Merge branch 'master' of /home/davem/src/GIT/linux-2.6/

Conflicts:
	include/net/tcp.h

8 files changed, 233 insertions, 159 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index ef169f3..8b4d88f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -260,27 +260,27 @@ int filemap_flush(struct address_space *mapping)
 EXPORT_SYMBOL(filemap_flush);
 
 /**
- * wait_on_page_writeback_range - wait for writeback to complete
- * @mapping:	target address_space
- * @start:	beginning page index
- * @end:	ending page index
+ * filemap_fdatawait_range - wait for writeback to complete
+ * @mapping:		address space structure to wait for
+ * @start_byte:		offset in bytes where the range starts
+ * @end_byte:		offset in bytes where the range ends (inclusive)
  *
- * Wait for writeback to complete against pages indexed by start->end
- * inclusive
+ * Walk the list of under-writeback pages of the given address space
+ * in the given range and wait for all of them.
  */
-int wait_on_page_writeback_range(struct address_space *mapping,
-				pgoff_t start, pgoff_t end)
+int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
+			    loff_t end_byte)
 {
+	pgoff_t index = start_byte >> PAGE_CACHE_SHIFT;
+	pgoff_t end = end_byte >> PAGE_CACHE_SHIFT;
 	struct pagevec pvec;
 	int nr_pages;
 	int ret = 0;
-	pgoff_t index;
 
-	if (end < start)
+	if (end_byte < start_byte)
 		return 0;
 
 	pagevec_init(&pvec, 0);
-	index = start;
 	while ((index <= end) &&
 			(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
 			PAGECACHE_TAG_WRITEBACK,
@@ -310,25 +310,6 @@ int wait_on_page_writeback_range(struct address_space *mapping,
 
 	return ret;
 }
-
-/**
- * filemap_fdatawait_range - wait for all under-writeback pages to complete in a given range
- * @mapping: address space structure to wait for
- * @start:	offset in bytes where the range starts
- * @end:	offset in bytes where the range ends (inclusive)
- *
- * Walk the list of under-writeback pages of the given address space
- * in the given range and wait for all of them.
- *
- * This is just a simple wrapper so that callers don't have to convert offsets
- * to page indexes themselves
- */
-int filemap_fdatawait_range(struct address_space *mapping, loff_t start,
-			    loff_t end)
-{
-	return wait_on_page_writeback_range(mapping, start >> PAGE_CACHE_SHIFT,
-					    end >> PAGE_CACHE_SHIFT);
-}
 EXPORT_SYMBOL(filemap_fdatawait_range);
 
 /**
@@ -345,8 +326,7 @@ int filemap_fdatawait(struct address_space *mapping)
 	if (i_size == 0)
 		return 0;
 
-	return wait_on_page_writeback_range(mapping, 0,
-				(i_size - 1) >> PAGE_CACHE_SHIFT);
+	return filemap_fdatawait_range(mapping, 0, i_size - 1);
 }
 EXPORT_SYMBOL(filemap_fdatawait);
 
@@ -393,9 +373,8 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 						 WB_SYNC_ALL);
 		/* See comment of filemap_write_and_wait() */
 		if (err != -EIO) {
-			int err2 = wait_on_page_writeback_range(mapping,
-						lstart >> PAGE_CACHE_SHIFT,
-						lend >> PAGE_CACHE_SHIFT);
+			int err2 = filemap_fdatawait_range(mapping,
+						lstart, lend);
 			if (!err)
 				err = err2;
 		}
@@ -1844,7 +1823,7 @@ static size_t __iovec_copy_from_user_inatomic(char *vaddr,
 
 /*
  * Copy as much as we can into the page and return the number of bytes which
- * were sucessfully copied.  If a fault is encountered then return the number of
+ * were successfully copied.  If a fault is encountered then return the number of
  * bytes which were copied.
  */
 size_t iov_iter_copy_from_user_atomic(struct page *page,
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 8bf765c..13f33b3 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1050,8 +1050,8 @@ static void scan_object(struct kmemleak_object *object)
 	unsigned long flags;
 
 	/*
-	 * Once the object->lock is aquired, the corresponding memory block
-	 * cannot be freed (the same lock is aquired in delete_object).
+	 * Once the object->lock is acquired, the corresponding memory block
+	 * cannot be freed (the same lock is acquired in delete_object).
 	 */
 	spin_lock_irqsave(&object->lock, flags);
 	if (object->flags & OBJECT_NO_SCAN)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f99f599..c31a310 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -209,7 +209,7 @@ struct mem_cgroup {
 	int	prev_priority;	/* for recording reclaim priority */
 
 	/*
-	 * While reclaiming in a hiearchy, we cache the last child we
+	 * While reclaiming in a hierarchy, we cache the last child we
 	 * reclaimed from.
 	 */
 	int last_scanned_child;
@@ -1720,7 +1720,7 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 /*
  * While swap-in, try_charge -> commit or cancel, the page is locked.
  * And when try_charge() successfully returns, one refcnt to memcg without
- * struct page_cgroup is aquired. This refcnt will be cumsumed by
+ * struct page_cgroup is acquired. This refcnt will be consumed by
  * "commit()" or removed by "cancel()"
  */
 int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
@@ -2466,7 +2466,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
 
 	cgroup_lock();
 	/*
-	 * If parent's use_hiearchy is set, we can't make any modifications
+	 * If parent's use_hierarchy is set, we can't make any modifications
 	 * in the child subtrees. If it is unset, then the change can
 	 * occur, provided the current cgroup has no children.
 	 *
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index dacc641..1ac49fe 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -174,7 +174,7 @@ static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno,
 	list_for_each_entry_safe (tk, next, to_kill, nd) {
 		if (doit) {
 			/*
-			 * In case something went wrong with munmaping
+			 * In case something went wrong with munmapping
 			 * make sure the process doesn't catch the
 			 * signal and then access the memory. Just kill it.
 			 * the signal handlers
diff --git a/mm/mmap.c b/mm/mmap.c
index 292ddc3..ed70a68 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -931,13 +931,9 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 	if (!(flags & MAP_FIXED))
 		addr = round_hint_to_min(addr);
 
-	error = arch_mmap_check(addr, len, flags);
-	if (error)
-		return error;
-
 	/* Careful about overflows.. */
 	len = PAGE_ALIGN(len);
-	if (!len || len > TASK_SIZE)
+	if (!len)
 		return -ENOMEM;
 
 	/* offset overflow? */
@@ -948,24 +944,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 	if (mm->map_count > sysctl_max_map_count)
 		return -ENOMEM;
 
-	if (flags & MAP_HUGETLB) {
-		struct user_struct *user = NULL;
-		if (file)
-			return -EINVAL;
-
-		/*
-		 * VM_NORESERVE is used because the reservations will be
-		 * taken when vm_ops->mmap() is called
-		 * A dummy user value is used because we are not locking
-		 * memory so no accounting is necessary
-		 */
-		len = ALIGN(len, huge_page_size(&default_hstate));
-		file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE,
-						&user, HUGETLB_ANONHUGE_INODE);
-		if (IS_ERR(file))
-			return PTR_ERR(file);
-	}
-
 	/* Obtain the address to map to. we verify (or select) it and ensure
 	 * that it represents a valid section of the address space.
 	 */
@@ -1455,6 +1433,14 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 	unsigned long (*get_area)(struct file *, unsigned long,
 				  unsigned long, unsigned long, unsigned long);
 
+	unsigned long error = arch_mmap_check(addr, len, flags);
+	if (error)
+		return error;
+
+	/* Careful about overflows.. */
+	if (len > TASK_SIZE)
+		return -ENOMEM;
+
 	get_area = current->mm->get_unmapped_area;
 	if (file && file->f_op && file->f_op->get_unmapped_area)
 		get_area = file->f_op->get_unmapped_area;
@@ -1999,20 +1985,14 @@ unsigned long do_brk(unsigned long addr, unsigned long len)
 	if (!len)
 		return addr;
 
-	if ((addr + len) > TASK_SIZE || (addr + len) < addr)
-		return -EINVAL;
-
-	if (is_hugepage_only_range(mm, addr, len))
-		return -EINVAL;
-
 	error = security_file_mmap(NULL, 0, 0, 0, addr, 1);
 	if (error)
 		return error;
 
 	flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
 
-	error = arch_mmap_check(addr, len, flags);
-	if (error)
+	error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED);
+	if (error & ~PAGE_MASK)
 		return error;
 
 	/*
diff --git a/mm/mremap.c b/mm/mremap.c
index 97bff25..8451908 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -261,6 +261,137 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 	return new_addr;
 }
 
+static struct vm_area_struct *vma_to_resize(unsigned long addr,
+	unsigned long old_len, unsigned long new_len, unsigned long *p)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma = find_vma(mm, addr);
+
+	if (!vma || vma->vm_start > addr)
+		goto Efault;
+
+	if (is_vm_hugetlb_page(vma))
+		goto Einval;
+
+	/* We can't remap across vm area boundaries */
+	if (old_len > vma->vm_end - addr)
+		goto Efault;
+
+	if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)) {
+		if (new_len > old_len)
+			goto Efault;
+	}
+
+	if (vma->vm_flags & VM_LOCKED) {
+		unsigned long locked, lock_limit;
+		locked = mm->locked_vm << PAGE_SHIFT;
+		lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
+		locked += new_len - old_len;
+		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
+			goto Eagain;
+	}
+
+	if (!may_expand_vm(mm, (new_len - old_len) >> PAGE_SHIFT))
+		goto Enomem;
+
+	if (vma->vm_flags & VM_ACCOUNT) {
+		unsigned long charged = (new_len - old_len) >> PAGE_SHIFT;
+		if (security_vm_enough_memory(charged))
+			goto Efault;
+		*p = charged;
+	}
+
+	return vma;
+
+Efault:	/* very odd choice for most of the cases, but... */
+	return ERR_PTR(-EFAULT);
+Einval:
+	return ERR_PTR(-EINVAL);
+Enomem:
+	return ERR_PTR(-ENOMEM);
+Eagain:
+	return ERR_PTR(-EAGAIN);
+}
+
+static unsigned long mremap_to(unsigned long addr,
+	unsigned long old_len, unsigned long new_addr,
+	unsigned long new_len)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long ret = -EINVAL;
+	unsigned long charged = 0;
+	unsigned long map_flags;
+
+	if (new_addr & ~PAGE_MASK)
+		goto out;
+
+	if (new_len > TASK_SIZE || new_addr > TASK_SIZE - new_len)
+		goto out;
+
+	/* Check if the location we're moving into overlaps the
+	 * old location at all, and fail if it does.
+	 */
+	if ((new_addr <= addr) && (new_addr+new_len) > addr)
+		goto out;
+
+	if ((addr <= new_addr) && (addr+old_len) > new_addr)
+		goto out;
+
+	ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1);
+	if (ret)
+		goto out;
+
+	ret = do_munmap(mm, new_addr, new_len);
+	if (ret)
+		goto out;
+
+	if (old_len >= new_len) {
+		ret = do_munmap(mm, addr+new_len, old_len - new_len);
+		if (ret && old_len != new_len)
+			goto out;
+		old_len = new_len;
+	}
+
+	vma = vma_to_resize(addr, old_len, new_len, &charged);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		goto out;
+	}
+
+	map_flags = MAP_FIXED;
+	if (vma->vm_flags & VM_MAYSHARE)
+		map_flags |= MAP_SHARED;
+
+	ret = get_unmapped_area(vma->vm_file, new_addr, new_len, vma->vm_pgoff +
+				((addr - vma->vm_start) >> PAGE_SHIFT),
+				map_flags);
+	if (ret & ~PAGE_MASK)
+		goto out1;
+
+	ret = move_vma(vma, addr, old_len, new_len, new_addr);
+	if (!(ret & ~PAGE_MASK))
+		goto out;
+out1:
+	vm_unacct_memory(charged);
+
+out:
+	return ret;
+}
+
+static int vma_expandable(struct vm_area_struct *vma, unsigned long delta)
+{
+	unsigned long end = vma->vm_end + delta;
+	if (end < vma->vm_end) /* overflow */
+		return 0;
+	if (vma->vm_next && vma->vm_next->vm_start < end) /* intersection */
+		return 0;
+	if (get_unmapped_area(NULL, vma->vm_start, end - vma->vm_start,
+			      0, MAP_FIXED) & ~PAGE_MASK)
+		return 0;
+	return 1;
+}
+
 /*
  * Expand (or shrink) an existing mapping, potentially moving it at the
  * same time (controlled by the MREMAP_MAYMOVE flag and available VM space)
@@ -294,32 +425,10 @@ unsigned long do_mremap(unsigned long addr,
 	if (!new_len)
 		goto out;
 
-	/* new_addr is only valid if MREMAP_FIXED is specified */
 	if (flags & MREMAP_FIXED) {
-		if (new_addr & ~PAGE_MASK)
-			goto out;
-		if (!(flags & MREMAP_MAYMOVE))
-			goto out;
-
-		if (new_len > TASK_SIZE || new_addr > TASK_SIZE - new_len)
-			goto out;
-
-		/* Check if the location we're moving into overlaps the
-		 * old location at all, and fail if it does.
-		 */
-		if ((new_addr <= addr) && (new_addr+new_len) > addr)
-			goto out;
-
-		if ((addr <= new_addr) && (addr+old_len) > new_addr)
-			goto out;
-
-		ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1);
-		if (ret)
-			goto out;
-
-		ret = do_munmap(mm, new_addr, new_len);
-		if (ret)
-			goto out;
+		if (flags & MREMAP_MAYMOVE)
+			ret = mremap_to(addr, old_len, new_addr, new_len);
+		goto out;
 	}
 
 	/*
@@ -332,60 +441,23 @@ unsigned long do_mremap(unsigned long addr,
 		if (ret && old_len != new_len)
 			goto out;
 		ret = addr;
-		if (!(flags & MREMAP_FIXED) || (new_addr == addr))
-			goto out;
-		old_len = new_len;
+		goto out;
 	}
 
 	/*
-	 * Ok, we need to grow..  or relocate.
+	 * Ok, we need to grow..
 	 */
-	ret = -EFAULT;
-	vma = find_vma(mm, addr);
-	if (!vma || vma->vm_start > addr)
-		goto out;
-	if (is_vm_hugetlb_page(vma)) {
-		ret = -EINVAL;
-		goto out;
-	}
-	/* We can't remap across vm area boundaries */
-	if (old_len > vma->vm_end - addr)
-		goto out;
-	if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)) {
-		if (new_len > old_len)
-			goto out;
-	}
-	if (vma->vm_flags & VM_LOCKED) {
-		unsigned long locked, lock_limit;
-		locked = mm->locked_vm << PAGE_SHIFT;
-		lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
-		locked += new_len - old_len;
-		ret = -EAGAIN;
-		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
-			goto out;
-	}
-	if (!may_expand_vm(mm, (new_len - old_len) >> PAGE_SHIFT)) {
-		ret = -ENOMEM;
+	vma = vma_to_resize(addr, old_len, new_len, &charged);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
 		goto out;
 	}
 
-	if (vma->vm_flags & VM_ACCOUNT) {
-		charged = (new_len - old_len) >> PAGE_SHIFT;
-		if (security_vm_enough_memory(charged))
-			goto out_nc;
-	}
-
 	/* old_len exactly to the end of the area..
-	 * And we're not relocating the area.
 	 */
-	if (old_len == vma->vm_end - addr &&
-	    !((flags & MREMAP_FIXED) && (addr != new_addr)) &&
-	    (old_len != new_len || !(flags & MREMAP_MAYMOVE))) {
-		unsigned long max_addr = TASK_SIZE;
-		if (vma->vm_next)
-			max_addr = vma->vm_next->vm_start;
+	if (old_len == vma->vm_end - addr) {
 		/* can we just expand the current mapping? */
-		if (max_addr - addr >= new_len) {
+		if (vma_expandable(vma, new_len - old_len)) {
 			int pages = (new_len - old_len) >> PAGE_SHIFT;
 
 			vma_adjust(vma, vma->vm_start,
@@ -409,28 +481,27 @@ unsigned long do_mremap(unsigned long addr,
 	 */
 	ret = -ENOMEM;
 	if (flags & MREMAP_MAYMOVE) {
-		if (!(flags & MREMAP_FIXED)) {
-			unsigned long map_flags = 0;
-			if (vma->vm_flags & VM_MAYSHARE)
-				map_flags |= MAP_SHARED;
-
-			new_addr = get_unmapped_area(vma->vm_file, 0, new_len,
-						vma->vm_pgoff, map_flags);
-			if (new_addr & ~PAGE_MASK) {
-				ret = new_addr;
-				goto out;
-			}
-
-			ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1);
-			if (ret)
-				goto out;
+		unsigned long map_flags = 0;
+		if (vma->vm_flags & VM_MAYSHARE)
+			map_flags |= MAP_SHARED;
+
+		new_addr = get_unmapped_area(vma->vm_file, 0, new_len,
+					vma->vm_pgoff +
+					((addr - vma->vm_start) >> PAGE_SHIFT),
+					map_flags);
+		if (new_addr & ~PAGE_MASK) {
+			ret = new_addr;
+			goto out;
 		}
+
+		ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1);
+		if (ret)
+			goto out;
 		ret = move_vma(vma, addr, old_len, new_len, new_addr);
 	}
 out:
 	if (ret & ~PAGE_MASK)
 		vm_unacct_memory(charged);
-out_nc:
 	return ret;
 }
 
diff --git a/mm/truncate.c b/mm/truncate.c
index 450cebd..2c147a7 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -490,7 +490,7 @@ EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range);
  * Any pages which are found to be mapped into pagetables are unmapped prior to
  * invalidation.
  *
- * Returns -EIO if any pages could not be invalidated.
+ * Returns -EBUSY if any pages could not be invalidated.
  */
 int invalidate_inode_pages2(struct address_space *mapping)
 {
diff --git a/mm/util.c b/mm/util.c
index 7c35ad9..b377ce4 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -4,6 +4,10 @@
 #include <linux/module.h>
 #include <linux/err.h>
 #include <linux/sched.h>
+#include <linux/hugetlb.h>
+#include <linux/syscalls.h>
+#include <linux/mman.h>
+#include <linux/file.h>
 #include <asm/uaccess.h>
 
 #define CREATE_TRACE_POINTS
@@ -268,6 +272,46 @@ int __attribute__((weak)) get_user_pages_fast(unsigned long start,
 }
 EXPORT_SYMBOL_GPL(get_user_pages_fast);
 
+SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
+		unsigned long, prot, unsigned long, flags,
+		unsigned long, fd, unsigned long, pgoff)
+{
+	struct file * file = NULL;
+	unsigned long retval = -EBADF;
+
+	if (!(flags & MAP_ANONYMOUS)) {
+		if (unlikely(flags & MAP_HUGETLB))
+			return -EINVAL;
+		file = fget(fd);
+		if (!file)
+			goto out;
+	} else if (flags & MAP_HUGETLB) {
+		struct user_struct *user = NULL;
+		/*
+		 * VM_NORESERVE is used because the reservations will be
+		 * taken when vm_ops->mmap() is called
+		 * A dummy user value is used because we are not locking
+		 * memory so no accounting is necessary
+		 */
+		len = ALIGN(len, huge_page_size(&default_hstate));
+		file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE,
+						&user, HUGETLB_ANONHUGE_INODE);
+		if (IS_ERR(file))
+			return PTR_ERR(file);
+	}
+
+	flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
+
+	down_write(&current->mm->mmap_sem);
+	retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+	up_write(&current->mm->mmap_sem);
+
+	if (file)
+		fput(file);
+out:
+	return retval;
+}
+
 /* Tracepoints definitions. */
 EXPORT_TRACEPOINT_SYMBOL(kmalloc);
 EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);