A-Team_Digital_Solutions/android_kernel_motorola_sm6375
Watch
2
0
Fork
You've already forked android_kernel_motorola_sm6375
 0
mirror of https://github.com/BobTheBlinker/android_kernel_motorola_sm6375.git synced 2026-10-28 18:51:56 -04:00
Code Issues Projects Releases Packages Wiki Activity

Merge branch 'block-dir' of git://brick.kernel.dk/data/git/linux-2.6-block

Browse source
This commit is contained in:
Linus Torvalds 2005-11-07 08:32:39 -08:00
commit 333c47c847
16 changed files with 32 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

12
drivers/block/Kconfig
View file

@ -409,16 +409,6 @@ config BLK_DEV_INITRD
for details.
#XXX - it makes sense to enable this only for 32-bit subarch's, not for x86_64
#for instance.
config LBD
bool "Support for Large Block Devices"
depends on X86 || (MIPS && 32BIT) || PPC32 || ARCH_S390_31 || SUPERH || UML
help
Say Y here if you want to attach large (bigger than 2TB) discs to
your machine, or if you want to have a raid or loopback device
bigger than 2TB. Otherwise say N.
config CDROM_PKTCDVD
tristate "Packet writing on CD/DVD media"
depends on !UML
@ -455,8 +445,6 @@ config CDROM_PKTCDVD_WCACHE
source "drivers/s390/block/Kconfig"
source "drivers/block/Kconfig.iosched"
config ATA_OVER_ETH
tristate "ATA over Ethernet support"
depends on NET

69
drivers/block/Kconfig.iosched
View file

@ -1,69 +0,0 @@
menu "IO Schedulers"
config IOSCHED_NOOP
bool
default y
---help---
The no-op I/O scheduler is a minimal scheduler that does basic merging
and sorting. Its main uses include non-disk based block devices like
memory devices, and specialised software or hardware environments
that do their own scheduling and require only minimal assistance from
the kernel.
config IOSCHED_AS
tristate "Anticipatory I/O scheduler"
default y
---help---
The anticipatory I/O scheduler is the default disk scheduler. It is
generally a good choice for most environments, but is quite large and
complex when compared to the deadline I/O scheduler, it can also be
slower in some cases especially some database loads.
config IOSCHED_DEADLINE
tristate "Deadline I/O scheduler"
default y
---help---
The deadline I/O scheduler is simple and compact, and is often as
good as the anticipatory I/O scheduler, and in some database
workloads, better. In the case of a single process performing I/O to
a disk at any one time, its behaviour is almost identical to the
anticipatory I/O scheduler and so is a good choice.
config IOSCHED_CFQ
tristate "CFQ I/O scheduler"
default y
---help---
The CFQ I/O scheduler tries to distribute bandwidth equally
among all processes in the system. It should provide a fair
working environment, suitable for desktop systems.
choice
prompt "Default I/O scheduler"
default DEFAULT_AS
help
Select the I/O scheduler which will be used by default for all
block devices.
config DEFAULT_AS
bool "Anticipatory" if IOSCHED_AS
config DEFAULT_DEADLINE
bool "Deadline" if IOSCHED_DEADLINE
config DEFAULT_CFQ
bool "CFQ" if IOSCHED_CFQ
config DEFAULT_NOOP
bool "No-op"
endchoice
config DEFAULT_IOSCHED
string
default "anticipatory" if DEFAULT_AS
default "deadline" if DEFAULT_DEADLINE
default "cfq" if DEFAULT_CFQ
default "noop" if DEFAULT_NOOP
endmenu

14
drivers/block/Makefile
View file

@ -4,21 +4,7 @@
# 12 June 2000, Christoph Hellwig <[email protected]>
# Rewritten to use lists instead of if-statements.
#
# Note : at this point, these files are compiled on all systems.
# In the future, some of these should be built conditionally.
#
#
# NOTE that ll_rw_blk.c must come early in linkage order - it starts the
# kblockd threads
#
obj-y := elevator.o ll_rw_blk.o ioctl.o genhd.o scsi_ioctl.o
obj-$(CONFIG_IOSCHED_NOOP) += noop-iosched.o
obj-$(CONFIG_IOSCHED_AS) += as-iosched.o
obj-$(CONFIG_IOSCHED_DEADLINE) += deadline-iosched.o
obj-$(CONFIG_IOSCHED_CFQ) += cfq-iosched.o
obj-$(CONFIG_MAC_FLOPPY) += swim3.o
obj-$(CONFIG_BLK_DEV_FD) += floppy.o
obj-$(CONFIG_BLK_DEV_FD98) += floppy98.o

2005
drivers/block/as-iosched.c
View file

File diff suppressed because it is too large Load diff

2428
drivers/block/cfq-iosched.c
View file

File diff suppressed because it is too large Load diff

878
drivers/block/deadline-iosched.c
View file

@ -1,878 +0,0 @@
/*
* linux/drivers/block/deadline-iosched.c
*
* Deadline i/o scheduler.
*
* Copyright (C) 2002 Jens Axboe <axboe@suse.de>
*/
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/bio.h>
#include <linux/config.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/compiler.h>
#include <linux/hash.h>
#include <linux/rbtree.h>
/*
* See Documentation/block/deadline-iosched.txt
*/
static int read_expire = HZ / 2; /* max time before a read is submitted. */
static int write_expire = 5 * HZ; /* ditto for writes, these limits are SOFT! */
static int writes_starved = 2; /* max times reads can starve a write */
static int fifo_batch = 16; /* # of sequential requests treated as one
by the above parameters. For throughput. */
static const int deadline_hash_shift = 5;
#define DL_HASH_BLOCK(sec) ((sec) >> 3)
#define DL_HASH_FN(sec) (hash_long(DL_HASH_BLOCK((sec)), deadline_hash_shift))
#define DL_HASH_ENTRIES (1 << deadline_hash_shift)
#define rq_hash_key(rq) ((rq)->sector + (rq)->nr_sectors)
#define list_entry_hash(ptr) list_entry((ptr), struct deadline_rq, hash)
#define ON_HASH(drq) (drq)->on_hash
struct deadline_data {
/*
* run time data
*/
/*
* requests (deadline_rq s) are present on both sort_list and fifo_list
*/
struct rb_root sort_list[2];
struct list_head fifo_list[2];
/*
* next in sort order. read, write or both are NULL
*/
struct deadline_rq *next_drq[2];
struct list_head *hash; /* request hash */
unsigned int batching; /* number of sequential requests made */
sector_t last_sector; /* head position */
unsigned int starved; /* times reads have starved writes */
/*
* settings that change how the i/o scheduler behaves
*/
int fifo_expire[2];
int fifo_batch;
int writes_starved;
int front_merges;
mempool_t *drq_pool;
};
/*
* pre-request data.
*/
struct deadline_rq {
/*
* rbtree index, key is the starting offset
*/
struct rb_node rb_node;
sector_t rb_key;
struct request *request;
/*
* request hash, key is the ending offset (for back merge lookup)
*/
struct list_head hash;
char on_hash;
/*
* expire fifo
*/
struct list_head fifo;
unsigned long expires;
};
static void deadline_move_request(struct deadline_data *dd, struct deadline_rq *drq);
static kmem_cache_t *drq_pool;
#define RQ_DATA(rq) ((struct deadline_rq *) (rq)->elevator_private)
/*
* the back merge hash support functions
*/
static inline void __deadline_del_drq_hash(struct deadline_rq *drq)
{
drq->on_hash = 0;
list_del_init(&drq->hash);
}
static inline void deadline_del_drq_hash(struct deadline_rq *drq)
{
if (ON_HASH(drq))
__deadline_del_drq_hash(drq);
}
static inline void
deadline_add_drq_hash(struct deadline_data *dd, struct deadline_rq *drq)
{
struct request *rq = drq->request;
BUG_ON(ON_HASH(drq));
drq->on_hash = 1;
list_add(&drq->hash, &dd->hash[DL_HASH_FN(rq_hash_key(rq))]);
}
/*
* move hot entry to front of chain
*/
static inline void
deadline_hot_drq_hash(struct deadline_data *dd, struct deadline_rq *drq)
{
struct request *rq = drq->request;
struct list_head *head = &dd->hash[DL_HASH_FN(rq_hash_key(rq))];
if (ON_HASH(drq) && drq->hash.prev != head) {
list_del(&drq->hash);
list_add(&drq->hash, head);
}
}
static struct request *
deadline_find_drq_hash(struct deadline_data *dd, sector_t offset)
{
struct list_head *hash_list = &dd->hash[DL_HASH_FN(offset)];
struct list_head *entry, *next = hash_list->next;
while ((entry = next) != hash_list) {
struct deadline_rq *drq = list_entry_hash(entry);
struct request *__rq = drq->request;
next = entry->next;
BUG_ON(!ON_HASH(drq));
if (!rq_mergeable(__rq)) {
__deadline_del_drq_hash(drq);
continue;
}
if (rq_hash_key(__rq) == offset)
return __rq;
}
return NULL;
}
/*
* rb tree support functions
*/
#define RB_NONE (2)
#define RB_EMPTY(root) ((root)->rb_node == NULL)
#define ON_RB(node) ((node)->rb_color != RB_NONE)
#define RB_CLEAR(node) ((node)->rb_color = RB_NONE)
#define rb_entry_drq(node) rb_entry((node), struct deadline_rq, rb_node)
#define DRQ_RB_ROOT(dd, drq) (&(dd)->sort_list[rq_data_dir((drq)->request)])
#define rq_rb_key(rq) (rq)->sector
static struct deadline_rq *
__deadline_add_drq_rb(struct deadline_data *dd, struct deadline_rq *drq)
{
struct rb_node **p = &DRQ_RB_ROOT(dd, drq)->rb_node;
struct rb_node *parent = NULL;
struct deadline_rq *__drq;
while (*p) {
parent = *p;
__drq = rb_entry_drq(parent);
if (drq->rb_key < __drq->rb_key)
p = &(*p)->rb_left;
else if (drq->rb_key > __drq->rb_key)
p = &(*p)->rb_right;
else
return __drq;
}
rb_link_node(&drq->rb_node, parent, p);
return NULL;
}
static void
deadline_add_drq_rb(struct deadline_data *dd, struct deadline_rq *drq)
{
struct deadline_rq *__alias;
drq->rb_key = rq_rb_key(drq->request);
retry:
__alias = __deadline_add_drq_rb(dd, drq);
if (!__alias) {
rb_insert_color(&drq->rb_node, DRQ_RB_ROOT(dd, drq));
return;
}
deadline_move_request(dd, __alias);
goto retry;
}
static inline void
deadline_del_drq_rb(struct deadline_data *dd, struct deadline_rq *drq)
{
const int data_dir = rq_data_dir(drq->request);
if (dd->next_drq[data_dir] == drq) {
struct rb_node *rbnext = rb_next(&drq->rb_node);
dd->next_drq[data_dir] = NULL;
if (rbnext)
dd->next_drq[data_dir] = rb_entry_drq(rbnext);
}
BUG_ON(!ON_RB(&drq->rb_node));
rb_erase(&drq->rb_node, DRQ_RB_ROOT(dd, drq));
RB_CLEAR(&drq->rb_node);
}
static struct request *
deadline_find_drq_rb(struct deadline_data *dd, sector_t sector, int data_dir)
{
struct rb_node *n = dd->sort_list[data_dir].rb_node;
struct deadline_rq *drq;
while (n) {
drq = rb_entry_drq(n);
if (sector < drq->rb_key)
n = n->rb_left;
else if (sector > drq->rb_key)
n = n->rb_right;
else
return drq->request;
}
return NULL;
}
/*
* deadline_find_first_drq finds the first (lowest sector numbered) request
* for the specified data_dir. Used to sweep back to the start of the disk
* (1-way elevator) after we process the last (highest sector) request.
*/
static struct deadline_rq *
deadline_find_first_drq(struct deadline_data *dd, int data_dir)
{
struct rb_node *n = dd->sort_list[data_dir].rb_node;
for (;;) {
if (n->rb_left == NULL)
return rb_entry_drq(n);
n = n->rb_left;
}
}
/*
* add drq to rbtree and fifo
*/
static void
deadline_add_request(struct request_queue *q, struct request *rq)
{
struct deadline_data *dd = q->elevator->elevator_data;
struct deadline_rq *drq = RQ_DATA(rq);
const int data_dir = rq_data_dir(drq->request);
deadline_add_drq_rb(dd, drq);
/*
* set expire time (only used for reads) and add to fifo list
*/
drq->expires = jiffies + dd->fifo_expire[data_dir];
list_add_tail(&drq->fifo, &dd->fifo_list[data_dir]);
if (rq_mergeable(rq))
deadline_add_drq_hash(dd, drq);
}
/*
* remove rq from rbtree, fifo, and hash
*/
static void deadline_remove_request(request_queue_t *q, struct request *rq)
{
struct deadline_rq *drq = RQ_DATA(rq);
struct deadline_data *dd = q->elevator->elevator_data;
list_del_init(&drq->fifo);
deadline_del_drq_rb(dd, drq);
deadline_del_drq_hash(drq);
}
static int
deadline_merge(request_queue_t *q, struct request **req, struct bio *bio)
{
struct deadline_data *dd = q->elevator->elevator_data;
struct request *__rq;
int ret;
/*
* see if the merge hash can satisfy a back merge
*/
__rq = deadline_find_drq_hash(dd, bio->bi_sector);
if (__rq) {
BUG_ON(__rq->sector + __rq->nr_sectors != bio->bi_sector);
if (elv_rq_merge_ok(__rq, bio)) {
ret = ELEVATOR_BACK_MERGE;
goto out;
}
}
/*
* check for front merge
*/
if (dd->front_merges) {
sector_t rb_key = bio->bi_sector + bio_sectors(bio);
__rq = deadline_find_drq_rb(dd, rb_key, bio_data_dir(bio));
if (__rq) {
BUG_ON(rb_key != rq_rb_key(__rq));
if (elv_rq_merge_ok(__rq, bio)) {
ret = ELEVATOR_FRONT_MERGE;
goto out;
}
}
}
return ELEVATOR_NO_MERGE;
out:
if (ret)
deadline_hot_drq_hash(dd, RQ_DATA(__rq));
*req = __rq;
return ret;
}
static void deadline_merged_request(request_queue_t *q, struct request *req)
{
struct deadline_data *dd = q->elevator->elevator_data;
struct deadline_rq *drq = RQ_DATA(req);
/*
* hash always needs to be repositioned, key is end sector
*/
deadline_del_drq_hash(drq);
deadline_add_drq_hash(dd, drq);
/*
* if the merge was a front merge, we need to reposition request
*/
if (rq_rb_key(req) != drq->rb_key) {
deadline_del_drq_rb(dd, drq);
deadline_add_drq_rb(dd, drq);
}
}
static void
deadline_merged_requests(request_queue_t *q, struct request *req,
struct request *next)
{
struct deadline_data *dd = q->elevator->elevator_data;
struct deadline_rq *drq = RQ_DATA(req);
struct deadline_rq *dnext = RQ_DATA(next);
BUG_ON(!drq);
BUG_ON(!dnext);
/*
* reposition drq (this is the merged request) in hash, and in rbtree
* in case of a front merge
*/
deadline_del_drq_hash(drq);
deadline_add_drq_hash(dd, drq);
if (rq_rb_key(req) != drq->rb_key) {
deadline_del_drq_rb(dd, drq);
deadline_add_drq_rb(dd, drq);
}
/*
* if dnext expires before drq, assign its expire time to drq
* and move into dnext position (dnext will be deleted) in fifo
*/
if (!list_empty(&drq->fifo) && !list_empty(&dnext->fifo)) {
if (time_before(dnext->expires, drq->expires)) {
list_move(&drq->fifo, &dnext->fifo);
drq->expires = dnext->expires;
}
}
/*
* kill knowledge of next, this one is a goner
*/
deadline_remove_request(q, next);
}
/*
* move request from sort list to dispatch queue.
*/
static inline void
deadline_move_to_dispatch(struct deadline_data *dd, struct deadline_rq *drq)
{
request_queue_t *q = drq->request->q;
deadline_remove_request(q, drq->request);
elv_dispatch_add_tail(q, drq->request);
}
/*
* move an entry to dispatch queue
*/
static void
deadline_move_request(struct deadline_data *dd, struct deadline_rq *drq)
{
const int data_dir = rq_data_dir(drq->request);
struct rb_node *rbnext = rb_next(&drq->rb_node);
dd->next_drq[READ] = NULL;
dd->next_drq[WRITE] = NULL;
if (rbnext)
dd->next_drq[data_dir] = rb_entry_drq(rbnext);
dd->last_sector = drq->request->sector + drq->request->nr_sectors;
/*
* take it off the sort and fifo list, move
* to dispatch queue
*/
deadline_move_to_dispatch(dd, drq);
}
#define list_entry_fifo(ptr) list_entry((ptr), struct deadline_rq, fifo)
/*
* deadline_check_fifo returns 0 if there are no expired reads on the fifo,
* 1 otherwise. Requires !list_empty(&dd->fifo_list[data_dir])
*/
static inline int deadline_check_fifo(struct deadline_data *dd, int ddir)
{
struct deadline_rq *drq = list_entry_fifo(dd->fifo_list[ddir].next);
/*
* drq is expired!
*/
if (time_after(jiffies, drq->expires))
return 1;
return 0;
}
/*
* deadline_dispatch_requests selects the best request according to
* read/write expire, fifo_batch, etc
*/
static int deadline_dispatch_requests(request_queue_t *q, int force)
{
struct deadline_data *dd = q->elevator->elevator_data;
const int reads = !list_empty(&dd->fifo_list[READ]);
const int writes = !list_empty(&dd->fifo_list[WRITE]);
struct deadline_rq *drq;
int data_dir;
/*
* batches are currently reads XOR writes
*/
if (dd->next_drq[WRITE])
drq = dd->next_drq[WRITE];
else
drq = dd->next_drq[READ];
if (drq) {
/* we have a "next request" */
if (dd->last_sector != drq->request->sector)
/* end the batch on a non sequential request */
dd->batching += dd->fifo_batch;
if (dd->batching < dd->fifo_batch)
/* we are still entitled to batch */
goto dispatch_request;
}
/*
* at this point we are not running a batch. select the appropriate
* data direction (read / write)
*/
if (reads) {
BUG_ON(RB_EMPTY(&dd->sort_list[READ]));
if (writes && (dd->starved++ >= dd->writes_starved))
goto dispatch_writes;
data_dir = READ;
goto dispatch_find_request;
}
/*
* there are either no reads or writes have been starved
*/
if (writes) {
dispatch_writes:
BUG_ON(RB_EMPTY(&dd->sort_list[WRITE]));
dd->starved = 0;
data_dir = WRITE;
goto dispatch_find_request;
}
return 0;
dispatch_find_request:
/*
* we are not running a batch, find best request for selected data_dir
*/
if (deadline_check_fifo(dd, data_dir)) {
/* An expired request exists - satisfy it */
dd->batching = 0;
drq = list_entry_fifo(dd->fifo_list[data_dir].next);
} else if (dd->next_drq[data_dir]) {
/*
* The last req was the same dir and we have a next request in
* sort order. No expired requests so continue on from here.
*/
drq = dd->next_drq[data_dir];
} else {
/*
* The last req was the other direction or we have run out of
* higher-sectored requests. Go back to the lowest sectored
* request (1 way elevator) and start a new batch.
*/
dd->batching = 0;
drq = deadline_find_first_drq(dd, data_dir);
}
dispatch_request:
/*
* drq is the selected appropriate request.
*/
dd->batching++;
deadline_move_request(dd, drq);
return 1;
}
static int deadline_queue_empty(request_queue_t *q)
{
struct deadline_data *dd = q->elevator->elevator_data;
return list_empty(&dd->fifo_list[WRITE])
&& list_empty(&dd->fifo_list[READ]);
}
static struct request *
deadline_former_request(request_queue_t *q, struct request *rq)
{
struct deadline_rq *drq = RQ_DATA(rq);
struct rb_node *rbprev = rb_prev(&drq->rb_node);
if (rbprev)
return rb_entry_drq(rbprev)->request;
return NULL;
}
static struct request *
deadline_latter_request(request_queue_t *q, struct request *rq)
{
struct deadline_rq *drq = RQ_DATA(rq);
struct rb_node *rbnext = rb_next(&drq->rb_node);
if (rbnext)
return rb_entry_drq(rbnext)->request;
return NULL;
}
static void deadline_exit_queue(elevator_t *e)
{
struct deadline_data *dd = e->elevator_data;
BUG_ON(!list_empty(&dd->fifo_list[READ]));
BUG_ON(!list_empty(&dd->fifo_list[WRITE]));
mempool_destroy(dd->drq_pool);
kfree(dd->hash);
kfree(dd);
}
/*
* initialize elevator private data (deadline_data), and alloc a drq for
* each request on the free lists
*/
static int deadline_init_queue(request_queue_t *q, elevator_t *e)
{
struct deadline_data *dd;
int i;
if (!drq_pool)
return -ENOMEM;
dd = kmalloc_node(sizeof(*dd), GFP_KERNEL, q->node);
if (!dd)
return -ENOMEM;
memset(dd, 0, sizeof(*dd));
dd->hash = kmalloc_node(sizeof(struct list_head)*DL_HASH_ENTRIES,
GFP_KERNEL, q->node);
if (!dd->hash) {
kfree(dd);
return -ENOMEM;
}
dd->drq_pool = mempool_create_node(BLKDEV_MIN_RQ, mempool_alloc_slab,
mempool_free_slab, drq_pool, q->node);
if (!dd->drq_pool) {
kfree(dd->hash);
kfree(dd);
return -ENOMEM;
}
for (i = 0; i < DL_HASH_ENTRIES; i++)
INIT_LIST_HEAD(&dd->hash[i]);
INIT_LIST_HEAD(&dd->fifo_list[READ]);
INIT_LIST_HEAD(&dd->fifo_list[WRITE]);
dd->sort_list[READ] = RB_ROOT;
dd->sort_list[WRITE] = RB_ROOT;
dd->fifo_expire[READ] = read_expire;
dd->fifo_expire[WRITE] = write_expire;
dd->writes_starved = writes_starved;
dd->front_merges = 1;
dd->fifo_batch = fifo_batch;
e->elevator_data = dd;
return 0;
}
static void deadline_put_request(request_queue_t *q, struct request *rq)
{
struct deadline_data *dd = q->elevator->elevator_data;
struct deadline_rq *drq = RQ_DATA(rq);
mempool_free(drq, dd->drq_pool);
rq->elevator_private = NULL;
}
static int
deadline_set_request(request_queue_t *q, struct request *rq, struct bio *bio,
gfp_t gfp_mask)
{
struct deadline_data *dd = q->elevator->elevator_data;
struct deadline_rq *drq;
drq = mempool_alloc(dd->drq_pool, gfp_mask);
if (drq) {
memset(drq, 0, sizeof(*drq));
RB_CLEAR(&drq->rb_node);
drq->request = rq;
INIT_LIST_HEAD(&drq->hash);
drq->on_hash = 0;
INIT_LIST_HEAD(&drq->fifo);
rq->elevator_private = drq;
return 0;
}
return 1;
}
/*
* sysfs parts below
*/
struct deadline_fs_entry {
struct attribute attr;
ssize_t (*show)(struct deadline_data *, char *);
ssize_t (*store)(struct deadline_data *, const char *, size_t);
};
static ssize_t
deadline_var_show(int var, char *page)
{
return sprintf(page, "%d\n", var);
}
static ssize_t
deadline_var_store(int *var, const char *page, size_t count)
{
char *p = (char *) page;
*var = simple_strtol(p, &p, 10);
return count;
}
#define SHOW_FUNCTION(__FUNC, __VAR, __CONV) \
static ssize_t __FUNC(struct deadline_data *dd, char *page) \
{ \
int __data = __VAR; \
if (__CONV) \
__data = jiffies_to_msecs(__data); \
return deadline_var_show(__data, (page)); \
}
SHOW_FUNCTION(deadline_readexpire_show, dd->fifo_expire[READ], 1);
SHOW_FUNCTION(deadline_writeexpire_show, dd->fifo_expire[WRITE], 1);
SHOW_FUNCTION(deadline_writesstarved_show, dd->writes_starved, 0);
SHOW_FUNCTION(deadline_frontmerges_show, dd->front_merges, 0);
SHOW_FUNCTION(deadline_fifobatch_show, dd->fifo_batch, 0);
#undef SHOW_FUNCTION
#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \
static ssize_t __FUNC(struct deadline_data *dd, const char *page, size_t count) \
{ \
int __data; \
int ret = deadline_var_store(&__data, (page), count); \
if (__data < (MIN)) \
__data = (MIN); \
else if (__data > (MAX)) \
__data = (MAX); \
if (__CONV) \
*(__PTR) = msecs_to_jiffies(__data); \
else \
*(__PTR) = __data; \
return ret; \
}
STORE_FUNCTION(deadline_readexpire_store, &dd->fifo_expire[READ], 0, INT_MAX, 1);
STORE_FUNCTION(deadline_writeexpire_store, &dd->fifo_expire[WRITE], 0, INT_MAX, 1);
STORE_FUNCTION(deadline_writesstarved_store, &dd->writes_starved, INT_MIN, INT_MAX, 0);
STORE_FUNCTION(deadline_frontmerges_store, &dd->front_merges, 0, 1, 0);
STORE_FUNCTION(deadline_fifobatch_store, &dd->fifo_batch, 0, INT_MAX, 0);
#undef STORE_FUNCTION
static struct deadline_fs_entry deadline_readexpire_entry = {
.attr = {.name = "read_expire", .mode = S_IRUGO | S_IWUSR },
.show = deadline_readexpire_show,
.store = deadline_readexpire_store,
};
static struct deadline_fs_entry deadline_writeexpire_entry = {
.attr = {.name = "write_expire", .mode = S_IRUGO | S_IWUSR },
.show = deadline_writeexpire_show,
.store = deadline_writeexpire_store,
};
static struct deadline_fs_entry deadline_writesstarved_entry = {
.attr = {.name = "writes_starved", .mode = S_IRUGO | S_IWUSR },
.show = deadline_writesstarved_show,
.store = deadline_writesstarved_store,
};
static struct deadline_fs_entry deadline_frontmerges_entry = {
.attr = {.name = "front_merges", .mode = S_IRUGO | S_IWUSR },
.show = deadline_frontmerges_show,
.store = deadline_frontmerges_store,
};
static struct deadline_fs_entry deadline_fifobatch_entry = {
.attr = {.name = "fifo_batch", .mode = S_IRUGO | S_IWUSR },
.show = deadline_fifobatch_show,
.store = deadline_fifobatch_store,
};
static struct attribute *default_attrs[] = {
&deadline_readexpire_entry.attr,
&deadline_writeexpire_entry.attr,
&deadline_writesstarved_entry.attr,
&deadline_frontmerges_entry.attr,
&deadline_fifobatch_entry.attr,
NULL,
};
#define to_deadline(atr) container_of((atr), struct deadline_fs_entry, attr)
static ssize_t
deadline_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
{
elevator_t *e = container_of(kobj, elevator_t, kobj);
struct deadline_fs_entry *entry = to_deadline(attr);
if (!entry->show)
return -EIO;
return entry->show(e->elevator_data, page);
}
static ssize_t
deadline_attr_store(struct kobject *kobj, struct attribute *attr,
const char *page, size_t length)
{
elevator_t *e = container_of(kobj, elevator_t, kobj);
struct deadline_fs_entry *entry = to_deadline(attr);
if (!entry->store)
return -EIO;
return entry->store(e->elevator_data, page, length);
}
static struct sysfs_ops deadline_sysfs_ops = {
.show = deadline_attr_show,
.store = deadline_attr_store,
};
static struct kobj_type deadline_ktype = {
.sysfs_ops = &deadline_sysfs_ops,
.default_attrs = default_attrs,
};
static struct elevator_type iosched_deadline = {
.ops = {
.elevator_merge_fn = deadline_merge,
.elevator_merged_fn = deadline_merged_request,
.elevator_merge_req_fn = deadline_merged_requests,
.elevator_dispatch_fn = deadline_dispatch_requests,
.elevator_add_req_fn = deadline_add_request,
.elevator_queue_empty_fn = deadline_queue_empty,
.elevator_former_req_fn = deadline_former_request,
.elevator_latter_req_fn = deadline_latter_request,
.elevator_set_req_fn = deadline_set_request,
.elevator_put_req_fn = deadline_put_request,
.elevator_init_fn = deadline_init_queue,
.elevator_exit_fn = deadline_exit_queue,
},
.elevator_ktype = &deadline_ktype,
.elevator_name = "deadline",
.elevator_owner = THIS_MODULE,
};
static int __init deadline_init(void)
{
int ret;
drq_pool = kmem_cache_create("deadline_drq", sizeof(struct deadline_rq),
0, 0, NULL, NULL);
if (!drq_pool)
return -ENOMEM;
ret = elv_register(&iosched_deadline);
if (ret)
kmem_cache_destroy(drq_pool);
return ret;
}
static void __exit deadline_exit(void)
{
kmem_cache_destroy(drq_pool);
elv_unregister(&iosched_deadline);
}
module_init(deadline_init);
module_exit(deadline_exit);
MODULE_AUTHOR("Jens Axboe");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("deadline IO scheduler");

802
drivers/block/elevator.c
View file

@ -1,802 +0,0 @@
/*
* linux/drivers/block/elevator.c
*
* Block device elevator/IO-scheduler.
*
* Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
*
* 30042000 Jens Axboe <axboe@suse.de> :
*
* Split the elevator a bit so that it is possible to choose a different
* one or even write a new "plug in". There are three pieces:
* - elevator_fn, inserts a new request in the queue list
* - elevator_merge_fn, decides whether a new buffer can be merged with
* an existing request
* - elevator_dequeue_fn, called when a request is taken off the active list
*
* 20082000 Dave Jones <davej@suse.de> :
* Removed tests for max-bomb-segments, which was breaking elvtune
* when run without -bN
*
* Jens:
* - Rework again to work with bio instead of buffer_heads
* - loose bi_dev comparisons, partition handling is right now
* - completely modularize elevator setup and teardown
*
*/
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/bio.h>
#include <linux/config.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/compiler.h>
#include <linux/delay.h>
#include <asm/uaccess.h>
static DEFINE_SPINLOCK(elv_list_lock);
static LIST_HEAD(elv_list);
/*
* can we safely merge with this request?
*/
inline int elv_rq_merge_ok(struct request *rq, struct bio *bio)
{
if (!rq_mergeable(rq))
return 0;
/*
* different data direction or already started, don't merge
*/
if (bio_data_dir(bio) != rq_data_dir(rq))
return 0;
/*
* same device and no special stuff set, merge is ok
*/
if (rq->rq_disk == bio->bi_bdev->bd_disk &&
!rq->waiting && !rq->special)
return 1;
return 0;
}
EXPORT_SYMBOL(elv_rq_merge_ok);
inline int elv_try_merge(struct request *__rq, struct bio *bio)
{
int ret = ELEVATOR_NO_MERGE;
/*
* we can merge and sequence is ok, check if it's possible
*/
if (elv_rq_merge_ok(__rq, bio)) {
if (__rq->sector + __rq->nr_sectors == bio->bi_sector)
ret = ELEVATOR_BACK_MERGE;
else if (__rq->sector - bio_sectors(bio) == bio->bi_sector)
ret = ELEVATOR_FRONT_MERGE;
}
return ret;
}
EXPORT_SYMBOL(elv_try_merge);
static struct elevator_type *elevator_find(const char *name)
{
struct elevator_type *e = NULL;
struct list_head *entry;
list_for_each(entry, &elv_list) {
struct elevator_type *__e;
__e = list_entry(entry, struct elevator_type, list);
if (!strcmp(__e->elevator_name, name)) {
e = __e;
break;
}
}
return e;
}
static void elevator_put(struct elevator_type *e)
{
module_put(e->elevator_owner);
}
static struct elevator_type *elevator_get(const char *name)
{
struct elevator_type *e;
spin_lock_irq(&elv_list_lock);
e = elevator_find(name);
if (e && !try_module_get(e->elevator_owner))
e = NULL;
spin_unlock_irq(&elv_list_lock);
return e;
}
static int elevator_attach(request_queue_t *q, struct elevator_type *e,
struct elevator_queue *eq)
{
int ret = 0;
memset(eq, 0, sizeof(*eq));
eq->ops = &e->ops;
eq->elevator_type = e;
q->elevator = eq;
if (eq->ops->elevator_init_fn)
ret = eq->ops->elevator_init_fn(q, eq);
return ret;
}
static char chosen_elevator[16];
static void elevator_setup_default(void)
{
struct elevator_type *e;
/*
* If default has not been set, use the compiled-in selection.
*/
if (!chosen_elevator[0])
strcpy(chosen_elevator, CONFIG_DEFAULT_IOSCHED);
/*
* If the given scheduler is not available, fall back to no-op.
*/
if (!(e = elevator_find(chosen_elevator)))
strcpy(chosen_elevator, "noop");
elevator_put(e);
}
static int __init elevator_setup(char *str)
{
strncpy(chosen_elevator, str, sizeof(chosen_elevator) - 1);
return 0;
}
__setup("elevator=", elevator_setup);
int elevator_init(request_queue_t *q, char *name)
{
struct elevator_type *e = NULL;
struct elevator_queue *eq;
int ret = 0;
INIT_LIST_HEAD(&q->queue_head);
q->last_merge = NULL;
q->end_sector = 0;
q->boundary_rq = NULL;
elevator_setup_default();
if (!name)
name = chosen_elevator;
e = elevator_get(name);
if (!e)
return -EINVAL;
eq = kmalloc(sizeof(struct elevator_queue), GFP_KERNEL);
if (!eq) {
elevator_put(e->elevator_type);
return -ENOMEM;
}
ret = elevator_attach(q, e, eq);
if (ret) {
kfree(eq);
elevator_put(e->elevator_type);
}
return ret;
}
void elevator_exit(elevator_t *e)
{
if (e->ops->elevator_exit_fn)
e->ops->elevator_exit_fn(e);
elevator_put(e->elevator_type);
e->elevator_type = NULL;
kfree(e);
}
/*
* Insert rq into dispatch queue of q. Queue lock must be held on
* entry. If sort != 0, rq is sort-inserted; otherwise, rq will be
* appended to the dispatch queue. To be used by specific elevators.
*/
void elv_dispatch_sort(request_queue_t *q, struct request *rq)
{
sector_t boundary;
struct list_head *entry;
if (q->last_merge == rq)
q->last_merge = NULL;
boundary = q->end_sector;
list_for_each_prev(entry, &q->queue_head) {
struct request *pos = list_entry_rq(entry);
if (pos->flags & (REQ_SOFTBARRIER|REQ_HARDBARRIER|REQ_STARTED))
break;
if (rq->sector >= boundary) {
if (pos->sector < boundary)
continue;
} else {
if (pos->sector >= boundary)
break;
}
if (rq->sector >= pos->sector)
break;
}
list_add(&rq->queuelist, entry);
}
int elv_merge(request_queue_t *q, struct request **req, struct bio *bio)
{
elevator_t *e = q->elevator;
int ret;
if (q->last_merge) {
ret = elv_try_merge(q->last_merge, bio);
if (ret != ELEVATOR_NO_MERGE) {
*req = q->last_merge;
return ret;
}
}
if (e->ops->elevator_merge_fn)
return e->ops->elevator_merge_fn(q, req, bio);
return ELEVATOR_NO_MERGE;
}
void elv_merged_request(request_queue_t *q, struct request *rq)
{
elevator_t *e = q->elevator;
if (e->ops->elevator_merged_fn)
e->ops->elevator_merged_fn(q, rq);
q->last_merge = rq;
}
void elv_merge_requests(request_queue_t *q, struct request *rq,
struct request *next)
{
elevator_t *e = q->elevator;
if (e->ops->elevator_merge_req_fn)
e->ops->elevator_merge_req_fn(q, rq, next);
q->last_merge = rq;
}
void elv_requeue_request(request_queue_t *q, struct request *rq)
{
elevator_t *e = q->elevator;
/*
* it already went through dequeue, we need to decrement the
* in_flight count again
*/
if (blk_account_rq(rq)) {
q->in_flight--;
if (blk_sorted_rq(rq) && e->ops->elevator_deactivate_req_fn)
e->ops->elevator_deactivate_req_fn(q, rq);
}
rq->flags &= ~REQ_STARTED;
/*
* if this is the flush, requeue the original instead and drop the flush
*/
if (rq->flags & REQ_BAR_FLUSH) {
clear_bit(QUEUE_FLAG_FLUSH, &q->queue_flags);
rq = rq->end_io_data;
}
__elv_add_request(q, rq, ELEVATOR_INSERT_FRONT, 0);
}
void __elv_add_request(request_queue_t *q, struct request *rq, int where,
int plug)
{
if (rq->flags & (REQ_SOFTBARRIER | REQ_HARDBARRIER)) {
/*
* barriers implicitly indicate back insertion
*/
if (where == ELEVATOR_INSERT_SORT)
where = ELEVATOR_INSERT_BACK;
/*
* this request is scheduling boundary, update end_sector
*/
if (blk_fs_request(rq)) {
q->end_sector = rq_end_sector(rq);
q->boundary_rq = rq;
}
} else if (!(rq->flags & REQ_ELVPRIV) && where == ELEVATOR_INSERT_SORT)
where = ELEVATOR_INSERT_BACK;
if (plug)
blk_plug_device(q);
rq->q = q;
switch (where) {
case ELEVATOR_INSERT_FRONT:
rq->flags |= REQ_SOFTBARRIER;
list_add(&rq->queuelist, &q->queue_head);
break;
case ELEVATOR_INSERT_BACK:
rq->flags |= REQ_SOFTBARRIER;
while (q->elevator->ops->elevator_dispatch_fn(q, 1))
;
list_add_tail(&rq->queuelist, &q->queue_head);
/*
* We kick the queue here for the following reasons.
* - The elevator might have returned NULL previously
* to delay requests and returned them now. As the
* queue wasn't empty before this request, ll_rw_blk
* won't run the queue on return, resulting in hang.
* - Usually, back inserted requests won't be merged
* with anything. There's no point in delaying queue
* processing.
*/
blk_remove_plug(q);
q->request_fn(q);
break;
case ELEVATOR_INSERT_SORT:
BUG_ON(!blk_fs_request(rq));
rq->flags |= REQ_SORTED;
if (q->last_merge == NULL && rq_mergeable(rq))
q->last_merge = rq;
/*
* Some ioscheds (cfq) run q->request_fn directly, so
* rq cannot be accessed after calling
* elevator_add_req_fn.
*/
q->elevator->ops->elevator_add_req_fn(q, rq);
break;
default:
printk(KERN_ERR "%s: bad insertion point %d\n",
__FUNCTION__, where);
BUG();
}
if (blk_queue_plugged(q)) {
int nrq = q->rq.count[READ] + q->rq.count[WRITE]
- q->in_flight;
if (nrq >= q->unplug_thresh)
__generic_unplug_device(q);
}
}
void elv_add_request(request_queue_t *q, struct request *rq, int where,
int plug)
{
unsigned long flags;
spin_lock_irqsave(q->queue_lock, flags);
__elv_add_request(q, rq, where, plug);
spin_unlock_irqrestore(q->queue_lock, flags);
}
static inline struct request *__elv_next_request(request_queue_t *q)
{
struct request *rq;
if (unlikely(list_empty(&q->queue_head) &&
!q->elevator->ops->elevator_dispatch_fn(q, 0)))
return NULL;
rq = list_entry_rq(q->queue_head.next);
/*
* if this is a barrier write and the device has to issue a
* flush sequence to support it, check how far we are
*/
if (blk_fs_request(rq) && blk_barrier_rq(rq)) {
BUG_ON(q->ordered == QUEUE_ORDERED_NONE);
if (q->ordered == QUEUE_ORDERED_FLUSH &&
!blk_barrier_preflush(rq))
rq = blk_start_pre_flush(q, rq);
}
return rq;
}
struct request *elv_next_request(request_queue_t *q)
{
struct request *rq;
int ret;
while ((rq = __elv_next_request(q)) != NULL) {
if (!(rq->flags & REQ_STARTED)) {
elevator_t *e = q->elevator;
/*
* This is the first time the device driver
* sees this request (possibly after
* requeueing). Notify IO scheduler.
*/
if (blk_sorted_rq(rq) &&
e->ops->elevator_activate_req_fn)
e->ops->elevator_activate_req_fn(q, rq);
/*
* just mark as started even if we don't start
* it, a request that has been delayed should
* not be passed by new incoming requests
*/
rq->flags |= REQ_STARTED;
}
if (!q->boundary_rq || q->boundary_rq == rq) {
q->end_sector = rq_end_sector(rq);
q->boundary_rq = NULL;
}
if ((rq->flags & REQ_DONTPREP) || !q->prep_rq_fn)
break;
ret = q->prep_rq_fn(q, rq);
if (ret == BLKPREP_OK) {
break;
} else if (ret == BLKPREP_DEFER) {
/*
* the request may have been (partially) prepped.
* we need to keep this request in the front to
* avoid resource deadlock. REQ_STARTED will
* prevent other fs requests from passing this one.
*/
rq = NULL;
break;
} else if (ret == BLKPREP_KILL) {
int nr_bytes = rq->hard_nr_sectors << 9;
if (!nr_bytes)
nr_bytes = rq->data_len;
blkdev_dequeue_request(rq);
rq->flags |= REQ_QUIET;
end_that_request_chunk(rq, 0, nr_bytes);
end_that_request_last(rq);
} else {
printk(KERN_ERR "%s: bad return=%d\n", __FUNCTION__,
ret);
break;
}
}
return rq;
}
void elv_dequeue_request(request_queue_t *q, struct request *rq)
{
BUG_ON(list_empty(&rq->queuelist));
list_del_init(&rq->queuelist);
/*
* the time frame between a request being removed from the lists
* and to it is freed is accounted as io that is in progress at
* the driver side.
*/
if (blk_account_rq(rq))
q->in_flight++;
}
int elv_queue_empty(request_queue_t *q)
{
elevator_t *e = q->elevator;
if (!list_empty(&q->queue_head))
return 0;
if (e->ops->elevator_queue_empty_fn)
return e->ops->elevator_queue_empty_fn(q);
return 1;
}
struct request *elv_latter_request(request_queue_t *q, struct request *rq)
{
struct list_head *next;
elevator_t *e = q->elevator;
if (e->ops->elevator_latter_req_fn)
return e->ops->elevator_latter_req_fn(q, rq);
next = rq->queuelist.next;
if (next != &q->queue_head && next != &rq->queuelist)
return list_entry_rq(next);
return NULL;
}
struct request *elv_former_request(request_queue_t *q, struct request *rq)
{
struct list_head *prev;
elevator_t *e = q->elevator;
if (e->ops->elevator_former_req_fn)
return e->ops->elevator_former_req_fn(q, rq);
prev = rq->queuelist.prev;
if (prev != &q->queue_head && prev != &rq->queuelist)
return list_entry_rq(prev);
return NULL;
}
int elv_set_request(request_queue_t *q, struct request *rq, struct bio *bio,
gfp_t gfp_mask)
{
elevator_t *e = q->elevator;
if (e->ops->elevator_set_req_fn)
return e->ops->elevator_set_req_fn(q, rq, bio, gfp_mask);
rq->elevator_private = NULL;
return 0;
}
void elv_put_request(request_queue_t *q, struct request *rq)
{
elevator_t *e = q->elevator;
if (e->ops->elevator_put_req_fn)
e->ops->elevator_put_req_fn(q, rq);
}
int elv_may_queue(request_queue_t *q, int rw, struct bio *bio)
{
elevator_t *e = q->elevator;
if (e->ops->elevator_may_queue_fn)
return e->ops->elevator_may_queue_fn(q, rw, bio);
return ELV_MQUEUE_MAY;
}
void elv_completed_request(request_queue_t *q, struct request *rq)
{
elevator_t *e = q->elevator;
/*
* request is released from the driver, io must be done
*/
if (blk_account_rq(rq)) {
q->in_flight--;
if (blk_sorted_rq(rq) && e->ops->elevator_completed_req_fn)
e->ops->elevator_completed_req_fn(q, rq);
}
}
int elv_register_queue(struct request_queue *q)
{
elevator_t *e = q->elevator;
e->kobj.parent = kobject_get(&q->kobj);
if (!e->kobj.parent)
return -EBUSY;
snprintf(e->kobj.name, KOBJ_NAME_LEN, "%s", "iosched");
e->kobj.ktype = e->elevator_type->elevator_ktype;
return kobject_register(&e->kobj);
}
void elv_unregister_queue(struct request_queue *q)
{
if (q) {
elevator_t *e = q->elevator;
kobject_unregister(&e->kobj);
kobject_put(&q->kobj);
}
}
int elv_register(struct elevator_type *e)
{
spin_lock_irq(&elv_list_lock);
if (elevator_find(e->elevator_name))
BUG();
list_add_tail(&e->list, &elv_list);
spin_unlock_irq(&elv_list_lock);
printk(KERN_INFO "io scheduler %s registered", e->elevator_name);
if (!strcmp(e->elevator_name, chosen_elevator))
printk(" (default)");
printk("\n");
return 0;
}
EXPORT_SYMBOL_GPL(elv_register);
void elv_unregister(struct elevator_type *e)
{
struct task_struct *g, *p;
/*
* Iterate every thread in the process to remove the io contexts.
*/
read_lock(&tasklist_lock);
do_each_thread(g, p) {
struct io_context *ioc = p->io_context;
if (ioc && ioc->cic) {
ioc->cic->exit(ioc->cic);
ioc->cic->dtor(ioc->cic);
ioc->cic = NULL;
}
if (ioc && ioc->aic) {
ioc->aic->exit(ioc->aic);
ioc->aic->dtor(ioc->aic);
ioc->aic = NULL;
}
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
spin_lock_irq(&elv_list_lock);
list_del_init(&e->list);
spin_unlock_irq(&elv_list_lock);
}
EXPORT_SYMBOL_GPL(elv_unregister);
/*
* switch to new_e io scheduler. be careful not to introduce deadlocks -
* we don't free the old io scheduler, before we have allocated what we
* need for the new one. this way we have a chance of going back to the old
* one, if the new one fails init for some reason.
*/
static void elevator_switch(request_queue_t *q, struct elevator_type *new_e)
{
elevator_t *old_elevator, *e;
/*
* Allocate new elevator
*/
e = kmalloc(sizeof(elevator_t), GFP_KERNEL);
if (!e)
goto error;
/*
* Turn on BYPASS and drain all requests w/ elevator private data
*/
spin_lock_irq(q->queue_lock);
set_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
while (q->elevator->ops->elevator_dispatch_fn(q, 1))
;
while (q->rq.elvpriv) {
spin_unlock_irq(q->queue_lock);
msleep(10);
spin_lock_irq(q->queue_lock);
}
spin_unlock_irq(q->queue_lock);
/*
* unregister old elevator data
*/
elv_unregister_queue(q);
old_elevator = q->elevator;
/*
* attach and start new elevator
*/
if (elevator_attach(q, new_e, e))
goto fail;
if (elv_register_queue(q))
goto fail_register;
/*
* finally exit old elevator and turn off BYPASS.
*/
elevator_exit(old_elevator);
clear_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
return;
fail_register:
/*
* switch failed, exit the new io scheduler and reattach the old
* one again (along with re-adding the sysfs dir)
*/
elevator_exit(e);
e = NULL;
fail:
q->elevator = old_elevator;
elv_register_queue(q);
clear_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
kfree(e);
error:
elevator_put(new_e);
printk(KERN_ERR "elevator: switch to %s failed\n",new_e->elevator_name);
}
ssize_t elv_iosched_store(request_queue_t *q, const char *name, size_t count)
{
char elevator_name[ELV_NAME_MAX];
struct elevator_type *e;
memset(elevator_name, 0, sizeof(elevator_name));
strncpy(elevator_name, name, sizeof(elevator_name));
if (elevator_name[strlen(elevator_name) - 1] == '\n')
elevator_name[strlen(elevator_name) - 1] = '\0';
e = elevator_get(elevator_name);
if (!e) {
printk(KERN_ERR "elevator: type %s not found\n", elevator_name);
return -EINVAL;
}
if (!strcmp(elevator_name, q->elevator->elevator_type->elevator_name)) {
elevator_put(e);
return count;
}
elevator_switch(q, e);
return count;
}
ssize_t elv_iosched_show(request_queue_t *q, char *name)
{
elevator_t *e = q->elevator;
struct elevator_type *elv = e->elevator_type;
struct list_head *entry;
int len = 0;
spin_lock_irq(q->queue_lock);
list_for_each(entry, &elv_list) {
struct elevator_type *__e;
__e = list_entry(entry, struct elevator_type, list);
if (!strcmp(elv->elevator_name, __e->elevator_name))
len += sprintf(name+len, "[%s] ", elv->elevator_name);
else
len += sprintf(name+len, "%s ", __e->elevator_name);
}
spin_unlock_irq(q->queue_lock);
len += sprintf(len+name, "\n");
return len;
}
EXPORT_SYMBOL(elv_dispatch_sort);
EXPORT_SYMBOL(elv_add_request);
EXPORT_SYMBOL(__elv_add_request);
EXPORT_SYMBOL(elv_requeue_request);
EXPORT_SYMBOL(elv_next_request);
EXPORT_SYMBOL(elv_dequeue_request);
EXPORT_SYMBOL(elv_queue_empty);
EXPORT_SYMBOL(elv_completed_request);
EXPORT_SYMBOL(elevator_exit);
EXPORT_SYMBOL(elevator_init);

726
drivers/block/genhd.c
View file

@ -1,726 +0,0 @@
/*
* gendisk handling
*/
#include <linux/config.h>
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/genhd.h>
#include <linux/kernel.h>
#include <linux/blkdev.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/kmod.h>
#include <linux/kobj_map.h>
#include <linux/buffer_head.h>
#define MAX_PROBE_HASH 255 /* random */
static struct subsystem block_subsys;
static DECLARE_MUTEX(block_subsys_sem);
/*
* Can be deleted altogether. Later.
*
*/
static struct blk_major_name {
struct blk_major_name *next;
int major;
char name[16];
} *major_names[MAX_PROBE_HASH];
/* index in the above - for now: assume no multimajor ranges */
static inline int major_to_index(int major)
{
return major % MAX_PROBE_HASH;
}
#ifdef CONFIG_PROC_FS
/* get block device names in somewhat random order */
int get_blkdev_list(char *p, int used)
{
struct blk_major_name *n;
int i, len;
len = snprintf(p, (PAGE_SIZE-used), "\nBlock devices:\n");
down(&block_subsys_sem);
for (i = 0; i < ARRAY_SIZE(major_names); i++) {
for (n = major_names[i]; n; n = n->next) {
/*
* If the curent string plus the 5 extra characters
* in the line would run us off the page, then we're done
*/
if ((len + used + strlen(n->name) + 5) >= PAGE_SIZE)
goto page_full;
len += sprintf(p+len, "%3d %s\n",
n->major, n->name);
}
}
page_full:
up(&block_subsys_sem);
return len;
}
#endif
int register_blkdev(unsigned int major, const char *name)
{
struct blk_major_name **n, *p;
int index, ret = 0;
down(&block_subsys_sem);
/* temporary */
if (major == 0) {
for (index = ARRAY_SIZE(major_names)-1; index > 0; index--) {
if (major_names[index] == NULL)
break;
}
if (index == 0) {
printk("register_blkdev: failed to get major for %s\n",
name);
ret = -EBUSY;
goto out;
}
major = index;
ret = major;
}
p = kmalloc(sizeof(struct blk_major_name), GFP_KERNEL);
if (p == NULL) {
ret = -ENOMEM;
goto out;
}
p->major = major;
strlcpy(p->name, name, sizeof(p->name));
p->next = NULL;
index = major_to_index(major);
for (n = &major_names[index]; *n; n = &(*n)->next) {
if ((*n)->major == major)
break;
}
if (!*n)
*n = p;
else
ret = -EBUSY;
if (ret < 0) {
printk("register_blkdev: cannot get major %d for %s\n",
major, name);
kfree(p);
}
out:
up(&block_subsys_sem);
return ret;
}
EXPORT_SYMBOL(register_blkdev);
/* todo: make void - error printk here */
int unregister_blkdev(unsigned int major, const char *name)
{
struct blk_major_name **n;
struct blk_major_name *p = NULL;
int index = major_to_index(major);
int ret = 0;
down(&block_subsys_sem);
for (n = &major_names[index]; *n; n = &(*n)->next)
if ((*n)->major == major)
break;
if (!*n || strcmp((*n)->name, name))
ret = -EINVAL;
else {
p = *n;
*n = p->next;
}
up(&block_subsys_sem);
kfree(p);
return ret;
}
EXPORT_SYMBOL(unregister_blkdev);
static struct kobj_map *bdev_map;
/*
* Register device numbers dev..(dev+range-1)
* range must be nonzero
* The hash chain is sorted on range, so that subranges can override.
*/
void blk_register_region(dev_t dev, unsigned long range, struct module *module,
struct kobject *(*probe)(dev_t, int *, void *),
int (*lock)(dev_t, void *), void *data)
{
kobj_map(bdev_map, dev, range, module, probe, lock, data);
}
EXPORT_SYMBOL(blk_register_region);
void blk_unregister_region(dev_t dev, unsigned long range)
{
kobj_unmap(bdev_map, dev, range);
}
EXPORT_SYMBOL(blk_unregister_region);
static struct kobject *exact_match(dev_t dev, int *part, void *data)
{
struct gendisk *p = data;
return &p->kobj;
}
static int exact_lock(dev_t dev, void *data)
{
struct gendisk *p = data;
if (!get_disk(p))
return -1;
return 0;
}
/**
* add_disk - add partitioning information to kernel list
* @disk: per-device partitioning information
*
* This function registers the partitioning information in @disk
* with the kernel.
*/
void add_disk(struct gendisk *disk)
{
disk->flags |= GENHD_FL_UP;
blk_register_region(MKDEV(disk->major, disk->first_minor),
disk->minors, NULL, exact_match, exact_lock, disk);
register_disk(disk);
blk_register_queue(disk);
}
EXPORT_SYMBOL(add_disk);
EXPORT_SYMBOL(del_gendisk); /* in partitions/check.c */
void unlink_gendisk(struct gendisk *disk)
{
blk_unregister_queue(disk);
blk_unregister_region(MKDEV(disk->major, disk->first_minor),
disk->minors);
}
#define to_disk(obj) container_of(obj,struct gendisk,kobj)
/**
* get_gendisk - get partitioning information for a given device
* @dev: device to get partitioning information for
*
* This function gets the structure containing partitioning
* information for the given device @dev.
*/
struct gendisk *get_gendisk(dev_t dev, int *part)
{
struct kobject *kobj = kobj_lookup(bdev_map, dev, part);
return kobj ? to_disk(kobj) : NULL;
}
#ifdef CONFIG_PROC_FS
/* iterator */
static void *part_start(struct seq_file *part, loff_t *pos)
{
struct list_head *p;
loff_t l = *pos;
down(&block_subsys_sem);
list_for_each(p, &block_subsys.kset.list)
if (!l--)
return list_entry(p, struct gendisk, kobj.entry);
return NULL;
}
static void *part_next(struct seq_file *part, void *v, loff_t *pos)
{
struct list_head *p = ((struct gendisk *)v)->kobj.entry.next;
++*pos;
return p==&block_subsys.kset.list ? NULL :
list_entry(p, struct gendisk, kobj.entry);
}
static void part_stop(struct seq_file *part, void *v)
{
up(&block_subsys_sem);
}
static int show_partition(struct seq_file *part, void *v)
{
struct gendisk *sgp = v;
int n;
char buf[BDEVNAME_SIZE];
if (&sgp->kobj.entry == block_subsys.kset.list.next)
seq_puts(part, "major minor #blocks name\n\n");
/* Don't show non-partitionable removeable devices or empty devices */
if (!get_capacity(sgp) ||
(sgp->minors == 1 && (sgp->flags & GENHD_FL_REMOVABLE)))
return 0;
if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO)
return 0;
/* show the full disk and all non-0 size partitions of it */
seq_printf(part, "%4d %4d %10llu %s\n",
sgp->major, sgp->first_minor,
(unsigned long long)get_capacity(sgp) >> 1,
disk_name(sgp, 0, buf));
for (n = 0; n < sgp->minors - 1; n++) {
if (!sgp->part[n])
continue;
if (sgp->part[n]->nr_sects == 0)
continue;
seq_printf(part, "%4d %4d %10llu %s\n",
sgp->major, n + 1 + sgp->first_minor,
(unsigned long long)sgp->part[n]->nr_sects >> 1 ,
disk_name(sgp, n + 1, buf));
}
return 0;
}
struct seq_operations partitions_op = {
.start =part_start,
.next = part_next,
.stop = part_stop,
.show = show_partition
};
#endif
extern int blk_dev_init(void);
static struct kobject *base_probe(dev_t dev, int *part, void *data)
{
if (request_module("block-major-%d-%d", MAJOR(dev), MINOR(dev)) > 0)
/* Make old-style 2.4 aliases work */
request_module("block-major-%d", MAJOR(dev));
return NULL;
}
static int __init genhd_device_init(void)
{
bdev_map = kobj_map_init(base_probe, &block_subsys_sem);
blk_dev_init();
subsystem_register(&block_subsys);
return 0;
}
subsys_initcall(genhd_device_init);
/*
* kobject & sysfs bindings for block devices
*/
static ssize_t disk_attr_show(struct kobject *kobj, struct attribute *attr,
char *page)
{
struct gendisk *disk = to_disk(kobj);
struct disk_attribute *disk_attr =
container_of(attr,struct disk_attribute,attr);
ssize_t ret = -EIO;
if (disk_attr->show)
ret = disk_attr->show(disk,page);
return ret;
}
static ssize_t disk_attr_store(struct kobject * kobj, struct attribute * attr,
const char *page, size_t count)
{
struct gendisk *disk = to_disk(kobj);
struct disk_attribute *disk_attr =
container_of(attr,struct disk_attribute,attr);
ssize_t ret = 0;
if (disk_attr->store)
ret = disk_attr->store(disk, page, count);
return ret;
}
static struct sysfs_ops disk_sysfs_ops = {
.show = &disk_attr_show,
.store = &disk_attr_store,
};
static ssize_t disk_uevent_store(struct gendisk * disk,
const char *buf, size_t count)
{
kobject_hotplug(&disk->kobj, KOBJ_ADD);
return count;
}
static ssize_t disk_dev_read(struct gendisk * disk, char *page)
{
dev_t base = MKDEV(disk->major, disk->first_minor);
return print_dev_t(page, base);
}
static ssize_t disk_range_read(struct gendisk * disk, char *page)
{
return sprintf(page, "%d\n", disk->minors);
}
static ssize_t disk_removable_read(struct gendisk * disk, char *page)
{
return sprintf(page, "%d\n",
(disk->flags & GENHD_FL_REMOVABLE ? 1 : 0));
}
static ssize_t disk_size_read(struct gendisk * disk, char *page)
{
return sprintf(page, "%llu\n", (unsigned long long)get_capacity(disk));
}
static ssize_t disk_stats_read(struct gendisk * disk, char *page)
{
preempt_disable();
disk_round_stats(disk);
preempt_enable();
return sprintf(page,
"%8u %8u %8llu %8u "
"%8u %8u %8llu %8u "
"%8u %8u %8u"
"\n",
disk_stat_read(disk, ios[0]), disk_stat_read(disk, merges[0]),
(unsigned long long)disk_stat_read(disk, sectors[0]),
jiffies_to_msecs(disk_stat_read(disk, ticks[0])),
disk_stat_read(disk, ios[1]), disk_stat_read(disk, merges[1]),
(unsigned long long)disk_stat_read(disk, sectors[1]),
jiffies_to_msecs(disk_stat_read(disk, ticks[1])),
disk->in_flight,
jiffies_to_msecs(disk_stat_read(disk, io_ticks)),
jiffies_to_msecs(disk_stat_read(disk, time_in_queue)));
}
static struct disk_attribute disk_attr_uevent = {
.attr = {.name = "uevent", .mode = S_IWUSR },
.store = disk_uevent_store
};
static struct disk_attribute disk_attr_dev = {
.attr = {.name = "dev", .mode = S_IRUGO },
.show = disk_dev_read
};
static struct disk_attribute disk_attr_range = {
.attr = {.name = "range", .mode = S_IRUGO },
.show = disk_range_read
};
static struct disk_attribute disk_attr_removable = {
.attr = {.name = "removable", .mode = S_IRUGO },
.show = disk_removable_read
};
static struct disk_attribute disk_attr_size = {
.attr = {.name = "size", .mode = S_IRUGO },
.show = disk_size_read
};
static struct disk_attribute disk_attr_stat = {
.attr = {.name = "stat", .mode = S_IRUGO },
.show = disk_stats_read
};
static struct attribute * default_attrs[] = {
&disk_attr_uevent.attr,
&disk_attr_dev.attr,
&disk_attr_range.attr,
&disk_attr_removable.attr,
&disk_attr_size.attr,
&disk_attr_stat.attr,
NULL,
};
static void disk_release(struct kobject * kobj)
{
struct gendisk *disk = to_disk(kobj);
kfree(disk->random);
kfree(disk->part);
free_disk_stats(disk);
kfree(disk);
}
static struct kobj_type ktype_block = {
.release = disk_release,
.sysfs_ops = &disk_sysfs_ops,
.default_attrs = default_attrs,
};
extern struct kobj_type ktype_part;
static int block_hotplug_filter(struct kset *kset, struct kobject *kobj)
{
struct kobj_type *ktype = get_ktype(kobj);
return ((ktype == &ktype_block) || (ktype == &ktype_part));
}
static int block_hotplug(struct kset *kset, struct kobject *kobj, char **envp,
int num_envp, char *buffer, int buffer_size)
{
struct kobj_type *ktype = get_ktype(kobj);
struct device *physdev;
struct gendisk *disk;
struct hd_struct *part;
int length = 0;
int i = 0;
if (ktype == &ktype_block) {
disk = container_of(kobj, struct gendisk, kobj);
add_hotplug_env_var(envp, num_envp, &i, buffer, buffer_size,
&length, "MINOR=%u", disk->first_minor);
} else if (ktype == &ktype_part) {
disk = container_of(kobj->parent, struct gendisk, kobj);
part = container_of(kobj, struct hd_struct, kobj);
add_hotplug_env_var(envp, num_envp, &i, buffer, buffer_size,
&length, "MINOR=%u",
disk->first_minor + part->partno);
} else
return 0;
add_hotplug_env_var(envp, num_envp, &i, buffer, buffer_size, &length,
"MAJOR=%u", disk->major);
/* add physical device, backing this device */
physdev = disk->driverfs_dev;
if (physdev) {
char *path = kobject_get_path(&physdev->kobj, GFP_KERNEL);
add_hotplug_env_var(envp, num_envp, &i, buffer, buffer_size,
&length, "PHYSDEVPATH=%s", path);
kfree(path);
if (physdev->bus)
add_hotplug_env_var(envp, num_envp, &i,
buffer, buffer_size, &length,
"PHYSDEVBUS=%s",
physdev->bus->name);
if (physdev->driver)
add_hotplug_env_var(envp, num_envp, &i,
buffer, buffer_size, &length,
"PHYSDEVDRIVER=%s",
physdev->driver->name);
}
/* terminate, set to next free slot, shrink available space */
envp[i] = NULL;
envp = &envp[i];
num_envp -= i;
buffer = &buffer[length];
buffer_size -= length;
return 0;
}
static struct kset_hotplug_ops block_hotplug_ops = {
.filter = block_hotplug_filter,
.hotplug = block_hotplug,
};
/* declare block_subsys. */
static decl_subsys(block, &ktype_block, &block_hotplug_ops);
/*
* aggregate disk stat collector. Uses the same stats that the sysfs
* entries do, above, but makes them available through one seq_file.
* Watching a few disks may be efficient through sysfs, but watching
* all of them will be more efficient through this interface.
*
* The output looks suspiciously like /proc/partitions with a bunch of
* extra fields.
*/
/* iterator */
static void *diskstats_start(struct seq_file *part, loff_t *pos)
{
loff_t k = *pos;
struct list_head *p;
down(&block_subsys_sem);
list_for_each(p, &block_subsys.kset.list)
if (!k--)
return list_entry(p, struct gendisk, kobj.entry);
return NULL;
}
static void *diskstats_next(struct seq_file *part, void *v, loff_t *pos)
{
struct list_head *p = ((struct gendisk *)v)->kobj.entry.next;
++*pos;
return p==&block_subsys.kset.list ? NULL :
list_entry(p, struct gendisk, kobj.entry);
}
static void diskstats_stop(struct seq_file *part, void *v)
{
up(&block_subsys_sem);
}
static int diskstats_show(struct seq_file *s, void *v)
{
struct gendisk *gp = v;
char buf[BDEVNAME_SIZE];
int n = 0;
/*
if (&sgp->kobj.entry == block_subsys.kset.list.next)
seq_puts(s, "major minor name"
" rio rmerge rsect ruse wio wmerge "
"wsect wuse running use aveq"
"\n\n");
*/
preempt_disable();
disk_round_stats(gp);
preempt_enable();
seq_printf(s, "%4d %4d %s %u %u %llu %u %u %u %llu %u %u %u %u\n",
gp->major, n + gp->first_minor, disk_name(gp, n, buf),
disk_stat_read(gp, ios[0]), disk_stat_read(gp, merges[0]),
(unsigned long long)disk_stat_read(gp, sectors[0]),
jiffies_to_msecs(disk_stat_read(gp, ticks[0])),
disk_stat_read(gp, ios[1]), disk_stat_read(gp, merges[1]),
(unsigned long long)disk_stat_read(gp, sectors[1]),
jiffies_to_msecs(disk_stat_read(gp, ticks[1])),
gp->in_flight,
jiffies_to_msecs(disk_stat_read(gp, io_ticks)),
jiffies_to_msecs(disk_stat_read(gp, time_in_queue)));
/* now show all non-0 size partitions of it */
for (n = 0; n < gp->minors - 1; n++) {
struct hd_struct *hd = gp->part[n];
if (hd && hd->nr_sects)
seq_printf(s, "%4d %4d %s %u %u %u %u\n",
gp->major, n + gp->first_minor + 1,
disk_name(gp, n + 1, buf),
hd->ios[0], hd->sectors[0],
hd->ios[1], hd->sectors[1]);
}
return 0;
}
struct seq_operations diskstats_op = {
.start = diskstats_start,
.next = diskstats_next,
.stop = diskstats_stop,
.show = diskstats_show
};
struct gendisk *alloc_disk(int minors)
{
return alloc_disk_node(minors, -1);
}
struct gendisk *alloc_disk_node(int minors, int node_id)
{
struct gendisk *disk;
disk = kmalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id);
if (disk) {
memset(disk, 0, sizeof(struct gendisk));
if (!init_disk_stats(disk)) {
kfree(disk);
return NULL;
}
if (minors > 1) {
int size = (minors - 1) * sizeof(struct hd_struct *);
disk->part = kmalloc_node(size, GFP_KERNEL, node_id);
if (!disk->part) {
kfree(disk);
return NULL;
}
memset(disk->part, 0, size);
}
disk->minors = minors;
kobj_set_kset_s(disk,block_subsys);
kobject_init(&disk->kobj);
rand_initialize_disk(disk);
}
return disk;
}
EXPORT_SYMBOL(alloc_disk);
EXPORT_SYMBOL(alloc_disk_node);
struct kobject *get_disk(struct gendisk *disk)
{
struct module *owner;
struct kobject *kobj;
if (!disk->fops)
return NULL;
owner = disk->fops->owner;
if (owner && !try_module_get(owner))
return NULL;
kobj = kobject_get(&disk->kobj);
if (kobj == NULL) {
module_put(owner);
return NULL;
}
return kobj;
}
EXPORT_SYMBOL(get_disk);
void put_disk(struct gendisk *disk)
{
if (disk)
kobject_put(&disk->kobj);
}
EXPORT_SYMBOL(put_disk);
void set_device_ro(struct block_device *bdev, int flag)
{
if (bdev->bd_contains != bdev)
bdev->bd_part->policy = flag;
else
bdev->bd_disk->policy = flag;
}
EXPORT_SYMBOL(set_device_ro);
void set_disk_ro(struct gendisk *disk, int flag)
{
int i;
disk->policy = flag;
for (i = 0; i < disk->minors - 1; i++)
if (disk->part[i]) disk->part[i]->policy = flag;
}
EXPORT_SYMBOL(set_disk_ro);
int bdev_read_only(struct block_device *bdev)
{
if (!bdev)
return 0;
else if (bdev->bd_contains != bdev)
return bdev->bd_part->policy;
else
return bdev->bd_disk->policy;
}
EXPORT_SYMBOL(bdev_read_only);
int invalidate_partition(struct gendisk *disk, int index)
{
int res = 0;
struct block_device *bdev = bdget_disk(disk, index);
if (bdev) {
fsync_bdev(bdev);
res = __invalidate_device(bdev);
bdput(bdev);
}
return res;
}
EXPORT_SYMBOL(invalidate_partition);

275
drivers/block/ioctl.c
View file

@ -1,275 +0,0 @@
#include <linux/sched.h> /* for capable() */
#include <linux/blkdev.h>
#include <linux/blkpg.h>
#include <linux/backing-dev.h>
#include <linux/buffer_head.h>
#include <linux/smp_lock.h>
#include <asm/uaccess.h>
static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user *arg)
{
struct block_device *bdevp;
struct gendisk *disk;
struct blkpg_ioctl_arg a;
struct blkpg_partition p;
long long start, length;
int part;
int i;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
if (copy_from_user(&a, arg, sizeof(struct blkpg_ioctl_arg)))
return -EFAULT;
if (copy_from_user(&p, a.data, sizeof(struct blkpg_partition)))
return -EFAULT;
disk = bdev->bd_disk;
if (bdev != bdev->bd_contains)
return -EINVAL;
part = p.pno;
if (part <= 0 || part >= disk->minors)
return -EINVAL;
switch (a.op) {
case BLKPG_ADD_PARTITION:
start = p.start >> 9;
length = p.length >> 9;
/* check for fit in a hd_struct */
if (sizeof(sector_t) == sizeof(long) &&
sizeof(long long) > sizeof(long)) {
long pstart = start, plength = length;
if (pstart != start || plength != length
|| pstart < 0 || plength < 0)
return -EINVAL;
}
/* partition number in use? */
down(&bdev->bd_sem);
if (disk->part[part - 1]) {
up(&bdev->bd_sem);
return -EBUSY;
}
/* overlap? */
for (i = 0; i < disk->minors - 1; i++) {
struct hd_struct *s = disk->part[i];
if (!s)
continue;
if (!(start+length <= s->start_sect ||
start >= s->start_sect + s->nr_sects)) {
up(&bdev->bd_sem);
return -EBUSY;
}
}
/* all seems OK */
add_partition(disk, part, start, length);
up(&bdev->bd_sem);
return 0;
case BLKPG_DEL_PARTITION:
if (!disk->part[part-1])
return -ENXIO;
if (disk->part[part - 1]->nr_sects == 0)
return -ENXIO;
bdevp = bdget_disk(disk, part);
if (!bdevp)
return -ENOMEM;
down(&bdevp->bd_sem);
if (bdevp->bd_openers) {
up(&bdevp->bd_sem);
bdput(bdevp);
return -EBUSY;
}
/* all seems OK */
fsync_bdev(bdevp);
invalidate_bdev(bdevp, 0);
down(&bdev->bd_sem);
delete_partition(disk, part);
up(&bdev->bd_sem);
up(&bdevp->bd_sem);
bdput(bdevp);
return 0;
default:
return -EINVAL;
}
}
static int blkdev_reread_part(struct block_device *bdev)
{
struct gendisk *disk = bdev->bd_disk;
int res;
if (disk->minors == 1 || bdev != bdev->bd_contains)
return -EINVAL;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
if (down_trylock(&bdev->bd_sem))
return -EBUSY;
res = rescan_partitions(disk, bdev);
up(&bdev->bd_sem);
return res;
}
static int put_ushort(unsigned long arg, unsigned short val)
{
return put_user(val, (unsigned short __user *)arg);
}
static int put_int(unsigned long arg, int val)
{
return put_user(val, (int __user *)arg);
}
static int put_long(unsigned long arg, long val)
{
return put_user(val, (long __user *)arg);
}
static int put_ulong(unsigned long arg, unsigned long val)
{
return put_user(val, (unsigned long __user *)arg);
}
static int put_u64(unsigned long arg, u64 val)
{
return put_user(val, (u64 __user *)arg);
}
static int blkdev_locked_ioctl(struct file *file, struct block_device *bdev,
unsigned cmd, unsigned long arg)
{
struct backing_dev_info *bdi;
int ret, n;
switch (cmd) {
case BLKRAGET:
case BLKFRAGET:
if (!arg)
return -EINVAL;
bdi = blk_get_backing_dev_info(bdev);
if (bdi == NULL)
return -ENOTTY;
return put_long(arg, (bdi->ra_pages * PAGE_CACHE_SIZE) / 512);
case BLKROGET:
return put_int(arg, bdev_read_only(bdev) != 0);
case BLKBSZGET: /* get the logical block size (cf. BLKSSZGET) */
return put_int(arg, block_size(bdev));
case BLKSSZGET: /* get block device hardware sector size */
return put_int(arg, bdev_hardsect_size(bdev));
case BLKSECTGET:
return put_ushort(arg, bdev_get_queue(bdev)->max_sectors);
case BLKRASET:
case BLKFRASET:
if(!capable(CAP_SYS_ADMIN))
return -EACCES;
bdi = blk_get_backing_dev_info(bdev);
if (bdi == NULL)
return -ENOTTY;
bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE;
return 0;
case BLKBSZSET:
/* set the logical block size */
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
if (!arg)
return -EINVAL;
if (get_user(n, (int __user *) arg))
return -EFAULT;
if (bd_claim(bdev, file) < 0)
return -EBUSY;
ret = set_blocksize(bdev, n);
bd_release(bdev);
return ret;
case BLKPG:
return blkpg_ioctl(bdev, (struct blkpg_ioctl_arg __user *) arg);
case BLKRRPART:
return blkdev_reread_part(bdev);
case BLKGETSIZE:
if ((bdev->bd_inode->i_size >> 9) > ~0UL)
return -EFBIG;
return put_ulong(arg, bdev->bd_inode->i_size >> 9);
case BLKGETSIZE64:
return put_u64(arg, bdev->bd_inode->i_size);
}
return -ENOIOCTLCMD;
}
static int blkdev_driver_ioctl(struct inode *inode, struct file *file,
struct gendisk *disk, unsigned cmd, unsigned long arg)
{
int ret;
if (disk->fops->unlocked_ioctl)
return disk->fops->unlocked_ioctl(file, cmd, arg);
if (disk->fops->ioctl) {
lock_kernel();
ret = disk->fops->ioctl(inode, file, cmd, arg);
unlock_kernel();
return ret;
}
return -ENOTTY;
}
int blkdev_ioctl(struct inode *inode, struct file *file, unsigned cmd,
unsigned long arg)
{
struct block_device *bdev = inode->i_bdev;
struct gendisk *disk = bdev->bd_disk;
int ret, n;
switch(cmd) {
case BLKFLSBUF:
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
ret = blkdev_driver_ioctl(inode, file, disk, cmd, arg);
/* -EINVAL to handle old uncorrected drivers */
if (ret != -EINVAL && ret != -ENOTTY)
return ret;
lock_kernel();
fsync_bdev(bdev);
invalidate_bdev(bdev, 0);
unlock_kernel();
return 0;
case BLKROSET:
ret = blkdev_driver_ioctl(inode, file, disk, cmd, arg);
/* -EINVAL to handle old uncorrected drivers */
if (ret != -EINVAL && ret != -ENOTTY)
return ret;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
if (get_user(n, (int __user *)(arg)))
return -EFAULT;
lock_kernel();
set_device_ro(bdev, n);
unlock_kernel();
return 0;
}
lock_kernel();
ret = blkdev_locked_ioctl(file, bdev, cmd, arg);
unlock_kernel();
if (ret != -ENOIOCTLCMD)
return ret;
return blkdev_driver_ioctl(inode, file, disk, cmd, arg);
}
/* Most of the generic ioctls are handled in the normal fallback path.
This assumes the blkdev's low level compat_ioctl always returns
ENOIOCTLCMD for unknown ioctls. */
long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{
struct block_device *bdev = file->f_dentry->d_inode->i_bdev;
struct gendisk *disk = bdev->bd_disk;
int ret = -ENOIOCTLCMD;
if (disk->fops->compat_ioctl) {
lock_kernel();
ret = disk->fops->compat_ioctl(file, cmd, arg);
unlock_kernel();
}
return ret;
}
EXPORT_SYMBOL_GPL(blkdev_ioctl);

3612
drivers/block/ll_rw_blk.c
View file

File diff suppressed because it is too large Load diff

46
drivers/block/noop-iosched.c
View file

@ -1,46 +0,0 @@
/*
* elevator noop
*/
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/bio.h>
#include <linux/module.h>
#include <linux/init.h>
static void elevator_noop_add_request(request_queue_t *q, struct request *rq)
{
rq->flags |= REQ_NOMERGE;
elv_dispatch_add_tail(q, rq);
}
static int elevator_noop_dispatch(request_queue_t *q, int force)
{
return 0;
}
static struct elevator_type elevator_noop = {
.ops = {
.elevator_dispatch_fn = elevator_noop_dispatch,
.elevator_add_req_fn = elevator_noop_add_request,
},
.elevator_name = "noop",
.elevator_owner = THIS_MODULE,
};
static int __init noop_init(void)
{
return elv_register(&elevator_noop);
}
static void __exit noop_exit(void)
{
elv_unregister(&elevator_noop);
}
module_init(noop_init);
module_exit(noop_exit);
MODULE_AUTHOR("Jens Axboe");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("No-op IO scheduler");

589
drivers/block/scsi_ioctl.c
View file

@ -1,589 +0,0 @@
/*
* Copyright (C) 2001 Jens Axboe <axboe@suse.de>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
*
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public Licens
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-
*
*/
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/module.h>
#include <linux/blkdev.h>
#include <linux/completion.h>
#include <linux/cdrom.h>
#include <linux/slab.h>
#include <linux/times.h>
#include <asm/uaccess.h>
#include <scsi/scsi.h>
#include <scsi/scsi_ioctl.h>
#include <scsi/scsi_cmnd.h>
/* Command group 3 is reserved and should never be used. */
const unsigned char scsi_command_size[8] =
{
6, 10, 10, 12,
16, 12, 10, 10
};
EXPORT_SYMBOL(scsi_command_size);
#define BLK_DEFAULT_TIMEOUT (60 * HZ)
#include <scsi/sg.h>
static int sg_get_version(int __user *p)
{
static int sg_version_num = 30527;
return put_user(sg_version_num, p);
}
static int scsi_get_idlun(request_queue_t *q, int __user *p)
{
return put_user(0, p);
}
static int scsi_get_bus(request_queue_t *q, int __user *p)
{
return put_user(0, p);
}
static int sg_get_timeout(request_queue_t *q)
{
return q->sg_timeout / (HZ / USER_HZ);
}
static int sg_set_timeout(request_queue_t *q, int __user *p)
{
int timeout, err = get_user(timeout, p);
if (!err)
q->sg_timeout = timeout * (HZ / USER_HZ);
return err;
}
static int sg_get_reserved_size(request_queue_t *q, int __user *p)
{
return put_user(q->sg_reserved_size, p);
}
static int sg_set_reserved_size(request_queue_t *q, int __user *p)
{
int size, err = get_user(size, p);
if (err)
return err;
if (size < 0)
return -EINVAL;
if (size > (q->max_sectors << 9))
size = q->max_sectors << 9;
q->sg_reserved_size = size;
return 0;
}
/*
* will always return that we are ATAPI even for a real SCSI drive, I'm not
* so sure this is worth doing anything about (why would you care??)
*/
static int sg_emulated_host(request_queue_t *q, int __user *p)
{
return put_user(1, p);
}
#define CMD_READ_SAFE 0x01
#define CMD_WRITE_SAFE 0x02
#define CMD_WARNED 0x04
#define safe_for_read(cmd) [cmd] = CMD_READ_SAFE
#define safe_for_write(cmd) [cmd] = CMD_WRITE_SAFE
static int verify_command(struct file *file, unsigned char *cmd)
{
static unsigned char cmd_type[256] = {
/* Basic read-only commands */
safe_for_read(TEST_UNIT_READY),
safe_for_read(REQUEST_SENSE),
safe_for_read(READ_6),
safe_for_read(READ_10),
safe_for_read(READ_12),
safe_for_read(READ_16),
safe_for_read(READ_BUFFER),
safe_for_read(READ_DEFECT_DATA),
safe_for_read(READ_LONG),
safe_for_read(INQUIRY),
safe_for_read(MODE_SENSE),
safe_for_read(MODE_SENSE_10),
safe_for_read(LOG_SENSE),
safe_for_read(START_STOP),
safe_for_read(GPCMD_VERIFY_10),
safe_for_read(VERIFY_16),
/* Audio CD commands */
safe_for_read(GPCMD_PLAY_CD),
safe_for_read(GPCMD_PLAY_AUDIO_10),
safe_for_read(GPCMD_PLAY_AUDIO_MSF),
safe_for_read(GPCMD_PLAY_AUDIO_TI),
safe_for_read(GPCMD_PAUSE_RESUME),
/* CD/DVD data reading */
safe_for_read(GPCMD_READ_BUFFER_CAPACITY),
safe_for_read(GPCMD_READ_CD),
safe_for_read(GPCMD_READ_CD_MSF),
safe_for_read(GPCMD_READ_DISC_INFO),
safe_for_read(GPCMD_READ_CDVD_CAPACITY),
safe_for_read(GPCMD_READ_DVD_STRUCTURE),
safe_for_read(GPCMD_READ_HEADER),
safe_for_read(GPCMD_READ_TRACK_RZONE_INFO),
safe_for_read(GPCMD_READ_SUBCHANNEL),
safe_for_read(GPCMD_READ_TOC_PMA_ATIP),
safe_for_read(GPCMD_REPORT_KEY),
safe_for_read(GPCMD_SCAN),
safe_for_read(GPCMD_GET_CONFIGURATION),
safe_for_read(GPCMD_READ_FORMAT_CAPACITIES),
safe_for_read(GPCMD_GET_EVENT_STATUS_NOTIFICATION),
safe_for_read(GPCMD_GET_PERFORMANCE),
safe_for_read(GPCMD_SEEK),
safe_for_read(GPCMD_STOP_PLAY_SCAN),
/* Basic writing commands */
safe_for_write(WRITE_6),
safe_for_write(WRITE_10),
safe_for_write(WRITE_VERIFY),
safe_for_write(WRITE_12),
safe_for_write(WRITE_VERIFY_12),
safe_for_write(WRITE_16),
safe_for_write(WRITE_LONG),
safe_for_write(WRITE_LONG_2),
safe_for_write(ERASE),
safe_for_write(GPCMD_MODE_SELECT_10),
safe_for_write(MODE_SELECT),
safe_for_write(LOG_SELECT),
safe_for_write(GPCMD_BLANK),
safe_for_write(GPCMD_CLOSE_TRACK),
safe_for_write(GPCMD_FLUSH_CACHE),
safe_for_write(GPCMD_FORMAT_UNIT),
safe_for_write(GPCMD_REPAIR_RZONE_TRACK),
safe_for_write(GPCMD_RESERVE_RZONE_TRACK),
safe_for_write(GPCMD_SEND_DVD_STRUCTURE),
safe_for_write(GPCMD_SEND_EVENT),
safe_for_write(GPCMD_SEND_KEY),
safe_for_write(GPCMD_SEND_OPC),
safe_for_write(GPCMD_SEND_CUE_SHEET),
safe_for_write(GPCMD_SET_SPEED),
safe_for_write(GPCMD_PREVENT_ALLOW_MEDIUM_REMOVAL),
safe_for_write(GPCMD_LOAD_UNLOAD),
safe_for_write(GPCMD_SET_STREAMING),
};
unsigned char type = cmd_type[cmd[0]];
/* Anybody who can open the device can do a read-safe command */
if (type & CMD_READ_SAFE)
return 0;
/* Write-safe commands just require a writable open.. */
if (type & CMD_WRITE_SAFE) {
if (file->f_mode & FMODE_WRITE)
return 0;
}
/* And root can do any command.. */
if (capable(CAP_SYS_RAWIO))
return 0;
if (!type) {
cmd_type[cmd[0]] = CMD_WARNED;
printk(KERN_WARNING "scsi: unknown opcode 0x%02x\n", cmd[0]);
}
/* Otherwise fail it with an "Operation not permitted" */
return -EPERM;
}
static int sg_io(struct file *file, request_queue_t *q,
struct gendisk *bd_disk, struct sg_io_hdr *hdr)
{
unsigned long start_time;
int writing = 0, ret = 0;
struct request *rq;
struct bio *bio;
char sense[SCSI_SENSE_BUFFERSIZE];
unsigned char cmd[BLK_MAX_CDB];
if (hdr->interface_id != 'S')
return -EINVAL;
if (hdr->cmd_len > BLK_MAX_CDB)
return -EINVAL;
if (copy_from_user(cmd, hdr->cmdp, hdr->cmd_len))
return -EFAULT;
if (verify_command(file, cmd))
return -EPERM;
if (hdr->dxfer_len > (q->max_sectors << 9))
return -EIO;
if (hdr->dxfer_len)
switch (hdr->dxfer_direction) {
default:
return -EINVAL;
case SG_DXFER_TO_FROM_DEV:
case SG_DXFER_TO_DEV:
writing = 1;
break;
case SG_DXFER_FROM_DEV:
break;
}
rq = blk_get_request(q, writing ? WRITE : READ, GFP_KERNEL);
if (!rq)
return -ENOMEM;
if (hdr->iovec_count) {
const int size = sizeof(struct sg_iovec) * hdr->iovec_count;
struct sg_iovec *iov;
iov = kmalloc(size, GFP_KERNEL);
if (!iov) {
ret = -ENOMEM;
goto out;
}
if (copy_from_user(iov, hdr->dxferp, size)) {
kfree(iov);
ret = -EFAULT;
goto out;
}
ret = blk_rq_map_user_iov(q, rq, iov, hdr->iovec_count);
kfree(iov);
} else if (hdr->dxfer_len)
ret = blk_rq_map_user(q, rq, hdr->dxferp, hdr->dxfer_len);
if (ret)
goto out;
/*
* fill in request structure
*/
rq->cmd_len = hdr->cmd_len;
memcpy(rq->cmd, cmd, hdr->cmd_len);
if (sizeof(rq->cmd) != hdr->cmd_len)
memset(rq->cmd + hdr->cmd_len, 0, sizeof(rq->cmd) - hdr->cmd_len);
memset(sense, 0, sizeof(sense));
rq->sense = sense;
rq->sense_len = 0;
rq->flags |= REQ_BLOCK_PC;
bio = rq->bio;
/*
* bounce this after holding a reference to the original bio, it's
* needed for proper unmapping
*/
if (rq->bio)
blk_queue_bounce(q, &rq->bio);
rq->timeout = (hdr->timeout * HZ) / 1000;
if (!rq->timeout)
rq->timeout = q->sg_timeout;
if (!rq->timeout)
rq->timeout = BLK_DEFAULT_TIMEOUT;
start_time = jiffies;
/* ignore return value. All information is passed back to caller
* (if he doesn't check that is his problem).
* N.B. a non-zero SCSI status is _not_ necessarily an error.
*/
blk_execute_rq(q, bd_disk, rq, 0);
/* write to all output members */
hdr->status = 0xff & rq->errors;
hdr->masked_status = status_byte(rq->errors);
hdr->msg_status = msg_byte(rq->errors);
hdr->host_status = host_byte(rq->errors);
hdr->driver_status = driver_byte(rq->errors);
hdr->info = 0;
if (hdr->masked_status || hdr->host_status || hdr->driver_status)
hdr->info |= SG_INFO_CHECK;
hdr->resid = rq->data_len;
hdr->duration = ((jiffies - start_time) * 1000) / HZ;
hdr->sb_len_wr = 0;
if (rq->sense_len && hdr->sbp) {
int len = min((unsigned int) hdr->mx_sb_len, rq->sense_len);
if (!copy_to_user(hdr->sbp, rq->sense, len))
hdr->sb_len_wr = len;
}
if (blk_rq_unmap_user(bio, hdr->dxfer_len))
ret = -EFAULT;
/* may not have succeeded, but output values written to control
* structure (struct sg_io_hdr). */
out:
blk_put_request(rq);
return ret;
}
#define OMAX_SB_LEN 16 /* For backward compatibility */
static int sg_scsi_ioctl(struct file *file, request_queue_t *q,
struct gendisk *bd_disk, Scsi_Ioctl_Command __user *sic)
{
struct request *rq;
int err;
unsigned int in_len, out_len, bytes, opcode, cmdlen;
char *buffer = NULL, sense[SCSI_SENSE_BUFFERSIZE];
/*
* get in an out lengths, verify they don't exceed a page worth of data
*/
if (get_user(in_len, &sic->inlen))
return -EFAULT;
if (get_user(out_len, &sic->outlen))
return -EFAULT;
if (in_len > PAGE_SIZE || out_len > PAGE_SIZE)
return -EINVAL;
if (get_user(opcode, sic->data))
return -EFAULT;
bytes = max(in_len, out_len);
if (bytes) {
buffer = kmalloc(bytes, q->bounce_gfp | GFP_USER| __GFP_NOWARN);
if (!buffer)
return -ENOMEM;
memset(buffer, 0, bytes);
}
rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_WAIT);
cmdlen = COMMAND_SIZE(opcode);
/*
* get command and data to send to device, if any
*/
err = -EFAULT;
rq->cmd_len = cmdlen;
if (copy_from_user(rq->cmd, sic->data, cmdlen))
goto error;
if (copy_from_user(buffer, sic->data + cmdlen, in_len))
goto error;
err = verify_command(file, rq->cmd);
if (err)
goto error;
switch (opcode) {
case SEND_DIAGNOSTIC:
case FORMAT_UNIT:
rq->timeout = FORMAT_UNIT_TIMEOUT;
break;
case START_STOP:
rq->timeout = START_STOP_TIMEOUT;
break;
case MOVE_MEDIUM:
rq->timeout = MOVE_MEDIUM_TIMEOUT;
break;
case READ_ELEMENT_STATUS:
rq->timeout = READ_ELEMENT_STATUS_TIMEOUT;
break;
case READ_DEFECT_DATA:
rq->timeout = READ_DEFECT_DATA_TIMEOUT;
break;
default:
rq->timeout = BLK_DEFAULT_TIMEOUT;
break;
}
memset(sense, 0, sizeof(sense));
rq->sense = sense;
rq->sense_len = 0;
rq->data = buffer;
rq->data_len = bytes;
rq->flags |= REQ_BLOCK_PC;
blk_execute_rq(q, bd_disk, rq, 0);
err = rq->errors & 0xff; /* only 8 bit SCSI status */
if (err) {
if (rq->sense_len && rq->sense) {
bytes = (OMAX_SB_LEN > rq->sense_len) ?
rq->sense_len : OMAX_SB_LEN;
if (copy_to_user(sic->data, rq->sense, bytes))
err = -EFAULT;
}
} else {
if (copy_to_user(sic->data, buffer, out_len))
err = -EFAULT;
}
error:
kfree(buffer);
blk_put_request(rq);
return err;
}
int scsi_cmd_ioctl(struct file *file, struct gendisk *bd_disk, unsigned int cmd, void __user *arg)
{
request_queue_t *q;
struct request *rq;
int close = 0, err;
q = bd_disk->queue;
if (!q)
return -ENXIO;
if (blk_get_queue(q))
return -ENXIO;
switch (cmd) {
/*
* new sgv3 interface
*/
case SG_GET_VERSION_NUM:
err = sg_get_version(arg);
break;
case SCSI_IOCTL_GET_IDLUN:
err = scsi_get_idlun(q, arg);
break;
case SCSI_IOCTL_GET_BUS_NUMBER:
err = scsi_get_bus(q, arg);
break;
case SG_SET_TIMEOUT:
err = sg_set_timeout(q, arg);
break;
case SG_GET_TIMEOUT:
err = sg_get_timeout(q);
break;
case SG_GET_RESERVED_SIZE:
err = sg_get_reserved_size(q, arg);
break;
case SG_SET_RESERVED_SIZE:
err = sg_set_reserved_size(q, arg);
break;
case SG_EMULATED_HOST:
err = sg_emulated_host(q, arg);
break;
case SG_IO: {
struct sg_io_hdr hdr;
err = -EFAULT;
if (copy_from_user(&hdr, arg, sizeof(hdr)))
break;
err = sg_io(file, q, bd_disk, &hdr);
if (err == -EFAULT)
break;
if (copy_to_user(arg, &hdr, sizeof(hdr)))
err = -EFAULT;
break;
}
case CDROM_SEND_PACKET: {
struct cdrom_generic_command cgc;
struct sg_io_hdr hdr;
err = -EFAULT;
if (copy_from_user(&cgc, arg, sizeof(cgc)))
break;
cgc.timeout = clock_t_to_jiffies(cgc.timeout);
memset(&hdr, 0, sizeof(hdr));
hdr.interface_id = 'S';
hdr.cmd_len = sizeof(cgc.cmd);
hdr.dxfer_len = cgc.buflen;
err = 0;
switch (cgc.data_direction) {
case CGC_DATA_UNKNOWN:
hdr.dxfer_direction = SG_DXFER_UNKNOWN;
break;
case CGC_DATA_WRITE:
hdr.dxfer_direction = SG_DXFER_TO_DEV;
break;
case CGC_DATA_READ:
hdr.dxfer_direction = SG_DXFER_FROM_DEV;
break;
case CGC_DATA_NONE:
hdr.dxfer_direction = SG_DXFER_NONE;
break;
default:
err = -EINVAL;
}
if (err)
break;
hdr.dxferp = cgc.buffer;
hdr.sbp = cgc.sense;
if (hdr.sbp)
hdr.mx_sb_len = sizeof(struct request_sense);
hdr.timeout = cgc.timeout;
hdr.cmdp = ((struct cdrom_generic_command __user*) arg)->cmd;
hdr.cmd_len = sizeof(cgc.cmd);
err = sg_io(file, q, bd_disk, &hdr);
if (err == -EFAULT)
break;
if (hdr.status)
err = -EIO;
cgc.stat = err;
cgc.buflen = hdr.resid;
if (copy_to_user(arg, &cgc, sizeof(cgc)))
err = -EFAULT;
break;
}
/*
* old junk scsi send command ioctl
*/
case SCSI_IOCTL_SEND_COMMAND:
printk(KERN_WARNING "program %s is using a deprecated SCSI ioctl, please convert it to SG_IO\n", current->comm);
err = -EINVAL;
if (!arg)
break;
err = sg_scsi_ioctl(file, q, bd_disk, arg);
break;
case CDROMCLOSETRAY:
close = 1;
case CDROMEJECT:
rq = blk_get_request(q, WRITE, __GFP_WAIT);
rq->flags |= REQ_BLOCK_PC;
rq->data = NULL;
rq->data_len = 0;
rq->timeout = BLK_DEFAULT_TIMEOUT;
memset(rq->cmd, 0, sizeof(rq->cmd));
rq->cmd[0] = GPCMD_START_STOP_UNIT;
rq->cmd[4] = 0x02 + (close != 0);
rq->cmd_len = 6;
err = blk_execute_rq(q, bd_disk, rq, 0);
blk_put_request(rq);
break;
default:
err = -ENOTTY;
}
blk_put_queue(q);
return err;
}
EXPORT_SYMBOL(scsi_cmd_ioctl);