From 26ebba25e210116053609f4c7ee701bffa7ebd7d Mon Sep 17 00:00:00 2001 From: Tao Chen Date: Fri, 8 Aug 2025 12:05:26 +0800 Subject: [PATCH 1/8] tools/latency-collector: Check pkg-config install The tool pkg-config used to check libtraceevent and libtracefs, if not installed, it will report the libs not found, even though they have already been installed. Before: libtraceevent is missing. Please install libtraceevent-dev/libtraceevent-devel libtracefs is missing. Please install libtracefs-dev/libtracefs-devel After: Makefile.config:10: *** Error: pkg-config needed by libtraceevent/libtracefs is missing on this system, please install it. Link: https://lore.kernel.org/20250808040527.2036023-1-chen.dylane@linux.dev Fixes: 9d56c88e5225 ("tools/tracing: Use tools/build makefiles on latency-collector") Signed-off-by: Tao Chen Signed-off-by: Steven Rostedt (Google) --- tools/tracing/latency/Makefile.config | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/tracing/latency/Makefile.config b/tools/tracing/latency/Makefile.config index 0fe6b50f029b..6efa13e3ca93 100644 --- a/tools/tracing/latency/Makefile.config +++ b/tools/tracing/latency/Makefile.config @@ -1,7 +1,15 @@ # SPDX-License-Identifier: GPL-2.0-only +include $(srctree)/tools/scripts/utilities.mak + STOP_ERROR := +ifndef ($(NO_LIBTRACEEVENT),1) + ifeq ($(call get-executable,$(PKG_CONFIG)),) + $(error Error: $(PKG_CONFIG) needed by libtraceevent/libtracefs is missing on this system, please install it) + endif +endif + define lib_setup $(eval LIB_INCLUDES += $(shell sh -c "$(PKG_CONFIG) --cflags lib$(1)")) $(eval LDFLAGS += $(shell sh -c "$(PKG_CONFIG) --libs-only-L lib$(1)")) From 7b128f1d53dcaa324d4aa05d821a6bf4a7b203e7 Mon Sep 17 00:00:00 2001 From: Tao Chen Date: Fri, 8 Aug 2025 12:05:27 +0800 Subject: [PATCH 2/8] rtla: Check pkg-config install The tool pkg-config used to check libtraceevent and libtracefs, if not installed, it will report the libs not found, even though they have already been installed. Before: libtraceevent is missing. Please install libtraceevent-dev/libtraceevent-devel libtracefs is missing. Please install libtracefs-dev/libtracefs-devel After: Makefile.config:10: *** Error: pkg-config needed by libtraceevent/libtracefs is missing on this system, please install it. Link: https://lore.kernel.org/20250808040527.2036023-2-chen.dylane@linux.dev Fixes: 01474dc706ca ("tools/rtla: Use tools/build makefiles to build rtla") Signed-off-by: Tao Chen Signed-off-by: Steven Rostedt (Google) --- tools/tracing/rtla/Makefile.config | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/tracing/rtla/Makefile.config b/tools/tracing/rtla/Makefile.config index 5f2231d8d626..07ff5e8f3006 100644 --- a/tools/tracing/rtla/Makefile.config +++ b/tools/tracing/rtla/Makefile.config @@ -1,10 +1,18 @@ # SPDX-License-Identifier: GPL-2.0-only +include $(srctree)/tools/scripts/utilities.mak + STOP_ERROR := LIBTRACEEVENT_MIN_VERSION = 1.5 LIBTRACEFS_MIN_VERSION = 1.6 +ifndef ($(NO_LIBTRACEEVENT),1) + ifeq ($(call get-executable,$(PKG_CONFIG)),) + $(error Error: $(PKG_CONFIG) needed by libtraceevent/libtracefs is missing on this system, please install it) + endif +endif + define lib_setup $(eval LIB_INCLUDES += $(shell sh -c "$(PKG_CONFIG) --cflags lib$(1)")) $(eval LDFLAGS += $(shell sh -c "$(PKG_CONFIG) --libs-only-L lib$(1)")) From 6a909ea83f226803ea0e718f6e88613df9234d58 Mon Sep 17 00:00:00 2001 From: Pu Lehui Date: Wed, 13 Aug 2025 04:02:32 +0000 Subject: [PATCH 3/8] tracing: Limit access to parser->buffer when trace_get_user failed When the length of the string written to set_ftrace_filter exceeds FTRACE_BUFF_MAX, the following KASAN alarm will be triggered: BUG: KASAN: slab-out-of-bounds in strsep+0x18c/0x1b0 Read of size 1 at addr ffff0000d00bd5ba by task ash/165 CPU: 1 UID: 0 PID: 165 Comm: ash Not tainted 6.16.0-g6bcdbd62bd56-dirty Hardware name: linux,dummy-virt (DT) Call trace: show_stack+0x34/0x50 (C) dump_stack_lvl+0xa0/0x158 print_address_description.constprop.0+0x88/0x398 print_report+0xb0/0x280 kasan_report+0xa4/0xf0 __asan_report_load1_noabort+0x20/0x30 strsep+0x18c/0x1b0 ftrace_process_regex.isra.0+0x100/0x2d8 ftrace_regex_release+0x484/0x618 __fput+0x364/0xa58 ____fput+0x28/0x40 task_work_run+0x154/0x278 do_notify_resume+0x1f0/0x220 el0_svc+0xec/0xf0 el0t_64_sync_handler+0xa0/0xe8 el0t_64_sync+0x1ac/0x1b0 The reason is that trace_get_user will fail when processing a string longer than FTRACE_BUFF_MAX, but not set the end of parser->buffer to 0. Then an OOB access will be triggered in ftrace_regex_release-> ftrace_process_regex->strsep->strpbrk. We can solve this problem by limiting access to parser->buffer when trace_get_user failed. Cc: stable@vger.kernel.org Link: https://lore.kernel.org/20250813040232.1344527-1-pulehui@huaweicloud.com Fixes: 8c9af478c06b ("ftrace: Handle commands when closing set_ftrace_filter file") Signed-off-by: Pu Lehui Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 18 ++++++++++++------ kernel/trace/trace.h | 8 +++++++- 2 files changed, 19 insertions(+), 7 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 4283ed4e8f59..8d8935ed416d 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1816,7 +1816,7 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf, ret = get_user(ch, ubuf++); if (ret) - return ret; + goto fail; read++; cnt--; @@ -1830,7 +1830,7 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf, while (cnt && isspace(ch)) { ret = get_user(ch, ubuf++); if (ret) - return ret; + goto fail; read++; cnt--; } @@ -1848,12 +1848,14 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf, while (cnt && !isspace(ch) && ch) { if (parser->idx < parser->size - 1) parser->buffer[parser->idx++] = ch; - else - return -EINVAL; + else { + ret = -EINVAL; + goto fail; + } ret = get_user(ch, ubuf++); if (ret) - return ret; + goto fail; read++; cnt--; } @@ -1868,11 +1870,15 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf, /* Make sure the parsed string always terminates with '\0'. */ parser->buffer[parser->idx] = 0; } else { - return -EINVAL; + ret = -EINVAL; + goto fail; } *ppos += read; return read; +fail: + trace_parser_fail(parser); + return ret; } /* TODO add a seq_buf_to_buffer() */ diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 1dbf1d3cf2f1..be6654899cae 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1292,6 +1292,7 @@ bool ftrace_event_is_function(struct trace_event_call *call); */ struct trace_parser { bool cont; + bool fail; char *buffer; unsigned idx; unsigned size; @@ -1299,7 +1300,7 @@ struct trace_parser { static inline bool trace_parser_loaded(struct trace_parser *parser) { - return (parser->idx != 0); + return !parser->fail && parser->idx != 0; } static inline bool trace_parser_cont(struct trace_parser *parser) @@ -1313,6 +1314,11 @@ static inline void trace_parser_clear(struct trace_parser *parser) parser->idx = 0; } +static inline void trace_parser_fail(struct trace_parser *parser) +{ + parser->fail = true; +} + extern int trace_parser_get_init(struct trace_parser *parser, int size); extern void trace_parser_put(struct trace_parser *parser); extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf, From cd6e4faba96fe41d6b686e144b96dad5e6f2e771 Mon Sep 17 00:00:00 2001 From: Liao Yuanhong Date: Wed, 13 Aug 2025 17:51:14 +0800 Subject: [PATCH 4/8] ring-buffer: Remove redundant semicolons Remove unnecessary semicolons. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20250813095114.559530-1-liaoyuanhong@vivo.com Signed-off-by: Liao Yuanhong Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index bb71a0dc9d69..43460949ad3f 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -7666,7 +7666,7 @@ static __init int test_ringbuffer(void) rb_test_started = true; set_current_state(TASK_INTERRUPTIBLE); - /* Just run for 10 seconds */; + /* Just run for 10 seconds */ schedule_timeout(10 * HZ); kthread_stop(rb_hammer); From edede7a6dcd7435395cf757d053974aaab6ab1c2 Mon Sep 17 00:00:00 2001 From: Ye Weihua Date: Mon, 18 Aug 2025 07:33:32 +0000 Subject: [PATCH 5/8] trace/fgraph: Fix the warning caused by missing unregister notifier This warning was triggered during testing on v6.16: notifier callback ftrace_suspend_notifier_call already registered WARNING: CPU: 2 PID: 86 at kernel/notifier.c:23 notifier_chain_register+0x44/0xb0 ... Call Trace: blocking_notifier_chain_register+0x34/0x60 register_ftrace_graph+0x330/0x410 ftrace_profile_write+0x1e9/0x340 vfs_write+0xf8/0x420 ? filp_flush+0x8a/0xa0 ? filp_close+0x1f/0x30 ? do_dup2+0xaf/0x160 ksys_write+0x65/0xe0 do_syscall_64+0xa4/0x260 entry_SYSCALL_64_after_hwframe+0x77/0x7f When writing to the function_profile_enabled interface, the notifier was not unregistered after start_graph_tracing failed, causing a warning the next time function_profile_enabled was written. Fixed by adding unregister_pm_notifier in the exception path. Link: https://lore.kernel.org/20250818073332.3890629-1-yeweihua4@huawei.com Fixes: 4a2b8dda3f870 ("tracing/function-graph-tracer: fix a regression while suspend to disk") Acked-by: Masami Hiramatsu (Google) Signed-off-by: Ye Weihua Signed-off-by: Steven Rostedt (Google) --- kernel/trace/fgraph.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index f4d200f0c610..2a42c1036ea8 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -1397,6 +1397,7 @@ int register_ftrace_graph(struct fgraph_ops *gops) ftrace_graph_active--; gops->saved_func = NULL; fgraph_lru_release_index(i); + unregister_pm_notifier(&ftrace_suspend_notifier); } return ret; } From e3d01979e4bff5c87eb4054a22e7568bb679b1fe Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 20 Aug 2025 19:55:22 -0400 Subject: [PATCH 6/8] fgraph: Copy args in intermediate storage with entry The output of the function graph tracer has two ways to display its entries. One way for leaf functions with no events recorded within them, and the other is for functions with events recorded inside it. As function graph has an entry and exit event, to simplify the output of leaf functions it combines the two, where as non leaf functions are separate: 2) | invoke_rcu_core() { 2) | raise_softirq() { 2) 0.391 us | __raise_softirq_irqoff(); 2) 1.191 us | } 2) 2.086 us | } The __raise_softirq_irqoff() function above is really two events that were merged into one. Otherwise it would have looked like: 2) | invoke_rcu_core() { 2) | raise_softirq() { 2) | __raise_softirq_irqoff() { 2) 0.391 us | } 2) 1.191 us | } 2) 2.086 us | } In order to do this merge, the reading of the trace output file needs to look at the next event before printing. But since the pointer to the event is on the ring buffer, it needs to save the entry event before it looks at the next event as the next event goes out of focus as soon as a new event is read from the ring buffer. After it reads the next event, it will print the entry event with either the '{' (non leaf) or ';' and timestamps (leaf). The iterator used to read the trace file has storage for this event. The problem happens when the function graph tracer has arguments attached to the entry event as the entry now has a variable length "args" field. This field only gets set when funcargs option is used. But the args are not recorded in this temp data and garbage could be printed. The entry field is copied via: data->ent = *curr; Where "curr" is the entry field. But this method only saves the non variable length fields from the structure. Add a helper structure to the iterator data that adds the max args size to the data storage in the iterator. Then simply copy the entire entry into this storage (with size protection). Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Mark Rutland Link: https://lore.kernel.org/20250820195522.51d4a268@gandalf.local.home Reported-by: Sasha Levin Tested-by: Sasha Levin Closes: https://lore.kernel.org/all/aJaxRVKverIjF4a6@lappy/ Fixes: ff5c9c576e75 ("ftrace: Add support for function argument to graph tracer") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_functions_graph.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 66e1a527cf1a..a7f4b9a47a71 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -27,14 +27,21 @@ struct fgraph_cpu_data { unsigned long enter_funcs[FTRACE_RETFUNC_DEPTH]; }; +struct fgraph_ent_args { + struct ftrace_graph_ent_entry ent; + /* Force the sizeof of args[] to have FTRACE_REGS_MAX_ARGS entries */ + unsigned long args[FTRACE_REGS_MAX_ARGS]; +}; + struct fgraph_data { struct fgraph_cpu_data __percpu *cpu_data; /* Place to preserve last processed entry. */ union { - struct ftrace_graph_ent_entry ent; + struct fgraph_ent_args ent; + /* TODO allow retaddr to have args */ struct fgraph_retaddr_ent_entry rent; - } ent; + }; struct ftrace_graph_ret_entry ret; int failed; int cpu; @@ -627,10 +634,13 @@ get_return_for_leaf(struct trace_iterator *iter, * Save current and next entries for later reference * if the output fails. */ - if (unlikely(curr->ent.type == TRACE_GRAPH_RETADDR_ENT)) - data->ent.rent = *(struct fgraph_retaddr_ent_entry *)curr; - else - data->ent.ent = *curr; + if (unlikely(curr->ent.type == TRACE_GRAPH_RETADDR_ENT)) { + data->rent = *(struct fgraph_retaddr_ent_entry *)curr; + } else { + int size = min((int)sizeof(data->ent), (int)iter->ent_size); + + memcpy(&data->ent, curr, size); + } /* * If the next event is not a return type, then * we only care about what type it is. Otherwise we can From 4013aef2ced9b756a410f50d12df9ebe6a883e4a Mon Sep 17 00:00:00 2001 From: Tengda Wu Date: Fri, 22 Aug 2025 03:33:43 +0000 Subject: [PATCH 7/8] ftrace: Fix potential warning in trace_printk_seq during ftrace_dump When calling ftrace_dump_one() concurrently with reading trace_pipe, a WARN_ON_ONCE() in trace_printk_seq() can be triggered due to a race condition. The issue occurs because: CPU0 (ftrace_dump) CPU1 (reader) echo z > /proc/sysrq-trigger !trace_empty(&iter) trace_iterator_reset(&iter) <- len = size = 0 cat /sys/kernel/tracing/trace_pipe trace_find_next_entry_inc(&iter) __find_next_entry ring_buffer_empty_cpu <- all empty return NULL trace_printk_seq(&iter.seq) WARN_ON_ONCE(s->seq.len >= s->seq.size) In the context between trace_empty() and trace_find_next_entry_inc() during ftrace_dump, the ring buffer data was consumed by other readers. This caused trace_find_next_entry_inc to return NULL, failing to populate `iter.seq`. At this point, due to the prior trace_iterator_reset, both `iter.seq.len` and `iter.seq.size` were set to 0. Since they are equal, the WARN_ON_ONCE condition is triggered. Move the trace_printk_seq() into the if block that checks to make sure the return value of trace_find_next_entry_inc() is non-NULL in ftrace_dump_one(), ensuring the 'iter.seq' is properly populated before subsequent operations. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Ingo Molnar Link: https://lore.kernel.org/20250822033343.3000289-1-wutengda@huaweicloud.com Fixes: d769041f8653 ("ring_buffer: implement new locking") Signed-off-by: Tengda Wu Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8d8935ed416d..1b7db732c0b1 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -10638,10 +10638,10 @@ static void ftrace_dump_one(struct trace_array *tr, enum ftrace_dump_mode dump_m ret = print_trace_line(&iter); if (ret != TRACE_TYPE_NO_CONSUME) trace_consume(&iter); + + trace_printk_seq(&iter.seq); } touch_nmi_watchdog(); - - trace_printk_seq(&iter.seq); } if (!cnt) From bfb336cf97df7b37b2b2edec0f69773e06d11955 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 22 Aug 2025 18:36:06 -0400 Subject: [PATCH 8/8] ftrace: Also allocate and copy hash for reading of filter files Currently the reader of set_ftrace_filter and set_ftrace_notrace just adds the pointer to the global tracer hash to its iterator. Unlike the writer that allocates a copy of the hash, the reader keeps the pointer to the filter hashes. This is problematic because this pointer is static across function calls that release the locks that can update the global tracer hashes. This can cause UAF and similar bugs. Allocate and copy the hash for reading the filter files like it is done for the writers. This not only fixes UAF bugs, but also makes the code a bit simpler as it doesn't have to differentiate when to free the iterator's hash between writers and readers. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Nathan Chancellor Cc: Linus Torvalds Link: https://lore.kernel.org/20250822183606.12962cc3@batman.local.home Fixes: c20489dad156 ("ftrace: Assign iter->hash to filter or notrace hashes on seq read") Closes: https://lore.kernel.org/all/20250813023044.2121943-1-wutengda@huaweicloud.com/ Closes: https://lore.kernel.org/all/20250822192437.GA458494@ax162/ Reported-by: Tengda Wu Tested-by: Tengda Wu Tested-by: Nathan Chancellor Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 00b76d450a89..a69067367c29 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4661,13 +4661,17 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, } else { iter->hash = alloc_and_copy_ftrace_hash(size_bits, hash); } + } else { + if (hash) + iter->hash = alloc_and_copy_ftrace_hash(hash->size_bits, hash); + else + iter->hash = EMPTY_HASH; + } - if (!iter->hash) { - trace_parser_put(&iter->parser); - goto out_unlock; - } - } else - iter->hash = hash; + if (!iter->hash) { + trace_parser_put(&iter->parser); + goto out_unlock; + } ret = 0; @@ -6543,9 +6547,6 @@ int ftrace_regex_release(struct inode *inode, struct file *file) ftrace_hash_move_and_update_ops(iter->ops, orig_hash, iter->hash, filter_hash); mutex_unlock(&ftrace_lock); - } else { - /* For read only, the hash is the ops hash */ - iter->hash = NULL; } mutex_unlock(&iter->ops->func_hash->regex_lock);