diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/bpf/core.c | 34 | ||||
-rw-r--r-- | kernel/bpf/local_storage.c | 3 | ||||
-rw-r--r-- | kernel/bpf/queue_stack_maps.c | 16 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 2 | ||||
-rw-r--r-- | kernel/events/uprobes.c | 12 | ||||
-rw-r--r-- | kernel/trace/bpf_trace.c | 8 | ||||
-rw-r--r-- | kernel/trace/ftrace.c | 7 | ||||
-rw-r--r-- | kernel/trace/trace.h | 57 | ||||
-rw-r--r-- | kernel/trace/trace_functions_graph.c | 53 | ||||
-rw-r--r-- | kernel/trace/trace_irqsoff.c | 2 | ||||
-rw-r--r-- | kernel/trace/trace_sched_wakeup.c | 2 |
11 files changed, 165 insertions, 31 deletions
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 1a796e0799ec..b1a3545d0ec8 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -672,6 +672,40 @@ void __weak bpf_jit_free(struct bpf_prog *fp) bpf_prog_unlock_free(fp); } +int bpf_jit_get_func_addr(const struct bpf_prog *prog, + const struct bpf_insn *insn, bool extra_pass, + u64 *func_addr, bool *func_addr_fixed) +{ + s16 off = insn->off; + s32 imm = insn->imm; + u8 *addr; + + *func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL; + if (!*func_addr_fixed) { + /* Place-holder address till the last pass has collected + * all addresses for JITed subprograms in which case we + * can pick them up from prog->aux. + */ + if (!extra_pass) + addr = NULL; + else if (prog->aux->func && + off >= 0 && off < prog->aux->func_cnt) + addr = (u8 *)prog->aux->func[off]->bpf_func; + else + return -EINVAL; + } else { + /* Address of a BPF helper call. Since part of the core + * kernel, it's always at a fixed location. __bpf_call_base + * and the helper with imm relative to it are both in core + * kernel. + */ + addr = (u8 *)__bpf_call_base + imm; + } + + *func_addr = (unsigned long)addr; + return 0; +} + static int bpf_jit_blind_insn(const struct bpf_insn *from, const struct bpf_insn *aux, struct bpf_insn *to_buff) diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index c97a8f968638..bed9d48a7ae9 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -139,7 +139,8 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key, return -ENOENT; new = kmalloc_node(sizeof(struct bpf_storage_buffer) + - map->value_size, __GFP_ZERO | GFP_USER, + map->value_size, + __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN, map->numa_node); if (!new) return -ENOMEM; diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index 8bbd72d3a121..b384ea9f3254 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -7,6 +7,7 @@ #include <linux/bpf.h> #include <linux/list.h> #include <linux/slab.h> +#include <linux/capability.h> #include "percpu_freelist.h" #define QUEUE_STACK_CREATE_FLAG_MASK \ @@ -45,8 +46,12 @@ static bool queue_stack_map_is_full(struct bpf_queue_stack *qs) /* Called from syscall */ static int queue_stack_map_alloc_check(union bpf_attr *attr) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 0 || + attr->value_size == 0 || attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK) return -EINVAL; @@ -63,15 +68,10 @@ static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr) { int ret, numa_node = bpf_map_attr_numa_node(attr); struct bpf_queue_stack *qs; - u32 size, value_size; - u64 queue_size, cost; - - size = attr->max_entries + 1; - value_size = attr->value_size; - - queue_size = sizeof(*qs) + (u64) value_size * size; + u64 size, queue_size, cost; - cost = queue_size; + size = (u64) attr->max_entries + 1; + cost = queue_size = sizeof(*qs) + size * attr->value_size; if (cost >= U32_MAX - PAGE_SIZE) return ERR_PTR(-E2BIG); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1971ca325fb4..6dd419550aba 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5650,7 +5650,7 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len return; /* NOTE: fake 'exit' subprog should be updated as well. */ for (i = 0; i <= env->subprog_cnt; i++) { - if (env->subprog_info[i].start < off) + if (env->subprog_info[i].start <= off) continue; env->subprog_info[i].start += len - 1; } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 96d4bee83489..322e97bbb437 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -829,7 +829,7 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file, BUG_ON((uprobe->offset & ~PAGE_MASK) + UPROBE_SWBP_INSN_SIZE > PAGE_SIZE); - smp_wmb(); /* pairs with rmb() in find_active_uprobe() */ + smp_wmb(); /* pairs with the smp_rmb() in handle_swbp() */ set_bit(UPROBE_COPY_INSN, &uprobe->flags); out: @@ -2178,10 +2178,18 @@ static void handle_swbp(struct pt_regs *regs) * After we hit the bp, _unregister + _register can install the * new and not-yet-analyzed uprobe at the same address, restart. */ - smp_rmb(); /* pairs with wmb() in install_breakpoint() */ if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags))) goto out; + /* + * Pairs with the smp_wmb() in prepare_uprobe(). + * + * Guarantees that if we see the UPROBE_COPY_INSN bit set, then + * we must also see the stores to &uprobe->arch performed by the + * prepare_uprobe() call. + */ + smp_rmb(); + /* Tracing handlers use ->utask to communicate with fetch methods */ if (!get_utask()) goto out; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 08fcfe440c63..9864a35c8bb5 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -196,11 +196,13 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, i++; } else if (fmt[i] == 'p' || fmt[i] == 's') { mod[fmt_cnt]++; - i++; - if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0) + /* disallow any further format extensions */ + if (fmt[i + 1] != 0 && + !isspace(fmt[i + 1]) && + !ispunct(fmt[i + 1])) return -EINVAL; fmt_cnt++; - if (fmt[i - 1] == 's') { + if (fmt[i] == 's') { if (str_seen) /* allow only one '%s' per fmt string */ return -EINVAL; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f536f601bd46..77734451cb05 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -817,7 +817,7 @@ function_profile_call(unsigned long ip, unsigned long parent_ip, #ifdef CONFIG_FUNCTION_GRAPH_TRACER static int profile_graph_entry(struct ftrace_graph_ent *trace) { - int index = trace->depth; + int index = current->curr_ret_stack; function_profile_call(trace->func, 0, NULL, NULL); @@ -852,7 +852,7 @@ static void profile_graph_return(struct ftrace_graph_ret *trace) if (!fgraph_graph_time) { int index; - index = trace->depth; + index = current->curr_ret_stack; /* Append this call time to the parent time to subtract */ if (index) @@ -6814,6 +6814,7 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list) atomic_set(&t->tracing_graph_pause, 0); atomic_set(&t->trace_overrun, 0); t->curr_ret_stack = -1; + t->curr_ret_depth = -1; /* Make sure the tasks see the -1 first: */ smp_wmb(); t->ret_stack = ret_stack_list[start++]; @@ -7038,6 +7039,7 @@ graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack) void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) { t->curr_ret_stack = -1; + t->curr_ret_depth = -1; /* * The idle task has no parent, it either has its own * stack or no stack at all. @@ -7068,6 +7070,7 @@ void ftrace_graph_init_task(struct task_struct *t) /* Make sure we do not use the parent ret_stack */ t->ret_stack = NULL; t->curr_ret_stack = -1; + t->curr_ret_depth = -1; if (ftrace_graph_active) { struct ftrace_ret_stack *ret_stack; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 3b8c0e24ab30..447bd96ee658 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -512,12 +512,44 @@ enum { * can only be modified by current, we can reuse trace_recursion. */ TRACE_IRQ_BIT, + + /* Set if the function is in the set_graph_function file */ + TRACE_GRAPH_BIT, + + /* + * In the very unlikely case that an interrupt came in + * at a start of graph tracing, and we want to trace + * the function in that interrupt, the depth can be greater + * than zero, because of the preempted start of a previous + * trace. In an even more unlikely case, depth could be 2 + * if a softirq interrupted the start of graph tracing, + * followed by an interrupt preempting a start of graph + * tracing in the softirq, and depth can even be 3 + * if an NMI came in at the start of an interrupt function + * that preempted a softirq start of a function that + * preempted normal context!!!! Luckily, it can't be + * greater than 3, so the next two bits are a mask + * of what the depth is when we set TRACE_GRAPH_BIT + */ + + TRACE_GRAPH_DEPTH_START_BIT, + TRACE_GRAPH_DEPTH_END_BIT, }; #define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0) #define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(1<<(bit)); } while (0) #define trace_recursion_test(bit) ((current)->trace_recursion & (1<<(bit))) +#define trace_recursion_depth() \ + (((current)->trace_recursion >> TRACE_GRAPH_DEPTH_START_BIT) & 3) +#define trace_recursion_set_depth(depth) \ + do { \ + current->trace_recursion &= \ + ~(3 << TRACE_GRAPH_DEPTH_START_BIT); \ + current->trace_recursion |= \ + ((depth) & 3) << TRACE_GRAPH_DEPTH_START_BIT; \ + } while (0) + #define TRACE_CONTEXT_BITS 4 #define TRACE_FTRACE_START TRACE_FTRACE_BIT @@ -843,8 +875,9 @@ extern void __trace_graph_return(struct trace_array *tr, extern struct ftrace_hash *ftrace_graph_hash; extern struct ftrace_hash *ftrace_graph_notrace_hash; -static inline int ftrace_graph_addr(unsigned long addr) +static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace) { + unsigned long addr = trace->func; int ret = 0; preempt_disable_notrace(); @@ -855,6 +888,14 @@ static inline int ftrace_graph_addr(unsigned long addr) } if (ftrace_lookup_ip(ftrace_graph_hash, addr)) { + + /* + * This needs to be cleared on the return functions + * when the depth is zero. + */ + trace_recursion_set(TRACE_GRAPH_BIT); + trace_recursion_set_depth(trace->depth); + /* * If no irqs are to be traced, but a set_graph_function * is set, and called by an interrupt handler, we still @@ -872,6 +913,13 @@ out: return ret; } +static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace) +{ + if (trace_recursion_test(TRACE_GRAPH_BIT) && + trace->depth == trace_recursion_depth()) + trace_recursion_clear(TRACE_GRAPH_BIT); +} + static inline int ftrace_graph_notrace_addr(unsigned long addr) { int ret = 0; @@ -885,7 +933,7 @@ static inline int ftrace_graph_notrace_addr(unsigned long addr) return ret; } #else -static inline int ftrace_graph_addr(unsigned long addr) +static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace) { return 1; } @@ -894,6 +942,8 @@ static inline int ftrace_graph_notrace_addr(unsigned long addr) { return 0; } +static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace) +{ } #endif /* CONFIG_DYNAMIC_FTRACE */ extern unsigned int fgraph_max_depth; @@ -901,7 +951,8 @@ extern unsigned int fgraph_max_depth; static inline bool ftrace_graph_ignore_func(struct ftrace_graph_ent *trace) { /* trace it when it is-nested-in or is a function enabled. */ - return !(trace->depth || ftrace_graph_addr(trace->func)) || + return !(trace_recursion_test(TRACE_GRAPH_BIT) || + ftrace_graph_addr(trace)) || (trace->depth < 0) || (fgraph_max_depth && trace->depth >= fgraph_max_depth); } diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 169b3c44ee97..086af4f5c3e8 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -118,8 +118,8 @@ print_graph_duration(struct trace_array *tr, unsigned long long duration, struct trace_seq *s, u32 flags); /* Add a function return address to the trace stack on thread info.*/ -int -ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, +static int +ftrace_push_return_trace(unsigned long ret, unsigned long func, unsigned long frame_pointer, unsigned long *retp) { unsigned long long calltime; @@ -177,9 +177,31 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, #ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR current->ret_stack[index].retp = retp; #endif - *depth = current->curr_ret_stack; + return 0; +} + +int function_graph_enter(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp) +{ + struct ftrace_graph_ent trace; + + trace.func = func; + trace.depth = ++current->curr_ret_depth; + + if (ftrace_push_return_trace(ret, func, + frame_pointer, retp)) + goto out; + + /* Only trace if the calling function expects to */ + if (!ftrace_graph_entry(&trace)) + goto out_ret; return 0; + out_ret: + current->curr_ret_stack--; + out: + current->curr_ret_depth--; + return -EBUSY; } /* Retrieve a function return address to the trace stack on thread info.*/ @@ -241,7 +263,13 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, trace->func = current->ret_stack[index].func; trace->calltime = current->ret_stack[index].calltime; trace->overrun = atomic_read(¤t->trace_overrun); - trace->depth = index; + trace->depth = current->curr_ret_depth--; + /* + * We still want to trace interrupts coming in if + * max_depth is set to 1. Make sure the decrement is + * seen before ftrace_graph_return. + */ + barrier(); } /* @@ -255,6 +283,12 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer) ftrace_pop_return_trace(&trace, &ret, frame_pointer); trace.rettime = trace_clock_local(); + ftrace_graph_return(&trace); + /* + * The ftrace_graph_return() may still access the current + * ret_stack structure, we need to make sure the update of + * curr_ret_stack is after that. + */ barrier(); current->curr_ret_stack--; /* @@ -267,13 +301,6 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer) return ret; } - /* - * The trace should run after decrementing the ret counter - * in case an interrupt were to come in. We don't want to - * lose the interrupt if max_depth is set. - */ - ftrace_graph_return(&trace); - if (unlikely(!ret)) { ftrace_graph_stop(); WARN_ON(1); @@ -482,6 +509,8 @@ void trace_graph_return(struct ftrace_graph_ret *trace) int cpu; int pc; + ftrace_graph_addr_finish(trace); + local_irq_save(flags); cpu = raw_smp_processor_id(); data = per_cpu_ptr(tr->trace_buffer.data, cpu); @@ -505,6 +534,8 @@ void set_graph_array(struct trace_array *tr) static void trace_graph_thresh_return(struct ftrace_graph_ret *trace) { + ftrace_graph_addr_finish(trace); + if (tracing_thresh && (trace->rettime - trace->calltime < tracing_thresh)) return; diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index b7357f9f82a3..98ea6d28df15 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -208,6 +208,8 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace) unsigned long flags; int pc; + ftrace_graph_addr_finish(trace); + if (!func_prolog_dec(tr, &data, &flags)) return; diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index a86b303e6c67..7d04b9890755 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -270,6 +270,8 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace) unsigned long flags; int pc; + ftrace_graph_addr_finish(trace); + if (!func_prolog_preempt_disable(tr, &data, &pc)) return; |