From ba27d8555867b0e02e15709f4ddb79aec5cf2efc Mon Sep 17 00:00:00 2001 From: Jakob Koschel Date: Wed, 27 Apr 2022 19:07:34 +0200 Subject: tracing: Remove check of list iterator against head past the loop body When list_for_each_entry() completes the iteration over the whole list without breaking the loop, the iterator value will be a bogus pointer computed based on the head element. While it is safe to use the pointer to determine if it was computed based on the head element, either with list_entry_is_head() or &pos->member == head, using the iterator variable after the loop should be avoided. In preparation to limit the scope of a list iterator to the list traversal loop, use a dedicated pointer to point to the found element [1]. Link: https://lkml.kernel.org/r/20220427170734.819891-5-jakobkoschel@gmail.com Cc: Ingo Molnar Link: https://lore.kernel.org/all/CAHk-=wgRr_D8CB-D9Kg-c=EHreAsk5SqXPwr9Y7k9sA6cWXJ6w@mail.gmail.com/ Signed-off-by: Jakob Koschel Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 4f1d2f5e7263..5c465e70d146 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4560,8 +4560,8 @@ register_ftrace_function_probe(char *glob, struct trace_array *tr, struct ftrace_probe_ops *probe_ops, void *data) { + struct ftrace_func_probe *probe = NULL, *iter; struct ftrace_func_entry *entry; - struct ftrace_func_probe *probe; struct ftrace_hash **orig_hash; struct ftrace_hash *old_hash; struct ftrace_hash *hash; @@ -4580,11 +4580,13 @@ register_ftrace_function_probe(char *glob, struct trace_array *tr, mutex_lock(&ftrace_lock); /* Check if the probe_ops is already registered */ - list_for_each_entry(probe, &tr->func_probes, list) { - if (probe->probe_ops == probe_ops) + list_for_each_entry(iter, &tr->func_probes, list) { + if (iter->probe_ops == probe_ops) { + probe = iter; break; + } } - if (&probe->list == &tr->func_probes) { + if (!probe) { probe = kzalloc(sizeof(*probe), GFP_KERNEL); if (!probe) { mutex_unlock(&ftrace_lock); @@ -4702,9 +4704,9 @@ int unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr, struct ftrace_probe_ops *probe_ops) { + struct ftrace_func_probe *probe = NULL, *iter; struct ftrace_ops_hash old_hash_ops; struct ftrace_func_entry *entry; - struct ftrace_func_probe *probe; struct ftrace_glob func_g; struct ftrace_hash **orig_hash; struct ftrace_hash *old_hash; @@ -4732,11 +4734,13 @@ unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr, mutex_lock(&ftrace_lock); /* Check if the probe_ops is already registered */ - list_for_each_entry(probe, &tr->func_probes, list) { - if (probe->probe_ops == probe_ops) + list_for_each_entry(iter, &tr->func_probes, list) { + if (iter->probe_ops == probe_ops) { + probe = iter; break; + } } - if (&probe->list == &tr->func_probes) + if (!probe) goto err_unlock_ftrace; ret = -EINVAL; -- cgit v1.2.3 From e4931b824a6f36cae9cc5632709f015cfa748a25 Mon Sep 17 00:00:00 2001 From: Yuntao Wang Date: Fri, 14 Jan 2022 21:10:52 +0800 Subject: tracing: Use trace_create_file() to simplify creation of tracefs entries Creating tracefs entries with tracefs_create_file() followed by pr_warn() is tedious and repetitive, we can use trace_create_file() to simplify this process and make the code more readable. Link: https://lkml.kernel.org/r/20220114131052.534382-1-ytcoode@gmail.com Acked-by: Masami Hiramatsu (Google) Signed-off-by: Yuntao Wang Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 9 +++------ kernel/trace/trace_dynevent.c | 9 ++------- kernel/trace/trace_events.c | 29 ++++++++++------------------- kernel/trace/trace_kprobe.c | 15 ++++----------- kernel/trace/trace_recursion_record.c | 7 ++----- 5 files changed, 21 insertions(+), 48 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 5c465e70d146..6c5b12669e06 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -952,7 +952,6 @@ static struct tracer_stat function_stats __initdata = { static __init void ftrace_profile_tracefs(struct dentry *d_tracer) { struct ftrace_profile_stat *stat; - struct dentry *entry; char *name; int ret; int cpu; @@ -983,11 +982,9 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer) } } - entry = tracefs_create_file("function_profile_enabled", - TRACE_MODE_WRITE, d_tracer, NULL, - &ftrace_profile_fops); - if (!entry) - pr_warn("Could not create tracefs 'function_profile_enabled' entry\n"); + trace_create_file("function_profile_enabled", + TRACE_MODE_WRITE, d_tracer, NULL, + &ftrace_profile_fops); } #else /* CONFIG_FUNCTION_PROFILER */ diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c index e34e8182ee4b..076b447a1b88 100644 --- a/kernel/trace/trace_dynevent.c +++ b/kernel/trace/trace_dynevent.c @@ -255,19 +255,14 @@ static const struct file_operations dynamic_events_ops = { /* Make a tracefs interface for controlling dynamic events */ static __init int init_dynamic_event(void) { - struct dentry *entry; int ret; ret = tracing_init_dentry(); if (ret) return 0; - entry = tracefs_create_file("dynamic_events", TRACE_MODE_WRITE, NULL, - NULL, &dynamic_events_ops); - - /* Event list interface */ - if (!entry) - pr_warn("Could not create tracefs 'dynamic_events' entry\n"); + trace_create_file("dynamic_events", TRACE_MODE_WRITE, NULL, + NULL, &dynamic_events_ops); return 0; } diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index d5913487821a..9a88de9d7815 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -3546,12 +3546,10 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr) struct dentry *d_events; struct dentry *entry; - entry = tracefs_create_file("set_event", TRACE_MODE_WRITE, parent, - tr, &ftrace_set_event_fops); - if (!entry) { - pr_warn("Could not create tracefs 'set_event' entry\n"); + entry = trace_create_file("set_event", TRACE_MODE_WRITE, parent, + tr, &ftrace_set_event_fops); + if (!entry) return -ENOMEM; - } d_events = tracefs_create_dir("events", parent); if (!d_events) { @@ -3566,16 +3564,12 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr) /* There are not as crucial, just warn if they are not created */ - entry = tracefs_create_file("set_event_pid", TRACE_MODE_WRITE, parent, - tr, &ftrace_set_event_pid_fops); - if (!entry) - pr_warn("Could not create tracefs 'set_event_pid' entry\n"); + trace_create_file("set_event_pid", TRACE_MODE_WRITE, parent, + tr, &ftrace_set_event_pid_fops); - entry = tracefs_create_file("set_event_notrace_pid", - TRACE_MODE_WRITE, parent, tr, - &ftrace_set_event_notrace_pid_fops); - if (!entry) - pr_warn("Could not create tracefs 'set_event_notrace_pid' entry\n"); + trace_create_file("set_event_notrace_pid", + TRACE_MODE_WRITE, parent, tr, + &ftrace_set_event_notrace_pid_fops); /* ring buffer internal formats */ trace_create_file("header_page", TRACE_MODE_READ, d_events, @@ -3790,17 +3784,14 @@ static __init int event_trace_init_fields(void) __init int event_trace_init(void) { struct trace_array *tr; - struct dentry *entry; int ret; tr = top_trace_array(); if (!tr) return -ENODEV; - entry = tracefs_create_file("available_events", TRACE_MODE_READ, - NULL, tr, &ftrace_avail_fops); - if (!entry) - pr_warn("Could not create tracefs 'available_events' entry\n"); + trace_create_file("available_events", TRACE_MODE_READ, + NULL, tr, &ftrace_avail_fops); ret = early_event_add_tracer(NULL, tr); if (ret) diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 47cebef78532..93507330462c 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1907,25 +1907,18 @@ core_initcall(init_kprobe_trace_early); static __init int init_kprobe_trace(void) { int ret; - struct dentry *entry; ret = tracing_init_dentry(); if (ret) return 0; - entry = tracefs_create_file("kprobe_events", TRACE_MODE_WRITE, - NULL, NULL, &kprobe_events_ops); - /* Event list interface */ - if (!entry) - pr_warn("Could not create tracefs 'kprobe_events' entry\n"); + trace_create_file("kprobe_events", TRACE_MODE_WRITE, + NULL, NULL, &kprobe_events_ops); /* Profile interface */ - entry = tracefs_create_file("kprobe_profile", TRACE_MODE_READ, - NULL, NULL, &kprobe_profile_ops); - - if (!entry) - pr_warn("Could not create tracefs 'kprobe_profile' entry\n"); + trace_create_file("kprobe_profile", TRACE_MODE_READ, + NULL, NULL, &kprobe_profile_ops); setup_boot_kprobe_events(); diff --git a/kernel/trace/trace_recursion_record.c b/kernel/trace/trace_recursion_record.c index 4d4b78c8ca25..a520b11afb0d 100644 --- a/kernel/trace/trace_recursion_record.c +++ b/kernel/trace/trace_recursion_record.c @@ -224,12 +224,9 @@ static const struct file_operations recursed_functions_fops = { __init static int create_recursed_functions(void) { - struct dentry *dentry; - dentry = trace_create_file("recursed_functions", TRACE_MODE_WRITE, - NULL, NULL, &recursed_functions_fops); - if (!dentry) - pr_warn("WARNING: Failed to create recursed_functions\n"); + trace_create_file("recursed_functions", TRACE_MODE_WRITE, + NULL, NULL, &recursed_functions_fops); return 0; } -- cgit v1.2.3 From 2889c658b2fbc7ad4c5d541734fdc1d97b130753 Mon Sep 17 00:00:00 2001 From: Yuntao Wang Date: Thu, 20 Jan 2022 06:59:49 +0000 Subject: ftrace: Deal with error return code of the ftrace_process_locs() function The ftrace_process_locs() function may return -ENOMEM error code, which should be handled by the callers. Link: https://lkml.kernel.org/r/20220120065949.1813231-1-ytcoode@gmail.com Signed-off-by: Yuntao Wang Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6c5b12669e06..737e895e2aad 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -6864,11 +6864,16 @@ void ftrace_module_enable(struct module *mod) void ftrace_module_init(struct module *mod) { + int ret; + if (ftrace_disabled || !mod->num_ftrace_callsites) return; - ftrace_process_locs(mod, mod->ftrace_callsites, - mod->ftrace_callsites + mod->num_ftrace_callsites); + ret = ftrace_process_locs(mod, mod->ftrace_callsites, + mod->ftrace_callsites + mod->num_ftrace_callsites); + if (ret) + pr_warn("ftrace: failed to allocate entries for module '%s' functions\n", + mod->name); } static void save_ftrace_mod_rec(struct ftrace_mod_map *mod_map, @@ -7201,15 +7206,19 @@ void __init ftrace_init(void) pr_info("ftrace: allocating %ld entries in %ld pages\n", count, count / ENTRIES_PER_PAGE + 1); - last_ftrace_enabled = ftrace_enabled = 1; - ret = ftrace_process_locs(NULL, __start_mcount_loc, __stop_mcount_loc); + if (ret) { + pr_warn("ftrace: failed to allocate entries for functions\n"); + goto failed; + } pr_info("ftrace: allocated %ld pages with %ld groups\n", ftrace_number_of_pages, ftrace_number_of_groups); + last_ftrace_enabled = ftrace_enabled = 1; + set_ftrace_early_filters(); return; -- cgit v1.2.3 From 3a2bfec0b02f2226ff3376a5d2ff604d799bd7ea Mon Sep 17 00:00:00 2001 From: Li kunyu Date: Wed, 18 May 2022 10:36:40 +0800 Subject: ftrace: Remove return value of ftrace_arch_modify_*() All instances of the function ftrace_arch_modify_prepare() and ftrace_arch_modify_post_process() return zero. There's no point in checking their return value. Just have them be void functions. Link: https://lkml.kernel.org/r/20220518023639.4065-1-kunyu@nfschina.com Signed-off-by: Li kunyu Signed-off-by: Steven Rostedt (Google) --- arch/arm/kernel/ftrace.c | 6 ++---- arch/riscv/kernel/ftrace.c | 6 ++---- arch/s390/kernel/ftrace.c | 3 +-- arch/x86/kernel/ftrace.c | 6 ++---- include/linux/ftrace.h | 4 ++-- kernel/trace/ftrace.c | 16 ++++------------ 6 files changed, 13 insertions(+), 28 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c index 83cc068586bc..a0b6d1e3812f 100644 --- a/arch/arm/kernel/ftrace.c +++ b/arch/arm/kernel/ftrace.c @@ -79,16 +79,14 @@ static unsigned long __ref adjust_address(struct dyn_ftrace *rec, return (unsigned long)&ftrace_regs_caller_from_init; } -int ftrace_arch_code_modify_prepare(void) +void ftrace_arch_code_modify_prepare(void) { - return 0; } -int ftrace_arch_code_modify_post_process(void) +void ftrace_arch_code_modify_post_process(void) { /* Make sure any TLB misses during machine stop are cleared. */ flush_tlb_all(); - return 0; } static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr, diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 4716f4cdc038..2086f6585773 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -12,16 +12,14 @@ #include #ifdef CONFIG_DYNAMIC_FTRACE -int ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex) +void ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex) { mutex_lock(&text_mutex); - return 0; } -int ftrace_arch_code_modify_post_process(void) __releases(&text_mutex) +void ftrace_arch_code_modify_post_process(void) __releases(&text_mutex) { mutex_unlock(&text_mutex); - return 0; } static int ftrace_check_current_call(unsigned long hook_pos, diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 1852d46babb1..416b5a94353d 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -225,14 +225,13 @@ void arch_ftrace_update_code(int command) ftrace_modify_all_code(command); } -int ftrace_arch_code_modify_post_process(void) +void ftrace_arch_code_modify_post_process(void) { /* * Flush any pre-fetched instructions on all * CPUs to make the new code visible. */ text_poke_sync_lock(); - return 0; } #ifdef CONFIG_MODULES diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 1e31c7d21597..73d2719ed12c 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -37,7 +37,7 @@ static int ftrace_poke_late = 0; -int ftrace_arch_code_modify_prepare(void) +void ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex) { /* @@ -47,10 +47,9 @@ int ftrace_arch_code_modify_prepare(void) */ mutex_lock(&text_mutex); ftrace_poke_late = 1; - return 0; } -int ftrace_arch_code_modify_post_process(void) +void ftrace_arch_code_modify_post_process(void) __releases(&text_mutex) { /* @@ -61,7 +60,6 @@ int ftrace_arch_code_modify_post_process(void) text_poke_finish(); ftrace_poke_late = 0; mutex_unlock(&text_mutex); - return 0; } static const char *ftrace_nop_replace(void) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 4816b7e11047..a5f74f6e7e4e 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -449,8 +449,8 @@ static inline void stack_tracer_enable(void) { } #ifdef CONFIG_DYNAMIC_FTRACE -int ftrace_arch_code_modify_prepare(void); -int ftrace_arch_code_modify_post_process(void); +void ftrace_arch_code_modify_prepare(void); +void ftrace_arch_code_modify_post_process(void); enum ftrace_bug_type { FTRACE_BUG_UNKNOWN, diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 737e895e2aad..852c731cbd9a 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2704,18 +2704,16 @@ ftrace_nop_initialize(struct module *mod, struct dyn_ftrace *rec) * archs can override this function if they must do something * before the modifying code is performed. */ -int __weak ftrace_arch_code_modify_prepare(void) +void __weak ftrace_arch_code_modify_prepare(void) { - return 0; } /* * archs can override this function if they must do something * after the modifying code is performed. */ -int __weak ftrace_arch_code_modify_post_process(void) +void __weak ftrace_arch_code_modify_post_process(void) { - return 0; } void ftrace_modify_all_code(int command) @@ -2801,12 +2799,7 @@ void __weak arch_ftrace_update_code(int command) static void ftrace_run_update_code(int command) { - int ret; - - ret = ftrace_arch_code_modify_prepare(); - FTRACE_WARN_ON(ret); - if (ret) - return; + ftrace_arch_code_modify_prepare(); /* * By default we use stop_machine() to modify the code. @@ -2816,8 +2809,7 @@ static void ftrace_run_update_code(int command) */ arch_ftrace_update_code(command); - ret = ftrace_arch_code_modify_post_process(); - FTRACE_WARN_ON(ret); + ftrace_arch_code_modify_post_process(); } static void ftrace_run_modify_code(struct ftrace_ops *ops, int command, -- cgit v1.2.3 From 50c697819d59c5013a66728940015348919a0c0c Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Sat, 21 May 2022 13:11:31 +0200 Subject: ftrace: Fix typo in comment Spelling mistake (triple letters) in comment. Detected with the help of Coccinelle. Link: https://lkml.kernel.org/r/20220521111145.81697-81-Julia.Lawall@inria.fr Signed-off-by: Julia Lawall Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 852c731cbd9a..fb8f08b4bd41 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -119,7 +119,7 @@ struct ftrace_ops __rcu *ftrace_ops_list __read_mostly = &ftrace_list_end; ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; struct ftrace_ops global_ops; -/* Defined by vmlinux.lds.h see the commment above arch_ftrace_ops_list_func for details */ +/* Defined by vmlinux.lds.h see the comment above arch_ftrace_ops_list_func for details */ void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs); -- cgit v1.2.3 From 7d54c15cb89a29a5f59e5ffc9ee62e6591769ef1 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Tue, 24 May 2022 10:08:39 -0700 Subject: ftrace: Clean up hash direct_functions on register failures We see the following GPF when register_ftrace_direct fails: [ ] general protection fault, probably for non-canonical address \ 0x200000000000010: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC PTI [...] [ ] RIP: 0010:ftrace_find_rec_direct+0x53/0x70 [ ] Code: 48 c1 e0 03 48 03 42 08 48 8b 10 31 c0 48 85 d2 74 [...] [ ] RSP: 0018:ffffc9000138bc10 EFLAGS: 00010206 [ ] RAX: 0000000000000000 RBX: ffffffff813e0df0 RCX: 000000000000003b [ ] RDX: 0200000000000000 RSI: 000000000000000c RDI: ffffffff813e0df0 [ ] RBP: ffffffffa00a3000 R08: ffffffff81180ce0 R09: 0000000000000001 [ ] R10: ffffc9000138bc18 R11: 0000000000000001 R12: ffffffff813e0df0 [ ] R13: ffffffff813e0df0 R14: ffff888171b56400 R15: 0000000000000000 [ ] FS: 00007fa9420c7780(0000) GS:ffff888ff6a00000(0000) knlGS:000000000 [ ] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ ] CR2: 000000000770d000 CR3: 0000000107d50003 CR4: 0000000000370ee0 [ ] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ ] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ ] Call Trace: [ ] [ ] register_ftrace_direct+0x54/0x290 [ ] ? render_sigset_t+0xa0/0xa0 [ ] bpf_trampoline_update+0x3f5/0x4a0 [ ] ? 0xffffffffa00a3000 [ ] bpf_trampoline_link_prog+0xa9/0x140 [ ] bpf_tracing_prog_attach+0x1dc/0x450 [ ] bpf_raw_tracepoint_open+0x9a/0x1e0 [ ] ? find_held_lock+0x2d/0x90 [ ] ? lock_release+0x150/0x430 [ ] __sys_bpf+0xbd6/0x2700 [ ] ? lock_is_held_type+0xd8/0x130 [ ] __x64_sys_bpf+0x1c/0x20 [ ] do_syscall_64+0x3a/0x80 [ ] entry_SYSCALL_64_after_hwframe+0x44/0xae [ ] RIP: 0033:0x7fa9421defa9 [ ] Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 9 f8 [...] [ ] RSP: 002b:00007ffed743bd78 EFLAGS: 00000246 ORIG_RAX: 0000000000000141 [ ] RAX: ffffffffffffffda RBX: 00000000069d2480 RCX: 00007fa9421defa9 [ ] RDX: 0000000000000078 RSI: 00007ffed743bd80 RDI: 0000000000000011 [ ] RBP: 00007ffed743be00 R08: 0000000000bb7270 R09: 0000000000000000 [ ] R10: 00000000069da210 R11: 0000000000000246 R12: 0000000000000001 [ ] R13: 00007ffed743c4b0 R14: 00000000069d2480 R15: 0000000000000001 [ ] [ ] Modules linked in: klp_vm(OK) [ ] ---[ end trace 0000000000000000 ]--- One way to trigger this is: 1. load a livepatch that patches kernel function xxx; 2. run bpftrace -e 'kfunc:xxx {}', this will fail (expected for now); 3. repeat #2 => gpf. This is because the entry is added to direct_functions, but not removed. Fix this by remove the entry from direct_functions when register_ftrace_direct fails. Also remove the last trailing space from ftrace.c, so we don't have to worry about it anymore. Link: https://lkml.kernel.org/r/20220524170839.900849-1-song@kernel.org Cc: stable@vger.kernel.org Fixes: 763e34e74bb7 ("ftrace: Add register_ftrace_direct()") Signed-off-by: Song Liu Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index fb8f08b4bd41..d653ef4febc5 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4454,7 +4454,7 @@ int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper, * @ip: The instruction pointer address to remove the data from * * Returns the data if it is found, otherwise NULL. - * Note, if the data pointer is used as the data itself, (see + * Note, if the data pointer is used as the data itself, (see * ftrace_func_mapper_find_ip(), then the return value may be meaningless, * if the data pointer was set to zero. */ @@ -5188,8 +5188,6 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr) goto out_unlock; ret = ftrace_set_filter_ip(&direct_ops, ip, 0, 0); - if (ret) - remove_hash_entry(direct_functions, entry); if (!ret && !(direct_ops.flags & FTRACE_OPS_FL_ENABLED)) { ret = register_ftrace_function(&direct_ops); @@ -5198,6 +5196,7 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr) } if (ret) { + remove_hash_entry(direct_functions, entry); kfree(entry); if (!direct->count) { list_del_rcu(&direct->next); -- cgit v1.2.3 From b39181f7c6907dc66ff937b74758671fa6ba430c Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Thu, 26 May 2022 14:19:12 -0400 Subject: ftrace: Add FTRACE_MCOUNT_MAX_OFFSET to avoid adding weak function If an unused weak function was traced, it's call to fentry will still exist, which gets added into the __mcount_loc table. Ftrace will use kallsyms to retrieve the name for each location in __mcount_loc to display it in the available_filter_functions and used to enable functions via the name matching in set_ftrace_filter/notrace. Enabling these functions do nothing but enable an unused call to ftrace_caller. If a traced weak function is overridden, the symbol of the function would be used for it, which will either created duplicate names, or if the previous function was not traced, it would be incorrectly be listed in available_filter_functions as a function that can be traced. This became an issue with BPF[1] as there are tooling that enables the direct callers via ftrace but then checks to see if the functions were actually enabled. The case of one function that was marked notrace, but was followed by an unused weak function that was traced. The unused function's call to fentry was added to the __mcount_loc section, and kallsyms retrieved the untraced function's symbol as the weak function was overridden. Since the untraced function would not get traced, the BPF check would detect this and fail. The real fix would be to fix kallsyms to not show addresses of weak functions as the function before it. But that would require adding code in the build to add function size to kallsyms so that it can know when the function ends instead of just using the start of the next known symbol. In the mean time, this is a work around. Add a FTRACE_MCOUNT_MAX_OFFSET macro that if defined, ftrace will ignore any function that has its call to fentry/mcount that has an offset from the symbol that is greater than FTRACE_MCOUNT_MAX_OFFSET. If CONFIG_HAVE_FENTRY is defined for x86, define FTRACE_MCOUNT_MAX_OFFSET to zero (unless IBT is enabled), which will have ftrace ignore all locations that are not at the start of the function (or one after the ENDBR instruction). A worker thread is added at boot up to scan all the ftrace record entries, and will mark any that fail the FTRACE_MCOUNT_MAX_OFFSET test as disabled. They will still appear in the available_filter_functions file as: __ftrace_invalid_address___ (showing the offset that caused it to be invalid). This is required for tools that use libtracefs (like trace-cmd does) that scan the available_filter_functions and enable set_ftrace_filter and set_ftrace_notrace using indexes of the function listed in the file (this is a speedup, as enabling thousands of files via names is an O(n^2) operation and can take minutes to complete, where the indexing takes less than a second). The invalid functions cannot be removed from available_filter_functions as the names there correspond to the ftrace records in the array that manages them (and the indexing depends on this). [1] https://lore.kernel.org/all/20220412094923.0abe90955e5db486b7bca279@kernel.org/ Link: https://lkml.kernel.org/r/20220526141912.794c2786@gandalf.local.home Signed-off-by: Steven Rostedt (Google) --- arch/x86/include/asm/ftrace.h | 7 +++ kernel/trace/ftrace.c | 141 +++++++++++++++++++++++++++++++++++++++++- 2 files changed, 146 insertions(+), 2 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 024d9797646e..b5ef474be858 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -9,6 +9,13 @@ # define MCOUNT_ADDR ((unsigned long)(__fentry__)) #define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */ +/* Ignore unused weak functions which will have non zero offsets */ +#ifdef CONFIG_HAVE_FENTRY +# include +/* Add offset for endbr64 if IBT enabled */ +# define FTRACE_MCOUNT_MAX_OFFSET ENDBR_INSN_SIZE +#endif + #ifdef CONFIG_DYNAMIC_FTRACE #define ARCH_SUPPORTS_FTRACE_OPS 1 #endif diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index d653ef4febc5..c5088c76a108 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -45,6 +45,8 @@ #include "trace_output.h" #include "trace_stat.h" +#define FTRACE_INVALID_FUNCTION "__ftrace_invalid_address__" + #define FTRACE_WARN_ON(cond) \ ({ \ int ___r = cond; \ @@ -3654,6 +3656,105 @@ static void add_trampoline_func(struct seq_file *m, struct ftrace_ops *ops, seq_printf(m, " ->%pS", ptr); } +#ifdef FTRACE_MCOUNT_MAX_OFFSET +/* + * Weak functions can still have an mcount/fentry that is saved in + * the __mcount_loc section. These can be detected by having a + * symbol offset of greater than FTRACE_MCOUNT_MAX_OFFSET, as the + * symbol found by kallsyms is not the function that the mcount/fentry + * is part of. The offset is much greater in these cases. + * + * Test the record to make sure that the ip points to a valid kallsyms + * and if not, mark it disabled. + */ +static int test_for_valid_rec(struct dyn_ftrace *rec) +{ + char str[KSYM_SYMBOL_LEN]; + unsigned long offset; + const char *ret; + + ret = kallsyms_lookup(rec->ip, NULL, &offset, NULL, str); + + /* Weak functions can cause invalid addresses */ + if (!ret || offset > FTRACE_MCOUNT_MAX_OFFSET) { + rec->flags |= FTRACE_FL_DISABLED; + return 0; + } + return 1; +} + +static struct workqueue_struct *ftrace_check_wq __initdata; +static struct work_struct ftrace_check_work __initdata; + +/* + * Scan all the mcount/fentry entries to make sure they are valid. + */ +static __init void ftrace_check_work_func(struct work_struct *work) +{ + struct ftrace_page *pg; + struct dyn_ftrace *rec; + + mutex_lock(&ftrace_lock); + do_for_each_ftrace_rec(pg, rec) { + test_for_valid_rec(rec); + } while_for_each_ftrace_rec(); + mutex_unlock(&ftrace_lock); +} + +static int __init ftrace_check_for_weak_functions(void) +{ + INIT_WORK(&ftrace_check_work, ftrace_check_work_func); + + ftrace_check_wq = alloc_workqueue("ftrace_check_wq", WQ_UNBOUND, 0); + + queue_work(ftrace_check_wq, &ftrace_check_work); + return 0; +} + +static int __init ftrace_check_sync(void) +{ + /* Make sure the ftrace_check updates are finished */ + if (ftrace_check_wq) + destroy_workqueue(ftrace_check_wq); + return 0; +} + +late_initcall_sync(ftrace_check_sync); +subsys_initcall(ftrace_check_for_weak_functions); + +static int print_rec(struct seq_file *m, unsigned long ip) +{ + unsigned long offset; + char str[KSYM_SYMBOL_LEN]; + char *modname; + const char *ret; + + ret = kallsyms_lookup(ip, NULL, &offset, &modname, str); + /* Weak functions can cause invalid addresses */ + if (!ret || offset > FTRACE_MCOUNT_MAX_OFFSET) { + snprintf(str, KSYM_SYMBOL_LEN, "%s_%ld", + FTRACE_INVALID_FUNCTION, offset); + ret = NULL; + } + + seq_puts(m, str); + if (modname) + seq_printf(m, " [%s]", modname); + return ret == NULL ? -1 : 0; +} +#else +static inline int test_for_valid_rec(struct dyn_ftrace *rec) +{ + return 1; +} + +static inline int print_rec(struct seq_file *m, unsigned long ip) +{ + seq_printf(m, "%ps", (void *)ip); + return 0; +} +#endif + static int t_show(struct seq_file *m, void *v) { struct ftrace_iterator *iter = m->private; @@ -3678,7 +3779,13 @@ static int t_show(struct seq_file *m, void *v) if (!rec) return 0; - seq_printf(m, "%ps", (void *)rec->ip); + if (print_rec(m, rec->ip)) { + /* This should only happen when a rec is disabled */ + WARN_ON_ONCE(!(rec->flags & FTRACE_FL_DISABLED)); + seq_putc(m, '\n'); + return 0; + } + if (iter->flags & FTRACE_ITER_ENABLED) { struct ftrace_ops *ops; @@ -3996,6 +4103,24 @@ add_rec_by_index(struct ftrace_hash *hash, struct ftrace_glob *func_g, return 0; } +#ifdef FTRACE_MCOUNT_MAX_OFFSET +static int lookup_ip(unsigned long ip, char **modname, char *str) +{ + unsigned long offset; + + kallsyms_lookup(ip, NULL, &offset, modname, str); + if (offset > FTRACE_MCOUNT_MAX_OFFSET) + return -1; + return 0; +} +#else +static int lookup_ip(unsigned long ip, char **modname, char *str) +{ + kallsyms_lookup(ip, NULL, NULL, modname, str); + return 0; +} +#endif + static int ftrace_match_record(struct dyn_ftrace *rec, struct ftrace_glob *func_g, struct ftrace_glob *mod_g, int exclude_mod) @@ -4003,7 +4128,12 @@ ftrace_match_record(struct dyn_ftrace *rec, struct ftrace_glob *func_g, char str[KSYM_SYMBOL_LEN]; char *modname; - kallsyms_lookup(rec->ip, NULL, NULL, &modname, str); + if (lookup_ip(rec->ip, &modname, str)) { + /* This should only happen when a rec is disabled */ + WARN_ON_ONCE(system_state == SYSTEM_RUNNING && + !(rec->flags & FTRACE_FL_DISABLED)); + return 0; + } if (mod_g) { int mod_matches = (modname) ? ftrace_match(modname, mod_g) : 0; @@ -6819,6 +6949,13 @@ void ftrace_module_enable(struct module *mod) !within_module_init(rec->ip, mod)) break; + /* Weak functions should still be ignored */ + if (!test_for_valid_rec(rec)) { + /* Clear all other flags. Should not be enabled anyway */ + rec->flags = FTRACE_FL_DISABLED; + continue; + } + cnt = 0; /* -- cgit v1.2.3