Merge branch 'perf/core' into perf/uprobes

Merge in latest upstream (and the latest perf development tree),
to prepare for tooling changes, and also to pick up v3.4 MM
changes that the uprobes code needs to take care of.

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

1 files changed, 260 insertions, 97 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 7dcd2a25049..2b9a7607cbd 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -209,16 +209,20 @@ static int do_maps_open(struct inode *inode, struct file *file,
 	return ret;
 }
 
-static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
+static void
+show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct file *file = vma->vm_file;
+	struct proc_maps_private *priv = m->private;
+	struct task_struct *task = priv->task;
 	vm_flags_t flags = vma->vm_flags;
 	unsigned long ino = 0;
 	unsigned long long pgoff = 0;
 	unsigned long start, end;
 	dev_t dev = 0;
 	int len;
+	const char *name = NULL;
 
 	if (file) {
 		struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
@@ -252,36 +256,57 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
 	if (file) {
 		pad_len_spaces(m, len);
 		seq_path(m, &file->f_path, "\n");
-	} else {
-		const char *name = arch_vma_name(vma);
-		if (!name) {
-			if (mm) {
-				if (vma->vm_start <= mm->brk &&
-						vma->vm_end >= mm->start_brk) {
-					name = "[heap]";
-				} else if (vma->vm_start <= mm->start_stack &&
-					   vma->vm_end >= mm->start_stack) {
-					name = "[stack]";
-				}
+		goto done;
+	}
+
+	name = arch_vma_name(vma);
+	if (!name) {
+		pid_t tid;
+
+		if (!mm) {
+			name = "[vdso]";
+			goto done;
+		}
+
+		if (vma->vm_start <= mm->brk &&
+		    vma->vm_end >= mm->start_brk) {
+			name = "[heap]";
+			goto done;
+		}
+
+		tid = vm_is_stack(task, vma, is_pid);
+
+		if (tid != 0) {
+			/*
+			 * Thread stack in /proc/PID/task/TID/maps or
+			 * the main process stack.
+			 */
+			if (!is_pid || (vma->vm_start <= mm->start_stack &&
+			    vma->vm_end >= mm->start_stack)) {
+				name = "[stack]";
 			} else {
-				name = "[vdso]";
+				/* Thread stack in /proc/PID/maps */
+				pad_len_spaces(m, len);
+				seq_printf(m, "[stack:%d]", tid);
 			}
 		}
-		if (name) {
-			pad_len_spaces(m, len);
-			seq_puts(m, name);
-		}
+	}
+
+done:
+	if (name) {
+		pad_len_spaces(m, len);
+		seq_puts(m, name);
 	}
 	seq_putc(m, '\n');
 }
 
-static int show_map(struct seq_file *m, void *v)
+static int show_map(struct seq_file *m, void *v, int is_pid)
 {
 	struct vm_area_struct *vma = v;
 	struct proc_maps_private *priv = m->private;
 	struct task_struct *task = priv->task;
 
-	show_map_vma(m, vma);
+	show_map_vma(m, vma, is_pid);
 
 	if (m->count < m->size)  /* vma is copied successfully */
 		m->version = (vma != get_gate_vma(task->mm))
@@ -289,20 +314,49 @@ static int show_map(struct seq_file *m, void *v)
 	return 0;
 }
 
+static int show_pid_map(struct seq_file *m, void *v)
+{
+	return show_map(m, v, 1);
+}
+
+static int show_tid_map(struct seq_file *m, void *v)
+{
+	return show_map(m, v, 0);
+}
+
 static const struct seq_operations proc_pid_maps_op = {
 	.start	= m_start,
 	.next	= m_next,
 	.stop	= m_stop,
-	.show	= show_map
+	.show	= show_pid_map
 };
 
-static int maps_open(struct inode *inode, struct file *file)
+static const struct seq_operations proc_tid_maps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_tid_map
+};
+
+static int pid_maps_open(struct inode *inode, struct file *file)
 {
 	return do_maps_open(inode, file, &proc_pid_maps_op);
 }
 
-const struct file_operations proc_maps_operations = {
-	.open		= maps_open,
+static int tid_maps_open(struct inode *inode, struct file *file)
+{
+	return do_maps_open(inode, file, &proc_tid_maps_op);
+}
+
+const struct file_operations proc_pid_maps_operations = {
+	.open		= pid_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+const struct file_operations proc_tid_maps_operations = {
+	.open		= tid_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,
@@ -394,21 +448,15 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	spin_lock(&walk->mm->page_table_lock);
-	if (pmd_trans_huge(*pmd)) {
-		if (pmd_trans_splitting(*pmd)) {
-			spin_unlock(&walk->mm->page_table_lock);
-			wait_split_huge_page(vma->anon_vma, pmd);
-		} else {
-			smaps_pte_entry(*(pte_t *)pmd, addr,
-					HPAGE_PMD_SIZE, walk);
-			spin_unlock(&walk->mm->page_table_lock);
-			mss->anonymous_thp += HPAGE_PMD_SIZE;
-			return 0;
-		}
-	} else {
+	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+		smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk);
 		spin_unlock(&walk->mm->page_table_lock);
+		mss->anonymous_thp += HPAGE_PMD_SIZE;
+		return 0;
 	}
+
+	if (pmd_trans_unstable(pmd))
+		return 0;
 	/*
 	 * The mmap_sem held all the way back in m_start() is what
 	 * keeps khugepaged out of here and from collapsing things
@@ -422,7 +470,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	return 0;
 }
 
-static int show_smap(struct seq_file *m, void *v)
+static int show_smap(struct seq_file *m, void *v, int is_pid)
 {
 	struct proc_maps_private *priv = m->private;
 	struct task_struct *task = priv->task;
@@ -440,7 +488,7 @@ static int show_smap(struct seq_file *m, void *v)
 	if (vma->vm_mm && !is_vm_hugetlb_page(vma))
 		walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk);
 
-	show_map_vma(m, vma);
+	show_map_vma(m, vma, is_pid);
 
 	seq_printf(m,
 		   "Size:           %8lu kB\n"
@@ -479,20 +527,49 @@ static int show_smap(struct seq_file *m, void *v)
 	return 0;
 }
 
+static int show_pid_smap(struct seq_file *m, void *v)
+{
+	return show_smap(m, v, 1);
+}
+
+static int show_tid_smap(struct seq_file *m, void *v)
+{
+	return show_smap(m, v, 0);
+}
+
 static const struct seq_operations proc_pid_smaps_op = {
 	.start	= m_start,
 	.next	= m_next,
 	.stop	= m_stop,
-	.show	= show_smap
+	.show	= show_pid_smap
+};
+
+static const struct seq_operations proc_tid_smaps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_tid_smap
 };
 
-static int smaps_open(struct inode *inode, struct file *file)
+static int pid_smaps_open(struct inode *inode, struct file *file)
 {
 	return do_maps_open(inode, file, &proc_pid_smaps_op);
 }
 
-const struct file_operations proc_smaps_operations = {
-	.open		= smaps_open,
+static int tid_smaps_open(struct inode *inode, struct file *file)
+{
+	return do_maps_open(inode, file, &proc_tid_smaps_op);
+}
+
+const struct file_operations proc_pid_smaps_operations = {
+	.open		= pid_smaps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+const struct file_operations proc_tid_smaps_operations = {
+	.open		= tid_smaps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,
@@ -507,6 +584,8 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	struct page *page;
 
 	split_huge_page_pmd(walk->mm, pmd);
+	if (pmd_trans_unstable(pmd))
+		return 0;
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
@@ -598,11 +677,18 @@ const struct file_operations proc_clear_refs_operations = {
 	.llseek		= noop_llseek,
 };
 
+typedef struct {
+	u64 pme;
+} pagemap_entry_t;
+
 struct pagemapread {
 	int pos, len;
-	u64 *buffer;
+	pagemap_entry_t *buffer;
 };
 
+#define PAGEMAP_WALK_SIZE	(PMD_SIZE)
+#define PAGEMAP_WALK_MASK	(PMD_MASK)
+
 #define PM_ENTRY_BYTES      sizeof(u64)
 #define PM_STATUS_BITS      3
 #define PM_STATUS_OFFSET    (64 - PM_STATUS_BITS)
@@ -620,10 +706,15 @@ struct pagemapread {
 #define PM_NOT_PRESENT      PM_PSHIFT(PAGE_SHIFT)
 #define PM_END_OF_BUFFER    1
 
-static int add_to_pagemap(unsigned long addr, u64 pfn,
+static inline pagemap_entry_t make_pme(u64 val)
+{
+	return (pagemap_entry_t) { .pme = val };
+}
+
+static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme,
 			  struct pagemapread *pm)
 {
-	pm->buffer[pm->pos++] = pfn;
+	pm->buffer[pm->pos++] = *pme;
 	if (pm->pos >= pm->len)
 		return PM_END_OF_BUFFER;
 	return 0;
@@ -635,8 +726,10 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
 	struct pagemapread *pm = walk->private;
 	unsigned long addr;
 	int err = 0;
+	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
+
 	for (addr = start; addr < end; addr += PAGE_SIZE) {
-		err = add_to_pagemap(addr, PM_NOT_PRESENT, pm);
+		err = add_to_pagemap(addr, &pme, pm);
 		if (err)
 			break;
 	}
@@ -649,17 +742,35 @@ static u64 swap_pte_to_pagemap_entry(pte_t pte)
 	return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT);
 }
 
-static u64 pte_to_pagemap_entry(pte_t pte)
+static void pte_to_pagemap_entry(pagemap_entry_t *pme, pte_t pte)
 {
-	u64 pme = 0;
 	if (is_swap_pte(pte))
-		pme = PM_PFRAME(swap_pte_to_pagemap_entry(pte))
-			| PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
+		*pme = make_pme(PM_PFRAME(swap_pte_to_pagemap_entry(pte))
+				| PM_PSHIFT(PAGE_SHIFT) | PM_SWAP);
 	else if (pte_present(pte))
-		pme = PM_PFRAME(pte_pfn(pte))
-			| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
-	return pme;
+		*pme = make_pme(PM_PFRAME(pte_pfn(pte))
+				| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme,
+					pmd_t pmd, int offset)
+{
+	/*
+	 * Currently pmd for thp is always present because thp can not be
+	 * swapped-out, migrated, or HWPOISONed (split in such cases instead.)
+	 * This if-check is just to prepare for future implementation.
+	 */
+	if (pmd_present(pmd))
+		*pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset)
+				| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
 }
+#else
+static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme,
+						pmd_t pmd, int offset)
+{
+}
+#endif
 
 static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			     struct mm_walk *walk)
@@ -668,13 +779,28 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	struct pagemapread *pm = walk->private;
 	pte_t *pte;
 	int err = 0;
-
-	split_huge_page_pmd(walk->mm, pmd);
+	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
 
 	/* find the first VMA at or above 'addr' */
 	vma = find_vma(walk->mm, addr);
+	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+		for (; addr != end; addr += PAGE_SIZE) {
+			unsigned long offset;
+
+			offset = (addr & ~PAGEMAP_WALK_MASK) >>
+					PAGE_SHIFT;
+			thp_pmd_to_pagemap_entry(&pme, *pmd, offset);
+			err = add_to_pagemap(addr, &pme, pm);
+			if (err)
+				break;
+		}
+		spin_unlock(&walk->mm->page_table_lock);
+		return err;
+	}
+
+	if (pmd_trans_unstable(pmd))
+		return 0;
 	for (; addr != end; addr += PAGE_SIZE) {
-		u64 pfn = PM_NOT_PRESENT;
 
 		/* check to see if we've left 'vma' behind
 		 * and need a new, higher one */
@@ -686,11 +812,11 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		if (vma && (vma->vm_start <= addr) &&
 		    !is_vm_hugetlb_page(vma)) {
 			pte = pte_offset_map(pmd, addr);
-			pfn = pte_to_pagemap_entry(*pte);
+			pte_to_pagemap_entry(&pme, *pte);
 			/* unmap before userspace copy */
 			pte_unmap(pte);
 		}
-		err = add_to_pagemap(addr, pfn, pm);
+		err = add_to_pagemap(addr, &pme, pm);
 		if (err)
 			return err;
 	}
@@ -701,13 +827,12 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
-static u64 huge_pte_to_pagemap_entry(pte_t pte, int offset)
+static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme,
+					pte_t pte, int offset)
 {
-	u64 pme = 0;
 	if (pte_present(pte))
-		pme = PM_PFRAME(pte_pfn(pte) + offset)
-			| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
-	return pme;
+		*pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset)
+				| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
 }
 
 /* This function walks within one hugetlb entry in the single call */
@@ -717,12 +842,12 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
 {
 	struct pagemapread *pm = walk->private;
 	int err = 0;
-	u64 pfn;
+	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
 
 	for (; addr != end; addr += PAGE_SIZE) {
 		int offset = (addr & ~hmask) >> PAGE_SHIFT;
-		pfn = huge_pte_to_pagemap_entry(*pte, offset);
-		err = add_to_pagemap(addr, pfn, pm);
+		huge_pte_to_pagemap_entry(&pme, *pte, offset);
+		err = add_to_pagemap(addr, &pme, pm);
 		if (err)
 			return err;
 	}
@@ -757,8 +882,6 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
  * determine which areas of memory are actually mapped and llseek to
  * skip over unmapped regions.
  */
-#define PAGEMAP_WALK_SIZE	(PMD_SIZE)
-#define PAGEMAP_WALK_MASK	(PMD_MASK)
 static ssize_t pagemap_read(struct file *file, char __user *buf,
 			    size_t count, loff_t *ppos)
 {
@@ -941,26 +1064,21 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 	pte_t *pte;
 
 	md = walk->private;
-	spin_lock(&walk->mm->page_table_lock);
-	if (pmd_trans_huge(*pmd)) {
-		if (pmd_trans_splitting(*pmd)) {
-			spin_unlock(&walk->mm->page_table_lock);
-			wait_split_huge_page(md->vma->anon_vma, pmd);
-		} else {
-			pte_t huge_pte = *(pte_t *)pmd;
-			struct page *page;
-
-			page = can_gather_numa_stats(huge_pte, md->vma, addr);
-			if (page)
-				gather_stats(page, md, pte_dirty(huge_pte),
-						HPAGE_PMD_SIZE/PAGE_SIZE);
-			spin_unlock(&walk->mm->page_table_lock);
-			return 0;
-		}
-	} else {
+
+	if (pmd_trans_huge_lock(pmd, md->vma) == 1) {
+		pte_t huge_pte = *(pte_t *)pmd;
+		struct page *page;
+
+		page = can_gather_numa_stats(huge_pte, md->vma, addr);
+		if (page)
+			gather_stats(page, md, pte_dirty(huge_pte),
+				     HPAGE_PMD_SIZE/PAGE_SIZE);
 		spin_unlock(&walk->mm->page_table_lock);
+		return 0;
 	}
 
+	if (pmd_trans_unstable(pmd))
+		return 0;
 	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	do {
 		struct page *page = can_gather_numa_stats(*pte, md->vma, addr);
@@ -1002,7 +1120,7 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
 /*
  * Display pages allocated per node and memory policy via /proc.
  */
-static int show_numa_map(struct seq_file *m, void *v)
+static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 {
 	struct numa_maps_private *numa_priv = m->private;
 	struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
@@ -1039,9 +1157,19 @@ static int show_numa_map(struct seq_file *m, void *v)
 		seq_path(m, &file->f_path, "\n\t= ");
 	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
 		seq_printf(m, " heap");
-	} else if (vma->vm_start <= mm->start_stack &&
-			vma->vm_end >= mm->start_stack) {
-		seq_printf(m, " stack");
+	} else {
+		pid_t tid = vm_is_stack(proc_priv->task, vma, is_pid);
+		if (tid != 0) {
+			/*
+			 * Thread stack in /proc/PID/task/TID/maps or
+			 * the main process stack.
+			 */
+			if (!is_pid || (vma->vm_start <= mm->start_stack &&
+			    vma->vm_end >= mm->start_stack))
+				seq_printf(m, " stack");
+			else
+				seq_printf(m, " stack:%d", tid);
+		}
 	}
 
 	if (is_vm_hugetlb_page(vma))
@@ -1084,21 +1212,39 @@ out:
 	return 0;
 }
 
+static int show_pid_numa_map(struct seq_file *m, void *v)
+{
+	return show_numa_map(m, v, 1);
+}
+
+static int show_tid_numa_map(struct seq_file *m, void *v)
+{
+	return show_numa_map(m, v, 0);
+}
+
 static const struct seq_operations proc_pid_numa_maps_op = {
-        .start  = m_start,
-        .next   = m_next,
-        .stop   = m_stop,
-        .show   = show_numa_map,
+	.start  = m_start,
+	.next   = m_next,
+	.stop   = m_stop,
+	.show   = show_pid_numa_map,
 };
 
-static int numa_maps_open(struct inode *inode, struct file *file)
+static const struct seq_operations proc_tid_numa_maps_op = {
+	.start  = m_start,
+	.next   = m_next,
+	.stop   = m_stop,
+	.show   = show_tid_numa_map,
+};
+
+static int numa_maps_open(struct inode *inode, struct file *file,
+			  const struct seq_operations *ops)
 {
 	struct numa_maps_private *priv;
 	int ret = -ENOMEM;
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (priv) {
 		priv->proc_maps.pid = proc_pid(inode);
-		ret = seq_open(file, &proc_pid_numa_maps_op);
+		ret = seq_open(file, ops);
 		if (!ret) {
 			struct seq_file *m = file->private_data;
 			m->private = priv;
@@ -1109,8 +1255,25 @@ static int numa_maps_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
-const struct file_operations proc_numa_maps_operations = {
-	.open		= numa_maps_open,
+static int pid_numa_maps_open(struct inode *inode, struct file *file)
+{
+	return numa_maps_open(inode, file, &proc_pid_numa_maps_op);
+}
+
+static int tid_numa_maps_open(struct inode *inode, struct file *file)
+{
+	return numa_maps_open(inode, file, &proc_tid_numa_maps_op);
+}
+
+const struct file_operations proc_pid_numa_maps_operations = {
+	.open		= pid_numa_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+const struct file_operations proc_tid_numa_maps_operations = {
+	.open		= tid_numa_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,