* Re: [PATCH RFC v5 01/53] KVM: guest_memfd: Introduce per-gmem attributes, use to guard user mappings
From: Liam R. Howlett @ 2026-05-07 3:34 UTC (permalink / raw)
To: ackerleytng
Cc: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Baoquan He, Barry Song,
Axel Rasmussen, Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng,
Shakeel Butt, Kiryl Shutsemau, Jason Gunthorpe, Vlastimil Babka,
kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco
In-Reply-To: <20260428-gmem-inplace-conversion-v5-1-d8608ccfca22@google.com>
On 26/04/28 04:24PM, Ackerley Tng via B4 Relay wrote:
> 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 69c9d6d546b28..17e5a23fec0a1 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>
> @@ -33,6 +34,12 @@ struct gmem_inode {
> struct list_head gmem_file_list;
>
> 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)
> @@ -60,6 +67,31 @@ 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.
> + */
Can you please elaborate how you see inaccurate information and which
information is inaccurate?
Your comment is incorrect and misleading as append will not be used in
rcu mode. Note that you have not set this tree up in rcu mode.
> + 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);
> @@ -944,6 +1023,15 @@ 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;
> INIT_LIST_HEAD(&gi->gmem_file_list);
> return &gi->vfs_inode;
> @@ -951,7 +1039,26 @@ static struct inode *kvm_gmem_alloc_inode(struct super_block *sb)
>
> 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)
>
> --
> 2.54.0.545.g6539524ca2-goog
>
>
>
^ permalink raw reply
* Re: [PATCH RFC v5 10/53] KVM: guest_memfd: Add basic support for KVM_SET_MEMORY_ATTRIBUTES2
From: Liam R. Howlett @ 2026-05-07 3:46 UTC (permalink / raw)
To: ackerleytng
Cc: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Baoquan He, Barry Song,
Axel Rasmussen, Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng,
Shakeel Butt, Kiryl Shutsemau, Jason Gunthorpe, Vlastimil Babka,
kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco
In-Reply-To: <20260428-gmem-inplace-conversion-v5-10-d8608ccfca22@google.com>
On 26/04/28 04:25PM, Ackerley Tng via B4 Relay wrote:
> From: Ackerley Tng <ackerleytng@google.com>
>
> Introduce basic support for KVM_SET_MEMORY_ATTRIBUTES2 in guest_memfd,
> which just updates attributes tracked by guest_memfd.
>
> Validate input fields in general. Guard usage of KVM_SET_MEMORY_ATTRIBUTES2
> by making sure requested attributes are supported for this instance of kvm.
>
> A new KVM_SET_MEMORY_ATTRIBUTES2 is defined to support writes (unlike
> KVM_SET_MEMORY_ATTRIBUTES) in addition to reads so it can provide error
> details to userspace. This will be used in a later patch.
>
> The two ioctls use their corresponding structs with no overlap, but
> backward compatibility is baked in for future support of
> KVM_SET_MEMORY_ATTRIBUTES2 and struct kvm_memory_attributes2 in the VM
> ioctl.
>
> The process of setting memory attributes is set up such that the later half
> will not fail due to allocation. Any necessary checks are performed before
> the point of no return.
>
> 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: Sean Christoperson <seanjc@google.com>
> Signed-off-by: Sean Christoperson <seanjc@google.com>
> ---
> include/uapi/linux/kvm.h | 13 ++++++
> virt/kvm/Kconfig | 1 +
> virt/kvm/guest_memfd.c | 114 +++++++++++++++++++++++++++++++++++++++++++++++
> virt/kvm/kvm_main.c | 12 +++++
> 4 files changed, 140 insertions(+)
>
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index 6c8afa2047bf3..e6bbf68a83813 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -1648,6 +1648,19 @@ struct kvm_memory_attributes {
> __u64 flags;
> };
>
> +#define KVM_SET_MEMORY_ATTRIBUTES2 _IOWR(KVMIO, 0xd2, struct kvm_memory_attributes2)
> +
> +struct kvm_memory_attributes2 {
> + union {
> + __u64 address;
> + __u64 offset;
> + };
> + __u64 size;
> + __u64 attributes;
> + __u64 flags;
> + __u64 reserved[12];
> +};
> +
> #define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3)
>
> #define KVM_CREATE_GUEST_MEMFD _IOWR(KVMIO, 0xd4, struct kvm_create_guest_memfd)
> diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
> index 3fea89c45cfb4..e371e079e2c50 100644
> --- a/virt/kvm/Kconfig
> +++ b/virt/kvm/Kconfig
> @@ -109,6 +109,7 @@ config KVM_VM_MEMORY_ATTRIBUTES
>
> config KVM_GUEST_MEMFD
> select XARRAY_MULTI
> + select KVM_MEMORY_ATTRIBUTES
> bool
>
> config HAVE_KVM_ARCH_GMEM_PREPARE
> diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
> index 506219e2359eb..9a26eca717047 100644
> --- a/virt/kvm/guest_memfd.c
> +++ b/virt/kvm/guest_memfd.c
> @@ -552,11 +552,125 @@ unsigned long kvm_gmem_get_memory_attributes(struct kvm *kvm, gfn_t gfn)
> }
> EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_memory_attributes);
>
> +/*
> + * Preallocate memory for attributes to be stored on a maple tree, pointed to
> + * by mas. Adjacent ranges with attributes identical to the new attributes
> + * will be merged. Also sets mas's bounds up for storing attributes.
> + *
> + * This maintains the invariant that ranges with the same attributes will
> + * always be merged.
> + */
> +static int kvm_gmem_mas_preallocate(struct ma_state *mas, u64 attributes,
> + pgoff_t start, size_t nr_pages)
> +{
> + pgoff_t end = start + nr_pages;
> + pgoff_t last = end - 1;
> + void *entry;
> +
> + /* Try extending range. entry is NULL on overflow/wrap-around. */
> + mas_set_range(mas, end, end);
> + entry = mas_find(mas, end);
Please read the documentation as I believe you have a bug here. What
happens if there is another range stored higher than end + 1?
Do you have testing of these functions somewhere?
> + if (entry && xa_to_value(entry) == attributes)
> + last = mas->last;
> +
> + if (start > 0) {
> + mas_set_range(mas, start - 1, start - 1);
> + entry = mas_find(mas, start - 1);
> + if (entry && xa_to_value(entry) == attributes)
> + start = mas->index;
> + }
> +
> + mas_set_range(mas, start, last);
> + return mas_preallocate(mas, xa_mk_value(attributes), GFP_KERNEL);
> +}
> +
> +static int __kvm_gmem_set_attributes(struct inode *inode, pgoff_t start,
> + size_t nr_pages, uint64_t attrs)
> +{
> + struct address_space *mapping = inode->i_mapping;
> + struct gmem_inode *gi = GMEM_I(inode);
> + pgoff_t end = start + nr_pages;
> + struct maple_tree *mt;
> + struct ma_state mas;
> + int r;
> +
> + mt = &gi->attributes;
> +
> + filemap_invalidate_lock(mapping);
> +
> + mas_init(&mas, mt, start);
> + r = kvm_gmem_mas_preallocate(&mas, attrs, start, nr_pages);
> + if (r)
> + goto out;
> +
> + /*
> + * From this point on guest_memfd has performed necessary
> + * checks and can proceed to do guest-breaking changes.
> + */
> +
> + kvm_gmem_invalidate_begin(inode, start, end);
> + mas_store_prealloc(&mas, xa_mk_value(attrs));
> + kvm_gmem_invalidate_end(inode, start, end);
> +out:
> + filemap_invalidate_unlock(mapping);
> + return r;
> +}
> +
> +static long kvm_gmem_set_attributes(struct file *file, void __user *argp)
> +{
> + struct gmem_file *f = file->private_data;
> + struct inode *inode = file_inode(file);
> + struct kvm_memory_attributes2 attrs;
> + size_t nr_pages;
> + pgoff_t index;
> + int i;
> +
> + if (copy_from_user(&attrs, argp, sizeof(attrs)))
> + return -EFAULT;
> +
> + if (attrs.flags)
> + return -EINVAL;
> + for (i = 0; i < ARRAY_SIZE(attrs.reserved); i++) {
> + if (attrs.reserved[i])
> + return -EINVAL;
> + }
> + if (attrs.attributes & ~kvm_supported_mem_attributes(f->kvm))
> + return -EINVAL;
> + if (attrs.size == 0 || attrs.offset + attrs.size < attrs.offset)
> + return -EINVAL;
> + if (!PAGE_ALIGNED(attrs.offset) || !PAGE_ALIGNED(attrs.size))
> + return -EINVAL;
> +
> + if (attrs.offset >= i_size_read(inode) ||
> + attrs.offset + attrs.size > i_size_read(inode))
> + return -EINVAL;
> +
> + nr_pages = attrs.size >> PAGE_SHIFT;
> + index = attrs.offset >> PAGE_SHIFT;
> + return __kvm_gmem_set_attributes(inode, index, nr_pages,
> + attrs.attributes);
> +}
> +
> +static long kvm_gmem_ioctl(struct file *file, unsigned int ioctl,
> + unsigned long arg)
> +{
> + switch (ioctl) {
> + case KVM_SET_MEMORY_ATTRIBUTES2:
> + if (vm_memory_attributes)
> + return -ENOTTY;
> +
> + return kvm_gmem_set_attributes(file, (void __user *)arg);
> + default:
> + return -ENOTTY;
> + }
> +}
> +
> static struct file_operations kvm_gmem_fops = {
> .mmap = kvm_gmem_mmap,
> .open = generic_file_open,
> .release = kvm_gmem_release,
> .fallocate = kvm_gmem_fallocate,
> + .unlocked_ioctl = kvm_gmem_ioctl,
> };
>
> static int kvm_gmem_migrate_folio(struct address_space *mapping,
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index ff20e63143642..4d7bf52b7b717 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -110,6 +110,18 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(STATIC_CALL_KEY(__kvm_get_memory_attributes));
> EXPORT_SYMBOL_FOR_KVM_INTERNAL(STATIC_CALL_TRAMP(__kvm_get_memory_attributes));
> #endif
>
> +#define MEMORY_ATTRIBUTES_MATCH(one, two) \
> + static_assert(offsetof(struct kvm_memory_attributes, one) == \
> + offsetof(struct kvm_memory_attributes2, two)); \
> + static_assert(sizeof_field(struct kvm_memory_attributes, one) ==\
> + sizeof_field(struct kvm_memory_attributes2, two))
> +
> +/* Ensure the common parts of the two structs are identical. */
> +MEMORY_ATTRIBUTES_MATCH(address, address);
> +MEMORY_ATTRIBUTES_MATCH(size, size);
> +MEMORY_ATTRIBUTES_MATCH(attributes, attributes);
> +MEMORY_ATTRIBUTES_MATCH(flags, flags);
> +
> /*
> * Ordering of locks:
> *
>
> --
> 2.54.0.545.g6539524ca2-goog
>
>
>
^ permalink raw reply
* Re: [RFC PATCH 04/12] vfio/pci: Allow MMIO regions to be exported through dma-buf
From: Alexey Kardashevskiy @ 2026-05-07 7:16 UTC (permalink / raw)
To: Jason Gunthorpe
Cc: Xu Yilun, kvm, dri-devel, linux-media, linaro-mm-sig,
sumit.semwal, christian.koenig, pbonzini, seanjc, alex.williamson,
vivek.kasireddy, dan.j.williams, yilun.xu, linux-coco,
linux-kernel, lukas, yan.y.zhao, daniel.vetter, leon, baolu.lu,
zhenzhong.duan, tao1.su
In-Reply-To: <afs/Jamxnj6GGFfM@nvidia.com>
On 6/5/26 23:16, Jason Gunthorpe wrote:
> On Wed, May 06, 2026 at 12:35:42PM +1000, Alexey Kardashevskiy wrote:
>> Hi!
>>
>> Let's reignite this topic.
>>
>> I've been using these patches + QEMU side hacks for 6+ months. And it's been fine until I got a device where MSIX BAR is in a middle of another BAR marked as TEE in the TDISP interface report. And no trusted MSIX yet.
>>
>> Every time QEMU mmaps a BAR - I request a dmabuf fd from VFIO in QEMU. Since mapping of an entire MSIX BAR is allowed by default, VFIORegion::nr_mmaps==1 and it is an entire BAR.
>>
>> Problem: KVM memslot mismatches the dmabuf fd size
>
> Huh? kvm does not care about dmabuf at all? Are you running other
> patches to hook kvm and dmabuf?
yup, 06/12 of this patchset.
> Putting a slice in a dmabuf is a well understood need for MSI, so I
> expect whatever kvm dmabuf interface that gets merged to accomodate
> this?
good to know.
>> Solution2: modify logic in VFIO dmabuf to allow multiple KVM memory
>> slots per dmabuf. Now it is kvm_memory_slot::dmabuf_attach with no
>> offset into the dmabuf and one kvm_vfio_dmabuf per dma_buf.
>
> Yes, when kvm learns to take in a dmabuf it needs to take in a slice,
> not the whole buf. Or you need to create multiple dmabufs with the
> necessary slices from the VFIO. The upstream vfio dmabuf creation
> allows creating it with a slice.
true but either way dmabuf slicing will be directed by QEMU's msix-table emulation MR and this slicing needs to match the TDISP report so I'll have to teach QEMU these reports, right? I am worried if I miss something obvious, again. Thanks,
ps. I like nntp.lore.kernel.org very much for ability to dig out old stuff and then just reply to it :)
>
> Jason
--
Alexey
^ permalink raw reply
* Re: [PATCH v2 1/4] x86/tdx: Use PFN directly for mapping guest private memory
From: Xiaoyao Li @ 2026-05-07 7:49 UTC (permalink / raw)
To: Yan Zhao, dave.hansen, pbonzini, seanjc
Cc: tglx, mingo, bp, kas, x86, linux-kernel, kvm, linux-coco,
kai.huang, rick.p.edgecombe, yilun.xu, vannapurve, ackerleytng,
sagis, binbin.wu, isaku.yamahata
In-Reply-To: <20260430014929.24210-1-yan.y.zhao@intel.com>
On 4/30/2026 9:49 AM, Yan Zhao wrote:
> From: Sean Christopherson <seanjc@google.com>
>
> Remove struct page assumptions/constraints in the SEAMCALL wrapper APIs for
> mapping guest private memory and have them take PFN directly.
>
> Having core TDX make assumptions that guest private memory must be backed
> by struct page (and/or folio) will create subtle dependencies on how
> KVM/guest_memfd allocates/manages memory (e.g., whether it uses memory
> allocated from core MM, if the memory is refcounted, or if the folio is
> split) that are easily avoided. [1].
>
> KVM's MMUs work with PFNs. This is very much an intentional design choice.
> It ensures that the KVM MMUs remain flexible and are not too tied to the
> regular CPU MMUs and the kernel code around them. Using 'struct page' for
> TDX guest memory is not a good fit anywhere near the KVM MMU code [2].
>
> Use "kvm_pfn_t pfn" for type safety. Using this KVM type is appropriate
> since APIs tdh_mem_page_add() and tdh_mem_page_aug() are exported to KVM
> only.
>
> [ Yan: Replace "u64 pfn" with "kvm_pfn_t pfn" ]
>
> Signed-off-by: Sean Christopherson <seanjc@google.com>
> Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
> Link: https://lore.kernel.org/all/aWgyhmTJphGQqO0Y@google.com [1]
> Link: https://lore.kernel.org/all/ac7V0g2q2hN3dU5u@google.com [2]
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
...
> +static void tdx_clflush_pfn(kvm_pfn_t pfn)
> +{
> + clflush_cache_range(__va(PFN_PHYS(pfn)), PAGE_SIZE);
If the pfn is not in the kernel direct map, we will get #PF, right?
There is on-going attempt to remove the direct map for guest_memfd. The
good news is TDX is excluded. [1]
[1] https://lore.kernel.org/all/20260410151746.61150-9-kalyazin@amazon.com/
^ permalink raw reply
* Re: [PATCH v2 2/4] x86/tdx: Use PFN directly for unmapping guest private memory
From: Xiaoyao Li @ 2026-05-07 7:54 UTC (permalink / raw)
To: Yan Zhao, dave.hansen, pbonzini, seanjc
Cc: tglx, mingo, bp, kas, x86, linux-kernel, kvm, linux-coco,
kai.huang, rick.p.edgecombe, yilun.xu, vannapurve, ackerleytng,
sagis, binbin.wu, isaku.yamahata
In-Reply-To: <20260430014948.24226-1-yan.y.zhao@intel.com>
On 4/30/2026 9:49 AM, Yan Zhao wrote:
> From: Sean Christopherson<seanjc@google.com>
>
> Remove struct page assumptions/constraints in APIs for unmapping guest
> private memory and have them take physical address directly.
>
> Having core TDX make assumptions that guest private memory must be backed
> by struct page (and/or folio) will create subtle dependencies on how
> KVM/guest_memfd allocates/manages memory (e.g., whether it uses memory
> allocated from core MM, if the memory is refcounted, or if the folio is
> split) that are easily avoided. [1].
>
> KVM's MMUs work with PFNs. This is very much an intentional design choice.
> It ensures that the KVM MMUs remain flexible and are not too tightly tied
> to the regular CPU MMUs and the kernel code around them. Using
> "struct page" for TDX guest memory is not a good fit anywhere near the KVM
> MMU code [2].
>
> Therefore, for unmapping guest private memory: export
> tdx_quirk_reset_paddr() for direct KVM invocation, and convert the SEAMCALL
> wrapper API tdh_phymem_page_wbinvd_hkid() to take PFN as input (thus
> updating mk_keyed_paddr() and tdh_phymem_page_wbinvd_tdr()).
>
> Intentionally have KVM pass PAGE_SIZE (rather than KVM_HPAGE_SIZE(level))
> to tdx_quirk_reset_paddr() in tdx_sept_remove_private_spte() to avoid
> mixing in huge page changes. The KVM_BUG_ON() check for !PG_LEVEL_4K in
> tdx_sept_remove_private_spte() justifies using PAGE_SIZE.
>
> Do not convert tdx_reclaim_page() to use PFN as input since it currently
> does not remove guest private memory.
>
> Use "kvm_pfn_t pfn" for type safety. Using this KVM type is appropriate
> since APIs tdh_phymem_page_wbinvd_hkid() and tdx_quirk_reset_paddr() are
> exported to KVM only.
>
> [Yan: Use kvm_pfn_t,exclude tdx_reclaim_page(),use tdx_quirk_reset_paddr()]
>
> Signed-off-by: Sean Christopherson<seanjc@google.com>
> Signed-off-by: Yan Zhao<yan.y.zhao@intel.com>
> Link:https://lore.kernel.org/all/aWgyhmTJphGQqO0Y@google.com [1]
> Link:https://lore.kernel.org/all/ac7V0g2q2hN3dU5u@google.com [2]
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
^ permalink raw reply
* Re: [PATCH v2 3/4] x86/tdx: Drop exported function tdx_quirk_reset_page()
From: Xiaoyao Li @ 2026-05-07 8:02 UTC (permalink / raw)
To: Yan Zhao, dave.hansen, pbonzini, seanjc
Cc: tglx, mingo, bp, kas, x86, linux-kernel, kvm, linux-coco,
kai.huang, rick.p.edgecombe, yilun.xu, vannapurve, ackerleytng,
sagis, binbin.wu, isaku.yamahata
In-Reply-To: <20260430015001.24242-1-yan.y.zhao@intel.com>
On 4/30/2026 9:50 AM, Yan Zhao wrote:
> KVM invokes tdx_quirk_reset_page() to reset TDX control pages (including
> S-EPT pages, TDR page, etc.), as all those pages are allocated by KVM TDX
> and thus always have struct page.
>
> However, it's also reasonable for KVM to reset those TDX control pages via
> tdx_quirk_reset_paddr() directly, eliminating the need to export two
> parallel APIs. Keeping tdx_quirk_reset_page() as a one-line helper in the
> header file is also unnecessary.
>
> No functional change intended.
>
> Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
> Suggested-by: Xiaoyao Li <xiaoyao.li@intel.com>
> Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
> ---
> arch/x86/include/asm/tdx.h | 1 -
> arch/x86/kvm/vmx/tdx.c | 4 ++--
> arch/x86/virt/vmx/tdx/tdx.c | 6 ------
> 3 files changed, 2 insertions(+), 9 deletions(-)
>
> diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
> index 65f7d874fb5a..9c63deaa0e8f 100644
> --- a/arch/x86/include/asm/tdx.h
> +++ b/arch/x86/include/asm/tdx.h
> @@ -153,7 +153,6 @@ int tdx_guest_keyid_alloc(void);
> u32 tdx_get_nr_guest_keyids(void);
> void tdx_guest_keyid_free(unsigned int keyid);
>
> -void tdx_quirk_reset_page(struct page *page);
> void tdx_quirk_reset_paddr(unsigned long base, unsigned long size);
>
> struct tdx_td {
> diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
> index a2aadc6d0174..9bd4fd748e2a 100644
> --- a/arch/x86/kvm/vmx/tdx.c
> +++ b/arch/x86/kvm/vmx/tdx.c
> @@ -343,7 +343,7 @@ static int tdx_reclaim_page(struct page *page)
>
> r = __tdx_reclaim_page(page);
> if (!r)
> - tdx_quirk_reset_page(page);
> + tdx_quirk_reset_paddr(page_to_phys(page), PAGE_SIZE);
> return r;
> }
>
> @@ -597,7 +597,7 @@ static void tdx_reclaim_td_control_pages(struct kvm *kvm)
> if (TDX_BUG_ON(err, TDH_PHYMEM_PAGE_WBINVD, kvm))
> return;
>
> - tdx_quirk_reset_page(kvm_tdx->td.tdr_page);
> + tdx_quirk_reset_paddr(page_to_phys(kvm_tdx->td.tdr_page), PAGE_SIZE);
>
> __free_page(kvm_tdx->td.tdr_page);
> kvm_tdx->td.tdr_page = NULL;
> diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
> index e5a37ea2d4a0..deb67e68f85f 100644
> --- a/arch/x86/virt/vmx/tdx/tdx.c
> +++ b/arch/x86/virt/vmx/tdx/tdx.c
> @@ -731,12 +731,6 @@ void tdx_quirk_reset_paddr(unsigned long base, unsigned long size)
> }
> EXPORT_SYMBOL_FOR_KVM(tdx_quirk_reset_paddr);
>
> -void tdx_quirk_reset_page(struct page *page)
> -{
> - tdx_quirk_reset_paddr(page_to_phys(page), PAGE_SIZE);
> -}
> -EXPORT_SYMBOL_FOR_KVM(tdx_quirk_reset_page);
> -
> static __init void tdmr_quirk_reset_pamt(struct tdmr_info *tdmr)
>
> {
^ permalink raw reply
* Re: [PATCH v2 4/4] x86/virt/tdx: Move mk_keyed_paddr() to tdx.c due to no external users
From: Xiaoyao Li @ 2026-05-07 8:07 UTC (permalink / raw)
To: Yan Zhao, dave.hansen, pbonzini, seanjc
Cc: tglx, mingo, bp, kas, x86, linux-kernel, kvm, linux-coco,
kai.huang, rick.p.edgecombe, yilun.xu, vannapurve, ackerleytng,
sagis, binbin.wu, isaku.yamahata
In-Reply-To: <20260430015014.24261-1-yan.y.zhao@intel.com>
On 4/30/2026 9:50 AM, Yan Zhao wrote:
> Move mk_keyed_paddr() from tdx.h to tdx.c to avoid unnecessary header
> inclusion and improve encapsulation since there are no users outside of
> tdx.c.
>
> No functional change intended.
Missing a new blank line.
> Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
> ---
> arch/x86/include/asm/tdx.h | 6 ------
> arch/x86/virt/vmx/tdx/tdx.c | 6 ++++++
> 2 files changed, 6 insertions(+), 6 deletions(-)
>
> diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
> index 9c63deaa0e8f..503f9a3f46d6 100644
> --- a/arch/x86/include/asm/tdx.h
> +++ b/arch/x86/include/asm/tdx.h
> @@ -177,12 +177,6 @@ struct tdx_vp {
> struct page **tdcx_pages;
> };
>
> -static inline u64 mk_keyed_paddr(u16 hkid, kvm_pfn_t pfn)
> -{
> - /* KeyID bits are just above the physical address bits. */
> - return PFN_PHYS(pfn) | ((u64)hkid << boot_cpu_data.x86_phys_bits);
> -}
> -
> u64 tdh_vp_enter(struct tdx_vp *vp, struct tdx_module_args *args);
> u64 tdh_mng_addcx(struct tdx_td *td, struct page *tdcs_page);
> u64 tdh_mem_page_add(struct tdx_td *td, u64 gpa, kvm_pfn_t pfn, struct page *source,
> diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
> index deb67e68f85f..967482ae3c80 100644
> --- a/arch/x86/virt/vmx/tdx/tdx.c
> +++ b/arch/x86/virt/vmx/tdx/tdx.c
> @@ -1911,6 +1911,12 @@ u64 tdh_phymem_cache_wb(bool resume)
> }
> EXPORT_SYMBOL_FOR_KVM(tdh_phymem_cache_wb);
>
> +static inline u64 mk_keyed_paddr(u16 hkid, kvm_pfn_t pfn)
> +{
> + /* KeyID bits are just above the physical address bits. */
> + return PFN_PHYS(pfn) | ((u64)hkid << boot_cpu_data.x86_phys_bits);
> +}
> +
> u64 tdh_phymem_page_wbinvd_tdr(struct tdx_td *td)
> {
> struct tdx_module_args args = {};
^ permalink raw reply
* Re: [PATCH v2 1/4] x86/tdx: Use PFN directly for mapping guest private memory
From: Yan Zhao @ 2026-05-07 8:08 UTC (permalink / raw)
To: Xiaoyao Li
Cc: dave.hansen, pbonzini, seanjc, tglx, mingo, bp, kas, x86,
linux-kernel, kvm, linux-coco, kai.huang, rick.p.edgecombe,
yilun.xu, vannapurve, ackerleytng, sagis, binbin.wu,
isaku.yamahata
In-Reply-To: <28c8d380-d2e5-4f70-96b0-00225e0ea86d@intel.com>
On Thu, May 07, 2026 at 03:49:09PM +0800, Xiaoyao Li wrote:
> On 4/30/2026 9:49 AM, Yan Zhao wrote:
> > From: Sean Christopherson <seanjc@google.com>
> >
> > Remove struct page assumptions/constraints in the SEAMCALL wrapper APIs for
> > mapping guest private memory and have them take PFN directly.
> >
> > Having core TDX make assumptions that guest private memory must be backed
> > by struct page (and/or folio) will create subtle dependencies on how
> > KVM/guest_memfd allocates/manages memory (e.g., whether it uses memory
> > allocated from core MM, if the memory is refcounted, or if the folio is
> > split) that are easily avoided. [1].
> >
> > KVM's MMUs work with PFNs. This is very much an intentional design choice.
> > It ensures that the KVM MMUs remain flexible and are not too tied to the
> > regular CPU MMUs and the kernel code around them. Using 'struct page' for
> > TDX guest memory is not a good fit anywhere near the KVM MMU code [2].
> >
> > Use "kvm_pfn_t pfn" for type safety. Using this KVM type is appropriate
> > since APIs tdh_mem_page_add() and tdh_mem_page_aug() are exported to KVM
> > only.
> >
> > [ Yan: Replace "u64 pfn" with "kvm_pfn_t pfn" ]
> >
> > Signed-off-by: Sean Christopherson <seanjc@google.com>
> > Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
> > Link: https://lore.kernel.org/all/aWgyhmTJphGQqO0Y@google.com [1]
> > Link: https://lore.kernel.org/all/ac7V0g2q2hN3dU5u@google.com [2]
>
> Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Thanks!
> > +static void tdx_clflush_pfn(kvm_pfn_t pfn)
> > +{
> > + clflush_cache_range(__va(PFN_PHYS(pfn)), PAGE_SIZE);
>
> If the pfn is not in the kernel direct map, we will get #PF, right?
Right.
There's no simple interface like pfn_range_is_mapped() that tells whether a PFN
has direct map or not if removing direct map is supported.
So, as PFNs not in the kernel direct map are unexpected for TDX, this series
leaves #PF, which is obvious enough for debugging.
> There is on-going attempt to remove the direct map for guest_memfd. The good
> news is TDX is excluded. [1]
We can see if any code refinement is necessary if TDX is included in the future.
> [1] https://lore.kernel.org/all/20260410151746.61150-9-kalyazin@amazon.com/
^ permalink raw reply
* Re: [PATCH v8 08/21] x86/virt/seamldr: Allocate and populate a module update request
From: Chao Gao @ 2026-05-07 13:19 UTC (permalink / raw)
To: Dave Hansen
Cc: kvm, linux-coco, linux-kernel, x86, binbin.wu, dave.hansen, djbw,
ira.weiny, kai.huang, kas, nik.borisov, paulmck, pbonzini,
reinette.chatre, rick.p.edgecombe, sagis, seanjc, tony.lindgren,
vannapurve, vishal.l.verma, yilun.xu, xiaoyao.li, yan.y.zhao,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, H. Peter Anvin
In-Reply-To: <a52c4701-c99d-48d5-9b63-8eb1c0e589f0@intel.com>
>> header is consumed solely by the kernel to extract the sigstruct and
>> module, so validate it before processing to protect the kernel ABI. The
>> sigstruct and module are passed to and validated by P-SEAMLDR, so don't
>> duplicate any validation in the kernel.
>>
>> Note: the sigstruct_pa field in SEAMLDR_PARAMS has been extended to
>> a 4-element array. The updated "SEAM Loader (SEAMLDR) Interface
>> Specification" will be published separately.
>
>These changelogs have all the right info, but I find them really hard to
>parse. For instance, if you're going to have a 'struct seamldr_params',
>then just stick with that name. Don't use the "SEAMLDR_PARAMS" name too.
>
>Start with the data structures:
>
>There are two important ABIs here:
>
>'struct tdx_blob' - the on-disk and in-memory format for a TDX
> module update image.
>'struct seamldr_params' - The in-memory ABI passed to the TDX module
> loader. Points to a single 'struct tdx_blob'
Thanks for the thorough review.
Your comments all make sense to me. I just want to confirm two points
below.
>> + /*
>> + * Don't care about user passing the wrong file, but protect
>> + * kernel ABI by preventing accepting garbage.
>> + */
>> + if (memcmp(blob->signature, "TDX-BLOB", 8))
>> + return ERR_PTR(-EINVAL);
>
>Is there really no helper in the kernel anywhere that can safely do the
>8-byte compare against two known-to-the-compiler 8-byte-wide fields
>without hard-coding the 8?
I couldn't find a helper that automatically derives the comparison
length from the operands. 'strcmp()' is not suitable here because
'blob->signature' is not NUL-terminated.
Do you mean just avoiding the hard-coded 8, e.g.
if (memcmp(blob->signature, "TDX-BLOB", sizeof(blob->signature)))
return ERR_PTR(-EINVAL);
or define the 'u8 signature[8]' as a u64 and compare it with a constant, like
/* Little-endian encoding of "TDX-BLOB" string */
#define TDX_IMAGE_SIGNATURE 0x424f4c422d584454ULL
if (blob->signature != TDX_IMAGE_SIGNATURE)
return ERR_PTR(-EINVAL);
>> + struct seamldr_params *params;
>> + int module_pg_cnt, sig_pg_cnt;
>> + const u8 *sig, *module;
>> + int i;
>> +
>> + params = (struct seamldr_params *)get_zeroed_page(GFP_KERNEL);
>> + if (!params)
>> + return ERR_PTR(-ENOMEM);
>
>kzmalloc(PAGE_SIZE, GFP_KERNEL) will save you a cast.
I noticed that 'kzalloc_obj()' can be used here, which avoids spelling out
the size and GFP flags explicitly. So I ended up with:
params = kzalloc_obj(*params);
If you would prefer 'kzalloc(PAGE_SIZE, GFP_KERNEL)', I can switch to that.
^ permalink raw reply
* Re: [PATCH RFC v5 10/53] KVM: guest_memfd: Add basic support for KVM_SET_MEMORY_ATTRIBUTES2
From: Ackerley Tng @ 2026-05-07 16:56 UTC (permalink / raw)
To: Liam R. Howlett
Cc: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Baoquan He, Barry Song,
Axel Rasmussen, Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng,
Shakeel Butt, Kiryl Shutsemau, Jason Gunthorpe, Vlastimil Babka,
kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco
In-Reply-To: <n5ce32wumzeiqqyqutom4apy2kqfetbvusc6j4k2xarsska5mw@klp5bmy7qhfm>
"Liam R. Howlett" <liam@infradead.org> writes:
> On 26/04/28 04:25PM, Ackerley Tng via B4 Relay wrote:
>>
>> [...snip...]
>>
>> +/*
>> + * Preallocate memory for attributes to be stored on a maple tree, pointed to
>> + * by mas. Adjacent ranges with attributes identical to the new attributes
>> + * will be merged. Also sets mas's bounds up for storing attributes.
>> + *
>> + * This maintains the invariant that ranges with the same attributes will
>> + * always be merged.
>> + */
>> +static int kvm_gmem_mas_preallocate(struct ma_state *mas, u64 attributes,
>> + pgoff_t start, size_t nr_pages)
>> +{
>> + pgoff_t end = start + nr_pages;
>> + pgoff_t last = end - 1;
>> + void *entry;
>> +
>> + /* Try extending range. entry is NULL on overflow/wrap-around. */
>> + mas_set_range(mas, end, end);
>> + entry = mas_find(mas, end);
Thank you for your reviews!
>
> Please read the documentation as I believe you have a bug here. What
> happens if there is another range stored higher than end + 1?
>
The invariant in this maple tree is that contiguous ranges with the same
attribute are stored as a single range.
The goal of this first part is to get the entry at the index just after
the requested range, and see what the attribute there is. If that
attribute is what we're about to set, extend the requested range for
storing to the end of that range.
If there is another range higher than end + 1, with the invariant
maintained, that attribute has to be different than the attribute stored
at end. Hence, we only want to extend this requested range up till end.
> Do you have testing of these functions somewhere?
>
GMEM_CONVERSION_MULTIPAGE_TEST_INIT_SHARED(indexing, 4) tests setting
attributes in ranges. If test_page is 2,
1. [0, 4) starts off shared (4 is the number of pages in the guest_memfd)
2. [2, 3) is converted to private
=> so the ranges should now be [0, 2), [2, 3), [3, 4)
3. [2, 3) is converted back to shared
=> so the ranges should now be [0, 4)
I verified this by inserting some trace_printk()s and inspecting manually.
>> + if (entry && xa_to_value(entry) == attributes)
>> + last = mas->last;
>> +
>> + if (start > 0) {
>> + mas_set_range(mas, start - 1, start - 1);
>> + entry = mas_find(mas, start - 1);
>> + if (entry && xa_to_value(entry) == attributes)
>> + start = mas->index;
>> + }
>> +
>> + mas_set_range(mas, start, last);
>> + return mas_preallocate(mas, xa_mk_value(attributes), GFP_KERNEL);
>> +}
>> +
>>
>> [...snip...]
>>
^ permalink raw reply
* Re: [PATCH RFC v5 01/53] KVM: guest_memfd: Introduce per-gmem attributes, use to guard user mappings
From: Ackerley Tng @ 2026-05-07 18:31 UTC (permalink / raw)
To: Liam R. Howlett
Cc: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Baoquan He, Barry Song,
Axel Rasmussen, Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng,
Shakeel Butt, Kiryl Shutsemau, Jason Gunthorpe, Vlastimil Babka,
kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco
In-Reply-To: <byywwfin2aenobdwuesqihm6nzxyx6ecedwgbt7f5tvaaul6fi@u7bmexpavwdn>
"Liam R. Howlett" <liam@infradead.org> writes:
>
> [...snip...]
>
>> +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.
>> + */
>
> Can you please elaborate how you see inaccurate information and which
> information is inaccurate?
>
> Your comment is incorrect and misleading as append will not be used in
> rcu mode. Note that you have not set this tree up in rcu mode.
>
My bad. Thanks for clarifying about usage of rcu mode.
>> + lockdep_assert(mt_lock_is_held(mt));
>> +
In the next revision I'll remove this lockdep and use RCU mode, and
kvm_gmem_get_memory_attributes() should get a stable result.
The other lookups using mt_for_each() in kvm_gmem_range_has_attributes()
and kvm_gmem_get_invalidate_filter() retain the lockdep since those
operate over multiple ranges. Those are called from paths that require
holding the lock to exclude other operations anyway, so the lockdep
requirement does not cost anything more.
>> + return WARN_ON_ONCE(!entry) ? 0 : xa_to_value(entry);
>> +}
>> +
>>
>> [...snip...]
>>
^ permalink raw reply
* Re: [PATCH v2 1/4] x86/tdx: Use PFN directly for mapping guest private memory
From: Sean Christopherson @ 2026-05-07 18:46 UTC (permalink / raw)
To: Yan Zhao
Cc: Xiaoyao Li, dave.hansen, pbonzini, tglx, mingo, bp, kas, x86,
linux-kernel, kvm, linux-coco, kai.huang, rick.p.edgecombe,
yilun.xu, vannapurve, ackerleytng, sagis, binbin.wu,
isaku.yamahata
In-Reply-To: <afxIc/0qNvwcr4VQ@yzhao56-desk.sh.intel.com>
On Thu, May 07, 2026, Yan Zhao wrote:
> On Thu, May 07, 2026 at 03:49:09PM +0800, Xiaoyao Li wrote:
> > On 4/30/2026 9:49 AM, Yan Zhao wrote:
> > There is on-going attempt to remove the direct map for guest_memfd. The good
> > news is TDX is excluded. [1]
> We can see if any code refinement is necessary if TDX is included in the future.
Yeah, I wouldn't worry too much about that effort. The onus will firmly be on
that series to do the right thing for TDX (and any other unique code).
^ permalink raw reply
* [PATCH v6 00/43] guest_memfd: In-place conversion support
From: Ackerley Tng via B4 Relay @ 2026-05-07 20:22 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, liam, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Baoquan He, Barry Song,
Axel Rasmussen, Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng,
Shakeel Butt, Kiryl Shutsemau, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco, Ackerley Tng
This is v6 of guest_memfd in-place conversion support, now out of RFC.
Up till now, guest_memfd supports the entire inode worth of memory being
used as all-shared, or all-private. CoCo VMs may request guest memory to be
converted between private and shared states, and the only way to support
that currently would be to have the userspace VMM provide two sources of
backing memory from completely different areas of physical memory.
pKVM has a use case for in-place sharing: the guest and host may be
cooperating on given data, and pKVM doesn't protect data through
encryption, so copying that given data between different areas of physical
memory as part of conversions would be unnecessary work.
This series also serves as a foundation for guest_memfd huge page
support. Now, guest_memfd only supports PAGE_SIZE pages, so if two sources
of backing memory are used, the userspace VMM could maintain a steady total
memory utilized by punching out the pages that are not used. When huge
pages are available in guest_memfd, even if the backing memory source
supports hole punching within a huge page, punching out pages to maintain
the total memory utilized by a VM would be introducing lots of
fragmentation.
In-place conversion avoids fragmentation by allowing the same physical
memory to be used for both shared and private memory, with guest_memfd
tracks the shared/private status of all the pages at a per-page
granularity.
The central principle, which guest_memfd continues to uphold, is that any
guest-private page will not be mappable to host userspace. All pages will
be mmap()-able in host userspace, but accesses to guest-private pages (as
tracked by guest_memfd) will result in a SIGBUS.
This series introduces a guest_memfd ioctl (not kvm, vm or vcpu, but
guest_memfd ioctl) that allows userspace to set memory
attributes (shared/private) directly through the guest_memfd. This is the
appropriate interface because shared/private-ness is a property of memory
and hence the request should be sent directly to the memory provider -
guest_memfd.
Tested with both CONFIG_KVM_VM_MEMORY_ATTRIBUTES enabled and disabled:
+ tools/testing/selftests/kvm/guest_memfd_test.c
+ tools/testing/selftests/kvm/pre_fault_memory_test.c
+ tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c
+ tools/testing/selftests/kvm/x86/private_mem_conversions_test.c
+ tools/testing/selftests/kvm/x86/private_mem_conversions_test.sh
+ tools/testing/selftests/kvm/x86/private_mem_kvm_exits_test.c
Updates for this revision:
+ Dropped everything to do with content modes (ZERO/PRESERVE) (thanks
Michael and Sean!)
+ Discussed this at PUCK on 2026-05-06
+ guest_memfd was taking on too much complexity to try to paper
over differences in how trusted firmware handle conversions
+ Addressed Liam's comments about usage of the maple_tree
TODOs
+ Resolve issue where guest_memfd_conversions_test, which uses the
kselftest framework, doesn't perform teardown on assertion
failure. Please see proposal at [9]
+ Test with TDX selftests. We're in the process of rebasing TDX selftests
on this series and will post updates when that's tested.
I would like feedback on:
+ The use of private_mem_conversions_test.sh to run different options in
private_mem_conversions_test. If this makes sense, I'll adjust the
Makefile to have private_mem_conversions_test tested only via the script.
This series is based on kvm/next, and here's the tree for your convenience:
https://github.com/googleprodkernel/linux-cc/commits/guest_memfd-inplace-conversion-v6
Older series:
+ RFCv5 is at [8]
+ RFCv4 is at [7]
+ RFCv3 is at [6]
+ RFCv2 is at [5]
+ RFCv1 is at [4]
+ Previous versions of this feature, part of other series, are available at
[1][2][3].
[1] https://lore.kernel.org/all/bd163de3118b626d1005aa88e71ef2fb72f0be0f.1726009989.git.ackerleytng@google.com/
[2] https://lore.kernel.org/all/20250117163001.2326672-6-tabba@google.com/
[3] https://lore.kernel.org/all/b784326e9ccae6a08388f1bf39db70a2204bdc51.1747264138.git.ackerleytng@google.com/
[4] https://lore.kernel.org/all/cover.1760731772.git.ackerleytng@google.com/T/
[5] https://lore.kernel.org/all/cover.1770071243.git.ackerleytng@google.com/T/
[6] https://lore.kernel.org/r/20260313-gmem-inplace-conversion-v3-0-5fc12a70ec89@google.com/T/
[7] https://lore.kernel.org/all/20260326-gmem-inplace-conversion-v4-0-e202fe950ffd@google.com/T/
[8] https://lore.kernel.org/r/20260428-gmem-inplace-conversion-v5-0-d8608ccfca22@google.com
[9] https://lore.kernel.org/all/20260414-selftest-global-metadata-v1-0-fd223922bc57@google.com/T/
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
Ackerley Tng (25):
KVM: x86/mmu: Bug the VM if gmem attributes are queried to determine max mapping level
KVM: guest_memfd: Update kvm_gmem_populate() to use gmem attributes
KVM: guest_memfd: Only prepare folios for private pages
KVM: Move kvm_supported_mem_attributes() to kvm_host.h
KVM: guest_memfd: Add base support for KVM_SET_MEMORY_ATTRIBUTES2
KVM: guest_memfd: Ensure pages are not in use before conversion
KVM: guest_memfd: Call arch invalidate hooks on conversion
KVM: guest_memfd: Return early if range already has requested attributes
KVM: guest_memfd: Advertise KVM_SET_MEMORY_ATTRIBUTES2 ioctl
KVM: guest_memfd: Handle lru_add fbatch refcounts during conversion safety check
KVM: guest_memfd: Use actual size for invalidation in kvm_gmem_release()
KVM: guest_memfd: Determine invalidation filter from memory attributes
KVM: TDX: Make source page optional for KVM_TDX_INIT_MEM_REGION
KVM: selftests: Test basic single-page conversion flow
KVM: selftests: Test conversion flow when INIT_SHARED
KVM: selftests: Test conversion precision in guest_memfd
KVM: selftests: Test conversion before allocation
KVM: selftests: Convert with allocated folios in different layouts
KVM: selftests: Test that truncation does not change shared/private status
KVM: selftests: Test conversion with elevated page refcount
KVM: selftests: Reset shared memory after hole-punching
KVM: selftests: Provide function to look up guest_memfd details from gpa
KVM: selftests: Make TEST_EXPECT_SIGBUS thread-safe
KVM: selftests: Update private_mem_conversions_test to mmap() guest_memfd
KVM: selftests: Add script to exercise private_mem_conversions_test
Michael Roth (1):
KVM: SEV: Make 'uaddr' parameter optional for KVM_SEV_SNP_LAUNCH_UPDATE
Sean Christopherson (17):
KVM: guest_memfd: Introduce per-gmem attributes, use to guard user mappings
KVM: Rename KVM_GENERIC_MEMORY_ATTRIBUTES to KVM_VM_MEMORY_ATTRIBUTES
KVM: Enumerate support for PRIVATE memory iff kvm_arch_has_private_mem is defined
KVM: Stub in ability to disable per-VM memory attribute tracking
KVM: guest_memfd: Wire up kvm_get_memory_attributes() to per-gmem attributes
KVM: Move KVM_VM_MEMORY_ATTRIBUTES config definition to x86
KVM: Let userspace disable per-VM mem attributes, enable per-gmem attributes
KVM: guest_memfd: Enable INIT_SHARED on guest_memfd for x86 Coco VMs
KVM: selftests: Create gmem fd before "regular" fd when adding memslot
KVM: selftests: Rename guest_memfd{,_offset} to gmem_{fd,offset}
KVM: selftests: Add support for mmap() on guest_memfd in core library
KVM: selftests: Add selftests global for guest memory attributes capability
KVM: selftests: Add helpers for calling ioctls on guest_memfd
KVM: selftests: Test that shared/private status is consistent across processes
KVM: selftests: Provide common function to set memory attributes
KVM: selftests: Check fd/flags provided to mmap() when setting up memslot
KVM: selftests: Update private memory exits test to work with per-gmem attributes
Documentation/virt/kvm/api.rst | 78 +++-
.../virt/kvm/x86/amd-memory-encryption.rst | 15 +-
Documentation/virt/kvm/x86/intel-tdx.rst | 4 +
arch/x86/include/asm/kvm_host.h | 2 +-
arch/x86/kvm/Kconfig | 15 +-
arch/x86/kvm/mmu/mmu.c | 13 +-
arch/x86/kvm/svm/sev.c | 18 +-
arch/x86/kvm/vmx/tdx.c | 11 +-
arch/x86/kvm/x86.c | 13 +-
include/linux/kvm_host.h | 53 ++-
include/trace/events/kvm.h | 4 +-
include/uapi/linux/kvm.h | 16 +
mm/swap.c | 2 +
tools/testing/selftests/kvm/Makefile.kvm | 5 +
tools/testing/selftests/kvm/include/kvm_util.h | 138 +++++-
tools/testing/selftests/kvm/include/test_util.h | 34 +-
.../selftests/kvm/kvm_has_gmem_attributes.c | 17 +
tools/testing/selftests/kvm/lib/kvm_util.c | 133 +++---
tools/testing/selftests/kvm/lib/test_util.c | 7 -
.../kvm/x86/guest_memfd_conversions_test.c | 487 +++++++++++++++++++++
.../kvm/x86/private_mem_conversions_test.c | 53 ++-
.../kvm/x86/private_mem_conversions_test.sh | 128 ++++++
.../selftests/kvm/x86/private_mem_kvm_exits_test.c | 36 +-
virt/kvm/Kconfig | 3 +-
virt/kvm/guest_memfd.c | 457 +++++++++++++++++--
virt/kvm/kvm_main.c | 82 +++-
26 files changed, 1636 insertions(+), 188 deletions(-)
---
base-commit: 6d35786de28116ecf78797a62b84e6bf3c45aa5a
change-id: 20260225-gmem-inplace-conversion-bd0dbd39753a
Best regards,
--
Ackerley Tng <ackerleytng@google.com>
^ permalink raw reply
* [PATCH v6 01/43] KVM: guest_memfd: Introduce per-gmem attributes, use to guard user mappings
From: Ackerley Tng via B4 Relay @ 2026-05-07 20:22 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, liam, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Baoquan He, Barry Song,
Axel Rasmussen, Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng,
Shakeel Butt, Kiryl Shutsemau, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco, Ackerley Tng
In-Reply-To: <20260507-gmem-inplace-conversion-v6-0-91ab5a8b19a4@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 | 133 +++++++++++++++++++++++++++++++++++++++++++------
1 file changed, 117 insertions(+), 16 deletions(-)
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 69c9d6d546b28..5011d38820d0d 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>
@@ -33,6 +34,13 @@ struct gmem_inode {
struct list_head gmem_file_list;
u64 flags;
+ /*
+ * Every index in this inode, whether memory is populated or
+ * not, is tracked in attributes. The entire range of indices,
+ * corresponding to the size of this inode, is represented in
+ * this maple tree.
+ */
+ struct maple_tree attributes;
};
static __always_inline struct gmem_inode *GMEM_I(struct inode *inode)
@@ -60,6 +68,24 @@ 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);
+
+ 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 +423,13 @@ 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 +585,51 @@ 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 +660,9 @@ 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 +864,13 @@ 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 +886,8 @@ 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);
@@ -944,6 +1017,15 @@ 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 | MT_FLAGS_USE_RCU);
+
gi->flags = 0;
INIT_LIST_HEAD(&gi->gmem_file_list);
return &gi->vfs_inode;
@@ -951,7 +1033,26 @@ static struct inode *kvm_gmem_alloc_inode(struct super_block *sb)
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)
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related
* [PATCH v6 02/43] KVM: Rename KVM_GENERIC_MEMORY_ATTRIBUTES to KVM_VM_MEMORY_ATTRIBUTES
From: Ackerley Tng via B4 Relay @ 2026-05-07 20:22 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, liam, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Baoquan He, Barry Song,
Axel Rasmussen, Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng,
Shakeel Butt, Kiryl Shutsemau, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco, Ackerley Tng
In-Reply-To: <20260507-gmem-inplace-conversion-v6-0-91ab5a8b19a4@google.com>
From: Sean Christopherson <seanjc@google.com>
Rename the per-VM memory attributes Kconfig to make it explicitly about
per-VM attributes in anticipation of adding memory attributes support to
guest_memfd, at which point it will be possible (and desirable) to have
memory attributes without the per-VM support, even in x86.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
arch/x86/include/asm/kvm_host.h | 2 +-
arch/x86/kvm/Kconfig | 6 +++---
arch/x86/kvm/mmu/mmu.c | 2 +-
arch/x86/kvm/x86.c | 2 +-
include/linux/kvm_host.h | 8 ++++----
include/trace/events/kvm.h | 4 ++--
virt/kvm/Kconfig | 2 +-
virt/kvm/kvm_main.c | 14 +++++++-------
8 files changed, 20 insertions(+), 20 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c470e40a00aa4..60b997764beef 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -2369,7 +2369,7 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level,
int tdp_max_root_level, int tdp_huge_page_level);
-#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.has_private_mem)
#endif
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 801bf9e520db3..26f6afd51bbdc 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -84,7 +84,7 @@ config KVM_SW_PROTECTED_VM
bool "Enable support for KVM software-protected VMs"
depends on EXPERT
depends on KVM_X86 && X86_64
- select KVM_GENERIC_MEMORY_ATTRIBUTES
+ select KVM_VM_MEMORY_ATTRIBUTES
help
Enable support for KVM software-protected VMs. Currently, software-
protected VMs are purely a development and testing vehicle for
@@ -135,7 +135,7 @@ config KVM_INTEL_TDX
bool "Intel Trust Domain Extensions (TDX) support"
default y
depends on INTEL_TDX_HOST
- select KVM_GENERIC_MEMORY_ATTRIBUTES
+ select KVM_VM_MEMORY_ATTRIBUTES
select HAVE_KVM_ARCH_GMEM_POPULATE
help
Provides support for launching Intel Trust Domain Extensions (TDX)
@@ -159,7 +159,7 @@ config KVM_AMD_SEV
depends on KVM_AMD && X86_64
depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m)
select ARCH_HAS_CC_PLATFORM
- select KVM_GENERIC_MEMORY_ATTRIBUTES
+ select KVM_VM_MEMORY_ATTRIBUTES
select HAVE_KVM_ARCH_GMEM_PREPARE
select HAVE_KVM_ARCH_GMEM_INVALIDATE
select HAVE_KVM_ARCH_GMEM_POPULATE
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 892246204435c..a80a876ab4ad6 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -7899,7 +7899,7 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
vhost_task_stop(kvm->arch.nx_huge_page_recovery_thread);
}
-#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
int level)
{
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0a1b63c63d1a9..1560de1e95be0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -13625,7 +13625,7 @@ static int kvm_alloc_memslot_metadata(struct kvm *kvm,
}
}
-#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
kvm_mmu_init_memslot_memory_attributes(kvm, slot);
#endif
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 4c14aee1fb063..7b9faa3545300 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -722,7 +722,7 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
}
#endif
-#ifndef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+#ifndef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
{
return false;
@@ -871,7 +871,7 @@ struct kvm {
#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
struct notifier_block pm_notifier;
#endif
-#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
/* Protected by slots_lock (for writes) and RCU (for reads) */
struct xarray mem_attr_array;
#endif
@@ -2528,7 +2528,7 @@ static inline bool kvm_memslot_is_gmem_only(const struct kvm_memory_slot *slot)
return slot->flags & KVM_MEMSLOT_GMEM_ONLY;
}
-#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn)
{
return xa_to_value(xa_load(&kvm->mem_attr_array, gfn));
@@ -2550,7 +2550,7 @@ static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
{
return false;
}
-#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
+#endif /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */
#ifdef CONFIG_KVM_GUEST_MEMFD
int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index b282e3a867696..1ba72bd73ea2f 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -358,7 +358,7 @@ TRACE_EVENT(kvm_dirty_ring_exit,
TP_printk("vcpu %d", __entry->vcpu_id)
);
-#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
/*
* @start: Starting address of guest memory range
* @end: End address of guest memory range
@@ -383,7 +383,7 @@ TRACE_EVENT(kvm_vm_set_mem_attributes,
TP_printk("%#016llx -- %#016llx [0x%lx]",
__entry->start, __entry->end, __entry->attr)
);
-#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
+#endif /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */
TRACE_EVENT(kvm_unmap_hva_range,
TP_PROTO(unsigned long start, unsigned long end),
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 794976b88c6f9..5119cb37145fc 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -100,7 +100,7 @@ config KVM_ELIDE_TLB_FLUSH_IF_YOUNG
config KVM_MMU_LOCKLESS_AGING
bool
-config KVM_GENERIC_MEMORY_ATTRIBUTES
+config KVM_VM_MEMORY_ATTRIBUTES
bool
config KVM_GUEST_MEMFD
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 89489996fbc1e..306153abbafa5 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1115,7 +1115,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
spin_lock_init(&kvm->mn_invalidate_lock);
rcuwait_init(&kvm->mn_memslots_update_rcuwait);
xa_init(&kvm->vcpu_array);
-#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
xa_init(&kvm->mem_attr_array);
#endif
@@ -1300,7 +1300,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
cleanup_srcu_struct(&kvm->irq_srcu);
srcu_barrier(&kvm->srcu);
cleanup_srcu_struct(&kvm->srcu);
-#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
xa_destroy(&kvm->mem_attr_array);
#endif
kvm_arch_free_vm(kvm);
@@ -2418,7 +2418,7 @@ static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm,
}
#endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */
-#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
static u64 kvm_supported_mem_attributes(struct kvm *kvm)
{
if (!kvm || kvm_arch_has_private_mem(kvm))
@@ -2623,7 +2623,7 @@ static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm,
return kvm_vm_set_mem_attributes(kvm, start, end, attrs->attributes);
}
-#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
+#endif /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */
struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
{
@@ -4921,7 +4921,7 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
case KVM_CAP_SYSTEM_EVENT_DATA:
case KVM_CAP_DEVICE_CTRL:
return 1;
-#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
case KVM_CAP_MEMORY_ATTRIBUTES:
return kvm_supported_mem_attributes(kvm);
#endif
@@ -5325,7 +5325,7 @@ static long kvm_vm_ioctl(struct file *filp,
break;
}
#endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */
-#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
case KVM_SET_MEMORY_ATTRIBUTES: {
struct kvm_memory_attributes attrs;
@@ -5336,7 +5336,7 @@ static long kvm_vm_ioctl(struct file *filp,
r = kvm_vm_ioctl_set_mem_attributes(kvm, &attrs);
break;
}
-#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
+#endif /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */
case KVM_CREATE_DEVICE: {
struct kvm_create_device cd;
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related
* [PATCH v6 04/43] KVM: Stub in ability to disable per-VM memory attribute tracking
From: Ackerley Tng via B4 Relay @ 2026-05-07 20:22 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, liam, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Baoquan He, Barry Song,
Axel Rasmussen, Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng,
Shakeel Butt, Kiryl Shutsemau, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco, Ackerley Tng
In-Reply-To: <20260507-gmem-inplace-conversion-v6-0-91ab5a8b19a4@google.com>
From: Sean Christopherson <seanjc@google.com>
Introduce the basic infrastructure to allow per-VM memory attribute
tracking to be disabled. This will be built-upon in a later patch, where a
module param can disable per-VM memory attribute tracking.
Split the Kconfig option into a base KVM_MEMORY_ATTRIBUTES and the
existing KVM_VM_MEMORY_ATTRIBUTES. The base option provides the core
plumbing, while the latter enables the full per-VM tracking via an xarray
and the associated ioctls.
kvm_get_memory_attributes() now performs a static call that either looks up
kvm->mem_attr_array with CONFIG_KVM_VM_MEMORY_ATTRIBUTES is enabled, or
just returns 0 otherwise. The static call can be patched depending on
whether per-VM tracking is enabled by the CONFIG.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
arch/x86/include/asm/kvm_host.h | 2 +-
include/linux/kvm_host.h | 23 ++++++++++++---------
virt/kvm/Kconfig | 4 ++++
virt/kvm/kvm_main.c | 44 ++++++++++++++++++++++++++++++++++++++++-
4 files changed, 62 insertions(+), 11 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 60b997764beef..c9aa50bcdac2d 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -2369,7 +2369,7 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level,
int tdp_max_root_level, int tdp_huge_page_level);
-#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
+#ifdef CONFIG_KVM_MEMORY_ATTRIBUTES
#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.has_private_mem)
#endif
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 7d079f9701346..c5ba2cb34e45c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2528,19 +2528,15 @@ static inline bool kvm_memslot_is_gmem_only(const struct kvm_memory_slot *slot)
return slot->flags & KVM_MEMSLOT_GMEM_ONLY;
}
-#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
+#ifdef CONFIG_KVM_MEMORY_ATTRIBUTES
+typedef unsigned long (kvm_get_memory_attributes_t)(struct kvm *kvm, gfn_t gfn);
+DECLARE_STATIC_CALL(__kvm_get_memory_attributes, kvm_get_memory_attributes_t);
+
static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn)
{
- return xa_to_value(xa_load(&kvm->mem_attr_array, gfn));
+ return static_call(__kvm_get_memory_attributes)(kvm, gfn);
}
-bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
- unsigned long mask, unsigned long attrs);
-bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
- struct kvm_gfn_range *range);
-bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
- struct kvm_gfn_range *range);
-
static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
{
return kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE;
@@ -2550,6 +2546,15 @@ static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
{
return false;
}
+#endif
+
+#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
+bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+ unsigned long mask, unsigned long attrs);
+bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
+ struct kvm_gfn_range *range);
+bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
+ struct kvm_gfn_range *range);
#endif /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */
#ifdef CONFIG_KVM_GUEST_MEMFD
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 5119cb37145fc..3fea89c45cfb4 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -100,7 +100,11 @@ config KVM_ELIDE_TLB_FLUSH_IF_YOUNG
config KVM_MMU_LOCKLESS_AGING
bool
+config KVM_MEMORY_ATTRIBUTES
+ bool
+
config KVM_VM_MEMORY_ATTRIBUTES
+ select KVM_MEMORY_ATTRIBUTES
bool
config KVM_GUEST_MEMFD
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index abb9cfa3eb04d..ee26f1d9b5fda 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -101,6 +101,17 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(halt_poll_ns_shrink);
static bool __ro_after_init allow_unsafe_mappings;
module_param(allow_unsafe_mappings, bool, 0444);
+#ifdef CONFIG_KVM_MEMORY_ATTRIBUTES
+#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
+static bool vm_memory_attributes = true;
+#else
+#define vm_memory_attributes false
+#endif
+DEFINE_STATIC_CALL_RET0(__kvm_get_memory_attributes, kvm_get_memory_attributes_t);
+EXPORT_SYMBOL_FOR_KVM_INTERNAL(STATIC_CALL_KEY(__kvm_get_memory_attributes));
+EXPORT_SYMBOL_FOR_KVM_INTERNAL(STATIC_CALL_TRAMP(__kvm_get_memory_attributes));
+#endif
+
/*
* Ordering of locks:
*
@@ -2418,7 +2429,7 @@ static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm,
}
#endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */
-#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
+#ifdef CONFIG_KVM_MEMORY_ATTRIBUTES
static u64 kvm_supported_mem_attributes(struct kvm *kvm)
{
#ifdef kvm_arch_has_private_mem
@@ -2429,6 +2440,12 @@ static u64 kvm_supported_mem_attributes(struct kvm *kvm)
return 0;
}
+#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
+static unsigned long kvm_get_vm_memory_attributes(struct kvm *kvm, gfn_t gfn)
+{
+ return xa_to_value(xa_load(&kvm->mem_attr_array, gfn));
+}
+
/*
* Returns true if _all_ gfns in the range [@start, @end) have attributes
* such that the bits in @mask match @attrs.
@@ -2625,7 +2642,24 @@ static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm,
return kvm_vm_set_mem_attributes(kvm, start, end, attrs->attributes);
}
+#else /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */
+static unsigned long kvm_get_vm_memory_attributes(struct kvm *kvm, gfn_t gfn)
+{
+ BUILD_BUG_ON(1);
+}
#endif /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */
+static void kvm_init_memory_attributes(void)
+{
+ if (vm_memory_attributes)
+ static_call_update(__kvm_get_memory_attributes,
+ kvm_get_vm_memory_attributes);
+ else
+ static_call_update(__kvm_get_memory_attributes,
+ (void *)__static_call_return0);
+}
+#else /* CONFIG_KVM_MEMORY_ATTRIBUTES */
+static void kvm_init_memory_attributes(void) { }
+#endif /* CONFIG_KVM_MEMORY_ATTRIBUTES */
struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
{
@@ -4925,6 +4959,9 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
return 1;
#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
case KVM_CAP_MEMORY_ATTRIBUTES:
+ if (!vm_memory_attributes)
+ return 0;
+
return kvm_supported_mem_attributes(kvm);
#endif
#ifdef CONFIG_KVM_GUEST_MEMFD
@@ -5331,6 +5368,10 @@ static long kvm_vm_ioctl(struct file *filp,
case KVM_SET_MEMORY_ATTRIBUTES: {
struct kvm_memory_attributes attrs;
+ r = -ENOTTY;
+ if (!vm_memory_attributes)
+ goto out;
+
r = -EFAULT;
if (copy_from_user(&attrs, argp, sizeof(attrs)))
goto out;
@@ -6527,6 +6568,7 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
kvm_preempt_ops.sched_in = kvm_sched_in;
kvm_preempt_ops.sched_out = kvm_sched_out;
+ kvm_init_memory_attributes();
kvm_init_debug();
r = kvm_vfio_ops_init();
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related
* [PATCH v6 03/43] KVM: Enumerate support for PRIVATE memory iff kvm_arch_has_private_mem is defined
From: Ackerley Tng via B4 Relay @ 2026-05-07 20:22 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, liam, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Baoquan He, Barry Song,
Axel Rasmussen, Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng,
Shakeel Butt, Kiryl Shutsemau, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco, Ackerley Tng
In-Reply-To: <20260507-gmem-inplace-conversion-v6-0-91ab5a8b19a4@google.com>
From: Sean Christopherson <seanjc@google.com>
Explicitly guard reporting support for KVM_MEMORY_ATTRIBUTE_PRIVATE based
on kvm_arch_has_private_mem being #defined in anticipation of decoupling
kvm_supported_mem_attributes() from CONFIG_KVM_VM_MEMORY_ATTRIBUTES.
guest_memfd support for memory attributes will be unconditional to avoid
yet more macros (all architectures that support guest_memfd are expected to
use per-gmem attributes at some point), at which point enumerating support
KVM_MEMORY_ATTRIBUTE_PRIVATE based solely on memory attributes being
supported _somewhere_ would result in KVM over-reporting support on arm64.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
include/linux/kvm_host.h | 2 +-
virt/kvm/kvm_main.c | 2 ++
2 files changed, 3 insertions(+), 1 deletion(-)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 7b9faa3545300..7d079f9701346 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -722,7 +722,7 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
}
#endif
-#ifndef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
+#ifndef kvm_arch_has_private_mem
static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
{
return false;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 306153abbafa5..abb9cfa3eb04d 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2421,8 +2421,10 @@ static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm,
#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
static u64 kvm_supported_mem_attributes(struct kvm *kvm)
{
+#ifdef kvm_arch_has_private_mem
if (!kvm || kvm_arch_has_private_mem(kvm))
return KVM_MEMORY_ATTRIBUTE_PRIVATE;
+#endif
return 0;
}
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related
* [PATCH v6 05/43] KVM: guest_memfd: Wire up kvm_get_memory_attributes() to per-gmem attributes
From: Ackerley Tng via B4 Relay @ 2026-05-07 20:22 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, liam, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Baoquan He, Barry Song,
Axel Rasmussen, Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng,
Shakeel Butt, Kiryl Shutsemau, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco, Ackerley Tng
In-Reply-To: <20260507-gmem-inplace-conversion-v6-0-91ab5a8b19a4@google.com>
From: Sean Christopherson <seanjc@google.com>
Implement kvm_gmem_get_memory_attributes() for guest_memfd to allow the KVM
core and architecture code to query per-GFN memory attributes.
kvm_gmem_get_memory_attributes() finds the memory slot for a given GFN and
queries the guest_memfd file's to determine if the page is marked as
private.
If vm_memory_attributes is not enabled, there is no shared/private tracking
at the VM level. Install the guest_memfd implementation as long as
guest_memfd is enabled to give guest_memfd a chance to respond on
attributes.
guest_memfd should look up attributes regardless of whether this memslot is
gmem-only since attributes are now tracked by gmem regardless of whether
mmap() is enabled.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Co-developed-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
include/linux/kvm_host.h | 2 ++
virt/kvm/guest_memfd.c | 31 +++++++++++++++++++++++++++++++
virt/kvm/kvm_main.c | 3 +++
3 files changed, 36 insertions(+)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c5ba2cb34e45c..28a54298d27db 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2557,6 +2557,8 @@ bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
struct kvm_gfn_range *range);
#endif /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */
+unsigned long kvm_gmem_get_memory_attributes(struct kvm *kvm, gfn_t gfn);
+
#ifdef CONFIG_KVM_GUEST_MEMFD
int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
gfn_t gfn, kvm_pfn_t *pfn, struct page **page,
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 5011d38820d0d..f055e058a3f28 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -509,6 +509,37 @@ static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma)
return 0;
}
+unsigned long kvm_gmem_get_memory_attributes(struct kvm *kvm, gfn_t gfn)
+{
+ struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
+ struct inode *inode;
+
+ /*
+ * If this gfn has no associated memslot, there's no chance of the gfn
+ * being backed by private memory, since guest_memfd must be used for
+ * private memory, and guest_memfd must be associated with some memslot.
+ */
+ if (!slot)
+ return 0;
+
+ CLASS(gmem_get_file, file)(slot);
+ if (!file)
+ return 0;
+
+ inode = file_inode(file);
+
+ /*
+ * Rely on the maple tree's internal RCU lock to ensure a
+ * stable result. This result can become stale as soon as the
+ * lock is dropped, so the caller _must_ still protect
+ * consumption of private vs. shared by checking
+ * mmu_invalidate_retry_gfn() under mmu_lock to serialize
+ * against ongoing attribute updates.
+ */
+ return kvm_gmem_get_attributes(inode, kvm_gmem_get_index(slot, gfn));
+}
+EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_memory_attributes);
+
static struct file_operations kvm_gmem_fops = {
.mmap = kvm_gmem_mmap,
.open = generic_file_open,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index ee26f1d9b5fda..4139e903f756a 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2653,6 +2653,9 @@ static void kvm_init_memory_attributes(void)
if (vm_memory_attributes)
static_call_update(__kvm_get_memory_attributes,
kvm_get_vm_memory_attributes);
+ else if (IS_ENABLED(CONFIG_KVM_GUEST_MEMFD))
+ static_call_update(__kvm_get_memory_attributes,
+ kvm_gmem_get_memory_attributes);
else
static_call_update(__kvm_get_memory_attributes,
(void *)__static_call_return0);
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related
* [PATCH v6 06/43] KVM: x86/mmu: Bug the VM if gmem attributes are queried to determine max mapping level
From: Ackerley Tng via B4 Relay @ 2026-05-07 20:22 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, liam, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Baoquan He, Barry Song,
Axel Rasmussen, Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng,
Shakeel Butt, Kiryl Shutsemau, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco, Ackerley Tng
In-Reply-To: <20260507-gmem-inplace-conversion-v6-0-91ab5a8b19a4@google.com>
From: Ackerley Tng <ackerleytng@google.com>
When the maximum mapping level is queried, KVM's MMU lock is held, and
while the MMU lock is held, guest_memfd cannot take the
filemap_invalidate_lock() to look up the current shared/private state of
the gfn, for these reasons:
+ The MMU lock is a spinlock or rwlock and cannot be held while taking a
lock that can sleep.
+ In guest_memfd's code paths (such as truncate), the
filemap_invalidate_lock() is held while taking the MMU lock, and taking
the locks in reverse order would introduce a AB-BA deadlock.
Currently, the maximum mapping level is only queried from guest_memfd in
the process of recovering huge pages, if dirty logging is disabled on a
memslot. Dirty logging is not currently supported for guest_memfd, and
guest_memfd memslots also cannot be updated.
For now, bug the VM if guest_memfd needs to be queried to determine the
maximum mapping level. This guard can be removed if/when support is added.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
arch/x86/kvm/mmu/mmu.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index a80a876ab4ad6..153bcc5369985 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3357,6 +3357,15 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, struct kvm_page_fault *fault,
max_level = fault->max_level;
is_private = fault->is_private;
} else {
+ /*
+ * Memory attributes cannot be obtained from guest_memfd while
+ * the MMU lock is held.
+ */
+ if (KVM_BUG_ON(static_call_query(__kvm_get_memory_attributes) ==
+ kvm_gmem_get_memory_attributes, kvm)) {
+ return 0;
+ }
+
max_level = PG_LEVEL_NUM;
is_private = kvm_mem_is_private(kvm, gfn);
}
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related
* [PATCH v6 07/43] KVM: guest_memfd: Update kvm_gmem_populate() to use gmem attributes
From: Ackerley Tng via B4 Relay @ 2026-05-07 20:22 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, liam, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Baoquan He, Barry Song,
Axel Rasmussen, Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng,
Shakeel Butt, Kiryl Shutsemau, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco, Ackerley Tng
In-Reply-To: <20260507-gmem-inplace-conversion-v6-0-91ab5a8b19a4@google.com>
From: Ackerley Tng <ackerleytng@google.com>
Update the guest_memfd populate() flow to pull memory attributes from the
gmem instance instead of the VM when KVM is not configured to track
shared/private status in the VM.
Rename the per-VM API to make it clear that it retrieves per-VM
attributes, i.e. is not suitable for use outside of flows that are
specific to generic per-VM attributes.
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
arch/x86/kvm/mmu/mmu.c | 2 +-
include/linux/kvm_host.h | 14 +++++++++++++-
virt/kvm/guest_memfd.c | 24 +++++++++++++++++++++---
virt/kvm/kvm_main.c | 8 +++-----
4 files changed, 38 insertions(+), 10 deletions(-)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 153bcc5369985..bfcf9be25598e 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -7997,7 +7997,7 @@ static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot,
const unsigned long end = start + KVM_PAGES_PER_HPAGE(level);
if (level == PG_LEVEL_2M)
- return kvm_range_has_memory_attributes(kvm, start, end, ~0, attrs);
+ return kvm_range_has_vm_memory_attributes(kvm, start, end, ~0, attrs);
for (gfn = start; gfn < end; gfn += KVM_PAGES_PER_HPAGE(level - 1)) {
if (hugepage_test_mixed(slot, gfn, level - 1) ||
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 28a54298d27db..1deab76dc0a2c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2549,12 +2549,24 @@ static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
#endif
#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
-bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+extern bool vm_memory_attributes;
+bool kvm_range_has_vm_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
unsigned long mask, unsigned long attrs);
bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
struct kvm_gfn_range *range);
bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
struct kvm_gfn_range *range);
+#else
+#define vm_memory_attributes false
+static inline bool kvm_range_has_vm_memory_attributes(struct kvm *kvm,
+ gfn_t start, gfn_t end,
+ unsigned long mask,
+ unsigned long attrs)
+{
+ WARN_ONCE(1, "Unexpected call to kvm_range_has_vm_memory_attributes()");
+
+ return false;
+}
#endif /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */
unsigned long kvm_gmem_get_memory_attributes(struct kvm *kvm, gfn_t gfn);
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index f055e058a3f28..9d025f518c025 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -924,12 +924,31 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_pfn);
#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_POPULATE
+static bool kvm_gmem_range_is_private(struct gmem_inode *gi, pgoff_t index,
+ size_t nr_pages, struct kvm *kvm, gfn_t gfn)
+{
+ pgoff_t end = index + nr_pages - 1;
+ void *entry;
+
+ if (vm_memory_attributes)
+ return kvm_range_has_vm_memory_attributes(kvm, gfn, gfn + nr_pages,
+ KVM_MEMORY_ATTRIBUTE_PRIVATE,
+ KVM_MEMORY_ATTRIBUTE_PRIVATE);
+
+ mt_for_each(&gi->attributes, entry, index, end) {
+ if (xa_to_value(entry) != KVM_MEMORY_ATTRIBUTE_PRIVATE)
+ return false;
+ }
+
+ return true;
+}
static long __kvm_gmem_populate(struct kvm *kvm, struct kvm_memory_slot *slot,
struct file *file, gfn_t gfn, struct page *src_page,
kvm_gmem_populate_cb post_populate, void *opaque)
{
pgoff_t index = kvm_gmem_get_index(slot, gfn);
+ struct gmem_inode *gi;
struct folio *folio;
kvm_pfn_t pfn;
int ret;
@@ -944,9 +963,8 @@ static long __kvm_gmem_populate(struct kvm *kvm, struct kvm_memory_slot *slot,
folio_unlock(folio);
- if (!kvm_range_has_memory_attributes(kvm, gfn, gfn + 1,
- KVM_MEMORY_ATTRIBUTE_PRIVATE,
- KVM_MEMORY_ATTRIBUTE_PRIVATE)) {
+ gi = GMEM_I(file_inode(file));
+ if (!kvm_gmem_range_is_private(gi, index, 1, kvm, gfn)) {
ret = -EINVAL;
goto out_put_folio;
}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 4139e903f756a..0a4024948711a 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -103,9 +103,7 @@ module_param(allow_unsafe_mappings, bool, 0444);
#ifdef CONFIG_KVM_MEMORY_ATTRIBUTES
#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
-static bool vm_memory_attributes = true;
-#else
-#define vm_memory_attributes false
+bool vm_memory_attributes = true;
#endif
DEFINE_STATIC_CALL_RET0(__kvm_get_memory_attributes, kvm_get_memory_attributes_t);
EXPORT_SYMBOL_FOR_KVM_INTERNAL(STATIC_CALL_KEY(__kvm_get_memory_attributes));
@@ -2450,7 +2448,7 @@ static unsigned long kvm_get_vm_memory_attributes(struct kvm *kvm, gfn_t gfn)
* Returns true if _all_ gfns in the range [@start, @end) have attributes
* such that the bits in @mask match @attrs.
*/
-bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+bool kvm_range_has_vm_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
unsigned long mask, unsigned long attrs)
{
XA_STATE(xas, &kvm->mem_attr_array, start);
@@ -2584,7 +2582,7 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
mutex_lock(&kvm->slots_lock);
/* Nothing to do if the entire range has the desired attributes. */
- if (kvm_range_has_memory_attributes(kvm, start, end, ~0, attributes))
+ if (kvm_range_has_vm_memory_attributes(kvm, start, end, ~0, attributes))
goto out_unlock;
/*
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related
* [PATCH v6 08/43] KVM: guest_memfd: Only prepare folios for private pages
From: Ackerley Tng via B4 Relay @ 2026-05-07 20:22 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, liam, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Baoquan He, Barry Song,
Axel Rasmussen, Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng,
Shakeel Butt, Kiryl Shutsemau, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco, Ackerley Tng
In-Reply-To: <20260507-gmem-inplace-conversion-v6-0-91ab5a8b19a4@google.com>
From: Ackerley Tng <ackerleytng@google.com>
All-shared guest_memfd used to be only supported for non-CoCo VMs where
preparation doesn't apply. INIT_SHARED is about to be supported for
non-CoCo VMs in a later patch in this series.
In addition, KVM_SET_MEMORY_ATTRIBUTES2 is about to be supported in
guest_memfd in a later patch in this series.
This means that the kvm fault handler may now call kvm_gmem_get_pfn() on a
shared folio for a CoCo VM where preparation applies.
Add a check to make sure that preparation is only performed for private
folios.
Preparation will be undone on freeing (see kvm_gmem_free_folio()) and on
conversion to shared.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
virt/kvm/guest_memfd.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 9d025f518c025..4f7c4824c3a45 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -888,6 +888,7 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
int *max_order)
{
pgoff_t index = kvm_gmem_get_index(slot, gfn);
+ struct inode *inode;
struct folio *folio;
int r = 0;
@@ -895,7 +896,8 @@ 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);
+ inode = file_inode(file);
+ filemap_invalidate_lock_shared(inode->i_mapping);
folio = __kvm_gmem_get_pfn(file, slot, index, pfn, max_order);
if (IS_ERR(folio)) {
@@ -908,7 +910,8 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
folio_mark_uptodate(folio);
}
- r = kvm_gmem_prepare_folio(kvm, slot, gfn, folio);
+ if (kvm_gmem_is_private_mem(inode, index))
+ r = kvm_gmem_prepare_folio(kvm, slot, gfn, folio);
folio_unlock(folio);
@@ -918,7 +921,7 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
folio_put(folio);
out:
- filemap_invalidate_unlock_shared(file_inode(file)->i_mapping);
+ filemap_invalidate_unlock_shared(inode->i_mapping);
return r;
}
EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_pfn);
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related
* [PATCH v6 09/43] KVM: Move kvm_supported_mem_attributes() to kvm_host.h
From: Ackerley Tng via B4 Relay @ 2026-05-07 20:22 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, liam, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Baoquan He, Barry Song,
Axel Rasmussen, Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng,
Shakeel Butt, Kiryl Shutsemau, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco, Ackerley Tng
In-Reply-To: <20260507-gmem-inplace-conversion-v6-0-91ab5a8b19a4@google.com>
From: Ackerley Tng <ackerleytng@google.com>
Move kvm_supported_mem_attributes() from kvm_main.c to kvm_host.h and
make it a static inline function. This allows the helper to be used in
other parts of the KVM subsystem outside of kvm_main.c. This helper will be
used later by guest_memfd.
No functional change intended.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
include/linux/kvm_host.h | 10 ++++++++++
virt/kvm/kvm_main.c | 10 ----------
2 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 1deab76dc0a2c..f9ea95e33d050 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2529,6 +2529,16 @@ static inline bool kvm_memslot_is_gmem_only(const struct kvm_memory_slot *slot)
}
#ifdef CONFIG_KVM_MEMORY_ATTRIBUTES
+static inline u64 kvm_supported_mem_attributes(struct kvm *kvm)
+{
+#ifdef kvm_arch_has_private_mem
+ if (!kvm || kvm_arch_has_private_mem(kvm))
+ return KVM_MEMORY_ATTRIBUTE_PRIVATE;
+#endif
+
+ return 0;
+}
+
typedef unsigned long (kvm_get_memory_attributes_t)(struct kvm *kvm, gfn_t gfn);
DECLARE_STATIC_CALL(__kvm_get_memory_attributes, kvm_get_memory_attributes_t);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 0a4024948711a..ff20e63143642 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2428,16 +2428,6 @@ static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm,
#endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */
#ifdef CONFIG_KVM_MEMORY_ATTRIBUTES
-static u64 kvm_supported_mem_attributes(struct kvm *kvm)
-{
-#ifdef kvm_arch_has_private_mem
- if (!kvm || kvm_arch_has_private_mem(kvm))
- return KVM_MEMORY_ATTRIBUTE_PRIVATE;
-#endif
-
- return 0;
-}
-
#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
static unsigned long kvm_get_vm_memory_attributes(struct kvm *kvm, gfn_t gfn)
{
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related
* [PATCH v6 10/43] KVM: guest_memfd: Add base support for KVM_SET_MEMORY_ATTRIBUTES2
From: Ackerley Tng via B4 Relay @ 2026-05-07 20:22 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, liam, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Baoquan He, Barry Song,
Axel Rasmussen, Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng,
Shakeel Butt, Kiryl Shutsemau, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco, Ackerley Tng
In-Reply-To: <20260507-gmem-inplace-conversion-v6-0-91ab5a8b19a4@google.com>
From: Ackerley Tng <ackerleytng@google.com>
Introduce base support for KVM_SET_MEMORY_ATTRIBUTES2 in guest_memfd, which
just updates attributes tracked by guest_memfd.
Validate input fields in general. Guard usage of KVM_SET_MEMORY_ATTRIBUTES2
by making sure requested attributes are supported for this instance of kvm.
A new KVM_SET_MEMORY_ATTRIBUTES2 is defined to support writes (unlike
KVM_SET_MEMORY_ATTRIBUTES) in addition to reads so it can provide error
details to userspace. This will be used in a later patch.
The two ioctls use their corresponding structs with no overlap, but
backward compatibility is baked in for future support of
KVM_SET_MEMORY_ATTRIBUTES2 and struct kvm_memory_attributes2 in the VM
ioctl.
The process of setting memory attributes is set up such that the later half
will not fail due to allocation. Any necessary checks are performed before
the point of no return.
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: Sean Christoperson <seanjc@google.com>
Signed-off-by: Sean Christoperson <seanjc@google.com>
---
include/uapi/linux/kvm.h | 13 ++++++
virt/kvm/Kconfig | 1 +
virt/kvm/guest_memfd.c | 114 +++++++++++++++++++++++++++++++++++++++++++++++
virt/kvm/kvm_main.c | 12 +++++
4 files changed, 140 insertions(+)
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 6c8afa2047bf3..e6bbf68a83813 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1648,6 +1648,19 @@ struct kvm_memory_attributes {
__u64 flags;
};
+#define KVM_SET_MEMORY_ATTRIBUTES2 _IOWR(KVMIO, 0xd2, struct kvm_memory_attributes2)
+
+struct kvm_memory_attributes2 {
+ union {
+ __u64 address;
+ __u64 offset;
+ };
+ __u64 size;
+ __u64 attributes;
+ __u64 flags;
+ __u64 reserved[12];
+};
+
#define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3)
#define KVM_CREATE_GUEST_MEMFD _IOWR(KVMIO, 0xd4, struct kvm_create_guest_memfd)
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 3fea89c45cfb4..e371e079e2c50 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -109,6 +109,7 @@ config KVM_VM_MEMORY_ATTRIBUTES
config KVM_GUEST_MEMFD
select XARRAY_MULTI
+ select KVM_MEMORY_ATTRIBUTES
bool
config HAVE_KVM_ARCH_GMEM_PREPARE
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 4f7c4824c3a45..91e89b188f583 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -540,11 +540,125 @@ unsigned long kvm_gmem_get_memory_attributes(struct kvm *kvm, gfn_t gfn)
}
EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_memory_attributes);
+/*
+ * Preallocate memory for attributes to be stored on a maple tree, pointed to
+ * by mas. Adjacent ranges with attributes identical to the new attributes
+ * will be merged. Also sets mas's bounds up for storing attributes.
+ *
+ * This maintains the invariant that ranges with the same attributes will
+ * always be merged.
+ */
+static int kvm_gmem_mas_preallocate(struct ma_state *mas, u64 attributes,
+ pgoff_t start, size_t nr_pages)
+{
+ pgoff_t end = start + nr_pages;
+ pgoff_t last = end - 1;
+ void *entry;
+
+ /* Try extending range. entry is NULL on overflow/wrap-around. */
+ mas_set(mas, end);
+ entry = mas_find(mas, end);
+ if (entry && xa_to_value(entry) == attributes)
+ last = mas->last;
+
+ if (start > 0) {
+ mas_set(mas, start - 1);
+ entry = mas_find(mas, start - 1);
+ if (entry && xa_to_value(entry) == attributes)
+ start = mas->index;
+ }
+
+ mas_set_range(mas, start, last);
+ return mas_preallocate(mas, xa_mk_value(attributes), GFP_KERNEL);
+}
+
+static int __kvm_gmem_set_attributes(struct inode *inode, pgoff_t start,
+ size_t nr_pages, uint64_t attrs)
+{
+ struct address_space *mapping = inode->i_mapping;
+ struct gmem_inode *gi = GMEM_I(inode);
+ pgoff_t end = start + nr_pages;
+ struct maple_tree *mt;
+ struct ma_state mas;
+ int r;
+
+ mt = &gi->attributes;
+
+ filemap_invalidate_lock(mapping);
+
+ mas_init(&mas, mt, start);
+ r = kvm_gmem_mas_preallocate(&mas, attrs, start, nr_pages);
+ if (r)
+ goto out;
+
+ /*
+ * From this point on guest_memfd has performed necessary
+ * checks and can proceed to do guest-breaking changes.
+ */
+
+ kvm_gmem_invalidate_begin(inode, start, end);
+ mas_store_prealloc(&mas, xa_mk_value(attrs));
+ kvm_gmem_invalidate_end(inode, start, end);
+out:
+ filemap_invalidate_unlock(mapping);
+ return r;
+}
+
+static long kvm_gmem_set_attributes(struct file *file, void __user *argp)
+{
+ struct gmem_file *f = file->private_data;
+ struct inode *inode = file_inode(file);
+ struct kvm_memory_attributes2 attrs;
+ size_t nr_pages;
+ pgoff_t index;
+ int i;
+
+ if (copy_from_user(&attrs, argp, sizeof(attrs)))
+ return -EFAULT;
+
+ if (attrs.flags)
+ return -EINVAL;
+ for (i = 0; i < ARRAY_SIZE(attrs.reserved); i++) {
+ if (attrs.reserved[i])
+ return -EINVAL;
+ }
+ if (attrs.attributes & ~kvm_supported_mem_attributes(f->kvm))
+ return -EINVAL;
+ if (attrs.size == 0 || attrs.offset + attrs.size < attrs.offset)
+ return -EINVAL;
+ if (!PAGE_ALIGNED(attrs.offset) || !PAGE_ALIGNED(attrs.size))
+ return -EINVAL;
+
+ if (attrs.offset >= i_size_read(inode) ||
+ attrs.offset + attrs.size > i_size_read(inode))
+ return -EINVAL;
+
+ nr_pages = attrs.size >> PAGE_SHIFT;
+ index = attrs.offset >> PAGE_SHIFT;
+ return __kvm_gmem_set_attributes(inode, index, nr_pages,
+ attrs.attributes);
+}
+
+static long kvm_gmem_ioctl(struct file *file, unsigned int ioctl,
+ unsigned long arg)
+{
+ switch (ioctl) {
+ case KVM_SET_MEMORY_ATTRIBUTES2:
+ if (vm_memory_attributes)
+ return -ENOTTY;
+
+ return kvm_gmem_set_attributes(file, (void __user *)arg);
+ default:
+ return -ENOTTY;
+ }
+}
+
static struct file_operations kvm_gmem_fops = {
.mmap = kvm_gmem_mmap,
.open = generic_file_open,
.release = kvm_gmem_release,
.fallocate = kvm_gmem_fallocate,
+ .unlocked_ioctl = kvm_gmem_ioctl,
};
static int kvm_gmem_migrate_folio(struct address_space *mapping,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index ff20e63143642..4d7bf52b7b717 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -110,6 +110,18 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(STATIC_CALL_KEY(__kvm_get_memory_attributes));
EXPORT_SYMBOL_FOR_KVM_INTERNAL(STATIC_CALL_TRAMP(__kvm_get_memory_attributes));
#endif
+#define MEMORY_ATTRIBUTES_MATCH(one, two) \
+ static_assert(offsetof(struct kvm_memory_attributes, one) == \
+ offsetof(struct kvm_memory_attributes2, two)); \
+ static_assert(sizeof_field(struct kvm_memory_attributes, one) ==\
+ sizeof_field(struct kvm_memory_attributes2, two))
+
+/* Ensure the common parts of the two structs are identical. */
+MEMORY_ATTRIBUTES_MATCH(address, address);
+MEMORY_ATTRIBUTES_MATCH(size, size);
+MEMORY_ATTRIBUTES_MATCH(attributes, attributes);
+MEMORY_ATTRIBUTES_MATCH(flags, flags);
+
/*
* Ordering of locks:
*
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related
* [PATCH v6 11/43] KVM: guest_memfd: Ensure pages are not in use before conversion
From: Ackerley Tng via B4 Relay @ 2026-05-07 20:22 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, liam, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Baoquan He, Barry Song,
Axel Rasmussen, Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng,
Shakeel Butt, Kiryl Shutsemau, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco, Ackerley Tng
In-Reply-To: <20260507-gmem-inplace-conversion-v6-0-91ab5a8b19a4@google.com>
From: Ackerley Tng <ackerleytng@google.com>
When converting memory to private in guest_memfd, it is necessary to ensure
that the pages are not currently being accessed by any other part of the
kernel or userspace to avoid any current user writing to guest private
memory.
guest_memfd checks for unexpected refcounts to determine whether a page is
still in use. The only expected refcounts after unmapping the range
requested for conversion are those that are held by guest_memfd itself.
Update the kvm_memory_attributes2 structure to include an error_offset
field. This allows KVM to report the exact offset where a conversion
failed to userspace. If the safety check fails, return -EAGAIN and copy
the error_offset back to userspace so that it can potentially retry the
operation or handle the failure gracefully.
Suggested-by: David Hildenbrand <david@kernel.org>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Vishal Annapurve <vannapurve@google.com>
Signed-off-by: Vishal Annapurve <vannapurve@google.com>
---
include/uapi/linux/kvm.h | 3 ++-
virt/kvm/guest_memfd.c | 65 ++++++++++++++++++++++++++++++++++++++++++++----
2 files changed, 62 insertions(+), 6 deletions(-)
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index e6bbf68a83813..0b55258573d3d 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1658,7 +1658,8 @@ struct kvm_memory_attributes2 {
__u64 size;
__u64 attributes;
__u64 flags;
- __u64 reserved[12];
+ __u64 error_offset;
+ __u64 reserved[11];
};
#define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3)
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 91e89b188f583..9d82642a025e9 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -572,9 +572,42 @@ static int kvm_gmem_mas_preallocate(struct ma_state *mas, u64 attributes,
return mas_preallocate(mas, xa_mk_value(attributes), GFP_KERNEL);
}
+static bool kvm_gmem_is_safe_for_conversion(struct inode *inode, pgoff_t start,
+ size_t nr_pages, pgoff_t *err_index)
+{
+ struct address_space *mapping = inode->i_mapping;
+ const int filemap_get_folios_refcount = 1;
+ pgoff_t last = start + nr_pages - 1;
+ struct folio_batch fbatch;
+ bool safe = true;
+ int i;
+
+ folio_batch_init(&fbatch);
+ while (safe && filemap_get_folios(mapping, &start, last, &fbatch)) {
+
+ for (i = 0; i < folio_batch_count(&fbatch); ++i) {
+ struct folio *folio = fbatch.folios[i];
+
+ if (folio_ref_count(folio) !=
+ folio_nr_pages(folio) + filemap_get_folios_refcount) {
+ safe = false;
+ *err_index = folio->index;
+ break;
+ }
+ }
+
+ folio_batch_release(&fbatch);
+ cond_resched();
+ }
+
+ return safe;
+}
+
static int __kvm_gmem_set_attributes(struct inode *inode, pgoff_t start,
- size_t nr_pages, uint64_t attrs)
+ size_t nr_pages, uint64_t attrs,
+ pgoff_t *err_index)
{
+ bool to_private = attrs & KVM_MEMORY_ATTRIBUTE_PRIVATE;
struct address_space *mapping = inode->i_mapping;
struct gmem_inode *gi = GMEM_I(inode);
pgoff_t end = start + nr_pages;
@@ -588,8 +621,21 @@ static int __kvm_gmem_set_attributes(struct inode *inode, pgoff_t start,
mas_init(&mas, mt, start);
r = kvm_gmem_mas_preallocate(&mas, attrs, start, nr_pages);
- if (r)
+ if (r) {
+ *err_index = start;
goto out;
+ }
+
+ if (to_private) {
+ unmap_mapping_pages(mapping, start, nr_pages, false);
+
+ if (!kvm_gmem_is_safe_for_conversion(inode, start, nr_pages,
+ err_index)) {
+ mas_destroy(&mas);
+ r = -EAGAIN;
+ goto out;
+ }
+ }
/*
* From this point on guest_memfd has performed necessary
@@ -609,9 +655,10 @@ static long kvm_gmem_set_attributes(struct file *file, void __user *argp)
struct gmem_file *f = file->private_data;
struct inode *inode = file_inode(file);
struct kvm_memory_attributes2 attrs;
+ pgoff_t err_index;
size_t nr_pages;
pgoff_t index;
- int i;
+ int i, r;
if (copy_from_user(&attrs, argp, sizeof(attrs)))
return -EFAULT;
@@ -635,8 +682,16 @@ static long kvm_gmem_set_attributes(struct file *file, void __user *argp)
nr_pages = attrs.size >> PAGE_SHIFT;
index = attrs.offset >> PAGE_SHIFT;
- return __kvm_gmem_set_attributes(inode, index, nr_pages,
- attrs.attributes);
+ r = __kvm_gmem_set_attributes(inode, index, nr_pages, attrs.attributes,
+ &err_index);
+ if (r) {
+ attrs.error_offset = ((uint64_t)err_index) << PAGE_SHIFT;
+
+ if (copy_to_user(argp, &attrs, sizeof(attrs)))
+ return -EFAULT;
+ }
+
+ return r;
}
static long kvm_gmem_ioctl(struct file *file, unsigned int ioctl,
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related
* [PATCH v6 12/43] KVM: guest_memfd: Call arch invalidate hooks on conversion
From: Ackerley Tng via B4 Relay @ 2026-05-07 20:22 UTC (permalink / raw)
To: aik, andrew.jones, binbin.wu, brauner, chao.p.peng, david,
ira.weiny, jmattson, jthoughton, michael.roth, oupton,
pankaj.gupta, qperret, rick.p.edgecombe, rientjes, shivankg,
steven.price, tabba, willy, wyihan, yan.y.zhao, forkloop,
pratyush, suzuki.poulose, aneesh.kumar, liam, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Baoquan He, Barry Song,
Axel Rasmussen, Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng,
Shakeel Butt, Kiryl Shutsemau, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco, Ackerley Tng
In-Reply-To: <20260507-gmem-inplace-conversion-v6-0-91ab5a8b19a4@google.com>
From: Ackerley Tng <ackerleytng@google.com>
When memory in guest_memfd is converted from private to shared, the
platform-specific state associated with the guest-private pages must be
invalidated or cleaned up.
Iterate over the folios in the affected range and call the
kvm_arch_gmem_invalidate() hook for each PFN range. This allows
architectures to perform necessary teardown, such as updating hardware
metadata or encryption states, before the pages are transitioned to the
shared state.
Invoke this helper after indicating to KVM's mmu code that an invalidation
is in progress to stop in-flight page faults from succeeding.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
virt/kvm/guest_memfd.c | 41 +++++++++++++++++++++++++++++++++++++++++
1 file changed, 41 insertions(+)
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 9d82642a025e9..baf4b88dead1f 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -603,6 +603,42 @@ static bool kvm_gmem_is_safe_for_conversion(struct inode *inode, pgoff_t start,
return safe;
}
+#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE
+static void kvm_gmem_invalidate(struct inode *inode, pgoff_t start, pgoff_t end)
+{
+ struct folio_batch fbatch;
+ pgoff_t next = start;
+ int i;
+
+ folio_batch_init(&fbatch);
+ while (filemap_get_folios(inode->i_mapping, &next, end - 1, &fbatch)) {
+ for (i = 0; i < folio_batch_count(&fbatch); ++i) {
+ struct folio *folio = fbatch.folios[i];
+ pgoff_t start_index, end_index;
+ kvm_pfn_t start_pfn, end_pfn;
+
+ start_index = max(start, folio->index);
+ end_index = min(end, folio_next_index(folio));
+ /*
+ * end_index is either in folio or points to
+ * the first page of the next folio. Hence,
+ * all pages in range [start_index, end_index)
+ * are contiguous.
+ */
+ start_pfn = folio_file_pfn(folio, start_index);
+ end_pfn = start_pfn + end_index - start_index;
+
+ kvm_arch_gmem_invalidate(start_pfn, end_pfn);
+ }
+
+ folio_batch_release(&fbatch);
+ cond_resched();
+ }
+}
+#else
+static void kvm_gmem_invalidate(struct inode *inode, pgoff_t start, pgoff_t end) {}
+#endif
+
static int __kvm_gmem_set_attributes(struct inode *inode, pgoff_t start,
size_t nr_pages, uint64_t attrs,
pgoff_t *err_index)
@@ -643,7 +679,12 @@ static int __kvm_gmem_set_attributes(struct inode *inode, pgoff_t start,
*/
kvm_gmem_invalidate_begin(inode, start, end);
+
+ if (!to_private)
+ kvm_gmem_invalidate(inode, start, end);
+
mas_store_prealloc(&mas, xa_mk_value(attrs));
+
kvm_gmem_invalidate_end(inode, start, end);
out:
filemap_invalidate_unlock(mapping);
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox