3 files changed, 96 insertions, 37 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index f5744010a8d..56003c6edfd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -119,7 +119,8 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
 
 #define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
 		       PERF_FLAG_FD_OUTPUT  |\
-		       PERF_FLAG_PID_CGROUP)
+		       PERF_FLAG_PID_CGROUP |\
+		       PERF_FLAG_FD_CLOEXEC)
 
 /*
  * branch priv levels that need permission checks
@@ -3542,7 +3543,7 @@ static void perf_event_for_each(struct perf_event *event,
 static int perf_event_period(struct perf_event *event, u64 __user *arg)
 {
 	struct perf_event_context *ctx = event->ctx;
-	int ret = 0;
+	int ret = 0, active;
 	u64 value;
 
 	if (!is_sampling_event(event))
@@ -3566,6 +3567,20 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 		event->attr.sample_period = value;
 		event->hw.sample_period = value;
 	}
+
+	active = (event->state == PERF_EVENT_STATE_ACTIVE);
+	if (active) {
+		perf_pmu_disable(ctx->pmu);
+		event->pmu->stop(event, PERF_EF_UPDATE);
+	}
+
+	local64_set(&event->hw.period_left, 0);
+
+	if (active) {
+		event->pmu->start(event, PERF_EF_RELOAD);
+		perf_pmu_enable(ctx->pmu);
+	}
+
 unlock:
 	raw_spin_unlock_irq(&ctx->lock);
 
@@ -6670,6 +6685,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	INIT_LIST_HEAD(&event->event_entry);
 	INIT_LIST_HEAD(&event->sibling_list);
 	INIT_LIST_HEAD(&event->rb_entry);
+	INIT_LIST_HEAD(&event->active_entry);
+	INIT_HLIST_NODE(&event->hlist_entry);
+
 
 	init_waitqueue_head(&event->waitq);
 	init_irq_work(&event->pending, perf_pending_event);
@@ -6980,6 +6998,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	int event_fd;
 	int move_group = 0;
 	int err;
+	int f_flags = O_RDWR;
 
 	/* for future expandability... */
 	if (flags & ~PERF_FLAG_ALL)
@@ -7008,7 +7027,10 @@ SYSCALL_DEFINE5(perf_event_open,
 	if ((flags & PERF_FLAG_PID_CGROUP) && (pid == -1 || cpu == -1))
 		return -EINVAL;
 
-	event_fd = get_unused_fd();
+	if (flags & PERF_FLAG_FD_CLOEXEC)
+		f_flags |= O_CLOEXEC;
+
+	event_fd = get_unused_fd_flags(f_flags);
 	if (event_fd < 0)
 		return event_fd;
 
@@ -7130,7 +7152,8 @@ SYSCALL_DEFINE5(perf_event_open,
 			goto err_context;
 	}
 
-	event_file = anon_inode_getfile("[perf_event]", &perf_fops, event, O_RDWR);
+	event_file = anon_inode_getfile("[perf_event]", &perf_fops, event,
+					f_flags);
 	if (IS_ERR(event_file)) {
 		err = PTR_ERR(event_file);
 		goto err_context;
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index e8b168af135..146a5792b1d 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -61,19 +61,20 @@ again:
 	 *
 	 *   kernel				user
 	 *
-	 *   READ ->data_tail			READ ->data_head
-	 *   smp_mb()	(A)			smp_rmb()	(C)
-	 *   WRITE $data			READ $data
-	 *   smp_wmb()	(B)			smp_mb()	(D)
-	 *   STORE ->data_head			WRITE ->data_tail
+	 *   if (LOAD ->data_tail) {		LOAD ->data_head
+	 *			(A)		smp_rmb()	(C)
+	 *	STORE $data			LOAD $data
+	 *	smp_wmb()	(B)		smp_mb()	(D)
+	 *	STORE ->data_head		STORE ->data_tail
+	 *   }
 	 *
 	 * Where A pairs with D, and B pairs with C.
 	 *
-	 * I don't think A needs to be a full barrier because we won't in fact
-	 * write data until we see the store from userspace. So we simply don't
-	 * issue the data WRITE until we observe it. Be conservative for now.
+	 * In our case (A) is a control dependency that separates the load of
+	 * the ->data_tail and the stores of $data. In case ->data_tail
+	 * indicates there is no room in the buffer to store $data we do not.
 	 *
-	 * OTOH, D needs to be a full barrier since it separates the data READ
+	 * D needs to be a full barrier since it separates the data READ
 	 * from the tail WRITE.
 	 *
 	 * For B a WMB is sufficient since it separates two WRITEs, and for C
@@ -81,7 +82,7 @@ again:
 	 *
 	 * See perf_output_begin().
 	 */
-	smp_wmb();
+	smp_wmb(); /* B, matches C */
 	rb->user_page->data_head = head;
 
 	/*
@@ -144,17 +145,26 @@ int perf_output_begin(struct perf_output_handle *handle,
 		if (!rb->overwrite &&
 		    unlikely(CIRC_SPACE(head, tail, perf_data_size(rb)) < size))
 			goto fail;
+
+		/*
+		 * The above forms a control dependency barrier separating the
+		 * @tail load above from the data stores below. Since the @tail
+		 * load is required to compute the branch to fail below.
+		 *
+		 * A, matches D; the full memory barrier userspace SHOULD issue
+		 * after reading the data and before storing the new tail
+		 * position.
+		 *
+		 * See perf_output_put_handle().
+		 */
+
 		head += size;
 	} while (local_cmpxchg(&rb->head, offset, head) != offset);
 
 	/*
-	 * Separate the userpage->tail read from the data stores below.
-	 * Matches the MB userspace SHOULD issue after reading the data
-	 * and before storing the new tail position.
-	 *
-	 * See perf_output_put_handle().
+	 * We rely on the implied barrier() by local_cmpxchg() to ensure
+	 * none of the data stores below can be lifted up by the compiler.
 	 */
-	smp_mb();
 
 	if (unlikely(head - local_read(&rb->wakeup) > rb->watermark))
 		local_add(rb->watermark, &rb->wakeup);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 24b7d6ca871..b886a5e7d4f 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -73,6 +73,17 @@ struct uprobe {
 	struct inode		*inode;		/* Also hold a ref to inode */
 	loff_t			offset;
 	unsigned long		flags;
+
+	/*
+	 * The generic code assumes that it has two members of unknown type
+	 * owned by the arch-specific code:
+	 *
+	 * 	insn -	copy_insn() saves the original instruction here for
+	 *		arch_uprobe_analyze_insn().
+	 *
+	 *	ixol -	potentially modified instruction to execute out of
+	 *		line, copied to xol_area by xol_get_insn_slot().
+	 */
 	struct arch_uprobe	arch;
 };
 
@@ -86,6 +97,29 @@ struct return_instance {
 };
 
 /*
+ * Execute out of line area: anonymous executable mapping installed
+ * by the probed task to execute the copy of the original instruction
+ * mangled by set_swbp().
+ *
+ * On a breakpoint hit, thread contests for a slot.  It frees the
+ * slot after singlestep. Currently a fixed number of slots are
+ * allocated.
+ */
+struct xol_area {
+	wait_queue_head_t 	wq;		/* if all slots are busy */
+	atomic_t 		slot_count;	/* number of in-use slots */
+	unsigned long 		*bitmap;	/* 0 = free slot */
+	struct page 		*page;
+
+	/*
+	 * We keep the vma's vm_start rather than a pointer to the vma
+	 * itself.  The probed process or a naughty kernel module could make
+	 * the vma go away, and we must handle that reasonably gracefully.
+	 */
+	unsigned long 		vaddr;		/* Page(s) of instruction slots */
+};
+
+/*
  * valid_vma: Verify if the specified vma is an executable vma
  * Relax restrictions while unregistering: vm_flags might have
  * changed after breakpoint was inserted.
@@ -330,7 +364,7 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned
 int __weak
 set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
 {
-	return uprobe_write_opcode(mm, vaddr, *(uprobe_opcode_t *)auprobe->insn);
+	return uprobe_write_opcode(mm, vaddr, *(uprobe_opcode_t *)&auprobe->insn);
 }
 
 static int match_uprobe(struct uprobe *l, struct uprobe *r)
@@ -529,8 +563,8 @@ static int copy_insn(struct uprobe *uprobe, struct file *filp)
 {
 	struct address_space *mapping = uprobe->inode->i_mapping;
 	loff_t offs = uprobe->offset;
-	void *insn = uprobe->arch.insn;
-	int size = MAX_UINSN_BYTES;
+	void *insn = &uprobe->arch.insn;
+	int size = sizeof(uprobe->arch.insn);
 	int len, err = -EIO;
 
 	/* Copy only available bytes, -EIO if nothing was read */
@@ -569,7 +603,7 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
 		goto out;
 
 	ret = -ENOTSUPP;
-	if (is_trap_insn((uprobe_opcode_t *)uprobe->arch.insn))
+	if (is_trap_insn((uprobe_opcode_t *)&uprobe->arch.insn))
 		goto out;
 
 	ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr);
@@ -1264,7 +1298,7 @@ static unsigned long xol_get_insn_slot(struct uprobe *uprobe)
 
 	/* Initialize the slot */
 	copy_to_page(area->page, xol_vaddr,
-			uprobe->arch.ixol, sizeof(uprobe->arch.ixol));
+			&uprobe->arch.ixol, sizeof(uprobe->arch.ixol));
 	/*
 	 * We probably need flush_icache_user_range() but it needs vma.
 	 * This should work on supported architectures too.
@@ -1403,12 +1437,10 @@ static void uprobe_warn(struct task_struct *t, const char *msg)
 
 static void dup_xol_work(struct callback_head *work)
 {
-	kfree(work);
-
 	if (current->flags & PF_EXITING)
 		return;
 
-	if (!__create_xol_area(current->utask->vaddr))
+	if (!__create_xol_area(current->utask->dup_xol_addr))
 		uprobe_warn(current, "dup xol area");
 }
 
@@ -1419,7 +1451,6 @@ void uprobe_copy_process(struct task_struct *t, unsigned long flags)
 {
 	struct uprobe_task *utask = current->utask;
 	struct mm_struct *mm = current->mm;
-	struct callback_head *work;
 	struct xol_area *area;
 
 	t->utask = NULL;
@@ -1441,14 +1472,9 @@ void uprobe_copy_process(struct task_struct *t, unsigned long flags)
 	if (mm == t->mm)
 		return;
 
-	/* TODO: move it into the union in uprobe_task */
-	work = kmalloc(sizeof(*work), GFP_KERNEL);
-	if (!work)
-		return uprobe_warn(t, "dup xol area");
-
-	t->utask->vaddr = area->vaddr;
-	init_task_work(work, dup_xol_work);
-	task_work_add(t, work, true);
+	t->utask->dup_xol_addr = area->vaddr;
+	init_task_work(&t->utask->dup_xol_work, dup_xol_work);
+	task_work_add(t, &t->utask->dup_xol_work, true);
 }
 
 /*