brd: partition fixes

index 47b6b9f..830edc8 100644
@@ -156,7 +156,7 @@ axon_ram_direct_access(struct block_device *device, sector_t sector,
 	}
 
 	*kaddr = (void *)(bank->ph_addr + offset);
-	*pfn = virt_to_phys(kaddr) >> PAGE_SHIFT;
+	*pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
 
 	return 0;
 }

index 830edc8..8709b9f 100644
@@ -139,26 +139,17 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
  * axon_ram_direct_access - direct_access() method for block device
  * @device, @sector, @data: see block_device_operations method
  */
-static int
+static long
 axon_ram_direct_access(struct block_device *device, sector_t sector,
-		       void **kaddr, unsigned long *pfn)
+		       void **kaddr, unsigned long *pfn, long size)
 {
 	struct axon_ram_bank *bank = device->bd_disk->private_data;
-	loff_t offset;
-
-	offset = sector;
-	if (device->bd_part != NULL)
-		offset += device->bd_part->start_sect;
-	offset <<= AXON_RAM_SECTOR_SHIFT;
-	if (offset >= bank->size) {
-		dev_err(&bank->device->dev, "Access outside of address space\n");
-		return -ERANGE;
-	}
+	loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT;
 
 	*kaddr = (void *)(bank->ph_addr + offset);
 	*pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
 
-	return 0;
+	return bank->size - offset;
 }
 
 static const struct block_device_operations axon_ram_devops = {

index 3598110..78fe510 100644
@@ -370,25 +370,23 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
 }
 
 #ifdef CONFIG_BLK_DEV_XIP
-static int brd_direct_access(struct block_device *bdev, sector_t sector,
-			void **kaddr, unsigned long *pfn)
+static long brd_direct_access(struct block_device *bdev, sector_t sector,
+			void **kaddr, unsigned long *pfn, long size)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	struct page *page;
 
 	if (!brd)
 		return -ENODEV;
-	if (sector & (PAGE_SECTORS-1))
-		return -EINVAL;
-	if (sector + PAGE_SECTORS > get_capacity(bdev->bd_disk))
-		return -ERANGE;
 	page = brd_insert_page(brd, sector);
 	if (!page)
 		return -ENOSPC;
 	*kaddr = page_address(page);
 	*pfn = page_to_pfn(page);
 
-	return 0;
+	/* If size > PAGE_SIZE, we could look to see if the next page in the
+	 * file happens to be mapped to the next page of physical RAM */
+	return PAGE_SIZE;
 }
 #endif
 

index 0f47175..96bc411 100644
@@ -28,8 +28,8 @@
 static int dcssblk_open(struct block_device *bdev, fmode_t mode);
 static void dcssblk_release(struct gendisk *disk, fmode_t mode);
 static void dcssblk_make_request(struct request_queue *q, struct bio *bio);
-static int dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
-				 void **kaddr, unsigned long *pfn);
+static long dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
+				 void **kaddr, unsigned long *pfn, long size);
 
 static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
 

@@ -866,25 +866,22 @@ fail:
 	bio_io_error(bio);
 }
 
-static int
+static long
 dcssblk_direct_access (struct block_device *bdev, sector_t secnum,
-			void **kaddr, unsigned long *pfn)
+			void **kaddr, unsigned long *pfn, long size)
 {
 	struct dcssblk_dev_info *dev_info;
-	unsigned long pgoff;
+	unsigned long offset, dev_sz;
 
 	dev_info = bdev->bd_disk->private_data;
 	if (!dev_info)
 		return -ENODEV;
-	if (secnum % (PAGE_SIZE/512))
-		return -EINVAL;
-	pgoff = secnum / (PAGE_SIZE / 512);
-	if ((pgoff+1)*PAGE_SIZE-1 > dev_info->end - dev_info->start)
-		return -ERANGE;
-	*kaddr = (void *) (dev_info->start+pgoff*PAGE_SIZE);
+	dev_sz = dev_info->end - dev_info->start;
+	offset = secnum * 512;
+	*kaddr = (void *) (dev_info->start + offset);
 	*pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
 
-	return 0;
+	return dev_sz - offset;
 }
 
 static void

index 6d72746..ffe0761 100644
@@ -427,6 +427,46 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL_GPL(bdev_write_page);
 
+/**
+ * bdev_direct_access() - Get the address for directly-accessibly memory
+ * @bdev: The device containing the memory
+ * @sector: The offset within the device
+ * @addr: Where to put the address of the memory
+ * @pfn: The Page Frame Number for the memory
+ * @size: The number of bytes requested
+ *
+ * If a block device is made up of directly addressable memory, this function
+ * will tell the caller the PFN and the address of the memory.  The address
+ * may be directly dereferenced within the kernel without the need to call
+ * ioremap(), kmap() or similar.  The PFN is suitable for inserting into
+ * page tables.
+ *
+ * Return: negative errno if an error occurs, otherwise the number of bytes
+ * accessible at this address.
+ */
+long bdev_direct_access(struct block_device *bdev, sector_t sector,
+			void **addr, unsigned long *pfn, long size)
+{
+	long avail;
+	const struct block_device_operations *ops = bdev->bd_disk->fops;
+
+	if (size < 0)
+		return size;
+	if (!ops->direct_access)
+		return -EOPNOTSUPP;
+	if ((sector + DIV_ROUND_UP(size, 512)) >
+					part_nr_sects_read(bdev->bd_part))
+		return -ERANGE;
+	sector += get_start_sect(bdev);
+	if (sector % (PAGE_SIZE / 512))
+		return -EINVAL;
+	avail = ops->direct_access(bdev, sector, addr, pfn, size);
+	if (!avail)
+		return -ERANGE;
+	return min(avail, size);
+}
+EXPORT_SYMBOL_GPL(bdev_direct_access);
+
 /*
  * pseudo-fs
  */

index e98171a..bbc5fec 100644
@@ -13,18 +13,12 @@
 #include "ext2.h"
 #include "xip.h"
 
-static inline int
-__inode_direct_access(struct inode *inode, sector_t block,
-		      void **kaddr, unsigned long *pfn)
+static inline long __inode_direct_access(struct inode *inode, sector_t block,
+				void **kaddr, unsigned long *pfn, long size)
 {
 	struct block_device *bdev = inode->i_sb->s_bdev;
-	const struct block_device_operations *ops = bdev->bd_disk->fops;
-	sector_t sector;
-
-	sector = block * (PAGE_SIZE / 512); /* ext2 block to bdev sector */
-
-	BUG_ON(!ops->direct_access);
-	return ops->direct_access(bdev, sector, kaddr, pfn);
+	sector_t sector = block * (PAGE_SIZE / 512);
+	return bdev_direct_access(bdev, sector, kaddr, pfn, size);
 }
 
 static inline int

@@ -53,12 +47,13 @@ ext2_clear_xip_target(struct inode *inode, sector_t block)
 {
 	void *kaddr;
 	unsigned long pfn;
-	int rc;
+	long size;
 
-	rc = __inode_direct_access(inode, block, &kaddr, &pfn);
-	if (!rc)
-		clear_page(kaddr);
-	return rc;
+	size = __inode_direct_access(inode, block, &kaddr, &pfn, PAGE_SIZE);
+	if (size < 0)
+		return size;
+	clear_page(kaddr);
+	return 0;
 }
 
 void ext2_xip_verify_sb(struct super_block *sb)

@@ -77,7 +72,7 @@ void ext2_xip_verify_sb(struct super_block *sb)
 int ext2_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, int create,
 				void **kmem, unsigned long *pfn)
 {
-	int rc;
+	long rc;
 	sector_t block;
 
 	/* first, retrieve the sector number */

@@ -86,6 +81,6 @@ int ext2_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, int create,
 		return rc;
 
 	/* retrieve address of the target data */
-	rc = __inode_direct_access(mapping->host, block, kmem, pfn);
-	return rc;
+	rc = __inode_direct_access(mapping->host, block, kmem, pfn, PAGE_SIZE);
+	return (rc < 0) ? rc : 0;
 }

index 518b465..ac25166 100644
@@ -1615,8 +1615,8 @@ struct block_device_operations {
 	int (*rw_page)(struct block_device *, sector_t, struct page *, int rw);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
-	int (*direct_access) (struct block_device *, sector_t,
-						void **, unsigned long *);
+	long (*direct_access)(struct block_device *, sector_t,
+					void **, unsigned long *pfn, long size);
 	unsigned int (*check_events) (struct gendisk *disk,
 				      unsigned int clearing);
 	/* ->media_changed() is DEPRECATED, use ->check_events() instead */

@@ -1634,6 +1634,8 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
 extern int bdev_read_page(struct block_device *, sector_t, struct page *);
 extern int bdev_write_page(struct block_device *, sector_t, struct page *,
 						struct writeback_control *);
+extern long bdev_direct_access(struct block_device *, sector_t, void **addr,
+						unsigned long *pfn, long size);
 #else /* CONFIG_BLOCK */
 
 struct block_device;

index 78fe510..f841d9e 100644
@@ -19,6 +19,7 @@
 #include <linux/radix-tree.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include <linux/hdreg.h>
 
 #include <asm/uaccess.h>
 

@@ -424,6 +425,23 @@ static int brd_ioctl(struct block_device *bdev, fmode_t mode,
 	return error;
 }
 
+static int brd_getgeo(struct block_device *bd, struct hd_geometry *geo)
+{
+	/* Just tell fdisk to get out of the way. The math here is so
+	 * convoluted and does not make any sense at all. With all 1s
+	 * The math just gets out of the way.
+	 * NOTE: I was trying to get some values that will make fdisk
+	 * Want to align first sector on 4K (like 8, 16, 20, ... sectors) but
+	 * nothing worked, I searched the net the math is not your regular
+	 * simple multiplication at all. If you managed to get these please
+	 * fix here. For now we use 4k physical sectors for this
+	 */
+	geo->heads = 1;
+	geo->sectors = 1;
+	geo->cylinders = 1;
+	return 0;
+}
+
 static const struct block_device_operations brd_fops = {
 	.owner =		THIS_MODULE,
 	.rw_page =		brd_rw_page,

@@ -431,6 +449,7 @@ static const struct block_device_operations brd_fops = {
 #ifdef CONFIG_BLK_DEV_XIP
 	.direct_access =	brd_direct_access,
 #endif
+	.getgeo =		brd_getgeo,
 };
 
 /*

index f841d9e..83e3d22 100644
@@ -455,19 +455,18 @@ static const struct block_device_operations brd_fops = {
 /*
  * And now the modules code and kernel interface.
  */
-static int rd_nr;
-int rd_size = CONFIG_BLK_DEV_RAM_SIZE;
-static int max_part;
-static int part_shift;
-static int part_show = 0;
+static int rd_nr = CONFIG_BLK_DEV_RAM_COUNT;
 module_param(rd_nr, int, S_IRUGO);
 MODULE_PARM_DESC(rd_nr, "Maximum number of brd devices");
+
+int rd_size = CONFIG_BLK_DEV_RAM_SIZE;
 module_param(rd_size, int, S_IRUGO);
 MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes.");
+
+static int max_part = 1;
 module_param(max_part, int, S_IRUGO);
-MODULE_PARM_DESC(max_part, "Maximum number of partitions per RAM disk");
-module_param(part_show, int, S_IRUGO);
-MODULE_PARM_DESC(part_show, "Control RAM disk visibility in /proc/partitions");
+MODULE_PARM_DESC(max_part, "Num Minors to reserve between devices");
+
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_BLOCKDEV_MAJOR(RAMDISK_MAJOR);
 MODULE_ALIAS("rd");

@@ -513,16 +512,15 @@ static struct brd_device *brd_alloc(int i)
 	brd->brd_queue->limits.discard_zeroes_data = 1;
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, brd->brd_queue);
 
-	disk = brd->brd_disk = alloc_disk(1 << part_shift);
+	disk = brd->brd_disk = alloc_disk(max_part);
 	if (!disk)
 		goto out_free_queue;
 	disk->major		= RAMDISK_MAJOR;
-	disk->first_minor	= i << part_shift;
+	disk->first_minor	= i * max_part;
 	disk->fops		= &brd_fops;
 	disk->private_data	= brd;
 	disk->queue		= brd->brd_queue;
-	if (!part_show)
-		disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO;
+	disk->flags		= GENHD_FL_EXT_DEVT;
 	sprintf(disk->disk_name, "ram%d", i);
 	set_capacity(disk, rd_size * 2);
 

@@ -544,10 +542,11 @@ static void brd_free(struct brd_device *brd)
 	kfree(brd);
 }
 
-static struct brd_device *brd_init_one(int i)
+static struct brd_device *brd_init_one(int i, bool *new)
 {
 	struct brd_device *brd;
 
+	*new = false;
 	list_for_each_entry(brd, &brd_devices, brd_list) {
 		if (brd->brd_number == i)
 			goto out;

@@ -558,6 +557,7 @@ static struct brd_device *brd_init_one(int i)
 		add_disk(brd->brd_disk);
 		list_add_tail(&brd->brd_list, &brd_devices);
 	}
+	*new = true;
 out:
 	return brd;
 }

@@ -573,70 +573,46 @@ static struct kobject *brd_probe(dev_t dev, int *part, void *data)
 {
 	struct brd_device *brd;
 	struct kobject *kobj;
+	bool new;
 
 	mutex_lock(&brd_devices_mutex);
-	brd = brd_init_one(MINOR(dev) >> part_shift);
+	brd = brd_init_one(MINOR(dev) / max_part, &new);
 	kobj = brd ? get_disk(brd->brd_disk) : NULL;
 	mutex_unlock(&brd_devices_mutex);
 
-	*part = 0;
+	if (new)
+		*part = 0;
+
 	return kobj;
 }
 
 static int __init brd_init(void)
 {
-	int i, nr;
-	unsigned long range;
 	struct brd_device *brd, *next;
+	int i;
 
 	/*
 	 * brd module now has a feature to instantiate underlying device
 	 * structure on-demand, provided that there is an access dev node.
-	 * However, this will not work well with user space tool that doesn't
-	 * know about such "feature".  In order to not break any existing
-	 * tool, we do the following:
 	 *
-	 * (1) if rd_nr is specified, create that many upfront, and this
-	 *     also becomes a hard limit.
-	 * (2) if rd_nr is not specified, create CONFIG_BLK_DEV_RAM_COUNT
-	 *     (default 16) rd device on module load, user can further
-	 *     extend brd device by create dev node themselves and have
-	 *     kernel automatically instantiate actual device on-demand.
+	 * (1) if rd_nr is specified, create that many upfront. else
+	 *     it defaults to CONFIG_BLK_DEV_RAM_COUNT
+	 * (2) User can further extend brd devices by create dev node themselves
+	 *     and have kernel automatically instantiate actual device
+	 *     on-demand. Example:
+	 *		mknod /path/devnod_name b 1 X	# 1 is the rd major
+	 *		fdisk -l /path/devnod_name
+	 *	If (X / max_part) was not already created it will be created
+	 *	dynamically.
 	 */
 
-	part_shift = 0;
-	if (max_part > 0) {
-		part_shift = fls(max_part);
-
-		/*
-		 * Adjust max_part according to part_shift as it is exported
-		 * to user space so that user can decide correct minor number
-		 * if [s]he want to create more devices.
-		 *
-		 * Note that -1 is required because partition 0 is reserved
-		 * for the whole disk.
-		 */
-		max_part = (1UL << part_shift) - 1;
-	}
-
-	if ((1UL << part_shift) > DISK_MAX_PARTS)
-		return -EINVAL;
-
-	if (rd_nr > 1UL << (MINORBITS - part_shift))
-		return -EINVAL;
-
-	if (rd_nr) {
-		nr = rd_nr;
-		range = rd_nr << part_shift;
-	} else {
-		nr = CONFIG_BLK_DEV_RAM_COUNT;
-		range = 1UL << MINORBITS;
-	}
-
 	if (register_blkdev(RAMDISK_MAJOR, "ramdisk"))
 		return -EIO;
 
-	for (i = 0; i < nr; i++) {
+	if (unlikely(!max_part))
+		max_part = 1;
+
+	for (i = 0; i < rd_nr; i++) {
 		brd = brd_alloc(i);
 		if (!brd)
 			goto out_free;

@@ -648,10 +624,10 @@ static int __init brd_init(void)
 	list_for_each_entry(brd, &brd_devices, brd_list)
 		add_disk(brd->brd_disk);
 
-	blk_register_region(MKDEV(RAMDISK_MAJOR, 0), range,
+	blk_register_region(MKDEV(RAMDISK_MAJOR, 0), 1UL << MINORBITS,
 				  THIS_MODULE, brd_probe, NULL, NULL);
 
-	printk(KERN_INFO "brd: module loaded\n");
+	pr_info("brd: module loaded\n");
 	return 0;
 
 out_free:

@@ -661,21 +637,21 @@ out_free:
 	}
 	unregister_blkdev(RAMDISK_MAJOR, "ramdisk");
 
+	pr_info("brd: module NOT loaded !!!\n");
 	return -ENOMEM;
 }
 
 static void __exit brd_exit(void)
 {
-	unsigned long range;
 	struct brd_device *brd, *next;
 
-	range = rd_nr ? rd_nr << part_shift : 1UL << MINORBITS;
-
 	list_for_each_entry_safe(brd, next, &brd_devices, brd_list)
 		brd_del_one(brd);
 
-	blk_unregister_region(MKDEV(RAMDISK_MAJOR, 0), range);
+	blk_unregister_region(MKDEV(RAMDISK_MAJOR, 0), 1UL << MINORBITS);
 	unregister_blkdev(RAMDISK_MAJOR, "ramdisk");
+
+	pr_info("brd: module unloaded\n");
 }
 
 module_init(brd_init);

index 83e3d22..6cc3034 100644
@@ -503,10 +503,17 @@ static struct brd_device *brd_alloc(int i)
 	brd->brd_queue = blk_alloc_queue(GFP_KERNEL);
 	if (!brd->brd_queue)
 		goto out_free_dev;
+
 	blk_queue_make_request(brd->brd_queue, brd_make_request);
 	blk_queue_max_hw_sectors(brd->brd_queue, 1024);
 	blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY);
 
+	/* This is so fdisk will align partitions on 4k, because of
+	 * direct_access API needing 4k alignment, returning a PFN
+	 */
+	blk_queue_physical_block_size(brd->brd_queue, PAGE_SIZE);
+	brd->brd_queue->limits.io_min = 512; /* Don't use the accessor */
+
 	brd->brd_queue->limits.discard_granularity = PAGE_SIZE;
 	brd->brd_queue->limits.max_discard_sectors = UINT_MAX;
 	brd->brd_queue->limits.discard_zeroes_data = 1;