Merge tag 'v3.9' into v4l_for_linus

Linux 3.9

* tag 'v3.9': (1099 commits)
  Linux 3.9
  vm: add no-mmu vm_iomap_memory() stub
  efivars: only check for duplicates on the registered list
  TTY: fix atime/mtime regression
  aio: fix possible invalid memory access when DEBUG is enabled
  parisc: use spin_lock_irqsave/spin_unlock_irqrestore for PTE updates
  parisc: disable -mlong-calls compiler option for kernel modules
  parisc: uaccess: fix compiler warnings caused by __put_user casting
  parisc: Change kunmap macro to static inline function
  parisc: Provide __ucmpdi2 to resolve undefined references in 32 bit builds.
  sparc64: Fix missing put_cpu_var() in tlb_batch_add_one() when not batching.
  Revert "gpio: pxa: set initcall level to module init"
  efi: Check EFI revision in setup_efi_vars
  x86, efi: Fix a build warning
  Revert "MIPS: page.h: Provide more readable definition for PAGE_MASK."
  kernel/hz.bc: ignore.
  Linux 3.9-rc8
  events: Protect access via task_subsys_state_check()
  net: fix incorrect credentials passing
  x86, microcode: Verify the family before dispatching microcode patching
  ...

8 files changed, 93 insertions, 24 deletions

diff --git a/mm/fremap.c b/mm/fremap.c
index 4723ac8d2fc..87da3590c61 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -204,10 +204,8 @@ get_write_lock:
 			unsigned long addr;
 			struct file *file = get_file(vma->vm_file);
 
-			vm_flags = vma->vm_flags;
-			if (!(flags & MAP_NONBLOCK))
-				vm_flags |= VM_POPULATE;
-			addr = mmap_region(file, start, size, vm_flags, pgoff);
+			addr = mmap_region(file, start, size,
+					vma->vm_flags, pgoff);
 			fput(file);
 			if (IS_ERR_VALUE(addr)) {
 				err = addr;
@@ -226,12 +224,6 @@ get_write_lock:
 		mutex_unlock(&mapping->i_mmap_mutex);
 	}
 
-	if (!(flags & MAP_NONBLOCK) && !(vma->vm_flags & VM_POPULATE)) {
-		if (!has_write_lock)
-			goto get_write_lock;
-		vma->vm_flags |= VM_POPULATE;
-	}
-
 	if (vma->vm_flags & VM_LOCKED) {
 		/*
 		 * drop PG_Mlocked flag for over-mapped range
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0a0be33bb19..1a12f5b9a0a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2124,8 +2124,12 @@ int hugetlb_report_node_meminfo(int nid, char *buf)
 /* Return the number pages of memory we physically have, in PAGE_SIZE units. */
 unsigned long hugetlb_total_pages(void)
 {
-	struct hstate *h = &default_hstate;
-	return h->nr_huge_pages * pages_per_huge_page(h);
+	struct hstate *h;
+	unsigned long nr_total_pages = 0;
+
+	for_each_hstate(h)
+		nr_total_pages += h->nr_huge_pages * pages_per_huge_page(h);
+	return nr_total_pages;
 }
 
 static int hugetlb_acct_memory(struct hstate *h, long delta)
@@ -2957,7 +2961,17 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			break;
 		}
 
-		if (absent ||
+		/*
+		 * We need call hugetlb_fault for both hugepages under migration
+		 * (in which case hugetlb_fault waits for the migration,) and
+		 * hwpoisoned hugepages (in which case we need to prevent the
+		 * caller from accessing to them.) In order to do this, we use
+		 * here is_swap_pte instead of is_hugetlb_entry_migration and
+		 * is_hugetlb_entry_hwpoisoned. This is because it simply covers
+		 * both cases, and because we can't follow correct pages
+		 * directly from any kind of swap entries.
+		 */
+		if (absent || is_swap_pte(huge_ptep_get(pte)) ||
 		    ((flags & FOLL_WRITE) && !pte_write(huge_ptep_get(pte)))) {
 			int ret;
 
diff --git a/mm/memory.c b/mm/memory.c
index 494526ae024..ba94dec5b25 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -216,6 +216,7 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
 	tlb->mm = mm;
 
 	tlb->fullmm     = fullmm;
+	tlb->need_flush_all = 0;
 	tlb->start	= -1UL;
 	tlb->end	= 0;
 	tlb->need_flush = 0;
@@ -2392,6 +2393,53 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL(remap_pfn_range);
 
+/**
+ * vm_iomap_memory - remap memory to userspace
+ * @vma: user vma to map to
+ * @start: start of area
+ * @len: size of area
+ *
+ * This is a simplified io_remap_pfn_range() for common driver use. The
+ * driver just needs to give us the physical memory range to be mapped,
+ * we'll figure out the rest from the vma information.
+ *
+ * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get
+ * whatever write-combining details or similar.
+ */
+int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len)
+{
+	unsigned long vm_len, pfn, pages;
+
+	/* Check that the physical memory area passed in looks valid */
+	if (start + len < start)
+		return -EINVAL;
+	/*
+	 * You *really* shouldn't map things that aren't page-aligned,
+	 * but we've historically allowed it because IO memory might
+	 * just have smaller alignment.
+	 */
+	len += start & ~PAGE_MASK;
+	pfn = start >> PAGE_SHIFT;
+	pages = (len + ~PAGE_MASK) >> PAGE_SHIFT;
+	if (pfn + pages < pfn)
+		return -EINVAL;
+
+	/* We start the mapping 'vm_pgoff' pages into the area */
+	if (vma->vm_pgoff > pages)
+		return -EINVAL;
+	pfn += vma->vm_pgoff;
+	pages -= vma->vm_pgoff;
+
+	/* Can we fit all of the mapping? */
+	vm_len = vma->vm_end - vma->vm_start;
+	if (vm_len >> PAGE_SHIFT > pages)
+		return -EINVAL;
+
+	/* Ok, let it rip */
+	return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot);
+}
+EXPORT_SYMBOL(vm_iomap_memory);
+
 static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				     unsigned long addr, unsigned long end,
 				     pte_fn_t fn, void *data)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 9597eec8239..ee376576081 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1779,7 +1779,11 @@ void try_offline_node(int nid)
 	for (i = 0; i < MAX_NR_ZONES; i++) {
 		struct zone *zone = pgdat->node_zones + i;
 
-		if (zone->wait_table)
+		/*
+		 * wait_table may be allocated from boot memory,
+		 * here only free if it's allocated by vmalloc.
+		 */
+		if (is_vmalloc_addr(zone->wait_table))
 			vfree(zone->wait_table);
 	}
 
diff --git a/mm/mlock.c b/mm/mlock.c
index 1c5e33fce63..79b7cf7d1bc 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -358,7 +358,7 @@ static int do_mlock(unsigned long start, size_t len, int on)
 
 		newflags = vma->vm_flags & ~VM_LOCKED;
 		if (on)
-			newflags |= VM_LOCKED | VM_POPULATE;
+			newflags |= VM_LOCKED;
 
 		tmp = vma->vm_end;
 		if (tmp > end)
@@ -418,8 +418,7 @@ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
 		 * range with the first VMA. Also, skip undesirable VMA types.
 		 */
 		nend = min(end, vma->vm_end);
-		if ((vma->vm_flags & (VM_IO | VM_PFNMAP | VM_POPULATE)) !=
-		    VM_POPULATE)
+		if (vma->vm_flags & (VM_IO | VM_PFNMAP))
 			continue;
 		if (nstart < vma->vm_start)
 			nstart = vma->vm_start;
@@ -492,9 +491,9 @@ static int do_mlockall(int flags)
 	struct vm_area_struct * vma, * prev = NULL;
 
 	if (flags & MCL_FUTURE)
-		current->mm->def_flags |= VM_LOCKED | VM_POPULATE;
+		current->mm->def_flags |= VM_LOCKED;
 	else
-		current->mm->def_flags &= ~(VM_LOCKED | VM_POPULATE);
+		current->mm->def_flags &= ~VM_LOCKED;
 	if (flags == MCL_FUTURE)
 		goto out;
 
@@ -503,7 +502,7 @@ static int do_mlockall(int flags)
 
 		newflags = vma->vm_flags & ~VM_LOCKED;
 		if (flags & MCL_CURRENT)
-			newflags |= VM_LOCKED | VM_POPULATE;
+			newflags |= VM_LOCKED;
 
 		/* Ignore errors */
 		mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
diff --git a/mm/mmap.c b/mm/mmap.c
index 2664a47cec9..0db0de1c2fb 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1306,7 +1306,9 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 	}
 
 	addr = mmap_region(file, addr, len, vm_flags, pgoff);
-	if (!IS_ERR_VALUE(addr) && (vm_flags & VM_POPULATE))
+	if (!IS_ERR_VALUE(addr) &&
+	    ((vm_flags & VM_LOCKED) ||
+	     (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE))
 		*populate = len;
 	return addr;
 }
@@ -1938,7 +1940,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 
 	/* Check the cache first. */
 	/* (Cache hit rate is typically around 35%.) */
-	vma = mm->mmap_cache;
+	vma = ACCESS_ONCE(mm->mmap_cache);
 	if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) {
 		struct rb_node *rb_node;
 
diff --git a/mm/nommu.c b/mm/nommu.c
index e1932808753..e001768b14e 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -821,7 +821,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 	struct vm_area_struct *vma;
 
 	/* check the cache first */
-	vma = mm->mmap_cache;
+	vma = ACCESS_ONCE(mm->mmap_cache);
 	if (vma && vma->vm_start <= addr && vma->vm_end > addr)
 		return vma;
 
@@ -1838,6 +1838,16 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL(remap_pfn_range);
 
+int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len)
+{
+	unsigned long pfn = start >> PAGE_SHIFT;
+	unsigned long vm_len = vma->vm_end - vma->vm_start;
+
+	pfn += vma->vm_pgoff;
+	return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot);
+}
+EXPORT_SYMBOL(vm_iomap_memory);
+
 int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 			unsigned long pgoff)
 {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 88c5fed8b9a..669fba39be1 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3188,9 +3188,9 @@ int kswapd_run(int nid)
 	if (IS_ERR(pgdat->kswapd)) {
 		/* failure at boot is fatal */
 		BUG_ON(system_state == SYSTEM_BOOTING);
-		pgdat->kswapd = NULL;
 		pr_err("Failed to start kswapd on node %d\n", nid);
 		ret = PTR_ERR(pgdat->kswapd);
+		pgdat->kswapd = NULL;
 	}
 	return ret;
 }