Merge branch 'perf/uprobes' into perf/core

These bits from Oleg are fully cooked, ship them to Linus.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 47 insertions, 34 deletions

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index d1edc5e..3b02c72 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -127,7 +127,7 @@ struct xol_area {
  */
 static bool valid_vma(struct vm_area_struct *vma, bool is_register)
 {
-	vm_flags_t flags = VM_HUGETLB | VM_MAYEXEC | VM_SHARED;
+	vm_flags_t flags = VM_HUGETLB | VM_MAYEXEC | VM_MAYSHARE;
 
 	if (is_register)
 		flags |= VM_WRITE;
@@ -279,18 +279,13 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t
  * supported by that architecture then we need to modify is_trap_at_addr and
  * uprobe_write_opcode accordingly. This would never be a problem for archs
  * that have fixed length instructions.
- */
-
-/*
+ *
  * uprobe_write_opcode - write the opcode at a given virtual address.
  * @mm: the probed process address space.
  * @vaddr: the virtual address to store the opcode.
  * @opcode: opcode to be written at @vaddr.
  *
- * Called with mm->mmap_sem held (for read and with a reference to
- * mm).
- *
- * For mm @mm, write the opcode at @vaddr.
+ * Called with mm->mmap_sem held for write.
  * Return 0 (success) or a negative errno.
  */
 int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr,
@@ -310,21 +305,25 @@ retry:
 	if (ret <= 0)
 		goto put_old;
 
+	ret = anon_vma_prepare(vma);
+	if (ret)
+		goto put_old;
+
 	ret = -ENOMEM;
 	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
 	if (!new_page)
 		goto put_old;
 
-	__SetPageUptodate(new_page);
+	if (mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL))
+		goto put_new;
 
+	__SetPageUptodate(new_page);
 	copy_highpage(new_page, old_page);
 	copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
 
-	ret = anon_vma_prepare(vma);
-	if (ret)
-		goto put_new;
-
 	ret = __replace_page(vma, vaddr, old_page, new_page);
+	if (ret)
+		mem_cgroup_uncharge_page(new_page);
 
 put_new:
 	page_cache_release(new_page);
@@ -1352,6 +1351,16 @@ unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs)
 	return instruction_pointer(regs) - UPROBE_SWBP_INSN_SIZE;
 }
 
+unsigned long uprobe_get_trap_addr(struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	if (unlikely(utask && utask->active_uprobe))
+		return utask->vaddr;
+
+	return instruction_pointer(regs);
+}
+
 /*
  * Called with no locks held.
  * Called in context of a exiting or a exec-ing thread.
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index c082a74..5a7f1a6 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1009,56 +1009,60 @@ uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event)
 	return __uprobe_perf_filter(&tu->filter, event->hw.tp_target->mm);
 }
 
-static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event)
+static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event)
 {
 	bool done;
 
 	write_lock(&tu->filter.rwlock);
 	if (event->hw.tp_target) {
-		/*
-		 * event->parent != NULL means copy_process(), we can avoid
-		 * uprobe_apply(). current->mm must be probed and we can rely
-		 * on dup_mmap() which preserves the already installed bp's.
-		 *
-		 * attr.enable_on_exec means that exec/mmap will install the
-		 * breakpoints we need.
-		 */
+		list_del(&event->hw.tp_list);
 		done = tu->filter.nr_systemwide ||
-			event->parent || event->attr.enable_on_exec ||
+			(event->hw.tp_target->flags & PF_EXITING) ||
 			uprobe_filter_event(tu, event);
-		list_add(&event->hw.tp_list, &tu->filter.perf_events);
 	} else {
+		tu->filter.nr_systemwide--;
 		done = tu->filter.nr_systemwide;
-		tu->filter.nr_systemwide++;
 	}
 	write_unlock(&tu->filter.rwlock);
 
 	if (!done)
-		uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
+		return uprobe_apply(tu->inode, tu->offset, &tu->consumer, false);
 
 	return 0;
 }
 
-static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event)
+static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event)
 {
 	bool done;
+	int err;
 
 	write_lock(&tu->filter.rwlock);
 	if (event->hw.tp_target) {
-		list_del(&event->hw.tp_list);
+		/*
+		 * event->parent != NULL means copy_process(), we can avoid
+		 * uprobe_apply(). current->mm must be probed and we can rely
+		 * on dup_mmap() which preserves the already installed bp's.
+		 *
+		 * attr.enable_on_exec means that exec/mmap will install the
+		 * breakpoints we need.
+		 */
 		done = tu->filter.nr_systemwide ||
-			(event->hw.tp_target->flags & PF_EXITING) ||
+			event->parent || event->attr.enable_on_exec ||
 			uprobe_filter_event(tu, event);
+		list_add(&event->hw.tp_list, &tu->filter.perf_events);
 	} else {
-		tu->filter.nr_systemwide--;
 		done = tu->filter.nr_systemwide;
+		tu->filter.nr_systemwide++;
 	}
 	write_unlock(&tu->filter.rwlock);
 
-	if (!done)
-		uprobe_apply(tu->inode, tu->offset, &tu->consumer, false);
-
-	return 0;
+	err = 0;
+	if (!done) {
+		err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
+		if (err)
+			uprobe_perf_close(tu, event);
+	}
+	return err;
 }
 
 static bool uprobe_perf_filter(struct uprobe_consumer *uc,