mirror of
https://github.com/torvalds/linux.git
synced 2024-11-10 14:11:52 +00:00
f772b3d9ca
There is a small problem in handling page bounce. At the moment blk_max_pfn equals max_pfn, which is in fact not maximum possible _number_ of a page frame, but the _amount_ of page frames. For example for the 32bit x86 node with 4Gb RAM, max_pfn = 0x100000, but not 0xFFFF. request_queue structure has a member q->bounce_pfn and queue needs bounce pages for the pages _above_ this limit. This routine is handled by blk_queue_bounce(), where the following check is produced: if (q->bounce_pfn >= blk_max_pfn) return; Assume, that a driver has set q->bounce_pfn to 0xFFFF, but blk_max_pfn equals 0x10000. In such situation the check above fails and for each bio we always fall down for iterating over pages tied to the bio. I want to notice, that for quite a big range of device drivers (ide, md, ...) such problem doesn't happen because they use BLK_BOUNCE_ANY for bounce_pfn. BLK_BOUNCE_ANY is defined as blk_max_pfn << PAGE_SHIFT, and then the check above doesn't fail. But for other drivers, which obtain reuired value from drivers, it fails. For example sata_nv uses ATA_DMA_MASK or dev->dma_mask. I propose to use (max_pfn - 1) for blk_max_pfn. And the same for blk_max_low_pfn. The patch also cleanses some checks related with bounce_pfn. Signed-off-by: Vasily Tarasov <vtaras@openvz.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
303 lines
6.5 KiB
C
303 lines
6.5 KiB
C
/* bounce buffer handling for block devices
|
|
*
|
|
* - Split from highmem.c
|
|
*/
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/module.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/bio.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/mempool.h>
|
|
#include <linux/blkdev.h>
|
|
#include <linux/init.h>
|
|
#include <linux/hash.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/blktrace_api.h>
|
|
#include <asm/tlbflush.h>
|
|
|
|
#define POOL_SIZE 64
|
|
#define ISA_POOL_SIZE 16
|
|
|
|
static mempool_t *page_pool, *isa_page_pool;
|
|
|
|
#ifdef CONFIG_HIGHMEM
|
|
static __init int init_emergency_pool(void)
|
|
{
|
|
struct sysinfo i;
|
|
si_meminfo(&i);
|
|
si_swapinfo(&i);
|
|
|
|
if (!i.totalhigh)
|
|
return 0;
|
|
|
|
page_pool = mempool_create_page_pool(POOL_SIZE, 0);
|
|
BUG_ON(!page_pool);
|
|
printk("highmem bounce pool size: %d pages\n", POOL_SIZE);
|
|
|
|
return 0;
|
|
}
|
|
|
|
__initcall(init_emergency_pool);
|
|
|
|
/*
|
|
* highmem version, map in to vec
|
|
*/
|
|
static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
|
|
{
|
|
unsigned long flags;
|
|
unsigned char *vto;
|
|
|
|
local_irq_save(flags);
|
|
vto = kmap_atomic(to->bv_page, KM_BOUNCE_READ);
|
|
memcpy(vto + to->bv_offset, vfrom, to->bv_len);
|
|
kunmap_atomic(vto, KM_BOUNCE_READ);
|
|
local_irq_restore(flags);
|
|
}
|
|
|
|
#else /* CONFIG_HIGHMEM */
|
|
|
|
#define bounce_copy_vec(to, vfrom) \
|
|
memcpy(page_address((to)->bv_page) + (to)->bv_offset, vfrom, (to)->bv_len)
|
|
|
|
#endif /* CONFIG_HIGHMEM */
|
|
|
|
/*
|
|
* allocate pages in the DMA region for the ISA pool
|
|
*/
|
|
static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data)
|
|
{
|
|
return mempool_alloc_pages(gfp_mask | GFP_DMA, data);
|
|
}
|
|
|
|
/*
|
|
* gets called "every" time someone init's a queue with BLK_BOUNCE_ISA
|
|
* as the max address, so check if the pool has already been created.
|
|
*/
|
|
int init_emergency_isa_pool(void)
|
|
{
|
|
if (isa_page_pool)
|
|
return 0;
|
|
|
|
isa_page_pool = mempool_create(ISA_POOL_SIZE, mempool_alloc_pages_isa,
|
|
mempool_free_pages, (void *) 0);
|
|
BUG_ON(!isa_page_pool);
|
|
|
|
printk("isa bounce pool size: %d pages\n", ISA_POOL_SIZE);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Simple bounce buffer support for highmem pages. Depending on the
|
|
* queue gfp mask set, *to may or may not be a highmem page. kmap it
|
|
* always, it will do the Right Thing
|
|
*/
|
|
static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
|
|
{
|
|
unsigned char *vfrom;
|
|
struct bio_vec *tovec, *fromvec;
|
|
int i;
|
|
|
|
__bio_for_each_segment(tovec, to, i, 0) {
|
|
fromvec = from->bi_io_vec + i;
|
|
|
|
/*
|
|
* not bounced
|
|
*/
|
|
if (tovec->bv_page == fromvec->bv_page)
|
|
continue;
|
|
|
|
/*
|
|
* fromvec->bv_offset and fromvec->bv_len might have been
|
|
* modified by the block layer, so use the original copy,
|
|
* bounce_copy_vec already uses tovec->bv_len
|
|
*/
|
|
vfrom = page_address(fromvec->bv_page) + tovec->bv_offset;
|
|
|
|
flush_dcache_page(tovec->bv_page);
|
|
bounce_copy_vec(tovec, vfrom);
|
|
}
|
|
}
|
|
|
|
static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
|
|
{
|
|
struct bio *bio_orig = bio->bi_private;
|
|
struct bio_vec *bvec, *org_vec;
|
|
int i;
|
|
|
|
if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags))
|
|
set_bit(BIO_EOPNOTSUPP, &bio_orig->bi_flags);
|
|
|
|
/*
|
|
* free up bounce indirect pages used
|
|
*/
|
|
__bio_for_each_segment(bvec, bio, i, 0) {
|
|
org_vec = bio_orig->bi_io_vec + i;
|
|
if (bvec->bv_page == org_vec->bv_page)
|
|
continue;
|
|
|
|
dec_zone_page_state(bvec->bv_page, NR_BOUNCE);
|
|
mempool_free(bvec->bv_page, pool);
|
|
}
|
|
|
|
bio_endio(bio_orig, bio_orig->bi_size, err);
|
|
bio_put(bio);
|
|
}
|
|
|
|
static int bounce_end_io_write(struct bio *bio, unsigned int bytes_done, int err)
|
|
{
|
|
if (bio->bi_size)
|
|
return 1;
|
|
|
|
bounce_end_io(bio, page_pool, err);
|
|
return 0;
|
|
}
|
|
|
|
static int bounce_end_io_write_isa(struct bio *bio, unsigned int bytes_done, int err)
|
|
{
|
|
if (bio->bi_size)
|
|
return 1;
|
|
|
|
bounce_end_io(bio, isa_page_pool, err);
|
|
return 0;
|
|
}
|
|
|
|
static void __bounce_end_io_read(struct bio *bio, mempool_t *pool, int err)
|
|
{
|
|
struct bio *bio_orig = bio->bi_private;
|
|
|
|
if (test_bit(BIO_UPTODATE, &bio->bi_flags))
|
|
copy_to_high_bio_irq(bio_orig, bio);
|
|
|
|
bounce_end_io(bio, pool, err);
|
|
}
|
|
|
|
static int bounce_end_io_read(struct bio *bio, unsigned int bytes_done, int err)
|
|
{
|
|
if (bio->bi_size)
|
|
return 1;
|
|
|
|
__bounce_end_io_read(bio, page_pool, err);
|
|
return 0;
|
|
}
|
|
|
|
static int bounce_end_io_read_isa(struct bio *bio, unsigned int bytes_done, int err)
|
|
{
|
|
if (bio->bi_size)
|
|
return 1;
|
|
|
|
__bounce_end_io_read(bio, isa_page_pool, err);
|
|
return 0;
|
|
}
|
|
|
|
static void __blk_queue_bounce(request_queue_t *q, struct bio **bio_orig,
|
|
mempool_t *pool)
|
|
{
|
|
struct page *page;
|
|
struct bio *bio = NULL;
|
|
int i, rw = bio_data_dir(*bio_orig);
|
|
struct bio_vec *to, *from;
|
|
|
|
bio_for_each_segment(from, *bio_orig, i) {
|
|
page = from->bv_page;
|
|
|
|
/*
|
|
* is destination page below bounce pfn?
|
|
*/
|
|
if (page_to_pfn(page) <= q->bounce_pfn)
|
|
continue;
|
|
|
|
/*
|
|
* irk, bounce it
|
|
*/
|
|
if (!bio)
|
|
bio = bio_alloc(GFP_NOIO, (*bio_orig)->bi_vcnt);
|
|
|
|
to = bio->bi_io_vec + i;
|
|
|
|
to->bv_page = mempool_alloc(pool, q->bounce_gfp);
|
|
to->bv_len = from->bv_len;
|
|
to->bv_offset = from->bv_offset;
|
|
inc_zone_page_state(to->bv_page, NR_BOUNCE);
|
|
|
|
if (rw == WRITE) {
|
|
char *vto, *vfrom;
|
|
|
|
flush_dcache_page(from->bv_page);
|
|
vto = page_address(to->bv_page) + to->bv_offset;
|
|
vfrom = kmap(from->bv_page) + from->bv_offset;
|
|
memcpy(vto, vfrom, to->bv_len);
|
|
kunmap(from->bv_page);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* no pages bounced
|
|
*/
|
|
if (!bio)
|
|
return;
|
|
|
|
blk_add_trace_bio(q, *bio_orig, BLK_TA_BOUNCE);
|
|
|
|
/*
|
|
* at least one page was bounced, fill in possible non-highmem
|
|
* pages
|
|
*/
|
|
__bio_for_each_segment(from, *bio_orig, i, 0) {
|
|
to = bio_iovec_idx(bio, i);
|
|
if (!to->bv_page) {
|
|
to->bv_page = from->bv_page;
|
|
to->bv_len = from->bv_len;
|
|
to->bv_offset = from->bv_offset;
|
|
}
|
|
}
|
|
|
|
bio->bi_bdev = (*bio_orig)->bi_bdev;
|
|
bio->bi_flags |= (1 << BIO_BOUNCED);
|
|
bio->bi_sector = (*bio_orig)->bi_sector;
|
|
bio->bi_rw = (*bio_orig)->bi_rw;
|
|
|
|
bio->bi_vcnt = (*bio_orig)->bi_vcnt;
|
|
bio->bi_idx = (*bio_orig)->bi_idx;
|
|
bio->bi_size = (*bio_orig)->bi_size;
|
|
|
|
if (pool == page_pool) {
|
|
bio->bi_end_io = bounce_end_io_write;
|
|
if (rw == READ)
|
|
bio->bi_end_io = bounce_end_io_read;
|
|
} else {
|
|
bio->bi_end_io = bounce_end_io_write_isa;
|
|
if (rw == READ)
|
|
bio->bi_end_io = bounce_end_io_read_isa;
|
|
}
|
|
|
|
bio->bi_private = *bio_orig;
|
|
*bio_orig = bio;
|
|
}
|
|
|
|
void blk_queue_bounce(request_queue_t *q, struct bio **bio_orig)
|
|
{
|
|
mempool_t *pool;
|
|
|
|
/*
|
|
* for non-isa bounce case, just check if the bounce pfn is equal
|
|
* to or bigger than the highest pfn in the system -- in that case,
|
|
* don't waste time iterating over bio segments
|
|
*/
|
|
if (!(q->bounce_gfp & GFP_DMA)) {
|
|
if (q->bounce_pfn >= blk_max_pfn)
|
|
return;
|
|
pool = page_pool;
|
|
} else {
|
|
BUG_ON(!isa_page_pool);
|
|
pool = isa_page_pool;
|
|
}
|
|
|
|
/*
|
|
* slow path
|
|
*/
|
|
__blk_queue_bounce(q, bio_orig, pool);
|
|
}
|
|
|
|
EXPORT_SYMBOL(blk_queue_bounce);
|