Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf events changes from Ingo Molnar:

 "- kernel side:

   - Intel uncore PMU support for Nehalem and Sandy Bridge CPUs, we
     support both the events available via the MSR and via the PCI
     access space.

   - various uprobes cleanups and restructurings

   - PMU driver quirks by microcode version and required x86 microcode
     loader cleanups/robustization

   - various tracing robustness updates

   - static keys: remove obsolete static_branch()

  - tooling side:

   - GTK browser improvements

   - perf report browser: support screenshots to file

   - more automated tests

   - perf kvm improvements

   - perf bench refinements

   - build environment improvements

   - pipe mode improvements

   - libtraceevent updates, we have now hopefully merged most bits with
     the out of tree forked code base

  ... and many other goodies."

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (138 commits)
  tracing: Check for allocation failure in __tracing_open()
  perf/x86: Fix intel_perfmon_event_mapformatting
  jump label: Remove static_branch()
  tracepoint: Use static_key_false(), since static_branch() is deprecated
  perf/x86: Uncore filter support for SandyBridge-EP
  perf/x86: Detect number of instances of uncore CBox
  perf/x86: Fix event constraint for SandyBridge-EP C-Box
  perf/x86: Use 0xff as pseudo code for fixed uncore event
  perf/x86: Save a few bytes in 'struct x86_pmu'
  perf/x86: Add a microcode revision check for SNB-PEBS
  perf/x86: Improve debug output in check_hw_exists()
  perf/x86/amd: Unify AMD's generic and family 15h pmus
  perf/x86: Move Intel specific code to intel_pmu_init()
  perf/x86: Rename Intel specific macros
  perf/x86: Fix USER/KERNEL tagging of samples
  perf tools: Split event symbols arrays to hw and sw parts
  perf tools: Split out PE_VALUE_SYM parsing token to SW and HW tokens
  perf tools: Add empty rule for new line in event syntax parsing
  perf test: Use ARRAY_SIZE in parse events tests
  tools lib traceevent: Cleanup realloc use
  ...

8 files changed, 313 insertions, 254 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index d7d71d6ec972..f1cf0edeb39a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1645,6 +1645,8 @@ perf_install_in_context(struct perf_event_context *ctx,
         lockdep_assert_held(&ctx->mutex);
 
         event->ctx = ctx;
+        if (event->cpu != -1)
+                event->cpu = cpu;
 
         if (!task) {
                 /*
@@ -6252,6 +6254,8 @@ SYSCALL_DEFINE5(perf_event_open,
                 }
         }
 
+        get_online_cpus();
+
         event = perf_event_alloc(&attr, cpu, task, group_leader, NULL,
                                  NULL, NULL);
         if (IS_ERR(event)) {
@@ -6304,7 +6308,7 @@ SYSCALL_DEFINE5(perf_event_open,
         /*
          * Get the target context (task or percpu):
          */
-        ctx = find_get_context(pmu, task, cpu);
+        ctx = find_get_context(pmu, task, event->cpu);
         if (IS_ERR(ctx)) {
                 err = PTR_ERR(ctx);
                 goto err_alloc;
@@ -6377,20 +6381,23 @@ SYSCALL_DEFINE5(perf_event_open,
         mutex_lock(&ctx->mutex);
 
         if (move_group) {
-                perf_install_in_context(ctx, group_leader, cpu);
+                synchronize_rcu();
+                perf_install_in_context(ctx, group_leader, event->cpu);
                 get_ctx(ctx);
                 list_for_each_entry(sibling, &group_leader->sibling_list,
                                     group_entry) {
-                        perf_install_in_context(ctx, sibling, cpu);
+                        perf_install_in_context(ctx, sibling, event->cpu);
                         get_ctx(ctx);
                 }
         }
 
-        perf_install_in_context(ctx, event, cpu);
+        perf_install_in_context(ctx, event, event->cpu);
         ++ctx->generation;
         perf_unpin_context(ctx);
         mutex_unlock(&ctx->mutex);
 
+        put_online_cpus();
+
         event->owner = current;
 
         mutex_lock(&current->perf_event_mutex);
@@ -6419,6 +6426,7 @@ err_context:
 err_alloc:
         free_event(event);
 err_task:
+        put_online_cpus();
         if (task)
                 put_task_struct(task);
 err_group_fd:
@@ -6479,6 +6487,39 @@ err:
 }
 EXPORT_SYMBOL_GPL(perf_event_create_kernel_counter);
 
+void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
+{
+        struct perf_event_context *src_ctx;
+        struct perf_event_context *dst_ctx;
+        struct perf_event *event, *tmp;
+        LIST_HEAD(events);
+
+        src_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, src_cpu)->ctx;
+        dst_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, dst_cpu)->ctx;
+
+        mutex_lock(&src_ctx->mutex);
+        list_for_each_entry_safe(event, tmp, &src_ctx->event_list,
+                                 event_entry) {
+                perf_remove_from_context(event);
+                put_ctx(src_ctx);
+                list_add(&event->event_entry, &events);
+        }
+        mutex_unlock(&src_ctx->mutex);
+
+        synchronize_rcu();
+
+        mutex_lock(&dst_ctx->mutex);
+        list_for_each_entry_safe(event, tmp, &events, event_entry) {
+                list_del(&event->event_entry);
+                if (event->state >= PERF_EVENT_STATE_OFF)
+                        event->state = PERF_EVENT_STATE_INACTIVE;
+                perf_install_in_context(dst_ctx, event, dst_cpu);
+                get_ctx(dst_ctx);
+        }
+        mutex_unlock(&dst_ctx->mutex);
+}
+EXPORT_SYMBOL_GPL(perf_pmu_migrate_context);
+
 static void sync_child_event(struct perf_event *child_event,
                                struct task_struct *child)
 {
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 985be4d80fe8..f93532748bca 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -38,13 +38,29 @@
 #define UINSNS_PER_PAGE                 (PAGE_SIZE/UPROBE_XOL_SLOT_BYTES)
 #define MAX_UPROBE_XOL_SLOTS            UINSNS_PER_PAGE
 
-static struct srcu_struct uprobes_srcu;
 static struct rb_root uprobes_tree = RB_ROOT;
 
 static DEFINE_SPINLOCK(uprobes_treelock);       /* serialize rbtree access */
 
 #define UPROBES_HASH_SZ 13
 
+/*
+ * We need separate register/unregister and mmap/munmap lock hashes because
+ * of mmap_sem nesting.
+ *
+ * uprobe_register() needs to install probes on (potentially) all processes
+ * and thus needs to acquire multiple mmap_sems (consequtively, not
+ * concurrently), whereas uprobe_mmap() is called while holding mmap_sem
+ * for the particular process doing the mmap.
+ *
+ * uprobe_register()->register_for_each_vma() needs to drop/acquire mmap_sem
+ * because of lock order against i_mmap_mutex. This means there's a hole in
+ * the register vma iteration where a mmap() can happen.
+ *
+ * Thus uprobe_register() can race with uprobe_mmap() and we can try and
+ * install a probe where one is already installed.
+ */
+
 /* serialize (un)register */
 static struct mutex uprobes_mutex[UPROBES_HASH_SZ];
 
@@ -61,17 +77,6 @@ static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ];
  */
 static atomic_t uprobe_events = ATOMIC_INIT(0);
 
-/*
- * Maintain a temporary per vma info that can be used to search if a vma
- * has already been handled. This structure is introduced since extending
- * vm_area_struct wasnt recommended.
- */
-struct vma_info {
-        struct list_head        probe_list;
-        struct mm_struct        *mm;
-        loff_t                  vaddr;
-};
-
 struct uprobe {
         struct rb_node          rb_node;        /* node in the rb tree */
         atomic_t                ref;
@@ -100,7 +105,8 @@ static bool valid_vma(struct vm_area_struct *vma, bool is_register)
         if (!is_register)
                 return true;
 
-        if ((vma->vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)) == (VM_READ|VM_EXEC))
+        if ((vma->vm_flags & (VM_HUGETLB|VM_READ|VM_WRITE|VM_EXEC|VM_SHARED))
+                                == (VM_READ|VM_EXEC))
                 return true;
 
         return false;
@@ -129,33 +135,17 @@ static loff_t vma_address(struct vm_area_struct *vma, loff_t offset)
 static int __replace_page(struct vm_area_struct *vma, struct page *page, struct page *kpage)
 {
         struct mm_struct *mm = vma->vm_mm;
-        pgd_t *pgd;
-        pud_t *pud;
-        pmd_t *pmd;
-        pte_t *ptep;
-        spinlock_t *ptl;
         unsigned long addr;
-        int err = -EFAULT;
+        spinlock_t *ptl;
+        pte_t *ptep;
 
         addr = page_address_in_vma(page, vma);
         if (addr == -EFAULT)
-                goto out;
-
-        pgd = pgd_offset(mm, addr);
-        if (!pgd_present(*pgd))
-                goto out;
-
-        pud = pud_offset(pgd, addr);
-        if (!pud_present(*pud))
-                goto out;
-
-        pmd = pmd_offset(pud, addr);
-        if (!pmd_present(*pmd))
-                goto out;
+                return -EFAULT;
 
-        ptep = pte_offset_map_lock(mm, pmd, addr, &ptl);
+        ptep = page_check_address(page, mm, addr, &ptl, 0);
         if (!ptep)
-                goto out;
+                return -EAGAIN;
 
         get_page(kpage);
         page_add_new_anon_rmap(kpage, vma, addr);
@@ -174,10 +164,8 @@ static int __replace_page(struct vm_area_struct *vma, struct page *page, struct
                 try_to_free_swap(page);
         put_page(page);
         pte_unmap_unlock(ptep, ptl);
-        err = 0;
 
-out:
-        return err;
+        return 0;
 }
 
 /**
@@ -222,9 +210,8 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
         void *vaddr_old, *vaddr_new;
         struct vm_area_struct *vma;
         struct uprobe *uprobe;
-        loff_t addr;
         int ret;
-
+retry:
         /* Read the page with vaddr into memory */
         ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &old_page, &vma);
         if (ret <= 0)
@@ -246,10 +233,6 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
         if (mapping != vma->vm_file->f_mapping)
                 goto put_out;
 
-        addr = vma_address(vma, uprobe->offset);
-        if (vaddr != (unsigned long)addr)
-                goto put_out;
-
         ret = -ENOMEM;
         new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
         if (!new_page)
@@ -267,11 +250,7 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
         vaddr_new = kmap_atomic(new_page);
 
         memcpy(vaddr_new, vaddr_old, PAGE_SIZE);
-
-        /* poke the new insn in, ASSUMES we don't cross page boundary */
-        vaddr &= ~PAGE_MASK;
-        BUG_ON(vaddr + UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
-        memcpy(vaddr_new + vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
+        memcpy(vaddr_new + (vaddr & ~PAGE_MASK), &opcode, UPROBE_SWBP_INSN_SIZE);
 
         kunmap_atomic(vaddr_new);
         kunmap_atomic(vaddr_old);
@@ -291,6 +270,8 @@ unlock_out:
 put_out:
         put_page(old_page);
 
+        if (unlikely(ret == -EAGAIN))
+                goto retry;
         return ret;
 }
 
@@ -312,7 +293,7 @@ static int read_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_
         void *vaddr_new;
         int ret;
 
-        ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &page, NULL);
+        ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &page, NULL);
         if (ret <= 0)
                 return ret;
 
@@ -333,10 +314,20 @@ static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr)
         uprobe_opcode_t opcode;
         int result;
 
+        if (current->mm == mm) {
+                pagefault_disable();
+                result = __copy_from_user_inatomic(&opcode, (void __user*)vaddr,
+                                                                sizeof(opcode));
+                pagefault_enable();
+
+                if (likely(result == 0))
+                        goto out;
+        }
+
         result = read_opcode(mm, vaddr, &opcode);
         if (result)
                 return result;
-
+out:
         if (is_swbp_insn(&opcode))
                 return 1;
 
@@ -355,7 +346,9 @@ static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr)
 int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
 {
         int result;
-
+        /*
+         * See the comment near uprobes_hash().
+         */
         result = is_swbp_at_addr(mm, vaddr);
         if (result == 1)
                 return -EEXIST;
@@ -520,7 +513,6 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset)
         uprobe->inode = igrab(inode);
         uprobe->offset = offset;
         init_rwsem(&uprobe->consumer_rwsem);
-        INIT_LIST_HEAD(&uprobe->pending_list);
 
         /* add to uprobes_tree, sorted on inode:offset */
         cur_uprobe = insert_uprobe(uprobe);
@@ -588,20 +580,22 @@ static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *uc)
 }
 
 static int
-__copy_insn(struct address_space *mapping, struct vm_area_struct *vma, char *insn,
-                        unsigned long nbytes, unsigned long offset)
+__copy_insn(struct address_space *mapping, struct file *filp, char *insn,
+                        unsigned long nbytes, loff_t offset)
 {
-        struct file *filp = vma->vm_file;
         struct page *page;
         void *vaddr;
-        unsigned long off1;
-        unsigned long idx;
+        unsigned long off;
+        pgoff_t idx;
 
         if (!filp)
                 return -EINVAL;
 
-        idx = (unsigned long)(offset >> PAGE_CACHE_SHIFT);
-        off1 = offset &= ~PAGE_MASK;
+        if (!mapping->a_ops->readpage)
+                return -EIO;
+
+        idx = offset >> PAGE_CACHE_SHIFT;
+        off = offset & ~PAGE_MASK;
 
         /*
          * Ensure that the page that has the original instruction is
@@ -612,22 +606,20 @@ __copy_insn(struct address_space *mapping, struct vm_area_struct *vma, char *ins
                 return PTR_ERR(page);
 
         vaddr = kmap_atomic(page);
-        memcpy(insn, vaddr + off1, nbytes);
+        memcpy(insn, vaddr + off, nbytes);
         kunmap_atomic(vaddr);
         page_cache_release(page);
 
         return 0;
 }
 
-static int
-copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr)
+static int copy_insn(struct uprobe *uprobe, struct file *filp)
 {
         struct address_space *mapping;
         unsigned long nbytes;
         int bytes;
 
-        addr &= ~PAGE_MASK;
-        nbytes = PAGE_SIZE - addr;
+        nbytes = PAGE_SIZE - (uprobe->offset & ~PAGE_MASK);
         mapping = uprobe->inode->i_mapping;
 
         /* Instruction at end of binary; copy only available bytes */
@@ -638,13 +630,13 @@ copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr)
 
         /* Instruction at the page-boundary; copy bytes in second page */
         if (nbytes < bytes) {
-                if (__copy_insn(mapping, vma, uprobe->arch.insn + nbytes,
-                                bytes - nbytes, uprobe->offset + nbytes))
-                        return -ENOMEM;
-
+                int err = __copy_insn(mapping, filp, uprobe->arch.insn + nbytes,
+                                bytes - nbytes, uprobe->offset + nbytes);
+                if (err)
+                        return err;
                 bytes = nbytes;
         }
-        return __copy_insn(mapping, vma, uprobe->arch.insn, bytes, uprobe->offset);
+        return __copy_insn(mapping, filp, uprobe->arch.insn, bytes, uprobe->offset);
 }
 
 /*
@@ -672,9 +664,8 @@ copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr)
  */
 static int
 install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
-                        struct vm_area_struct *vma, loff_t vaddr)
+                        struct vm_area_struct *vma, unsigned long vaddr)
 {
-        unsigned long addr;
         int ret;
 
         /*
@@ -687,20 +678,22 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
         if (!uprobe->consumers)
                 return -EEXIST;
 
-        addr = (unsigned long)vaddr;
-
         if (!(uprobe->flags & UPROBE_COPY_INSN)) {
-                ret = copy_insn(uprobe, vma, addr);
+                ret = copy_insn(uprobe, vma->vm_file);
                 if (ret)
                         return ret;
 
                 if (is_swbp_insn((uprobe_opcode_t *)uprobe->arch.insn))
-                        return -EEXIST;
+                        return -ENOTSUPP;
 
-                ret = arch_uprobe_analyze_insn(&uprobe->arch, mm);
+                ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr);
                 if (ret)
                         return ret;
 
+                /* write_opcode() assumes we don't cross page boundary */
+                BUG_ON((uprobe->offset & ~PAGE_MASK) +
+                                UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
+
                 uprobe->flags |= UPROBE_COPY_INSN;
         }
 
@@ -713,7 +706,7 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
          * Hence increment before and decrement on failure.
          */
         atomic_inc(&mm->uprobes_state.count);
-        ret = set_swbp(&uprobe->arch, mm, addr);
+        ret = set_swbp(&uprobe->arch, mm, vaddr);
         if (ret)
                 atomic_dec(&mm->uprobes_state.count);
 
@@ -721,27 +714,21 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 }
 
 static void
-remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, loff_t vaddr)
+remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)
 {
-        if (!set_orig_insn(&uprobe->arch, mm, (unsigned long)vaddr, true))
+        if (!set_orig_insn(&uprobe->arch, mm, vaddr, true))
                 atomic_dec(&mm->uprobes_state.count);
 }
 
 /*
- * There could be threads that have hit the breakpoint and are entering the
- * notifier code and trying to acquire the uprobes_treelock. The thread
- * calling delete_uprobe() that is removing the uprobe from the rb_tree can
- * race with these threads and might acquire the uprobes_treelock compared
- * to some of the breakpoint hit threads. In such a case, the breakpoint
- * hit threads will not find the uprobe. The current unregistering thread
- * waits till all other threads have hit a breakpoint, to acquire the
- * uprobes_treelock before the uprobe is removed from the rbtree.
+ * There could be threads that have already hit the breakpoint. They
+ * will recheck the current insn and restart if find_uprobe() fails.
+ * See find_active_uprobe().
  */
 static void delete_uprobe(struct uprobe *uprobe)
 {
         unsigned long flags;
 
-        synchronize_srcu(&uprobes_srcu);
         spin_lock_irqsave(&uprobes_treelock, flags);
         rb_erase(&uprobe->rb_node, &uprobes_tree);
         spin_unlock_irqrestore(&uprobes_treelock, flags);
@@ -750,139 +737,135 @@ static void delete_uprobe(struct uprobe *uprobe)
         atomic_dec(&uprobe_events);
 }
 
-static struct vma_info *
-__find_next_vma_info(struct address_space *mapping, struct list_head *head,
-                        struct vma_info *vi, loff_t offset, bool is_register)
+struct map_info {
+        struct map_info *next;
+        struct mm_struct *mm;
+        unsigned long vaddr;
+};
+
+static inline struct map_info *free_map_info(struct map_info *info)
+{
+        struct map_info *next = info->next;
+        kfree(info);
+        return next;
+}
+
+static struct map_info *
+build_map_info(struct address_space *mapping, loff_t offset, bool is_register)
 {
+        unsigned long pgoff = offset >> PAGE_SHIFT;
         struct prio_tree_iter iter;
         struct vm_area_struct *vma;
-        struct vma_info *tmpvi;
-        unsigned long pgoff;
-        int existing_vma;
-        loff_t vaddr;
-
-        pgoff = offset >> PAGE_SHIFT;
+        struct map_info *curr = NULL;
+        struct map_info *prev = NULL;
+        struct map_info *info;
+        int more = 0;
 
+ again:
+        mutex_lock(&mapping->i_mmap_mutex);
         vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
                 if (!valid_vma(vma, is_register))
                         continue;
 
-                existing_vma = 0;
-                vaddr = vma_address(vma, offset);
-
-                list_for_each_entry(tmpvi, head, probe_list) {
-                        if (tmpvi->mm == vma->vm_mm && tmpvi->vaddr == vaddr) {
-                                existing_vma = 1;
-                                break;
-                        }
+                if (!prev && !more) {
+                        /*
+                         * Needs GFP_NOWAIT to avoid i_mmap_mutex recursion through
+                         * reclaim. This is optimistic, no harm done if it fails.
+                         */
+                        prev = kmalloc(sizeof(struct map_info),
+                                        GFP_NOWAIT | __GFP_NOMEMALLOC | __GFP_NOWARN);
+                        if (prev)
+                                prev->next = NULL;
                 }
-
-                /*
-                 * Another vma needs a probe to be installed. However skip
-                 * installing the probe if the vma is about to be unlinked.
-                 */
-                if (!existing_vma && atomic_inc_not_zero(&vma->vm_mm->mm_users)) {
-                        vi->mm = vma->vm_mm;
-                        vi->vaddr = vaddr;
-                        list_add(&vi->probe_list, head);
-
-                        return vi;
+                if (!prev) {
+                        more++;
+                        continue;
                 }
-        }
 
-        return NULL;
-}
-
-/*
- * Iterate in the rmap prio tree  and find a vma where a probe has not
- * yet been inserted.
- */
-static struct vma_info *
-find_next_vma_info(struct address_space *mapping, struct list_head *head,
-                loff_t offset, bool is_register)
-{
-        struct vma_info *vi, *retvi;
+                if (!atomic_inc_not_zero(&vma->vm_mm->mm_users))
+                        continue;
 
-        vi = kzalloc(sizeof(struct vma_info), GFP_KERNEL);
-        if (!vi)
-                return ERR_PTR(-ENOMEM);
+                info = prev;
+                prev = prev->next;
+                info->next = curr;
+                curr = info;
 
-        mutex_lock(&mapping->i_mmap_mutex);
-        retvi = __find_next_vma_info(mapping, head, vi, offset, is_register);
+                info->mm = vma->vm_mm;
+                info->vaddr = vma_address(vma, offset);
+        }
         mutex_unlock(&mapping->i_mmap_mutex);
 
-        if (!retvi)
-                kfree(vi);
+        if (!more)
+                goto out;
+
+        prev = curr;
+        while (curr) {
+                mmput(curr->mm);
+                curr = curr->next;
+        }
 
-        return retvi;
+        do {
+                info = kmalloc(sizeof(struct map_info), GFP_KERNEL);
+                if (!info) {
+                        curr = ERR_PTR(-ENOMEM);
+                        goto out;
+                }
+                info->next = prev;
+                prev = info;
+        } while (--more);
+
+        goto again;
+ out:
+        while (prev)
+                prev = free_map_info(prev);
+        return curr;
 }
 
 static int register_for_each_vma(struct uprobe *uprobe, bool is_register)
 {
-        struct list_head try_list;
-        struct vm_area_struct *vma;
-        struct address_space *mapping;
-        struct vma_info *vi, *tmpvi;
-        struct mm_struct *mm;
-        loff_t vaddr;
-        int ret;
+        struct map_info *info;
+        int err = 0;
 
-        mapping = uprobe->inode->i_mapping;
-        INIT_LIST_HEAD(&try_list);
+        info = build_map_info(uprobe->inode->i_mapping,
+                                        uprobe->offset, is_register);
+        if (IS_ERR(info))
+                return PTR_ERR(info);
 
-        ret = 0;
+        while (info) {
+                struct mm_struct *mm = info->mm;
+                struct vm_area_struct *vma;
 
-        for (;;) {
-                vi = find_next_vma_info(mapping, &try_list, uprobe->offset, is_register);
-                if (!vi)
-                        break;
+                if (err)
+                        goto free;
 
-                if (IS_ERR(vi)) {
-                        ret = PTR_ERR(vi);
-                        break;
-                }
+                down_write(&mm->mmap_sem);
+                vma = find_vma(mm, (unsigned long)info->vaddr);
+                if (!vma || !valid_vma(vma, is_register))
+                        goto unlock;
 
-                mm = vi->mm;
-                down_read(&mm->mmap_sem);
-                vma = find_vma(mm, (unsigned long)vi->vaddr);
-                if (!vma || !valid_vma(vma, is_register)) {
-                        list_del(&vi->probe_list);
-                        kfree(vi);
-                        up_read(&mm->mmap_sem);
-                        mmput(mm);
-                        continue;
-                }
-                vaddr = vma_address(vma, uprobe->offset);
                 if (vma->vm_file->f_mapping->host != uprobe->inode ||
-                                                vaddr != vi->vaddr) {
-                        list_del(&vi->probe_list);
-                        kfree(vi);
-                        up_read(&mm->mmap_sem);
-                        mmput(mm);
-                        continue;
-                }
-
-                if (is_register)
-                        ret = install_breakpoint(uprobe, mm, vma, vi->vaddr);
-                else
-                        remove_breakpoint(uprobe, mm, vi->vaddr);
+                    vma_address(vma, uprobe->offset) != info->vaddr)
+                        goto unlock;
 
-                up_read(&mm->mmap_sem);
-                mmput(mm);
                 if (is_register) {
-                        if (ret && ret == -EEXIST)
-                                ret = 0;
-                        if (ret)
-                                break;
+                        err = install_breakpoint(uprobe, mm, vma, info->vaddr);
+                        /*
+                         * We can race against uprobe_mmap(), see the
+                         * comment near uprobe_hash().
+                         */
+                        if (err == -EEXIST)
+                                err = 0;
+                } else {
+                        remove_breakpoint(uprobe, mm, info->vaddr);
                 }
+ unlock:
+                up_write(&mm->mmap_sem);
+ free:
+                mmput(mm);
+                info = free_map_info(info);
         }
 
-        list_for_each_entry_safe(vi, tmpvi, &try_list, probe_list) {
-                list_del(&vi->probe_list);
-                kfree(vi);
-        }
-
-        return ret;
+        return err;
 }
 
 static int __uprobe_register(struct uprobe *uprobe)
@@ -1048,7 +1031,7 @@ static void build_probe_list(struct inode *inode, struct list_head *head)
 int uprobe_mmap(struct vm_area_struct *vma)
 {
         struct list_head tmp_list;
-        struct uprobe *uprobe, *u;
+        struct uprobe *uprobe;
         struct inode *inode;
         int ret, count;
 
@@ -1066,12 +1049,9 @@ int uprobe_mmap(struct vm_area_struct *vma)
         ret = 0;
         count = 0;
 
-        list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) {
-                loff_t vaddr;
-
-                list_del(&uprobe->pending_list);
+        list_for_each_entry(uprobe, &tmp_list, pending_list) {
                 if (!ret) {
-                        vaddr = vma_address(vma, uprobe->offset);
+                        loff_t vaddr = vma_address(vma, uprobe->offset);
 
                         if (vaddr < vma->vm_start || vaddr >= vma->vm_end) {
                                 put_uprobe(uprobe);
@@ -1079,8 +1059,10 @@ int uprobe_mmap(struct vm_area_struct *vma)
                         }
 
                         ret = install_breakpoint(uprobe, vma->vm_mm, vma, vaddr);
-
-                        /* Ignore double add: */
+                        /*
+                         * We can race against uprobe_register(), see the
+                         * comment near uprobe_hash().
+                         */
                         if (ret == -EEXIST) {
                                 ret = 0;
 
@@ -1115,7 +1097,7 @@ int uprobe_mmap(struct vm_area_struct *vma)
 void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end)
 {
         struct list_head tmp_list;
-        struct uprobe *uprobe, *u;
+        struct uprobe *uprobe;
         struct inode *inode;
 
         if (!atomic_read(&uprobe_events) || !valid_vma(vma, false))
@@ -1132,11 +1114,8 @@ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned lon
         mutex_lock(uprobes_mmap_hash(inode));
         build_probe_list(inode, &tmp_list);
 
-        list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) {
-                loff_t vaddr;
-
-                list_del(&uprobe->pending_list);
-                vaddr = vma_address(vma, uprobe->offset);
+        list_for_each_entry(uprobe, &tmp_list, pending_list) {
+                loff_t vaddr = vma_address(vma, uprobe->offset);
 
                 if (vaddr >= start && vaddr < end) {
                         /*
@@ -1378,9 +1357,6 @@ void uprobe_free_utask(struct task_struct *t)
 {
         struct uprobe_task *utask = t->utask;
 
-        if (t->uprobe_srcu_id != -1)
-                srcu_read_unlock_raw(&uprobes_srcu, t->uprobe_srcu_id);
-
         if (!utask)
                 return;
 
@@ -1398,7 +1374,6 @@ void uprobe_free_utask(struct task_struct *t)
 void uprobe_copy_process(struct task_struct *t)
 {
         t->utask = NULL;
-        t->uprobe_srcu_id = -1;
 }
 
 /*
@@ -1417,7 +1392,6 @@ static struct uprobe_task *add_utask(void)
         if (unlikely(!utask))
                 return NULL;
 
-        utask->active_uprobe = NULL;
         current->utask = utask;
         return utask;
 }
@@ -1479,41 +1453,64 @@ static bool can_skip_sstep(struct uprobe *uprobe, struct pt_regs *regs)
         return false;
 }
 
+static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp)
+{
+        struct mm_struct *mm = current->mm;
+        struct uprobe *uprobe = NULL;
+        struct vm_area_struct *vma;
+
+        down_read(&mm->mmap_sem);
+        vma = find_vma(mm, bp_vaddr);
+        if (vma && vma->vm_start <= bp_vaddr) {
+                if (valid_vma(vma, false)) {
+                        struct inode *inode;
+                        loff_t offset;
+
+                        inode = vma->vm_file->f_mapping->host;
+                        offset = bp_vaddr - vma->vm_start;
+                        offset += (vma->vm_pgoff << PAGE_SHIFT);
+                        uprobe = find_uprobe(inode, offset);
+                }
+
+                if (!uprobe)
+                        *is_swbp = is_swbp_at_addr(mm, bp_vaddr);
+        } else {
+                *is_swbp = -EFAULT;
+        }
+        up_read(&mm->mmap_sem);
+
+        return uprobe;
+}
+
 /*
  * Run handler and ask thread to singlestep.
  * Ensure all non-fatal signals cannot interrupt thread while it singlesteps.
  */
 static void handle_swbp(struct pt_regs *regs)
 {
-        struct vm_area_struct *vma;
         struct uprobe_task *utask;
         struct uprobe *uprobe;
-        struct mm_struct *mm;
         unsigned long bp_vaddr;
+        int uninitialized_var(is_swbp);
 
-        uprobe = NULL;
         bp_vaddr = uprobe_get_swbp_addr(regs);
-        mm = current->mm;
-        down_read(&mm->mmap_sem);
-        vma = find_vma(mm, bp_vaddr);
-
-        if (vma && vma->vm_start <= bp_vaddr && valid_vma(vma, false)) {
-                struct inode *inode;
-                loff_t offset;
-
-                inode = vma->vm_file->f_mapping->host;
-                offset = bp_vaddr - vma->vm_start;
-                offset += (vma->vm_pgoff << PAGE_SHIFT);
-                uprobe = find_uprobe(inode, offset);
-        }
-
-        srcu_read_unlock_raw(&uprobes_srcu, current->uprobe_srcu_id);
-        current->uprobe_srcu_id = -1;
-        up_read(&mm->mmap_sem);
+        uprobe = find_active_uprobe(bp_vaddr, &is_swbp);
 
         if (!uprobe) {
-                /* No matching uprobe; signal SIGTRAP. */
-                send_sig(SIGTRAP, current, 0);
+                if (is_swbp > 0) {
+                        /* No matching uprobe; signal SIGTRAP. */
+                        send_sig(SIGTRAP, current, 0);
+                } else {
+                        /*
+                         * Either we raced with uprobe_unregister() or we can't
+                         * access this memory. The latter is only possible if
+                         * another thread plays with our ->mm. In both cases
+                         * we can simply restart. If this vma was unmapped we
+                         * can pretend this insn was not executed yet and get
+                         * the (correct) SIGSEGV after restart.
+                         */
+                        instruction_pointer_set(regs, bp_vaddr);
+                }
                 return;
         }
 
@@ -1620,7 +1617,6 @@ int uprobe_pre_sstep_notifier(struct pt_regs *regs)
                 utask->state = UTASK_BP_HIT;
 
         set_thread_flag(TIF_UPROBE);
-        current->uprobe_srcu_id = srcu_read_lock_raw(&uprobes_srcu);
 
         return 1;
 }
@@ -1655,7 +1651,6 @@ static int __init init_uprobes(void)
                 mutex_init(&uprobes_mutex[i]);
                 mutex_init(&uprobes_mmap_mutex[i]);
         }
-        init_srcu_struct(&uprobes_srcu);
 
         return register_die_notifier(&uprobe_exception_nb);
 }
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index a008663d86c8..b4f20fba09fc 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -312,7 +312,7 @@ static int remove_ftrace_list_ops(struct ftrace_ops **list,
 
 static int __register_ftrace_function(struct ftrace_ops *ops)
 {
-        if (ftrace_disabled)
+        if (unlikely(ftrace_disabled))
                 return -ENODEV;
 
         if (FTRACE_WARN_ON(ops == &global_ops))
@@ -4299,16 +4299,12 @@ int register_ftrace_function(struct ftrace_ops *ops)
 
         mutex_lock(&ftrace_lock);
 
-        if (unlikely(ftrace_disabled))
-                goto out_unlock;
-
         ret = __register_ftrace_function(ops);
         if (!ret)
                 ret = ftrace_startup(ops, 0);
 
-
- out_unlock:
         mutex_unlock(&ftrace_lock);
+
         return ret;
 }
 EXPORT_SYMBOL_GPL(register_ftrace_function);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index f765465bffe4..49491fa7daa2 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3239,6 +3239,10 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
         if (cpu_buffer->commit_page == cpu_buffer->reader_page)
                 goto out;
 
+        /* Don't bother swapping if the ring buffer is empty */
+        if (rb_num_of_entries(cpu_buffer) == 0)
+                goto out;
+
         /*
          * Reset the reader page to size zero.
          */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a7fa0702be1c..a120f98c4112 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -830,6 +830,8 @@ int register_tracer(struct tracer *type)
                 current_trace = saved_tracer;
                 if (ret) {
                         printk(KERN_CONT "FAILED!\n");
+                        /* Add the warning after printing 'FAILED' */
+                        WARN_ON(1);
                         goto out;
                 }
                 /* Only reset on passing, to avoid touching corrupted buffers */
@@ -1708,9 +1710,11 @@ EXPORT_SYMBOL_GPL(trace_vprintk);
 
 static void trace_iterator_increment(struct trace_iterator *iter)
 {
+        struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, iter->cpu);
+
         iter->idx++;
-        if (iter->buffer_iter[iter->cpu])
-                ring_buffer_read(iter->buffer_iter[iter->cpu], NULL);
+        if (buf_iter)
+                ring_buffer_read(buf_iter, NULL);
 }
 
 static struct trace_entry *
@@ -1718,7 +1722,7 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
                 unsigned long *lost_events)
 {
         struct ring_buffer_event *event;
-        struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu];
+        struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, cpu);
 
         if (buf_iter)
                 event = ring_buffer_iter_peek(buf_iter, ts);
@@ -1856,10 +1860,10 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 
         tr->data[cpu]->skipped_entries = 0;
 
-        if (!iter->buffer_iter[cpu])
+        buf_iter = trace_buffer_iter(iter, cpu);
+        if (!buf_iter)
                 return;
 
-        buf_iter = iter->buffer_iter[cpu];
         ring_buffer_iter_reset(buf_iter);
 
         /*
@@ -2205,13 +2209,15 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
 
 int trace_empty(struct trace_iterator *iter)
 {
+        struct ring_buffer_iter *buf_iter;
         int cpu;
 
         /* If we are looking at one CPU buffer, only check that one */
         if (iter->cpu_file != TRACE_PIPE_ALL_CPU) {
                 cpu = iter->cpu_file;
-                if (iter->buffer_iter[cpu]) {
-                        if (!ring_buffer_iter_empty(iter->buffer_iter[cpu]))
+                buf_iter = trace_buffer_iter(iter, cpu);
+                if (buf_iter) {
+                        if (!ring_buffer_iter_empty(buf_iter))
                                 return 0;
                 } else {
                         if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu))
@@ -2221,8 +2227,9 @@ int trace_empty(struct trace_iterator *iter)
         }
 
         for_each_tracing_cpu(cpu) {
-                if (iter->buffer_iter[cpu]) {
-                        if (!ring_buffer_iter_empty(iter->buffer_iter[cpu]))
+                buf_iter = trace_buffer_iter(iter, cpu);
+                if (buf_iter) {
+                        if (!ring_buffer_iter_empty(buf_iter))
                                 return 0;
                 } else {
                         if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu))
@@ -2381,6 +2388,11 @@ __tracing_open(struct inode *inode, struct file *file)
         if (!iter)
                 return ERR_PTR(-ENOMEM);
 
+        iter->buffer_iter = kzalloc(sizeof(*iter->buffer_iter) * num_possible_cpus(),
+                                    GFP_KERNEL);
+        if (!iter->buffer_iter)
+                goto release;
+
         /*
          * We make a copy of the current tracer to avoid concurrent
          * changes on it while we are reading.
@@ -2441,6 +2453,8 @@ __tracing_open(struct inode *inode, struct file *file)
  fail:
         mutex_unlock(&trace_types_lock);
         kfree(iter->trace);
+        kfree(iter->buffer_iter);
+release:
         seq_release_private(inode, file);
         return ERR_PTR(-ENOMEM);
 }
@@ -2481,6 +2495,7 @@ static int tracing_release(struct inode *inode, struct file *file)
         mutex_destroy(&iter->mutex);
         free_cpumask_var(iter->started);
         kfree(iter->trace);
+        kfree(iter->buffer_iter);
         seq_release_private(inode, file);
         return 0;
 }
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 5aec220d2de0..55e1f7f0db12 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -317,6 +317,14 @@ struct tracer {
 
 #define TRACE_PIPE_ALL_CPU      -1
 
+static inline struct ring_buffer_iter *
+trace_buffer_iter(struct trace_iterator *iter, int cpu)
+{
+        if (iter->buffer_iter && iter->buffer_iter[cpu])
+                return iter->buffer_iter[cpu];
+        return NULL;
+}
+
 int tracer_init(struct tracer *t, struct trace_array *tr);
 int tracing_is_enabled(void);
 void trace_wake_up(void);
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index a7d2a4c653d8..ce27c8ba8d31 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -538,7 +538,7 @@ get_return_for_leaf(struct trace_iterator *iter,
                 next = &data->ret;
         } else {
 
-                ring_iter = iter->buffer_iter[iter->cpu];
+                ring_iter = trace_buffer_iter(iter, iter->cpu);
 
                 /* First peek to compare current entry and the next one */
                 if (ring_iter)
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index df611a0e76c5..123b189c732c 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1325,4 +1325,4 @@ __init static int init_events(void)
 
         return 0;
 }
-device_initcall(init_events);
+early_initcall(init_events);