From 7d137e604aaacf2723ced2fca0b46b3f563e1d5e Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 23 Dec 2024 13:46:19 -0500 Subject: fgraph: Remove unnecessary disabling of interrupts and recursion The function graph tracer disables interrupts as well as prevents recursion via NMIs when recording the graph tracer code. There's no reason to do this today. That disabling goes back to 2008 when the function graph tracer was first introduced and recursion protection wasn't part of the code. Today, there's no reason to disable interrupts or prevent the code from recursing as the infrastructure can easily handle it. Before this change: ~# echo function_graph > /sys/kernel/tracing/current_tracer ~# perf stat -r 10 ./hackbench 10 Time: 4.240 Time: 4.236 Time: 4.106 Time: 4.014 Time: 4.314 Time: 3.830 Time: 4.063 Time: 4.323 Time: 3.763 Time: 3.727 Performance counter stats for '/work/c/hackbench 10' (10 runs): 33,937.20 msec task-clock # 7.008 CPUs utilized ( +- 1.85% ) 18,220 context-switches # 536.874 /sec ( +- 6.41% ) 624 cpu-migrations # 18.387 /sec ( +- 9.07% ) 11,319 page-faults # 333.528 /sec ( +- 1.97% ) 76,657,643,617 cycles # 2.259 GHz ( +- 0.40% ) 141,403,302,768 instructions # 1.84 insn per cycle ( +- 0.37% ) 25,518,463,888 branches # 751.932 M/sec ( +- 0.35% ) 156,151,050 branch-misses # 0.61% of all branches ( +- 0.63% ) 4.8423 +- 0.0892 seconds time elapsed ( +- 1.84% ) After this change: ~# echo function_graph > /sys/kernel/tracing/current_tracer ~# perf stat -r 10 ./hackbench 10 Time: 3.340 Time: 3.192 Time: 3.129 Time: 2.579 Time: 2.589 Time: 2.798 Time: 2.791 Time: 2.955 Time: 3.044 Time: 3.065 Performance counter stats for './hackbench 10' (10 runs): 24,416.30 msec task-clock # 6.996 CPUs utilized ( +- 2.74% ) 16,764 context-switches # 686.590 /sec ( +- 5.85% ) 469 cpu-migrations # 19.208 /sec ( +- 6.14% ) 11,519 page-faults # 471.775 /sec ( +- 1.92% ) 53,895,628,450 cycles # 2.207 GHz ( +- 0.52% ) 105,552,664,638 instructions # 1.96 insn per cycle ( +- 0.47% ) 17,808,672,667 branches # 729.376 M/sec ( +- 0.48% ) 133,075,435 branch-misses # 0.75% of all branches ( +- 0.59% ) 3.490 +- 0.112 seconds time elapsed ( +- 3.22% ) Also removed unneeded "unlikely()" around the retaddr code. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://lore.kernel.org/20241223184941.204074053@goodmis.org Fixes: 9cd2992f2d6c8 ("fgraph: Have set_graph_notrace only affect function_graph tracer") # Performance only Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_functions_graph.c | 37 +++++++++++++++--------------------- 1 file changed, 15 insertions(+), 22 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 5504b5e4e7b4..f513603d7df9 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -181,10 +181,9 @@ int trace_graph_entry(struct ftrace_graph_ent *trace, struct trace_array *tr = gops->private; struct trace_array_cpu *data; struct fgraph_times *ftimes; - unsigned long flags; unsigned int trace_ctx; long disabled; - int ret; + int ret = 0; int cpu; if (*task_var & TRACE_GRAPH_NOTRACE) @@ -235,25 +234,21 @@ int trace_graph_entry(struct ftrace_graph_ent *trace, if (tracing_thresh) return 1; - local_irq_save(flags); + preempt_disable_notrace(); cpu = raw_smp_processor_id(); data = per_cpu_ptr(tr->array_buffer.data, cpu); - disabled = atomic_inc_return(&data->disabled); - if (likely(disabled == 1)) { - trace_ctx = tracing_gen_ctx_flags(flags); - if (unlikely(IS_ENABLED(CONFIG_FUNCTION_GRAPH_RETADDR) && - tracer_flags_is_set(TRACE_GRAPH_PRINT_RETADDR))) { + disabled = atomic_read(&data->disabled); + if (likely(!disabled)) { + trace_ctx = tracing_gen_ctx(); + if (IS_ENABLED(CONFIG_FUNCTION_GRAPH_RETADDR) && + tracer_flags_is_set(TRACE_GRAPH_PRINT_RETADDR)) { unsigned long retaddr = ftrace_graph_top_ret_addr(current); - ret = __trace_graph_retaddr_entry(tr, trace, trace_ctx, retaddr); - } else + } else { ret = __trace_graph_entry(tr, trace, trace_ctx); - } else { - ret = 0; + } } - - atomic_dec(&data->disabled); - local_irq_restore(flags); + preempt_enable_notrace(); return ret; } @@ -320,7 +315,6 @@ void trace_graph_return(struct ftrace_graph_ret *trace, struct trace_array *tr = gops->private; struct trace_array_cpu *data; struct fgraph_times *ftimes; - unsigned long flags; unsigned int trace_ctx; long disabled; int size; @@ -341,16 +335,15 @@ void trace_graph_return(struct ftrace_graph_ret *trace, trace->calltime = ftimes->calltime; - local_irq_save(flags); + preempt_disable_notrace(); cpu = raw_smp_processor_id(); data = per_cpu_ptr(tr->array_buffer.data, cpu); - disabled = atomic_inc_return(&data->disabled); - if (likely(disabled == 1)) { - trace_ctx = tracing_gen_ctx_flags(flags); + disabled = atomic_read(&data->disabled); + if (likely(!disabled)) { + trace_ctx = tracing_gen_ctx(); __trace_graph_return(tr, trace, trace_ctx); } - atomic_dec(&data->disabled); - local_irq_restore(flags); + preempt_enable_notrace(); } static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, -- cgit v1.2.3 From ac8c3b02fc33be9deda48532326d301333d39f16 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 23 Dec 2024 13:46:20 -0500 Subject: ftrace: Do not disable interrupts in profiler The function profiler disables interrupts before processing. This was there since the profiler was introduced back in 2009 when there were recursion issues to deal with. The function tracer is much more robust today and has its own internal recursion protection. There's no reason to disable interrupts in the function profiler. Instead, just disable preemption and use the guard() infrastructure while at it. Before this change: ~# echo 1 > /sys/kernel/tracing/function_profile_enabled ~# perf stat -r 10 ./hackbench 10 Time: 3.099 Time: 2.556 Time: 2.500 Time: 2.705 Time: 2.985 Time: 2.959 Time: 2.859 Time: 2.621 Time: 2.742 Time: 2.631 Performance counter stats for '/work/c/hackbench 10' (10 runs): 23,156.77 msec task-clock # 6.951 CPUs utilized ( +- 2.36% ) 18,306 context-switches # 790.525 /sec ( +- 5.95% ) 495 cpu-migrations # 21.376 /sec ( +- 8.61% ) 11,522 page-faults # 497.565 /sec ( +- 1.80% ) 47,967,124,606 cycles # 2.071 GHz ( +- 0.41% ) 80,009,078,371 instructions # 1.67 insn per cycle ( +- 0.34% ) 16,389,249,798 branches # 707.752 M/sec ( +- 0.36% ) 139,943,109 branch-misses # 0.85% of all branches ( +- 0.61% ) 3.332 +- 0.101 seconds time elapsed ( +- 3.04% ) After this change: ~# echo 1 > /sys/kernel/tracing/function_profile_enabled ~# perf stat -r 10 ./hackbench 10 Time: 1.869 Time: 1.428 Time: 1.575 Time: 1.569 Time: 1.685 Time: 1.511 Time: 1.611 Time: 1.672 Time: 1.724 Time: 1.715 Performance counter stats for '/work/c/hackbench 10' (10 runs): 13,578.21 msec task-clock # 6.931 CPUs utilized ( +- 2.23% ) 12,736 context-switches # 937.973 /sec ( +- 3.86% ) 341 cpu-migrations # 25.114 /sec ( +- 5.27% ) 11,378 page-faults # 837.960 /sec ( +- 1.74% ) 27,638,039,036 cycles # 2.035 GHz ( +- 0.27% ) 45,107,762,498 instructions # 1.63 insn per cycle ( +- 0.23% ) 8,623,868,018 branches # 635.125 M/sec ( +- 0.27% ) 125,738,443 branch-misses # 1.46% of all branches ( +- 0.32% ) 1.9590 +- 0.0484 seconds time elapsed ( +- 2.47% ) Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://lore.kernel.org/20241223184941.373853944@goodmis.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 20 +++++++------------- 1 file changed, 7 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 9b17efb1a87d..63a9ffa65e17 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -789,27 +789,24 @@ function_profile_call(unsigned long ip, unsigned long parent_ip, { struct ftrace_profile_stat *stat; struct ftrace_profile *rec; - unsigned long flags; if (!ftrace_profile_enabled) return; - local_irq_save(flags); + guard(preempt_notrace)(); stat = this_cpu_ptr(&ftrace_profile_stats); if (!stat->hash || !ftrace_profile_enabled) - goto out; + return; rec = ftrace_find_profiled_func(stat, ip); if (!rec) { rec = ftrace_profile_alloc(stat, ip); if (!rec) - goto out; + return; } rec->counter++; - out: - local_irq_restore(flags); } #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -856,19 +853,19 @@ static void profile_graph_return(struct ftrace_graph_ret *trace, unsigned long long calltime; unsigned long long rettime = trace_clock_local(); struct ftrace_profile *rec; - unsigned long flags; int size; - local_irq_save(flags); + guard(preempt_notrace)(); + stat = this_cpu_ptr(&ftrace_profile_stats); if (!stat->hash || !ftrace_profile_enabled) - goto out; + return; profile_data = fgraph_retrieve_data(gops->idx, &size); /* If the calltime was zero'd ignore it */ if (!profile_data || !profile_data->calltime) - goto out; + return; calltime = rettime - profile_data->calltime; @@ -896,9 +893,6 @@ static void profile_graph_return(struct ftrace_graph_ret *trace, rec->time += calltime; rec->time_squared += calltime * calltime; } - - out: - local_irq_restore(flags); } static struct fgraph_ops fprofiler_ops = { -- cgit v1.2.3 From 77e53cb2fcf2c5e81f06f4a41783d8752cf9d038 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 23 Dec 2024 13:46:21 -0500 Subject: ftrace: Remove unneeded goto jumps There are some goto jumps to exit a program to just return a value. The code after the label doesn't free anything nor does it do any unlocks. It simply returns the variable that was set before the jump. Remove these unneeded goto jumps. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://lore.kernel.org/20241223184941.544855549@goodmis.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 63a9ffa65e17..2c1691aa1d2f 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1669,14 +1669,12 @@ unsigned long ftrace_location(unsigned long ip) loc = ftrace_location_range(ip, ip); if (!loc) { if (!kallsyms_lookup_size_offset(ip, &size, &offset)) - goto out; + return 0; /* map sym+0 to __fentry__ */ if (!offset) loc = ftrace_location_range(ip, ip + size - 1); } - -out: return loc; } @@ -2071,7 +2069,7 @@ rollback: continue; if (rec == end) - goto err_out; + return -EBUSY; in_old = !!ftrace_lookup_ip(old_hash, rec->ip); in_new = !!ftrace_lookup_ip(new_hash, rec->ip); @@ -2084,7 +2082,6 @@ rollback: rec->flags |= FTRACE_FL_IPMODIFY; } while_for_each_ftrace_rec(); -err_out: return -EBUSY; } @@ -5720,12 +5717,10 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, parser->idx, enable); trace_parser_clear(parser); if (ret < 0) - goto out; + return ret; } - ret = read; - out: - return ret; + return read; } ssize_t -- cgit v1.2.3 From 1d95fd9d6b1a1750da2dec1485a4c58f5a7d3ebd Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 23 Dec 2024 13:46:22 -0500 Subject: ftrace: Switch ftrace.c code over to use guard() There are a few functions in ftrace.c that have "goto out" or equivalent on error in order to release locks that were taken. This can be error prone or just simply make the code more complex. Switch every location that ends with unlocking a mutex on error over to using the guard(mutex)() infrastructure to let the compiler worry about releasing locks. This makes the code easier to read and understand. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://lore.kernel.org/20241223184941.718001540@goodmis.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 97 ++++++++++++++++++--------------------------------- 1 file changed, 34 insertions(+), 63 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 2c1691aa1d2f..6ebc76bafd38 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -536,24 +536,21 @@ static int function_stat_show(struct seq_file *m, void *v) { struct ftrace_profile *rec = v; char str[KSYM_SYMBOL_LEN]; - int ret = 0; #ifdef CONFIG_FUNCTION_GRAPH_TRACER static struct trace_seq s; unsigned long long avg; unsigned long long stddev; #endif - mutex_lock(&ftrace_profile_lock); + guard(mutex)(&ftrace_profile_lock); /* we raced with function_profile_reset() */ - if (unlikely(rec->counter == 0)) { - ret = -EBUSY; - goto out; - } + if (unlikely(rec->counter == 0)) + return -EBUSY; #ifdef CONFIG_FUNCTION_GRAPH_TRACER avg = div64_ul(rec->time, rec->counter); if (tracing_thresh && (avg < tracing_thresh)) - goto out; + return 0; #endif kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); @@ -590,10 +587,8 @@ static int function_stat_show(struct seq_file *m, void *v) trace_print_seq(m, &s); #endif seq_putc(m, '\n'); -out: - mutex_unlock(&ftrace_profile_lock); - return ret; + return 0; } static void ftrace_profile_reset(struct ftrace_profile_stat *stat) @@ -944,20 +939,16 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf, val = !!val; - mutex_lock(&ftrace_profile_lock); + guard(mutex)(&ftrace_profile_lock); if (ftrace_profile_enabled ^ val) { if (val) { ret = ftrace_profile_init(); - if (ret < 0) { - cnt = ret; - goto out; - } + if (ret < 0) + return ret; ret = register_ftrace_profiler(); - if (ret < 0) { - cnt = ret; - goto out; - } + if (ret < 0) + return ret; ftrace_profile_enabled = 1; } else { ftrace_profile_enabled = 0; @@ -968,8 +959,6 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf, unregister_ftrace_profiler(); } } - out: - mutex_unlock(&ftrace_profile_lock); *ppos += cnt; @@ -5610,20 +5599,15 @@ static DEFINE_MUTEX(ftrace_cmd_mutex); __init int register_ftrace_command(struct ftrace_func_command *cmd) { struct ftrace_func_command *p; - int ret = 0; - mutex_lock(&ftrace_cmd_mutex); + guard(mutex)(&ftrace_cmd_mutex); list_for_each_entry(p, &ftrace_commands, list) { - if (strcmp(cmd->name, p->name) == 0) { - ret = -EBUSY; - goto out_unlock; - } + if (strcmp(cmd->name, p->name) == 0) + return -EBUSY; } list_add(&cmd->list, &ftrace_commands); - out_unlock: - mutex_unlock(&ftrace_cmd_mutex); - return ret; + return 0; } /* @@ -5633,20 +5617,17 @@ __init int register_ftrace_command(struct ftrace_func_command *cmd) __init int unregister_ftrace_command(struct ftrace_func_command *cmd) { struct ftrace_func_command *p, *n; - int ret = -ENODEV; - mutex_lock(&ftrace_cmd_mutex); + guard(mutex)(&ftrace_cmd_mutex); + list_for_each_entry_safe(p, n, &ftrace_commands, list) { if (strcmp(cmd->name, p->name) == 0) { - ret = 0; list_del_init(&p->list); - goto out_unlock; + return 0; } } - out_unlock: - mutex_unlock(&ftrace_cmd_mutex); - return ret; + return -ENODEV; } static int ftrace_process_regex(struct ftrace_iterator *iter, @@ -5656,7 +5637,7 @@ static int ftrace_process_regex(struct ftrace_iterator *iter, struct trace_array *tr = iter->ops->private; char *func, *command, *next = buff; struct ftrace_func_command *p; - int ret = -EINVAL; + int ret; func = strsep(&next, ":"); @@ -5673,17 +5654,14 @@ static int ftrace_process_regex(struct ftrace_iterator *iter, command = strsep(&next, ":"); - mutex_lock(&ftrace_cmd_mutex); + guard(mutex)(&ftrace_cmd_mutex); + list_for_each_entry(p, &ftrace_commands, list) { - if (strcmp(p->name, command) == 0) { - ret = p->func(tr, hash, func, command, next, enable); - goto out_unlock; - } + if (strcmp(p->name, command) == 0) + return p->func(tr, hash, func, command, next, enable); } - out_unlock: - mutex_unlock(&ftrace_cmd_mutex); - return ret; + return -EINVAL; } static ssize_t @@ -8280,7 +8258,7 @@ pid_write(struct file *filp, const char __user *ubuf, if (!cnt) return 0; - mutex_lock(&ftrace_lock); + guard(mutex)(&ftrace_lock); switch (type) { case TRACE_PIDS: @@ -8296,14 +8274,13 @@ pid_write(struct file *filp, const char __user *ubuf, lockdep_is_held(&ftrace_lock)); break; default: - ret = -EINVAL; WARN_ON_ONCE(1); - goto out; + return -EINVAL; } ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt); if (ret < 0) - goto out; + return ret; switch (type) { case TRACE_PIDS: @@ -8332,11 +8309,8 @@ pid_write(struct file *filp, const char __user *ubuf, ftrace_update_pid_func(); ftrace_startup_all(0); - out: - mutex_unlock(&ftrace_lock); - if (ret > 0) - *ppos += ret; + *ppos += ret; return ret; } @@ -8739,17 +8713,17 @@ static int ftrace_enable_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - int ret = -ENODEV; + int ret; - mutex_lock(&ftrace_lock); + guard(mutex)(&ftrace_lock); if (unlikely(ftrace_disabled)) - goto out; + return -ENODEV; ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled)) - goto out; + return ret; if (ftrace_enabled) { @@ -8763,8 +8737,7 @@ ftrace_enable_sysctl(const struct ctl_table *table, int write, } else { if (is_permanent_ops_registered()) { ftrace_enabled = true; - ret = -EBUSY; - goto out; + return -EBUSY; } /* stopping ftrace calls (just send to ftrace_stub) */ @@ -8774,9 +8747,7 @@ ftrace_enable_sysctl(const struct ctl_table *table, int write, } last_ftrace_enabled = !!ftrace_enabled; - out: - mutex_unlock(&ftrace_lock); - return ret; + return 0; } static struct ctl_table ftrace_sysctls[] = { -- cgit v1.2.3 From d576aec24df9f58ed0ebe2ff854daafe837f0225 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Tue, 10 Dec 2024 11:08:57 +0900 Subject: fgraph: Get ftrace recursion lock in function_graph_enter Get the ftrace recursion lock in the generic function_graph_enter() instead of each architecture code. This changes all function_graph tracer callbacks running in non-preemptive state. On x86 and powerpc, this is by default, but on the other architecutres, this will be new. Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Christophe Leroy Cc: Naveen N Rao Cc: Madhavan Srinivasan Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: x86@kernel.org Cc: "H. Peter Anvin" Cc: Mathieu Desnoyers Link: https://lore.kernel.org/173379653720.973433.18438622234884980494.stgit@devnote2 Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/fgraph.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index ddedcb50917f..5c68d6109119 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -650,8 +650,13 @@ int function_graph_enter(unsigned long ret, unsigned long func, struct ftrace_graph_ent trace; unsigned long bitmap = 0; int offset; + int bit; int i; + bit = ftrace_test_recursion_trylock(func, ret); + if (bit < 0) + return -EBUSY; + trace.func = func; trace.depth = ++current->curr_ret_depth; @@ -697,12 +702,13 @@ int function_graph_enter(unsigned long ret, unsigned long func, * flag, set that bit always. */ set_bitmap(current, offset, bitmap | BIT(0)); - + ftrace_test_recursion_unlock(bit); return 0; out_ret: current->curr_ret_stack -= FGRAPH_FRAME_OFFSET + 1; out: current->curr_ret_depth--; + ftrace_test_recursion_unlock(bit); return -EBUSY; } -- cgit v1.2.3 From 41705c4262aaca49b8d9fe9b24fe048dc6c2b301 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:11:40 +0900 Subject: fgraph: Pass ftrace_regs to entryfunc Pass ftrace_regs to the fgraph_ops::entryfunc(). If ftrace_regs is not available, it passes a NULL instead. User callback function can access some registers (including return address) via this ftrace_regs. Note that the ftrace_regs can be NULL when the arch does NOT define: HAVE_DYNAMIC_FTRACE_WITH_ARGS or HAVE_DYNAMIC_FTRACE_WITH_REGS. More specifically, if HAVE_DYNAMIC_FTRACE_WITH_REGS is defined but not the HAVE_DYNAMIC_FTRACE_WITH_ARGS, and the ftrace ops used to register the function callback does not set FTRACE_OPS_FL_SAVE_REGS. In this case, ftrace_regs can be NULL in user callback. Signed-off-by: Masami Hiramatsu (Google) Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Cc: Catalin Marinas Cc: Will Deacon Cc: Huacai Chen Cc: WANG Xuerui Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Christophe Leroy Cc: Naveen N Rao Cc: Madhavan Srinivasan Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: x86@kernel.org Cc: "H. Peter Anvin" Cc: Mathieu Desnoyers Link: https://lore.kernel.org/173518990044.391279.17406984900626078579.stgit@devnote2 Signed-off-by: Steven Rostedt (Google) --- kernel/trace/fgraph.c | 20 ++++++++++++-------- kernel/trace/ftrace.c | 3 ++- kernel/trace/trace.h | 3 ++- kernel/trace/trace_functions_graph.c | 3 ++- kernel/trace/trace_irqsoff.c | 3 ++- kernel/trace/trace_sched_wakeup.c | 3 ++- kernel/trace/trace_selftest.c | 8 +++++--- 7 files changed, 27 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 5c68d6109119..4791fd704e28 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -292,7 +292,8 @@ static inline unsigned long make_data_type_val(int idx, int size, int offset) } /* ftrace_graph_entry set to this to tell some archs to run function graph */ -static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops) +static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops, + struct ftrace_regs *fregs) { return 0; } @@ -520,7 +521,8 @@ int __weak ftrace_disable_ftrace_graph_caller(void) #endif int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { return 0; } @@ -644,8 +646,9 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, #endif /* If the caller does not use ftrace, call this function. */ -int function_graph_enter(unsigned long ret, unsigned long func, - unsigned long frame_pointer, unsigned long *retp) +int function_graph_enter_regs(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp, + struct ftrace_regs *fregs) { struct ftrace_graph_ent trace; unsigned long bitmap = 0; @@ -668,7 +671,7 @@ int function_graph_enter(unsigned long ret, unsigned long func, if (static_branch_likely(&fgraph_do_direct)) { int save_curr_ret_stack = current->curr_ret_stack; - if (static_call(fgraph_func)(&trace, fgraph_direct_gops)) + if (static_call(fgraph_func)(&trace, fgraph_direct_gops, fregs)) bitmap |= BIT(fgraph_direct_gops->idx); else /* Clear out any saved storage */ @@ -686,7 +689,7 @@ int function_graph_enter(unsigned long ret, unsigned long func, save_curr_ret_stack = current->curr_ret_stack; if (ftrace_ops_test(&gops->ops, func, NULL) && - gops->entryfunc(&trace, gops)) + gops->entryfunc(&trace, gops, fregs)) bitmap |= BIT(i); else /* Clear out any saved storage */ @@ -1180,7 +1183,8 @@ void ftrace_graph_exit_task(struct task_struct *t) #ifdef CONFIG_DYNAMIC_FTRACE static int fgraph_pid_func(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = gops->ops.private; int pid; @@ -1194,7 +1198,7 @@ static int fgraph_pid_func(struct ftrace_graph_ent *trace, return 0; } - return gops->saved_func(trace, gops); + return gops->saved_func(trace, gops, fregs); } void fgraph_update_pid_func(void) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6ebc76bafd38..ae29e1c4177d 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -819,7 +819,8 @@ struct profile_fgraph_data { }; static int profile_graph_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct profile_fgraph_data *profile_data; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 9691b47b5f3d..0f38f36a5a8a 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -694,7 +694,8 @@ void trace_default_header(struct seq_file *m); void print_trace_header(struct seq_file *m, struct trace_iterator *iter); void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops); -int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops); +int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, + struct ftrace_regs *fregs); void tracing_start_cmdline_record(void); void tracing_stop_cmdline_record(void); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index f513603d7df9..676cf3e38f51 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -175,7 +175,8 @@ struct fgraph_times { }; int trace_graph_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { unsigned long *task_var = fgraph_get_task_var(gops); struct trace_array *tr = gops->private; diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index fce064e20570..ad739d76fc86 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -176,7 +176,8 @@ static int irqsoff_display_graph(struct trace_array *tr, int set) } static int irqsoff_graph_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = irqsoff_trace; struct trace_array_cpu *data; diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index d6c7f18daa15..0d9e1075d815 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -113,7 +113,8 @@ static int wakeup_display_graph(struct trace_array *tr, int set) } static int wakeup_graph_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = wakeup_trace; struct trace_array_cpu *data; diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 38b5754790c9..f54493f8783d 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -774,7 +774,8 @@ struct fgraph_fixture { }; static __init int store_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct fgraph_fixture *fixture = container_of(gops, struct fgraph_fixture, gops); const char *type = fixture->store_type_name; @@ -1025,7 +1026,8 @@ static unsigned int graph_hang_thresh; /* Wrap the real function entry probe to avoid possible hanging */ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { /* This is harmlessly racy, we want to approximately detect a hang */ if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) { @@ -1039,7 +1041,7 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace, return 0; } - return trace_graph_entry(trace, gops); + return trace_graph_entry(trace, gops, fregs); } static struct fgraph_ops fgraph_ops __initdata = { -- cgit v1.2.3 From a3ed4157b7d89800a0008de0c9e46a438a5c3745 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:11:55 +0900 Subject: fgraph: Replace fgraph_ret_regs with ftrace_regs Use ftrace_regs instead of fgraph_ret_regs for tracing return value on function_graph tracer because of simplifying the callback interface. The CONFIG_HAVE_FUNCTION_GRAPH_RETVAL is also replaced by CONFIG_HAVE_FUNCTION_GRAPH_FREGS. Signed-off-by: Masami Hiramatsu (Google) Acked-by: Heiko Carstens Acked-by: Will Deacon Cc: Catalin Marinas Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Cc: Huacai Chen Cc: WANG Xuerui Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Vasily Gorbik Cc: Alexander Gordeev Cc: Heiko Carstens Cc: Christian Borntraeger Cc: Sven Schnelle Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: x86@kernel.org Cc: "H. Peter Anvin" Cc: Mathieu Desnoyers Link: https://lore.kernel.org/173518991508.391279.16635322774382197642.stgit@devnote2 Signed-off-by: Steven Rostedt (Google) --- kernel/trace/Kconfig | 4 ++-- kernel/trace/fgraph.c | 21 +++++++++------------ 2 files changed, 11 insertions(+), 14 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 74c2b1d43bb9..c5ab2a561272 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -31,7 +31,7 @@ config HAVE_FUNCTION_GRAPH_TRACER help See Documentation/trace/ftrace-design.rst -config HAVE_FUNCTION_GRAPH_RETVAL +config HAVE_FUNCTION_GRAPH_FREGS bool config HAVE_DYNAMIC_FTRACE @@ -232,7 +232,7 @@ config FUNCTION_GRAPH_TRACER config FUNCTION_GRAPH_RETVAL bool "Kernel Function Graph Return Value" - depends on HAVE_FUNCTION_GRAPH_RETVAL + depends on HAVE_FUNCTION_GRAPH_FREGS depends on FUNCTION_GRAPH_TRACER default n help diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 4791fd704e28..51196f10d96e 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -801,15 +801,12 @@ static struct notifier_block ftrace_suspend_notifier = { .notifier_call = ftrace_suspend_notifier_call, }; -/* fgraph_ret_regs is not defined without CONFIG_FUNCTION_GRAPH_RETVAL */ -struct fgraph_ret_regs; - /* * Send the trace to the ring-buffer. * @return the original return address. */ -static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs, - unsigned long frame_pointer) +static inline unsigned long +__ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointer) { struct ftrace_ret_stack *ret_stack; struct ftrace_graph_ret trace; @@ -829,7 +826,7 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs trace.rettime = trace_clock_local(); #ifdef CONFIG_FUNCTION_GRAPH_RETVAL - trace.retval = fgraph_ret_regs_return_value(ret_regs); + trace.retval = ftrace_regs_get_return_value(fregs); #endif bitmap = get_bitmap_bits(current, offset); @@ -864,14 +861,14 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs } /* - * After all architecures have selected HAVE_FUNCTION_GRAPH_RETVAL, we can - * leave only ftrace_return_to_handler(ret_regs). + * After all architecures have selected HAVE_FUNCTION_GRAPH_FREGS, we can + * leave only ftrace_return_to_handler(fregs). */ -#ifdef CONFIG_HAVE_FUNCTION_GRAPH_RETVAL -unsigned long ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs) +#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FREGS +unsigned long ftrace_return_to_handler(struct ftrace_regs *fregs) { - return __ftrace_return_to_handler(ret_regs, - fgraph_ret_regs_frame_pointer(ret_regs)); + return __ftrace_return_to_handler(fregs, + ftrace_regs_get_frame_pointer(fregs)); } #else unsigned long ftrace_return_to_handler(unsigned long frame_pointer) -- cgit v1.2.3 From 2ca8c112c9676e2394d76760db78ffddf21d93b5 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:12:09 +0900 Subject: fgraph: Pass ftrace_regs to retfunc Pass ftrace_regs to the fgraph_ops::retfunc(). If ftrace_regs is not available, it passes a NULL instead. User callback function can access some registers (including return address) via this ftrace_regs. Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Link: https://lore.kernel.org/173518992972.391279.14055405490327765506.stgit@devnote2 Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/fgraph.c | 16 +++++++++++----- kernel/trace/ftrace.c | 3 ++- kernel/trace/trace.h | 3 ++- kernel/trace/trace_functions_graph.c | 7 ++++--- kernel/trace/trace_irqsoff.c | 3 ++- kernel/trace/trace_sched_wakeup.c | 3 ++- kernel/trace/trace_selftest.c | 3 ++- 7 files changed, 25 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 51196f10d96e..c928527251e3 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -299,7 +299,8 @@ static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops, } /* ftrace_graph_return set to this to tell some archs to run function graph */ -static void return_run(struct ftrace_graph_ret *trace, struct fgraph_ops *ops) +static void return_run(struct ftrace_graph_ret *trace, struct fgraph_ops *ops, + struct ftrace_regs *fregs) { } @@ -528,7 +529,8 @@ int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace, } static void ftrace_graph_ret_stub(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { } @@ -825,6 +827,9 @@ __ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointe } trace.rettime = trace_clock_local(); + if (fregs) + ftrace_regs_set_instruction_pointer(fregs, ret); + #ifdef CONFIG_FUNCTION_GRAPH_RETVAL trace.retval = ftrace_regs_get_return_value(fregs); #endif @@ -834,7 +839,7 @@ __ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointe #ifdef CONFIG_HAVE_STATIC_CALL if (static_branch_likely(&fgraph_do_direct)) { if (test_bit(fgraph_direct_gops->idx, &bitmap)) - static_call(fgraph_retfunc)(&trace, fgraph_direct_gops); + static_call(fgraph_retfunc)(&trace, fgraph_direct_gops, fregs); } else #endif { @@ -844,7 +849,7 @@ __ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointe if (gops == &fgraph_stub) continue; - gops->retfunc(&trace, gops); + gops->retfunc(&trace, gops, fregs); } } @@ -1016,7 +1021,8 @@ void ftrace_graph_sleep_time_control(bool enable) * Simply points to ftrace_stub, but with the proper protocol. * Defined by the linker script in linux/vmlinux.lds.h */ -void ftrace_stub_graph(struct ftrace_graph_ret *trace, struct fgraph_ops *gops); +void ftrace_stub_graph(struct ftrace_graph_ret *trace, struct fgraph_ops *gops, + struct ftrace_regs *fregs); /* The callbacks that hook a function */ trace_func_graph_ret_t ftrace_graph_return = ftrace_stub_graph; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index ae29e1c4177d..f054343be026 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -842,7 +842,8 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace, } static void profile_graph_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct profile_fgraph_data *profile_data; struct ftrace_profile_stat *stat; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 0f38f36a5a8a..5f3e68a8d8a0 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -693,7 +693,8 @@ void trace_latency_header(struct seq_file *m); void trace_default_header(struct seq_file *m); void print_trace_header(struct seq_file *m, struct trace_iterator *iter); -void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops); +void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops, + struct ftrace_regs *fregs); int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, struct ftrace_regs *fregs); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 676cf3e38f51..dc62eb93837a 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -310,7 +310,7 @@ static void handle_nosleeptime(struct ftrace_graph_ret *trace, } void trace_graph_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, struct ftrace_regs *fregs) { unsigned long *task_var = fgraph_get_task_var(gops); struct trace_array *tr = gops->private; @@ -348,7 +348,8 @@ void trace_graph_return(struct ftrace_graph_ret *trace, } static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct fgraph_times *ftimes; int size; @@ -372,7 +373,7 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, (trace->rettime - ftimes->calltime < tracing_thresh)) return; else - trace_graph_return(trace, gops); + trace_graph_return(trace, gops, fregs); } static struct fgraph_ops funcgraph_ops = { diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index ad739d76fc86..504de7a05498 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -208,7 +208,8 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace, } static void irqsoff_graph_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = irqsoff_trace; struct trace_array_cpu *data; diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 0d9e1075d815..8165382a174a 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -144,7 +144,8 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace, } static void wakeup_graph_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = wakeup_trace; struct trace_array_cpu *data; diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index f54493f8783d..d88c44f1dfa5 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -808,7 +808,8 @@ static __init int store_entry(struct ftrace_graph_ent *trace, } static __init void store_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct fgraph_fixture *fixture = container_of(gops, struct fgraph_fixture, gops); const char *type = fixture->store_type_name; -- cgit v1.2.3 From 46bc082388560a95e3649b698a4675e5ea3262e6 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:12:20 +0900 Subject: fprobe: Use ftrace_regs in fprobe entry handler This allows fprobes to be available with CONFIG_DYNAMIC_FTRACE_WITH_ARGS instead of CONFIG_DYNAMIC_FTRACE_WITH_REGS, then we can enable fprobe on arm64. Cc: Alexei Starovoitov Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Link: https://lore.kernel.org/173518994037.391279.2786805566359674586.stgit@devnote2 Signed-off-by: Masami Hiramatsu (Google) Acked-by: Florent Revest Signed-off-by: Steven Rostedt (Google) --- kernel/trace/Kconfig | 3 ++- kernel/trace/bpf_trace.c | 10 +++++++--- kernel/trace/fprobe.c | 3 ++- kernel/trace/trace_fprobe.c | 11 ++++++++--- 4 files changed, 19 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index c5ab2a561272..f10ca86fbfad 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -297,7 +297,7 @@ config DYNAMIC_FTRACE_WITH_ARGS config FPROBE bool "Kernel Function Probe (fprobe)" depends on FUNCTION_TRACER - depends on DYNAMIC_FTRACE_WITH_REGS + depends on DYNAMIC_FTRACE_WITH_REGS || DYNAMIC_FTRACE_WITH_ARGS depends on HAVE_RETHOOK select RETHOOK default n @@ -682,6 +682,7 @@ config FPROBE_EVENTS select TRACING select PROBE_EVENTS select DYNAMIC_EVENTS + depends on DYNAMIC_FTRACE_WITH_REGS default y help This allows user to add tracing events on the function entry and diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 1b8db5aee9d3..7bb2e6ecd31f 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2561,7 +2561,7 @@ struct bpf_session_run_ctx { void *data; }; -#ifdef CONFIG_FPROBE +#if defined(CONFIG_FPROBE) && defined(CONFIG_DYNAMIC_FTRACE_WITH_REGS) struct bpf_kprobe_multi_link { struct bpf_link link; struct fprobe fp; @@ -2813,12 +2813,16 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, static int kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *data) { + struct pt_regs *regs = ftrace_get_regs(fregs); struct bpf_kprobe_multi_link *link; int err; + if (!regs) + return 0; + link = container_of(fp, struct bpf_kprobe_multi_link, fp); err = kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, false, data); return is_kprobe_session(link->link.prog) ? err : 0; @@ -3093,7 +3097,7 @@ error: kvfree(cookies); return err; } -#else /* !CONFIG_FPROBE */ +#else /* !CONFIG_FPROBE || !CONFIG_DYNAMIC_FTRACE_WITH_REGS */ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EOPNOTSUPP; diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 9ff018245840..3d3789283873 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -46,7 +46,7 @@ static inline void __fprobe_handler(unsigned long ip, unsigned long parent_ip, } if (fp->entry_handler) - ret = fp->entry_handler(fp, ip, parent_ip, ftrace_get_regs(fregs), entry_data); + ret = fp->entry_handler(fp, ip, parent_ip, fregs, entry_data); /* If entry_handler returns !0, nmissed is not counted. */ if (rh) { @@ -182,6 +182,7 @@ static void fprobe_init(struct fprobe *fp) fp->ops.func = fprobe_kprobe_handler; else fp->ops.func = fprobe_handler; + fp->ops.flags |= FTRACE_OPS_FL_SAVE_REGS; } diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c index c62d1629cffe..0f254685e26a 100644 --- a/kernel/trace/trace_fprobe.c +++ b/kernel/trace/trace_fprobe.c @@ -217,12 +217,13 @@ NOKPROBE_SYMBOL(fentry_trace_func); /* function exit handler */ static int trace_fprobe_entry_handler(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); + struct pt_regs *regs = ftrace_get_regs(fregs); - if (tf->tp.entry_arg) + if (regs && tf->tp.entry_arg) store_trace_entry_data(entry_data, &tf->tp, regs); return 0; @@ -339,12 +340,16 @@ NOKPROBE_SYMBOL(fexit_perf_func); #endif /* CONFIG_PERF_EVENTS */ static int fentry_dispatcher(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); + struct pt_regs *regs = ftrace_get_regs(fregs); int ret = 0; + if (!regs) + return 0; + if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE)) fentry_trace_func(tf, entry_ip, regs); #ifdef CONFIG_PERF_EVENTS -- cgit v1.2.3 From 762abbc0d09f7ae123c82d315eb1a961c1a2cf7b Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:12:31 +0900 Subject: fprobe: Use ftrace_regs in fprobe exit handler Change the fprobe exit handler to use ftrace_regs structure instead of pt_regs. This also introduce HAVE_FTRACE_REGS_HAVING_PT_REGS which means the ftrace_regs is including the pt_regs so that ftrace_regs can provide pt_regs without memory allocation. Fprobe introduces a new dependency with that. Signed-off-by: Masami Hiramatsu (Google) Acked-by: Heiko Carstens # s390 Cc: Huacai Chen Cc: Alexei Starovoitov Cc: Florent Revest Cc: bpf Cc: Alan Maguire Cc: Heiko Carstens Cc: WANG Xuerui Cc: Vasily Gorbik Cc: Alexander Gordeev Cc: Christian Borntraeger Cc: Sven Schnelle Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: x86@kernel.org Cc: "H. Peter Anvin" Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Song Liu Cc: Jiri Olsa Cc: KP Singh Cc: Matt Bobrowski Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Andrii Nakryiko Cc: Martin KaFai Lau Cc: Eduard Zingerman Cc: Yonghong Song Cc: John Fastabend Cc: Stanislav Fomichev Cc: Hao Luo Cc: Andrew Morton Link: https://lore.kernel.org/173518995092.391279.6765116450352977627.stgit@devnote2 Signed-off-by: Steven Rostedt (Google) --- kernel/trace/Kconfig | 7 +++++++ kernel/trace/bpf_trace.c | 6 +++++- kernel/trace/fprobe.c | 3 ++- kernel/trace/trace_fprobe.c | 6 +++++- 4 files changed, 19 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index f10ca86fbfad..7f8165f2049a 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -57,6 +57,12 @@ config HAVE_DYNAMIC_FTRACE_WITH_ARGS This allows for use of ftrace_regs_get_argument() and ftrace_regs_get_stack_pointer(). +config HAVE_FTRACE_REGS_HAVING_PT_REGS + bool + help + If this is set, ftrace_regs has pt_regs, thus it can convert to + pt_regs without allocating memory. + config HAVE_DYNAMIC_FTRACE_NO_PATCHABLE bool help @@ -298,6 +304,7 @@ config FPROBE bool "Kernel Function Probe (fprobe)" depends on FUNCTION_TRACER depends on DYNAMIC_FTRACE_WITH_REGS || DYNAMIC_FTRACE_WITH_ARGS + depends on HAVE_FTRACE_REGS_HAVING_PT_REGS || !HAVE_DYNAMIC_FTRACE_WITH_ARGS depends on HAVE_RETHOOK select RETHOOK default n diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 7bb2e6ecd31f..e469fcbed210 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2830,10 +2830,14 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip, static void kprobe_multi_link_exit_handler(struct fprobe *fp, unsigned long fentry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *data) { struct bpf_kprobe_multi_link *link; + struct pt_regs *regs = ftrace_get_regs(fregs); + + if (!regs) + return; link = container_of(fp, struct bpf_kprobe_multi_link, fp); kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, true, data); diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 3d3789283873..90a3c8e2bbdf 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -124,6 +124,7 @@ static void fprobe_exit_handler(struct rethook_node *rh, void *data, { struct fprobe *fp = (struct fprobe *)data; struct fprobe_rethook_node *fpr; + struct ftrace_regs *fregs = (struct ftrace_regs *)regs; int bit; if (!fp || fprobe_disabled(fp)) @@ -141,7 +142,7 @@ static void fprobe_exit_handler(struct rethook_node *rh, void *data, return; } - fp->exit_handler(fp, fpr->entry_ip, ret_ip, regs, + fp->exit_handler(fp, fpr->entry_ip, ret_ip, fregs, fp->entry_data_size ? (void *)fpr->data : NULL); ftrace_test_recursion_unlock(bit); } diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c index 0f254685e26a..ed49d21269cf 100644 --- a/kernel/trace/trace_fprobe.c +++ b/kernel/trace/trace_fprobe.c @@ -361,10 +361,14 @@ static int fentry_dispatcher(struct fprobe *fp, unsigned long entry_ip, NOKPROBE_SYMBOL(fentry_dispatcher); static void fexit_dispatcher(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); + struct pt_regs *regs = ftrace_get_regs(fregs); + + if (!regs) + return; if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE)) fexit_trace_func(tf, entry_ip, ret_ip, regs, entry_data); -- cgit v1.2.3 From 0566cefe73b9a6ea38357b428d27460db032a03d Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:13:13 +0900 Subject: tracing/fprobe: Enable fprobe events with CONFIG_DYNAMIC_FTRACE_WITH_ARGS Allow fprobe events to be enabled with CONFIG_DYNAMIC_FTRACE_WITH_ARGS. With this change, fprobe events mostly use ftrace_regs instead of pt_regs. Note that if the arch doesn't enable HAVE_FTRACE_REGS_HAVING_PT_REGS, fprobe events will not be able to be used from perf. Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Link: https://lore.kernel.org/173518999352.391279.13332699755290175168.stgit@devnote2 Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/Kconfig | 1 - kernel/trace/trace_fprobe.c | 108 +++++++++++++++++++++++++--------------- kernel/trace/trace_probe_tmpl.h | 2 +- 3 files changed, 69 insertions(+), 42 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 7f8165f2049a..82654bbfad9a 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -689,7 +689,6 @@ config FPROBE_EVENTS select TRACING select PROBE_EVENTS select DYNAMIC_EVENTS - depends on DYNAMIC_FTRACE_WITH_REGS default y help This allows user to add tracing events on the function entry and diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c index ed49d21269cf..5030aaae8183 100644 --- a/kernel/trace/trace_fprobe.c +++ b/kernel/trace/trace_fprobe.c @@ -134,7 +134,7 @@ static int process_fetch_insn(struct fetch_insn *code, void *rec, void *edata, void *dest, void *base) { - struct pt_regs *regs = rec; + struct ftrace_regs *fregs = rec; unsigned long val; int ret; @@ -142,17 +142,17 @@ retry: /* 1st stage: get value from context */ switch (code->op) { case FETCH_OP_STACK: - val = regs_get_kernel_stack_nth(regs, code->param); + val = ftrace_regs_get_kernel_stack_nth(fregs, code->param); break; case FETCH_OP_STACKP: - val = kernel_stack_pointer(regs); + val = ftrace_regs_get_stack_pointer(fregs); break; case FETCH_OP_RETVAL: - val = regs_return_value(regs); + val = ftrace_regs_get_return_value(fregs); break; #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API case FETCH_OP_ARG: - val = regs_get_kernel_argument(regs, code->param); + val = ftrace_regs_get_argument(fregs, code->param); break; case FETCH_OP_EDATA: val = *(unsigned long *)((unsigned long)edata + code->offset); @@ -175,7 +175,7 @@ NOKPROBE_SYMBOL(process_fetch_insn) /* function entry handler */ static nokprobe_inline void __fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, - struct pt_regs *regs, + struct ftrace_regs *fregs, struct trace_event_file *trace_file) { struct fentry_trace_entry_head *entry; @@ -189,42 +189,71 @@ __fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, if (trace_trigger_soft_disabled(trace_file)) return; - dsize = __get_data_size(&tf->tp, regs, NULL); + dsize = __get_data_size(&tf->tp, fregs, NULL); entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry) + tf->tp.size + dsize); if (!entry) return; - fbuffer.regs = regs; + fbuffer.regs = ftrace_get_regs(fregs); entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); entry->ip = entry_ip; - store_trace_args(&entry[1], &tf->tp, regs, NULL, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, fregs, NULL, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); } static void fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, - struct pt_regs *regs) + struct ftrace_regs *fregs) { struct event_file_link *link; trace_probe_for_each_link_rcu(link, &tf->tp) - __fentry_trace_func(tf, entry_ip, regs, link->file); + __fentry_trace_func(tf, entry_ip, fregs, link->file); } NOKPROBE_SYMBOL(fentry_trace_func); +static nokprobe_inline +void store_fprobe_entry_data(void *edata, struct trace_probe *tp, struct ftrace_regs *fregs) +{ + struct probe_entry_arg *earg = tp->entry_arg; + unsigned long val = 0; + int i; + + if (!earg) + return; + + for (i = 0; i < earg->size; i++) { + struct fetch_insn *code = &earg->code[i]; + + switch (code->op) { + case FETCH_OP_ARG: + val = ftrace_regs_get_argument(fregs, code->param); + break; + case FETCH_OP_ST_EDATA: + *(unsigned long *)((unsigned long)edata + code->offset) = val; + break; + case FETCH_OP_END: + goto end; + default: + break; + } + } +end: + return; +} + /* function exit handler */ static int trace_fprobe_entry_handler(struct fprobe *fp, unsigned long entry_ip, unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); - struct pt_regs *regs = ftrace_get_regs(fregs); - if (regs && tf->tp.entry_arg) - store_trace_entry_data(entry_data, &tf->tp, regs); + if (tf->tp.entry_arg) + store_fprobe_entry_data(entry_data, &tf->tp, fregs); return 0; } @@ -232,7 +261,7 @@ NOKPROBE_SYMBOL(trace_fprobe_entry_handler) static nokprobe_inline void __fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data, struct trace_event_file *trace_file) { struct fexit_trace_entry_head *entry; @@ -246,60 +275,63 @@ __fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, if (trace_trigger_soft_disabled(trace_file)) return; - dsize = __get_data_size(&tf->tp, regs, entry_data); + dsize = __get_data_size(&tf->tp, fregs, entry_data); entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry) + tf->tp.size + dsize); if (!entry) return; - fbuffer.regs = regs; + fbuffer.regs = ftrace_get_regs(fregs); entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); entry->func = entry_ip; entry->ret_ip = ret_ip; - store_trace_args(&entry[1], &tf->tp, regs, entry_data, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, fregs, entry_data, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); } static void fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, void *entry_data) + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct event_file_link *link; trace_probe_for_each_link_rcu(link, &tf->tp) - __fexit_trace_func(tf, entry_ip, ret_ip, regs, entry_data, link->file); + __fexit_trace_func(tf, entry_ip, ret_ip, fregs, entry_data, link->file); } NOKPROBE_SYMBOL(fexit_trace_func); #ifdef CONFIG_PERF_EVENTS static int fentry_perf_func(struct trace_fprobe *tf, unsigned long entry_ip, - struct pt_regs *regs) + struct ftrace_regs *fregs) { struct trace_event_call *call = trace_probe_event_call(&tf->tp); struct fentry_trace_entry_head *entry; struct hlist_head *head; int size, __size, dsize; + struct pt_regs *regs; int rctx; head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) return 0; - dsize = __get_data_size(&tf->tp, regs, NULL); + dsize = __get_data_size(&tf->tp, fregs, NULL); __size = sizeof(*entry) + tf->tp.size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - entry = perf_trace_buf_alloc(size, NULL, &rctx); + entry = perf_trace_buf_alloc(size, ®s, &rctx); if (!entry) return 0; + regs = ftrace_fill_perf_regs(fregs, regs); + entry->ip = entry_ip; memset(&entry[1], 0, dsize); - store_trace_args(&entry[1], &tf->tp, regs, NULL, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, fregs, NULL, sizeof(*entry), dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); return 0; @@ -308,31 +340,34 @@ NOKPROBE_SYMBOL(fentry_perf_func); static void fexit_perf_func(struct trace_fprobe *tf, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct trace_event_call *call = trace_probe_event_call(&tf->tp); struct fexit_trace_entry_head *entry; struct hlist_head *head; int size, __size, dsize; + struct pt_regs *regs; int rctx; head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) return; - dsize = __get_data_size(&tf->tp, regs, entry_data); + dsize = __get_data_size(&tf->tp, fregs, entry_data); __size = sizeof(*entry) + tf->tp.size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - entry = perf_trace_buf_alloc(size, NULL, &rctx); + entry = perf_trace_buf_alloc(size, ®s, &rctx); if (!entry) return; + regs = ftrace_fill_perf_regs(fregs, regs); + entry->func = entry_ip; entry->ret_ip = ret_ip; - store_trace_args(&entry[1], &tf->tp, regs, entry_data, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, fregs, entry_data, sizeof(*entry), dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); } @@ -344,17 +379,14 @@ static int fentry_dispatcher(struct fprobe *fp, unsigned long entry_ip, void *entry_data) { struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); - struct pt_regs *regs = ftrace_get_regs(fregs); int ret = 0; - if (!regs) - return 0; - if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE)) - fentry_trace_func(tf, entry_ip, regs); + fentry_trace_func(tf, entry_ip, fregs); + #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tf->tp, TP_FLAG_PROFILE)) - ret = fentry_perf_func(tf, entry_ip, regs); + ret = fentry_perf_func(tf, entry_ip, fregs); #endif return ret; } @@ -365,16 +397,12 @@ static void fexit_dispatcher(struct fprobe *fp, unsigned long entry_ip, void *entry_data) { struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); - struct pt_regs *regs = ftrace_get_regs(fregs); - - if (!regs) - return; if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE)) - fexit_trace_func(tf, entry_ip, ret_ip, regs, entry_data); + fexit_trace_func(tf, entry_ip, ret_ip, fregs, entry_data); #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tf->tp, TP_FLAG_PROFILE)) - fexit_perf_func(tf, entry_ip, ret_ip, regs, entry_data); + fexit_perf_func(tf, entry_ip, ret_ip, fregs, entry_data); #endif } NOKPROBE_SYMBOL(fexit_dispatcher); diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h index 2caf0d2afb32..f39b37fcdb3b 100644 --- a/kernel/trace/trace_probe_tmpl.h +++ b/kernel/trace/trace_probe_tmpl.h @@ -232,7 +232,7 @@ array: /* Sum up total data length for dynamic arrays (strings) */ static nokprobe_inline int -__get_data_size(struct trace_probe *tp, struct pt_regs *regs, void *edata) +__get_data_size(struct trace_probe *tp, void *regs, void *edata) { struct probe_arg *arg; int i, len, ret = 0; -- cgit v1.2.3 From 8e2759da9378120a53078077a44b5a4f6dc95018 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:13:24 +0900 Subject: bpf: Enable kprobe_multi feature if CONFIG_FPROBE is enabled Enable kprobe_multi feature if CONFIG_FPROBE is enabled. The pt_regs is converted from ftrace_regs by ftrace_partial_regs(), thus some registers may always returns 0. But it should be enough for function entry (access arguments) and exit (access return value). Cc: Alexei Starovoitov Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Link: https://lore.kernel.org/173519000417.391279.14011193569589886419.stgit@devnote2 Signed-off-by: Masami Hiramatsu (Google) Acked-by: Florent Revest Signed-off-by: Steven Rostedt (Google) --- kernel/trace/bpf_trace.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index e469fcbed210..863351559334 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2561,7 +2561,7 @@ struct bpf_session_run_ctx { void *data; }; -#if defined(CONFIG_FPROBE) && defined(CONFIG_DYNAMIC_FTRACE_WITH_REGS) +#ifdef CONFIG_FPROBE struct bpf_kprobe_multi_link { struct bpf_link link; struct fprobe fp; @@ -2584,6 +2584,13 @@ struct user_syms { char *buf; }; +#ifndef CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS +static DEFINE_PER_CPU(struct pt_regs, bpf_kprobe_multi_pt_regs); +#define bpf_kprobe_multi_pt_regs_ptr() this_cpu_ptr(&bpf_kprobe_multi_pt_regs) +#else +#define bpf_kprobe_multi_pt_regs_ptr() (NULL) +#endif + static int copy_user_syms(struct user_syms *us, unsigned long __user *usyms, u32 cnt) { unsigned long __user usymbol; @@ -2778,7 +2785,7 @@ static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx) static int kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, - unsigned long entry_ip, struct pt_regs *regs, + unsigned long entry_ip, struct ftrace_regs *fregs, bool is_return, void *data) { struct bpf_kprobe_multi_run_ctx run_ctx = { @@ -2790,6 +2797,7 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, .entry_ip = entry_ip, }; struct bpf_run_ctx *old_run_ctx; + struct pt_regs *regs; int err; if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { @@ -2800,6 +2808,7 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, migrate_disable(); rcu_read_lock(); + regs = ftrace_partial_regs(fregs, bpf_kprobe_multi_pt_regs_ptr()); old_run_ctx = bpf_set_run_ctx(&run_ctx.session_ctx.run_ctx); err = bpf_prog_run(link->link.prog, regs); bpf_reset_run_ctx(old_run_ctx); @@ -2816,15 +2825,11 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip, unsigned long ret_ip, struct ftrace_regs *fregs, void *data) { - struct pt_regs *regs = ftrace_get_regs(fregs); struct bpf_kprobe_multi_link *link; int err; - if (!regs) - return 0; - link = container_of(fp, struct bpf_kprobe_multi_link, fp); - err = kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, false, data); + err = kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), fregs, false, data); return is_kprobe_session(link->link.prog) ? err : 0; } @@ -2834,13 +2839,9 @@ kprobe_multi_link_exit_handler(struct fprobe *fp, unsigned long fentry_ip, void *data) { struct bpf_kprobe_multi_link *link; - struct pt_regs *regs = ftrace_get_regs(fregs); - - if (!regs) - return; link = container_of(fp, struct bpf_kprobe_multi_link, fp); - kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, true, data); + kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), fregs, true, data); } static int symbols_cmp_r(const void *a, const void *b, const void *priv) @@ -3101,7 +3102,7 @@ error: kvfree(cookies); return err; } -#else /* !CONFIG_FPROBE || !CONFIG_DYNAMIC_FTRACE_WITH_REGS */ +#else /* !CONFIG_FPROBE */ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EOPNOTSUPP; -- cgit v1.2.3 From a762e9267dca843ced943ec24f20e110ba7c8431 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:13:34 +0900 Subject: ftrace: Add CONFIG_HAVE_FTRACE_GRAPH_FUNC Add CONFIG_HAVE_FTRACE_GRAPH_FUNC kconfig in addition to ftrace_graph_func macro check. This is for the other feature (e.g. FPROBE) which requires to access ftrace_regs from fgraph_ops::entryfunc() can avoid compiling if the fgraph can not pass the valid ftrace_regs. Signed-off-by: Masami Hiramatsu (Google) Cc: Catalin Marinas Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Cc: Will Deacon Cc: Huacai Chen Cc: WANG Xuerui Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Christophe Leroy Cc: Naveen N Rao Cc: Madhavan Srinivasan Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: x86@kernel.org Cc: "H. Peter Anvin" Cc: Mathieu Desnoyers Link: https://lore.kernel.org/173519001472.391279.1174901685282588467.stgit@devnote2 Signed-off-by: Steven Rostedt (Google) --- kernel/trace/Kconfig | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 82654bbfad9a..2fc55a1a88aa 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -34,6 +34,11 @@ config HAVE_FUNCTION_GRAPH_TRACER config HAVE_FUNCTION_GRAPH_FREGS bool +config HAVE_FTRACE_GRAPH_FUNC + bool + help + True if ftrace_graph_func() is defined. + config HAVE_DYNAMIC_FTRACE bool help -- cgit v1.2.3 From 4346ba1604093305a287e08eb465a9c15ba05b80 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:13:59 +0900 Subject: fprobe: Rewrite fprobe on function-graph tracer Rewrite fprobe implementation on function-graph tracer. Major API changes are: - 'nr_maxactive' field is deprecated. - This depends on CONFIG_DYNAMIC_FTRACE_WITH_ARGS or !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS, and CONFIG_HAVE_FUNCTION_GRAPH_FREGS. So currently works only on x86_64. - Currently the entry size is limited in 15 * sizeof(long). - If there is too many fprobe exit handler set on the same function, it will fail to probe. Signed-off-by: Masami Hiramatsu (Google) Acked-by: Heiko Carstens # s390 Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Heiko Carstens Cc: Mark Rutland Cc: Catalin Marinas Cc: Will Deacon Cc: Huacai Chen Cc: WANG Xuerui Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Christophe Leroy Cc: Naveen N Rao Cc: Madhavan Srinivasan Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Vasily Gorbik Cc: Alexander Gordeev Cc: Christian Borntraeger Cc: Sven Schnelle Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: x86@kernel.org Cc: "H. Peter Anvin" Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://lore.kernel.org/173519003970.391279.14406792285453830996.stgit@devnote2 Signed-off-by: Steven Rostedt (Google) --- kernel/trace/Kconfig | 8 +- kernel/trace/fprobe.c | 637 ++++++++++++++++++++++++++++++++++++-------------- 2 files changed, 460 insertions(+), 185 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 2fc55a1a88aa..d570b8b9c0a9 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -307,11 +307,9 @@ config DYNAMIC_FTRACE_WITH_ARGS config FPROBE bool "Kernel Function Probe (fprobe)" - depends on FUNCTION_TRACER - depends on DYNAMIC_FTRACE_WITH_REGS || DYNAMIC_FTRACE_WITH_ARGS - depends on HAVE_FTRACE_REGS_HAVING_PT_REGS || !HAVE_DYNAMIC_FTRACE_WITH_ARGS - depends on HAVE_RETHOOK - select RETHOOK + depends on HAVE_FUNCTION_GRAPH_FREGS && HAVE_FTRACE_GRAPH_FUNC + depends on DYNAMIC_FTRACE_WITH_ARGS + select FUNCTION_GRAPH_TRACER default n help This option enables kernel function probe (fprobe) based on ftrace. diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 90a3c8e2bbdf..ed9c1d79426a 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -8,98 +8,195 @@ #include #include #include -#include +#include +#include #include #include #include "trace.h" -struct fprobe_rethook_node { - struct rethook_node node; - unsigned long entry_ip; - unsigned long entry_parent_ip; - char data[]; -}; +#define FPROBE_IP_HASH_BITS 8 +#define FPROBE_IP_TABLE_SIZE (1 << FPROBE_IP_HASH_BITS) -static inline void __fprobe_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct ftrace_regs *fregs) -{ - struct fprobe_rethook_node *fpr; - struct rethook_node *rh = NULL; - struct fprobe *fp; - void *entry_data = NULL; - int ret = 0; +#define FPROBE_HASH_BITS 6 +#define FPROBE_TABLE_SIZE (1 << FPROBE_HASH_BITS) - fp = container_of(ops, struct fprobe, ops); +#define SIZE_IN_LONG(x) ((x + sizeof(long) - 1) >> (sizeof(long) == 8 ? 3 : 2)) - if (fp->exit_handler) { - rh = rethook_try_get(fp->rethook); - if (!rh) { - fp->nmissed++; - return; - } - fpr = container_of(rh, struct fprobe_rethook_node, node); - fpr->entry_ip = ip; - fpr->entry_parent_ip = parent_ip; - if (fp->entry_data_size) - entry_data = fpr->data; +/* + * fprobe_table: hold 'fprobe_hlist::hlist' for checking the fprobe still + * exists. The key is the address of fprobe instance. + * fprobe_ip_table: hold 'fprobe_hlist::array[*]' for searching the fprobe + * instance related to the funciton address. The key is the ftrace IP + * address. + * + * When unregistering the fprobe, fprobe_hlist::fp and fprobe_hlist::array[*].fp + * are set NULL and delete those from both hash tables (by hlist_del_rcu). + * After an RCU grace period, the fprobe_hlist itself will be released. + * + * fprobe_table and fprobe_ip_table can be accessed from either + * - Normal hlist traversal and RCU add/del under 'fprobe_mutex' is held. + * - RCU hlist traversal under disabling preempt + */ +static struct hlist_head fprobe_table[FPROBE_TABLE_SIZE]; +static struct hlist_head fprobe_ip_table[FPROBE_IP_TABLE_SIZE]; +static DEFINE_MUTEX(fprobe_mutex); + +/* + * Find first fprobe in the hlist. It will be iterated twice in the entry + * probe, once for correcting the total required size, the second time is + * calling back the user handlers. + * Thus the hlist in the fprobe_table must be sorted and new probe needs to + * be added *before* the first fprobe. + */ +static struct fprobe_hlist_node *find_first_fprobe_node(unsigned long ip) +{ + struct fprobe_hlist_node *node; + struct hlist_head *head; + + head = &fprobe_ip_table[hash_ptr((void *)ip, FPROBE_IP_HASH_BITS)]; + hlist_for_each_entry_rcu(node, head, hlist, + lockdep_is_held(&fprobe_mutex)) { + if (node->addr == ip) + return node; } + return NULL; +} +NOKPROBE_SYMBOL(find_first_fprobe_node); - if (fp->entry_handler) - ret = fp->entry_handler(fp, ip, parent_ip, fregs, entry_data); +/* Node insertion and deletion requires the fprobe_mutex */ +static void insert_fprobe_node(struct fprobe_hlist_node *node) +{ + unsigned long ip = node->addr; + struct fprobe_hlist_node *next; + struct hlist_head *head; - /* If entry_handler returns !0, nmissed is not counted. */ - if (rh) { - if (ret) - rethook_recycle(rh); - else - rethook_hook(rh, ftrace_get_regs(fregs), true); + lockdep_assert_held(&fprobe_mutex); + + next = find_first_fprobe_node(ip); + if (next) { + hlist_add_before_rcu(&node->hlist, &next->hlist); + return; } + head = &fprobe_ip_table[hash_ptr((void *)ip, FPROBE_IP_HASH_BITS)]; + hlist_add_head_rcu(&node->hlist, head); } -static void fprobe_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct ftrace_regs *fregs) +/* Return true if there are synonims */ +static bool delete_fprobe_node(struct fprobe_hlist_node *node) { - struct fprobe *fp; - int bit; + lockdep_assert_held(&fprobe_mutex); - fp = container_of(ops, struct fprobe, ops); - if (fprobe_disabled(fp)) - return; + WRITE_ONCE(node->fp, NULL); + hlist_del_rcu(&node->hlist); + return !!find_first_fprobe_node(node->addr); +} - /* recursion detection has to go before any traceable function and - * all functions before this point should be marked as notrace - */ - bit = ftrace_test_recursion_trylock(ip, parent_ip); - if (bit < 0) { - fp->nmissed++; - return; +/* Check existence of the fprobe */ +static bool is_fprobe_still_exist(struct fprobe *fp) +{ + struct hlist_head *head; + struct fprobe_hlist *fph; + + head = &fprobe_table[hash_ptr(fp, FPROBE_HASH_BITS)]; + hlist_for_each_entry_rcu(fph, head, hlist, + lockdep_is_held(&fprobe_mutex)) { + if (fph->fp == fp) + return true; } - __fprobe_handler(ip, parent_ip, ops, fregs); - ftrace_test_recursion_unlock(bit); + return false; +} +NOKPROBE_SYMBOL(is_fprobe_still_exist); + +static int add_fprobe_hash(struct fprobe *fp) +{ + struct fprobe_hlist *fph = fp->hlist_array; + struct hlist_head *head; + + lockdep_assert_held(&fprobe_mutex); + + if (WARN_ON_ONCE(!fph)) + return -EINVAL; + + if (is_fprobe_still_exist(fp)) + return -EEXIST; + head = &fprobe_table[hash_ptr(fp, FPROBE_HASH_BITS)]; + hlist_add_head_rcu(&fp->hlist_array->hlist, head); + return 0; } -NOKPROBE_SYMBOL(fprobe_handler); -static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct ftrace_regs *fregs) +static int del_fprobe_hash(struct fprobe *fp) { + struct fprobe_hlist *fph = fp->hlist_array; + + lockdep_assert_held(&fprobe_mutex); + + if (WARN_ON_ONCE(!fph)) + return -EINVAL; + + if (!is_fprobe_still_exist(fp)) + return -ENOENT; + + fph->fp = NULL; + hlist_del_rcu(&fph->hlist); + return 0; +} + +/* Generic fprobe_header */ +struct __fprobe_header { struct fprobe *fp; - int bit; + unsigned long size_words; +} __packed; - fp = container_of(ops, struct fprobe, ops); - if (fprobe_disabled(fp)) - return; +#define FPROBE_HEADER_SIZE_IN_LONG SIZE_IN_LONG(sizeof(struct __fprobe_header)) - /* recursion detection has to go before any traceable function and - * all functions called before this point should be marked as notrace - */ - bit = ftrace_test_recursion_trylock(ip, parent_ip); - if (bit < 0) { - fp->nmissed++; - return; - } +static inline bool write_fprobe_header(unsigned long *stack, + struct fprobe *fp, unsigned int size_words) +{ + struct __fprobe_header *fph = (struct __fprobe_header *)stack; + if (WARN_ON_ONCE(size_words > MAX_FPROBE_DATA_SIZE_WORD)) + return false; + + fph->fp = fp; + fph->size_words = size_words; + return true; +} + +static inline void read_fprobe_header(unsigned long *stack, + struct fprobe **fp, unsigned int *size_words) +{ + struct __fprobe_header *fph = (struct __fprobe_header *)stack; + + *fp = fph->fp; + *size_words = fph->size_words; +} + +/* + * fprobe shadow stack management: + * Since fprobe shares a single fgraph_ops, it needs to share the stack entry + * among the probes on the same function exit. Note that a new probe can be + * registered before a target function is returning, we can not use the hash + * table to find the corresponding probes. Thus the probe address is stored on + * the shadow stack with its entry data size. + * + */ +static inline int __fprobe_handler(unsigned long ip, unsigned long parent_ip, + struct fprobe *fp, struct ftrace_regs *fregs, + void *data) +{ + if (!fp->entry_handler) + return 0; + + return fp->entry_handler(fp, ip, parent_ip, fregs, data); +} + +static inline int __fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip, + struct fprobe *fp, struct ftrace_regs *fregs, + void *data) +{ + int ret; /* * This user handler is shared with other kprobes and is not expected to be * called recursively. So if any other kprobe handler is running, this will @@ -108,45 +205,183 @@ static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip, */ if (unlikely(kprobe_running())) { fp->nmissed++; - goto recursion_unlock; + return 0; } kprobe_busy_begin(); - __fprobe_handler(ip, parent_ip, ops, fregs); + ret = __fprobe_handler(ip, parent_ip, fp, fregs, data); kprobe_busy_end(); - -recursion_unlock: - ftrace_test_recursion_unlock(bit); + return ret; } -static void fprobe_exit_handler(struct rethook_node *rh, void *data, - unsigned long ret_ip, struct pt_regs *regs) +static int fprobe_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, + struct ftrace_regs *fregs) { - struct fprobe *fp = (struct fprobe *)data; - struct fprobe_rethook_node *fpr; - struct ftrace_regs *fregs = (struct ftrace_regs *)regs; - int bit; + struct fprobe_hlist_node *node, *first; + unsigned long *fgraph_data = NULL; + unsigned long func = trace->func; + unsigned long ret_ip; + int reserved_words; + struct fprobe *fp; + int used, ret; - if (!fp || fprobe_disabled(fp)) - return; + if (WARN_ON_ONCE(!fregs)) + return 0; - fpr = container_of(rh, struct fprobe_rethook_node, node); + first = node = find_first_fprobe_node(func); + if (unlikely(!first)) + return 0; + + reserved_words = 0; + hlist_for_each_entry_from_rcu(node, hlist) { + if (node->addr != func) + break; + fp = READ_ONCE(node->fp); + if (!fp || !fp->exit_handler) + continue; + /* + * Since fprobe can be enabled until the next loop, we ignore the + * fprobe's disabled flag in this loop. + */ + reserved_words += + FPROBE_HEADER_SIZE_IN_LONG + SIZE_IN_LONG(fp->entry_data_size); + } + node = first; + if (reserved_words) { + fgraph_data = fgraph_reserve_data(gops->idx, reserved_words * sizeof(long)); + if (unlikely(!fgraph_data)) { + hlist_for_each_entry_from_rcu(node, hlist) { + if (node->addr != func) + break; + fp = READ_ONCE(node->fp); + if (fp && !fprobe_disabled(fp)) + fp->nmissed++; + } + return 0; + } + } /* - * we need to assure no calls to traceable functions in-between the - * end of fprobe_handler and the beginning of fprobe_exit_handler. + * TODO: recursion detection has been done in the fgraph. Thus we need + * to add a callback to increment missed counter. */ - bit = ftrace_test_recursion_trylock(fpr->entry_ip, fpr->entry_parent_ip); - if (bit < 0) { - fp->nmissed++; + ret_ip = ftrace_regs_get_return_address(fregs); + used = 0; + hlist_for_each_entry_from_rcu(node, hlist) { + int data_size; + void *data; + + if (node->addr != func) + break; + fp = READ_ONCE(node->fp); + if (!fp || fprobe_disabled(fp)) + continue; + + data_size = fp->entry_data_size; + if (data_size && fp->exit_handler) + data = fgraph_data + used + FPROBE_HEADER_SIZE_IN_LONG; + else + data = NULL; + + if (fprobe_shared_with_kprobes(fp)) + ret = __fprobe_kprobe_handler(func, ret_ip, fp, fregs, data); + else + ret = __fprobe_handler(func, ret_ip, fp, fregs, data); + + /* If entry_handler returns !0, nmissed is not counted but skips exit_handler. */ + if (!ret && fp->exit_handler) { + int size_words = SIZE_IN_LONG(data_size); + + if (write_fprobe_header(&fgraph_data[used], fp, size_words)) + used += FPROBE_HEADER_SIZE_IN_LONG + size_words; + } + } + if (used < reserved_words) + memset(fgraph_data + used, 0, reserved_words - used); + + /* If any exit_handler is set, data must be used. */ + return used != 0; +} +NOKPROBE_SYMBOL(fprobe_entry); + +static void fprobe_return(struct ftrace_graph_ret *trace, + struct fgraph_ops *gops, + struct ftrace_regs *fregs) +{ + unsigned long *fgraph_data = NULL; + unsigned long ret_ip; + struct fprobe *fp; + int size, curr; + int size_words; + + fgraph_data = (unsigned long *)fgraph_retrieve_data(gops->idx, &size); + if (WARN_ON_ONCE(!fgraph_data)) return; + size_words = SIZE_IN_LONG(size); + ret_ip = ftrace_regs_get_instruction_pointer(fregs); + + preempt_disable(); + + curr = 0; + while (size_words > curr) { + read_fprobe_header(&fgraph_data[curr], &fp, &size); + if (!fp) + break; + curr += FPROBE_HEADER_SIZE_IN_LONG; + if (is_fprobe_still_exist(fp) && !fprobe_disabled(fp)) { + if (WARN_ON_ONCE(curr + size > size_words)) + break; + fp->exit_handler(fp, trace->func, ret_ip, fregs, + size ? fgraph_data + curr : NULL); + } + curr += size; } + preempt_enable(); +} +NOKPROBE_SYMBOL(fprobe_return); + +static struct fgraph_ops fprobe_graph_ops = { + .entryfunc = fprobe_entry, + .retfunc = fprobe_return, +}; +static int fprobe_graph_active; + +/* Add @addrs to the ftrace filter and register fgraph if needed. */ +static int fprobe_graph_add_ips(unsigned long *addrs, int num) +{ + int ret; - fp->exit_handler(fp, fpr->entry_ip, ret_ip, fregs, - fp->entry_data_size ? (void *)fpr->data : NULL); - ftrace_test_recursion_unlock(bit); + lockdep_assert_held(&fprobe_mutex); + + ret = ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 0, 0); + if (ret) + return ret; + + if (!fprobe_graph_active) { + ret = register_ftrace_graph(&fprobe_graph_ops); + if (WARN_ON_ONCE(ret)) { + ftrace_free_filter(&fprobe_graph_ops.ops); + return ret; + } + } + fprobe_graph_active++; + return 0; +} + +/* Remove @addrs from the ftrace filter and unregister fgraph if possible. */ +static void fprobe_graph_remove_ips(unsigned long *addrs, int num) +{ + lockdep_assert_held(&fprobe_mutex); + + fprobe_graph_active--; + if (!fprobe_graph_active) { + /* Q: should we unregister it ? */ + unregister_ftrace_graph(&fprobe_graph_ops); + return; + } + + ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); } -NOKPROBE_SYMBOL(fprobe_exit_handler); static int symbols_cmp(const void *a, const void *b) { @@ -176,54 +411,97 @@ static unsigned long *get_ftrace_locations(const char **syms, int num) return ERR_PTR(-ENOENT); } -static void fprobe_init(struct fprobe *fp) -{ - fp->nmissed = 0; - if (fprobe_shared_with_kprobes(fp)) - fp->ops.func = fprobe_kprobe_handler; - else - fp->ops.func = fprobe_handler; - - fp->ops.flags |= FTRACE_OPS_FL_SAVE_REGS; -} +struct filter_match_data { + const char *filter; + const char *notfilter; + size_t index; + size_t size; + unsigned long *addrs; +}; -static int fprobe_init_rethook(struct fprobe *fp, int num) +static int filter_match_callback(void *data, const char *name, unsigned long addr) { - int size; + struct filter_match_data *match = data; - if (!fp->exit_handler) { - fp->rethook = NULL; + if (!glob_match(match->filter, name) || + (match->notfilter && glob_match(match->notfilter, name))) return 0; - } - /* Initialize rethook if needed */ - if (fp->nr_maxactive) - num = fp->nr_maxactive; - else - num *= num_possible_cpus() * 2; - if (num <= 0) - return -EINVAL; + if (!ftrace_location(addr)) + return 0; - size = sizeof(struct fprobe_rethook_node) + fp->entry_data_size; + if (match->addrs) + match->addrs[match->index] = addr; - /* Initialize rethook */ - fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler, size, num); - if (IS_ERR(fp->rethook)) - return PTR_ERR(fp->rethook); + match->index++; + return match->index == match->size; +} - return 0; +/* + * Make IP list from the filter/no-filter glob patterns. + * Return the number of matched symbols, or -ENOENT. + */ +static int ip_list_from_filter(const char *filter, const char *notfilter, + unsigned long *addrs, size_t size) +{ + struct filter_match_data match = { .filter = filter, .notfilter = notfilter, + .index = 0, .size = size, .addrs = addrs}; + int ret; + + ret = kallsyms_on_each_symbol(filter_match_callback, &match); + if (ret < 0) + return ret; + ret = module_kallsyms_on_each_symbol(NULL, filter_match_callback, &match); + if (ret < 0) + return ret; + + return match.index ?: -ENOENT; } static void fprobe_fail_cleanup(struct fprobe *fp) { - if (!IS_ERR_OR_NULL(fp->rethook)) { - /* Don't need to cleanup rethook->handler because this is not used. */ - rethook_free(fp->rethook); - fp->rethook = NULL; + kfree(fp->hlist_array); + fp->hlist_array = NULL; +} + +/* Initialize the fprobe data structure. */ +static int fprobe_init(struct fprobe *fp, unsigned long *addrs, int num) +{ + struct fprobe_hlist *hlist_array; + unsigned long addr; + int size, i; + + if (!fp || !addrs || num <= 0) + return -EINVAL; + + size = ALIGN(fp->entry_data_size, sizeof(long)); + if (size > MAX_FPROBE_DATA_SIZE) + return -E2BIG; + fp->entry_data_size = size; + + hlist_array = kzalloc(struct_size(hlist_array, array, num), GFP_KERNEL); + if (!hlist_array) + return -ENOMEM; + + fp->nmissed = 0; + + hlist_array->size = num; + fp->hlist_array = hlist_array; + hlist_array->fp = fp; + for (i = 0; i < num; i++) { + hlist_array->array[i].fp = fp; + addr = ftrace_location(addrs[i]); + if (!addr) { + fprobe_fail_cleanup(fp); + return -ENOENT; + } + hlist_array->array[i].addr = addr; } - ftrace_free_filter(&fp->ops); + return 0; } +#define FPROBE_IPS_MAX INT_MAX + /** * register_fprobe() - Register fprobe to ftrace by pattern. * @fp: A fprobe data structure to be registered. @@ -237,46 +515,24 @@ static void fprobe_fail_cleanup(struct fprobe *fp) */ int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter) { - struct ftrace_hash *hash; - unsigned char *str; - int ret, len; + unsigned long *addrs; + int ret; if (!fp || !filter) return -EINVAL; - fprobe_init(fp); - - len = strlen(filter); - str = kstrdup(filter, GFP_KERNEL); - ret = ftrace_set_filter(&fp->ops, str, len, 0); - kfree(str); - if (ret) + ret = ip_list_from_filter(filter, notfilter, NULL, FPROBE_IPS_MAX); + if (ret < 0) return ret; - if (notfilter) { - len = strlen(notfilter); - str = kstrdup(notfilter, GFP_KERNEL); - ret = ftrace_set_notrace(&fp->ops, str, len, 0); - kfree(str); - if (ret) - goto out; - } - - /* TODO: - * correctly calculate the total number of filtered symbols - * from both filter and notfilter. - */ - hash = rcu_access_pointer(fp->ops.local_hash.filter_hash); - if (WARN_ON_ONCE(!hash)) - goto out; - - ret = fprobe_init_rethook(fp, (int)hash->count); - if (!ret) - ret = register_ftrace_function(&fp->ops); + addrs = kcalloc(ret, sizeof(unsigned long), GFP_KERNEL); + if (!addrs) + return -ENOMEM; + ret = ip_list_from_filter(filter, notfilter, addrs, ret); + if (ret > 0) + ret = register_fprobe_ips(fp, addrs, ret); -out: - if (ret) - fprobe_fail_cleanup(fp); + kfree(addrs); return ret; } EXPORT_SYMBOL_GPL(register_fprobe); @@ -284,7 +540,7 @@ EXPORT_SYMBOL_GPL(register_fprobe); /** * register_fprobe_ips() - Register fprobe to ftrace by address. * @fp: A fprobe data structure to be registered. - * @addrs: An array of target ftrace location addresses. + * @addrs: An array of target function address. * @num: The number of entries of @addrs. * * Register @fp to ftrace for enabling the probe on the address given by @addrs. @@ -296,23 +552,27 @@ EXPORT_SYMBOL_GPL(register_fprobe); */ int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num) { - int ret; - - if (!fp || !addrs || num <= 0) - return -EINVAL; + struct fprobe_hlist *hlist_array; + int ret, i; - fprobe_init(fp); - - ret = ftrace_set_filter_ips(&fp->ops, addrs, num, 0, 0); + ret = fprobe_init(fp, addrs, num); if (ret) return ret; - ret = fprobe_init_rethook(fp, num); - if (!ret) - ret = register_ftrace_function(&fp->ops); + mutex_lock(&fprobe_mutex); + + hlist_array = fp->hlist_array; + ret = fprobe_graph_add_ips(addrs, num); + if (!ret) { + add_fprobe_hash(fp); + for (i = 0; i < hlist_array->size; i++) + insert_fprobe_node(&hlist_array->array[i]); + } + mutex_unlock(&fprobe_mutex); if (ret) fprobe_fail_cleanup(fp); + return ret; } EXPORT_SYMBOL_GPL(register_fprobe_ips); @@ -350,14 +610,13 @@ EXPORT_SYMBOL_GPL(register_fprobe_syms); bool fprobe_is_registered(struct fprobe *fp) { - if (!fp || (fp->ops.saved_func != fprobe_handler && - fp->ops.saved_func != fprobe_kprobe_handler)) + if (!fp || !fp->hlist_array) return false; return true; } /** - * unregister_fprobe() - Unregister fprobe from ftrace + * unregister_fprobe() - Unregister fprobe. * @fp: A fprobe data structure to be unregistered. * * Unregister fprobe (and remove ftrace hooks from the function entries). @@ -366,23 +625,41 @@ bool fprobe_is_registered(struct fprobe *fp) */ int unregister_fprobe(struct fprobe *fp) { - int ret; + struct fprobe_hlist *hlist_array; + unsigned long *addrs = NULL; + int ret = 0, i, count; - if (!fprobe_is_registered(fp)) - return -EINVAL; + mutex_lock(&fprobe_mutex); + if (!fp || !is_fprobe_still_exist(fp)) { + ret = -EINVAL; + goto out; + } - if (!IS_ERR_OR_NULL(fp->rethook)) - rethook_stop(fp->rethook); + hlist_array = fp->hlist_array; + addrs = kcalloc(hlist_array->size, sizeof(unsigned long), GFP_KERNEL); + if (!addrs) { + ret = -ENOMEM; /* TODO: Fallback to one-by-one loop */ + goto out; + } - ret = unregister_ftrace_function(&fp->ops); - if (ret < 0) - return ret; + /* 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[count++] = hlist_array->array[i].addr; + } + del_fprobe_hash(fp); - if (!IS_ERR_OR_NULL(fp->rethook)) - rethook_free(fp->rethook); + if (count) + fprobe_graph_remove_ips(addrs, count); - ftrace_free_filter(&fp->ops); + kfree_rcu(hlist_array, rcu); + fp->hlist_array = NULL; +out: + mutex_unlock(&fprobe_mutex); + + kfree(addrs); return ret; } EXPORT_SYMBOL_GPL(unregister_fprobe); -- cgit v1.2.3 From b5fa903b7f7c7ffc07430d1380936f72aaf09068 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:14:17 +0900 Subject: fprobe: Add fprobe_header encoding feature Fprobe store its data structure address and size on the fgraph return stack by __fprobe_header. But most 64bit architecture can combine those to one unsigned long value because 4 MSB in the kernel address are the same. With this encoding, fprobe can consume less space on ret_stack. This introduces asm/fprobe.h to define arch dependent encode/decode macros. Note that since fprobe depends on CONFIG_HAVE_FUNCTION_GRAPH_FREGS, currently only arm64, loongarch, riscv, s390 and x86 are supported. Signed-off-by: Masami Hiramatsu (Google) Acked-by: Heiko Carstens # s390 Cc: Catalin Marinas Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Cc: Heiko Carstens Cc: Will Deacon Cc: Huacai Chen Cc: WANG Xuerui Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Vasily Gorbik Cc: Alexander Gordeev Cc: Christian Borntraeger Cc: Sven Schnelle Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: x86@kernel.org Cc: "H. Peter Anvin" Cc: Arnd Bergmann Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/173519005783.391279.5307910947400277525.stgit@devnote2 Signed-off-by: Steven Rostedt (Google) --- kernel/trace/fprobe.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index ed9c1d79426a..2560b312ad57 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -13,6 +13,8 @@ #include #include +#include + #include "trace.h" #define FPROBE_IP_HASH_BITS 8 @@ -143,6 +145,31 @@ static int del_fprobe_hash(struct fprobe *fp) return 0; } +#ifdef ARCH_DEFINE_ENCODE_FPROBE_HEADER + +/* The arch should encode fprobe_header info into one unsigned long */ +#define FPROBE_HEADER_SIZE_IN_LONG 1 + +static inline bool write_fprobe_header(unsigned long *stack, + struct fprobe *fp, unsigned int size_words) +{ + if (WARN_ON_ONCE(size_words > MAX_FPROBE_DATA_SIZE_WORD || + !arch_fprobe_header_encodable(fp))) + return false; + + *stack = arch_encode_fprobe_header(fp, size_words); + return true; +} + +static inline void read_fprobe_header(unsigned long *stack, + struct fprobe **fp, unsigned int *size_words) +{ + *fp = arch_decode_fprobe_header_fp(*stack); + *size_words = arch_decode_fprobe_header_size(*stack); +} + +#else + /* Generic fprobe_header */ struct __fprobe_header { struct fprobe *fp; @@ -173,6 +200,8 @@ static inline void read_fprobe_header(unsigned long *stack, *size_words = fph->size_words; } +#endif + /* * fprobe shadow stack management: * Since fprobe shares a single fgraph_ops, it needs to share the stack entry -- cgit v1.2.3 From a2224559cbba1db3a998dd100c60c85a1d078ad6 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:14:32 +0900 Subject: tracing/fprobe: Remove nr_maxactive from fprobe Remove depercated fprobe::nr_maxactive. This involves fprobe events to rejects the maxactive number. Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Link: https://lore.kernel.org/173519007257.391279.946804046982289337.stgit@devnote2 Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_fprobe.c | 43 ++++++------------------------------------- 1 file changed, 6 insertions(+), 37 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c index 5030aaae8183..f487fadc2c08 100644 --- a/kernel/trace/trace_fprobe.c +++ b/kernel/trace/trace_fprobe.c @@ -424,7 +424,6 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group, const char *symbol, struct tracepoint *tpoint, struct module *mod, - int maxactive, int nargs, bool is_return) { struct trace_fprobe *tf; @@ -445,7 +444,6 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group, tf->tpoint = tpoint; tf->mod = mod; - tf->fp.nr_maxactive = maxactive; ret = trace_probe_init(&tf->tp, event, group, false, nargs); if (ret < 0) @@ -1098,12 +1096,11 @@ static int __trace_fprobe_create(int argc, const char *argv[]) * FETCHARG:TYPE : use TYPE instead of unsigned long. */ struct trace_fprobe *tf = NULL; - int i, len, new_argc = 0, ret = 0; + int i, new_argc = 0, ret = 0; bool is_return = false; char *symbol = NULL; const char *event = NULL, *group = FPROBE_EVENT_SYSTEM; const char **new_argv = NULL; - int maxactive = 0; char buf[MAX_EVENT_NAME_LEN]; char gbuf[MAX_EVENT_NAME_LEN]; char sbuf[KSYM_NAME_LEN]; @@ -1126,33 +1123,13 @@ static int __trace_fprobe_create(int argc, const char *argv[]) trace_probe_log_init("trace_fprobe", argc, argv); - event = strchr(&argv[0][1], ':'); - if (event) - event++; - - if (isdigit(argv[0][1])) { - if (event) - len = event - &argv[0][1] - 1; - else - len = strlen(&argv[0][1]); - if (len > MAX_EVENT_NAME_LEN - 1) { - trace_probe_log_err(1, BAD_MAXACT); - goto parse_error; - } - memcpy(buf, &argv[0][1], len); - buf[len] = '\0'; - ret = kstrtouint(buf, 0, &maxactive); - if (ret || !maxactive) { + if (argv[0][1] != '\0') { + if (argv[0][1] != ':') { + trace_probe_log_set_index(0); trace_probe_log_err(1, BAD_MAXACT); goto parse_error; } - /* fprobe rethook instances are iterated over via a list. The - * maximum should stay reasonable. - */ - if (maxactive > RETHOOK_MAXACTIVE_MAX) { - trace_probe_log_err(1, MAXACT_TOO_BIG); - goto parse_error; - } + event = &argv[0][2]; } trace_probe_log_set_index(1); @@ -1162,12 +1139,6 @@ static int __trace_fprobe_create(int argc, const char *argv[]) if (ret < 0) goto parse_error; - if (!is_return && maxactive) { - trace_probe_log_set_index(0); - trace_probe_log_err(1, BAD_MAXACT_TYPE); - goto parse_error; - } - trace_probe_log_set_index(0); if (event) { ret = traceprobe_parse_event_name(&event, &group, gbuf, @@ -1235,7 +1206,7 @@ static int __trace_fprobe_create(int argc, const char *argv[]) /* setup a probe */ tf = alloc_trace_fprobe(group, event, symbol, tpoint, tp_mod, - maxactive, argc, is_return); + argc, is_return); if (IS_ERR(tf)) { ret = PTR_ERR(tf); /* This must return -ENOMEM, else there is a bug */ @@ -1315,8 +1286,6 @@ static int trace_fprobe_show(struct seq_file *m, struct dyn_event *ev) seq_putc(m, 't'); else seq_putc(m, 'f'); - if (trace_fprobe_is_return(tf) && tf->fp.nr_maxactive) - seq_printf(m, "%d", tf->fp.nr_maxactive); seq_printf(m, ":%s/%s", trace_probe_group_name(&tf->tp), trace_probe_name(&tf->tp)); -- cgit v1.2.3 From 4f7caaa2f92b47e9d27d85f8a60bb7634becd669 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Wed, 1 Jan 2025 01:00:14 +0900 Subject: bpf: Use ftrace_get_symaddr() for kprobe_multi probes Add ftrace_get_entry_ip() which is only for ftrace based probes, and use it for kprobe multi probes because they are based on fprobe which uses ftrace instead of kprobes. Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Link: https://lore.kernel.org/173566081414.878879.10631096557346094362.stgit@devnote2 Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/bpf_trace.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 863351559334..9bfd52913a5b 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2591,6 +2591,13 @@ static DEFINE_PER_CPU(struct pt_regs, bpf_kprobe_multi_pt_regs); #define bpf_kprobe_multi_pt_regs_ptr() (NULL) #endif +static unsigned long ftrace_get_entry_ip(unsigned long fentry_ip) +{ + unsigned long ip = ftrace_get_symaddr(fentry_ip); + + return ip ? : fentry_ip; +} + static int copy_user_syms(struct user_syms *us, unsigned long __user *usyms, u32 cnt) { unsigned long __user usymbol; @@ -2829,7 +2836,8 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip, int err; link = container_of(fp, struct bpf_kprobe_multi_link, fp); - err = kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), fregs, false, data); + err = kprobe_multi_link_prog_run(link, ftrace_get_entry_ip(fentry_ip), + fregs, false, data); return is_kprobe_session(link->link.prog) ? err : 0; } @@ -2841,7 +2849,8 @@ kprobe_multi_link_exit_handler(struct fprobe *fp, unsigned long fentry_ip, struct bpf_kprobe_multi_link *link; link = container_of(fp, struct bpf_kprobe_multi_link, fp); - kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), fregs, true, data); + kprobe_multi_link_prog_run(link, ftrace_get_entry_ip(fentry_ip), + fregs, true, data); } static int symbols_cmp_r(const void *a, const void *b, const void *priv) -- cgit v1.2.3 From 8275637215bd3d447b31d37f9b8231a013adb042 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Fri, 17 Jan 2025 11:20:34 +0900 Subject: tracing: Adopt __free() and guard() for trace_fprobe.c Adopt __free() and guard() for trace_fprobe.c to remove gotos. Link: https://lore.kernel.org/173708043449.319651.12242878905778792182.stgit@mhiramat.roam.corp.google.com Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_fprobe.c | 124 +++++++++++++++++++++----------------------- 1 file changed, 58 insertions(+), 66 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c index f487fadc2c08..b8f3c4ba309b 100644 --- a/kernel/trace/trace_fprobe.c +++ b/kernel/trace/trace_fprobe.c @@ -416,6 +416,9 @@ static void free_trace_fprobe(struct trace_fprobe *tf) } } +/* Since alloc_trace_fprobe() can return error, check the pointer is ERR too. */ +DEFINE_FREE(free_trace_fprobe, struct trace_fprobe *, if (!IS_ERR_OR_NULL(_T)) free_trace_fprobe(_T)) + /* * Allocate new trace_probe and initialize it (including fprobe). */ @@ -426,7 +429,7 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group, struct module *mod, int nargs, bool is_return) { - struct trace_fprobe *tf; + struct trace_fprobe *tf __free(free_trace_fprobe) = NULL; int ret = -ENOMEM; tf = kzalloc(struct_size(tf, tp.args, nargs), GFP_KERNEL); @@ -435,7 +438,7 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group, tf->symbol = kstrdup(symbol, GFP_KERNEL); if (!tf->symbol) - goto error; + return ERR_PTR(-ENOMEM); if (is_return) tf->fp.exit_handler = fexit_dispatcher; @@ -447,13 +450,10 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group, ret = trace_probe_init(&tf->tp, event, group, false, nargs); if (ret < 0) - goto error; + return ERR_PTR(ret); dyn_event_init(&tf->devent, &trace_fprobe_ops); - return tf; -error: - free_trace_fprobe(tf); - return ERR_PTR(ret); + return_ptr(tf); } static struct trace_fprobe *find_trace_fprobe(const char *event, @@ -880,14 +880,12 @@ static int register_trace_fprobe(struct trace_fprobe *tf) struct trace_fprobe *old_tf; int ret; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); old_tf = find_trace_fprobe(trace_probe_name(&tf->tp), trace_probe_group_name(&tf->tp)); - if (old_tf) { - ret = append_trace_fprobe(tf, old_tf); - goto end; - } + if (old_tf) + return append_trace_fprobe(tf, old_tf); /* Register new event */ ret = register_fprobe_event(tf); @@ -897,7 +895,7 @@ static int register_trace_fprobe(struct trace_fprobe *tf) trace_probe_log_err(0, EVENT_EXIST); } else pr_warn("Failed to register probe event(%d)\n", ret); - goto end; + return ret; } /* Register fprobe */ @@ -907,8 +905,6 @@ static int register_trace_fprobe(struct trace_fprobe *tf) else dyn_event_add(&tf->devent, trace_probe_event_call(&tf->tp)); -end: - mutex_unlock(&event_mutex); return ret; } @@ -1069,7 +1065,10 @@ static int parse_symbol_and_return(int argc, const char *argv[], return 0; } -static int __trace_fprobe_create(int argc, const char *argv[]) +DEFINE_FREE(module_put, struct module *, if (_T) module_put(_T)) + +static int trace_fprobe_create_internal(int argc, const char *argv[], + struct traceprobe_parse_context *ctx) { /* * Argument syntax: @@ -1095,23 +1094,20 @@ static int __trace_fprobe_create(int argc, const char *argv[]) * Type of args: * FETCHARG:TYPE : use TYPE instead of unsigned long. */ - struct trace_fprobe *tf = NULL; + struct trace_fprobe *tf __free(free_trace_fprobe) = NULL; int i, new_argc = 0, ret = 0; bool is_return = false; - char *symbol = NULL; + char *symbol __free(kfree) = NULL; const char *event = NULL, *group = FPROBE_EVENT_SYSTEM; - const char **new_argv = NULL; + const char **new_argv __free(kfree) = NULL; char buf[MAX_EVENT_NAME_LEN]; char gbuf[MAX_EVENT_NAME_LEN]; char sbuf[KSYM_NAME_LEN]; char abuf[MAX_BTF_ARGS_LEN]; - char *dbuf = NULL; + char *dbuf __free(kfree) = NULL; bool is_tracepoint = false; - struct module *tp_mod = NULL; + struct module *tp_mod __free(module_put) = NULL; struct tracepoint *tpoint = NULL; - struct traceprobe_parse_context ctx = { - .flags = TPARG_FL_KERNEL | TPARG_FL_FPROBE, - }; if ((argv[0][0] != 'f' && argv[0][0] != 't') || argc < 2) return -ECANCELED; @@ -1121,13 +1117,11 @@ static int __trace_fprobe_create(int argc, const char *argv[]) group = TRACEPOINT_EVENT_SYSTEM; } - trace_probe_log_init("trace_fprobe", argc, argv); - if (argv[0][1] != '\0') { if (argv[0][1] != ':') { trace_probe_log_set_index(0); trace_probe_log_err(1, BAD_MAXACT); - goto parse_error; + return -EINVAL; } event = &argv[0][2]; } @@ -1137,14 +1131,14 @@ static int __trace_fprobe_create(int argc, const char *argv[]) /* a symbol(or tracepoint) must be specified */ ret = parse_symbol_and_return(argc, argv, &symbol, &is_return, is_tracepoint); if (ret < 0) - goto parse_error; + return -EINVAL; trace_probe_log_set_index(0); if (event) { ret = traceprobe_parse_event_name(&event, &group, gbuf, event - argv[0]); if (ret) - goto parse_error; + return -EINVAL; } if (!event) { @@ -1160,49 +1154,44 @@ static int __trace_fprobe_create(int argc, const char *argv[]) } if (is_return) - ctx.flags |= TPARG_FL_RETURN; + ctx->flags |= TPARG_FL_RETURN; else - ctx.flags |= TPARG_FL_FENTRY; + ctx->flags |= TPARG_FL_FENTRY; if (is_tracepoint) { - ctx.flags |= TPARG_FL_TPOINT; + ctx->flags |= TPARG_FL_TPOINT; tpoint = find_tracepoint(symbol, &tp_mod); if (tpoint) { - ctx.funcname = kallsyms_lookup( + ctx->funcname = kallsyms_lookup( (unsigned long)tpoint->probestub, NULL, NULL, NULL, sbuf); } else if (IS_ENABLED(CONFIG_MODULES)) { /* This *may* be loaded afterwards */ tpoint = TRACEPOINT_STUB; - ctx.funcname = symbol; + ctx->funcname = symbol; } else { trace_probe_log_set_index(1); trace_probe_log_err(0, NO_TRACEPOINT); - goto parse_error; + return -EINVAL; } } else - ctx.funcname = symbol; + ctx->funcname = symbol; argc -= 2; argv += 2; new_argv = traceprobe_expand_meta_args(argc, argv, &new_argc, - abuf, MAX_BTF_ARGS_LEN, &ctx); - if (IS_ERR(new_argv)) { - ret = PTR_ERR(new_argv); - new_argv = NULL; - goto out; - } + abuf, MAX_BTF_ARGS_LEN, ctx); + if (IS_ERR(new_argv)) + return PTR_ERR(new_argv); if (new_argv) { argc = new_argc; argv = new_argv; } - if (argc > MAX_TRACE_ARGS) { - ret = -E2BIG; - goto out; - } + if (argc > MAX_TRACE_ARGS) + return -E2BIG; ret = traceprobe_expand_dentry_args(argc, argv, &dbuf); if (ret) - goto out; + return ret; /* setup a probe */ tf = alloc_trace_fprobe(group, event, symbol, tpoint, tp_mod, @@ -1211,16 +1200,16 @@ static int __trace_fprobe_create(int argc, const char *argv[]) ret = PTR_ERR(tf); /* This must return -ENOMEM, else there is a bug */ WARN_ON_ONCE(ret != -ENOMEM); - goto out; /* We know tf is not allocated */ + return ret; } /* parse arguments */ for (i = 0; i < argc; i++) { trace_probe_log_set_index(i + 2); - ctx.offset = 0; - ret = traceprobe_parse_probe_arg(&tf->tp, i, argv[i], &ctx); + ctx->offset = 0; + ret = traceprobe_parse_probe_arg(&tf->tp, i, argv[i], ctx); if (ret) - goto error; /* This can be -ENOMEM */ + return ret; /* This can be -ENOMEM */ } if (is_return && tf->tp.entry_arg) { @@ -1231,7 +1220,7 @@ static int __trace_fprobe_create(int argc, const char *argv[]) ret = traceprobe_set_print_fmt(&tf->tp, is_return ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL); if (ret < 0) - goto error; + return ret; ret = register_trace_fprobe(tf); if (ret) { @@ -1242,29 +1231,32 @@ static int __trace_fprobe_create(int argc, const char *argv[]) trace_probe_log_err(0, BAD_PROBE_ADDR); else if (ret != -ENOMEM && ret != -EEXIST) trace_probe_log_err(0, FAIL_REG_PROBE); - goto error; + return -EINVAL; } -out: - if (tp_mod) - module_put(tp_mod); + /* 'tf' is successfully registered. To avoid freeing, assign NULL. */ + tf = NULL; + + return 0; +} + +static int trace_fprobe_create_cb(int argc, const char *argv[]) +{ + struct traceprobe_parse_context ctx = { + .flags = TPARG_FL_KERNEL | TPARG_FL_FPROBE, + }; + int ret; + + trace_probe_log_init("trace_fprobe", argc, argv); + ret = trace_fprobe_create_internal(argc, argv, &ctx); traceprobe_finish_parse(&ctx); trace_probe_log_clear(); - kfree(new_argv); - kfree(symbol); - kfree(dbuf); return ret; - -parse_error: - ret = -EINVAL; -error: - free_trace_fprobe(tf); - goto out; } static int trace_fprobe_create(const char *raw_command) { - return trace_probe_create(raw_command, __trace_fprobe_create); + return trace_probe_create(raw_command, trace_fprobe_create_cb); } static int trace_fprobe_release(struct dyn_event *ev) -- cgit v1.2.3 From 31f505dc70331243fbb54af868c14bb5f44a15bc Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 16 Jan 2025 17:58:32 -0500 Subject: ftrace: Implement :mod: cache filtering on kernel command line Module functions can be set to set_ftrace_filter before the module is loaded. # echo :mod:snd_hda_intel > set_ftrace_filter This will enable all the functions for the module snd_hda_intel. If that module is not loaded, it is "cached" in the trace array for when the module is loaded, its functions will be traced. But this is not implemented in the kernel command line. That's because the kernel command line filtering is added very early in boot up as it is needed to be done before boot time function tracing can start, which is also available very early in boot up. The code used by the "set_ftrace_filter" file can not be used that early as it depends on some other initialization to occur first. But some of the functions can. Implement the ":mod:" feature of "set_ftrace_filter" in the kernel command line parsing. Now function tracing on just a single module that is loaded at boot up can be done. Adding: ftrace=function ftrace_filter=:mod:sna_hda_intel To the kernel command line will only enable the sna_hda_intel module functions when the module is loaded, and it will start tracing. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20250116175832.34e39779@gandalf.local.home Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 67 ++++++++++++++++++++++++++++++++++++++++++++------- kernel/trace/trace.c | 8 ++++++ kernel/trace/trace.h | 2 ++ 3 files changed, 68 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f054343be026..9387e2865ca8 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4968,10 +4968,6 @@ static int cache_mod(struct trace_array *tr, return ftrace_add_mod(tr, func, module, enable); } -static int -ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, - int reset, int enable); - #ifdef CONFIG_MODULES static void process_mod_list(struct list_head *head, struct ftrace_ops *ops, char *mod, bool enable) @@ -5761,7 +5757,7 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long *ips, static int ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, unsigned long *ips, unsigned int cnt, - int remove, int reset, int enable) + int remove, int reset, int enable, char *mod) { struct ftrace_hash **orig_hash; struct ftrace_hash *hash; @@ -5787,7 +5783,15 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, goto out_regex_unlock; } - if (buf && !ftrace_match_records(hash, buf, len)) { + if (buf && !match_records(hash, buf, len, mod)) { + /* If this was for a module and nothing was enabled, flag it */ + if (mod) + (*orig_hash)->flags |= FTRACE_HASH_FL_MOD; + + /* + * Even if it is a mod, return error to let caller know + * nothing was added + */ ret = -EINVAL; goto out_regex_unlock; } @@ -5812,7 +5816,7 @@ static int ftrace_set_addr(struct ftrace_ops *ops, unsigned long *ips, unsigned int cnt, int remove, int reset, int enable) { - return ftrace_set_hash(ops, NULL, 0, ips, cnt, remove, reset, enable); + return ftrace_set_hash(ops, NULL, 0, ips, cnt, remove, reset, enable, NULL); } #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS @@ -6190,7 +6194,38 @@ static int ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, int reset, int enable) { - return ftrace_set_hash(ops, buf, len, NULL, 0, 0, reset, enable); + char *mod = NULL, *func, *command, *next = buf; + char *tmp __free(kfree) = NULL; + struct trace_array *tr = ops->private; + int ret; + + func = strsep(&next, ":"); + + /* This can also handle :mod: parsing */ + if (next) { + if (!tr) + return -EINVAL; + + command = strsep(&next, ":"); + if (strcmp(command, "mod") != 0) + return -EINVAL; + + mod = next; + len = command - func; + /* Save the original func as ftrace_set_hash() can modify it */ + tmp = kstrdup(func, GFP_KERNEL); + } + + ret = ftrace_set_hash(ops, func, len, NULL, 0, 0, reset, enable, mod); + + if (tr && mod && ret < 0) { + /* Did tmp fail to allocate? */ + if (!tmp) + return -ENOMEM; + ret = cache_mod(tr, tmp, mod, enable); + } + + return ret; } /** @@ -6354,6 +6389,14 @@ ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable) ftrace_ops_init(ops); + /* The trace_array is needed for caching module function filters */ + if (!ops->private) { + struct trace_array *tr = trace_get_global_array(); + + ops->private = tr; + ftrace_init_trace_array(tr); + } + while (buf) { func = strsep(&buf, ","); ftrace_set_regex(ops, func, strlen(func), 0, enable); @@ -7787,9 +7830,14 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops) void ftrace_init_trace_array(struct trace_array *tr) { + if (tr->flags & TRACE_ARRAY_FL_MOD_INIT) + return; + INIT_LIST_HEAD(&tr->func_probes); INIT_LIST_HEAD(&tr->mod_trace); INIT_LIST_HEAD(&tr->mod_notrace); + + tr->flags |= TRACE_ARRAY_FL_MOD_INIT; } #else @@ -7818,7 +7866,8 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops) __init void ftrace_init_global_array_ops(struct trace_array *tr) { tr->ops = &global_ops; - tr->ops->private = tr; + if (!global_ops.private) + global_ops.private = tr; ftrace_init_trace_array(tr); init_array_fgraph_ops(tr, tr->ops); } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 957f941a08e7..a553f1e7a057 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -10657,6 +10657,14 @@ out: return ret; } +#ifdef CONFIG_FUNCTION_TRACER +/* Used to set module cached ftrace filtering at boot up */ +__init struct trace_array *trace_get_global_array(void) +{ + return &global_trace; +} +#endif + void __init ftrace_boot_snapshot(void) { #ifdef CONFIG_TRACER_MAX_TRACE diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 5f3e68a8d8a0..ba68a5a54092 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -432,6 +432,7 @@ struct trace_array { enum { TRACE_ARRAY_FL_GLOBAL = BIT(0), TRACE_ARRAY_FL_BOOT = BIT(1), + TRACE_ARRAY_FL_MOD_INIT = BIT(2), }; extern struct list_head ftrace_trace_arrays; @@ -1116,6 +1117,7 @@ void ftrace_destroy_function_files(struct trace_array *tr); int ftrace_allocate_ftrace_ops(struct trace_array *tr); void ftrace_free_ftrace_ops(struct trace_array *tr); void ftrace_init_global_array_ops(struct trace_array *tr); +struct trace_array *trace_get_global_array(void); void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func); void ftrace_reset_array_ops(struct trace_array *tr); void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer); -- cgit v1.2.3