diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/drivers/block/ll_rw_blk.c linux/drivers/block/ll_rw_blk.c --- /opt/kernel/linux-2.4.5/drivers/block/ll_rw_blk.c Thu Apr 12 21:15:52 2001 +++ linux/drivers/block/ll_rw_blk.c Mon May 28 01:31:08 2001 @@ -22,6 +22,7 @@ #include #include #include +#include #include #include @@ -129,6 +130,7 @@ static int high_queued_sectors, low_queued_sectors; static int batch_requests, queue_nr_requests; static DECLARE_WAIT_QUEUE_HEAD(blk_buffers_wait); +unsigned long blk_max_low_pfn; static inline int get_max_sectors(kdev_t dev) { @@ -267,6 +269,32 @@ q->make_request_fn = mfn; } +/** + * blk_queue_bounce_limit - set bounce buffer limit for queue + * @q: the request queue for the device + * @bus_addr: bus address limit + * + * Description: + * Different hardware can have different requirements as to what pages + * it can do I/O directly to. A low level driver can call + * blk_queue_bounce_limit to have lower memory pages allocated as bounce + * buffers for doing I/O to pages residing above @page. By default + * the block layer sets this to the highest numbered "low" memory page, ie + * one the driver can still call bio_page() and get a valid address on. + **/ +void blk_queue_bounce_limit(request_queue_t *q, unsigned long dma_addr) +{ + q->bounce_limit = mem_map + (dma_addr >> PAGE_SHIFT); + + /* + * set page alloc gfp mask for bounce pages + */ + q->bounce_gfp = GFP_BUFFER; + + if (dma_addr > BLK_BOUNCE_HIGH) + q->bounce_gfp |= __GFP_DMA32; +} + static inline int ll_new_segment(request_queue_t *q, struct request *req, int max_segments) { if (req->nr_segments < max_segments) { @@ -279,7 +307,7 @@ static int ll_back_merge_fn(request_queue_t *q, struct request *req, struct buffer_head *bh, int max_segments) { - if (req->bhtail->b_data + req->bhtail->b_size == bh->b_data) + if (bh_bus(req->bhtail) + req->bhtail->b_size == bh_bus(bh)) return 1; return ll_new_segment(q, req, max_segments); } @@ -287,7 +315,7 @@ static int ll_front_merge_fn(request_queue_t *q, struct request *req, struct buffer_head *bh, int max_segments) { - if (bh->b_data + bh->b_size == req->bh->b_data) + if (bh_bus(bh) + bh->b_size == bh_bus(req->bh)) return 1; return ll_new_segment(q, req, max_segments); } @@ -297,7 +325,7 @@ { int total_segments = req->nr_segments + next->nr_segments; - if (req->bhtail->b_data + req->bhtail->b_size == next->bh->b_data) + if (bh_bus(req->bhtail) + req->bhtail->b_size == bh_bus(next->bh)) total_segments--; if (total_segments > max_segments) @@ -431,6 +459,8 @@ */ q->plug_device_fn = generic_plug_device; q->head_active = 1; + + blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH); } #define blkdev_free_rq(list) list_entry((list)->next, struct request, table); @@ -704,9 +734,7 @@ * driver. Create a bounce buffer if the buffer data points into * high memory - keep the original buffer otherwise. */ -#if CONFIG_HIGHMEM - bh = create_bounce(rw, bh); -#endif + bh = blk_queue_bounce(q, rw, bh); /* look for a free request. */ /* @@ -751,8 +779,13 @@ elevator->elevator_merge_cleanup_fn(q, req, count); bh->b_reqnext = req->bh; req->bh = bh; + /* + * may not be valid, but queues not having bounce + * enabled for highmem pages must not look at + * ->buffer anyway + */ req->buffer = bh->b_data; - req->current_nr_sectors = count; + req->current_nr_sectors = req->hard_cur_sectors = count; req->sector = req->hard_sector = sector; req->nr_sectors = req->hard_nr_sectors += count; blk_started_io(count); @@ -802,7 +835,7 @@ req->errors = 0; req->hard_sector = req->sector = sector; req->hard_nr_sectors = req->nr_sectors = count; - req->current_nr_sectors = count; + req->current_nr_sectors = req->hard_cur_sectors = count; req->nr_segments = 1; /* Always 1 for a new request. */ req->nr_hw_segments = 1; /* Always 1 for a new request. */ req->buffer = bh->b_data; @@ -1125,6 +1158,7 @@ req->nr_sectors = req->hard_nr_sectors; req->current_nr_sectors = bh->b_size >> 9; + req->hard_cur_sectors = req->current_nr_sectors; if (req->nr_sectors < req->current_nr_sectors) { req->nr_sectors = req->current_nr_sectors; printk("end_request: buffer-list destroyed\n"); @@ -1202,6 +1236,8 @@ low_queued_sectors / 2, queue_nr_requests); + blk_max_low_pfn = max_low_pfn; + #ifdef CONFIG_AMIGA_Z2RAM z2_init(); #endif @@ -1322,3 +1358,5 @@ EXPORT_SYMBOL(blkdev_release_request); EXPORT_SYMBOL(generic_unplug_device); EXPORT_SYMBOL(queued_sectors); +EXPORT_SYMBOL(blk_queue_bounce_limit); +EXPORT_SYMBOL(blk_max_low_pfn); diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/drivers/block/loop.c linux/drivers/block/loop.c --- /opt/kernel/linux-2.4.5/drivers/block/loop.c Thu Apr 12 04:05:14 2001 +++ linux/drivers/block/loop.c Sun May 27 18:26:41 2001 @@ -453,9 +453,7 @@ goto err; } -#if CONFIG_HIGHMEM - rbh = create_bounce(rw, rbh); -#endif + rbh = blk_queue_bounce(q, rw, rbh); /* * file backed, queue for loop_thread to handle diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/drivers/ide/hpt34x.c linux/drivers/ide/hpt34x.c --- /opt/kernel/linux-2.4.5/drivers/ide/hpt34x.c Sat May 26 13:30:48 2001 +++ linux/drivers/ide/hpt34x.c Sun May 27 17:50:26 2001 @@ -425,6 +425,7 @@ hwif->autodma = 0; hwif->dmaproc = &hpt34x_dmaproc; + hwif->highmem = 1; } else { hwif->drives[0].autotune = 1; hwif->drives[1].autotune = 1; diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/drivers/ide/hpt366.c linux/drivers/ide/hpt366.c --- /opt/kernel/linux-2.4.5/drivers/ide/hpt366.c Sat May 26 13:30:48 2001 +++ linux/drivers/ide/hpt366.c Sun May 27 17:50:26 2001 @@ -710,6 +710,7 @@ hwif->autodma = 1; else hwif->autodma = 0; + hwif->highmem = 1; } else { hwif->autodma = 0; hwif->drives[0].autotune = 1; diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/drivers/ide/ide-disk.c linux/drivers/ide/ide-disk.c --- /opt/kernel/linux-2.4.5/drivers/ide/ide-disk.c Fri Feb 9 20:30:23 2001 +++ linux/drivers/ide/ide-disk.c Mon May 28 02:10:44 2001 @@ -27,9 +27,10 @@ * Version 1.09 added increment of rq->sector in ide_multwrite * added UDMA 3/4 reporting * Version 1.10 request queue changes, Ultra DMA 100 + * Version 1.11 Highmem I/O support, Jens Axboe */ -#define IDEDISK_VERSION "1.10" +#define IDEDISK_VERSION "1.11" #undef REALLY_SLOW_IO /* most systems can safely undef this */ @@ -140,6 +141,7 @@ int i; unsigned int msect, nsect; struct request *rq; + char *to; /* new way for dealing with premature shared PCI interrupts */ if (!OK_STAT(stat=GET_STAT(),DATA_READY,BAD_R_STAT)) { @@ -150,8 +152,8 @@ ide_set_handler(drive, &read_intr, WAIT_CMD, NULL); return ide_started; } + msect = drive->mult_count; - read_next: rq = HWGROUP(drive)->rq; if (msect) { @@ -160,14 +162,15 @@ msect -= nsect; } else nsect = 1; - idedisk_input_data(drive, rq->buffer, nsect * SECTOR_WORDS); + to = ide_map_buffer(rq); + idedisk_input_data(drive, to, nsect * SECTOR_WORDS); #ifdef DEBUG printk("%s: read: sectors(%ld-%ld), buffer=0x%08lx, remaining=%ld\n", drive->name, rq->sector, rq->sector+nsect-1, (unsigned long) rq->buffer+(nsect<<9), rq->nr_sectors-nsect); #endif + ide_unmap_buffer(to); rq->sector += nsect; - rq->buffer += nsect<<9; rq->errors = 0; i = (rq->nr_sectors -= nsect); if (((long)(rq->current_nr_sectors -= nsect)) <= 0) @@ -201,14 +204,15 @@ #endif if ((rq->nr_sectors == 1) ^ ((stat & DRQ_STAT) != 0)) { rq->sector++; - rq->buffer += 512; rq->errors = 0; i = --rq->nr_sectors; --rq->current_nr_sectors; if (((long)rq->current_nr_sectors) <= 0) ide_end_request(1, hwgroup); if (i > 0) { - idedisk_output_data (drive, rq->buffer, SECTOR_WORDS); + char *to = ide_map_buffer(rq); + idedisk_output_data (drive, to, SECTOR_WORDS); + ide_unmap_buffer(to); ide_set_handler (drive, &write_intr, WAIT_CMD, NULL); return ide_started; } @@ -238,14 +242,13 @@ do { char *buffer; int nsect = rq->current_nr_sectors; - + if (nsect > mcount) nsect = mcount; mcount -= nsect; - buffer = rq->buffer; + buffer = ide_map_buffer(rq); rq->sector += nsect; - rq->buffer += nsect << 9; rq->nr_sectors -= nsect; rq->current_nr_sectors -= nsect; @@ -259,7 +262,7 @@ } else { rq->bh = bh; rq->current_nr_sectors = bh->b_size >> 9; - rq->buffer = bh->b_data; + rq->hard_cur_sectors = rq->current_nr_sectors; } } @@ -268,6 +271,7 @@ * re-entering us on the last transfer. */ idedisk_output_data(drive, buffer, nsect<<7); + ide_unmap_buffer(buffer); } while (mcount); return 0; @@ -451,8 +455,10 @@ return ide_stopped; } } else { + char *buffer = ide_map_buffer(rq); ide_set_handler (drive, &write_intr, WAIT_CMD, NULL); - idedisk_output_data(drive, rq->buffer, SECTOR_WORDS); + idedisk_output_data(drive, buffer, SECTOR_WORDS); + ide_unmap_buffer(buffer); } return ide_started; } diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/drivers/ide/ide-dma.c linux/drivers/ide/ide-dma.c --- /opt/kernel/linux-2.4.5/drivers/ide/ide-dma.c Mon Jan 15 22:08:15 2001 +++ linux/drivers/ide/ide-dma.c Mon May 28 02:10:54 2001 @@ -221,24 +221,23 @@ hwif->sg_dma_direction = PCI_DMA_FROMDEVICE; else hwif->sg_dma_direction = PCI_DMA_TODEVICE; + + /* + * the PRD table is ridiculously oversized, so don't bother + * coalescing segments + */ bh = rq->bh; do { - unsigned char *virt_addr = bh->b_data; - unsigned int size = bh->b_size; + struct scatterlist *sge; if (nents >= PRD_ENTRIES) return 0; - while ((bh = bh->b_reqnext) != NULL) { - if ((virt_addr + size) != (unsigned char *) bh->b_data) - break; - size += bh->b_size; - } - memset(&sg[nents], 0, sizeof(*sg)); - sg[nents].address = virt_addr; - sg[nents].length = size; + sge = &sg[nents]; + memset(sge, 0, sizeof(*sge)); + set_bh_sg(sge, bh); nents++; - } while (bh != NULL); + } while ((bh = bh->b_reqnext) != NULL); return pci_map_sg(hwif->pci_dev, sg, nents, hwif->sg_dma_direction); } @@ -471,15 +470,19 @@ ide_hwif_t *hwif = HWIF(drive); unsigned long dma_base = hwif->dma_base; byte unit = (drive->select.b.unit & 0x01); - unsigned int count, reading = 0; + unsigned int count, reading = 0, set_high = 1; byte dma_stat; switch (func) { case ide_dma_off: printk("%s: DMA disabled\n", drive->name); + blk_queue_bounce_limit(&drive->queue, BLK_BOUNCE_HIGH); + set_high = 0; case ide_dma_off_quietly: outb(inb(dma_base+2) & ~(1<<(5+unit)), dma_base+2); case ide_dma_on: + if (set_high && drive->media == ide_disk && HWIF(drive)->highmem) + blk_queue_bounce_limit(&drive->queue, BLK_BOUNCE_4G); drive->using_dma = (func == ide_dma_on); if (drive->using_dma) outb(inb(dma_base+2)|(1<<(5+unit)), dma_base+2); diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/drivers/ide/pdc202xx.c linux/drivers/ide/pdc202xx.c --- /opt/kernel/linux-2.4.5/drivers/ide/pdc202xx.c Sat May 26 13:30:48 2001 +++ linux/drivers/ide/pdc202xx.c Sun May 27 17:50:26 2001 @@ -855,6 +855,7 @@ #ifdef CONFIG_BLK_DEV_IDEDMA if (hwif->dma_base) { hwif->dmaproc = &pdc202xx_dmaproc; + hwif->highmem = 1; if (!noautodma) hwif->autodma = 1; } else { diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/drivers/ide/piix.c linux/drivers/ide/piix.c --- /opt/kernel/linux-2.4.5/drivers/ide/piix.c Wed Mar 7 04:44:34 2001 +++ linux/drivers/ide/piix.c Sun May 27 17:50:26 2001 @@ -510,6 +510,7 @@ if (!hwif->dma_base) return; + hwif->highmem = 1; #ifndef CONFIG_BLK_DEV_IDEDMA hwif->autodma = 0; #else /* CONFIG_BLK_DEV_IDEDMA */ diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/drivers/scsi/aic7xxx/aic7xxx_linux_host.h linux/drivers/scsi/aic7xxx/aic7xxx_linux_host.h --- /opt/kernel/linux-2.4.5/drivers/scsi/aic7xxx/aic7xxx_linux_host.h Sat May 26 13:30:49 2001 +++ linux/drivers/scsi/aic7xxx/aic7xxx_linux_host.h Sun May 27 17:50:26 2001 @@ -81,7 +81,8 @@ present: 0, /* number of 7xxx's present */\ unchecked_isa_dma: 0, /* no memory DMA restrictions */\ use_clustering: ENABLE_CLUSTERING, \ - use_new_eh_code: 1 \ + use_new_eh_code: 1, \ + can_dma_32: 1 \ } #endif /* _AIC7XXX_LINUX_HOST_H_ */ diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/drivers/scsi/hosts.c linux/drivers/scsi/hosts.c --- /opt/kernel/linux-2.4.5/drivers/scsi/hosts.c Mon Oct 30 23:44:29 2000 +++ linux/drivers/scsi/hosts.c Sun May 27 17:50:26 2001 @@ -230,6 +230,7 @@ retval->cmd_per_lun = tpnt->cmd_per_lun; retval->unchecked_isa_dma = tpnt->unchecked_isa_dma; retval->use_clustering = tpnt->use_clustering; + retval->can_dma_32 = tpnt->can_dma_32; retval->select_queue_depths = tpnt->select_queue_depths; diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/drivers/scsi/hosts.h linux/drivers/scsi/hosts.h --- /opt/kernel/linux-2.4.5/drivers/scsi/hosts.h Sat Apr 28 00:49:20 2001 +++ linux/drivers/scsi/hosts.h Mon May 28 02:09:44 2001 @@ -286,6 +286,8 @@ */ unsigned emulated:1; + unsigned can_dma_32:1; + /* * Name of proc directory */ @@ -384,6 +386,7 @@ unsigned in_recovery:1; unsigned unchecked_isa_dma:1; unsigned use_clustering:1; + unsigned can_dma_32:1; /* * True if this host was loaded as a loadable module */ diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/drivers/scsi/scsi.c linux/drivers/scsi/scsi.c --- /opt/kernel/linux-2.4.5/drivers/scsi/scsi.c Sat May 26 13:30:49 2001 +++ linux/drivers/scsi/scsi.c Mon May 28 00:10:34 2001 @@ -176,10 +176,13 @@ * handler in the list - ultimately they call scsi_request_fn * to do the dirty deed. */ -void scsi_initialize_queue(Scsi_Device * SDpnt, struct Scsi_Host * SHpnt) { - blk_init_queue(&SDpnt->request_queue, scsi_request_fn); - blk_queue_headactive(&SDpnt->request_queue, 0); - SDpnt->request_queue.queuedata = (void *) SDpnt; +void scsi_initialize_queue(Scsi_Device * SDpnt, struct Scsi_Host * SHpnt) +{ + request_queue_t *q = &SDpnt->request_queue; + + blk_init_queue(q, scsi_request_fn); + blk_queue_headactive(q, 0); + q->queuedata = (void *) SDpnt; } #ifdef MODULE @@ -478,6 +481,7 @@ SCpnt->old_use_sg = 0; SCpnt->transfersize = 0; /* No default transfer size */ SCpnt->cmd_len = 0; + SCpnt->buf_mapped = 0; SCpnt->sc_data_direction = SCSI_DATA_UNKNOWN; SCpnt->sc_request = NULL; diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/drivers/scsi/scsi.h linux/drivers/scsi/scsi.h --- /opt/kernel/linux-2.4.5/drivers/scsi/scsi.h Sat Apr 28 00:49:19 2001 +++ linux/drivers/scsi/scsi.h Mon May 28 02:09:44 2001 @@ -391,7 +391,7 @@ #define CONTIGUOUS_BUFFERS(X,Y) \ (virt_to_phys((X)->b_data+(X)->b_size-1)+1==virt_to_phys((Y)->b_data)) #else -#define CONTIGUOUS_BUFFERS(X,Y) ((X->b_data+X->b_size) == Y->b_data) +#define CONTIGUOUS_BUFFERS(X,Y) (bh_bus((X)) + (X)->b_size == bh_bus((Y))) #endif @@ -787,6 +787,12 @@ * timeout handler is already running. */ unsigned done_late:1; + + /* + * higmem capable host, but we needed to resort to kmapping + * the buffer in. + */ + unsigned buf_mapped:1; /* Low-level done function - can be used by low-level driver to point * to completion function. Not used by mid/upper level code. */ diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/drivers/scsi/scsi_lib.c linux/drivers/scsi/scsi_lib.c --- /opt/kernel/linux-2.4.5/drivers/scsi/scsi_lib.c Sat May 26 13:30:49 2001 +++ linux/drivers/scsi/scsi_lib.c Mon May 28 01:13:45 2001 @@ -406,7 +406,6 @@ q = &SCpnt->device->request_queue; - req->buffer = bh->b_data; /* * Bleah. Leftovers again. Stick the leftovers in * the front of the queue, and goose the queue again. @@ -485,6 +484,8 @@ */ static void scsi_release_buffers(Scsi_Cmnd * SCpnt) { + struct request *req = &SCpnt->request; + ASSERT_LOCK(&io_request_lock, 0); /* @@ -503,9 +504,10 @@ } scsi_free(SCpnt->request_buffer, SCpnt->sglist_len); } else { - if (SCpnt->request_buffer != SCpnt->request.buffer) { - scsi_free(SCpnt->request_buffer, SCpnt->request_bufflen); - } + if (SCpnt->request_buffer != req->buffer) + scsi_free(SCpnt->request_buffer,SCpnt->request_bufflen); + if (SCpnt->buf_mapped) + bh_kunmap_irq(req->buffer); } /* @@ -516,6 +518,7 @@ SCpnt->bufflen = 0; SCpnt->request_buffer = NULL; SCpnt->request_bufflen = 0; + SCpnt->buf_mapped = 0; } /* @@ -587,6 +590,8 @@ } scsi_free(SCpnt->buffer, SCpnt->bufflen); } + if (SCpnt->buf_mapped) + bh_kunmap_irq(SCpnt->request.buffer); } /* @@ -597,6 +602,7 @@ SCpnt->bufflen = 0; SCpnt->request_buffer = NULL; SCpnt->request_bufflen = 0; + SCpnt->buf_mapped = 0; /* * Next deal with any sectors which we were able to correctly diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/drivers/scsi/scsi_merge.c linux/drivers/scsi/scsi_merge.c --- /opt/kernel/linux-2.4.5/drivers/scsi/scsi_merge.c Fri Feb 9 20:30:23 2001 +++ linux/drivers/scsi/scsi_merge.c Mon May 28 01:29:55 2001 @@ -6,6 +6,7 @@ * Based upon conversations with large numbers * of people at Linux Expo. * Support for dynamic DMA mapping: Jakub Jelinek (jakub@redhat.com). + * Support for highmem I/O: Jens Axboe */ /* @@ -95,7 +96,7 @@ printk("Segment 0x%p, blocks %d, addr 0x%lx\n", bh, bh->b_size >> 9, - virt_to_phys(bh->b_data - 1)); + bh_bus(bh) - 1); } panic("Ththththaats all folks. Too dangerous to continue.\n"); } @@ -223,8 +224,7 @@ * DMA capable host, make sure that a segment doesn't span * the DMA threshold boundary. */ - if (dma_host && - virt_to_phys(bhnext->b_data) - 1 == ISA_DMA_THRESHOLD) { + if (dma_host && bh_bus(bhnext) - 1 == ISA_DMA_THRESHOLD) { ret++; reqsize = bhnext->b_size; } else if (CONTIGUOUS_BUFFERS(bh, bhnext)) { @@ -241,8 +241,7 @@ * kind of screwed and we need to start * another segment. */ - if( dma_host - && virt_to_phys(bh->b_data) - 1 >= ISA_DMA_THRESHOLD + if( dma_host && bh_bus(bh) - 1 >= ISA_DMA_THRESHOLD && reqsize + bhnext->b_size > PAGE_SIZE ) { ret++; @@ -304,7 +303,7 @@ } #define MERGEABLE_BUFFERS(X,Y) \ -(((((long)(X)->b_data+(X)->b_size)|((long)(Y)->b_data)) & \ +(((((long)bh_bus((X))+(X)->b_size)|((long)bh_bus((Y)))) & \ (DMA_CHUNK_SIZE - 1)) == 0) #ifdef DMA_CHUNK_SIZE @@ -424,14 +423,11 @@ * DMA capable host, make sure that a segment doesn't span * the DMA threshold boundary. */ - if (dma_host && - virt_to_phys(req->bhtail->b_data) - 1 == ISA_DMA_THRESHOLD) { + if (dma_host && bh_bus(req->bhtail) - 1 == ISA_DMA_THRESHOLD) goto new_end_segment; - } if (CONTIGUOUS_BUFFERS(req->bhtail, bh)) { #ifdef DMA_SEGMENT_SIZE_LIMITED - if( dma_host - && virt_to_phys(bh->b_data) - 1 >= ISA_DMA_THRESHOLD ) { + if (dma_host && bh_bus(bh) - 1 >= ISA_DMA_THRESHOLD) { segment_size = 0; count = __count_segments(req, use_clustering, dma_host, &segment_size); if( segment_size + bh->b_size > PAGE_SIZE ) { @@ -480,14 +476,12 @@ * DMA capable host, make sure that a segment doesn't span * the DMA threshold boundary. */ - if (dma_host && - virt_to_phys(bh->b_data) - 1 == ISA_DMA_THRESHOLD) { + if (dma_host && bh_bus(bh) - 1 == ISA_DMA_THRESHOLD) { goto new_start_segment; } if (CONTIGUOUS_BUFFERS(bh, req->bh)) { #ifdef DMA_SEGMENT_SIZE_LIMITED - if( dma_host - && virt_to_phys(bh->b_data) - 1 >= ISA_DMA_THRESHOLD ) { + if (dma_host && bh_bus(bh) - 1 >= ISA_DMA_THRESHOLD) { segment_size = bh->b_size; count = __count_segments(req, use_clustering, dma_host, &segment_size); if( count != req->nr_segments ) { @@ -635,10 +629,8 @@ * DMA capable host, make sure that a segment doesn't span * the DMA threshold boundary. */ - if (dma_host && - virt_to_phys(req->bhtail->b_data) - 1 == ISA_DMA_THRESHOLD) { + if (dma_host && bh_bus(req->bhtail) - 1 == ISA_DMA_THRESHOLD) goto dont_combine; - } #ifdef DMA_SEGMENT_SIZE_LIMITED /* * We currently can only allocate scatter-gather bounce @@ -646,7 +638,7 @@ */ if (dma_host && CONTIGUOUS_BUFFERS(req->bhtail, next->bh) - && virt_to_phys(req->bhtail->b_data) - 1 >= ISA_DMA_THRESHOLD ) + && bh_bus(req->bhtail) - 1 >= ISA_DMA_THRESHOLD ) { int segment_size = 0; int count = 0; @@ -791,29 +783,6 @@ struct scatterlist * sgpnt; int this_count; - /* - * FIXME(eric) - don't inline this - it doesn't depend on the - * integer flags. Come to think of it, I don't think this is even - * needed any more. Need to play with it and see if we hit the - * panic. If not, then don't bother. - */ - if (!SCpnt->request.bh) { - /* - * Case of page request (i.e. raw device), or unlinked buffer - * Typically used for swapping, but this isn't how we do - * swapping any more. - */ - panic("I believe this is dead code. If we hit this, I was wrong"); -#if 0 - SCpnt->request_bufflen = SCpnt->request.nr_sectors << 9; - SCpnt->request_buffer = SCpnt->request.buffer; - SCpnt->use_sg = 0; - /* - * FIXME(eric) - need to handle DMA here. - */ -#endif - return 1; - } req = &SCpnt->request; /* * First we need to know how many scatter gather segments are needed. @@ -830,24 +799,16 @@ * buffer. */ if (dma_host && scsi_dma_free_sectors <= 10) { - this_count = SCpnt->request.current_nr_sectors; - goto single_segment; - } - /* - * Don't bother with scatter-gather if there is only one segment. - */ - if (count == 1) { - this_count = SCpnt->request.nr_sectors; + this_count = req->current_nr_sectors; goto single_segment; } - SCpnt->use_sg = count; /* * Allocate the actual scatter-gather table itself. * scsi_malloc can only allocate in chunks of 512 bytes */ - SCpnt->sglist_len = (SCpnt->use_sg - * sizeof(struct scatterlist) + 511) & ~511; + SCpnt->use_sg = count; + SCpnt->sglist_len = (count * sizeof(struct scatterlist) + 511) & ~511; sgpnt = (struct scatterlist *) scsi_malloc(SCpnt->sglist_len); @@ -860,7 +821,7 @@ * simply write the first buffer all by itself. */ printk("Warning - running *really* short on DMA buffers\n"); - this_count = SCpnt->request.current_nr_sectors; + this_count = req->current_nr_sectors; goto single_segment; } /* @@ -872,11 +833,9 @@ SCpnt->request_bufflen = 0; bhprev = NULL; - for (count = 0, bh = SCpnt->request.bh; - bh; bh = bh->b_reqnext) { + for (count = 0, bh = req->bh; bh; bh = bh->b_reqnext) { if (use_clustering && bhprev != NULL) { - if (dma_host && - virt_to_phys(bhprev->b_data) - 1 == ISA_DMA_THRESHOLD) { + if (dma_host && bh_bus(bhprev) - 1 == ISA_DMA_THRESHOLD) { /* Nothing - fall through */ } else if (CONTIGUOUS_BUFFERS(bhprev, bh)) { /* @@ -887,7 +846,7 @@ */ if( dma_host ) { #ifdef DMA_SEGMENT_SIZE_LIMITED - if( virt_to_phys(bh->b_data) - 1 < ISA_DMA_THRESHOLD + if (bh_bus(bh) - 1 < ISA_DMA_THRESHOLD || sgpnt[count - 1].length + bh->b_size <= PAGE_SIZE ) { sgpnt[count - 1].length += bh->b_size; bhprev = bh; @@ -906,12 +865,12 @@ } } } - count++; - sgpnt[count - 1].address = bh->b_data; - sgpnt[count - 1].length += bh->b_size; - if (!dma_host) { + + set_bh_sg(&sgpnt[count], bh); + if (!dma_host) SCpnt->request_bufflen += bh->b_size; - } + + count++; bhprev = bh; } @@ -934,6 +893,10 @@ for (i = 0; i < count; i++) { sectors = (sgpnt[i].length >> 9); SCpnt->request_bufflen += sgpnt[i].length; + /* + * only done for dma_host, in which case .page is not + * set since it's guarenteed to be a low memory page + */ if (virt_to_phys(sgpnt[i].address) + sgpnt[i].length - 1 > ISA_DMA_THRESHOLD) { if( scsi_dma_free_sectors - sectors <= 10 ) { @@ -969,7 +932,7 @@ } break; } - if (SCpnt->request.cmd == WRITE) { + if (req->cmd == WRITE) { memcpy(sgpnt[i].address, sgpnt[i].alt_address, sgpnt[i].length); } @@ -1014,8 +977,7 @@ * single-block requests if we had hundreds of free sectors. */ if( scsi_dma_free_sectors > 30 ) { - for (this_count = 0, bh = SCpnt->request.bh; - bh; bh = bh->b_reqnext) { + for (this_count = 0, bh = req->bh; bh; bh = bh->b_reqnext) { if( scsi_dma_free_sectors - this_count < 30 || this_count == sectors ) { @@ -1028,7 +990,7 @@ /* * Yow! Take the absolute minimum here. */ - this_count = SCpnt->request.current_nr_sectors; + this_count = req->current_nr_sectors; } /* @@ -1041,8 +1003,8 @@ * segment. Possibly the entire request, or possibly a small * chunk of the entire request. */ - bh = SCpnt->request.bh; - buff = SCpnt->request.buffer; + buff = req->buffer = bh_kmap_irq(req->bh); + SCpnt->buf_mapped = 1; if (dma_host) { /* @@ -1050,19 +1012,18 @@ * back and allocate a really small one - enough to satisfy * the first buffer. */ - if (virt_to_phys(SCpnt->request.bh->b_data) - + (this_count << 9) - 1 > ISA_DMA_THRESHOLD) { + if (bh_bus(req->bh) + (this_count << 9) - 1 > ISA_DMA_THRESHOLD) { buff = (char *) scsi_malloc(this_count << 9); if (!buff) { printk("Warning - running low on DMA memory\n"); - this_count = SCpnt->request.current_nr_sectors; + this_count = req->current_nr_sectors; buff = (char *) scsi_malloc(this_count << 9); if (!buff) { dma_exhausted(SCpnt, 0); } } if (SCpnt->request.cmd == WRITE) - memcpy(buff, (char *) SCpnt->request.buffer, this_count << 9); + memcpy(buff, req->buffer, this_count << 9); } } SCpnt->request_bufflen = this_count << 9; @@ -1110,14 +1071,6 @@ q = &SDpnt->request_queue; /* - * If the host has already selected a merge manager, then don't - * pick a new one. - */ -#if 0 - if (q->back_merge_fn && q->front_merge_fn) - return; -#endif - /* * If this host has an unlimited tablesize, then don't bother with a * merge manager. The whole point of the operation is to make sure * that requests don't grow too large, and this host isn't picky. @@ -1149,4 +1102,12 @@ q->merge_requests_fn = scsi_merge_requests_fn_dc; SDpnt->scsi_init_io_fn = scsi_init_io_vdc; } + + /* + * now enable highmem I/O, if appropriate + */ + if (SHpnt->can_dma_32 && (SDpnt->type == TYPE_DISK)) + blk_queue_bounce_limit(q, BLK_BOUNCE_4G); + else + blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH); } diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/drivers/scsi/sym53c8xx.h linux/drivers/scsi/sym53c8xx.h --- /opt/kernel/linux-2.4.5/drivers/scsi/sym53c8xx.h Sat Apr 28 00:50:16 2001 +++ linux/drivers/scsi/sym53c8xx.h Sun May 27 17:50:26 2001 @@ -96,7 +96,8 @@ this_id: 7, \ sg_tablesize: SCSI_NCR_SG_TABLESIZE, \ cmd_per_lun: SCSI_NCR_CMD_PER_LUN, \ - use_clustering: DISABLE_CLUSTERING} + use_clustering: DISABLE_CLUSTERING, \ + can_dma_32: 1} #else diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/fs/buffer.c linux/fs/buffer.c --- /opt/kernel/linux-2.4.5/fs/buffer.c Sat May 26 13:30:49 2001 +++ linux/fs/buffer.c Sun May 27 23:45:46 2001 @@ -150,10 +150,10 @@ atomic_inc(&bh->b_count); add_wait_queue(&bh->b_wait, &wait); do { - run_task_queue(&tq_disk); set_task_state(tsk, TASK_UNINTERRUPTIBLE); if (!buffer_locked(bh)) break; + run_task_queue(&tq_disk); schedule(); } while (buffer_locked(bh)); tsk->state = TASK_RUNNING; @@ -1267,13 +1267,11 @@ bh->b_page = page; if (offset >= PAGE_SIZE) BUG(); - if (PageHighMem(page)) - /* - * This catches illegal uses and preserves the offset: - */ - bh->b_data = (char *)(0 + offset); - else - bh->b_data = page_address(page) + offset; + /* + * ->virtual is NULL on highmem pages, so we can catch the + * offset even though using page_address on it + */ + bh->b_data = page_address(page) + offset; } /* diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/include/asm-i386/kmap_types.h linux/include/asm-i386/kmap_types.h --- /opt/kernel/linux-2.4.5/include/asm-i386/kmap_types.h Thu Apr 12 21:11:39 2001 +++ linux/include/asm-i386/kmap_types.h Mon May 28 01:28:29 2001 @@ -6,6 +6,7 @@ KM_BOUNCE_WRITE, KM_SKB_DATA, KM_SKB_DATA_SOFTIRQ, + KM_BH_IRQ, KM_TYPE_NR }; diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/include/asm-i386/page.h linux/include/asm-i386/page.h --- /opt/kernel/linux-2.4.5/include/asm-i386/page.h Sat Apr 28 00:48:20 2001 +++ linux/include/asm-i386/page.h Sun May 27 18:26:59 2001 @@ -116,7 +116,8 @@ #define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET)) #define virt_to_page(kaddr) (mem_map + (__pa(kaddr) >> PAGE_SHIFT)) #define VALID_PAGE(page) ((page - mem_map) < max_mapnr) - +#define page_to_phys(page) (((page) - mem_map) * PAGE_SIZE) +#define page_to_bus(page) page_to_phys((page)) #endif /* __KERNEL__ */ diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/include/asm-i386/pci.h linux/include/asm-i386/pci.h --- /opt/kernel/linux-2.4.5/include/asm-i386/pci.h Sat May 26 13:30:49 2001 +++ linux/include/asm-i386/pci.h Mon May 28 02:07:54 2001 @@ -22,6 +22,7 @@ #include #include +#include #include #include #include @@ -78,6 +79,27 @@ /* Nothing to do */ } +/* + * pci_{map,unmap}_single_page maps a kernel page to a dma_addr_t. identical + * to pci_map_single, but takes a struct page instead of a virtual address + */ +extern inline dma_addr_t pci_map_page(struct pci_dev *hwdev, struct page *page, + size_t size, int offset, int direction) +{ + if (direction == PCI_DMA_NONE) + BUG(); + + return (page - mem_map) * PAGE_SIZE + offset; +} + +extern inline void pci_unmap_page(struct pci_dev *hwdev, dma_addr_t dma_address, + size_t size, int direction) +{ + if (direction == PCI_DMA_NONE) + BUG(); + /* Nothing to do */ +} + /* Map a set of buffers described by scatterlist in streaming * mode for DMA. This is the scather-gather version of the * above pci_map_single interface. Here the scatter gather list @@ -96,8 +118,26 @@ extern inline int pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sg, int nents, int direction) { + int i; + if (direction == PCI_DMA_NONE) BUG(); + + /* + * temporary 2.4 hack + */ + for (i = 0; i < nents; i++ ) { + if (sg[i].address && sg[i].page) + BUG(); + else if (!sg[i].address && !sg[i].page) + BUG(); + + if (sg[i].page) + sg[i].dma_address = page_to_bus(sg[i].page) + sg[i].offset; + else + sg[i].dma_address = virt_to_bus(sg[i].address); + } + return nents; } @@ -167,10 +207,9 @@ /* These macros should be used after a pci_map_sg call has been done * to get bus addresses of each of the SG entries and their lengths. * You should only work with the number of sg entries pci_map_sg - * returns, or alternatively stop on the first sg_dma_len(sg) which - * is 0. + * returns. */ -#define sg_dma_address(sg) (virt_to_bus((sg)->address)) +#define sg_dma_address(sg) ((sg)->dma_address) #define sg_dma_len(sg) ((sg)->length) /* Return the index of the PCI controller for device. */ diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/include/asm-i386/scatterlist.h linux/include/asm-i386/scatterlist.h --- /opt/kernel/linux-2.4.5/include/asm-i386/scatterlist.h Mon Dec 30 12:01:10 1996 +++ linux/include/asm-i386/scatterlist.h Mon May 28 02:02:36 2001 @@ -1,12 +1,34 @@ #ifndef _I386_SCATTERLIST_H #define _I386_SCATTERLIST_H +/* + * temporary measure, include a page and offset. + */ struct scatterlist { - char * address; /* Location data is to be transferred to */ + struct page * page; /* Location for highmem page, if any */ + char * address; /* Location data is to be transferred to, NULL for + * highmem page */ char * alt_address; /* Location of actual if address is a * dma indirect buffer. NULL otherwise */ + dma_addr_t dma_address; unsigned int length; + unsigned int offset;/* for highmem, page offset */ }; + +extern inline void set_bh_sg(struct scatterlist *sg, struct buffer_head *bh) +{ + if (PageHighMem(bh->b_page)) { + sg->page = bh->b_page; + sg->offset = bh_offset(bh); + sg->address = NULL; + } else { + sg->page = NULL; + sg->offset = 0; + sg->address = bh->b_data; + } + + sg->length = bh->b_size; +} #define ISA_DMA_THRESHOLD (0x00ffffff) diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/include/linux/blkdev.h linux/include/linux/blkdev.h --- /opt/kernel/linux-2.4.5/include/linux/blkdev.h Sat Apr 28 00:48:49 2001 +++ linux/include/linux/blkdev.h Mon May 28 02:07:38 2001 @@ -38,7 +38,7 @@ unsigned long hard_sector, hard_nr_sectors; unsigned int nr_segments; unsigned int nr_hw_segments; - unsigned long current_nr_sectors; + unsigned long current_nr_sectors, hard_cur_sectors; void * special; char * buffer; struct semaphore * sem; @@ -112,6 +112,9 @@ */ char head_active; + struct page *bounce_limit; + int bounce_gfp; + /* * Is meant to protect the queue in the future instead of * io_request_lock @@ -123,6 +126,27 @@ */ wait_queue_head_t wait_for_request; }; + +extern unsigned long blk_max_low_pfn; + +#define BLK_BOUNCE_HIGH (blk_max_low_pfn * PAGE_SIZE) +#define BLK_BOUNCE_4G PCI_MAX_DMA32 + +extern void blk_queue_bounce_limit(request_queue_t *, unsigned long); + +#ifdef CONFIG_HIGHMEM +extern struct buffer_head *create_bounce(int, struct buffer_head *, int); +extern inline struct buffer_head *blk_queue_bounce(request_queue_t *q, int rw, + struct buffer_head *bh) +{ + if (bh->b_page <= q->bounce_limit) + return bh; + + return create_bounce(rw, bh, q->bounce_gfp); +} +#else +#define blk_queue_bounce(q, rw, bh) (bh) +#endif struct blk_dev_struct { /* diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/include/linux/fs.h linux/include/linux/fs.h --- /opt/kernel/linux-2.4.5/include/linux/fs.h Sat May 26 13:30:50 2001 +++ linux/include/linux/fs.h Sun May 27 18:41:23 2001 @@ -271,6 +271,8 @@ #define bh_offset(bh) ((unsigned long)(bh)->b_data & ~PAGE_MASK) +#define bh_bus(bh) (page_to_bus((bh)->b_page) + bh_offset((bh))) + extern void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset); #define touch_buffer(bh) SetPageReferenced(bh->b_page) diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/include/linux/highmem.h linux/include/linux/highmem.h --- /opt/kernel/linux-2.4.5/include/linux/highmem.h Sat Apr 28 00:48:31 2001 +++ linux/include/linux/highmem.h Mon May 28 02:07:43 2001 @@ -13,7 +13,8 @@ /* declarations for linux/mm/highmem.c */ FASTCALL(unsigned int nr_free_highpages(void)); -extern struct buffer_head * create_bounce(int rw, struct buffer_head * bh_orig); +extern struct buffer_head *create_bounce(int rw, struct buffer_head * bh_orig, + int gfp_mask); static inline char *bh_kmap(struct buffer_head *bh) @@ -26,6 +27,26 @@ kunmap(bh->b_page); } +/* + * remember to add offset! + */ +static inline char *bh_kmap_irq(struct buffer_head *bh) +{ + unsigned long addr = (unsigned long) kmap_atomic(bh->b_page, KM_BH_IRQ); + + if (addr & ~PAGE_MASK) + BUG(); + + return (char *) addr + bh_offset(bh); +} + +static inline void bh_kunmap_irq(char *buffer) +{ + char *ptr = buffer - (((unsigned long) buffer) & ~PAGE_MASK); + + kunmap_atomic(ptr, KM_BH_IRQ); +} + #else /* CONFIG_HIGHMEM */ static inline unsigned int nr_free_highpages(void) { return 0; } @@ -39,6 +60,8 @@ #define bh_kmap(bh) ((bh)->b_data) #define bh_kunmap(bh) do { } while (0) +#define bh_kmap_irq(bh) ((bh)->b_data) +#define bh_kunmap_irq(bh) do { } while (0) #endif /* CONFIG_HIGHMEM */ diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/include/linux/ide.h linux/include/linux/ide.h --- /opt/kernel/linux-2.4.5/include/linux/ide.h Sat May 26 13:30:50 2001 +++ linux/include/linux/ide.h Mon May 28 02:08:33 2001 @@ -457,6 +457,7 @@ unsigned reset : 1; /* reset after probe */ unsigned autodma : 1; /* automatically try to enable DMA at boot */ unsigned udma_four : 1; /* 1=ATA-66 capable, 0=default */ + unsigned highmem : 1; /* can do full 32-bit dma */ byte channel; /* for dual-port chips: 0=primary, 1=secondary */ #ifdef CONFIG_BLK_DEV_IDEPCI struct pci_dev *pci_dev; /* for pci chipsets */ @@ -752,6 +753,21 @@ ide_preempt, /* insert rq in front of current request */ ide_end /* insert rq at end of list, but don't wait for it */ } ide_action_t; + +/* + * temporarily mapping a (possible) highmem bio + */ +#define ide_rq_offset(rq) (((rq)->hard_cur_sectors - (rq)->current_nr_sectors) << 9) + +extern inline void *ide_map_buffer(struct request *rq) +{ + return bh_kmap_irq(rq->bh) + ide_rq_offset(rq); +} + +extern inline void ide_unmap_buffer(char *buffer) +{ + bh_kunmap_irq(buffer); +} /* * This function issues a special IDE device request diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/include/linux/pci.h linux/include/linux/pci.h --- /opt/kernel/linux-2.4.5/include/linux/pci.h Sat May 26 13:30:50 2001 +++ linux/include/linux/pci.h Mon May 28 02:11:10 2001 @@ -314,6 +314,8 @@ #define PCI_DMA_FROMDEVICE 2 #define PCI_DMA_NONE 3 +#define PCI_MAX_DMA32 (0xffffffff) + #define DEVICE_COUNT_COMPATIBLE 4 #define DEVICE_COUNT_IRQ 2 #define DEVICE_COUNT_DMA 2 diff -urN --exclude-from /home/axboe/exclude /opt/kernel/linux-2.4.5/mm/highmem.c linux/mm/highmem.c --- /opt/kernel/linux-2.4.5/mm/highmem.c Sat May 26 13:30:50 2001 +++ linux/mm/highmem.c Mon May 28 00:04:31 2001 @@ -180,20 +180,19 @@ static inline void copy_from_high_bh (struct buffer_head *to, struct buffer_head *from) { - struct page *p_from; - char *vfrom; + char *vfrom, *vto; unsigned long flags; - p_from = from->b_page; - /* * Since this can be executed from IRQ context, reentrance * on the same CPU must be avoided: */ __save_flags(flags); __cli(); - vfrom = kmap_atomic(p_from, KM_BOUNCE_WRITE); - memcpy(to->b_data, vfrom + bh_offset(from), to->b_size); + vfrom = kmap_atomic(from->b_page, KM_BOUNCE_WRITE); + vto = kmap_atomic(to->b_page, KM_BOUNCE_WRITE); + memcpy(vto, vfrom + bh_offset(from), to->b_size); + kunmap_atomic(vto, KM_BOUNCE_WRITE); kunmap_atomic(vfrom, KM_BOUNCE_WRITE); __restore_flags(flags); } @@ -201,15 +200,15 @@ static inline void copy_to_high_bh_irq (struct buffer_head *to, struct buffer_head *from) { - struct page *p_to; - char *vto; + char *vto, *vfrom; unsigned long flags; - p_to = to->b_page; __save_flags(flags); __cli(); - vto = kmap_atomic(p_to, KM_BOUNCE_READ); - memcpy(vto + bh_offset(to), from->b_data, to->b_size); + vto = kmap_atomic(to->b_page, KM_BOUNCE_READ); + vfrom = kmap_atomic(from->b_page, KM_BOUNCE_READ); + memcpy(vto + bh_offset(to), vfrom, to->b_size); + kunmap_atomic(vfrom, KM_BOUNCE_READ); kunmap_atomic(vto, KM_BOUNCE_READ); __restore_flags(flags); } @@ -296,13 +295,13 @@ bounce_end_io(bh, uptodate); } -struct page *alloc_bounce_page (void) +struct page *alloc_bounce_page (int gfp_mask) { struct list_head *tmp; struct page *page; repeat_alloc: - page = alloc_page(GFP_BUFFER); + page = alloc_page(gfp_mask); if (page) return page; /* @@ -372,14 +371,12 @@ goto repeat_alloc; } -struct buffer_head * create_bounce(int rw, struct buffer_head * bh_orig) +struct buffer_head * create_bounce(int rw, struct buffer_head * bh_orig, + int gfp_mask) { struct page *page; struct buffer_head *bh; - if (!PageHighMem(bh_orig->b_page)) - return bh_orig; - bh = alloc_bounce_bh(); /* * This is wasteful for 1k buffers, but this is a stopgap measure @@ -387,7 +384,7 @@ * things immensly. On boxes with more than 4GB RAM this should * not be an issue anyway. */ - page = alloc_bounce_page(); + page = alloc_bounce_page(gfp_mask); set_bh_page(bh, page, 0);