uio_hv_generic: Fix sysfs creation path for ring buffer

On regular bootup, devices get registered to VMBus first, so when
uio_hv_generic driver for a particular device type is probed,
the device is already initialized and added, so sysfs creation in
hv_uio_probe() works fine. However, when the device is removed
and brought back, the channel gets rescinded and the device again gets
registered to VMBus. However this time, the uio_hv_generic driver is
already registered to probe for that device and in this case sysfs
creation is tried before the device's kobject gets initialized
completely.

Fix this by moving the core logic of sysfs creation of ring buffer,
from uio_hv_generic to HyperV's VMBus driver, where the rest of the
sysfs attributes for the channels are defined. While doing that, make
use of attribute groups and macros, instead of creating sysfs
directly, to ensure better error handling and code flow.

Problematic path:
vmbus_process_offer (A new offer comes for the VMBus device)
  vmbus_add_channel_work
    vmbus_device_register
      |-> device_register
      |     |...
      |     |-> hv_uio_probe
      |           |...
      |           |-> sysfs_create_bin_file (leads to a warning as
      |                 the primary channel's kobject, which is used to
      |                 create the sysfs file, is not yet initialized)
      |-> kset_create_and_add
      |-> vmbus_add_channel_kobj (initialization of the primary
                                  channel's kobject happens later)

Above code flow is sequential and the warning is always reproducible in
this path.

Fixes: 9ab877a6ccf8 ("uio_hv_generic: make ring buffer attribute for primary channel")
Cc: stable@kernel.org
Suggested-by: Saurabh Sengar <ssengar@linux.microsoft.com>
Suggested-by: Michael Kelley <mhklinux@outlook.com>
Reviewed-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Michael Kelley <mhklinux@outlook.com>
Reviewed-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Naman Jain <namjain@linux.microsoft.com>
Link: https://lore.kernel.org/r/20250502074811.2022-2-namjain@linux.microsoft.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 99 insertions, 1 deletions

diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 8d3cff42bdbb..0f16a83cc2d6 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -1802,6 +1802,27 @@ static ssize_t subchannel_id_show(struct vmbus_channel *channel,
 }
 static VMBUS_CHAN_ATTR_RO(subchannel_id);
 
+static int hv_mmap_ring_buffer_wrapper(struct file *filp, struct kobject *kobj,
+				       const struct bin_attribute *attr,
+				       struct vm_area_struct *vma)
+{
+	struct vmbus_channel *channel = container_of(kobj, struct vmbus_channel, kobj);
+
+	/*
+	 * hv_(create|remove)_ring_sysfs implementation ensures that mmap_ring_buffer
+	 * is not NULL.
+	 */
+	return channel->mmap_ring_buffer(channel, vma);
+}
+
+static struct bin_attribute chan_attr_ring_buffer = {
+	.attr = {
+		.name = "ring",
+		.mode = 0600,
+	},
+	.size = 2 * SZ_2M,
+	.mmap = hv_mmap_ring_buffer_wrapper,
+};
 static struct attribute *vmbus_chan_attrs[] = {
 	&chan_attr_out_mask.attr,
 	&chan_attr_in_mask.attr,
@@ -1821,6 +1842,11 @@ static struct attribute *vmbus_chan_attrs[] = {
 	NULL
 };
 
+static struct bin_attribute *vmbus_chan_bin_attrs[] = {
+	&chan_attr_ring_buffer,
+	NULL
+};
+
 /*
  * Channel-level attribute_group callback function. Returns the permission for
  * each attribute, and returns 0 if an attribute is not visible.
@@ -1841,9 +1867,24 @@ static umode_t vmbus_chan_attr_is_visible(struct kobject *kobj,
 	return attr->mode;
 }
 
+static umode_t vmbus_chan_bin_attr_is_visible(struct kobject *kobj,
+					      const struct bin_attribute *attr, int idx)
+{
+	const struct vmbus_channel *channel =
+		container_of(kobj, struct vmbus_channel, kobj);
+
+	/* Hide ring attribute if channel's ring_sysfs_visible is set to false */
+	if (attr ==  &chan_attr_ring_buffer && !channel->ring_sysfs_visible)
+		return 0;
+
+	return attr->attr.mode;
+}
+
 static const struct attribute_group vmbus_chan_group = {
 	.attrs = vmbus_chan_attrs,
-	.is_visible = vmbus_chan_attr_is_visible
+	.bin_attrs = vmbus_chan_bin_attrs,
+	.is_visible = vmbus_chan_attr_is_visible,
+	.is_bin_visible = vmbus_chan_bin_attr_is_visible,
 };
 
 static const struct kobj_type vmbus_chan_ktype = {
@@ -1851,6 +1892,63 @@ static const struct kobj_type vmbus_chan_ktype = {
 	.release = vmbus_chan_release,
 };
 
+/**
+ * hv_create_ring_sysfs() - create "ring" sysfs entry corresponding to ring buffers for a channel.
+ * @channel: Pointer to vmbus_channel structure
+ * @hv_mmap_ring_buffer: function pointer for initializing the function to be called on mmap of
+ *                       channel's "ring" sysfs node, which is for the ring buffer of that channel.
+ *                       Function pointer is of below type:
+ *                       int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel,
+ *                                                  struct vm_area_struct *vma))
+ *                       This has a pointer to the channel and a pointer to vm_area_struct,
+ *                       used for mmap, as arguments.
+ *
+ * Sysfs node for ring buffer of a channel is created along with other fields, however its
+ * visibility is disabled by default. Sysfs creation needs to be controlled when the use-case
+ * is running.
+ * For example, HV_NIC device is used either by uio_hv_generic or hv_netvsc at any given point of
+ * time, and "ring" sysfs is needed only when uio_hv_generic is bound to that device. To avoid
+ * exposing the ring buffer by default, this function is reponsible to enable visibility of
+ * ring for userspace to use.
+ * Note: Race conditions can happen with userspace and it is not encouraged to create new
+ * use-cases for this. This was added to maintain backward compatibility, while solving
+ * one of the race conditions in uio_hv_generic while creating sysfs.
+ *
+ * Returns 0 on success or error code on failure.
+ */
+int hv_create_ring_sysfs(struct vmbus_channel *channel,
+			 int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel,
+						    struct vm_area_struct *vma))
+{
+	struct kobject *kobj = &channel->kobj;
+
+	channel->mmap_ring_buffer = hv_mmap_ring_buffer;
+	channel->ring_sysfs_visible = true;
+
+	return sysfs_update_group(kobj, &vmbus_chan_group);
+}
+EXPORT_SYMBOL_GPL(hv_create_ring_sysfs);
+
+/**
+ * hv_remove_ring_sysfs() - remove ring sysfs entry corresponding to ring buffers for a channel.
+ * @channel: Pointer to vmbus_channel structure
+ *
+ * Hide "ring" sysfs for a channel by changing its is_visible attribute and updating sysfs group.
+ *
+ * Returns 0 on success or error code on failure.
+ */
+int hv_remove_ring_sysfs(struct vmbus_channel *channel)
+{
+	struct kobject *kobj = &channel->kobj;
+	int ret;
+
+	channel->ring_sysfs_visible = false;
+	ret = sysfs_update_group(kobj, &vmbus_chan_group);
+	channel->mmap_ring_buffer = NULL;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hv_remove_ring_sysfs);
+
 /*
  * vmbus_add_channel_kobj - setup a sub-directory under device/channels
  */