2 files changed, 119 insertions, 88 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 647698f91988..8fac2056d51e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -39,6 +39,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/mm_types.h>
 #include <linux/cgroup.h>
+#include <linux/module.h>
 
 #include "internal.h"
 
@@ -1677,6 +1678,8 @@ event_sched_in(struct perf_event *event,
 	u64 tstamp = perf_event_time(event);
 	int ret = 0;
 
+	lockdep_assert_held(&ctx->lock);
+
 	if (event->state <= PERF_EVENT_STATE_OFF)
 		return 0;
 
@@ -3260,9 +3263,13 @@ static void __free_event(struct perf_event *event)
 	if (event->ctx)
 		put_ctx(event->ctx);
 
+	if (event->pmu)
+		module_put(event->pmu->module);
+
 	call_rcu(&event->rcu_head, free_event_rcu);
 }
-static void free_event(struct perf_event *event)
+
+static void _free_event(struct perf_event *event)
 {
 	irq_work_sync(&event->pending);
 
@@ -3283,42 +3290,31 @@ static void free_event(struct perf_event *event)
 	if (is_cgroup_event(event))
 		perf_detach_cgroup(event);
 
-
 	__free_event(event);
 }
 
-int perf_event_release_kernel(struct perf_event *event)
+/*
+ * Used to free events which have a known refcount of 1, such as in error paths
+ * where the event isn't exposed yet and inherited events.
+ */
+static void free_event(struct perf_event *event)
 {
-	struct perf_event_context *ctx = event->ctx;
-
-	WARN_ON_ONCE(ctx->parent_ctx);
-	/*
-	 * There are two ways this annotation is useful:
-	 *
-	 *  1) there is a lock recursion from perf_event_exit_task
-	 *     see the comment there.
-	 *
-	 *  2) there is a lock-inversion with mmap_sem through
-	 *     perf_event_read_group(), which takes faults while
-	 *     holding ctx->mutex, however this is called after
-	 *     the last filedesc died, so there is no possibility
-	 *     to trigger the AB-BA case.
-	 */
-	mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
-	perf_remove_from_context(event, true);
-	mutex_unlock(&ctx->mutex);
-
-	free_event(event);
+	if (WARN(atomic_long_cmpxchg(&event->refcount, 1, 0) != 1,
+				"unexpected event refcount: %ld; ptr=%p\n",
+				atomic_long_read(&event->refcount), event)) {
+		/* leak to avoid use-after-free */
+		return;
+	}
 
-	return 0;
+	_free_event(event);
 }
-EXPORT_SYMBOL_GPL(perf_event_release_kernel);
 
 /*
  * Called when the last reference to the file is gone.
  */
 static void put_event(struct perf_event *event)
 {
+	struct perf_event_context *ctx = event->ctx;
 	struct task_struct *owner;
 
 	if (!atomic_long_dec_and_test(&event->refcount))
@@ -3357,8 +3353,32 @@ static void put_event(struct perf_event *event)
 		put_task_struct(owner);
 	}
 
-	perf_event_release_kernel(event);
+	WARN_ON_ONCE(ctx->parent_ctx);
+	/*
+	 * There are two ways this annotation is useful:
+	 *
+	 *  1) there is a lock recursion from perf_event_exit_task
+	 *     see the comment there.
+	 *
+	 *  2) there is a lock-inversion with mmap_sem through
+	 *     perf_event_read_group(), which takes faults while
+	 *     holding ctx->mutex, however this is called after
+	 *     the last filedesc died, so there is no possibility
+	 *     to trigger the AB-BA case.
+	 */
+	mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
+	perf_remove_from_context(event, true);
+	mutex_unlock(&ctx->mutex);
+
+	_free_event(event);
+}
+
+int perf_event_release_kernel(struct perf_event *event)
+{
+	put_event(event);
+	return 0;
 }
+EXPORT_SYMBOL_GPL(perf_event_release_kernel);
 
 static int perf_release(struct inode *inode, struct file *file)
 {
@@ -6582,6 +6602,7 @@ free_pdc:
 	free_percpu(pmu->pmu_disable_count);
 	goto unlock;
 }
+EXPORT_SYMBOL_GPL(perf_pmu_register);
 
 void perf_pmu_unregister(struct pmu *pmu)
 {
@@ -6603,6 +6624,7 @@ void perf_pmu_unregister(struct pmu *pmu)
 	put_device(pmu->dev);
 	free_pmu_context(pmu);
 }
+EXPORT_SYMBOL_GPL(perf_pmu_unregister);
 
 struct pmu *perf_init_event(struct perf_event *event)
 {
@@ -6616,6 +6638,10 @@ struct pmu *perf_init_event(struct perf_event *event)
 	pmu = idr_find(&pmu_idr, event->attr.type);
 	rcu_read_unlock();
 	if (pmu) {
+		if (!try_module_get(pmu->module)) {
+			pmu = ERR_PTR(-ENODEV);
+			goto unlock;
+		}
 		event->pmu = pmu;
 		ret = pmu->event_init(event);
 		if (ret)
@@ -6624,6 +6650,10 @@ struct pmu *perf_init_event(struct perf_event *event)
 	}
 
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		if (!try_module_get(pmu->module)) {
+			pmu = ERR_PTR(-ENODEV);
+			goto unlock;
+		}
 		event->pmu = pmu;
 		ret = pmu->event_init(event);
 		if (!ret)
@@ -6802,6 +6832,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 err_pmu:
 	if (event->destroy)
 		event->destroy(event);
+	module_put(pmu->module);
 err_ns:
 	if (event->ns)
 		put_pid_ns(event->ns);
@@ -7071,20 +7102,33 @@ SYSCALL_DEFINE5(perf_event_open,
 		}
 	}
 
+	if (task && group_leader &&
+	    group_leader->attr.inherit != attr.inherit) {
+		err = -EINVAL;
+		goto err_task;
+	}
+
 	get_online_cpus();
 
 	event = perf_event_alloc(&attr, cpu, task, group_leader, NULL,
 				 NULL, NULL);
 	if (IS_ERR(event)) {
 		err = PTR_ERR(event);
-		goto err_task;
+		goto err_cpus;
 	}
 
 	if (flags & PERF_FLAG_PID_CGROUP) {
 		err = perf_cgroup_connect(pid, event, &attr, group_leader);
 		if (err) {
 			__free_event(event);
-			goto err_task;
+			goto err_cpus;
+		}
+	}
+
+	if (is_sampling_event(event)) {
+		if (event->pmu->capabilities & PERF_PMU_CAP_NO_INTERRUPT) {
+			err = -ENOTSUPP;
+			goto err_alloc;
 		}
 	}
 
@@ -7246,8 +7290,9 @@ err_context:
 	put_ctx(ctx);
 err_alloc:
 	free_event(event);
-err_task:
+err_cpus:
 	put_online_cpus();
+err_task:
 	if (task)
 		put_task_struct(task);
 err_group_fd:
@@ -7383,7 +7428,7 @@ __perf_event_exit_task(struct perf_event *child_event,
 			 struct perf_event_context *child_ctx,
 			 struct task_struct *child)
 {
-	perf_remove_from_context(child_event, !!child_event->parent);
+	perf_remove_from_context(child_event, true);
 
 	/*
 	 * It can happen that the parent exits first, and has events
@@ -7398,7 +7443,7 @@ __perf_event_exit_task(struct perf_event *child_event,
 
 static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 {
-	struct perf_event *child_event, *tmp;
+	struct perf_event *child_event, *next;
 	struct perf_event_context *child_ctx;
 	unsigned long flags;
 
@@ -7452,24 +7497,9 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	 */
 	mutex_lock(&child_ctx->mutex);
 
-again:
-	list_for_each_entry_safe(child_event, tmp, &child_ctx->pinned_groups,
-				 group_entry)
-		__perf_event_exit_task(child_event, child_ctx, child);
-
-	list_for_each_entry_safe(child_event, tmp, &child_ctx->flexible_groups,
-				 group_entry)
+	list_for_each_entry_safe(child_event, next, &child_ctx->event_list, event_entry)
 		__perf_event_exit_task(child_event, child_ctx, child);
 
-	/*
-	 * If the last event was a group event, it will have appended all
-	 * its siblings to the list, but we obtained 'tmp' before that which
-	 * will still point to the list head terminating the iteration.
-	 */
-	if (!list_empty(&child_ctx->pinned_groups) ||
-	    !list_empty(&child_ctx->flexible_groups))
-		goto again;
-
 	mutex_unlock(&child_ctx->mutex);
 
 	put_ctx(child_ctx);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 04709b66369d..6bfb6717f878 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -36,6 +36,7 @@
 #include "../../mm/internal.h"	/* munlock_vma_page */
 #include <linux/percpu-rwsem.h>
 #include <linux/task_work.h>
+#include <linux/shmem_fs.h>
 
 #include <linux/uprobes.h>
 
@@ -60,8 +61,6 @@ static struct percpu_rw_semaphore dup_mmap_sem;
 
 /* Have a copy of original instruction */
 #define UPROBE_COPY_INSN	0
-/* Can skip singlestep */
-#define UPROBE_SKIP_SSTEP	1
 
 struct uprobe {
 	struct rb_node		rb_node;	/* node in the rb tree */
@@ -129,7 +128,7 @@ 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;
@@ -281,18 +280,13 @@ 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,
@@ -312,21 +306,25 @@ 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);
@@ -491,12 +489,9 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset)
 	uprobe->offset = offset;
 	init_rwsem(&uprobe->register_rwsem);
 	init_rwsem(&uprobe->consumer_rwsem);
-	/* For now assume that the instruction need not be single-stepped */
-	__set_bit(UPROBE_SKIP_SSTEP, &uprobe->flags);
 
 	/* add to uprobes_tree, sorted on inode:offset */
 	cur_uprobe = insert_uprobe(uprobe);
-
 	/* a uprobe exists for this inode:offset combination */
 	if (cur_uprobe) {
 		kfree(uprobe);
@@ -542,14 +537,15 @@ static int __copy_insn(struct address_space *mapping, struct file *filp,
 			void *insn, int nbytes, loff_t offset)
 {
 	struct page *page;
-
-	if (!mapping->a_ops->readpage)
-		return -EIO;
 	/*
-	 * Ensure that the page that has the original instruction is
-	 * populated and in page-cache.
+	 * Ensure that the page that has the original instruction is populated
+	 * and in page-cache. If ->readpage == NULL it must be shmem_mapping(),
+	 * see uprobe_register().
 	 */
-	page = read_mapping_page(mapping, offset >> PAGE_CACHE_SHIFT, filp);
+	if (mapping->a_ops->readpage)
+		page = read_mapping_page(mapping, offset >> PAGE_CACHE_SHIFT, filp);
+	else
+		page = shmem_read_mapping_page(mapping, offset >> PAGE_CACHE_SHIFT);
 	if (IS_ERR(page))
 		return PTR_ERR(page);
 
@@ -885,6 +881,9 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *
 	if (!uc->handler && !uc->ret_handler)
 		return -EINVAL;
 
+	/* copy_insn() uses read_mapping_page() or shmem_read_mapping_page() */
+	if (!inode->i_mapping->a_ops->readpage && !shmem_mapping(inode->i_mapping))
+		return -EIO;
 	/* Racy, just to catch the obvious mistakes */
 	if (offset > i_size_read(inode))
 		return -EINVAL;
@@ -1357,6 +1356,16 @@ 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.
@@ -1628,20 +1637,6 @@ bool uprobe_deny_signal(void)
 	return true;
 }
 
-/*
- * Avoid singlestepping the original instruction if the original instruction
- * is a NOP or can be emulated.
- */
-static bool can_skip_sstep(struct uprobe *uprobe, struct pt_regs *regs)
-{
-	if (test_bit(UPROBE_SKIP_SSTEP, &uprobe->flags)) {
-		if (arch_uprobe_skip_sstep(&uprobe->arch, regs))
-			return true;
-		clear_bit(UPROBE_SKIP_SSTEP, &uprobe->flags);
-	}
-	return false;
-}
-
 static void mmf_recalc_uprobes(struct mm_struct *mm)
 {
 	struct vm_area_struct *vma;
@@ -1868,13 +1863,13 @@ static void handle_swbp(struct pt_regs *regs)
 
 	handler_chain(uprobe, regs);
 
-	if (can_skip_sstep(uprobe, regs))
+	if (arch_uprobe_skip_sstep(&uprobe->arch, regs))
 		goto out;
 
 	if (!pre_ssout(uprobe, regs, bp_vaddr))
 		return;
 
-	/* can_skip_sstep() succeeded, or restart if can't singlestep */
+	/* arch_uprobe_skip_sstep() succeeded, or restart if can't singlestep */
 out:
 	put_uprobe(uprobe);
 }
@@ -1886,10 +1881,11 @@ out:
 static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs)
 {
 	struct uprobe *uprobe;
+	int err = 0;
 
 	uprobe = utask->active_uprobe;
 	if (utask->state == UTASK_SSTEP_ACK)
-		arch_uprobe_post_xol(&uprobe->arch, regs);
+		err = arch_uprobe_post_xol(&uprobe->arch, regs);
 	else if (utask->state == UTASK_SSTEP_TRAPPED)
 		arch_uprobe_abort_xol(&uprobe->arch, regs);
 	else
@@ -1903,6 +1899,11 @@ static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs)
 	spin_lock_irq(&current->sighand->siglock);
 	recalc_sigpending(); /* see uprobe_deny_signal() */
 	spin_unlock_irq(&current->sighand->siglock);
+
+	if (unlikely(err)) {
+		uprobe_warn(current, "execute the probed insn, sending SIGILL.");
+		force_sig_info(SIGILL, SEND_SIG_FORCED, current);
+	}
 }
 
 /*