Merge branch 'linux-linaro-lsk-v4.4' into linux-linaro-lsk-v4.4-android

* linux-linaro-lsk-v4.4: (622 commits)
  Linux 4.4.166
  drm/ast: Remove existing framebuffers before loading driver
  s390/mm: Check for valid vma before zapping in gmap_discard
  namei: allow restricted O_CREAT of FIFOs and regular files
  sched/core: Allow __sched_setscheduler() in interrupts when PI is not used
  btrfs: Ensure btrfs_trim_fs can trim the whole filesystem
  usb: xhci: fix uninitialized completion when USB3 port got wrong status
  tty: wipe buffer if not echoing data
  tty: wipe buffer.
  iwlwifi: mvm: fix regulatory domain update when the firmware starts
  scsi: qla2xxx: do not queue commands when unloading
  scsi: ufshcd: release resources if probe fails
  scsi: ufs: fix race between clock gating and devfreq scaling work
  scsi: ufshcd: Fix race between clk scaling and ungate work
  scsi: ufs: fix bugs related to null pointer access and array size
  netfilter: nf_tables: fix oops when inserting an element into a verdict map
  mwifiex: fix p2p device doesn't find in scan problem
  mwifiex: Fix NULL pointer dereference in skb_dequeue()
  cw1200: Don't leak memory if krealloc failes
  Input: xpad - add support for Xbox1 PDP Camo series gamepad
  ...

  Conflicts:
    Makefile
    arch/x86/Makefile
    drivers/base/power/main.c
    drivers/block/zram/zram_drv.c
    kernel/debug/kdb/kdb_io.c
    net/ipv6/route.c
    scripts/Kbuild.include
      Conflicts in above files are fixed as done in AOSP Change-Id:
      I5bd20327e0c1139c46f74e8d5916fa0530a307d3 ("Merge 4.4.165 into android-4.4").

    arch/arm64/include/asm/cpufeature.h
    arch/arm64/kernel/cpufeature.c
      Conflicts in above files is due to AOSP Change-Id:
      I11cb874d12a7d0921f452c62b0752e0028a8e0a7 ("FROMLIST: arm64: entry: Add
      fake CPU feature for unmapping the kernel at EL0"), which needed a minor
      rebasing.

Signed-off-by: Amit Pundir <amit.pundir@linaro.org>

11 files changed, 183 insertions, 29 deletions

diff --git a/mm/gup.c b/mm/gup.c
index b599526db9f7..018144c4b9ec 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -940,8 +940,6 @@ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
 	int locked = 0;
 	long ret = 0;
 
-	VM_BUG_ON(start & ~PAGE_MASK);
-	VM_BUG_ON(len != PAGE_ALIGN(len));
 	end = start + len;
 
 	for (nstart = start; nstart < end; nstart = nend) {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 67f5a8ca0af1..b2d56b1c3276 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1510,7 +1510,7 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 	spinlock_t *old_ptl, *new_ptl;
 	int ret = 0;
 	pmd_t pmd;
-
+	bool force_flush = false;
 	struct mm_struct *mm = vma->vm_mm;
 
 	if ((old_addr & ~HPAGE_PMD_MASK) ||
@@ -1538,6 +1538,8 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 		if (new_ptl != old_ptl)
 			spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
 		pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd);
+		if (pmd_present(pmd))
+			force_flush = true;
 		VM_BUG_ON(!pmd_none(*new_pmd));
 
 		if (pmd_move_must_withdraw(new_ptl, old_ptl)) {
@@ -1546,6 +1548,8 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 			pgtable_trans_huge_deposit(mm, new_pmd, pgtable);
 		}
 		set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd));
+		if (force_flush)
+			flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE);
 		if (new_ptl != old_ptl)
 			spin_unlock(new_ptl);
 		spin_unlock(old_ptl);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a813b03021b7..6f99a0f906bb 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3103,7 +3103,7 @@ static int is_hugetlb_entry_hwpoisoned(pte_t pte)
 int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			    struct vm_area_struct *vma)
 {
-	pte_t *src_pte, *dst_pte, entry;
+	pte_t *src_pte, *dst_pte, entry, dst_entry;
 	struct page *ptepage;
 	unsigned long addr;
 	int cow;
@@ -3131,15 +3131,30 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			break;
 		}
 
-		/* If the pagetables are shared don't copy or take references */
-		if (dst_pte == src_pte)
+		/*
+		 * If the pagetables are shared don't copy or take references.
+		 * dst_pte == src_pte is the common case of src/dest sharing.
+		 *
+		 * However, src could have 'unshared' and dst shares with
+		 * another vma.  If dst_pte !none, this implies sharing.
+		 * Check here before taking page table lock, and once again
+		 * after taking the lock below.
+		 */
+		dst_entry = huge_ptep_get(dst_pte);
+		if ((dst_pte == src_pte) || !huge_pte_none(dst_entry))
 			continue;
 
 		dst_ptl = huge_pte_lock(h, dst, dst_pte);
 		src_ptl = huge_pte_lockptr(h, src, src_pte);
 		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 		entry = huge_ptep_get(src_pte);
-		if (huge_pte_none(entry)) { /* skip none entry */
+		dst_entry = huge_ptep_get(dst_pte);
+		if (huge_pte_none(entry) || !huge_pte_none(dst_entry)) {
+			/*
+			 * Skip if src entry none.  Also, skip in the
+			 * unlikely case dst entry !none as this implies
+			 * sharing with another vma.
+			 */
 			;
 		} else if (unlikely(is_hugetlb_entry_migration(entry) ||
 				    is_hugetlb_entry_hwpoisoned(entry))) {
@@ -3537,6 +3552,12 @@ int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
 		return err;
 	ClearPagePrivate(page);
 
+	/*
+	 * set page dirty so that it will not be removed from cache/file
+	 * by non-hugetlbfs specific code paths.
+	 */
+	set_page_dirty(page);
+
 	spin_lock(&inode->i_lock);
 	inode->i_blocks += blocks_per_huge_page(h);
 	spin_unlock(&inode->i_lock);
@@ -4195,13 +4216,41 @@ static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr)
 	/*
 	 * check on proper vm_flags and page table alignment
 	 */
-	if (vma->vm_flags & VM_MAYSHARE &&
-	    vma->vm_start <= base && end <= vma->vm_end)
+	if (vma->vm_flags & VM_MAYSHARE && range_in_vma(vma, base, end))
 		return true;
 	return false;
 }
 
 /*
+ * Determine if start,end range within vma could be mapped by shared pmd.
+ * If yes, adjust start and end to cover range associated with possible
+ * shared pmd mappings.
+ */
+void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end)
+{
+	unsigned long check_addr = *start;
+
+	if (!(vma->vm_flags & VM_MAYSHARE))
+		return;
+
+	for (check_addr = *start; check_addr < *end; check_addr += PUD_SIZE) {
+		unsigned long a_start = check_addr & PUD_MASK;
+		unsigned long a_end = a_start + PUD_SIZE;
+
+		/*
+		 * If sharing is possible, adjust start/end if necessary.
+		 */
+		if (range_in_vma(vma, a_start, a_end)) {
+			if (a_start < *start)
+				*start = a_start;
+			if (a_end > *end)
+				*end = a_end;
+		}
+	}
+}
+
+/*
  * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
  * and returns the corresponding pte. While this is not necessary for the
  * !shared pmd case because we can allocate the pmd later as well, it makes the
@@ -4297,6 +4346,11 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 {
 	return 0;
 }
+
+void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end)
+{
+}
 #define want_pmd_share()	(0)
 #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
 
diff --git a/mm/madvise.c b/mm/madvise.c
index b04f2d26cdb8..d1d09bdf9a72 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -76,7 +76,7 @@ static long madvise_behavior(struct vm_area_struct *vma,
 		new_flags |= VM_DONTDUMP;
 		break;
 	case MADV_DODUMP:
-		if (new_flags & VM_SPECIAL) {
+		if (!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL) {
 			error = -EINVAL;
 			goto out;
 		}
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index b9b2e25342d4..e48fa18e1828 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2011,8 +2011,36 @@ retry_cpuset:
 		nmask = policy_nodemask(gfp, pol);
 		if (!nmask || node_isset(hpage_node, *nmask)) {
 			mpol_cond_put(pol);
-			page = __alloc_pages_node(hpage_node,
-						gfp | __GFP_THISNODE, order);
+			/*
+			 * We cannot invoke reclaim if __GFP_THISNODE
+			 * is set. Invoking reclaim with
+			 * __GFP_THISNODE set, would cause THP
+			 * allocations to trigger heavy swapping
+			 * despite there may be tons of free memory
+			 * (including potentially plenty of THP
+			 * already available in the buddy) on all the
+			 * other NUMA nodes.
+			 *
+			 * At most we could invoke compaction when
+			 * __GFP_THISNODE is set (but we would need to
+			 * refrain from invoking reclaim even if
+			 * compaction returned COMPACT_SKIPPED because
+			 * there wasn't not enough memory to succeed
+			 * compaction). For now just avoid
+			 * __GFP_THISNODE instead of limiting the
+			 * allocation path to a strict and single
+			 * compaction invocation.
+			 *
+			 * Supposedly if direct reclaim was enabled by
+			 * the caller, the app prefers THP regardless
+			 * of the node it comes from so this would be
+			 * more desiderable behavior than only
+			 * providing THP originated from the local
+			 * node in such case.
+			 */
+			if (!(gfp & __GFP_DIRECT_RECLAIM))
+				gfp |= __GFP_THISNODE;
+			page = __alloc_pages_node(hpage_node, gfp, order);
 			goto out;
 		}
 	}
diff --git a/mm/mmap.c b/mm/mmap.c
index 3f8142e22490..f325aa33f327 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2838,10 +2838,6 @@ static unsigned long do_brk(unsigned long addr, unsigned long len)
 	pgoff_t pgoff = addr >> PAGE_SHIFT;
 	int error;
 
-	len = PAGE_ALIGN(len);
-	if (!len)
-		return addr;
-
 	flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
 
 	error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED);
@@ -2909,12 +2905,19 @@ out:
 	return addr;
 }
 
-unsigned long vm_brk(unsigned long addr, unsigned long len)
+unsigned long vm_brk(unsigned long addr, unsigned long request)
 {
 	struct mm_struct *mm = current->mm;
+	unsigned long len;
 	unsigned long ret;
 	bool populate;
 
+	len = PAGE_ALIGN(request);
+	if (len < request)
+		return -ENOMEM;
+	if (!len)
+		return addr;
+
 	down_write(&mm->mmap_sem);
 	ret = do_brk(addr, len);
 	populate = ((mm->def_flags & VM_LOCKED) != 0);
diff --git a/mm/mremap.c b/mm/mremap.c
index fe7b7f65f4f4..450b306d473e 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -96,6 +96,8 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	struct mm_struct *mm = vma->vm_mm;
 	pte_t *old_pte, *new_pte, pte;
 	spinlock_t *old_ptl, *new_ptl;
+	bool force_flush = false;
+	unsigned long len = old_end - old_addr;
 
 	/*
 	 * When need_rmap_locks is true, we take the i_mmap_rwsem and anon_vma
@@ -143,12 +145,26 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 		if (pte_none(*old_pte))
 			continue;
 		pte = ptep_get_and_clear(mm, old_addr, old_pte);
+		/*
+		 * If we are remapping a valid PTE, make sure
+		 * to flush TLB before we drop the PTL for the PTE.
+		 *
+		 * NOTE! Both old and new PTL matter: the old one
+		 * for racing with page_mkclean(), the new one to
+		 * make sure the physical page stays valid until
+		 * the TLB entry for the old mapping has been
+		 * flushed.
+		 */
+		if (pte_present(pte))
+			force_flush = true;
 		pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr);
 		pte = move_soft_dirty_pte(pte);
 		set_pte_at(mm, new_addr, new_pte, pte);
 	}
 
 	arch_leave_lazy_mmu_mode();
+	if (force_flush)
+		flush_tlb_range(vma, old_end - len, old_end);
 	if (new_ptl != old_ptl)
 		spin_unlock(new_ptl);
 	pte_unmap(new_pte - 1);
@@ -168,7 +184,6 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 {
 	unsigned long extent, next, old_end;
 	pmd_t *old_pmd, *new_pmd;
-	bool need_flush = false;
 	unsigned long mmun_start;	/* For mmu_notifiers */
 	unsigned long mmun_end;		/* For mmu_notifiers */
 
@@ -207,7 +222,6 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 					anon_vma_unlock_write(vma->anon_vma);
 			}
 			if (err > 0) {
-				need_flush = true;
 				continue;
 			} else if (!err) {
 				split_huge_page_pmd(vma, old_addr, old_pmd);
@@ -224,10 +238,7 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 			extent = LATENCY_LIMIT;
 		move_ptes(vma, old_pmd, old_addr, old_addr + extent,
 			  new_vma, new_pmd, new_addr, need_rmap_locks);
-		need_flush = true;
 	}
-	if (likely(need_flush))
-		flush_tlb_range(vma, old_end-len, old_addr);
 
 	mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end);
 
diff --git a/mm/rmap.c b/mm/rmap.c
index 1bceb49aa214..488dda209431 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1324,12 +1324,41 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	pte_t pteval;
 	spinlock_t *ptl;
 	int ret = SWAP_AGAIN;
+	unsigned long sh_address;
+	bool pmd_sharing_possible = false;
+	unsigned long spmd_start, spmd_end;
 	enum ttu_flags flags = (enum ttu_flags)arg;
 
 	/* munlock has nothing to gain from examining un-locked vmas */
 	if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED))
 		goto out;
 
+	/*
+	 * Only use the range_start/end mmu notifiers if huge pmd sharing
+	 * is possible.  In the normal case, mmu_notifier_invalidate_page
+	 * is sufficient as we only unmap a page.  However, if we unshare
+	 * a pmd, we will unmap a PUD_SIZE range.
+	 */
+	if (PageHuge(page)) {
+		spmd_start = address;
+		spmd_end = spmd_start + vma_mmu_pagesize(vma);
+
+		/*
+		 * Check if pmd sharing is possible.  If possible, we could
+		 * unmap a PUD_SIZE range.  spmd_start/spmd_end will be
+		 * modified if sharing is possible.
+		 */
+		adjust_range_if_pmd_sharing_possible(vma, &spmd_start,
+								&spmd_end);
+		if (spmd_end - spmd_start != vma_mmu_pagesize(vma)) {
+			sh_address = address;
+
+			pmd_sharing_possible = true;
+			mmu_notifier_invalidate_range_start(vma->vm_mm,
+							spmd_start, spmd_end);
+		}
+	}
+
 	pte = page_check_address(page, mm, address, &ptl, 0);
 	if (!pte)
 		goto out;
@@ -1356,6 +1385,30 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		}
   	}
 
+	/*
+	 * Call huge_pmd_unshare to potentially unshare a huge pmd.  Pass
+	 * sh_address as it will be modified if unsharing is successful.
+	 */
+	if (PageHuge(page) && huge_pmd_unshare(mm, &sh_address, pte)) {
+		/*
+		 * huge_pmd_unshare unmapped an entire PMD page.  There is
+		 * no way of knowing exactly which PMDs may be cached for
+		 * this mm, so flush them all.  spmd_start/spmd_end cover
+		 * this PUD_SIZE range.
+		 */
+		flush_cache_range(vma, spmd_start, spmd_end);
+		flush_tlb_range(vma, spmd_start, spmd_end);
+
+		/*
+		 * The ref count of the PMD page was dropped which is part
+		 * of the way map counting is done for shared PMDs.  When
+		 * there is no other sharing, huge_pmd_unshare returns false
+		 * and we will unmap the actual page and drop map count
+		 * to zero.
+		 */
+		goto out_unmap;
+	}
+
 	/* Nuke the page table entry. */
 	flush_cache_page(vma, address, page_to_pfn(page));
 	if (should_defer_flush(mm, flags)) {
@@ -1450,6 +1503,9 @@ out_unmap:
 	if (ret != SWAP_FAIL && ret != SWAP_MLOCK && !(flags & TTU_MUNLOCK))
 		mmu_notifier_invalidate_page(mm, address);
 out:
+	if (pmd_sharing_possible)
+		mmu_notifier_invalidate_range_end(vma->vm_mm,
+							spmd_start, spmd_end);
 	return ret;
 }
 
diff --git a/mm/shmem.c b/mm/shmem.c
index afdd2b957f1b..a06b31b8ff8d 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1818,9 +1818,7 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence)
 	mutex_lock(&inode->i_mutex);
 	/* We're holding i_mutex so we can access i_size directly */
 
-	if (offset < 0)
-		offset = -EINVAL;
-	else if (offset >= inode->i_size)
+	if (offset < 0 || offset >= inode->i_size)
 		offset = -ENXIO;
 	else {
 		start = offset >> PAGE_CACHE_SHIFT;
diff --git a/mm/slub.c b/mm/slub.c
index 4a22f9d4e44d..191bbc3378d3 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1712,7 +1712,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
 {
 	struct page *page, *page2;
 	void *object = NULL;
-	int available = 0;
+	unsigned int available = 0;
 	int objects;
 
 	/*
@@ -4791,10 +4791,10 @@ static ssize_t cpu_partial_show(struct kmem_cache *s, char *buf)
 static ssize_t cpu_partial_store(struct kmem_cache *s, const char *buf,
 				 size_t length)
 {
-	unsigned long objects;
+	unsigned int objects;
 	int err;
 
-	err = kstrtoul(buf, 10, &objects);
+	err = kstrtouint(buf, 10, &objects);
 	if (err)
 		return err;
 	if (objects && !kmem_cache_has_cpu_partial(s))
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 8640a185dfc6..6af9bbad94c7 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -860,6 +860,9 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_SMP
 	"nr_tlb_remote_flush",
 	"nr_tlb_remote_flush_received",
+#else
+	"", /* nr_tlb_remote_flush */
+	"", /* nr_tlb_remote_flush_received */
 #endif /* CONFIG_SMP */
 	"nr_tlb_local_flush_all",
 	"nr_tlb_local_flush_one",
@@ -868,7 +871,6 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_DEBUG_VM_VMACACHE
 	"vmacache_find_calls",
 	"vmacache_find_hits",
-	"vmacache_full_flushes",
 #endif
 #endif /* CONFIG_VM_EVENTS_COUNTERS */
 };