readahead: remove the limit max_sectors_kb imposed on max_readahead_kb

@@ -771,12 +771,12 @@ struct fown_struct {
  * Track a single file's readahead state
  */
 struct file_ra_state {
-	pgoff_t start;                  /* where readahead started */
-	unsigned long size;             /* # of readahead pages */
-	unsigned long async_size;       /* do asynchronous readahead when
+	pgoff_t start;			/* where readahead started */
+	unsigned int size;		/* # of readahead pages */
+	unsigned int async_size;	/* do asynchronous readahead when
 					   there are only # of pages ahead */
 
-	unsigned long ra_pages;		/* Maximum readahead window */
+	unsigned int ra_pages;		/* Maximum readahead window */
 	unsigned long mmap_hit;		/* Cache hit stat for mmap accesses */
 	unsigned long mmap_miss;	/* Cache miss stat for mmap accesses */
 	unsigned long prev_index;	/* Cache last read() position */

@@ -840,7 +840,7 @@ static void shrink_readahead_size_eio(st
 	if (count > 5)
 		return;
 	count++;
-	printk(KERN_WARNING "Reducing readahead size to %luK\n",
+	printk(KERN_WARNING "Reducing readahead size to %dK\n",
 		ra->ra_pages << (PAGE_CACHE_SHIFT - 10));
 }
 

@@ -342,7 +342,7 @@ ondemand_readahead(struct address_space 
 		   bool hit_readahead_marker, pgoff_t offset,
 		   unsigned long req_size)
 {
-	unsigned long max;	/* max readahead pages */
+	int max;	/* max readahead pages */
 	int sequential;
 
 	max = ra->ra_pages;

@@ -777,8 +777,7 @@ struct file_ra_state {
 					   there are only # of pages ahead */
 
 	unsigned int ra_pages;		/* Maximum readahead window */
-	unsigned long mmap_hit;		/* Cache hit stat for mmap accesses */
-	unsigned long mmap_miss;	/* Cache miss stat for mmap accesses */
+	int mmap_miss;			/* Cache miss stat for mmap accesses */
 	unsigned long prev_index;	/* Cache last read() position */
 	unsigned int prev_offset;	/* Offset where last read() ended in a page */
 };

@@ -1389,7 +1389,7 @@ retry_find:
 		 * Do we miss much more than hit in this file? If so,
 		 * stop bothering with read-ahead. It will only hurt.
 		 */
-		if (ra->mmap_miss > ra->mmap_hit + MMAP_LOTSAMISS)
+		if (ra->mmap_miss > MMAP_LOTSAMISS)
 			goto no_cached_page;
 
 		/*

@@ -1415,7 +1415,7 @@ retry_find:
 	}
 
 	if (!did_readaround)
-		ra->mmap_hit++;
+		ra->mmap_miss--;
 
 	/*
 	 * We have a locked page in the page cache, now we need to check

@@ -778,8 +778,7 @@ struct file_ra_state {
 
 	unsigned int ra_pages;		/* Maximum readahead window */
 	int mmap_miss;			/* Cache miss stat for mmap accesses */
-	unsigned long prev_index;	/* Cache last read() position */
-	unsigned int prev_offset;	/* Offset where last read() ended in a page */
+	loff_t prev_pos;		/* Cache last read() position */
 };
 
 /*

@@ -881,8 +881,8 @@ void do_generic_mapping_read(struct addr
 
 	index = *ppos >> PAGE_CACHE_SHIFT;
 	next_index = index;
-	prev_index = ra.prev_index;
-	prev_offset = ra.prev_offset;
+	prev_index = ra.prev_pos >> PAGE_CACHE_SHIFT;
+	prev_offset = ra.prev_pos & (PAGE_CACHE_SIZE-1);
 	last_index = (*ppos + desc->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
 	offset = *ppos & ~PAGE_CACHE_MASK;
 

@@ -968,7 +968,6 @@ page_ok:
 		index += offset >> PAGE_CACHE_SHIFT;
 		offset &= ~PAGE_CACHE_MASK;
 		prev_offset = offset;
-		ra.prev_offset = offset;
 
 		page_cache_release(page);
 		if (ret == nr && desc->count)

@@ -1055,7 +1054,9 @@ no_cached_page:
 
 out:
 	*_ra = ra;
-	_ra->prev_index = prev_index;
+	_ra->prev_pos = prev_index;
+	_ra->prev_pos <<= PAGE_CACHE_SHIFT;
+	_ra->prev_pos |= prev_offset;
 
 	*ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;
 	if (filp)

@@ -1435,7 +1436,7 @@ retry_find:
 	 * Found the page and have a reference on it.
 	 */
 	mark_page_accessed(page);
-	ra->prev_index = page->index;
+	ra->prev_pos = page->index << PAGE_CACHE_SHIFT;
 	return page;
 
 outside_data_content:

@@ -45,7 +45,7 @@ void
 file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping)
 {
 	ra->ra_pages = mapping->backing_dev_info->ra_pages;
-	ra->prev_index = -1;
+	ra->prev_pos = -1;
 }
 EXPORT_SYMBOL_GPL(file_ra_state_init);
 

@@ -318,7 +318,7 @@ static unsigned long get_next_ra_size(st
  * indicator. The flag won't be set on already cached pages, to avoid the
  * readahead-for-nothing fuss, saving pointless page cache lookups.
  *
- * prev_index tracks the last visited page in the _previous_ read request.
+ * prev_pos tracks the last visited byte in the _previous_ read request.
  * It should be maintained by the caller, and will be used for detecting
  * small random reads. Note that the readahead algorithm checks loosely
  * for sequential patterns. Hence interleaved reads might be served as

@@ -342,11 +342,9 @@ ondemand_readahead(struct address_space 
 		   bool hit_readahead_marker, pgoff_t offset,
 		   unsigned long req_size)
 {
-	int max;	/* max readahead pages */
-	int sequential;
-
-	max = ra->ra_pages;
-	sequential = (offset - ra->prev_index <= 1UL) || (req_size > max);
+	int	max = ra->ra_pages;	/* max readahead pages */
+	pgoff_t prev_offset;
+	int	sequential;
 
 	/*
 	 * It's the expected callback offset, assume sequential access.

@@ -360,6 +358,9 @@ ondemand_readahead(struct address_space 
 		goto readit;
 	}
 
+	prev_offset = ra->prev_pos >> PAGE_CACHE_SHIFT;
+	sequential = offset - prev_offset <= 1UL || req_size > max;
+
 	/*
 	 * Standalone, small read.
 	 * Read as is, and do not pollute the readahead state.

@@ -143,7 +143,7 @@ static int ext3_readdir(struct file * fi
 					sb->s_bdev->bd_inode->i_mapping,
 					&filp->f_ra, filp,
 					index, 1);
-			filp->f_ra.prev_index = index;
+			filp->f_ra.prev_pos = index << PAGE_CACHE_SHIFT;
 			bh = ext3_bread(NULL, inode, blk, 0, &err);
 		}
 

@@ -142,7 +142,7 @@ static int ext4_readdir(struct file * fi
 					sb->s_bdev->bd_inode->i_mapping,
 					&filp->f_ra, filp,
 					index, 1);
-			filp->f_ra.prev_index = index;
+			filp->f_ra.prev_pos = index << PAGE_CACHE_SHIFT;
 			bh = ext4_bread(NULL, inode, blk, 0, &err);
 		}
 

@@ -455,7 +455,7 @@ fill_it:
 	 */
 	while (page_nr < nr_pages)
 		page_cache_release(pages[page_nr++]);
-	in->f_ra.prev_index = index;
+	in->f_ra.prev_pos = index << PAGE_CACHE_SHIFT;
 
 	if (spd.nr_pages)
 		return splice_to_pipe(pipe, &spd);

@@ -1148,8 +1148,6 @@ int write_one_page(struct page *page, in
 /* readahead.c */
 #define VM_MAX_READAHEAD	128	/* kbytes */
 #define VM_MIN_READAHEAD	16	/* kbytes (includes current page) */
-#define VM_MAX_CACHE_HIT    	256	/* max pages in a row in cache before
-					 * turning readahead off */
 
 int do_page_cache_readahead(struct address_space *mapping, struct file *filp,
 			pgoff_t offset, unsigned long nr_to_read);

@@ -21,16 +21,8 @@ void default_unplug_io_fn(struct backing
 }
 EXPORT_SYMBOL(default_unplug_io_fn);
 
-/*
- * Convienent macros for min/max read-ahead pages.
- * Note that MAX_RA_PAGES is rounded down, while MIN_RA_PAGES is rounded up.
- * The latter is necessary for systems with large page size(i.e. 64k).
- */
-#define MAX_RA_PAGES	(VM_MAX_READAHEAD*1024 / PAGE_CACHE_SIZE)
-#define MIN_RA_PAGES	DIV_ROUND_UP(VM_MIN_READAHEAD*1024, PAGE_CACHE_SIZE)
-
 struct backing_dev_info default_backing_dev_info = {
-	.ra_pages	= MAX_RA_PAGES,
+	.ra_pages	= VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
 	.state		= 0,
 	.capabilities	= BDI_CAP_MAP_COPY,
 	.unplug_io_fn	= default_unplug_io_fn,

@@ -3945,7 +3945,6 @@ queue_max_sectors_store(struct request_q
 			max_hw_sectors_kb = q->max_hw_sectors >> 1,
 			page_kb = 1 << (PAGE_CACHE_SHIFT - 10);
 	ssize_t ret = queue_var_store(&max_sectors_kb, page, count);
-	int ra_kb;
 
 	if (max_sectors_kb > max_hw_sectors_kb || max_sectors_kb < page_kb)
 		return -EINVAL;

@@ -3954,14 +3953,6 @@ queue_max_sectors_store(struct request_q
 	 * values synchronously:
 	 */
 	spin_lock_irq(q->queue_lock);
-	/*
-	 * Trim readahead window as well, if necessary:
-	 */
-	ra_kb = q->backing_dev_info.ra_pages << (PAGE_CACHE_SHIFT - 10);
-	if (ra_kb > max_sectors_kb)
-		q->backing_dev_info.ra_pages =
-				max_sectors_kb >> (PAGE_CACHE_SHIFT - 10);
-
 	q->max_sectors = max_sectors_kb << 1;
 	spin_unlock_irq(q->queue_lock);
 

@@ -155,6 +155,8 @@ void *radix_tree_delete(struct radix_tre
 unsigned int
 radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 			unsigned long first_index, unsigned int max_items);
+unsigned long radix_tree_scan_hole(struct radix_tree_root *root,
+				unsigned long index, unsigned long max_scan);
 int radix_tree_preload(gfp_t gfp_mask);
 void radix_tree_init(void);
 void *radix_tree_tag_set(struct radix_tree_root *root,

@@ -601,6 +601,40 @@ int radix_tree_tag_get(struct radix_tree
 EXPORT_SYMBOL(radix_tree_tag_get);
 #endif
 
+static unsigned long
+radix_tree_scan_hole_dumb(struct radix_tree_root *root,
+				unsigned long index, unsigned long max_scan)
+{
+	unsigned long i;
+
+	for (i = 0; i < max_scan; i++) {
+		if (!radix_tree_lookup(root, index))
+			break;
+		if (++index == 0)
+			break;
+	}
+
+	return index;
+}
+
+/**
+ *	radix_tree_scan_hole    -    scan for hole
+ *	@root:		radix tree root
+ *	@index:		index key
+ *	@max_scan:      advice on max items to scan (it may scan a little more)
+ *
+ *      Scan forward from @index for a hole/empty item, stop when
+ *      - hit hole
+ *      - wrap-around to index 0
+ *      - @max_scan or more items scanned
+ */
+unsigned long radix_tree_scan_hole(struct radix_tree_root *root,
+				unsigned long index, unsigned long max_scan)
+{
+	return radix_tree_scan_hole_dumb(root, index, max_scan);
+}
+EXPORT_SYMBOL(radix_tree_scan_hole);
+
 static unsigned int
 __lookup(struct radix_tree_node *slot, void **results, unsigned long index,
 	unsigned int max_items, unsigned long *next_index)

@@ -155,6 +155,8 @@ void *radix_tree_delete(struct radix_tre
 unsigned int
 radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 			unsigned long first_index, unsigned int max_items);
+unsigned long radix_tree_next_hole(struct radix_tree_root *root,
+				unsigned long index, unsigned long max_scan);
 int radix_tree_preload(gfp_t gfp_mask);
 void radix_tree_init(void);
 void *radix_tree_tag_set(struct radix_tree_root *root,

@@ -601,6 +601,42 @@ int radix_tree_tag_get(struct radix_tree
 EXPORT_SYMBOL(radix_tree_tag_get);
 #endif
 
+/**
+ *	radix_tree_next_hole    -    find the next hole (not-present entry)
+ *	@root:		tree root
+ *	@index:		index key
+ *	@max_scan:	maximum range to search
+ *
+ *	Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the lowest
+ *	indexed hole.
+ *
+ *	Returns: the index of the hole if found, otherwise returns an index
+ *	outside of the set specified (in which case 'return - index >= max_scan'
+ *	will be true).
+ *
+ *	radix_tree_next_hole may be called under rcu_read_lock. However, like
+ *	radix_tree_gang_lookup, this will not atomically search a snapshot of the
+ *	tree at a single point in time. For example, if a hole is created at index
+ *	5, then subsequently a hole is created at index 10, radix_tree_next_hole
+ *	covering both indexes may return 10 if called under rcu_read_lock.
+ */
+unsigned long radix_tree_next_hole(struct radix_tree_root *root,
+				unsigned long index, unsigned long max_scan)
+{
+	unsigned long i;
+
+	for (i = 0; i < max_scan; i++) {
+		if (!radix_tree_lookup(root, index))
+			break;
+		index++;
+		if (index == 0)
+			break;
+	}
+
+	return index;
+}
+EXPORT_SYMBOL(radix_tree_next_hole);
+
 static unsigned int
 __lookup(struct radix_tree_node *slot, void **results, unsigned long index,
 	unsigned int max_items, unsigned long *next_index)

@@ -372,7 +372,7 @@ ondemand_readahead(struct address_space 
 		pgoff_t start;
 
 		read_lock_irq(&mapping->tree_lock);
-		start = radix_tree_scan_hole(&mapping->page_tree, offset, max+1);
+		start = radix_tree_next_hole(&mapping->page_tree, offset, max+1);
 		read_unlock_irq(&mapping->tree_lock);
 
 		if (!start || start - offset > max)

@@ -363,6 +363,29 @@ ondemand_readahead(struct address_space 
 	}
 
 	/*
+	 * Hit a marked page without valid readahead state.
+	 * E.g. interleaved reads.
+	 * Query the pagecache for async_size, which normally equals to
+	 * readahead size. Ramp it up and use it as the new readahead size.
+	 */
+	if (hit_readahead_marker) {
+		pgoff_t start;
+
+		read_lock_irq(&mapping->tree_lock);
+		start = radix_tree_scan_hole(&mapping->page_tree, offset, max+1);
+		read_unlock_irq(&mapping->tree_lock);
+
+		if (!start || start - offset > max)
+			return 0;
+
+		ra->start = start;
+		ra->size = start - offset;	/* old async_size */
+		ra->size = get_next_ra_size(ra, max);
+		ra->async_size = ra->size;
+		goto readit;
+	}
+
+	/*
 	 * It may be one of
 	 * 	- first read on start of file
 	 * 	- sequential cache miss

@@ -373,16 +396,6 @@ ondemand_readahead(struct address_space 
 	ra->size = get_init_ra_size(req_size, max);
 	ra->async_size = ra->size > req_size ? ra->size - req_size : ra->size;
 
-	/*
-	 * Hit on a marked page without valid readahead state.
-	 * E.g. interleaved reads.
-	 * Not knowing its readahead pos/size, bet on the minimal possible one.
-	 */
-	if (hit_readahead_marker) {
-		ra->start++;
-		ra->size = get_next_ra_size(ra, max);
-	}
-
 readit:
 	return ra_submit(ra, mapping, filp);
 }