From: Dave Jiang <dave.jiang@intel.com>
To: linux-cxl@vger.kernel.org, nvdimm@lists.linux.dev
Cc: djbw@kernel.org, iweiny@kernel.org, pasha.tatashin@soleen.com,
mclapinski@google.com, rppt@kernel.org,
joao.m.martins@oracle.com, jic23@kernel.org, gourry@gourry.net,
john@groves.net, rick.p.edgecombe@intel.com
Subject: [RFC PATCH 07/12] KVM: guest_memfd: Add setup of daxfd when binding gmem
Date: Thu, 23 Apr 2026 10:02:14 -0700 [thread overview]
Message-ID: <20260423170219.281618-8-dave.jiang@intel.com> (raw)
In-Reply-To: <20260423170219.281618-1-dave.jiang@intel.com>
A DAX fd comes from device dax char dev passed in from userspace. It's
not a fd that is created by the kernel unlike gmem fd.
kvm_guest_memfd_bind() seems to be the place to setup additional gmem
context for daxfd at this moment when it is passed in through the ioctl
to bind to gmem. Add a helper function to setup the necessary bits
when the fd is verified to be DAX.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
arch/x86/kvm/Kconfig | 1 +
drivers/dax/bus.c | 3 +++
drivers/dax/dax-private.h | 4 ++++
include/linux/kvm_host.h | 24 +++++++++++++++++++
virt/kvm/Kconfig | 4 ++++
virt/kvm/guest_memfd.c | 50 ++++++++++++++++++++++++++-------------
6 files changed, 70 insertions(+), 16 deletions(-)
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 278f08194ec8..bdcaff9c49e7 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -48,6 +48,7 @@ config KVM_X86
select KVM_GENERIC_PRE_FAULT_MEMORY
select KVM_WERROR if WERROR
select KVM_GUEST_MEMFD if X86_64
+ select KVM_GUEST_DAXFD if X86_64
config KVM
tristate "Kernel-based Virtual Machine (KVM) support"
diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 1ef447747876..759163722e4c 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -1621,6 +1621,9 @@ static struct dev_dax *__devm_create_dev_dax(struct dev_dax_data *data)
dev->parent = parent;
dev->type = &dev_dax_type;
+ xa_init(&dev_dax->gmem_file.bindings);
+ list_add(&dev_dax->gmem_file.entry, &inode->i_mapping->i_private_list);
+
rc = device_add(dev);
if (rc) {
kill_dev_dax(dev_dax);
diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h
index 425a515905e5..2b3c44cb0dbe 100644
--- a/drivers/dax/dax-private.h
+++ b/drivers/dax/dax-private.h
@@ -8,6 +8,7 @@
#include <linux/device.h>
#include <linux/cdev.h>
#include <linux/idr.h>
+#include <linux/kvm_host.h>
/* private routines between core files */
struct dax_device;
@@ -67,6 +68,8 @@ struct dev_dax_range {
/**
* struct dev_dax - instance data for a subdivision of a dax region, and
* data while the device is activated in the driver.
+ *
+ * @gmem_file: guest mem file for this dev_dax. Must be first member
* @region: parent region
* @dax_dev: core dax functionality
* @virt_addr: kva from memremap; used by fsdev_dax
@@ -83,6 +86,7 @@ struct dev_dax_range {
* @ranges: range tuples of memory used
*/
struct dev_dax {
+ struct gmem_file gmem_file;
struct dax_region *region;
struct dax_device *dax_dev;
void *virt_addr;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index d93f75b05ae2..9afce6d02d9e 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -56,6 +56,7 @@
*/
#define KVM_MEMSLOT_INVALID (1UL << 16)
#define KVM_MEMSLOT_GMEM_ONLY (1UL << 17)
+#define KVM_MEMSLOT_DAX_ONLY (1UL << 18)
/*
* Bit 63 of the memslot generation number is an "update in-progress flag",
@@ -2515,6 +2516,14 @@ static inline bool kvm_memslot_is_gmem_only(const struct kvm_memory_slot *slot)
return slot->flags & KVM_MEMSLOT_GMEM_ONLY;
}
+static inline bool kvm_memslot_is_dax_only(const struct kvm_memory_slot *slot)
+{
+ if (!IS_ENABLED(CONFIG_KVM_GUEST_DAXFD))
+ return false;
+
+ return slot->flags & KVM_MEMSLOT_DAX_ONLY;
+}
+
#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn)
{
@@ -2604,4 +2613,19 @@ static inline int kvm_enable_virtualization(void) { return 0; }
static inline void kvm_disable_virtualization(void) { }
#endif
+/*
+ * A guest_memfd instance can be associated multiple VMs, each with its own
+ * "view" of the underlying physical memory.
+ *
+ * The gmem's inode is effectively the raw underlying physical storage, and is
+ * used to track properties of the physical memory, while each gmem file is
+ * effectively a single VM's view of that storage, and is used to track assets
+ * specific to its associated VM, e.g. memslots=>gmem bindings.
+ */
+struct gmem_file {
+ struct kvm *kvm;
+ struct xarray bindings;
+ struct list_head entry;
+};
+
#endif
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 267c7369c765..7f0598af868b 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -125,3 +125,7 @@ config HAVE_KVM_ARCH_GMEM_INVALIDATE
config HAVE_KVM_ARCH_GMEM_POPULATE
bool
depends on KVM_GUEST_MEMFD
+
+config KVM_GUEST_DAXFD
+ bool
+ depends on KVM_GUEST_MEMFD
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index fdaea3422c30..959f690c1d1d 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -7,26 +7,12 @@
#include <linux/mempolicy.h>
#include <linux/pseudo_fs.h>
#include <linux/pagemap.h>
+#include <linux/dax.h>
#include "kvm_mm.h"
static struct vfsmount *kvm_gmem_mnt;
-/*
- * A guest_memfd instance can be associated multiple VMs, each with its own
- * "view" of the underlying physical memory.
- *
- * The gmem's inode is effectively the raw underlying physical storage, and is
- * used to track properties of the physical memory, while each gmem file is
- * effectively a single VM's view of that storage, and is used to track assets
- * specific to its associated VM, e.g. memslots=>gmem bindings.
- */
-struct gmem_file {
- struct kvm *kvm;
- struct xarray bindings;
- struct list_head entry;
-};
-
struct gmem_inode {
struct shared_policy policy;
struct inode vfs_inode;
@@ -644,6 +630,32 @@ int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args)
return __kvm_gmem_create(kvm, size, flags);
}
+/*
+ * DAX fd files are not initialized with gmem bits since it's passed in from
+ * user space and not created by the kernel (at least right now). So when
+ * the daxfd is being bound during kvm_gmem_bind(), the gmem bits needs to be
+ * initialized.
+ */
+static int kvm_daxfd_init(struct file *file, struct kvm_memory_slot *slot,
+ struct kvm *kvm)
+{
+ struct gmem_file *f;
+ struct inode *inode;
+
+ if (!is_file_dax(file))
+ return -EINVAL;
+
+ inode = file_inode(file);
+ GMEM_I(inode)->flags |= GUEST_MEMFD_FLAG_MMAP;
+ slot->flags |= KVM_MEMSLOT_DAX_ONLY;
+
+ kvm_get_kvm(kvm);
+ f = file->private_data;
+ f->kvm = kvm;
+
+ return 0;
+}
+
int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
unsigned int fd, loff_t offset)
{
@@ -660,7 +672,13 @@ int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
if (!file)
return -EBADF;
- if (file->f_op != &kvm_gmem_fops)
+ if (is_file_dax(file)) {
+ r = kvm_daxfd_init(file, slot, kvm);
+ if (r)
+ goto err;
+ }
+
+ if (file->f_op != &kvm_gmem_fops && !is_file_dax(file))
goto err;
f = file->private_data;
--
2.53.0
next prev parent reply other threads:[~2026-04-23 17:02 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-04-23 17:02 [RFC PATCH 00/12] dax: Add DAX to guest memfd support for KVM Dave Jiang
2026-04-23 17:02 ` [RFC PATCH 01/12] dax: rate limit dev_dax_huge_fault() output Dave Jiang
2026-04-23 17:02 ` [RFC PATCH 02/12] dax: Save the kva from memremap Dave Jiang
2026-04-23 17:02 ` [RFC PATCH 03/12] dax: Add fallocate support to device dax Dave Jiang
2026-04-23 17:02 ` [RFC PATCH 04/12] dax: Move dax_pgoff_to_phys() to dax bus to be used by dev dax Dave Jiang
2026-04-23 17:02 ` [RFC PATCH 05/12] dax: Add dax_operations and supporting functions to device dax Dave Jiang
2026-04-23 17:02 ` [RFC PATCH 06/12] dax: Add helper to determine if a 'struct file' supports dax Dave Jiang
2026-04-23 17:02 ` Dave Jiang [this message]
2026-04-23 17:02 ` [RFC PATCH 08/12] fs: allow char dev to go through fallocate Dave Jiang
2026-04-23 17:02 ` [RFC PATCH 09/12] dax: Add dax_get_dev_dax() helper function Dave Jiang
2026-04-23 17:02 ` [RFC PATCH 10/12] kvm: Implement dax support for KVM faulting Dave Jiang
2026-04-23 17:02 ` [RFC PATCH 11/12] kvm: Add daxfd support for supported flags Dave Jiang
2026-04-23 17:02 ` [RFC PATCH 12/12] selftest/kvm: Add daxfd support for gmem selftest Dave Jiang
2026-04-23 17:27 ` [RFC PATCH 00/12] dax: Add DAX to guest memfd support for KVM Pasha Tatashin
2026-04-23 18:08 ` Dave Jiang
2026-04-23 18:21 ` Dave Jiang
2026-04-24 3:43 ` Gregory Price
2026-04-24 17:38 ` Frank van der Linden
2026-04-29 13:21 ` Ira Weiny
2026-04-29 23:58 ` Gregory Price
2026-04-24 17:13 ` Frank van der Linden
2026-04-24 18:23 ` Dave Jiang
2026-04-24 20:01 ` Frank van der Linden
2026-04-24 20:59 ` Dave Jiang
2026-05-06 20:23 ` Ackerley Tng
2026-05-06 20:37 ` Dave Jiang
2026-05-08 1:09 ` Ira Weiny
2026-05-10 14:40 ` Gregory Price
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260423170219.281618-8-dave.jiang@intel.com \
--to=dave.jiang@intel.com \
--cc=djbw@kernel.org \
--cc=gourry@gourry.net \
--cc=iweiny@kernel.org \
--cc=jic23@kernel.org \
--cc=joao.m.martins@oracle.com \
--cc=john@groves.net \
--cc=linux-cxl@vger.kernel.org \
--cc=mclapinski@google.com \
--cc=nvdimm@lists.linux.dev \
--cc=pasha.tatashin@soleen.com \
--cc=rick.p.edgecombe@intel.com \
--cc=rppt@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox