2007-10-22 05:03:38 +04:00
//#define DEBUG
# include <linux/spinlock.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 11:04:11 +03:00
# include <linux/slab.h>
2007-10-22 05:03:38 +04:00
# include <linux/blkdev.h>
# include <linux/hdreg.h>
2011-07-01 23:56:05 +04:00
# include <linux/module.h>
2012-01-12 09:14:44 +04:00
# include <linux/mutex.h>
2007-10-22 05:03:38 +04:00
# include <linux/virtio.h>
# include <linux/virtio_blk.h>
2007-10-24 15:21:21 +04:00
# include <linux/scatterlist.h>
2011-02-01 23:43:48 +03:00
# include <linux/string_helpers.h>
2011-04-23 22:49:26 +04:00
# include <scsi/scsi_cmnd.h>
2011-10-30 23:29:59 +04:00
# include <linux/idr.h>
2007-10-24 15:21:21 +04:00
2008-01-31 17:53:53 +03:00
# define PART_BITS 4
2007-10-22 05:03:38 +04:00
2011-10-30 23:29:59 +04:00
static int major ;
static DEFINE_IDA ( vd_index_ida ) ;
2011-02-01 23:43:48 +03:00
struct workqueue_struct * virtblk_wq ;
2008-01-31 17:53:53 +03:00
2007-10-22 05:03:38 +04:00
struct virtio_blk
{
struct virtio_device * vdev ;
struct virtqueue * vq ;
/* The disk structure for the kernel. */
struct gendisk * disk ;
mempool_t * pool ;
2011-02-01 23:43:48 +03:00
/* Process context for config space updates */
struct work_struct config_work ;
2012-01-12 09:14:44 +04:00
/* Lock for config space updates */
struct mutex config_lock ;
/* enable config space updates */
bool config_enable ;
2008-12-30 18:26:05 +03:00
/* What host tells us, plus 2 for header & tailer. */
unsigned int sg_elems ;
2011-10-30 23:29:59 +04:00
/* Ida index - used to track minor number allocations. */
int index ;
2007-10-22 05:03:38 +04:00
/* Scatterlist: can be too big for stack. */
2008-12-30 18:26:05 +03:00
struct scatterlist sg [ /*sg_elems*/ ] ;
2007-10-22 05:03:38 +04:00
} ;
struct virtblk_req
{
struct request * req ;
struct virtio_blk_outhdr out_hdr ;
2009-05-18 16:41:30 +04:00
struct virtio_scsi_inhdr in_hdr ;
2008-05-03 06:50:45 +04:00
u8 status ;
2007-10-22 05:03:38 +04:00
} ;
2008-02-05 07:49:57 +03:00
static void blk_done ( struct virtqueue * vq )
2007-10-22 05:03:38 +04:00
{
struct virtio_blk * vblk = vq - > vdev - > priv ;
struct virtblk_req * vbr ;
unsigned int len ;
unsigned long flags ;
2012-05-25 12:03:27 +04:00
spin_lock_irqsave ( vblk - > disk - > queue - > queue_lock , flags ) ;
2010-04-12 17:18:36 +04:00
while ( ( vbr = virtqueue_get_buf ( vblk - > vq , & len ) ) ! = NULL ) {
2008-10-01 18:11:20 +04:00
int error ;
2009-05-18 16:41:30 +04:00
2008-05-03 06:50:45 +04:00
switch ( vbr - > status ) {
2007-10-22 05:03:38 +04:00
case VIRTIO_BLK_S_OK :
2008-10-01 18:11:20 +04:00
error = 0 ;
2007-10-22 05:03:38 +04:00
break ;
case VIRTIO_BLK_S_UNSUPP :
2008-10-01 18:11:20 +04:00
error = - ENOTTY ;
2007-10-22 05:03:38 +04:00
break ;
default :
2008-10-01 18:11:20 +04:00
error = - EIO ;
2007-10-22 05:03:38 +04:00
break ;
}
2010-08-07 20:17:56 +04:00
switch ( vbr - > req - > cmd_type ) {
case REQ_TYPE_BLOCK_PC :
2009-05-18 16:41:30 +04:00
vbr - > req - > resid_len = vbr - > in_hdr . residual ;
vbr - > req - > sense_len = vbr - > in_hdr . sense_len ;
vbr - > req - > errors = vbr - > in_hdr . errors ;
2010-08-07 20:17:56 +04:00
break ;
case REQ_TYPE_SPECIAL :
2010-03-25 08:33:33 +03:00
vbr - > req - > errors = ( error ! = 0 ) ;
2010-08-07 20:17:56 +04:00
break ;
2010-06-18 14:10:18 +04:00
default :
break ;
2010-08-07 20:17:56 +04:00
}
2009-05-18 16:41:30 +04:00
2009-04-23 06:05:19 +04:00
__blk_end_request_all ( vbr - > req , error ) ;
2007-10-22 05:03:38 +04:00
mempool_free ( vbr , vblk - > pool ) ;
}
/* In case queue is stopped waiting for more buffers. */
blk_start_queue ( vblk - > disk - > queue ) ;
2012-05-25 12:03:27 +04:00
spin_unlock_irqrestore ( vblk - > disk - > queue - > queue_lock , flags ) ;
2007-10-22 05:03:38 +04:00
}
static bool do_req ( struct request_queue * q , struct virtio_blk * vblk ,
struct request * req )
{
2009-05-18 16:41:30 +04:00
unsigned long num , out = 0 , in = 0 ;
2007-10-22 05:03:38 +04:00
struct virtblk_req * vbr ;
vbr = mempool_alloc ( vblk - > pool , GFP_ATOMIC ) ;
if ( ! vbr )
/* When another request finishes we'll try again. */
return false ;
vbr - > req = req ;
2010-07-03 12:45:38 +04:00
if ( req - > cmd_flags & REQ_FLUSH ) {
vbr - > out_hdr . type = VIRTIO_BLK_T_FLUSH ;
2010-03-25 08:33:33 +03:00
vbr - > out_hdr . sector = 0 ;
vbr - > out_hdr . ioprio = req_get_ioprio ( vbr - > req ) ;
2010-07-03 12:45:38 +04:00
} else {
switch ( req - > cmd_type ) {
case REQ_TYPE_FS :
vbr - > out_hdr . type = 0 ;
vbr - > out_hdr . sector = blk_rq_pos ( vbr - > req ) ;
vbr - > out_hdr . ioprio = req_get_ioprio ( vbr - > req ) ;
break ;
case REQ_TYPE_BLOCK_PC :
vbr - > out_hdr . type = VIRTIO_BLK_T_SCSI_CMD ;
2009-09-17 21:57:42 +04:00
vbr - > out_hdr . sector = 0 ;
vbr - > out_hdr . ioprio = req_get_ioprio ( vbr - > req ) ;
break ;
2010-07-03 12:45:38 +04:00
case REQ_TYPE_SPECIAL :
vbr - > out_hdr . type = VIRTIO_BLK_T_GET_ID ;
vbr - > out_hdr . sector = 0 ;
vbr - > out_hdr . ioprio = req_get_ioprio ( vbr - > req ) ;
break ;
default :
/* We don't put anything else in the queue. */
BUG ( ) ;
2009-09-17 21:57:42 +04:00
}
2007-10-22 05:03:38 +04:00
}
2009-05-18 16:41:30 +04:00
sg_set_buf ( & vblk - > sg [ out + + ] , & vbr - > out_hdr , sizeof ( vbr - > out_hdr ) ) ;
2007-10-22 05:03:38 +04:00
2009-05-18 16:41:30 +04:00
/*
* If this is a packet command we need a couple of additional headers .
* Behind the normal outhdr we put a segment with the scsi command
* block , and before the normal inhdr we put the sense data and the
* inhdr with additional status information before the normal inhdr .
*/
2010-08-07 20:17:56 +04:00
if ( vbr - > req - > cmd_type = = REQ_TYPE_BLOCK_PC )
2009-05-18 16:41:30 +04:00
sg_set_buf ( & vblk - > sg [ out + + ] , vbr - > req - > cmd , vbr - > req - > cmd_len ) ;
num = blk_rq_map_sg ( q , vbr - > req , vblk - > sg + out ) ;
2010-08-07 20:17:56 +04:00
if ( vbr - > req - > cmd_type = = REQ_TYPE_BLOCK_PC ) {
2011-04-23 22:49:26 +04:00
sg_set_buf ( & vblk - > sg [ num + out + in + + ] , vbr - > req - > sense , SCSI_SENSE_BUFFERSIZE ) ;
2009-05-18 16:41:30 +04:00
sg_set_buf ( & vblk - > sg [ num + out + in + + ] , & vbr - > in_hdr ,
sizeof ( vbr - > in_hdr ) ) ;
}
sg_set_buf ( & vblk - > sg [ num + out + in + + ] , & vbr - > status ,
sizeof ( vbr - > status ) ) ;
if ( num ) {
if ( rq_data_dir ( vbr - > req ) = = WRITE ) {
vbr - > out_hdr . type | = VIRTIO_BLK_T_OUT ;
out + = num ;
} else {
vbr - > out_hdr . type | = VIRTIO_BLK_T_IN ;
in + = num ;
}
2007-10-22 05:03:38 +04:00
}
2012-01-12 09:14:42 +04:00
if ( virtqueue_add_buf ( vblk - > vq , vblk - > sg , out , in , vbr , GFP_ATOMIC ) < 0 ) {
2007-10-22 05:03:38 +04:00
mempool_free ( vbr , vblk - > pool ) ;
return false ;
}
return true ;
}
static void do_virtblk_request ( struct request_queue * q )
{
2009-05-18 16:38:28 +04:00
struct virtio_blk * vblk = q - > queuedata ;
2007-10-22 05:03:38 +04:00
struct request * req ;
unsigned int issued = 0 ;
2009-05-08 06:54:16 +04:00
while ( ( req = blk_peek_request ( q ) ) ! = NULL ) {
2008-12-30 18:26:05 +03:00
BUG_ON ( req - > nr_phys_segments + 2 > vblk - > sg_elems ) ;
2007-10-22 05:03:38 +04:00
/* If this request fails, stop queue and wait for something to
finish to restart it . */
if ( ! do_req ( q , vblk , req ) ) {
blk_stop_queue ( q ) ;
break ;
}
2009-05-08 06:54:16 +04:00
blk_start_request ( req ) ;
2007-10-22 05:03:38 +04:00
issued + + ;
}
if ( issued )
2010-04-12 17:18:36 +04:00
virtqueue_kick ( vblk - > vq ) ;
2007-10-22 05:03:38 +04:00
}
2010-03-25 08:33:33 +03:00
/* return id (s/n) string for *disk to *id_str
*/
static int virtblk_get_id ( struct gendisk * disk , char * id_str )
{
struct virtio_blk * vblk = disk - > private_data ;
struct request * req ;
struct bio * bio ;
2010-10-09 05:42:13 +04:00
int err ;
2010-03-25 08:33:33 +03:00
bio = bio_map_kern ( vblk - > disk - > queue , id_str , VIRTIO_BLK_ID_BYTES ,
GFP_KERNEL ) ;
if ( IS_ERR ( bio ) )
return PTR_ERR ( bio ) ;
req = blk_make_request ( vblk - > disk - > queue , bio , GFP_KERNEL ) ;
if ( IS_ERR ( req ) ) {
bio_put ( bio ) ;
return PTR_ERR ( req ) ;
}
req - > cmd_type = REQ_TYPE_SPECIAL ;
2010-10-09 05:42:13 +04:00
err = blk_execute_rq ( vblk - > disk - > queue , vblk - > disk , req , false ) ;
blk_put_request ( req ) ;
return err ;
2010-03-25 08:33:33 +03:00
}
2010-09-15 03:27:23 +04:00
static int virtblk_ioctl ( struct block_device * bdev , fmode_t mode ,
unsigned int cmd , unsigned long data )
2007-10-22 05:03:38 +04:00
{
2009-05-18 16:41:30 +04:00
struct gendisk * disk = bdev - > bd_disk ;
struct virtio_blk * vblk = disk - > private_data ;
/*
* Only allow the generic SCSI ioctls if the host can support it .
*/
if ( ! virtio_has_feature ( vblk - > vdev , VIRTIO_BLK_F_SCSI ) )
2009-06-20 23:29:41 +04:00
return - ENOTTY ;
2009-05-18 16:41:30 +04:00
2012-01-12 19:01:27 +04:00
return scsi_cmd_blk_ioctl ( bdev , mode , cmd ,
( void __user * ) data ) ;
2007-10-22 05:03:38 +04:00
}
2008-01-23 19:56:50 +03:00
/* We provide getgeo only to please some old bootloader/partitioning tools */
static int virtblk_getgeo ( struct block_device * bd , struct hd_geometry * geo )
{
2008-04-16 22:56:37 +04:00
struct virtio_blk * vblk = bd - > bd_disk - > private_data ;
struct virtio_blk_geometry vgeo ;
int err ;
/* see if the host passed in geometry config */
err = virtio_config_val ( vblk - > vdev , VIRTIO_BLK_F_GEOMETRY ,
offsetof ( struct virtio_blk_config , geometry ) ,
& vgeo ) ;
if ( ! err ) {
geo - > heads = vgeo . heads ;
geo - > sectors = vgeo . sectors ;
geo - > cylinders = vgeo . cylinders ;
} else {
/* some standard values, similar to sd */
geo - > heads = 1 < < 6 ;
geo - > sectors = 1 < < 5 ;
geo - > cylinders = get_capacity ( bd - > bd_disk ) > > 11 ;
}
2008-01-23 19:56:50 +03:00
return 0 ;
}
2009-09-22 04:01:13 +04:00
static const struct block_device_operations virtblk_fops = {
2010-07-08 12:18:46 +04:00
. ioctl = virtblk_ioctl ,
2008-01-23 19:56:50 +03:00
. owner = THIS_MODULE ,
. getgeo = virtblk_getgeo ,
2007-10-22 05:03:38 +04:00
} ;
2008-02-01 11:05:00 +03:00
static int index_to_minor ( int index )
{
return index < < PART_BITS ;
}
2011-10-30 23:29:59 +04:00
static int minor_to_index ( int minor )
{
return minor > > PART_BITS ;
}
2010-06-24 07:19:57 +04:00
static ssize_t virtblk_serial_show ( struct device * dev ,
struct device_attribute * attr , char * buf )
{
struct gendisk * disk = dev_to_disk ( dev ) ;
int err ;
/* sysfs gives us a PAGE_SIZE buffer */
BUILD_BUG_ON ( PAGE_SIZE < VIRTIO_BLK_ID_BYTES ) ;
buf [ VIRTIO_BLK_ID_BYTES ] = ' \0 ' ;
err = virtblk_get_id ( disk , buf ) ;
if ( ! err )
return strlen ( buf ) ;
if ( err = = - EIO ) /* Unsupported? Make it empty. */
return 0 ;
return err ;
}
DEVICE_ATTR ( serial , S_IRUGO , virtblk_serial_show , NULL ) ;
2011-02-01 23:43:48 +03:00
static void virtblk_config_changed_work ( struct work_struct * work )
{
struct virtio_blk * vblk =
container_of ( work , struct virtio_blk , config_work ) ;
struct virtio_device * vdev = vblk - > vdev ;
struct request_queue * q = vblk - > disk - > queue ;
char cap_str_2 [ 10 ] , cap_str_10 [ 10 ] ;
u64 capacity , size ;
2012-01-12 09:14:44 +04:00
mutex_lock ( & vblk - > config_lock ) ;
if ( ! vblk - > config_enable )
goto done ;
2011-02-01 23:43:48 +03:00
/* Host must always specify the capacity. */
vdev - > config - > get ( vdev , offsetof ( struct virtio_blk_config , capacity ) ,
& capacity , sizeof ( capacity ) ) ;
/* If capacity is too big, truncate with warning. */
if ( ( sector_t ) capacity ! = capacity ) {
dev_warn ( & vdev - > dev , " Capacity %llu too large: truncating \n " ,
( unsigned long long ) capacity ) ;
capacity = ( sector_t ) - 1 ;
}
size = capacity * queue_logical_block_size ( q ) ;
string_get_size ( size , STRING_UNITS_2 , cap_str_2 , sizeof ( cap_str_2 ) ) ;
string_get_size ( size , STRING_UNITS_10 , cap_str_10 , sizeof ( cap_str_10 ) ) ;
dev_notice ( & vdev - > dev ,
" new size: %llu %d-byte logical blocks (%s/%s) \n " ,
( unsigned long long ) capacity ,
queue_logical_block_size ( q ) ,
cap_str_10 , cap_str_2 ) ;
set_capacity ( vblk - > disk , capacity ) ;
2012-03-29 12:09:44 +04:00
revalidate_disk ( vblk - > disk ) ;
2012-01-12 09:14:44 +04:00
done :
mutex_unlock ( & vblk - > config_lock ) ;
2011-02-01 23:43:48 +03:00
}
static void virtblk_config_changed ( struct virtio_device * vdev )
{
struct virtio_blk * vblk = vdev - > priv ;
queue_work ( virtblk_wq , & vblk - > config_work ) ;
}
2011-12-22 15:28:29 +04:00
static int init_vq ( struct virtio_blk * vblk )
{
int err = 0 ;
/* We expect one virtqueue, for output. */
vblk - > vq = virtio_find_single_vq ( vblk - > vdev , blk_done , " requests " ) ;
if ( IS_ERR ( vblk - > vq ) )
err = PTR_ERR ( vblk - > vq ) ;
return err ;
}
2012-04-10 11:28:05 +04:00
/*
* Legacy naming scheme used for virtio devices . We are stuck with it for
* virtio blk but don ' t ever use it for any new driver .
*/
static int virtblk_name_format ( char * prefix , int index , char * buf , int buflen )
{
const int base = ' z ' - ' a ' + 1 ;
char * begin = buf + strlen ( prefix ) ;
char * end = buf + buflen ;
char * p ;
int unit ;
p = end - 1 ;
* p = ' \0 ' ;
unit = base ;
do {
if ( p = = begin )
return - EINVAL ;
* - - p = ' a ' + ( index % unit ) ;
index = ( index / unit ) - 1 ;
} while ( index > = 0 ) ;
memmove ( begin , p , end - p ) ;
memcpy ( buf , prefix , strlen ( prefix ) ) ;
return 0 ;
}
2012-07-03 17:19:37 +04:00
static int virtblk_get_cache_mode ( struct virtio_device * vdev )
{
u8 writeback ;
int err ;
err = virtio_config_val ( vdev , VIRTIO_BLK_F_CONFIG_WCE ,
offsetof ( struct virtio_blk_config , wce ) ,
& writeback ) ;
if ( err )
writeback = virtio_has_feature ( vdev , VIRTIO_BLK_F_WCE ) ;
return writeback ;
}
static void virtblk_update_cache_mode ( struct virtio_device * vdev )
{
u8 writeback = virtblk_get_cache_mode ( vdev ) ;
struct virtio_blk * vblk = vdev - > priv ;
if ( writeback )
blk_queue_flush ( vblk - > disk - > queue , REQ_FLUSH ) ;
else
blk_queue_flush ( vblk - > disk - > queue , 0 ) ;
revalidate_disk ( vblk - > disk ) ;
}
static const char * const virtblk_cache_types [ ] = {
" write through " , " write back "
} ;
static ssize_t
virtblk_cache_type_store ( struct device * dev , struct device_attribute * attr ,
const char * buf , size_t count )
{
struct gendisk * disk = dev_to_disk ( dev ) ;
struct virtio_blk * vblk = disk - > private_data ;
struct virtio_device * vdev = vblk - > vdev ;
int i ;
u8 writeback ;
BUG_ON ( ! virtio_has_feature ( vblk - > vdev , VIRTIO_BLK_F_CONFIG_WCE ) ) ;
for ( i = ARRAY_SIZE ( virtblk_cache_types ) ; - - i > = 0 ; )
if ( sysfs_streq ( buf , virtblk_cache_types [ i ] ) )
break ;
if ( i < 0 )
return - EINVAL ;
writeback = i ;
vdev - > config - > set ( vdev ,
offsetof ( struct virtio_blk_config , wce ) ,
& writeback , sizeof ( writeback ) ) ;
virtblk_update_cache_mode ( vdev ) ;
return count ;
}
static ssize_t
virtblk_cache_type_show ( struct device * dev , struct device_attribute * attr ,
char * buf )
{
struct gendisk * disk = dev_to_disk ( dev ) ;
struct virtio_blk * vblk = disk - > private_data ;
u8 writeback = virtblk_get_cache_mode ( vblk - > vdev ) ;
BUG_ON ( writeback > = ARRAY_SIZE ( virtblk_cache_types ) ) ;
return snprintf ( buf , 40 , " %s \n " , virtblk_cache_types [ writeback ] ) ;
}
static const struct device_attribute dev_attr_cache_type_ro =
__ATTR ( cache_type , S_IRUGO ,
virtblk_cache_type_show , NULL ) ;
static const struct device_attribute dev_attr_cache_type_rw =
__ATTR ( cache_type , S_IRUGO | S_IWUSR ,
virtblk_cache_type_show , virtblk_cache_type_store ) ;
2009-05-18 11:39:09 +04:00
static int __devinit virtblk_probe ( struct virtio_device * vdev )
2007-10-22 05:03:38 +04:00
{
struct virtio_blk * vblk ;
2010-02-24 23:22:25 +03:00
struct request_queue * q ;
2011-10-30 23:29:59 +04:00
int err , index ;
2007-10-22 05:03:38 +04:00
u64 cap ;
2010-02-24 23:22:25 +03:00
u32 v , blk_size , sg_elems , opt_io_size ;
u16 min_io_size ;
u8 physical_block_exp , alignment_offset ;
2007-10-22 05:03:38 +04:00
2011-10-30 23:29:59 +04:00
err = ida_simple_get ( & vd_index_ida , 0 , minor_to_index ( 1 < < MINORBITS ) ,
GFP_KERNEL ) ;
if ( err < 0 )
goto out ;
index = err ;
2008-01-31 17:53:53 +03:00
2008-12-30 18:26:05 +03:00
/* We need to know how many segments before we allocate. */
err = virtio_config_val ( vdev , VIRTIO_BLK_F_SEG_MAX ,
offsetof ( struct virtio_blk_config , seg_max ) ,
& sg_elems ) ;
2010-05-25 16:17:54 +04:00
/* We need at least one SG element, whatever they say. */
if ( err | | ! sg_elems )
2008-12-30 18:26:05 +03:00
sg_elems = 1 ;
/* We need an extra sg elements at head and tail. */
sg_elems + = 2 ;
vdev - > priv = vblk = kmalloc ( sizeof ( * vblk ) +
sizeof ( vblk - > sg [ 0 ] ) * sg_elems , GFP_KERNEL ) ;
2007-10-22 05:03:38 +04:00
if ( ! vblk ) {
err = - ENOMEM ;
2011-10-30 23:29:59 +04:00
goto out_free_index ;
2007-10-22 05:03:38 +04:00
}
vblk - > vdev = vdev ;
2008-12-30 18:26:05 +03:00
vblk - > sg_elems = sg_elems ;
sg_init_table ( vblk - > sg , vblk - > sg_elems ) ;
2012-01-12 09:14:44 +04:00
mutex_init ( & vblk - > config_lock ) ;
2011-02-01 23:43:48 +03:00
INIT_WORK ( & vblk - > config_work , virtblk_config_changed_work ) ;
2012-01-12 09:14:44 +04:00
vblk - > config_enable = true ;
2007-10-22 05:03:38 +04:00
2011-12-22 15:28:29 +04:00
err = init_vq ( vblk ) ;
if ( err )
2007-10-22 05:03:38 +04:00
goto out_free_vblk ;
vblk - > pool = mempool_create_kmalloc_pool ( 1 , sizeof ( struct virtblk_req ) ) ;
if ( ! vblk - > pool ) {
err = - ENOMEM ;
goto out_free_vq ;
}
/* FIXME: How many partitions? How long is a piece of string? */
2008-01-31 17:53:53 +03:00
vblk - > disk = alloc_disk ( 1 < < PART_BITS ) ;
2007-10-22 05:03:38 +04:00
if ( ! vblk - > disk ) {
err = - ENOMEM ;
2008-01-31 17:53:53 +03:00
goto out_mempool ;
2007-10-22 05:03:38 +04:00
}
2012-05-25 12:03:27 +04:00
q = vblk - > disk - > queue = blk_init_queue ( do_virtblk_request , NULL ) ;
2010-02-24 23:22:25 +03:00
if ( ! q ) {
2007-10-22 05:03:38 +04:00
err = - ENOMEM ;
goto out_put_disk ;
}
2010-02-24 23:22:25 +03:00
q - > queuedata = vblk ;
2008-10-27 12:45:15 +03:00
2012-04-10 11:28:05 +04:00
virtblk_name_format ( " vd " , index , vblk - > disk - > disk_name , DISK_NAME_LEN ) ;
2008-02-01 11:05:00 +03:00
2007-10-22 05:03:38 +04:00
vblk - > disk - > major = major ;
2008-02-01 11:05:00 +03:00
vblk - > disk - > first_minor = index_to_minor ( index ) ;
2007-10-22 05:03:38 +04:00
vblk - > disk - > private_data = vblk ;
vblk - > disk - > fops = & virtblk_fops ;
2008-03-03 01:00:15 +03:00
vblk - > disk - > driverfs_dev = & vdev - > dev ;
2011-10-30 23:29:59 +04:00
vblk - > index = index ;
2008-01-31 17:53:53 +03:00
2010-09-03 13:56:18 +04:00
/* configure queue flush support */
2012-07-03 17:19:37 +04:00
virtblk_update_cache_mode ( vdev ) ;
2007-10-22 05:03:38 +04:00
2008-05-16 13:17:03 +04:00
/* If disk is read-only in the host, the guest should obey */
if ( virtio_has_feature ( vdev , VIRTIO_BLK_F_RO ) )
set_disk_ro ( vblk - > disk , 1 ) ;
2008-02-05 07:49:56 +03:00
/* Host must always specify the capacity. */
2008-05-03 06:50:49 +04:00
vdev - > config - > get ( vdev , offsetof ( struct virtio_blk_config , capacity ) ,
& cap , sizeof ( cap ) ) ;
2007-10-22 05:03:38 +04:00
/* If capacity is too big, truncate with warning. */
if ( ( sector_t ) cap ! = cap ) {
dev_warn ( & vdev - > dev , " Capacity %llu too large: truncating \n " ,
( unsigned long long ) cap ) ;
cap = ( sector_t ) - 1 ;
}
set_capacity ( vblk - > disk , cap ) ;
2008-12-30 18:26:05 +03:00
/* We can handle whatever the host told us to handle. */
2010-03-10 08:48:32 +03:00
blk_queue_max_segments ( q , vblk - > sg_elems - 2 ) ;
2008-12-30 18:26:05 +03:00
2009-07-18 07:47:45 +04:00
/* No need to bounce any requests */
2010-02-24 23:22:25 +03:00
blk_queue_bounce_limit ( q , BLK_BOUNCE_ANY ) ;
2009-07-18 07:47:45 +04:00
2008-12-30 18:26:04 +03:00
/* No real sector limit. */
2010-03-10 08:48:32 +03:00
blk_queue_max_hw_sectors ( q , - 1U ) ;
2008-12-30 18:26:04 +03:00
2008-02-05 07:49:56 +03:00
/* Host can optionally specify maximum segment size and number of
* segments . */
err = virtio_config_val ( vdev , VIRTIO_BLK_F_SIZE_MAX ,
offsetof ( struct virtio_blk_config , size_max ) ,
& v ) ;
2007-10-22 05:03:38 +04:00
if ( ! err )
2010-02-24 23:22:25 +03:00
blk_queue_max_segment_size ( q , v ) ;
2008-12-30 18:26:04 +03:00
else
2010-02-24 23:22:25 +03:00
blk_queue_max_segment_size ( q , - 1U ) ;
2007-10-22 05:03:38 +04:00
2008-05-29 13:08:26 +04:00
/* Host can optionally specify the block size of the device */
err = virtio_config_val ( vdev , VIRTIO_BLK_F_BLK_SIZE ,
offsetof ( struct virtio_blk_config , blk_size ) ,
& blk_size ) ;
if ( ! err )
2010-02-24 23:22:25 +03:00
blk_queue_logical_block_size ( q , blk_size ) ;
else
blk_size = queue_logical_block_size ( q ) ;
/* Use topology information if available */
err = virtio_config_val ( vdev , VIRTIO_BLK_F_TOPOLOGY ,
offsetof ( struct virtio_blk_config , physical_block_exp ) ,
& physical_block_exp ) ;
if ( ! err & & physical_block_exp )
blk_queue_physical_block_size ( q ,
blk_size * ( 1 < < physical_block_exp ) ) ;
err = virtio_config_val ( vdev , VIRTIO_BLK_F_TOPOLOGY ,
offsetof ( struct virtio_blk_config , alignment_offset ) ,
& alignment_offset ) ;
if ( ! err & & alignment_offset )
blk_queue_alignment_offset ( q , blk_size * alignment_offset ) ;
err = virtio_config_val ( vdev , VIRTIO_BLK_F_TOPOLOGY ,
offsetof ( struct virtio_blk_config , min_io_size ) ,
& min_io_size ) ;
if ( ! err & & min_io_size )
blk_queue_io_min ( q , blk_size * min_io_size ) ;
err = virtio_config_val ( vdev , VIRTIO_BLK_F_TOPOLOGY ,
offsetof ( struct virtio_blk_config , opt_io_size ) ,
& opt_io_size ) ;
if ( ! err & & opt_io_size )
blk_queue_io_opt ( q , blk_size * opt_io_size ) ;
2008-05-29 13:08:26 +04:00
2007-10-22 05:03:38 +04:00
add_disk ( vblk - > disk ) ;
2010-06-24 07:19:57 +04:00
err = device_create_file ( disk_to_dev ( vblk - > disk ) , & dev_attr_serial ) ;
if ( err )
goto out_del_disk ;
2012-07-03 17:19:37 +04:00
if ( virtio_has_feature ( vdev , VIRTIO_BLK_F_CONFIG_WCE ) )
err = device_create_file ( disk_to_dev ( vblk - > disk ) ,
& dev_attr_cache_type_rw ) ;
else
err = device_create_file ( disk_to_dev ( vblk - > disk ) ,
& dev_attr_cache_type_ro ) ;
if ( err )
goto out_del_disk ;
2007-10-22 05:03:38 +04:00
return 0 ;
2010-06-24 07:19:57 +04:00
out_del_disk :
del_gendisk ( vblk - > disk ) ;
blk_cleanup_queue ( vblk - > disk - > queue ) ;
2007-10-22 05:03:38 +04:00
out_put_disk :
put_disk ( vblk - > disk ) ;
out_mempool :
mempool_destroy ( vblk - > pool ) ;
out_free_vq :
2009-06-13 08:16:36 +04:00
vdev - > config - > del_vqs ( vdev ) ;
2007-10-22 05:03:38 +04:00
out_free_vblk :
kfree ( vblk ) ;
2011-10-30 23:29:59 +04:00
out_free_index :
ida_simple_remove ( & vd_index_ida , index ) ;
2007-10-22 05:03:38 +04:00
out :
return err ;
}
2009-05-18 11:39:09 +04:00
static void __devexit virtblk_remove ( struct virtio_device * vdev )
2007-10-22 05:03:38 +04:00
{
struct virtio_blk * vblk = vdev - > priv ;
2011-10-30 23:29:59 +04:00
int index = vblk - > index ;
2007-10-22 05:03:38 +04:00
2012-01-12 09:14:44 +04:00
/* Prevent config work handler from accessing the device. */
mutex_lock ( & vblk - > config_lock ) ;
vblk - > config_enable = false ;
mutex_unlock ( & vblk - > config_lock ) ;
2011-02-01 23:43:48 +03:00
2012-05-25 06:34:47 +04:00
del_gendisk ( vblk - > disk ) ;
2012-05-25 06:34:48 +04:00
blk_cleanup_queue ( vblk - > disk - > queue ) ;
2012-05-25 06:34:47 +04:00
2008-02-05 07:50:03 +03:00
/* Stop all the virtqueues. */
vdev - > config - > reset ( vdev ) ;
2012-01-12 09:14:44 +04:00
flush_work ( & vblk - > config_work ) ;
2007-10-22 05:03:38 +04:00
put_disk ( vblk - > disk ) ;
mempool_destroy ( vblk - > pool ) ;
2009-06-13 08:16:36 +04:00
vdev - > config - > del_vqs ( vdev ) ;
2007-10-22 05:03:38 +04:00
kfree ( vblk ) ;
2011-10-30 23:29:59 +04:00
ida_simple_remove ( & vd_index_ida , index ) ;
2007-10-22 05:03:38 +04:00
}
2011-12-22 15:28:30 +04:00
# ifdef CONFIG_PM
static int virtblk_freeze ( struct virtio_device * vdev )
{
struct virtio_blk * vblk = vdev - > priv ;
/* Ensure we don't receive any more interrupts */
vdev - > config - > reset ( vdev ) ;
/* Prevent config work handler from accessing the device. */
mutex_lock ( & vblk - > config_lock ) ;
vblk - > config_enable = false ;
mutex_unlock ( & vblk - > config_lock ) ;
flush_work ( & vblk - > config_work ) ;
spin_lock_irq ( vblk - > disk - > queue - > queue_lock ) ;
blk_stop_queue ( vblk - > disk - > queue ) ;
spin_unlock_irq ( vblk - > disk - > queue - > queue_lock ) ;
blk_sync_queue ( vblk - > disk - > queue ) ;
vdev - > config - > del_vqs ( vdev ) ;
return 0 ;
}
static int virtblk_restore ( struct virtio_device * vdev )
{
struct virtio_blk * vblk = vdev - > priv ;
int ret ;
vblk - > config_enable = true ;
ret = init_vq ( vdev - > priv ) ;
if ( ! ret ) {
spin_lock_irq ( vblk - > disk - > queue - > queue_lock ) ;
blk_start_queue ( vblk - > disk - > queue ) ;
spin_unlock_irq ( vblk - > disk - > queue - > queue_lock ) ;
}
return ret ;
}
# endif
2010-01-10 15:40:02 +03:00
static const struct virtio_device_id id_table [ ] = {
2007-10-22 05:03:38 +04:00
{ VIRTIO_ID_BLOCK , VIRTIO_DEV_ANY_ID } ,
{ 0 } ,
} ;
2008-05-03 06:50:50 +04:00
static unsigned int features [ ] = {
2010-09-03 13:56:18 +04:00
VIRTIO_BLK_F_SEG_MAX , VIRTIO_BLK_F_SIZE_MAX , VIRTIO_BLK_F_GEOMETRY ,
VIRTIO_BLK_F_RO , VIRTIO_BLK_F_BLK_SIZE , VIRTIO_BLK_F_SCSI ,
2012-07-03 17:19:37 +04:00
VIRTIO_BLK_F_WCE , VIRTIO_BLK_F_TOPOLOGY , VIRTIO_BLK_F_CONFIG_WCE
2008-05-03 06:50:50 +04:00
} ;
virtio_blk: mark virtio_blk with __refdata to kill spurious section mismatch
The variable virtio_blk references the function virtblk_probe() (which
is in .devinit section) and also references the function
virtblk_remove() ( which is in .devexit section). So, virtio_blk
simultaneously refers .devinit and .devexit section. To avoid this
messup, we mark virtio_blk as __refdata.
We were warned by the following warning:
LD drivers/block/built-in.o
WARNING: drivers/block/built-in.o(.data+0xc8dc): Section mismatch in
reference from the variable virtio_blk to the function
.devinit.text:virtblk_probe()
The variable virtio_blk references
the function __devinit virtblk_probe()
If the reference is valid then annotate the
variable with __init* or __refdata (see linux/init.h) or name the variable:
*driver, *_template, *_timer, *_sht, *_ops, *_probe, *_probe_one, *_console,
WARNING: drivers/block/built-in.o(.data+0xc8e0): Section mismatch in
reference from the variable virtio_blk to the function
.devexit.text:virtblk_remove()
The variable virtio_blk references
the function __devexit virtblk_remove()
If the reference is valid then annotate the
variable with __exit* (see linux/init.h) or name the variable:
*driver, *_template, *_timer, *_sht, *_ops, *_probe, *_probe_one, *_console,
Signed-off-by: Rakib Mullick <rakib.mullick@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
2009-07-17 18:13:22 +04:00
/*
* virtio_blk causes spurious section mismatch warning by
* simultaneously referring to a __devinit and a __devexit function .
* Use __refdata to avoid this warning .
*/
static struct virtio_driver __refdata virtio_blk = {
2011-02-01 23:43:48 +03:00
. feature_table = features ,
. feature_table_size = ARRAY_SIZE ( features ) ,
. driver . name = KBUILD_MODNAME ,
. driver . owner = THIS_MODULE ,
. id_table = id_table ,
. probe = virtblk_probe ,
. remove = __devexit_p ( virtblk_remove ) ,
. config_changed = virtblk_config_changed ,
2011-12-22 15:28:30 +04:00
# ifdef CONFIG_PM
. freeze = virtblk_freeze ,
. restore = virtblk_restore ,
# endif
2007-10-22 05:03:38 +04:00
} ;
static int __init init ( void )
{
2011-02-01 23:43:48 +03:00
int error ;
virtblk_wq = alloc_workqueue ( " virtio-blk " , 0 , 0 ) ;
if ( ! virtblk_wq )
return - ENOMEM ;
2008-01-31 17:53:53 +03:00
major = register_blkdev ( 0 , " virtblk " ) ;
2011-02-01 23:43:48 +03:00
if ( major < 0 ) {
error = major ;
goto out_destroy_workqueue ;
}
error = register_virtio_driver ( & virtio_blk ) ;
if ( error )
goto out_unregister_blkdev ;
return 0 ;
out_unregister_blkdev :
unregister_blkdev ( major , " virtblk " ) ;
out_destroy_workqueue :
destroy_workqueue ( virtblk_wq ) ;
return error ;
2007-10-22 05:03:38 +04:00
}
static void __exit fini ( void )
{
2008-01-31 17:53:53 +03:00
unregister_blkdev ( major , " virtblk " ) ;
2007-10-22 05:03:38 +04:00
unregister_virtio_driver ( & virtio_blk ) ;
2011-02-01 23:43:48 +03:00
destroy_workqueue ( virtblk_wq ) ;
2007-10-22 05:03:38 +04:00
}
module_init ( init ) ;
module_exit ( fini ) ;
MODULE_DEVICE_TABLE ( virtio , id_table ) ;
MODULE_DESCRIPTION ( " Virtio block driver " ) ;
MODULE_LICENSE ( " GPL " ) ;