* [PATCH 6.18.y 2/4] tracing: fprobe: use ftrace if CONFIG_DYNAMIC_FTRACE_WITH_ARGS
2026-05-21 12:58 ` [PATCH 6.18.y 1/4] tracing: fprobe: Remove unused local variable Sasha Levin
@ 2026-05-21 12:58 ` Sasha Levin
2026-05-21 12:58 ` [PATCH 6.18.y 3/4] tracing/fprobe: Avoid kcalloc() in rcu_read_lock section Sasha Levin
2026-05-21 12:58 ` [PATCH 6.18.y 4/4] tracing/fprobe: Check the same type fprobe on table as the unregistered one Sasha Levin
2 siblings, 0 replies; 5+ messages in thread
From: Sasha Levin @ 2026-05-21 12:58 UTC (permalink / raw)
To: stable; +Cc: Menglong Dong, Menglong Dong, Masami Hiramatsu (Google),
Sasha Levin
From: Menglong Dong <menglong8.dong@gmail.com>
[ Upstream commit cd06078a38aaedfebbf8fa0c009da0f99f4473fb ]
For now, we will use ftrace for the fprobe if fp->exit_handler not exists
and CONFIG_DYNAMIC_FTRACE_WITH_REGS is enabled.
However, CONFIG_DYNAMIC_FTRACE_WITH_REGS is not supported by some arch,
such as arm. What we need in the fprobe is the function arguments, so we
can use ftrace for fprobe if CONFIG_DYNAMIC_FTRACE_WITH_ARGS is enabled.
Therefore, use ftrace if CONFIG_DYNAMIC_FTRACE_WITH_REGS or
CONFIG_DYNAMIC_FTRACE_WITH_ARGS enabled.
Link: https://lore.kernel.org/all/20251103063434.47388-1-dongml2@chinatelecom.cn/
Signed-off-by: Menglong Dong <dongml2@chinatelecom.cn>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Stable-dep-of: 0ac0058a74ac ("tracing/fprobe: Check the same type fprobe on table as the unregistered one")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
kernel/trace/fprobe.c | 32 ++++++++++++++++++++++----------
1 file changed, 22 insertions(+), 10 deletions(-)
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 51003d85933d9..574f2886cc9e3 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -45,6 +45,7 @@
static struct hlist_head fprobe_table[FPROBE_TABLE_SIZE];
static struct rhltable fprobe_ip_table;
static DEFINE_MUTEX(fprobe_mutex);
+static struct fgraph_ops fprobe_graph_ops;
static u32 fprobe_node_hashfn(const void *data, u32 len, u32 seed)
{
@@ -259,7 +260,7 @@ static inline int __fprobe_kprobe_handler(unsigned long ip, unsigned long parent
return ret;
}
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#if defined(CONFIG_DYNAMIC_FTRACE_WITH_ARGS) || defined(CONFIG_DYNAMIC_FTRACE_WITH_REGS)
/* ftrace_ops callback, this processes fprobes which have only entry_handler. */
static void fprobe_ftrace_entry(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *ops, struct ftrace_regs *fregs)
@@ -300,7 +301,7 @@ NOKPROBE_SYMBOL(fprobe_ftrace_entry);
static struct ftrace_ops fprobe_ftrace_ops = {
.func = fprobe_ftrace_entry,
- .flags = FTRACE_OPS_FL_SAVE_REGS,
+ .flags = FTRACE_OPS_FL_SAVE_ARGS,
};
static int fprobe_ftrace_active;
@@ -341,6 +342,15 @@ static bool fprobe_is_ftrace(struct fprobe *fp)
{
return !fp->exit_handler;
}
+
+#ifdef CONFIG_MODULES
+static void fprobe_set_ips(unsigned long *ips, unsigned int cnt, int remove,
+ int reset)
+{
+ ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, remove, reset);
+ ftrace_set_filter_ips(&fprobe_ftrace_ops, ips, cnt, remove, reset);
+}
+#endif
#else
static int fprobe_ftrace_add_ips(unsigned long *addrs, int num)
{
@@ -355,7 +365,15 @@ static bool fprobe_is_ftrace(struct fprobe *fp)
{
return false;
}
+
+#ifdef CONFIG_MODULES
+static void fprobe_set_ips(unsigned long *ips, unsigned int cnt, int remove,
+ int reset)
+{
+ ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, remove, reset);
+}
#endif
+#endif /* !CONFIG_DYNAMIC_FTRACE_WITH_ARGS && !CONFIG_DYNAMIC_FTRACE_WITH_REGS */
/* fgraph_ops callback, this processes fprobes which have exit_handler. */
static int fprobe_fgraph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops,
@@ -601,14 +619,8 @@ static int fprobe_module_callback(struct notifier_block *nb,
} while (node == ERR_PTR(-EAGAIN));
rhashtable_walk_exit(&iter);
- if (alist.index > 0) {
- ftrace_set_filter_ips(&fprobe_graph_ops.ops,
- alist.addrs, alist.index, 1, 0);
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
- ftrace_set_filter_ips(&fprobe_ftrace_ops,
- alist.addrs, alist.index, 1, 0);
-#endif
- }
+ if (alist.index > 0)
+ fprobe_set_ips(alist.addrs, alist.index, 1, 0);
mutex_unlock(&fprobe_mutex);
kfree(alist.addrs);
--
2.53.0
^ permalink raw reply related [flat|nested] 5+ messages in thread* [PATCH 6.18.y 3/4] tracing/fprobe: Avoid kcalloc() in rcu_read_lock section
2026-05-21 12:58 ` [PATCH 6.18.y 1/4] tracing: fprobe: Remove unused local variable Sasha Levin
2026-05-21 12:58 ` [PATCH 6.18.y 2/4] tracing: fprobe: use ftrace if CONFIG_DYNAMIC_FTRACE_WITH_ARGS Sasha Levin
@ 2026-05-21 12:58 ` Sasha Levin
2026-05-21 12:58 ` [PATCH 6.18.y 4/4] tracing/fprobe: Check the same type fprobe on table as the unregistered one Sasha Levin
2 siblings, 0 replies; 5+ messages in thread
From: Sasha Levin @ 2026-05-21 12:58 UTC (permalink / raw)
To: stable; +Cc: Masami Hiramatsu (Google), Sasha Levin
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
[ Upstream commit aa72812b49104bb5a38272fc9541feb62ca6fd32 ]
fprobe_remove_node_in_module() is called under RCU read locked, but
this invokes kcalloc() if there are more than 8 fprobes installed
on the module. Sashiko warns it because kcalloc() can sleep [1].
[1] https://sashiko.dev/#/patchset/177552432201.853249.5125045538812833325.stgit%40mhiramat.tok.corp.google.com
To fix this issue, expand the batch size to 128 and do not expand
the fprobe_addr_list, but just cancel walking on fprobe_ip_table,
update fgraph/ftrace_ops and retry the loop again.
Link: https://lore.kernel.org/all/177669367206.132053.1493637946869032744.stgit@mhiramat.tok.corp.google.com/
Fixes: 0de4c70d04a4 ("tracing: fprobe: use rhltable for fprobe_ip_table")
Cc: stable@vger.kernel.org
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Stable-dep-of: 0ac0058a74ac ("tracing/fprobe: Check the same type fprobe on table as the unregistered one")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
kernel/trace/fprobe.c | 92 +++++++++++++++++++++----------------------
1 file changed, 45 insertions(+), 47 deletions(-)
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 574f2886cc9e3..37a4352efb4da 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -344,11 +344,10 @@ static bool fprobe_is_ftrace(struct fprobe *fp)
}
#ifdef CONFIG_MODULES
-static void fprobe_set_ips(unsigned long *ips, unsigned int cnt, int remove,
- int reset)
+static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt)
{
- ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, remove, reset);
- ftrace_set_filter_ips(&fprobe_ftrace_ops, ips, cnt, remove, reset);
+ ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, 1, 0);
+ ftrace_set_filter_ips(&fprobe_ftrace_ops, ips, cnt, 1, 0);
}
#endif
#else
@@ -367,10 +366,9 @@ static bool fprobe_is_ftrace(struct fprobe *fp)
}
#ifdef CONFIG_MODULES
-static void fprobe_set_ips(unsigned long *ips, unsigned int cnt, int remove,
- int reset)
+static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt)
{
- ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, remove, reset);
+ ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, 1, 0);
}
#endif
#endif /* !CONFIG_DYNAMIC_FTRACE_WITH_ARGS && !CONFIG_DYNAMIC_FTRACE_WITH_REGS */
@@ -543,7 +541,7 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num)
#ifdef CONFIG_MODULES
-#define FPROBE_IPS_BATCH_INIT 8
+#define FPROBE_IPS_BATCH_INIT 128
/* instruction pointer address list */
struct fprobe_addr_list {
int index;
@@ -551,45 +549,24 @@ struct fprobe_addr_list {
unsigned long *addrs;
};
-static int fprobe_addr_list_add(struct fprobe_addr_list *alist, unsigned long addr)
+static int fprobe_remove_node_in_module(struct module *mod, struct fprobe_hlist_node *node,
+ struct fprobe_addr_list *alist)
{
- unsigned long *addrs;
-
- /* Previously we failed to expand the list. */
- if (alist->index == alist->size)
- return -ENOSPC;
-
- alist->addrs[alist->index++] = addr;
- if (alist->index < alist->size)
+ if (!within_module(node->addr, mod))
return 0;
- /* Expand the address list */
- addrs = kcalloc(alist->size * 2, sizeof(*addrs), GFP_KERNEL);
- if (!addrs)
- return -ENOMEM;
-
- memcpy(addrs, alist->addrs, alist->size * sizeof(*addrs));
- alist->size *= 2;
- kfree(alist->addrs);
- alist->addrs = addrs;
+ if (delete_fprobe_node(node))
+ return 0;
+ /* If no address list is available, we can't track this address. */
+ if (!alist->addrs)
+ return 0;
+ alist->addrs[alist->index++] = node->addr;
+ if (alist->index == alist->size)
+ return -ENOSPC;
return 0;
}
-static void fprobe_remove_node_in_module(struct module *mod, struct fprobe_hlist_node *node,
- struct fprobe_addr_list *alist)
-{
- if (!within_module(node->addr, mod))
- return;
- if (delete_fprobe_node(node))
- return;
- /*
- * If failed to update alist, just continue to update hlist.
- * Therefore, at list user handler will not hit anymore.
- */
- fprobe_addr_list_add(alist, node->addr);
-}
-
/* Handle module unloading to manage fprobe_ip_table. */
static int fprobe_module_callback(struct notifier_block *nb,
unsigned long val, void *data)
@@ -598,29 +575,50 @@ static int fprobe_module_callback(struct notifier_block *nb,
struct fprobe_hlist_node *node;
struct rhashtable_iter iter;
struct module *mod = data;
+ bool retry;
if (val != MODULE_STATE_GOING)
return NOTIFY_DONE;
alist.addrs = kcalloc(alist.size, sizeof(*alist.addrs), GFP_KERNEL);
- /* If failed to alloc memory, we can not remove ips from hash. */
- if (!alist.addrs)
- return NOTIFY_DONE;
+ /*
+ * If failed to alloc memory, ftrace_ops will not be able to remove ips from
+ * hash, but we can still remove nodes from fprobe_ip_table, so we can avoid
+ * the potential wrong callback. So just print a warning here and try to
+ * continue without address list.
+ */
+ WARN_ONCE(!alist.addrs,
+ "Failed to allocate memory for fprobe_addr_list, ftrace_ops will not be updated");
mutex_lock(&fprobe_mutex);
+again:
+ retry = false;
+ alist.index = 0;
rhltable_walk_enter(&fprobe_ip_table, &iter);
do {
rhashtable_walk_start(&iter);
while ((node = rhashtable_walk_next(&iter)) && !IS_ERR(node))
- fprobe_remove_node_in_module(mod, node, &alist);
+ if (fprobe_remove_node_in_module(mod, node, &alist) < 0) {
+ retry = true;
+ break;
+ }
rhashtable_walk_stop(&iter);
- } while (node == ERR_PTR(-EAGAIN));
+ } while (node == ERR_PTR(-EAGAIN) && !retry);
rhashtable_walk_exit(&iter);
+ /* Remove any ips from hash table(s) */
+ if (alist.index > 0) {
+ fprobe_remove_ips(alist.addrs, alist.index);
+ /*
+ * If we break rhashtable walk loop except for -EAGAIN, we need
+ * to restart looping from start for safety. Anyway, this is
+ * not a hotpath.
+ */
+ if (retry)
+ goto again;
+ }
- if (alist.index > 0)
- fprobe_set_ips(alist.addrs, alist.index, 1, 0);
mutex_unlock(&fprobe_mutex);
kfree(alist.addrs);
--
2.53.0
^ permalink raw reply related [flat|nested] 5+ messages in thread* [PATCH 6.18.y 4/4] tracing/fprobe: Check the same type fprobe on table as the unregistered one
2026-05-21 12:58 ` [PATCH 6.18.y 1/4] tracing: fprobe: Remove unused local variable Sasha Levin
2026-05-21 12:58 ` [PATCH 6.18.y 2/4] tracing: fprobe: use ftrace if CONFIG_DYNAMIC_FTRACE_WITH_ARGS Sasha Levin
2026-05-21 12:58 ` [PATCH 6.18.y 3/4] tracing/fprobe: Avoid kcalloc() in rcu_read_lock section Sasha Levin
@ 2026-05-21 12:58 ` Sasha Levin
2 siblings, 0 replies; 5+ messages in thread
From: Sasha Levin @ 2026-05-21 12:58 UTC (permalink / raw)
To: stable; +Cc: Masami Hiramatsu (Google), Sasha Levin
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
[ Upstream commit 0ac0058a74ac5765c7ce09ea630f4fdeaf4d80fa ]
Commit 2c67dc457bc6 ("tracing: fprobe: optimization for entry only case")
introduced a different ftrace_ops for entry-only fprobes.
However, when unregistering an fprobe, the kernel only checks if another
fprobe exists at the same address, without checking which type of fprobe
it is.
If different fprobes are registered at the same address, the same address
will be registered in both fgraph_ops and ftrace_ops, but only one of
them will be deleted when unregistering. (the one removed first will not
be deleted from the ops).
This results in junk entries remaining in either fgraph_ops or ftrace_ops.
For example:
=======
cd /sys/kernel/tracing
# 'Add entry and exit events on the same place'
echo 'f:event1 vfs_read' >> dynamic_events
echo 'f:event2 vfs_read%return' >> dynamic_events
# 'Enable both of them'
echo 1 > events/fprobes/enable
cat enabled_functions
vfs_read (2) ->arch_ftrace_ops_list_func+0x0/0x210
# 'Disable and remove exit event'
echo 0 > events/fprobes/event2/enable
echo -:event2 >> dynamic_events
# 'Disable and remove all events'
echo 0 > events/fprobes/enable
echo > dynamic_events
# 'Add another event'
echo 'f:event3 vfs_open%return' > dynamic_events
cat dynamic_events
f:fprobes/event3 vfs_open%return
echo 1 > events/fprobes/enable
cat enabled_functions
vfs_open (1) tramp: 0xffffffffa0001000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 subops: {ent:fprobe_fgraph_entry+0x0/0x620 ret:fprobe_return+0x0/0x150}
vfs_read (1) tramp: 0xffffffffa0001000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 subops: {ent:fprobe_fgraph_entry+0x0/0x620 ret:fprobe_return+0x0/0x150}
=======
As you can see, an entry for the vfs_read remains.
To fix this issue, when unregistering, the kernel should also check if
there is the same type of fprobes still exist at the same address, and
if not, delete its entry from either fgraph_ops or ftrace_ops.
Link: https://lore.kernel.org/all/177669367993.132053.10553046138528674802.stgit@mhiramat.tok.corp.google.com/
Fixes: 2c67dc457bc6 ("tracing: fprobe: optimization for entry only case")
Cc: stable@vger.kernel.org
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
kernel/trace/fprobe.c | 82 ++++++++++++++++++++++++++++++++++---------
1 file changed, 65 insertions(+), 17 deletions(-)
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 37a4352efb4da..6419c8d772731 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -92,11 +92,8 @@ static int insert_fprobe_node(struct fprobe_hlist_node *node, struct fprobe *fp)
return ret;
}
-/* Return true if there are synonims */
-static bool delete_fprobe_node(struct fprobe_hlist_node *node)
+static void delete_fprobe_node(struct fprobe_hlist_node *node)
{
- bool ret;
-
lockdep_assert_held(&fprobe_mutex);
/* Avoid double deleting and non-inserted nodes */
@@ -105,13 +102,6 @@ static bool delete_fprobe_node(struct fprobe_hlist_node *node)
rhltable_remove(&fprobe_ip_table, &node->hlist,
fprobe_rht_params);
}
-
- rcu_read_lock();
- ret = !!rhltable_lookup(&fprobe_ip_table, &node->addr,
- fprobe_rht_params);
- rcu_read_unlock();
-
- return ret;
}
/* Check existence of the fprobe */
@@ -343,6 +333,32 @@ static bool fprobe_is_ftrace(struct fprobe *fp)
return !fp->exit_handler;
}
+static bool fprobe_exists_on_hash(unsigned long ip, bool ftrace)
+{
+ struct rhlist_head *head, *pos;
+ struct fprobe_hlist_node *node;
+ struct fprobe *fp;
+
+ guard(rcu)();
+ head = rhltable_lookup(&fprobe_ip_table, &ip,
+ fprobe_rht_params);
+ if (!head)
+ return false;
+ /* We have to check the same type on the list. */
+ rhl_for_each_entry_rcu(node, pos, head, hlist) {
+ if (node->addr != ip)
+ break;
+ fp = READ_ONCE(node->fp);
+ if (likely(fp)) {
+ if ((!ftrace && fp->exit_handler) ||
+ (ftrace && !fp->exit_handler))
+ return true;
+ }
+ }
+
+ return false;
+}
+
#ifdef CONFIG_MODULES
static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt)
{
@@ -365,6 +381,29 @@ static bool fprobe_is_ftrace(struct fprobe *fp)
return false;
}
+static bool fprobe_exists_on_hash(unsigned long ip, bool ftrace __maybe_unused)
+{
+ struct rhlist_head *head, *pos;
+ struct fprobe_hlist_node *node;
+ struct fprobe *fp;
+
+ guard(rcu)();
+ head = rhltable_lookup(&fprobe_ip_table, &ip,
+ fprobe_rht_params);
+ if (!head)
+ return false;
+ /* We only need to check fp is there. */
+ rhl_for_each_entry_rcu(node, pos, head, hlist) {
+ if (node->addr != ip)
+ break;
+ fp = READ_ONCE(node->fp);
+ if (likely(fp))
+ return true;
+ }
+
+ return false;
+}
+
#ifdef CONFIG_MODULES
static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt)
{
@@ -552,18 +591,25 @@ struct fprobe_addr_list {
static int fprobe_remove_node_in_module(struct module *mod, struct fprobe_hlist_node *node,
struct fprobe_addr_list *alist)
{
+ lockdep_assert_in_rcu_read_lock();
+
if (!within_module(node->addr, mod))
return 0;
- if (delete_fprobe_node(node))
- return 0;
+ delete_fprobe_node(node);
/* If no address list is available, we can't track this address. */
if (!alist->addrs)
return 0;
+ /*
+ * Don't care the type here, because all fprobes on the same
+ * address must be removed eventually.
+ */
+ if (!rhltable_lookup(&fprobe_ip_table, &node->addr, fprobe_rht_params)) {
+ alist->addrs[alist->index++] = node->addr;
+ if (alist->index == alist->size)
+ return -ENOSPC;
+ }
- alist->addrs[alist->index++] = node->addr;
- if (alist->index == alist->size)
- return -ENOSPC;
return 0;
}
@@ -934,7 +980,9 @@ static int unregister_fprobe_nolock(struct fprobe *fp)
/* Remove non-synonim ips from table and hash */
count = 0;
for (i = 0; i < hlist_array->size; i++) {
- if (!delete_fprobe_node(&hlist_array->array[i]) && addrs)
+ delete_fprobe_node(&hlist_array->array[i]);
+ if (addrs && !fprobe_exists_on_hash(hlist_array->array[i].addr,
+ fprobe_is_ftrace(fp)))
addrs[count++] = hlist_array->array[i].addr;
}
del_fprobe_hash(fp);
--
2.53.0
^ permalink raw reply related [flat|nested] 5+ messages in thread