x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 837 insertions, 0 deletions

diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c
new file mode 100644
index 000000000..83b0df460
--- /dev/null
+++ b/drivers/xen/gntdev-dmabuf.c
@@ -0,0 +1,837 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Xen dma-buf functionality for gntdev.
+ *
+ * DMA buffer implementation is based on drivers/gpu/drm/drm_prime.c.
+ *
+ * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/dma-buf.h>
+#include <linux/dma-direct.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+
+#include <xen/xen.h>
+#include <xen/grant_table.h>
+
+#include "gntdev-common.h"
+#include "gntdev-dmabuf.h"
+
+MODULE_IMPORT_NS("DMA_BUF");
+
+struct gntdev_dmabuf {
+	struct gntdev_dmabuf_priv *priv;
+	struct dma_buf *dmabuf;
+	struct list_head next;
+	int fd;
+
+	union {
+		struct {
+			/* Exported buffers are reference counted. */
+			struct kref refcount;
+
+			struct gntdev_priv *priv;
+			struct gntdev_grant_map *map;
+		} exp;
+		struct {
+			/* Granted references of the imported buffer. */
+			grant_ref_t *refs;
+			/* Scatter-gather table of the imported buffer. */
+			struct sg_table *sgt;
+			/* dma-buf attachment of the imported buffer. */
+			struct dma_buf_attachment *attach;
+		} imp;
+	} u;
+
+	/* Number of pages this buffer has. */
+	int nr_pages;
+	/* Pages of this buffer (only for dma-buf export). */
+	struct page **pages;
+};
+
+struct gntdev_dmabuf_wait_obj {
+	struct list_head next;
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	struct completion completion;
+};
+
+struct gntdev_dmabuf_attachment {
+	struct sg_table *sgt;
+	enum dma_data_direction dir;
+};
+
+struct gntdev_dmabuf_priv {
+	/* List of exported DMA buffers. */
+	struct list_head exp_list;
+	/* List of wait objects. */
+	struct list_head exp_wait_list;
+	/* List of imported DMA buffers. */
+	struct list_head imp_list;
+	/* This is the lock which protects dma_buf_xxx lists. */
+	struct mutex lock;
+	/*
+	 * We reference this file while exporting dma-bufs, so
+	 * the grant device context is not destroyed while there are
+	 * external users alive.
+	 */
+	struct file *filp;
+};
+
+/* DMA buffer export support. */
+
+/* Implementation of wait for exported DMA buffer to be released. */
+
+static void dmabuf_exp_release(struct kref *kref);
+
+static struct gntdev_dmabuf_wait_obj *
+dmabuf_exp_wait_obj_new(struct gntdev_dmabuf_priv *priv,
+			struct gntdev_dmabuf *gntdev_dmabuf)
+{
+	struct gntdev_dmabuf_wait_obj *obj;
+
+	obj = kzalloc_obj(*obj);
+	if (!obj)
+		return ERR_PTR(-ENOMEM);
+
+	init_completion(&obj->completion);
+	obj->gntdev_dmabuf = gntdev_dmabuf;
+
+	mutex_lock(&priv->lock);
+	list_add(&obj->next, &priv->exp_wait_list);
+	/* Put our reference and wait for gntdev_dmabuf's release to fire. */
+	kref_put(&gntdev_dmabuf->u.exp.refcount, dmabuf_exp_release);
+	mutex_unlock(&priv->lock);
+	return obj;
+}
+
+static void dmabuf_exp_wait_obj_free(struct gntdev_dmabuf_priv *priv,
+				     struct gntdev_dmabuf_wait_obj *obj)
+{
+	mutex_lock(&priv->lock);
+	list_del(&obj->next);
+	mutex_unlock(&priv->lock);
+	kfree(obj);
+}
+
+static int dmabuf_exp_wait_obj_wait(struct gntdev_dmabuf_wait_obj *obj,
+				    u32 wait_to_ms)
+{
+	if (wait_for_completion_timeout(&obj->completion,
+			msecs_to_jiffies(wait_to_ms)) <= 0)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static void dmabuf_exp_wait_obj_signal(struct gntdev_dmabuf_priv *priv,
+				       struct gntdev_dmabuf *gntdev_dmabuf)
+{
+	struct gntdev_dmabuf_wait_obj *obj;
+
+	list_for_each_entry(obj, &priv->exp_wait_list, next)
+		if (obj->gntdev_dmabuf == gntdev_dmabuf) {
+			pr_debug("Found gntdev_dmabuf in the wait list, wake\n");
+			complete_all(&obj->completion);
+			break;
+		}
+}
+
+static struct gntdev_dmabuf *
+dmabuf_exp_wait_obj_get_dmabuf(struct gntdev_dmabuf_priv *priv, int fd)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf, *ret = ERR_PTR(-ENOENT);
+
+	mutex_lock(&priv->lock);
+	list_for_each_entry(gntdev_dmabuf, &priv->exp_list, next)
+		if (gntdev_dmabuf->fd == fd) {
+			pr_debug("Found gntdev_dmabuf in the wait list\n");
+			kref_get(&gntdev_dmabuf->u.exp.refcount);
+			ret = gntdev_dmabuf;
+			break;
+		}
+	mutex_unlock(&priv->lock);
+	return ret;
+}
+
+static int dmabuf_exp_wait_released(struct gntdev_dmabuf_priv *priv, int fd,
+				    int wait_to_ms)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	struct gntdev_dmabuf_wait_obj *obj;
+	int ret;
+
+	pr_debug("Will wait for dma-buf with fd %d\n", fd);
+	/*
+	 * Try to find the DMA buffer: if not found means that
+	 * either the buffer has already been released or file descriptor
+	 * provided is wrong.
+	 */
+	gntdev_dmabuf = dmabuf_exp_wait_obj_get_dmabuf(priv, fd);
+	if (IS_ERR(gntdev_dmabuf))
+		return PTR_ERR(gntdev_dmabuf);
+
+	/*
+	 * gntdev_dmabuf still exists and is reference count locked by us now,
+	 * so prepare to wait: allocate wait object and add it to the wait list,
+	 * so we can find it on release.
+	 */
+	obj = dmabuf_exp_wait_obj_new(priv, gntdev_dmabuf);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	ret = dmabuf_exp_wait_obj_wait(obj, wait_to_ms);
+	dmabuf_exp_wait_obj_free(priv, obj);
+	return ret;
+}
+
+/* DMA buffer export support. */
+
+static struct sg_table *
+dmabuf_pages_to_sgt(struct page **pages, unsigned int nr_pages)
+{
+	struct sg_table *sgt;
+	int ret;
+
+	sgt = kmalloc_obj(*sgt);
+	if (!sgt) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = sg_alloc_table_from_pages(sgt, pages, nr_pages, 0,
+					nr_pages << PAGE_SHIFT,
+					GFP_KERNEL);
+	if (ret)
+		goto out;
+
+	return sgt;
+
+out:
+	kfree(sgt);
+	return ERR_PTR(ret);
+}
+
+static int dmabuf_exp_ops_attach(struct dma_buf *dma_buf,
+				 struct dma_buf_attachment *attach)
+{
+	struct gntdev_dmabuf_attachment *gntdev_dmabuf_attach;
+
+	gntdev_dmabuf_attach = kzalloc_obj(*gntdev_dmabuf_attach);
+	if (!gntdev_dmabuf_attach)
+		return -ENOMEM;
+
+	gntdev_dmabuf_attach->dir = DMA_NONE;
+	attach->priv = gntdev_dmabuf_attach;
+	return 0;
+}
+
+static void dmabuf_exp_ops_detach(struct dma_buf *dma_buf,
+				  struct dma_buf_attachment *attach)
+{
+	struct gntdev_dmabuf_attachment *gntdev_dmabuf_attach = attach->priv;
+
+	if (gntdev_dmabuf_attach) {
+		struct sg_table *sgt = gntdev_dmabuf_attach->sgt;
+
+		if (sgt) {
+			if (gntdev_dmabuf_attach->dir != DMA_NONE)
+				dma_unmap_sgtable(attach->dev, sgt,
+						  gntdev_dmabuf_attach->dir,
+						  DMA_ATTR_SKIP_CPU_SYNC);
+			sg_free_table(sgt);
+		}
+
+		kfree(sgt);
+		kfree(gntdev_dmabuf_attach);
+		attach->priv = NULL;
+	}
+}
+
+static struct sg_table *
+dmabuf_exp_ops_map_dma_buf(struct dma_buf_attachment *attach,
+			   enum dma_data_direction dir)
+{
+	struct gntdev_dmabuf_attachment *gntdev_dmabuf_attach = attach->priv;
+	struct gntdev_dmabuf *gntdev_dmabuf = attach->dmabuf->priv;
+	struct sg_table *sgt;
+
+	pr_debug("Mapping %d pages for dev %p\n", gntdev_dmabuf->nr_pages,
+		 attach->dev);
+
+	if (dir == DMA_NONE || !gntdev_dmabuf_attach)
+		return ERR_PTR(-EINVAL);
+
+	/* Return the cached mapping when possible. */
+	if (gntdev_dmabuf_attach->dir == dir)
+		return gntdev_dmabuf_attach->sgt;
+
+	/*
+	 * Two mappings with different directions for the same attachment are
+	 * not allowed.
+	 */
+	if (gntdev_dmabuf_attach->dir != DMA_NONE)
+		return ERR_PTR(-EBUSY);
+
+	sgt = dmabuf_pages_to_sgt(gntdev_dmabuf->pages,
+				  gntdev_dmabuf->nr_pages);
+	if (!IS_ERR(sgt)) {
+		if (dma_map_sgtable(attach->dev, sgt, dir,
+				    DMA_ATTR_SKIP_CPU_SYNC)) {
+			sg_free_table(sgt);
+			kfree(sgt);
+			sgt = ERR_PTR(-ENOMEM);
+		} else {
+			gntdev_dmabuf_attach->sgt = sgt;
+			gntdev_dmabuf_attach->dir = dir;
+		}
+	}
+	if (IS_ERR(sgt))
+		pr_debug("Failed to map sg table for dev %p\n", attach->dev);
+	return sgt;
+}
+
+static void dmabuf_exp_ops_unmap_dma_buf(struct dma_buf_attachment *attach,
+					 struct sg_table *sgt,
+					 enum dma_data_direction dir)
+{
+	/* Not implemented. The unmap is done at dmabuf_exp_ops_detach(). */
+}
+
+static void dmabuf_exp_release(struct kref *kref)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf =
+		container_of(kref, struct gntdev_dmabuf, u.exp.refcount);
+
+	dmabuf_exp_wait_obj_signal(gntdev_dmabuf->priv, gntdev_dmabuf);
+	list_del(&gntdev_dmabuf->next);
+	fput(gntdev_dmabuf->priv->filp);
+	kfree(gntdev_dmabuf);
+}
+
+static void dmabuf_exp_remove_map(struct gntdev_priv *priv,
+				  struct gntdev_grant_map *map)
+{
+	mutex_lock(&priv->lock);
+	list_del(&map->next);
+	gntdev_put_map(NULL /* already removed */, map);
+	mutex_unlock(&priv->lock);
+}
+
+static void dmabuf_exp_ops_release(struct dma_buf *dma_buf)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf = dma_buf->priv;
+	struct gntdev_dmabuf_priv *priv = gntdev_dmabuf->priv;
+
+	dmabuf_exp_remove_map(gntdev_dmabuf->u.exp.priv,
+			      gntdev_dmabuf->u.exp.map);
+	mutex_lock(&priv->lock);
+	kref_put(&gntdev_dmabuf->u.exp.refcount, dmabuf_exp_release);
+	mutex_unlock(&priv->lock);
+}
+
+static const struct dma_buf_ops dmabuf_exp_ops =  {
+	.attach = dmabuf_exp_ops_attach,
+	.detach = dmabuf_exp_ops_detach,
+	.map_dma_buf = dmabuf_exp_ops_map_dma_buf,
+	.unmap_dma_buf = dmabuf_exp_ops_unmap_dma_buf,
+	.release = dmabuf_exp_ops_release,
+};
+
+struct gntdev_dmabuf_export_args {
+	struct gntdev_priv *priv;
+	struct gntdev_grant_map *map;
+	struct gntdev_dmabuf_priv *dmabuf_priv;
+	struct device *dev;
+	int count;
+	struct page **pages;
+	u32 fd;
+};
+
+static int dmabuf_exp_from_pages(struct gntdev_dmabuf_export_args *args)
+{
+	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+	struct gntdev_dmabuf *gntdev_dmabuf __free(kfree) = NULL;
+	CLASS(get_unused_fd, ret)(O_CLOEXEC);
+
+	if (ret < 0)
+		return ret;
+
+	gntdev_dmabuf = kzalloc_obj(*gntdev_dmabuf);
+	if (!gntdev_dmabuf)
+		return -ENOMEM;
+
+	kref_init(&gntdev_dmabuf->u.exp.refcount);
+
+	gntdev_dmabuf->priv = args->dmabuf_priv;
+	gntdev_dmabuf->nr_pages = args->count;
+	gntdev_dmabuf->pages = args->pages;
+	gntdev_dmabuf->u.exp.priv = args->priv;
+	gntdev_dmabuf->u.exp.map = args->map;
+
+	exp_info.exp_name = KBUILD_MODNAME;
+	if (args->dev->driver && args->dev->driver->owner)
+		exp_info.owner = args->dev->driver->owner;
+	else
+		exp_info.owner = THIS_MODULE;
+	exp_info.ops = &dmabuf_exp_ops;
+	exp_info.size = args->count << PAGE_SHIFT;
+	exp_info.flags = O_RDWR;
+	exp_info.priv = gntdev_dmabuf;
+
+	gntdev_dmabuf->dmabuf = dma_buf_export(&exp_info);
+	if (IS_ERR(gntdev_dmabuf->dmabuf))
+		return PTR_ERR(gntdev_dmabuf->dmabuf);
+
+	gntdev_dmabuf->fd = ret;
+	args->fd = ret;
+
+	pr_debug("Exporting DMA buffer with fd %d\n", ret);
+
+	get_file(gntdev_dmabuf->priv->filp);
+	mutex_lock(&args->dmabuf_priv->lock);
+	list_add(&gntdev_dmabuf->next, &args->dmabuf_priv->exp_list);
+	mutex_unlock(&args->dmabuf_priv->lock);
+
+	fd_install(take_fd(ret), no_free_ptr(gntdev_dmabuf)->dmabuf->file);
+	return 0;
+}
+
+static struct gntdev_grant_map *
+dmabuf_exp_alloc_backing_storage(struct gntdev_priv *priv, int dmabuf_flags,
+				 int count)
+{
+	struct gntdev_grant_map *map;
+
+	if (unlikely(gntdev_test_page_count(count)))
+		return ERR_PTR(-EINVAL);
+
+	if ((dmabuf_flags & GNTDEV_DMA_FLAG_WC) &&
+	    (dmabuf_flags & GNTDEV_DMA_FLAG_COHERENT)) {
+		pr_debug("Wrong dma-buf flags: 0x%x\n", dmabuf_flags);
+		return ERR_PTR(-EINVAL);
+	}
+
+	map = gntdev_alloc_map(priv, count, dmabuf_flags);
+	if (!map)
+		return ERR_PTR(-ENOMEM);
+
+	return map;
+}
+
+static int dmabuf_exp_from_refs(struct gntdev_priv *priv, int flags,
+				int count, u32 domid, u32 *refs, u32 *fd)
+{
+	struct gntdev_grant_map *map;
+	struct gntdev_dmabuf_export_args args;
+	int i, ret;
+
+	map = dmabuf_exp_alloc_backing_storage(priv, flags, count);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	for (i = 0; i < count; i++) {
+		map->grants[i].domid = domid;
+		map->grants[i].ref = refs[i];
+	}
+
+	mutex_lock(&priv->lock);
+	gntdev_add_map(priv, map);
+	mutex_unlock(&priv->lock);
+
+	map->flags |= GNTMAP_host_map;
+#if defined(CONFIG_X86)
+	map->flags |= GNTMAP_device_map;
+#endif
+
+	ret = gntdev_map_grant_pages(map);
+	if (ret < 0)
+		goto out;
+
+	args.priv = priv;
+	args.map = map;
+	args.dev = priv->dma_dev;
+	args.dmabuf_priv = priv->dmabuf_priv;
+	args.count = map->count;
+	args.pages = map->pages;
+	args.fd = -1; /* Shut up unnecessary gcc warning for i386 */
+
+	ret = dmabuf_exp_from_pages(&args);
+	if (ret < 0)
+		goto out;
+
+	*fd = args.fd;
+	return 0;
+
+out:
+	dmabuf_exp_remove_map(priv, map);
+	return ret;
+}
+
+/* DMA buffer import support. */
+
+static int
+dmabuf_imp_grant_foreign_access(unsigned long *gfns, u32 *refs,
+				int count, int domid)
+{
+	grant_ref_t priv_gref_head;
+	int i, ret;
+
+	ret = gnttab_alloc_grant_references(count, &priv_gref_head);
+	if (ret < 0) {
+		pr_debug("Cannot allocate grant references, ret %d\n", ret);
+		return ret;
+	}
+
+	for (i = 0; i < count; i++) {
+		int cur_ref;
+
+		cur_ref = gnttab_claim_grant_reference(&priv_gref_head);
+		if (cur_ref < 0) {
+			ret = cur_ref;
+			pr_debug("Cannot claim grant reference, ret %d\n", ret);
+			goto out;
+		}
+
+		gnttab_grant_foreign_access_ref(cur_ref, domid,
+						gfns[i], 0);
+		refs[i] = cur_ref;
+	}
+
+	return 0;
+
+out:
+	gnttab_free_grant_references(priv_gref_head);
+	return ret;
+}
+
+static void dmabuf_imp_end_foreign_access(u32 *refs, int count)
+{
+	int i;
+
+	for (i = 0; i < count; i++)
+		if (refs[i] != INVALID_GRANT_REF)
+			gnttab_end_foreign_access(refs[i], NULL);
+}
+
+static void dmabuf_imp_free_storage(struct gntdev_dmabuf *gntdev_dmabuf)
+{
+	kfree(gntdev_dmabuf->u.imp.refs);
+	kfree(gntdev_dmabuf);
+}
+
+static struct gntdev_dmabuf *dmabuf_imp_alloc_storage(int count)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	int i;
+
+	gntdev_dmabuf = kzalloc_obj(*gntdev_dmabuf);
+	if (!gntdev_dmabuf)
+		goto fail_no_free;
+
+	gntdev_dmabuf->u.imp.refs = kzalloc_objs(gntdev_dmabuf->u.imp.refs[0],
+						 count);
+	if (!gntdev_dmabuf->u.imp.refs)
+		goto fail;
+
+	gntdev_dmabuf->nr_pages = count;
+
+	for (i = 0; i < count; i++)
+		gntdev_dmabuf->u.imp.refs[i] = INVALID_GRANT_REF;
+
+	return gntdev_dmabuf;
+
+fail:
+	dmabuf_imp_free_storage(gntdev_dmabuf);
+fail_no_free:
+	return ERR_PTR(-ENOMEM);
+}
+
+static struct gntdev_dmabuf *
+dmabuf_imp_to_refs(struct gntdev_dmabuf_priv *priv, struct device *dev,
+		   int fd, int count, int domid)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf, *ret;
+	struct dma_buf *dma_buf;
+	struct dma_buf_attachment *attach;
+	struct sg_table *sgt;
+	struct sg_dma_page_iter sg_iter;
+	unsigned long *gfns;
+	int i;
+
+	dma_buf = dma_buf_get(fd);
+	if (IS_ERR(dma_buf))
+		return ERR_CAST(dma_buf);
+
+	gntdev_dmabuf = dmabuf_imp_alloc_storage(count);
+	if (IS_ERR(gntdev_dmabuf)) {
+		ret = gntdev_dmabuf;
+		goto fail_put;
+	}
+
+	gntdev_dmabuf->priv = priv;
+	gntdev_dmabuf->fd = fd;
+
+	attach = dma_buf_attach(dma_buf, dev);
+	if (IS_ERR(attach)) {
+		ret = ERR_CAST(attach);
+		goto fail_free_obj;
+	}
+
+	gntdev_dmabuf->u.imp.attach = attach;
+
+	sgt = dma_buf_map_attachment_unlocked(attach, DMA_BIDIRECTIONAL);
+	if (IS_ERR(sgt)) {
+		ret = ERR_CAST(sgt);
+		goto fail_detach;
+	}
+
+	/* Check that we have zero offset. */
+	if (sgt->sgl->offset) {
+		ret = ERR_PTR(-EINVAL);
+		pr_debug("DMA buffer has %d bytes offset, user-space expects 0\n",
+			 sgt->sgl->offset);
+		goto fail_unmap;
+	}
+
+	/* Check number of pages that imported buffer has. */
+	if (attach->dmabuf->size != gntdev_dmabuf->nr_pages << PAGE_SHIFT) {
+		ret = ERR_PTR(-EINVAL);
+		pr_debug("DMA buffer has %zu pages, user-space expects %d\n",
+			 attach->dmabuf->size, gntdev_dmabuf->nr_pages);
+		goto fail_unmap;
+	}
+
+	gntdev_dmabuf->u.imp.sgt = sgt;
+
+	gfns = kcalloc(count, sizeof(*gfns), GFP_KERNEL);
+	if (!gfns) {
+		ret = ERR_PTR(-ENOMEM);
+		goto fail_unmap;
+	}
+
+	/*
+	 * Now convert sgt to array of gfns without accessing underlying pages.
+	 * It is not allowed to access the underlying struct page of an sg table
+	 * exported by DMA-buf, but since we deal with special Xen dma device here
+	 * (not a normal physical one) look at the dma addresses in the sg table
+	 * and then calculate gfns directly from them.
+	 */
+	i = 0;
+	for_each_sgtable_dma_page(sgt, &sg_iter, 0) {
+		dma_addr_t addr = sg_page_iter_dma_address(&sg_iter);
+		unsigned long pfn = bfn_to_pfn(XEN_PFN_DOWN(dma_to_phys(dev, addr)));
+
+		gfns[i++] = pfn_to_gfn(pfn);
+	}
+
+	ret = ERR_PTR(dmabuf_imp_grant_foreign_access(gfns,
+						      gntdev_dmabuf->u.imp.refs,
+						      count, domid));
+	kfree(gfns);
+	if (IS_ERR(ret))
+		goto fail_end_access;
+
+	pr_debug("Imported DMA buffer with fd %d\n", fd);
+
+	mutex_lock(&priv->lock);
+	list_add(&gntdev_dmabuf->next, &priv->imp_list);
+	mutex_unlock(&priv->lock);
+
+	return gntdev_dmabuf;
+
+fail_end_access:
+	dmabuf_imp_end_foreign_access(gntdev_dmabuf->u.imp.refs, count);
+fail_unmap:
+	dma_buf_unmap_attachment_unlocked(attach, sgt, DMA_BIDIRECTIONAL);
+fail_detach:
+	dma_buf_detach(dma_buf, attach);
+fail_free_obj:
+	dmabuf_imp_free_storage(gntdev_dmabuf);
+fail_put:
+	dma_buf_put(dma_buf);
+	return ret;
+}
+
+/*
+ * Find the hyper dma-buf by its file descriptor and remove
+ * it from the buffer's list.
+ */
+static struct gntdev_dmabuf *
+dmabuf_imp_find_unlink(struct gntdev_dmabuf_priv *priv, int fd)
+{
+	struct gntdev_dmabuf *q, *gntdev_dmabuf, *ret = ERR_PTR(-ENOENT);
+
+	mutex_lock(&priv->lock);
+	list_for_each_entry_safe(gntdev_dmabuf, q, &priv->imp_list, next) {
+		if (gntdev_dmabuf->fd == fd) {
+			pr_debug("Found gntdev_dmabuf in the import list\n");
+			ret = gntdev_dmabuf;
+			list_del(&gntdev_dmabuf->next);
+			break;
+		}
+	}
+	mutex_unlock(&priv->lock);
+	return ret;
+}
+
+static int dmabuf_imp_release(struct gntdev_dmabuf_priv *priv, u32 fd)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	struct dma_buf_attachment *attach;
+	struct dma_buf *dma_buf;
+
+	gntdev_dmabuf = dmabuf_imp_find_unlink(priv, fd);
+	if (IS_ERR(gntdev_dmabuf))
+		return PTR_ERR(gntdev_dmabuf);
+
+	pr_debug("Releasing DMA buffer with fd %d\n", fd);
+
+	dmabuf_imp_end_foreign_access(gntdev_dmabuf->u.imp.refs,
+				      gntdev_dmabuf->nr_pages);
+
+	attach = gntdev_dmabuf->u.imp.attach;
+
+	if (gntdev_dmabuf->u.imp.sgt)
+		dma_buf_unmap_attachment_unlocked(attach, gntdev_dmabuf->u.imp.sgt,
+						  DMA_BIDIRECTIONAL);
+	dma_buf = attach->dmabuf;
+	dma_buf_detach(attach->dmabuf, attach);
+	dma_buf_put(dma_buf);
+
+	dmabuf_imp_free_storage(gntdev_dmabuf);
+	return 0;
+}
+
+static void dmabuf_imp_release_all(struct gntdev_dmabuf_priv *priv)
+{
+	struct gntdev_dmabuf *q, *gntdev_dmabuf;
+
+	list_for_each_entry_safe(gntdev_dmabuf, q, &priv->imp_list, next)
+		dmabuf_imp_release(priv, gntdev_dmabuf->fd);
+}
+
+/* DMA buffer IOCTL support. */
+
+long gntdev_ioctl_dmabuf_exp_from_refs(struct gntdev_priv *priv,
+				       struct ioctl_gntdev_dmabuf_exp_from_refs __user *u)
+{
+	struct ioctl_gntdev_dmabuf_exp_from_refs op;
+	u32 *refs;
+	long ret;
+
+	if (xen_pv_domain()) {
+		pr_debug("Cannot provide dma-buf in a PV domain\n");
+		return -EINVAL;
+	}
+
+	if (copy_from_user(&op, u, sizeof(op)) != 0)
+		return -EFAULT;
+
+	if (unlikely(gntdev_test_page_count(op.count)))
+		return -EINVAL;
+
+	refs = kcalloc(op.count, sizeof(*refs), GFP_KERNEL);
+	if (!refs)
+		return -ENOMEM;
+
+	if (copy_from_user(refs, u->refs, sizeof(*refs) * op.count) != 0) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	ret = dmabuf_exp_from_refs(priv, op.flags, op.count,
+				   op.domid, refs, &op.fd);
+	if (ret)
+		goto out;
+
+	if (copy_to_user(u, &op, sizeof(op)) != 0)
+		ret = -EFAULT;
+
+out:
+	kfree(refs);
+	return ret;
+}
+
+long gntdev_ioctl_dmabuf_exp_wait_released(struct gntdev_priv *priv,
+					   struct ioctl_gntdev_dmabuf_exp_wait_released __user *u)
+{
+	struct ioctl_gntdev_dmabuf_exp_wait_released op;
+
+	if (copy_from_user(&op, u, sizeof(op)) != 0)
+		return -EFAULT;
+
+	return dmabuf_exp_wait_released(priv->dmabuf_priv, op.fd,
+					op.wait_to_ms);
+}
+
+long gntdev_ioctl_dmabuf_imp_to_refs(struct gntdev_priv *priv,
+				     struct ioctl_gntdev_dmabuf_imp_to_refs __user *u)
+{
+	struct ioctl_gntdev_dmabuf_imp_to_refs op;
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	long ret;
+
+	if (copy_from_user(&op, u, sizeof(op)) != 0)
+		return -EFAULT;
+
+	if (unlikely(gntdev_test_page_count(op.count)))
+		return -EINVAL;
+
+	gntdev_dmabuf = dmabuf_imp_to_refs(priv->dmabuf_priv,
+					   priv->dma_dev, op.fd,
+					   op.count, op.domid);
+	if (IS_ERR(gntdev_dmabuf))
+		return PTR_ERR(gntdev_dmabuf);
+
+	if (copy_to_user(u->refs, gntdev_dmabuf->u.imp.refs,
+			 sizeof(*u->refs) * op.count) != 0) {
+		ret = -EFAULT;
+		goto out_release;
+	}
+	return 0;
+
+out_release:
+	dmabuf_imp_release(priv->dmabuf_priv, op.fd);
+	return ret;
+}
+
+long gntdev_ioctl_dmabuf_imp_release(struct gntdev_priv *priv,
+				     struct ioctl_gntdev_dmabuf_imp_release __user *u)
+{
+	struct ioctl_gntdev_dmabuf_imp_release op;
+
+	if (copy_from_user(&op, u, sizeof(op)) != 0)
+		return -EFAULT;
+
+	return dmabuf_imp_release(priv->dmabuf_priv, op.fd);
+}
+
+struct gntdev_dmabuf_priv *gntdev_dmabuf_init(struct file *filp)
+{
+	struct gntdev_dmabuf_priv *priv;
+
+	priv = kzalloc_obj(*priv);
+	if (!priv)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_init(&priv->lock);
+	INIT_LIST_HEAD(&priv->exp_list);
+	INIT_LIST_HEAD(&priv->exp_wait_list);
+	INIT_LIST_HEAD(&priv->imp_list);
+
+	priv->filp = filp;
+
+	return priv;
+}
+
+void gntdev_dmabuf_fini(struct gntdev_dmabuf_priv *priv)
+{
+	dmabuf_imp_release_all(priv);
+	kfree(priv);
+}