diff options
-rw-r--r-- | arch/ia64/Kconfig | 4 | ||||
-rw-r--r-- | arch/ia64/lib/Makefile | 2 | ||||
-rw-r--r-- | arch/x86_64/kernel/Makefile | 2 | ||||
-rw-r--r-- | drivers/block/aoe/aoecmd.c | 13 | ||||
-rw-r--r-- | drivers/block/genhd.c | 29 | ||||
-rw-r--r-- | drivers/block/ll_rw_blk.c | 47 | ||||
-rw-r--r-- | drivers/md/linear.c | 10 | ||||
-rw-r--r-- | drivers/md/md.c | 4 | ||||
-rw-r--r-- | drivers/md/multipath.c | 10 | ||||
-rw-r--r-- | drivers/md/raid0.c | 10 | ||||
-rw-r--r-- | drivers/md/raid1.c | 12 | ||||
-rw-r--r-- | drivers/md/raid10.c | 12 | ||||
-rw-r--r-- | drivers/md/raid5.c | 10 | ||||
-rw-r--r-- | drivers/md/raid6main.c | 12 | ||||
-rw-r--r-- | fs/partitions/check.c | 7 | ||||
-rw-r--r-- | include/asm-x86_64/dma-mapping.h | 31 | ||||
-rw-r--r-- | include/asm-x86_64/swiotlb.h | 8 | ||||
-rw-r--r-- | include/linux/genhd.h | 10 | ||||
-rw-r--r-- | lib/Makefile | 2 | ||||
-rw-r--r-- | lib/swiotlb.c (renamed from arch/ia64/lib/swiotlb.c) | 142 |
20 files changed, 209 insertions, 168 deletions
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 1642375fb14..3b4248cff9a 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -26,6 +26,10 @@ config MMU bool default y +config SWIOTLB + bool + default y + config RWSEM_XCHGADD_ALGORITHM bool default y diff --git a/arch/ia64/lib/Makefile b/arch/ia64/lib/Makefile index cb1af597370..ac64664a180 100644 --- a/arch/ia64/lib/Makefile +++ b/arch/ia64/lib/Makefile @@ -9,7 +9,7 @@ lib-y := __divsi3.o __udivsi3.o __modsi3.o __umodsi3.o \ bitop.o checksum.o clear_page.o csum_partial_copy.o \ clear_user.o strncpy_from_user.o strlen_user.o strnlen_user.o \ flush.o ip_fast_csum.o do_csum.o \ - memset.o strlen.o swiotlb.o + memset.o strlen.o lib-$(CONFIG_ITANIUM) += copy_page.o copy_user.o memcpy.o lib-$(CONFIG_MCKINLEY) += copy_page_mck.o memcpy_mck.o diff --git a/arch/x86_64/kernel/Makefile b/arch/x86_64/kernel/Makefile index bcdd0a805fe..14328cab5d3 100644 --- a/arch/x86_64/kernel/Makefile +++ b/arch/x86_64/kernel/Makefile @@ -27,7 +27,6 @@ obj-$(CONFIG_CPU_FREQ) += cpufreq/ obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_GART_IOMMU) += pci-gart.o aperture.o obj-$(CONFIG_DUMMY_IOMMU) += pci-nommu.o pci-dma.o -obj-$(CONFIG_SWIOTLB) += swiotlb.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_X86_PM_TIMER) += pmtimer.o @@ -41,7 +40,6 @@ CFLAGS_vsyscall.o := $(PROFILING) -g0 bootflag-y += ../../i386/kernel/bootflag.o cpuid-$(subst m,y,$(CONFIG_X86_CPUID)) += ../../i386/kernel/cpuid.o topology-y += ../../i386/mach-default/topology.o -swiotlb-$(CONFIG_SWIOTLB) += ../../ia64/lib/swiotlb.o microcode-$(subst m,y,$(CONFIG_MICROCODE)) += ../../i386/kernel/microcode.o intel_cacheinfo-y += ../../i386/kernel/cpu/intel_cacheinfo.o quirks-y += ../../i386/kernel/quirks.o diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index 5c9c7c1a3d4..326ca3876b6 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -468,16 +468,11 @@ aoecmd_ata_rsp(struct sk_buff *skb) unsigned long duration = jiffies - buf->start_time; unsigned long n_sect = buf->bio->bi_size >> 9; struct gendisk *disk = d->gd; + const int rw = bio_data_dir(buf->bio); - if (bio_data_dir(buf->bio) == WRITE) { - disk_stat_inc(disk, writes); - disk_stat_add(disk, write_ticks, duration); - disk_stat_add(disk, write_sectors, n_sect); - } else { - disk_stat_inc(disk, reads); - disk_stat_add(disk, read_ticks, duration); - disk_stat_add(disk, read_sectors, n_sect); - } + disk_stat_inc(disk, ios[rw]); + disk_stat_add(disk, ticks[rw], duration); + disk_stat_add(disk, sectors[rw], n_sect); disk_stat_add(disk, io_ticks, duration); n = (buf->flags & BUFFL_FAIL) ? -EIO : 0; bio_endio(buf->bio, buf->bio->bi_size, n); diff --git a/drivers/block/genhd.c b/drivers/block/genhd.c index 486ce1fdeb8..54aec4a1ae1 100644 --- a/drivers/block/genhd.c +++ b/drivers/block/genhd.c @@ -391,13 +391,12 @@ static ssize_t disk_stats_read(struct gendisk * disk, char *page) "%8u %8u %8llu %8u " "%8u %8u %8u" "\n", - disk_stat_read(disk, reads), disk_stat_read(disk, read_merges), - (unsigned long long)disk_stat_read(disk, read_sectors), - jiffies_to_msecs(disk_stat_read(disk, read_ticks)), - disk_stat_read(disk, writes), - disk_stat_read(disk, write_merges), - (unsigned long long)disk_stat_read(disk, write_sectors), - jiffies_to_msecs(disk_stat_read(disk, write_ticks)), + 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))); @@ -583,12 +582,12 @@ static int diskstats_show(struct seq_file *s, void *v) 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, reads), disk_stat_read(gp, read_merges), - (unsigned long long)disk_stat_read(gp, read_sectors), - jiffies_to_msecs(disk_stat_read(gp, read_ticks)), - disk_stat_read(gp, writes), disk_stat_read(gp, write_merges), - (unsigned long long)disk_stat_read(gp, write_sectors), - jiffies_to_msecs(disk_stat_read(gp, write_ticks)), + 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))); @@ -601,8 +600,8 @@ static int diskstats_show(struct seq_file *s, void *v) 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->reads, hd->read_sectors, - hd->writes, hd->write_sectors); + hd->ios[0], hd->sectors[0], + hd->ios[1], hd->sectors[1]); } return 0; diff --git a/drivers/block/ll_rw_blk.c b/drivers/block/ll_rw_blk.c index 0af73512b9a..2747741677f 100644 --- a/drivers/block/ll_rw_blk.c +++ b/drivers/block/ll_rw_blk.c @@ -2387,16 +2387,9 @@ static void drive_stat_acct(struct request *rq, int nr_sectors, int new_io) if (!blk_fs_request(rq) || !rq->rq_disk) return; - if (rw == READ) { - __disk_stat_add(rq->rq_disk, read_sectors, nr_sectors); - if (!new_io) - __disk_stat_inc(rq->rq_disk, read_merges); - } else if (rw == WRITE) { - __disk_stat_add(rq->rq_disk, write_sectors, nr_sectors); - if (!new_io) - __disk_stat_inc(rq->rq_disk, write_merges); - } - if (new_io) { + if (!new_io) { + __disk_stat_inc(rq->rq_disk, merges[rw]); + } else { disk_round_stats(rq->rq_disk); rq->rq_disk->in_flight++; } @@ -2791,17 +2784,11 @@ static inline void blk_partition_remap(struct bio *bio) if (bdev != bdev->bd_contains) { struct hd_struct *p = bdev->bd_part; + const int rw = bio_data_dir(bio); + + p->sectors[rw] += bio_sectors(bio); + p->ios[rw]++; - switch (bio_data_dir(bio)) { - case READ: - p->read_sectors += bio_sectors(bio); - p->reads++; - break; - case WRITE: - p->write_sectors += bio_sectors(bio); - p->writes++; - break; - } bio->bi_sector += p->start_sect; bio->bi_bdev = bdev->bd_contains; } @@ -3048,6 +3035,12 @@ static int __end_that_request_first(struct request *req, int uptodate, (unsigned long long)req->sector); } + if (blk_fs_request(req) && req->rq_disk) { + const int rw = rq_data_dir(req); + + __disk_stat_add(req->rq_disk, sectors[rw], nr_bytes >> 9); + } + total_bytes = bio_nbytes = 0; while ((bio = req->bio) != NULL) { int nbytes; @@ -3176,16 +3169,10 @@ void end_that_request_last(struct request *req) if (disk && blk_fs_request(req)) { unsigned long duration = jiffies - req->start_time; - switch (rq_data_dir(req)) { - case WRITE: - __disk_stat_inc(disk, writes); - __disk_stat_add(disk, write_ticks, duration); - break; - case READ: - __disk_stat_inc(disk, reads); - __disk_stat_add(disk, read_ticks, duration); - break; - } + const int rw = rq_data_dir(req); + + __disk_stat_inc(disk, ios[rw]); + __disk_stat_add(disk, ticks[rw], duration); disk_round_stats(disk); disk->in_flight--; } diff --git a/drivers/md/linear.c b/drivers/md/linear.c index bb279fad2fd..946efef3a8f 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -271,6 +271,7 @@ static int linear_stop (mddev_t *mddev) static int linear_make_request (request_queue_t *q, struct bio *bio) { + const int rw = bio_data_dir(bio); mddev_t *mddev = q->queuedata; dev_info_t *tmp_dev; sector_t block; @@ -280,13 +281,8 @@ static int linear_make_request (request_queue_t *q, struct bio *bio) return 0; } - if (bio_data_dir(bio)==WRITE) { - disk_stat_inc(mddev->gendisk, writes); - disk_stat_add(mddev->gendisk, write_sectors, bio_sectors(bio)); - } else { - disk_stat_inc(mddev->gendisk, reads); - disk_stat_add(mddev->gendisk, read_sectors, bio_sectors(bio)); - } + disk_stat_inc(mddev->gendisk, ios[rw]); + disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(bio)); tmp_dev = which_dev(mddev, bio->bi_sector); block = bio->bi_sector >> 1; diff --git a/drivers/md/md.c b/drivers/md/md.c index 2a8a5696bf8..9ecf51ee596 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -3466,8 +3466,8 @@ static int is_mddev_idle(mddev_t *mddev) idle = 1; ITERATE_RDEV(mddev,rdev,tmp) { struct gendisk *disk = rdev->bdev->bd_contains->bd_disk; - curr_events = disk_stat_read(disk, read_sectors) + - disk_stat_read(disk, write_sectors) - + curr_events = disk_stat_read(disk, sectors[0]) + + disk_stat_read(disk, sectors[1]) - atomic_read(&disk->sync_io); /* Allow some slack between valud of curr_events and last_events, * as there are some uninteresting races. diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index 1151c3ed300..c06f4474192 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -168,6 +168,7 @@ static int multipath_make_request (request_queue_t *q, struct bio * bio) multipath_conf_t *conf = mddev_to_conf(mddev); struct multipath_bh * mp_bh; struct multipath_info *multipath; + const int rw = bio_data_dir(bio); if (unlikely(bio_barrier(bio))) { bio_endio(bio, bio->bi_size, -EOPNOTSUPP); @@ -179,13 +180,8 @@ static int multipath_make_request (request_queue_t *q, struct bio * bio) mp_bh->master_bio = bio; mp_bh->mddev = mddev; - if (bio_data_dir(bio)==WRITE) { - disk_stat_inc(mddev->gendisk, writes); - disk_stat_add(mddev->gendisk, write_sectors, bio_sectors(bio)); - } else { - disk_stat_inc(mddev->gendisk, reads); - disk_stat_add(mddev->gendisk, read_sectors, bio_sectors(bio)); - } + disk_stat_inc(mddev->gendisk, ios[rw]); + disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(bio)); mp_bh->path = multipath_map(conf); if (mp_bh->path < 0) { diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index f6757259ce7..fece3277c2a 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -403,19 +403,15 @@ static int raid0_make_request (request_queue_t *q, struct bio *bio) mdk_rdev_t *tmp_dev; unsigned long chunk; sector_t block, rsect; + const int rw = bio_data_dir(bio); if (unlikely(bio_barrier(bio))) { bio_endio(bio, bio->bi_size, -EOPNOTSUPP); return 0; } - if (bio_data_dir(bio)==WRITE) { - disk_stat_inc(mddev->gendisk, writes); - disk_stat_add(mddev->gendisk, write_sectors, bio_sectors(bio)); - } else { - disk_stat_inc(mddev->gendisk, reads); - disk_stat_add(mddev->gendisk, read_sectors, bio_sectors(bio)); - } + disk_stat_inc(mddev->gendisk, ios[rw]); + disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(bio)); chunk_size = mddev->chunk_size >> 10; chunk_sects = mddev->chunk_size >> 9; diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 0e1f148dd41..e16f473bcf4 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -647,6 +647,7 @@ static int make_request(request_queue_t *q, struct bio * bio) unsigned long flags; struct bio_list bl; struct page **behind_pages = NULL; + const int rw = bio_data_dir(bio); if (unlikely(bio_barrier(bio))) { bio_endio(bio, bio->bi_size, -EOPNOTSUPP); @@ -665,13 +666,8 @@ static int make_request(request_queue_t *q, struct bio * bio) conf->nr_pending++; spin_unlock_irq(&conf->resync_lock); - if (bio_data_dir(bio)==WRITE) { - disk_stat_inc(mddev->gendisk, writes); - disk_stat_add(mddev->gendisk, write_sectors, bio_sectors(bio)); - } else { - disk_stat_inc(mddev->gendisk, reads); - disk_stat_add(mddev->gendisk, read_sectors, bio_sectors(bio)); - } + disk_stat_inc(mddev->gendisk, ios[rw]); + disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(bio)); /* * make_request() can abort the operation when READA is being @@ -686,7 +682,7 @@ static int make_request(request_queue_t *q, struct bio * bio) r1_bio->mddev = mddev; r1_bio->sector = bio->bi_sector; - if (bio_data_dir(bio) == READ) { + if (rw == READ) { /* * read balancing logic: */ diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 28dd028415e..bbe40e9cf92 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -668,6 +668,7 @@ static int make_request(request_queue_t *q, struct bio * bio) struct bio *read_bio; int i; int chunk_sects = conf->chunk_mask + 1; + const int rw = bio_data_dir(bio); if (unlikely(bio_barrier(bio))) { bio_endio(bio, bio->bi_size, -EOPNOTSUPP); @@ -718,13 +719,8 @@ static int make_request(request_queue_t *q, struct bio * bio) conf->nr_pending++; spin_unlock_irq(&conf->resync_lock); - if (bio_data_dir(bio)==WRITE) { - disk_stat_inc(mddev->gendisk, writes); - disk_stat_add(mddev->gendisk, write_sectors, bio_sectors(bio)); - } else { - disk_stat_inc(mddev->gendisk, reads); - disk_stat_add(mddev->gendisk, read_sectors, bio_sectors(bio)); - } + disk_stat_inc(mddev->gendisk, ios[rw]); + disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(bio)); r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO); @@ -734,7 +730,7 @@ static int make_request(request_queue_t *q, struct bio * bio) r10_bio->mddev = mddev; r10_bio->sector = bio->bi_sector; - if (bio_data_dir(bio) == READ) { + if (rw == READ) { /* * read balancing logic: */ diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 4683ca24c04..6497295ebfb 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1462,6 +1462,7 @@ static int make_request (request_queue_t *q, struct bio * bi) sector_t new_sector; sector_t logical_sector, last_sector; struct stripe_head *sh; + const int rw = bio_data_dir(bi); if (unlikely(bio_barrier(bi))) { bio_endio(bi, bi->bi_size, -EOPNOTSUPP); @@ -1470,13 +1471,8 @@ static int make_request (request_queue_t *q, struct bio * bi) md_write_start(mddev, bi); - if (bio_data_dir(bi)==WRITE) { - disk_stat_inc(mddev->gendisk, writes); - disk_stat_add(mddev->gendisk, write_sectors, bio_sectors(bi)); - } else { - disk_stat_inc(mddev->gendisk, reads); - disk_stat_add(mddev->gendisk, read_sectors, bio_sectors(bi)); - } + disk_stat_inc(mddev->gendisk, ios[rw]); + disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(bi)); logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1); last_sector = bi->bi_sector + (bi->bi_size>>9); diff --git a/drivers/md/raid6main.c b/drivers/md/raid6main.c index 267eb1430c8..6437a95ffc1 100644 --- a/drivers/md/raid6main.c +++ b/drivers/md/raid6main.c @@ -1621,6 +1621,7 @@ static int make_request (request_queue_t *q, struct bio * bi) sector_t new_sector; sector_t logical_sector, last_sector; struct stripe_head *sh; + const int rw = bio_data_dir(bi); if (unlikely(bio_barrier(bi))) { bio_endio(bi, bi->bi_size, -EOPNOTSUPP); @@ -1629,13 +1630,8 @@ static int make_request (request_queue_t *q, struct bio * bi) md_write_start(mddev, bi); - if (bio_data_dir(bi)==WRITE) { - disk_stat_inc(mddev->gendisk, writes); - disk_stat_add(mddev->gendisk, write_sectors, bio_sectors(bi)); - } else { - disk_stat_inc(mddev->gendisk, reads); - disk_stat_add(mddev->gendisk, read_sectors, bio_sectors(bi)); - } + disk_stat_inc(mddev->gendisk, ios[rw]); + disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(bi)); logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1); last_sector = bi->bi_sector + (bi->bi_size>>9); @@ -1682,7 +1678,7 @@ static int make_request (request_queue_t *q, struct bio * bi) if (--bi->bi_phys_segments == 0) { int bytes = bi->bi_size; - if ( bio_data_dir(bi) == WRITE ) + if (rw == WRITE ) md_write_end(mddev); bi->bi_size = 0; bi->bi_end_io(bi, bytes, 0); diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 9c06c5434ec..8dc1822a702 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -246,8 +246,8 @@ static ssize_t part_size_read(struct hd_struct * p, char *page) static ssize_t part_stat_read(struct hd_struct * p, char *page) { return sprintf(page, "%8u %8llu %8u %8llu\n", - p->reads, (unsigned long long)p->read_sectors, - p->writes, (unsigned long long)p->write_sectors); + p->ios[0], (unsigned long long)p->sectors[0], + p->ios[1], (unsigned long long)p->sectors[1]); } static struct part_attribute part_attr_uevent = { .attr = {.name = "uevent", .mode = S_IWUSR }, @@ -303,7 +303,8 @@ void delete_partition(struct gendisk *disk, int part) disk->part[part-1] = NULL; p->start_sect = 0; p->nr_sects = 0; - p->reads = p->writes = p->read_sectors = p->write_sectors = 0; + p->ios[0] = p->ios[1] = 0; + p->sectors[0] = p->sectors[1] = 0; devfs_remove("%s/part%d", disk->devfs_name, part); kobject_unregister(&p->kobj); } diff --git a/include/asm-x86_64/dma-mapping.h b/include/asm-x86_64/dma-mapping.h index 54a380efed4..36d16dfbac8 100644 --- a/include/asm-x86_64/dma-mapping.h +++ b/include/asm-x86_64/dma-mapping.h @@ -85,10 +85,33 @@ static inline void dma_sync_single_for_device(struct device *hwdev, flush_write_buffers(); } -#define dma_sync_single_range_for_cpu(dev, dma_handle, offset, size, dir) \ - dma_sync_single_for_cpu(dev, dma_handle, size, dir) -#define dma_sync_single_range_for_device(dev, dma_handle, offset, size, dir) \ - dma_sync_single_for_device(dev, dma_handle, size, dir) +static inline void dma_sync_single_range_for_cpu(struct device *hwdev, + dma_addr_t dma_handle, + unsigned long offset, + size_t size, int direction) +{ + if (direction == DMA_NONE) + out_of_line_bug(); + + if (swiotlb) + return swiotlb_sync_single_range_for_cpu(hwdev,dma_handle,offset,size,direction); + + flush_write_buffers(); +} + +static inline void dma_sync_single_range_for_device(struct device *hwdev, + dma_addr_t dma_handle, + unsigned long offset, + size_t size, int direction) +{ + if (direction == DMA_NONE) + out_of_line_bug(); + + if (swiotlb) + return swiotlb_sync_single_range_for_device(hwdev,dma_handle,offset,size,direction); + + flush_write_buffers(); +} static inline void dma_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, diff --git a/include/asm-x86_64/swiotlb.h b/include/asm-x86_64/swiotlb.h index 7cbfd10ecc3..dddf1b21868 100644 --- a/include/asm-x86_64/swiotlb.h +++ b/include/asm-x86_64/swiotlb.h @@ -15,6 +15,14 @@ extern void swiotlb_sync_single_for_cpu(struct device *hwdev, extern void swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, size_t size, int dir); +extern void swiotlb_sync_single_range_for_cpu(struct device *hwdev, + dma_addr_t dev_addr, + unsigned long offset, + size_t size, int dir); +extern void swiotlb_sync_single_range_for_device(struct device *hwdev, + dma_addr_t dev_addr, + unsigned long offset, + size_t size, int dir); extern void swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, int nelems, int dir); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index eabdb5cce35..8eeaa53a68c 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -78,7 +78,7 @@ struct hd_struct { sector_t start_sect; sector_t nr_sects; struct kobject kobj; - unsigned reads, read_sectors, writes, write_sectors; + unsigned ios[2], sectors[2]; int policy, partno; }; @@ -89,10 +89,10 @@ struct hd_struct { #define GENHD_FL_SUPPRESS_PARTITION_INFO 32 struct disk_stats { - unsigned read_sectors, write_sectors; - unsigned reads, writes; - unsigned read_merges, write_merges; - unsigned read_ticks, write_ticks; + unsigned sectors[2]; + unsigned ios[2]; + unsigned merges[2]; + unsigned ticks[2]; unsigned io_ticks; unsigned time_in_queue; }; diff --git a/lib/Makefile b/lib/Makefile index 44a46750690..8535f4d7d1c 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -44,6 +44,8 @@ obj-$(CONFIG_TEXTSEARCH_KMP) += ts_kmp.o obj-$(CONFIG_TEXTSEARCH_BM) += ts_bm.o obj-$(CONFIG_TEXTSEARCH_FSM) += ts_fsm.o +obj-$(CONFIG_SWIOTLB) += swiotlb.o + hostprogs-y := gen_crc32table clean-files := crc32table.h diff --git a/arch/ia64/lib/swiotlb.c b/lib/swiotlb.c index 96edcc0fdcd..57216f3544c 100644 --- a/arch/ia64/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -1,7 +1,7 @@ /* * Dynamic DMA mapping support. * - * This implementation is for IA-64 platforms that do not support + * This implementation is for IA-64 and EM64T platforms that do not support * I/O TLBs (aka DMA address translation hardware). * Copyright (C) 2000 Asit Mallick <Asit.K.Mallick@intel.com> * Copyright (C) 2000 Goutham Rao <goutham.rao@intel.com> @@ -11,21 +11,23 @@ * 03/05/07 davidm Switch from PCI-DMA to generic device DMA API. * 00/12/13 davidm Rename to swiotlb.c and add mark_clean() to avoid * unnecessary i-cache flushing. - * 04/07/.. ak Better overflow handling. Assorted fixes. + * 04/07/.. ak Better overflow handling. Assorted fixes. + * 05/09/10 linville Add support for syncing ranges, support syncing for + * DMA_BIDIRECTIONAL mappings, miscellaneous cleanup. */ #include <linux/cache.h> +#include <linux/dma-mapping.h> #include <linux/mm.h> #include <linux/module.h> -#include <linux/pci.h> #include <linux/spinlock.h> #include <linux/string.h> #include <linux/types.h> #include <linux/ctype.h> #include <asm/io.h> -#include <asm/pci.h> #include <asm/dma.h> +#include <asm/scatterlist.h> #include <linux/init.h> #include <linux/bootmem.h> @@ -58,6 +60,14 @@ */ #define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT) +/* + * Enumeration for sync targets + */ +enum dma_sync_target { + SYNC_FOR_CPU = 0, + SYNC_FOR_DEVICE = 1, +}; + int swiotlb_force; /* @@ -117,7 +127,7 @@ __setup("swiotlb=", setup_io_tlb_npages); /* * Statically reserve bounce buffer space and initialize bounce buffer data - * structures for the software IO TLB used to implement the PCI DMA API. + * structures for the software IO TLB used to implement the DMA API. */ void swiotlb_init_with_default_size (size_t default_size) @@ -397,21 +407,28 @@ unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir) } static void -sync_single(struct device *hwdev, char *dma_addr, size_t size, int dir) +sync_single(struct device *hwdev, char *dma_addr, size_t size, + int dir, int target) { int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT; char *buffer = io_tlb_orig_addr[index]; - /* - * bounce... copy the data back into/from the original buffer - * XXX How do you handle DMA_BIDIRECTIONAL here ? - */ - if (dir == DMA_FROM_DEVICE) - memcpy(buffer, dma_addr, size); - else if (dir == DMA_TO_DEVICE) - memcpy(dma_addr, buffer, size); - else + switch (target) { + case SYNC_FOR_CPU: + if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) + memcpy(buffer, dma_addr, size); + else if (dir != DMA_TO_DEVICE) + BUG(); + break; + case SYNC_FOR_DEVICE: + if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) + memcpy(dma_addr, buffer, size); + else if (dir != DMA_FROM_DEVICE) + BUG(); + break; + default: BUG(); + } } void * @@ -485,24 +502,24 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic) /* * Ran out of IOMMU space for this operation. This is very bad. * Unfortunately the drivers cannot handle this operation properly. - * unless they check for pci_dma_mapping_error (most don't) + * unless they check for dma_mapping_error (most don't) * When the mapping is small enough return a static buffer to limit * the damage, or panic when the transfer is too big. */ - printk(KERN_ERR "PCI-DMA: Out of SW-IOMMU space for %lu bytes at " + printk(KERN_ERR "DMA: Out of SW-IOMMU space for %lu bytes at " "device %s\n", size, dev ? dev->bus_id : "?"); if (size > io_tlb_overflow && do_panic) { - if (dir == PCI_DMA_FROMDEVICE || dir == PCI_DMA_BIDIRECTIONAL) - panic("PCI-DMA: Memory would be corrupted\n"); - if (dir == PCI_DMA_TODEVICE || dir == PCI_DMA_BIDIRECTIONAL) - panic("PCI-DMA: Random memory would be DMAed\n"); + if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) + panic("DMA: Memory would be corrupted\n"); + if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) + panic("DMA: Random memory would be DMAed\n"); } } /* * Map a single buffer of the indicated size for DMA in streaming mode. The - * PCI address to use is returned. + * physical address to use is returned. * * Once the device is given the dma address, the device owns this memory until * either swiotlb_unmap_single or swiotlb_dma_sync_single is performed. @@ -589,39 +606,73 @@ swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, size_t size, * after a transfer. * * If you perform a swiotlb_map_single() but wish to interrogate the buffer - * using the cpu, yet do not wish to teardown the PCI dma mapping, you must - * call this function before doing so. At the next point you give the PCI dma + * using the cpu, yet do not wish to teardown the dma mapping, you must + * call this function before doing so. At the next point you give the dma * address back to the card, you must first perform a * swiotlb_dma_sync_for_device, and then the device again owns the buffer */ -void -swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, - size_t size, int dir) +static inline void +swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr, + size_t size, int dir, int target) { char *dma_addr = phys_to_virt(dev_addr); if (dir == DMA_NONE) BUG(); if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end) - sync_single(hwdev, dma_addr, size, dir); + sync_single(hwdev, dma_addr, size, dir, target); else if (dir == DMA_FROM_DEVICE) mark_clean(dma_addr, size); } void +swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, + size_t size, int dir) +{ + swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU); +} + +void swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, size_t size, int dir) { - char *dma_addr = phys_to_virt(dev_addr); + swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE); +} + +/* + * Same as above, but for a sub-range of the mapping. + */ +static inline void +swiotlb_sync_single_range(struct device *hwdev, dma_addr_t dev_addr, + unsigned long offset, size_t size, + int dir, int target) +{ + char *dma_addr = phys_to_virt(dev_addr) + offset; if (dir == DMA_NONE) BUG(); if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end) - sync_single(hwdev, dma_addr, size, dir); + sync_single(hwdev, dma_addr, size, dir, target); else if (dir == DMA_FROM_DEVICE) mark_clean(dma_addr, size); } +void +swiotlb_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dev_addr, + unsigned long offset, size_t size, int dir) +{ + swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir, + SYNC_FOR_CPU); +} + +void +swiotlb_sync_single_range_for_device(struct device *hwdev, dma_addr_t dev_addr, + unsigned long offset, size_t size, int dir) +{ + swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir, + SYNC_FOR_DEVICE); +} + /* * Map a set of buffers described by scatterlist in streaming mode for DMA. * This is the scatter-gather version of the above swiotlb_map_single @@ -696,9 +747,9 @@ swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nelems, * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules * and usage. */ -void -swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, - int nelems, int dir) +static inline void +swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sg, + int nelems, int dir, int target) { int i; @@ -708,22 +759,21 @@ swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, for (i = 0; i < nelems; i++, sg++) if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg)) sync_single(hwdev, (void *) sg->dma_address, - sg->dma_length, dir); + sg->dma_length, dir, target); +} + +void +swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, + int nelems, int dir) +{ + swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU); } void swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, int nelems, int dir) { - int i; - - if (dir == DMA_NONE) - BUG(); - - for (i = 0; i < nelems; i++, sg++) - if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg)) - sync_single(hwdev, (void *) sg->dma_address, - sg->dma_length, dir); + swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE); } int @@ -733,9 +783,9 @@ swiotlb_dma_mapping_error(dma_addr_t dma_addr) } /* - * Return whether the given PCI device DMA address mask can be supported + * Return whether the given device DMA address mask can be supported * properly. For example, if your device can only drive the low 24-bits - * during PCI bus mastering, then you would pass 0x00ffffff as the mask to + * during bus mastering, then you would pass 0x00ffffff as the mask to * this function. */ int @@ -751,6 +801,8 @@ EXPORT_SYMBOL(swiotlb_map_sg); EXPORT_SYMBOL(swiotlb_unmap_sg); EXPORT_SYMBOL(swiotlb_sync_single_for_cpu); EXPORT_SYMBOL(swiotlb_sync_single_for_device); +EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_cpu); +EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_device); EXPORT_SYMBOL(swiotlb_sync_sg_for_cpu); EXPORT_SYMBOL(swiotlb_sync_sg_for_device); EXPORT_SYMBOL(swiotlb_dma_mapping_error); |