] KVM: selftests: Test content modes ZERO and PRESERVE " Ackerley Tng
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=20260326-gmem-inplace-conversion-v4-1-e202fe950ffd@google.com \
--to=ackerleytng@google.com \
--cc=aik@amd.com \
--cc=akpm@linux-foundation.org \
--cc=andrew.jones@linux.dev \
--cc=aneesh.kumar@kernel.org \
--cc=axelrasmussen@google.com \
--cc=baohua@kernel.org \
--cc=bhe@redhat.com \
--cc=binbin.wu@linux.intel.com \
--cc=bp@alien8.de \
--cc=brauner@kernel.org \
--cc=chao.p.peng@linux.intel.com \
--cc=chrisl@kernel.org \
--cc=corbet@lwn.net \
--cc=dave.hansen@linux.intel.com \
--cc=david@kernel.org \
--cc=forkloop@google.com \
--cc=hpa@zytor.com \
--cc=ira.weiny@intel.com \
--cc=jgg@ziepe.ca \
--cc=jmattson@google.com \
--cc=jroedel@suse.de \
--cc=jthoughton@google.com \
--cc=kasong@tencent.com \
--cc=kvm@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-trace-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mhiramat@kernel.org \
--cc=michael.roth@amd.com \
--cc=mingo@redhat.com \
--cc=nphamcs@gmail.com \
--cc=oupton@kernel.org \
--cc=pankaj.gupta@amd.com \
--cc=pbonzini@redhat.com \
--cc=pratyush@kernel.org \
--cc=qperret@google.com \
--cc=rick.p.edgecombe@intel.com \
--cc=rientjes@google.com \
--cc=rostedt@goodmis.org \
--cc=seanjc@google.com \
--cc=shikemeng@huaweicloud.com \
--cc=shivankg@amd.com \
--cc=shuah@kernel.org \
--cc=skhan@linuxfoundation.org \
--cc=steven.price@arm.com \
--cc=suzuki.poulose@arm.com \
--cc=tabba@google.com \
--cc=tglx@kernel.org \
--cc=vannapurve@google.com \
--cc=vbabka@kernel.org \
--cc=weixugc@google.com \
--cc=willy@infradead.org \
--cc=wyihan@google.com \
--cc=x86@kernel.org \
--cc=yan.y.zhao@intel.com \
--cc=yuanchu@google.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