diff options
Diffstat (limited to 'kernel/trace')
| -rw-r--r-- | kernel/trace/Kconfig | 40 | ||||
| -rw-r--r-- | kernel/trace/Makefile | 3 | ||||
| -rw-r--r-- | kernel/trace/blktrace.c | 27 | ||||
| -rw-r--r-- | kernel/trace/bpf_trace.c | 357 | ||||
| -rw-r--r-- | kernel/trace/fgraph.c | 4 | ||||
| -rw-r--r-- | kernel/trace/fprobe.c | 332 | ||||
| -rw-r--r-- | kernel/trace/ftrace.c | 64 | ||||
| -rw-r--r-- | kernel/trace/rethook.c | 317 | ||||
| -rw-r--r-- | kernel/trace/trace.c | 73 | ||||
| -rw-r--r-- | kernel/trace/trace.h | 2 | ||||
| -rw-r--r-- | kernel/trace/trace_events.c | 104 | ||||
| -rw-r--r-- | kernel/trace/trace_events_hist.c | 33 | ||||
| -rw-r--r-- | kernel/trace/trace_events_synth.c | 14 | ||||
| -rw-r--r-- | kernel/trace/trace_events_user.c | 1690 | ||||
| -rw-r--r-- | kernel/trace/trace_osnoise.c | 4 | ||||
| -rw-r--r-- | kernel/trace/trace_sched_switch.c | 3 | ||||
| -rw-r--r-- | kernel/trace/trace_sched_wakeup.c | 1 |
17 files changed, 3014 insertions, 54 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index a5eb5e7fd624..9bb54c0b3b2d 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -10,6 +10,17 @@ config USER_STACKTRACE_SUPPORT config NOP_TRACER bool +config HAVE_RETHOOK + bool + +config RETHOOK + bool + depends on HAVE_RETHOOK + help + Enable generic return hooking feature. This is an internal + API, which will be used by other function-entry hooking + features like fprobe and kprobes. + config HAVE_FUNCTION_TRACER bool help @@ -236,6 +247,21 @@ config DYNAMIC_FTRACE_WITH_ARGS depends on DYNAMIC_FTRACE depends on HAVE_DYNAMIC_FTRACE_WITH_ARGS +config FPROBE + bool "Kernel Function Probe (fprobe)" + depends on FUNCTION_TRACER + depends on DYNAMIC_FTRACE_WITH_REGS + depends on HAVE_RETHOOK + select RETHOOK + default n + help + This option enables kernel function probe (fprobe) based on ftrace. + The fprobe is similar to kprobes, but probes only for kernel function + entries and exits. This also can probe multiple functions by one + fprobe. + + If unsure, say N. + config FUNCTION_PROFILER bool "Kernel function profiler" depends on FUNCTION_TRACER @@ -737,6 +763,20 @@ config SYNTH_EVENTS If in doubt, say N. +config USER_EVENTS + bool "User trace events" + select TRACING + select DYNAMIC_EVENTS + help + User trace events are user-defined trace events that + can be used like an existing kernel trace event. User trace + events are generated by writing to a tracefs file. User + processes can determine if their tracing events should be + generated by memory mapping a tracefs file and checking for + an associated byte being non-zero. + + If in doubt, say N. + config HIST_TRIGGERS bool "Histogram triggers" depends on ARCH_HAVE_NMI_SAFE_CMPXCHG diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index bedc5caceec7..d77cd8032213 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -82,6 +82,7 @@ obj-$(CONFIG_PROBE_EVENTS) += trace_eprobe.o obj-$(CONFIG_TRACE_EVENT_INJECT) += trace_events_inject.o obj-$(CONFIG_SYNTH_EVENTS) += trace_events_synth.o obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o +obj-$(CONFIG_USER_EVENTS) += trace_events_user.o obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o obj-$(CONFIG_TRACEPOINTS) += error_report-traces.o @@ -97,6 +98,8 @@ obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o obj-$(CONFIG_BOOTTIME_TRACING) += trace_boot.o obj-$(CONFIG_FTRACE_RECORD_RECURSION) += trace_recursion_record.o +obj-$(CONFIG_FPROBE) += fprobe.o +obj-$(CONFIG_RETHOOK) += rethook.o obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index af68a67179b4..4d5629196d01 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -310,10 +310,20 @@ record_it: local_irq_restore(flags); } -static void blk_trace_free(struct blk_trace *bt) +static void blk_trace_free(struct request_queue *q, struct blk_trace *bt) { relay_close(bt->rchan); - debugfs_remove(bt->dir); + + /* + * If 'bt->dir' is not set, then both 'dropped' and 'msg' are created + * under 'q->debugfs_dir', thus lookup and remove them. + */ + if (!bt->dir) { + debugfs_remove(debugfs_lookup("dropped", q->debugfs_dir)); + debugfs_remove(debugfs_lookup("msg", q->debugfs_dir)); + } else { + debugfs_remove(bt->dir); + } free_percpu(bt->sequence); free_percpu(bt->msg_data); kfree(bt); @@ -335,10 +345,10 @@ static void put_probe_ref(void) mutex_unlock(&blk_probe_mutex); } -static void blk_trace_cleanup(struct blk_trace *bt) +static void blk_trace_cleanup(struct request_queue *q, struct blk_trace *bt) { synchronize_rcu(); - blk_trace_free(bt); + blk_trace_free(q, bt); put_probe_ref(); } @@ -352,7 +362,7 @@ static int __blk_trace_remove(struct request_queue *q) return -EINVAL; if (bt->trace_state != Blktrace_running) - blk_trace_cleanup(bt); + blk_trace_cleanup(q, bt); return 0; } @@ -572,7 +582,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, ret = 0; err: if (ret) - blk_trace_free(bt); + blk_trace_free(q, bt); return ret; } @@ -1616,7 +1626,7 @@ static int blk_trace_remove_queue(struct request_queue *q) put_probe_ref(); synchronize_rcu(); - blk_trace_free(bt); + blk_trace_free(q, bt); return 0; } @@ -1647,7 +1657,7 @@ static int blk_trace_setup_queue(struct request_queue *q, return 0; free_bt: - blk_trace_free(bt); + blk_trace_free(q, bt); return ret; } @@ -1892,7 +1902,6 @@ void blk_fill_rwbs(char *rwbs, unsigned int op) switch (op & REQ_OP_MASK) { case REQ_OP_WRITE: - case REQ_OP_WRITE_SAME: rwbs[i++] = 'W'; break; case REQ_OP_DISCARD: diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 21aa30644219..7fa2ebc07f60 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -17,6 +17,9 @@ #include <linux/error-injection.h> #include <linux/btf_ids.h> #include <linux/bpf_lsm.h> +#include <linux/fprobe.h> +#include <linux/bsearch.h> +#include <linux/sort.h> #include <net/bpf_sk_storage.h> @@ -77,6 +80,8 @@ u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags, const struct btf **btf, s32 *btf_id); +static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx); +static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx); /** * trace_call_bpf - invoke BPF program @@ -332,8 +337,6 @@ BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src, if (unlikely(in_interrupt() || current->flags & (PF_KTHREAD | PF_EXITING))) return -EPERM; - if (unlikely(uaccess_kernel())) - return -EPERM; if (unlikely(!nmi_uaccess_okay())) return -EPERM; @@ -835,8 +838,6 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type) */ if (unlikely(current->flags & (PF_KTHREAD | PF_EXITING))) return -EPERM; - if (unlikely(uaccess_kernel())) - return -EPERM; if (unlikely(!nmi_uaccess_okay())) return -EPERM; @@ -1036,6 +1037,30 @@ static const struct bpf_func_proto bpf_get_func_ip_proto_kprobe = { .arg1_type = ARG_PTR_TO_CTX, }; +BPF_CALL_1(bpf_get_func_ip_kprobe_multi, struct pt_regs *, regs) +{ + return bpf_kprobe_multi_entry_ip(current->bpf_ctx); +} + +static const struct bpf_func_proto bpf_get_func_ip_proto_kprobe_multi = { + .func = bpf_get_func_ip_kprobe_multi, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + +BPF_CALL_1(bpf_get_attach_cookie_kprobe_multi, struct pt_regs *, regs) +{ + return bpf_kprobe_multi_cookie(current->bpf_ctx); +} + +static const struct bpf_func_proto bpf_get_attach_cookie_proto_kmulti = { + .func = bpf_get_attach_cookie_kprobe_multi, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + BPF_CALL_1(bpf_get_attach_cookie_trace, void *, ctx) { struct bpf_trace_run_ctx *run_ctx; @@ -1235,6 +1260,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_task_stack_proto; case BPF_FUNC_copy_from_user: return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL; + case BPF_FUNC_copy_from_user_task: + return prog->aux->sleepable ? &bpf_copy_from_user_task_proto : NULL; case BPF_FUNC_snprintf_btf: return &bpf_snprintf_btf_proto; case BPF_FUNC_per_cpu_ptr: @@ -1277,9 +1304,13 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_override_return_proto; #endif case BPF_FUNC_get_func_ip: - return &bpf_get_func_ip_proto_kprobe; + return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI ? + &bpf_get_func_ip_proto_kprobe_multi : + &bpf_get_func_ip_proto_kprobe; case BPF_FUNC_get_attach_cookie: - return &bpf_get_attach_cookie_proto_trace; + return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI ? + &bpf_get_attach_cookie_proto_kmulti : + &bpf_get_attach_cookie_proto_trace; default: return bpf_tracing_func_proto(func_id, prog); } @@ -1562,6 +1593,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = { extern const struct bpf_func_proto bpf_skb_output_proto; extern const struct bpf_func_proto bpf_xdp_output_proto; +extern const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto; BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args, struct bpf_map *, map, u64, flags) @@ -1661,6 +1693,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sock_from_file_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_ptr_cookie_proto; + case BPF_FUNC_xdp_get_buff_len: + return &bpf_xdp_get_buff_len_trace_proto; #endif case BPF_FUNC_seq_printf: return prog->expected_attach_type == BPF_TRACE_ITER ? @@ -2176,3 +2210,314 @@ static int __init bpf_event_init(void) fs_initcall(bpf_event_init); #endif /* CONFIG_MODULES */ + +#ifdef CONFIG_FPROBE +struct bpf_kprobe_multi_link { + struct bpf_link link; + struct fprobe fp; + unsigned long *addrs; + u64 *cookies; + u32 cnt; +}; + +struct bpf_kprobe_multi_run_ctx { + struct bpf_run_ctx run_ctx; + struct bpf_kprobe_multi_link *link; + unsigned long entry_ip; +}; + +static void bpf_kprobe_multi_link_release(struct bpf_link *link) +{ + struct bpf_kprobe_multi_link *kmulti_link; + + kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); + unregister_fprobe(&kmulti_link->fp); +} + +static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link) +{ + struct bpf_kprobe_multi_link *kmulti_link; + + kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); + kvfree(kmulti_link->addrs); + kvfree(kmulti_link->cookies); + kfree(kmulti_link); +} + +static const struct bpf_link_ops bpf_kprobe_multi_link_lops = { + .release = bpf_kprobe_multi_link_release, + .dealloc = bpf_kprobe_multi_link_dealloc, +}; + +static void bpf_kprobe_multi_cookie_swap(void *a, void *b, int size, const void *priv) +{ + const struct bpf_kprobe_multi_link *link = priv; + unsigned long *addr_a = a, *addr_b = b; + u64 *cookie_a, *cookie_b; + unsigned long tmp1; + u64 tmp2; + + cookie_a = link->cookies + (addr_a - link->addrs); + cookie_b = link->cookies + (addr_b - link->addrs); + + /* swap addr_a/addr_b and cookie_a/cookie_b values */ + tmp1 = *addr_a; *addr_a = *addr_b; *addr_b = tmp1; + tmp2 = *cookie_a; *cookie_a = *cookie_b; *cookie_b = tmp2; +} + +static int __bpf_kprobe_multi_cookie_cmp(const void *a, const void *b) +{ + const unsigned long *addr_a = a, *addr_b = b; + + if (*addr_a == *addr_b) + return 0; + return *addr_a < *addr_b ? -1 : 1; +} + +static int bpf_kprobe_multi_cookie_cmp(const void *a, const void *b, const void *priv) +{ + return __bpf_kprobe_multi_cookie_cmp(a, b); +} + +static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx) +{ + struct bpf_kprobe_multi_run_ctx *run_ctx; + struct bpf_kprobe_multi_link *link; + u64 *cookie, entry_ip; + unsigned long *addr; + + if (WARN_ON_ONCE(!ctx)) + return 0; + run_ctx = container_of(current->bpf_ctx, struct bpf_kprobe_multi_run_ctx, run_ctx); + link = run_ctx->link; + if (!link->cookies) + return 0; + entry_ip = run_ctx->entry_ip; + addr = bsearch(&entry_ip, link->addrs, link->cnt, sizeof(entry_ip), + __bpf_kprobe_multi_cookie_cmp); + if (!addr) + return 0; + cookie = link->cookies + (addr - link->addrs); + return *cookie; +} + +static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx) +{ + struct bpf_kprobe_multi_run_ctx *run_ctx; + + run_ctx = container_of(current->bpf_ctx, struct bpf_kprobe_multi_run_ctx, run_ctx); + return run_ctx->entry_ip; +} + +static int +kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, + unsigned long entry_ip, struct pt_regs *regs) +{ + struct bpf_kprobe_multi_run_ctx run_ctx = { + .link = link, + .entry_ip = entry_ip, + }; + struct bpf_run_ctx *old_run_ctx; + int err; + + if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { + err = 0; + goto out; + } + + migrate_disable(); + rcu_read_lock(); + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + err = bpf_prog_run(link->link.prog, regs); + bpf_reset_run_ctx(old_run_ctx); + rcu_read_unlock(); + migrate_enable(); + + out: + __this_cpu_dec(bpf_prog_active); + return err; +} + +static void +kprobe_multi_link_handler(struct fprobe *fp, unsigned long entry_ip, + struct pt_regs *regs) +{ + struct bpf_kprobe_multi_link *link; + + link = container_of(fp, struct bpf_kprobe_multi_link, fp); + kprobe_multi_link_prog_run(link, entry_ip, regs); +} + +static int +kprobe_multi_resolve_syms(const void *usyms, u32 cnt, + unsigned long *addrs) +{ + unsigned long addr, size; + const char **syms; + int err = -ENOMEM; + unsigned int i; + char *func; + + size = cnt * sizeof(*syms); + syms = kvzalloc(size, GFP_KERNEL); + if (!syms) + return -ENOMEM; + + func = kmalloc(KSYM_NAME_LEN, GFP_KERNEL); + if (!func) + goto error; + + if (copy_from_user(syms, usyms, size)) { + err = -EFAULT; + goto error; + } + + for (i = 0; i < cnt; i++) { + err = strncpy_from_user(func, syms[i], KSYM_NAME_LEN); + if (err == KSYM_NAME_LEN) + err = -E2BIG; + if (err < 0) + goto error; + err = -EINVAL; + addr = kallsyms_lookup_name(func); + if (!addr) + goto error; + if (!kallsyms_lookup_size_offset(addr, &size, NULL)) + goto error; + addr = ftrace_location_range(addr, addr + size - 1); + if (!addr) + goto error; + addrs[i] = addr; + } + + err = 0; +error: + kvfree(syms); + kfree(func); + return err; +} + +int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_kprobe_multi_link *link = NULL; + struct bpf_link_primer link_primer; + void __user *ucookies; + unsigned long *addrs; + u32 flags, cnt, size; + void __user *uaddrs; + u64 *cookies = NULL; + void __user *usyms; + int err; + + /* no support for 32bit archs yet */ + if (sizeof(u64) != sizeof(void *)) + return -EOPNOTSUPP; + + if (prog->expected_attach_type != BPF_TRACE_KPROBE_MULTI) + return -EINVAL; + + flags = attr->link_create.kprobe_multi.flags; + if (flags & ~BPF_F_KPROBE_MULTI_RETURN) + return -EINVAL; + + uaddrs = u64_to_user_ptr(attr->link_create.kprobe_multi.addrs); + usyms = u64_to_user_ptr(attr->link_create.kprobe_multi.syms); + if (!!uaddrs == !!usyms) + return -EINVAL; + + cnt = attr->link_create.kprobe_multi.cnt; + if (!cnt) + return -EINVAL; + + size = cnt * sizeof(*addrs); + addrs = kvmalloc(size, GFP_KERNEL); + if (!addrs) + return -ENOMEM; + + if (uaddrs) { + if (copy_from_user(addrs, uaddrs, size)) { + err = -EFAULT; + goto error; + } + } else { + err = kprobe_multi_resolve_syms(usyms, cnt, addrs); + if (err) + goto error; + } + + ucookies = u64_to_user_ptr(attr->link_create.kprobe_multi.cookies); + if (ucookies) { + cookies = kvmalloc(size, GFP_KERNEL); + if (!cookies) { + err = -ENOMEM; + goto error; + } + if (copy_from_user(cookies, ucookies, size)) { + err = -EFAULT; + goto error; + } + } + + link = kzalloc(sizeof(*link), GFP_KERNEL); + if (!link) { + err = -ENOMEM; + goto error; + } + + bpf_link_init(&link->link, BPF_LINK_TYPE_KPROBE_MULTI, + &bpf_kprobe_multi_link_lops, prog); + + err = bpf_link_prime(&link->link, &link_primer); + if (err) + goto error; + + if (flags & BPF_F_KPROBE_MULTI_RETURN) + link->fp.exit_handler = kprobe_multi_link_handler; + else + link->fp.entry_handler = kprobe_multi_link_handler; + + link->addrs = addrs; + link->cookies = cookies; + link->cnt = cnt; + + if (cookies) { + /* + * Sorting addresses will trigger sorting cookies as well + * (check bpf_kprobe_multi_cookie_swap). This way we can + * find cookie based on the address in bpf_get_attach_cookie + * helper. + */ + sort_r(addrs, cnt, sizeof(*addrs), + bpf_kprobe_multi_cookie_cmp, + bpf_kprobe_multi_cookie_swap, + link); + } + + err = register_fprobe_ips(&link->fp, addrs, cnt); + if (err) { + bpf_link_cleanup(&link_primer); + return err; + } + + return bpf_link_settle(&link_primer); + +error: + kfree(link); + kvfree(addrs); + kvfree(cookies); + return err; +} +#else /* !CONFIG_FPROBE */ +int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} +static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx) +{ + return 0; +} +static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx) +{ + return 0; +} +#endif diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 22061d38fc00..19028e072cdb 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -415,7 +415,9 @@ free: static void ftrace_graph_probe_sched_switch(void *ignore, bool preempt, - struct task_struct *prev, struct task_struct *next) + unsigned int prev_state, + struct task_struct *prev, + struct task_struct *next) { unsigned long long timestamp; int index; diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c new file mode 100644 index 000000000000..8b2dd5b9dcd1 --- /dev/null +++ b/kernel/trace/fprobe.c @@ -0,0 +1,332 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * fprobe - Simple ftrace probe wrapper for function entry. + */ +#define pr_fmt(fmt) "fprobe: " fmt + +#include <linux/err.h> +#include <linux/fprobe.h> +#include <linux/kallsyms.h> +#include <linux/kprobes.h> +#include <linux/rethook.h> +#include <linux/slab.h> +#include <linux/sort.h> + +#include "trace.h" + +struct fprobe_rethook_node { + struct rethook_node node; + unsigned long entry_ip; +}; + +static 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; + struct fprobe *fp; + int bit; + + fp = container_of(ops, struct fprobe, ops); + if (fprobe_disabled(fp)) + return; + + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) { + fp->nmissed++; + return; + } + + if (fp->entry_handler) + fp->entry_handler(fp, ip, ftrace_get_regs(fregs)); + + if (fp->exit_handler) { + rh = rethook_try_get(fp->rethook); + if (!rh) { + fp->nmissed++; + goto out; + } + fpr = container_of(rh, struct fprobe_rethook_node, node); + fpr->entry_ip = ip; + rethook_hook(rh, ftrace_get_regs(fregs), true); + } + +out: + ftrace_test_recursion_unlock(bit); +} +NOKPROBE_SYMBOL(fprobe_handler); + +static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct ftrace_regs *fregs) +{ + struct fprobe *fp = container_of(ops, struct fprobe, ops); + + if (unlikely(kprobe_running())) { + fp->nmissed++; + return; + } + kprobe_busy_begin(); + fprobe_handler(ip, parent_ip, ops, fregs); + kprobe_busy_end(); +} + +static void fprobe_exit_handler(struct rethook_node *rh, void *data, + struct pt_regs *regs) +{ + struct fprobe *fp = (struct fprobe *)data; + struct fprobe_rethook_node *fpr; + + if (!fp || fprobe_disabled(fp)) + return; + + fpr = container_of(rh, struct fprobe_rethook_node, node); + + fp->exit_handler(fp, fpr->entry_ip, regs); +} +NOKPROBE_SYMBOL(fprobe_exit_handler); + +/* Convert ftrace location address from symbols */ +static unsigned long *get_ftrace_locations(const char **syms, int num) +{ + unsigned long addr, size; + unsigned long *addrs; + int i; + + /* Convert symbols to symbol address */ + addrs = kcalloc(num, sizeof(*addrs), GFP_KERNEL); + if (!addrs) + return ERR_PTR(-ENOMEM); + + for (i = 0; i < num; i++) { + addr = kallsyms_lookup_name(syms[i]); + if (!addr) /* Maybe wrong symbol */ + goto error; + + /* Convert symbol address to ftrace location. */ + if (!kallsyms_lookup_size_offset(addr, &size, NULL) || !size) + goto error; + + addr = ftrace_location_range(addr, addr + size - 1); + if (!addr) /* No dynamic ftrace there. */ + goto error; + + addrs[i] = addr; + } + + return addrs; + +error: + kfree(addrs); + + 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; +} + +static int fprobe_init_rethook(struct fprobe *fp, int num) +{ + int i, size; + + if (num < 0) + return -EINVAL; + + if (!fp->exit_handler) { + fp->rethook = NULL; + return 0; + } + + /* Initialize rethook if needed */ + size = num * num_possible_cpus() * 2; + if (size < 0) + return -E2BIG; + + fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler); + for (i = 0; i < size; i++) { + struct rethook_node *node; + + node = kzalloc(sizeof(struct fprobe_rethook_node), GFP_KERNEL); + if (!node) { + rethook_free(fp->rethook); + fp->rethook = NULL; + return -ENOMEM; + } + rethook_add_node(fp->rethook, node); + } + return 0; +} + +static void fprobe_fail_cleanup(struct fprobe *fp) +{ + if (fp->rethook) { + /* Don't need to cleanup rethook->handler because this is not used. */ + rethook_free(fp->rethook); + fp->rethook = NULL; + } + ftrace_free_filter(&fp->ops); +} + +/** + * register_fprobe() - Register fprobe to ftrace by pattern. + * @fp: A fprobe data structure to be registered. + * @filter: A wildcard pattern of probed symbols. + * @notfilter: A wildcard pattern of NOT probed symbols. + * + * Register @fp to ftrace for enabling the probe on the symbols matched to @filter. + * If @notfilter is not NULL, the symbols matched the @notfilter are not probed. + * + * Return 0 if @fp is registered successfully, -errno if not. + */ +int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter) +{ + struct ftrace_hash *hash; + unsigned char *str; + int ret, len; + + 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) + 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 = 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); + +out: + if (ret) + fprobe_fail_cleanup(fp); + return ret; +} +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. + * @num: The number of entries of @addrs. + * + * Register @fp to ftrace for enabling the probe on the address given by @addrs. + * The @addrs must be the addresses of ftrace location address, which may be + * the symbol address + arch-dependent offset. + * If you unsure what this mean, please use other registration functions. + * + * Return 0 if @fp is registered successfully, -errno if not. + */ +int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num) +{ + int ret; + + if (!fp || !addrs || num <= 0) + return -EINVAL; + + fprobe_init(fp); + + ret = ftrace_set_filter_ips(&fp->ops, addrs, num, 0, 0); + if (ret) + return ret; + + ret = fprobe_init_rethook(fp, num); + if (!ret) + ret = register_ftrace_function(&fp->ops); + + if (ret) + fprobe_fail_cleanup(fp); + return ret; +} +EXPORT_SYMBOL_GPL(register_fprobe_ips); + +/** + * register_fprobe_syms() - Register fprobe to ftrace by symbols. + * @fp: A fprobe data structure to be registered. + * @syms: An array of target symbols. + * @num: The number of entries of @syms. + * + * Register @fp to the symbols given by @syms array. This will be useful if + * you are sure the symbols exist in the kernel. + * + * Return 0 if @fp is registered successfully, -errno if not. + */ +int register_fprobe_syms(struct fprobe *fp, const char **syms, int num) +{ + unsigned long *addrs; + int ret; + + if (!fp || !syms || num <= 0) + return -EINVAL; + + addrs = get_ftrace_locations(syms, num); + if (IS_ERR(addrs)) + return PTR_ERR(addrs); + + ret = register_fprobe_ips(fp, addrs, num); + + kfree(addrs); + + return ret; +} +EXPORT_SYMBOL_GPL(register_fprobe_syms); + +/** + * unregister_fprobe() - Unregister fprobe from ftrace + * @fp: A fprobe data structure to be unregistered. + * + * Unregister fprobe (and remove ftrace hooks from the function entries). + * + * Return 0 if @fp is unregistered successfully, -errno if not. + */ +int unregister_fprobe(struct fprobe *fp) +{ + int ret; + + if (!fp || fp->ops.func != fprobe_handler) + return -EINVAL; + + /* + * rethook_free() starts disabling the rethook, but the rethook handlers + * may be running on other processors at this point. To make sure that all + * current running handlers are finished, call unregister_ftrace_function() + * after this. + */ + if (fp->rethook) + rethook_free(fp->rethook); + + ret = unregister_ftrace_function(&fp->ops); + if (ret < 0) + return ret; + + ftrace_free_filter(&fp->ops); + + return ret; +} +EXPORT_SYMBOL_GPL(unregister_fprobe); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6105b7036482..2e114659f7f8 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4958,7 +4958,7 @@ ftrace_notrace_write(struct file *file, const char __user *ubuf, } static int -ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) +__ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) { struct ftrace_func_entry *entry; @@ -4977,8 +4977,29 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) } static int +ftrace_match_addr(struct ftrace_hash *hash, unsigned long *ips, + unsigned int cnt, int remove) +{ + unsigned int i; + int err; + + for (i = 0; i < cnt; i++) { + err = __ftrace_match_addr(hash, ips[i], remove); + if (err) { + /* + * This expects the @hash is a temporary hash and if this + * fails the caller must free the @hash. + */ + return err; + } + } + return 0; +} + +static int ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, - unsigned long ip, int remove, int reset, int enable) + unsigned long *ips, unsigned int cnt, + int remove, int reset, int enable) { struct ftrace_hash **orig_hash; struct ftrace_hash *hash; @@ -5008,8 +5029,8 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, ret = -EINVAL; goto out_regex_unlock; } - if (ip) { - ret = ftrace_match_addr(hash, ip, remove); + if (ips) { + ret = ftrace_match_addr(hash, ips, cnt, remove); if (ret < 0) goto out_regex_unlock; } @@ -5026,10 +5047,10 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, } static int -ftrace_set_addr(struct ftrace_ops *ops, unsigned long ip, int remove, - int reset, int enable) +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, ip, remove, reset, enable); + return ftrace_set_hash(ops, NULL, 0, ips, cnt, remove, reset, enable); } #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS @@ -5634,11 +5655,30 @@ int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip, int remove, int reset) { ftrace_ops_init(ops); - return ftrace_set_addr(ops, ip, remove, reset, 1); + return ftrace_set_addr(ops, &ip, 1, remove, reset, 1); } EXPORT_SYMBOL_GPL(ftrace_set_filter_ip); /** + * ftrace_set_filter_ips - set functions to filter on in ftrace by addresses + * @ops - the ops to set the filter with + * @ips - the array of addresses to add to or remove from the filter. + * @cnt - the number of addresses in @ips + * @remove - non zero to remove ips from the filter + * @reset - non zero to reset all filters before applying this filter. + * + * Filters denote which functions should be enabled when tracing is enabled + * If @ips array or any ip specified within is NULL , it fails to update filter. + */ +int ftrace_set_filter_ips(struct ftrace_ops *ops, unsigned long *ips, + unsigned int cnt, int remove, int reset) +{ + ftrace_ops_init(ops); + return ftrace_set_addr(ops, ips, cnt, remove, reset, 1); +} +EXPORT_SYMBOL_GPL(ftrace_set_filter_ips); + +/** * ftrace_ops_set_global_filter - setup ops to use global filters * @ops - the ops which will use the global filters * @@ -5659,7 +5699,7 @@ 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, 0, 0, reset, enable); + return ftrace_set_hash(ops, buf, len, NULL, 0, 0, reset, enable); } /** @@ -7096,6 +7136,8 @@ void __init ftrace_free_init_mem(void) void *start = (void *)(&__init_begin); void *end = (void *)(&__init_end); + ftrace_boot_snapshot(); + ftrace_free_mem(NULL, start, end); } @@ -7346,7 +7388,9 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops) static void ftrace_filter_pid_sched_switch_probe(void *data, bool preempt, - struct task_struct *prev, struct task_struct *next) + unsigned int prev_state, + struct task_struct *prev, + struct task_struct *next) { struct trace_array *tr = data; struct trace_pid_list *pid_list; diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c new file mode 100644 index 000000000000..ab463a4d2b23 --- /dev/null +++ b/kernel/trace/rethook.c @@ -0,0 +1,317 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define pr_fmt(fmt) "rethook: " fmt + +#include <linux/bug.h> +#include <linux/kallsyms.h> +#include <linux/kprobes.h> +#include <linux/preempt.h> +#include <linux/rethook.h> +#include <linux/slab.h> +#include <linux/sort.h> + +/* Return hook list (shadow stack by list) */ + +/* + * This function is called from delayed_put_task_struct() when a task is + * dead and cleaned up to recycle any kretprobe instances associated with + * this task. These left over instances represent probed functions that + * have been called but will never return. + */ +void rethook_flush_task(struct task_struct *tk) +{ + struct rethook_node *rhn; + struct llist_node *node; + + node = __llist_del_all(&tk->rethooks); + while (node) { + rhn = container_of(node, struct rethook_node, llist); + node = node->next; + preempt_disable(); + rethook_recycle(rhn); + preempt_enable(); + } +} + +static void rethook_free_rcu(struct rcu_head *head) +{ + struct rethook *rh = container_of(head, struct rethook, rcu); + struct rethook_node *rhn; + struct freelist_node *node; + int count = 1; + + node = rh->pool.head; + while (node) { + rhn = container_of(node, struct rethook_node, freelist); + node = node->next; + kfree(rhn); + count++; + } + + /* The rh->ref is the number of pooled node + 1 */ + if (refcount_sub_and_test(count, &rh->ref)) + kfree(rh); +} + +/** + * rethook_free() - Free struct rethook. + * @rh: the struct rethook to be freed. + * + * Free the rethook. Before calling this function, user must ensure the + * @rh::data is cleaned if needed (or, the handler can access it after + * calling this function.) This function will set the @rh to be freed + * after all rethook_node are freed (not soon). And the caller must + * not touch @rh after calling this. + */ +void rethook_free(struct rethook *rh) +{ + rcu_assign_pointer(rh->handler, NULL); + + call_rcu(&rh->rcu, rethook_free_rcu); +} + +/** + * rethook_alloc() - Allocate struct rethook. + * @data: a data to pass the @handler when hooking the return. + * @handler: the return hook callback function. + * + * Allocate and initialize a new rethook with @data and @handler. + * Return NULL if memory allocation fails or @handler is NULL. + * Note that @handler == NULL means this rethook is going to be freed. + */ +struct rethook *rethook_alloc(void *data, rethook_handler_t handler) +{ + struct rethook *rh = kzalloc(sizeof(struct rethook), GFP_KERNEL); + + if (!rh || !handler) + return NULL; + + rh->data = data; + rh->handler = handler; + rh->pool.head = NULL; + refcount_set(&rh->ref, 1); + + return rh; +} + +/** + * rethook_add_node() - Add a new node to the rethook. + * @rh: the struct rethook. + * @node: the struct rethook_node to be added. + * + * Add @node to @rh. User must allocate @node (as a part of user's + * data structure.) The @node fields are initialized in this function. + */ +void rethook_add_node(struct rethook *rh, struct rethook_node *node) +{ + node->rethook = rh; + freelist_add(&node->freelist, &rh->pool); + refcount_inc(&rh->ref); +} + +static void free_rethook_node_rcu(struct rcu_head *head) +{ + struct rethook_node *node = container_of(head, struct rethook_node, rcu); + + if (refcount_dec_and_test(&node->rethook->ref)) + kfree(node->rethook); + kfree(node); +} + +/** + * rethook_recycle() - return the node to rethook. + * @node: The struct rethook_node to be returned. + * + * Return back the @node to @node::rethook. If the @node::rethook is already + * marked as freed, this will free the @node. + */ +void rethook_recycle(struct rethook_node *node) +{ + lockdep_assert_preemption_disabled(); + + if (likely(READ_ONCE(node->rethook->handler))) + freelist_add(&node->freelist, &node->rethook->pool); + else + call_rcu(&node->rcu, free_rethook_node_rcu); +} +NOKPROBE_SYMBOL(rethook_recycle); + +/** + * rethook_try_get() - get an unused rethook node. + * @rh: The struct rethook which pools the nodes. + * + * Get an unused rethook node from @rh. If the node pool is empty, this + * will return NULL. Caller must disable preemption. + */ +struct rethook_node *rethook_try_get(struct rethook *rh) +{ + rethook_handler_t handler = READ_ONCE(rh->handler); + struct freelist_node *fn; + + lockdep_assert_preemption_disabled(); + + /* Check whether @rh is going to be freed. */ + if (unlikely(!handler)) + return NULL; + + fn = freelist_try_get(&rh->pool); + if (!fn) + return NULL; + + return container_of(fn, struct rethook_node, freelist); +} +NOKPROBE_SYMBOL(rethook_try_get); + +/** + * rethook_hook() - Hook the current function return. + * @node: The struct rethook node to hook the function return. + * @regs: The struct pt_regs for the function entry. + * @mcount: True if this is called from mcount(ftrace) context. + * + * Hook the current running function return. This must be called when the + * function entry (or at least @regs must be the registers of the function + * entry.) @mcount is used for identifying the context. If this is called + * from ftrace (mcount) callback, @mcount must be set true. If this is called + * from the real function entry (e.g. kprobes) @mcount must be set false. + * This is because the way to hook the function return depends on the context. + */ +void rethook_hook(struct rethook_node *node, struct pt_regs *regs, bool mcount) +{ + arch_rethook_prepare(node, regs, mcount); + __llist_add(&node->llist, ¤t->rethooks); +} +NOKPROBE_SYMBOL(rethook_hook); + +/* This assumes the 'tsk' is the current task or is not running. */ +static unsigned long __rethook_find_ret_addr(struct task_struct *tsk, + struct llist_node **cur) +{ + struct rethook_node *rh = NULL; + struct llist_node *node = *cur; + + if (!node) + node = tsk->rethooks.first; + else + node = node->next; + + while (node) { + rh = container_of(node, struct rethook_node, llist); + if (rh->ret_addr != (unsigned long)arch_rethook_trampoline) { + *cur = node; + return rh->ret_addr; + } + node = node->next; + } + return 0; +} +NOKPROBE_SYMBOL(__rethook_find_ret_addr); + +/** + * rethook_find_ret_addr -- Find correct return address modified by rethook + * @tsk: Target task + * @frame: A frame pointer + * @cur: a storage of the loop cursor llist_node pointer for next call + * + * Find the correct return address modified by a rethook on @tsk in unsigned + * long type. + * The @tsk must be 'current' or a task which is not running. @frame is a hint + * to get the currect return address - which is compared with the + * rethook::frame field. The @cur is a loop cursor for searching the + * kretprobe return addresses on the @tsk. The '*@cur' should be NULL at the + * first call, but '@cur' itself must NOT NULL. + * + * Returns found address value or zero if not found. + */ +unsigned long rethook_find_ret_addr(struct task_struct *tsk, unsigned long frame, + struct llist_node **cur) +{ + struct rethook_node *rhn = NULL; + unsigned long ret; + + if (WARN_ON_ONCE(!cur)) + return 0; + + if (WARN_ON_ONCE(tsk != current && task_is_running(tsk))) + return 0; + + do { + ret = __rethook_find_ret_addr(tsk, cur); + if (!ret) + break; + rhn = container_of(*cur, struct rethook_node, llist); + } while (rhn->frame != frame); + + return ret; +} +NOKPROBE_SYMBOL(rethook_find_ret_addr); + +void __weak arch_rethook_fixup_return(struct pt_regs *regs, + unsigned long correct_ret_addr) +{ + /* + * Do nothing by default. If the architecture which uses a + * frame pointer to record real return address on the stack, + * it should fill this function to fixup the return address + * so that stacktrace works from the rethook handler. + */ +} + +/* This function will be called from each arch-defined trampoline. */ +unsigned long rethook_trampoline_handler(struct pt_regs *regs, + unsigned long frame) +{ + struct llist_node *first, *node = NULL; + unsigned long correct_ret_addr; + rethook_handler_t handler; + struct rethook_node *rhn; + + correct_ret_addr = __rethook_find_ret_addr(current, &node); + if (!correct_ret_addr) { + pr_err("rethook: Return address not found! Maybe there is a bug in the kernel\n"); + BUG_ON(1); + } + + instruction_pointer_set(regs, correct_ret_addr); + + /* + * These loops must be protected from rethook_free_rcu() because those + * are accessing 'rhn->rethook'. + */ + preempt_disable(); + + /* + * Run the handler on the shadow stack. Do not unlink the list here because + * stackdump inside the handlers needs to decode it. + */ + first = current->rethooks.first; + while (first) { + rhn = container_of(first, struct rethook_node, llist); + if (WARN_ON_ONCE(rhn->frame != frame)) + break; + handler = READ_ONCE(rhn->rethook->handler); + if (handler) + handler(rhn, rhn->rethook->data, regs); + + if (first == node) + break; + first = first->next; + } + + /* Fixup registers for returning to correct address. */ + arch_rethook_fixup_return(regs, correct_ret_addr); + + /* Unlink used shadow stack */ + first = current->rethooks.first; + current->rethooks.first = node->next; + node->next = NULL; + + while (first) { + rhn = container_of(first, struct rethook_node, llist); + first = first->next; + rethook_recycle(rhn); + } + preempt_enable(); + + return correct_ret_addr; +} +NOKPROBE_SYMBOL(rethook_trampoline_handler); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 96265a717ca4..f4de111fa18f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -185,6 +185,7 @@ static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata; static char *default_bootup_tracer; static bool allocate_snapshot; +static bool snapshot_at_boot; static int __init set_cmdline_ftrace(char *str) { @@ -230,6 +231,15 @@ static int __init boot_alloc_snapshot(char *str) __setup("alloc_snapshot", boot_alloc_snapshot); +static int __init boot_snapshot(char *str) +{ + snapshot_at_boot = true; + boot_alloc_snapshot(str); + return 1; +} +__setup("ftrace_boot_snapshot", boot_snapshot); + + static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata; static int __init set_trace_boot_options(char *str) @@ -7730,7 +7740,7 @@ const struct file_operations trace_min_max_fops = { struct err_info { const char **errs; /* ptr to loc-specific array of err strings */ u8 type; /* index into errs -> specific err string */ - u8 pos; /* MAX_FILTER_STR_VAL = 256 */ + u16 pos; /* caret position */ u64 ts; }; @@ -7738,26 +7748,52 @@ struct tracing_log_err { struct list_head list; struct err_info info; char loc[TRACING_LOG_LOC_MAX]; /* err location */ - char cmd[MAX_FILTER_STR_VAL]; /* what caused err */ + char *cmd; /* what caused err */ }; static DEFINE_MUTEX(tracing_err_log_lock); -static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr) +static struct tracing_log_err *alloc_tracing_log_err(int len) +{ + struct tracing_log_err *err; + + err = kzalloc(sizeof(*err), GFP_KERNEL); + if (!err) + return ERR_PTR(-ENOMEM); + + err->cmd = kzalloc(len, GFP_KERNEL); + if (!err->cmd) { + kfree(err); + return ERR_PTR(-ENOMEM); + } + + return err; +} + +static void free_tracing_log_err(struct tracing_log_err *err) +{ + kfree(err->cmd); + kfree(err); +} + +static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr, + int len) { struct tracing_log_err *err; if (tr->n_err_log_entries < TRACING_LOG_ERRS_MAX) { - err = kzalloc(sizeof(*err), GFP_KERNEL); - if (!err) - err = ERR_PTR(-ENOMEM); - else + err = alloc_tracing_log_err(len); + if (PTR_ERR(err) != -ENOMEM) tr->n_err_log_entries++; return err; } err = list_first_entry(&tr->err_log, struct tracing_log_err, list); + kfree(err->cmd); + err->cmd = kzalloc(len, GFP_KERNEL); + if (!err->cmd) + return ERR_PTR(-ENOMEM); list_del(&err->list); return err; @@ -7818,22 +7854,25 @@ unsigned int err_pos(char *cmd, const char *str) */ void tracing_log_err(struct trace_array *tr, const char *loc, const char *cmd, - const char **errs, u8 type, u8 pos) + const char **errs, u8 type, u16 pos) { struct tracing_log_err *err; + int len = 0; if (!tr) tr = &global_trace; + len += sizeof(CMD_PREFIX) + 2 * sizeof("\n") + strlen(cmd) + 1; + mutex_lock(&tracing_err_log_lock); - err = get_tracing_log_err(tr); + err = get_tracing_log_err(tr, len); if (PTR_ERR(err) == -ENOMEM) { mutex_unlock(&tracing_err_log_lock); return; } snprintf(err->loc, TRACING_LOG_LOC_MAX, "%s: error: ", loc); - snprintf(err->cmd, MAX_FILTER_STR_VAL,"\n" CMD_PREFIX "%s\n", cmd); + snprintf(err->cmd, len, "\n" CMD_PREFIX "%s\n", cmd); err->info.errs = errs; err->info.type = type; @@ -7851,7 +7890,7 @@ static void clear_tracing_err_log(struct trace_array *tr) mutex_lock(&tracing_err_log_lock); list_for_each_entry_safe(err, next, &tr->err_log, list) { list_del(&err->list); - kfree(err); + free_tracing_log_err(err); } tr->n_err_log_entries = 0; @@ -7879,9 +7918,9 @@ static void tracing_err_log_seq_stop(struct seq_file *m, void *v) mutex_unlock(&tracing_err_log_lock); } -static void tracing_err_log_show_pos(struct seq_file *m, u8 pos) +static void tracing_err_log_show_pos(struct seq_file *m, u16 pos) { - u8 i; + u16 i; for (i = 0; i < sizeof(CMD_PREFIX) - 1; i++) seq_putc(m, ' '); @@ -10127,6 +10166,14 @@ out: return ret; } +void __init ftrace_boot_snapshot(void) +{ + if (snapshot_at_boot) { + tracing_snapshot(); + internal_trace_puts("** Boot snapshot taken **\n"); + } +} + void __init early_trace_init(void) { if (tracepoint_printk) { diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index c5b09c31e077..07d990270e2a 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1877,7 +1877,7 @@ extern ssize_t trace_parse_run_command(struct file *file, extern unsigned int err_pos(char *cmd, const char *str); extern void tracing_log_err(struct trace_array *tr, const char *loc, const char *cmd, - const char **errs, u8 type, u8 pos); + const char **errs, u8 type, u16 pos); /* * Normal trace_printk() and friends allocates special buffers diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 3147614c1812..e11e167b7809 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -40,6 +40,14 @@ static LIST_HEAD(ftrace_generic_fields); static LIST_HEAD(ftrace_common_fields); static bool eventdir_initialized; +static LIST_HEAD(module_strings); + +struct module_string { + struct list_head next; + struct module *module; + char *str; +}; + #define GFP_TRACE (GFP_KERNEL | __GFP_ZERO) static struct kmem_cache *field_cachep; @@ -384,6 +392,12 @@ static void test_event_printk(struct trace_event_call *call) if (!(dereference_flags & (1ULL << arg))) goto next_arg; + /* Check for __get_sockaddr */; + if (str_has_prefix(fmt + i, "__get_sockaddr(")) { + dereference_flags &= ~(1ULL << arg); + goto next_arg; + } + /* Find the REC-> in the argument */ c = strchr(fmt + i, ','); r = strstr(fmt + i, "REC->"); @@ -759,7 +773,9 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable) static void event_filter_pid_sched_switch_probe_pre(void *data, bool preempt, - struct task_struct *prev, struct task_struct *next) + unsigned int prev_state, + struct task_struct *prev, + struct task_struct *next) { struct trace_array *tr = data; struct trace_pid_list *no_pid_list; @@ -783,7 +799,9 @@ event_filter_pid_sched_switch_probe_pre(void *data, bool preempt, static void event_filter_pid_sched_switch_probe_post(void *data, bool preempt, - struct task_struct *prev, struct task_struct *next) + unsigned int prev_state, + struct task_struct *prev, + struct task_struct *next) { struct trace_array *tr = data; struct trace_pid_list *no_pid_list; @@ -2633,6 +2651,76 @@ static void update_event_printk(struct trace_event_call *call, } } +static void add_str_to_module(struct module *module, char *str) +{ + struct module_string *modstr; + + modstr = kmalloc(sizeof(*modstr), GFP_KERNEL); + + /* + * If we failed to allocate memory here, then we'll just + * let the str memory leak when the module is removed. + * If this fails to allocate, there's worse problems than + * a leaked string on module removal. + */ + if (WARN_ON_ONCE(!modstr)) + return; + + modstr->module = module; + modstr->str = str; + + list_add(&modstr->next, &module_strings); +} + +static void update_event_fields(struct trace_event_call *call, + struct trace_eval_map *map) +{ + struct ftrace_event_field *field; + struct list_head *head; + char *ptr; + char *str; + int len = strlen(map->eval_string); + + /* Dynamic events should never have field maps */ + if (WARN_ON_ONCE(call->flags & TRACE_EVENT_FL_DYNAMIC)) + return; + + head = trace_get_fields(call); + list_for_each_entry(field, head, link) { + ptr = strchr(field->type, '['); + if (!ptr) + continue; + ptr++; + + if (!isalpha(*ptr) && *ptr != '_') + continue; + + if (strncmp(map->eval_string, ptr, len) != 0) + continue; + + str = kstrdup(field->type, GFP_KERNEL); + if (WARN_ON_ONCE(!str)) + return; + ptr = str + (ptr - field->type); + ptr = eval_replace(ptr, map, len); + /* enum/sizeof string smaller than value */ + if (WARN_ON_ONCE(!ptr)) { + kfree(str); + continue; + } + + /* + * If the event is part of a module, then we need to free the string + * when the module is removed. Otherwise, it will stay allocated + * until a reboot. + */ + if (call->module) + add_str_to_module(call->module, str); + + field->type = str; + } +} + void trace_event_eval_update(struct trace_eval_map **map, int len) { struct trace_event_call *call, *p; @@ -2668,6 +2756,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len) first = false; } update_event_printk(call, map[i]); + update_event_fields(call, map[i]); } } } @@ -2758,6 +2847,7 @@ int trace_add_event_call(struct trace_event_call *call) mutex_unlock(&trace_types_lock); return ret; } +EXPORT_SYMBOL_GPL(trace_add_event_call); /* * Must be called under locking of trace_types_lock, event_mutex and @@ -2819,6 +2909,7 @@ int trace_remove_event_call(struct trace_event_call *call) return ret; } +EXPORT_SYMBOL_GPL(trace_remove_event_call); #define for_each_event(event, start, end) \ for (event = start; \ @@ -2853,6 +2944,7 @@ static void trace_module_add_events(struct module *mod) static void trace_module_remove_events(struct module *mod) { struct trace_event_call *call, *p; + struct module_string *modstr, *m; down_write(&trace_event_sem); list_for_each_entry_safe(call, p, &ftrace_events, list) { @@ -2861,6 +2953,14 @@ static void trace_module_remove_events(struct module *mod) if (call->module == mod) __trace_remove_event_call(call); } + /* Check for any strings allocade for this module */ + list_for_each_entry_safe(modstr, m, &module_strings, next) { + if (modstr->module != mod) + continue; + list_del(&modstr->next); + kfree(modstr->str); + kfree(modstr); + } up_write(&trace_event_sem); /* diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index dc7f733b4cb3..44db5ba9cabb 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -727,11 +727,16 @@ static struct track_data *track_data_alloc(unsigned int key_len, return data; } -static char last_cmd[MAX_FILTER_STR_VAL]; +#define HIST_PREFIX "hist:" + +static char *last_cmd; static char last_cmd_loc[MAX_FILTER_STR_VAL]; static int errpos(char *str) { + if (!str || !last_cmd) + return 0; + return err_pos(last_cmd, str); } @@ -739,12 +744,22 @@ static void last_cmd_set(struct trace_event_file *file, char *str) { const char *system = NULL, *name = NULL; struct trace_event_call *call; + int len; if (!str) return; - strcpy(last_cmd, "hist:"); - strncat(last_cmd, str, MAX_FILTER_STR_VAL - 1 - sizeof("hist:")); + /* sizeof() contains the nul byte */ + len = sizeof(HIST_PREFIX) + strlen(str); + kfree(last_cmd); + last_cmd = kzalloc(len, GFP_KERNEL); + if (!last_cmd) + return; + + strcpy(last_cmd, HIST_PREFIX); + /* Again, sizeof() contains the nul byte */ + len -= sizeof(HIST_PREFIX); + strncat(last_cmd, str, len); if (file) { call = file->event_call; @@ -757,18 +772,22 @@ static void last_cmd_set(struct trace_event_file *file, char *str) } if (system) - snprintf(last_cmd_loc, MAX_FILTER_STR_VAL, "hist:%s:%s", system, name); + snprintf(last_cmd_loc, MAX_FILTER_STR_VAL, HIST_PREFIX "%s:%s", system, name); } -static void hist_err(struct trace_array *tr, u8 err_type, u8 err_pos) +static void hist_err(struct trace_array *tr, u8 err_type, u16 err_pos) { + if (!last_cmd) + return; + tracing_log_err(tr, last_cmd_loc, last_cmd, err_text, err_type, err_pos); } static void hist_err_clear(void) { - last_cmd[0] = '\0'; + if (last_cmd) + last_cmd[0] = '\0'; last_cmd_loc[0] = '\0'; } @@ -5610,7 +5629,7 @@ static int event_hist_trigger_print(struct seq_file *m, bool have_var = false; unsigned int i; - seq_puts(m, "hist:"); + seq_puts(m, HIST_PREFIX); if (data->name) seq_printf(m, "%s:", data->name); diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 154db74dadbc..5e8c07aef071 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -42,10 +42,13 @@ enum { ERRORS }; static const char *err_text[] = { ERRORS }; -static char last_cmd[MAX_FILTER_STR_VAL]; +static char *last_cmd; static int errpos(const char *str) { + if (!str || !last_cmd) + return 0; + return err_pos(last_cmd, str); } @@ -54,11 +57,16 @@ static void last_cmd_set(const char *str) if (!str) return; - strncpy(last_cmd, str, MAX_FILTER_STR_VAL - 1); + kfree(last_cmd); + + last_cmd = kstrdup(str, GFP_KERNEL); } -static void synth_err(u8 err_type, u8 err_pos) +static void synth_err(u8 err_type, u16 err_pos) { + if (!last_cmd) + return; + tracing_log_err(NULL, "synthetic_events", last_cmd, err_text, err_type, err_pos); } diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c new file mode 100644 index 000000000000..8b3d241a31c2 --- /dev/null +++ b/kernel/trace/trace_events_user.c @@ -0,0 +1,1690 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2021, Microsoft Corporation. + * + * Authors: + * Beau Belgrave <beaub@linux.microsoft.com> + */ + +#include <linux/bitmap.h> +#include <linux/cdev.h> +#include <linux/hashtable.h> +#include <linux/list.h> +#include <linux/io.h> +#include <linux/uio.h> +#include <linux/ioctl.h> +#include <linux/jhash.h> +#include <linux/trace_events.h> +#include <linux/tracefs.h> +#include <linux/types.h> +#include <linux/uaccess.h> +#include <uapi/linux/user_events.h> +#include "trace.h" +#include "trace_dynevent.h" + +#define USER_EVENTS_PREFIX_LEN (sizeof(USER_EVENTS_PREFIX)-1) + +#define FIELD_DEPTH_TYPE 0 +#define FIELD_DEPTH_NAME 1 +#define FIELD_DEPTH_SIZE 2 + +/* + * Limits how many trace_event calls user processes can create: + * Must be a power of two of PAGE_SIZE. + */ +#define MAX_PAGE_ORDER 0 +#define MAX_PAGES (1 << MAX_PAGE_ORDER) +#define MAX_EVENTS (MAX_PAGES * PAGE_SIZE) + +/* Limit how long of an event name plus args within the subsystem. */ +#define MAX_EVENT_DESC 512 +#define EVENT_NAME(user_event) ((user_event)->tracepoint.name) +#define MAX_FIELD_ARRAY_SIZE 1024 +#define MAX_FIELD_ARG_NAME 256 + +#define MAX_BPF_COPY_SIZE PAGE_SIZE +#define MAX_STACK_BPF_DATA 512 + +static char *register_page_data; + +static DEFINE_MUTEX(reg_mutex); +static DEFINE_HASHTABLE(register_table, 4); +static DECLARE_BITMAP(page_bitmap, MAX_EVENTS); + +/* + * Stores per-event properties, as users register events + * within a file a user_event might be created if it does not + * already exist. These are globally used and their lifetime + * is tied to the refcnt member. These cannot go away until the + * refcnt reaches zero. + */ +struct user_event { + struct tracepoint tracepoint; + struct trace_event_call call; + struct trace_event_class class; + struct dyn_event devent; + struct hlist_node node; + struct list_head fields; + struct list_head validators; + atomic_t refcnt; + int index; + int flags; + int min_size; +}; + +/* + * Stores per-file events references, as users register events + * within a file this structure is modified and freed via RCU. + * The lifetime of this struct is tied to the lifetime of the file. + * These are not shared and only accessible by the file that created it. + */ +struct user_event_refs { + struct rcu_head rcu; + int count; + struct user_event *events[]; +}; + +#define VALIDATOR_ENSURE_NULL (1 << 0) +#define VALIDATOR_REL (1 << 1) + +struct user_event_validator { + struct list_head link; + int offset; + int flags; +}; + +typedef void (*user_event_func_t) (struct user_event *user, struct iov_iter *i, + void *tpdata, bool *faulted); + +static int user_event_parse(char *name, char *args, char *flags, + struct user_event **newuser); + +static u32 user_event_key(char *name) +{ + return jhash(name, strlen(name), 0); +} + +static __always_inline __must_check +size_t copy_nofault(void *addr, size_t bytes, struct iov_iter *i) +{ + size_t ret; + + pagefault_disable(); + + ret = copy_from_iter_nocache(addr, bytes, i); + + pagefault_enable(); + + return ret; +} + +static struct list_head *user_event_get_fields(struct trace_event_call *call) +{ + struct user_event *user = (struct user_event *)call->data; + + return &user->fields; +} + +/* + * Parses a register command for user_events + * Format: event_name[:FLAG1[,FLAG2...]] [field1[;field2...]] + * + * Example event named 'test' with a 20 char 'msg' field with an unsigned int + * 'id' field after: + * test char[20] msg;unsigned int id + * + * NOTE: Offsets are from the user data perspective, they are not from the + * trace_entry/buffer perspective. We automatically add the common properties + * sizes to the offset for the user. + * + * Upon success user_event has its ref count increased by 1. + */ +static int user_event_parse_cmd(char *raw_command, struct user_event **newuser) +{ + char *name = raw_command; + char *args = strpbrk(name, " "); + char *flags; + + if (args) + *args++ = '\0'; + + flags = strpbrk(name, ":"); + + if (flags) + *flags++ = '\0'; + + return user_event_parse(name, args, flags, newuser); +} + +static int user_field_array_size(const char *type) +{ + const char *start = strchr(type, '['); + char val[8]; + char *bracket; + int size = 0; + + if (start == NULL) + return -EINVAL; + + if (strscpy(val, start + 1, sizeof(val)) <= 0) + return -EINVAL; + + bracket = strchr(val, ']'); + + if (!bracket) + return -EINVAL; + + *bracket = '\0'; + + if (kstrtouint(val, 0, &size)) + return -EINVAL; + + if (size > MAX_FIELD_ARRAY_SIZE) + return -EINVAL; + + return size; +} + +static int user_field_size(const char *type) +{ + /* long is not allowed from a user, since it's ambigious in size */ + if (strcmp(type, "s64") == 0) + return sizeof(s64); + if (strcmp(type, "u64") == 0) + return sizeof(u64); + if (strcmp(type, "s32") == 0) + return sizeof(s32); + if (strcmp(type, "u32") == 0) + return sizeof(u32); + if (strcmp(type, "int") == 0) + return sizeof(int); + if (strcmp(type, "unsigned int") == 0) + return sizeof(unsigned int); + if (strcmp(type, "s16") == 0) + return sizeof(s16); + if (strcmp(type, "u16") == 0) + return sizeof(u16); + if (strcmp(type, "short") == 0) + return sizeof(short); + if (strcmp(type, "unsigned short") == 0) + return sizeof(unsigned short); + if (strcmp(type, "s8") == 0) + return sizeof(s8); + if (strcmp(type, "u8") == 0) + return sizeof(u8); + if (strcmp(type, "char") == 0) + return sizeof(char); + if (strcmp(type, "unsigned char") == 0) + return sizeof(unsigned char); + if (str_has_prefix(type, "char[")) + return user_field_array_size(type); + if (str_has_prefix(type, "unsigned char[")) + return user_field_array_size(type); + if (str_has_prefix(type, "__data_loc ")) + return sizeof(u32); + if (str_has_prefix(type, "__rel_loc ")) + return sizeof(u32); + + /* Uknown basic type, error */ + return -EINVAL; +} + +static void user_event_destroy_validators(struct user_event *user) +{ + struct user_event_validator *validator, *next; + struct list_head *head = &user->validators; + + list_for_each_entry_safe(validator, next, head, link) { + list_del(&validator->link); + kfree(validator); + } +} + +static void user_event_destroy_fields(struct user_event *user) +{ + struct ftrace_event_field *field, *next; + struct list_head *head = &user->fields; + + list_for_each_entry_safe(field, next, head, link) { + list_del(&field->link); + kfree(field); + } +} + +static int user_event_add_field(struct user_event *user, const char *type, + const char *name, int offset, int size, + int is_signed, int filter_type) +{ + struct user_event_validator *validator; + struct ftrace_event_field *field; + int validator_flags = 0; + + field = kmalloc(sizeof(*field), GFP_KERNEL); + + if (!field) + return -ENOMEM; + + if (str_has_prefix(type, "__data_loc ")) + goto add_validator; + + if (str_has_prefix(type, "__rel_loc ")) { + validator_flags |= VALIDATOR_REL; + goto add_validator; + } + + goto add_field; + +add_validator: + if (strstr(type, "char") != 0) + validator_flags |= VALIDATOR_ENSURE_NULL; + + validator = kmalloc(sizeof(*validator), GFP_KERNEL); + + if (!validator) { + kfree(field); + return -ENOMEM; + } + + validator->flags = validator_flags; + validator->offset = offset; + + /* Want sequential access when validating */ + list_add_tail(&validator->link, &user->validators); + +add_field: + field->type = type; + field->name = name; + field->offset = offset; + field->size = size; + field->is_signed = is_signed; + field->filter_type = filter_type; + + list_add(&field->link, &user->fields); + + /* + * Min size from user writes that are required, this does not include + * the size of trace_entry (common fields). + */ + user->min_size = (offset + size) - sizeof(struct trace_entry); + + return 0; +} + +/* + * Parses the values of a field within the description + * Format: type name [size] + */ +static int user_event_parse_field(char *field, struct user_event *user, + u32 *offset) +{ + char *part, *type, *name; + u32 depth = 0, saved_offset = *offset; + int len, size = -EINVAL; + bool is_struct = false; + + field = skip_spaces(field); + + if (*field == '\0') + return 0; + + /* Handle types that have a space within */ + len = str_has_prefix(field, "unsigned "); + if (len) + goto skip_next; + + len = str_has_prefix(field, "struct "); + if (len) { + is_struct = true; + goto skip_next; + } + + len = str_has_prefix(field, "__data_loc unsigned "); + if (len) + goto skip_next; + + len = str_has_prefix(field, "__data_loc "); + if (len) + goto skip_next; + + len = str_has_prefix(field, "__rel_loc unsigned "); + if (len) + goto skip_next; + + len = str_has_prefix(field, "__rel_loc "); + if (len) + goto skip_next; + + goto parse; +skip_next: + type = field; + field = strpbrk(field + len, " "); + + if (field == NULL) + return -EINVAL; + + *field++ = '\0'; + depth++; +parse: + name = NULL; + + while ((part = strsep(&field, " ")) != NULL) { + switch (depth++) { + case FIELD_DEPTH_TYPE: + type = part; + break; + case FIELD_DEPTH_NAME: + name = part; + break; + case FIELD_DEPTH_SIZE: + if (!is_struct) + return -EINVAL; + + if (kstrtou32(part, 10, &size)) + return -EINVAL; + break; + default: + return -EINVAL; + } + } + + if (depth < FIELD_DEPTH_SIZE || !name) + return -EINVAL; + + if (depth == FIELD_DEPTH_SIZE) + size = user_field_size(type); + + if (size == 0) + return -EINVAL; + + if (size < 0) + return size; + + *offset = saved_offset + size; + + return user_event_add_field(user, type, name, saved_offset, size, + type[0] != 'u', FILTER_OTHER); +} + +static void user_event_parse_flags(struct user_event *user, char *flags) +{ + char *flag; + + if (flags == NULL) + return; + + while ((flag = strsep(&flags, ",")) != NULL) { + if (strcmp(flag, "BPF_ITER") == 0) + user->flags |= FLAG_BPF_ITER; + } +} + +static int user_event_parse_fields(struct user_event *user, char *args) +{ + char *field; + u32 offset = sizeof(struct trace_entry); + int ret = -EINVAL; + + if (args == NULL) + return 0; + + while ((field = strsep(&args, ";")) != NULL) { + ret = user_event_parse_field(field, user, &offset); + + if (ret) + break; + } + + return ret; +} + +static struct trace_event_fields user_event_fields_array[1]; + +static const char *user_field_format(const char *type) +{ + if (strcmp(type, "s64") == 0) + return "%lld"; + if (strcmp(type, "u64") == 0) + return "%llu"; + if (strcmp(type, "s32") == 0) + return "%d"; + if (strcmp(type, "u32") == 0) + return "%u"; + if (strcmp(type, "int") == 0) + return "%d"; + if (strcmp(type, "unsigned int") == 0) + return "%u"; + if (strcmp(type, "s16") == 0) + return "%d"; + if (strcmp(type, "u16") == 0) + return "%u"; + if (strcmp(type, "short") == 0) + return "%d"; + if (strcmp(type, "unsigned short") == 0) + return "%u"; + if (strcmp(type, "s8") == 0) + return "%d"; + if (strcmp(type, "u8") == 0) + return "%u"; + if (strcmp(type, "char") == 0) + return "%d"; + if (strcmp(type, "unsigned char") == 0) + return "%u"; + if (strstr(type, "char[") != 0) + return "%s"; + + /* Unknown, likely struct, allowed treat as 64-bit */ + return "%llu"; +} + +static bool user_field_is_dyn_string(const char *type, const char **str_func) +{ + if (str_has_prefix(type, "__data_loc ")) { + *str_func = "__get_str"; + goto check; + } + + if (str_has_prefix(type, "__rel_loc ")) { + *str_func = "__get_rel_str"; + goto check; + } + + return false; +check: + return strstr(type, "char") != 0; +} + +#define LEN_OR_ZERO (len ? len - pos : 0) +static int user_event_set_print_fmt(struct user_event *user, char *buf, int len) +{ + struct ftrace_event_field *field, *next; + struct list_head *head = &user->fields; + int pos = 0, depth = 0; + const char *str_func; + + pos += snprintf(buf + pos, LEN_OR_ZERO, "\""); + + list_for_each_entry_safe_reverse(field, next, head, link) { + if (depth != 0) + pos += snprintf(buf + pos, LEN_OR_ZERO, " "); + + pos += snprintf(buf + pos, LEN_OR_ZERO, "%s=%s", + field->name, user_field_format(field->type)); + + depth++; + } + + pos += snprintf(buf + pos, LEN_OR_ZERO, "\""); + + list_for_each_entry_safe_reverse(field, next, head, link) { + if (user_field_is_dyn_string(field->type, &str_func)) + pos += snprintf(buf + pos, LEN_OR_ZERO, + ", %s(%s)", str_func, field->name); + else + pos += snprintf(buf + pos, LEN_OR_ZERO, + ", REC->%s", field->name); + } + + return pos + 1; +} +#undef LEN_OR_ZERO + +static int user_event_create_print_fmt(struct user_event *user) +{ + char *print_fmt; + int len; + + len = user_event_set_print_fmt(user, NULL, 0); + + print_fmt = kmalloc(len, GFP_KERNEL); + + if (!print_fmt) + return -ENOMEM; + + user_event_set_print_fmt(user, print_fmt, len); + + user->call.print_fmt = print_fmt; + + return 0; +} + +static enum print_line_t user_event_print_trace(struct trace_iterator *iter, + int flags, + struct trace_event *event) +{ + /* Unsafe to try to decode user provided print_fmt, use hex */ + trace_print_hex_dump_seq(&iter->seq, "", DUMP_PREFIX_OFFSET, 16, + 1, iter->ent, iter->ent_size, true); + + return trace_handle_return(&iter->seq); +} + +static struct trace_event_functions user_event_funcs = { + .trace = user_event_print_trace, +}; + +static int user_event_set_call_visible(struct user_event *user, bool visible) +{ + int ret; + const struct cred *old_cred; + struct cred *cred; + + cred = prepare_creds(); + + if (!cred) + return -ENOMEM; + + /* + * While by default tracefs is locked down, systems can be configured + * to allow user_event files to be less locked down. The extreme case + * being "other" has read/write access to user_events_data/status. + * + * When not locked down, processes may not have have permissions to + * add/remove calls themselves to tracefs. We need to temporarily + * switch to root file permission to allow for this scenario. + */ + cred->fsuid = GLOBAL_ROOT_UID; + + old_cred = override_creds(cred); + + if (visible) + ret = trace_add_event_call(&user->call); + else + ret = trace_remove_event_call(&user->call); + + revert_creds(old_cred); + put_cred(cred); + + return ret; +} + +static int destroy_user_event(struct user_event *user) +{ + int ret = 0; + + /* Must destroy fields before call removal */ + user_event_destroy_fields(user); + + ret = user_event_set_call_visible(user, false); + + if (ret) + return ret; + + dyn_event_remove(&user->devent); + + register_page_data[user->index] = 0; + clear_bit(user->index, page_bitmap); + hash_del(&user->node); + + user_event_destroy_validators(user); + kfree(user->call.print_fmt); + kfree(EVENT_NAME(user)); + kfree(user); + + return ret; +} + +static struct user_event *find_user_event(char *name, u32 *outkey) +{ + struct user_event *user; + u32 key = user_event_key(name); + + *outkey = key; + + hash_for_each_possible(register_table, user, node, key) + if (!strcmp(EVENT_NAME(user), name)) { + atomic_inc(&user->refcnt); + return user; + } + + return NULL; +} + +static int user_event_validate(struct user_event *user, void *data, int len) +{ + struct list_head *head = &user->validators; + struct user_event_validator *validator; + void *pos, *end = data + len; + u32 loc, offset, size; + + list_for_each_entry(validator, head, link) { + pos = data + validator->offset; + + /* Already done min_size check, no bounds check here */ + loc = *(u32 *)pos; + offset = loc & 0xffff; + size = loc >> 16; + + if (likely(validator->flags & VALIDATOR_REL)) + pos += offset + sizeof(loc); + else + pos = data + offset; + + pos += size; + + if (unlikely(pos > end)) + return -EFAULT; + + if (likely(validator->flags & VALIDATOR_ENSURE_NULL)) + if (unlikely(*(char *)(pos - 1) != '\0')) + return -EFAULT; + } + + return 0; +} + +/* + * Writes the user supplied payload out to a trace file. + */ +static void user_event_ftrace(struct user_event *user, struct iov_iter *i, + void *tpdata, bool *faulted) +{ + struct trace_event_file *file; + struct trace_entry *entry; + struct trace_event_buffer event_buffer; + size_t size = sizeof(*entry) + i->count; + + file = (struct trace_event_file *)tpdata; + + if (!file || + !(file->flags & EVENT_FILE_FL_ENABLED) || + trace_trigger_soft_disabled(file)) + return; + + /* Allocates and fills trace_entry, + 1 of this is data payload */ + entry = trace_event_buffer_reserve(&event_buffer, file, size); + + if (unlikely(!entry)) + return; + + if (unlikely(!copy_nofault(entry + 1, i->count, i))) + goto discard; + + if (!list_empty(&user->validators) && + unlikely(user_event_validate(user, entry, size))) + goto discard; + + trace_event_buffer_commit(&event_buffer); + + return; +discard: + *faulted = true; + __trace_event_discard_commit(event_buffer.buffer, + event_buffer.event); +} + +#ifdef CONFIG_PERF_EVENTS +static void user_event_bpf(struct user_event *user, struct iov_iter *i) +{ + struct user_bpf_context context; + struct user_bpf_iter bpf_i; + char fast_data[MAX_STACK_BPF_DATA]; + void *temp = NULL; + + if ((user->flags & FLAG_BPF_ITER) && iter_is_iovec(i)) { + /* Raw iterator */ + context.data_type = USER_BPF_DATA_ITER; + context.data_len = i->count; + context.iter = &bpf_i; + + bpf_i.iov_offset = i->iov_offset; + bpf_i.iov = i->iov; + bpf_i.nr_segs = i->nr_segs; + } else if (i->nr_segs == 1 && iter_is_iovec(i)) { + /* Single buffer from user */ + context.data_type = USER_BPF_DATA_USER; + context.data_len = i->count; + context.udata = i->iov->iov_base + i->iov_offset; + } else { + /* Multi buffer from user */ + struct iov_iter copy = *i; + size_t copy_size = min_t(size_t, i->count, MAX_BPF_COPY_SIZE); + + context.data_type = USER_BPF_DATA_KERNEL; + context.kdata = fast_data; + + if (unlikely(copy_size > sizeof(fast_data))) { + temp = kmalloc(copy_size, GFP_NOWAIT); + + if (temp) + context.kdata = temp; + else + copy_size = sizeof(fast_data); + } + + context.data_len = copy_nofault(context.kdata, + copy_size, ©); + } + + trace_call_bpf(&user->call, &context); + + kfree(temp); +} + +/* + * Writes the user supplied payload out to perf ring buffer or eBPF program. + */ +static void user_event_perf(struct user_event *user, struct iov_iter *i, + void *tpdata, bool *faulted) +{ + struct hlist_head *perf_head; + + if (bpf_prog_array_valid(&user->call)) + user_event_bpf(user, i); + + perf_head = this_cpu_ptr(user->call.perf_events); + + if (perf_head && !hlist_empty(perf_head)) { + struct trace_entry *perf_entry; + struct pt_regs *regs; + size_t size = sizeof(*perf_entry) + i->count; + int context; + + perf_entry = perf_trace_buf_alloc(ALIGN(size, 8), + ®s, &context); + + if (unlikely(!perf_entry)) + return; + + perf_fetch_caller_regs(regs); + + if (unlikely(!copy_nofault(perf_entry + 1, i->count, i))) + goto discard; + + if (!list_empty(&user->validators) && + unlikely(user_event_validate(user, perf_entry, size))) + goto discard; + + perf_trace_buf_submit(perf_entry, size, context, + user->call.event.type, 1, regs, + perf_head, NULL); + + return; +discard: + *faulted = true; + perf_swevent_put_recursion_context(context); + } +} +#endif + +/* + * Update the register page that is shared between user processes. + */ +static void update_reg_page_for(struct user_event *user) +{ + struct tracepoint *tp = &user->tracepoint; + char status = 0; + + if (atomic_read(&tp->key.enabled) > 0) { + struct tracepoint_func *probe_func_ptr; + user_event_func_t probe_func; + + rcu_read_lock_sched(); + + probe_func_ptr = rcu_dereference_sched(tp->funcs); + + if (probe_func_ptr) { + do { + probe_func = probe_func_ptr->func; + + if (probe_func == user_event_ftrace) + status |= EVENT_STATUS_FTRACE; +#ifdef CONFIG_PERF_EVENTS + else if (probe_func == user_event_perf) + status |= EVENT_STATUS_PERF; +#endif + else + status |= EVENT_STATUS_OTHER; + } while ((++probe_func_ptr)->func); + } + + rcu_read_unlock_sched(); + } + + register_page_data[user->index] = status; +} + +/* + * Register callback for our events from tracing sub-systems. + */ +static int user_event_reg(struct trace_event_call *call, + enum trace_reg type, + void *data) +{ + struct user_event *user = (struct user_event *)call->data; + int ret = 0; + + if (!user) + return -ENOENT; + + switch (type) { + case TRACE_REG_REGISTER: + ret = tracepoint_probe_register(call->tp, + call->class->probe, + data); + if (!ret) + goto inc; + break; + + case TRACE_REG_UNREGISTER: + tracepoint_probe_unregister(call->tp, + call->class->probe, + data); + goto dec; + +#ifdef CONFIG_PERF_EVENTS + case TRACE_REG_PERF_REGISTER: + ret = tracepoint_probe_register(call->tp, + call->class->perf_probe, + data); + if (!ret) + goto inc; + break; + + case TRACE_REG_PERF_UNREGISTER: + tracepoint_probe_unregister(call->tp, + call->class->perf_probe, + data); + goto dec; + + case TRACE_REG_PERF_OPEN: + case TRACE_REG_PERF_CLOSE: + case TRACE_REG_PERF_ADD: + case TRACE_REG_PERF_DEL: + break; +#endif + } + + return ret; +inc: + atomic_inc(&user->refcnt); + update_reg_page_for(user); + return 0; +dec: + update_reg_page_for(user); + atomic_dec(&user->refcnt); + return 0; +} + +static int user_event_create(const char *raw_command) +{ + struct user_event *user; + char *name; + int ret; + + if (!str_has_prefix(raw_command, USER_EVENTS_PREFIX)) + return -ECANCELED; + + raw_command += USER_EVENTS_PREFIX_LEN; + raw_command = skip_spaces(raw_command); + + name = kstrdup(raw_command, GFP_KERNEL); + + if (!name) + return -ENOMEM; + + mutex_lock(®_mutex); + + ret = user_event_parse_cmd(name, &user); + + if (!ret) + atomic_dec(&user->refcnt); + + mutex_unlock(®_mutex); + + if (ret) + kfree(name); + + return ret; +} + +static int user_event_show(struct seq_file *m, struct dyn_event *ev) +{ + struct user_event *user = container_of(ev, struct user_event, devent); + struct ftrace_event_field *field, *next; + struct list_head *head; + int depth = 0; + + seq_printf(m, "%s%s", USER_EVENTS_PREFIX, EVENT_NAME(user)); + + head = trace_get_fields(&user->call); + + list_for_each_entry_safe_reverse(field, next, head, link) { + if (depth == 0) + seq_puts(m, " "); + else + seq_puts(m, "; "); + + seq_printf(m, "%s %s", field->type, field->name); + + if (str_has_prefix(field->type, "struct ")) + seq_printf(m, " %d", field->size); + + depth++; + } + + seq_puts(m, "\n"); + + return 0; +} + +static bool user_event_is_busy(struct dyn_event *ev) +{ + struct user_event *user = container_of(ev, struct user_event, devent); + + return atomic_read(&user->refcnt) != 0; +} + +static int user_event_free(struct dyn_event *ev) +{ + struct user_event *user = container_of(ev, struct user_event, devent); + + if (atomic_read(&user->refcnt) != 0) + return -EBUSY; + + return destroy_user_event(user); +} + +static bool user_field_match(struct ftrace_event_field *field, int argc, + const char **argv, int *iout) +{ + char *field_name, *arg_name; + int len, pos, i = *iout; + bool colon = false, match = false; + + if (i >= argc) + return false; + + len = MAX_FIELD_ARG_NAME; + field_name = kmalloc(len, GFP_KERNEL); + arg_name = kmalloc(len, GFP_KERNEL); + + if (!arg_name || !field_name) + goto out; + + pos = 0; + + for (; i < argc; ++i) { + if (i != *iout) + pos += snprintf(arg_name + pos, len - pos, " "); + + pos += snprintf(arg_name + pos, len - pos, argv[i]); + + if (strchr(argv[i], ';')) { + ++i; + colon = true; + break; + } + } + + pos = 0; + + pos += snprintf(field_name + pos, len - pos, field->type); + pos += snprintf(field_name + pos, len - pos, " "); + pos += snprintf(field_name + pos, len - pos, field->name); + + if (colon) + pos += snprintf(field_name + pos, len - pos, ";"); + + *iout = i; + + match = strcmp(arg_name, field_name) == 0; +out: + kfree(arg_name); + kfree(field_name); + + return match; +} + +static bool user_fields_match(struct user_event *user, int argc, + const char **argv) +{ + struct ftrace_event_field *field, *next; + struct list_head *head = &user->fields; + int i = 0; + + list_for_each_entry_safe_reverse(field, next, head, link) + if (!user_field_match(field, argc, argv, &i)) + return false; + + if (i != argc) + return false; + + return true; +} + +static bool user_event_match(const char *system, const char *event, + int argc, const char **argv, struct dyn_event *ev) +{ + struct user_event *user = container_of(ev, struct user_event, devent); + bool match; + + match = strcmp(EVENT_NAME(user), event) == 0 && + (!system || strcmp(system, USER_EVENTS_SYSTEM) == 0); + + if (match && argc > 0) + match = user_fields_match(user, argc, argv); + + return match; +} + +static struct dyn_event_operations user_event_dops = { + .create = user_event_create, + .show = user_event_show, + .is_busy = user_event_is_busy, + .free = user_event_free, + .match = user_event_match, +}; + +static int user_event_trace_register(struct user_event *user) +{ + int ret; + + ret = register_trace_event(&user->call.event); + + if (!ret) + return -ENODEV; + + ret = user_event_set_call_visible(user, true); + + if (ret) + unregister_trace_event(&user->call.event); + + return ret; +} + +/* + * Parses the event name, arguments and flags then registers if successful. + * The name buffer lifetime is owned by this method for success cases only. + * Upon success the returned user_event has its ref count increased by 1. + */ +static int user_event_parse(char *name, char *args, char *flags, + struct user_event **newuser) +{ + int ret; + int index; + u32 key; + struct user_event *user; + + /* Prevent dyn_event from racing */ + mutex_lock(&event_mutex); + user = find_user_event(name, &key); + mutex_unlock(&event_mutex); + + if (user) { + *newuser = user; + /* + * Name is allocated by caller, free it since it already exists. + * Caller only worries about failure cases for freeing. + */ + kfree(name); + return 0; + } + + index = find_first_zero_bit(page_bitmap, MAX_EVENTS); + + if (index == MAX_EVENTS) + return -EMFILE; + + user = kzalloc(sizeof(*user), GFP_KERNEL); + + if (!user) + return -ENOMEM; + + INIT_LIST_HEAD(&user->class.fields); + INIT_LIST_HEAD(&user->fields); + INIT_LIST_HEAD(&user->validators); + + user->tracepoint.name = name; + + user_event_parse_flags(user, flags); + + ret = user_event_parse_fields(user, args); + + if (ret) + goto put_user; + + ret = user_event_create_print_fmt(user); + + if (ret) + goto put_user; + + user->call.data = user; + user->call.class = &user->class; + user->call.name = name; + user->call.flags = TRACE_EVENT_FL_TRACEPOINT; + user->call.tp = &user->tracepoint; + user->call.event.funcs = &user_event_funcs; + + user->class.system = USER_EVENTS_SYSTEM; + user->class.fields_array = user_event_fields_array; + user->class.get_fields = user_event_get_fields; + user->class.reg = user_event_reg; + user->class.probe = user_event_ftrace; +#ifdef CONFIG_PERF_EVENTS + user->class.perf_probe = user_event_perf; +#endif + + mutex_lock(&event_mutex); + ret = user_event_trace_register(user); + mutex_unlock(&event_mutex); + + if (ret) + goto put_user; + + user->index = index; + + /* Ensure we track ref */ + atomic_inc(&user->refcnt); + + dyn_event_init(&user->devent, &user_event_dops); + dyn_event_add(&user->devent, &user->call); + set_bit(user->index, page_bitmap); + hash_add(register_table, &user->node, key); + + *newuser = user; + return 0; +put_user: + user_event_destroy_fields(user); + user_event_destroy_validators(user); + kfree(user); + return ret; +} + +/* + * Deletes a previously created event if it is no longer being used. + */ +static int delete_user_event(char *name) +{ + u32 key; + int ret; + struct user_event *user = find_user_event(name, &key); + + if (!user) + return -ENOENT; + + /* Ensure we are the last ref */ + if (atomic_read(&user->refcnt) != 1) { + ret = -EBUSY; + goto put_ref; + } + + ret = destroy_user_event(user); + + if (ret) + goto put_ref; + + return ret; +put_ref: + /* No longer have this ref */ + atomic_dec(&user->refcnt); + + return ret; +} + +/* + * Validates the user payload and writes via iterator. + */ +static ssize_t user_events_write_core(struct file *file, struct iov_iter *i) +{ + struct user_event_refs *refs; + struct user_event *user = NULL; + struct tracepoint *tp; + ssize_t ret = i->count; + int idx; + + if (unlikely(copy_from_iter(&idx, sizeof(idx), i) != sizeof(idx))) + return -EFAULT; + + rcu_read_lock_sched(); + + refs = rcu_dereference_sched(file->private_data); + + /* + * The refs->events array is protected by RCU, and new items may be + * added. But the user retrieved from indexing into the events array + * shall be immutable while the file is opened. + */ + if (likely(refs && idx < refs->count)) + user = refs->events[idx]; + + rcu_read_unlock_sched(); + + if (unlikely(user == NULL)) + return -ENOENT; + + if (unlikely(i->count < user->min_size)) + return -EINVAL; + + tp = &user->tracepoint; + + /* + * It's possible key.enabled disables after this check, however + * we don't mind if a few events are included in this condition. + */ + if (likely(atomic_read(&tp->key.enabled) > 0)) { + struct tracepoint_func *probe_func_ptr; + user_event_func_t probe_func; + struct iov_iter copy; + void *tpdata; + bool faulted; + + if (unlikely(fault_in_iov_iter_readable(i, i->count))) + return -EFAULT; + + faulted = false; + + rcu_read_lock_sched(); + + probe_func_ptr = rcu_dereference_sched(tp->funcs); + + if (probe_func_ptr) { + do { + copy = *i; + probe_func = probe_func_ptr->func; + tpdata = probe_func_ptr->data; + probe_func(user, ©, tpdata, &faulted); + } while ((++probe_func_ptr)->func); + } + + rcu_read_unlock_sched(); + + if (unlikely(faulted)) + return -EFAULT; + } + + return ret; +} + +static ssize_t user_events_write(struct file *file, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct iovec iov; + struct iov_iter i; + + if (unlikely(*ppos != 0)) + return -EFAULT; + + if (unlikely(import_single_range(READ, (char *)ubuf, count, &iov, &i))) + return -EFAULT; + + return user_events_write_core(file, &i); +} + +static ssize_t user_events_write_iter(struct kiocb *kp, struct iov_iter *i) +{ + return user_events_write_core(kp->ki_filp, i); +} + +static int user_events_ref_add(struct file *file, struct user_event *user) +{ + struct user_event_refs *refs, *new_refs; + int i, size, count = 0; + + refs = rcu_dereference_protected(file->private_data, + lockdep_is_held(®_mutex)); + + if (refs) { + count = refs->count; + + for (i = 0; i < count; ++i) + if (refs->events[i] == user) + return i; + } + + size = struct_size(refs, events, count + 1); + + new_refs = kzalloc(size, GFP_KERNEL); + + if (!new_refs) + return -ENOMEM; + + new_refs->count = count + 1; + + for (i = 0; i < count; ++i) + new_refs->events[i] = refs->events[i]; + + new_refs->events[i] = user; + + atomic_inc(&user->refcnt); + + rcu_assign_pointer(file->private_data, new_refs); + + if (refs) + kfree_rcu(refs, rcu); + + return i; +} + +static long user_reg_get(struct user_reg __user *ureg, struct user_reg *kreg) +{ + u32 size; + long ret; + + ret = get_user(size, &ureg->size); + + if (ret) + return ret; + + if (size > PAGE_SIZE) + return -E2BIG; + + return copy_struct_from_user(kreg, sizeof(*kreg), ureg, size); +} + +/* + * Registers a user_event on behalf of a user process. + */ +static long user_events_ioctl_reg(struct file *file, unsigned long uarg) +{ + struct user_reg __user *ureg = (struct user_reg __user *)uarg; + struct user_reg reg; + struct user_event *user; + char *name; + long ret; + + ret = user_reg_get(ureg, ®); + + if (ret) + return ret; + + name = strndup_user((const char __user *)(uintptr_t)reg.name_args, + MAX_EVENT_DESC); + + if (IS_ERR(name)) { + ret = PTR_ERR(name); + return ret; + } + + ret = user_event_parse_cmd(name, &user); + + if (ret) { + kfree(name); + return ret; + } + + ret = user_events_ref_add(file, user); + + /* No longer need parse ref, ref_add either worked or not */ + atomic_dec(&user->refcnt); + + /* Positive number is index and valid */ + if (ret < 0) + return ret; + + put_user((u32)ret, &ureg->write_index); + put_user(user->index, &ureg->status_index); + + return 0; +} + +/* + * Deletes a user_event on behalf of a user process. + */ +static long user_events_ioctl_del(struct file *file, unsigned long uarg) +{ + void __user *ubuf = (void __user *)uarg; + char *name; + long ret; + + name = strndup_user(ubuf, MAX_EVENT_DESC); + + if (IS_ERR(name)) + return PTR_ERR(name); + + /* event_mutex prevents dyn_event from racing */ + mutex_lock(&event_mutex); + ret = delete_user_event(name); + mutex_unlock(&event_mutex); + + kfree(name); + + return ret; +} + +/* + * Handles the ioctl from user mode to register or alter operations. + */ +static long user_events_ioctl(struct file *file, unsigned int cmd, + unsigned long uarg) +{ + long ret = -ENOTTY; + + switch (cmd) { + case DIAG_IOCSREG: + mutex_lock(®_mutex); + ret = user_events_ioctl_reg(file, uarg); + mutex_unlock(®_mutex); + break; + + case DIAG_IOCSDEL: + mutex_lock(®_mutex); + ret = user_events_ioctl_del(file, uarg); + mutex_unlock(®_mutex); + break; + } + + return ret; +} + +/* + * Handles the final close of the file from user mode. + */ +static int user_events_release(struct inode *node, struct file *file) +{ + struct user_event_refs *refs; + struct user_event *user; + int i; + + /* + * Ensure refs cannot change under any situation by taking the + * register mutex during the final freeing of the references. + */ + mutex_lock(®_mutex); + + refs = file->private_data; + + if (!refs) + goto out; + + /* + * The lifetime of refs has reached an end, it's tied to this file. + * The underlying user_events are ref counted, and cannot be freed. + * After this decrement, the user_events may be freed elsewhere. + */ + for (i = 0; i < refs->count; ++i) { + user = refs->events[i]; + + if (user) + atomic_dec(&user->refcnt); + } +out: + file->private_data = NULL; + + mutex_unlock(®_mutex); + + kfree(refs); + + return 0; +} + +static const struct file_operations user_data_fops = { + .write = user_events_write, + .write_iter = user_events_write_iter, + .unlocked_ioctl = user_events_ioctl, + .release = user_events_release, +}; + +/* + * Maps the shared page into the user process for checking if event is enabled. + */ +static int user_status_mmap(struct file *file, struct vm_area_struct *vma) +{ + unsigned long size = vma->vm_end - vma->vm_start; + + if (size != MAX_EVENTS) + return -EINVAL; + + return remap_pfn_range(vma, vma->vm_start, + virt_to_phys(register_page_data) >> PAGE_SHIFT, + size, vm_get_page_prot(VM_READ)); +} + +static void *user_seq_start(struct seq_file *m, loff_t *pos) +{ + if (*pos) + return NULL; + + return (void *)1; +} + +static void *user_seq_next(struct seq_file *m, void *p, loff_t *pos) +{ + ++*pos; + return NULL; +} + +static void user_seq_stop(struct seq_file *m, void *p) +{ +} + +static int user_seq_show(struct seq_file *m, void *p) +{ + struct user_event *user; + char status; + int i, active = 0, busy = 0, flags; + + mutex_lock(®_mutex); + + hash_for_each(register_table, i, user, node) { + status = register_page_data[user->index]; + flags = user->flags; + + seq_printf(m, "%d:%s", user->index, EVENT_NAME(user)); + + if (flags != 0 || status != 0) + seq_puts(m, " #"); + + if (status != 0) { + seq_puts(m, " Used by"); + if (status & EVENT_STATUS_FTRACE) + seq_puts(m, " ftrace"); + if (status & EVENT_STATUS_PERF) + seq_puts(m, " perf"); + if (status & EVENT_STATUS_OTHER) + seq_puts(m, " other"); + busy++; + } + + if (flags & FLAG_BPF_ITER) + seq_puts(m, " FLAG:BPF_ITER"); + + seq_puts(m, "\n"); + active++; + } + + mutex_unlock(®_mutex); + + seq_puts(m, "\n"); + seq_printf(m, "Active: %d\n", active); + seq_printf(m, "Busy: %d\n", busy); + seq_printf(m, "Max: %ld\n", MAX_EVENTS); + + return 0; +} + +static const struct seq_operations user_seq_ops = { + .start = user_seq_start, + .next = user_seq_next, + .stop = user_seq_stop, + .show = user_seq_show, +}; + +static int user_status_open(struct inode *node, struct file *file) +{ + return seq_open(file, &user_seq_ops); +} + +static const struct file_operations user_status_fops = { + .open = user_status_open, + .mmap = user_status_mmap, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +/* + * Creates a set of tracefs files to allow user mode interactions. + */ +static int create_user_tracefs(void) +{ + struct dentry *edata, *emmap; + + edata = tracefs_create_file("user_events_data", TRACE_MODE_WRITE, + NULL, NULL, &user_data_fops); + + if (!edata) { + pr_warn("Could not create tracefs 'user_events_data' entry\n"); + goto err; + } + + /* mmap with MAP_SHARED requires writable fd */ + emmap = tracefs_create_file("user_events_status", TRACE_MODE_WRITE, + NULL, NULL, &user_status_fops); + + if (!emmap) { + tracefs_remove(edata); + pr_warn("Could not create tracefs 'user_events_mmap' entry\n"); + goto err; + } + + return 0; +err: + return -ENODEV; +} + +static void set_page_reservations(bool set) +{ + int page; + + for (page = 0; page < MAX_PAGES; ++page) { + void *addr = register_page_data + (PAGE_SIZE * page); + + if (set) + SetPageReserved(virt_to_page(addr)); + else + ClearPageReserved(virt_to_page(addr)); + } +} + +static int __init trace_events_user_init(void) +{ + struct page *pages; + int ret; + + /* Zero all bits beside 0 (which is reserved for failures) */ + bitmap_zero(page_bitmap, MAX_EVENTS); + set_bit(0, page_bitmap); + + pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, MAX_PAGE_ORDER); + if (!pages) + return -ENOMEM; + register_page_data = page_address(pages); + + set_page_reservations(true); + + ret = create_user_tracefs(); + + if (ret) { + pr_warn("user_events could not register with tracefs\n"); + set_page_reservations(false); + __free_pages(pages, MAX_PAGE_ORDER); + return ret; + } + + if (dyn_event_register(&user_event_dops)) + pr_warn("user_events could not register with dyn_events\n"); + + return 0; +} + +fs_initcall(trace_events_user_init); diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 5e3c62a08fc0..e9ae1f33a7f0 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1167,7 +1167,9 @@ thread_exit(struct osnoise_variables *osn_var, struct task_struct *t) * used to record the beginning and to report the end of a thread noise window. */ static void -trace_sched_switch_callback(void *data, bool preempt, struct task_struct *p, +trace_sched_switch_callback(void *data, bool preempt, + unsigned int prev_state, + struct task_struct *p, struct task_struct *n) { struct osnoise_variables *osn_var = this_cpu_osn_var(); diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index e304196d7c28..45796d8bd4b2 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -22,6 +22,7 @@ static DEFINE_MUTEX(sched_register_mutex); static void probe_sched_switch(void *ignore, bool preempt, + unsigned int prev_state, struct task_struct *prev, struct task_struct *next) { int flags; @@ -44,7 +45,7 @@ probe_sched_wakeup(void *ignore, struct task_struct *wakee) if (!flags) return; - tracing_record_taskinfo(current, flags); + tracing_record_taskinfo_sched_switch(current, wakee, flags); } static int tracing_sched_register(void) diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 2402de520eca..46429f9a96fa 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -426,6 +426,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr, static void notrace probe_wakeup_sched_switch(void *ignore, bool preempt, + unsigned int prev_state, struct task_struct *prev, struct task_struct *next) { struct trace_array_cpu *data; |