cxl/mem: Fix synchronization mechanism for device removal vs ioctl operations

The percpu_ref to gate whether cxl_memdev_ioctl() is free to use the
driver context (@cxlm) to issue I/O is overkill, implemented incorrectly
(missing a device reference before accessing the percpu_ref), and the
complexities of shutting down a percpu_ref contributed to a bug in the
error unwind in cxl_mem_add_memdev() (missing put_device() to be fixed
separately).

Use an rwsem to explicitly synchronize the usage of cxlmd->cxlm, and add
the missing reference counting for cxlmd in cxl_memdev_open() and
cxl_memdev_release_file().

Fixes: b39cb1052a ("cxl/mem: Register CXL memX devices")
Reported-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/161728759948.2474381.17481500816783671817.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
This commit is contained in:
Dan Williams 2021-04-01 07:33:19 -07:00
parent 6eff572193
commit 5877515912
1 changed files with 52 additions and 49 deletions

View File

@ -96,21 +96,18 @@ struct mbox_cmd {
* @dev: driver core device object
* @cdev: char dev core object for ioctl operations
* @cxlm: pointer to the parent device driver data
* @ops_active: active user of @cxlm in ops handlers
* @ops_dead: completion when all @cxlm ops users have exited
* @id: id number of this memdev instance.
*/
struct cxl_memdev {
struct device dev;
struct cdev cdev;
struct cxl_mem *cxlm;
struct percpu_ref ops_active;
struct completion ops_dead;
int id;
};
static int cxl_mem_major;
static DEFINE_IDA(cxl_memdev_ida);
static DECLARE_RWSEM(cxl_memdev_rwsem);
static struct dentry *cxl_debugfs;
static bool cxl_raw_allow_all;
@ -776,26 +773,43 @@ static long __cxl_memdev_ioctl(struct cxl_memdev *cxlmd, unsigned int cmd,
static long cxl_memdev_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
struct cxl_memdev *cxlmd;
struct inode *inode;
int rc = -ENOTTY;
struct cxl_memdev *cxlmd = file->private_data;
int rc = -ENXIO;
inode = file_inode(file);
cxlmd = container_of(inode->i_cdev, typeof(*cxlmd), cdev);
if (!percpu_ref_tryget_live(&cxlmd->ops_active))
return -ENXIO;
rc = __cxl_memdev_ioctl(cxlmd, cmd, arg);
percpu_ref_put(&cxlmd->ops_active);
down_read(&cxl_memdev_rwsem);
if (cxlmd->cxlm)
rc = __cxl_memdev_ioctl(cxlmd, cmd, arg);
up_read(&cxl_memdev_rwsem);
return rc;
}
static int cxl_memdev_open(struct inode *inode, struct file *file)
{
struct cxl_memdev *cxlmd =
container_of(inode->i_cdev, typeof(*cxlmd), cdev);
get_device(&cxlmd->dev);
file->private_data = cxlmd;
return 0;
}
static int cxl_memdev_release_file(struct inode *inode, struct file *file)
{
struct cxl_memdev *cxlmd =
container_of(inode->i_cdev, typeof(*cxlmd), cdev);
put_device(&cxlmd->dev);
return 0;
}
static const struct file_operations cxl_memdev_fops = {
.owner = THIS_MODULE,
.unlocked_ioctl = cxl_memdev_ioctl,
.open = cxl_memdev_open,
.release = cxl_memdev_release_file,
.compat_ioctl = compat_ptr_ioctl,
.llseek = noop_llseek,
};
@ -1049,7 +1063,6 @@ static void cxl_memdev_release(struct device *dev)
{
struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
percpu_ref_exit(&cxlmd->ops_active);
ida_free(&cxl_memdev_ida, cxlmd->id);
kfree(cxlmd);
}
@ -1150,26 +1163,23 @@ static const struct device_type cxl_memdev_type = {
.groups = cxl_memdev_attribute_groups,
};
static void cxlmdev_unregister(void *_cxlmd)
static void cxl_memdev_shutdown(struct cxl_memdev *cxlmd)
{
down_write(&cxl_memdev_rwsem);
cxlmd->cxlm = NULL;
up_write(&cxl_memdev_rwsem);
}
static void cxl_memdev_unregister(void *_cxlmd)
{
struct cxl_memdev *cxlmd = _cxlmd;
struct device *dev = &cxlmd->dev;
percpu_ref_kill(&cxlmd->ops_active);
cdev_device_del(&cxlmd->cdev, dev);
wait_for_completion(&cxlmd->ops_dead);
cxlmd->cxlm = NULL;
cxl_memdev_shutdown(cxlmd);
put_device(dev);
}
static void cxlmdev_ops_active_release(struct percpu_ref *ref)
{
struct cxl_memdev *cxlmd =
container_of(ref, typeof(*cxlmd), ops_active);
complete(&cxlmd->ops_dead);
}
static int cxl_mem_add_memdev(struct cxl_mem *cxlm)
{
struct pci_dev *pdev = cxlm->pdev;
@ -1181,17 +1191,6 @@ static int cxl_mem_add_memdev(struct cxl_mem *cxlm)
cxlmd = kzalloc(sizeof(*cxlmd), GFP_KERNEL);
if (!cxlmd)
return -ENOMEM;
init_completion(&cxlmd->ops_dead);
/*
* @cxlm is deallocated when the driver unbinds so operations
* that are using it need to hold a live reference.
*/
cxlmd->cxlm = cxlm;
rc = percpu_ref_init(&cxlmd->ops_active, cxlmdev_ops_active_release, 0,
GFP_KERNEL);
if (rc)
goto err_ref;
rc = ida_alloc_range(&cxl_memdev_ida, 0, CXL_MEM_MAX_DEVS, GFP_KERNEL);
if (rc < 0)
@ -1209,23 +1208,27 @@ static int cxl_mem_add_memdev(struct cxl_mem *cxlm)
cdev = &cxlmd->cdev;
cdev_init(cdev, &cxl_memdev_fops);
/*
* Activate ioctl operations, no cxl_memdev_rwsem manipulation
* needed as this is ordered with cdev_add() publishing the device.
*/
cxlmd->cxlm = cxlm;
rc = cdev_device_add(cdev, dev);
if (rc)
goto err_add;
return devm_add_action_or_reset(dev->parent, cxlmdev_unregister, cxlmd);
return devm_add_action_or_reset(dev->parent, cxl_memdev_unregister,
cxlmd);
err_add:
/*
* The cdev was briefly live, shutdown any ioctl operations that
* saw that state.
*/
cxl_memdev_shutdown(cxlmd);
ida_free(&cxl_memdev_ida, cxlmd->id);
err_id:
/*
* Theoretically userspace could have already entered the fops,
* so flush ops_active.
*/
percpu_ref_kill(&cxlmd->ops_active);
wait_for_completion(&cxlmd->ops_dead);
percpu_ref_exit(&cxlmd->ops_active);
err_ref:
kfree(cxlmd);
return rc;