As Miklos reported and suggested:
This pattern repeats two times in trace_uprobe.c and in
kernel/events/core.c as well:
ret = kern_path(filename, LOOKUP_FOLLOW, &path);
if (ret)
goto fail_address_parse;
inode = igrab(d_inode(path.dentry));
path_put(&path);
And it's wrong. You can only hold a reference to the inode if you
have an active ref to the superblock as well (which is normally
through path.mnt) or holding s_umount.
This way unmounting the containing filesystem while the tracepoint is
active will give you the "VFS: Busy inodes after unmount..." message
and a crash when the inode is finally put.
Solution: store path instead of inode.
This patch fixes the issue in kernel/event/core.c.
NOTE: Based on my understanding, perf_addr_filter only supports intel_pt.
However, my test system doesn't support address filtering (or I made a
mistake?). Therefore, I have NOT tested this patch.
Could someone please help test it?
Fixes: 375637bc5249 ("perf/core: Introduce address range filtering")
Cc: Alexander Shishkin <alexander.shish...@linux.intel.com>
Cc: Ingo Molnar <mi...@redhat.com>
Cc: Peter Zijlstra (Intel) <pet...@infradead.org>
Reported-by: Miklos Szeredi <mik...@szeredi.hu>
Signed-off-by: Song Liu <songliubrav...@fb.com>
---
arch/x86/events/intel/pt.c | 4 ++--
include/linux/perf_event.h | 2 +-
kernel/events/core.c | 21 +++++++++------------
3 files changed, 12 insertions(+), 15 deletions(-)
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 3b99394..8d016ce 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1194,7 +1194,7 @@ static int pt_event_addr_filters_validate(struct
list_head *filters)
filter->action == PERF_ADDR_FILTER_ACTION_START)
return -EOPNOTSUPP;
- if (!filter->inode) {
+ if (!filter->path.dentry) {
if (!valid_kernel_ip(filter->offset))
return -EINVAL;
@@ -1221,7 +1221,7 @@ static void pt_event_addr_filters_sync(struct perf_event
*event)
return;
list_for_each_entry(filter, &head->list, entry) {
- if (filter->inode && !offs[range]) {
+ if (filter->path.dentry && !offs[range]) {
msr_a = msr_b = 0;
} else {
/* apply the offset */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e71e99e..88922d8 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -467,7 +467,7 @@ enum perf_addr_filter_action_t {
*/
struct perf_addr_filter {
struct list_head entry;
- struct inode *inode;
+ struct path path;
unsigned long offset;
unsigned long size;
enum perf_addr_filter_action_t action;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d7af828..7d711ed 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6668,7 +6668,7 @@ static void perf_event_addr_filters_exec(struct
perf_event *event, void *data)
raw_spin_lock_irqsave(&ifh->lock, flags);
list_for_each_entry(filter, &ifh->list, entry) {
- if (filter->inode) {
+ if (filter->path.dentry) {
event->addr_filters_offs[count] = 0;
restart++;
}
@@ -7333,7 +7333,7 @@ static bool perf_addr_filter_match(struct
perf_addr_filter *filter,
struct file *file, unsigned long offset,
unsigned long size)
{
- if (filter->inode != file_inode(file))
+ if (d_inode(filter->path.dentry) != file_inode(file))
return false;
if (filter->offset > offset + size)
@@ -8674,8 +8674,7 @@ static void free_filters_list(struct list_head *filters)
struct perf_addr_filter *filter, *iter;
list_for_each_entry_safe(filter, iter, filters, entry) {
- if (filter->inode)
- iput(filter->inode);
+ path_put(&filter->path);
list_del(&filter->entry);
kfree(filter);
}
@@ -8772,7 +8771,7 @@ static void perf_event_addr_filters_apply(struct
perf_event *event)
* Adjust base offset if the filter is associated to a binary
* that needs to be mapped:
*/
- if (filter->inode)
+ if (filter->path.dentry)
event->addr_filters_offs[count] =
perf_addr_filter_apply(filter, mm);
@@ -8846,7 +8845,6 @@ perf_event_parse_addr_filter(struct perf_event *event,
char *fstr,
{
struct perf_addr_filter *filter = NULL;
char *start, *orig, *filename = NULL;
- struct path path;
substring_t args[MAX_OPT_ARGS];
int state = IF_STATE_ACTION, token;
unsigned int kernel = 0;
@@ -8959,19 +8957,18 @@ perf_event_parse_addr_filter(struct perf_event *event,
char *fstr,
goto fail_free_name;
/* look up the path and grab its inode */
- ret = kern_path(filename, LOOKUP_FOLLOW, &path);
+ ret = kern_path(filename, LOOKUP_FOLLOW,
+ &filter->path);
if (ret)
goto fail_free_name;
- filter->inode = igrab(d_inode(path.dentry));
- path_put(&path);
kfree(filename);
filename = NULL;
ret = -EINVAL;
- if (!filter->inode ||
- !S_ISREG(filter->inode->i_mode))
- /* free_filters_list() will iput() */
+ if (!filter->path.dentry ||
+ !S_ISREG(d_inode(filter->path.dentry)
+ ->i_mode))
goto fail;
event->addr_filters.nr_file_filters++;
--
2.9.5
