| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <53E2119A.2090803@plexistor.com>
Date: Wed, 06 Aug 2014 14:29:30 +0300
From: Boaz Harrosh <boaz@...xistor.com>
To: Jens Axboe <axboe@...nel.dk>,
Ross Zwisler <ross.zwisler@...ux.intel.com>,
Matthew Wilcox <willy@...ux.intel.com>,
linux-kernel <linux-kernel@...r.kernel.org>
CC: linux-fsdevel <linux-fsdevel@...r.kernel.org>
Subject: [PATCH 1/4] Change direct_access calling convention
From: Matthew Wilcox <matthew.r.wilcox@...el.com>
In order to support accesses to larger chunks of memory, pass in a
'size' parameter (counted in bytes), and return the amount available at
that address.
Add a new helper function, bdev_direct_access(), to handle common
functionality including partition handling, checking for the sector
being page-aligned, and checking the length of the request does not
pass the end of the partition.
[Boaz] checkpatch fixes, add prints.
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@...el.com>
Reviewed-by: Jan Kara <jack@...e.cz>
Signed-off-by: Boaz Harrosh <boaz@...xistor.com>
---
Documentation/filesystems/xip.txt | 15 ++++++++------
arch/powerpc/sysdev/axonram.c | 17 ++++------------
drivers/block/brd.c | 12 +++++------
drivers/s390/block/dcssblk.c | 21 ++++++++-----------
fs/block_dev.c | 43 +++++++++++++++++++++++++++++++++++++++
fs/ext2/xip.c | 30 ++++++++++++---------------
include/linux/blkdev.h | 6 ++++--
7 files changed, 87 insertions(+), 57 deletions(-)
diff --git a/Documentation/filesystems/xip.txt b/Documentation/filesystems/xip.txt
index 0466ee5..b62eabf 100644
--- a/Documentation/filesystems/xip.txt
+++ b/Documentation/filesystems/xip.txt
@@ -28,12 +28,15 @@ Implementation
Execute-in-place is implemented in three steps: block device operation,
address space operation, and file operations.
-A block device operation named direct_access is used to retrieve a
-reference (pointer) to a block on-disk. The reference is supposed to be
-cpu-addressable, physical address and remain valid until the release operation
-is performed. A struct block_device reference is used to address the device,
-and a sector_t argument is used to identify the individual block. As an
-alternative, memory technology devices can be used for this.
+A block device operation named direct_access is used to translate the
+block device sector number to a page frame number (pfn) that identifies
+the physical page for the memory. It also returns a kernel virtual
+address that can be used to access the memory.
+
+The direct_access method takes a 'size' parameter that indicates the
+number of bytes being requested. The function should return the number
+of bytes that it can provide, although it must not exceed the number of
+bytes requested. It may also return a negative errno if an error occurs.
The block device operation is optional, these block devices support it as of
today:
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index 47b6b9f..142892b 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -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 min_t(long, size, bank->size - offset);
}
static const struct block_device_operations axon_ram_devops = {
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index c7d138e..a10a0a9 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -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;
+ /* Could optimistically check to see if the next page in the
+ * file is mapped to the next page of physical RAM */
+ return min_t(long, PAGE_SIZE, size);
}
#endif
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 0f47175..2ee5556 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -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 min_t(long, size, dev_sz - offset);
}
static void
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 6d72746..002d5d6 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -427,6 +427,49 @@ 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)
+{
+ const struct block_device_operations *ops = bdev->bd_disk->fops;
+
+ 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)) {
+ if (get_start_sect(bdev) % (PAGE_SIZE / 512)) {
+ pr_err_ratelimited(
+ "%s: [%s:%d,%d] partition not 4K aligned!!!\n",
+ __func__, bdev->bd_disk->disk_name,
+ MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev));
+ }
+ return -EINVAL;
+ }
+
+ size = ops->direct_access(bdev, sector, addr, pfn, size);
+ return size ? size : -ERANGE;
+}
+EXPORT_SYMBOL_GPL(bdev_direct_access);
+
/*
* pseudo-fs
*/
diff --git a/fs/ext2/xip.c b/fs/ext2/xip.c
index e98171a..a4d5435 100644
--- a/fs/ext2/xip.c
+++ b/fs/ext2/xip.c
@@ -13,18 +13,13 @@
#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 */
+ sector_t sector = block * (PAGE_SIZE / 512);
- BUG_ON(!ops->direct_access);
- return ops->direct_access(bdev, sector, kaddr, pfn);
+ return bdev_direct_access(bdev, sector, kaddr, pfn, size);
}
static inline int
@@ -53,12 +48,13 @@ 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 +73,7 @@ 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 +82,6 @@ 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;
}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8699bcf..bc5ea9e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1613,8 +1613,8 @@ 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 */
@@ -1632,6 +1632,8 @@ 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;
--
1.9.3
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists