1 files changed, 131 insertions, 13 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 856d98c36f56..5bfe8e3c6e44 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -394,6 +394,7 @@ static atomic_t nr_switch_events __read_mostly;
 static atomic_t nr_ksymbol_events __read_mostly;
 static atomic_t nr_bpf_events __read_mostly;
 static atomic_t nr_cgroup_events __read_mostly;
+static atomic_t nr_text_poke_events __read_mostly;
 
 static LIST_HEAD(pmus);
 static DEFINE_MUTEX(pmus_lock);
@@ -1237,12 +1238,26 @@ static void get_ctx(struct perf_event_context *ctx)
 	refcount_inc(&ctx->refcount);
 }
 
+static void *alloc_task_ctx_data(struct pmu *pmu)
+{
+	if (pmu->task_ctx_cache)
+		return kmem_cache_zalloc(pmu->task_ctx_cache, GFP_KERNEL);
+
+	return NULL;
+}
+
+static void free_task_ctx_data(struct pmu *pmu, void *task_ctx_data)
+{
+	if (pmu->task_ctx_cache && task_ctx_data)
+		kmem_cache_free(pmu->task_ctx_cache, task_ctx_data);
+}
+
 static void free_ctx(struct rcu_head *head)
 {
 	struct perf_event_context *ctx;
 
 	ctx = container_of(head, struct perf_event_context, rcu_head);
-	kfree(ctx->task_ctx_data);
+	free_task_ctx_data(ctx->pmu, ctx->task_ctx_data);
 	kfree(ctx);
 }
 
@@ -4470,7 +4485,7 @@ find_get_context(struct pmu *pmu, struct task_struct *task,
 		goto errout;
 
 	if (event->attach_state & PERF_ATTACH_TASK_DATA) {
-		task_ctx_data = kzalloc(pmu->task_ctx_size, GFP_KERNEL);
+		task_ctx_data = alloc_task_ctx_data(pmu);
 		if (!task_ctx_data) {
 			err = -ENOMEM;
 			goto errout;
@@ -4528,11 +4543,11 @@ retry:
 		}
 	}
 
-	kfree(task_ctx_data);
+	free_task_ctx_data(pmu, task_ctx_data);
 	return ctx;
 
 errout:
-	kfree(task_ctx_data);
+	free_task_ctx_data(pmu, task_ctx_data);
 	return ERR_PTR(err);
 }
 
@@ -4575,7 +4590,7 @@ static bool is_sb_event(struct perf_event *event)
 	if (attr->mmap || attr->mmap_data || attr->mmap2 ||
 	    attr->comm || attr->comm_exec ||
 	    attr->task || attr->ksymbol ||
-	    attr->context_switch ||
+	    attr->context_switch || attr->text_poke ||
 	    attr->bpf_event)
 		return true;
 	return false;
@@ -4651,6 +4666,8 @@ static void unaccount_event(struct perf_event *event)
 		atomic_dec(&nr_ksymbol_events);
 	if (event->attr.bpf_event)
 		atomic_dec(&nr_bpf_events);
+	if (event->attr.text_poke)
+		atomic_dec(&nr_text_poke_events);
 
 	if (dec) {
 		if (!atomic_add_unless(&perf_sched_count, -1, 1))
@@ -6436,10 +6453,9 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
 
 		/* Data. */
 		sp = perf_user_stack_pointer(regs);
-		fs = get_fs();
-		set_fs(USER_DS);
+		fs = force_uaccess_begin();
 		rem = __output_copy_user(handle, (void *) sp, dump_size);
-		set_fs(fs);
+		force_uaccess_end(fs);
 		dyn_size = dump_size - rem;
 
 		perf_output_skip(handle, rem);
@@ -8628,6 +8644,89 @@ void perf_event_bpf_event(struct bpf_prog *prog,
 	perf_iterate_sb(perf_event_bpf_output, &bpf_event, NULL);
 }
 
+struct perf_text_poke_event {
+	const void		*old_bytes;
+	const void		*new_bytes;
+	size_t			pad;
+	u16			old_len;
+	u16			new_len;
+
+	struct {
+		struct perf_event_header	header;
+
+		u64				addr;
+	} event_id;
+};
+
+static int perf_event_text_poke_match(struct perf_event *event)
+{
+	return event->attr.text_poke;
+}
+
+static void perf_event_text_poke_output(struct perf_event *event, void *data)
+{
+	struct perf_text_poke_event *text_poke_event = data;
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	u64 padding = 0;
+	int ret;
+
+	if (!perf_event_text_poke_match(event))
+		return;
+
+	perf_event_header__init_id(&text_poke_event->event_id.header, &sample, event);
+
+	ret = perf_output_begin(&handle, event, text_poke_event->event_id.header.size);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, text_poke_event->event_id);
+	perf_output_put(&handle, text_poke_event->old_len);
+	perf_output_put(&handle, text_poke_event->new_len);
+
+	__output_copy(&handle, text_poke_event->old_bytes, text_poke_event->old_len);
+	__output_copy(&handle, text_poke_event->new_bytes, text_poke_event->new_len);
+
+	if (text_poke_event->pad)
+		__output_copy(&handle, &padding, text_poke_event->pad);
+
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+}
+
+void perf_event_text_poke(const void *addr, const void *old_bytes,
+			  size_t old_len, const void *new_bytes, size_t new_len)
+{
+	struct perf_text_poke_event text_poke_event;
+	size_t tot, pad;
+
+	if (!atomic_read(&nr_text_poke_events))
+		return;
+
+	tot  = sizeof(text_poke_event.old_len) + old_len;
+	tot += sizeof(text_poke_event.new_len) + new_len;
+	pad  = ALIGN(tot, sizeof(u64)) - tot;
+
+	text_poke_event = (struct perf_text_poke_event){
+		.old_bytes    = old_bytes,
+		.new_bytes    = new_bytes,
+		.pad          = pad,
+		.old_len      = old_len,
+		.new_len      = new_len,
+		.event_id  = {
+			.header = {
+				.type = PERF_RECORD_TEXT_POKE,
+				.misc = PERF_RECORD_MISC_KERNEL,
+				.size = sizeof(text_poke_event.event_id) + tot + pad,
+			},
+			.addr = (unsigned long)addr,
+		},
+	};
+
+	perf_iterate_sb(perf_event_text_poke_output, &text_poke_event, NULL);
+}
+
 void perf_event_itrace_started(struct perf_event *event)
 {
 	event->attach_state |= PERF_ATTACH_ITRACE;
@@ -9544,6 +9643,24 @@ static int perf_event_set_bpf_handler(struct perf_event *event, u32 prog_fd)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
+	if (event->attr.precise_ip &&
+	    prog->call_get_stack &&
+	    (!(event->attr.sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY) ||
+	     event->attr.exclude_callchain_kernel ||
+	     event->attr.exclude_callchain_user)) {
+		/*
+		 * On perf_event with precise_ip, calling bpf_get_stack()
+		 * may trigger unwinder warnings and occasional crashes.
+		 * bpf_get_[stack|stackid] works around this issue by using
+		 * callchain attached to perf_sample_data. If the
+		 * perf_event does not full (kernel and user) callchain
+		 * attached to perf_sample_data, do not allow attaching BPF
+		 * program that calls bpf_get_[stack|stackid].
+		 */
+		bpf_prog_put(prog);
+		return -EPROTO;
+	}
+
 	event->prog = prog;
 	event->orig_overflow_handler = READ_ONCE(event->overflow_handler);
 	WRITE_ONCE(event->overflow_handler, bpf_overflow_handler);
@@ -10945,6 +11062,8 @@ static void account_event(struct perf_event *event)
 		atomic_inc(&nr_ksymbol_events);
 	if (event->attr.bpf_event)
 		atomic_inc(&nr_bpf_events);
+	if (event->attr.text_poke)
+		atomic_inc(&nr_text_poke_events);
 
 	if (inc) {
 		/*
@@ -11483,7 +11602,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	struct perf_event *group_leader = NULL, *output_event = NULL;
 	struct perf_event *event, *sibling;
 	struct perf_event_attr attr;
-	struct perf_event_context *ctx, *uninitialized_var(gctx);
+	struct perf_event_context *ctx, *gctx;
 	struct file *event_file = NULL;
 	struct fd group = {NULL, 0};
 	struct task_struct *task = NULL;
@@ -11587,7 +11706,7 @@ SYSCALL_DEFINE5(perf_event_open,
 			goto err_task;
 
 		/*
-		 * Reuse ptrace permission checks for now.
+		 * Preserve ptrace permission check for backwards compatibility.
 		 *
 		 * We must hold exec_update_mutex across this and any potential
 		 * perf_install_in_context() call for this new event to
@@ -11595,7 +11714,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		 * perf_event_exit_task() that could imply).
 		 */
 		err = -EACCES;
-		if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
+		if (!perfmon_capable() && !ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
 			goto err_cred;
 	}
 
@@ -12409,8 +12528,7 @@ inherit_event(struct perf_event *parent_event,
 	    !child_ctx->task_ctx_data) {
 		struct pmu *pmu = child_event->pmu;
 
-		child_ctx->task_ctx_data = kzalloc(pmu->task_ctx_size,
-						   GFP_KERNEL);
+		child_ctx->task_ctx_data = alloc_task_ctx_data(pmu);
 		if (!child_ctx->task_ctx_data) {
 			free_event(child_event);
 			return ERR_PTR(-ENOMEM);