diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-05-06 13:11:48 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-05-06 13:11:48 -0700 |
commit | 2c6a392cddacde153865b15e8295ad0a35ed3c02 (patch) | |
tree | 558c34595f8987c87d26fc0fa0dc644fca9ef2cd /kernel | |
parent | 0a499fc5c37e6db096969a83534fd98a2bf2b36c (diff) | |
parent | 3599fe12a125fa7118da2bcc5033d7741fb5f3a1 (diff) |
Merge branch 'core-stacktrace-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull stack trace updates from Ingo Molnar:
"So Thomas looked at the stacktrace code recently and noticed a few
weirdnesses, and we all know how such stories of crummy kernel code
meeting German engineering perfection end: a 45-patch series to clean
it all up! :-)
Here's the changes in Thomas's words:
'Struct stack_trace is a sinkhole for input and output parameters
which is largely pointless for most usage sites. In fact if embedded
into other data structures it creates indirections and extra storage
overhead for no benefit.
Looking at all usage sites makes it clear that they just require an
interface which is based on a storage array. That array is either on
stack, global or embedded into some other data structure.
Some of the stack depot usage sites are outright wrong, but
fortunately the wrongness just causes more stack being used for
nothing and does not have functional impact.
Another oddity is the inconsistent termination of the stack trace
with ULONG_MAX. It's pointless as the number of entries is what
determines the length of the stored trace. In fact quite some call
sites remove the ULONG_MAX marker afterwards with or without nasty
comments about it. Not all architectures do that and those which do,
do it inconsistenly either conditional on nr_entries == 0 or
unconditionally.
The following series cleans that up by:
1) Removing the ULONG_MAX termination in the architecture code
2) Removing the ULONG_MAX fixups at the call sites
3) Providing plain storage array based interfaces for stacktrace
and stackdepot.
4) Cleaning up the mess at the callsites including some related
cleanups.
5) Removing the struct stack_trace based interfaces
This is not changing the struct stack_trace interfaces at the
architecture level, but it removes the exposure to the generic
code'"
* 'core-stacktrace-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (45 commits)
x86/stacktrace: Use common infrastructure
stacktrace: Provide common infrastructure
lib/stackdepot: Remove obsolete functions
stacktrace: Remove obsolete functions
livepatch: Simplify stack trace retrieval
tracing: Remove the last struct stack_trace usage
tracing: Simplify stack trace retrieval
tracing: Make ftrace_trace_userstack() static and conditional
tracing: Use percpu stack trace buffer more intelligently
tracing: Simplify stacktrace retrieval in histograms
lockdep: Simplify stack trace handling
lockdep: Remove save argument from check_prev_add()
lockdep: Remove unused trace argument from print_circular_bug()
drm: Simplify stacktrace handling
dm persistent data: Simplify stack trace handling
dm bufio: Simplify stack trace retrieval
btrfs: ref-verify: Simplify stack trace retrieval
dma/debug: Simplify stracktrace retrieval
fault-inject: Simplify stacktrace retrieval
mm/page_owner: Simplify stack trace handling
...
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/backtracetest.c | 11 | ||||
-rw-r--r-- | kernel/dma/debug.c | 14 | ||||
-rw-r--r-- | kernel/latencytop.c | 29 | ||||
-rw-r--r-- | kernel/livepatch/transition.c | 22 | ||||
-rw-r--r-- | kernel/locking/lockdep.c | 87 | ||||
-rw-r--r-- | kernel/stacktrace.c | 333 | ||||
-rw-r--r-- | kernel/trace/trace.c | 105 | ||||
-rw-r--r-- | kernel/trace/trace.h | 8 | ||||
-rw-r--r-- | kernel/trace/trace_events_hist.c | 14 | ||||
-rw-r--r-- | kernel/trace/trace_stack.c | 85 |
10 files changed, 458 insertions, 250 deletions
diff --git a/kernel/backtracetest.c b/kernel/backtracetest.c index 1323360d90e3..a563c8fdad0d 100644 --- a/kernel/backtracetest.c +++ b/kernel/backtracetest.c @@ -48,19 +48,14 @@ static void backtrace_test_irq(void) #ifdef CONFIG_STACKTRACE static void backtrace_test_saved(void) { - struct stack_trace trace; unsigned long entries[8]; + unsigned int nr_entries; pr_info("Testing a saved backtrace.\n"); pr_info("The following trace is a kernel self test and not a bug!\n"); - trace.nr_entries = 0; - trace.max_entries = ARRAY_SIZE(entries); - trace.entries = entries; - trace.skip = 0; - - save_stack_trace(&trace); - print_stack_trace(&trace, 0); + nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0); + stack_trace_print(entries, nr_entries, 0); } #else static void backtrace_test_saved(void) diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index a218e43cc382..badd77670d00 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -89,8 +89,8 @@ struct dma_debug_entry { int sg_mapped_ents; enum map_err_types map_err_type; #ifdef CONFIG_STACKTRACE - struct stack_trace stacktrace; - unsigned long st_entries[DMA_DEBUG_STACKTRACE_ENTRIES]; + unsigned int stack_len; + unsigned long stack_entries[DMA_DEBUG_STACKTRACE_ENTRIES]; #endif }; @@ -174,7 +174,7 @@ static inline void dump_entry_trace(struct dma_debug_entry *entry) #ifdef CONFIG_STACKTRACE if (entry) { pr_warning("Mapped at:\n"); - print_stack_trace(&entry->stacktrace, 0); + stack_trace_print(entry->stack_entries, entry->stack_len, 0); } #endif } @@ -704,12 +704,10 @@ static struct dma_debug_entry *dma_entry_alloc(void) spin_unlock_irqrestore(&free_entries_lock, flags); #ifdef CONFIG_STACKTRACE - entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES; - entry->stacktrace.entries = entry->st_entries; - entry->stacktrace.skip = 1; - save_stack_trace(&entry->stacktrace); + entry->stack_len = stack_trace_save(entry->stack_entries, + ARRAY_SIZE(entry->stack_entries), + 1); #endif - return entry; } diff --git a/kernel/latencytop.c b/kernel/latencytop.c index 96b4179cee6a..99a5b5f46dc5 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -120,8 +120,8 @@ account_global_scheduler_latency(struct task_struct *tsk, break; } - /* 0 and ULONG_MAX entries mean end of backtrace: */ - if (record == 0 || record == ULONG_MAX) + /* 0 entry marks end of backtrace: */ + if (!record) break; } if (same) { @@ -141,20 +141,6 @@ account_global_scheduler_latency(struct task_struct *tsk, memcpy(&latency_record[i], lat, sizeof(struct latency_record)); } -/* - * Iterator to store a backtrace into a latency record entry - */ -static inline void store_stacktrace(struct task_struct *tsk, - struct latency_record *lat) -{ - struct stack_trace trace; - - memset(&trace, 0, sizeof(trace)); - trace.max_entries = LT_BACKTRACEDEPTH; - trace.entries = &lat->backtrace[0]; - save_stack_trace_tsk(tsk, &trace); -} - /** * __account_scheduler_latency - record an occurred latency * @tsk - the task struct of the task hitting the latency @@ -191,7 +177,8 @@ __account_scheduler_latency(struct task_struct *tsk, int usecs, int inter) lat.count = 1; lat.time = usecs; lat.max = usecs; - store_stacktrace(tsk, &lat); + + stack_trace_save_tsk(tsk, lat.backtrace, LT_BACKTRACEDEPTH, 0); raw_spin_lock_irqsave(&latency_lock, flags); @@ -210,8 +197,8 @@ __account_scheduler_latency(struct task_struct *tsk, int usecs, int inter) break; } - /* 0 and ULONG_MAX entries mean end of backtrace: */ - if (record == 0 || record == ULONG_MAX) + /* 0 entry is end of backtrace */ + if (!record) break; } if (same) { @@ -252,10 +239,10 @@ static int lstats_show(struct seq_file *m, void *v) lr->count, lr->time, lr->max); for (q = 0; q < LT_BACKTRACEDEPTH; q++) { unsigned long bt = lr->backtrace[q]; + if (!bt) break; - if (bt == ULONG_MAX) - break; + seq_printf(m, " %ps", (void *)bt); } seq_puts(m, "\n"); diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c index 9c89ae8b337a..c53370d596be 100644 --- a/kernel/livepatch/transition.c +++ b/kernel/livepatch/transition.c @@ -202,15 +202,15 @@ void klp_update_patch_state(struct task_struct *task) * Determine whether the given stack trace includes any references to a * to-be-patched or to-be-unpatched function. */ -static int klp_check_stack_func(struct klp_func *func, - struct stack_trace *trace) +static int klp_check_stack_func(struct klp_func *func, unsigned long *entries, + unsigned int nr_entries) { unsigned long func_addr, func_size, address; struct klp_ops *ops; int i; - for (i = 0; i < trace->nr_entries; i++) { - address = trace->entries[i]; + for (i = 0; i < nr_entries; i++) { + address = entries[i]; if (klp_target_state == KLP_UNPATCHED) { /* @@ -254,29 +254,25 @@ static int klp_check_stack_func(struct klp_func *func, static int klp_check_stack(struct task_struct *task, char *err_buf) { static unsigned long entries[MAX_STACK_ENTRIES]; - struct stack_trace trace; struct klp_object *obj; struct klp_func *func; - int ret; + int ret, nr_entries; - trace.skip = 0; - trace.nr_entries = 0; - trace.max_entries = MAX_STACK_ENTRIES; - trace.entries = entries; - ret = save_stack_trace_tsk_reliable(task, &trace); + ret = stack_trace_save_tsk_reliable(task, entries, ARRAY_SIZE(entries)); WARN_ON_ONCE(ret == -ENOSYS); - if (ret) { + if (ret < 0) { snprintf(err_buf, STACK_ERR_BUF_SIZE, "%s: %s:%d has an unreliable stack\n", __func__, task->comm, task->pid); return ret; } + nr_entries = ret; klp_for_each_object(klp_transition_patch, obj) { if (!obj->patched) continue; klp_for_each_func(obj, func) { - ret = klp_check_stack_func(func, &trace); + ret = klp_check_stack_func(func, entries, nr_entries); if (ret) { snprintf(err_buf, STACK_ERR_BUF_SIZE, "%s: %s:%d is sleeping on function %s\n", diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index e221be724fe8..91c6b89f04df 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -434,29 +434,14 @@ static void print_lockdep_off(const char *bug_msg) #endif } -static int save_trace(struct stack_trace *trace) +static int save_trace(struct lock_trace *trace) { - trace->nr_entries = 0; - trace->max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries; - trace->entries = stack_trace + nr_stack_trace_entries; - - trace->skip = 3; - - save_stack_trace(trace); - - /* - * Some daft arches put -1 at the end to indicate its a full trace. - * - * <rant> this is buggy anyway, since it takes a whole extra entry so a - * complete trace that maxes out the entries provided will be reported - * as incomplete, friggin useless </rant> - */ - if (trace->nr_entries != 0 && - trace->entries[trace->nr_entries-1] == ULONG_MAX) - trace->nr_entries--; - - trace->max_entries = trace->nr_entries; + unsigned long *entries = stack_trace + nr_stack_trace_entries; + unsigned int max_entries; + trace->offset = nr_stack_trace_entries; + max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries; + trace->nr_entries = stack_trace_save(entries, max_entries, 3); nr_stack_trace_entries += trace->nr_entries; if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES-1) { @@ -1207,7 +1192,7 @@ static struct lock_list *alloc_list_entry(void) static int add_lock_to_list(struct lock_class *this, struct lock_class *links_to, struct list_head *head, unsigned long ip, int distance, - struct stack_trace *trace) + struct lock_trace *trace) { struct lock_list *entry; /* @@ -1426,6 +1411,13 @@ static inline int __bfs_backwards(struct lock_list *src_entry, * checking. */ +static void print_lock_trace(struct lock_trace *trace, unsigned int spaces) +{ + unsigned long *entries = stack_trace + trace->offset; + + stack_trace_print(entries, trace->nr_entries, spaces); +} + /* * Print a dependency chain entry (this is only done when a deadlock * has been detected): @@ -1438,8 +1430,7 @@ print_circular_bug_entry(struct lock_list *target, int depth) printk("\n-> #%u", depth); print_lock_name(target->class); printk(KERN_CONT ":\n"); - print_stack_trace(&target->trace, 6); - + print_lock_trace(&target->trace, 6); return 0; } @@ -1533,10 +1524,9 @@ static inline int class_equal(struct lock_list *entry, void *data) } static noinline int print_circular_bug(struct lock_list *this, - struct lock_list *target, - struct held_lock *check_src, - struct held_lock *check_tgt, - struct stack_trace *trace) + struct lock_list *target, + struct held_lock *check_src, + struct held_lock *check_tgt) { struct task_struct *curr = current; struct lock_list *parent; @@ -1752,7 +1742,7 @@ static void print_lock_class_header(struct lock_class *class, int depth) len += printk("%*s %s", depth, "", usage_str[bit]); len += printk(KERN_CONT " at:\n"); - print_stack_trace(class->usage_traces + bit, len); + print_lock_trace(class->usage_traces + bit, len); } } printk("%*s }\n", depth, ""); @@ -1777,7 +1767,7 @@ print_shortest_lock_dependencies(struct lock_list *leaf, do { print_lock_class_header(entry->class, depth); printk("%*s ... acquired at:\n", depth, ""); - print_stack_trace(&entry->trace, 2); + print_lock_trace(&entry->trace, 2); printk("\n"); if (depth == 0 && (entry != root)) { @@ -1890,14 +1880,14 @@ print_bad_irq_dependency(struct task_struct *curr, print_lock_name(backwards_entry->class); pr_warn("\n... which became %s-irq-safe at:\n", irqclass); - print_stack_trace(backwards_entry->class->usage_traces + bit1, 1); + print_lock_trace(backwards_entry->class->usage_traces + bit1, 1); pr_warn("\nto a %s-irq-unsafe lock:\n", irqclass); print_lock_name(forwards_entry->class); pr_warn("\n... which became %s-irq-unsafe at:\n", irqclass); pr_warn("..."); - print_stack_trace(forwards_entry->class->usage_traces + bit2, 1); + print_lock_trace(forwards_entry->class->usage_traces + bit2, 1); pr_warn("\nother info that might help us debug this:\n\n"); print_irq_lock_scenario(backwards_entry, forwards_entry, @@ -2170,8 +2160,7 @@ check_deadlock(struct task_struct *curr, struct held_lock *next, */ static int check_prev_add(struct task_struct *curr, struct held_lock *prev, - struct held_lock *next, int distance, struct stack_trace *trace, - int (*save)(struct stack_trace *trace)) + struct held_lock *next, int distance, struct lock_trace *trace) { struct lock_list *uninitialized_var(target_entry); struct lock_list *entry; @@ -2209,15 +2198,15 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, this.parent = NULL; ret = check_noncircular(&this, hlock_class(prev), &target_entry); if (unlikely(!ret)) { - if (!trace->entries) { + if (!trace->nr_entries) { /* - * If @save fails here, the printing might trigger - * a WARN but because of the !nr_entries it should - * not do bad things. + * If save_trace fails here, the printing might + * trigger a WARN but because of the !nr_entries it + * should not do bad things. */ - save(trace); + save_trace(trace); } - return print_circular_bug(&this, target_entry, next, prev, trace); + return print_circular_bug(&this, target_entry, next, prev); } else if (unlikely(ret < 0)) return print_bfs_bug(ret); @@ -2265,7 +2254,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, return print_bfs_bug(ret); - if (!trace->entries && !save(trace)) + if (!trace->nr_entries && !save_trace(trace)) return 0; /* @@ -2297,14 +2286,9 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, static int check_prevs_add(struct task_struct *curr, struct held_lock *next) { + struct lock_trace trace = { .nr_entries = 0 }; int depth = curr->lockdep_depth; struct held_lock *hlock; - struct stack_trace trace = { - .nr_entries = 0, - .max_entries = 0, - .entries = NULL, - .skip = 0, - }; /* * Debugging checks. @@ -2330,7 +2314,8 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next) * added: */ if (hlock->read != 2 && hlock->check) { - int ret = check_prev_add(curr, hlock, next, distance, &trace, save_trace); + int ret = check_prev_add(curr, hlock, next, distance, + &trace); if (!ret) return 0; @@ -2731,6 +2716,10 @@ static inline int validate_chain(struct task_struct *curr, { return 1; } + +static void print_lock_trace(struct lock_trace *trace, unsigned int spaces) +{ +} #endif /* @@ -2827,7 +2816,7 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this, print_lock(this); pr_warn("{%s} state was registered at:\n", usage_str[prev_bit]); - print_stack_trace(hlock_class(this)->usage_traces + prev_bit, 1); + print_lock_trace(hlock_class(this)->usage_traces + prev_bit, 1); print_irqtrace_events(curr); pr_warn("\nother info that might help us debug this:\n"); diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c index f8edee9c792d..27bafc1e271e 100644 --- a/kernel/stacktrace.c +++ b/kernel/stacktrace.c @@ -5,41 +5,56 @@ * * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> */ +#include <linux/sched/task_stack.h> +#include <linux/sched/debug.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/kallsyms.h> #include <linux/stacktrace.h> -void print_stack_trace(struct stack_trace *trace, int spaces) +/** + * stack_trace_print - Print the entries in the stack trace + * @entries: Pointer to storage array + * @nr_entries: Number of entries in the storage array + * @spaces: Number of leading spaces to print + */ +void stack_trace_print(unsigned long *entries, unsigned int nr_entries, + int spaces) { - int i; + unsigned int i; - if (WARN_ON(!trace->entries)) + if (WARN_ON(!entries)) return; - for (i = 0; i < trace->nr_entries; i++) - printk("%*c%pS\n", 1 + spaces, ' ', (void *)trace->entries[i]); + for (i = 0; i < nr_entries; i++) + printk("%*c%pS\n", 1 + spaces, ' ', (void *)entries[i]); } -EXPORT_SYMBOL_GPL(print_stack_trace); +EXPORT_SYMBOL_GPL(stack_trace_print); -int snprint_stack_trace(char *buf, size_t size, - struct stack_trace *trace, int spaces) +/** + * stack_trace_snprint - Print the entries in the stack trace into a buffer + * @buf: Pointer to the print buffer + * @size: Size of the print buffer + * @entries: Pointer to storage array + * @nr_entries: Number of entries in the storage array + * @spaces: Number of leading spaces to print + * + * Return: Number of bytes printed. + */ +int stack_trace_snprint(char *buf, size_t size, unsigned long *entries, + unsigned int nr_entries, int spaces) { - int i; - int generated; - int total = 0; + unsigned int generated, i, total = 0; - if (WARN_ON(!trace->entries)) + if (WARN_ON(!entries)) return 0; - for (i = 0; i < trace->nr_entries; i++) { + for (i = 0; i < nr_entries && size; i++) { generated = snprintf(buf, size, "%*c%pS\n", 1 + spaces, ' ', - (void *)trace->entries[i]); + (void *)entries[i]); total += generated; - - /* Assume that generated isn't a negative number */ if (generated >= size) { buf += size; size = 0; @@ -51,7 +66,176 @@ int snprint_stack_trace(char *buf, size_t size, return total; } -EXPORT_SYMBOL_GPL(snprint_stack_trace); +EXPORT_SYMBOL_GPL(stack_trace_snprint); + +#ifdef CONFIG_ARCH_STACKWALK + +struct stacktrace_cookie { + unsigned long *store; + unsigned int size; + unsigned int skip; + unsigned int len; +}; + +static bool stack_trace_consume_entry(void *cookie, unsigned long addr, + bool reliable) +{ + struct stacktrace_cookie *c = cookie; + + if (c->len >= c->size) + return false; + + if (c->skip > 0) { + c->skip--; + return true; + } + c->store[c->len++] = addr; + return c->len < c->size; +} + +static bool stack_trace_consume_entry_nosched(void *cookie, unsigned long addr, + bool reliable) +{ + if (in_sched_functions(addr)) + return true; + return stack_trace_consume_entry(cookie, addr, reliable); +} + +/** + * stack_trace_save - Save a stack trace into a storage array + * @store: Pointer to storage array + * @size: Size of the storage array + * @skipnr: Number of entries to skip at the start of the stack trace + * + * Return: Number of trace entries stored. + */ +unsigned int stack_trace_save(unsigned long *store, unsigned int size, + unsigned int skipnr) +{ + stack_trace_consume_fn consume_entry = stack_trace_consume_entry; + struct stacktrace_cookie c = { + .store = store, + .size = size, + .skip = skipnr + 1, + }; + + arch_stack_walk(consume_entry, &c, current, NULL); + return c.len; +} +EXPORT_SYMBOL_GPL(stack_trace_save); + +/** + * stack_trace_save_tsk - Save a task stack trace into a storage array + * @task: The task to examine + * @store: Pointer to storage array + * @size: Size of the storage array + * @skipnr: Number of entries to skip at the start of the stack trace + * + * Return: Number of trace entries stored. + */ +unsigned int stack_trace_save_tsk(struct task_struct *tsk, unsigned long *store, + unsigned int size, unsigned int skipnr) +{ + stack_trace_consume_fn consume_entry = stack_trace_consume_entry_nosched; + struct stacktrace_cookie c = { + .store = store, + .size = size, + .skip = skipnr + 1, + }; + + if (!try_get_task_stack(tsk)) + return 0; + + arch_stack_walk(consume_entry, &c, tsk, NULL); + put_task_stack(tsk); + return c.len; +} + +/** + * stack_trace_save_regs - Save a stack trace based on pt_regs into a storage array + * @regs: Pointer to pt_regs to examine + * @store: Pointer to storage array + * @size: Size of the storage array + * @skipnr: Number of entries to skip at the start of the stack trace + * + * Return: Number of trace entries stored. + */ +unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store, + unsigned int size, unsigned int skipnr) +{ + stack_trace_consume_fn consume_entry = stack_trace_consume_entry; + struct stacktrace_cookie c = { + .store = store, + .size = size, + .skip = skipnr, + }; + + arch_stack_walk(consume_entry, &c, current, regs); + return c.len; +} + +#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE +/** + * stack_trace_save_tsk_reliable - Save task stack with verification + * @tsk: Pointer to the task to examine + * @store: Pointer to storage array + * @size: Size of the storage array + * + * Return: An error if it detects any unreliable features of the + * stack. Otherwise it guarantees that the stack trace is + * reliable and returns the number of entries stored. + * + * If the task is not 'current', the caller *must* ensure the task is inactive. + */ +int stack_trace_save_tsk_reliable(struct task_struct *tsk, unsigned long *store, + unsigned int size) +{ + stack_trace_consume_fn consume_entry = stack_trace_consume_entry; + struct stacktrace_cookie c = { + .store = store, + .size = size, + }; + int ret; + + /* + * If the task doesn't have a stack (e.g., a zombie), the stack is + * "reliably" empty. + */ + if (!try_get_task_stack(tsk)) + return 0; + + ret = arch_stack_walk_reliable(consume_entry, &c, tsk); + put_task_stack(tsk); + return ret; +} +#endif + +#ifdef CONFIG_USER_STACKTRACE_SUPPORT +/** + * stack_trace_save_user - Save a user space stack trace into a storage array + * @store: Pointer to storage array + * @size: Size of the storage array + * + * Return: Number of trace entries stored. + */ +unsigned int stack_trace_save_user(unsigned long *store, unsigned int size) +{ + stack_trace_consume_fn consume_entry = stack_trace_consume_entry; + struct stacktrace_cookie c = { + .store = store, + .size = size, + }; + + /* Trace user stack if not a kernel thread */ + if (!current->mm) + return 0; + + arch_stack_walk_user(consume_entry, &c, task_pt_regs(current)); + return c.len; +} +#endif + +#else /* CONFIG_ARCH_STACKWALK */ /* * Architectures that do not implement save_stack_trace_*() @@ -77,3 +261,118 @@ save_stack_trace_tsk_reliable(struct task_struct *tsk, WARN_ONCE(1, KERN_INFO "save_stack_tsk_reliable() not implemented yet.\n"); return -ENOSYS; } + +/** + * stack_trace_save - Save a stack trace into a storage array + * @store: Pointer to storage array + * @size: Size of the storage array + * @skipnr: Number of entries to skip at the start of the stack trace + * + * Return: Number of trace entries stored + */ +unsigned int stack_trace_save(unsigned long *store, unsigned int size, + unsigned int skipnr) +{ + struct stack_trace trace = { + .entries = store, + .max_entries = size, + .skip = skipnr + 1, + }; + + save_stack_trace(&trace); + return trace.nr_entries; +} +EXPORT_SYMBOL_GPL(stack_trace_save); + +/** + * stack_trace_save_tsk - Save a task stack trace into a storage array + * @task: The task to examine + * @store: Pointer to storage array + * @size: Size of the storage array + * @skipnr: Number of entries to skip at the start of the stack trace + * + * Return: Number of trace entries stored + */ +unsigned int stack_trace_save_tsk(struct task_struct *task, + unsigned long *store, unsigned int size, + unsigned int skipnr) +{ + struct stack_trace trace = { + .entries = store, + .max_entries = size, + .skip = skipnr + 1, + }; + + save_stack_trace_tsk(task, &trace); + return trace.nr_entries; +} + +/** + * stack_trace_save_regs - Save a stack trace based on pt_regs into a storage array + * @regs: Pointer to pt_regs to examine + * @store: Pointer to storage array + * @size: Size of the storage array + * @skipnr: Number of entries to skip at the start of the stack trace + * + * Return: Number of trace entries stored + */ +unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store, + unsigned int size, unsigned int skipnr) +{ + struct stack_trace trace = { + .entries = store, + .max_entries = size, + .skip = skipnr, + }; + + save_stack_trace_regs(regs, &trace); + return trace.nr_entries; +} + +#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE +/** + * stack_trace_save_tsk_reliable - Save task stack with verification + * @tsk: Pointer to the task to examine + * @store: Pointer to storage array + * @size: Size of the storage array + * + * Return: An error if it detects any unreliable features of the + * stack. Otherwise it guarantees that the stack trace is + * reliable and returns the number of entries stored. + * + * If the task is not 'current', the caller *must* ensure the task is inactive. + */ +int stack_trace_save_tsk_reliable(struct task_struct *tsk, unsigned long *store, + unsigned int size) +{ + struct stack_trace trace = { + .entries = store, + .max_entries = size, + }; + int ret = save_stack_trace_tsk_reliable(tsk, &trace); + + return ret ? ret : trace.nr_entries; +} +#endif + +#ifdef CONFIG_USER_STACKTRACE_SUPPORT +/** + * stack_trace_save_user - Save a user space stack trace into a storage array + * @store: Pointer to storage array + * @size: Size of the storage array + * + * Return: Number of trace entries stored + */ +unsigned int stack_trace_save_user(unsigned long *store, unsigned int size) +{ + struct stack_trace trace = { + .entries = store, + .max_entries = size, + }; + + save_stack_trace_user(&trace); + return trace.nr_entries; +} +#endif /* CONFIG_USER_STACKTRACE_SUPPORT */ + +#endif /* !CONFIG_ARCH_STACKWALK */ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ca1ee656d6d8..ec439999f387 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -159,6 +159,8 @@ static union trace_eval_map_item *trace_eval_maps; #endif /* CONFIG_TRACE_EVAL_MAP_FILE */ static int tracing_set_tracer(struct trace_array *tr, const char *buf); +static void ftrace_trace_userstack(struct ring_buffer *buffer, + unsigned long flags, int pc); #define MAX_TRACER_SIZE 100 static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata; @@ -2752,12 +2754,21 @@ trace_function(struct trace_array *tr, #ifdef CONFIG_STACKTRACE -#define FTRACE_STACK_MAX_ENTRIES (PAGE_SIZE / sizeof(unsigned long)) +/* Allow 4 levels of nesting: normal, softirq, irq, NMI */ +#define FTRACE_KSTACK_NESTING 4 + +#define FTRACE_KSTACK_ENTRIES (PAGE_SIZE / FTRACE_KSTACK_NESTING) + struct ftrace_stack { - unsigned long calls[FTRACE_STACK_MAX_ENTRIES]; + unsigned long calls[FTRACE_KSTACK_ENTRIES]; +}; + + +struct ftrace_stacks { + struct ftrace_stack stacks[FTRACE_KSTACK_NESTING]; }; -static DEFINE_PER_CPU(struct ftrace_stack, ftrace_stack); +static DEFINE_PER_CPU(struct ftrace_stacks, ftrace_stacks); static DEFINE_PER_CPU(int, ftrace_stack_reserve); static void __ftrace_trace_stack(struct ring_buffer *buffer, @@ -2766,13 +2777,10 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, { struct trace_event_call *call = &event_kernel_stack; struct ring_buffer_event *event; + unsigned int size, nr_entries; + struct ftrace_stack *fstack; struct stack_entry *entry; - struct stack_trace trace; - int use_stack; - int size = FTRACE_STACK_ENTRIES; - - trace.nr_entries = 0; - trace.skip = skip; + int stackidx; /* * Add one, for this function and the call to save_stack_trace() @@ -2780,7 +2788,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, */ #ifndef CONFIG_UNWINDER_ORC if (!regs) - trace.skip++; + skip++; #endif /* @@ -2791,53 +2799,40 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, */ preempt_disable_notrace(); - use_stack = __this_cpu_inc_return(ftrace_stack_reserve); + stackidx = __this_cpu_inc_return(ftrace_stack_reserve) - 1; + + /* This should never happen. If it does, yell once and skip */ + if (WARN_ON_ONCE(stackidx > FTRACE_KSTACK_NESTING)) + goto out; + /* - * We don't need any atomic variables, just a barrier. - * If an interrupt comes in, we don't care, because it would - * have exited and put the counter back to what we want. - * We just need a barrier to keep gcc from moving things - * around. + * The above __this_cpu_inc_return() is 'atomic' cpu local. An + * interrupt will either see the value pre increment or post + * increment. If the interrupt happens pre increment it will have + * restored the counter when it returns. We just need a barrier to + * keep gcc from moving things around. */ barrier(); - if (use_stack == 1) { - trace.entries = this_cpu_ptr(ftrace_stack.calls); - trace.max_entries = FTRACE_STACK_MAX_ENTRIES; - if (regs) - save_stack_trace_regs(regs, &trace); - else - save_stack_trace(&trace); - - if (trace.nr_entries > size) - size = trace.nr_entries; - } else - /* From now on, use_stack is a boolean */ - use_stack = 0; + fstack = this_cpu_ptr(ftrace_stacks.stacks) + stackidx; + size = ARRAY_SIZE(fstack->calls); - size *= sizeof(unsigned long); + if (regs) { + nr_entries = stack_trace_save_regs(regs, fstack->calls, + size, skip); + } else { + nr_entries = stack_trace_save(fstack->calls, size, skip); + } + size = nr_entries * sizeof(unsigned long); event = __trace_buffer_lock_reserve(buffer, TRACE_STACK, sizeof(*entry) + size, flags, pc); if (!event) goto out; entry = ring_buffer_event_data(event); - memset(&entry->caller, 0, size); - - if (use_stack) - memcpy(&entry->caller, trace.entries, - trace.nr_entries * sizeof(unsigned long)); - else { - trace.max_entries = FTRACE_STACK_ENTRIES; - trace.entries = entry->caller; - if (regs) - save_stack_trace_regs(regs, &trace); - else - save_stack_trace(&trace); - } - - entry->size = trace.nr_entries; + memcpy(&entry->caller, fstack->calls, size); + entry->size = nr_entries; if (!call_filter_check_discard(call, entry, buffer, event)) __buffer_unlock_commit(buffer, event); @@ -2907,15 +2902,15 @@ void trace_dump_stack(int skip) } EXPORT_SYMBOL_GPL(trace_dump_stack); +#ifdef CONFIG_USER_STACKTRACE_SUPPORT static DEFINE_PER_CPU(int, user_stack_count); -void +static void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) { struct trace_event_call *call = &event_user_stack; struct ring_buffer_event *event; struct userstack_entry *entry; - struct stack_trace trace; if (!(global_trace.trace_flags & TRACE_ITER_USERSTACKTRACE)) return; @@ -2946,12 +2941,7 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) entry->tgid = current->tgid; memset(&entry->caller, 0, sizeof(entry->caller)); - trace.nr_entries = 0; - trace.max_entries = FTRACE_STACK_ENTRIES; - trace.skip = 0; - trace.entries = entry->caller; - - save_stack_trace_user(&trace); + stack_trace_save_user(entry->caller, FTRACE_STACK_ENTRIES); if (!call_filter_check_discard(call, entry, buffer, event)) __buffer_unlock_commit(buffer, event); @@ -2960,13 +2950,12 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) out: preempt_enable(); } - -#ifdef UNUSED -static void __trace_userstack(struct trace_array *tr, unsigned long flags) +#else /* CONFIG_USER_STACKTRACE_SUPPORT */ +static void ftrace_trace_userstack(struct ring_buffer *buffer, + unsigned long flags, int pc) { - ftrace_trace_userstack(tr, flags, preempt_count()); } -#endif /* UNUSED */ +#endif /* !CONFIG_USER_STACKTRACE_SUPPORT */ #endif /* CONFIG_STACKTRACE */ diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index d80cee49e0eb..639047b259d7 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -782,17 +782,9 @@ void update_max_tr_single(struct trace_array *tr, #endif /* CONFIG_TRACER_MAX_TRACE */ #ifdef CONFIG_STACKTRACE -void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, - int pc); - void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, int pc); #else -static inline void ftrace_trace_userstack(struct ring_buffer *buffer, - unsigned long flags, int pc) -{ -} - static inline void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, int pc) { diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 795aa2038377..a1d20421f4b0 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5186,7 +5186,6 @@ static void event_hist_trigger(struct event_trigger_data *data, void *rec, u64 var_ref_vals[TRACING_MAP_VARS_MAX]; char compound_key[HIST_KEY_SIZE_MAX]; struct tracing_map_elt *elt = NULL; - struct stack_trace stacktrace; struct hist_field *key_field; u64 field_contents; void *key = NULL; @@ -5198,14 +5197,9 @@ static void event_hist_trigger(struct event_trigger_data *data, void *rec, key_field = hist_data->fields[i]; if (key_field->flags & HIST_FIELD_FL_STACKTRACE) { - stacktrace.max_entries = HIST_STACKTRACE_DEPTH; - stacktrace.entries = entries; - stacktrace.nr_entries = 0; - stacktrace.skip = HIST_STACKTRACE_SKIP; - - memset(stacktrace.entries, 0, HIST_STACKTRACE_SIZE); - save_stack_trace(&stacktrace); - + memset(entries, 0, HIST_STACKTRACE_SIZE); + stack_trace_save(entries, HIST_STACKTRACE_DEPTH, + HIST_STACKTRACE_SKIP); key = entries; } else { field_contents = key_field->fn(key_field, elt, rbe, rec); @@ -5246,7 +5240,7 @@ static void hist_trigger_stacktrace_print(struct seq_file *m, unsigned int i; for (i = 0; i < max_entries; i++) { - if (stacktrace_entries[i] == ULONG_MAX) + if (!stacktrace_entries[i]) return; seq_printf(m, "%*c", 1 + spaces, ' '); diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index eec648a0d673..5d16f73898db 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -18,44 +18,32 @@ #include "trace.h" -static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] = - { [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX }; -unsigned stack_trace_index[STACK_TRACE_ENTRIES]; +#define STACK_TRACE_ENTRIES 500 -/* - * Reserve one entry for the passed in ip. This will allow - * us to remove most or all of the stack size overhead - * added by the stack tracer itself. - */ -struct stack_trace stack_trace_max = { - .max_entries = STACK_TRACE_ENTRIES - 1, - .entries = &stack_dump_trace[0], -}; +static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES]; +static unsigned stack_trace_index[STACK_TRACE_ENTRIES]; -unsigned long stack_trace_max_size; -arch_spinlock_t stack_trace_max_lock = +static unsigned int stack_trace_nr_entries; +static unsigned long stack_trace_max_size; +static arch_spinlock_t stack_trace_max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; DEFINE_PER_CPU(int, disable_stack_tracer); static DEFINE_MUTEX(stack_sysctl_mutex); int stack_tracer_enabled; -static int last_stack_tracer_enabled; -void stack_trace_print(void) +static void print_max_stack(void) { long i; int size; pr_emerg(" Depth Size Location (%d entries)\n" " ----- ---- --------\n", - stack_trace_max.nr_entries); + stack_trace_nr_entries); - for (i = 0; i < stack_trace_max.nr_entries; i++) { - if (stack_dump_trace[i] == ULONG_MAX) - break; - if (i+1 == stack_trace_max.nr_entries || - stack_dump_trace[i+1] == ULONG_MAX) + for (i = 0; i < stack_trace_nr_entries; i++) { + if (i + 1 == stack_trace_nr_entries) size = stack_trace_index[i]; else size = stack_trace_index[i] - stack_trace_index[i+1]; @@ -65,16 +53,7 @@ void stack_trace_print(void) } } -/* - * When arch-specific code overrides this function, the following - * data should be filled up, assuming stack_trace_max_lock is held to - * prevent concurrent updates. - * stack_trace_index[] - * stack_trace_max - * stack_trace_max_size - */ -void __weak -check_stack(unsigned long ip, unsigned long *stack) +static void check_stack(unsigned long ip, unsigned long *stack) { unsigned long this_size, flags; unsigned long *p, *top, *start; static int tracer_frame; @@ -110,13 +89,12 @@ check_stack(unsigned long ip, unsigned long *stack) stack_trace_max_size = this_size; - stack_trace_max.nr_entries = 0; - stack_trace_max.skip = 0; - - save_stack_trace(&stack_trace_max); + stack_trace_nr_entries = stack_trace_save(stack_dump_trace, + ARRAY_SIZE(stack_dump_trace) - 1, + 0); /* Skip over the overhead of the stack tracer itself */ - for (i = 0; i < stack_trace_max.nr_entries; i++) { + for (i = 0; i < stack_trace_nr_entries; i++) { if (stack_dump_trace[i] == ip) break; } @@ -125,7 +103,7 @@ check_stack(unsigned long ip, unsigned long *stack) * Some archs may not have the passed in ip in the dump. * If that happens, we need to show everything. */ - if (i == stack_trace_max.nr_entries) + if (i == stack_trace_nr_entries) i = 0; /* @@ -143,15 +121,13 @@ check_stack(unsigned long ip, unsigned long *stack) * loop will only happen once. This code only takes place * on a new max, so it is far from a fast path. */ - while (i < stack_trace_max.nr_entries) { + while (i < stack_trace_nr_entries) { int found = 0; stack_trace_index[x] = this_size; p = start; - for (; p < top && i < stack_trace_max.nr_entries; p++) { - if (stack_dump_trace[i] == ULONG_MAX) - break; + for (; p < top && i < stack_trace_nr_entries; p++) { /* * The READ_ONCE_NOCHECK is used to let KASAN know that * this is not a stack-out-of-bounds error. @@ -182,12 +158,10 @@ check_stack(unsigned long ip, unsigned long *stack) i++; } - stack_trace_max.nr_entries = x; - for (; x < i; x++) - stack_dump_trace[x] = ULONG_MAX; + stack_trace_nr_entries = x; if (task_stack_end_corrupted(current)) { - stack_trace_print(); + print_max_stack(); BUG(); } @@ -286,7 +260,7 @@ __next(struct seq_file *m, loff_t *pos) { long n = *pos - 1; - if (n >= stack_trace_max.nr_entries || stack_dump_trace[n] == ULONG_MAX) + if (n >= stack_trace_nr_entries) return NULL; m->private = (void *)n; @@ -350,7 +324,7 @@ static int t_show(struct seq_file *m, void *v) seq_printf(m, " Depth Size Location" " (%d entries)\n" " ----- ---- --------\n", - stack_trace_max.nr_entries); + stack_trace_nr_entries); if (!stack_tracer_enabled && !stack_trace_max_size) print_disabled(m); @@ -360,12 +334,10 @@ static int t_show(struct seq_file *m, void *v) i = *(long *)v; - if (i >= stack_trace_max.nr_entries || - stack_dump_trace[i] == ULONG_MAX) + if (i >= stack_trace_nr_entries) return 0; - if (i+1 == stack_trace_max.nr_entries || - stack_dump_trace[i+1] == ULONG_MAX) + if (i + 1 == stack_trace_nr_entries) size = stack_trace_index[i]; else size = stack_trace_index[i] - stack_trace_index[i+1]; @@ -422,23 +394,21 @@ stack_trace_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + int was_enabled; int ret; mutex_lock(&stack_sysctl_mutex); + was_enabled = !!stack_tracer_enabled; ret = proc_dointvec(table, write, buffer, lenp, ppos); - if (ret || !write || - (last_stack_tracer_enabled == !!stack_tracer_enabled)) + if (ret || !write || (was_enabled == !!stack_tracer_enabled)) goto out; - last_stack_tracer_enabled = !!stack_tracer_enabled; - if (stack_tracer_enabled) register_ftrace_function(&trace_ops); else unregister_ftrace_function(&trace_ops); - out: mutex_unlock(&stack_sysctl_mutex); return ret; @@ -454,7 +424,6 @@ static __init int enable_stacktrace(char *str) strncpy(stack_trace_filter_buf, str + len, COMMAND_LINE_SIZE); stack_tracer_enabled = 1; - last_stack_tracer_enabled = 1; return 1; } __setup("stacktrace", enable_stacktrace); |