Am 16.05.22 um 20:08 schrieb T.J. Mercier:
On Mon, May 16, 2022 at 10:20 AM Christian König
<christian.koenig@xxxxxxx> wrote:
Am 16.05.22 um 19:13 schrieb T.J. Mercier:
Recently, we noticed an issue where a process went into direct reclaim
while holding the kernfs rw semaphore for sysfs in write (exclusive)
mode. This caused processes who were doing DMA-BUF exports and releases
to go into uninterruptible sleep since they needed to acquire the same
semaphore for the DMA-BUF sysfs entry creation/deletion. In order to avoid
blocking DMA-BUF export for an indeterminate amount of time while
another process is holding the sysfs rw semaphore in exclusive mode,
this patch moves the per-buffer sysfs file creation to the default work
queue. Note that this can lead to a short-term inaccuracy in the dmabuf
sysfs statistics, but this is a tradeoff to prevent the hot path from
being blocked. A work_struct is added to dma_buf to achieve this, but as
it is unioned with the kobject in the sysfs_entry, dma_buf does not
increase in size.
I'm still not very keen of this approach as it strongly feels like we
are working around shortcoming somewhere else.
My read of the thread for the last version is that we're running into
a situation where sysfs is getting used for something it wasn't
originally intended for, but we're also stuck with this sysfs
functionality for dmabufs.
Fixes: bdb8d06dfefd ("dmabuf: Add the capability to expose DMA-BUF stats in sysfs")
Originally-by: Hridya Valsaraju <hridya@xxxxxxxxxx>
Signed-off-by: T.J. Mercier <tjmercier@xxxxxxxxxx>
---
See the originally submitted patch by Hridya Valsaraju here:
https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flkml.org%2Flkml%2F2022%2F1%2F4%2F1066&data=05%7C01%7Cchristian.koenig%40amd.com%7C794614324d114880a25508da37672e4b%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637883213566903705%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=bGlA2FeubfSeL5XDHYyWMZqUXfScoCphZjjK4jrqQJs%3D&reserved=0
v2 changes:
- Defer only sysfs creation instead of creation and teardown per
Christian König
- Use a work queue instead of a kthread for deferred work per
Christian König
---
drivers/dma-buf/dma-buf-sysfs-stats.c | 56 ++++++++++++++++++++-------
include/linux/dma-buf.h | 14 ++++++-
2 files changed, 54 insertions(+), 16 deletions(-)
diff --git a/drivers/dma-buf/dma-buf-sysfs-stats.c b/drivers/dma-buf/dma-buf-sysfs-stats.c
index 2bba0babcb62..67b0a298291c 100644
--- a/drivers/dma-buf/dma-buf-sysfs-stats.c
+++ b/drivers/dma-buf/dma-buf-sysfs-stats.c
@@ -11,6 +11,7 @@
#include <linux/printk.h>
#include <linux/slab.h>
#include <linux/sysfs.h>
+#include <linux/workqueue.h>
#include "dma-buf-sysfs-stats.h"
@@ -168,10 +169,46 @@ void dma_buf_uninit_sysfs_statistics(void)
kset_unregister(dma_buf_stats_kset);
}
+static void sysfs_add_workfn(struct work_struct *work)
+{
+ struct dma_buf_sysfs_entry *sysfs_entry =
+ container_of(work, struct dma_buf_sysfs_entry, sysfs_add_work);
+ struct dma_buf *dmabuf = sysfs_entry->dmabuf;
+
+ /*
+ * A dmabuf is ref-counted via its file member. If this handler holds the only
+ * reference to the dmabuf, there is no need for sysfs kobject creation. This is an
+ * optimization and a race; when the reference count drops to 1 immediately after
+ * this check it is not harmful as the sysfs entry will still get cleaned up in
+ * dma_buf_stats_teardown, which won't get called until the final dmabuf reference
+ * is released, and that can't happen until the end of this function.
+ */
+ if (file_count(dmabuf->file) > 1) {
Please completely drop that. I see absolutely no justification for this
additional complexity.
This case gets hit around 5% of the time in my testing so the else is
not a completely unused branch.
Well I can only repeat myself: This means that your userspace is
severely broken!
DMA-buf are meant to be long living objects and when you create and
destroy it faster than a work item can create the sysfs entries than
there is some serious design issue here.
My suspicion is that your IOCTL to create the DMA-buf is somehow
interrupted/aborted after it was already exported which results in it's
immediate destruction.
Regards,
Christian.
It's only 3 extra lines of actual
code. I'd prefer to keep it, but I'll remove it to reduce complexity.
This means doing work that we know is useless some of the time, and
adding contention for a global kernfs lock which this patch is aimed
at avoiding (on the hot path), but at least that work is on a worker
thread with this patch.
+ /*
+ * kobject_init_and_add expects kobject to be zero-filled, but we have populated it
+ * (the sysfs_add_work union member) to trigger this work function.
+ */
+ memset(&dmabuf->sysfs_entry->kobj, 0, sizeof(dmabuf->sysfs_entry->kobj));
+ dmabuf->sysfs_entry->kobj.kset = dma_buf_per_buffer_stats_kset;
+ if (kobject_init_and_add(&dmabuf->sysfs_entry->kobj, &dma_buf_ktype, NULL,
+ "%lu", file_inode(dmabuf->file)->i_ino)) {
+ kobject_put(&dmabuf->sysfs_entry->kobj);
+ dmabuf->sysfs_entry = NULL;
+ }
+ } else {
+ /*
+ * Free the sysfs_entry and reset the pointer so dma_buf_stats_teardown doesn't
+ * attempt to operate on it.
+ */
+ kfree(dmabuf->sysfs_entry);
+ dmabuf->sysfs_entry = NULL;
+ }
+ dma_buf_put(dmabuf);
+}
+
int dma_buf_stats_setup(struct dma_buf *dmabuf)
{
struct dma_buf_sysfs_entry *sysfs_entry;
- int ret;
if (!dmabuf || !dmabuf->file)
return -EINVAL;
@@ -181,25 +218,16 @@ int dma_buf_stats_setup(struct dma_buf *dmabuf)
return -EINVAL;
}
- sysfs_entry = kzalloc(sizeof(struct dma_buf_sysfs_entry), GFP_KERNEL);
+ sysfs_entry = kmalloc(sizeof(struct dma_buf_sysfs_entry), GFP_KERNEL);
if (!sysfs_entry)
return -ENOMEM;
- sysfs_entry->kobj.kset = dma_buf_per_buffer_stats_kset;
sysfs_entry->dmabuf = dmabuf;
-
dmabuf->sysfs_entry = sysfs_entry;
- /* create the directory for buffer stats */
- ret = kobject_init_and_add(&sysfs_entry->kobj, &dma_buf_ktype, NULL,
- "%lu", file_inode(dmabuf->file)->i_ino);
- if (ret)
- goto err_sysfs_dmabuf;
+ INIT_WORK(&dmabuf->sysfs_entry->sysfs_add_work, sysfs_add_workfn);
+ get_dma_buf(dmabuf); /* This reference will be dropped in sysfs_add_workfn. */
+ schedule_work(&dmabuf->sysfs_entry->sysfs_add_work);
return 0;
-
-err_sysfs_dmabuf:
- kobject_put(&sysfs_entry->kobj);
- dmabuf->sysfs_entry = NULL;
- return ret;
}
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 2097760e8e95..0200caa3c515 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -22,6 +22,7 @@
#include <linux/fs.h>
#include <linux/dma-fence.h>
#include <linux/wait.h>
+#include <linux/workqueue.h>
struct device;
struct dma_buf;
@@ -365,7 +366,7 @@ struct dma_buf {
*/
const char *name;
- /** @name_lock: Spinlock to protect name acces for read access. */
+ /** @name_lock: Spinlock to protect name access for read access. */
spinlock_t name_lock;
/**
@@ -441,6 +442,7 @@ struct dma_buf {
__poll_t active;
} cb_in, cb_out;
+
Those changes are unrelated.
I included it here because I thought it was bad form to submit a
typo-only patch. Will remove.
Regards,
Christian.
#ifdef CONFIG_DMABUF_SYSFS_STATS
/**
* @sysfs_entry:
@@ -449,7 +451,15 @@ struct dma_buf {
* `DMA-BUF statistics`_ for the uapi this enables.
*/
struct dma_buf_sysfs_entry {
- struct kobject kobj;
+ union {
+ struct kobject kobj;
+
+ /** @sysfs_add_work:
+ *
+ * For deferred sysfs kobject creation using a workqueue.
+ */
+ struct work_struct sysfs_add_work;
+ };
struct dma_buf *dmabuf;
} *sysfs_entry;
#endif
