From f7edb451fa51e44e62177347ea7850aa0e901ea5 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 7 Aug 2019 11:28:59 -0400 Subject: tracing/arm64: Have max stack tracer handle the case of return address after data Most archs (well at least x86) store the function call return address on the stack before storing the local variables for the function. The max stack tracer depends on this in its algorithm to display the stack size of each function it finds in the back trace. Some archs (arm64), may store the return address (from its link register) just before calling a nested function. There's no reason to save the link register on leaf functions, as it wont be updated. This breaks the algorithm of the max stack tracer. Add a new define ARCH_FTRACE_SHIFT_STACK_TRACER that an architecture may set if it stores the return address (link register) after it stores the function's local variables, and have the stack trace shift the values of the mapped stack size to the appropriate functions. Link: 20190802094103.163576-1-jiping.ma2@windriver.com Reported-by: Jiping Ma Acked-by: Will Deacon Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_stack.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'kernel/trace/trace_stack.c') diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 5d16f73898db..642a850af81a 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -158,6 +158,20 @@ static void check_stack(unsigned long ip, unsigned long *stack) i++; } +#ifdef ARCH_FTRACE_SHIFT_STACK_TRACER + /* + * Some archs will store the link register before calling + * nested functions. This means the saved return address + * comes after the local storage, and we need to shift + * for that. + */ + if (x > 1) { + memmove(&stack_trace_index[0], &stack_trace_index[1], + sizeof(stack_trace_index[0]) * (x - 1)); + x--; + } +#endif + stack_trace_nr_entries = x; if (task_stack_end_corrupted(current)) { -- cgit v1.3-6-gb490 From 58fe7a87db51ea00596187765dabfc2c4ea2b436 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 7 Aug 2019 12:27:30 -0400 Subject: tracing: Document the stack trace algorithm in the comments As the max stack tracer algorithm is not that easy to understand from the code, add comments that explain the algorithm and mentions how ARCH_FTRACE_SHIFT_STACK_TRACER affects it. Link: http://lkml.kernel.org/r/20190806123455.487ac02b@gandalf.local.home Suggested-by: Joel Fernandes Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_stack.c | 98 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 98 insertions(+) (limited to 'kernel/trace/trace_stack.c') diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 642a850af81a..ec9a34a97129 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -53,6 +53,104 @@ static void print_max_stack(void) } } +/* + * The stack tracer looks for a maximum stack at each call from a function. It + * registers a callback from ftrace, and in that callback it examines the stack + * size. It determines the stack size from the variable passed in, which is the + * address of a local variable in the stack_trace_call() callback function. + * The stack size is calculated by the address of the local variable to the top + * of the current stack. If that size is smaller than the currently saved max + * stack size, nothing more is done. + * + * If the size of the stack is greater than the maximum recorded size, then the + * following algorithm takes place. + * + * For architectures (like x86) that store the function's return address before + * saving the function's local variables, the stack will look something like + * this: + * + * [ top of stack ] + * 0: sys call entry frame + * 10: return addr to entry code + * 11: start of sys_foo frame + * 20: return addr to sys_foo + * 21: start of kernel_func_bar frame + * 30: return addr to kernel_func_bar + * 31: [ do trace stack here ] + * + * The save_stack_trace() is called returning all the functions it finds in the + * current stack. Which would be (from the bottom of the stack to the top): + * + * return addr to kernel_func_bar + * return addr to sys_foo + * return addr to entry code + * + * Now to figure out how much each of these functions' local variable size is, + * a search of the stack is made to find these values. When a match is made, it + * is added to the stack_dump_trace[] array. The offset into the stack is saved + * in the stack_trace_index[] array. The above example would show: + * + * stack_dump_trace[] | stack_trace_index[] + * ------------------ + ------------------- + * return addr to kernel_func_bar | 30 + * return addr to sys_foo | 20 + * return addr to entry | 10 + * + * The print_max_stack() function above, uses these values to print the size of + * each function's portion of the stack. + * + * for (i = 0; i < nr_entries; i++) { + * size = i == nr_entries - 1 ? stack_trace_index[i] : + * stack_trace_index[i] - stack_trace_index[i+1] + * print "%d %d %d %s\n", i, stack_trace_index[i], size, stack_dump_trace[i]); + * } + * + * The above shows + * + * depth size location + * ----- ---- -------- + * 0 30 10 kernel_func_bar + * 1 20 10 sys_foo + * 2 10 10 entry code + * + * Now for architectures that might save the return address after the functions + * local variables (saving the link register before calling nested functions), + * this will cause the stack to look a little different: + * + * [ top of stack ] + * 0: sys call entry frame + * 10: start of sys_foo_frame + * 19: return addr to entry code << lr saved before calling kernel_func_bar + * 20: start of kernel_func_bar frame + * 29: return addr to sys_foo_frame << lr saved before calling next function + * 30: [ do trace stack here ] + * + * Although the functions returned by save_stack_trace() may be the same, the + * placement in the stack will be different. Using the same algorithm as above + * would yield: + * + * stack_dump_trace[] | stack_trace_index[] + * ------------------ + ------------------- + * return addr to kernel_func_bar | 30 + * return addr to sys_foo | 29 + * return addr to entry | 19 + * + * Where the mapping is off by one: + * + * kernel_func_bar stack frame size is 29 - 19 not 30 - 29! + * + * To fix this, if the architecture sets ARCH_RET_ADDR_AFTER_LOCAL_VARS the + * values in stack_trace_index[] are shifted by one to and the number of + * stack trace entries is decremented by one. + * + * stack_dump_trace[] | stack_trace_index[] + * ------------------ + ------------------- + * return addr to kernel_func_bar | 29 + * return addr to sys_foo | 19 + * + * Although the entry function is not displayed, the first function (sys_foo) + * will still include the stack size of it. + */ static void check_stack(unsigned long ip, unsigned long *stack) { unsigned long this_size, flags; unsigned long *p, *top, *start; -- cgit v1.3-6-gb490 From 17911ff38aa58d3c95c07589dbf5d3564c4cf3c5 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 11 Oct 2019 17:22:50 -0400 Subject: tracing: Add locked_down checks to the open calls of files created for tracefs Added various checks on open tracefs calls to see if tracefs is in lockdown mode, and if so, to return -EPERM. Note, the event format files (which are basically standard on all machines) as well as the enabled_functions file (which shows what is currently being traced) are not lockde down. Perhaps they should be, but it seems counter intuitive to lockdown information to help you know if the system has been modified. Link: http://lkml.kernel.org/r/CAHk-=wj7fGPKUspr579Cii-w_y60PtRaiDgKuxVtBAMK0VNNkA@mail.gmail.com Suggested-by: Linus Torvalds Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 23 ++++++++++++++++++++++- kernel/trace/trace.c | 8 ++++++++ kernel/trace/trace_events.c | 8 ++++++++ kernel/trace/trace_events_hist.c | 11 +++++++++++ kernel/trace/trace_events_trigger.c | 8 +++++++- kernel/trace/trace_kprobe.c | 12 +++++++++++- kernel/trace/trace_printk.c | 7 +++++++ kernel/trace/trace_stack.c | 8 ++++++++ kernel/trace/trace_stat.c | 6 +++++- kernel/trace/trace_uprobe.c | 11 +++++++++++ 10 files changed, 98 insertions(+), 4 deletions(-) (limited to 'kernel/trace/trace_stack.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 8b765a55e01c..f296d89be757 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -3486,6 +3487,11 @@ static int ftrace_avail_open(struct inode *inode, struct file *file) { struct ftrace_iterator *iter; + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; if (unlikely(ftrace_disabled)) return -ENODEV; @@ -3505,6 +3511,15 @@ ftrace_enabled_open(struct inode *inode, struct file *file) { struct ftrace_iterator *iter; + /* + * This shows us what functions are currently being + * traced and by what. Not sure if we want lockdown + * to hide such critical information for an admin. + * Although, perhaps it can show information we don't + * want people to see, but if something is tracing + * something, we probably want to know about it. + */ + iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter)); if (!iter) return -ENOMEM; @@ -3625,6 +3640,7 @@ ftrace_filter_open(struct inode *inode, struct file *file) { struct ftrace_ops *ops = inode->i_private; + /* Checks for tracefs lockdown */ return ftrace_regex_open(ops, FTRACE_ITER_FILTER | FTRACE_ITER_DO_PROBES, inode, file); @@ -3635,6 +3651,7 @@ ftrace_notrace_open(struct inode *inode, struct file *file) { struct ftrace_ops *ops = inode->i_private; + /* Checks for tracefs lockdown */ return ftrace_regex_open(ops, FTRACE_ITER_NOTRACE, inode, file); } @@ -5203,9 +5220,13 @@ static int __ftrace_graph_open(struct inode *inode, struct file *file, struct ftrace_graph_data *fgd) { - int ret = 0; + int ret; struct ftrace_hash *new_hash = NULL; + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + if (file->f_mode & FMODE_WRITE) { const int size_bits = FTRACE_HASH_DEFAULT_BITS; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 26ee280f852b..2b4eff383505 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -306,6 +307,12 @@ void trace_array_put(struct trace_array *this_tr) int tracing_check_open_get_tr(struct trace_array *tr) { + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + if (tracing_disabled) return -ENODEV; @@ -6813,6 +6820,7 @@ static int snapshot_raw_open(struct inode *inode, struct file *filp) struct ftrace_buffer_info *info; int ret; + /* The following checks for tracefs lockdown */ ret = tracing_buffers_open(inode, filp); if (ret < 0) return ret; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 71ab0a3660f4..fba87d10f0c1 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -12,6 +12,7 @@ #define pr_fmt(fmt) fmt #include +#include #include #include #include @@ -1294,6 +1295,8 @@ static int trace_format_open(struct inode *inode, struct file *file) struct seq_file *m; int ret; + /* Do we want to hide event format files on tracefs lockdown? */ + ret = seq_open(file, &trace_format_seq_ops); if (ret < 0) return ret; @@ -1760,6 +1763,10 @@ ftrace_event_open(struct inode *inode, struct file *file, struct seq_file *m; int ret; + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + ret = seq_open(file, seq_ops); if (ret < 0) return ret; @@ -1784,6 +1791,7 @@ ftrace_event_avail_open(struct inode *inode, struct file *file) { const struct seq_operations *seq_ops = &show_event_seq_ops; + /* Checks for tracefs lockdown */ return ftrace_event_open(inode, file, seq_ops); } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index dd18d76bf1bd..57648c5aa679 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -7,6 +7,7 @@ #include #include +#include #include #include #include @@ -1448,6 +1449,10 @@ static int synth_events_open(struct inode *inode, struct file *file) { int ret; + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { ret = dyn_events_release_all(&synth_event_ops); if (ret < 0) @@ -5515,6 +5520,12 @@ static int hist_show(struct seq_file *m, void *v) static int event_hist_open(struct inode *inode, struct file *file) { + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + return single_open(file, hist_show, file); } diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 2a2912cb4533..2cd53ca21b51 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -5,6 +5,7 @@ * Copyright (C) 2013 Tom Zanussi */ +#include #include #include #include @@ -173,7 +174,11 @@ static const struct seq_operations event_triggers_seq_ops = { static int event_trigger_regex_open(struct inode *inode, struct file *file) { - int ret = 0; + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; mutex_lock(&event_mutex); @@ -292,6 +297,7 @@ event_trigger_write(struct file *filp, const char __user *ubuf, static int event_trigger_open(struct inode *inode, struct file *filp) { + /* Checks for tracefs lockdown */ return event_trigger_regex_open(inode, filp); } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 324ffbea3556..1552a95c743b 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -7,11 +7,11 @@ */ #define pr_fmt(fmt) "trace_kprobe: " fmt +#include #include #include #include #include -#include #include /* for COMMAND_LINE_SIZE */ @@ -936,6 +936,10 @@ static int probes_open(struct inode *inode, struct file *file) { int ret; + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { ret = dyn_events_release_all(&trace_kprobe_ops); if (ret < 0) @@ -988,6 +992,12 @@ static const struct seq_operations profile_seq_op = { static int profile_open(struct inode *inode, struct file *file) { + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + return seq_open(file, &profile_seq_op); } diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index c3fd849d4a8f..d4e31e969206 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -6,6 +6,7 @@ * */ #include +#include #include #include #include @@ -348,6 +349,12 @@ static const struct seq_operations show_format_seq_ops = { static int ftrace_formats_open(struct inode *inode, struct file *file) { + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + return seq_open(file, &show_format_seq_ops); } diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index ec9a34a97129..4df9a209f7ca 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -5,6 +5,7 @@ */ #include #include +#include #include #include #include @@ -470,6 +471,12 @@ static const struct seq_operations stack_trace_seq_ops = { static int stack_trace_open(struct inode *inode, struct file *file) { + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + return seq_open(file, &stack_trace_seq_ops); } @@ -487,6 +494,7 @@ stack_trace_filter_open(struct inode *inode, struct file *file) { struct ftrace_ops *ops = inode->i_private; + /* Checks for tracefs lockdown */ return ftrace_regex_open(ops, FTRACE_ITER_FILTER, inode, file); } diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index 75bf1bcb4a8a..9ab0a1a7ad5e 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -9,7 +9,7 @@ * */ - +#include #include #include #include @@ -238,6 +238,10 @@ static int tracing_stat_open(struct inode *inode, struct file *file) struct seq_file *m; struct stat_session *session = inode->i_private; + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + ret = stat_seq_init(session); if (ret) return ret; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index dd884341f5c5..352073d36585 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -7,6 +7,7 @@ */ #define pr_fmt(fmt) "trace_uprobe: " fmt +#include #include #include #include @@ -769,6 +770,10 @@ static int probes_open(struct inode *inode, struct file *file) { int ret; + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { ret = dyn_events_release_all(&trace_uprobe_ops); if (ret) @@ -818,6 +823,12 @@ static const struct seq_operations profile_seq_op = { static int profile_open(struct inode *inode, struct file *file) { + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + return seq_open(file, &profile_seq_op); } -- cgit v1.3-6-gb490