dmabuf: Add the capability to expose DMA-BUF stats in sysfs

Overview
========
The patch adds DMA-BUF statistics to /sys/kernel/dmabuf/buffers. It
allows statistics to be enabled for each DMA-BUF in sysfs by enabling
the config CONFIG_DMABUF_SYSFS_STATS.

The following stats will be exposed by the interface:

/sys/kernel/dmabuf/buffers/<inode_number>/exporter_name
/sys/kernel/dmabuf/buffers/<inode_number>/size
/sys/kernel/dmabuf/buffers/<inode_number>/attachments/<attach_uid>/device
/sys/kernel/dmabuf/buffers/<inode_number>/attachments/<attach_uid>/map_counter

The inode_number is unique for each DMA-BUF and was added earlier [1]
in order to allow userspace to track DMA-BUF usage across different
processes.

Use Cases
=========
The interface provides a way to gather DMA-BUF per-buffer statistics
from production devices. These statistics will be used to derive DMA-BUF
per-exporter stats and per-device usage stats for Android Bug reports.
The corresponding userspace changes can be found at [2].
Telemetry tools will also capture this information(along with other
memory metrics) periodically as well as on important events like a
foreground app kill (which might have been triggered by Low Memory
Killer). It will also contribute to provide a snapshot of the system
memory usage on other events such as OOM kills and Application Not
Responding events.

Background
==========
Currently, there are two existing interfaces that provide information
about DMA-BUFs.
1) /sys/kernel/debug/dma_buf/bufinfo
debugfs is however unsuitable to be mounted in production systems and
cannot be considered as an alternative to the sysfs interface being
proposed.
2) proc/<pid>/fdinfo/<fd>
The proc/<pid>/fdinfo/<fd> files expose information about DMA-BUF fds.
However, the existing procfs interfaces can only provide information
about the buffers for which processes hold fds or have the buffers
mmapped into their address space. Since the procfs interfaces alone
cannot provide a full picture of all DMA-BUFs in the system, there is
the need for an alternate interface to provide this information on
production systems.

The patch contains the following major improvements over v1:
1) Each attachment is represented by its own directory to allow creating
a symlink to the importing device and to also provide room for future
expansion.
2) The number of distinct mappings of each attachment is exposed in a
separate file.
3) The per-buffer statistics are now in /sys/kernel/dmabuf/buffers
inorder to make the interface expandable in future.

All of the improvements above are based on suggestions/feedback from
Daniel Vetter and Christian König.

A shell script that can be run on a classic Linux environment to read
out the DMA-BUF statistics can be found at [3](suggested by John
Stultz).

[1]: https://lore.kernel.org/patchwork/patch/1088791/
[2]: https://android-review.googlesource.com/q/topic:%22dmabuf-sysfs%22+(status:open%20OR%20status:merged)
[3]: https://android-review.googlesource.com/c/platform/system/memory/libmeminfo/+/1549734

Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Hridya Valsaraju <hridya@google.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210603214758.2955251-1-hridya@google.com

1 files changed, 37 insertions, 0 deletions

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 511fe0d217a0..d0121402c58c 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -29,6 +29,8 @@
 #include <uapi/linux/dma-buf.h>
 #include <uapi/linux/magic.h>
 
+#include "dma-buf-sysfs-stats.h"
+
 static inline int is_dma_buf_file(struct file *);
 
 struct dma_buf_list {
@@ -79,6 +81,7 @@ static void dma_buf_release(struct dentry *dentry)
 	if (dmabuf->resv == (struct dma_resv *)&dmabuf[1])
 		dma_resv_fini(dmabuf->resv);
 
+	dma_buf_stats_teardown(dmabuf);
 	module_put(dmabuf->owner);
 	kfree(dmabuf->name);
 	kfree(dmabuf);
@@ -580,6 +583,10 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
 	file->f_mode |= FMODE_LSEEK;
 	dmabuf->file = file;
 
+	ret = dma_buf_stats_setup(dmabuf);
+	if (ret)
+		goto err_sysfs;
+
 	mutex_init(&dmabuf->lock);
 	INIT_LIST_HEAD(&dmabuf->attachments);
 
@@ -589,6 +596,14 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
 
 	return dmabuf;
 
+err_sysfs:
+	/*
+	 * Set file->f_path.dentry->d_fsdata to NULL so that when
+	 * dma_buf_release() gets invoked by dentry_ops, it exits
+	 * early before calling the release() dma_buf op.
+	 */
+	file->f_path.dentry->d_fsdata = NULL;
+	fput(file);
 err_dmabuf:
 	kfree(dmabuf);
 err_module:
@@ -723,6 +738,7 @@ dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev,
 {
 	struct dma_buf_attachment *attach;
 	int ret;
+	unsigned int attach_uid;
 
 	if (WARN_ON(!dmabuf || !dev))
 		return ERR_PTR(-EINVAL);
@@ -748,8 +764,13 @@ dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev,
 	}
 	dma_resv_lock(dmabuf->resv, NULL);
 	list_add(&attach->node, &dmabuf->attachments);
+	attach_uid = dma_buf_update_attach_uid(dmabuf);
 	dma_resv_unlock(dmabuf->resv);
 
+	ret = dma_buf_attach_stats_setup(attach, attach_uid);
+	if (ret)
+		goto err_sysfs;
+
 	/* When either the importer or the exporter can't handle dynamic
 	 * mappings we cache the mapping here to avoid issues with the
 	 * reservation object lock.
@@ -776,6 +797,7 @@ dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev,
 			dma_resv_unlock(attach->dmabuf->resv);
 		attach->sgt = sgt;
 		attach->dir = DMA_BIDIRECTIONAL;
+		dma_buf_update_attachment_map_count(attach, 1 /* delta */);
 	}
 
 	return attach;
@@ -792,6 +814,7 @@ err_unlock:
 	if (dma_buf_is_dynamic(attach->dmabuf))
 		dma_resv_unlock(attach->dmabuf->resv);
 
+err_sysfs:
 	dma_buf_detach(dmabuf, attach);
 	return ERR_PTR(ret);
 }
@@ -841,6 +864,7 @@ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach)
 			dma_resv_lock(attach->dmabuf->resv, NULL);
 
 		__unmap_dma_buf(attach, attach->sgt, attach->dir);
+		dma_buf_update_attachment_map_count(attach, -1 /* delta */);
 
 		if (dma_buf_is_dynamic(attach->dmabuf)) {
 			dmabuf->ops->unpin(attach);
@@ -854,6 +878,7 @@ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach)
 	if (dmabuf->ops->detach)
 		dmabuf->ops->detach(dmabuf, attach);
 
+	dma_buf_attach_stats_teardown(attach);
 	kfree(attach);
 }
 EXPORT_SYMBOL_GPL(dma_buf_detach);
@@ -993,6 +1018,9 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 	}
 #endif /* CONFIG_DMA_API_DEBUG */
 
+	if (!IS_ERR(sg_table))
+		dma_buf_update_attachment_map_count(attach, 1 /* delta */);
+
 	return sg_table;
 }
 EXPORT_SYMBOL_GPL(dma_buf_map_attachment);
@@ -1030,6 +1058,8 @@ void dma_buf_unmap_attachment(struct dma_buf_attachment *attach,
 	if (dma_buf_is_dynamic(attach->dmabuf) &&
 	    !IS_ENABLED(CONFIG_DMABUF_MOVE_NOTIFY))
 		dma_buf_unpin(attach);
+
+	dma_buf_update_attachment_map_count(attach, -1 /* delta */);
 }
 EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment);
 
@@ -1469,6 +1499,12 @@ static inline void dma_buf_uninit_debugfs(void)
 
 static int __init dma_buf_init(void)
 {
+	int ret;
+
+	ret = dma_buf_init_sysfs_statistics();
+	if (ret)
+		return ret;
+
 	dma_buf_mnt = kern_mount(&dma_buf_fs_type);
 	if (IS_ERR(dma_buf_mnt))
 		return PTR_ERR(dma_buf_mnt);
@@ -1484,5 +1520,6 @@ static void __exit dma_buf_deinit(void)
 {
 	dma_buf_uninit_debugfs();
 	kern_unmount(dma_buf_mnt);
+	dma_buf_uninit_sysfs_statistics();
 }
 __exitcall(dma_buf_deinit);