diff options
Diffstat (limited to 'drivers/s390')
80 files changed, 4992 insertions, 2827 deletions
diff --git a/drivers/s390/block/Kconfig b/drivers/s390/block/Kconfig index 9ac7574e3cfb..a8682f69effc 100644 --- a/drivers/s390/block/Kconfig +++ b/drivers/s390/block/Kconfig @@ -38,7 +38,7 @@ config DASD_PROFILE depends on DASD help Enable this option if you want to see profiling information - in /proc/dasd/statistics. + in /proc/dasd/statistics. config DASD_ECKD def_tristate y diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index e03304fe25bb..6cca72782af6 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -70,7 +70,6 @@ MODULE_LICENSE("GPL"); * SECTION: prototypes for static functions of dasd.c */ static int dasd_alloc_queue(struct dasd_block *); -static void dasd_setup_queue(struct dasd_block *); static void dasd_free_queue(struct dasd_block *); static int dasd_flush_block_queue(struct dasd_block *); static void dasd_device_tasklet(unsigned long); @@ -120,9 +119,18 @@ struct dasd_device *dasd_alloc_device(void) kfree(device); return ERR_PTR(-ENOMEM); } + /* Get two pages for ese format. */ + device->ese_mem = (void *)__get_free_pages(GFP_ATOMIC | GFP_DMA, 1); + if (!device->ese_mem) { + free_page((unsigned long) device->erp_mem); + free_pages((unsigned long) device->ccw_mem, 1); + kfree(device); + return ERR_PTR(-ENOMEM); + } dasd_init_chunklist(&device->ccw_chunks, device->ccw_mem, PAGE_SIZE*2); dasd_init_chunklist(&device->erp_chunks, device->erp_mem, PAGE_SIZE); + dasd_init_chunklist(&device->ese_chunks, device->ese_mem, PAGE_SIZE * 2); spin_lock_init(&device->mem_lock); atomic_set(&device->tasklet_scheduled, 0); tasklet_init(&device->tasklet, dasd_device_tasklet, @@ -146,6 +154,7 @@ struct dasd_device *dasd_alloc_device(void) void dasd_free_device(struct dasd_device *device) { kfree(device->private); + free_pages((unsigned long) device->ese_mem, 1); free_page((unsigned long) device->erp_mem); free_pages((unsigned long) device->ccw_mem, 1); kfree(device); @@ -348,7 +357,8 @@ static int dasd_state_basic_to_ready(struct dasd_device *device) } return rc; } - dasd_setup_queue(block); + if (device->discipline->setup_blk_queue) + device->discipline->setup_blk_queue(block); set_capacity(block->gdp, block->blocks << block->s2b_shift); device->state = DASD_STATE_READY; @@ -1258,6 +1268,49 @@ struct dasd_ccw_req *dasd_smalloc_request(int magic, int cplength, int datasize, } EXPORT_SYMBOL(dasd_smalloc_request); +struct dasd_ccw_req *dasd_fmalloc_request(int magic, int cplength, + int datasize, + struct dasd_device *device) +{ + struct dasd_ccw_req *cqr; + unsigned long flags; + int size, cqr_size; + char *data; + + cqr_size = (sizeof(*cqr) + 7L) & -8L; + size = cqr_size; + if (cplength > 0) + size += cplength * sizeof(struct ccw1); + if (datasize > 0) + size += datasize; + + spin_lock_irqsave(&device->mem_lock, flags); + cqr = dasd_alloc_chunk(&device->ese_chunks, size); + spin_unlock_irqrestore(&device->mem_lock, flags); + if (!cqr) + return ERR_PTR(-ENOMEM); + memset(cqr, 0, sizeof(*cqr)); + data = (char *)cqr + cqr_size; + cqr->cpaddr = NULL; + if (cplength > 0) { + cqr->cpaddr = data; + data += cplength * sizeof(struct ccw1); + memset(cqr->cpaddr, 0, cplength * sizeof(struct ccw1)); + } + cqr->data = NULL; + if (datasize > 0) { + cqr->data = data; + memset(cqr->data, 0, datasize); + } + + cqr->magic = magic; + set_bit(DASD_CQR_FLAGS_USE_ERP, &cqr->flags); + dasd_get_device(device); + + return cqr; +} +EXPORT_SYMBOL(dasd_fmalloc_request); + void dasd_sfree_request(struct dasd_ccw_req *cqr, struct dasd_device *device) { unsigned long flags; @@ -1269,6 +1322,17 @@ void dasd_sfree_request(struct dasd_ccw_req *cqr, struct dasd_device *device) } EXPORT_SYMBOL(dasd_sfree_request); +void dasd_ffree_request(struct dasd_ccw_req *cqr, struct dasd_device *device) +{ + unsigned long flags; + + spin_lock_irqsave(&device->mem_lock, flags); + dasd_free_chunk(&device->ese_chunks, cqr); + spin_unlock_irqrestore(&device->mem_lock, flags); + dasd_put_device(device); +} +EXPORT_SYMBOL(dasd_ffree_request); + /* * Check discipline magic in cqr. */ @@ -1573,13 +1637,43 @@ static int dasd_check_hpf_error(struct irb *irb) irb->scsw.tm.sesq == SCSW_SESQ_PATH_NOFCX)); } +static int dasd_ese_needs_format(struct dasd_block *block, struct irb *irb) +{ + struct dasd_device *device = NULL; + u8 *sense = NULL; + + if (!block) + return 0; + device = block->base; + if (!device || !device->discipline->is_ese) + return 0; + if (!device->discipline->is_ese(device)) + return 0; + + sense = dasd_get_sense(irb); + if (!sense) + return 0; + + return !!(sense[1] & SNS1_NO_REC_FOUND) || + !!(sense[1] & SNS1_FILE_PROTECTED) || + scsw_cstat(&irb->scsw) == SCHN_STAT_INCORR_LEN; +} + +static int dasd_ese_oos_cond(u8 *sense) +{ + return sense[0] & SNS0_EQUIPMENT_CHECK && + sense[1] & SNS1_PERM_ERR && + sense[1] & SNS1_WRITE_INHIBITED && + sense[25] == 0x01; +} + /* * Interrupt handler for "normal" ssch-io based dasd devices. */ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, struct irb *irb) { - struct dasd_ccw_req *cqr, *next; + struct dasd_ccw_req *cqr, *next, *fcqr; struct dasd_device *device; unsigned long now; int nrf_suppressed = 0; @@ -1641,6 +1735,17 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, test_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags); nrf_suppressed = (sense[1] & SNS1_NO_REC_FOUND) && test_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags); + + /* + * Extent pool probably out-of-space. + * Stop device and check exhaust level. + */ + if (dasd_ese_oos_cond(sense)) { + dasd_generic_space_exhaust(device, cqr); + device->discipline->ext_pool_exhaust(device, cqr); + dasd_put_device(device); + return; + } } if (!(fp_suppressed || nrf_suppressed)) device->discipline->dump_sense_dbf(device, irb, "int"); @@ -1672,6 +1777,31 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, return; } + if (dasd_ese_needs_format(cqr->block, irb)) { + if (rq_data_dir((struct request *)cqr->callback_data) == READ) { + device->discipline->ese_read(cqr); + cqr->status = DASD_CQR_SUCCESS; + cqr->stopclk = now; + dasd_device_clear_timer(device); + dasd_schedule_device_bh(device); + return; + } + fcqr = device->discipline->ese_format(device, cqr); + if (IS_ERR(fcqr)) { + /* + * If we can't format now, let the request go + * one extra round. Maybe we can format later. + */ + cqr->status = DASD_CQR_QUEUED; + } else { + fcqr->status = DASD_CQR_QUEUED; + cqr->status = DASD_CQR_QUEUED; + list_add(&fcqr->devlist, &device->ccw_queue); + dasd_schedule_device_bh(device); + return; + } + } + /* Check for clear pending */ if (cqr->status == DASD_CQR_CLEAR_PENDING && scsw_fctl(&irb->scsw) & SCSW_FCTL_CLEAR_FUNC) { @@ -1910,7 +2040,7 @@ static void __dasd_device_check_expire(struct dasd_device *device) static int __dasd_device_is_unusable(struct dasd_device *device, struct dasd_ccw_req *cqr) { - int mask = ~(DASD_STOPPED_DC_WAIT | DASD_UNRESUMED_PM); + int mask = ~(DASD_STOPPED_DC_WAIT | DASD_UNRESUMED_PM | DASD_STOPPED_NOSPC); if (test_bit(DASD_FLAG_OFFLINE, &device->flags) && !test_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) { @@ -2412,6 +2542,15 @@ int dasd_sleep_on_queue(struct list_head *ccw_queue) EXPORT_SYMBOL(dasd_sleep_on_queue); /* + * Start requests from a ccw_queue and wait interruptible for their completion. + */ +int dasd_sleep_on_queue_interruptible(struct list_head *ccw_queue) +{ + return _dasd_sleep_on_queue(ccw_queue, 1); +} +EXPORT_SYMBOL(dasd_sleep_on_queue_interruptible); + +/* * Queue a request to the tail of the device ccw_queue and wait * interruptible for it's completion. */ @@ -3130,55 +3269,6 @@ static int dasd_alloc_queue(struct dasd_block *block) } /* - * Allocate and initialize request queue. - */ -static void dasd_setup_queue(struct dasd_block *block) -{ - unsigned int logical_block_size = block->bp_block; - struct request_queue *q = block->request_queue; - unsigned int max_bytes, max_discard_sectors; - int max; - - if (block->base->features & DASD_FEATURE_USERAW) { - /* - * the max_blocks value for raw_track access is 256 - * it is higher than the native ECKD value because we - * only need one ccw per track - * so the max_hw_sectors are - * 2048 x 512B = 1024kB = 16 tracks - */ - max = 2048; - } else { - max = block->base->discipline->max_blocks << block->s2b_shift; - } - blk_queue_flag_set(QUEUE_FLAG_NONROT, q); - q->limits.max_dev_sectors = max; - blk_queue_logical_block_size(q, logical_block_size); - blk_queue_max_hw_sectors(q, max); - blk_queue_max_segments(q, USHRT_MAX); - /* with page sized segments we can translate each segement into - * one idaw/tidaw - */ - blk_queue_max_segment_size(q, PAGE_SIZE); - blk_queue_segment_boundary(q, PAGE_SIZE - 1); - - /* Only activate blocklayer discard support for devices that support it */ - if (block->base->features & DASD_FEATURE_DISCARD) { - q->limits.discard_granularity = logical_block_size; - q->limits.discard_alignment = PAGE_SIZE; - - /* Calculate max_discard_sectors and make it PAGE aligned */ - max_bytes = USHRT_MAX * logical_block_size; - max_bytes = ALIGN(max_bytes, PAGE_SIZE) - PAGE_SIZE; - max_discard_sectors = max_bytes / logical_block_size; - - blk_queue_max_discard_sectors(q, max_discard_sectors); - blk_queue_max_write_zeroes_sectors(q, max_discard_sectors); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); - } -} - -/* * Deactivate and free request queue. */ static void dasd_free_queue(struct dasd_block *block) @@ -3806,6 +3896,43 @@ int dasd_generic_verify_path(struct dasd_device *device, __u8 lpm) } EXPORT_SYMBOL_GPL(dasd_generic_verify_path); +void dasd_generic_space_exhaust(struct dasd_device *device, + struct dasd_ccw_req *cqr) +{ + dasd_eer_write(device, NULL, DASD_EER_NOSPC); + + if (device->state < DASD_STATE_BASIC) + return; + + if (cqr->status == DASD_CQR_IN_IO || + cqr->status == DASD_CQR_CLEAR_PENDING) { + cqr->status = DASD_CQR_QUEUED; + cqr->retries++; + } + dasd_device_set_stop_bits(device, DASD_STOPPED_NOSPC); + dasd_device_clear_timer(device); + dasd_schedule_device_bh(device); +} +EXPORT_SYMBOL_GPL(dasd_generic_space_exhaust); + +void dasd_generic_space_avail(struct dasd_device *device) +{ + dev_info(&device->cdev->dev, "Extent pool space is available\n"); + DBF_DEV_EVENT(DBF_WARNING, device, "%s", "space available"); + + dasd_device_remove_stop_bits(device, DASD_STOPPED_NOSPC); + dasd_schedule_device_bh(device); + + if (device->block) { + dasd_schedule_block_bh(device->block); + if (device->block->request_queue) + blk_mq_run_hw_queues(device->block->request_queue, true); + } + if (!device->stopped) + wake_up(&generic_waitq); +} +EXPORT_SYMBOL_GPL(dasd_generic_space_avail); + /* * clear active requests and requeue them to block layer if possible */ diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c index fab35c6170cc..32fc51341d99 100644 --- a/drivers/s390/block/dasd_devmap.c +++ b/drivers/s390/block/dasd_devmap.c @@ -203,7 +203,7 @@ static int __init dasd_feature_list(char *str) else if (len == 8 && !strncmp(str, "failfast", 8)) features |= DASD_FEATURE_FAILFAST; else { - pr_warn("%*s is not a supported device option\n", + pr_warn("%.*s is not a supported device option\n", len, str); rc = -EINVAL; } @@ -1642,6 +1642,35 @@ static DEVICE_ATTR(path_interval, 0644, dasd_path_interval_show, dasd_path_interval_store); +#define DASD_DEFINE_ATTR(_name, _func) \ +static ssize_t dasd_##_name##_show(struct device *dev, \ + struct device_attribute *attr, \ + char *buf) \ +{ \ + struct ccw_device *cdev = to_ccwdev(dev); \ + struct dasd_device *device = dasd_device_from_cdev(cdev); \ + int val = 0; \ + \ + if (IS_ERR(device)) \ + return -ENODEV; \ + if (device->discipline && _func) \ + val = _func(device); \ + dasd_put_device(device); \ + \ + return snprintf(buf, PAGE_SIZE, "%d\n", val); \ +} \ +static DEVICE_ATTR(_name, 0444, dasd_##_name##_show, NULL); \ + +DASD_DEFINE_ATTR(ese, device->discipline->is_ese); +DASD_DEFINE_ATTR(extent_size, device->discipline->ext_size); +DASD_DEFINE_ATTR(pool_id, device->discipline->ext_pool_id); +DASD_DEFINE_ATTR(space_configured, device->discipline->space_configured); +DASD_DEFINE_ATTR(space_allocated, device->discipline->space_allocated); +DASD_DEFINE_ATTR(logical_capacity, device->discipline->logical_capacity); +DASD_DEFINE_ATTR(warn_threshold, device->discipline->ext_pool_warn_thrshld); +DASD_DEFINE_ATTR(cap_at_warnlevel, device->discipline->ext_pool_cap_at_warnlevel); +DASD_DEFINE_ATTR(pool_oos, device->discipline->ext_pool_oos); + static struct attribute * dasd_attrs[] = { &dev_attr_readonly.attr, &dev_attr_discipline.attr, @@ -1667,6 +1696,7 @@ static struct attribute * dasd_attrs[] = { &dev_attr_path_interval.attr, &dev_attr_path_reset.attr, &dev_attr_hpf.attr, + &dev_attr_ese.attr, NULL, }; @@ -1674,6 +1704,39 @@ static const struct attribute_group dasd_attr_group = { .attrs = dasd_attrs, }; +static struct attribute *capacity_attrs[] = { + &dev_attr_space_configured.attr, + &dev_attr_space_allocated.attr, + &dev_attr_logical_capacity.attr, + NULL, +}; + +static const struct attribute_group capacity_attr_group = { + .name = "capacity", + .attrs = capacity_attrs, +}; + +static struct attribute *ext_pool_attrs[] = { + &dev_attr_pool_id.attr, + &dev_attr_extent_size.attr, + &dev_attr_warn_threshold.attr, + &dev_attr_cap_at_warnlevel.attr, + &dev_attr_pool_oos.attr, + NULL, +}; + +static const struct attribute_group ext_pool_attr_group = { + .name = "extent_pool", + .attrs = ext_pool_attrs, +}; + +static const struct attribute_group *dasd_attr_groups[] = { + &dasd_attr_group, + &capacity_attr_group, + &ext_pool_attr_group, + NULL, +}; + /* * Return value of the specified feature. */ @@ -1715,16 +1778,15 @@ dasd_set_feature(struct ccw_device *cdev, int feature, int flag) EXPORT_SYMBOL(dasd_set_feature); -int -dasd_add_sysfs_files(struct ccw_device *cdev) +int dasd_add_sysfs_files(struct ccw_device *cdev) { - return sysfs_create_group(&cdev->dev.kobj, &dasd_attr_group); + return sysfs_create_groups(&cdev->dev.kobj, dasd_attr_groups); } void dasd_remove_sysfs_files(struct ccw_device *cdev) { - sysfs_remove_group(&cdev->dev.kobj, &dasd_attr_group); + sysfs_remove_groups(&cdev->dev.kobj, dasd_attr_groups); } diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c index e1fe02477ea8..8d4971645cf1 100644 --- a/drivers/s390/block/dasd_diag.c +++ b/drivers/s390/block/dasd_diag.c @@ -615,14 +615,34 @@ dasd_diag_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req, "dump sense not available for DIAG data"); } +/* + * Initialize block layer request queue. + */ +static void dasd_diag_setup_blk_queue(struct dasd_block *block) +{ + unsigned int logical_block_size = block->bp_block; + struct request_queue *q = block->request_queue; + int max; + + max = DIAG_MAX_BLOCKS << block->s2b_shift; + blk_queue_flag_set(QUEUE_FLAG_NONROT, q); + q->limits.max_dev_sectors = max; + blk_queue_logical_block_size(q, logical_block_size); + blk_queue_max_hw_sectors(q, max); + blk_queue_max_segments(q, USHRT_MAX); + /* With page sized segments each segment can be translated into one idaw/tidaw */ + blk_queue_max_segment_size(q, PAGE_SIZE); + blk_queue_segment_boundary(q, PAGE_SIZE - 1); +} + static struct dasd_discipline dasd_diag_discipline = { .owner = THIS_MODULE, .name = "DIAG", .ebcname = "DIAG", - .max_blocks = DIAG_MAX_BLOCKS, .check_device = dasd_diag_check_device, .verify_path = dasd_generic_verify_path, .fill_geometry = dasd_diag_fill_geometry, + .setup_blk_queue = dasd_diag_setup_blk_queue, .start_IO = dasd_start_diag, .term_IO = dasd_diag_term_IO, .handle_terminated_request = dasd_diag_handle_terminated_request, diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index f89f9d02e788..fc53e1e221f0 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -42,20 +42,6 @@ #endif /* PRINTK_HEADER */ #define PRINTK_HEADER "dasd(eckd):" -#define ECKD_C0(i) (i->home_bytes) -#define ECKD_F(i) (i->formula) -#define ECKD_F1(i) (ECKD_F(i)==0x01?(i->factors.f_0x01.f1):\ - (i->factors.f_0x02.f1)) -#define ECKD_F2(i) (ECKD_F(i)==0x01?(i->factors.f_0x01.f2):\ - (i->factors.f_0x02.f2)) -#define ECKD_F3(i) (ECKD_F(i)==0x01?(i->factors.f_0x01.f3):\ - (i->factors.f_0x02.f3)) -#define ECKD_F4(i) (ECKD_F(i)==0x02?(i->factors.f_0x02.f4):0) -#define ECKD_F5(i) (ECKD_F(i)==0x02?(i->factors.f_0x02.f5):0) -#define ECKD_F6(i) (i->factor6) -#define ECKD_F7(i) (i->factor7) -#define ECKD_F8(i) (i->factor8) - /* * raw track access always map to 64k in memory * so it maps to 16 blocks of 4k per track @@ -103,6 +89,19 @@ static struct { } *dasd_reserve_req; static DEFINE_MUTEX(dasd_reserve_mutex); +static struct { + struct dasd_ccw_req cqr; + struct ccw1 ccw[2]; + char data[40]; +} *dasd_vol_info_req; +static DEFINE_MUTEX(dasd_vol_info_mutex); + +struct ext_pool_exhaust_work_data { + struct work_struct worker; + struct dasd_device *device; + struct dasd_device *base; +}; + /* definitions for the path verification worker */ struct path_verification_work_data { struct work_struct worker; @@ -122,6 +121,7 @@ struct check_attention_work_data { __u8 lpum; }; +static int dasd_eckd_ext_pool_id(struct dasd_device *); static int prepare_itcw(struct itcw *, unsigned int, unsigned int, int, struct dasd_device *, struct dasd_device *, unsigned int, int, unsigned int, unsigned int, @@ -157,17 +157,10 @@ static const int sizes_trk0[] = { 28, 148, 84 }; #define LABEL_SIZE 140 /* head and record addresses of count_area read in analysis ccw */ -static const int count_area_head[] = { 0, 0, 0, 0, 2 }; +static const int count_area_head[] = { 0, 0, 0, 0, 1 }; static const int count_area_rec[] = { 1, 2, 3, 4, 1 }; static inline unsigned int -round_up_multiple(unsigned int no, unsigned int mult) -{ - int rem = no % mult; - return (rem ? no - rem + mult : no); -} - -static inline unsigned int ceil_quot(unsigned int d1, unsigned int d2) { return (d1 + (d2 - 1)) / d2; @@ -1491,6 +1484,311 @@ static int dasd_eckd_read_features(struct dasd_device *device) return rc; } +/* Read Volume Information - Volume Storage Query */ +static int dasd_eckd_read_vol_info(struct dasd_device *device) +{ + struct dasd_eckd_private *private = device->private; + struct dasd_psf_prssd_data *prssdp; + struct dasd_rssd_vsq *vsq; + struct dasd_ccw_req *cqr; + struct ccw1 *ccw; + int useglobal; + int rc; + + /* This command cannot be executed on an alias device */ + if (private->uid.type == UA_BASE_PAV_ALIAS || + private->uid.type == UA_HYPER_PAV_ALIAS) + return 0; + + useglobal = 0; + cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 2 /* PSF + RSSD */, + sizeof(*prssdp) + sizeof(*vsq), device, NULL); + if (IS_ERR(cqr)) { + DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s", + "Could not allocate initialization request"); + mutex_lock(&dasd_vol_info_mutex); + useglobal = 1; + cqr = &dasd_vol_info_req->cqr; + memset(cqr, 0, sizeof(*cqr)); + memset(dasd_vol_info_req, 0, sizeof(*dasd_vol_info_req)); + cqr->cpaddr = &dasd_vol_info_req->ccw; + cqr->data = &dasd_vol_info_req->data; + cqr->magic = DASD_ECKD_MAGIC; + } + + /* Prepare for Read Subsystem Data */ + prssdp = cqr->data; + prssdp->order = PSF_ORDER_PRSSD; + prssdp->suborder = PSF_SUBORDER_VSQ; /* Volume Storage Query */ + prssdp->lss = private->ned->ID; + prssdp->volume = private->ned->unit_addr; + + ccw = cqr->cpaddr; + ccw->cmd_code = DASD_ECKD_CCW_PSF; + ccw->count = sizeof(*prssdp); + ccw->flags |= CCW_FLAG_CC; + ccw->cda = (__u32)(addr_t)prssdp; + + /* Read Subsystem Data - Volume Storage Query */ + vsq = (struct dasd_rssd_vsq *)(prssdp + 1); + memset(vsq, 0, sizeof(*vsq)); + + ccw++; + ccw->cmd_code = DASD_ECKD_CCW_RSSD; + ccw->count = sizeof(*vsq); + ccw->flags |= CCW_FLAG_SLI; + ccw->cda = (__u32)(addr_t)vsq; + + cqr->buildclk = get_tod_clock(); + cqr->status = DASD_CQR_FILLED; + cqr->startdev = device; + cqr->memdev = device; + cqr->block = NULL; + cqr->retries = 256; + cqr->expires = device->default_expires * HZ; + /* The command might not be supported. Suppress the error output */ + __set_bit(DASD_CQR_SUPPRESS_CR, &cqr->flags); + + rc = dasd_sleep_on_interruptible(cqr); + if (rc == 0) { + memcpy(&private->vsq, vsq, sizeof(*vsq)); + } else { + dev_warn(&device->cdev->dev, + "Reading the volume storage information failed with rc=%d\n", rc); + } + + if (useglobal) + mutex_unlock(&dasd_vol_info_mutex); + else + dasd_sfree_request(cqr, cqr->memdev); + + return rc; +} + +static int dasd_eckd_is_ese(struct dasd_device *device) +{ + struct dasd_eckd_private *private = device->private; + + return private->vsq.vol_info.ese; +} + +static int dasd_eckd_ext_pool_id(struct dasd_device *device) +{ + struct dasd_eckd_private *private = device->private; + + return private->vsq.extent_pool_id; +} + +/* + * This value represents the total amount of available space. As more space is + * allocated by ESE volumes, this value will decrease. + * The data for this value is therefore updated on any call. + */ +static int dasd_eckd_space_configured(struct dasd_device *device) +{ + struct dasd_eckd_private *private = device->private; + int rc; + + rc = dasd_eckd_read_vol_info(device); + + return rc ? : private->vsq.space_configured; +} + +/* + * The value of space allocated by an ESE volume may have changed and is + * therefore updated on any call. + */ +static int dasd_eckd_space_allocated(struct dasd_device *device) +{ + struct dasd_eckd_private *private = device->private; + int rc; + + rc = dasd_eckd_read_vol_info(device); + + return rc ? : private->vsq.space_allocated; +} + +static int dasd_eckd_logical_capacity(struct dasd_device *device) +{ + struct dasd_eckd_private *private = device->private; + + return private->vsq.logical_capacity; +} + +static void dasd_eckd_ext_pool_exhaust_work(struct work_struct *work) +{ + struct ext_pool_exhaust_work_data *data; + struct dasd_device *device; + struct dasd_device *base; + + data = container_of(work, struct ext_pool_exhaust_work_data, worker); + device = data->device; + base = data->base; + + if (!base) + base = device; + if (dasd_eckd_space_configured(base) != 0) { + dasd_generic_space_avail(device); + } else { + dev_warn(&device->cdev->dev, "No space left in the extent pool\n"); + DBF_DEV_EVENT(DBF_WARNING, device, "%s", "out of space"); + } + + dasd_put_device(device); + kfree(data); +} + +static int dasd_eckd_ext_pool_exhaust(struct dasd_device *device, + struct dasd_ccw_req *cqr) +{ + struct ext_pool_exhaust_work_data *data; + + data = kzalloc(sizeof(*data), GFP_ATOMIC); + if (!data) + return -ENOMEM; + INIT_WORK(&data->worker, dasd_eckd_ext_pool_exhaust_work); + dasd_get_device(device); + data->device = device; + + if (cqr->block) + data->base = cqr->block->base; + else if (cqr->basedev) + data->base = cqr->basedev; + else + data->base = NULL; + + schedule_work(&data->worker); + + return 0; +} + +static void dasd_eckd_cpy_ext_pool_data(struct dasd_device *device, + struct dasd_rssd_lcq *lcq) +{ + struct dasd_eckd_private *private = device->private; + int pool_id = dasd_eckd_ext_pool_id(device); + struct dasd_ext_pool_sum eps; + int i; + + for (i = 0; i < lcq->pool_count; i++) { + eps = lcq->ext_pool_sum[i]; + if (eps.pool_id == pool_id) { + memcpy(&private->eps, &eps, + sizeof(struct dasd_ext_pool_sum)); + } + } +} + +/* Read Extent Pool Information - Logical Configuration Query */ +static int dasd_eckd_read_ext_pool_info(struct dasd_device *device) +{ + struct dasd_eckd_private *private = device->private; + struct dasd_psf_prssd_data *prssdp; + struct dasd_rssd_lcq *lcq; + struct dasd_ccw_req *cqr; + struct ccw1 *ccw; + int rc; + + /* This command cannot be executed on an alias device */ + if (private->uid.type == UA_BASE_PAV_ALIAS || + private->uid.type == UA_HYPER_PAV_ALIAS) + return 0; + + cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 2 /* PSF + RSSD */, + sizeof(*prssdp) + sizeof(*lcq), device, NULL); + if (IS_ERR(cqr)) { + DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s", + "Could not allocate initialization request"); + return PTR_ERR(cqr); + } + + /* Prepare for Read Subsystem Data */ + prssdp = cqr->data; + memset(prssdp, 0, sizeof(*prssdp)); + prssdp->order = PSF_ORDER_PRSSD; + prssdp->suborder = PSF_SUBORDER_LCQ; /* Logical Configuration Query */ + + ccw = cqr->cpaddr; + ccw->cmd_code = DASD_ECKD_CCW_PSF; + ccw->count = sizeof(*prssdp); + ccw->flags |= CCW_FLAG_CC; + ccw->cda = (__u32)(addr_t)prssdp; + + lcq = (struct dasd_rssd_lcq *)(prssdp + 1); + memset(lcq, 0, sizeof(*lcq)); + + ccw++; + ccw->cmd_code = DASD_ECKD_CCW_RSSD; + ccw->count = sizeof(*lcq); + ccw->flags |= CCW_FLAG_SLI; + ccw->cda = (__u32)(addr_t)lcq; + + cqr->buildclk = get_tod_clock(); + cqr->status = DASD_CQR_FILLED; + cqr->startdev = device; + cqr->memdev = device; + cqr->block = NULL; + cqr->retries = 256; + cqr->expires = device->default_expires * HZ; + /* The command might not be supported. Suppress the error output */ + __set_bit(DASD_CQR_SUPPRESS_CR, &cqr->flags); + + rc = dasd_sleep_on_interruptible(cqr); + if (rc == 0) { + dasd_eckd_cpy_ext_pool_data(device, lcq); + } else { + dev_warn(&device->cdev->dev, + "Reading the logical configuration failed with rc=%d\n", rc); + } + + dasd_sfree_request(cqr, cqr->memdev); + + return rc; +} + +/* + * Depending on the device type, the extent size is specified either as + * cylinders per extent (CKD) or size per extent (FBA) + * A 1GB size corresponds to 1113cyl, and 16MB to 21cyl. + */ +static int dasd_eckd_ext_size(struct dasd_device *device) +{ + struct dasd_eckd_private *private = device->private; + struct dasd_ext_pool_sum eps = private->eps; + + if (!eps.flags.extent_size_valid) + return 0; + if (eps.extent_size.size_1G) + return 1113; + if (eps.extent_size.size_16M) + return 21; + + return 0; +} + +static int dasd_eckd_ext_pool_warn_thrshld(struct dasd_device *device) +{ + struct dasd_eckd_private *private = device->private; + + return private->eps.warn_thrshld; +} + +static int dasd_eckd_ext_pool_cap_at_warnlevel(struct dasd_device *device) +{ + struct dasd_eckd_private *private = device->private; + + return private->eps.flags.capacity_at_warnlevel; +} + +/* + * Extent Pool out of space + */ +static int dasd_eckd_ext_pool_oos(struct dasd_device *device) +{ + struct dasd_eckd_private *private = device->private; + + return private->eps.flags.pool_oos; +} /* * Build CP for Perform Subsystem Function - SSC. @@ -1721,6 +2019,16 @@ dasd_eckd_check_characteristics(struct dasd_device *device) /* Read Feature Codes */ dasd_eckd_read_features(device); + /* Read Volume Information */ + rc = dasd_eckd_read_vol_info(device); + if (rc) + goto out_err3; + + /* Read Extent Pool Information */ + rc = dasd_eckd_read_ext_pool_info(device); + if (rc) + goto out_err3; + /* Read Device Characteristics */ rc = dasd_generic_read_dev_chars(device, DASD_ECKD_MAGIC, &private->rdc_data, 64); @@ -1751,6 +2059,9 @@ dasd_eckd_check_characteristics(struct dasd_device *device) if (readonly) set_bit(DASD_FLAG_DEVICE_RO, &device->flags); + if (dasd_eckd_is_ese(device)) + dasd_set_feature(device->cdev, DASD_FEATURE_DISCARD, 1); + dev_info(&device->cdev->dev, "New DASD %04X/%02X (CU %04X/%02X) " "with %d cylinders, %d heads, %d sectors%s\n", private->rdc_data.dev_type, @@ -1823,8 +2134,8 @@ dasd_eckd_analysis_ccw(struct dasd_device *device) if (IS_ERR(cqr)) return cqr; ccw = cqr->cpaddr; - /* Define extent for the first 3 tracks. */ - define_extent(ccw++, cqr->data, 0, 2, + /* Define extent for the first 2 tracks. */ + define_extent(ccw++, cqr->data, 0, 1, DASD_ECKD_CCW_READ_COUNT, device, 0); LO_data = cqr->data + sizeof(struct DE_eckd_data); /* Locate record for the first 4 records on track 0. */ @@ -1843,9 +2154,9 @@ dasd_eckd_analysis_ccw(struct dasd_device *device) count_data++; } - /* Locate record for the first record on track 2. */ + /* Locate record for the first record on track 1. */ ccw[-1].flags |= CCW_FLAG_CC; - locate_record(ccw++, LO_data++, 2, 0, 1, + locate_record(ccw++, LO_data++, 1, 0, 1, DASD_ECKD_CCW_READ_COUNT, device, 0); /* Read count ccw. */ ccw[-1].flags |= CCW_FLAG_CC; @@ -1860,6 +2171,9 @@ dasd_eckd_analysis_ccw(struct dasd_device *device) cqr->retries = 255; cqr->buildclk = get_tod_clock(); cqr->status = DASD_CQR_FILLED; + /* Set flags to suppress output for expected errors */ + set_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags); + return cqr; } @@ -1967,7 +2281,7 @@ static int dasd_eckd_end_analysis(struct dasd_block *block) } } if (i == 3) - count_area = &private->count_area[4]; + count_area = &private->count_area[3]; if (private->uses_cdl == 0) { for (i = 0; i < 5; i++) { @@ -2099,8 +2413,7 @@ dasd_eckd_build_check_tcw(struct dasd_device *base, struct format_data_t *fdata, */ itcw_size = itcw_calc_size(0, count, 0); - cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 0, itcw_size, startdev, - NULL); + cqr = dasd_fmalloc_request(DASD_ECKD_MAGIC, 0, itcw_size, startdev); if (IS_ERR(cqr)) return cqr; @@ -2193,8 +2506,7 @@ dasd_eckd_build_check(struct dasd_device *base, struct format_data_t *fdata, } cplength += count; - cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, datasize, - startdev, NULL); + cqr = dasd_fmalloc_request(DASD_ECKD_MAGIC, cplength, datasize, startdev); if (IS_ERR(cqr)) return cqr; @@ -2241,13 +2553,11 @@ dasd_eckd_build_check(struct dasd_device *base, struct format_data_t *fdata, } static struct dasd_ccw_req * -dasd_eckd_build_format(struct dasd_device *base, - struct format_data_t *fdata, - int enable_pav) +dasd_eckd_build_format(struct dasd_device *base, struct dasd_device *startdev, + struct format_data_t *fdata, int enable_pav) { struct dasd_eckd_private *base_priv; struct dasd_eckd_private *start_priv; - struct dasd_device *startdev = NULL; struct dasd_ccw_req *fcp; struct eckd_count *ect; struct ch_t address; @@ -2338,9 +2648,8 @@ dasd_eckd_build_format(struct dasd_device *base, fdata->intensity); return ERR_PTR(-EINVAL); } - /* Allocate the format ccw request. */ - fcp = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, - datasize, startdev, NULL); + + fcp = dasd_fmalloc_request(DASD_ECKD_MAGIC, cplength, datasize, startdev); if (IS_ERR(fcp)) return fcp; @@ -2513,7 +2822,7 @@ dasd_eckd_format_build_ccw_req(struct dasd_device *base, struct dasd_ccw_req *ccw_req; if (!fmt_buffer) { - ccw_req = dasd_eckd_build_format(base, fdata, enable_pav); + ccw_req = dasd_eckd_build_format(base, NULL, fdata, enable_pav); } else { if (tpm) ccw_req = dasd_eckd_build_check_tcw(base, fdata, @@ -2659,7 +2968,7 @@ out_err: rc = -EIO; } list_del_init(&cqr->blocklist); - dasd_sfree_request(cqr, device); + dasd_ffree_request(cqr, device); private->count--; } @@ -2699,6 +3008,96 @@ static int dasd_eckd_format_device(struct dasd_device *base, } /* + * Callback function to free ESE format requests. + */ +static void dasd_eckd_ese_format_cb(struct dasd_ccw_req *cqr, void *data) +{ + struct dasd_device *device = cqr->startdev; + struct dasd_eckd_private *private = device->private; + + private->count--; + dasd_ffree_request(cqr, device); +} + +static struct dasd_ccw_req * +dasd_eckd_ese_format(struct dasd_device *startdev, struct dasd_ccw_req *cqr) +{ + struct dasd_eckd_private *private; + struct format_data_t fdata; + unsigned int recs_per_trk; + struct dasd_ccw_req *fcqr; + struct dasd_device *base; + struct dasd_block *block; + unsigned int blksize; + struct request *req; + sector_t first_trk; + sector_t last_trk; + int rc; + + req = cqr->callback_data; + base = cqr->block->base; + private = base->private; + block = base->block; + blksize = block->bp_block; + recs_per_trk = recs_per_track(&private->rdc_data, 0, blksize); + + first_trk = blk_rq_pos(req) >> block->s2b_shift; + sector_div(first_trk, recs_per_trk); + last_trk = + (blk_rq_pos(req) + blk_rq_sectors(req) - 1) >> block->s2b_shift; + sector_div(last_trk, recs_per_trk); + + fdata.start_unit = first_trk; + fdata.stop_unit = last_trk; + fdata.blksize = blksize; + fdata.intensity = private->uses_cdl ? DASD_FMT_INT_COMPAT : 0; + + rc = dasd_eckd_format_sanity_checks(base, &fdata); + if (rc) + return ERR_PTR(-EINVAL); + + /* + * We're building the request with PAV disabled as we're reusing + * the former startdev. + */ + fcqr = dasd_eckd_build_format(base, startdev, &fdata, 0); + if (IS_ERR(fcqr)) + return fcqr; + + fcqr->callback = dasd_eckd_ese_format_cb; + + return fcqr; +} + +/* + * When data is read from an unformatted area of an ESE volume, this function + * returns zeroed data and thereby mimics a read of zero data. + */ +static void dasd_eckd_ese_read(struct dasd_ccw_req *cqr) +{ + unsigned int blksize, off; + struct dasd_device *base; + struct req_iterator iter; + struct request *req; + struct bio_vec bv; + char *dst; + + req = (struct request *) cqr->callback_data; + base = cqr->block->base; + blksize = base->block->bp_block; + + rq_for_each_segment(bv, req, iter) { + dst = page_address(bv.bv_page) + bv.bv_offset; + for (off = 0; off < bv.bv_len; off += blksize) { + if (dst && rq_data_dir(req) == READ) { + dst += off; + memset(dst, 0, blksize); + } + } + } +} + +/* * Helper function to count consecutive records of a single track. */ static int dasd_eckd_count_records(struct eckd_count *fmt_buffer, int start, @@ -3033,6 +3432,277 @@ static void dasd_eckd_check_for_device_change(struct dasd_device *device, } } +static int dasd_eckd_ras_sanity_checks(struct dasd_device *device, + unsigned int first_trk, + unsigned int last_trk) +{ + struct dasd_eckd_private *private = device->private; + unsigned int trks_per_vol; + int rc = 0; + + trks_per_vol = private->real_cyl * private->rdc_data.trk_per_cyl; + + if (first_trk >= trks_per_vol) { + dev_warn(&device->cdev->dev, + "Start track number %u used in the space release command is too big\n", + first_trk); + rc = -EINVAL; + } else if (last_trk >= trks_per_vol) { + dev_warn(&device->cdev->dev, + "Stop track number %u used in the space release command is too big\n", + last_trk); + rc = -EINVAL; + } else if (first_trk > last_trk) { + dev_warn(&device->cdev->dev, + "Start track %u used in the space release command exceeds the end track\n", + first_trk); + rc = -EINVAL; + } + return rc; +} + +/* + * Helper function to count the amount of involved extents within a given range + * with extent alignment in mind. + */ +static int count_exts(unsigned int from, unsigned int to, int trks_per_ext) +{ + int cur_pos = 0; + int count = 0; + int tmp; + + if (from == to) + return 1; + + /* Count first partial extent */ + if (from % trks_per_ext != 0) { + tmp = from + trks_per_ext - (from % trks_per_ext) - 1; + if (tmp > to) + tmp = to; + cur_pos = tmp - from + 1; + count++; + } + /* Count full extents */ + if (to - (from + cur_pos) + 1 >= trks_per_ext) { + tmp = to - ((to - trks_per_ext + 1) % trks_per_ext); + count += (tmp - (from + cur_pos) + 1) / trks_per_ext; + cur_pos = tmp; + } + /* Count last partial extent */ + if (cur_pos < to) + count++; + + return count; +} + +/* + * Release allocated space for a given range or an entire volume. + */ +static struct dasd_ccw_req * +dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block, + struct request *req, unsigned int first_trk, + unsigned int last_trk, int by_extent) +{ + struct dasd_eckd_private *private = device->private; + struct dasd_dso_ras_ext_range *ras_range; + struct dasd_rssd_features *features; + struct dasd_dso_ras_data *ras_data; + u16 heads, beg_head, end_head; + int cur_to_trk, cur_from_trk; + struct dasd_ccw_req *cqr; + u32 beg_cyl, end_cyl; + struct ccw1 *ccw; + int trks_per_ext; + size_t ras_size; + size_t size; + int nr_exts; + void *rq; + int i; + + if (dasd_eckd_ras_sanity_checks(device, first_trk, last_trk)) + return ERR_PTR(-EINVAL); + + rq = req ? blk_mq_rq_to_pdu(req) : NULL; + + features = &private->features; + + trks_per_ext = dasd_eckd_ext_size(device) * private->rdc_data.trk_per_cyl; + nr_exts = 0; + if (by_extent) + nr_exts = count_exts(first_trk, last_trk, trks_per_ext); + ras_size = sizeof(*ras_data); + size = ras_size + (nr_exts * sizeof(*ras_range)); + + cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, size, device, rq); + if (IS_ERR(cqr)) { + DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s", + "Could not allocate RAS request"); + return cqr; + } + + ras_data = cqr->data; + memset(ras_data, 0, size); + + ras_data->order = DSO_ORDER_RAS; + ras_data->flags.vol_type = 0; /* CKD volume */ + /* Release specified extents or entire volume */ + ras_data->op_flags.by_extent = by_extent; + /* + * This bit guarantees initialisation of tracks within an extent that is + * not fully specified, but is only supported with a certain feature + * subset. + */ + ras_data->op_flags.guarantee_init = !!(features->feature[56] & 0x01); + ras_data->lss = private->ned->ID; + ras_data->dev_addr = private->ned->unit_addr; + ras_data->nr_exts = nr_exts; + + if (by_extent) { + heads = private->rdc_data.trk_per_cyl; + cur_from_trk = first_trk; + cur_to_trk = first_trk + trks_per_ext - + (first_trk % trks_per_ext) - 1; + if (cur_to_trk > last_trk) + cur_to_trk = last_trk; + ras_range = (struct dasd_dso_ras_ext_range *)(cqr->data + ras_size); + + for (i = 0; i < nr_exts; i++) { + beg_cyl = cur_from_trk / heads; + beg_head = cur_from_trk % heads; + end_cyl = cur_to_trk / heads; + end_head = cur_to_trk % heads; + + set_ch_t(&ras_range->beg_ext, beg_cyl, beg_head); + set_ch_t(&ras_range->end_ext, end_cyl, end_head); + + cur_from_trk = cur_to_trk + 1; + cur_to_trk = cur_from_trk + trks_per_ext - 1; + if (cur_to_trk > last_trk) + cur_to_trk = last_trk; + ras_range++; + } + } + + ccw = cqr->cpaddr; + ccw->cda = (__u32)(addr_t)cqr->data; + ccw->cmd_code = DASD_ECKD_CCW_DSO; + ccw->count = size; + + cqr->startdev = device; + cqr->memdev = device; + cqr->block = block; + cqr->retries = 256; + cqr->expires = device->default_expires * HZ; + cqr->buildclk = get_tod_clock(); + cqr->status = DASD_CQR_FILLED; + + return cqr; +} + +static int dasd_eckd_release_space_full(struct dasd_device *device) +{ + struct dasd_ccw_req *cqr; + int rc; + + cqr = dasd_eckd_dso_ras(device, NULL, NULL, 0, 0, 0); + if (IS_ERR(cqr)) + return PTR_ERR(cqr); + + rc = dasd_sleep_on_interruptible(cqr); + + dasd_sfree_request(cqr, cqr->memdev); + + return rc; +} + +static int dasd_eckd_release_space_trks(struct dasd_device *device, + unsigned int from, unsigned int to) +{ + struct dasd_eckd_private *private = device->private; + struct dasd_block *block = device->block; + struct dasd_ccw_req *cqr, *n; + struct list_head ras_queue; + unsigned int device_exts; + int trks_per_ext; + int stop, step; + int cur_pos; + int rc = 0; + int retry; + + INIT_LIST_HEAD(&ras_queue); + + device_exts = private->real_cyl / dasd_eckd_ext_size(device); + trks_per_ext = dasd_eckd_ext_size(device) * private->rdc_data.trk_per_cyl; + + /* Make sure device limits are not exceeded */ + step = trks_per_ext * min(device_exts, DASD_ECKD_RAS_EXTS_MAX); + cur_pos = from; + + do { + retry = 0; + while (cur_pos < to) { + stop = cur_pos + step - + ((cur_pos + step) % trks_per_ext) - 1; + if (stop > to) + stop = to; + + cqr = dasd_eckd_dso_ras(device, NULL, NULL, cur_pos, stop, 1); + if (IS_ERR(cqr)) { + rc = PTR_ERR(cqr); + if (rc == -ENOMEM) { + if (list_empty(&ras_queue)) + goto out; + retry = 1; + break; + } + goto err_out; + } + + spin_lock_irq(&block->queue_lock); + list_add_tail(&cqr->blocklist, &ras_queue); + spin_unlock_irq(&block->queue_lock); + cur_pos = stop + 1; + } + + rc = dasd_sleep_on_queue_interruptible(&ras_queue); + +err_out: + list_for_each_entry_safe(cqr, n, &ras_queue, blocklist) { + device = cqr->startdev; + private = device->private; + + spin_lock_irq(&block->queue_lock); + list_del_init(&cqr->blocklist); + spin_unlock_irq(&block->queue_lock); + dasd_sfree_request(cqr, device); + private->count--; + } + } while (retry); + +out: + return rc; +} + +static int dasd_eckd_release_space(struct dasd_device *device, + struct format_data_t *rdata) +{ + if (rdata->intensity & DASD_FMT_INT_ESE_FULL) + return dasd_eckd_release_space_full(device); + else if (rdata->intensity == 0) + return dasd_eckd_release_space_trks(device, rdata->start_unit, + rdata->stop_unit); + else + return -EINVAL; +} + +static struct dasd_ccw_req * +dasd_eckd_build_cp_discard(struct dasd_device *device, struct dasd_block *block, + struct request *req, sector_t first_trk, + sector_t last_trk) +{ + return dasd_eckd_dso_ras(device, block, req, first_trk, last_trk, 1); +} + static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_single( struct dasd_device *startdev, struct dasd_block *block, @@ -3214,6 +3884,14 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_single( cqr->retries = startdev->default_retries; cqr->buildclk = get_tod_clock(); cqr->status = DASD_CQR_FILLED; + + /* Set flags to suppress output for expected errors */ + if (dasd_eckd_is_ese(basedev)) { + set_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags); + set_bit(DASD_CQR_SUPPRESS_IL, &cqr->flags); + set_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags); + } + return cqr; } @@ -3385,6 +4063,11 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_track( cqr->retries = startdev->default_retries; cqr->buildclk = get_tod_clock(); cqr->status = DASD_CQR_FILLED; + + /* Set flags to suppress output for expected errors */ + if (dasd_eckd_is_ese(basedev)) + set_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags); + return cqr; } @@ -3704,6 +4387,14 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_tpm_track( cqr->retries = startdev->default_retries; cqr->buildclk = get_tod_clock(); cqr->status = DASD_CQR_FILLED; + + /* Set flags to suppress output for expected errors */ + if (dasd_eckd_is_ese(basedev)) { + set_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags); + set_bit(DASD_CQR_SUPPRESS_IL, &cqr->flags); + set_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags); + } + return cqr; out_error: dasd_sfree_request(cqr, startdev); @@ -3756,6 +4447,10 @@ static struct dasd_ccw_req *dasd_eckd_build_cp(struct dasd_device *startdev, cmdwtd = private->features.feature[12] & 0x40; use_prefix = private->features.feature[8] & 0x01; + if (req_op(req) == REQ_OP_DISCARD) + return dasd_eckd_build_cp_discard(startdev, block, req, + first_trk, last_trk); + cqr = NULL; if (cdlspecial || dasd_page_cache) { /* do nothing, just fall through to the cmd mode single case */ @@ -3827,7 +4522,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_raw(struct dasd_device *startdev, if ((start_padding_sectors || end_padding_sectors) && (rq_data_dir(req) == WRITE)) { DBF_DEV_EVENT(DBF_ERR, basedev, - "raw write not track aligned (%lu,%lu) req %p", + "raw write not track aligned (%llu,%llu) req %p", start_padding_sectors, end_padding_sectors, req); return ERR_PTR(-EINVAL); } @@ -4034,12 +4729,14 @@ static struct dasd_ccw_req *dasd_eckd_build_alias_cp(struct dasd_device *base, struct dasd_block *block, struct request *req) { + struct dasd_device *startdev = NULL; struct dasd_eckd_private *private; - struct dasd_device *startdev; - unsigned long flags; struct dasd_ccw_req *cqr; + unsigned long flags; - startdev = dasd_alias_get_start_dev(base); + /* Discard requests can only be processed on base devices */ + if (req_op(req) != REQ_OP_DISCARD) + startdev = dasd_alias_get_start_dev(base); if (!startdev) startdev = base; private = startdev->private; @@ -4965,6 +5662,16 @@ static int dasd_eckd_restore_device(struct dasd_device *device) /* Read Feature Codes */ dasd_eckd_read_features(device); + /* Read Volume Information */ + rc = dasd_eckd_read_vol_info(device); + if (rc) + goto out_err2; + + /* Read Extent Pool Information */ + rc = dasd_eckd_read_ext_pool_info(device); + if (rc) + goto out_err2; + /* Read Device Characteristics */ rc = dasd_generic_read_dev_chars(device, DASD_ECKD_MAGIC, &temp_rdc_data, 64); @@ -5635,6 +6342,73 @@ static void dasd_eckd_handle_cuir(struct dasd_device *device, void *messages, device->discipline->check_attention(device, lpum); } +static void dasd_eckd_oos_resume(struct dasd_device *device) +{ + struct dasd_eckd_private *private = device->private; + struct alias_pav_group *pavgroup, *tempgroup; + struct dasd_device *dev, *n; + unsigned long flags; + + spin_lock_irqsave(&private->lcu->lock, flags); + list_for_each_entry_safe(dev, n, &private->lcu->active_devices, + alias_list) { + if (dev->stopped & DASD_STOPPED_NOSPC) + dasd_generic_space_avail(dev); + } + list_for_each_entry_safe(dev, n, &private->lcu->inactive_devices, + alias_list) { + if (dev->stopped & DASD_STOPPED_NOSPC) + dasd_generic_space_avail(dev); + } + /* devices in PAV groups */ + list_for_each_entry_safe(pavgroup, tempgroup, + &private->lcu->grouplist, + group) { + list_for_each_entry_safe(dev, n, &pavgroup->baselist, + alias_list) { + if (dev->stopped & DASD_STOPPED_NOSPC) + dasd_generic_space_avail(dev); + } + list_for_each_entry_safe(dev, n, &pavgroup->aliaslist, + alias_list) { + if (dev->stopped & DASD_STOPPED_NOSPC) + dasd_generic_space_avail(dev); + } + } + spin_unlock_irqrestore(&private->lcu->lock, flags); +} + +static void dasd_eckd_handle_oos(struct dasd_device *device, void *messages, + __u8 lpum) +{ + struct dasd_oos_message *oos = messages; + + switch (oos->code) { + case REPO_WARN: + case POOL_WARN: + dev_warn(&device->cdev->dev, + "Extent pool usage has reached a critical value\n"); + dasd_eckd_oos_resume(device); + break; + case REPO_EXHAUST: + case POOL_EXHAUST: + dev_warn(&device->cdev->dev, + "Extent pool is exhausted\n"); + break; + case REPO_RELIEVE: + case POOL_RELIEVE: + dev_info(&device->cdev->dev, + "Extent pool physical space constraint has been relieved\n"); + break; + } + + /* In any case, update related data */ + dasd_eckd_read_ext_pool_info(device); + + /* to make sure there is no attention left schedule work again */ + device->discipline->check_attention(device, lpum); +} + static void dasd_eckd_check_attention_work(struct work_struct *work) { struct check_attention_work_data *data; @@ -5653,9 +6427,14 @@ static void dasd_eckd_check_attention_work(struct work_struct *work) rc = dasd_eckd_read_message_buffer(device, messages, data->lpum); if (rc) goto out; + if (messages->length == ATTENTION_LENGTH_CUIR && messages->format == ATTENTION_FORMAT_CUIR) dasd_eckd_handle_cuir(device, messages, data->lpum); + if (messages->length == ATTENTION_LENGTH_OOS && + messages->format == ATTENTION_FORMAT_OOS) + dasd_eckd_handle_oos(device, messages, data->lpum); + out: dasd_put_device(device); kfree(messages); @@ -5734,6 +6513,72 @@ static void dasd_eckd_handle_hpf_error(struct dasd_device *device, dasd_schedule_requeue(device); } +/* + * Initialize block layer request queue. + */ +static void dasd_eckd_setup_blk_queue(struct dasd_block *block) +{ + unsigned int logical_block_size = block->bp_block; + struct request_queue *q = block->request_queue; + struct dasd_device *device = block->base; + struct dasd_eckd_private *private; + unsigned int max_discard_sectors; + unsigned int max_bytes; + unsigned int ext_bytes; /* Extent Size in Bytes */ + int recs_per_trk; + int trks_per_cyl; + int ext_limit; + int ext_size; /* Extent Size in Cylinders */ + int max; + + private = device->private; + trks_per_cyl = private->rdc_data.trk_per_cyl; + recs_per_trk = recs_per_track(&private->rdc_data, 0, logical_block_size); + + if (device->features & DASD_FEATURE_USERAW) { + /* + * the max_blocks value for raw_track access is 256 + * it is higher than the native ECKD value because we + * only need one ccw per track + * so the max_hw_sectors are + * 2048 x 512B = 1024kB = 16 tracks + */ + max = DASD_ECKD_MAX_BLOCKS_RAW << block->s2b_shift; + } else { + max = DASD_ECKD_MAX_BLOCKS << block->s2b_shift; + } + blk_queue_flag_set(QUEUE_FLAG_NONROT, q); + q->limits.max_dev_sectors = max; + blk_queue_logical_block_size(q, logical_block_size); + blk_queue_max_hw_sectors(q, max); + blk_queue_max_segments(q, USHRT_MAX); + /* With page sized segments each segment can be translated into one idaw/tidaw */ + blk_queue_max_segment_size(q, PAGE_SIZE); + blk_queue_segment_boundary(q, PAGE_SIZE - 1); + + if (dasd_eckd_is_ese(device)) { + /* + * Depending on the extent size, up to UINT_MAX bytes can be + * accepted. However, neither DASD_ECKD_RAS_EXTS_MAX nor the + * device limits should be exceeded. + */ + ext_size = dasd_eckd_ext_size(device); + ext_limit = min(private->real_cyl / ext_size, DASD_ECKD_RAS_EXTS_MAX); + ext_bytes = ext_size * trks_per_cyl * recs_per_trk * + logical_block_size; + max_bytes = UINT_MAX - (UINT_MAX % ext_bytes); + if (max_bytes / ext_bytes > ext_limit) + max_bytes = ext_bytes * ext_limit; + + max_discard_sectors = max_bytes / 512; + + blk_queue_max_discard_sectors(q, max_discard_sectors); + blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); + q->limits.discard_granularity = ext_bytes; + q->limits.discard_alignment = ext_bytes; + } +} + static struct ccw_driver dasd_eckd_driver = { .driver = { .name = "dasd-eckd", @@ -5754,24 +6599,10 @@ static struct ccw_driver dasd_eckd_driver = { .int_class = IRQIO_DAS, }; -/* - * max_blocks is dependent on the amount of storage that is available - * in the static io buffer for each device. Currently each device has - * 8192 bytes (=2 pages). For 64 bit one dasd_mchunkt_t structure has - * 24 bytes, the struct dasd_ccw_req has 136 bytes and each block can use - * up to 16 bytes (8 for the ccw and 8 for the idal pointer). In - * addition we have one define extent ccw + 16 bytes of data and one - * locate record ccw + 16 bytes of data. That makes: - * (8192 - 24 - 136 - 8 - 16 - 8 - 16) / 16 = 499 blocks at maximum. - * We want to fit two into the available memory so that we can immediately - * start the next request if one finishes off. That makes 249.5 blocks - * for one request. Give a little safety and the result is 240. - */ static struct dasd_discipline dasd_eckd_discipline = { .owner = THIS_MODULE, .name = "ECKD", .ebcname = "ECKD", - .max_blocks = 190, .check_device = dasd_eckd_check_characteristics, .uncheck_device = dasd_eckd_uncheck_device, .do_analysis = dasd_eckd_do_analysis, @@ -5779,6 +6610,7 @@ static struct dasd_discipline dasd_eckd_discipline = { .basic_to_ready = dasd_eckd_basic_to_ready, .online_to_ready = dasd_eckd_online_to_ready, .basic_to_known = dasd_eckd_basic_to_known, + .setup_blk_queue = dasd_eckd_setup_blk_queue, .fill_geometry = dasd_eckd_fill_geometry, .start_IO = dasd_start_IO, .term_IO = dasd_term_IO, @@ -5806,6 +6638,19 @@ static struct dasd_discipline dasd_eckd_discipline = { .disable_hpf = dasd_eckd_disable_hpf_device, .hpf_enabled = dasd_eckd_hpf_enabled, .reset_path = dasd_eckd_reset_path, + .is_ese = dasd_eckd_is_ese, + .space_allocated = dasd_eckd_space_allocated, + .space_configured = dasd_eckd_space_configured, + .logical_capacity = dasd_eckd_logical_capacity, + .release_space = dasd_eckd_release_space, + .ext_pool_id = dasd_eckd_ext_pool_id, + .ext_size = dasd_eckd_ext_size, + .ext_pool_cap_at_warnlevel = dasd_eckd_ext_pool_cap_at_warnlevel, + .ext_pool_warn_thrshld = dasd_eckd_ext_pool_warn_thrshld, + .ext_pool_oos = dasd_eckd_ext_pool_oos, + .ext_pool_exhaust = dasd_eckd_ext_pool_exhaust, + .ese_format = dasd_eckd_ese_format, + .ese_read = dasd_eckd_ese_read, }; static int __init @@ -5818,16 +6663,22 @@ dasd_eckd_init(void) GFP_KERNEL | GFP_DMA); if (!dasd_reserve_req) return -ENOMEM; + dasd_vol_info_req = kmalloc(sizeof(*dasd_vol_info_req), + GFP_KERNEL | GFP_DMA); + if (!dasd_vol_info_req) + return -ENOMEM; path_verification_worker = kmalloc(sizeof(*path_verification_worker), GFP_KERNEL | GFP_DMA); if (!path_verification_worker) { kfree(dasd_reserve_req); + kfree(dasd_vol_info_req); return -ENOMEM; } rawpadpage = (void *)__get_free_page(GFP_KERNEL); if (!rawpadpage) { kfree(path_verification_worker); kfree(dasd_reserve_req); + kfree(dasd_vol_info_req); return -ENOMEM; } ret = ccw_driver_register(&dasd_eckd_driver); @@ -5836,6 +6687,7 @@ dasd_eckd_init(void) else { kfree(path_verification_worker); kfree(dasd_reserve_req); + kfree(dasd_vol_info_req); free_page((unsigned long)rawpadpage); } return ret; diff --git a/drivers/s390/block/dasd_eckd.h b/drivers/s390/block/dasd_eckd.h index 5869d2fede35..6943508d0f1d 100644 --- a/drivers/s390/block/dasd_eckd.h +++ b/drivers/s390/block/dasd_eckd.h @@ -50,16 +50,26 @@ #define DASD_ECKD_CCW_PFX_READ 0xEA #define DASD_ECKD_CCW_RSCK 0xF9 #define DASD_ECKD_CCW_RCD 0xFA +#define DASD_ECKD_CCW_DSO 0xF7 + +/* Define Subssystem Function / Orders */ +#define DSO_ORDER_RAS 0x81 /* - * Perform Subsystem Function / Sub-Orders + * Perform Subsystem Function / Orders */ #define PSF_ORDER_PRSSD 0x18 #define PSF_ORDER_CUIR_RESPONSE 0x1A -#define PSF_SUBORDER_QHA 0x1C #define PSF_ORDER_SSC 0x1D /* + * Perform Subsystem Function / Sub-Orders + */ +#define PSF_SUBORDER_QHA 0x1C /* Query Host Access */ +#define PSF_SUBORDER_VSQ 0x52 /* Volume Storage Query */ +#define PSF_SUBORDER_LCQ 0x53 /* Logical Configuration Query */ + +/* * CUIR response condition codes */ #define PSF_CUIR_INVALID 0x00 @@ -80,10 +90,22 @@ #define CUIR_RESUME 0x02 /* + * Out-of-space (OOS) Codes + */ +#define REPO_WARN 0x01 +#define REPO_EXHAUST 0x02 +#define POOL_WARN 0x03 +#define POOL_EXHAUST 0x04 +#define REPO_RELIEVE 0x05 +#define POOL_RELIEVE 0x06 + +/* * attention message definitions */ #define ATTENTION_LENGTH_CUIR 0x0e #define ATTENTION_FORMAT_CUIR 0x01 +#define ATTENTION_LENGTH_OOS 0x10 +#define ATTENTION_FORMAT_OOS 0x06 #define DASD_ECKD_PG_GROUPED 0x10 @@ -99,6 +121,12 @@ #define DASD_ECKD_PATH_THRHLD 256 #define DASD_ECKD_PATH_INTERVAL 300 +/* + * Maximum number of blocks to be chained + */ +#define DASD_ECKD_MAX_BLOCKS 190 +#define DASD_ECKD_MAX_BLOCKS_RAW 256 + /***************************************************************************** * SECTION: Type Definitions ****************************************************************************/ @@ -116,35 +144,12 @@ struct ch_t { __u16 head; } __attribute__ ((packed)); -struct chs_t { - __u16 cyl; - __u16 head; - __u32 sector; -} __attribute__ ((packed)); - struct chr_t { __u16 cyl; __u16 head; __u8 record; } __attribute__ ((packed)); -struct geom_t { - __u16 cyl; - __u16 head; - __u32 sector; -} __attribute__ ((packed)); - -struct eckd_home { - __u8 skip_control[14]; - __u16 cell_number; - __u8 physical_addr[3]; - __u8 flag; - struct ch_t track_addr; - __u8 reserved; - __u8 key_length; - __u8 reserved2[2]; -} __attribute__ ((packed)); - struct DE_eckd_data { struct { unsigned char perm:2; /* Permissions on this extent */ @@ -387,6 +392,86 @@ struct dasd_rssd_messages { char messages[4087]; } __packed; +/* + * Read Subsystem Data - Volume Storage Query + */ +struct dasd_rssd_vsq { + struct { + __u8 tse:1; + __u8 space_not_available:1; + __u8 ese:1; + __u8 unused:5; + } __packed vol_info; + __u8 unused1; + __u16 extent_pool_id; + __u8 warn_cap_limit; + __u8 warn_cap_guaranteed; + __u16 unused2; + __u32 limit_capacity; + __u32 guaranteed_capacity; + __u32 space_allocated; + __u32 space_configured; + __u32 logical_capacity; +} __packed; + +/* + * Extent Pool Summary + */ +struct dasd_ext_pool_sum { + __u16 pool_id; + __u8 repo_warn_thrshld; + __u8 warn_thrshld; + struct { + __u8 type:1; /* 0 - CKD / 1 - FB */ + __u8 track_space_efficient:1; + __u8 extent_space_efficient:1; + __u8 standard_volume:1; + __u8 extent_size_valid:1; + __u8 capacity_at_warnlevel:1; + __u8 pool_oos:1; + __u8 unused0:1; + __u8 unused1; + } __packed flags; + struct { + __u8 reserved0:1; + __u8 size_1G:1; + __u8 reserved1:5; + __u8 size_16M:1; + } __packed extent_size; + __u8 unused; +} __packed; + +/* + * Read Subsystem Data-Response - Logical Configuration Query - Header + */ +struct dasd_rssd_lcq { + __u16 data_length; /* Length of data returned */ + __u16 pool_count; /* Count of extent pools returned - Max: 448 */ + struct { + __u8 pool_info_valid:1; /* Detailed Information valid */ + __u8 pool_id_volume:1; + __u8 pool_id_cec:1; + __u8 unused0:5; + __u8 unused1; + } __packed header_flags; + char sfi_type[6]; /* Storage Facility Image Type (EBCDIC) */ + char sfi_model[3]; /* Storage Facility Image Model (EBCDIC) */ + __u8 sfi_seq_num[10]; /* Storage Facility Image Sequence Number */ + __u8 reserved[7]; + struct dasd_ext_pool_sum ext_pool_sum[448]; +} __packed; + +struct dasd_oos_message { + __u16 length; + __u8 format; + __u8 code; + __u8 percentage_empty; + __u8 reserved; + __u16 ext_pool_id; + __u16 token; + __u8 unused[6]; +} __packed; + struct dasd_cuir_message { __u16 length; __u8 format; @@ -461,6 +546,42 @@ struct dasd_psf_ssc_data { unsigned char reserved[59]; } __attribute__((packed)); +/* Maximum number of extents for a single Release Allocated Space command */ +#define DASD_ECKD_RAS_EXTS_MAX 110U + +struct dasd_dso_ras_ext_range { + struct ch_t beg_ext; + struct ch_t end_ext; +} __packed; + +/* + * Define Subsytem Operation - Release Allocated Space + */ +struct dasd_dso_ras_data { + __u8 order; + struct { + __u8 message:1; /* Must be zero */ + __u8 reserved1:2; + __u8 vol_type:1; /* 0 - CKD/FBA, 1 - FB */ + __u8 reserved2:4; + } __packed flags; + /* Operation Flags to specify scope */ + struct { + __u8 reserved1:2; + /* Release Space by Extent */ + __u8 by_extent:1; /* 0 - entire volume, 1 - specified extents */ + __u8 guarantee_init:1; + __u8 force_release:1; /* Internal - will be ignored */ + __u16 reserved2:11; + } __packed op_flags; + __u8 lss; + __u8 dev_addr; + __u32 reserved1; + __u8 reserved2[10]; + __u16 nr_exts; /* Defines number of ext_scope - max 110 */ + __u16 reserved3; +} __packed; + /* * some structures and definitions for alias handling @@ -551,6 +672,8 @@ struct dasd_eckd_private { int uses_cdl; struct attrib_data_t attrib; /* e.g. cache operations */ struct dasd_rssd_features features; + struct dasd_rssd_vsq vsq; + struct dasd_ext_pool_sum eps; u32 real_cyl; /* alias managemnet */ @@ -572,7 +695,5 @@ int dasd_alias_remove_device(struct dasd_device *); struct dasd_device *dasd_alias_get_start_dev(struct dasd_device *); void dasd_alias_handle_summary_unit_check(struct work_struct *); void dasd_eckd_reset_ccw_to_base_io(struct dasd_ccw_req *); -void dasd_alias_lcu_setup_complete(struct dasd_device *); -void dasd_alias_wait_for_lcu_setup(struct dasd_device *); int dasd_alias_update_add_device(struct dasd_device *); #endif /* DASD_ECKD_H */ diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c index 93bb09da7fdc..5ae64af9ccea 100644 --- a/drivers/s390/block/dasd_eer.c +++ b/drivers/s390/block/dasd_eer.c @@ -386,6 +386,7 @@ void dasd_eer_write(struct dasd_device *device, struct dasd_ccw_req *cqr, dasd_eer_write_standard_trigger(device, cqr, id); break; case DASD_EER_NOPATH: + case DASD_EER_NOSPC: dasd_eer_write_standard_trigger(device, NULL, id); break; case DASD_EER_STATECHANGE: diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c index 56007a3e7f11..cbb770824226 100644 --- a/drivers/s390/block/dasd_fba.c +++ b/drivers/s390/block/dasd_fba.c @@ -770,27 +770,46 @@ dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req, } /* - * max_blocks is dependent on the amount of storage that is available - * in the static io buffer for each device. Currently each device has - * 8192 bytes (=2 pages). For 64 bit one dasd_mchunkt_t structure has - * 24 bytes, the struct dasd_ccw_req has 136 bytes and each block can use - * up to 16 bytes (8 for the ccw and 8 for the idal pointer). In - * addition we have one define extent ccw + 16 bytes of data and a - * locate record ccw for each block (stupid devices!) + 16 bytes of data. - * That makes: - * (8192 - 24 - 136 - 8 - 16) / 40 = 200.2 blocks at maximum. - * We want to fit two into the available memory so that we can immediately - * start the next request if one finishes off. That makes 100.1 blocks - * for one request. Give a little safety and the result is 96. + * Initialize block layer request queue. */ +static void dasd_fba_setup_blk_queue(struct dasd_block *block) +{ + unsigned int logical_block_size = block->bp_block; + struct request_queue *q = block->request_queue; + unsigned int max_bytes, max_discard_sectors; + int max; + + max = DASD_FBA_MAX_BLOCKS << block->s2b_shift; + blk_queue_flag_set(QUEUE_FLAG_NONROT, q); + q->limits.max_dev_sectors = max; + blk_queue_logical_block_size(q, logical_block_size); + blk_queue_max_hw_sectors(q, max); + blk_queue_max_segments(q, USHRT_MAX); + /* With page sized segments each segment can be translated into one idaw/tidaw */ + blk_queue_max_segment_size(q, PAGE_SIZE); + blk_queue_segment_boundary(q, PAGE_SIZE - 1); + + q->limits.discard_granularity = logical_block_size; + q->limits.discard_alignment = PAGE_SIZE; + + /* Calculate max_discard_sectors and make it PAGE aligned */ + max_bytes = USHRT_MAX * logical_block_size; + max_bytes = ALIGN_DOWN(max_bytes, PAGE_SIZE); + max_discard_sectors = max_bytes / logical_block_size; + + blk_queue_max_discard_sectors(q, max_discard_sectors); + blk_queue_max_write_zeroes_sectors(q, max_discard_sectors); + blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); +} + static struct dasd_discipline dasd_fba_discipline = { .owner = THIS_MODULE, .name = "FBA ", .ebcname = "FBA ", - .max_blocks = 96, .check_device = dasd_fba_check_characteristics, .do_analysis = dasd_fba_do_analysis, .verify_path = dasd_generic_verify_path, + .setup_blk_queue = dasd_fba_setup_blk_queue, .fill_geometry = dasd_fba_fill_geometry, .start_IO = dasd_start_IO, .term_IO = dasd_term_IO, diff --git a/drivers/s390/block/dasd_fba.h b/drivers/s390/block/dasd_fba.h index b14bf1b2c691..8f75df06e893 100644 --- a/drivers/s390/block/dasd_fba.h +++ b/drivers/s390/block/dasd_fba.h @@ -9,6 +9,11 @@ #ifndef DASD_FBA_H #define DASD_FBA_H +/* + * Maximum number of blocks to be chained + */ +#define DASD_FBA_MAX_BLOCKS 96 + struct DE_fba_data { struct { unsigned char perm:2; /* Permissions on this extent */ diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index de6b96036aa4..91c9f9586e0f 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -268,7 +268,6 @@ struct dasd_discipline { struct module *owner; char ebcname[8]; /* a name used for tagging and printks */ char name[8]; /* a name used for tagging and printks */ - int max_blocks; /* maximum number of blocks to be chained */ struct list_head list; /* used for list of disciplines */ @@ -307,6 +306,10 @@ struct dasd_discipline { int (*online_to_ready) (struct dasd_device *); int (*basic_to_known)(struct dasd_device *); + /* + * Initialize block layer request queue. + */ + void (*setup_blk_queue)(struct dasd_block *); /* (struct dasd_device *); * Device operation functions. build_cp creates a ccw chain for * a block device request, start_io starts the request and @@ -367,6 +370,25 @@ struct dasd_discipline { void (*disable_hpf)(struct dasd_device *); int (*hpf_enabled)(struct dasd_device *); void (*reset_path)(struct dasd_device *, __u8); + + /* + * Extent Space Efficient (ESE) relevant functions + */ + int (*is_ese)(struct dasd_device *); + /* Capacity */ + int (*space_allocated)(struct dasd_device *); + int (*space_configured)(struct dasd_device *); + int (*logical_capacity)(struct dasd_device *); + int (*release_space)(struct dasd_device *, struct format_data_t *); + /* Extent Pool */ + int (*ext_pool_id)(struct dasd_device *); + int (*ext_size)(struct dasd_device *); + int (*ext_pool_cap_at_warnlevel)(struct dasd_device *); + int (*ext_pool_warn_thrshld)(struct dasd_device *); + int (*ext_pool_oos)(struct dasd_device *); + int (*ext_pool_exhaust)(struct dasd_device *, struct dasd_ccw_req *); + struct dasd_ccw_req *(*ese_format)(struct dasd_device *, struct dasd_ccw_req *); + void (*ese_read)(struct dasd_ccw_req *); }; extern struct dasd_discipline *dasd_diag_discipline_pointer; @@ -386,6 +408,7 @@ extern struct dasd_discipline *dasd_diag_discipline_pointer; #define DASD_EER_NOPATH 2 #define DASD_EER_STATECHANGE 3 #define DASD_EER_PPRCSUSPEND 4 +#define DASD_EER_NOSPC 5 /* DASD path handling */ @@ -482,8 +505,10 @@ struct dasd_device { spinlock_t mem_lock; void *ccw_mem; void *erp_mem; + void *ese_mem; struct list_head ccw_chunks; struct list_head erp_chunks; + struct list_head ese_chunks; atomic_t tasklet_scheduled; struct tasklet_struct tasklet; @@ -558,6 +583,7 @@ struct dasd_queue { #define DASD_STOPPED_SU 16 /* summary unit check handling */ #define DASD_STOPPED_PM 32 /* pm state transition */ #define DASD_UNRESUMED_PM 64 /* pm resume failed state */ +#define DASD_STOPPED_NOSPC 128 /* no space left */ /* per device flags */ #define DASD_FLAG_OFFLINE 3 /* device is in offline processing */ @@ -700,7 +726,9 @@ extern struct kmem_cache *dasd_page_cache; struct dasd_ccw_req * dasd_smalloc_request(int, int, int, struct dasd_device *, struct dasd_ccw_req *); +struct dasd_ccw_req *dasd_fmalloc_request(int, int, int, struct dasd_device *); void dasd_sfree_request(struct dasd_ccw_req *, struct dasd_device *); +void dasd_ffree_request(struct dasd_ccw_req *, struct dasd_device *); void dasd_wakeup_cb(struct dasd_ccw_req *, void *); struct dasd_device *dasd_alloc_device(void); @@ -727,6 +755,7 @@ void dasd_schedule_block_bh(struct dasd_block *); int dasd_sleep_on(struct dasd_ccw_req *); int dasd_sleep_on_queue(struct list_head *); int dasd_sleep_on_immediatly(struct dasd_ccw_req *); +int dasd_sleep_on_queue_interruptible(struct list_head *); int dasd_sleep_on_interruptible(struct dasd_ccw_req *); void dasd_device_set_timer(struct dasd_device *, int); void dasd_device_clear_timer(struct dasd_device *); @@ -750,6 +779,8 @@ int dasd_generic_restore_device(struct ccw_device *); enum uc_todo dasd_generic_uc_handler(struct ccw_device *, struct irb *); void dasd_generic_path_event(struct ccw_device *, int *); int dasd_generic_verify_path(struct dasd_device *, __u8); +void dasd_generic_space_exhaust(struct dasd_device *, struct dasd_ccw_req *); +void dasd_generic_space_avail(struct dasd_device *); int dasd_generic_read_dev_chars(struct dasd_device *, int, void *, int); char *dasd_get_sense(struct irb *); diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c index 8e26001dc11c..9a5f3add325f 100644 --- a/drivers/s390/block/dasd_ioctl.c +++ b/drivers/s390/block/dasd_ioctl.c @@ -333,6 +333,59 @@ out_err: return rc; } +static int dasd_release_space(struct dasd_device *device, + struct format_data_t *rdata) +{ + if (!device->discipline->is_ese && !device->discipline->is_ese(device)) + return -ENOTSUPP; + if (!device->discipline->release_space) + return -ENOTSUPP; + + return device->discipline->release_space(device, rdata); +} + +/* + * Release allocated space + */ +static int dasd_ioctl_release_space(struct block_device *bdev, void __user *argp) +{ + struct format_data_t rdata; + struct dasd_device *base; + int rc = 0; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + if (!argp) + return -EINVAL; + + base = dasd_device_from_gendisk(bdev->bd_disk); + if (!base) + return -ENODEV; + if (base->features & DASD_FEATURE_READONLY || + test_bit(DASD_FLAG_DEVICE_RO, &base->flags)) { + rc = -EROFS; + goto out_err; + } + if (bdev != bdev->bd_contains) { + pr_warn("%s: The specified DASD is a partition and tracks cannot be released\n", + dev_name(&base->cdev->dev)); + rc = -EINVAL; + goto out_err; + } + + if (copy_from_user(&rdata, argp, sizeof(rdata))) { + rc = -EFAULT; + goto out_err; + } + + rc = dasd_release_space(base, &rdata); + +out_err: + dasd_put_device(base); + + return rc; +} + #ifdef CONFIG_DASD_PROFILE /* * Reset device profile information @@ -595,6 +648,9 @@ int dasd_ioctl(struct block_device *bdev, fmode_t mode, case BIODASDREADALLCMB: rc = dasd_ioctl_readall_cmb(block, cmd, argp); break; + case BIODASDRAS: + rc = dasd_ioctl_release_space(bdev, argp); + break; default: /* if the discipline has an ioctl method try it. */ rc = -ENOTTY; diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 4e8aedd50cb0..d04d4378ca50 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -59,6 +59,7 @@ static size_t dcssblk_dax_copy_to_iter(struct dax_device *dax_dev, static const struct dax_operations dcssblk_dax_ops = { .direct_access = dcssblk_dax_direct_access, + .dax_supported = generic_fsdax_supported, .copy_from_iter = dcssblk_dax_copy_from_iter, .copy_to_iter = dcssblk_dax_copy_to_iter, }; diff --git a/drivers/s390/char/Kconfig b/drivers/s390/char/Kconfig index ab0b243a947d..6cc4b19acf85 100644 --- a/drivers/s390/char/Kconfig +++ b/drivers/s390/char/Kconfig @@ -79,27 +79,6 @@ config SCLP_VT220_CONSOLE Include support for using an IBM SCLP VT220-compatible terminal as a Linux system console. -config SCLP_ASYNC - def_tristate m - prompt "Support for Call Home via Asynchronous SCLP Records" - depends on S390 - help - This option enables the call home function, which is able to inform - the service element and connected organisations about a kernel panic. - You should only select this option if you know what you are doing, - want for inform other people about your kernel panics, - need this feature and intend to run your kernel in LPAR. - -config SCLP_ASYNC_ID - string "Component ID for Call Home" - depends on SCLP_ASYNC - default "000000000" - help - The Component ID for Call Home is used to identify the correct - problem reporting queue the call home records should be sent to. - - If your are unsure, please use the default value "000000000". - config HMC_DRV def_tristate m prompt "Support for file transfers from HMC drive CD/DVD-ROM" @@ -205,4 +184,3 @@ config S390_VMUR depends on S390 help Character device driver for z/VM reader, puncher and printer. - diff --git a/drivers/s390/char/Makefile b/drivers/s390/char/Makefile index 3072b89785dd..b8a8816d94e7 100644 --- a/drivers/s390/char/Makefile +++ b/drivers/s390/char/Makefile @@ -31,7 +31,6 @@ obj-$(CONFIG_TN3215) += con3215.o obj-$(CONFIG_SCLP_TTY) += sclp_tty.o obj-$(CONFIG_SCLP_CONSOLE) += sclp_con.o obj-$(CONFIG_SCLP_VT220_TTY) += sclp_vt220.o -obj-$(CONFIG_SCLP_ASYNC) += sclp_async.o obj-$(CONFIG_PCI) += sclp_pci.o diff --git a/drivers/s390/char/fs3270.c b/drivers/s390/char/fs3270.c index 8b48ba9c598e..4c4683d8784a 100644 --- a/drivers/s390/char/fs3270.c +++ b/drivers/s390/char/fs3270.c @@ -486,7 +486,7 @@ fs3270_open(struct inode *inode, struct file *filp) raw3270_del_view(&fp->view); goto out; } - nonseekable_open(inode, filp); + stream_open(inode, filp); filp->private_data = fp; out: mutex_unlock(&fs3270_mutex); diff --git a/drivers/s390/char/sclp.c b/drivers/s390/char/sclp.c index e9aa71cdfc44..d2ab3f07c008 100644 --- a/drivers/s390/char/sclp.c +++ b/drivers/s390/char/sclp.c @@ -45,8 +45,8 @@ static struct list_head sclp_req_queue; /* Data for read and and init requests. */ static struct sclp_req sclp_read_req; static struct sclp_req sclp_init_req; -static char sclp_read_sccb[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE))); -static char sclp_init_sccb[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE))); +static void *sclp_read_sccb; +static struct init_sccb *sclp_init_sccb; /* Suspend request */ static DECLARE_COMPLETION(sclp_request_queue_flushed); @@ -753,9 +753,8 @@ EXPORT_SYMBOL(sclp_remove_processed); static inline void __sclp_make_init_req(sccb_mask_t receive_mask, sccb_mask_t send_mask) { - struct init_sccb *sccb; + struct init_sccb *sccb = sclp_init_sccb; - sccb = (struct init_sccb *) sclp_init_sccb; clear_page(sccb); memset(&sclp_init_req, 0, sizeof(struct sclp_req)); sclp_init_req.command = SCLP_CMDW_WRITE_EVENT_MASK; @@ -782,7 +781,7 @@ static int sclp_init_mask(int calculate) { unsigned long flags; - struct init_sccb *sccb = (struct init_sccb *) sclp_init_sccb; + struct init_sccb *sccb = sclp_init_sccb; sccb_mask_t receive_mask; sccb_mask_t send_mask; int retry; @@ -1175,6 +1174,9 @@ sclp_init(void) if (sclp_init_state != sclp_init_state_uninitialized) goto fail_unlock; sclp_init_state = sclp_init_state_initializing; + sclp_read_sccb = (void *) __get_free_page(GFP_ATOMIC | GFP_DMA); + sclp_init_sccb = (void *) __get_free_page(GFP_ATOMIC | GFP_DMA); + BUG_ON(!sclp_read_sccb || !sclp_init_sccb); /* Set up variables */ INIT_LIST_HEAD(&sclp_req_queue); INIT_LIST_HEAD(&sclp_reg_list); @@ -1207,6 +1209,8 @@ fail_unregister_reboot_notifier: unregister_reboot_notifier(&sclp_reboot_notifier); fail_init_state_uninitialized: sclp_init_state = sclp_init_state_uninitialized; + free_page((unsigned long) sclp_read_sccb); + free_page((unsigned long) sclp_init_sccb); fail_unlock: spin_unlock_irqrestore(&sclp_lock, flags); return rc; diff --git a/drivers/s390/char/sclp.h b/drivers/s390/char/sclp.h index 367e9d384d85..196333013e54 100644 --- a/drivers/s390/char/sclp.h +++ b/drivers/s390/char/sclp.h @@ -197,7 +197,9 @@ struct read_info_sccb { u32 hmfai; /* 124-127 */ u8 _pad_128[134 - 128]; /* 128-133 */ u8 byte_134; /* 134 */ - u8 _pad_135[4096 - 135]; /* 135-4095 */ + u8 cpudirq; /* 135 */ + u16 cbl; /* 136-137 */ + u8 _pad_138[4096 - 138]; /* 138-4095 */ } __packed __aligned(PAGE_SIZE); struct read_storage_sccb { @@ -319,7 +321,7 @@ extern int sclp_console_drop; extern unsigned long sclp_console_full; extern bool sclp_mask_compat_mode; -extern char sclp_early_sccb[PAGE_SIZE]; +extern char *sclp_early_sccb; void sclp_early_wait_irq(void); int sclp_early_cmd(sclp_cmdw_t cmd, void *sccb); @@ -365,14 +367,14 @@ sclp_ascebc(unsigned char ch) /* translate string from EBCDIC to ASCII */ static inline void -sclp_ebcasc_str(unsigned char *str, int nr) +sclp_ebcasc_str(char *str, int nr) { (MACHINE_IS_VM) ? EBCASC(str, nr) : EBCASC_500(str, nr); } /* translate string from ASCII to EBCDIC */ static inline void -sclp_ascebc_str(unsigned char *str, int nr) +sclp_ascebc_str(char *str, int nr) { (MACHINE_IS_VM) ? ASCEBC(str, nr) : ASCEBC_500(str, nr); } diff --git a/drivers/s390/char/sclp_async.c b/drivers/s390/char/sclp_async.c deleted file mode 100644 index e69b12a40636..000000000000 --- a/drivers/s390/char/sclp_async.c +++ /dev/null @@ -1,189 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Enable Asynchronous Notification via SCLP. - * - * Copyright IBM Corp. 2009 - * Author(s): Hans-Joachim Picht <hans@linux.vnet.ibm.com> - * - */ - -#include <linux/init.h> -#include <linux/module.h> -#include <linux/device.h> -#include <linux/stat.h> -#include <linux/string.h> -#include <linux/slab.h> -#include <linux/ctype.h> -#include <linux/kmod.h> -#include <linux/err.h> -#include <linux/errno.h> -#include <linux/proc_fs.h> -#include <linux/sysctl.h> -#include <linux/utsname.h> -#include "sclp.h" - -static int callhome_enabled; -static struct sclp_req *request; -static struct sclp_async_sccb *sccb; -static int sclp_async_send_wait(char *message); -static struct ctl_table_header *callhome_sysctl_header; -static DEFINE_SPINLOCK(sclp_async_lock); -#define SCLP_NORMAL_WRITE 0x00 - -struct async_evbuf { - struct evbuf_header header; - u64 reserved; - u8 rflags; - u8 empty; - u8 rtype; - u8 otype; - char comp_id[12]; - char data[3000]; /* there is still some space left */ -} __attribute__((packed)); - -struct sclp_async_sccb { - struct sccb_header header; - struct async_evbuf evbuf; -} __attribute__((packed)); - -static struct sclp_register sclp_async_register = { - .send_mask = EVTYP_ASYNC_MASK, -}; - -static int call_home_on_panic(struct notifier_block *self, - unsigned long event, void *data) -{ - strncat(data, init_utsname()->nodename, - sizeof(init_utsname()->nodename)); - sclp_async_send_wait(data); - return NOTIFY_DONE; -} - -static struct notifier_block call_home_panic_nb = { - .notifier_call = call_home_on_panic, - .priority = INT_MAX, -}; - -static int zero; -static int one = 1; - -static struct ctl_table callhome_table[] = { - { - .procname = "callhome", - .data = &callhome_enabled, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, - }, - {} -}; - -static struct ctl_table kern_dir_table[] = { - { - .procname = "kernel", - .maxlen = 0, - .mode = 0555, - .child = callhome_table, - }, - {} -}; - -/* - * Function used to transfer asynchronous notification - * records which waits for send completion - */ -static int sclp_async_send_wait(char *message) -{ - struct async_evbuf *evb; - int rc; - unsigned long flags; - - if (!callhome_enabled) - return 0; - sccb->evbuf.header.type = EVTYP_ASYNC; - sccb->evbuf.rtype = 0xA5; - sccb->evbuf.otype = 0x00; - evb = &sccb->evbuf; - request->command = SCLP_CMDW_WRITE_EVENT_DATA; - request->sccb = sccb; - request->status = SCLP_REQ_FILLED; - strncpy(sccb->evbuf.data, message, sizeof(sccb->evbuf.data)); - /* - * Retain Queue - * e.g. 5639CC140 500 Red Hat RHEL5 Linux for zSeries (RHEL AS) - */ - strncpy(sccb->evbuf.comp_id, CONFIG_SCLP_ASYNC_ID, - sizeof(sccb->evbuf.comp_id)); - sccb->evbuf.header.length = sizeof(sccb->evbuf); - sccb->header.length = sizeof(sccb->evbuf) + sizeof(sccb->header); - sccb->header.function_code = SCLP_NORMAL_WRITE; - rc = sclp_add_request(request); - if (rc) - return rc; - spin_lock_irqsave(&sclp_async_lock, flags); - while (request->status != SCLP_REQ_DONE && - request->status != SCLP_REQ_FAILED) { - sclp_sync_wait(); - } - spin_unlock_irqrestore(&sclp_async_lock, flags); - if (request->status != SCLP_REQ_DONE) - return -EIO; - rc = ((struct sclp_async_sccb *) - request->sccb)->header.response_code; - if (rc != 0x0020) - return -EIO; - if (evb->header.flags != 0x80) - return -EIO; - return rc; -} - -static int __init sclp_async_init(void) -{ - int rc; - - rc = sclp_register(&sclp_async_register); - if (rc) - return rc; - rc = -EOPNOTSUPP; - if (!(sclp_async_register.sclp_receive_mask & EVTYP_ASYNC_MASK)) - goto out_sclp; - rc = -ENOMEM; - callhome_sysctl_header = register_sysctl_table(kern_dir_table); - if (!callhome_sysctl_header) - goto out_sclp; - request = kzalloc(sizeof(struct sclp_req), GFP_KERNEL); - sccb = (struct sclp_async_sccb *) get_zeroed_page(GFP_KERNEL | GFP_DMA); - if (!request || !sccb) - goto out_mem; - rc = atomic_notifier_chain_register(&panic_notifier_list, - &call_home_panic_nb); - if (!rc) - goto out; -out_mem: - kfree(request); - free_page((unsigned long) sccb); - unregister_sysctl_table(callhome_sysctl_header); -out_sclp: - sclp_unregister(&sclp_async_register); -out: - return rc; -} -module_init(sclp_async_init); - -static void __exit sclp_async_exit(void) -{ - atomic_notifier_chain_unregister(&panic_notifier_list, - &call_home_panic_nb); - unregister_sysctl_table(callhome_sysctl_header); - sclp_unregister(&sclp_async_register); - free_page((unsigned long) sccb); - kfree(request); -} -module_exit(sclp_async_exit); - -MODULE_AUTHOR("Copyright IBM Corp. 2009"); -MODULE_AUTHOR("Hans-Joachim Picht <hans@linux.vnet.ibm.com>"); -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("SCLP Asynchronous Notification Records"); diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c index 8332788681c4..e71992a3c55f 100644 --- a/drivers/s390/char/sclp_early.c +++ b/drivers/s390/char/sclp_early.c @@ -40,6 +40,7 @@ static void __init sclp_early_facilities_detect(struct read_info_sccb *sccb) sclp.has_gisaf = !!(sccb->fac118 & 0x08); sclp.has_hvs = !!(sccb->fac119 & 0x80); sclp.has_kss = !!(sccb->fac98 & 0x01); + sclp.has_sipl = !!(sccb->cbl & 0x02); if (sccb->fac85 & 0x02) S390_lowcore.machine_flags |= MACHINE_FLAG_ESOP; if (sccb->fac91 & 0x40) @@ -93,6 +94,7 @@ static void __init sclp_early_facilities_detect(struct read_info_sccb *sccb) sclp.mtid_prev = (sccb->fac42 & 0x80) ? (sccb->fac66 & 31) : 0; sclp.hmfai = sccb->hmfai; + sclp.has_dirq = !!(sccb->cpudirq & 0x80); } /* @@ -144,7 +146,7 @@ static void __init sclp_early_console_detect(struct init_sccb *sccb) void __init sclp_early_detect(void) { - void *sccb = &sclp_early_sccb; + void *sccb = sclp_early_sccb; sclp_early_facilities_detect(sccb); sclp_early_init_core_info(sccb); diff --git a/drivers/s390/char/sclp_early_core.c b/drivers/s390/char/sclp_early_core.c index 387c114ded3f..7737470f8498 100644 --- a/drivers/s390/char/sclp_early_core.c +++ b/drivers/s390/char/sclp_early_core.c @@ -16,7 +16,7 @@ static struct read_info_sccb __bootdata(sclp_info_sccb); static int __bootdata(sclp_info_sccb_valid); -char sclp_early_sccb[PAGE_SIZE] __aligned(PAGE_SIZE) __section(.data); +char *sclp_early_sccb = (char *) EARLY_SCCB_OFFSET; int sclp_init_state __section(.data) = sclp_init_state_uninitialized; /* * Used to keep track of the size of the event masks. Qemu until version 2.11 @@ -91,8 +91,8 @@ static void sclp_early_print_lm(const char *str, unsigned int len) struct mto *mto; struct go *go; - sccb = (struct write_sccb *) &sclp_early_sccb; - end = (unsigned char *) sccb + sizeof(sclp_early_sccb) - 1; + sccb = (struct write_sccb *) sclp_early_sccb; + end = (unsigned char *) sccb + EARLY_SCCB_SIZE - 1; memset(sccb, 0, sizeof(*sccb)); ptr = (unsigned char *) &sccb->msg.mdb.mto; offset = 0; @@ -139,9 +139,9 @@ static void sclp_early_print_vt220(const char *str, unsigned int len) { struct vt220_sccb *sccb; - sccb = (struct vt220_sccb *) &sclp_early_sccb; - if (sizeof(*sccb) + len >= sizeof(sclp_early_sccb)) - len = sizeof(sclp_early_sccb) - sizeof(*sccb); + sccb = (struct vt220_sccb *) sclp_early_sccb; + if (sizeof(*sccb) + len >= EARLY_SCCB_SIZE) + len = EARLY_SCCB_SIZE - sizeof(*sccb); memset(sccb, 0, sizeof(*sccb)); memcpy(&sccb->msg.data, str, len); sccb->header.length = sizeof(*sccb) + len; @@ -199,7 +199,7 @@ static int sclp_early_setup(int disable, int *have_linemode, int *have_vt220) BUILD_BUG_ON(sizeof(struct init_sccb) > PAGE_SIZE); *have_linemode = *have_vt220 = 0; - sccb = (struct init_sccb *) &sclp_early_sccb; + sccb = (struct init_sccb *) sclp_early_sccb; receive_mask = disable ? 0 : EVTYP_OPCMD_MASK; send_mask = disable ? 0 : EVTYP_VT220MSG_MASK | EVTYP_MSG_MASK; rc = sclp_early_set_event_mask(sccb, receive_mask, send_mask); @@ -304,7 +304,7 @@ int __init sclp_early_get_hsa_size(unsigned long *hsa_size) void __weak __init add_mem_detect_block(u64 start, u64 end) {} int __init sclp_early_read_storage_info(void) { - struct read_storage_sccb *sccb = (struct read_storage_sccb *)&sclp_early_sccb; + struct read_storage_sccb *sccb = (struct read_storage_sccb *)sclp_early_sccb; int rc, id, max_id = 0; unsigned long rn, rzm; sclp_cmdw_t command; @@ -320,8 +320,8 @@ int __init sclp_early_read_storage_info(void) rzm <<= 20; for (id = 0; id <= max_id; id++) { - memset(sclp_early_sccb, 0, sizeof(sclp_early_sccb)); - sccb->header.length = sizeof(sclp_early_sccb); + memset(sclp_early_sccb, 0, EARLY_SCCB_SIZE); + sccb->header.length = EARLY_SCCB_SIZE; command = SCLP_CMDW_READ_STORAGE_INFO | (id << 8); rc = sclp_early_cmd(command, sccb); if (rc) diff --git a/drivers/s390/char/sclp_sdias.c b/drivers/s390/char/sclp_sdias.c index 8e0b69a2f11a..13f97fd73aca 100644 --- a/drivers/s390/char/sclp_sdias.c +++ b/drivers/s390/char/sclp_sdias.c @@ -29,7 +29,7 @@ static struct sclp_register sclp_sdias_register = { .send_mask = EVTYP_SDIAS_MASK, }; -static struct sdias_sccb sccb __attribute__((aligned(4096))); +static struct sdias_sccb *sclp_sdias_sccb; static struct sdias_evbuf sdias_evbuf; static DECLARE_COMPLETION(evbuf_accepted); @@ -58,6 +58,7 @@ static void sdias_callback(struct sclp_req *request, void *data) static int sdias_sclp_send(struct sclp_req *req) { + struct sdias_sccb *sccb = sclp_sdias_sccb; int retries; int rc; @@ -78,16 +79,16 @@ static int sdias_sclp_send(struct sclp_req *req) continue; } /* if not accepted, retry */ - if (!(sccb.evbuf.hdr.flags & 0x80)) { + if (!(sccb->evbuf.hdr.flags & 0x80)) { TRACE("sclp request failed: flags=%x\n", - sccb.evbuf.hdr.flags); + sccb->evbuf.hdr.flags); continue; } /* * for the sync interface the response is in the initial sccb */ if (!sclp_sdias_register.receiver_fn) { - memcpy(&sdias_evbuf, &sccb.evbuf, sizeof(sdias_evbuf)); + memcpy(&sdias_evbuf, &sccb->evbuf, sizeof(sdias_evbuf)); TRACE("sync request done\n"); return 0; } @@ -104,23 +105,24 @@ static int sdias_sclp_send(struct sclp_req *req) */ int sclp_sdias_blk_count(void) { + struct sdias_sccb *sccb = sclp_sdias_sccb; struct sclp_req request; int rc; mutex_lock(&sdias_mutex); - memset(&sccb, 0, sizeof(sccb)); + memset(sccb, 0, sizeof(*sccb)); memset(&request, 0, sizeof(request)); - sccb.hdr.length = sizeof(sccb); - sccb.evbuf.hdr.length = sizeof(struct sdias_evbuf); - sccb.evbuf.hdr.type = EVTYP_SDIAS; - sccb.evbuf.event_qual = SDIAS_EQ_SIZE; - sccb.evbuf.data_id = SDIAS_DI_FCP_DUMP; - sccb.evbuf.event_id = 4712; - sccb.evbuf.dbs = 1; + sccb->hdr.length = sizeof(*sccb); + sccb->evbuf.hdr.length = sizeof(struct sdias_evbuf); + sccb->evbuf.hdr.type = EVTYP_SDIAS; + sccb->evbuf.event_qual = SDIAS_EQ_SIZE; + sccb->evbuf.data_id = SDIAS_DI_FCP_DUMP; + sccb->evbuf.event_id = 4712; + sccb->evbuf.dbs = 1; - request.sccb = &sccb; + request.sccb = sccb; request.command = SCLP_CMDW_WRITE_EVENT_DATA; request.status = SCLP_REQ_FILLED; request.callback = sdias_callback; @@ -130,8 +132,8 @@ int sclp_sdias_blk_count(void) pr_err("sclp_send failed for get_nr_blocks\n"); goto out; } - if (sccb.hdr.response_code != 0x0020) { - TRACE("send failed: %x\n", sccb.hdr.response_code); + if (sccb->hdr.response_code != 0x0020) { + TRACE("send failed: %x\n", sccb->hdr.response_code); rc = -EIO; goto out; } @@ -163,30 +165,31 @@ out: */ int sclp_sdias_copy(void *dest, int start_blk, int nr_blks) { + struct sdias_sccb *sccb = sclp_sdias_sccb; struct sclp_req request; int rc; mutex_lock(&sdias_mutex); - memset(&sccb, 0, sizeof(sccb)); + memset(sccb, 0, sizeof(*sccb)); memset(&request, 0, sizeof(request)); - sccb.hdr.length = sizeof(sccb); - sccb.evbuf.hdr.length = sizeof(struct sdias_evbuf); - sccb.evbuf.hdr.type = EVTYP_SDIAS; - sccb.evbuf.hdr.flags = 0; - sccb.evbuf.event_qual = SDIAS_EQ_STORE_DATA; - sccb.evbuf.data_id = SDIAS_DI_FCP_DUMP; - sccb.evbuf.event_id = 4712; - sccb.evbuf.asa_size = SDIAS_ASA_SIZE_64; - sccb.evbuf.event_status = 0; - sccb.evbuf.blk_cnt = nr_blks; - sccb.evbuf.asa = (unsigned long)dest; - sccb.evbuf.fbn = start_blk; - sccb.evbuf.lbn = 0; - sccb.evbuf.dbs = 1; - - request.sccb = &sccb; + sccb->hdr.length = sizeof(*sccb); + sccb->evbuf.hdr.length = sizeof(struct sdias_evbuf); + sccb->evbuf.hdr.type = EVTYP_SDIAS; + sccb->evbuf.hdr.flags = 0; + sccb->evbuf.event_qual = SDIAS_EQ_STORE_DATA; + sccb->evbuf.data_id = SDIAS_DI_FCP_DUMP; + sccb->evbuf.event_id = 4712; + sccb->evbuf.asa_size = SDIAS_ASA_SIZE_64; + sccb->evbuf.event_status = 0; + sccb->evbuf.blk_cnt = nr_blks; + sccb->evbuf.asa = (unsigned long)dest; + sccb->evbuf.fbn = start_blk; + sccb->evbuf.lbn = 0; + sccb->evbuf.dbs = 1; + + request.sccb = sccb; request.command = SCLP_CMDW_WRITE_EVENT_DATA; request.status = SCLP_REQ_FILLED; request.callback = sdias_callback; @@ -196,8 +199,8 @@ int sclp_sdias_copy(void *dest, int start_blk, int nr_blks) pr_err("sclp_send failed: %x\n", rc); goto out; } - if (sccb.hdr.response_code != 0x0020) { - TRACE("copy failed: %x\n", sccb.hdr.response_code); + if (sccb->hdr.response_code != 0x0020) { + TRACE("copy failed: %x\n", sccb->hdr.response_code); rc = -EIO; goto out; } @@ -256,6 +259,8 @@ int __init sclp_sdias_init(void) { if (ipl_info.type != IPL_TYPE_FCP_DUMP) return 0; + sclp_sdias_sccb = (void *) __get_free_page(GFP_KERNEL | GFP_DMA); + BUG_ON(!sclp_sdias_sccb); sdias_dbf = debug_register("dump_sdias", 4, 1, 4 * sizeof(long)); debug_register_view(sdias_dbf, &debug_sprintf_view); debug_set_level(sdias_dbf, 6); @@ -264,6 +269,7 @@ int __init sclp_sdias_init(void) if (sclp_sdias_init_async() == 0) goto out; TRACE("init failed\n"); + free_page((unsigned long) sclp_sdias_sccb); return -ENODEV; out: TRACE("init done\n"); diff --git a/drivers/s390/char/tape_char.c b/drivers/s390/char/tape_char.c index fc206c9d1c56..ea4253939555 100644 --- a/drivers/s390/char/tape_char.c +++ b/drivers/s390/char/tape_char.c @@ -290,7 +290,7 @@ tapechar_open (struct inode *inode, struct file *filp) rc = tape_open(device); if (rc == 0) { filp->private_data = device; - nonseekable_open(inode, filp); + stream_open(inode, filp); } else tape_put_device(device); diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c index 76d3c50bf078..08f812475f5e 100644 --- a/drivers/s390/char/zcore.c +++ b/drivers/s390/char/zcore.c @@ -4,7 +4,7 @@ * dumps on SCSI disks (zfcpdump). The "zcore/mem" debugfs file shows the same * dump format as s390 standalone dumps. * - * For more information please refer to Documentation/s390/zfcpdump.txt + * For more information please refer to Documentation/s390/zfcpdump.rst * * Copyright IBM Corp. 2003, 2008 * Author(s): Michael Holzheu @@ -51,7 +51,7 @@ static struct dentry *zcore_dir; static struct dentry *zcore_memmap_file; static struct dentry *zcore_reipl_file; static struct dentry *zcore_hsa_file; -static struct ipl_parameter_block *ipl_block; +static struct ipl_parameter_block *zcore_ipl_block; static char hsa_buf[PAGE_SIZE] __aligned(PAGE_SIZE); @@ -182,8 +182,8 @@ static const struct file_operations zcore_memmap_fops = { static ssize_t zcore_reipl_write(struct file *filp, const char __user *buf, size_t count, loff_t *ppos) { - if (ipl_block) { - diag308(DIAG308_SET, ipl_block); + if (zcore_ipl_block) { + diag308(DIAG308_SET, zcore_ipl_block); diag308(DIAG308_LOAD_CLEAR, NULL); } return count; @@ -191,7 +191,7 @@ static ssize_t zcore_reipl_write(struct file *filp, const char __user *buf, static int zcore_reipl_open(struct inode *inode, struct file *filp) { - return nonseekable_open(inode, filp); + return stream_open(inode, filp); } static int zcore_reipl_release(struct inode *inode, struct file *filp) @@ -265,18 +265,20 @@ static int __init zcore_reipl_init(void) return rc; if (ipib_info.ipib == 0) return 0; - ipl_block = (void *) __get_free_page(GFP_KERNEL); - if (!ipl_block) + zcore_ipl_block = (void *) __get_free_page(GFP_KERNEL); + if (!zcore_ipl_block) return -ENOMEM; if (ipib_info.ipib < sclp.hsa_size) - rc = memcpy_hsa_kernel(ipl_block, ipib_info.ipib, PAGE_SIZE); + rc = memcpy_hsa_kernel(zcore_ipl_block, ipib_info.ipib, + PAGE_SIZE); else - rc = memcpy_real(ipl_block, (void *) ipib_info.ipib, PAGE_SIZE); - if (rc || (__force u32)csum_partial(ipl_block, ipl_block->hdr.len, 0) != + rc = memcpy_real(zcore_ipl_block, (void *) ipib_info.ipib, + PAGE_SIZE); + if (rc || (__force u32)csum_partial(zcore_ipl_block, zcore_ipl_block->hdr.len, 0) != ipib_info.checksum) { TRACE("Checksum does not match\n"); - free_page((unsigned long) ipl_block); - ipl_block = NULL; + free_page((unsigned long) zcore_ipl_block); + zcore_ipl_block = NULL; } return 0; } diff --git a/drivers/s390/cio/Makefile b/drivers/s390/cio/Makefile index f230516abb96..f6a8db04177c 100644 --- a/drivers/s390/cio/Makefile +++ b/drivers/s390/cio/Makefile @@ -20,5 +20,6 @@ obj-$(CONFIG_CCWGROUP) += ccwgroup.o qdio-objs := qdio_main.o qdio_thinint.o qdio_debug.o qdio_setup.o obj-$(CONFIG_QDIO) += qdio.o -vfio_ccw-objs += vfio_ccw_drv.o vfio_ccw_cp.o vfio_ccw_ops.o vfio_ccw_fsm.o +vfio_ccw-objs += vfio_ccw_drv.o vfio_ccw_cp.o vfio_ccw_ops.o vfio_ccw_fsm.o \ + vfio_ccw_async.o obj-$(CONFIG_VFIO_CCW) += vfio_ccw.o diff --git a/drivers/s390/cio/airq.c b/drivers/s390/cio/airq.c index a45011e4529e..427b2e24a8ce 100644 --- a/drivers/s390/cio/airq.c +++ b/drivers/s390/cio/airq.c @@ -16,9 +16,11 @@ #include <linux/mutex.h> #include <linux/rculist.h> #include <linux/slab.h> +#include <linux/dmapool.h> #include <asm/airq.h> #include <asm/isc.h> +#include <asm/cio.h> #include "cio.h" #include "cio_debug.h" @@ -27,6 +29,8 @@ static DEFINE_SPINLOCK(airq_lists_lock); static struct hlist_head airq_lists[MAX_ISC+1]; +static struct dma_pool *airq_iv_cache; + /** * register_adapter_interrupt() - register adapter interrupt handler * @airq: pointer to adapter interrupt descriptor @@ -95,7 +99,7 @@ static irqreturn_t do_airq_interrupt(int irq, void *dummy) rcu_read_lock(); hlist_for_each_entry_rcu(airq, head, list) if ((*airq->lsi_ptr & airq->lsi_mask) != 0) - airq->handler(airq); + airq->handler(airq, !tpi_info->directed_irq); rcu_read_unlock(); return IRQ_HANDLED; @@ -113,6 +117,11 @@ void __init init_airq_interrupts(void) setup_irq(THIN_INTERRUPT, &airq_interrupt); } +static inline unsigned long iv_size(unsigned long bits) +{ + return BITS_TO_LONGS(bits) * sizeof(unsigned long); +} + /** * airq_iv_create - create an interrupt vector * @bits: number of bits in the interrupt vector @@ -129,10 +138,23 @@ struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags) if (!iv) goto out; iv->bits = bits; - size = BITS_TO_LONGS(bits) * sizeof(unsigned long); - iv->vector = kzalloc(size, GFP_KERNEL); - if (!iv->vector) - goto out_free; + iv->flags = flags; + size = iv_size(bits); + + if (flags & AIRQ_IV_CACHELINE) { + if ((cache_line_size() * BITS_PER_BYTE) < bits + || !airq_iv_cache) + goto out_free; + + iv->vector = dma_pool_zalloc(airq_iv_cache, GFP_KERNEL, + &iv->vector_dma); + if (!iv->vector) + goto out_free; + } else { + iv->vector = cio_dma_zalloc(size); + if (!iv->vector) + goto out_free; + } if (flags & AIRQ_IV_ALLOC) { iv->avail = kmalloc(size, GFP_KERNEL); if (!iv->avail) @@ -165,7 +187,10 @@ out_free: kfree(iv->ptr); kfree(iv->bitlock); kfree(iv->avail); - kfree(iv->vector); + if (iv->flags & AIRQ_IV_CACHELINE && iv->vector) + dma_pool_free(airq_iv_cache, iv->vector, iv->vector_dma); + else + cio_dma_free(iv->vector, size); kfree(iv); out: return NULL; @@ -181,7 +206,10 @@ void airq_iv_release(struct airq_iv *iv) kfree(iv->data); kfree(iv->ptr); kfree(iv->bitlock); - kfree(iv->vector); + if (iv->flags & AIRQ_IV_CACHELINE) + dma_pool_free(airq_iv_cache, iv->vector, iv->vector_dma); + else + cio_dma_free(iv->vector, iv_size(iv->bits)); kfree(iv->avail); kfree(iv); } @@ -275,3 +303,13 @@ unsigned long airq_iv_scan(struct airq_iv *iv, unsigned long start, return bit; } EXPORT_SYMBOL(airq_iv_scan); + +int __init airq_init(void) +{ + airq_iv_cache = dma_pool_create("airq_iv_cache", cio_get_dma_css_dev(), + cache_line_size(), + cache_line_size(), PAGE_SIZE); + if (!airq_iv_cache) + return -ENOMEM; + return 0; +} diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c index 4ebf6d4fc66c..c522e9313c50 100644 --- a/drivers/s390/cio/ccwgroup.c +++ b/drivers/s390/cio/ccwgroup.c @@ -581,7 +581,7 @@ int ccwgroup_driver_register(struct ccwgroup_driver *cdriver) } EXPORT_SYMBOL(ccwgroup_driver_register); -static int __ccwgroup_match_all(struct device *dev, void *data) +static int __ccwgroup_match_all(struct device *dev, const void *data) { return 1; } @@ -608,9 +608,9 @@ void ccwgroup_driver_unregister(struct ccwgroup_driver *cdriver) } EXPORT_SYMBOL(ccwgroup_driver_unregister); -static int __ccwgroupdev_check_busid(struct device *dev, void *id) +static int __ccwgroupdev_check_busid(struct device *dev, const void *id) { - char *bus_id = id; + const char *bus_id = id; return (strcmp(bus_id, dev_name(dev)) == 0); } diff --git a/drivers/s390/cio/ccwreq.c b/drivers/s390/cio/ccwreq.c index 603268a33ea1..73582a0a2622 100644 --- a/drivers/s390/cio/ccwreq.c +++ b/drivers/s390/cio/ccwreq.c @@ -63,7 +63,7 @@ static void ccwreq_stop(struct ccw_device *cdev, int rc) return; req->done = 1; ccw_device_set_timeout(cdev, 0); - memset(&cdev->private->irb, 0, sizeof(struct irb)); + memset(&cdev->private->dma_area->irb, 0, sizeof(struct irb)); if (rc && rc != -ENODEV && req->drc) rc = req->drc; req->callback(cdev, req->data, rc); @@ -86,7 +86,7 @@ static void ccwreq_do(struct ccw_device *cdev) continue; } /* Perform start function. */ - memset(&cdev->private->irb, 0, sizeof(struct irb)); + memset(&cdev->private->dma_area->irb, 0, sizeof(struct irb)); rc = cio_start(sch, cp, (u8) req->mask); if (rc == 0) { /* I/O started successfully. */ @@ -169,7 +169,7 @@ int ccw_request_cancel(struct ccw_device *cdev) */ static enum io_status ccwreq_status(struct ccw_device *cdev, struct irb *lcirb) { - struct irb *irb = &cdev->private->irb; + struct irb *irb = &cdev->private->dma_area->irb; struct cmd_scsw *scsw = &irb->scsw.cmd; enum uc_todo todo; @@ -187,7 +187,8 @@ static enum io_status ccwreq_status(struct ccw_device *cdev, struct irb *lcirb) CIO_TRACE_EVENT(2, "sensedata"); CIO_HEX_EVENT(2, &cdev->private->dev_id, sizeof(struct ccw_dev_id)); - CIO_HEX_EVENT(2, &cdev->private->irb.ecw, SENSE_MAX_COUNT); + CIO_HEX_EVENT(2, &cdev->private->dma_area->irb.ecw, + SENSE_MAX_COUNT); /* Check for command reject. */ if (irb->ecw[0] & SNS0_CMD_REJECT) return IO_REJECTED; diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c index a835b31aad99..6392a1b95b02 100644 --- a/drivers/s390/cio/chsc.c +++ b/drivers/s390/cio/chsc.c @@ -323,36 +323,6 @@ struct chsc_sei { } __packed __aligned(PAGE_SIZE); /* - * Node Descriptor as defined in SA22-7204, "Common I/O-Device Commands" - */ - -#define ND_VALIDITY_VALID 0 -#define ND_VALIDITY_OUTDATED 1 -#define ND_VALIDITY_INVALID 2 - -struct node_descriptor { - /* Flags. */ - union { - struct { - u32 validity:3; - u32 reserved:5; - } __packed; - u8 byte0; - } __packed; - - /* Node parameters. */ - u32 params:24; - - /* Node ID. */ - char type[6]; - char model[3]; - char manufacturer[3]; - char plant[2]; - char seq[12]; - u16 tag; -} __packed; - -/* * Link Incident Record as defined in SA22-7202, "ESCON I/O Interface" */ diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c index 8d9f36625ba5..8f080d3fd380 100644 --- a/drivers/s390/cio/chsc_sch.c +++ b/drivers/s390/cio/chsc_sch.c @@ -203,7 +203,7 @@ static void chsc_cleanup_sch_driver(void) static DEFINE_SPINLOCK(chsc_lock); -static int chsc_subchannel_match_next_free(struct device *dev, void *data) +static int chsc_subchannel_match_next_free(struct device *dev, const void *data) { struct subchannel *sch = to_subchannel(dev); diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c index de744ca158fd..18f5458f90e8 100644 --- a/drivers/s390/cio/cio.c +++ b/drivers/s390/cio/cio.c @@ -564,7 +564,7 @@ static irqreturn_t do_cio_interrupt(int irq, void *dummy) } static struct irqaction io_interrupt = { - .name = "IO", + .name = "I/O", .handler = do_cio_interrupt, }; diff --git a/drivers/s390/cio/cio.h b/drivers/s390/cio/cio.h index 9811fd8a0c73..ba7d2480613b 100644 --- a/drivers/s390/cio/cio.h +++ b/drivers/s390/cio/cio.h @@ -51,7 +51,7 @@ struct tpi_info { struct subchannel_id schid; u32 intparm; u32 adapter_IO:1; - u32 :1; + u32 directed_irq:1; u32 isc:3; u32 :27; u32 type:3; @@ -113,9 +113,10 @@ struct subchannel { enum sch_todo todo; struct work_struct todo_work; struct schib_config config; + char *driver_override; /* Driver name to force a match */ } __attribute__ ((aligned(8))); -DECLARE_PER_CPU(struct irb, cio_irb); +DECLARE_PER_CPU_ALIGNED(struct irb, cio_irb); #define to_subchannel(n) container_of(n, struct subchannel, dev) @@ -135,6 +136,8 @@ extern int cio_commit_config(struct subchannel *sch); int cio_tm_start_key(struct subchannel *sch, struct tcw *tcw, u8 lpm, u8 key); int cio_tm_intrg(struct subchannel *sch); +extern int __init airq_init(void); + /* Use with care. */ #ifdef CONFIG_CCW_CONSOLE extern struct subchannel *cio_probe_console(void); diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index aea502922646..22c55816100b 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -20,6 +20,8 @@ #include <linux/reboot.h> #include <linux/suspend.h> #include <linux/proc_fs.h> +#include <linux/genalloc.h> +#include <linux/dma-mapping.h> #include <asm/isc.h> #include <asm/crw.h> @@ -165,6 +167,7 @@ static void css_subchannel_release(struct device *dev) sch->config.intparm = 0; cio_commit_config(sch); + kfree(sch->driver_override); kfree(sch->lock); kfree(sch); } @@ -224,6 +227,12 @@ struct subchannel *css_alloc_subchannel(struct subchannel_id schid, INIT_WORK(&sch->todo_work, css_sch_todo); sch->dev.release = &css_subchannel_release; device_initialize(&sch->dev); + /* + * The physical addresses of some the dma structures that can + * belong to a subchannel need to fit 31 bit width (e.g. ccw). + */ + sch->dev.coherent_dma_mask = DMA_BIT_MASK(31); + sch->dev.dma_mask = &sch->dev.coherent_dma_mask; return sch; err: @@ -315,9 +324,57 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, static DEVICE_ATTR_RO(modalias); +static ssize_t driver_override_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct subchannel *sch = to_subchannel(dev); + char *driver_override, *old, *cp; + + /* We need to keep extra room for a newline */ + if (count >= (PAGE_SIZE - 1)) + return -EINVAL; + + driver_override = kstrndup(buf, count, GFP_KERNEL); + if (!driver_override) + return -ENOMEM; + + cp = strchr(driver_override, '\n'); + if (cp) + *cp = '\0'; + + device_lock(dev); + old = sch->driver_override; + if (strlen(driver_override)) { + sch->driver_override = driver_override; + } else { + kfree(driver_override); + sch->driver_override = NULL; + } + device_unlock(dev); + + kfree(old); + + return count; +} + +static ssize_t driver_override_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct subchannel *sch = to_subchannel(dev); + ssize_t len; + + device_lock(dev); + len = snprintf(buf, PAGE_SIZE, "%s\n", sch->driver_override); + device_unlock(dev); + return len; +} +static DEVICE_ATTR_RW(driver_override); + static struct attribute *subch_attrs[] = { &dev_attr_type.attr, &dev_attr_modalias.attr, + &dev_attr_driver_override.attr, NULL, }; @@ -434,10 +491,10 @@ static int css_probe_device(struct subchannel_id schid, struct schib *schib) } static int -check_subchannel(struct device * dev, void * data) +check_subchannel(struct device *dev, const void *data) { struct subchannel *sch; - struct subchannel_id *schid = data; + struct subchannel_id *schid = (void *)data; sch = to_subchannel(dev); return schid_equal(&sch->schid, schid); @@ -899,6 +956,13 @@ static int __init setup_css(int nr) dev_set_name(&css->device, "css%x", nr); css->device.groups = cssdev_attr_groups; css->device.release = channel_subsystem_release; + /* + * We currently allocate notifier bits with this (using + * css->device as the device argument with the DMA API) + * and are fine with 64 bit addresses. + */ + css->device.coherent_dma_mask = DMA_BIT_MASK(64); + css->device.dma_mask = &css->device.coherent_dma_mask; mutex_init(&css->mutex); css->cssid = chsc_get_cssid(nr); @@ -1018,6 +1082,111 @@ static struct notifier_block css_power_notifier = { .notifier_call = css_power_event, }; +#define CIO_DMA_GFP (GFP_KERNEL | __GFP_ZERO) +static struct gen_pool *cio_dma_pool; + +/* Currently cio supports only a single css */ +struct device *cio_get_dma_css_dev(void) +{ + return &channel_subsystems[0]->device; +} + +struct gen_pool *cio_gp_dma_create(struct device *dma_dev, int nr_pages) +{ + struct gen_pool *gp_dma; + void *cpu_addr; + dma_addr_t dma_addr; + int i; + + gp_dma = gen_pool_create(3, -1); + if (!gp_dma) + return NULL; + for (i = 0; i < nr_pages; ++i) { + cpu_addr = dma_alloc_coherent(dma_dev, PAGE_SIZE, &dma_addr, + CIO_DMA_GFP); + if (!cpu_addr) + return gp_dma; + gen_pool_add_virt(gp_dma, (unsigned long) cpu_addr, + dma_addr, PAGE_SIZE, -1); + } + return gp_dma; +} + +static void __gp_dma_free_dma(struct gen_pool *pool, + struct gen_pool_chunk *chunk, void *data) +{ + size_t chunk_size = chunk->end_addr - chunk->start_addr + 1; + + dma_free_coherent((struct device *) data, chunk_size, + (void *) chunk->start_addr, + (dma_addr_t) chunk->phys_addr); +} + +void cio_gp_dma_destroy(struct gen_pool *gp_dma, struct device *dma_dev) +{ + if (!gp_dma) + return; + /* this is quite ugly but no better idea */ + gen_pool_for_each_chunk(gp_dma, __gp_dma_free_dma, dma_dev); + gen_pool_destroy(gp_dma); +} + +static int cio_dma_pool_init(void) +{ + /* No need to free up the resources: compiled in */ + cio_dma_pool = cio_gp_dma_create(cio_get_dma_css_dev(), 1); + if (!cio_dma_pool) + return -ENOMEM; + return 0; +} + +void *cio_gp_dma_zalloc(struct gen_pool *gp_dma, struct device *dma_dev, + size_t size) +{ + dma_addr_t dma_addr; + unsigned long addr; + size_t chunk_size; + + if (!gp_dma) + return NULL; + addr = gen_pool_alloc(gp_dma, size); + while (!addr) { + chunk_size = round_up(size, PAGE_SIZE); + addr = (unsigned long) dma_alloc_coherent(dma_dev, + chunk_size, &dma_addr, CIO_DMA_GFP); + if (!addr) + return NULL; + gen_pool_add_virt(gp_dma, addr, dma_addr, chunk_size, -1); + addr = gen_pool_alloc(gp_dma, size); + } + return (void *) addr; +} + +void cio_gp_dma_free(struct gen_pool *gp_dma, void *cpu_addr, size_t size) +{ + if (!cpu_addr) + return; + memset(cpu_addr, 0, size); + gen_pool_free(gp_dma, (unsigned long) cpu_addr, size); +} + +/* + * Allocate dma memory from the css global pool. Intended for memory not + * specific to any single device within the css. The allocated memory + * is not guaranteed to be 31-bit addressable. + * + * Caution: Not suitable for early stuff like console. + */ +void *cio_dma_zalloc(size_t size) +{ + return cio_gp_dma_zalloc(cio_dma_pool, cio_get_dma_css_dev(), size); +} + +void cio_dma_free(void *cpu_addr, size_t size) +{ + cio_gp_dma_free(cio_dma_pool, cpu_addr, size); +} + /* * Now that the driver core is running, we can setup our channel subsystem. * The struct subchannel's are created during probing. @@ -1059,16 +1228,22 @@ static int __init css_bus_init(void) if (ret) goto out_unregister; ret = register_pm_notifier(&css_power_notifier); - if (ret) { - unregister_reboot_notifier(&css_reboot_notifier); - goto out_unregister; - } + if (ret) + goto out_unregister_rn; + ret = cio_dma_pool_init(); + if (ret) + goto out_unregister_pmn; + airq_init(); css_init_done = 1; /* Enable default isc for I/O subchannels. */ isc_register(IO_SCH_ISC); return 0; +out_unregister_pmn: + unregister_pm_notifier(&css_power_notifier); +out_unregister_rn: + unregister_reboot_notifier(&css_reboot_notifier); out_unregister: while (i-- > 0) { struct channel_subsystem *css = channel_subsystems[i]; @@ -1222,6 +1397,10 @@ static int css_bus_match(struct device *dev, struct device_driver *drv) struct css_driver *driver = to_cssdriver(drv); struct css_device_id *id; + /* When driver_override is set, only bind to the matching driver */ + if (sch->driver_override && strcmp(sch->driver_override, drv->name)) + return 0; + for (id = driver->subchannel_type; id->match_flags; id++) { if (sch->st == id->type) return 1; diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index 1540229a37bb..c421899be20f 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -24,6 +24,7 @@ #include <linux/timer.h> #include <linux/kernel_stat.h> #include <linux/sched/signal.h> +#include <linux/dma-mapping.h> #include <asm/ccwdev.h> #include <asm/cio.h> @@ -642,10 +643,10 @@ static int ccw_device_add(struct ccw_device *cdev) return device_add(dev); } -static int match_dev_id(struct device *dev, void *data) +static int match_dev_id(struct device *dev, const void *data) { struct ccw_device *cdev = to_ccwdev(dev); - struct ccw_dev_id *dev_id = data; + struct ccw_dev_id *dev_id = (void *)data; return ccw_dev_id_is_equal(&cdev->private->dev_id, dev_id); } @@ -687,6 +688,9 @@ ccw_device_release(struct device *dev) struct ccw_device *cdev; cdev = to_ccwdev(dev); + cio_gp_dma_free(cdev->private->dma_pool, cdev->private->dma_area, + sizeof(*cdev->private->dma_area)); + cio_gp_dma_destroy(cdev->private->dma_pool, &cdev->dev); /* Release reference of parent subchannel. */ put_device(cdev->dev.parent); kfree(cdev->private); @@ -696,15 +700,33 @@ ccw_device_release(struct device *dev) static struct ccw_device * io_subchannel_allocate_dev(struct subchannel *sch) { struct ccw_device *cdev; + struct gen_pool *dma_pool; cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); - if (cdev) { - cdev->private = kzalloc(sizeof(struct ccw_device_private), - GFP_KERNEL | GFP_DMA); - if (cdev->private) - return cdev; - } + if (!cdev) + goto err_cdev; + cdev->private = kzalloc(sizeof(struct ccw_device_private), + GFP_KERNEL | GFP_DMA); + if (!cdev->private) + goto err_priv; + cdev->dev.coherent_dma_mask = sch->dev.coherent_dma_mask; + cdev->dev.dma_mask = &cdev->dev.coherent_dma_mask; + dma_pool = cio_gp_dma_create(&cdev->dev, 1); + if (!dma_pool) + goto err_dma_pool; + cdev->private->dma_pool = dma_pool; + cdev->private->dma_area = cio_gp_dma_zalloc(dma_pool, &cdev->dev, + sizeof(*cdev->private->dma_area)); + if (!cdev->private->dma_area) + goto err_dma_area; + return cdev; +err_dma_area: + cio_gp_dma_destroy(dma_pool, &cdev->dev); +err_dma_pool: + kfree(cdev->private); +err_priv: kfree(cdev); +err_cdev: return ERR_PTR(-ENOMEM); } @@ -884,7 +906,7 @@ io_subchannel_recog_done(struct ccw_device *cdev) wake_up(&ccw_device_init_wq); break; case DEV_STATE_OFFLINE: - /* + /* * We can't register the device in interrupt context so * we schedule a work item. */ @@ -1062,6 +1084,14 @@ static int io_subchannel_probe(struct subchannel *sch) if (!io_priv) goto out_schedule; + io_priv->dma_area = dma_alloc_coherent(&sch->dev, + sizeof(*io_priv->dma_area), + &io_priv->dma_area_dma, GFP_KERNEL); + if (!io_priv->dma_area) { + kfree(io_priv); + goto out_schedule; + } + set_io_private(sch, io_priv); css_schedule_eval(sch->schid); return 0; @@ -1088,6 +1118,8 @@ static int io_subchannel_remove(struct subchannel *sch) set_io_private(sch, NULL); spin_unlock_irq(sch->lock); out_free: + dma_free_coherent(&sch->dev, sizeof(*io_priv->dma_area), + io_priv->dma_area, io_priv->dma_area_dma); kfree(io_priv); sysfs_remove_group(&sch->dev.kobj, &io_subchannel_attr_group); return 0; @@ -1593,13 +1625,19 @@ struct ccw_device * __init ccw_device_create_console(struct ccw_driver *drv) return ERR_CAST(sch); io_priv = kzalloc(sizeof(*io_priv), GFP_KERNEL | GFP_DMA); - if (!io_priv) { - put_device(&sch->dev); - return ERR_PTR(-ENOMEM); - } + if (!io_priv) + goto err_priv; + io_priv->dma_area = dma_alloc_coherent(&sch->dev, + sizeof(*io_priv->dma_area), + &io_priv->dma_area_dma, GFP_KERNEL); + if (!io_priv->dma_area) + goto err_dma_area; set_io_private(sch, io_priv); cdev = io_subchannel_create_ccwdev(sch); if (IS_ERR(cdev)) { + dma_free_coherent(&sch->dev, sizeof(*io_priv->dma_area), + io_priv->dma_area, io_priv->dma_area_dma); + set_io_private(sch, NULL); put_device(&sch->dev); kfree(io_priv); return cdev; @@ -1607,6 +1645,12 @@ struct ccw_device * __init ccw_device_create_console(struct ccw_driver *drv) cdev->drv = drv; ccw_device_set_int_class(cdev); return cdev; + +err_dma_area: + kfree(io_priv); +err_priv: + put_device(&sch->dev); + return ERR_PTR(-ENOMEM); } void __init ccw_device_destroy_console(struct ccw_device *cdev) @@ -1617,6 +1661,8 @@ void __init ccw_device_destroy_console(struct ccw_device *cdev) set_io_private(sch, NULL); put_device(&sch->dev); put_device(&cdev->dev); + dma_free_coherent(&sch->dev, sizeof(*io_priv->dma_area), + io_priv->dma_area, io_priv->dma_area_dma); kfree(io_priv); } @@ -1653,11 +1699,9 @@ EXPORT_SYMBOL_GPL(ccw_device_force_console); * get ccw_device matching the busid, but only if owned by cdrv */ static int -__ccwdev_check_busid(struct device *dev, void *id) +__ccwdev_check_busid(struct device *dev, const void *id) { - char *bus_id; - - bus_id = id; + const char *bus_id = id; return (strcmp(bus_id, dev_name(dev)) == 0); } diff --git a/drivers/s390/cio/device_fsm.c b/drivers/s390/cio/device_fsm.c index 9169af7dbb43..8fc267324ebb 100644 --- a/drivers/s390/cio/device_fsm.c +++ b/drivers/s390/cio/device_fsm.c @@ -67,8 +67,10 @@ static void ccw_timeout_log(struct ccw_device *cdev) sizeof(struct tcw), 0); } else { printk(KERN_WARNING "cio: orb indicates command mode\n"); - if ((void *)(addr_t)orb->cmd.cpa == &private->sense_ccw || - (void *)(addr_t)orb->cmd.cpa == cdev->private->iccws) + if ((void *)(addr_t)orb->cmd.cpa == + &private->dma_area->sense_ccw || + (void *)(addr_t)orb->cmd.cpa == + cdev->private->dma_area->iccws) printk(KERN_WARNING "cio: last channel program " "(intern):\n"); else @@ -143,18 +145,22 @@ ccw_device_cancel_halt_clear(struct ccw_device *cdev) void ccw_device_update_sense_data(struct ccw_device *cdev) { memset(&cdev->id, 0, sizeof(cdev->id)); - cdev->id.cu_type = cdev->private->senseid.cu_type; - cdev->id.cu_model = cdev->private->senseid.cu_model; - cdev->id.dev_type = cdev->private->senseid.dev_type; - cdev->id.dev_model = cdev->private->senseid.dev_model; + cdev->id.cu_type = cdev->private->dma_area->senseid.cu_type; + cdev->id.cu_model = cdev->private->dma_area->senseid.cu_model; + cdev->id.dev_type = cdev->private->dma_area->senseid.dev_type; + cdev->id.dev_model = cdev->private->dma_area->senseid.dev_model; } int ccw_device_test_sense_data(struct ccw_device *cdev) { - return cdev->id.cu_type == cdev->private->senseid.cu_type && - cdev->id.cu_model == cdev->private->senseid.cu_model && - cdev->id.dev_type == cdev->private->senseid.dev_type && - cdev->id.dev_model == cdev->private->senseid.dev_model; + return cdev->id.cu_type == + cdev->private->dma_area->senseid.cu_type && + cdev->id.cu_model == + cdev->private->dma_area->senseid.cu_model && + cdev->id.dev_type == + cdev->private->dma_area->senseid.dev_type && + cdev->id.dev_model == + cdev->private->dma_area->senseid.dev_model; } /* @@ -342,7 +348,7 @@ ccw_device_done(struct ccw_device *cdev, int state) cio_disable_subchannel(sch); /* Reset device status. */ - memset(&cdev->private->irb, 0, sizeof(struct irb)); + memset(&cdev->private->dma_area->irb, 0, sizeof(struct irb)); cdev->private->state = state; @@ -509,13 +515,14 @@ callback: ccw_device_done(cdev, DEV_STATE_ONLINE); /* Deliver fake irb to device driver, if needed. */ if (cdev->private->flags.fake_irb) { - create_fake_irb(&cdev->private->irb, + create_fake_irb(&cdev->private->dma_area->irb, cdev->private->flags.fake_irb); cdev->private->flags.fake_irb = 0; if (cdev->handler) cdev->handler(cdev, cdev->private->intparm, - &cdev->private->irb); - memset(&cdev->private->irb, 0, sizeof(struct irb)); + &cdev->private->dma_area->irb); + memset(&cdev->private->dma_area->irb, 0, + sizeof(struct irb)); } ccw_device_report_path_events(cdev); ccw_device_handle_broken_paths(cdev); @@ -672,7 +679,8 @@ ccw_device_online_verify(struct ccw_device *cdev, enum dev_event dev_event) if (scsw_actl(&sch->schib.scsw) != 0 || (scsw_stctl(&sch->schib.scsw) & SCSW_STCTL_STATUS_PEND) || - (scsw_stctl(&cdev->private->irb.scsw) & SCSW_STCTL_STATUS_PEND)) { + (scsw_stctl(&cdev->private->dma_area->irb.scsw) & + SCSW_STCTL_STATUS_PEND)) { /* * No final status yet or final status not yet delivered * to the device driver. Can't do path verification now, @@ -719,7 +727,7 @@ static int ccw_device_call_handler(struct ccw_device *cdev) * - fast notification was requested (primary status) * - unsolicited interrupts */ - stctl = scsw_stctl(&cdev->private->irb.scsw); + stctl = scsw_stctl(&cdev->private->dma_area->irb.scsw); ending_status = (stctl & SCSW_STCTL_SEC_STATUS) || (stctl == (SCSW_STCTL_ALERT_STATUS | SCSW_STCTL_STATUS_PEND)) || (stctl == SCSW_STCTL_STATUS_PEND); @@ -735,9 +743,9 @@ static int ccw_device_call_handler(struct ccw_device *cdev) if (cdev->handler) cdev->handler(cdev, cdev->private->intparm, - &cdev->private->irb); + &cdev->private->dma_area->irb); - memset(&cdev->private->irb, 0, sizeof(struct irb)); + memset(&cdev->private->dma_area->irb, 0, sizeof(struct irb)); return 1; } @@ -759,7 +767,8 @@ ccw_device_irq(struct ccw_device *cdev, enum dev_event dev_event) /* Unit check but no sense data. Need basic sense. */ if (ccw_device_do_sense(cdev, irb) != 0) goto call_handler_unsol; - memcpy(&cdev->private->irb, irb, sizeof(struct irb)); + memcpy(&cdev->private->dma_area->irb, irb, + sizeof(struct irb)); cdev->private->state = DEV_STATE_W4SENSE; cdev->private->intparm = 0; return; @@ -842,7 +851,7 @@ ccw_device_w4sense(struct ccw_device *cdev, enum dev_event dev_event) if (scsw_fctl(&irb->scsw) & (SCSW_FCTL_CLEAR_FUNC | SCSW_FCTL_HALT_FUNC)) { cdev->private->flags.dosense = 0; - memset(&cdev->private->irb, 0, sizeof(struct irb)); + memset(&cdev->private->dma_area->irb, 0, sizeof(struct irb)); ccw_device_accumulate_irb(cdev, irb); goto call_handler; } diff --git a/drivers/s390/cio/device_id.c b/drivers/s390/cio/device_id.c index f6df83a9dfbb..740996d0dc8c 100644 --- a/drivers/s390/cio/device_id.c +++ b/drivers/s390/cio/device_id.c @@ -99,7 +99,7 @@ static int diag210_to_senseid(struct senseid *senseid, struct diag210 *diag) static int diag210_get_dev_info(struct ccw_device *cdev) { struct ccw_dev_id *dev_id = &cdev->private->dev_id; - struct senseid *senseid = &cdev->private->senseid; + struct senseid *senseid = &cdev->private->dma_area->senseid; struct diag210 diag_data; int rc; @@ -134,8 +134,10 @@ err_failed: static void snsid_init(struct ccw_device *cdev) { cdev->private->flags.esid = 0; - memset(&cdev->private->senseid, 0, sizeof(cdev->private->senseid)); - cdev->private->senseid.cu_type = 0xffff; + + memset(&cdev->private->dma_area->senseid, 0, + sizeof(cdev->private->dma_area->senseid)); + cdev->private->dma_area->senseid.cu_type = 0xffff; } /* @@ -143,16 +145,16 @@ static void snsid_init(struct ccw_device *cdev) */ static int snsid_check(struct ccw_device *cdev, void *data) { - struct cmd_scsw *scsw = &cdev->private->irb.scsw.cmd; + struct cmd_scsw *scsw = &cdev->private->dma_area->irb.scsw.cmd; int len = sizeof(struct senseid) - scsw->count; /* Check for incomplete SENSE ID data. */ if (len < SENSE_ID_MIN_LEN) goto out_restart; - if (cdev->private->senseid.cu_type == 0xffff) + if (cdev->private->dma_area->senseid.cu_type == 0xffff) goto out_restart; /* Check for incompatible SENSE ID data. */ - if (cdev->private->senseid.reserved != 0xff) + if (cdev->private->dma_area->senseid.reserved != 0xff) return -EOPNOTSUPP; /* Check for extended-identification information. */ if (len > SENSE_ID_BASIC_LEN) @@ -170,7 +172,7 @@ out_restart: static void snsid_callback(struct ccw_device *cdev, void *data, int rc) { struct ccw_dev_id *id = &cdev->private->dev_id; - struct senseid *senseid = &cdev->private->senseid; + struct senseid *senseid = &cdev->private->dma_area->senseid; int vm = 0; if (rc && MACHINE_IS_VM) { @@ -200,7 +202,7 @@ void ccw_device_sense_id_start(struct ccw_device *cdev) { struct subchannel *sch = to_subchannel(cdev->dev.parent); struct ccw_request *req = &cdev->private->req; - struct ccw1 *cp = cdev->private->iccws; + struct ccw1 *cp = cdev->private->dma_area->iccws; CIO_TRACE_EVENT(4, "snsid"); CIO_HEX_EVENT(4, &cdev->private->dev_id, sizeof(cdev->private->dev_id)); @@ -208,7 +210,7 @@ void ccw_device_sense_id_start(struct ccw_device *cdev) snsid_init(cdev); /* Channel program setup. */ cp->cmd_code = CCW_CMD_SENSE_ID; - cp->cda = (u32) (addr_t) &cdev->private->senseid; + cp->cda = (u32) (addr_t) &cdev->private->dma_area->senseid; cp->count = sizeof(struct senseid); cp->flags = CCW_FLAG_SLI; /* Request setup. */ diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c index 4435ae0b3027..d722458c5928 100644 --- a/drivers/s390/cio/device_ops.c +++ b/drivers/s390/cio/device_ops.c @@ -429,8 +429,8 @@ struct ciw *ccw_device_get_ciw(struct ccw_device *cdev, __u32 ct) if (cdev->private->flags.esid == 0) return NULL; for (ciw_cnt = 0; ciw_cnt < MAX_CIWS; ciw_cnt++) - if (cdev->private->senseid.ciw[ciw_cnt].ct == ct) - return cdev->private->senseid.ciw + ciw_cnt; + if (cdev->private->dma_area->senseid.ciw[ciw_cnt].ct == ct) + return cdev->private->dma_area->senseid.ciw + ciw_cnt; return NULL; } @@ -699,6 +699,23 @@ void ccw_device_get_schid(struct ccw_device *cdev, struct subchannel_id *schid) } EXPORT_SYMBOL_GPL(ccw_device_get_schid); +/* + * Allocate zeroed dma coherent 31 bit addressable memory using + * the subchannels dma pool. Maximal size of allocation supported + * is PAGE_SIZE. + */ +void *ccw_device_dma_zalloc(struct ccw_device *cdev, size_t size) +{ + return cio_gp_dma_zalloc(cdev->private->dma_pool, &cdev->dev, size); +} +EXPORT_SYMBOL(ccw_device_dma_zalloc); + +void ccw_device_dma_free(struct ccw_device *cdev, void *cpu_addr, size_t size) +{ + cio_gp_dma_free(cdev->private->dma_pool, cpu_addr, size); +} +EXPORT_SYMBOL(ccw_device_dma_free); + EXPORT_SYMBOL(ccw_device_set_options_mask); EXPORT_SYMBOL(ccw_device_set_options); EXPORT_SYMBOL(ccw_device_clear_options); diff --git a/drivers/s390/cio/device_pgid.c b/drivers/s390/cio/device_pgid.c index d30a3babf176..767a85635a0f 100644 --- a/drivers/s390/cio/device_pgid.c +++ b/drivers/s390/cio/device_pgid.c @@ -57,7 +57,7 @@ out: static void nop_build_cp(struct ccw_device *cdev) { struct ccw_request *req = &cdev->private->req; - struct ccw1 *cp = cdev->private->iccws; + struct ccw1 *cp = cdev->private->dma_area->iccws; cp->cmd_code = CCW_CMD_NOOP; cp->cda = 0; @@ -134,9 +134,9 @@ err: static void spid_build_cp(struct ccw_device *cdev, u8 fn) { struct ccw_request *req = &cdev->private->req; - struct ccw1 *cp = cdev->private->iccws; + struct ccw1 *cp = cdev->private->dma_area->iccws; int i = pathmask_to_pos(req->lpm); - struct pgid *pgid = &cdev->private->pgid[i]; + struct pgid *pgid = &cdev->private->dma_area->pgid[i]; pgid->inf.fc = fn; cp->cmd_code = CCW_CMD_SET_PGID; @@ -300,7 +300,7 @@ static int pgid_cmp(struct pgid *p1, struct pgid *p2) static void pgid_analyze(struct ccw_device *cdev, struct pgid **p, int *mismatch, u8 *reserved, u8 *reset) { - struct pgid *pgid = &cdev->private->pgid[0]; + struct pgid *pgid = &cdev->private->dma_area->pgid[0]; struct pgid *first = NULL; int lpm; int i; @@ -342,7 +342,7 @@ static u8 pgid_to_donepm(struct ccw_device *cdev) lpm = 0x80 >> i; if ((cdev->private->pgid_valid_mask & lpm) == 0) continue; - pgid = &cdev->private->pgid[i]; + pgid = &cdev->private->dma_area->pgid[i]; if (sch->opm & lpm) { if (pgid->inf.ps.state1 != SNID_STATE1_GROUPED) continue; @@ -368,7 +368,8 @@ static void pgid_fill(struct ccw_device *cdev, struct pgid *pgid) int i; for (i = 0; i < 8; i++) - memcpy(&cdev->private->pgid[i], pgid, sizeof(struct pgid)); + memcpy(&cdev->private->dma_area->pgid[i], pgid, + sizeof(struct pgid)); } /* @@ -435,12 +436,12 @@ out: static void snid_build_cp(struct ccw_device *cdev) { struct ccw_request *req = &cdev->private->req; - struct ccw1 *cp = cdev->private->iccws; + struct ccw1 *cp = cdev->private->dma_area->iccws; int i = pathmask_to_pos(req->lpm); /* Channel program setup. */ cp->cmd_code = CCW_CMD_SENSE_PGID; - cp->cda = (u32) (addr_t) &cdev->private->pgid[i]; + cp->cda = (u32) (addr_t) &cdev->private->dma_area->pgid[i]; cp->count = sizeof(struct pgid); cp->flags = CCW_FLAG_SLI; req->cp = cp; @@ -516,7 +517,8 @@ static void verify_start(struct ccw_device *cdev) sch->lpm = sch->schib.pmcw.pam; /* Initialize PGID data. */ - memset(cdev->private->pgid, 0, sizeof(cdev->private->pgid)); + memset(cdev->private->dma_area->pgid, 0, + sizeof(cdev->private->dma_area->pgid)); cdev->private->pgid_valid_mask = 0; cdev->private->pgid_todo_mask = sch->schib.pmcw.pam; cdev->private->path_notoper_mask = 0; @@ -626,7 +628,7 @@ struct stlck_data { static void stlck_build_cp(struct ccw_device *cdev, void *buf1, void *buf2) { struct ccw_request *req = &cdev->private->req; - struct ccw1 *cp = cdev->private->iccws; + struct ccw1 *cp = cdev->private->dma_area->iccws; cp[0].cmd_code = CCW_CMD_STLCK; cp[0].cda = (u32) (addr_t) buf1; diff --git a/drivers/s390/cio/device_status.c b/drivers/s390/cio/device_status.c index 7d5c7892b2c4..0bd8f2642732 100644 --- a/drivers/s390/cio/device_status.c +++ b/drivers/s390/cio/device_status.c @@ -79,15 +79,15 @@ ccw_device_accumulate_ecw(struct ccw_device *cdev, struct irb *irb) * are condition that have to be met for the extended control * bit to have meaning. Sick. */ - cdev->private->irb.scsw.cmd.ectl = 0; + cdev->private->dma_area->irb.scsw.cmd.ectl = 0; if ((irb->scsw.cmd.stctl & SCSW_STCTL_ALERT_STATUS) && !(irb->scsw.cmd.stctl & SCSW_STCTL_INTER_STATUS)) - cdev->private->irb.scsw.cmd.ectl = irb->scsw.cmd.ectl; + cdev->private->dma_area->irb.scsw.cmd.ectl = irb->scsw.cmd.ectl; /* Check if extended control word is valid. */ - if (!cdev->private->irb.scsw.cmd.ectl) + if (!cdev->private->dma_area->irb.scsw.cmd.ectl) return; /* Copy concurrent sense / model dependent information. */ - memcpy (&cdev->private->irb.ecw, irb->ecw, sizeof (irb->ecw)); + memcpy(&cdev->private->dma_area->irb.ecw, irb->ecw, sizeof(irb->ecw)); } /* @@ -118,7 +118,7 @@ ccw_device_accumulate_esw(struct ccw_device *cdev, struct irb *irb) if (!ccw_device_accumulate_esw_valid(irb)) return; - cdev_irb = &cdev->private->irb; + cdev_irb = &cdev->private->dma_area->irb; /* Copy last path used mask. */ cdev_irb->esw.esw1.lpum = irb->esw.esw1.lpum; @@ -210,7 +210,7 @@ ccw_device_accumulate_irb(struct ccw_device *cdev, struct irb *irb) ccw_device_path_notoper(cdev); /* No irb accumulation for transport mode irbs. */ if (scsw_is_tm(&irb->scsw)) { - memcpy(&cdev->private->irb, irb, sizeof(struct irb)); + memcpy(&cdev->private->dma_area->irb, irb, sizeof(struct irb)); return; } /* @@ -219,7 +219,7 @@ ccw_device_accumulate_irb(struct ccw_device *cdev, struct irb *irb) if (!scsw_is_solicited(&irb->scsw)) return; - cdev_irb = &cdev->private->irb; + cdev_irb = &cdev->private->dma_area->irb; /* * If the clear function had been performed, all formerly pending @@ -227,7 +227,7 @@ ccw_device_accumulate_irb(struct ccw_device *cdev, struct irb *irb) * intermediate accumulated status to the device driver. */ if (irb->scsw.cmd.fctl & SCSW_FCTL_CLEAR_FUNC) - memset(&cdev->private->irb, 0, sizeof(struct irb)); + memset(&cdev->private->dma_area->irb, 0, sizeof(struct irb)); /* Copy bits which are valid only for the start function. */ if (irb->scsw.cmd.fctl & SCSW_FCTL_START_FUNC) { @@ -329,9 +329,9 @@ ccw_device_do_sense(struct ccw_device *cdev, struct irb *irb) /* * We have ending status but no sense information. Do a basic sense. */ - sense_ccw = &to_io_private(sch)->sense_ccw; + sense_ccw = &to_io_private(sch)->dma_area->sense_ccw; sense_ccw->cmd_code = CCW_CMD_BASIC_SENSE; - sense_ccw->cda = (__u32) __pa(cdev->private->irb.ecw); + sense_ccw->cda = (__u32) __pa(cdev->private->dma_area->irb.ecw); sense_ccw->count = SENSE_MAX_COUNT; sense_ccw->flags = CCW_FLAG_SLI; @@ -364,7 +364,7 @@ ccw_device_accumulate_basic_sense(struct ccw_device *cdev, struct irb *irb) if (!(irb->scsw.cmd.dstat & DEV_STAT_UNIT_CHECK) && (irb->scsw.cmd.dstat & DEV_STAT_CHN_END)) { - cdev->private->irb.esw.esw0.erw.cons = 1; + cdev->private->dma_area->irb.esw.esw0.erw.cons = 1; cdev->private->flags.dosense = 0; } /* Check if path verification is required. */ @@ -386,7 +386,7 @@ ccw_device_accumulate_and_sense(struct ccw_device *cdev, struct irb *irb) /* Check for basic sense. */ if (cdev->private->flags.dosense && !(irb->scsw.cmd.dstat & DEV_STAT_UNIT_CHECK)) { - cdev->private->irb.esw.esw0.erw.cons = 1; + cdev->private->dma_area->irb.esw.esw0.erw.cons = 1; cdev->private->flags.dosense = 0; return 0; } diff --git a/drivers/s390/cio/io_sch.h b/drivers/s390/cio/io_sch.h index 90e4e3a7841b..c03b4a19974e 100644 --- a/drivers/s390/cio/io_sch.h +++ b/drivers/s390/cio/io_sch.h @@ -9,15 +9,20 @@ #include "css.h" #include "orb.h" +struct io_subchannel_dma_area { + struct ccw1 sense_ccw; /* static ccw for sense command */ +}; + struct io_subchannel_private { union orb orb; /* operation request block */ - struct ccw1 sense_ccw; /* static ccw for sense command */ struct ccw_device *cdev;/* pointer to the child ccw device */ struct { unsigned int suspend:1; /* allow suspend */ unsigned int prefetch:1;/* deny prefetch */ unsigned int inter:1; /* suppress intermediate interrupts */ } __packed options; + struct io_subchannel_dma_area *dma_area; + dma_addr_t dma_area_dma; } __aligned(8); #define to_io_private(n) ((struct io_subchannel_private *) \ @@ -115,6 +120,13 @@ enum cdev_todo { #define FAKE_CMD_IRB 1 #define FAKE_TM_IRB 2 +struct ccw_device_dma_area { + struct senseid senseid; /* SenseID info */ + struct ccw1 iccws[2]; /* ccws for SNID/SID/SPGID commands */ + struct irb irb; /* device status */ + struct pgid pgid[8]; /* path group IDs per chpid*/ +}; + struct ccw_device_private { struct ccw_device *cdev; struct subchannel *sch; @@ -156,11 +168,7 @@ struct ccw_device_private { } __attribute__((packed)) flags; unsigned long intparm; /* user interruption parameter */ struct qdio_irq *qdio_data; - struct irb irb; /* device status */ int async_kill_io_rc; - struct senseid senseid; /* SenseID info */ - struct pgid pgid[8]; /* path group IDs per chpid*/ - struct ccw1 iccws[2]; /* ccws for SNID/SID/SPGID commands */ struct work_struct todo_work; enum cdev_todo todo; wait_queue_head_t wait_q; @@ -169,6 +177,8 @@ struct ccw_device_private { struct list_head cmb_list; /* list of measured devices */ u64 cmb_start_time; /* clock value of cmb reset */ void *cmb_wait; /* deferred cmb enable/disable */ + struct gen_pool *dma_pool; + struct ccw_device_dma_area *dma_area; enum interruption_class int_class; }; diff --git a/drivers/s390/cio/ioasm.c b/drivers/s390/cio/ioasm.c index 14d328338ce2..08eb10283b18 100644 --- a/drivers/s390/cio/ioasm.c +++ b/drivers/s390/cio/ioasm.c @@ -233,6 +233,7 @@ int hsch(struct subchannel_id schid) return ccode; } +EXPORT_SYMBOL(hsch); static inline int __xsch(struct subchannel_id schid) { diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h index a6f7c2986b94..a06944399865 100644 --- a/drivers/s390/cio/qdio.h +++ b/drivers/s390/cio/qdio.h @@ -228,9 +228,6 @@ struct qdio_q { */ int first_to_check; - /* first_to_check of the last time */ - int last_move; - /* beginning position for calling the program */ int first_to_kick; @@ -341,8 +338,7 @@ static inline int multicast_outbound(struct qdio_q *q) (q->nr == q->irq_ptr->nr_output_qs - 1); } -#define pci_out_supported(q) \ - (q->irq_ptr->qib.ac & QIB_AC_OUTBOUND_PCI_SUPPORTED) +#define pci_out_supported(irq) ((irq)->qib.ac & QIB_AC_OUTBOUND_PCI_SUPPORTED) #define is_qebsm(q) (q->irq_ptr->sch_token != 0) #define need_siga_in(q) (q->irq_ptr->siga_flag.input) diff --git a/drivers/s390/cio/qdio_debug.c b/drivers/s390/cio/qdio_debug.c index d2f98e5829d4..35410e6eda2e 100644 --- a/drivers/s390/cio/qdio_debug.c +++ b/drivers/s390/cio/qdio_debug.c @@ -121,15 +121,14 @@ static int qstat_show(struct seq_file *m, void *v) seq_printf(m, "Timestamp: %Lx Last AI: %Lx\n", q->timestamp, last_ai_time); - seq_printf(m, "nr_used: %d ftc: %d last_move: %d\n", - atomic_read(&q->nr_buf_used), - q->first_to_check, q->last_move); + seq_printf(m, "nr_used: %d ftc: %d\n", + atomic_read(&q->nr_buf_used), q->first_to_check); if (q->is_input_q) { seq_printf(m, "polling: %d ack start: %d ack count: %d\n", q->u.in.polling, q->u.in.ack_start, q->u.in.ack_count); - seq_printf(m, "DSCI: %d IRQs disabled: %u\n", - *(u32 *)q->irq_ptr->dsci, + seq_printf(m, "DSCI: %x IRQs disabled: %u\n", + *(u8 *)q->irq_ptr->dsci, test_bit(QDIO_QUEUE_IRQS_DISABLED, &q->u.in.queue_irq_state)); } diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index 9537e656e927..730c4e68094b 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -205,17 +205,22 @@ static inline int get_buf_states(struct qdio_q *q, unsigned int bufnr, int auto_ack, int merge_pending) { unsigned char __state = 0; - int i; + int i = 1; if (is_qebsm(q)) return qdio_do_eqbs(q, state, bufnr, count, auto_ack); /* get initial state: */ __state = q->slsb.val[bufnr]; + + /* Bail out early if there is no work on the queue: */ + if (__state & SLSB_OWNER_CU) + goto out; + if (merge_pending && __state == SLSB_P_OUTPUT_PENDING) __state = SLSB_P_OUTPUT_EMPTY; - for (i = 1; i < count; i++) { + for (; i < count; i++) { bufnr = next_buf(bufnr); /* merge PENDING into EMPTY: */ @@ -228,6 +233,8 @@ static inline int get_buf_states(struct qdio_q *q, unsigned int bufnr, if (q->slsb.val[bufnr] != __state) break; } + +out: *state = __state; return i; } @@ -371,7 +378,7 @@ static inline int qdio_siga_input(struct qdio_q *q) static inline void qdio_sync_queues(struct qdio_q *q) { /* PCI capable outbound queues will also be scanned so sync them too */ - if (pci_out_supported(q)) + if (pci_out_supported(q->irq_ptr)) qdio_siga_sync_all(q); else qdio_siga_sync_q(q); @@ -382,7 +389,7 @@ int debug_get_buf_state(struct qdio_q *q, unsigned int bufnr, { if (need_siga_sync(q)) qdio_siga_sync_q(q); - return get_buf_states(q, bufnr, state, 1, 0, 0); + return get_buf_state(q, bufnr, state, 0); } static inline void qdio_stop_polling(struct qdio_q *q) @@ -415,7 +422,8 @@ static inline void account_sbals(struct qdio_q *q, unsigned int count) q->q_stats.nr_sbals[pos]++; } -static void process_buffer_error(struct qdio_q *q, int count) +static void process_buffer_error(struct qdio_q *q, unsigned int start, + int count) { unsigned char state = (q->is_input_q) ? SLSB_P_INPUT_NOT_INIT : SLSB_P_OUTPUT_NOT_INIT; @@ -424,29 +432,29 @@ static void process_buffer_error(struct qdio_q *q, int count) /* special handling for no target buffer empty */ if (queue_type(q) == QDIO_IQDIO_QFMT && !q->is_input_q && - q->sbal[q->first_to_check]->element[15].sflags == 0x10) { + q->sbal[start]->element[15].sflags == 0x10) { qperf_inc(q, target_full); - DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "OUTFULL FTC:%02x", - q->first_to_check); + DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "OUTFULL FTC:%02x", start); goto set; } DBF_ERROR("%4x BUF ERROR", SCH_NO(q)); DBF_ERROR((q->is_input_q) ? "IN:%2d" : "OUT:%2d", q->nr); - DBF_ERROR("FTC:%3d C:%3d", q->first_to_check, count); + DBF_ERROR("FTC:%3d C:%3d", start, count); DBF_ERROR("F14:%2x F15:%2x", - q->sbal[q->first_to_check]->element[14].sflags, - q->sbal[q->first_to_check]->element[15].sflags); + q->sbal[start]->element[14].sflags, + q->sbal[start]->element[15].sflags); set: /* * Interrupts may be avoided as long as the error is present * so change the buffer state immediately to avoid starvation. */ - set_buf_states(q, q->first_to_check, state, count); + set_buf_states(q, start, state, count); } -static inline void inbound_primed(struct qdio_q *q, int count) +static inline void inbound_primed(struct qdio_q *q, unsigned int start, + int count) { int new; @@ -457,7 +465,7 @@ static inline void inbound_primed(struct qdio_q *q, int count) if (!q->u.in.polling) { q->u.in.polling = 1; q->u.in.ack_count = count; - q->u.in.ack_start = q->first_to_check; + q->u.in.ack_start = start; return; } @@ -465,7 +473,7 @@ static inline void inbound_primed(struct qdio_q *q, int count) set_buf_states(q, q->u.in.ack_start, SLSB_P_INPUT_NOT_INIT, q->u.in.ack_count); q->u.in.ack_count = count; - q->u.in.ack_start = q->first_to_check; + q->u.in.ack_start = start; return; } @@ -473,7 +481,7 @@ static inline void inbound_primed(struct qdio_q *q, int count) * ACK the newest buffer. The ACK will be removed in qdio_stop_polling * or by the next inbound run. */ - new = add_buf(q->first_to_check, count - 1); + new = add_buf(start, count - 1); if (q->u.in.polling) { /* reset the previous ACK but first set the new one */ set_buf_state(q, new, SLSB_P_INPUT_ACK); @@ -488,10 +496,10 @@ static inline void inbound_primed(struct qdio_q *q, int count) if (!count) return; /* need to change ALL buffers to get more interrupts */ - set_buf_states(q, q->first_to_check, SLSB_P_INPUT_NOT_INIT, count); + set_buf_states(q, start, SLSB_P_INPUT_NOT_INIT, count); } -static int get_inbound_buffer_frontier(struct qdio_q *q) +static int get_inbound_buffer_frontier(struct qdio_q *q, unsigned int start) { unsigned char state = 0; int count; @@ -504,64 +512,58 @@ static int get_inbound_buffer_frontier(struct qdio_q *q) */ count = min(atomic_read(&q->nr_buf_used), QDIO_MAX_BUFFERS_MASK); if (!count) - goto out; + return 0; /* * No siga sync here, as a PCI or we after a thin interrupt * already sync'ed the queues. */ - count = get_buf_states(q, q->first_to_check, &state, count, 1, 0); + count = get_buf_states(q, start, &state, count, 1, 0); if (!count) - goto out; + return 0; switch (state) { case SLSB_P_INPUT_PRIMED: - inbound_primed(q, count); - q->first_to_check = add_buf(q->first_to_check, count); + inbound_primed(q, start, count); if (atomic_sub_return(count, &q->nr_buf_used) == 0) qperf_inc(q, inbound_queue_full); if (q->irq_ptr->perf_stat_enabled) account_sbals(q, count); - break; + return count; case SLSB_P_INPUT_ERROR: - process_buffer_error(q, count); - q->first_to_check = add_buf(q->first_to_check, count); + process_buffer_error(q, start, count); if (atomic_sub_return(count, &q->nr_buf_used) == 0) qperf_inc(q, inbound_queue_full); if (q->irq_ptr->perf_stat_enabled) account_sbals_error(q, count); - break; + return count; case SLSB_CU_INPUT_EMPTY: case SLSB_P_INPUT_NOT_INIT: case SLSB_P_INPUT_ACK: if (q->irq_ptr->perf_stat_enabled) q->q_stats.nr_sbal_nop++; DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "in nop:%1d %#02x", - q->nr, q->first_to_check); - break; + q->nr, start); + return 0; default: WARN_ON_ONCE(1); + return 0; } -out: - return q->first_to_check; } -static int qdio_inbound_q_moved(struct qdio_q *q) +static int qdio_inbound_q_moved(struct qdio_q *q, unsigned int start) { - int bufnr; + int count; - bufnr = get_inbound_buffer_frontier(q); + count = get_inbound_buffer_frontier(q, start); - if (bufnr != q->last_move) { - q->last_move = bufnr; - if (!is_thinint_irq(q->irq_ptr) && MACHINE_IS_LPAR) - q->u.in.timestamp = get_tod_clock(); - return 1; - } else - return 0; + if (count && !is_thinint_irq(q->irq_ptr) && MACHINE_IS_LPAR) + q->u.in.timestamp = get_tod_clock(); + + return count; } -static inline int qdio_inbound_q_done(struct qdio_q *q) +static inline int qdio_inbound_q_done(struct qdio_q *q, unsigned int start) { unsigned char state = 0; @@ -570,7 +572,7 @@ static inline int qdio_inbound_q_done(struct qdio_q *q) if (need_siga_sync(q)) qdio_siga_sync_q(q); - get_buf_state(q, q->first_to_check, &state, 0); + get_buf_state(q, start, &state, 0); if (state == SLSB_P_INPUT_PRIMED || state == SLSB_P_INPUT_ERROR) /* more work coming */ @@ -588,8 +590,7 @@ static inline int qdio_inbound_q_done(struct qdio_q *q) * has (probably) not moved (see qdio_inbound_processing). */ if (get_tod_clock_fast() > q->u.in.timestamp + QDIO_INPUT_THRESHOLD) { - DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "in done:%02x", - q->first_to_check); + DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "in done:%02x", start); return 1; } else return 0; @@ -637,17 +638,13 @@ static inline unsigned long qdio_aob_for_buffer(struct qdio_output_q *q, return phys_aob; } -static void qdio_kick_handler(struct qdio_q *q) +static void qdio_kick_handler(struct qdio_q *q, unsigned int count) { int start = q->first_to_kick; - int end = q->first_to_check; - int count; if (unlikely(q->irq_ptr->state != QDIO_IRQ_STATE_ACTIVE)) return; - count = sub_buf(end, start); - if (q->is_input_q) { qperf_inc(q, inbound_handler); DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "kih s:%02x c:%02x", start, count); @@ -663,7 +660,7 @@ static void qdio_kick_handler(struct qdio_q *q) q->irq_ptr->int_parm); /* for the next time */ - q->first_to_kick = end; + q->first_to_kick = add_buf(start, count); q->qdio_error = 0; } @@ -678,14 +675,20 @@ static inline int qdio_tasklet_schedule(struct qdio_q *q) static void __qdio_inbound_processing(struct qdio_q *q) { + unsigned int start = q->first_to_check; + int count; + qperf_inc(q, tasklet_inbound); - if (!qdio_inbound_q_moved(q)) + count = qdio_inbound_q_moved(q, start); + if (count == 0) return; - qdio_kick_handler(q); + start = add_buf(start, count); + q->first_to_check = start; + qdio_kick_handler(q, count); - if (!qdio_inbound_q_done(q)) { + if (!qdio_inbound_q_done(q, start)) { /* means poll time is not yet over */ qperf_inc(q, tasklet_inbound_resched); if (!qdio_tasklet_schedule(q)) @@ -697,7 +700,7 @@ static void __qdio_inbound_processing(struct qdio_q *q) * We need to check again to not lose initiative after * resetting the ACK state. */ - if (!qdio_inbound_q_done(q)) { + if (!qdio_inbound_q_done(q, start)) { qperf_inc(q, tasklet_inbound_resched2); qdio_tasklet_schedule(q); } @@ -709,7 +712,7 @@ void qdio_inbound_processing(unsigned long data) __qdio_inbound_processing(q); } -static int get_outbound_buffer_frontier(struct qdio_q *q) +static int get_outbound_buffer_frontier(struct qdio_q *q, unsigned int start) { unsigned char state = 0; int count; @@ -718,59 +721,50 @@ static int get_outbound_buffer_frontier(struct qdio_q *q) if (need_siga_sync(q)) if (((queue_type(q) != QDIO_IQDIO_QFMT) && - !pci_out_supported(q)) || + !pci_out_supported(q->irq_ptr)) || (queue_type(q) == QDIO_IQDIO_QFMT && multicast_outbound(q))) qdio_siga_sync_q(q); - /* - * Don't check 128 buffers, as otherwise qdio_inbound_q_moved - * would return 0. - */ - count = min(atomic_read(&q->nr_buf_used), QDIO_MAX_BUFFERS_MASK); + count = atomic_read(&q->nr_buf_used); if (!count) - goto out; + return 0; - count = get_buf_states(q, q->first_to_check, &state, count, 0, - q->u.out.use_cq); + count = get_buf_states(q, start, &state, count, 0, q->u.out.use_cq); if (!count) - goto out; + return 0; switch (state) { case SLSB_P_OUTPUT_EMPTY: + case SLSB_P_OUTPUT_PENDING: /* the adapter got it */ DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "out empty:%1d %02x", q->nr, count); atomic_sub(count, &q->nr_buf_used); - q->first_to_check = add_buf(q->first_to_check, count); if (q->irq_ptr->perf_stat_enabled) account_sbals(q, count); - - break; + return count; case SLSB_P_OUTPUT_ERROR: - process_buffer_error(q, count); - q->first_to_check = add_buf(q->first_to_check, count); + process_buffer_error(q, start, count); atomic_sub(count, &q->nr_buf_used); if (q->irq_ptr->perf_stat_enabled) account_sbals_error(q, count); - break; + return count; case SLSB_CU_OUTPUT_PRIMED: /* the adapter has not fetched the output yet */ if (q->irq_ptr->perf_stat_enabled) q->q_stats.nr_sbal_nop++; DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "out primed:%1d", q->nr); - break; + return 0; case SLSB_P_OUTPUT_NOT_INIT: case SLSB_P_OUTPUT_HALTED: - break; + return 0; default: WARN_ON_ONCE(1); + return 0; } - -out: - return q->first_to_check; } /* all buffers processed? */ @@ -779,18 +773,16 @@ static inline int qdio_outbound_q_done(struct qdio_q *q) return atomic_read(&q->nr_buf_used) == 0; } -static inline int qdio_outbound_q_moved(struct qdio_q *q) +static inline int qdio_outbound_q_moved(struct qdio_q *q, unsigned int start) { - int bufnr; + int count; - bufnr = get_outbound_buffer_frontier(q); + count = get_outbound_buffer_frontier(q, start); - if (bufnr != q->last_move) { - q->last_move = bufnr; + if (count) DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "out moved:%1d", q->nr); - return 1; - } else - return 0; + + return count; } static int qdio_kick_outbound_q(struct qdio_q *q, unsigned long aob) @@ -837,15 +829,21 @@ retry: static void __qdio_outbound_processing(struct qdio_q *q) { + unsigned int start = q->first_to_check; + int count; + qperf_inc(q, tasklet_outbound); WARN_ON_ONCE(atomic_read(&q->nr_buf_used) < 0); - if (qdio_outbound_q_moved(q)) - qdio_kick_handler(q); + count = qdio_outbound_q_moved(q, start); + if (count) { + q->first_to_check = add_buf(start, count); + qdio_kick_handler(q, count); + } - if (queue_type(q) == QDIO_ZFCP_QFMT) - if (!pci_out_supported(q) && !qdio_outbound_q_done(q)) - goto sched; + if (queue_type(q) == QDIO_ZFCP_QFMT && !pci_out_supported(q->irq_ptr) && + !qdio_outbound_q_done(q)) + goto sched; if (q->u.out.pci_out_enabled) return; @@ -881,37 +879,40 @@ void qdio_outbound_timer(struct timer_list *t) qdio_tasklet_schedule(q); } -static inline void qdio_check_outbound_after_thinint(struct qdio_q *q) +static inline void qdio_check_outbound_pci_queues(struct qdio_irq *irq) { struct qdio_q *out; int i; - if (!pci_out_supported(q)) + if (!pci_out_supported(irq)) return; - for_each_output_queue(q->irq_ptr, out, i) + for_each_output_queue(irq, out, i) if (!qdio_outbound_q_done(out)) qdio_tasklet_schedule(out); } static void __tiqdio_inbound_processing(struct qdio_q *q) { + unsigned int start = q->first_to_check; + int count; + qperf_inc(q, tasklet_inbound); if (need_siga_sync(q) && need_siga_sync_after_ai(q)) qdio_sync_queues(q); - /* - * The interrupt could be caused by a PCI request. Check the - * PCI capable outbound queues. - */ - qdio_check_outbound_after_thinint(q); + /* The interrupt could be caused by a PCI request: */ + qdio_check_outbound_pci_queues(q->irq_ptr); - if (!qdio_inbound_q_moved(q)) + count = qdio_inbound_q_moved(q, start); + if (count == 0) return; - qdio_kick_handler(q); + start = add_buf(start, count); + q->first_to_check = start; + qdio_kick_handler(q, count); - if (!qdio_inbound_q_done(q)) { + if (!qdio_inbound_q_done(q, start)) { qperf_inc(q, tasklet_inbound_resched); if (!qdio_tasklet_schedule(q)) return; @@ -922,7 +923,7 @@ static void __tiqdio_inbound_processing(struct qdio_q *q) * We need to check again to not lose initiative after * resetting the ACK state. */ - if (!qdio_inbound_q_done(q)) { + if (!qdio_inbound_q_done(q, start)) { qperf_inc(q, tasklet_inbound_resched2); qdio_tasklet_schedule(q); } @@ -976,7 +977,7 @@ static void qdio_int_handler_pci(struct qdio_irq *irq_ptr) } } - if (!(irq_ptr->qib.ac & QIB_AC_OUTBOUND_PCI_SUPPORTED)) + if (!pci_out_supported(irq_ptr)) return; for_each_output_queue(irq_ptr, q, i) { @@ -1642,7 +1643,7 @@ int qdio_start_irq(struct ccw_device *cdev, int nr) */ if (test_nonshared_ind(irq_ptr)) goto rescan; - if (!qdio_inbound_q_done(q)) + if (!qdio_inbound_q_done(q, q->first_to_check)) goto rescan; return 0; @@ -1672,12 +1673,14 @@ int qdio_get_next_buffers(struct ccw_device *cdev, int nr, int *bufnr, int *error) { struct qdio_q *q; - int start, end; struct qdio_irq *irq_ptr = cdev->private->qdio_data; + unsigned int start; + int count; if (!irq_ptr) return -ENODEV; q = irq_ptr->input_qs[nr]; + start = q->first_to_check; /* * Cannot rely on automatic sync after interrupt since queues may @@ -1686,25 +1689,27 @@ int qdio_get_next_buffers(struct ccw_device *cdev, int nr, int *bufnr, if (need_siga_sync(q)) qdio_sync_queues(q); - /* check the PCI capable outbound queues. */ - qdio_check_outbound_after_thinint(q); + qdio_check_outbound_pci_queues(irq_ptr); - if (!qdio_inbound_q_moved(q)) + count = qdio_inbound_q_moved(q, start); + if (count == 0) return 0; + start = add_buf(start, count); + q->first_to_check = start; + /* Note: upper-layer MUST stop processing immediately here ... */ if (unlikely(q->irq_ptr->state != QDIO_IRQ_STATE_ACTIVE)) return -EIO; - start = q->first_to_kick; - end = q->first_to_check; - *bufnr = start; + *bufnr = q->first_to_kick; *error = q->qdio_error; /* for the next time */ - q->first_to_kick = end; + q->first_to_kick = add_buf(q->first_to_kick, count); q->qdio_error = 0; - return sub_buf(end, start); + + return count; } EXPORT_SYMBOL(qdio_get_next_buffers); diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c index a59887fad13e..d4101cecdc8d 100644 --- a/drivers/s390/cio/qdio_setup.c +++ b/drivers/s390/cio/qdio_setup.c @@ -150,6 +150,7 @@ static int __qdio_allocate_qs(struct qdio_q **irq_ptr_qs, int nr_queues) return -ENOMEM; } irq_ptr_qs[i] = q; + INIT_LIST_HEAD(&q->entry); } return 0; } @@ -178,6 +179,7 @@ static void setup_queues_misc(struct qdio_q *q, struct qdio_irq *irq_ptr, q->mask = 1 << (31 - i); q->nr = i; q->handler = handler; + INIT_LIST_HEAD(&q->entry); } static void setup_storage_lists(struct qdio_q *q, struct qdio_irq *irq_ptr, @@ -523,7 +525,7 @@ void qdio_print_subchannel_info(struct qdio_irq *irq_ptr, irq_ptr->schid.sch_no, is_thinint_irq(irq_ptr), (irq_ptr->sch_token) ? 1 : 0, - (irq_ptr->qib.ac & QIB_AC_OUTBOUND_PCI_SUPPORTED) ? 1 : 0, + pci_out_supported(irq_ptr) ? 1 : 0, css_general_characteristics.aif_tdd, (irq_ptr->siga_flag.input) ? "R" : " ", (irq_ptr->siga_flag.output) ? "W" : " ", diff --git a/drivers/s390/cio/qdio_thinint.c b/drivers/s390/cio/qdio_thinint.c index 07dea602205b..93ee067c10ca 100644 --- a/drivers/s390/cio/qdio_thinint.c +++ b/drivers/s390/cio/qdio_thinint.c @@ -40,7 +40,7 @@ static LIST_HEAD(tiq_list); static DEFINE_MUTEX(tiq_list_lock); /* Adapter interrupt definitions */ -static void tiqdio_thinint_handler(struct airq_struct *airq); +static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating); static struct airq_struct tiqdio_airq = { .handler = tiqdio_thinint_handler, @@ -79,7 +79,6 @@ void tiqdio_add_input_queues(struct qdio_irq *irq_ptr) mutex_lock(&tiq_list_lock); list_add_rcu(&irq_ptr->input_qs[0]->entry, &tiq_list); mutex_unlock(&tiq_list_lock); - xchg(irq_ptr->dsci, 1 << 7); } void tiqdio_remove_input_queues(struct qdio_irq *irq_ptr) @@ -87,14 +86,14 @@ void tiqdio_remove_input_queues(struct qdio_irq *irq_ptr) struct qdio_q *q; q = irq_ptr->input_qs[0]; - /* if establish triggered an error */ - if (!q || !q->entry.prev || !q->entry.next) + if (!q) return; mutex_lock(&tiq_list_lock); list_del_rcu(&q->entry); mutex_unlock(&tiq_list_lock); synchronize_rcu(); + INIT_LIST_HEAD(&q->entry); } static inline int has_multiple_inq_on_dsci(struct qdio_irq *irq_ptr) @@ -178,8 +177,9 @@ static inline void tiqdio_call_inq_handlers(struct qdio_irq *irq) /** * tiqdio_thinint_handler - thin interrupt handler for qdio * @airq: pointer to adapter interrupt descriptor + * @floating: flag to recognize floating vs. directed interrupts (unused) */ -static void tiqdio_thinint_handler(struct airq_struct *airq) +static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating) { u32 si_used = clear_shared_ind(); struct qdio_q *q; diff --git a/drivers/s390/cio/scm.c b/drivers/s390/cio/scm.c index 6bca1d5455d4..9f26d4310bb3 100644 --- a/drivers/s390/cio/scm.c +++ b/drivers/s390/cio/scm.c @@ -174,10 +174,10 @@ out: kobject_uevent(&scmdev->dev.kobj, KOBJ_CHANGE); } -static int check_address(struct device *dev, void *data) +static int check_address(struct device *dev, const void *data) { struct scm_device *scmdev = to_scm_dev(dev); - struct sale *sale = data; + const struct sale *sale = data; return scmdev->address == sale->sa; } diff --git a/drivers/s390/cio/trace.c b/drivers/s390/cio/trace.c index e331cd97e83b..882ee538ca30 100644 --- a/drivers/s390/cio/trace.c +++ b/drivers/s390/cio/trace.c @@ -21,5 +21,4 @@ EXPORT_TRACEPOINT_SYMBOL(s390_cio_csch); EXPORT_TRACEPOINT_SYMBOL(s390_cio_hsch); EXPORT_TRACEPOINT_SYMBOL(s390_cio_xsch); EXPORT_TRACEPOINT_SYMBOL(s390_cio_rsch); -EXPORT_TRACEPOINT_SYMBOL(s390_cio_rchp); EXPORT_TRACEPOINT_SYMBOL(s390_cio_chsc); diff --git a/drivers/s390/cio/trace.h b/drivers/s390/cio/trace.h index 0ebb29b6fd6d..4803139bce14 100644 --- a/drivers/s390/cio/trace.h +++ b/drivers/s390/cio/trace.h @@ -274,29 +274,6 @@ DEFINE_EVENT(s390_class_schid, s390_cio_rsch, TP_ARGS(schid, cc) ); -/** - * s390_cio_rchp - Reset Channel Path (RCHP) instruction was performed - * @chpid: Channel-Path Identifier - * @cc: Condition code - */ -TRACE_EVENT(s390_cio_rchp, - TP_PROTO(struct chp_id chpid, int cc), - TP_ARGS(chpid, cc), - TP_STRUCT__entry( - __field(u8, cssid) - __field(u8, id) - __field(int, cc) - ), - TP_fast_assign( - __entry->cssid = chpid.cssid; - __entry->id = chpid.id; - __entry->cc = cc; - ), - TP_printk("chpid=%x.%02x cc=%d", __entry->cssid, __entry->id, - __entry->cc - ) -); - #define CHSC_MAX_REQUEST_LEN 64 #define CHSC_MAX_RESPONSE_LEN 64 diff --git a/drivers/s390/cio/vfio_ccw_async.c b/drivers/s390/cio/vfio_ccw_async.c new file mode 100644 index 000000000000..8c1d2357ef5b --- /dev/null +++ b/drivers/s390/cio/vfio_ccw_async.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Async I/O region for vfio_ccw + * + * Copyright Red Hat, Inc. 2019 + * + * Author(s): Cornelia Huck <cohuck@redhat.com> + */ + +#include <linux/vfio.h> +#include <linux/mdev.h> + +#include "vfio_ccw_private.h" + +static ssize_t vfio_ccw_async_region_read(struct vfio_ccw_private *private, + char __user *buf, size_t count, + loff_t *ppos) +{ + unsigned int i = VFIO_CCW_OFFSET_TO_INDEX(*ppos) - VFIO_CCW_NUM_REGIONS; + loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK; + struct ccw_cmd_region *region; + int ret; + + if (pos + count > sizeof(*region)) + return -EINVAL; + + mutex_lock(&private->io_mutex); + region = private->region[i].data; + if (copy_to_user(buf, (void *)region + pos, count)) + ret = -EFAULT; + else + ret = count; + mutex_unlock(&private->io_mutex); + return ret; +} + +static ssize_t vfio_ccw_async_region_write(struct vfio_ccw_private *private, + const char __user *buf, size_t count, + loff_t *ppos) +{ + unsigned int i = VFIO_CCW_OFFSET_TO_INDEX(*ppos) - VFIO_CCW_NUM_REGIONS; + loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK; + struct ccw_cmd_region *region; + int ret; + + if (pos + count > sizeof(*region)) + return -EINVAL; + + if (!mutex_trylock(&private->io_mutex)) + return -EAGAIN; + + region = private->region[i].data; + if (copy_from_user((void *)region + pos, buf, count)) { + ret = -EFAULT; + goto out_unlock; + } + + vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_ASYNC_REQ); + + ret = region->ret_code ? region->ret_code : count; + +out_unlock: + mutex_unlock(&private->io_mutex); + return ret; +} + +static void vfio_ccw_async_region_release(struct vfio_ccw_private *private, + struct vfio_ccw_region *region) +{ + +} + +const struct vfio_ccw_regops vfio_ccw_async_region_ops = { + .read = vfio_ccw_async_region_read, + .write = vfio_ccw_async_region_write, + .release = vfio_ccw_async_region_release, +}; + +int vfio_ccw_register_async_dev_regions(struct vfio_ccw_private *private) +{ + return vfio_ccw_register_dev_region(private, + VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD, + &vfio_ccw_async_region_ops, + sizeof(struct ccw_cmd_region), + VFIO_REGION_INFO_FLAG_READ | + VFIO_REGION_INFO_FLAG_WRITE, + private->cmd_region); +} diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index 384b3987eeb4..1d4c893ead23 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -16,12 +16,6 @@ #include "vfio_ccw_cp.h" -/* - * Max length for ccw chain. - * XXX: Limit to 256, need to check more? - */ -#define CCWCHAIN_LEN_MAX 256 - struct pfn_array { /* Starting guest physical I/O address. */ unsigned long pa_iova; @@ -33,11 +27,6 @@ struct pfn_array { int pa_nr; }; -struct pfn_array_table { - struct pfn_array *pat_pa; - int pat_nr; -}; - struct ccwchain { struct list_head next; struct ccw1 *ch_ccw; @@ -46,35 +35,29 @@ struct ccwchain { /* Count of the valid ccws in chain. */ int ch_len; /* Pinned PAGEs for the original data. */ - struct pfn_array_table *ch_pat; + struct pfn_array *ch_pa; }; /* - * pfn_array_alloc_pin() - alloc memory for PFNs, then pin user pages in memory + * pfn_array_alloc() - alloc memory for PFNs * @pa: pfn_array on which to perform the operation - * @mdev: the mediated device to perform pin/unpin operations * @iova: target guest physical address * @len: number of bytes that should be pinned from @iova * - * Attempt to allocate memory for PFNs, and pin user pages in memory. + * Attempt to allocate memory for PFNs. * * Usage of pfn_array: * We expect (pa_nr == 0) and (pa_iova_pfn == NULL), any field in * this structure will be filled in by this function. * * Returns: - * Number of pages pinned on success. - * If @pa->pa_nr is not 0, or @pa->pa_iova_pfn is not NULL initially, - * returns -EINVAL. - * If no pages were pinned, returns -errno. + * 0 if PFNs are allocated + * -EINVAL if pa->pa_nr is not initially zero, or pa->pa_iova_pfn is not NULL + * -ENOMEM if alloc failed */ -static int pfn_array_alloc_pin(struct pfn_array *pa, struct device *mdev, - u64 iova, unsigned int len) +static int pfn_array_alloc(struct pfn_array *pa, u64 iova, unsigned int len) { - int i, ret = 0; - - if (!len) - return 0; + int i; if (pa->pa_nr || pa->pa_iova_pfn) return -EINVAL; @@ -94,8 +77,27 @@ static int pfn_array_alloc_pin(struct pfn_array *pa, struct device *mdev, pa->pa_pfn = pa->pa_iova_pfn + pa->pa_nr; pa->pa_iova_pfn[0] = pa->pa_iova >> PAGE_SHIFT; - for (i = 1; i < pa->pa_nr; i++) + pa->pa_pfn[0] = -1ULL; + for (i = 1; i < pa->pa_nr; i++) { pa->pa_iova_pfn[i] = pa->pa_iova_pfn[i - 1] + 1; + pa->pa_pfn[i] = -1ULL; + } + + return 0; +} + +/* + * pfn_array_pin() - Pin user pages in memory + * @pa: pfn_array on which to perform the operation + * @mdev: the mediated device to perform pin operations + * + * Returns number of pages pinned upon success. + * If the pin request partially succeeds, or fails completely, + * all pages are left unpinned and a negative error value is returned. + */ +static int pfn_array_pin(struct pfn_array *pa, struct device *mdev) +{ + int ret = 0; ret = vfio_pin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr, IOMMU_READ | IOMMU_WRITE, pa->pa_pfn); @@ -112,8 +114,6 @@ static int pfn_array_alloc_pin(struct pfn_array *pa, struct device *mdev, err_out: pa->pa_nr = 0; - kfree(pa->pa_iova_pfn); - pa->pa_iova_pfn = NULL; return ret; } @@ -121,60 +121,30 @@ err_out: /* Unpin the pages before releasing the memory. */ static void pfn_array_unpin_free(struct pfn_array *pa, struct device *mdev) { - vfio_unpin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr); + /* Only unpin if any pages were pinned to begin with */ + if (pa->pa_nr) + vfio_unpin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr); pa->pa_nr = 0; kfree(pa->pa_iova_pfn); } -static int pfn_array_table_init(struct pfn_array_table *pat, int nr) -{ - pat->pat_pa = kcalloc(nr, sizeof(*pat->pat_pa), GFP_KERNEL); - if (unlikely(ZERO_OR_NULL_PTR(pat->pat_pa))) { - pat->pat_nr = 0; - return -ENOMEM; - } - - pat->pat_nr = nr; - - return 0; -} - -static void pfn_array_table_unpin_free(struct pfn_array_table *pat, - struct device *mdev) -{ - int i; - - for (i = 0; i < pat->pat_nr; i++) - pfn_array_unpin_free(pat->pat_pa + i, mdev); - - if (pat->pat_nr) { - kfree(pat->pat_pa); - pat->pat_pa = NULL; - pat->pat_nr = 0; - } -} - -static bool pfn_array_table_iova_pinned(struct pfn_array_table *pat, - unsigned long iova) +static bool pfn_array_iova_pinned(struct pfn_array *pa, unsigned long iova) { - struct pfn_array *pa = pat->pat_pa; unsigned long iova_pfn = iova >> PAGE_SHIFT; - int i, j; + int i; - for (i = 0; i < pat->pat_nr; i++, pa++) - for (j = 0; j < pa->pa_nr; j++) - if (pa->pa_iova_pfn[j] == iova_pfn) - return true; + for (i = 0; i < pa->pa_nr; i++) + if (pa->pa_iova_pfn[i] == iova_pfn) + return true; return false; } -/* Create the list idal words for a pfn_array_table. */ -static inline void pfn_array_table_idal_create_words( - struct pfn_array_table *pat, +/* Create the list of IDAL words for a pfn_array. */ +static inline void pfn_array_idal_create_words( + struct pfn_array *pa, unsigned long *idaws) { - struct pfn_array *pa; - int i, j, k; + int i; /* * Idal words (execept the first one) rely on the memory being 4k @@ -183,19 +153,36 @@ static inline void pfn_array_table_idal_create_words( * there will be no problem here to simply use the phys to create an * idaw. */ - k = 0; - for (i = 0; i < pat->pat_nr; i++) { - pa = pat->pat_pa + i; - for (j = 0; j < pa->pa_nr; j++) { - idaws[k] = pa->pa_pfn[j] << PAGE_SHIFT; - if (k == 0) - idaws[k] += pa->pa_iova & (PAGE_SIZE - 1); - k++; + + for (i = 0; i < pa->pa_nr; i++) + idaws[i] = pa->pa_pfn[i] << PAGE_SHIFT; + + /* Adjust the first IDAW, since it may not start on a page boundary */ + idaws[0] += pa->pa_iova & (PAGE_SIZE - 1); +} + +static void convert_ccw0_to_ccw1(struct ccw1 *source, unsigned long len) +{ + struct ccw0 ccw0; + struct ccw1 *pccw1 = source; + int i; + + for (i = 0; i < len; i++) { + ccw0 = *(struct ccw0 *)pccw1; + if ((pccw1->cmd_code & 0x0f) == CCW_CMD_TIC) { + pccw1->cmd_code = CCW_CMD_TIC; + pccw1->flags = 0; + pccw1->count = 0; + } else { + pccw1->cmd_code = ccw0.cmd_code; + pccw1->flags = ccw0.flags; + pccw1->count = ccw0.count; } + pccw1->cda = ccw0.cda; + pccw1++; } } - /* * Within the domain (@mdev), copy @n bytes from a guest physical * address (@iova) to a host physical address (@to). @@ -209,9 +196,15 @@ static long copy_from_iova(struct device *mdev, int i, ret; unsigned long l, m; - ret = pfn_array_alloc_pin(&pa, mdev, iova, n); - if (ret <= 0) + ret = pfn_array_alloc(&pa, iova, n); + if (ret < 0) + return ret; + + ret = pfn_array_pin(&pa, mdev); + if (ret < 0) { + pfn_array_unpin_free(&pa, mdev); return ret; + } l = n; for (i = 0; i < pa.pa_nr; i++) { @@ -235,55 +228,60 @@ static long copy_from_iova(struct device *mdev, return l; } -static long copy_ccw_from_iova(struct channel_program *cp, - struct ccw1 *to, u64 iova, - unsigned long len) -{ - struct ccw0 ccw0; - struct ccw1 *pccw1; - int ret; - int i; - - ret = copy_from_iova(cp->mdev, to, iova, len * sizeof(struct ccw1)); - if (ret) - return ret; - - if (!cp->orb.cmd.fmt) { - pccw1 = to; - for (i = 0; i < len; i++) { - ccw0 = *(struct ccw0 *)pccw1; - if ((pccw1->cmd_code & 0x0f) == CCW_CMD_TIC) { - pccw1->cmd_code = CCW_CMD_TIC; - pccw1->flags = 0; - pccw1->count = 0; - } else { - pccw1->cmd_code = ccw0.cmd_code; - pccw1->flags = ccw0.flags; - pccw1->count = ccw0.count; - } - pccw1->cda = ccw0.cda; - pccw1++; - } - } - - return ret; -} - /* * Helpers to operate ccwchain. */ -#define ccw_is_test(_ccw) (((_ccw)->cmd_code & 0x0F) == 0) +#define ccw_is_read(_ccw) (((_ccw)->cmd_code & 0x03) == 0x02) +#define ccw_is_read_backward(_ccw) (((_ccw)->cmd_code & 0x0F) == 0x0C) +#define ccw_is_sense(_ccw) (((_ccw)->cmd_code & 0x0F) == CCW_CMD_BASIC_SENSE) #define ccw_is_noop(_ccw) ((_ccw)->cmd_code == CCW_CMD_NOOP) #define ccw_is_tic(_ccw) ((_ccw)->cmd_code == CCW_CMD_TIC) #define ccw_is_idal(_ccw) ((_ccw)->flags & CCW_FLAG_IDA) - +#define ccw_is_skip(_ccw) ((_ccw)->flags & CCW_FLAG_SKIP) #define ccw_is_chain(_ccw) ((_ccw)->flags & (CCW_FLAG_CC | CCW_FLAG_DC)) /* + * ccw_does_data_transfer() + * + * Determine whether a CCW will move any data, such that the guest pages + * would need to be pinned before performing the I/O. + * + * Returns 1 if yes, 0 if no. + */ +static inline int ccw_does_data_transfer(struct ccw1 *ccw) +{ + /* If the count field is zero, then no data will be transferred */ + if (ccw->count == 0) + return 0; + + /* If the command is a NOP, then no data will be transferred */ + if (ccw_is_noop(ccw)) + return 0; + + /* If the skip flag is off, then data will be transferred */ + if (!ccw_is_skip(ccw)) + return 1; + + /* + * If the skip flag is on, it is only meaningful if the command + * code is a read, read backward, sense, or sense ID. In those + * cases, no data will be transferred. + */ + if (ccw_is_read(ccw) || ccw_is_read_backward(ccw)) + return 0; + + if (ccw_is_sense(ccw)) + return 0; + + /* The skip flag is on, but it is ignored for this command code. */ + return 1; +} + +/* * is_cpa_within_range() * * @cpa: channel program address being questioned @@ -319,7 +317,7 @@ static struct ccwchain *ccwchain_alloc(struct channel_program *cp, int len) /* Make ccw address aligned to 8. */ size = ((sizeof(*chain) + 7L) & -8L) + sizeof(*chain->ch_ccw) * len + - sizeof(*chain->ch_pat) * len; + sizeof(*chain->ch_pa) * len; chain = kzalloc(size, GFP_DMA | GFP_KERNEL); if (!chain) return NULL; @@ -328,7 +326,7 @@ static struct ccwchain *ccwchain_alloc(struct channel_program *cp, int len) chain->ch_ccw = (struct ccw1 *)data; data = (u8 *)(chain->ch_ccw) + sizeof(*chain->ch_ccw) * len; - chain->ch_pat = (struct pfn_array_table *)data; + chain->ch_pa = (struct pfn_array *)data; chain->ch_len = len; @@ -348,30 +346,12 @@ static void ccwchain_cda_free(struct ccwchain *chain, int idx) { struct ccw1 *ccw = chain->ch_ccw + idx; - if (ccw_is_test(ccw) || ccw_is_noop(ccw) || ccw_is_tic(ccw)) - return; - if (!ccw->count) + if (ccw_is_tic(ccw)) return; kfree((void *)(u64)ccw->cda); } -/* Unpin the pages then free the memory resources. */ -static void cp_unpin_free(struct channel_program *cp) -{ - struct ccwchain *chain, *temp; - int i; - - list_for_each_entry_safe(chain, temp, &cp->ccwchain_list, next) { - for (i = 0; i < chain->ch_len; i++) { - pfn_array_table_unpin_free(chain->ch_pat + i, - cp->mdev); - ccwchain_cda_free(chain, i); - } - ccwchain_free(chain); - } -} - /** * ccwchain_calc_length - calculate the length of the ccw chain. * @iova: guest physical address of the target ccw chain @@ -387,25 +367,9 @@ static void cp_unpin_free(struct channel_program *cp) */ static int ccwchain_calc_length(u64 iova, struct channel_program *cp) { - struct ccw1 *ccw, *p; - int cnt; - - /* - * Copy current chain from guest to host kernel. - * Currently the chain length is limited to CCWCHAIN_LEN_MAX (256). - * So copying 2K is enough (safe). - */ - p = ccw = kcalloc(CCWCHAIN_LEN_MAX, sizeof(*ccw), GFP_KERNEL); - if (!ccw) - return -ENOMEM; - - cnt = copy_ccw_from_iova(cp, ccw, iova, CCWCHAIN_LEN_MAX); - if (cnt) { - kfree(ccw); - return cnt; - } + struct ccw1 *ccw = cp->guest_cp; + int cnt = 0; - cnt = 0; do { cnt++; @@ -414,10 +378,8 @@ static int ccwchain_calc_length(u64 iova, struct channel_program *cp) * orb specified one of the unsupported formats, we defer * checking for IDAWs in unsupported formats to here. */ - if ((!cp->orb.cmd.c64 || cp->orb.cmd.i2k) && ccw_is_idal(ccw)) { - kfree(p); + if ((!cp->orb.cmd.c64 || cp->orb.cmd.i2k) && ccw_is_idal(ccw)) return -EOPNOTSUPP; - } /* * We want to keep counting if the current CCW has the @@ -436,7 +398,6 @@ static int ccwchain_calc_length(u64 iova, struct channel_program *cp) if (cnt == CCWCHAIN_LEN_MAX + 1) cnt = -EINVAL; - kfree(p); return cnt; } @@ -457,17 +418,23 @@ static int tic_target_chain_exists(struct ccw1 *tic, struct channel_program *cp) static int ccwchain_loop_tic(struct ccwchain *chain, struct channel_program *cp); -static int ccwchain_handle_tic(struct ccw1 *tic, struct channel_program *cp) +static int ccwchain_handle_ccw(u32 cda, struct channel_program *cp) { struct ccwchain *chain; - int len, ret; + int len; - /* May transfer to an existing chain. */ - if (tic_target_chain_exists(tic, cp)) - return 0; + /* Copy 2K (the most we support today) of possible CCWs */ + len = copy_from_iova(cp->mdev, cp->guest_cp, cda, + CCWCHAIN_LEN_MAX * sizeof(struct ccw1)); + if (len) + return len; + + /* Convert any Format-0 CCWs to Format-1 */ + if (!cp->orb.cmd.fmt) + convert_ccw0_to_ccw1(cp->guest_cp, CCWCHAIN_LEN_MAX); - /* Get chain length. */ - len = ccwchain_calc_length(tic->cda, cp); + /* Count the CCWs in the current chain */ + len = ccwchain_calc_length(cda, cp); if (len < 0) return len; @@ -475,14 +442,10 @@ static int ccwchain_handle_tic(struct ccw1 *tic, struct channel_program *cp) chain = ccwchain_alloc(cp, len); if (!chain) return -ENOMEM; - chain->ch_iova = tic->cda; + chain->ch_iova = cda; - /* Copy the new chain from user. */ - ret = copy_ccw_from_iova(cp, chain->ch_ccw, tic->cda, len); - if (ret) { - ccwchain_free(chain); - return ret; - } + /* Copy the actual CCWs into the new chain */ + memcpy(chain->ch_ccw, cp->guest_cp, len * sizeof(struct ccw1)); /* Loop for tics on this new chain. */ return ccwchain_loop_tic(chain, cp); @@ -500,7 +463,12 @@ static int ccwchain_loop_tic(struct ccwchain *chain, struct channel_program *cp) if (!ccw_is_tic(tic)) continue; - ret = ccwchain_handle_tic(tic, cp); + /* May transfer to an existing chain. */ + if (tic_target_chain_exists(tic, cp)) + continue; + + /* Build a ccwchain for the next segment */ + ret = ccwchain_handle_ccw(tic->cda, cp); if (ret) return ret; } @@ -533,115 +501,90 @@ static int ccwchain_fetch_direct(struct ccwchain *chain, struct channel_program *cp) { struct ccw1 *ccw; - struct pfn_array_table *pat; + struct pfn_array *pa; + u64 iova; unsigned long *idaws; int ret; + int bytes = 1; + int idaw_nr, idal_len; + int i; ccw = chain->ch_ccw + idx; - if (!ccw->count) { - /* - * We just want the translation result of any direct ccw - * to be an IDA ccw, so let's add the IDA flag for it. - * Although the flag will be ignored by firmware. - */ - ccw->flags |= CCW_FLAG_IDA; - return 0; - } + if (ccw->count) + bytes = ccw->count; - /* - * Pin data page(s) in memory. - * The number of pages actually is the count of the idaws which will be - * needed when translating a direct ccw to a idal ccw. - */ - pat = chain->ch_pat + idx; - ret = pfn_array_table_init(pat, 1); - if (ret) - goto out_init; - - ret = pfn_array_alloc_pin(pat->pat_pa, cp->mdev, ccw->cda, ccw->count); - if (ret < 0) - goto out_unpin; - - /* Translate this direct ccw to a idal ccw. */ - idaws = kcalloc(ret, sizeof(*idaws), GFP_DMA | GFP_KERNEL); - if (!idaws) { - ret = -ENOMEM; - goto out_unpin; + /* Calculate size of IDAL */ + if (ccw_is_idal(ccw)) { + /* Read first IDAW to see if it's 4K-aligned or not. */ + /* All subsequent IDAws will be 4K-aligned. */ + ret = copy_from_iova(cp->mdev, &iova, ccw->cda, sizeof(iova)); + if (ret) + return ret; + } else { + iova = ccw->cda; } - ccw->cda = (__u32) virt_to_phys(idaws); - ccw->flags |= CCW_FLAG_IDA; - - pfn_array_table_idal_create_words(pat, idaws); - - return 0; - -out_unpin: - pfn_array_table_unpin_free(pat, cp->mdev); -out_init: - ccw->cda = 0; - return ret; -} - -static int ccwchain_fetch_idal(struct ccwchain *chain, - int idx, - struct channel_program *cp) -{ - struct ccw1 *ccw; - struct pfn_array_table *pat; - unsigned long *idaws; - u64 idaw_iova; - unsigned int idaw_nr, idaw_len; - int i, ret; - - ccw = chain->ch_ccw + idx; + idaw_nr = idal_nr_words((void *)iova, bytes); + idal_len = idaw_nr * sizeof(*idaws); - if (!ccw->count) - return 0; - - /* Calculate size of idaws. */ - ret = copy_from_iova(cp->mdev, &idaw_iova, ccw->cda, sizeof(idaw_iova)); - if (ret) - return ret; - idaw_nr = idal_nr_words((void *)(idaw_iova), ccw->count); - idaw_len = idaw_nr * sizeof(*idaws); - - /* Pin data page(s) in memory. */ - pat = chain->ch_pat + idx; - ret = pfn_array_table_init(pat, idaw_nr); - if (ret) - goto out_init; - - /* Translate idal ccw to use new allocated idaws. */ - idaws = kzalloc(idaw_len, GFP_DMA | GFP_KERNEL); + /* Allocate an IDAL from host storage */ + idaws = kcalloc(idaw_nr, sizeof(*idaws), GFP_DMA | GFP_KERNEL); if (!idaws) { ret = -ENOMEM; - goto out_unpin; + goto out_init; } - ret = copy_from_iova(cp->mdev, idaws, ccw->cda, idaw_len); - if (ret) + /* + * Allocate an array of pfn's for pages to pin/translate. + * The number of pages is actually the count of the idaws + * required for the data transfer, since we only only support + * 4K IDAWs today. + */ + pa = chain->ch_pa + idx; + ret = pfn_array_alloc(pa, iova, bytes); + if (ret < 0) goto out_free_idaws; - ccw->cda = virt_to_phys(idaws); + if (ccw_is_idal(ccw)) { + /* Copy guest IDAL into host IDAL */ + ret = copy_from_iova(cp->mdev, idaws, ccw->cda, idal_len); + if (ret) + goto out_unpin; - for (i = 0; i < idaw_nr; i++) { - idaw_iova = *(idaws + i); + /* + * Copy guest IDAWs into pfn_array, in case the memory they + * occupy is not contiguous. + */ + for (i = 0; i < idaw_nr; i++) + pa->pa_iova_pfn[i] = idaws[i] >> PAGE_SHIFT; + } else { + /* + * No action is required here; the iova addresses in pfn_array + * were initialized sequentially in pfn_array_alloc() beginning + * with the contents of ccw->cda. + */ + } - ret = pfn_array_alloc_pin(pat->pat_pa + i, cp->mdev, - idaw_iova, 1); + if (ccw_does_data_transfer(ccw)) { + ret = pfn_array_pin(pa, cp->mdev); if (ret < 0) - goto out_free_idaws; + goto out_unpin; + } else { + pa->pa_nr = 0; } - pfn_array_table_idal_create_words(pat, idaws); + ccw->cda = (__u32) virt_to_phys(idaws); + ccw->flags |= CCW_FLAG_IDA; + + /* Populate the IDAL with pinned/translated addresses from pfn */ + pfn_array_idal_create_words(pa, idaws); return 0; +out_unpin: + pfn_array_unpin_free(pa, cp->mdev); out_free_idaws: kfree(idaws); -out_unpin: - pfn_array_table_unpin_free(pat, cp->mdev); out_init: ccw->cda = 0; return ret; @@ -659,15 +602,9 @@ static int ccwchain_fetch_one(struct ccwchain *chain, { struct ccw1 *ccw = chain->ch_ccw + idx; - if (ccw_is_test(ccw) || ccw_is_noop(ccw)) - return 0; - if (ccw_is_tic(ccw)) return ccwchain_fetch_tic(chain, idx, cp); - if (ccw_is_idal(ccw)) - return ccwchain_fetch_idal(chain, idx, cp); - return ccwchain_fetch_direct(chain, idx, cp); } @@ -690,9 +627,7 @@ static int ccwchain_fetch_one(struct ccwchain *chain, */ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb) { - u64 iova = orb->cmd.cpa; - struct ccwchain *chain; - int len, ret; + int ret; /* * XXX: @@ -705,33 +640,19 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb) memcpy(&cp->orb, orb, sizeof(*orb)); cp->mdev = mdev; - /* Get chain length. */ - len = ccwchain_calc_length(iova, cp); - if (len < 0) - return len; - - /* Alloc mem for the head chain. */ - chain = ccwchain_alloc(cp, len); - if (!chain) - return -ENOMEM; - chain->ch_iova = iova; - - /* Copy the head chain from guest. */ - ret = copy_ccw_from_iova(cp, chain->ch_ccw, iova, len); - if (ret) { - ccwchain_free(chain); - return ret; - } - - /* Now loop for its TICs. */ - ret = ccwchain_loop_tic(chain, cp); + /* Build a ccwchain for the first CCW segment */ + ret = ccwchain_handle_ccw(orb->cmd.cpa, cp); if (ret) - cp_unpin_free(cp); + cp_free(cp); + /* It is safe to force: if not set but idals used * ccwchain_calc_length returns an error. */ cp->orb.cmd.c64 = 1; + if (!ret) + cp->initialized = true; + return ret; } @@ -746,7 +667,20 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb) */ void cp_free(struct channel_program *cp) { - cp_unpin_free(cp); + struct ccwchain *chain, *temp; + int i; + + if (!cp->initialized) + return; + + cp->initialized = false; + list_for_each_entry_safe(chain, temp, &cp->ccwchain_list, next) { + for (i = 0; i < chain->ch_len; i++) { + pfn_array_unpin_free(chain->ch_pa + i, cp->mdev); + ccwchain_cda_free(chain, i); + } + ccwchain_free(chain); + } } /** @@ -791,6 +725,10 @@ int cp_prefetch(struct channel_program *cp) struct ccwchain *chain; int len, idx, ret; + /* this is an error in the caller */ + if (!cp->initialized) + return -EINVAL; + list_for_each_entry(chain, &cp->ccwchain_list, next) { len = chain->ch_len; for (idx = 0; idx < len; idx++) { @@ -826,6 +764,10 @@ union orb *cp_get_orb(struct channel_program *cp, u32 intparm, u8 lpm) struct ccwchain *chain; struct ccw1 *cpa; + /* this is an error in the caller */ + if (!cp->initialized) + return NULL; + orb = &cp->orb; orb->cmd.intparm = intparm; @@ -862,6 +804,9 @@ void cp_update_scsw(struct channel_program *cp, union scsw *scsw) u32 cpa = scsw->cmd.cpa; u32 ccw_head; + if (!cp->initialized) + return; + /* * LATER: * For now, only update the cmd.cpa part. We may need to deal with @@ -870,7 +815,11 @@ void cp_update_scsw(struct channel_program *cp, union scsw *scsw) */ list_for_each_entry(chain, &cp->ccwchain_list, next) { ccw_head = (u32)(u64)chain->ch_ccw; - if (is_cpa_within_range(cpa, ccw_head, chain->ch_len)) { + /* + * On successful execution, cpa points just beyond the end + * of the chain. + */ + if (is_cpa_within_range(cpa, ccw_head, chain->ch_len + 1)) { /* * (cpa - ccw_head) is the offset value of the host * physical ccw to its chain head. @@ -898,10 +847,12 @@ bool cp_iova_pinned(struct channel_program *cp, u64 iova) struct ccwchain *chain; int i; + if (!cp->initialized) + return false; + list_for_each_entry(chain, &cp->ccwchain_list, next) { for (i = 0; i < chain->ch_len; i++) - if (pfn_array_table_iova_pinned(chain->ch_pat + i, - iova)) + if (pfn_array_iova_pinned(chain->ch_pa + i, iova)) return true; } diff --git a/drivers/s390/cio/vfio_ccw_cp.h b/drivers/s390/cio/vfio_ccw_cp.h index a4b74fb1aa57..7cdc38049033 100644 --- a/drivers/s390/cio/vfio_ccw_cp.h +++ b/drivers/s390/cio/vfio_ccw_cp.h @@ -16,11 +16,18 @@ #include "orb.h" +/* + * Max length for ccw chain. + * XXX: Limit to 256, need to check more? + */ +#define CCWCHAIN_LEN_MAX 256 + /** * struct channel_program - manage information for channel program * @ccwchain_list: list head of ccwchains * @orb: orb for the currently processed ssch request * @mdev: the mediated device to perform page pinning/unpinning + * @initialized: whether this instance is actually initialized * * @ccwchain_list is the head of a ccwchain list, that contents the * translated result of the guest channel program that pointed out by @@ -30,6 +37,8 @@ struct channel_program { struct list_head ccwchain_list; union orb orb; struct device *mdev; + bool initialized; + struct ccw1 *guest_cp; }; extern int cp_init(struct channel_program *cp, struct device *mdev, diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c index 0b3b9de45c60..2b90a5ecaeb9 100644 --- a/drivers/s390/cio/vfio_ccw_drv.c +++ b/drivers/s390/cio/vfio_ccw_drv.c @@ -3,9 +3,11 @@ * VFIO based Physical Subchannel device driver * * Copyright IBM Corp. 2017 + * Copyright Red Hat, Inc. 2019 * * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com> * Xiao Feng Ren <renxiaof@linux.vnet.ibm.com> + * Cornelia Huck <cohuck@redhat.com> */ #include <linux/module.h> @@ -23,6 +25,7 @@ struct workqueue_struct *vfio_ccw_work_q; static struct kmem_cache *vfio_ccw_io_region; +static struct kmem_cache *vfio_ccw_cmd_region; /* * Helpers @@ -40,26 +43,30 @@ int vfio_ccw_sch_quiesce(struct subchannel *sch) if (ret != -EBUSY) goto out_unlock; + iretry = 255; do { - iretry = 255; ret = cio_cancel_halt_clear(sch, &iretry); - while (ret == -EBUSY) { - /* - * Flush all I/O and wait for - * cancel/halt/clear completion. - */ - private->completion = &completion; - spin_unlock_irq(sch->lock); - wait_for_completion_timeout(&completion, 3*HZ); + if (ret == -EIO) { + pr_err("vfio_ccw: could not quiesce subchannel 0.%x.%04x!\n", + sch->schid.ssid, sch->schid.sch_no); + break; + } + + /* + * Flush all I/O and wait for + * cancel/halt/clear completion. + */ + private->completion = &completion; + spin_unlock_irq(sch->lock); - spin_lock_irq(sch->lock); - private->completion = NULL; - flush_workqueue(vfio_ccw_work_q); - ret = cio_cancel_halt_clear(sch, &iretry); - }; + if (ret == -EBUSY) + wait_for_completion_timeout(&completion, 3*HZ); + private->completion = NULL; + flush_workqueue(vfio_ccw_work_q); + spin_lock_irq(sch->lock); ret = cio_disable_subchannel(sch); } while (ret == -EBUSY); out_unlock: @@ -84,13 +91,15 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work) if (is_final) cp_free(&private->cp); } + mutex_lock(&private->io_mutex); memcpy(private->io_region->irb_area, irb, sizeof(*irb)); - - if (private->io_trigger) - eventfd_signal(private->io_trigger, 1); + mutex_unlock(&private->io_mutex); if (private->mdev && is_final) private->state = VFIO_CCW_STATE_IDLE; + + if (private->io_trigger) + eventfd_signal(private->io_trigger, 1); } /* @@ -108,7 +117,7 @@ static int vfio_ccw_sch_probe(struct subchannel *sch) { struct pmcw *pmcw = &sch->schib.pmcw; struct vfio_ccw_private *private; - int ret; + int ret = -ENOMEM; if (pmcw->qf) { dev_warn(&sch->dev, "vfio: ccw: does not support QDIO: %s\n", @@ -120,15 +129,24 @@ static int vfio_ccw_sch_probe(struct subchannel *sch) if (!private) return -ENOMEM; + private->cp.guest_cp = kcalloc(CCWCHAIN_LEN_MAX, sizeof(struct ccw1), + GFP_KERNEL); + if (!private->cp.guest_cp) + goto out_free; + private->io_region = kmem_cache_zalloc(vfio_ccw_io_region, GFP_KERNEL | GFP_DMA); - if (!private->io_region) { - kfree(private); - return -ENOMEM; - } + if (!private->io_region) + goto out_free; + + private->cmd_region = kmem_cache_zalloc(vfio_ccw_cmd_region, + GFP_KERNEL | GFP_DMA); + if (!private->cmd_region) + goto out_free; private->sch = sch; dev_set_drvdata(&sch->dev, private); + mutex_init(&private->io_mutex); spin_lock_irq(sch->lock); private->state = VFIO_CCW_STATE_NOT_OPER; @@ -152,7 +170,11 @@ out_disable: cio_disable_subchannel(sch); out_free: dev_set_drvdata(&sch->dev, NULL); - kmem_cache_free(vfio_ccw_io_region, private->io_region); + if (private->cmd_region) + kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region); + if (private->io_region) + kmem_cache_free(vfio_ccw_io_region, private->io_region); + kfree(private->cp.guest_cp); kfree(private); return ret; } @@ -167,7 +189,9 @@ static int vfio_ccw_sch_remove(struct subchannel *sch) dev_set_drvdata(&sch->dev, NULL); + kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region); kmem_cache_free(vfio_ccw_io_region, private->io_region); + kfree(private->cp.guest_cp); kfree(private); return 0; @@ -241,7 +265,7 @@ static struct css_driver vfio_ccw_sch_driver = { static int __init vfio_ccw_sch_init(void) { - int ret; + int ret = -ENOMEM; vfio_ccw_work_q = create_singlethread_workqueue("vfio-ccw"); if (!vfio_ccw_work_q) @@ -251,20 +275,30 @@ static int __init vfio_ccw_sch_init(void) sizeof(struct ccw_io_region), 0, SLAB_ACCOUNT, 0, sizeof(struct ccw_io_region), NULL); - if (!vfio_ccw_io_region) { - destroy_workqueue(vfio_ccw_work_q); - return -ENOMEM; - } + if (!vfio_ccw_io_region) + goto out_err; + + vfio_ccw_cmd_region = kmem_cache_create_usercopy("vfio_ccw_cmd_region", + sizeof(struct ccw_cmd_region), 0, + SLAB_ACCOUNT, 0, + sizeof(struct ccw_cmd_region), NULL); + if (!vfio_ccw_cmd_region) + goto out_err; isc_register(VFIO_CCW_ISC); ret = css_driver_register(&vfio_ccw_sch_driver); if (ret) { isc_unregister(VFIO_CCW_ISC); - kmem_cache_destroy(vfio_ccw_io_region); - destroy_workqueue(vfio_ccw_work_q); + goto out_err; } return ret; + +out_err: + kmem_cache_destroy(vfio_ccw_cmd_region); + kmem_cache_destroy(vfio_ccw_io_region); + destroy_workqueue(vfio_ccw_work_q); + return ret; } static void __exit vfio_ccw_sch_exit(void) @@ -272,6 +306,7 @@ static void __exit vfio_ccw_sch_exit(void) css_driver_unregister(&vfio_ccw_sch_driver); isc_unregister(VFIO_CCW_ISC); kmem_cache_destroy(vfio_ccw_io_region); + kmem_cache_destroy(vfio_ccw_cmd_region); destroy_workqueue(vfio_ccw_work_q); } module_init(vfio_ccw_sch_init); diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c index cab17865aafe..49d9d3da0282 100644 --- a/drivers/s390/cio/vfio_ccw_fsm.c +++ b/drivers/s390/cio/vfio_ccw_fsm.c @@ -3,8 +3,10 @@ * Finite state machine for vfio-ccw device handling * * Copyright IBM Corp. 2017 + * Copyright Red Hat, Inc. 2019 * * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com> + * Cornelia Huck <cohuck@redhat.com> */ #include <linux/vfio.h> @@ -28,9 +30,12 @@ static int fsm_io_helper(struct vfio_ccw_private *private) sch = private->sch; spin_lock_irqsave(sch->lock, flags); - private->state = VFIO_CCW_STATE_BUSY; orb = cp_get_orb(&private->cp, (u32)(addr_t)sch, sch->lpm); + if (!orb) { + ret = -EIO; + goto out; + } /* Issue "Start Subchannel" */ ccode = ssch(sch->schid, orb); @@ -42,6 +47,7 @@ static int fsm_io_helper(struct vfio_ccw_private *private) */ sch->schib.scsw.cmd.actl |= SCSW_ACTL_START_PEND; ret = 0; + private->state = VFIO_CCW_STATE_CP_PENDING; break; case 1: /* Status pending */ case 2: /* Busy */ @@ -64,6 +70,76 @@ static int fsm_io_helper(struct vfio_ccw_private *private) default: ret = ccode; } +out: + spin_unlock_irqrestore(sch->lock, flags); + return ret; +} + +static int fsm_do_halt(struct vfio_ccw_private *private) +{ + struct subchannel *sch; + unsigned long flags; + int ccode; + int ret; + + sch = private->sch; + + spin_lock_irqsave(sch->lock, flags); + + /* Issue "Halt Subchannel" */ + ccode = hsch(sch->schid); + + switch (ccode) { + case 0: + /* + * Initialize device status information + */ + sch->schib.scsw.cmd.actl |= SCSW_ACTL_HALT_PEND; + ret = 0; + break; + case 1: /* Status pending */ + case 2: /* Busy */ + ret = -EBUSY; + break; + case 3: /* Device not operational */ + ret = -ENODEV; + break; + default: + ret = ccode; + } + spin_unlock_irqrestore(sch->lock, flags); + return ret; +} + +static int fsm_do_clear(struct vfio_ccw_private *private) +{ + struct subchannel *sch; + unsigned long flags; + int ccode; + int ret; + + sch = private->sch; + + spin_lock_irqsave(sch->lock, flags); + + /* Issue "Clear Subchannel" */ + ccode = csch(sch->schid); + + switch (ccode) { + case 0: + /* + * Initialize device status information + */ + sch->schib.scsw.cmd.actl = SCSW_ACTL_CLEAR_PEND; + /* TODO: check what else we might need to clear */ + ret = 0; + break; + case 3: /* Device not operational */ + ret = -ENODEV; + break; + default: + ret = ccode; + } spin_unlock_irqrestore(sch->lock, flags); return ret; } @@ -102,6 +178,30 @@ static void fsm_io_busy(struct vfio_ccw_private *private, private->io_region->ret_code = -EBUSY; } +static void fsm_io_retry(struct vfio_ccw_private *private, + enum vfio_ccw_event event) +{ + private->io_region->ret_code = -EAGAIN; +} + +static void fsm_async_error(struct vfio_ccw_private *private, + enum vfio_ccw_event event) +{ + struct ccw_cmd_region *cmd_region = private->cmd_region; + + pr_err("vfio-ccw: FSM: %s request from state:%d\n", + cmd_region->command == VFIO_CCW_ASYNC_CMD_HSCH ? "halt" : + cmd_region->command == VFIO_CCW_ASYNC_CMD_CSCH ? "clear" : + "<unknown>", private->state); + cmd_region->ret_code = -EIO; +} + +static void fsm_async_retry(struct vfio_ccw_private *private, + enum vfio_ccw_event event) +{ + private->cmd_region->ret_code = -EAGAIN; +} + static void fsm_disabled_irq(struct vfio_ccw_private *private, enum vfio_ccw_event event) { @@ -130,8 +230,7 @@ static void fsm_io_request(struct vfio_ccw_private *private, struct mdev_device *mdev = private->mdev; char *errstr = "request"; - private->state = VFIO_CCW_STATE_BUSY; - + private->state = VFIO_CCW_STATE_CP_PROCESSING; memcpy(scsw, io_region->scsw_area, sizeof(*scsw)); if (scsw->cmd.fctl & SCSW_FCTL_START_FUNC) { @@ -166,22 +265,42 @@ static void fsm_io_request(struct vfio_ccw_private *private, } return; } else if (scsw->cmd.fctl & SCSW_FCTL_HALT_FUNC) { - /* XXX: Handle halt. */ + /* halt is handled via the async cmd region */ io_region->ret_code = -EOPNOTSUPP; goto err_out; } else if (scsw->cmd.fctl & SCSW_FCTL_CLEAR_FUNC) { - /* XXX: Handle clear. */ + /* clear is handled via the async cmd region */ io_region->ret_code = -EOPNOTSUPP; goto err_out; } err_out: - private->state = VFIO_CCW_STATE_IDLE; trace_vfio_ccw_io_fctl(scsw->cmd.fctl, get_schid(private), io_region->ret_code, errstr); } /* + * Deal with an async request from userspace. + */ +static void fsm_async_request(struct vfio_ccw_private *private, + enum vfio_ccw_event event) +{ + struct ccw_cmd_region *cmd_region = private->cmd_region; + + switch (cmd_region->command) { + case VFIO_CCW_ASYNC_CMD_HSCH: + cmd_region->ret_code = fsm_do_halt(private); + break; + case VFIO_CCW_ASYNC_CMD_CSCH: + cmd_region->ret_code = fsm_do_clear(private); + break; + default: + /* should not happen? */ + cmd_region->ret_code = -EINVAL; + } +} + +/* * Got an interrupt for a normal io (state busy). */ static void fsm_irq(struct vfio_ccw_private *private, @@ -204,21 +323,31 @@ fsm_func_t *vfio_ccw_jumptable[NR_VFIO_CCW_STATES][NR_VFIO_CCW_EVENTS] = { [VFIO_CCW_STATE_NOT_OPER] = { [VFIO_CCW_EVENT_NOT_OPER] = fsm_nop, [VFIO_CCW_EVENT_IO_REQ] = fsm_io_error, + [VFIO_CCW_EVENT_ASYNC_REQ] = fsm_async_error, [VFIO_CCW_EVENT_INTERRUPT] = fsm_disabled_irq, }, [VFIO_CCW_STATE_STANDBY] = { [VFIO_CCW_EVENT_NOT_OPER] = fsm_notoper, [VFIO_CCW_EVENT_IO_REQ] = fsm_io_error, + [VFIO_CCW_EVENT_ASYNC_REQ] = fsm_async_error, [VFIO_CCW_EVENT_INTERRUPT] = fsm_irq, }, [VFIO_CCW_STATE_IDLE] = { [VFIO_CCW_EVENT_NOT_OPER] = fsm_notoper, [VFIO_CCW_EVENT_IO_REQ] = fsm_io_request, + [VFIO_CCW_EVENT_ASYNC_REQ] = fsm_async_request, + [VFIO_CCW_EVENT_INTERRUPT] = fsm_irq, + }, + [VFIO_CCW_STATE_CP_PROCESSING] = { + [VFIO_CCW_EVENT_NOT_OPER] = fsm_notoper, + [VFIO_CCW_EVENT_IO_REQ] = fsm_io_retry, + [VFIO_CCW_EVENT_ASYNC_REQ] = fsm_async_retry, [VFIO_CCW_EVENT_INTERRUPT] = fsm_irq, }, - [VFIO_CCW_STATE_BUSY] = { + [VFIO_CCW_STATE_CP_PENDING] = { [VFIO_CCW_EVENT_NOT_OPER] = fsm_notoper, [VFIO_CCW_EVENT_IO_REQ] = fsm_io_busy, + [VFIO_CCW_EVENT_ASYNC_REQ] = fsm_async_request, [VFIO_CCW_EVENT_INTERRUPT] = fsm_irq, }, }; diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c index f673e106c041..5eb61116ca6f 100644 --- a/drivers/s390/cio/vfio_ccw_ops.c +++ b/drivers/s390/cio/vfio_ccw_ops.c @@ -3,13 +3,17 @@ * Physical device callbacks for vfio_ccw * * Copyright IBM Corp. 2017 + * Copyright Red Hat, Inc. 2019 * * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com> * Xiao Feng Ren <renxiaof@linux.vnet.ibm.com> + * Cornelia Huck <cohuck@redhat.com> */ #include <linux/vfio.h> #include <linux/mdev.h> +#include <linux/nospec.h> +#include <linux/slab.h> #include "vfio_ccw_private.h" @@ -130,11 +134,12 @@ static int vfio_ccw_mdev_remove(struct mdev_device *mdev) if ((private->state != VFIO_CCW_STATE_NOT_OPER) && (private->state != VFIO_CCW_STATE_STANDBY)) { - if (!vfio_ccw_mdev_reset(mdev)) + if (!vfio_ccw_sch_quiesce(private->sch)) private->state = VFIO_CCW_STATE_STANDBY; /* The state will be NOT_OPER on error. */ } + cp_free(&private->cp); private->mdev = NULL; atomic_inc(&private->avail); @@ -146,20 +151,66 @@ static int vfio_ccw_mdev_open(struct mdev_device *mdev) struct vfio_ccw_private *private = dev_get_drvdata(mdev_parent_dev(mdev)); unsigned long events = VFIO_IOMMU_NOTIFY_DMA_UNMAP; + int ret; private->nb.notifier_call = vfio_ccw_mdev_notifier; - return vfio_register_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY, - &events, &private->nb); + ret = vfio_register_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY, + &events, &private->nb); + if (ret) + return ret; + + ret = vfio_ccw_register_async_dev_regions(private); + if (ret) + vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY, + &private->nb); + return ret; } static void vfio_ccw_mdev_release(struct mdev_device *mdev) { struct vfio_ccw_private *private = dev_get_drvdata(mdev_parent_dev(mdev)); + int i; + if ((private->state != VFIO_CCW_STATE_NOT_OPER) && + (private->state != VFIO_CCW_STATE_STANDBY)) { + if (!vfio_ccw_mdev_reset(mdev)) + private->state = VFIO_CCW_STATE_STANDBY; + /* The state will be NOT_OPER on error. */ + } + + cp_free(&private->cp); vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY, &private->nb); + + for (i = 0; i < private->num_regions; i++) + private->region[i].ops->release(private, &private->region[i]); + + private->num_regions = 0; + kfree(private->region); + private->region = NULL; +} + +static ssize_t vfio_ccw_mdev_read_io_region(struct vfio_ccw_private *private, + char __user *buf, size_t count, + loff_t *ppos) +{ + loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK; + struct ccw_io_region *region; + int ret; + + if (pos + count > sizeof(*region)) + return -EINVAL; + + mutex_lock(&private->io_mutex); + region = private->io_region; + if (copy_to_user(buf, (void *)region + pos, count)) + ret = -EFAULT; + else + ret = count; + mutex_unlock(&private->io_mutex); + return ret; } static ssize_t vfio_ccw_mdev_read(struct mdev_device *mdev, @@ -167,18 +218,54 @@ static ssize_t vfio_ccw_mdev_read(struct mdev_device *mdev, size_t count, loff_t *ppos) { + unsigned int index = VFIO_CCW_OFFSET_TO_INDEX(*ppos); struct vfio_ccw_private *private; + + private = dev_get_drvdata(mdev_parent_dev(mdev)); + + if (index >= VFIO_CCW_NUM_REGIONS + private->num_regions) + return -EINVAL; + + switch (index) { + case VFIO_CCW_CONFIG_REGION_INDEX: + return vfio_ccw_mdev_read_io_region(private, buf, count, ppos); + default: + index -= VFIO_CCW_NUM_REGIONS; + return private->region[index].ops->read(private, buf, count, + ppos); + } + + return -EINVAL; +} + +static ssize_t vfio_ccw_mdev_write_io_region(struct vfio_ccw_private *private, + const char __user *buf, + size_t count, loff_t *ppos) +{ + loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK; struct ccw_io_region *region; + int ret; - if (*ppos + count > sizeof(*region)) + if (pos + count > sizeof(*region)) return -EINVAL; - private = dev_get_drvdata(mdev_parent_dev(mdev)); + if (!mutex_trylock(&private->io_mutex)) + return -EAGAIN; + region = private->io_region; - if (copy_to_user(buf, (void *)region + *ppos, count)) - return -EFAULT; + if (copy_from_user((void *)region + pos, buf, count)) { + ret = -EFAULT; + goto out_unlock; + } - return count; + vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_IO_REQ); + if (region->ret_code != 0) + private->state = VFIO_CCW_STATE_IDLE; + ret = (region->ret_code != 0) ? region->ret_code : count; + +out_unlock: + mutex_unlock(&private->io_mutex); + return ret; } static ssize_t vfio_ccw_mdev_write(struct mdev_device *mdev, @@ -186,42 +273,47 @@ static ssize_t vfio_ccw_mdev_write(struct mdev_device *mdev, size_t count, loff_t *ppos) { + unsigned int index = VFIO_CCW_OFFSET_TO_INDEX(*ppos); struct vfio_ccw_private *private; - struct ccw_io_region *region; - - if (*ppos + count > sizeof(*region)) - return -EINVAL; private = dev_get_drvdata(mdev_parent_dev(mdev)); - if (private->state != VFIO_CCW_STATE_IDLE) - return -EACCES; - region = private->io_region; - if (copy_from_user((void *)region + *ppos, buf, count)) - return -EFAULT; + if (index >= VFIO_CCW_NUM_REGIONS + private->num_regions) + return -EINVAL; - vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_IO_REQ); - if (region->ret_code != 0) { - private->state = VFIO_CCW_STATE_IDLE; - return region->ret_code; + switch (index) { + case VFIO_CCW_CONFIG_REGION_INDEX: + return vfio_ccw_mdev_write_io_region(private, buf, count, ppos); + default: + index -= VFIO_CCW_NUM_REGIONS; + return private->region[index].ops->write(private, buf, count, + ppos); } - return count; + return -EINVAL; } -static int vfio_ccw_mdev_get_device_info(struct vfio_device_info *info) +static int vfio_ccw_mdev_get_device_info(struct vfio_device_info *info, + struct mdev_device *mdev) { + struct vfio_ccw_private *private; + + private = dev_get_drvdata(mdev_parent_dev(mdev)); info->flags = VFIO_DEVICE_FLAGS_CCW | VFIO_DEVICE_FLAGS_RESET; - info->num_regions = VFIO_CCW_NUM_REGIONS; + info->num_regions = VFIO_CCW_NUM_REGIONS + private->num_regions; info->num_irqs = VFIO_CCW_NUM_IRQS; return 0; } static int vfio_ccw_mdev_get_region_info(struct vfio_region_info *info, - u16 *cap_type_id, - void **cap_type) + struct mdev_device *mdev, + unsigned long arg) { + struct vfio_ccw_private *private; + int i; + + private = dev_get_drvdata(mdev_parent_dev(mdev)); switch (info->index) { case VFIO_CCW_CONFIG_REGION_INDEX: info->offset = 0; @@ -229,9 +321,55 @@ static int vfio_ccw_mdev_get_region_info(struct vfio_region_info *info, info->flags = VFIO_REGION_INFO_FLAG_READ | VFIO_REGION_INFO_FLAG_WRITE; return 0; - default: - return -EINVAL; + default: /* all other regions are handled via capability chain */ + { + struct vfio_info_cap caps = { .buf = NULL, .size = 0 }; + struct vfio_region_info_cap_type cap_type = { + .header.id = VFIO_REGION_INFO_CAP_TYPE, + .header.version = 1 }; + int ret; + + if (info->index >= + VFIO_CCW_NUM_REGIONS + private->num_regions) + return -EINVAL; + + info->index = array_index_nospec(info->index, + VFIO_CCW_NUM_REGIONS + + private->num_regions); + + i = info->index - VFIO_CCW_NUM_REGIONS; + + info->offset = VFIO_CCW_INDEX_TO_OFFSET(info->index); + info->size = private->region[i].size; + info->flags = private->region[i].flags; + + cap_type.type = private->region[i].type; + cap_type.subtype = private->region[i].subtype; + + ret = vfio_info_add_capability(&caps, &cap_type.header, + sizeof(cap_type)); + if (ret) + return ret; + + info->flags |= VFIO_REGION_INFO_FLAG_CAPS; + if (info->argsz < sizeof(*info) + caps.size) { + info->argsz = sizeof(*info) + caps.size; + info->cap_offset = 0; + } else { + vfio_info_cap_shift(&caps, sizeof(*info)); + if (copy_to_user((void __user *)arg + sizeof(*info), + caps.buf, caps.size)) { + kfree(caps.buf); + return -EFAULT; + } + info->cap_offset = sizeof(*info); + } + + kfree(caps.buf); + } + } + return 0; } static int vfio_ccw_mdev_get_irq_info(struct vfio_irq_info *info) @@ -308,6 +446,32 @@ static int vfio_ccw_mdev_set_irqs(struct mdev_device *mdev, } } +int vfio_ccw_register_dev_region(struct vfio_ccw_private *private, + unsigned int subtype, + const struct vfio_ccw_regops *ops, + size_t size, u32 flags, void *data) +{ + struct vfio_ccw_region *region; + + region = krealloc(private->region, + (private->num_regions + 1) * sizeof(*region), + GFP_KERNEL); + if (!region) + return -ENOMEM; + + private->region = region; + private->region[private->num_regions].type = VFIO_REGION_TYPE_CCW; + private->region[private->num_regions].subtype = subtype; + private->region[private->num_regions].ops = ops; + private->region[private->num_regions].size = size; + private->region[private->num_regions].flags = flags; + private->region[private->num_regions].data = data; + + private->num_regions++; + + return 0; +} + static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev, unsigned int cmd, unsigned long arg) @@ -328,7 +492,7 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev, if (info.argsz < minsz) return -EINVAL; - ret = vfio_ccw_mdev_get_device_info(&info); + ret = vfio_ccw_mdev_get_device_info(&info, mdev); if (ret) return ret; @@ -337,8 +501,6 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev, case VFIO_DEVICE_GET_REGION_INFO: { struct vfio_region_info info; - u16 cap_type_id = 0; - void *cap_type = NULL; minsz = offsetofend(struct vfio_region_info, offset); @@ -348,8 +510,7 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev, if (info.argsz < minsz) return -EINVAL; - ret = vfio_ccw_mdev_get_region_info(&info, &cap_type_id, - &cap_type); + ret = vfio_ccw_mdev_get_region_info(&info, mdev, arg); if (ret) return ret; diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h index 08e9a7dc9176..f1092c3dc1b1 100644 --- a/drivers/s390/cio/vfio_ccw_private.h +++ b/drivers/s390/cio/vfio_ccw_private.h @@ -3,9 +3,11 @@ * Private stuff for vfio_ccw driver * * Copyright IBM Corp. 2017 + * Copyright Red Hat, Inc. 2019 * * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com> * Xiao Feng Ren <renxiaof@linux.vnet.ibm.com> + * Cornelia Huck <cohuck@redhat.com> */ #ifndef _VFIO_CCW_PRIVATE_H_ @@ -19,6 +21,40 @@ #include "css.h" #include "vfio_ccw_cp.h" +#define VFIO_CCW_OFFSET_SHIFT 10 +#define VFIO_CCW_OFFSET_TO_INDEX(off) (off >> VFIO_CCW_OFFSET_SHIFT) +#define VFIO_CCW_INDEX_TO_OFFSET(index) ((u64)(index) << VFIO_CCW_OFFSET_SHIFT) +#define VFIO_CCW_OFFSET_MASK (((u64)(1) << VFIO_CCW_OFFSET_SHIFT) - 1) + +/* capability chain handling similar to vfio-pci */ +struct vfio_ccw_private; +struct vfio_ccw_region; + +struct vfio_ccw_regops { + ssize_t (*read)(struct vfio_ccw_private *private, char __user *buf, + size_t count, loff_t *ppos); + ssize_t (*write)(struct vfio_ccw_private *private, + const char __user *buf, size_t count, loff_t *ppos); + void (*release)(struct vfio_ccw_private *private, + struct vfio_ccw_region *region); +}; + +struct vfio_ccw_region { + u32 type; + u32 subtype; + const struct vfio_ccw_regops *ops; + void *data; + size_t size; + u32 flags; +}; + +int vfio_ccw_register_dev_region(struct vfio_ccw_private *private, + unsigned int subtype, + const struct vfio_ccw_regops *ops, + size_t size, u32 flags, void *data); + +int vfio_ccw_register_async_dev_regions(struct vfio_ccw_private *private); + /** * struct vfio_ccw_private * @sch: pointer to the subchannel @@ -28,6 +64,10 @@ * @mdev: pointer to the mediated device * @nb: notifier for vfio events * @io_region: MMIO region to input/output I/O arguments/results + * @io_mutex: protect against concurrent update of I/O regions + * @region: additional regions for other subchannel operations + * @cmd_region: MMIO region for asynchronous I/O commands other than START + * @num_regions: number of additional regions * @cp: channel program for the current I/O operation * @irb: irb info received from interrupt * @scsw: scsw info @@ -42,6 +82,10 @@ struct vfio_ccw_private { struct mdev_device *mdev; struct notifier_block nb; struct ccw_io_region *io_region; + struct mutex io_mutex; + struct vfio_ccw_region *region; + struct ccw_cmd_region *cmd_region; + int num_regions; struct channel_program cp; struct irb irb; @@ -63,7 +107,8 @@ enum vfio_ccw_state { VFIO_CCW_STATE_NOT_OPER, VFIO_CCW_STATE_STANDBY, VFIO_CCW_STATE_IDLE, - VFIO_CCW_STATE_BUSY, + VFIO_CCW_STATE_CP_PROCESSING, + VFIO_CCW_STATE_CP_PENDING, /* last element! */ NR_VFIO_CCW_STATES }; @@ -75,6 +120,7 @@ enum vfio_ccw_event { VFIO_CCW_EVENT_NOT_OPER, VFIO_CCW_EVENT_IO_REQ, VFIO_CCW_EVENT_INTERRUPT, + VFIO_CCW_EVENT_ASYNC_REQ, /* last element! */ NR_VFIO_CCW_EVENTS }; diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 1546389d71db..a76b8a8bcbbb 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -116,7 +116,7 @@ static int user_set_domain; static struct bus_type ap_bus_type; /* Adapter interrupt definitions */ -static void ap_interrupt_handler(struct airq_struct *airq); +static void ap_interrupt_handler(struct airq_struct *airq, bool floating); static int ap_airq_flag; @@ -208,7 +208,6 @@ static inline int ap_query_configuration(struct ap_config_info *info) return -EINVAL; return ap_qci(info); } -EXPORT_SYMBOL(ap_query_configuration); /** * ap_init_configuration(): Allocate and query configuration array. @@ -254,19 +253,37 @@ static inline int ap_test_config_card_id(unsigned int id) } /* - * ap_test_config_domain(): Test, whether an AP usage domain is configured. + * ap_test_config_usage_domain(): Test, whether an AP usage domain + * is configured. * @domain AP usage domain ID * * Returns 0 if the usage domain is not configured * 1 if the usage domain is configured or * if the configuration information is not available */ -static inline int ap_test_config_domain(unsigned int domain) +int ap_test_config_usage_domain(unsigned int domain) { if (!ap_configuration) /* QCI not supported */ return domain < 16; return ap_test_config(ap_configuration->aqm, domain); } +EXPORT_SYMBOL(ap_test_config_usage_domain); + +/* + * ap_test_config_ctrl_domain(): Test, whether an AP control domain + * is configured. + * @domain AP control domain ID + * + * Returns 1 if the control domain is configured + * 0 in all other cases + */ +int ap_test_config_ctrl_domain(unsigned int domain) +{ + if (!ap_configuration) /* QCI not supported */ + return 0; + return ap_test_config(ap_configuration->adm, domain); +} +EXPORT_SYMBOL(ap_test_config_ctrl_domain); /** * ap_query_queue(): Check if an AP queue is available. @@ -393,7 +410,7 @@ static enum hrtimer_restart ap_poll_timeout(struct hrtimer *unused) * ap_interrupt_handler() - Schedule ap_tasklet on interrupt * @airq: pointer to adapter interrupt descriptor */ -static void ap_interrupt_handler(struct airq_struct *airq) +static void ap_interrupt_handler(struct airq_struct *airq, bool floating) { inc_irq_stat(IRQIO_APB); if (!ap_suspend_flag) @@ -1267,7 +1284,7 @@ static void ap_select_domain(void) best_domain = -1; max_count = 0; for (i = 0; i < AP_DOMAINS; i++) { - if (!ap_test_config_domain(i) || + if (!ap_test_config_usage_domain(i) || !test_bit_inv(i, ap_perms.aqm)) continue; count = 0; @@ -1338,16 +1355,16 @@ static int ap_get_compatible_type(ap_qid_t qid, int rawtype, unsigned int func) * Helper function to be used with bus_find_dev * matches for the card device with the given id */ -static int __match_card_device_with_id(struct device *dev, void *data) +static int __match_card_device_with_id(struct device *dev, const void *data) { - return is_card_dev(dev) && to_ap_card(dev)->id == (int)(long) data; + return is_card_dev(dev) && to_ap_card(dev)->id == (int)(long)(void *) data; } /* * Helper function to be used with bus_find_dev * matches for the queue device with a given qid */ -static int __match_queue_device_with_qid(struct device *dev, void *data) +static int __match_queue_device_with_qid(struct device *dev, const void *data) { return is_queue_dev(dev) && to_ap_queue(dev)->qid == (int)(long) data; } @@ -1356,7 +1373,7 @@ static int __match_queue_device_with_qid(struct device *dev, void *data) * Helper function to be used with bus_find_dev * matches any queue device with given queue id */ -static int __match_queue_device_with_queue_id(struct device *dev, void *data) +static int __match_queue_device_with_queue_id(struct device *dev, const void *data) { return is_queue_dev(dev) && AP_QID_QUEUE(to_ap_queue(dev)->qid) == (int)(long) data; @@ -1442,7 +1459,7 @@ static void _ap_scan_bus_adapter(int id) (void *)(long) qid, __match_queue_device_with_qid); aq = dev ? to_ap_queue(dev) : NULL; - if (!ap_test_config_domain(dom)) { + if (!ap_test_config_usage_domain(dom)) { if (dev) { /* Queue device exists but has been * removed from configuration. diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index 15a98a673c5c..6f3cf37776ca 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -251,6 +251,9 @@ void ap_wait(enum ap_wait wait); void ap_request_timeout(struct timer_list *t); void ap_bus_force_rescan(void); +int ap_test_config_usage_domain(unsigned int domain); +int ap_test_config_ctrl_domain(unsigned int domain); + void ap_queue_init_reply(struct ap_queue *aq, struct ap_message *ap_msg); struct ap_queue *ap_queue_create(ap_qid_t qid, int device_type); void ap_queue_prepare_remove(struct ap_queue *aq); diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index 45eb0c14b880..7f418d2d8cdf 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -690,7 +690,7 @@ int pkey_clr2protkey(u32 keytype, */ if (!cpacf_test_func(&pckmo_functions, fc)) { DEBUG_ERR("%s pckmo functions not available\n", __func__); - return -EOPNOTSUPP; + return -ENODEV; } /* prepare param block */ @@ -1695,15 +1695,15 @@ static int __init pkey_init(void) * are able to work with protected keys. */ if (!cpacf_query(CPACF_PCKMO, &pckmo_functions)) - return -EOPNOTSUPP; + return -ENODEV; /* check for kmc instructions available */ if (!cpacf_query(CPACF_KMC, &kmc_functions)) - return -EOPNOTSUPP; + return -ENODEV; if (!cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_128) || !cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_192) || !cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_256)) - return -EOPNOTSUPP; + return -ENODEV; pkey_debug_init(); diff --git a/drivers/s390/crypto/vfio_ap_drv.c b/drivers/s390/crypto/vfio_ap_drv.c index e9824c35c34f..003662aa8060 100644 --- a/drivers/s390/crypto/vfio_ap_drv.c +++ b/drivers/s390/crypto/vfio_ap_drv.c @@ -5,6 +5,7 @@ * Copyright IBM Corp. 2018 * * Author(s): Tony Krowiak <akrowiak@linux.ibm.com> + * Pierre Morel <pmorel@linux.ibm.com> */ #include <linux/module.h> @@ -40,14 +41,45 @@ static struct ap_device_id ap_queue_ids[] = { MODULE_DEVICE_TABLE(vfio_ap, ap_queue_ids); +/** + * vfio_ap_queue_dev_probe: + * + * Allocate a vfio_ap_queue structure and associate it + * with the device as driver_data. + */ static int vfio_ap_queue_dev_probe(struct ap_device *apdev) { + struct vfio_ap_queue *q; + + q = kzalloc(sizeof(*q), GFP_KERNEL); + if (!q) + return -ENOMEM; + dev_set_drvdata(&apdev->device, q); + q->apqn = to_ap_queue(&apdev->device)->qid; + q->saved_isc = VFIO_AP_ISC_INVALID; return 0; } +/** + * vfio_ap_queue_dev_remove: + * + * Takes the matrix lock to avoid actions on this device while removing + * Free the associated vfio_ap_queue structure + */ static void vfio_ap_queue_dev_remove(struct ap_device *apdev) { - /* Nothing to do yet */ + struct vfio_ap_queue *q; + int apid, apqi; + + mutex_lock(&matrix_dev->lock); + q = dev_get_drvdata(&apdev->device); + dev_set_drvdata(&apdev->device, NULL); + apid = AP_QID_CARD(q->apqn); + apqi = AP_QID_QUEUE(q->apqn); + vfio_ap_mdev_reset_queue(apid, apqi, 1); + vfio_ap_irq_disable(q); + kfree(q); + mutex_unlock(&matrix_dev->lock); } static void vfio_ap_matrix_dev_release(struct device *dev) diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index 900b9cf20ca5..0604b49a4d32 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -24,6 +24,295 @@ #define VFIO_AP_MDEV_TYPE_HWVIRT "passthrough" #define VFIO_AP_MDEV_NAME_HWVIRT "VFIO AP Passthrough Device" +static int vfio_ap_mdev_reset_queues(struct mdev_device *mdev); + +static int match_apqn(struct device *dev, const void *data) +{ + struct vfio_ap_queue *q = dev_get_drvdata(dev); + + return (q->apqn == *(int *)(data)) ? 1 : 0; +} + +/** + * vfio_ap_get_queue: Retrieve a queue with a specific APQN from a list + * @matrix_mdev: the associated mediated matrix + * @apqn: The queue APQN + * + * Retrieve a queue with a specific APQN from the list of the + * devices of the vfio_ap_drv. + * Verify that the APID and the APQI are set in the matrix. + * + * Returns the pointer to the associated vfio_ap_queue + */ +static struct vfio_ap_queue *vfio_ap_get_queue( + struct ap_matrix_mdev *matrix_mdev, + int apqn) +{ + struct vfio_ap_queue *q; + struct device *dev; + + if (!test_bit_inv(AP_QID_CARD(apqn), matrix_mdev->matrix.apm)) + return NULL; + if (!test_bit_inv(AP_QID_QUEUE(apqn), matrix_mdev->matrix.aqm)) + return NULL; + + dev = driver_find_device(&matrix_dev->vfio_ap_drv->driver, NULL, + &apqn, match_apqn); + if (!dev) + return NULL; + q = dev_get_drvdata(dev); + q->matrix_mdev = matrix_mdev; + put_device(dev); + + return q; +} + +/** + * vfio_ap_wait_for_irqclear + * @apqn: The AP Queue number + * + * Checks the IRQ bit for the status of this APQN using ap_tapq. + * Returns if the ap_tapq function succeeded and the bit is clear. + * Returns if ap_tapq function failed with invalid, deconfigured or + * checkstopped AP. + * Otherwise retries up to 5 times after waiting 20ms. + * + */ +static void vfio_ap_wait_for_irqclear(int apqn) +{ + struct ap_queue_status status; + int retry = 5; + + do { + status = ap_tapq(apqn, NULL); + switch (status.response_code) { + case AP_RESPONSE_NORMAL: + case AP_RESPONSE_RESET_IN_PROGRESS: + if (!status.irq_enabled) + return; + /* Fall through */ + case AP_RESPONSE_BUSY: + msleep(20); + break; + case AP_RESPONSE_Q_NOT_AVAIL: + case AP_RESPONSE_DECONFIGURED: + case AP_RESPONSE_CHECKSTOPPED: + default: + WARN_ONCE(1, "%s: tapq rc %02x: %04x\n", __func__, + status.response_code, apqn); + return; + } + } while (--retry); + + WARN_ONCE(1, "%s: tapq rc %02x: %04x could not clear IR bit\n", + __func__, status.response_code, apqn); +} + +/** + * vfio_ap_free_aqic_resources + * @q: The vfio_ap_queue + * + * Unregisters the ISC in the GIB when the saved ISC not invalid. + * Unpin the guest's page holding the NIB when it exist. + * Reset the saved_pfn and saved_isc to invalid values. + * + */ +static void vfio_ap_free_aqic_resources(struct vfio_ap_queue *q) +{ + if (q->saved_isc != VFIO_AP_ISC_INVALID && q->matrix_mdev) + kvm_s390_gisc_unregister(q->matrix_mdev->kvm, q->saved_isc); + if (q->saved_pfn && q->matrix_mdev) + vfio_unpin_pages(mdev_dev(q->matrix_mdev->mdev), + &q->saved_pfn, 1); + q->saved_pfn = 0; + q->saved_isc = VFIO_AP_ISC_INVALID; +} + +/** + * vfio_ap_irq_disable + * @q: The vfio_ap_queue + * + * Uses ap_aqic to disable the interruption and in case of success, reset + * in progress or IRQ disable command already proceeded: calls + * vfio_ap_wait_for_irqclear() to check for the IRQ bit to be clear + * and calls vfio_ap_free_aqic_resources() to free the resources associated + * with the AP interrupt handling. + * + * In the case the AP is busy, or a reset is in progress, + * retries after 20ms, up to 5 times. + * + * Returns if ap_aqic function failed with invalid, deconfigured or + * checkstopped AP. + */ +struct ap_queue_status vfio_ap_irq_disable(struct vfio_ap_queue *q) +{ + struct ap_qirq_ctrl aqic_gisa = {}; + struct ap_queue_status status; + int retries = 5; + + do { + status = ap_aqic(q->apqn, aqic_gisa, NULL); + switch (status.response_code) { + case AP_RESPONSE_OTHERWISE_CHANGED: + case AP_RESPONSE_NORMAL: + vfio_ap_wait_for_irqclear(q->apqn); + goto end_free; + case AP_RESPONSE_RESET_IN_PROGRESS: + case AP_RESPONSE_BUSY: + msleep(20); + break; + case AP_RESPONSE_Q_NOT_AVAIL: + case AP_RESPONSE_DECONFIGURED: + case AP_RESPONSE_CHECKSTOPPED: + case AP_RESPONSE_INVALID_ADDRESS: + default: + /* All cases in default means AP not operational */ + WARN_ONCE(1, "%s: ap_aqic status %d\n", __func__, + status.response_code); + goto end_free; + } + } while (retries--); + + WARN_ONCE(1, "%s: ap_aqic status %d\n", __func__, + status.response_code); +end_free: + vfio_ap_free_aqic_resources(q); + q->matrix_mdev = NULL; + return status; +} + +/** + * vfio_ap_setirq: Enable Interruption for a APQN + * + * @dev: the device associated with the ap_queue + * @q: the vfio_ap_queue holding AQIC parameters + * + * Pin the NIB saved in *q + * Register the guest ISC to GIB interface and retrieve the + * host ISC to issue the host side PQAP/AQIC + * + * Response.status may be set to AP_RESPONSE_INVALID_ADDRESS in case the + * vfio_pin_pages failed. + * + * Otherwise return the ap_queue_status returned by the ap_aqic(), + * all retry handling will be done by the guest. + */ +static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q, + int isc, + unsigned long nib) +{ + struct ap_qirq_ctrl aqic_gisa = {}; + struct ap_queue_status status = {}; + struct kvm_s390_gisa *gisa; + struct kvm *kvm; + unsigned long h_nib, g_pfn, h_pfn; + int ret; + + g_pfn = nib >> PAGE_SHIFT; + ret = vfio_pin_pages(mdev_dev(q->matrix_mdev->mdev), &g_pfn, 1, + IOMMU_READ | IOMMU_WRITE, &h_pfn); + switch (ret) { + case 1: + break; + default: + status.response_code = AP_RESPONSE_INVALID_ADDRESS; + return status; + } + + kvm = q->matrix_mdev->kvm; + gisa = kvm->arch.gisa_int.origin; + + h_nib = (h_pfn << PAGE_SHIFT) | (nib & ~PAGE_MASK); + aqic_gisa.gisc = isc; + aqic_gisa.isc = kvm_s390_gisc_register(kvm, isc); + aqic_gisa.ir = 1; + aqic_gisa.gisa = (uint64_t)gisa >> 4; + + status = ap_aqic(q->apqn, aqic_gisa, (void *)h_nib); + switch (status.response_code) { + case AP_RESPONSE_NORMAL: + /* See if we did clear older IRQ configuration */ + vfio_ap_free_aqic_resources(q); + q->saved_pfn = g_pfn; + q->saved_isc = isc; + break; + case AP_RESPONSE_OTHERWISE_CHANGED: + /* We could not modify IRQ setings: clear new configuration */ + vfio_unpin_pages(mdev_dev(q->matrix_mdev->mdev), &g_pfn, 1); + kvm_s390_gisc_unregister(kvm, isc); + break; + default: + pr_warn("%s: apqn %04x: response: %02x\n", __func__, q->apqn, + status.response_code); + vfio_ap_irq_disable(q); + break; + } + + return status; +} + +/** + * handle_pqap: PQAP instruction callback + * + * @vcpu: The vcpu on which we received the PQAP instruction + * + * Get the general register contents to initialize internal variables. + * REG[0]: APQN + * REG[1]: IR and ISC + * REG[2]: NIB + * + * Response.status may be set to following Response Code: + * - AP_RESPONSE_Q_NOT_AVAIL: if the queue is not available + * - AP_RESPONSE_DECONFIGURED: if the queue is not configured + * - AP_RESPONSE_NORMAL (0) : in case of successs + * Check vfio_ap_setirq() and vfio_ap_clrirq() for other possible RC. + * We take the matrix_dev lock to ensure serialization on queues and + * mediated device access. + * + * Return 0 if we could handle the request inside KVM. + * otherwise, returns -EOPNOTSUPP to let QEMU handle the fault. + */ +static int handle_pqap(struct kvm_vcpu *vcpu) +{ + uint64_t status; + uint16_t apqn; + struct vfio_ap_queue *q; + struct ap_queue_status qstatus = { + .response_code = AP_RESPONSE_Q_NOT_AVAIL, }; + struct ap_matrix_mdev *matrix_mdev; + + /* If we do not use the AIV facility just go to userland */ + if (!(vcpu->arch.sie_block->eca & ECA_AIV)) + return -EOPNOTSUPP; + + apqn = vcpu->run->s.regs.gprs[0] & 0xffff; + mutex_lock(&matrix_dev->lock); + + if (!vcpu->kvm->arch.crypto.pqap_hook) + goto out_unlock; + matrix_mdev = container_of(vcpu->kvm->arch.crypto.pqap_hook, + struct ap_matrix_mdev, pqap_hook); + + q = vfio_ap_get_queue(matrix_mdev, apqn); + if (!q) + goto out_unlock; + + status = vcpu->run->s.regs.gprs[1]; + + /* If IR bit(16) is set we enable the interrupt */ + if ((status >> (63 - 16)) & 0x01) + qstatus = vfio_ap_irq_enable(q, status & 0x07, + vcpu->run->s.regs.gprs[2]); + else + qstatus = vfio_ap_irq_disable(q); + +out_unlock: + memcpy(&vcpu->run->s.regs.gprs[1], &qstatus, sizeof(qstatus)); + vcpu->run->s.regs.gprs[1] >>= 32; + mutex_unlock(&matrix_dev->lock); + return 0; +} + static void vfio_ap_matrix_init(struct ap_config_info *info, struct ap_matrix *matrix) { @@ -45,8 +334,11 @@ static int vfio_ap_mdev_create(struct kobject *kobj, struct mdev_device *mdev) return -ENOMEM; } + matrix_mdev->mdev = mdev; vfio_ap_matrix_init(&matrix_dev->info, &matrix_mdev->matrix); mdev_set_drvdata(mdev, matrix_mdev); + matrix_mdev->pqap_hook.hook = handle_pqap; + matrix_mdev->pqap_hook.owner = THIS_MODULE; mutex_lock(&matrix_dev->lock); list_add(&matrix_mdev->node, &matrix_dev->mdev_list); mutex_unlock(&matrix_dev->lock); @@ -62,6 +354,7 @@ static int vfio_ap_mdev_remove(struct mdev_device *mdev) return -EBUSY; mutex_lock(&matrix_dev->lock); + vfio_ap_mdev_reset_queues(mdev); list_del(&matrix_mdev->node); mutex_unlock(&matrix_dev->lock); @@ -754,11 +1047,42 @@ static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev, } matrix_mdev->kvm = kvm; + kvm_get_kvm(kvm); + kvm->arch.crypto.pqap_hook = &matrix_mdev->pqap_hook; mutex_unlock(&matrix_dev->lock); return 0; } +/* + * vfio_ap_mdev_iommu_notifier: IOMMU notifier callback + * + * @nb: The notifier block + * @action: Action to be taken + * @data: data associated with the request + * + * For an UNMAP request, unpin the guest IOVA (the NIB guest address we + * pinned before). Other requests are ignored. + * + */ +static int vfio_ap_mdev_iommu_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct ap_matrix_mdev *matrix_mdev; + + matrix_mdev = container_of(nb, struct ap_matrix_mdev, iommu_notifier); + + if (action == VFIO_IOMMU_NOTIFY_DMA_UNMAP) { + struct vfio_iommu_type1_dma_unmap *unmap = data; + unsigned long g_pfn = unmap->iova >> PAGE_SHIFT; + + vfio_unpin_pages(mdev_dev(matrix_mdev->mdev), &g_pfn, 1); + return NOTIFY_OK; + } + + return NOTIFY_DONE; +} + static int vfio_ap_mdev_group_notifier(struct notifier_block *nb, unsigned long action, void *data) { @@ -790,15 +1114,36 @@ static int vfio_ap_mdev_group_notifier(struct notifier_block *nb, return NOTIFY_OK; } -static int vfio_ap_mdev_reset_queue(unsigned int apid, unsigned int apqi, - unsigned int retry) +static void vfio_ap_irq_disable_apqn(int apqn) +{ + struct device *dev; + struct vfio_ap_queue *q; + + dev = driver_find_device(&matrix_dev->vfio_ap_drv->driver, NULL, + &apqn, match_apqn); + if (dev) { + q = dev_get_drvdata(dev); + vfio_ap_irq_disable(q); + put_device(dev); + } +} + +int vfio_ap_mdev_reset_queue(unsigned int apid, unsigned int apqi, + unsigned int retry) { struct ap_queue_status status; + int retry2 = 2; + int apqn = AP_MKQID(apid, apqi); do { - status = ap_zapq(AP_MKQID(apid, apqi)); + status = ap_zapq(apqn); switch (status.response_code) { case AP_RESPONSE_NORMAL: + while (!status.queue_empty && retry2--) { + msleep(20); + status = ap_tapq(apqn, NULL); + } + WARN_ON_ONCE(retry <= 0); return 0; case AP_RESPONSE_RESET_IN_PROGRESS: case AP_RESPONSE_BUSY: @@ -832,6 +1177,7 @@ static int vfio_ap_mdev_reset_queues(struct mdev_device *mdev) */ if (ret) rc = ret; + vfio_ap_irq_disable_apqn(AP_MKQID(apid, apqi)); } } @@ -858,20 +1204,37 @@ static int vfio_ap_mdev_open(struct mdev_device *mdev) return ret; } - return 0; + matrix_mdev->iommu_notifier.notifier_call = vfio_ap_mdev_iommu_notifier; + events = VFIO_IOMMU_NOTIFY_DMA_UNMAP; + ret = vfio_register_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY, + &events, &matrix_mdev->iommu_notifier); + if (!ret) + return ret; + + vfio_unregister_notifier(mdev_dev(mdev), VFIO_GROUP_NOTIFY, + &matrix_mdev->group_notifier); + module_put(THIS_MODULE); + return ret; } static void vfio_ap_mdev_release(struct mdev_device *mdev) { struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev); - if (matrix_mdev->kvm) + mutex_lock(&matrix_dev->lock); + if (matrix_mdev->kvm) { kvm_arch_crypto_clear_masks(matrix_mdev->kvm); + matrix_mdev->kvm->arch.crypto.pqap_hook = NULL; + vfio_ap_mdev_reset_queues(mdev); + kvm_put_kvm(matrix_mdev->kvm); + matrix_mdev->kvm = NULL; + } + mutex_unlock(&matrix_dev->lock); - vfio_ap_mdev_reset_queues(mdev); + vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY, + &matrix_mdev->iommu_notifier); vfio_unregister_notifier(mdev_dev(mdev), VFIO_GROUP_NOTIFY, &matrix_mdev->group_notifier); - matrix_mdev->kvm = NULL; module_put(THIS_MODULE); } @@ -900,6 +1263,7 @@ static ssize_t vfio_ap_mdev_ioctl(struct mdev_device *mdev, { int ret; + mutex_lock(&matrix_dev->lock); switch (cmd) { case VFIO_DEVICE_GET_INFO: ret = vfio_ap_mdev_get_device_info(arg); @@ -911,6 +1275,7 @@ static ssize_t vfio_ap_mdev_ioctl(struct mdev_device *mdev, ret = -EOPNOTSUPP; break; } + mutex_unlock(&matrix_dev->lock); return ret; } diff --git a/drivers/s390/crypto/vfio_ap_private.h b/drivers/s390/crypto/vfio_ap_private.h index 76b7f98e47e9..f46dde56b464 100644 --- a/drivers/s390/crypto/vfio_ap_private.h +++ b/drivers/s390/crypto/vfio_ap_private.h @@ -4,6 +4,7 @@ * * Author(s): Tony Krowiak <akrowiak@linux.ibm.com> * Halil Pasic <pasic@linux.ibm.com> + * Pierre Morel <pmorel@linux.ibm.com> * * Copyright IBM Corp. 2018 */ @@ -16,6 +17,7 @@ #include <linux/mdev.h> #include <linux/delay.h> #include <linux/mutex.h> +#include <linux/kvm_host.h> #include "ap_bus.h" @@ -80,10 +82,23 @@ struct ap_matrix_mdev { struct list_head node; struct ap_matrix matrix; struct notifier_block group_notifier; + struct notifier_block iommu_notifier; struct kvm *kvm; + struct kvm_s390_module_hook pqap_hook; + struct mdev_device *mdev; }; extern int vfio_ap_mdev_register(void); extern void vfio_ap_mdev_unregister(void); +int vfio_ap_mdev_reset_queue(unsigned int apid, unsigned int apqi, + unsigned int retry); +struct vfio_ap_queue { + struct ap_matrix_mdev *matrix_mdev; + unsigned long saved_pfn; + int apqn; +#define VFIO_AP_ISC_INVALID 0xff + unsigned char saved_isc; +}; +struct ap_queue_status vfio_ap_irq_disable(struct vfio_ap_queue *q); #endif /* _VFIO_AP_PRIVATE_H_ */ diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 689c2af7026a..1058b4b5cc1e 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -525,7 +525,7 @@ static int zcrypt_open(struct inode *inode, struct file *filp) filp->private_data = (void *) perms; atomic_inc(&zcrypt_open_count); - return nonseekable_open(inode, filp); + return stream_open(inode, filp); } /** @@ -659,6 +659,7 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms, trace_s390_zcrypt_req(mex, TP_ICARSAMODEXPO); if (mex->outputdatalength < mex->inputdatalength) { + func_code = 0; rc = -EINVAL; goto out; } @@ -742,6 +743,7 @@ static long zcrypt_rsa_crt(struct ap_perms *perms, trace_s390_zcrypt_req(crt, TP_ICARSACRT); if (crt->outputdatalength < crt->inputdatalength) { + func_code = 0; rc = -EINVAL; goto out; } @@ -820,7 +822,7 @@ static long _zcrypt_send_cprb(struct ap_perms *perms, struct ap_message ap_msg; unsigned int weight, pref_weight; unsigned int func_code; - unsigned short *domain; + unsigned short *domain, tdom; int qid = 0, rc = -ENODEV; struct module *mod; @@ -832,6 +834,17 @@ static long _zcrypt_send_cprb(struct ap_perms *perms, if (rc) goto out; + /* + * If a valid target domain is set and this domain is NOT a usage + * domain but a control only domain, use the default domain as target. + */ + tdom = *domain; + if (tdom >= 0 && tdom < AP_DOMAINS && + !ap_test_config_usage_domain(tdom) && + ap_test_config_ctrl_domain(tdom) && + ap_domain_index >= 0) + tdom = ap_domain_index; + pref_zc = NULL; pref_zq = NULL; spin_lock(&zcrypt_list_lock); @@ -854,8 +867,8 @@ static long _zcrypt_send_cprb(struct ap_perms *perms, /* check if device is online and eligible */ if (!zq->online || !zq->ops->send_cprb || - ((*domain != (unsigned short) AUTOSELECT) && - (*domain != AP_QID_QUEUE(zq->queue->qid)))) + (tdom != (unsigned short) AUTOSELECT && + tdom != AP_QID_QUEUE(zq->queue->qid))) continue; /* check if device node has admission for this queue */ if (!zcrypt_check_queue(perms, @@ -951,6 +964,7 @@ static long zcrypt_send_ep11_cprb(struct ap_perms *perms, targets = kcalloc(target_num, sizeof(*targets), GFP_KERNEL); if (!targets) { + func_code = 0; rc = -ENOMEM; goto out; } @@ -958,6 +972,7 @@ static long zcrypt_send_ep11_cprb(struct ap_perms *perms, uptr = (struct ep11_target_dev __force __user *) xcrb->targets; if (copy_from_user(targets, uptr, target_num * sizeof(*targets))) { + func_code = 0; rc = -EFAULT; goto out_free; } diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index 0cbcc238ef98..12fe9deb265e 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -567,6 +567,10 @@ static int xcrb_msg_to_type6_ep11cprb_msgx(struct ap_message *ap_msg, payload_hdr = (struct pld_hdr *)((&(msg->pld_lenfmt))+lfmt); *fcode = payload_hdr->func_val & 0xFFFF; + /* enable special processing based on the cprbs flags special bit */ + if (msg->cprbx.flags & 0x20) + ap_msg->special = 1; + return 0; } diff --git a/drivers/s390/net/Kconfig b/drivers/s390/net/Kconfig index 7c5a25ddf832..ced896d1534a 100644 --- a/drivers/s390/net/Kconfig +++ b/drivers/s390/net/Kconfig @@ -7,10 +7,10 @@ config LCS prompt "Lan Channel Station Interface" depends on CCW && NETDEVICES && (ETHERNET || FDDI) help - Select this option if you want to use LCS networking on IBM System z. - This device driver supports FDDI (IEEE 802.7) and Ethernet. - To compile as a module, choose M. The module name is lcs. - If you do not know what it is, it's safe to choose Y. + Select this option if you want to use LCS networking on IBM System z. + This device driver supports FDDI (IEEE 802.7) and Ethernet. + To compile as a module, choose M. The module name is lcs. + If you do not know what it is, it's safe to choose Y. config CTCM def_tristate m diff --git a/drivers/s390/net/ism.h b/drivers/s390/net/ism.h index 0aab90817326..66eac2b9704d 100644 --- a/drivers/s390/net/ism.h +++ b/drivers/s390/net/ism.h @@ -6,6 +6,7 @@ #include <linux/types.h> #include <linux/pci.h> #include <net/smc.h> +#include <asm/pci_insn.h> #define UTIL_STR_LEN 16 @@ -194,8 +195,6 @@ struct ism_dev { struct pci_dev *pdev; struct smcd_dev *smcd; - void __iomem *ctl; - struct ism_sba *sba; dma_addr_t sba_dma_addr; DECLARE_BITMAP(sba_bitmap, ISM_NR_DMBS); @@ -209,13 +208,37 @@ struct ism_dev { #define ISM_CREATE_REQ(dmb, idx, sf, offset) \ ((dmb) | (idx) << 24 | (sf) << 23 | (offset)) +static inline void __ism_read_cmd(struct ism_dev *ism, void *data, + unsigned long offset, unsigned long len) +{ + struct zpci_dev *zdev = to_zpci(ism->pdev); + u64 req = ZPCI_CREATE_REQ(zdev->fh, 2, 8); + + while (len > 0) { + __zpci_load(data, req, offset); + offset += 8; + data += 8; + len -= 8; + } +} + +static inline void __ism_write_cmd(struct ism_dev *ism, void *data, + unsigned long offset, unsigned long len) +{ + struct zpci_dev *zdev = to_zpci(ism->pdev); + u64 req = ZPCI_CREATE_REQ(zdev->fh, 2, len); + + if (len) + __zpci_store_block(data, req, offset); +} + static inline int __ism_move(struct ism_dev *ism, u64 dmb_req, void *data, unsigned int size) { struct zpci_dev *zdev = to_zpci(ism->pdev); u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, size); - return zpci_write_block(req, data, dmb_req); + return __zpci_store_block(data, req, dmb_req); } #endif /* S390_ISM_H */ diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index 3e132592c1fe..4fc2056bd227 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -38,19 +38,18 @@ static int ism_cmd(struct ism_dev *ism, void *cmd) struct ism_req_hdr *req = cmd; struct ism_resp_hdr *resp = cmd; - memcpy_toio(ism->ctl + sizeof(*req), req + 1, req->len - sizeof(*req)); - memcpy_toio(ism->ctl, req, sizeof(*req)); + __ism_write_cmd(ism, req + 1, sizeof(*req), req->len - sizeof(*req)); + __ism_write_cmd(ism, req, 0, sizeof(*req)); WRITE_ONCE(resp->ret, ISM_ERROR); - memcpy_fromio(resp, ism->ctl, sizeof(*resp)); + __ism_read_cmd(ism, resp, 0, sizeof(*resp)); if (resp->ret) { debug_text_event(ism_debug_info, 0, "cmd failure"); debug_event(ism_debug_info, 0, resp, sizeof(*resp)); goto out; } - memcpy_fromio(resp + 1, ism->ctl + sizeof(*resp), - resp->len - sizeof(*resp)); + __ism_read_cmd(ism, resp + 1, sizeof(*resp), resp->len - sizeof(*resp)); out: return resp->ret; } @@ -512,13 +511,9 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (ret) goto err_disable; - ism->ctl = pci_iomap(pdev, 2, 0); - if (!ism->ctl) - goto err_resource; - ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); if (ret) - goto err_unmap; + goto err_resource; dma_set_seg_boundary(&pdev->dev, SZ_1M - 1); dma_set_max_seg_size(&pdev->dev, SZ_1M); @@ -527,7 +522,7 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id) ism->smcd = smcd_alloc_dev(&pdev->dev, dev_name(&pdev->dev), &ism_ops, ISM_NR_DMBS); if (!ism->smcd) - goto err_unmap; + goto err_resource; ism->smcd->priv = ism; ret = ism_dev_init(ism); @@ -538,8 +533,6 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id) err_free: smcd_free_dev(ism->smcd); -err_unmap: - pci_iounmap(pdev, ism->ctl); err_resource: pci_release_mem_regions(pdev); err_disable: @@ -568,7 +561,6 @@ static void ism_remove(struct pci_dev *pdev) ism_dev_exit(ism); smcd_free_dev(ism->smcd); - pci_iounmap(pdev, ism->ctl); pci_release_mem_regions(pdev); pci_disable_device(pdev); dev_set_drvdata(&pdev->dev, NULL); diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index c851cf6e01c4..c7ee07ce3615 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -10,6 +10,7 @@ #ifndef __QETH_CORE_H__ #define __QETH_CORE_H__ +#include <linux/completion.h> #include <linux/if.h> #include <linux/if_arp.h> #include <linux/etherdevice.h> @@ -21,8 +22,11 @@ #include <linux/hashtable.h> #include <linux/ip.h> #include <linux/refcount.h> +#include <linux/wait.h> #include <linux/workqueue.h> +#include <net/dst.h> +#include <net/ip6_fib.h> #include <net/ipv6.h> #include <net/if_inet6.h> #include <net/addrconf.h> @@ -58,7 +62,7 @@ struct qeth_dbf_info { debug_info_t *id; }; -#define QETH_DBF_CTRL_LEN 256 +#define QETH_DBF_CTRL_LEN 256U #define QETH_DBF_TEXT(name, level, text) \ debug_text_event(qeth_dbf[QETH_DBF_##name].id, level, text) @@ -163,6 +167,12 @@ struct qeth_vnicc_info { bool rx_bcast_enabled; }; +static inline int qeth_is_adp_supported(struct qeth_ipa_info *ipa, + enum qeth_ipa_setadp_cmd func) +{ + return (ipa->supported_funcs & func); +} + static inline int qeth_is_ipa_supported(struct qeth_ipa_info *ipa, enum qeth_ipa_funcs func) { @@ -176,9 +186,7 @@ static inline int qeth_is_ipa_enabled(struct qeth_ipa_info *ipa, } #define qeth_adp_supported(c, f) \ - qeth_is_ipa_supported(&c->options.adp, f) -#define qeth_adp_enabled(c, f) \ - qeth_is_ipa_enabled(&c->options.adp, f) + qeth_is_adp_supported(&c->options.adp, f) #define qeth_is_supported(c, f) \ qeth_is_ipa_supported(&c->options.ipa4, f) #define qeth_is_enabled(c, f) \ @@ -217,6 +225,9 @@ static inline int qeth_is_ipa_enabled(struct qeth_ipa_info *ipa, /* QDIO queue and buffer handling */ /*****************************************************************************/ #define QETH_MAX_QUEUES 4 +#define QETH_IQD_MIN_TXQ 2 /* One for ucast, one for mcast. */ +#define QETH_IQD_MCAST_TXQ 0 +#define QETH_IQD_MIN_UCAST_TXQ 1 #define QETH_IN_BUF_SIZE_DEFAULT 65536 #define QETH_IN_BUF_COUNT_DEFAULT 64 #define QETH_IN_BUF_COUNT_HSDEFAULT 128 @@ -365,34 +376,6 @@ enum qeth_header_ids { #define QETH_HDR_EXT_CSUM_TRANSP_REQ 0x20 #define QETH_HDR_EXT_UDP 0x40 /*bit off for TCP*/ -enum qeth_qdio_buffer_states { - /* - * inbound: read out by driver; owned by hardware in order to be filled - * outbound: owned by driver in order to be filled - */ - QETH_QDIO_BUF_EMPTY, - /* - * inbound: filled by hardware; owned by driver in order to be read out - * outbound: filled by driver; owned by hardware in order to be sent - */ - QETH_QDIO_BUF_PRIMED, - /* - * inbound: not applicable - * outbound: identified to be pending in TPQ - */ - QETH_QDIO_BUF_PENDING, - /* - * inbound: not applicable - * outbound: found in completion queue - */ - QETH_QDIO_BUF_IN_CQ, - /* - * inbound: not applicable - * outbound: handled via transfer pending / completion queue - */ - QETH_QDIO_BUF_HANDLED_DELAYED, -}; - enum qeth_qdio_info_states { QETH_QDIO_UNINITIALIZED, QETH_QDIO_ALLOCATED, @@ -424,6 +407,19 @@ struct qeth_qdio_q { int next_buf_to_init; }; +enum qeth_qdio_out_buffer_state { + /* Owned by driver, in order to be filled. */ + QETH_QDIO_BUF_EMPTY, + /* Filled by driver; owned by hardware in order to be sent. */ + QETH_QDIO_BUF_PRIMED, + /* Identified to be pending in TPQ. */ + QETH_QDIO_BUF_PENDING, + /* Found in completion queue. */ + QETH_QDIO_BUF_IN_CQ, + /* Handled via transfer pending / completion queue. */ + QETH_QDIO_BUF_HANDLED_DELAYED, +}; + struct qeth_qdio_out_buffer { struct qdio_buffer *buffer; atomic_t state; @@ -462,7 +458,6 @@ struct qeth_card_stats { u64 rx_errors; u64 rx_dropped; u64 rx_multicast; - u64 tx_errors; }; struct qeth_out_q_stats { @@ -477,6 +472,7 @@ struct qeth_out_q_stats { u64 skbs_linearized_fail; u64 tso_bytes; u64 packing_mode_switch; + u64 stopped; /* rtnl_link_stats64 */ u64 tx_packets; @@ -490,14 +486,12 @@ struct qeth_qdio_out_q { struct qeth_qdio_out_buffer *bufs[QDIO_MAX_BUFFERS_PER_Q]; struct qdio_outbuf_state *bufstates; /* convenience pointer */ struct qeth_out_q_stats stats; - int queue_no; + u8 next_buf_to_fill; + u8 max_elements; + u8 queue_no; + u8 do_pack; struct qeth_card *card; atomic_t state; - int do_pack; - /* - * index of buffer to be filled by driver; state EMPTY or PACKING - */ - int next_buf_to_fill; /* * number of buffers that are currently filled (PRIMED) * -> these buffers are hardware-owned @@ -507,6 +501,11 @@ struct qeth_qdio_out_q { atomic_t set_pci_flags_count; }; +static inline bool qeth_out_queue_is_full(struct qeth_qdio_out_q *queue) +{ + return atomic_read(&queue->used_buffers) >= QDIO_MAX_BUFFERS_PER_Q; +} + struct qeth_qdio_info { atomic_t state; /* input */ @@ -528,21 +527,13 @@ struct qeth_qdio_info { }; /** - * buffer stuff for read channel - */ -#define QETH_CMD_BUFFER_NO 8 - -/** * channel state machine */ enum qeth_channel_states { CH_STATE_UP, CH_STATE_DOWN, - CH_STATE_ACTIVATING, CH_STATE_HALTED, CH_STATE_STOPPED, - CH_STATE_RCD, - CH_STATE_RCD_DONE, }; /** * card state machine @@ -557,15 +548,11 @@ enum qeth_card_states { * Protocol versions */ enum qeth_prot_versions { + QETH_PROT_NONE = 0x0000, QETH_PROT_IPV4 = 0x0004, QETH_PROT_IPV6 = 0x0006, }; -enum qeth_cmd_buffer_state { - BUF_STATE_FREE, - BUF_STATE_LOCKED, -}; - enum qeth_cq { QETH_CQ_DISABLED = 0, QETH_CQ_ENABLED = 1, @@ -579,36 +566,42 @@ struct qeth_ipato { struct list_head entries; }; -struct qeth_channel; +struct qeth_channel { + struct ccw_device *ccwdev; + enum qeth_channel_states state; + atomic_t irq_pending; +}; struct qeth_cmd_buffer { - enum qeth_cmd_buffer_state state; + unsigned int length; + refcount_t ref_count; struct qeth_channel *channel; struct qeth_reply *reply; + long timeout; unsigned char *data; - void (*callback)(struct qeth_card *card, struct qeth_channel *channel, - struct qeth_cmd_buffer *iob); + void (*finalize)(struct qeth_card *card, struct qeth_cmd_buffer *iob); + void (*callback)(struct qeth_card *card, struct qeth_cmd_buffer *iob); }; +static inline void qeth_get_cmd(struct qeth_cmd_buffer *iob) +{ + refcount_inc(&iob->ref_count); +} + static inline struct qeth_ipa_cmd *__ipa_cmd(struct qeth_cmd_buffer *iob) { return (struct qeth_ipa_cmd *)(iob->data + IPA_PDU_HEADER_SIZE); } -/** - * definition of a qeth channel, used for read and write - */ -struct qeth_channel { - enum qeth_channel_states state; - struct ccw1 *ccw; - spinlock_t iob_lock; - wait_queue_head_t wait_q; - struct ccw_device *ccwdev; -/*command buffer for control data*/ - struct qeth_cmd_buffer iob[QETH_CMD_BUFFER_NO]; - atomic_t irq_pending; - int io_buf_no; -}; +static inline struct ccw1 *__ccw_from_cmd(struct qeth_cmd_buffer *iob) +{ + return (struct ccw1 *)(iob->data + ALIGN(iob->length, 8)); +} + +static inline bool qeth_trylock_channel(struct qeth_channel *channel) +{ + return atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0; +} /** * OSA card related definitions @@ -631,17 +624,15 @@ struct qeth_seqno { __u32 pdu_hdr; __u32 pdu_hdr_ack; __u16 ipa; - __u32 pkt_seqno; }; struct qeth_reply { struct list_head list; - wait_queue_head_t wait_q; + struct completion received; int (*callback)(struct qeth_card *, struct qeth_reply *, unsigned long); u32 seqno; unsigned long offset; - atomic_t received; int rc; void *param; refcount_t refcnt; @@ -663,7 +654,8 @@ struct qeth_card_info { __u16 func_level; char mcl_level[QETH_MCL_LENGTH + 1]; u8 open_when_online:1; - int guestlan; + u8 use_v1_blkt:1; + u8 is_vm_nic:1; int mac_bits; enum qeth_card_types type; enum qeth_link_types link_type; @@ -723,9 +715,6 @@ struct qeth_discipline { void (*remove) (struct ccwgroup_device *); int (*set_online) (struct ccwgroup_device *); int (*set_offline) (struct ccwgroup_device *); - int (*freeze)(struct ccwgroup_device *); - int (*thaw) (struct ccwgroup_device *); - int (*restore)(struct ccwgroup_device *); int (*do_ioctl)(struct net_device *dev, struct ifreq *rq, int cmd); int (*control_event_handler)(struct qeth_card *card, struct qeth_ipa_cmd *cmd); @@ -762,6 +751,7 @@ struct qeth_card { enum qeth_card_states state; spinlock_t lock; struct ccwgroup_device *gdev; + struct qeth_cmd_buffer *read_cmd; struct qeth_channel read; struct qeth_channel write; struct qeth_channel data; @@ -774,18 +764,19 @@ struct qeth_card { struct qeth_card_options options; struct workqueue_struct *event_wq; + struct workqueue_struct *cmd_wq; wait_queue_head_t wait_q; - spinlock_t mclock; unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; DECLARE_HASHTABLE(mac_htable, 4); DECLARE_HASHTABLE(ip_htable, 4); + struct mutex ip_lock; DECLARE_HASHTABLE(ip_mc_htable, 4); + struct work_struct rx_mode_work; struct work_struct kernel_thread_starter; spinlock_t thread_mask_lock; unsigned long thread_start_mask; unsigned long thread_allowed_mask; unsigned long thread_running_mask; - spinlock_t ip_lock; struct qeth_ipato ipato; struct list_head cmd_waiter_list; /* QDIO buffer handling */ @@ -827,6 +818,15 @@ static inline bool qeth_netdev_is_registered(struct net_device *dev) return dev->netdev_ops != NULL; } +static inline u16 qeth_iqd_translate_txq(struct net_device *dev, u16 txq) +{ + if (txq == QETH_IQD_MCAST_TXQ) + return dev->num_tx_queues - 1; + if (txq == dev->num_tx_queues - 1) + return QETH_IQD_MCAST_TXQ; + return txq; +} + static inline void qeth_scrub_qdio_buffer(struct qdio_buffer *buf, unsigned int elements) { @@ -869,6 +869,27 @@ static inline int qeth_get_ip_version(struct sk_buff *skb) } } +static inline int qeth_get_ether_cast_type(struct sk_buff *skb) +{ + u8 *addr = eth_hdr(skb)->h_dest; + + if (is_multicast_ether_addr(addr)) + return is_broadcast_ether_addr(addr) ? RTN_BROADCAST : + RTN_MULTICAST; + return RTN_UNICAST; +} + +static inline struct dst_entry *qeth_dst_check_rcu(struct sk_buff *skb, int ipv) +{ + struct dst_entry *dst = skb_dst(skb); + struct rt6_info *rt; + + rt = (struct rt6_info *) dst; + if (dst) + dst = dst_check(dst, (ipv == 6) ? rt6_get_cookie(rt) : 0); + return dst; +} + static inline void qeth_rx_csum(struct qeth_card *card, struct sk_buff *skb, u8 flags) { @@ -903,12 +924,12 @@ static inline int qeth_is_diagass_supported(struct qeth_card *card, int qeth_send_simple_setassparms_prot(struct qeth_card *card, enum qeth_ipa_funcs ipa_func, - u16 cmd_code, long data, + u16 cmd_code, u32 *data, enum qeth_prot_versions prot); /* IPv4 variant */ static inline int qeth_send_simple_setassparms(struct qeth_card *card, enum qeth_ipa_funcs ipa_func, - u16 cmd_code, long data) + u16 cmd_code, u32 *data) { return qeth_send_simple_setassparms_prot(card, ipa_func, cmd_code, data, QETH_PROT_IPV4); @@ -916,24 +937,13 @@ static inline int qeth_send_simple_setassparms(struct qeth_card *card, static inline int qeth_send_simple_setassparms_v6(struct qeth_card *card, enum qeth_ipa_funcs ipa_func, - u16 cmd_code, long data) + u16 cmd_code, u32 *data) { return qeth_send_simple_setassparms_prot(card, ipa_func, cmd_code, data, QETH_PROT_IPV6); } -int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb, - int ipv); -static inline struct qeth_qdio_out_q *qeth_get_tx_queue(struct qeth_card *card, - struct sk_buff *skb, - int ipv, int cast_type) -{ - if (IS_IQD(card) && cast_type != RTN_UNICAST) - return card->qdio.out_qs[card->qdio.no_out_queues - 1]; - if (!card->qdio.do_prio_queueing) - return card->qdio.out_qs[card->qdio.default_out_queue]; - return card->qdio.out_qs[qeth_get_priority_queue(card, skb, ipv)]; -} +int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb); extern struct qeth_discipline qeth_l2_discipline; extern struct qeth_discipline qeth_l3_discipline; @@ -968,8 +978,23 @@ int qeth_send_ipa_cmd(struct qeth_card *, struct qeth_cmd_buffer *, int (*reply_cb) (struct qeth_card *, struct qeth_reply *, unsigned long), void *); -struct qeth_cmd_buffer *qeth_get_ipacmd_buffer(struct qeth_card *, - enum qeth_ipa_cmds, enum qeth_prot_versions); +struct qeth_cmd_buffer *qeth_ipa_alloc_cmd(struct qeth_card *card, + enum qeth_ipa_cmds cmd_code, + enum qeth_prot_versions prot, + unsigned int data_length); +struct qeth_cmd_buffer *qeth_alloc_cmd(struct qeth_channel *channel, + unsigned int length, unsigned int ccws, + long timeout); +struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *card, + enum qeth_ipa_funcs ipa_func, + u16 cmd_code, + unsigned int data_length, + enum qeth_prot_versions prot); +struct qeth_cmd_buffer *qeth_get_diag_cmd(struct qeth_card *card, + enum qeth_diags_cmds sub_cmd, + unsigned int data_length); +void qeth_put_cmd(struct qeth_cmd_buffer *iob); + struct sk_buff *qeth_core_get_next_skb(struct qeth_card *, struct qeth_qdio_buffer *, struct qdio_buffer_element **, int *, struct qeth_hdr **); @@ -978,17 +1003,13 @@ int qeth_poll(struct napi_struct *napi, int budget); void qeth_clear_ipacmd_list(struct qeth_card *); int qeth_qdio_clear_card(struct qeth_card *, int); void qeth_clear_working_pool_list(struct qeth_card *); -void qeth_clear_cmd_buffers(struct qeth_channel *); -void qeth_clear_qdio_buffers(struct qeth_card *); +void qeth_drain_output_queues(struct qeth_card *card); void qeth_setadp_promisc_mode(struct qeth_card *); int qeth_setadpparms_change_macaddr(struct qeth_card *); void qeth_tx_timeout(struct net_device *); -void qeth_prepare_control_data(struct qeth_card *, int, - struct qeth_cmd_buffer *); -void qeth_release_buffer(struct qeth_channel *, struct qeth_cmd_buffer *); +void qeth_notify_reply(struct qeth_reply *reply, int reason); void qeth_prepare_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob, u16 cmd_length); -struct qeth_cmd_buffer *qeth_wait_for_buffer(struct qeth_channel *); int qeth_query_switch_attributes(struct qeth_card *card, struct qeth_switch_info *sw_info); int qeth_query_card_info(struct qeth_card *card, @@ -1005,10 +1026,6 @@ int qeth_configure_cq(struct qeth_card *, enum qeth_cq); int qeth_hw_trap(struct qeth_card *, enum qeth_diags_trap_action); void qeth_trace_features(struct qeth_card *); int qeth_setassparms_cb(struct qeth_card *, struct qeth_reply *, unsigned long); -struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *, - enum qeth_ipa_funcs, - __u16, __u16, - enum qeth_prot_versions); int qeth_set_features(struct net_device *, netdev_features_t); void qeth_enable_hw_features(struct net_device *dev); netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t); @@ -1016,16 +1033,17 @@ netdev_features_t qeth_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features); void qeth_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats); +u16 qeth_iqd_select_queue(struct net_device *dev, struct sk_buff *skb, + u8 cast_type, struct net_device *sb_dev); int qeth_open(struct net_device *dev); int qeth_stop(struct net_device *dev); int qeth_vm_request_mac(struct qeth_card *card); int qeth_xmit(struct qeth_card *card, struct sk_buff *skb, - struct qeth_qdio_out_q *queue, int ipv, int cast_type, + struct qeth_qdio_out_q *queue, int ipv, void (*fill_header)(struct qeth_qdio_out_q *queue, struct qeth_hdr *hdr, struct sk_buff *skb, - int ipv, int cast_type, - unsigned int data_len)); + int ipv, unsigned int data_len)); /* exports for OSN */ int qeth_osn_assist(struct net_device *, void *, int); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 44bd6f04c145..4d0caeebc802 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -20,6 +20,7 @@ #include <linux/ip.h> #include <linux/tcp.h> #include <linux/mii.h> +#include <linux/mm.h> #include <linux/kthread.h> #include <linux/slab.h> #include <linux/if_vlan.h> @@ -61,13 +62,11 @@ static struct kmem_cache *qeth_qdio_outbuf_cache; static struct device *qeth_core_root_dev; static struct lock_class_key qdio_out_skb_queue_key; -static void qeth_send_control_data_cb(struct qeth_card *card, - struct qeth_channel *channel, - struct qeth_cmd_buffer *iob); -static struct qeth_cmd_buffer *qeth_get_buffer(struct qeth_channel *); +static void qeth_issue_next_read_cb(struct qeth_card *card, + struct qeth_cmd_buffer *iob); static void qeth_free_buffer_pool(struct qeth_card *); static int qeth_qdio_establish(struct qeth_card *); -static void qeth_free_qdio_buffers(struct qeth_card *); +static void qeth_free_qdio_queues(struct qeth_card *card); static void qeth_notify_skbs(struct qeth_qdio_out_q *queue, struct qeth_qdio_out_buffer *buf, enum iucv_tx_notify notification); @@ -85,7 +84,7 @@ static void qeth_close_dev_handler(struct work_struct *work) static const char *qeth_get_cardname(struct qeth_card *card) { - if (card->info.guestlan) { + if (IS_VM_NIC(card)) { switch (card->info.type) { case QETH_CARD_TYPE_OSD: return " Virtual NIC QDIO"; @@ -120,7 +119,7 @@ static const char *qeth_get_cardname(struct qeth_card *card) /* max length to be returned: 14 */ const char *qeth_get_cardname_short(struct qeth_card *card) { - if (card->info.guestlan) { + if (IS_VM_NIC(card)) { switch (card->info.type) { case QETH_CARD_TYPE_OSD: return "Virt.NIC QDIO"; @@ -292,7 +291,7 @@ static int qeth_cq_init(struct qeth_card *card) int rc; if (card->options.cq == QETH_CQ_ENABLED) { - QETH_DBF_TEXT(SETUP, 2, "cqinit"); + QETH_CARD_TEXT(card, 2, "cqinit"); qdio_reset_buffers(card->qdio.c_q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q); card->qdio.c_q->next_buf_to_init = 127; @@ -300,7 +299,7 @@ static int qeth_cq_init(struct qeth_card *card) card->qdio.no_in_queues - 1, 0, 127); if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc); + QETH_CARD_TEXT_(card, 2, "1err%d", rc); goto out; } } @@ -317,7 +316,7 @@ static int qeth_alloc_cq(struct qeth_card *card) int i; struct qdio_outbuf_state *outbuf_states; - QETH_DBF_TEXT(SETUP, 2, "cqon"); + QETH_CARD_TEXT(card, 2, "cqon"); card->qdio.c_q = qeth_alloc_qdio_queue(); if (!card->qdio.c_q) { rc = -1; @@ -339,11 +338,11 @@ static int qeth_alloc_cq(struct qeth_card *card) outbuf_states += QDIO_MAX_BUFFERS_PER_Q; } } else { - QETH_DBF_TEXT(SETUP, 2, "nocq"); + QETH_CARD_TEXT(card, 2, "nocq"); card->qdio.c_q = NULL; card->qdio.no_in_queues = 1; } - QETH_DBF_TEXT_(SETUP, 2, "iqc%d", card->qdio.no_in_queues); + QETH_CARD_TEXT_(card, 2, "iqc%d", card->qdio.no_in_queues); rc = 0; out: return rc; @@ -486,40 +485,39 @@ static inline int qeth_is_cq(struct qeth_card *card, unsigned int queue) queue == card->qdio.no_in_queues - 1; } -static void qeth_setup_ccw(struct ccw1 *ccw, u8 cmd_code, u32 len, void *data) +static void qeth_setup_ccw(struct ccw1 *ccw, u8 cmd_code, u8 flags, u32 len, + void *data) { ccw->cmd_code = cmd_code; - ccw->flags = CCW_FLAG_SLI; + ccw->flags = flags | CCW_FLAG_SLI; ccw->count = len; ccw->cda = (__u32) __pa(data); } static int __qeth_issue_next_read(struct qeth_card *card) { - struct qeth_channel *channel = &card->read; - struct qeth_cmd_buffer *iob; + struct qeth_cmd_buffer *iob = card->read_cmd; + struct qeth_channel *channel = iob->channel; + struct ccw1 *ccw = __ccw_from_cmd(iob); int rc; QETH_CARD_TEXT(card, 5, "issnxrd"); if (channel->state != CH_STATE_UP) return -EIO; - iob = qeth_get_buffer(channel); - if (!iob) { - dev_warn(&card->gdev->dev, "The qeth device driver " - "failed to recover an error on the device\n"); - QETH_DBF_MESSAGE(2, "issue_next_read on device %x failed: no iob available\n", - CARD_DEVID(card)); - return -ENOMEM; - } - qeth_setup_ccw(channel->ccw, CCW_CMD_READ, QETH_BUFSIZE, iob->data); + + memset(iob->data, 0, iob->length); + qeth_setup_ccw(ccw, CCW_CMD_READ, 0, iob->length, iob->data); + iob->callback = qeth_issue_next_read_cb; + /* keep the cmd alive after completion: */ + qeth_get_cmd(iob); + QETH_CARD_TEXT(card, 6, "noirqpnd"); - rc = ccw_device_start(channel->ccwdev, channel->ccw, - (addr_t) iob, 0, 0); + rc = ccw_device_start(channel->ccwdev, ccw, (addr_t) iob, 0, 0); if (rc) { QETH_DBF_MESSAGE(2, "error %i on device %x when starting next read ccw!\n", rc, CARD_DEVID(card)); atomic_set(&channel->irq_pending, 0); - qeth_release_buffer(channel, iob); + qeth_put_cmd(iob); card->read_or_write_problem = 1; qeth_schedule_recovery(card); wake_up(&card->wait_q); @@ -542,11 +540,10 @@ static struct qeth_reply *qeth_alloc_reply(struct qeth_card *card) { struct qeth_reply *reply; - reply = kzalloc(sizeof(struct qeth_reply), GFP_ATOMIC); + reply = kzalloc(sizeof(*reply), GFP_KERNEL); if (reply) { refcount_set(&reply->refcnt, 1); - atomic_set(&reply->received, 0); - init_waitqueue_head(&reply->wait_q); + init_completion(&reply->received); } return reply; } @@ -576,11 +573,12 @@ static void qeth_dequeue_reply(struct qeth_card *card, struct qeth_reply *reply) spin_unlock_irq(&card->lock); } -static void qeth_notify_reply(struct qeth_reply *reply) +void qeth_notify_reply(struct qeth_reply *reply, int reason) { - atomic_inc(&reply->received); - wake_up(&reply->wait_q); + reply->rc = reason; + complete(&reply->received); } +EXPORT_SYMBOL_GPL(qeth_notify_reply); static void qeth_issue_ipa_msg(struct qeth_ipa_cmd *cmd, int rc, struct qeth_card *card) @@ -664,10 +662,8 @@ void qeth_clear_ipacmd_list(struct qeth_card *card) QETH_CARD_TEXT(card, 4, "clipalst"); spin_lock_irqsave(&card->lock, flags); - list_for_each_entry(reply, &card->cmd_waiter_list, list) { - reply->rc = -EIO; - qeth_notify_reply(reply); - } + list_for_each_entry(reply, &card->cmd_waiter_list, list) + qeth_notify_reply(reply, -EIO); spin_unlock_irqrestore(&card->lock, flags); } EXPORT_SYMBOL_GPL(qeth_clear_ipacmd_list); @@ -675,9 +671,6 @@ EXPORT_SYMBOL_GPL(qeth_clear_ipacmd_list); static int qeth_check_idx_response(struct qeth_card *card, unsigned char *buffer) { - if (!buffer) - return 0; - QETH_DBF_HEX(CTRL, 2, buffer, QETH_DBF_CTRL_LEN); if ((buffer[2] & 0xc0) == 0xc0) { QETH_DBF_MESSAGE(2, "received an IDX TERMINATE with cause code %#04x\n", @@ -696,93 +689,62 @@ static int qeth_check_idx_response(struct qeth_card *card, return 0; } -static struct qeth_cmd_buffer *__qeth_get_buffer(struct qeth_channel *channel) +void qeth_put_cmd(struct qeth_cmd_buffer *iob) { - __u8 index; - - index = channel->io_buf_no; - do { - if (channel->iob[index].state == BUF_STATE_FREE) { - channel->iob[index].state = BUF_STATE_LOCKED; - channel->io_buf_no = (channel->io_buf_no + 1) % - QETH_CMD_BUFFER_NO; - memset(channel->iob[index].data, 0, QETH_BUFSIZE); - return channel->iob + index; - } - index = (index + 1) % QETH_CMD_BUFFER_NO; - } while (index != channel->io_buf_no); - - return NULL; -} - -void qeth_release_buffer(struct qeth_channel *channel, - struct qeth_cmd_buffer *iob) -{ - unsigned long flags; - - spin_lock_irqsave(&channel->iob_lock, flags); - iob->state = BUF_STATE_FREE; - iob->callback = qeth_send_control_data_cb; - if (iob->reply) { - qeth_put_reply(iob->reply); - iob->reply = NULL; + if (refcount_dec_and_test(&iob->ref_count)) { + if (iob->reply) + qeth_put_reply(iob->reply); + kfree(iob->data); + kfree(iob); } - spin_unlock_irqrestore(&channel->iob_lock, flags); - wake_up(&channel->wait_q); } -EXPORT_SYMBOL_GPL(qeth_release_buffer); +EXPORT_SYMBOL_GPL(qeth_put_cmd); static void qeth_release_buffer_cb(struct qeth_card *card, - struct qeth_channel *channel, struct qeth_cmd_buffer *iob) { - qeth_release_buffer(channel, iob); + qeth_put_cmd(iob); } static void qeth_cancel_cmd(struct qeth_cmd_buffer *iob, int rc) { struct qeth_reply *reply = iob->reply; - if (reply) { - reply->rc = rc; - qeth_notify_reply(reply); - } - qeth_release_buffer(iob->channel, iob); + if (reply) + qeth_notify_reply(reply, rc); + qeth_put_cmd(iob); } -static struct qeth_cmd_buffer *qeth_get_buffer(struct qeth_channel *channel) +struct qeth_cmd_buffer *qeth_alloc_cmd(struct qeth_channel *channel, + unsigned int length, unsigned int ccws, + long timeout) { - struct qeth_cmd_buffer *buffer = NULL; - unsigned long flags; + struct qeth_cmd_buffer *iob; - spin_lock_irqsave(&channel->iob_lock, flags); - buffer = __qeth_get_buffer(channel); - spin_unlock_irqrestore(&channel->iob_lock, flags); - return buffer; -} + if (length > QETH_BUFSIZE) + return NULL; -struct qeth_cmd_buffer *qeth_wait_for_buffer(struct qeth_channel *channel) -{ - struct qeth_cmd_buffer *buffer; - wait_event(channel->wait_q, - ((buffer = qeth_get_buffer(channel)) != NULL)); - return buffer; -} -EXPORT_SYMBOL_GPL(qeth_wait_for_buffer); + iob = kzalloc(sizeof(*iob), GFP_KERNEL); + if (!iob) + return NULL; -void qeth_clear_cmd_buffers(struct qeth_channel *channel) -{ - int cnt; + iob->data = kzalloc(ALIGN(length, 8) + ccws * sizeof(struct ccw1), + GFP_KERNEL | GFP_DMA); + if (!iob->data) { + kfree(iob); + return NULL; + } - for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++) - qeth_release_buffer(channel, &channel->iob[cnt]); - channel->io_buf_no = 0; + refcount_set(&iob->ref_count, 1); + iob->channel = channel; + iob->timeout = timeout; + iob->length = length; + return iob; } -EXPORT_SYMBOL_GPL(qeth_clear_cmd_buffers); +EXPORT_SYMBOL_GPL(qeth_alloc_cmd); -static void qeth_send_control_data_cb(struct qeth_card *card, - struct qeth_channel *channel, - struct qeth_cmd_buffer *iob) +static void qeth_issue_next_read_cb(struct qeth_card *card, + struct qeth_cmd_buffer *iob) { struct qeth_ipa_cmd *cmd = NULL; struct qeth_reply *reply = NULL; @@ -846,18 +808,16 @@ static void qeth_send_control_data_cb(struct qeth_card *card, } } - if (rc <= 0) { - reply->rc = rc; - qeth_notify_reply(reply); - } - + if (rc <= 0) + qeth_notify_reply(reply, rc); qeth_put_reply(reply); out: memcpy(&card->seqno.pdu_hdr_ack, QETH_PDU_HEADER_SEQ_NO(iob->data), QETH_SEQ_NO_LENGTH); - qeth_release_buffer(channel, iob); + qeth_put_cmd(iob); + __qeth_issue_next_read(card); } static int qeth_set_thread_start_bit(struct qeth_card *card, @@ -984,7 +944,7 @@ static int qeth_get_problem(struct qeth_card *card, struct ccw_device *cdev, } static int qeth_check_irb_error(struct qeth_card *card, struct ccw_device *cdev, - unsigned long intparm, struct irb *irb) + struct irb *irb) { if (!IS_ERR(irb)) return 0; @@ -1001,12 +961,6 @@ static int qeth_check_irb_error(struct qeth_card *card, struct ccw_device *cdev, " on the device\n"); QETH_CARD_TEXT(card, 2, "ckirberr"); QETH_CARD_TEXT_(card, 2, " rc%d", -ETIMEDOUT); - if (intparm == QETH_RCD_PARM) { - if (card->data.ccwdev == cdev) { - card->data.state = CH_STATE_DOWN; - wake_up(&card->wait_q); - } - } return -ETIMEDOUT; default: QETH_DBF_MESSAGE(2, "unknown error %ld on channel %x\n", @@ -1049,7 +1003,7 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, if (qeth_intparm_is_iob(intparm)) iob = (struct qeth_cmd_buffer *) __va((addr_t)intparm); - rc = qeth_check_irb_error(card, cdev, intparm, irb); + rc = qeth_check_irb_error(card, cdev, irb); if (rc) { /* IO was terminated, free its resources. */ if (iob) @@ -1067,11 +1021,6 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, if (irb->scsw.cmd.fctl & (SCSW_FCTL_HALT_FUNC)) channel->state = CH_STATE_HALTED; - /*let's wake up immediately on data channel*/ - if ((channel == &card->data) && (intparm != 0) && - (intparm != QETH_RCD_PARM)) - goto out; - if (intparm == QETH_CLEAR_CHANNEL_PARM) { QETH_CARD_TEXT(card, 6, "clrchpar"); /* we don't have to handle this further */ @@ -1101,10 +1050,7 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, print_hex_dump(KERN_WARNING, "qeth: sense data ", DUMP_PREFIX_OFFSET, 16, 1, irb->ecw, 32, 1); } - if (intparm == QETH_RCD_PARM) { - channel->state = CH_STATE_DOWN; - goto out; - } + rc = qeth_get_problem(card, cdev, irb); if (rc) { card->read_or_write_problem = 1; @@ -1116,18 +1062,8 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, } } - if (intparm == QETH_RCD_PARM) { - channel->state = CH_STATE_RCD_DONE; - goto out; - } - if (channel == &card->data) - return; - if (channel == &card->read && - channel->state == CH_STATE_UP) - __qeth_issue_next_read(card); - if (iob && iob->callback) - iob->callback(card, iob->channel, iob); + iob->callback(card, iob); out: wake_up(&card->wait_q); @@ -1173,20 +1109,19 @@ static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue, qeth_release_skbs(buf); - for (i = 0; i < QETH_MAX_BUFFER_ELEMENTS(queue->card); ++i) { + for (i = 0; i < queue->max_elements; ++i) { if (buf->buffer->element[i].addr && buf->is_header[i]) kmem_cache_free(qeth_core_header_cache, buf->buffer->element[i].addr); buf->is_header[i] = 0; } - qeth_scrub_qdio_buffer(buf->buffer, - QETH_MAX_BUFFER_ELEMENTS(queue->card)); + qeth_scrub_qdio_buffer(buf->buffer, queue->max_elements); buf->next_element_to_fill = 0; atomic_set(&buf->state, QETH_QDIO_BUF_EMPTY); } -static void qeth_clear_outq_buffers(struct qeth_qdio_out_q *q, int free) +static void qeth_drain_output_queue(struct qeth_qdio_out_q *q, bool free) { int j; @@ -1202,19 +1137,18 @@ static void qeth_clear_outq_buffers(struct qeth_qdio_out_q *q, int free) } } -void qeth_clear_qdio_buffers(struct qeth_card *card) +void qeth_drain_output_queues(struct qeth_card *card) { int i; QETH_CARD_TEXT(card, 2, "clearqdbf"); /* clear outbound buffers to free skbs */ for (i = 0; i < card->qdio.no_out_queues; ++i) { - if (card->qdio.out_qs[i]) { - qeth_clear_outq_buffers(card->qdio.out_qs[i], 0); - } + if (card->qdio.out_qs[i]) + qeth_drain_output_queue(card->qdio.out_qs[i], false); } } -EXPORT_SYMBOL_GPL(qeth_clear_qdio_buffers); +EXPORT_SYMBOL_GPL(qeth_drain_output_queues); static void qeth_free_buffer_pool(struct qeth_card *card) { @@ -1232,121 +1166,90 @@ static void qeth_free_buffer_pool(struct qeth_card *card) static void qeth_clean_channel(struct qeth_channel *channel) { struct ccw_device *cdev = channel->ccwdev; - int cnt; QETH_DBF_TEXT(SETUP, 2, "freech"); spin_lock_irq(get_ccwdev_lock(cdev)); cdev->handler = NULL; spin_unlock_irq(get_ccwdev_lock(cdev)); - - for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++) - kfree(channel->iob[cnt].data); - kfree(channel->ccw); } -static int qeth_setup_channel(struct qeth_channel *channel, bool alloc_buffers) +static void qeth_setup_channel(struct qeth_channel *channel) { struct ccw_device *cdev = channel->ccwdev; - int cnt; QETH_DBF_TEXT(SETUP, 2, "setupch"); - channel->ccw = kmalloc(sizeof(struct ccw1), GFP_KERNEL | GFP_DMA); - if (!channel->ccw) - return -ENOMEM; channel->state = CH_STATE_DOWN; atomic_set(&channel->irq_pending, 0); - init_waitqueue_head(&channel->wait_q); spin_lock_irq(get_ccwdev_lock(cdev)); cdev->handler = qeth_irq; spin_unlock_irq(get_ccwdev_lock(cdev)); +} - if (!alloc_buffers) - return 0; +static int qeth_osa_set_output_queues(struct qeth_card *card, bool single) +{ + unsigned int count = single ? 1 : card->dev->num_tx_queues; + int rc; - for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++) { - channel->iob[cnt].data = kmalloc(QETH_BUFSIZE, - GFP_KERNEL | GFP_DMA); - if (channel->iob[cnt].data == NULL) - break; - channel->iob[cnt].state = BUF_STATE_FREE; - channel->iob[cnt].channel = channel; - channel->iob[cnt].callback = qeth_send_control_data_cb; - } - if (cnt < QETH_CMD_BUFFER_NO) { - qeth_clean_channel(channel); - return -ENOMEM; - } - channel->io_buf_no = 0; - spin_lock_init(&channel->iob_lock); + rtnl_lock(); + rc = netif_set_real_num_tx_queues(card->dev, count); + rtnl_unlock(); - return 0; -} + if (rc) + return rc; -static void qeth_set_single_write_queues(struct qeth_card *card) -{ - if ((atomic_read(&card->qdio.state) != QETH_QDIO_UNINITIALIZED) && - (card->qdio.no_out_queues == 4)) - qeth_free_qdio_buffers(card); + if (card->qdio.no_out_queues == count) + return 0; - card->qdio.no_out_queues = 1; - if (card->qdio.default_out_queue != 0) - dev_info(&card->gdev->dev, "Priority Queueing not supported\n"); + if (atomic_read(&card->qdio.state) != QETH_QDIO_UNINITIALIZED) + qeth_free_qdio_queues(card); - card->qdio.default_out_queue = 0; -} + if (count == 1) + dev_info(&card->gdev->dev, "Priority Queueing not supported\n"); -static void qeth_set_multiple_write_queues(struct qeth_card *card) -{ - if ((atomic_read(&card->qdio.state) != QETH_QDIO_UNINITIALIZED) && - (card->qdio.no_out_queues == 1)) { - qeth_free_qdio_buffers(card); - card->qdio.default_out_queue = 2; - } - card->qdio.no_out_queues = 4; + card->qdio.default_out_queue = single ? 0 : QETH_DEFAULT_QUEUE; + card->qdio.no_out_queues = count; + return 0; } -static void qeth_update_from_chp_desc(struct qeth_card *card) +static int qeth_update_from_chp_desc(struct qeth_card *card) { struct ccw_device *ccwdev; struct channel_path_desc_fmt0 *chp_dsc; + int rc = 0; - QETH_DBF_TEXT(SETUP, 2, "chp_desc"); + QETH_CARD_TEXT(card, 2, "chp_desc"); ccwdev = card->data.ccwdev; chp_dsc = ccw_device_get_chp_desc(ccwdev, 0); if (!chp_dsc) - goto out; + return -ENOMEM; card->info.func_level = 0x4100 + chp_dsc->desc; - if (card->info.type == QETH_CARD_TYPE_IQD) - goto out; - /* CHPP field bit 6 == 1 -> single queue */ - if ((chp_dsc->chpp & 0x02) == 0x02) - qeth_set_single_write_queues(card); - else - qeth_set_multiple_write_queues(card); -out: + if (IS_OSD(card) || IS_OSX(card)) + /* CHPP field bit 6 == 1 -> single queue */ + rc = qeth_osa_set_output_queues(card, chp_dsc->chpp & 0x02); + kfree(chp_dsc); - QETH_DBF_TEXT_(SETUP, 2, "nr:%x", card->qdio.no_out_queues); - QETH_DBF_TEXT_(SETUP, 2, "lvl:%02x", card->info.func_level); + QETH_CARD_TEXT_(card, 2, "nr:%x", card->qdio.no_out_queues); + QETH_CARD_TEXT_(card, 2, "lvl:%02x", card->info.func_level); + return rc; } static void qeth_init_qdio_info(struct qeth_card *card) { - QETH_DBF_TEXT(SETUP, 4, "intqdinf"); + QETH_CARD_TEXT(card, 4, "intqdinf"); atomic_set(&card->qdio.state, QETH_QDIO_UNINITIALIZED); card->qdio.do_prio_queueing = QETH_PRIOQ_DEFAULT; card->qdio.default_out_queue = QETH_DEFAULT_QUEUE; - card->qdio.no_out_queues = QETH_MAX_QUEUES; /* inbound */ card->qdio.no_in_queues = 1; card->qdio.in_buf_size = QETH_IN_BUF_SIZE_DEFAULT; - if (card->info.type == QETH_CARD_TYPE_IQD) + if (IS_IQD(card)) card->qdio.init_pool.buf_count = QETH_IN_BUF_COUNT_HSDEFAULT; else card->qdio.init_pool.buf_count = QETH_IN_BUF_COUNT_DEFAULT; @@ -1404,14 +1307,11 @@ static void qeth_start_kernel_thread(struct work_struct *work) static void qeth_buffer_reclaim_work(struct work_struct *); static void qeth_setup_card(struct qeth_card *card) { - QETH_DBF_TEXT(SETUP, 2, "setupcrd"); - QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *)); + QETH_CARD_TEXT(card, 2, "setupcrd"); card->info.type = CARD_RDEV(card)->id.driver_info; card->state = CARD_STATE_DOWN; - spin_lock_init(&card->mclock); spin_lock_init(&card->lock); - spin_lock_init(&card->ip_lock); spin_lock_init(&card->thread_mask_lock); mutex_init(&card->conf_mutex); mutex_init(&card->discipline_mutex); @@ -1451,24 +1351,23 @@ static struct qeth_card *qeth_alloc_card(struct ccwgroup_device *gdev) CARD_WDEV(card) = gdev->cdev[1]; CARD_DDEV(card) = gdev->cdev[2]; - card->event_wq = alloc_ordered_workqueue("%s", 0, dev_name(&gdev->dev)); + card->event_wq = alloc_ordered_workqueue("%s_event", 0, + dev_name(&gdev->dev)); if (!card->event_wq) goto out_wq; - if (qeth_setup_channel(&card->read, true)) - goto out_ip; - if (qeth_setup_channel(&card->write, true)) - goto out_channel; - if (qeth_setup_channel(&card->data, false)) - goto out_data; + + card->read_cmd = qeth_alloc_cmd(&card->read, QETH_BUFSIZE, 1, 0); + if (!card->read_cmd) + goto out_read_cmd; + + qeth_setup_channel(&card->read); + qeth_setup_channel(&card->write); + qeth_setup_channel(&card->data); card->qeth_service_level.seq_print = qeth_core_sl_print; register_service_level(&card->qeth_service_level); return card; -out_data: - qeth_clean_channel(&card->write); -out_channel: - qeth_clean_channel(&card->read); -out_ip: +out_read_cmd: destroy_workqueue(card->event_wq); out_wq: dev_set_drvdata(&gdev->dev, NULL); @@ -1571,7 +1470,7 @@ int qeth_qdio_clear_card(struct qeth_card *card, int use_halt) switch (atomic_cmpxchg(&card->qdio.state, QETH_QDIO_ESTABLISHED, QETH_QDIO_CLEANING)) { case QETH_QDIO_ESTABLISHED: - if (card->info.type == QETH_CARD_TYPE_IQD) + if (IS_IQD(card)) rc = qdio_shutdown(CARD_DDEV(card), QDIO_FLAG_CLEANUP_USING_HALT); else @@ -1594,60 +1493,6 @@ int qeth_qdio_clear_card(struct qeth_card *card, int use_halt) } EXPORT_SYMBOL_GPL(qeth_qdio_clear_card); -static int qeth_read_conf_data(struct qeth_card *card, void **buffer, - int *length) -{ - struct ciw *ciw; - char *rcd_buf; - int ret; - struct qeth_channel *channel = &card->data; - - /* - * scan for RCD command in extended SenseID data - */ - ciw = ccw_device_get_ciw(channel->ccwdev, CIW_TYPE_RCD); - if (!ciw || ciw->cmd == 0) - return -EOPNOTSUPP; - rcd_buf = kzalloc(ciw->count, GFP_KERNEL | GFP_DMA); - if (!rcd_buf) - return -ENOMEM; - - qeth_setup_ccw(channel->ccw, ciw->cmd, ciw->count, rcd_buf); - channel->state = CH_STATE_RCD; - spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); - ret = ccw_device_start_timeout(channel->ccwdev, channel->ccw, - QETH_RCD_PARM, LPM_ANYPATH, 0, - QETH_RCD_TIMEOUT); - spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); - if (!ret) - wait_event(card->wait_q, - (channel->state == CH_STATE_RCD_DONE || - channel->state == CH_STATE_DOWN)); - if (channel->state == CH_STATE_DOWN) - ret = -EIO; - else - channel->state = CH_STATE_DOWN; - if (ret) { - kfree(rcd_buf); - *buffer = NULL; - *length = 0; - } else { - *length = ciw->count; - *buffer = rcd_buf; - } - return ret; -} - -static void qeth_configure_unitaddr(struct qeth_card *card, char *prcd) -{ - QETH_DBF_TEXT(SETUP, 2, "cfgunit"); - card->info.chpid = prcd[30]; - card->info.unit_addr2 = prcd[31]; - card->info.cula = prcd[63]; - card->info.guestlan = ((prcd[0x10] == _ascebc['V']) && - (prcd[0x11] == _ascebc['M'])); -} - static enum qeth_discipline_id qeth_vm_detect_layer(struct qeth_card *card) { enum qeth_discipline_id disc = QETH_DISCIPLINE_UNDETERMINED; @@ -1657,7 +1502,7 @@ static enum qeth_discipline_id qeth_vm_detect_layer(struct qeth_card *card) char userid[80]; int rc = 0; - QETH_DBF_TEXT(SETUP, 2, "vmlayer"); + QETH_CARD_TEXT(card, 2, "vmlayer"); cpcmd("QUERY USERID", userid, sizeof(userid), &rc); if (rc) @@ -1700,7 +1545,7 @@ out: kfree(response); kfree(request); if (rc) - QETH_DBF_TEXT_(SETUP, 2, "err%x", rc); + QETH_CARD_TEXT_(card, 2, "err%x", rc); return disc; } @@ -1709,34 +1554,31 @@ static enum qeth_discipline_id qeth_enforce_discipline(struct qeth_card *card) { enum qeth_discipline_id disc = QETH_DISCIPLINE_UNDETERMINED; - if (card->info.type == QETH_CARD_TYPE_OSM || - card->info.type == QETH_CARD_TYPE_OSN) + if (IS_OSM(card) || IS_OSN(card)) disc = QETH_DISCIPLINE_LAYER2; - else if (card->info.guestlan) - disc = (card->info.type == QETH_CARD_TYPE_IQD) ? - QETH_DISCIPLINE_LAYER3 : - qeth_vm_detect_layer(card); + else if (IS_VM_NIC(card)) + disc = IS_IQD(card) ? QETH_DISCIPLINE_LAYER3 : + qeth_vm_detect_layer(card); switch (disc) { case QETH_DISCIPLINE_LAYER2: - QETH_DBF_TEXT(SETUP, 3, "force l2"); + QETH_CARD_TEXT(card, 3, "force l2"); break; case QETH_DISCIPLINE_LAYER3: - QETH_DBF_TEXT(SETUP, 3, "force l3"); + QETH_CARD_TEXT(card, 3, "force l3"); break; default: - QETH_DBF_TEXT(SETUP, 3, "force no"); + QETH_CARD_TEXT(card, 3, "force no"); } return disc; } -static void qeth_configure_blkt_default(struct qeth_card *card, char *prcd) +static void qeth_set_blkt_defaults(struct qeth_card *card) { - QETH_DBF_TEXT(SETUP, 2, "cfgblkt"); + QETH_CARD_TEXT(card, 2, "cfgblkt"); - if (prcd[74] == 0xF0 && prcd[75] == 0xF0 && - prcd[76] >= 0xF1 && prcd[76] <= 0xF4) { + if (card->info.use_v1_blkt) { card->info.blkt.time_total = 0; card->info.blkt.inter_packet = 0; card->info.blkt.inter_packet_jumbo = 0; @@ -1771,121 +1613,13 @@ static void qeth_init_func_level(struct qeth_card *card) } } -static int qeth_idx_activate_get_answer(struct qeth_card *card, - struct qeth_channel *channel, - void (*reply_cb)(struct qeth_card *, - struct qeth_channel *, - struct qeth_cmd_buffer *)) -{ - struct qeth_cmd_buffer *iob; - int rc; - - QETH_DBF_TEXT(SETUP, 2, "idxanswr"); - iob = qeth_get_buffer(channel); - if (!iob) - return -ENOMEM; - iob->callback = reply_cb; - qeth_setup_ccw(channel->ccw, CCW_CMD_READ, QETH_BUFSIZE, iob->data); - - wait_event(card->wait_q, - atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0); - QETH_DBF_TEXT(SETUP, 6, "noirqpnd"); - spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); - rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw, - (addr_t) iob, 0, 0, QETH_TIMEOUT); - spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); - - if (rc) { - QETH_DBF_MESSAGE(2, "Error2 in activating channel rc=%d\n", rc); - QETH_DBF_TEXT_(SETUP, 2, "2err%d", rc); - atomic_set(&channel->irq_pending, 0); - qeth_release_buffer(channel, iob); - wake_up(&card->wait_q); - return rc; - } - rc = wait_event_interruptible_timeout(card->wait_q, - channel->state == CH_STATE_UP, QETH_TIMEOUT); - if (rc == -ERESTARTSYS) - return rc; - if (channel->state != CH_STATE_UP) { - rc = -ETIME; - QETH_DBF_TEXT_(SETUP, 2, "3err%d", rc); - } else - rc = 0; - return rc; -} - -static int qeth_idx_activate_channel(struct qeth_card *card, - struct qeth_channel *channel, - void (*reply_cb)(struct qeth_card *, - struct qeth_channel *, - struct qeth_cmd_buffer *)) +static void qeth_idx_finalize_cmd(struct qeth_card *card, + struct qeth_cmd_buffer *iob) { - struct qeth_cmd_buffer *iob; - __u16 temp; - __u8 tmp; - int rc; - struct ccw_dev_id temp_devid; - - QETH_DBF_TEXT(SETUP, 2, "idxactch"); - - iob = qeth_get_buffer(channel); - if (!iob) - return -ENOMEM; - iob->callback = reply_cb; - qeth_setup_ccw(channel->ccw, CCW_CMD_WRITE, IDX_ACTIVATE_SIZE, - iob->data); - if (channel == &card->write) { - memcpy(iob->data, IDX_ACTIVATE_WRITE, IDX_ACTIVATE_SIZE); - memcpy(QETH_TRANSPORT_HEADER_SEQ_NO(iob->data), - &card->seqno.trans_hdr, QETH_SEQ_NO_LENGTH); + memcpy(QETH_TRANSPORT_HEADER_SEQ_NO(iob->data), &card->seqno.trans_hdr, + QETH_SEQ_NO_LENGTH); + if (iob->channel == &card->write) card->seqno.trans_hdr++; - } else { - memcpy(iob->data, IDX_ACTIVATE_READ, IDX_ACTIVATE_SIZE); - memcpy(QETH_TRANSPORT_HEADER_SEQ_NO(iob->data), - &card->seqno.trans_hdr, QETH_SEQ_NO_LENGTH); - } - tmp = ((u8)card->dev->dev_port) | 0x80; - memcpy(QETH_IDX_ACT_PNO(iob->data), &tmp, 1); - memcpy(QETH_IDX_ACT_ISSUER_RM_TOKEN(iob->data), - &card->token.issuer_rm_w, QETH_MPC_TOKEN_LENGTH); - memcpy(QETH_IDX_ACT_FUNC_LEVEL(iob->data), - &card->info.func_level, sizeof(__u16)); - ccw_device_get_id(CARD_DDEV(card), &temp_devid); - memcpy(QETH_IDX_ACT_QDIO_DEV_CUA(iob->data), &temp_devid.devno, 2); - temp = (card->info.cula << 8) + card->info.unit_addr2; - memcpy(QETH_IDX_ACT_QDIO_DEV_REALADDR(iob->data), &temp, 2); - - wait_event(card->wait_q, - atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0); - QETH_DBF_TEXT(SETUP, 6, "noirqpnd"); - spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); - rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw, - (addr_t) iob, 0, 0, QETH_TIMEOUT); - spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); - - if (rc) { - QETH_DBF_MESSAGE(2, "Error1 in activating channel. rc=%d\n", - rc); - QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc); - atomic_set(&channel->irq_pending, 0); - qeth_release_buffer(channel, iob); - wake_up(&card->wait_q); - return rc; - } - rc = wait_event_interruptible_timeout(card->wait_q, - channel->state == CH_STATE_ACTIVATING, QETH_TIMEOUT); - if (rc == -ERESTARTSYS) - return rc; - if (channel->state != CH_STATE_ACTIVATING) { - dev_warn(&channel->ccwdev->dev, "The qeth device driver" - " failed to recover an error on the device\n"); - QETH_DBF_MESSAGE(2, "IDX activate timed out on channel %x\n", - CCW_DEVID(channel->ccwdev)); - QETH_DBF_TEXT_(SETUP, 2, "2err%d", -ETIME); - return -ETIME; - } - return qeth_idx_activate_get_answer(card, channel, reply_cb); } static int qeth_peer_func_level(int level) @@ -1897,117 +1631,41 @@ static int qeth_peer_func_level(int level) return level; } -static void qeth_idx_write_cb(struct qeth_card *card, - struct qeth_channel *channel, - struct qeth_cmd_buffer *iob) +static void qeth_mpc_finalize_cmd(struct qeth_card *card, + struct qeth_cmd_buffer *iob) { - __u16 temp; + qeth_idx_finalize_cmd(card, iob); - QETH_DBF_TEXT(SETUP , 2, "idxwrcb"); - - if (channel->state == CH_STATE_DOWN) { - channel->state = CH_STATE_ACTIVATING; - goto out; - } + memcpy(QETH_PDU_HEADER_SEQ_NO(iob->data), + &card->seqno.pdu_hdr, QETH_SEQ_NO_LENGTH); + card->seqno.pdu_hdr++; + memcpy(QETH_PDU_HEADER_ACK_SEQ_NO(iob->data), + &card->seqno.pdu_hdr_ack, QETH_SEQ_NO_LENGTH); - if (!(QETH_IS_IDX_ACT_POS_REPLY(iob->data))) { - if (QETH_IDX_ACT_CAUSE_CODE(iob->data) == QETH_IDX_ACT_ERR_EXCL) - dev_err(&channel->ccwdev->dev, - "The adapter is used exclusively by another " - "host\n"); - else - QETH_DBF_MESSAGE(2, "IDX_ACTIVATE on channel %x: negative reply\n", - CCW_DEVID(channel->ccwdev)); - goto out; - } - memcpy(&temp, QETH_IDX_ACT_FUNC_LEVEL(iob->data), 2); - if ((temp & ~0x0100) != qeth_peer_func_level(card->info.func_level)) { - QETH_DBF_MESSAGE(2, "IDX_ACTIVATE on channel %x: function level mismatch (sent: %#x, received: %#x)\n", - CCW_DEVID(channel->ccwdev), - card->info.func_level, temp); - goto out; - } - channel->state = CH_STATE_UP; -out: - qeth_release_buffer(channel, iob); + iob->reply->seqno = QETH_IDX_COMMAND_SEQNO; + iob->callback = qeth_release_buffer_cb; } -static void qeth_idx_read_cb(struct qeth_card *card, - struct qeth_channel *channel, - struct qeth_cmd_buffer *iob) +static struct qeth_cmd_buffer *qeth_mpc_alloc_cmd(struct qeth_card *card, + void *data, + unsigned int data_length) { - __u16 temp; - - QETH_DBF_TEXT(SETUP , 2, "idxrdcb"); - if (channel->state == CH_STATE_DOWN) { - channel->state = CH_STATE_ACTIVATING; - goto out; - } - - if (qeth_check_idx_response(card, iob->data)) - goto out; - - if (!(QETH_IS_IDX_ACT_POS_REPLY(iob->data))) { - switch (QETH_IDX_ACT_CAUSE_CODE(iob->data)) { - case QETH_IDX_ACT_ERR_EXCL: - dev_err(&channel->ccwdev->dev, - "The adapter is used exclusively by another " - "host\n"); - break; - case QETH_IDX_ACT_ERR_AUTH: - case QETH_IDX_ACT_ERR_AUTH_USER: - dev_err(&channel->ccwdev->dev, - "Setting the device online failed because of " - "insufficient authorization\n"); - break; - default: - QETH_DBF_MESSAGE(2, "IDX_ACTIVATE on channel %x: negative reply\n", - CCW_DEVID(channel->ccwdev)); - } - QETH_CARD_TEXT_(card, 2, "idxread%c", - QETH_IDX_ACT_CAUSE_CODE(iob->data)); - goto out; - } - - memcpy(&temp, QETH_IDX_ACT_FUNC_LEVEL(iob->data), 2); - if (temp != qeth_peer_func_level(card->info.func_level)) { - QETH_DBF_MESSAGE(2, "IDX_ACTIVATE on channel %x: function level mismatch (sent: %#x, received: %#x)\n", - CCW_DEVID(channel->ccwdev), - card->info.func_level, temp); - goto out; - } - memcpy(&card->token.issuer_rm_r, - QETH_IDX_ACT_ISSUER_RM_TOKEN(iob->data), - QETH_MPC_TOKEN_LENGTH); - memcpy(&card->info.mcl_level[0], - QETH_IDX_REPLY_LEVEL(iob->data), QETH_MCL_LENGTH); - channel->state = CH_STATE_UP; -out: - qeth_release_buffer(channel, iob); -} + struct qeth_cmd_buffer *iob; -void qeth_prepare_control_data(struct qeth_card *card, int len, - struct qeth_cmd_buffer *iob) -{ - qeth_setup_ccw(iob->channel->ccw, CCW_CMD_WRITE, len, iob->data); - iob->callback = qeth_release_buffer_cb; + iob = qeth_alloc_cmd(&card->write, data_length, 1, QETH_TIMEOUT); + if (!iob) + return NULL; - memcpy(QETH_TRANSPORT_HEADER_SEQ_NO(iob->data), - &card->seqno.trans_hdr, QETH_SEQ_NO_LENGTH); - card->seqno.trans_hdr++; - memcpy(QETH_PDU_HEADER_SEQ_NO(iob->data), - &card->seqno.pdu_hdr, QETH_SEQ_NO_LENGTH); - card->seqno.pdu_hdr++; - memcpy(QETH_PDU_HEADER_ACK_SEQ_NO(iob->data), - &card->seqno.pdu_hdr_ack, QETH_SEQ_NO_LENGTH); - QETH_DBF_HEX(CTRL, 2, iob->data, min(len, QETH_DBF_CTRL_LEN)); + memcpy(iob->data, data, data_length); + qeth_setup_ccw(__ccw_from_cmd(iob), CCW_CMD_WRITE, 0, data_length, + iob->data); + iob->finalize = qeth_mpc_finalize_cmd; + return iob; } -EXPORT_SYMBOL_GPL(qeth_prepare_control_data); /** * qeth_send_control_data() - send control command to the card * @card: qeth_card structure pointer - * @len: size of the command buffer * @iob: qeth_cmd_buffer pointer * @reply_cb: callback function pointer * @cb_card: pointer to the qeth_card structure @@ -2027,7 +1685,7 @@ EXPORT_SYMBOL_GPL(qeth_prepare_control_data); * field 'param' of the structure qeth_reply. */ -static int qeth_send_control_data(struct qeth_card *card, int len, +static int qeth_send_control_data(struct qeth_card *card, struct qeth_cmd_buffer *iob, int (*reply_cb)(struct qeth_card *cb_card, struct qeth_reply *cb_reply, @@ -2035,50 +1693,43 @@ static int qeth_send_control_data(struct qeth_card *card, int len, void *reply_param) { struct qeth_channel *channel = iob->channel; + long timeout = iob->timeout; int rc; struct qeth_reply *reply = NULL; - unsigned long timeout, event_timeout; - struct qeth_ipa_cmd *cmd = NULL; QETH_CARD_TEXT(card, 2, "sendctl"); - if (card->read_or_write_problem) { - qeth_release_buffer(channel, iob); - return -EIO; - } reply = qeth_alloc_reply(card); if (!reply) { - qeth_release_buffer(channel, iob); + qeth_put_cmd(iob); return -ENOMEM; } reply->callback = reply_cb; reply->param = reply_param; - /* pairs with qeth_release_buffer(): */ + /* pairs with qeth_put_cmd(): */ qeth_get_reply(reply); iob->reply = reply; - while (atomic_cmpxchg(&channel->irq_pending, 0, 1)) ; - - if (IS_IPA(iob->data)) { - cmd = __ipa_cmd(iob); - cmd->hdr.seqno = card->seqno.ipa++; - reply->seqno = cmd->hdr.seqno; - event_timeout = QETH_IPA_TIMEOUT; - } else { - reply->seqno = QETH_IDX_COMMAND_SEQNO; - event_timeout = QETH_TIMEOUT; + timeout = wait_event_interruptible_timeout(card->wait_q, + qeth_trylock_channel(channel), + timeout); + if (timeout <= 0) { + qeth_put_reply(reply); + qeth_put_cmd(iob); + return (timeout == -ERESTARTSYS) ? -EINTR : -ETIME; } - qeth_prepare_control_data(card, len, iob); - qeth_enqueue_reply(card, reply); + if (iob->finalize) + iob->finalize(card, iob); + QETH_DBF_HEX(CTRL, 2, iob->data, min(iob->length, QETH_DBF_CTRL_LEN)); - timeout = jiffies + event_timeout; + qeth_enqueue_reply(card, reply); QETH_CARD_TEXT(card, 6, "noirqpnd"); spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); - rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw, - (addr_t) iob, 0, 0, event_timeout); + rc = ccw_device_start_timeout(channel->ccwdev, __ccw_from_cmd(iob), + (addr_t) iob, 0, 0, timeout); spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (rc) { QETH_DBF_MESSAGE(2, "qeth_send_control_data on device %x: ccw_device_start rc = %i\n", @@ -2086,36 +1737,227 @@ static int qeth_send_control_data(struct qeth_card *card, int len, QETH_CARD_TEXT_(card, 2, " err%d", rc); qeth_dequeue_reply(card, reply); qeth_put_reply(reply); - qeth_release_buffer(channel, iob); + qeth_put_cmd(iob); atomic_set(&channel->irq_pending, 0); wake_up(&card->wait_q); return rc; } - /* we have only one long running ipassist, since we can ensure - process context of this command we can sleep */ - if (cmd && cmd->hdr.command == IPA_CMD_SETIP && - cmd->hdr.prot_version == QETH_PROT_IPV4) { - if (!wait_event_timeout(reply->wait_q, - atomic_read(&reply->received), event_timeout)) - goto time_err; - } else { - while (!atomic_read(&reply->received)) { - if (time_after(jiffies, timeout)) - goto time_err; - cpu_relax(); - } - } + timeout = wait_for_completion_interruptible_timeout(&reply->received, + timeout); + if (timeout <= 0) + rc = (timeout == -ERESTARTSYS) ? -EINTR : -ETIME; qeth_dequeue_reply(card, reply); - rc = reply->rc; + if (!rc) + rc = reply->rc; qeth_put_reply(reply); return rc; +} -time_err: - qeth_dequeue_reply(card, reply); - qeth_put_reply(reply); - return -ETIME; +static void qeth_read_conf_data_cb(struct qeth_card *card, + struct qeth_cmd_buffer *iob) +{ + unsigned char *prcd = iob->data; + + QETH_CARD_TEXT(card, 2, "cfgunit"); + card->info.chpid = prcd[30]; + card->info.unit_addr2 = prcd[31]; + card->info.cula = prcd[63]; + card->info.is_vm_nic = ((prcd[0x10] == _ascebc['V']) && + (prcd[0x11] == _ascebc['M'])); + card->info.use_v1_blkt = prcd[74] == 0xF0 && prcd[75] == 0xF0 && + prcd[76] >= 0xF1 && prcd[76] <= 0xF4; + + qeth_notify_reply(iob->reply, 0); + qeth_put_cmd(iob); +} + +static int qeth_read_conf_data(struct qeth_card *card) +{ + struct qeth_channel *channel = &card->data; + struct qeth_cmd_buffer *iob; + struct ciw *ciw; + + /* scan for RCD command in extended SenseID data */ + ciw = ccw_device_get_ciw(channel->ccwdev, CIW_TYPE_RCD); + if (!ciw || ciw->cmd == 0) + return -EOPNOTSUPP; + + iob = qeth_alloc_cmd(channel, ciw->count, 1, QETH_RCD_TIMEOUT); + if (!iob) + return -ENOMEM; + + iob->callback = qeth_read_conf_data_cb; + qeth_setup_ccw(__ccw_from_cmd(iob), ciw->cmd, 0, iob->length, + iob->data); + + return qeth_send_control_data(card, iob, NULL, NULL); +} + +static int qeth_idx_check_activate_response(struct qeth_card *card, + struct qeth_channel *channel, + struct qeth_cmd_buffer *iob) +{ + int rc; + + rc = qeth_check_idx_response(card, iob->data); + if (rc) + return rc; + + if (QETH_IS_IDX_ACT_POS_REPLY(iob->data)) + return 0; + + /* negative reply: */ + QETH_CARD_TEXT_(card, 2, "idxneg%c", + QETH_IDX_ACT_CAUSE_CODE(iob->data)); + + switch (QETH_IDX_ACT_CAUSE_CODE(iob->data)) { + case QETH_IDX_ACT_ERR_EXCL: + dev_err(&channel->ccwdev->dev, + "The adapter is used exclusively by another host\n"); + return -EBUSY; + case QETH_IDX_ACT_ERR_AUTH: + case QETH_IDX_ACT_ERR_AUTH_USER: + dev_err(&channel->ccwdev->dev, + "Setting the device online failed because of insufficient authorization\n"); + return -EPERM; + default: + QETH_DBF_MESSAGE(2, "IDX_ACTIVATE on channel %x: negative reply\n", + CCW_DEVID(channel->ccwdev)); + return -EIO; + } +} + +static void qeth_idx_activate_read_channel_cb(struct qeth_card *card, + struct qeth_cmd_buffer *iob) +{ + struct qeth_channel *channel = iob->channel; + u16 peer_level; + int rc; + + QETH_CARD_TEXT(card, 2, "idxrdcb"); + + rc = qeth_idx_check_activate_response(card, channel, iob); + if (rc) + goto out; + + memcpy(&peer_level, QETH_IDX_ACT_FUNC_LEVEL(iob->data), 2); + if (peer_level != qeth_peer_func_level(card->info.func_level)) { + QETH_DBF_MESSAGE(2, "IDX_ACTIVATE on channel %x: function level mismatch (sent: %#x, received: %#x)\n", + CCW_DEVID(channel->ccwdev), + card->info.func_level, peer_level); + rc = -EINVAL; + goto out; + } + + memcpy(&card->token.issuer_rm_r, + QETH_IDX_ACT_ISSUER_RM_TOKEN(iob->data), + QETH_MPC_TOKEN_LENGTH); + memcpy(&card->info.mcl_level[0], + QETH_IDX_REPLY_LEVEL(iob->data), QETH_MCL_LENGTH); + +out: + qeth_notify_reply(iob->reply, rc); + qeth_put_cmd(iob); +} + +static void qeth_idx_activate_write_channel_cb(struct qeth_card *card, + struct qeth_cmd_buffer *iob) +{ + struct qeth_channel *channel = iob->channel; + u16 peer_level; + int rc; + + QETH_CARD_TEXT(card, 2, "idxwrcb"); + + rc = qeth_idx_check_activate_response(card, channel, iob); + if (rc) + goto out; + + memcpy(&peer_level, QETH_IDX_ACT_FUNC_LEVEL(iob->data), 2); + if ((peer_level & ~0x0100) != + qeth_peer_func_level(card->info.func_level)) { + QETH_DBF_MESSAGE(2, "IDX_ACTIVATE on channel %x: function level mismatch (sent: %#x, received: %#x)\n", + CCW_DEVID(channel->ccwdev), + card->info.func_level, peer_level); + rc = -EINVAL; + } + +out: + qeth_notify_reply(iob->reply, rc); + qeth_put_cmd(iob); +} + +static void qeth_idx_setup_activate_cmd(struct qeth_card *card, + struct qeth_cmd_buffer *iob) +{ + u16 addr = (card->info.cula << 8) + card->info.unit_addr2; + u8 port = ((u8)card->dev->dev_port) | 0x80; + struct ccw1 *ccw = __ccw_from_cmd(iob); + struct ccw_dev_id dev_id; + + qeth_setup_ccw(&ccw[0], CCW_CMD_WRITE, CCW_FLAG_CC, IDX_ACTIVATE_SIZE, + iob->data); + qeth_setup_ccw(&ccw[1], CCW_CMD_READ, 0, iob->length, iob->data); + ccw_device_get_id(CARD_DDEV(card), &dev_id); + iob->finalize = qeth_idx_finalize_cmd; + + memcpy(QETH_IDX_ACT_PNO(iob->data), &port, 1); + memcpy(QETH_IDX_ACT_ISSUER_RM_TOKEN(iob->data), + &card->token.issuer_rm_w, QETH_MPC_TOKEN_LENGTH); + memcpy(QETH_IDX_ACT_FUNC_LEVEL(iob->data), + &card->info.func_level, 2); + memcpy(QETH_IDX_ACT_QDIO_DEV_CUA(iob->data), &dev_id.devno, 2); + memcpy(QETH_IDX_ACT_QDIO_DEV_REALADDR(iob->data), &addr, 2); +} + +static int qeth_idx_activate_read_channel(struct qeth_card *card) +{ + struct qeth_channel *channel = &card->read; + struct qeth_cmd_buffer *iob; + int rc; + + QETH_CARD_TEXT(card, 2, "idxread"); + + iob = qeth_alloc_cmd(channel, QETH_BUFSIZE, 2, QETH_TIMEOUT); + if (!iob) + return -ENOMEM; + + memcpy(iob->data, IDX_ACTIVATE_READ, IDX_ACTIVATE_SIZE); + qeth_idx_setup_activate_cmd(card, iob); + iob->callback = qeth_idx_activate_read_channel_cb; + + rc = qeth_send_control_data(card, iob, NULL, NULL); + if (rc) + return rc; + + channel->state = CH_STATE_UP; + return 0; +} + +static int qeth_idx_activate_write_channel(struct qeth_card *card) +{ + struct qeth_channel *channel = &card->write; + struct qeth_cmd_buffer *iob; + int rc; + + QETH_CARD_TEXT(card, 2, "idxwrite"); + + iob = qeth_alloc_cmd(channel, QETH_BUFSIZE, 2, QETH_TIMEOUT); + if (!iob) + return -ENOMEM; + + memcpy(iob->data, IDX_ACTIVATE_WRITE, IDX_ACTIVATE_SIZE); + qeth_idx_setup_activate_cmd(card, iob); + iob->callback = qeth_idx_activate_write_channel_cb; + + rc = qeth_send_control_data(card, iob, NULL, NULL); + if (rc) + return rc; + + channel->state = CH_STATE_UP; + return 0; } static int qeth_cm_enable_cb(struct qeth_card *card, struct qeth_reply *reply, @@ -2123,7 +1965,7 @@ static int qeth_cm_enable_cb(struct qeth_card *card, struct qeth_reply *reply, { struct qeth_cmd_buffer *iob; - QETH_DBF_TEXT(SETUP, 2, "cmenblcb"); + QETH_CARD_TEXT(card, 2, "cmenblcb"); iob = (struct qeth_cmd_buffer *) data; memcpy(&card->token.cm_filter_r, @@ -2134,21 +1976,20 @@ static int qeth_cm_enable_cb(struct qeth_card *card, struct qeth_reply *reply, static int qeth_cm_enable(struct qeth_card *card) { - int rc; struct qeth_cmd_buffer *iob; - QETH_DBF_TEXT(SETUP, 2, "cmenable"); + QETH_CARD_TEXT(card, 2, "cmenable"); + + iob = qeth_mpc_alloc_cmd(card, CM_ENABLE, CM_ENABLE_SIZE); + if (!iob) + return -ENOMEM; - iob = qeth_wait_for_buffer(&card->write); - memcpy(iob->data, CM_ENABLE, CM_ENABLE_SIZE); memcpy(QETH_CM_ENABLE_ISSUER_RM_TOKEN(iob->data), &card->token.issuer_rm_r, QETH_MPC_TOKEN_LENGTH); memcpy(QETH_CM_ENABLE_FILTER_TOKEN(iob->data), &card->token.cm_filter_w, QETH_MPC_TOKEN_LENGTH); - rc = qeth_send_control_data(card, CM_ENABLE_SIZE, iob, - qeth_cm_enable_cb, NULL); - return rc; + return qeth_send_control_data(card, iob, qeth_cm_enable_cb, NULL); } static int qeth_cm_setup_cb(struct qeth_card *card, struct qeth_reply *reply, @@ -2156,7 +1997,7 @@ static int qeth_cm_setup_cb(struct qeth_card *card, struct qeth_reply *reply, { struct qeth_cmd_buffer *iob; - QETH_DBF_TEXT(SETUP, 2, "cmsetpcb"); + QETH_CARD_TEXT(card, 2, "cmsetpcb"); iob = (struct qeth_cmd_buffer *) data; memcpy(&card->token.cm_connection_r, @@ -2167,22 +2008,21 @@ static int qeth_cm_setup_cb(struct qeth_card *card, struct qeth_reply *reply, static int qeth_cm_setup(struct qeth_card *card) { - int rc; struct qeth_cmd_buffer *iob; - QETH_DBF_TEXT(SETUP, 2, "cmsetup"); + QETH_CARD_TEXT(card, 2, "cmsetup"); + + iob = qeth_mpc_alloc_cmd(card, CM_SETUP, CM_SETUP_SIZE); + if (!iob) + return -ENOMEM; - iob = qeth_wait_for_buffer(&card->write); - memcpy(iob->data, CM_SETUP, CM_SETUP_SIZE); memcpy(QETH_CM_SETUP_DEST_ADDR(iob->data), &card->token.issuer_rm_r, QETH_MPC_TOKEN_LENGTH); memcpy(QETH_CM_SETUP_CONNECTION_TOKEN(iob->data), &card->token.cm_connection_w, QETH_MPC_TOKEN_LENGTH); memcpy(QETH_CM_SETUP_FILTER_TOKEN(iob->data), &card->token.cm_filter_r, QETH_MPC_TOKEN_LENGTH); - rc = qeth_send_control_data(card, CM_SETUP_SIZE, iob, - qeth_cm_setup_cb, NULL); - return rc; + return qeth_send_control_data(card, iob, qeth_cm_setup_cb, NULL); } static int qeth_update_max_mtu(struct qeth_card *card, unsigned int max_mtu) @@ -2206,7 +2046,7 @@ static int qeth_update_max_mtu(struct qeth_card *card, unsigned int max_mtu) /* adjust RX buffer size to new max MTU: */ card->qdio.in_buf_size = max_mtu + 2 * PAGE_SIZE; if (dev->max_mtu && dev->max_mtu != max_mtu) - qeth_free_qdio_buffers(card); + qeth_free_qdio_queues(card); } else { if (dev->mtu) new_mtu = dev->mtu; @@ -2247,13 +2087,13 @@ static int qeth_ulp_enable_cb(struct qeth_card *card, struct qeth_reply *reply, __u8 link_type; struct qeth_cmd_buffer *iob; - QETH_DBF_TEXT(SETUP, 2, "ulpenacb"); + QETH_CARD_TEXT(card, 2, "ulpenacb"); iob = (struct qeth_cmd_buffer *) data; memcpy(&card->token.ulp_filter_r, QETH_ULP_ENABLE_RESP_FILTER_TOKEN(iob->data), QETH_MPC_TOKEN_LENGTH); - if (card->info.type == QETH_CARD_TYPE_IQD) { + if (IS_IQD(card)) { memcpy(&framesize, QETH_ULP_ENABLE_RESP_MAX_MTU(iob->data), 2); mtu = qeth_get_mtu_outof_framesize(framesize); } else { @@ -2268,7 +2108,7 @@ static int qeth_ulp_enable_cb(struct qeth_card *card, struct qeth_reply *reply, card->info.link_type = link_type; } else card->info.link_type = 0; - QETH_DBF_TEXT_(SETUP, 2, "link%d", card->info.link_type); + QETH_CARD_TEXT_(card, 2, "link%d", card->info.link_type); return 0; } @@ -2286,11 +2126,11 @@ static int qeth_ulp_enable(struct qeth_card *card) u16 max_mtu; int rc; - /*FIXME: trace view callbacks*/ - QETH_DBF_TEXT(SETUP, 2, "ulpenabl"); + QETH_CARD_TEXT(card, 2, "ulpenabl"); - iob = qeth_wait_for_buffer(&card->write); - memcpy(iob->data, ULP_ENABLE, ULP_ENABLE_SIZE); + iob = qeth_mpc_alloc_cmd(card, ULP_ENABLE, ULP_ENABLE_SIZE); + if (!iob) + return -ENOMEM; *(QETH_ULP_ENABLE_LINKNUM(iob->data)) = (u8) card->dev->dev_port; memcpy(QETH_ULP_ENABLE_PROT_TYPE(iob->data), &prot_type, 1); @@ -2298,8 +2138,7 @@ static int qeth_ulp_enable(struct qeth_card *card) &card->token.cm_connection_r, QETH_MPC_TOKEN_LENGTH); memcpy(QETH_ULP_ENABLE_FILTER_TOKEN(iob->data), &card->token.ulp_filter_w, QETH_MPC_TOKEN_LENGTH); - rc = qeth_send_control_data(card, ULP_ENABLE_SIZE, iob, - qeth_ulp_enable_cb, &max_mtu); + rc = qeth_send_control_data(card, iob, qeth_ulp_enable_cb, &max_mtu); if (rc) return rc; return qeth_update_max_mtu(card, max_mtu); @@ -2310,7 +2149,7 @@ static int qeth_ulp_setup_cb(struct qeth_card *card, struct qeth_reply *reply, { struct qeth_cmd_buffer *iob; - QETH_DBF_TEXT(SETUP, 2, "ulpstpcb"); + QETH_CARD_TEXT(card, 2, "ulpstpcb"); iob = (struct qeth_cmd_buffer *) data; memcpy(&card->token.ulp_connection_r, @@ -2318,7 +2157,7 @@ static int qeth_ulp_setup_cb(struct qeth_card *card, struct qeth_reply *reply, QETH_MPC_TOKEN_LENGTH); if (!strncmp("00S", QETH_ULP_SETUP_RESP_CONNECTION_TOKEN(iob->data), 3)) { - QETH_DBF_TEXT(SETUP, 2, "olmlimit"); + QETH_CARD_TEXT(card, 2, "olmlimit"); dev_err(&card->gdev->dev, "A connection could not be " "established because of an OLM limit\n"); return -EMLINK; @@ -2328,15 +2167,15 @@ static int qeth_ulp_setup_cb(struct qeth_card *card, struct qeth_reply *reply, static int qeth_ulp_setup(struct qeth_card *card) { - int rc; __u16 temp; struct qeth_cmd_buffer *iob; struct ccw_dev_id dev_id; - QETH_DBF_TEXT(SETUP, 2, "ulpsetup"); + QETH_CARD_TEXT(card, 2, "ulpsetup"); - iob = qeth_wait_for_buffer(&card->write); - memcpy(iob->data, ULP_SETUP, ULP_SETUP_SIZE); + iob = qeth_mpc_alloc_cmd(card, ULP_SETUP, ULP_SETUP_SIZE); + if (!iob) + return -ENOMEM; memcpy(QETH_ULP_SETUP_DEST_ADDR(iob->data), &card->token.cm_connection_r, QETH_MPC_TOKEN_LENGTH); @@ -2349,9 +2188,7 @@ static int qeth_ulp_setup(struct qeth_card *card) memcpy(QETH_ULP_SETUP_CUA(iob->data), &dev_id.devno, 2); temp = (card->info.cula << 8) + card->info.unit_addr2; memcpy(QETH_ULP_SETUP_REAL_DEVADDR(iob->data), &temp, 2); - rc = qeth_send_control_data(card, ULP_SETUP_SIZE, iob, - qeth_ulp_setup_cb, NULL); - return rc; + return qeth_send_control_data(card, iob, qeth_ulp_setup_cb, NULL); } static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *q, int bidx) @@ -2377,12 +2214,12 @@ static void qeth_free_output_queue(struct qeth_qdio_out_q *q) if (!q) return; - qeth_clear_outq_buffers(q, 1); + qeth_drain_output_queue(q, true); qdio_free_buffers(q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q); kfree(q); } -static struct qeth_qdio_out_q *qeth_alloc_qdio_out_buf(void) +static struct qeth_qdio_out_q *qeth_alloc_output_queue(void) { struct qeth_qdio_out_q *q = kzalloc(sizeof(*q), GFP_KERNEL); @@ -2396,17 +2233,17 @@ static struct qeth_qdio_out_q *qeth_alloc_qdio_out_buf(void) return q; } -static int qeth_alloc_qdio_buffers(struct qeth_card *card) +static int qeth_alloc_qdio_queues(struct qeth_card *card) { int i, j; - QETH_DBF_TEXT(SETUP, 2, "allcqdbf"); + QETH_CARD_TEXT(card, 2, "allcqdbf"); if (atomic_cmpxchg(&card->qdio.state, QETH_QDIO_UNINITIALIZED, QETH_QDIO_ALLOCATED) != QETH_QDIO_UNINITIALIZED) return 0; - QETH_DBF_TEXT(SETUP, 2, "inq"); + QETH_CARD_TEXT(card, 2, "inq"); card->qdio.in_q = qeth_alloc_qdio_queue(); if (!card->qdio.in_q) goto out_nomem; @@ -2417,11 +2254,12 @@ static int qeth_alloc_qdio_buffers(struct qeth_card *card) /* outbound */ for (i = 0; i < card->qdio.no_out_queues; ++i) { - card->qdio.out_qs[i] = qeth_alloc_qdio_out_buf(); + card->qdio.out_qs[i] = qeth_alloc_output_queue(); if (!card->qdio.out_qs[i]) goto out_freeoutq; - QETH_DBF_TEXT_(SETUP, 2, "outq %i", i); - QETH_DBF_HEX(SETUP, 2, &card->qdio.out_qs[i], sizeof(void *)); + QETH_CARD_TEXT_(card, 2, "outq %i", i); + QETH_CARD_HEX(card, 2, &card->qdio.out_qs[i], sizeof(void *)); + card->qdio.out_qs[i]->card = card; card->qdio.out_qs[i]->queue_no = i; /* give outbound qeth_qdio_buffers their qdio_buffers */ for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j) { @@ -2458,7 +2296,7 @@ out_nomem: return -ENOMEM; } -static void qeth_free_qdio_buffers(struct qeth_card *card) +static void qeth_free_qdio_queues(struct qeth_card *card) { int i, j; @@ -2511,84 +2349,83 @@ static void qeth_create_qib_param_field_blkt(struct qeth_card *card, static int qeth_qdio_activate(struct qeth_card *card) { - QETH_DBF_TEXT(SETUP, 3, "qdioact"); + QETH_CARD_TEXT(card, 3, "qdioact"); return qdio_activate(CARD_DDEV(card)); } static int qeth_dm_act(struct qeth_card *card) { - int rc; struct qeth_cmd_buffer *iob; - QETH_DBF_TEXT(SETUP, 2, "dmact"); + QETH_CARD_TEXT(card, 2, "dmact"); - iob = qeth_wait_for_buffer(&card->write); - memcpy(iob->data, DM_ACT, DM_ACT_SIZE); + iob = qeth_mpc_alloc_cmd(card, DM_ACT, DM_ACT_SIZE); + if (!iob) + return -ENOMEM; memcpy(QETH_DM_ACT_DEST_ADDR(iob->data), &card->token.cm_connection_r, QETH_MPC_TOKEN_LENGTH); memcpy(QETH_DM_ACT_CONNECTION_TOKEN(iob->data), &card->token.ulp_connection_r, QETH_MPC_TOKEN_LENGTH); - rc = qeth_send_control_data(card, DM_ACT_SIZE, iob, NULL, NULL); - return rc; + return qeth_send_control_data(card, iob, NULL, NULL); } static int qeth_mpc_initialize(struct qeth_card *card) { int rc; - QETH_DBF_TEXT(SETUP, 2, "mpcinit"); + QETH_CARD_TEXT(card, 2, "mpcinit"); rc = qeth_issue_next_read(card); if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc); + QETH_CARD_TEXT_(card, 2, "1err%d", rc); return rc; } rc = qeth_cm_enable(card); if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "2err%d", rc); + QETH_CARD_TEXT_(card, 2, "2err%d", rc); goto out_qdio; } rc = qeth_cm_setup(card); if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "3err%d", rc); + QETH_CARD_TEXT_(card, 2, "3err%d", rc); goto out_qdio; } rc = qeth_ulp_enable(card); if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "4err%d", rc); + QETH_CARD_TEXT_(card, 2, "4err%d", rc); goto out_qdio; } rc = qeth_ulp_setup(card); if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "5err%d", rc); + QETH_CARD_TEXT_(card, 2, "5err%d", rc); goto out_qdio; } - rc = qeth_alloc_qdio_buffers(card); + rc = qeth_alloc_qdio_queues(card); if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "5err%d", rc); + QETH_CARD_TEXT_(card, 2, "5err%d", rc); goto out_qdio; } rc = qeth_qdio_establish(card); if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "6err%d", rc); - qeth_free_qdio_buffers(card); + QETH_CARD_TEXT_(card, 2, "6err%d", rc); + qeth_free_qdio_queues(card); goto out_qdio; } rc = qeth_qdio_activate(card); if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "7err%d", rc); + QETH_CARD_TEXT_(card, 2, "7err%d", rc); goto out_qdio; } rc = qeth_dm_act(card); if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "8err%d", rc); + QETH_CARD_TEXT_(card, 2, "8err%d", rc); goto out_qdio; } return 0; out_qdio: - qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD); + qeth_qdio_clear_card(card, !IS_IQD(card)); qdio_free(CARD_DDEV(card)); return rc; } @@ -2611,8 +2448,7 @@ void qeth_print_status_message(struct qeth_card *card) } /* fallthrough */ case QETH_CARD_TYPE_IQD: - if ((card->info.guestlan) || - (card->info.mcl_level[0] & 0x80)) { + if (IS_VM_NIC(card) || (card->info.mcl_level[0] & 0x80)) { card->info.mcl_level[0] = (char) _ebcasc[(__u8) card->info.mcl_level[0]]; card->info.mcl_level[1] = (char) _ebcasc[(__u8) @@ -2733,10 +2569,10 @@ static int qeth_init_input_buffer(struct qeth_card *card, int qeth_init_qdio_queues(struct qeth_card *card) { - int i, j; + unsigned int i; int rc; - QETH_DBF_TEXT(SETUP, 2, "initqdqs"); + QETH_CARD_TEXT(card, 2, "initqdqs"); /* inbound queue */ qdio_reset_buffers(card->qdio.in_q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q); @@ -2750,7 +2586,7 @@ int qeth_init_qdio_queues(struct qeth_card *card) rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_INPUT, 0, 0, card->qdio.in_buf_pool.buf_count - 1); if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc); + QETH_CARD_TEXT_(card, 2, "1err%d", rc); return rc; } @@ -2762,54 +2598,39 @@ int qeth_init_qdio_queues(struct qeth_card *card) /* outbound queue */ for (i = 0; i < card->qdio.no_out_queues; ++i) { - qdio_reset_buffers(card->qdio.out_qs[i]->qdio_bufs, - QDIO_MAX_BUFFERS_PER_Q); - for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j) { - qeth_clear_output_buffer(card->qdio.out_qs[i], - card->qdio.out_qs[i]->bufs[j]); - } - card->qdio.out_qs[i]->card = card; - card->qdio.out_qs[i]->next_buf_to_fill = 0; - card->qdio.out_qs[i]->do_pack = 0; - atomic_set(&card->qdio.out_qs[i]->used_buffers, 0); - atomic_set(&card->qdio.out_qs[i]->set_pci_flags_count, 0); - atomic_set(&card->qdio.out_qs[i]->state, - QETH_OUT_Q_UNLOCKED); + struct qeth_qdio_out_q *queue = card->qdio.out_qs[i]; + + qdio_reset_buffers(queue->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q); + queue->max_elements = QETH_MAX_BUFFER_ELEMENTS(card); + queue->next_buf_to_fill = 0; + queue->do_pack = 0; + atomic_set(&queue->used_buffers, 0); + atomic_set(&queue->set_pci_flags_count, 0); + atomic_set(&queue->state, QETH_OUT_Q_UNLOCKED); } return 0; } EXPORT_SYMBOL_GPL(qeth_init_qdio_queues); -static __u8 qeth_get_ipa_adp_type(enum qeth_link_types link_type) +static void qeth_ipa_finalize_cmd(struct qeth_card *card, + struct qeth_cmd_buffer *iob) { - switch (link_type) { - case QETH_LINK_TYPE_HSTR: - return 2; - default: - return 1; - } -} + qeth_mpc_finalize_cmd(card, iob); -static void qeth_fill_ipacmd_header(struct qeth_card *card, - struct qeth_ipa_cmd *cmd, - enum qeth_ipa_cmds command, - enum qeth_prot_versions prot) -{ - cmd->hdr.command = command; - cmd->hdr.initiator = IPA_CMD_INITIATOR_HOST; - /* cmd->hdr.seqno is set by qeth_send_control_data() */ - cmd->hdr.adapter_type = qeth_get_ipa_adp_type(card->info.link_type); - cmd->hdr.rel_adapter_no = (u8) card->dev->dev_port; - cmd->hdr.prim_version_no = IS_LAYER2(card) ? 2 : 1; - cmd->hdr.param_count = 1; - cmd->hdr.prot_version = prot; + /* override with IPA-specific values: */ + __ipa_cmd(iob)->hdr.seqno = card->seqno.ipa; + iob->reply->seqno = card->seqno.ipa++; } void qeth_prepare_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob, u16 cmd_length) { - u16 total_length = IPA_PDU_HEADER_SIZE + cmd_length; u8 prot_type = qeth_mpc_select_prot_type(card); + u16 total_length = iob->length; + + qeth_setup_ccw(__ccw_from_cmd(iob), CCW_CMD_WRITE, 0, total_length, + iob->data); + iob->finalize = qeth_ipa_finalize_cmd; memcpy(iob->data, IPA_PDU_HEADER, IPA_PDU_HEADER_SIZE); memcpy(QETH_IPA_PDU_LEN_TOTAL(iob->data), &total_length, 2); @@ -2822,25 +2643,35 @@ void qeth_prepare_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob, } EXPORT_SYMBOL_GPL(qeth_prepare_ipa_cmd); -struct qeth_cmd_buffer *qeth_get_ipacmd_buffer(struct qeth_card *card, - enum qeth_ipa_cmds ipacmd, enum qeth_prot_versions prot) +struct qeth_cmd_buffer *qeth_ipa_alloc_cmd(struct qeth_card *card, + enum qeth_ipa_cmds cmd_code, + enum qeth_prot_versions prot, + unsigned int data_length) { + enum qeth_link_types link_type = card->info.link_type; struct qeth_cmd_buffer *iob; + struct qeth_ipacmd_hdr *hdr; - iob = qeth_get_buffer(&card->write); - if (iob) { - qeth_prepare_ipa_cmd(card, iob, sizeof(struct qeth_ipa_cmd)); - qeth_fill_ipacmd_header(card, __ipa_cmd(iob), ipacmd, prot); - } else { - dev_warn(&card->gdev->dev, - "The qeth driver ran out of channel command buffers\n"); - QETH_DBF_MESSAGE(1, "device %x ran out of channel command buffers", - CARD_DEVID(card)); - } + data_length += offsetof(struct qeth_ipa_cmd, data); + iob = qeth_alloc_cmd(&card->write, IPA_PDU_HEADER_SIZE + data_length, 1, + QETH_IPA_TIMEOUT); + if (!iob) + return NULL; + qeth_prepare_ipa_cmd(card, iob, data_length); + + hdr = &__ipa_cmd(iob)->hdr; + hdr->command = cmd_code; + hdr->initiator = IPA_CMD_INITIATOR_HOST; + /* hdr->seqno is set by qeth_send_control_data() */ + hdr->adapter_type = (link_type == QETH_LINK_TYPE_HSTR) ? 2 : 1; + hdr->rel_adapter_no = (u8) card->dev->dev_port; + hdr->prim_version_no = IS_LAYER2(card) ? 2 : 1; + hdr->param_count = 1; + hdr->prot_version = prot; return iob; } -EXPORT_SYMBOL_GPL(qeth_get_ipacmd_buffer); +EXPORT_SYMBOL_GPL(qeth_ipa_alloc_cmd); static int qeth_send_ipa_cmd_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) @@ -2861,15 +2692,18 @@ int qeth_send_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob, unsigned long), void *reply_param) { - u16 length; int rc; QETH_CARD_TEXT(card, 4, "sendipa"); + if (card->read_or_write_problem) { + qeth_put_cmd(iob); + return -EIO; + } + if (reply_cb == NULL) reply_cb = qeth_send_ipa_cmd_cb; - memcpy(&length, QETH_IPA_PDU_LEN_TOTAL(iob->data), 2); - rc = qeth_send_control_data(card, length, iob, reply_cb, reply_param); + rc = qeth_send_control_data(card, iob, reply_cb, reply_param); if (rc == -ETIME) { qeth_clear_ipacmd_list(card); qeth_schedule_recovery(card); @@ -2893,9 +2727,9 @@ static int qeth_send_startlan(struct qeth_card *card) { struct qeth_cmd_buffer *iob; - QETH_DBF_TEXT(SETUP, 2, "strtlan"); + QETH_CARD_TEXT(card, 2, "strtlan"); - iob = qeth_get_ipacmd_buffer(card, IPA_CMD_STARTLAN, 0); + iob = qeth_ipa_alloc_cmd(card, IPA_CMD_STARTLAN, QETH_PROT_NONE, 0); if (!iob) return -ENOMEM; return qeth_send_ipa_cmd(card, iob, qeth_send_startlan_cb, NULL); @@ -2921,7 +2755,7 @@ static int qeth_query_setadapterparms_cb(struct qeth_card *card, if (cmd->data.setadapterparms.data.query_cmds_supp.lan_type & 0x7f) { card->info.link_type = cmd->data.setadapterparms.data.query_cmds_supp.lan_type; - QETH_DBF_TEXT_(SETUP, 2, "lnk %d", card->info.link_type); + QETH_CARD_TEXT_(card, 2, "lnk %d", card->info.link_type); } card->options.adp.supported_funcs = cmd->data.setadapterparms.data.query_cmds_supp.supported_cmds; @@ -2929,21 +2763,24 @@ static int qeth_query_setadapterparms_cb(struct qeth_card *card, } static struct qeth_cmd_buffer *qeth_get_adapter_cmd(struct qeth_card *card, - __u32 command, __u32 cmdlen) + enum qeth_ipa_setadp_cmd adp_cmd, + unsigned int data_length) { + struct qeth_ipacmd_setadpparms_hdr *hdr; struct qeth_cmd_buffer *iob; - struct qeth_ipa_cmd *cmd; - iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SETADAPTERPARMS, - QETH_PROT_IPV4); - if (iob) { - cmd = __ipa_cmd(iob); - cmd->data.setadapterparms.hdr.cmdlength = cmdlen; - cmd->data.setadapterparms.hdr.command_code = command; - cmd->data.setadapterparms.hdr.used_total = 1; - cmd->data.setadapterparms.hdr.seq_no = 1; - } + iob = qeth_ipa_alloc_cmd(card, IPA_CMD_SETADAPTERPARMS, QETH_PROT_IPV4, + data_length + + offsetof(struct qeth_ipacmd_setadpparms, + data)); + if (!iob) + return NULL; + hdr = &__ipa_cmd(iob)->data.setadapterparms.hdr; + hdr->cmdlength = sizeof(*hdr) + data_length; + hdr->command_code = adp_cmd; + hdr->used_total = 1; + hdr->seq_no = 1; return iob; } @@ -2954,7 +2791,7 @@ static int qeth_query_setadapterparms(struct qeth_card *card) QETH_CARD_TEXT(card, 3, "queryadp"); iob = qeth_get_adapter_cmd(card, IPA_SETADP_QUERY_COMMANDS_SUPPORTED, - sizeof(struct qeth_ipacmd_setadpparms)); + SETADP_DATA_SIZEOF(query_cmds_supp)); if (!iob) return -ENOMEM; rc = qeth_send_ipa_cmd(card, iob, qeth_query_setadapterparms_cb, NULL); @@ -2966,7 +2803,7 @@ static int qeth_query_ipassists_cb(struct qeth_card *card, { struct qeth_ipa_cmd *cmd; - QETH_DBF_TEXT(SETUP, 2, "qipasscb"); + QETH_CARD_TEXT(card, 2, "qipasscb"); cmd = (struct qeth_ipa_cmd *) data; @@ -2975,7 +2812,7 @@ static int qeth_query_ipassists_cb(struct qeth_card *card, break; case IPA_RC_NOTSUPP: case IPA_RC_L2_UNSUPPORTED_CMD: - QETH_DBF_TEXT(SETUP, 2, "ipaunsup"); + QETH_CARD_TEXT(card, 2, "ipaunsup"); card->options.ipa4.supported_funcs |= IPA_SETADAPTERPARMS; card->options.ipa6.supported_funcs |= IPA_SETADAPTERPARMS; return -EOPNOTSUPP; @@ -3003,8 +2840,8 @@ static int qeth_query_ipassists(struct qeth_card *card, int rc; struct qeth_cmd_buffer *iob; - QETH_DBF_TEXT_(SETUP, 2, "qipassi%i", prot); - iob = qeth_get_ipacmd_buffer(card, IPA_CMD_QIPASSIST, prot); + QETH_CARD_TEXT_(card, 2, "qipassi%i", prot); + iob = qeth_ipa_alloc_cmd(card, IPA_CMD_QIPASSIST, prot, 0); if (!iob) return -ENOMEM; rc = qeth_send_ipa_cmd(card, iob, qeth_query_ipassists_cb, NULL); @@ -3041,14 +2878,32 @@ int qeth_query_switch_attributes(struct qeth_card *card, return -EOPNOTSUPP; if (!netif_carrier_ok(card->dev)) return -ENOMEDIUM; - iob = qeth_get_adapter_cmd(card, IPA_SETADP_QUERY_SWITCH_ATTRIBUTES, - sizeof(struct qeth_ipacmd_setadpparms_hdr)); + iob = qeth_get_adapter_cmd(card, IPA_SETADP_QUERY_SWITCH_ATTRIBUTES, 0); if (!iob) return -ENOMEM; return qeth_send_ipa_cmd(card, iob, qeth_query_switch_attributes_cb, sw_info); } +struct qeth_cmd_buffer *qeth_get_diag_cmd(struct qeth_card *card, + enum qeth_diags_cmds sub_cmd, + unsigned int data_length) +{ + struct qeth_ipacmd_diagass *cmd; + struct qeth_cmd_buffer *iob; + + iob = qeth_ipa_alloc_cmd(card, IPA_CMD_SET_DIAG_ASS, QETH_PROT_NONE, + DIAG_HDR_LEN + data_length); + if (!iob) + return NULL; + + cmd = &__ipa_cmd(iob)->data.diagass; + cmd->subcmd_len = DIAG_SUB_HDR_LEN + data_length; + cmd->subcmd = sub_cmd; + return iob; +} +EXPORT_SYMBOL_GPL(qeth_get_diag_cmd); + static int qeth_query_setdiagass_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { @@ -3067,15 +2922,11 @@ static int qeth_query_setdiagass_cb(struct qeth_card *card, static int qeth_query_setdiagass(struct qeth_card *card) { struct qeth_cmd_buffer *iob; - struct qeth_ipa_cmd *cmd; - QETH_DBF_TEXT(SETUP, 2, "qdiagass"); - iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SET_DIAG_ASS, 0); + QETH_CARD_TEXT(card, 2, "qdiagass"); + iob = qeth_get_diag_cmd(card, QETH_DIAGS_CMD_QUERY, 0); if (!iob) return -ENOMEM; - cmd = __ipa_cmd(iob); - cmd->data.diagass.subcmd_len = 16; - cmd->data.diagass.subcmd = QETH_DIAGS_CMD_QUERY; return qeth_send_ipa_cmd(card, iob, qeth_query_setdiagass_cb, NULL); } @@ -3122,13 +2973,11 @@ int qeth_hw_trap(struct qeth_card *card, enum qeth_diags_trap_action action) struct qeth_cmd_buffer *iob; struct qeth_ipa_cmd *cmd; - QETH_DBF_TEXT(SETUP, 2, "diagtrap"); - iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SET_DIAG_ASS, 0); + QETH_CARD_TEXT(card, 2, "diagtrap"); + iob = qeth_get_diag_cmd(card, QETH_DIAGS_CMD_TRAP, 64); if (!iob) return -ENOMEM; cmd = __ipa_cmd(iob); - cmd->data.diagass.subcmd_len = 80; - cmd->data.diagass.subcmd = QETH_DIAGS_CMD_TRAP; cmd->data.diagass.type = 1; cmd->data.diagass.action = action; switch (action) { @@ -3251,13 +3100,6 @@ static void qeth_handle_send_error(struct qeth_card *card, int sbalf15 = buffer->buffer->element[15].sflags; QETH_CARD_TEXT(card, 6, "hdsnderr"); - if (card->info.type == QETH_CARD_TYPE_IQD) { - if (sbalf15 == 0) { - qdio_err = 0; - } else { - qdio_err = 1; - } - } qeth_check_qdio_errors(card, buffer->buffer, qdio_err, "qouterr"); if (!qdio_err) @@ -3348,7 +3190,7 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index, if (queue->bufstates) queue->bufstates[bidx].user = buf; - if (queue->card->info.type == QETH_CARD_TYPE_IQD) + if (IS_IQD(queue->card)) continue; if (!queue->do_pack) { @@ -3378,11 +3220,9 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index, } QETH_TXQ_STAT_ADD(queue, bufs, count); - netif_trans_update(queue->card->dev); qdio_flags = QDIO_FLAG_SYNC_OUTPUT; if (atomic_read(&queue->set_pci_flags_count)) qdio_flags |= QDIO_FLAG_PCI_OUT; - atomic_add(count, &queue->used_buffers); rc = do_QDIO(CARD_DDEV(queue->card), qdio_flags, queue->queue_no, index, count); if (rc) { @@ -3422,7 +3262,6 @@ static void qeth_check_outbound_queue(struct qeth_qdio_out_q *queue) * do_send_packet. So, we check if there is a * packing buffer to be flushed here. */ - netif_stop_queue(queue->card->dev); index = queue->next_buf_to_fill; q_was_packing = queue->do_pack; /* queue->do_pack may change */ @@ -3467,7 +3306,7 @@ int qeth_configure_cq(struct qeth_card *card, enum qeth_cq cq) goto out; } - qeth_free_qdio_buffers(card); + qeth_free_qdio_queues(card); card->options.cq = cq; rc = 0; } @@ -3493,7 +3332,7 @@ static void qeth_qdio_cq_handler(struct qeth_card *card, unsigned int qdio_err, QETH_CARD_TEXT_(card, 5, "qcqherr%d", qdio_err); if (qdio_err) { - netif_stop_queue(card->dev); + netif_tx_stop_all_queues(card->dev); qeth_schedule_recovery(card); return; } @@ -3549,12 +3388,14 @@ static void qeth_qdio_output_handler(struct ccw_device *ccwdev, struct qeth_card *card = (struct qeth_card *) card_ptr; struct qeth_qdio_out_q *queue = card->qdio.out_qs[__queue]; struct qeth_qdio_out_buffer *buffer; + struct net_device *dev = card->dev; + struct netdev_queue *txq; int i; QETH_CARD_TEXT(card, 6, "qdouhdl"); if (qdio_error & QDIO_ERROR_FATAL) { QETH_CARD_TEXT(card, 2, "achkcond"); - netif_stop_queue(card->dev); + netif_tx_stop_all_queues(dev); qeth_schedule_recovery(card); return; } @@ -3580,7 +3421,7 @@ static void qeth_qdio_output_handler(struct ccw_device *ccwdev, /* prepare the queue slot for re-use: */ qeth_scrub_qdio_buffer(buffer->buffer, - QETH_MAX_BUFFER_ELEMENTS(card)); + queue->max_elements); if (qeth_init_qdio_out_buf(queue, bidx)) { QETH_CARD_TEXT(card, 2, "outofbuf"); qeth_schedule_recovery(card); @@ -3600,33 +3441,32 @@ static void qeth_qdio_output_handler(struct ccw_device *ccwdev, } atomic_sub(count, &queue->used_buffers); /* check if we need to do something on this outbound queue */ - if (card->info.type != QETH_CARD_TYPE_IQD) + if (!IS_IQD(card)) qeth_check_outbound_queue(queue); - netif_wake_queue(queue->card->dev); -} - -/* We cannot use outbound queue 3 for unicast packets on HiperSockets */ -static inline int qeth_cut_iqd_prio(struct qeth_card *card, int queue_num) -{ - if ((card->info.type == QETH_CARD_TYPE_IQD) && (queue_num == 3)) - return 2; - return queue_num; + if (IS_IQD(card)) + __queue = qeth_iqd_translate_txq(dev, __queue); + txq = netdev_get_tx_queue(dev, __queue); + /* xmit may have observed the full-condition, but not yet stopped the + * txq. In which case the code below won't trigger. So before returning, + * xmit will re-check the txq's fill level and wake it up if needed. + */ + if (netif_tx_queue_stopped(txq) && !qeth_out_queue_is_full(queue)) + netif_tx_wake_queue(txq); } /** * Note: Function assumes that we have 4 outbound queues. */ -int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb, - int ipv) +int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb) { - __be16 *tci; + struct vlan_ethhdr *veth = vlan_eth_hdr(skb); u8 tos; switch (card->qdio.do_prio_queueing) { case QETH_PRIO_Q_ING_TOS: case QETH_PRIO_Q_ING_PREC: - switch (ipv) { + switch (qeth_get_ip_version(skb)) { case 4: tos = ipv4_get_dsfield(ip_hdr(skb)); break; @@ -3637,9 +3477,9 @@ int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb, return card->qdio.default_out_queue; } if (card->qdio.do_prio_queueing == QETH_PRIO_Q_ING_PREC) - return qeth_cut_iqd_prio(card, ~tos >> 6 & 3); + return ~tos >> 6 & 3; if (tos & IPTOS_MINCOST) - return qeth_cut_iqd_prio(card, 3); + return 3; if (tos & IPTOS_RELIABILITY) return 2; if (tos & IPTOS_THROUGHPUT) @@ -3650,12 +3490,11 @@ int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb, case QETH_PRIO_Q_ING_SKB: if (skb->priority > 5) return 0; - return qeth_cut_iqd_prio(card, ~skb->priority >> 1 & 3); + return ~skb->priority >> 1 & 3; case QETH_PRIO_Q_ING_VLAN: - tci = &((struct ethhdr *)skb->data)->h_proto; - if (be16_to_cpu(*tci) == ETH_P_8021Q) - return qeth_cut_iqd_prio(card, - ~be16_to_cpu(*(tci + 1)) >> (VLAN_PRIO_SHIFT + 1) & 3); + if (veth->h_vlan_proto == htons(ETH_P_8021Q)) + return ~ntohs(veth->h_vlan_TCI) >> + (VLAN_PRIO_SHIFT + 1) & 3; break; default: break; @@ -3729,8 +3568,8 @@ static int qeth_add_hw_header(struct qeth_qdio_out_q *queue, unsigned int hdr_len, unsigned int proto_len, unsigned int *elements) { - const unsigned int max_elements = QETH_MAX_BUFFER_ELEMENTS(queue->card); const unsigned int contiguous = proto_len ? proto_len : 1; + const unsigned int max_elements = queue->max_elements; unsigned int __elements; addr_t start, end; bool push_ok; @@ -3748,8 +3587,8 @@ check_layout: __elements = 1 + qeth_count_elements(skb, proto_len); else __elements = qeth_count_elements(skb, 0); - } else if (!proto_len && qeth_get_elements_for_range(start, end) == 1) { - /* Push HW header into a new page. */ + } else if (!proto_len && PAGE_ALIGNED(skb->data)) { + /* Push HW header into preceding page, flush with skb->data. */ push_ok = true; __elements = 1 + qeth_count_elements(skb, 0); } else { @@ -3803,18 +3642,16 @@ static void __qeth_fill_buffer(struct sk_buff *skb, int element = buf->next_element_to_fill; int length = skb_headlen(skb) - offset; char *data = skb->data + offset; - int length_here, cnt; + unsigned int elem_length, cnt; /* map linear part into buffer element(s) */ while (length > 0) { - /* length_here is the remaining amount of data in this page */ - length_here = PAGE_SIZE - ((unsigned long) data % PAGE_SIZE); - if (length < length_here) - length_here = length; + elem_length = min_t(unsigned int, length, + PAGE_SIZE - offset_in_page(data)); buffer->element[element].addr = data; - buffer->element[element].length = length_here; - length -= length_here; + buffer->element[element].length = elem_length; + length -= elem_length; if (is_first_elem) { is_first_elem = false; if (length || skb_is_nonlinear(skb)) @@ -3827,7 +3664,8 @@ static void __qeth_fill_buffer(struct sk_buff *skb, buffer->element[element].eflags = SBAL_EFLAGS_MIDDLE_FRAG; } - data += length_here; + + data += elem_length; element++; } @@ -3838,17 +3676,16 @@ static void __qeth_fill_buffer(struct sk_buff *skb, data = skb_frag_address(frag); length = skb_frag_size(frag); while (length > 0) { - length_here = PAGE_SIZE - - ((unsigned long) data % PAGE_SIZE); - if (length < length_here) - length_here = length; + elem_length = min_t(unsigned int, length, + PAGE_SIZE - offset_in_page(data)); buffer->element[element].addr = data; - buffer->element[element].length = length_here; + buffer->element[element].length = elem_length; buffer->element[element].eflags = SBAL_EFLAGS_MIDDLE_FRAG; - length -= length_here; - data += length_here; + + length -= elem_length; + data += elem_length; element++; } } @@ -3867,11 +3704,13 @@ static void __qeth_fill_buffer(struct sk_buff *skb, * from qeth_core_header_cache. * @offset: when mapping the skb, start at skb->data + offset * @hd_len: if > 0, build a dedicated header element of this size + * flush: Prepare the buffer to be flushed, regardless of its fill level. */ static int qeth_fill_buffer(struct qeth_qdio_out_q *queue, struct qeth_qdio_out_buffer *buf, struct sk_buff *skb, struct qeth_hdr *hdr, - unsigned int offset, unsigned int hd_len) + unsigned int offset, unsigned int hd_len, + bool flush) { struct qdio_buffer *buffer = buf->buffer; bool is_first_elem = true; @@ -3900,8 +3739,8 @@ static int qeth_fill_buffer(struct qeth_qdio_out_q *queue, QETH_TXQ_STAT_INC(queue, skbs_pack); /* If the buffer still has free elements, keep using it. */ - if (buf->next_element_to_fill < - QETH_MAX_BUFFER_ELEMENTS(queue->card)) + if (!flush && + buf->next_element_to_fill < queue->max_elements) return 0; } @@ -3918,15 +3757,31 @@ static int qeth_do_send_packet_fast(struct qeth_qdio_out_q *queue, { int index = queue->next_buf_to_fill; struct qeth_qdio_out_buffer *buffer = queue->bufs[index]; + struct netdev_queue *txq; + bool stopped = false; - /* - * check if buffer is empty to make sure that we do not 'overtake' - * ourselves and try to fill a buffer that is already primed + /* Just a sanity check, the wake/stop logic should ensure that we always + * get a free buffer. */ if (atomic_read(&buffer->state) != QETH_QDIO_BUF_EMPTY) return -EBUSY; - qeth_fill_buffer(queue, buffer, skb, hdr, offset, hd_len); + + txq = netdev_get_tx_queue(queue->card->dev, skb_get_queue_mapping(skb)); + + if (atomic_inc_return(&queue->used_buffers) >= QDIO_MAX_BUFFERS_PER_Q) { + /* If a TX completion happens right _here_ and misses to wake + * the txq, then our re-check below will catch the race. + */ + QETH_TXQ_STAT_INC(queue, stopped); + netif_tx_stop_queue(txq); + stopped = true; + } + + qeth_fill_buffer(queue, buffer, skb, hdr, offset, hd_len, stopped); qeth_flush_buffers(queue, index, 1); + + if (stopped && !qeth_out_queue_is_full(queue)) + netif_tx_start_queue(txq); return 0; } @@ -3936,6 +3791,8 @@ int qeth_do_send_packet(struct qeth_card *card, struct qeth_qdio_out_q *queue, int elements_needed) { struct qeth_qdio_out_buffer *buffer; + struct netdev_queue *txq; + bool stopped = false; int start_index; int flush_count = 0; int do_pack = 0; @@ -3947,21 +3804,24 @@ int qeth_do_send_packet(struct qeth_card *card, struct qeth_qdio_out_q *queue, QETH_OUT_Q_LOCKED) != QETH_OUT_Q_UNLOCKED); start_index = queue->next_buf_to_fill; buffer = queue->bufs[queue->next_buf_to_fill]; - /* - * check if buffer is empty to make sure that we do not 'overtake' - * ourselves and try to fill a buffer that is already primed + + /* Just a sanity check, the wake/stop logic should ensure that we always + * get a free buffer. */ if (atomic_read(&buffer->state) != QETH_QDIO_BUF_EMPTY) { atomic_set(&queue->state, QETH_OUT_Q_UNLOCKED); return -EBUSY; } + + txq = netdev_get_tx_queue(card->dev, skb_get_queue_mapping(skb)); + /* check if we need to switch packing state of this queue */ qeth_switch_to_packing_if_needed(queue); if (queue->do_pack) { do_pack = 1; /* does packet fit in current buffer? */ - if ((QETH_MAX_BUFFER_ELEMENTS(card) - - buffer->next_element_to_fill) < elements_needed) { + if (buffer->next_element_to_fill + elements_needed > + queue->max_elements) { /* ... no -> set state PRIMED */ atomic_set(&buffer->state, QETH_QDIO_BUF_PRIMED); flush_count++; @@ -3969,8 +3829,8 @@ int qeth_do_send_packet(struct qeth_card *card, struct qeth_qdio_out_q *queue, (queue->next_buf_to_fill + 1) % QDIO_MAX_BUFFERS_PER_Q; buffer = queue->bufs[queue->next_buf_to_fill]; - /* we did a step forward, so check buffer state - * again */ + + /* We stepped forward, so sanity-check again: */ if (atomic_read(&buffer->state) != QETH_QDIO_BUF_EMPTY) { qeth_flush_buffers(queue, start_index, @@ -3983,8 +3843,18 @@ int qeth_do_send_packet(struct qeth_card *card, struct qeth_qdio_out_q *queue, } } - flush_count += qeth_fill_buffer(queue, buffer, skb, hdr, offset, - hd_len); + if (buffer->next_element_to_fill == 0 && + atomic_inc_return(&queue->used_buffers) >= QDIO_MAX_BUFFERS_PER_Q) { + /* If a TX completion happens right _here_ and misses to wake + * the txq, then our re-check below will catch the race. + */ + QETH_TXQ_STAT_INC(queue, stopped); + netif_tx_stop_queue(txq); + stopped = true; + } + + flush_count += qeth_fill_buffer(queue, buffer, skb, hdr, offset, hd_len, + stopped); if (flush_count) qeth_flush_buffers(queue, start_index, flush_count); else if (!atomic_read(&queue->set_pci_flags_count)) @@ -4015,6 +3885,8 @@ out: if (do_pack) QETH_TXQ_STAT_ADD(queue, bufs_pack, flush_count); + if (stopped && !qeth_out_queue_is_full(queue)) + netif_tx_start_queue(txq); return rc; } EXPORT_SYMBOL_GPL(qeth_do_send_packet); @@ -4036,11 +3908,10 @@ static void qeth_fill_tso_ext(struct qeth_hdr_tso *hdr, } int qeth_xmit(struct qeth_card *card, struct sk_buff *skb, - struct qeth_qdio_out_q *queue, int ipv, int cast_type, + struct qeth_qdio_out_q *queue, int ipv, void (*fill_header)(struct qeth_qdio_out_q *queue, struct qeth_hdr *hdr, struct sk_buff *skb, - int ipv, int cast_type, - unsigned int data_len)) + int ipv, unsigned int data_len)) { unsigned int proto_len, hw_hdr_len; unsigned int frame_len = skb->len; @@ -4074,7 +3945,7 @@ int qeth_xmit(struct qeth_card *card, struct sk_buff *skb, data_offset = push_len + proto_len; } memset(hdr, 0, hw_hdr_len); - fill_header(queue, hdr, skb, ipv, cast_type, frame_len); + fill_header(queue, hdr, skb, ipv, frame_len); if (is_tso) qeth_fill_tso_ext((struct qeth_hdr_tso *) hdr, frame_len - proto_len, skb, proto_len); @@ -4101,9 +3972,6 @@ int qeth_xmit(struct qeth_card *card, struct sk_buff *skb, } else { if (!push_len) kmem_cache_free(qeth_core_header_cache, hdr); - if (rc == -EBUSY) - /* roll back to ETH header */ - skb_pull(skb, push_len); } return rc; } @@ -4146,7 +4014,7 @@ void qeth_setadp_promisc_mode(struct qeth_card *card) QETH_CARD_TEXT_(card, 4, "mode:%x", mode); iob = qeth_get_adapter_cmd(card, IPA_SETADP_SET_PROMISC_MODE, - sizeof(struct qeth_ipacmd_setadpparms_hdr) + 8); + SETADP_DATA_SIZEOF(mode)); if (!iob) return; cmd = __ipa_cmd(iob); @@ -4186,8 +4054,7 @@ int qeth_setadpparms_change_macaddr(struct qeth_card *card) QETH_CARD_TEXT(card, 4, "chgmac"); iob = qeth_get_adapter_cmd(card, IPA_SETADP_ALTER_MAC_ADDRESS, - sizeof(struct qeth_ipacmd_setadpparms_hdr) + - sizeof(struct qeth_change_addr)); + SETADP_DATA_SIZEOF(change_addr)); if (!iob) return -ENOMEM; cmd = __ipa_cmd(iob); @@ -4214,10 +4081,8 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card, qeth_setadpparms_inspect_rc(cmd); access_ctrl_req = &cmd->data.setadapterparms.data.set_access_ctrl; - QETH_DBF_TEXT_(SETUP, 2, "setaccb"); - QETH_DBF_TEXT_(SETUP, 2, "%s", card->gdev->dev.kobj.name); - QETH_DBF_TEXT_(SETUP, 2, "rc=%d", - cmd->data.setadapterparms.hdr.return_code); + QETH_CARD_TEXT_(card, 2, "rc=%d", + cmd->data.setadapterparms.hdr.return_code); if (cmd->data.setadapterparms.hdr.return_code != SET_ACCESS_CTRL_RC_SUCCESS) QETH_DBF_MESSAGE(3, "ERR:SET_ACCESS_CTRL(%#x) on device %x: %#x\n", @@ -4297,12 +4162,8 @@ static int qeth_setadpparms_set_access_ctrl(struct qeth_card *card, QETH_CARD_TEXT(card, 4, "setacctl"); - QETH_DBF_TEXT_(SETUP, 2, "setacctl"); - QETH_DBF_TEXT_(SETUP, 2, "%s", card->gdev->dev.kobj.name); - iob = qeth_get_adapter_cmd(card, IPA_SETADP_SET_ACCESS_CONTROL, - sizeof(struct qeth_ipacmd_setadpparms_hdr) + - sizeof(struct qeth_set_access_ctrl)); + SETADP_DATA_SIZEOF(set_access_ctrl)); if (!iob) return -ENOMEM; cmd = __ipa_cmd(iob); @@ -4311,7 +4172,7 @@ static int qeth_setadpparms_set_access_ctrl(struct qeth_card *card, rc = qeth_send_ipa_cmd(card, iob, qeth_setadpparms_set_access_ctrl_cb, &fallback); - QETH_DBF_TEXT_(SETUP, 2, "rc=%d", rc); + QETH_CARD_TEXT_(card, 2, "rc=%d", rc); return rc; } @@ -4321,9 +4182,8 @@ int qeth_set_access_ctrl_online(struct qeth_card *card, int fallback) QETH_CARD_TEXT(card, 4, "setactlo"); - if ((card->info.type == QETH_CARD_TYPE_OSD || - card->info.type == QETH_CARD_TYPE_OSX) && - qeth_adp_supported(card, IPA_SETADP_SET_ACCESS_CONTROL)) { + if ((IS_OSD(card) || IS_OSX(card)) && + qeth_adp_supported(card, IPA_SETADP_SET_ACCESS_CONTROL)) { rc = qeth_setadpparms_set_access_ctrl(card, card->options.isolation, fallback); if (rc) { @@ -4348,7 +4208,6 @@ void qeth_tx_timeout(struct net_device *dev) card = dev->ml_priv; QETH_CARD_TEXT(card, 4, "txtimeo"); - QETH_CARD_STAT_INC(card, tx_errors); qeth_schedule_recovery(card); } EXPORT_SYMBOL_GPL(qeth_tx_timeout); @@ -4460,18 +4319,13 @@ static int qeth_snmp_command_cb(struct qeth_card *card, return -ENOSPC; } QETH_CARD_TEXT_(card, 4, "snore%i", - cmd->data.setadapterparms.hdr.used_total); + cmd->data.setadapterparms.hdr.used_total); QETH_CARD_TEXT_(card, 4, "sseqn%i", - cmd->data.setadapterparms.hdr.seq_no); + cmd->data.setadapterparms.hdr.seq_no); /*copy entries to user buffer*/ memcpy(qinfo->udata + qinfo->udata_offset, snmp_data, data_len); qinfo->udata_offset += data_len; - /* check if all replies received ... */ - QETH_CARD_TEXT_(card, 4, "srtot%i", - cmd->data.setadapterparms.hdr.used_total); - QETH_CARD_TEXT_(card, 4, "srseq%i", - cmd->data.setadapterparms.hdr.seq_no); if (cmd->data.setadapterparms.hdr.seq_no < cmd->data.setadapterparms.hdr.used_total) return 1; @@ -4480,54 +4334,43 @@ static int qeth_snmp_command_cb(struct qeth_card *card, static int qeth_snmp_command(struct qeth_card *card, char __user *udata) { + struct qeth_snmp_ureq __user *ureq; struct qeth_cmd_buffer *iob; - struct qeth_ipa_cmd *cmd; - struct qeth_snmp_ureq *ureq; unsigned int req_len; struct qeth_arp_query_info qinfo = {0, }; int rc = 0; QETH_CARD_TEXT(card, 3, "snmpcmd"); - if (card->info.guestlan) + if (IS_VM_NIC(card)) return -EOPNOTSUPP; if ((!qeth_adp_supported(card, IPA_SETADP_SET_SNMP_CONTROL)) && IS_LAYER3(card)) return -EOPNOTSUPP; - /* skip 4 bytes (data_len struct member) to get req_len */ - if (copy_from_user(&req_len, udata + sizeof(int), sizeof(int))) + ureq = (struct qeth_snmp_ureq __user *) udata; + if (get_user(qinfo.udata_len, &ureq->hdr.data_len) || + get_user(req_len, &ureq->hdr.req_len)) + return -EFAULT; + + iob = qeth_get_adapter_cmd(card, IPA_SETADP_SET_SNMP_CONTROL, req_len); + if (!iob) + return -ENOMEM; + + if (copy_from_user(&__ipa_cmd(iob)->data.setadapterparms.data.snmp, + &ureq->cmd, req_len)) { + qeth_put_cmd(iob); return -EFAULT; - if (req_len > (QETH_BUFSIZE - IPA_PDU_HEADER_SIZE - - sizeof(struct qeth_ipacmd_hdr) - - sizeof(struct qeth_ipacmd_setadpparms_hdr))) - return -EINVAL; - ureq = memdup_user(udata, req_len + sizeof(struct qeth_snmp_ureq_hdr)); - if (IS_ERR(ureq)) { - QETH_CARD_TEXT(card, 2, "snmpnome"); - return PTR_ERR(ureq); } - qinfo.udata_len = ureq->hdr.data_len; + qinfo.udata = kzalloc(qinfo.udata_len, GFP_KERNEL); if (!qinfo.udata) { - kfree(ureq); + qeth_put_cmd(iob); return -ENOMEM; } qinfo.udata_offset = sizeof(struct qeth_snmp_ureq_hdr); - iob = qeth_get_adapter_cmd(card, IPA_SETADP_SET_SNMP_CONTROL, - QETH_SNMP_SETADP_CMDLENGTH + req_len); - if (!iob) { - rc = -ENOMEM; - goto out; - } - - /* for large requests, fix-up the length fields: */ - qeth_prepare_ipa_cmd(card, iob, QETH_SETADP_BASE_LEN + req_len); - - cmd = __ipa_cmd(iob); - memcpy(&cmd->data.setadapterparms.data.snmp, &ureq->cmd, req_len); rc = qeth_send_ipa_cmd(card, iob, qeth_snmp_command_cb, &qinfo); if (rc) QETH_DBF_MESSAGE(2, "SNMP command failed on device %x: (%#x)\n", @@ -4536,8 +4379,7 @@ static int qeth_snmp_command(struct qeth_card *card, char __user *udata) if (copy_to_user(udata, qinfo.udata, qinfo.udata_len)) rc = -EFAULT; } -out: - kfree(ureq); + kfree(qinfo.udata); return rc; } @@ -4603,8 +4445,7 @@ static int qeth_query_oat_command(struct qeth_card *card, char __user *udata) } iob = qeth_get_adapter_cmd(card, IPA_SETADP_QUERY_OAT, - sizeof(struct qeth_ipacmd_setadpparms_hdr) + - sizeof(struct qeth_query_oat)); + SETADP_DATA_SIZEOF(query_oat)); if (!iob) { rc = -ENOMEM; goto out_free; @@ -4666,8 +4507,7 @@ int qeth_query_card_info(struct qeth_card *card, QETH_CARD_TEXT(card, 2, "qcrdinfo"); if (!qeth_adp_supported(card, IPA_SETADP_QUERY_CARD_INFO)) return -EOPNOTSUPP; - iob = qeth_get_adapter_cmd(card, IPA_SETADP_QUERY_CARD_INFO, - sizeof(struct qeth_ipacmd_setadpparms_hdr)); + iob = qeth_get_adapter_cmd(card, IPA_SETADP_QUERY_CARD_INFO, 0); if (!iob) return -ENOMEM; return qeth_send_ipa_cmd(card, iob, qeth_query_card_info_cb, @@ -4689,7 +4529,7 @@ int qeth_vm_request_mac(struct qeth_card *card) struct ccw_dev_id id; int rc; - QETH_DBF_TEXT(SETUP, 2, "vmreqmac"); + QETH_CARD_TEXT(card, 2, "vmreqmac"); request = kzalloc(sizeof(*request), GFP_KERNEL | GFP_DMA); response = kzalloc(sizeof(*response), GFP_KERNEL | GFP_DMA); @@ -4714,13 +4554,13 @@ int qeth_vm_request_mac(struct qeth_card *card) if (request->resp_buf_len < sizeof(*response) || response->version != request->resp_version) { rc = -EIO; - QETH_DBF_TEXT(SETUP, 2, "badresp"); - QETH_DBF_HEX(SETUP, 2, &request->resp_buf_len, - sizeof(request->resp_buf_len)); + QETH_CARD_TEXT(card, 2, "badresp"); + QETH_CARD_HEX(card, 2, &request->resp_buf_len, + sizeof(request->resp_buf_len)); } else if (!is_valid_ether_addr(response->mac)) { rc = -EINVAL; - QETH_DBF_TEXT(SETUP, 2, "badmac"); - QETH_DBF_HEX(SETUP, 2, response->mac, ETH_ALEN); + QETH_CARD_TEXT(card, 2, "badmac"); + QETH_CARD_HEX(card, 2, response->mac, ETH_ALEN); } else { ether_addr_copy(card->dev->dev_addr, response->mac); } @@ -4732,54 +4572,40 @@ out: } EXPORT_SYMBOL_GPL(qeth_vm_request_mac); -static int qeth_get_qdio_q_format(struct qeth_card *card) -{ - if (card->info.type == QETH_CARD_TYPE_IQD) - return QDIO_IQDIO_QFMT; - else - return QDIO_QETH_QFMT; -} - static void qeth_determine_capabilities(struct qeth_card *card) { int rc; - int length; - char *prcd; struct ccw_device *ddev; int ddev_offline = 0; - QETH_DBF_TEXT(SETUP, 2, "detcapab"); + QETH_CARD_TEXT(card, 2, "detcapab"); ddev = CARD_DDEV(card); if (!ddev->online) { ddev_offline = 1; rc = ccw_device_set_online(ddev); if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "3err%d", rc); + QETH_CARD_TEXT_(card, 2, "3err%d", rc); goto out; } } - rc = qeth_read_conf_data(card, (void **) &prcd, &length); + rc = qeth_read_conf_data(card); if (rc) { QETH_DBF_MESSAGE(2, "qeth_read_conf_data on device %x returned %i\n", CARD_DEVID(card), rc); - QETH_DBF_TEXT_(SETUP, 2, "5err%d", rc); + QETH_CARD_TEXT_(card, 2, "5err%d", rc); goto out_offline; } - qeth_configure_unitaddr(card, prcd); - if (ddev_offline) - qeth_configure_blkt_default(card, prcd); - kfree(prcd); rc = qdio_get_ssqd_desc(ddev, &card->ssqd); if (rc) - QETH_DBF_TEXT_(SETUP, 2, "6err%d", rc); + QETH_CARD_TEXT_(card, 2, "6err%d", rc); - QETH_DBF_TEXT_(SETUP, 2, "qfmt%d", card->ssqd.qfmt); - QETH_DBF_TEXT_(SETUP, 2, "ac1:%02x", card->ssqd.qdioac1); - QETH_DBF_TEXT_(SETUP, 2, "ac2:%04x", card->ssqd.qdioac2); - QETH_DBF_TEXT_(SETUP, 2, "ac3:%04x", card->ssqd.qdioac3); - QETH_DBF_TEXT_(SETUP, 2, "icnt%d", card->ssqd.icnt); + QETH_CARD_TEXT_(card, 2, "qfmt%d", card->ssqd.qfmt); + QETH_CARD_TEXT_(card, 2, "ac1:%02x", card->ssqd.qdioac1); + QETH_CARD_TEXT_(card, 2, "ac2:%04x", card->ssqd.qdioac2); + QETH_CARD_TEXT_(card, 2, "ac3:%04x", card->ssqd.qdioac3); + QETH_CARD_TEXT_(card, 2, "icnt%d", card->ssqd.icnt); if (!((card->ssqd.qfmt != QDIO_IQDIO_QFMT) || ((card->ssqd.qdioac1 & CHSC_AC1_INITIATE_INPUTQ) == 0) || ((card->ssqd.qdioac3 & CHSC_AC3_FORMAT2_CQ_AVAILABLE) == 0))) { @@ -4827,7 +4653,7 @@ static int qeth_qdio_establish(struct qeth_card *card) int i, j, k; int rc = 0; - QETH_DBF_TEXT(SETUP, 2, "qdioest"); + QETH_CARD_TEXT(card, 2, "qdioest"); qib_param_field = kzalloc(QDIO_MAX_BUFFERS_PER_Q, GFP_KERNEL); @@ -4878,7 +4704,8 @@ static int qeth_qdio_establish(struct qeth_card *card) memset(&init_data, 0, sizeof(struct qdio_initialize)); init_data.cdev = CARD_DDEV(card); - init_data.q_format = qeth_get_qdio_q_format(card); + init_data.q_format = IS_IQD(card) ? QDIO_IQDIO_QFMT : + QDIO_QETH_QFMT; init_data.qib_param_field_format = 0; init_data.qib_param_field = qib_param_field; init_data.no_input_qs = card->qdio.no_in_queues; @@ -4890,8 +4717,7 @@ static int qeth_qdio_establish(struct qeth_card *card) init_data.input_sbal_addr_array = in_sbal_ptrs; init_data.output_sbal_addr_array = out_sbal_ptrs; init_data.output_sbal_state_array = card->qdio.out_bufstates; - init_data.scan_threshold = - (card->info.type == QETH_CARD_TYPE_IQD) ? 1 : 32; + init_data.scan_threshold = IS_IQD(card) ? 1 : 32; if (atomic_cmpxchg(&card->qdio.state, QETH_QDIO_ALLOCATED, QETH_QDIO_ESTABLISHED) == QETH_QDIO_ALLOCATED) { @@ -4931,13 +4757,13 @@ out_free_nothing: static void qeth_core_free_card(struct qeth_card *card) { - QETH_DBF_TEXT(SETUP, 2, "freecrd"); - QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *)); + QETH_CARD_TEXT(card, 2, "freecrd"); qeth_clean_channel(&card->read); qeth_clean_channel(&card->write); qeth_clean_channel(&card->data); + qeth_put_cmd(card->read_cmd); destroy_workqueue(card->event_wq); - qeth_free_qdio_buffers(card); + qeth_free_qdio_queues(card); unregister_service_level(&card->qeth_service_level); dev_set_drvdata(&card->gdev->dev, NULL); kfree(card); @@ -4984,14 +4810,16 @@ int qeth_core_hardsetup_card(struct qeth_card *card, bool *carrier_ok) int retries = 3; int rc; - QETH_DBF_TEXT(SETUP, 2, "hrdsetup"); + QETH_CARD_TEXT(card, 2, "hrdsetup"); atomic_set(&card->force_alloc_skb, 0); - qeth_update_from_chp_desc(card); + rc = qeth_update_from_chp_desc(card); + if (rc) + return rc; retry: if (retries < 3) QETH_DBF_MESSAGE(2, "Retrying to do IDX activates on device %x.\n", CARD_DEVID(card)); - rc = qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD); + rc = qeth_qdio_clear_card(card, !IS_IQD(card)); ccw_device_set_offline(CARD_DDEV(card)); ccw_device_set_offline(CARD_WDEV(card)); ccw_device_set_offline(CARD_RDEV(card)); @@ -5007,10 +4835,10 @@ retry: goto retriable; retriable: if (rc == -ERESTARTSYS) { - QETH_DBF_TEXT(SETUP, 2, "break1"); + QETH_CARD_TEXT(card, 2, "break1"); return rc; } else if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc); + QETH_CARD_TEXT_(card, 2, "1err%d", rc); if (--retries < 0) goto out; else @@ -5019,23 +4847,25 @@ retriable: qeth_determine_capabilities(card); qeth_init_tokens(card); qeth_init_func_level(card); - rc = qeth_idx_activate_channel(card, &card->read, qeth_idx_read_cb); - if (rc == -ERESTARTSYS) { - QETH_DBF_TEXT(SETUP, 2, "break2"); + + rc = qeth_idx_activate_read_channel(card); + if (rc == -EINTR) { + QETH_CARD_TEXT(card, 2, "break2"); return rc; } else if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "3err%d", rc); + QETH_CARD_TEXT_(card, 2, "3err%d", rc); if (--retries < 0) goto out; else goto retry; } - rc = qeth_idx_activate_channel(card, &card->write, qeth_idx_write_cb); - if (rc == -ERESTARTSYS) { - QETH_DBF_TEXT(SETUP, 2, "break3"); + + rc = qeth_idx_activate_write_channel(card); + if (rc == -EINTR) { + QETH_CARD_TEXT(card, 2, "break3"); return rc; } else if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "4err%d", rc); + QETH_CARD_TEXT_(card, 2, "4err%d", rc); if (--retries < 0) goto out; else @@ -5044,13 +4874,13 @@ retriable: card->read_or_write_problem = 0; rc = qeth_mpc_initialize(card); if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "5err%d", rc); + QETH_CARD_TEXT_(card, 2, "5err%d", rc); goto out; } rc = qeth_send_startlan(card); if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "6err%d", rc); + QETH_CARD_TEXT_(card, 2, "6err%d", rc); if (rc == -ENETDOWN) { dev_warn(&card->gdev->dev, "The LAN is offline\n"); *carrier_ok = false; @@ -5077,14 +4907,14 @@ retriable: if (qeth_is_supported(card, IPA_SETADAPTERPARMS)) { rc = qeth_query_setadapterparms(card); if (rc < 0) { - QETH_DBF_TEXT_(SETUP, 2, "7err%d", rc); + QETH_CARD_TEXT_(card, 2, "7err%d", rc); goto out; } } if (qeth_adp_supported(card, IPA_SETADP_SET_DIAG_ASSIST)) { rc = qeth_query_setdiagass(card); if (rc < 0) { - QETH_DBF_TEXT_(SETUP, 2, "8err%d", rc); + QETH_CARD_TEXT_(card, 2, "8err%d", rc); goto out; } } @@ -5171,7 +5001,7 @@ struct sk_buff *qeth_core_get_next_skb(struct qeth_card *card, return NULL; if (((skb_len >= card->options.rx_sg_cb) && - (!(card->info.type == QETH_CARD_TYPE_OSN)) && + !IS_OSN(card) && (!atomic_read(&card->force_alloc_skb))) || (card->options.cq == QETH_CQ_ENABLED)) use_rx_sg = 1; @@ -5344,42 +5174,47 @@ EXPORT_SYMBOL_GPL(qeth_setassparms_cb); struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *card, enum qeth_ipa_funcs ipa_func, - __u16 cmd_code, __u16 len, + u16 cmd_code, + unsigned int data_length, enum qeth_prot_versions prot) { + struct qeth_ipacmd_setassparms *setassparms; + struct qeth_ipacmd_setassparms_hdr *hdr; struct qeth_cmd_buffer *iob; - struct qeth_ipa_cmd *cmd; QETH_CARD_TEXT(card, 4, "getasscm"); - iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SETASSPARMS, prot); + iob = qeth_ipa_alloc_cmd(card, IPA_CMD_SETASSPARMS, prot, + data_length + + offsetof(struct qeth_ipacmd_setassparms, + data)); + if (!iob) + return NULL; - if (iob) { - cmd = __ipa_cmd(iob); - cmd->data.setassparms.hdr.assist_no = ipa_func; - cmd->data.setassparms.hdr.length = 8 + len; - cmd->data.setassparms.hdr.command_code = cmd_code; - } + setassparms = &__ipa_cmd(iob)->data.setassparms; + setassparms->assist_no = ipa_func; + hdr = &setassparms->hdr; + hdr->length = sizeof(*hdr) + data_length; + hdr->command_code = cmd_code; return iob; } EXPORT_SYMBOL_GPL(qeth_get_setassparms_cmd); int qeth_send_simple_setassparms_prot(struct qeth_card *card, enum qeth_ipa_funcs ipa_func, - u16 cmd_code, long data, + u16 cmd_code, u32 *data, enum qeth_prot_versions prot) { - int length = 0; + unsigned int length = data ? SETASS_DATA_SIZEOF(flags_32bit) : 0; struct qeth_cmd_buffer *iob; QETH_CARD_TEXT_(card, 4, "simassp%i", prot); - if (data) - length = sizeof(__u32); iob = qeth_get_setassparms_cmd(card, ipa_func, cmd_code, length, prot); if (!iob) return -ENOMEM; - __ipa_cmd(iob)->data.setassparms.data.flags_32bit = (__u32) data; + if (data) + __ipa_cmd(iob)->data.setassparms.data.flags_32bit = *data; return qeth_send_ipa_cmd(card, iob, qeth_setassparms_cb, NULL); } EXPORT_SYMBOL_GPL(qeth_send_simple_setassparms_prot); @@ -5562,13 +5397,17 @@ static struct net_device *qeth_alloc_netdev(struct qeth_card *card) switch (card->info.type) { case QETH_CARD_TYPE_IQD: - dev = alloc_netdev(0, "hsi%d", NET_NAME_UNKNOWN, ether_setup); + dev = alloc_netdev_mqs(0, "hsi%d", NET_NAME_UNKNOWN, + ether_setup, QETH_MAX_QUEUES, 1); + break; + case QETH_CARD_TYPE_OSM: + dev = alloc_etherdev(0); break; case QETH_CARD_TYPE_OSN: dev = alloc_netdev(0, "osn%d", NET_NAME_UNKNOWN, ether_setup); break; default: - dev = alloc_etherdev(0); + dev = alloc_etherdev_mqs(0, QETH_MAX_QUEUES, 1); } if (!dev) @@ -5590,8 +5429,14 @@ static struct net_device *qeth_alloc_netdev(struct qeth_card *card) dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->hw_features |= NETIF_F_SG; dev->vlan_features |= NETIF_F_SG; - if (IS_IQD(card)) + if (IS_IQD(card)) { dev->features |= NETIF_F_SG; + if (netif_set_real_num_tx_queues(dev, + QETH_IQD_MIN_TXQ)) { + free_netdev(dev); + return NULL; + } + } } return dev; @@ -5641,15 +5486,19 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) } qeth_setup_card(card); - qeth_update_from_chp_desc(card); - card->dev = qeth_alloc_netdev(card); if (!card->dev) { rc = -ENOMEM; goto err_card; } + card->qdio.no_out_queues = card->dev->num_tx_queues; + rc = qeth_update_from_chp_desc(card); + if (rc) + goto err_chp_desc; qeth_determine_capabilities(card); + qeth_set_blkt_defaults(card); + enforced_disc = qeth_enforce_discipline(card); switch (enforced_disc) { case QETH_DISCIPLINE_UNDETERMINED: @@ -5661,9 +5510,8 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) if (rc) goto err_load; - gdev->dev.type = (card->info.type != QETH_CARD_TYPE_OSN) - ? card->discipline->devtype - : &qeth_osn_devtype; + gdev->dev.type = IS_OSN(card) ? &qeth_osn_devtype : + card->discipline->devtype; rc = card->discipline->setup(card->gdev); if (rc) goto err_disc; @@ -5675,6 +5523,7 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) err_disc: qeth_core_free_discipline(card); err_load: +err_chp_desc: free_netdev(card->dev); err_card: qeth_core_free_card(card); @@ -5687,7 +5536,7 @@ static void qeth_core_remove_device(struct ccwgroup_device *gdev) { struct qeth_card *card = dev_get_drvdata(&gdev->dev); - QETH_DBF_TEXT(SETUP, 2, "removedv"); + QETH_CARD_TEXT(card, 2, "removedv"); if (card->discipline) { card->discipline->remove(gdev); @@ -5706,10 +5555,8 @@ static int qeth_core_set_online(struct ccwgroup_device *gdev) enum qeth_discipline_id def_discipline; if (!card->discipline) { - if (card->info.type == QETH_CARD_TYPE_IQD) - def_discipline = QETH_DISCIPLINE_LAYER3; - else - def_discipline = QETH_DISCIPLINE_LAYER2; + def_discipline = IS_IQD(card) ? QETH_DISCIPLINE_LAYER3 : + QETH_DISCIPLINE_LAYER2; rc = qeth_core_load_discipline(card, def_discipline); if (rc) goto err; @@ -5737,32 +5584,34 @@ static void qeth_core_shutdown(struct ccwgroup_device *gdev) if ((gdev->state == CCWGROUP_ONLINE) && card->info.hwtrap) qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM); qeth_qdio_clear_card(card, 0); - qeth_clear_qdio_buffers(card); + qeth_drain_output_queues(card); qdio_free(CARD_DDEV(card)); } -static int qeth_core_freeze(struct ccwgroup_device *gdev) +static int qeth_suspend(struct ccwgroup_device *gdev) { struct qeth_card *card = dev_get_drvdata(&gdev->dev); - if (card->discipline && card->discipline->freeze) - return card->discipline->freeze(gdev); - return 0; -} -static int qeth_core_thaw(struct ccwgroup_device *gdev) -{ - struct qeth_card *card = dev_get_drvdata(&gdev->dev); - if (card->discipline && card->discipline->thaw) - return card->discipline->thaw(gdev); + qeth_set_allowed_threads(card, 0, 1); + wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0); + if (gdev->state == CCWGROUP_OFFLINE) + return 0; + + card->discipline->set_offline(gdev); return 0; } -static int qeth_core_restore(struct ccwgroup_device *gdev) +static int qeth_resume(struct ccwgroup_device *gdev) { struct qeth_card *card = dev_get_drvdata(&gdev->dev); - if (card->discipline && card->discipline->restore) - return card->discipline->restore(gdev); - return 0; + int rc; + + rc = card->discipline->set_online(gdev); + + qeth_set_allowed_threads(card, 0xffffffff, 0); + if (rc) + dev_warn(&card->gdev->dev, "The qeth device driver failed to recover an error on the device\n"); + return rc; } static ssize_t group_store(struct device_driver *ddrv, const char *buf, @@ -5803,9 +5652,9 @@ static struct ccwgroup_driver qeth_core_ccwgroup_driver = { .shutdown = qeth_core_shutdown, .prepare = NULL, .complete = NULL, - .freeze = qeth_core_freeze, - .thaw = qeth_core_thaw, - .restore = qeth_core_restore, + .freeze = qeth_suspend, + .thaw = qeth_resume, + .restore = qeth_resume, }; struct qeth_card *qeth_get_card_by_busid(char *bus_id) @@ -5837,13 +5686,10 @@ int qeth_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) rc = qeth_snmp_command(card, rq->ifr_ifru.ifru_data); break; case SIOC_QETH_GET_CARD_TYPE: - if ((card->info.type == QETH_CARD_TYPE_OSD || - card->info.type == QETH_CARD_TYPE_OSM || - card->info.type == QETH_CARD_TYPE_OSX) && - !card->info.guestlan) + if ((IS_OSD(card) || IS_OSM(card) || IS_OSX(card)) && + !IS_VM_NIC(card)) return 1; - else - return 0; + return 0; case SIOCGMIIPHY: mii_data = if_mii(rq); mii_data->phy_id = 0; @@ -5887,8 +5733,8 @@ static int qeth_start_csum_cb(struct qeth_card *card, struct qeth_reply *reply, static int qeth_set_csum_off(struct qeth_card *card, enum qeth_ipa_funcs cstype, enum qeth_prot_versions prot) { - return qeth_send_simple_setassparms_prot(card, cstype, - IPA_CMD_ASS_STOP, 0, prot); + return qeth_send_simple_setassparms_prot(card, cstype, IPA_CMD_ASS_STOP, + NULL, prot); } static int qeth_set_csum_on(struct qeth_card *card, enum qeth_ipa_funcs cstype, @@ -5919,7 +5765,8 @@ static int qeth_set_csum_on(struct qeth_card *card, enum qeth_ipa_funcs cstype, return -EOPNOTSUPP; } - iob = qeth_get_setassparms_cmd(card, cstype, IPA_CMD_ASS_ENABLE, 4, + iob = qeth_get_setassparms_cmd(card, cstype, IPA_CMD_ASS_ENABLE, + SETASS_DATA_SIZEOF(flags_32bit), prot); if (!iob) { qeth_set_csum_off(card, cstype, prot); @@ -5976,7 +5823,7 @@ static int qeth_set_tso_off(struct qeth_card *card, enum qeth_prot_versions prot) { return qeth_send_simple_setassparms_prot(card, IPA_OUTBOUND_TSO, - IPA_CMD_ASS_STOP, 0, prot); + IPA_CMD_ASS_STOP, NULL, prot); } static int qeth_set_tso_on(struct qeth_card *card, @@ -6002,7 +5849,8 @@ static int qeth_set_tso_on(struct qeth_card *card, } iob = qeth_get_setassparms_cmd(card, IPA_OUTBOUND_TSO, - IPA_CMD_ASS_ENABLE, sizeof(caps), prot); + IPA_CMD_ASS_ENABLE, + SETASS_DATA_SIZEOF(caps), prot); if (!iob) { qeth_set_tso_off(card, prot); return -ENOMEM; @@ -6089,8 +5937,8 @@ int qeth_set_features(struct net_device *dev, netdev_features_t features) netdev_features_t changed = dev->features ^ features; int rc = 0; - QETH_DBF_TEXT(SETUP, 2, "setfeat"); - QETH_DBF_HEX(SETUP, 2, &features, sizeof(features)); + QETH_CARD_TEXT(card, 2, "setfeat"); + QETH_CARD_HEX(card, 2, &features, sizeof(features)); if ((changed & NETIF_F_IP_CSUM)) { rc = qeth_set_ipa_csum(card, features & NETIF_F_IP_CSUM, @@ -6136,7 +5984,7 @@ netdev_features_t qeth_fix_features(struct net_device *dev, { struct qeth_card *card = dev->ml_priv; - QETH_DBF_TEXT(SETUP, 2, "fixfeat"); + QETH_CARD_TEXT(card, 2, "fixfeat"); if (!qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM)) features &= ~NETIF_F_IP_CSUM; if (!qeth_is_supported6(card, IPA_OUTBOUND_CHECKSUM_V6)) @@ -6149,7 +5997,7 @@ netdev_features_t qeth_fix_features(struct net_device *dev, if (!qeth_is_supported6(card, IPA_OUTBOUND_TSO)) features &= ~NETIF_F_TSO6; - QETH_DBF_HEX(SETUP, 2, &features, sizeof(features)); + QETH_CARD_HEX(card, 2, &features, sizeof(features)); return features; } EXPORT_SYMBOL_GPL(qeth_fix_features); @@ -6193,7 +6041,6 @@ void qeth_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->rx_errors = card->stats.rx_errors; stats->rx_dropped = card->stats.rx_dropped; stats->multicast = card->stats.rx_multicast; - stats->tx_errors = card->stats.tx_errors; for (i = 0; i < card->qdio.no_out_queues; i++) { queue = card->qdio.out_qs[i]; @@ -6206,6 +6053,15 @@ void qeth_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) } EXPORT_SYMBOL_GPL(qeth_get_stats64); +u16 qeth_iqd_select_queue(struct net_device *dev, struct sk_buff *skb, + u8 cast_type, struct net_device *sb_dev) +{ + if (cast_type != RTN_UNICAST) + return QETH_IQD_MCAST_TXQ; + return QETH_IQD_MIN_UCAST_TXQ; +} +EXPORT_SYMBOL_GPL(qeth_iqd_select_queue); + int qeth_open(struct net_device *dev) { struct qeth_card *card = dev->ml_priv; @@ -6216,7 +6072,7 @@ int qeth_open(struct net_device *dev) return -EIO; card->data.state = CH_STATE_UP; - netif_start_queue(dev); + netif_tx_start_all_queues(dev); napi_enable(&card->napi); local_bh_disable(); diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index f8c5d4a9be13..75b5834ed28d 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -31,14 +31,12 @@ extern unsigned char IPA_PDU_HEADER[]; #define QETH_CLEAR_CHANNEL_PARM -10 #define QETH_HALT_CHANNEL_PARM -11 -#define QETH_RCD_PARM -12 static inline bool qeth_intparm_is_iob(unsigned long intparm) { switch (intparm) { case QETH_CLEAR_CHANNEL_PARM: case QETH_HALT_CHANNEL_PARM: - case QETH_RCD_PARM: case 0: return false; } @@ -82,7 +80,7 @@ enum qeth_card_types { #define IS_OSM(card) ((card)->info.type == QETH_CARD_TYPE_OSM) #define IS_OSN(card) ((card)->info.type == QETH_CARD_TYPE_OSN) #define IS_OSX(card) ((card)->info.type == QETH_CARD_TYPE_OSX) -#define IS_VM_NIC(card) ((card)->info.guestlan) +#define IS_VM_NIC(card) ((card)->info.is_vm_nic) #define QETH_MPC_DIFINFO_LEN_INDICATES_LINK_TYPE 0x18 /* only the first two bytes are looked at in qeth_get_cardname_short */ @@ -381,9 +379,7 @@ struct qeth_ipacmd_layer2setdelvlan { __u16 vlan_id; } __attribute__ ((packed)); - struct qeth_ipacmd_setassparms_hdr { - __u32 assist_no; __u16 length; __u16 command_code; __u16 return_code; @@ -428,6 +424,7 @@ struct qeth_tso_start_data { /* SETASSPARMS IPA Command: */ struct qeth_ipacmd_setassparms { + u32 assist_no; struct qeth_ipacmd_setassparms_hdr hdr; union { __u32 flags_32bit; @@ -439,6 +436,8 @@ struct qeth_ipacmd_setassparms { } data; } __attribute__ ((packed)); +#define SETASS_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipacmd_setassparms,\ + data.field) /* SETRTG IPA Command: ****************************************************/ struct qeth_set_routing { @@ -526,8 +525,6 @@ struct qeth_query_switch_attributes { #define QETH_SETADP_FLAGS_VIRTUAL_MAC 0x80 /* for CHANGE_ADDR_READ_MAC */ struct qeth_ipacmd_setadpparms_hdr { - u32 supp_hw_cmds; - u32 reserved1; u16 cmdlength; u16 reserved2; u32 command_code; @@ -539,6 +536,7 @@ struct qeth_ipacmd_setadpparms_hdr { }; struct qeth_ipacmd_setadpparms { + struct qeth_ipa_caps hw_cmds; struct qeth_ipacmd_setadpparms_hdr hdr; union { struct qeth_query_cmds_supp query_cmds_supp; @@ -552,6 +550,9 @@ struct qeth_ipacmd_setadpparms { } data; } __attribute__ ((packed)); +#define SETADP_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipacmd_setadpparms,\ + data.field) + /* CREATE_ADDR IPA Command: ***********************************************/ struct qeth_create_destroy_address { __u8 unique_id[8]; @@ -598,6 +599,11 @@ struct qeth_ipacmd_diagass { __u8 cdata[64]; } __attribute__ ((packed)); +#define DIAG_HDR_LEN offsetofend(struct qeth_ipacmd_diagass, ext) +#define DIAG_SUB_HDR_LEN (offsetofend(struct qeth_ipacmd_diagass, ext) -\ + offsetof(struct qeth_ipacmd_diagass, \ + subcmd_len)) + /* VNIC Characteristics IPA Command: *****************************************/ /* IPA commands/sub commands for VNICC */ #define IPA_VNICC_QUERY_CHARS 0x00000000L @@ -624,12 +630,6 @@ struct qeth_ipacmd_diagass { /* VNICC header */ struct qeth_ipacmd_vnicc_hdr { - u32 sup; - u32 cur; -}; - -/* VNICC sub command header */ -struct qeth_vnicc_sub_hdr { u16 data_length; u16 reserved; u32 sub_command; @@ -654,15 +654,18 @@ struct qeth_vnicc_getset_timeout { /* complete VNICC IPA command message */ struct qeth_ipacmd_vnicc { + struct qeth_ipa_caps vnicc_cmds; struct qeth_ipacmd_vnicc_hdr hdr; - struct qeth_vnicc_sub_hdr sub_hdr; union { struct qeth_vnicc_query_cmds query_cmds; struct qeth_vnicc_set_char set_char; struct qeth_vnicc_getset_timeout getset_timeout; - }; + } data; }; +#define VNICC_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipacmd_vnicc,\ + data.field) + /* SETBRIDGEPORT IPA Command: *********************************************/ enum qeth_ipa_sbp_cmd { IPA_SBP_QUERY_COMMANDS_SUPPORTED = 0x00000000L, @@ -688,8 +691,6 @@ struct mac_addr_lnid { } __packed; struct qeth_ipacmd_sbp_hdr { - __u32 supported_sbp_cmds; - __u32 enabled_sbp_cmds; __u16 cmdlength; __u16 reserved1; __u32 command_code; @@ -704,16 +705,10 @@ struct qeth_sbp_query_cmds_supp { __u32 reserved; } __packed; -struct qeth_sbp_reset_role { -} __packed; - struct qeth_sbp_set_primary { struct net_if_token token; } __packed; -struct qeth_sbp_set_secondary { -} __packed; - struct qeth_sbp_port_entry { __u8 role; __u8 state; @@ -739,17 +734,19 @@ struct qeth_sbp_state_change { } __packed; struct qeth_ipacmd_setbridgeport { + struct qeth_ipa_caps sbp_cmds; struct qeth_ipacmd_sbp_hdr hdr; union { struct qeth_sbp_query_cmds_supp query_cmds_supp; - struct qeth_sbp_reset_role reset_role; struct qeth_sbp_set_primary set_primary; - struct qeth_sbp_set_secondary set_secondary; struct qeth_sbp_query_ports query_ports; struct qeth_sbp_state_change state_change; } data; } __packed; +#define SBP_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipacmd_setbridgeport,\ + data.field) + /* ADDRESS_CHANGE_NOTIFICATION adapter-initiated "command" *******************/ /* Bitmask for entry->change_code. Both bits may be raised. */ enum qeth_ipa_addr_change_code { @@ -808,6 +805,8 @@ struct qeth_ipa_cmd { } data; } __attribute__ ((packed)); +#define IPA_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipa_cmd, data.field) + /* * special command for ARP processing. * this is not included in setassparms command before, because we get @@ -825,10 +824,6 @@ enum qeth_ipa_arp_return_codes { extern const char *qeth_get_ipa_msg(enum qeth_ipa_return_codes rc); extern const char *qeth_get_ipa_cmd_name(enum qeth_ipa_cmds cmd); -#define QETH_SETADP_BASE_LEN (sizeof(struct qeth_ipacmd_hdr) + \ - sizeof(struct qeth_ipacmd_setadpparms_hdr)) -#define QETH_SNMP_SETADP_CMDLENGTH 16 - /* Helper functions */ #define IS_IPA_REPLY(cmd) ((cmd->hdr.initiator == IPA_CMD_INITIATOR_HOST) || \ (cmd->hdr.initiator == IPA_CMD_INITIATOR_OSA_REPLY)) diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c index 56deeb6f7bc0..9f392497d570 100644 --- a/drivers/s390/net/qeth_core_sys.c +++ b/drivers/s390/net/qeth_core_sys.c @@ -198,6 +198,9 @@ static ssize_t qeth_dev_prioqing_store(struct device *dev, if (!card) return -EINVAL; + if (IS_IQD(card)) + return -EOPNOTSUPP; + mutex_lock(&card->conf_mutex); if (card->state != CARD_STATE_DOWN) { rc = -EPERM; @@ -239,10 +242,6 @@ static ssize_t qeth_dev_prioqing_store(struct device *dev, card->qdio.do_prio_queueing = QETH_NO_PRIO_QUEUEING; card->qdio.default_out_queue = 2; } else if (sysfs_streq(buf, "no_prio_queueing:3")) { - if (card->info.type == QETH_CARD_TYPE_IQD) { - rc = -EPERM; - goto out; - } card->qdio.do_prio_queueing = QETH_NO_PRIO_QUEUEING; card->qdio.default_out_queue = 3; } else if (sysfs_streq(buf, "no_prio_queueing")) { @@ -480,8 +479,7 @@ static ssize_t qeth_dev_isolation_store(struct device *dev, return -EINVAL; mutex_lock(&card->conf_mutex); - if (card->info.type != QETH_CARD_TYPE_OSD && - card->info.type != QETH_CARD_TYPE_OSX) { + if (!IS_OSD(card) && !IS_OSX(card)) { rc = -EOPNOTSUPP; dev_err(&card->gdev->dev, "Adapter does not " "support QDIO data connection isolation\n"); diff --git a/drivers/s390/net/qeth_ethtool.c b/drivers/s390/net/qeth_ethtool.c index 93a53fed4cf8..4166eb29f0bd 100644 --- a/drivers/s390/net/qeth_ethtool.c +++ b/drivers/s390/net/qeth_ethtool.c @@ -38,6 +38,7 @@ static const struct qeth_stats txq_stats[] = { QETH_TXQ_STAT("linearized+error skbs", skbs_linearized_fail), QETH_TXQ_STAT("TSO bytes", tso_bytes), QETH_TXQ_STAT("Packing mode switches", packing_mode_switch), + QETH_TXQ_STAT("Queue stopped", stopped), }; static const struct qeth_stats card_stats[] = { @@ -154,6 +155,21 @@ static void qeth_get_drvinfo(struct net_device *dev, CARD_RDEV_ID(card), CARD_WDEV_ID(card), CARD_DDEV_ID(card)); } +static void qeth_get_channels(struct net_device *dev, + struct ethtool_channels *channels) +{ + struct qeth_card *card = dev->ml_priv; + + channels->max_rx = dev->num_rx_queues; + channels->max_tx = card->qdio.no_out_queues; + channels->max_other = 0; + channels->max_combined = 0; + channels->rx_count = dev->real_num_rx_queues; + channels->tx_count = dev->real_num_tx_queues; + channels->other_count = 0; + channels->combined_count = 0; +} + /* Helper function to fill 'advertising' and 'supported' which are the same. */ /* Autoneg and full-duplex are supported and advertised unconditionally. */ /* Always advertise and support all speeds up to specified, and only one */ @@ -359,6 +375,7 @@ const struct ethtool_ops qeth_ethtool_ops = { .get_ethtool_stats = qeth_get_ethtool_stats, .get_sset_count = qeth_get_sset_count, .get_drvinfo = qeth_get_drvinfo, + .get_channels = qeth_get_channels, .get_link_ksettings = qeth_get_link_ksettings, }; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index c3067fd3bd9e..fd64bc3f4062 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -85,7 +85,8 @@ static int qeth_l2_send_setdelmac(struct qeth_card *card, __u8 *mac, struct qeth_cmd_buffer *iob; QETH_CARD_TEXT(card, 2, "L2sdmac"); - iob = qeth_get_ipacmd_buffer(card, ipacmd, QETH_PROT_IPV4); + iob = qeth_ipa_alloc_cmd(card, ipacmd, QETH_PROT_IPV4, + IPA_DATA_SIZEOF(setdelmac)); if (!iob) return -ENOMEM; cmd = __ipa_cmd(iob); @@ -149,35 +150,23 @@ static int qeth_l2_remove_mac(struct qeth_card *card, u8 *mac) return rc; } -static void qeth_l2_del_all_macs(struct qeth_card *card) +static void qeth_l2_drain_rx_mode_cache(struct qeth_card *card) { struct qeth_mac *mac; struct hlist_node *tmp; int i; - spin_lock_bh(&card->mclock); hash_for_each_safe(card->mac_htable, i, tmp, mac, hnode) { hash_del(&mac->hnode); kfree(mac); } - spin_unlock_bh(&card->mclock); -} - -static int qeth_l2_get_cast_type(struct qeth_card *card, struct sk_buff *skb) -{ - if (card->info.type == QETH_CARD_TYPE_OSN) - return RTN_UNICAST; - if (is_broadcast_ether_addr(skb->data)) - return RTN_BROADCAST; - if (is_multicast_ether_addr(skb->data)) - return RTN_MULTICAST; - return RTN_UNICAST; } static void qeth_l2_fill_header(struct qeth_qdio_out_q *queue, struct qeth_hdr *hdr, struct sk_buff *skb, - int ipv, int cast_type, unsigned int data_len) + int ipv, unsigned int data_len) { + int cast_type = qeth_get_ether_cast_type(skb); struct vlan_ethhdr *veth = vlan_eth_hdr(skb); hdr->hdr.l2.pkt_length = data_len; @@ -253,7 +242,8 @@ static int qeth_l2_send_setdelvlan(struct qeth_card *card, __u16 i, struct qeth_cmd_buffer *iob; QETH_CARD_TEXT_(card, 4, "L2sdv%x", ipacmd); - iob = qeth_get_ipacmd_buffer(card, ipacmd, QETH_PROT_IPV4); + iob = qeth_ipa_alloc_cmd(card, ipacmd, QETH_PROT_IPV4, + IPA_DATA_SIZEOF(setdelvlan)); if (!iob) return -ENOMEM; cmd = __ipa_cmd(iob); @@ -287,26 +277,23 @@ static int qeth_l2_vlan_rx_kill_vid(struct net_device *dev, static void qeth_l2_stop_card(struct qeth_card *card) { - QETH_DBF_TEXT(SETUP , 2, "stopcard"); - QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *)); + QETH_CARD_TEXT(card, 2, "stopcard"); qeth_set_allowed_threads(card, 0, 1); + cancel_work_sync(&card->rx_mode_work); + qeth_l2_drain_rx_mode_cache(card); + if (card->state == CARD_STATE_SOFTSETUP) { - qeth_l2_del_all_macs(card); qeth_clear_ipacmd_list(card); card->state = CARD_STATE_HARDSETUP; } if (card->state == CARD_STATE_HARDSETUP) { qeth_qdio_clear_card(card, 0); - qeth_clear_qdio_buffers(card); + qeth_drain_output_queues(card); qeth_clear_working_pool_list(card); card->state = CARD_STATE_DOWN; } - if (card->state == CARD_STATE_DOWN) { - qeth_clear_cmd_buffers(&card->read); - qeth_clear_cmd_buffers(&card->write); - } flush_workqueue(card->event_wq); card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED; @@ -334,13 +321,11 @@ static int qeth_l2_process_inbound_buffer(struct qeth_card *card, case QETH_HEADER_TYPE_LAYER2: skb->protocol = eth_type_trans(skb, skb->dev); qeth_rx_csum(card, skb, hdr->hdr.l2.flags[1]); - if (skb->protocol == htons(ETH_P_802_2)) - *((__u32 *)skb->cb) = ++card->seqno.pkt_seqno; len = skb->len; napi_gro_receive(&card->napi, skb); break; case QETH_HEADER_TYPE_OSN: - if (card->info.type == QETH_CARD_TYPE_OSN) { + if (IS_OSN(card)) { skb_push(skb, sizeof(struct qeth_hdr)); skb_copy_to_linear_data(skb, hdr, sizeof(struct qeth_hdr)); @@ -367,8 +352,7 @@ static int qeth_l2_request_initial_mac(struct qeth_card *card) { int rc = 0; - QETH_DBF_TEXT(SETUP, 2, "l2reqmac"); - QETH_DBF_TEXT_(SETUP, 2, "doL2%s", CARD_BUS_ID(card)); + QETH_CARD_TEXT(card, 2, "l2reqmac"); if (MACHINE_IS_VM) { rc = qeth_vm_request_mac(card); @@ -376,7 +360,7 @@ static int qeth_l2_request_initial_mac(struct qeth_card *card) goto out; QETH_DBF_MESSAGE(2, "z/VM MAC Service failed on device %x: %#x\n", CARD_DEVID(card), rc); - QETH_DBF_TEXT_(SETUP, 2, "err%04x", rc); + QETH_CARD_TEXT_(card, 2, "err%04x", rc); /* fall back to alternative mechanism: */ } @@ -386,18 +370,17 @@ static int qeth_l2_request_initial_mac(struct qeth_card *card) goto out; QETH_DBF_MESSAGE(2, "READ_MAC Assist failed on device %x: %#x\n", CARD_DEVID(card), rc); - QETH_DBF_TEXT_(SETUP, 2, "1err%04x", rc); + QETH_CARD_TEXT_(card, 2, "1err%04x", rc); /* fall back once more: */ } /* some devices don't support a custom MAC address: */ - if (card->info.type == QETH_CARD_TYPE_OSM || - card->info.type == QETH_CARD_TYPE_OSX) + if (IS_OSM(card) || IS_OSX(card)) return (rc) ? rc : -EADDRNOTAVAIL; eth_hw_addr_random(card->dev); out: - QETH_DBF_HEX(SETUP, 2, card->dev->dev_addr, card->dev->addr_len); + QETH_CARD_HEX(card, 2, card->dev->dev_addr, card->dev->addr_len); return 0; } @@ -481,7 +464,7 @@ static void qeth_promisc_to_bridge(struct qeth_card *card) role = QETH_SBP_ROLE_NONE; rc = qeth_bridgeport_setrole(card, role); - QETH_DBF_TEXT_(SETUP, 2, "bpm%c%04x", + QETH_CARD_TEXT_(card, 2, "bpm%c%04x", (promisc_mode == SET_PROMISC_MODE_ON) ? '+' : '-', rc); if (!rc) { card->options.sbp.role = role; @@ -515,9 +498,11 @@ static void qeth_l2_add_mac(struct qeth_card *card, struct netdev_hw_addr *ha) hash_add(card->mac_htable, &mac->hnode, mac_hash); } -static void qeth_l2_set_rx_mode(struct net_device *dev) +static void qeth_l2_rx_mode_work(struct work_struct *work) { - struct qeth_card *card = dev->ml_priv; + struct qeth_card *card = container_of(work, struct qeth_card, + rx_mode_work); + struct net_device *dev = card->dev; struct netdev_hw_addr *ha; struct qeth_mac *mac; struct hlist_node *tmp; @@ -526,12 +511,12 @@ static void qeth_l2_set_rx_mode(struct net_device *dev) QETH_CARD_TEXT(card, 3, "setmulti"); - spin_lock_bh(&card->mclock); - + netif_addr_lock_bh(dev); netdev_for_each_mc_addr(ha, dev) qeth_l2_add_mac(card, ha); netdev_for_each_uc_addr(ha, dev) qeth_l2_add_mac(card, ha); + netif_addr_unlock_bh(dev); hash_for_each_safe(card->mac_htable, i, tmp, mac, hnode) { switch (mac->disp_flag) { @@ -554,8 +539,6 @@ static void qeth_l2_set_rx_mode(struct net_device *dev) } } - spin_unlock_bh(&card->mclock); - if (qeth_adp_supported(card, IPA_SETADP_SET_PROMISC_MODE)) qeth_setadp_promisc_mode(card); else @@ -586,7 +569,7 @@ static int qeth_l2_xmit_osn(struct qeth_card *card, struct sk_buff *skb, } elements += qeth_count_elements(skb, hd_len); - if (elements > QETH_MAX_BUFFER_ELEMENTS(card)) { + if (elements > queue->max_elements) { rc = -E2BIG; goto out; } @@ -603,37 +586,44 @@ static netdev_tx_t qeth_l2_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct qeth_card *card = dev->ml_priv; - int cast_type = qeth_l2_get_cast_type(card, skb); - int ipv = qeth_get_ip_version(skb); + u16 txq = skb_get_queue_mapping(skb); struct qeth_qdio_out_q *queue; int tx_bytes = skb->len; int rc; - queue = qeth_get_tx_queue(card, skb, ipv, cast_type); - - netif_stop_queue(dev); + if (IS_IQD(card)) + txq = qeth_iqd_translate_txq(dev, txq); + queue = card->qdio.out_qs[txq]; if (IS_OSN(card)) rc = qeth_l2_xmit_osn(card, skb, queue); else - rc = qeth_xmit(card, skb, queue, ipv, cast_type, + rc = qeth_xmit(card, skb, queue, qeth_get_ip_version(skb), qeth_l2_fill_header); if (!rc) { QETH_TXQ_STAT_INC(queue, tx_packets); QETH_TXQ_STAT_ADD(queue, tx_bytes, tx_bytes); - netif_wake_queue(dev); return NETDEV_TX_OK; - } else if (rc == -EBUSY) { - return NETDEV_TX_BUSY; - } /* else fall through */ + } QETH_TXQ_STAT_INC(queue, tx_dropped); kfree_skb(skb); - netif_wake_queue(dev); return NETDEV_TX_OK; } +static u16 qeth_l2_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev) +{ + struct qeth_card *card = dev->ml_priv; + + if (IS_IQD(card)) + return qeth_iqd_select_queue(dev, skb, + qeth_get_ether_cast_type(skb), + sb_dev); + return qeth_get_priority_queue(card, skb); +} + static const struct device_type qeth_l2_devtype = { .name = "qeth_layer2", .groups = qeth_l2_attr_groups, @@ -653,6 +643,7 @@ static int qeth_l2_probe_device(struct ccwgroup_device *gdev) } hash_init(card->mac_htable); + INIT_WORK(&card->rx_mode_work, qeth_l2_rx_mode_work); return 0; } @@ -673,12 +664,20 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev) unregister_netdev(card->dev); } +static void qeth_l2_set_rx_mode(struct net_device *dev) +{ + struct qeth_card *card = dev->ml_priv; + + schedule_work(&card->rx_mode_work); +} + static const struct net_device_ops qeth_l2_netdev_ops = { .ndo_open = qeth_open, .ndo_stop = qeth_stop, .ndo_get_stats64 = qeth_get_stats64, .ndo_start_xmit = qeth_l2_hard_start_xmit, .ndo_features_check = qeth_features_check, + .ndo_select_queue = qeth_l2_select_queue, .ndo_validate_addr = qeth_l2_validate_addr, .ndo_set_rx_mode = qeth_l2_set_rx_mode, .ndo_do_ioctl = qeth_do_ioctl, @@ -721,7 +720,7 @@ static int qeth_l2_setup_netdev(struct qeth_card *card, bool carrier_ok) card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; } - if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) { + if (IS_OSD(card) && !IS_VM_NIC(card)) { card->dev->features |= NETIF_F_SG; /* OSA 3S and earlier has no RX/TX support */ if (qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM)) { @@ -793,12 +792,11 @@ static int qeth_l2_set_online(struct ccwgroup_device *gdev) mutex_lock(&card->discipline_mutex); mutex_lock(&card->conf_mutex); - QETH_DBF_TEXT(SETUP, 2, "setonlin"); - QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *)); + QETH_CARD_TEXT(card, 2, "setonlin"); rc = qeth_core_hardsetup_card(card, &carrier_ok); if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "2err%04x", rc); + QETH_CARD_TEXT_(card, 2, "2err%04x", rc); rc = -ENODEV; goto out_remove; } @@ -829,10 +827,9 @@ static int qeth_l2_set_online(struct ccwgroup_device *gdev) qeth_print_status_message(card); /* softsetup */ - QETH_DBF_TEXT(SETUP, 2, "softsetp"); + QETH_CARD_TEXT(card, 2, "softsetp"); - if ((card->info.type == QETH_CARD_TYPE_OSD) || - (card->info.type == QETH_CARD_TYPE_OSX)) { + if (IS_OSD(card) || IS_OSX(card)) { rc = qeth_l2_start_ipassists(card); if (rc) goto out_remove; @@ -840,7 +837,7 @@ static int qeth_l2_set_online(struct ccwgroup_device *gdev) rc = qeth_init_qdio_queues(card); if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "6err%d", rc); + QETH_CARD_TEXT_(card, 2, "6err%d", rc); rc = -ENODEV; goto out_remove; } @@ -880,7 +877,6 @@ out_remove: ccw_device_set_offline(CARD_WDEV(card)); ccw_device_set_offline(CARD_RDEV(card)); qdio_free(CARD_DDEV(card)); - card->state = CARD_STATE_DOWN; mutex_unlock(&card->conf_mutex); mutex_unlock(&card->discipline_mutex); @@ -895,8 +891,7 @@ static int __qeth_l2_set_offline(struct ccwgroup_device *cgdev, mutex_lock(&card->discipline_mutex); mutex_lock(&card->conf_mutex); - QETH_DBF_TEXT(SETUP, 3, "setoffl"); - QETH_DBF_HEX(SETUP, 3, &card, sizeof(void *)); + QETH_CARD_TEXT(card, 3, "setoffl"); if ((!recovery_mode && card->info.hwtrap) || card->info.hwtrap == 2) { qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM); @@ -917,7 +912,7 @@ static int __qeth_l2_set_offline(struct ccwgroup_device *cgdev, if (!rc) rc = (rc2) ? rc2 : rc3; if (rc) - QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc); + QETH_CARD_TEXT_(card, 2, "1err%d", rc); qdio_free(CARD_DDEV(card)); /* let user_space know that device is offline */ @@ -970,33 +965,6 @@ static void __exit qeth_l2_exit(void) pr_info("unregister layer 2 discipline\n"); } -static int qeth_l2_pm_suspend(struct ccwgroup_device *gdev) -{ - struct qeth_card *card = dev_get_drvdata(&gdev->dev); - - qeth_set_allowed_threads(card, 0, 1); - wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0); - if (gdev->state == CCWGROUP_OFFLINE) - return 0; - - qeth_l2_set_offline(gdev); - return 0; -} - -static int qeth_l2_pm_resume(struct ccwgroup_device *gdev) -{ - struct qeth_card *card = dev_get_drvdata(&gdev->dev); - int rc; - - rc = qeth_l2_set_online(gdev); - - qeth_set_allowed_threads(card, 0xffffffff, 0); - if (rc) - dev_warn(&card->gdev->dev, "The qeth device driver " - "failed to recover an error on the device\n"); - return rc; -} - /* Returns zero if the command is successfully "consumed" */ static int qeth_l2_control_event(struct qeth_card *card, struct qeth_ipa_cmd *cmd) @@ -1026,50 +994,16 @@ struct qeth_discipline qeth_l2_discipline = { .remove = qeth_l2_remove_device, .set_online = qeth_l2_set_online, .set_offline = qeth_l2_set_offline, - .freeze = qeth_l2_pm_suspend, - .thaw = qeth_l2_pm_resume, - .restore = qeth_l2_pm_resume, .do_ioctl = NULL, .control_event_handler = qeth_l2_control_event, }; EXPORT_SYMBOL_GPL(qeth_l2_discipline); -static int qeth_osn_send_control_data(struct qeth_card *card, int len, - struct qeth_cmd_buffer *iob) +static void qeth_osn_assist_cb(struct qeth_card *card, + struct qeth_cmd_buffer *iob) { - struct qeth_channel *channel = iob->channel; - int rc = 0; - - QETH_CARD_TEXT(card, 5, "osndctrd"); - - wait_event(card->wait_q, - atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0); - qeth_prepare_control_data(card, len, iob); - QETH_CARD_TEXT(card, 6, "osnoirqp"); - spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); - rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw, - (addr_t) iob, 0, 0, QETH_IPA_TIMEOUT); - spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); - if (rc) { - QETH_DBF_MESSAGE(2, "qeth_osn_send_control_data: " - "ccw_device_start rc = %i\n", rc); - QETH_CARD_TEXT_(card, 2, " err%d", rc); - qeth_release_buffer(channel, iob); - atomic_set(&channel->irq_pending, 0); - wake_up(&card->wait_q); - } - return rc; -} - -static int qeth_osn_send_ipa_cmd(struct qeth_card *card, - struct qeth_cmd_buffer *iob) -{ - u16 length; - - QETH_CARD_TEXT(card, 4, "osndipa"); - - memcpy(&length, QETH_IPA_PDU_LEN_TOTAL(iob->data), 2); - return qeth_osn_send_control_data(card, length, iob); + qeth_notify_reply(iob->reply, 0); + qeth_put_cmd(iob); } int qeth_osn_assist(struct net_device *dev, void *data, int data_len) @@ -1077,6 +1011,8 @@ int qeth_osn_assist(struct net_device *dev, void *data, int data_len) struct qeth_cmd_buffer *iob; struct qeth_card *card; + if (data_len < 0) + return -EINVAL; if (!dev) return -ENODEV; card = dev->ml_priv; @@ -1085,10 +1021,16 @@ int qeth_osn_assist(struct net_device *dev, void *data, int data_len) QETH_CARD_TEXT(card, 2, "osnsdmc"); if (!qeth_card_hw_is_reachable(card)) return -ENODEV; - iob = qeth_wait_for_buffer(&card->write); + + iob = qeth_alloc_cmd(&card->write, IPA_PDU_HEADER_SIZE + data_len, 1, + QETH_IPA_TIMEOUT); + if (!iob) + return -ENOMEM; + qeth_prepare_ipa_cmd(card, iob, (u16) data_len); memcpy(__ipa_cmd(iob), data, data_len); - return qeth_osn_send_ipa_cmd(card, iob); + iob->callback = qeth_osn_assist_cb; + return qeth_send_ipa_cmd(card, iob, NULL, NULL); } EXPORT_SYMBOL(qeth_osn_assist); @@ -1454,23 +1396,25 @@ static int qeth_bridgeport_makerc(struct qeth_card *card, static struct qeth_cmd_buffer *qeth_sbp_build_cmd(struct qeth_card *card, enum qeth_ipa_sbp_cmd sbp_cmd, - unsigned int cmd_length) + unsigned int data_length) { - enum qeth_ipa_cmds ipa_cmd = (card->info.type == QETH_CARD_TYPE_IQD) ? - IPA_CMD_SETBRIDGEPORT_IQD : - IPA_CMD_SETBRIDGEPORT_OSA; + enum qeth_ipa_cmds ipa_cmd = IS_IQD(card) ? IPA_CMD_SETBRIDGEPORT_IQD : + IPA_CMD_SETBRIDGEPORT_OSA; + struct qeth_ipacmd_sbp_hdr *hdr; struct qeth_cmd_buffer *iob; - struct qeth_ipa_cmd *cmd; - iob = qeth_get_ipacmd_buffer(card, ipa_cmd, 0); + iob = qeth_ipa_alloc_cmd(card, ipa_cmd, QETH_PROT_NONE, + data_length + + offsetof(struct qeth_ipacmd_setbridgeport, + data)); if (!iob) return iob; - cmd = __ipa_cmd(iob); - cmd->data.sbp.hdr.cmdlength = sizeof(struct qeth_ipacmd_sbp_hdr) + - cmd_length; - cmd->data.sbp.hdr.command_code = sbp_cmd; - cmd->data.sbp.hdr.used_total = 1; - cmd->data.sbp.hdr.seq_no = 1; + + hdr = &__ipa_cmd(iob)->data.sbp.hdr; + hdr->cmdlength = sizeof(*hdr) + data_length; + hdr->command_code = sbp_cmd; + hdr->used_total = 1; + hdr->seq_no = 1; return iob; } @@ -1505,7 +1449,7 @@ static void qeth_bridgeport_query_support(struct qeth_card *card) QETH_CARD_TEXT(card, 2, "brqsuppo"); iob = qeth_sbp_build_cmd(card, IPA_SBP_QUERY_COMMANDS_SUPPORTED, - sizeof(struct qeth_sbp_query_cmds_supp)); + SBP_DATA_SIZEOF(query_cmds_supp)); if (!iob) return; @@ -1597,23 +1541,21 @@ static int qeth_bridgeport_set_cb(struct qeth_card *card, */ int qeth_bridgeport_setrole(struct qeth_card *card, enum qeth_sbp_roles role) { - int cmdlength; struct qeth_cmd_buffer *iob; enum qeth_ipa_sbp_cmd setcmd; + unsigned int cmdlength = 0; QETH_CARD_TEXT(card, 2, "brsetrol"); switch (role) { case QETH_SBP_ROLE_NONE: setcmd = IPA_SBP_RESET_BRIDGE_PORT_ROLE; - cmdlength = sizeof(struct qeth_sbp_reset_role); break; case QETH_SBP_ROLE_PRIMARY: setcmd = IPA_SBP_SET_PRIMARY_BRIDGE_PORT; - cmdlength = sizeof(struct qeth_sbp_set_primary); + cmdlength = SBP_DATA_SIZEOF(set_primary); break; case QETH_SBP_ROLE_SECONDARY: setcmd = IPA_SBP_SET_SECONDARY_BRIDGE_PORT; - cmdlength = sizeof(struct qeth_sbp_set_secondary); break; default: return -EINVAL; @@ -1679,7 +1621,7 @@ static void qeth_bridgeport_an_set_cb(void *priv, l2entry = (struct qdio_brinfo_entry_l2 *)entry; code = IPA_ADDR_CHANGE_CODE_MACADDR; - if (l2entry->addr_lnid.lnid) + if (l2entry->addr_lnid.lnid < VLAN_N_VID) code |= IPA_ADDR_CHANGE_CODE_VLANID; qeth_bridge_emit_host_event(card, anev_reg_unreg, code, (struct net_if_token *)&l2entry->nit, @@ -1763,10 +1705,6 @@ static int qeth_l2_vnicc_makerc(struct qeth_card *card, u16 ipa_rc) struct _qeth_l2_vnicc_request_cbctl { u32 sub_cmd; struct { - u32 vnic_char; - u32 timeout; - } param; - struct { union{ u32 *sup_cmds; u32 *timeout; @@ -1788,80 +1726,52 @@ static int qeth_l2_vnicc_request_cb(struct qeth_card *card, if (cmd->hdr.return_code) return qeth_l2_vnicc_makerc(card, cmd->hdr.return_code); /* return results to caller */ - card->options.vnicc.sup_chars = rep->hdr.sup; - card->options.vnicc.cur_chars = rep->hdr.cur; + card->options.vnicc.sup_chars = rep->vnicc_cmds.supported; + card->options.vnicc.cur_chars = rep->vnicc_cmds.enabled; if (cbctl->sub_cmd == IPA_VNICC_QUERY_CMDS) - *cbctl->result.sup_cmds = rep->query_cmds.sup_cmds; + *cbctl->result.sup_cmds = rep->data.query_cmds.sup_cmds; if (cbctl->sub_cmd == IPA_VNICC_GET_TIMEOUT) - *cbctl->result.timeout = rep->getset_timeout.timeout; + *cbctl->result.timeout = rep->data.getset_timeout.timeout; return 0; } -/* generic VNICC request */ -static int qeth_l2_vnicc_request(struct qeth_card *card, - struct _qeth_l2_vnicc_request_cbctl *cbctl) +static struct qeth_cmd_buffer *qeth_l2_vnicc_build_cmd(struct qeth_card *card, + u32 vnicc_cmd, + unsigned int data_length) { - struct qeth_ipacmd_vnicc *req; + struct qeth_ipacmd_vnicc_hdr *hdr; struct qeth_cmd_buffer *iob; - struct qeth_ipa_cmd *cmd; - - QETH_CARD_TEXT(card, 2, "vniccreq"); - /* get new buffer for request */ - iob = qeth_get_ipacmd_buffer(card, IPA_CMD_VNICC, 0); + iob = qeth_ipa_alloc_cmd(card, IPA_CMD_VNICC, QETH_PROT_NONE, + data_length + + offsetof(struct qeth_ipacmd_vnicc, data)); if (!iob) - return -ENOMEM; - - /* create header for request */ - cmd = __ipa_cmd(iob); - req = &cmd->data.vnicc; + return NULL; - /* create sub command header for request */ - req->sub_hdr.data_length = sizeof(req->sub_hdr); - req->sub_hdr.sub_command = cbctl->sub_cmd; - - /* create sub command specific request fields */ - switch (cbctl->sub_cmd) { - case IPA_VNICC_QUERY_CHARS: - break; - case IPA_VNICC_QUERY_CMDS: - req->sub_hdr.data_length += sizeof(req->query_cmds); - req->query_cmds.vnic_char = cbctl->param.vnic_char; - break; - case IPA_VNICC_ENABLE: - case IPA_VNICC_DISABLE: - req->sub_hdr.data_length += sizeof(req->set_char); - req->set_char.vnic_char = cbctl->param.vnic_char; - break; - case IPA_VNICC_SET_TIMEOUT: - req->getset_timeout.timeout = cbctl->param.timeout; - /* fallthrough */ - case IPA_VNICC_GET_TIMEOUT: - req->sub_hdr.data_length += sizeof(req->getset_timeout); - req->getset_timeout.vnic_char = cbctl->param.vnic_char; - break; - default: - qeth_release_buffer(iob->channel, iob); - return -EOPNOTSUPP; - } - - /* send request */ - return qeth_send_ipa_cmd(card, iob, qeth_l2_vnicc_request_cb, cbctl); + hdr = &__ipa_cmd(iob)->data.vnicc.hdr; + hdr->data_length = sizeof(*hdr) + data_length; + hdr->sub_command = vnicc_cmd; + return iob; } /* VNICC query VNIC characteristics request */ static int qeth_l2_vnicc_query_chars(struct qeth_card *card) { struct _qeth_l2_vnicc_request_cbctl cbctl; + struct qeth_cmd_buffer *iob; + + QETH_CARD_TEXT(card, 2, "vniccqch"); + iob = qeth_l2_vnicc_build_cmd(card, IPA_VNICC_QUERY_CHARS, 0); + if (!iob) + return -ENOMEM; /* prepare callback control */ cbctl.sub_cmd = IPA_VNICC_QUERY_CHARS; - QETH_CARD_TEXT(card, 2, "vniccqch"); - return qeth_l2_vnicc_request(card, &cbctl); + return qeth_send_ipa_cmd(card, iob, qeth_l2_vnicc_request_cb, &cbctl); } /* VNICC query sub commands request */ @@ -1869,14 +1779,21 @@ static int qeth_l2_vnicc_query_cmds(struct qeth_card *card, u32 vnic_char, u32 *sup_cmds) { struct _qeth_l2_vnicc_request_cbctl cbctl; + struct qeth_cmd_buffer *iob; + + QETH_CARD_TEXT(card, 2, "vniccqcm"); + iob = qeth_l2_vnicc_build_cmd(card, IPA_VNICC_QUERY_CMDS, + VNICC_DATA_SIZEOF(query_cmds)); + if (!iob) + return -ENOMEM; + + __ipa_cmd(iob)->data.vnicc.data.query_cmds.vnic_char = vnic_char; /* prepare callback control */ cbctl.sub_cmd = IPA_VNICC_QUERY_CMDS; - cbctl.param.vnic_char = vnic_char; cbctl.result.sup_cmds = sup_cmds; - QETH_CARD_TEXT(card, 2, "vniccqcm"); - return qeth_l2_vnicc_request(card, &cbctl); + return qeth_send_ipa_cmd(card, iob, qeth_l2_vnicc_request_cb, &cbctl); } /* VNICC enable/disable characteristic request */ @@ -1884,31 +1801,47 @@ static int qeth_l2_vnicc_set_char(struct qeth_card *card, u32 vnic_char, u32 cmd) { struct _qeth_l2_vnicc_request_cbctl cbctl; + struct qeth_cmd_buffer *iob; + + QETH_CARD_TEXT(card, 2, "vniccedc"); + iob = qeth_l2_vnicc_build_cmd(card, cmd, VNICC_DATA_SIZEOF(set_char)); + if (!iob) + return -ENOMEM; + + __ipa_cmd(iob)->data.vnicc.data.set_char.vnic_char = vnic_char; /* prepare callback control */ cbctl.sub_cmd = cmd; - cbctl.param.vnic_char = vnic_char; - QETH_CARD_TEXT(card, 2, "vniccedc"); - return qeth_l2_vnicc_request(card, &cbctl); + return qeth_send_ipa_cmd(card, iob, qeth_l2_vnicc_request_cb, &cbctl); } /* VNICC get/set timeout for characteristic request */ static int qeth_l2_vnicc_getset_timeout(struct qeth_card *card, u32 vnicc, u32 cmd, u32 *timeout) { + struct qeth_vnicc_getset_timeout *getset_timeout; struct _qeth_l2_vnicc_request_cbctl cbctl; + struct qeth_cmd_buffer *iob; + + QETH_CARD_TEXT(card, 2, "vniccgst"); + iob = qeth_l2_vnicc_build_cmd(card, cmd, + VNICC_DATA_SIZEOF(getset_timeout)); + if (!iob) + return -ENOMEM; + + getset_timeout = &__ipa_cmd(iob)->data.vnicc.data.getset_timeout; + getset_timeout->vnic_char = vnicc; + + if (cmd == IPA_VNICC_SET_TIMEOUT) + getset_timeout->timeout = *timeout; /* prepare callback control */ cbctl.sub_cmd = cmd; - cbctl.param.vnic_char = vnicc; - if (cmd == IPA_VNICC_SET_TIMEOUT) - cbctl.param.timeout = *timeout; if (cmd == IPA_VNICC_GET_TIMEOUT) cbctl.result.timeout = timeout; - QETH_CARD_TEXT(card, 2, "vniccgst"); - return qeth_l2_vnicc_request(card, &cbctl); + return qeth_send_ipa_cmd(card, iob, qeth_l2_vnicc_request_cb, &cbctl); } /* set current VNICC flag state; called from sysfs store function */ diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 53712cf26406..2dd99f103671 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -32,7 +32,6 @@ #include <net/route.h> #include <net/ipv6.h> #include <net/ip6_route.h> -#include <net/ip6_fib.h> #include <net/iucv/af_iucv.h> #include <linux/hashtable.h> @@ -246,9 +245,9 @@ static int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) */ if (addr->proto == QETH_PROT_IPV4) { addr->in_progress = 1; - spin_unlock_bh(&card->ip_lock); + mutex_unlock(&card->ip_lock); rc = qeth_l3_register_addr_entry(card, addr); - spin_lock_bh(&card->ip_lock); + mutex_lock(&card->ip_lock); addr->in_progress = 0; } else rc = qeth_l3_register_addr_entry(card, addr); @@ -268,6 +267,30 @@ static int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) return rc; } +static int qeth_l3_modify_ip(struct qeth_card *card, struct qeth_ipaddr *addr, + bool add) +{ + int rc; + + mutex_lock(&card->ip_lock); + rc = add ? qeth_l3_add_ip(card, addr) : qeth_l3_delete_ip(card, addr); + mutex_unlock(&card->ip_lock); + + return rc; +} + +static void qeth_l3_drain_rx_mode_cache(struct qeth_card *card) +{ + struct qeth_ipaddr *addr; + struct hlist_node *tmp; + int i; + + hash_for_each_safe(card->ip_mc_htable, i, tmp, addr, hnode) { + hash_del(&addr->hnode); + kfree(addr); + } +} + static void qeth_l3_clear_ip_htable(struct qeth_card *card, int recover) { struct qeth_ipaddr *addr; @@ -276,7 +299,7 @@ static void qeth_l3_clear_ip_htable(struct qeth_card *card, int recover) QETH_CARD_TEXT(card, 4, "clearip"); - spin_lock_bh(&card->ip_lock); + mutex_lock(&card->ip_lock); hash_for_each_safe(card->ip_htable, i, tmp, addr, hnode) { if (!recover) { @@ -287,19 +310,9 @@ static void qeth_l3_clear_ip_htable(struct qeth_card *card, int recover) addr->disp_flag = QETH_DISP_ADDR_ADD; } - spin_unlock_bh(&card->ip_lock); - - spin_lock_bh(&card->mclock); - - hash_for_each_safe(card->ip_mc_htable, i, tmp, addr, hnode) { - hash_del(&addr->hnode); - kfree(addr); - } - - spin_unlock_bh(&card->mclock); - - + mutex_unlock(&card->ip_lock); } + static void qeth_l3_recover_ip(struct qeth_card *card) { struct qeth_ipaddr *addr; @@ -309,15 +322,15 @@ static void qeth_l3_recover_ip(struct qeth_card *card) QETH_CARD_TEXT(card, 4, "recovrip"); - spin_lock_bh(&card->ip_lock); + mutex_lock(&card->ip_lock); hash_for_each_safe(card->ip_htable, i, tmp, addr, hnode) { if (addr->disp_flag == QETH_DISP_ADDR_ADD) { if (addr->proto == QETH_PROT_IPV4) { addr->in_progress = 1; - spin_unlock_bh(&card->ip_lock); + mutex_unlock(&card->ip_lock); rc = qeth_l3_register_addr_entry(card, addr); - spin_lock_bh(&card->ip_lock); + mutex_lock(&card->ip_lock); addr->in_progress = 0; } else rc = qeth_l3_register_addr_entry(card, addr); @@ -333,8 +346,7 @@ static void qeth_l3_recover_ip(struct qeth_card *card) } } - spin_unlock_bh(&card->ip_lock); - + mutex_unlock(&card->ip_lock); } static int qeth_l3_setdelip_cb(struct qeth_card *card, struct qeth_reply *reply, @@ -364,7 +376,8 @@ static int qeth_l3_send_setdelmc(struct qeth_card *card, QETH_CARD_TEXT(card, 4, "setdelmc"); - iob = qeth_get_ipacmd_buffer(card, ipacmd, addr->proto); + iob = qeth_ipa_alloc_cmd(card, ipacmd, addr->proto, + IPA_DATA_SIZEOF(setdelipm)); if (!iob) return -ENOMEM; cmd = __ipa_cmd(iob); @@ -416,7 +429,8 @@ static int qeth_l3_send_setdelip(struct qeth_card *card, QETH_CARD_TEXT(card, 4, "setdelip"); - iob = qeth_get_ipacmd_buffer(card, ipacmd, addr->proto); + iob = qeth_ipa_alloc_cmd(card, ipacmd, addr->proto, + IPA_DATA_SIZEOF(setdelip6)); if (!iob) return -ENOMEM; cmd = __ipa_cmd(iob); @@ -448,7 +462,8 @@ static int qeth_l3_send_setrouting(struct qeth_card *card, struct qeth_cmd_buffer *iob; QETH_CARD_TEXT(card, 4, "setroutg"); - iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SETRTG, prot); + iob = qeth_ipa_alloc_cmd(card, IPA_CMD_SETRTG, prot, + IPA_DATA_SIZEOF(setrtg)); if (!iob) return -ENOMEM; cmd = __ipa_cmd(iob); @@ -461,7 +476,7 @@ static int qeth_l3_send_setrouting(struct qeth_card *card, static int qeth_l3_correct_routing_type(struct qeth_card *card, enum qeth_routing_types *type, enum qeth_prot_versions prot) { - if (card->info.type == QETH_CARD_TYPE_IQD) { + if (IS_IQD(card)) { switch (*type) { case NO_ROUTER: case PRIMARY_CONNECTOR: @@ -559,7 +574,7 @@ static void qeth_l3_clear_ipato_list(struct qeth_card *card) { struct qeth_ipato_entry *ipatoe, *tmp; - spin_lock_bh(&card->ip_lock); + mutex_lock(&card->ip_lock); list_for_each_entry_safe(ipatoe, tmp, &card->ipato.entries, entry) { list_del(&ipatoe->entry); @@ -567,7 +582,7 @@ static void qeth_l3_clear_ipato_list(struct qeth_card *card) } qeth_l3_update_ipato(card); - spin_unlock_bh(&card->ip_lock); + mutex_unlock(&card->ip_lock); } int qeth_l3_add_ipato_entry(struct qeth_card *card, @@ -578,7 +593,7 @@ int qeth_l3_add_ipato_entry(struct qeth_card *card, QETH_CARD_TEXT(card, 2, "addipato"); - spin_lock_bh(&card->ip_lock); + mutex_lock(&card->ip_lock); list_for_each_entry(ipatoe, &card->ipato.entries, entry) { if (ipatoe->proto != new->proto) @@ -596,7 +611,7 @@ int qeth_l3_add_ipato_entry(struct qeth_card *card, qeth_l3_update_ipato(card); } - spin_unlock_bh(&card->ip_lock); + mutex_unlock(&card->ip_lock); return rc; } @@ -610,7 +625,7 @@ int qeth_l3_del_ipato_entry(struct qeth_card *card, QETH_CARD_TEXT(card, 2, "delipato"); - spin_lock_bh(&card->ip_lock); + mutex_lock(&card->ip_lock); list_for_each_entry_safe(ipatoe, tmp, &card->ipato.entries, entry) { if (ipatoe->proto != proto) @@ -625,7 +640,7 @@ int qeth_l3_del_ipato_entry(struct qeth_card *card, } } - spin_unlock_bh(&card->ip_lock); + mutex_unlock(&card->ip_lock); return rc; } @@ -634,7 +649,6 @@ int qeth_l3_modify_rxip_vipa(struct qeth_card *card, bool add, const u8 *ip, enum qeth_prot_versions proto) { struct qeth_ipaddr addr; - int rc; qeth_l3_init_ipaddr(&addr, type, proto); if (proto == QETH_PROT_IPV4) @@ -642,16 +656,13 @@ int qeth_l3_modify_rxip_vipa(struct qeth_card *card, bool add, const u8 *ip, else memcpy(&addr.u.a6.addr, ip, 16); - spin_lock_bh(&card->ip_lock); - rc = add ? qeth_l3_add_ip(card, &addr) : qeth_l3_delete_ip(card, &addr); - spin_unlock_bh(&card->ip_lock); - return rc; + return qeth_l3_modify_ip(card, &addr, add); } int qeth_l3_modify_hsuid(struct qeth_card *card, bool add) { struct qeth_ipaddr addr; - int rc, i; + unsigned int i; qeth_l3_init_ipaddr(&addr, QETH_IP_TYPE_NORMAL, QETH_PROT_IPV6); addr.u.a6.addr.s6_addr[0] = 0xfe; @@ -659,10 +670,7 @@ int qeth_l3_modify_hsuid(struct qeth_card *card, bool add) for (i = 0; i < 8; i++) addr.u.a6.addr.s6_addr[8+i] = card->options.hsuid[i]; - spin_lock_bh(&card->ip_lock); - rc = add ? qeth_l3_add_ip(card, &addr) : qeth_l3_delete_ip(card, &addr); - spin_unlock_bh(&card->ip_lock); - return rc; + return qeth_l3_modify_ip(card, &addr, add); } static int qeth_l3_register_addr_entry(struct qeth_card *card, @@ -736,7 +744,7 @@ static int qeth_l3_setadapter_parms(struct qeth_card *card) { int rc = 0; - QETH_DBF_TEXT(SETUP, 2, "setadprm"); + QETH_CARD_TEXT(card, 2, "setadprm"); if (qeth_adp_supported(card, IPA_SETADP_ALTER_MAC_ADDRESS)) { rc = qeth_setadpparms_change_macaddr(card); @@ -761,7 +769,7 @@ static int qeth_l3_start_ipa_arp_processing(struct qeth_card *card) return 0; } rc = qeth_send_simple_setassparms(card, IPA_ARP_PROCESSING, - IPA_CMD_ASS_START, 0); + IPA_CMD_ASS_START, NULL); if (rc) { dev_warn(&card->gdev->dev, "Starting ARP processing support for %s failed\n", @@ -784,7 +792,7 @@ static int qeth_l3_start_ipa_source_mac(struct qeth_card *card) } rc = qeth_send_simple_setassparms(card, IPA_SOURCE_MAC, - IPA_CMD_ASS_START, 0); + IPA_CMD_ASS_START, NULL); if (rc) dev_warn(&card->gdev->dev, "Starting source MAC-address support for %s failed\n", @@ -805,7 +813,7 @@ static int qeth_l3_start_ipa_vlan(struct qeth_card *card) } rc = qeth_send_simple_setassparms(card, IPA_VLAN_PRIO, - IPA_CMD_ASS_START, 0); + IPA_CMD_ASS_START, NULL); if (rc) { dev_warn(&card->gdev->dev, "Starting VLAN support for %s failed\n", @@ -830,7 +838,7 @@ static int qeth_l3_start_ipa_multicast(struct qeth_card *card) } rc = qeth_send_simple_setassparms(card, IPA_MULTICASTING, - IPA_CMD_ASS_START, 0); + IPA_CMD_ASS_START, NULL); if (rc) { dev_warn(&card->gdev->dev, "Starting multicast support for %s failed\n", @@ -844,23 +852,24 @@ static int qeth_l3_start_ipa_multicast(struct qeth_card *card) static int qeth_l3_softsetup_ipv6(struct qeth_card *card) { + u32 ipv6_data = 3; int rc; QETH_CARD_TEXT(card, 3, "softipv6"); - if (card->info.type == QETH_CARD_TYPE_IQD) + if (IS_IQD(card)) goto out; - rc = qeth_send_simple_setassparms(card, IPA_IPV6, - IPA_CMD_ASS_START, 3); + rc = qeth_send_simple_setassparms(card, IPA_IPV6, IPA_CMD_ASS_START, + &ipv6_data); if (rc) { dev_err(&card->gdev->dev, "Activating IPv6 support for %s failed\n", QETH_CARD_IFNAME(card)); return rc; } - rc = qeth_send_simple_setassparms_v6(card, IPA_IPV6, - IPA_CMD_ASS_START, 0); + rc = qeth_send_simple_setassparms_v6(card, IPA_IPV6, IPA_CMD_ASS_START, + NULL); if (rc) { dev_err(&card->gdev->dev, "Activating IPv6 support for %s failed\n", @@ -868,7 +877,7 @@ static int qeth_l3_softsetup_ipv6(struct qeth_card *card) return rc; } rc = qeth_send_simple_setassparms_v6(card, IPA_PASSTHRU, - IPA_CMD_ASS_START, 0); + IPA_CMD_ASS_START, NULL); if (rc) { dev_warn(&card->gdev->dev, "Enabling the passthrough mode for %s failed\n", @@ -894,6 +903,7 @@ static int qeth_l3_start_ipa_ipv6(struct qeth_card *card) static int qeth_l3_start_ipa_broadcast(struct qeth_card *card) { + u32 filter_data = 1; int rc; QETH_CARD_TEXT(card, 3, "stbrdcst"); @@ -906,7 +916,7 @@ static int qeth_l3_start_ipa_broadcast(struct qeth_card *card) goto out; } rc = qeth_send_simple_setassparms(card, IPA_FILTERING, - IPA_CMD_ASS_START, 0); + IPA_CMD_ASS_START, NULL); if (rc) { dev_warn(&card->gdev->dev, "Enabling broadcast filtering for " "%s failed\n", QETH_CARD_IFNAME(card)); @@ -914,7 +924,7 @@ static int qeth_l3_start_ipa_broadcast(struct qeth_card *card) } rc = qeth_send_simple_setassparms(card, IPA_FILTERING, - IPA_CMD_ASS_CONFIGURE, 1); + IPA_CMD_ASS_CONFIGURE, &filter_data); if (rc) { dev_warn(&card->gdev->dev, "Setting up broadcast filtering for %s failed\n", @@ -924,7 +934,7 @@ static int qeth_l3_start_ipa_broadcast(struct qeth_card *card) card->info.broadcast_capable = QETH_BROADCAST_WITH_ECHO; dev_info(&card->gdev->dev, "Broadcast enabled\n"); rc = qeth_send_simple_setassparms(card, IPA_FILTERING, - IPA_CMD_ASS_ENABLE, 1); + IPA_CMD_ASS_ENABLE, &filter_data); if (rc) { dev_warn(&card->gdev->dev, "Setting up broadcast echo " "filtering for %s failed\n", QETH_CARD_IFNAME(card)); @@ -973,10 +983,10 @@ static int qeth_l3_iqd_read_initial_mac(struct qeth_card *card) struct qeth_cmd_buffer *iob; struct qeth_ipa_cmd *cmd; - QETH_DBF_TEXT(SETUP, 2, "hsrmac"); + QETH_CARD_TEXT(card, 2, "hsrmac"); - iob = qeth_get_ipacmd_buffer(card, IPA_CMD_CREATE_ADDR, - QETH_PROT_IPV6); + iob = qeth_ipa_alloc_cmd(card, IPA_CMD_CREATE_ADDR, QETH_PROT_IPV6, + IPA_DATA_SIZEOF(create_destroy_addr)); if (!iob) return -ENOMEM; cmd = __ipa_cmd(iob); @@ -1011,7 +1021,7 @@ static int qeth_l3_get_unique_id(struct qeth_card *card) struct qeth_cmd_buffer *iob; struct qeth_ipa_cmd *cmd; - QETH_DBF_TEXT(SETUP, 2, "guniqeid"); + QETH_CARD_TEXT(card, 2, "guniqeid"); if (!qeth_is_supported(card, IPA_IPV6)) { card->info.unique_id = UNIQUE_ID_IF_CREATE_ADDR_FAILED | @@ -1019,8 +1029,8 @@ static int qeth_l3_get_unique_id(struct qeth_card *card) return 0; } - iob = qeth_get_ipacmd_buffer(card, IPA_CMD_CREATE_ADDR, - QETH_PROT_IPV6); + iob = qeth_ipa_alloc_cmd(card, IPA_CMD_CREATE_ADDR, QETH_PROT_IPV6, + IPA_DATA_SIZEOF(create_destroy_addr)); if (!iob) return -ENOMEM; cmd = __ipa_cmd(iob); @@ -1038,7 +1048,7 @@ qeth_diags_trace_cb(struct qeth_card *card, struct qeth_reply *reply, struct qeth_ipa_cmd *cmd; __u16 rc; - QETH_DBF_TEXT(SETUP, 2, "diastrcb"); + QETH_CARD_TEXT(card, 2, "diastrcb"); cmd = (struct qeth_ipa_cmd *)data; rc = cmd->hdr.return_code; @@ -1094,14 +1104,12 @@ qeth_diags_trace(struct qeth_card *card, enum qeth_diags_trace_cmds diags_cmd) struct qeth_cmd_buffer *iob; struct qeth_ipa_cmd *cmd; - QETH_DBF_TEXT(SETUP, 2, "diagtrac"); + QETH_CARD_TEXT(card, 2, "diagtrac"); - iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SET_DIAG_ASS, 0); + iob = qeth_get_diag_cmd(card, QETH_DIAGS_CMD_TRACE, 0); if (!iob) return -ENOMEM; cmd = __ipa_cmd(iob); - cmd->data.diagass.subcmd_len = 16; - cmd->data.diagass.subcmd = QETH_DIAGS_CMD_TRACE; cmd->data.diagass.type = QETH_DIAGS_TYPE_HIPERSOCKET; cmd->data.diagass.action = diags_cmd; return qeth_send_ipa_cmd(card, iob, qeth_diags_trace_cb, NULL); @@ -1303,6 +1311,15 @@ static int qeth_l3_vlan_rx_kill_vid(struct net_device *dev, static void qeth_l3_rebuild_skb(struct qeth_card *card, struct sk_buff *skb, struct qeth_hdr *hdr) { + struct af_iucv_trans_hdr *iucv = (struct af_iucv_trans_hdr *) skb->data; + struct net_device *dev = skb->dev; + + if (IS_IQD(card) && iucv->magic == ETH_P_AF_IUCV) { + dev_hard_header(skb, dev, ETH_P_AF_IUCV, dev->dev_addr, + "FAKELL", skb->len); + return; + } + if (!(hdr->hdr.l3.flags & QETH_HDR_PASSTHRU)) { u16 prot = (hdr->hdr.l3.flags & QETH_HDR_IPV6) ? ETH_P_IPV6 : ETH_P_IP; @@ -1336,8 +1353,6 @@ static void qeth_l3_rebuild_skb(struct qeth_card *card, struct sk_buff *skb, tg_addr, "FAKELL", skb->len); } - skb->protocol = eth_type_trans(skb, card->dev); - /* copy VLAN tag from hdr into skb */ if (!card->options.sniffer && (hdr->hdr.l3.ext_flags & (QETH_HDR_EXT_VLAN_FRAME | @@ -1354,12 +1369,10 @@ static void qeth_l3_rebuild_skb(struct qeth_card *card, struct sk_buff *skb, static int qeth_l3_process_inbound_buffer(struct qeth_card *card, int budget, int *done) { - struct net_device *dev = card->dev; int work_done = 0; struct sk_buff *skb; struct qeth_hdr *hdr; unsigned int len; - __u16 magic; *done = 0; WARN_ON_ONCE(!budget); @@ -1373,24 +1386,12 @@ static int qeth_l3_process_inbound_buffer(struct qeth_card *card, } switch (hdr->hdr.l3.id) { case QETH_HEADER_TYPE_LAYER3: - magic = *(__u16 *)skb->data; - if ((card->info.type == QETH_CARD_TYPE_IQD) && - (magic == ETH_P_AF_IUCV)) { - len = skb->len; - dev_hard_header(skb, dev, ETH_P_AF_IUCV, - dev->dev_addr, "FAKELL", len); - skb->protocol = eth_type_trans(skb, dev); - netif_receive_skb(skb); - } else { - qeth_l3_rebuild_skb(card, skb, hdr); - len = skb->len; - napi_gro_receive(&card->napi, skb); - } - break; + qeth_l3_rebuild_skb(card, skb, hdr); + /* fall through */ case QETH_HEADER_TYPE_LAYER2: /* for HiperSockets sniffer */ skb->protocol = eth_type_trans(skb, skb->dev); len = skb->len; - netif_receive_skb(skb); + napi_gro_receive(&card->napi, skb); break; default: dev_kfree_skb_any(skb); @@ -1408,11 +1409,13 @@ static int qeth_l3_process_inbound_buffer(struct qeth_card *card, static void qeth_l3_stop_card(struct qeth_card *card) { - QETH_DBF_TEXT(SETUP, 2, "stopcard"); - QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *)); + QETH_CARD_TEXT(card, 2, "stopcard"); qeth_set_allowed_threads(card, 0, 1); + cancel_work_sync(&card->rx_mode_work); + qeth_l3_drain_rx_mode_cache(card); + if (card->options.sniffer && (card->info.promisc_mode == SET_PROMISC_MODE_ON)) qeth_diags_trace(card, QETH_DIAGS_CMD_TRACE_DISABLE); @@ -1424,14 +1427,10 @@ static void qeth_l3_stop_card(struct qeth_card *card) } if (card->state == CARD_STATE_HARDSETUP) { qeth_qdio_clear_card(card, 0); - qeth_clear_qdio_buffers(card); + qeth_drain_output_queues(card); qeth_clear_working_pool_list(card); card->state = CARD_STATE_DOWN; } - if (card->state == CARD_STATE_DOWN) { - qeth_clear_cmd_buffers(&card->read); - qeth_clear_cmd_buffers(&card->write); - } flush_workqueue(card->event_wq); } @@ -1451,7 +1450,7 @@ qeth_l3_handle_promisc_mode(struct qeth_card *card) (card->info.promisc_mode == SET_PROMISC_MODE_OFF))) return; - if (card->info.guestlan) { /* Guestlan trace */ + if (IS_VM_NIC(card)) { /* Guestlan trace */ if (qeth_adp_supported(card, IPA_SETADP_SET_PROMISC_MODE)) qeth_setadp_promisc_mode(card); } else if (card->options.sniffer && /* HiperSockets trace */ @@ -1466,9 +1465,10 @@ qeth_l3_handle_promisc_mode(struct qeth_card *card) } } -static void qeth_l3_set_rx_mode(struct net_device *dev) +static void qeth_l3_rx_mode_work(struct work_struct *work) { - struct qeth_card *card = dev->ml_priv; + struct qeth_card *card = container_of(work, struct qeth_card, + rx_mode_work); struct qeth_ipaddr *addr; struct hlist_node *tmp; int i, rc; @@ -1476,8 +1476,6 @@ static void qeth_l3_set_rx_mode(struct net_device *dev) QETH_CARD_TEXT(card, 3, "setmulti"); if (!card->options.sniffer) { - spin_lock_bh(&card->mclock); - qeth_l3_add_multicast_ipv4(card); qeth_l3_add_multicast_ipv6(card); @@ -1505,8 +1503,6 @@ static void qeth_l3_set_rx_mode(struct net_device *dev) } } - spin_unlock_bh(&card->mclock); - if (!qeth_adp_supported(card, IPA_SETADP_SET_PROMISC_MODE)) return; } @@ -1551,14 +1547,15 @@ static int qeth_l3_arp_set_no_entries(struct qeth_card *card, int no_entries) * IPA_CMD_ASS_ARP_QUERY_INFO, but not IPA_CMD_ASS_ARP_SET_NO_ENTRIES; * thus we say EOPNOTSUPP for this ARP function */ - if (card->info.guestlan) + if (IS_VM_NIC(card)) return -EOPNOTSUPP; if (!qeth_is_supported(card, IPA_ARP_PROCESSING)) { return -EOPNOTSUPP; } iob = qeth_get_setassparms_cmd(card, IPA_ARP_PROCESSING, - IPA_CMD_ASS_ARP_SET_NO_ENTRIES, 4, + IPA_CMD_ASS_ARP_SET_NO_ENTRIES, + SETASS_DATA_SIZEOF(flags_32bit), QETH_PROT_IPV4); if (!iob) return -ENOMEM; @@ -1704,9 +1701,7 @@ static int qeth_l3_query_arp_cache_info(struct qeth_card *card, iob = qeth_get_setassparms_cmd(card, IPA_ARP_PROCESSING, IPA_CMD_ASS_ARP_QUERY_INFO, - sizeof(struct qeth_arp_query_data) - - sizeof(char), - prot); + SETASS_DATA_SIZEOF(query_arp), prot); if (!iob) return -ENOMEM; cmd = __ipa_cmd(iob); @@ -1783,14 +1778,15 @@ static int qeth_l3_arp_modify_entry(struct qeth_card *card, * IPA_CMD_ASS_ARP_QUERY_INFO, but not IPA_CMD_ASS_ARP_ADD_ENTRY; * thus we say EOPNOTSUPP for this ARP function */ - if (card->info.guestlan) + if (IS_VM_NIC(card)) return -EOPNOTSUPP; if (!qeth_is_supported(card, IPA_ARP_PROCESSING)) { return -EOPNOTSUPP; } iob = qeth_get_setassparms_cmd(card, IPA_ARP_PROCESSING, arp_cmd, - sizeof(*cmd_entry), QETH_PROT_IPV4); + SETASS_DATA_SIZEOF(arp_entry), + QETH_PROT_IPV4); if (!iob) return -ENOMEM; @@ -1816,7 +1812,7 @@ static int qeth_l3_arp_flush_cache(struct qeth_card *card) * IPA_CMD_ASS_ARP_QUERY_INFO, but not IPA_CMD_ASS_ARP_FLUSH_CACHE; * thus we say EOPNOTSUPP for this ARP function */ - if (card->info.guestlan || (card->info.type == QETH_CARD_TYPE_IQD)) + if (IS_VM_NIC(card) || IS_IQD(card)) return -EOPNOTSUPP; if (!qeth_is_supported(card, IPA_ARP_PROCESSING)) { return -EOPNOTSUPP; @@ -1881,19 +1877,17 @@ static int qeth_l3_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) return rc; } -static int qeth_l3_get_cast_type(struct sk_buff *skb) +static int qeth_l3_get_cast_type_rcu(struct sk_buff *skb, struct dst_entry *dst, + int ipv) { struct neighbour *n = NULL; - struct dst_entry *dst; - rcu_read_lock(); - dst = skb_dst(skb); if (dst) n = dst_neigh_lookup_skb(dst, skb); + if (n) { int cast_type = n->type; - rcu_read_unlock(); neigh_release(n); if ((cast_type == RTN_BROADCAST) || (cast_type == RTN_MULTICAST) || @@ -1901,11 +1895,12 @@ static int qeth_l3_get_cast_type(struct sk_buff *skb) return cast_type; return RTN_UNICAST; } - rcu_read_unlock(); /* no neighbour (eg AF_PACKET), fall back to target's IP address ... */ - switch (qeth_get_ip_version(skb)) { + switch (ipv) { case 4: + if (ipv4_is_lbcast(ip_hdr(skb)->daddr)) + return RTN_BROADCAST; return ipv4_is_multicast(ip_hdr(skb)->daddr) ? RTN_MULTICAST : RTN_UNICAST; case 6: @@ -1913,16 +1908,24 @@ static int qeth_l3_get_cast_type(struct sk_buff *skb) RTN_MULTICAST : RTN_UNICAST; default: /* ... and MAC address */ - if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, - skb->dev->broadcast)) - return RTN_BROADCAST; - if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) - return RTN_MULTICAST; - /* default to unicast */ - return RTN_UNICAST; + return qeth_get_ether_cast_type(skb); } } +static int qeth_l3_get_cast_type(struct sk_buff *skb) +{ + int ipv = qeth_get_ip_version(skb); + struct dst_entry *dst; + int cast_type; + + rcu_read_lock(); + dst = qeth_dst_check_rcu(skb, ipv); + cast_type = qeth_l3_get_cast_type_rcu(skb, dst, ipv); + rcu_read_unlock(); + + return cast_type; +} + static u8 qeth_l3_cast_type_to_flag(int cast_type) { if (cast_type == RTN_MULTICAST) @@ -1936,11 +1939,13 @@ static u8 qeth_l3_cast_type_to_flag(int cast_type) static void qeth_l3_fill_header(struct qeth_qdio_out_q *queue, struct qeth_hdr *hdr, struct sk_buff *skb, - int ipv, int cast_type, unsigned int data_len) + int ipv, unsigned int data_len) { struct qeth_hdr_layer3 *l3_hdr = &hdr->hdr.l3; struct vlan_ethhdr *veth = vlan_eth_hdr(skb); struct qeth_card *card = queue->card; + struct dst_entry *dst; + int cast_type; hdr->hdr.l3.length = data_len; @@ -1977,29 +1982,23 @@ static void qeth_l3_fill_header(struct qeth_qdio_out_q *queue, hdr->hdr.l3.vlan_id = ntohs(veth->h_vlan_TCI); } - /* OSA only: */ - if (!ipv) { - hdr->hdr.l3.flags = QETH_HDR_PASSTHRU; - if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, - skb->dev->broadcast)) - hdr->hdr.l3.flags |= QETH_CAST_BROADCAST; - else - hdr->hdr.l3.flags |= (cast_type == RTN_MULTICAST) ? - QETH_CAST_MULTICAST : QETH_CAST_UNICAST; - return; - } - - hdr->hdr.l3.flags = qeth_l3_cast_type_to_flag(cast_type); rcu_read_lock(); + dst = qeth_dst_check_rcu(skb, ipv); + + if (IS_IQD(card) && skb_get_queue_mapping(skb) != QETH_IQD_MCAST_TXQ) + cast_type = RTN_UNICAST; + else + cast_type = qeth_l3_get_cast_type_rcu(skb, dst, ipv); + l3_hdr->flags |= qeth_l3_cast_type_to_flag(cast_type); + if (ipv == 4) { - struct rtable *rt = skb_rtable(skb); + struct rtable *rt = (struct rtable *) dst; *((__be32 *) &hdr->hdr.l3.next_hop.ipv4.addr) = (rt) ? rt_nexthop(rt, ip_hdr(skb)->daddr) : ip_hdr(skb)->daddr; - } else { - /* IPv6 */ - const struct rt6_info *rt = skb_rt6_info(skb); + } else if (ipv == 6) { + struct rt6_info *rt = (struct rt6_info *) dst; if (rt && !ipv6_addr_any(&rt->rt6i_gateway)) l3_hdr->next_hop.ipv6_addr = rt->rt6i_gateway; @@ -2007,8 +2006,11 @@ static void qeth_l3_fill_header(struct qeth_qdio_out_q *queue, l3_hdr->next_hop.ipv6_addr = ipv6_hdr(skb)->daddr; hdr->hdr.l3.flags |= QETH_HDR_IPV6; - if (card->info.type != QETH_CARD_TYPE_IQD) + if (!IS_IQD(card)) hdr->hdr.l3.flags |= QETH_HDR_PASSTHRU; + } else { + /* OSA only: */ + l3_hdr->flags |= QETH_HDR_PASSTHRU; } rcu_read_unlock(); } @@ -2028,9 +2030,8 @@ static void qeth_l3_fixup_headers(struct sk_buff *skb) } static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb, - struct qeth_qdio_out_q *queue, int ipv, int cast_type) + struct qeth_qdio_out_q *queue, int ipv) { - unsigned char eth_hdr[ETH_HLEN]; unsigned int hw_hdr_len; int rc; @@ -2040,67 +2041,63 @@ static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb, rc = skb_cow_head(skb, hw_hdr_len - ETH_HLEN); if (rc) return rc; - skb_copy_from_linear_data(skb, eth_hdr, ETH_HLEN); skb_pull(skb, ETH_HLEN); qeth_l3_fixup_headers(skb); - rc = qeth_xmit(card, skb, queue, ipv, cast_type, qeth_l3_fill_header); - if (rc == -EBUSY) { - /* roll back to ETH header */ - skb_push(skb, ETH_HLEN); - skb_copy_to_linear_data(skb, eth_hdr, ETH_HLEN); - } - return rc; + return qeth_xmit(card, skb, queue, ipv, qeth_l3_fill_header); } static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) { - int cast_type = qeth_l3_get_cast_type(skb); struct qeth_card *card = dev->ml_priv; + u16 txq = skb_get_queue_mapping(skb); int ipv = qeth_get_ip_version(skb); struct qeth_qdio_out_q *queue; int tx_bytes = skb->len; int rc; - queue = qeth_get_tx_queue(card, skb, ipv, cast_type); - if (IS_IQD(card)) { + queue = card->qdio.out_qs[qeth_iqd_translate_txq(dev, txq)]; + if (card->options.sniffer) goto tx_drop; if ((card->options.cq != QETH_CQ_ENABLED && !ipv) || (card->options.cq == QETH_CQ_ENABLED && skb->protocol != htons(ETH_P_AF_IUCV))) goto tx_drop; + } else { + queue = card->qdio.out_qs[txq]; } - if (cast_type == RTN_BROADCAST && !card->info.broadcast_capable) + if (!(dev->flags & IFF_BROADCAST) && + qeth_l3_get_cast_type(skb) == RTN_BROADCAST) goto tx_drop; - netif_stop_queue(dev); - if (ipv == 4 || IS_IQD(card)) - rc = qeth_l3_xmit(card, skb, queue, ipv, cast_type); + rc = qeth_l3_xmit(card, skb, queue, ipv); else - rc = qeth_xmit(card, skb, queue, ipv, cast_type, - qeth_l3_fill_header); + rc = qeth_xmit(card, skb, queue, ipv, qeth_l3_fill_header); if (!rc) { QETH_TXQ_STAT_INC(queue, tx_packets); QETH_TXQ_STAT_ADD(queue, tx_bytes, tx_bytes); - netif_wake_queue(dev); return NETDEV_TX_OK; - } else if (rc == -EBUSY) { - return NETDEV_TX_BUSY; - } /* else fall through */ + } tx_drop: QETH_TXQ_STAT_INC(queue, tx_dropped); kfree_skb(skb); - netif_wake_queue(dev); return NETDEV_TX_OK; } +static void qeth_l3_set_rx_mode(struct net_device *dev) +{ + struct qeth_card *card = dev->ml_priv; + + schedule_work(&card->rx_mode_work); +} + /* * we need NOARP for IPv4 but we want neighbor solicitation for IPv6. Setting * NOARP on the netdevice is no option because it also turns off neighbor @@ -2134,11 +2131,27 @@ static netdev_features_t qeth_l3_osa_features_check(struct sk_buff *skb, return qeth_features_check(skb, dev, features); } +static u16 qeth_l3_iqd_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev) +{ + return qeth_iqd_select_queue(dev, skb, qeth_l3_get_cast_type(skb), + sb_dev); +} + +static u16 qeth_l3_osa_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev) +{ + struct qeth_card *card = dev->ml_priv; + + return qeth_get_priority_queue(card, skb); +} + static const struct net_device_ops qeth_l3_netdev_ops = { .ndo_open = qeth_open, .ndo_stop = qeth_stop, .ndo_get_stats64 = qeth_get_stats64, .ndo_start_xmit = qeth_l3_hard_start_xmit, + .ndo_select_queue = qeth_l3_iqd_select_queue, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = qeth_l3_set_rx_mode, .ndo_do_ioctl = qeth_do_ioctl, @@ -2155,6 +2168,7 @@ static const struct net_device_ops qeth_l3_osa_netdev_ops = { .ndo_get_stats64 = qeth_get_stats64, .ndo_start_xmit = qeth_l3_hard_start_xmit, .ndo_features_check = qeth_l3_osa_features_check, + .ndo_select_queue = qeth_l3_osa_select_queue, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = qeth_l3_set_rx_mode, .ndo_do_ioctl = qeth_do_ioctl, @@ -2171,8 +2185,7 @@ static int qeth_l3_setup_netdev(struct qeth_card *card, bool carrier_ok) unsigned int headroom; int rc; - if (card->info.type == QETH_CARD_TYPE_OSD || - card->info.type == QETH_CARD_TYPE_OSX) { + if (IS_OSD(card) || IS_OSX(card)) { if ((card->info.link_type == QETH_LINK_TYPE_LANE_TR) || (card->info.link_type == QETH_LINK_TYPE_HSTR)) { pr_info("qeth_l3: ignoring TR device\n"); @@ -2186,7 +2199,7 @@ static int qeth_l3_setup_netdev(struct qeth_card *card, bool carrier_ok) if (!(card->info.unique_id & UNIQUE_ID_NOT_BY_CARD)) card->dev->dev_id = card->info.unique_id & 0xffff; - if (!card->info.guestlan) { + if (!IS_VM_NIC(card)) { card->dev->features |= NETIF_F_SG; card->dev->hw_features |= NETIF_F_TSO | NETIF_F_RXCSUM | NETIF_F_IP_CSUM; @@ -2210,7 +2223,7 @@ static int qeth_l3_setup_netdev(struct qeth_card *card, bool carrier_ok) headroom = sizeof(struct qeth_hdr_tso); else headroom = sizeof(struct qeth_hdr) + VLAN_HLEN; - } else if (card->info.type == QETH_CARD_TYPE_IQD) { + } else if (IS_IQD(card)) { card->dev->flags |= IFF_NOARP; card->dev->netdev_ops = &qeth_l3_netdev_ops; headroom = sizeof(struct qeth_hdr) - ETH_HLEN; @@ -2253,14 +2266,22 @@ static int qeth_l3_probe_device(struct ccwgroup_device *gdev) int rc; hash_init(card->ip_htable); + mutex_init(&card->ip_lock); + card->cmd_wq = alloc_ordered_workqueue("%s_cmd", 0, + dev_name(&gdev->dev)); + if (!card->cmd_wq) + return -ENOMEM; if (gdev->dev.type == &qeth_generic_devtype) { rc = qeth_l3_create_device_attributes(&gdev->dev); - if (rc) + if (rc) { + destroy_workqueue(card->cmd_wq); return rc; + } } hash_init(card->ip_mc_htable); + INIT_WORK(&card->rx_mode_work, qeth_l3_rx_mode_work); return 0; } @@ -2280,6 +2301,9 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev) cancel_work_sync(&card->close_dev_work); if (qeth_netdev_is_registered(card->dev)) unregister_netdev(card->dev); + + flush_workqueue(card->cmd_wq); + destroy_workqueue(card->cmd_wq); qeth_l3_clear_ip_htable(card, 0); qeth_l3_clear_ipato_list(card); } @@ -2293,12 +2317,11 @@ static int qeth_l3_set_online(struct ccwgroup_device *gdev) mutex_lock(&card->discipline_mutex); mutex_lock(&card->conf_mutex); - QETH_DBF_TEXT(SETUP, 2, "setonlin"); - QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *)); + QETH_CARD_TEXT(card, 2, "setonlin"); rc = qeth_core_hardsetup_card(card, &carrier_ok); if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "2err%04x", rc); + QETH_CARD_TEXT_(card, 2, "2err%04x", rc); rc = -ENODEV; goto out_remove; } @@ -2314,28 +2337,28 @@ static int qeth_l3_set_online(struct ccwgroup_device *gdev) qeth_print_status_message(card); /* softsetup */ - QETH_DBF_TEXT(SETUP, 2, "softsetp"); + QETH_CARD_TEXT(card, 2, "softsetp"); rc = qeth_l3_setadapter_parms(card); if (rc) - QETH_DBF_TEXT_(SETUP, 2, "2err%04x", rc); + QETH_CARD_TEXT_(card, 2, "2err%04x", rc); if (!card->options.sniffer) { rc = qeth_l3_start_ipassists(card); if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "3err%d", rc); + QETH_CARD_TEXT_(card, 2, "3err%d", rc); goto out_remove; } rc = qeth_l3_setrouting_v4(card); if (rc) - QETH_DBF_TEXT_(SETUP, 2, "4err%04x", rc); + QETH_CARD_TEXT_(card, 2, "4err%04x", rc); rc = qeth_l3_setrouting_v6(card); if (rc) - QETH_DBF_TEXT_(SETUP, 2, "5err%04x", rc); + QETH_CARD_TEXT_(card, 2, "5err%04x", rc); } rc = qeth_init_qdio_queues(card); if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "6err%d", rc); + QETH_CARD_TEXT_(card, 2, "6err%d", rc); rc = -ENODEV; goto out_remove; } @@ -2376,7 +2399,6 @@ out_remove: ccw_device_set_offline(CARD_WDEV(card)); ccw_device_set_offline(CARD_RDEV(card)); qdio_free(CARD_DDEV(card)); - card->state = CARD_STATE_DOWN; mutex_unlock(&card->conf_mutex); mutex_unlock(&card->discipline_mutex); @@ -2391,8 +2413,7 @@ static int __qeth_l3_set_offline(struct ccwgroup_device *cgdev, mutex_lock(&card->discipline_mutex); mutex_lock(&card->conf_mutex); - QETH_DBF_TEXT(SETUP, 3, "setoffl"); - QETH_DBF_HEX(SETUP, 3, &card, sizeof(void *)); + QETH_CARD_TEXT(card, 3, "setoffl"); if ((!recovery_mode && card->info.hwtrap) || card->info.hwtrap == 2) { qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM); @@ -2418,7 +2439,7 @@ static int __qeth_l3_set_offline(struct ccwgroup_device *cgdev, if (!rc) rc = (rc2) ? rc2 : rc3; if (rc) - QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc); + QETH_CARD_TEXT_(card, 2, "1err%d", rc); qdio_free(CARD_DDEV(card)); /* let user_space know that device is offline */ @@ -2461,33 +2482,6 @@ static int qeth_l3_recover(void *ptr) return 0; } -static int qeth_l3_pm_suspend(struct ccwgroup_device *gdev) -{ - struct qeth_card *card = dev_get_drvdata(&gdev->dev); - - qeth_set_allowed_threads(card, 0, 1); - wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0); - if (gdev->state == CCWGROUP_OFFLINE) - return 0; - - qeth_l3_set_offline(gdev); - return 0; -} - -static int qeth_l3_pm_resume(struct ccwgroup_device *gdev) -{ - struct qeth_card *card = dev_get_drvdata(&gdev->dev); - int rc; - - rc = qeth_l3_set_online(gdev); - - qeth_set_allowed_threads(card, 0xffffffff, 0); - if (rc) - dev_warn(&card->gdev->dev, "The qeth device driver " - "failed to recover an error on the device\n"); - return rc; -} - /* Returns zero if the command is successfully "consumed" */ static int qeth_l3_control_event(struct qeth_card *card, struct qeth_ipa_cmd *cmd) @@ -2503,9 +2497,6 @@ struct qeth_discipline qeth_l3_discipline = { .remove = qeth_l3_remove_device, .set_online = qeth_l3_set_online, .set_offline = qeth_l3_set_offline, - .freeze = qeth_l3_pm_suspend, - .thaw = qeth_l3_pm_resume, - .restore = qeth_l3_pm_resume, .do_ioctl = qeth_l3_do_ioctl, .control_event_handler = qeth_l3_control_event, }; @@ -2517,20 +2508,40 @@ static int qeth_l3_handle_ip_event(struct qeth_card *card, { switch (event) { case NETDEV_UP: - spin_lock_bh(&card->ip_lock); - qeth_l3_add_ip(card, addr); - spin_unlock_bh(&card->ip_lock); + qeth_l3_modify_ip(card, addr, true); return NOTIFY_OK; case NETDEV_DOWN: - spin_lock_bh(&card->ip_lock); - qeth_l3_delete_ip(card, addr); - spin_unlock_bh(&card->ip_lock); + qeth_l3_modify_ip(card, addr, false); return NOTIFY_OK; default: return NOTIFY_DONE; } } +struct qeth_l3_ip_event_work { + struct work_struct work; + struct qeth_card *card; + struct qeth_ipaddr addr; +}; + +#define to_ip_work(w) container_of((w), struct qeth_l3_ip_event_work, work) + +static void qeth_l3_add_ip_worker(struct work_struct *work) +{ + struct qeth_l3_ip_event_work *ip_work = to_ip_work(work); + + qeth_l3_modify_ip(ip_work->card, &ip_work->addr, true); + kfree(work); +} + +static void qeth_l3_delete_ip_worker(struct work_struct *work) +{ + struct qeth_l3_ip_event_work *ip_work = to_ip_work(work); + + qeth_l3_modify_ip(ip_work->card, &ip_work->addr, false); + kfree(work); +} + static struct qeth_card *qeth_l3_get_card_from_dev(struct net_device *dev) { if (is_vlan_dev(dev)) @@ -2575,9 +2586,12 @@ static int qeth_l3_ip6_event(struct notifier_block *this, { struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr; struct net_device *dev = ifa->idev->dev; - struct qeth_ipaddr addr; + struct qeth_l3_ip_event_work *ip_work; struct qeth_card *card; + if (event != NETDEV_UP && event != NETDEV_DOWN) + return NOTIFY_DONE; + card = qeth_l3_get_card_from_dev(dev); if (!card) return NOTIFY_DONE; @@ -2585,11 +2599,23 @@ static int qeth_l3_ip6_event(struct notifier_block *this, if (!qeth_is_supported(card, IPA_IPV6)) return NOTIFY_DONE; - qeth_l3_init_ipaddr(&addr, QETH_IP_TYPE_NORMAL, QETH_PROT_IPV6); - addr.u.a6.addr = ifa->addr; - addr.u.a6.pfxlen = ifa->prefix_len; + ip_work = kmalloc(sizeof(*ip_work), GFP_ATOMIC); + if (!ip_work) + return NOTIFY_DONE; - return qeth_l3_handle_ip_event(card, &addr, event); + if (event == NETDEV_UP) + INIT_WORK(&ip_work->work, qeth_l3_add_ip_worker); + else + INIT_WORK(&ip_work->work, qeth_l3_delete_ip_worker); + + ip_work->card = card; + qeth_l3_init_ipaddr(&ip_work->addr, QETH_IP_TYPE_NORMAL, + QETH_PROT_IPV6); + ip_work->addr.u.a6.addr = ifa->addr; + ip_work->addr.u.a6.pfxlen = ifa->prefix_len; + + queue_work(card->cmd_wq, &ip_work->work); + return NOTIFY_OK; } static struct notifier_block qeth_l3_ip6_notifier = { diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c index cff518b0f904..2f73b33c9347 100644 --- a/drivers/s390/net/qeth_l3_sys.c +++ b/drivers/s390/net/qeth_l3_sys.c @@ -206,7 +206,7 @@ static ssize_t qeth_l3_dev_sniffer_store(struct device *dev, if (!card) return -EINVAL; - if (card->info.type != QETH_CARD_TYPE_IQD) + if (!IS_IQD(card)) return -EPERM; if (card->options.cq == QETH_CQ_ENABLED) return -EPERM; @@ -258,7 +258,7 @@ static ssize_t qeth_l3_dev_hsuid_show(struct device *dev, if (!card) return -EINVAL; - if (card->info.type != QETH_CARD_TYPE_IQD) + if (!IS_IQD(card)) return -EPERM; memcpy(tmp_hsuid, card->options.hsuid, sizeof(tmp_hsuid)); @@ -276,7 +276,7 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev, if (!card) return -EINVAL; - if (card->info.type != QETH_CARD_TYPE_IQD) + if (!IS_IQD(card)) return -EPERM; if (card->state != CARD_STATE_DOWN) return -EPERM; @@ -367,9 +367,9 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev, if (card->ipato.enabled != enable) { card->ipato.enabled = enable; - spin_lock_bh(&card->ip_lock); + mutex_lock(&card->ip_lock); qeth_l3_update_ipato(card); - spin_unlock_bh(&card->ip_lock); + mutex_unlock(&card->ip_lock); } out: mutex_unlock(&card->conf_mutex); @@ -412,9 +412,9 @@ static ssize_t qeth_l3_dev_ipato_invert4_store(struct device *dev, if (card->ipato.invert4 != invert) { card->ipato.invert4 = invert; - spin_lock_bh(&card->ip_lock); + mutex_lock(&card->ip_lock); qeth_l3_update_ipato(card); - spin_unlock_bh(&card->ip_lock); + mutex_unlock(&card->ip_lock); } out: mutex_unlock(&card->conf_mutex); @@ -436,7 +436,7 @@ static ssize_t qeth_l3_dev_ipato_add_show(char *buf, struct qeth_card *card, entry_len = (proto == QETH_PROT_IPV4)? 12 : 40; /* add strlen for "/<mask>\n" */ entry_len += (proto == QETH_PROT_IPV4)? 5 : 6; - spin_lock_bh(&card->ip_lock); + mutex_lock(&card->ip_lock); list_for_each_entry(ipatoe, &card->ipato.entries, entry) { if (ipatoe->proto != proto) continue; @@ -449,7 +449,7 @@ static ssize_t qeth_l3_dev_ipato_add_show(char *buf, struct qeth_card *card, i += snprintf(buf + i, PAGE_SIZE - i, "%s/%i\n", addr_str, ipatoe->mask_bits); } - spin_unlock_bh(&card->ip_lock); + mutex_unlock(&card->ip_lock); i += snprintf(buf + i, PAGE_SIZE - i, "\n"); return i; @@ -598,9 +598,9 @@ static ssize_t qeth_l3_dev_ipato_invert6_store(struct device *dev, if (card->ipato.invert6 != invert) { card->ipato.invert6 = invert; - spin_lock_bh(&card->ip_lock); + mutex_lock(&card->ip_lock); qeth_l3_update_ipato(card); - spin_unlock_bh(&card->ip_lock); + mutex_unlock(&card->ip_lock); } out: mutex_unlock(&card->conf_mutex); @@ -684,7 +684,7 @@ static ssize_t qeth_l3_dev_ip_add_show(struct device *dev, char *buf, entry_len = (proto == QETH_PROT_IPV4)? 12 : 40; entry_len += 2; /* \n + terminator */ - spin_lock_bh(&card->ip_lock); + mutex_lock(&card->ip_lock); hash_for_each(card->ip_htable, i, ipaddr, hnode) { if (ipaddr->proto != proto || ipaddr->type != type) continue; @@ -698,7 +698,7 @@ static ssize_t qeth_l3_dev_ip_add_show(struct device *dev, char *buf, str_len += snprintf(buf + str_len, PAGE_SIZE - str_len, "%s\n", addr_str); } - spin_unlock_bh(&card->ip_lock); + mutex_unlock(&card->ip_lock); str_len += snprintf(buf + str_len, PAGE_SIZE - str_len, "\n"); return str_len; diff --git a/drivers/s390/scsi/zfcp_ext.h b/drivers/s390/scsi/zfcp_ext.h index c6acca521ffe..31e8a7240fd7 100644 --- a/drivers/s390/scsi/zfcp_ext.h +++ b/drivers/s390/scsi/zfcp_ext.h @@ -167,6 +167,7 @@ extern const struct attribute_group *zfcp_port_attr_groups[]; extern struct mutex zfcp_sysfs_port_units_mutex; extern struct device_attribute *zfcp_sysfs_sdev_attrs[]; extern struct device_attribute *zfcp_sysfs_shost_attrs[]; +bool zfcp_sysfs_port_is_removing(const struct zfcp_port *const port); /* zfcp_unit.c */ extern int zfcp_unit_add(struct zfcp_port *, u64); diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c index 33eddb02ee30..b018b61bd168 100644 --- a/drivers/s390/scsi/zfcp_fc.c +++ b/drivers/s390/scsi/zfcp_fc.c @@ -620,7 +620,7 @@ static void zfcp_fc_sg_free_table(struct scatterlist *sg, int count) { int i; - for (i = 0; i < count; i++, sg++) + for (i = 0; i < count; i++, sg = sg_next(sg)) if (sg) free_page((unsigned long) sg_virt(sg)); else @@ -641,7 +641,7 @@ static int zfcp_fc_sg_setup_table(struct scatterlist *sg, int count) int i; sg_init_table(sg, count); - for (i = 0; i < count; i++, sg++) { + for (i = 0; i < count; i++, sg = sg_next(sg)) { addr = (void *) get_zeroed_page(GFP_KERNEL); if (!addr) { zfcp_fc_sg_free_table(sg, i); diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c index 221d0dfb8493..e9ded2befa0d 100644 --- a/drivers/s390/scsi/zfcp_scsi.c +++ b/drivers/s390/scsi/zfcp_scsi.c @@ -129,6 +129,15 @@ static int zfcp_scsi_slave_alloc(struct scsi_device *sdev) zfcp_sdev->erp_action.port = port; + mutex_lock(&zfcp_sysfs_port_units_mutex); + if (zfcp_sysfs_port_is_removing(port)) { + /* port is already gone */ + mutex_unlock(&zfcp_sysfs_port_units_mutex); + put_device(&port->dev); /* undo zfcp_get_port_by_wwpn() */ + return -ENXIO; + } + mutex_unlock(&zfcp_sysfs_port_units_mutex); + unit = zfcp_unit_find(port, zfcp_scsi_dev_lun(sdev)); if (unit) put_device(&unit->dev); diff --git a/drivers/s390/scsi/zfcp_sysfs.c b/drivers/s390/scsi/zfcp_sysfs.c index b277be6f7611..af197e2b3e69 100644 --- a/drivers/s390/scsi/zfcp_sysfs.c +++ b/drivers/s390/scsi/zfcp_sysfs.c @@ -235,6 +235,53 @@ static ZFCP_DEV_ATTR(adapter, port_rescan, S_IWUSR, NULL, DEFINE_MUTEX(zfcp_sysfs_port_units_mutex); +static void zfcp_sysfs_port_set_removing(struct zfcp_port *const port) +{ + lockdep_assert_held(&zfcp_sysfs_port_units_mutex); + atomic_set(&port->units, -1); +} + +bool zfcp_sysfs_port_is_removing(const struct zfcp_port *const port) +{ + lockdep_assert_held(&zfcp_sysfs_port_units_mutex); + return atomic_read(&port->units) == -1; +} + +static bool zfcp_sysfs_port_in_use(struct zfcp_port *const port) +{ + struct zfcp_adapter *const adapter = port->adapter; + unsigned long flags; + struct scsi_device *sdev; + bool in_use = true; + + mutex_lock(&zfcp_sysfs_port_units_mutex); + if (atomic_read(&port->units) > 0) + goto unlock_port_units_mutex; /* zfcp_unit(s) under port */ + + spin_lock_irqsave(adapter->scsi_host->host_lock, flags); + __shost_for_each_device(sdev, adapter->scsi_host) { + const struct zfcp_scsi_dev *zsdev = sdev_to_zfcp(sdev); + + if (sdev->sdev_state == SDEV_DEL || + sdev->sdev_state == SDEV_CANCEL) + continue; + if (zsdev->port != port) + continue; + /* alive scsi_device under port of interest */ + goto unlock_host_lock; + } + + /* port is about to be removed, so no more unit_add or slave_alloc */ + zfcp_sysfs_port_set_removing(port); + in_use = false; + +unlock_host_lock: + spin_unlock_irqrestore(adapter->scsi_host->host_lock, flags); +unlock_port_units_mutex: + mutex_unlock(&zfcp_sysfs_port_units_mutex); + return in_use; +} + static ssize_t zfcp_sysfs_port_remove_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -257,15 +304,11 @@ static ssize_t zfcp_sysfs_port_remove_store(struct device *dev, else retval = 0; - mutex_lock(&zfcp_sysfs_port_units_mutex); - if (atomic_read(&port->units) > 0) { + if (zfcp_sysfs_port_in_use(port)) { retval = -EBUSY; - mutex_unlock(&zfcp_sysfs_port_units_mutex); + put_device(&port->dev); /* undo zfcp_get_port_by_wwpn() */ goto out; } - /* port is about to be removed, so no more unit_add */ - atomic_set(&port->units, -1); - mutex_unlock(&zfcp_sysfs_port_units_mutex); write_lock_irq(&adapter->port_list_lock); list_del(&port->list); diff --git a/drivers/s390/scsi/zfcp_unit.c b/drivers/s390/scsi/zfcp_unit.c index 1bf0a0984a09..e67bf7388cae 100644 --- a/drivers/s390/scsi/zfcp_unit.c +++ b/drivers/s390/scsi/zfcp_unit.c @@ -124,7 +124,7 @@ int zfcp_unit_add(struct zfcp_port *port, u64 fcp_lun) int retval = 0; mutex_lock(&zfcp_sysfs_port_units_mutex); - if (atomic_read(&port->units) == -1) { + if (zfcp_sysfs_port_is_removing(port)) { /* port is already gone */ retval = -ENODEV; goto out; @@ -168,8 +168,14 @@ int zfcp_unit_add(struct zfcp_port *port, u64 fcp_lun) write_lock_irq(&port->unit_list_lock); list_add_tail(&unit->list, &port->unit_list); write_unlock_irq(&port->unit_list_lock); + /* + * lock order: shost->scan_mutex before zfcp_sysfs_port_units_mutex + * due to zfcp_unit_scsi_scan() => zfcp_scsi_slave_alloc() + */ + mutex_unlock(&zfcp_sysfs_port_units_mutex); zfcp_unit_scsi_scan(unit); + return retval; out: mutex_unlock(&zfcp_sysfs_port_units_mutex); diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c index 74c328321889..1a55e5942d36 100644 --- a/drivers/s390/virtio/virtio_ccw.c +++ b/drivers/s390/virtio/virtio_ccw.c @@ -46,9 +46,15 @@ struct vq_config_block { #define VIRTIO_CCW_CONFIG_SIZE 0x100 /* same as PCI config space size, should be enough for all drivers */ +struct vcdev_dma_area { + unsigned long indicators; + unsigned long indicators2; + struct vq_config_block config_block; + __u8 status; +}; + struct virtio_ccw_device { struct virtio_device vdev; - __u8 *status; __u8 config[VIRTIO_CCW_CONFIG_SIZE]; struct ccw_device *cdev; __u32 curr_io; @@ -58,16 +64,24 @@ struct virtio_ccw_device { spinlock_t lock; struct mutex io_lock; /* Serializes I/O requests */ struct list_head virtqueues; - unsigned long indicators; - unsigned long indicators2; - struct vq_config_block *config_block; bool is_thinint; bool going_away; bool device_lost; unsigned int config_ready; void *airq_info; + struct vcdev_dma_area *dma_area; }; +static inline unsigned long *indicators(struct virtio_ccw_device *vcdev) +{ + return &vcdev->dma_area->indicators; +} + +static inline unsigned long *indicators2(struct virtio_ccw_device *vcdev) +{ + return &vcdev->dma_area->indicators2; +} + struct vq_info_block_legacy { __u64 queue; __u32 align; @@ -108,7 +122,6 @@ struct virtio_rev_info { struct virtio_ccw_vq_info { struct virtqueue *vq; int num; - void *queue; union { struct vq_info_block s; struct vq_info_block_legacy l; @@ -127,11 +140,17 @@ static int virtio_ccw_use_airq = 1; struct airq_info { rwlock_t lock; - u8 summary_indicator; + u8 summary_indicator_idx; struct airq_struct airq; struct airq_iv *aiv; }; static struct airq_info *airq_areas[MAX_AIRQ_AREAS]; +static u8 *summary_indicators; + +static inline u8 *get_summary_indicator(struct airq_info *info) +{ + return summary_indicators + info->summary_indicator_idx; +} #define CCW_CMD_SET_VQ 0x13 #define CCW_CMD_VDEV_RESET 0x33 @@ -182,7 +201,7 @@ static void drop_airq_indicator(struct virtqueue *vq, struct airq_info *info) write_unlock_irqrestore(&info->lock, flags); } -static void virtio_airq_handler(struct airq_struct *airq) +static void virtio_airq_handler(struct airq_struct *airq, bool floating) { struct airq_info *info = container_of(airq, struct airq_info, airq); unsigned long ai; @@ -196,7 +215,7 @@ static void virtio_airq_handler(struct airq_struct *airq) break; vring_interrupt(0, (void *)airq_iv_get_ptr(info->aiv, ai)); } - info->summary_indicator = 0; + *(get_summary_indicator(info)) = 0; smp_wmb(); /* Walk through indicators field, summary indicator not active. */ for (ai = 0;;) { @@ -208,7 +227,7 @@ static void virtio_airq_handler(struct airq_struct *airq) read_unlock(&info->lock); } -static struct airq_info *new_airq_info(void) +static struct airq_info *new_airq_info(int index) { struct airq_info *info; int rc; @@ -217,13 +236,15 @@ static struct airq_info *new_airq_info(void) if (!info) return NULL; rwlock_init(&info->lock); - info->aiv = airq_iv_create(VIRTIO_IV_BITS, AIRQ_IV_ALLOC | AIRQ_IV_PTR); + info->aiv = airq_iv_create(VIRTIO_IV_BITS, AIRQ_IV_ALLOC | AIRQ_IV_PTR + | AIRQ_IV_CACHELINE); if (!info->aiv) { kfree(info); return NULL; } info->airq.handler = virtio_airq_handler; - info->airq.lsi_ptr = &info->summary_indicator; + info->summary_indicator_idx = index; + info->airq.lsi_ptr = get_summary_indicator(info); info->airq.lsi_mask = 0xff; info->airq.isc = VIRTIO_AIRQ_ISC; rc = register_adapter_interrupt(&info->airq); @@ -245,7 +266,7 @@ static unsigned long get_airq_indicator(struct virtqueue *vqs[], int nvqs, for (i = 0; i < MAX_AIRQ_AREAS && !indicator_addr; i++) { if (!airq_areas[i]) - airq_areas[i] = new_airq_info(); + airq_areas[i] = new_airq_info(i); info = airq_areas[i]; if (!info) return 0; @@ -326,29 +347,29 @@ static void virtio_ccw_drop_indicator(struct virtio_ccw_device *vcdev, struct airq_info *airq_info = vcdev->airq_info; if (vcdev->is_thinint) { - thinint_area = kzalloc(sizeof(*thinint_area), - GFP_DMA | GFP_KERNEL); + thinint_area = ccw_device_dma_zalloc(vcdev->cdev, + sizeof(*thinint_area)); if (!thinint_area) return; thinint_area->summary_indicator = - (unsigned long) &airq_info->summary_indicator; + (unsigned long) get_summary_indicator(airq_info); thinint_area->isc = VIRTIO_AIRQ_ISC; ccw->cmd_code = CCW_CMD_SET_IND_ADAPTER; ccw->count = sizeof(*thinint_area); ccw->cda = (__u32)(unsigned long) thinint_area; } else { /* payload is the address of the indicators */ - indicatorp = kmalloc(sizeof(&vcdev->indicators), - GFP_DMA | GFP_KERNEL); + indicatorp = ccw_device_dma_zalloc(vcdev->cdev, + sizeof(indicators(vcdev))); if (!indicatorp) return; *indicatorp = 0; ccw->cmd_code = CCW_CMD_SET_IND; - ccw->count = sizeof(&vcdev->indicators); + ccw->count = sizeof(indicators(vcdev)); ccw->cda = (__u32)(unsigned long) indicatorp; } /* Deregister indicators from host. */ - vcdev->indicators = 0; + *indicators(vcdev) = 0; ccw->flags = 0; ret = ccw_io_helper(vcdev, ccw, vcdev->is_thinint ? @@ -359,8 +380,8 @@ static void virtio_ccw_drop_indicator(struct virtio_ccw_device *vcdev, "Failed to deregister indicators (%d)\n", ret); else if (vcdev->is_thinint) virtio_ccw_drop_indicators(vcdev); - kfree(indicatorp); - kfree(thinint_area); + ccw_device_dma_free(vcdev->cdev, indicatorp, sizeof(indicators(vcdev))); + ccw_device_dma_free(vcdev->cdev, thinint_area, sizeof(*thinint_area)); } static inline long __do_kvm_notify(struct subchannel_id schid, @@ -407,15 +428,15 @@ static int virtio_ccw_read_vq_conf(struct virtio_ccw_device *vcdev, { int ret; - vcdev->config_block->index = index; + vcdev->dma_area->config_block.index = index; ccw->cmd_code = CCW_CMD_READ_VQ_CONF; ccw->flags = 0; ccw->count = sizeof(struct vq_config_block); - ccw->cda = (__u32)(unsigned long)(vcdev->config_block); + ccw->cda = (__u32)(unsigned long)(&vcdev->dma_area->config_block); ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_READ_VQ_CONF); if (ret) return ret; - return vcdev->config_block->num ?: -ENOENT; + return vcdev->dma_area->config_block.num ?: -ENOENT; } static void virtio_ccw_del_vq(struct virtqueue *vq, struct ccw1 *ccw) @@ -423,7 +444,6 @@ static void virtio_ccw_del_vq(struct virtqueue *vq, struct ccw1 *ccw) struct virtio_ccw_device *vcdev = to_vc_device(vq->vdev); struct virtio_ccw_vq_info *info = vq->priv; unsigned long flags; - unsigned long size; int ret; unsigned int index = vq->index; @@ -461,9 +481,8 @@ static void virtio_ccw_del_vq(struct virtqueue *vq, struct ccw1 *ccw) ret, index); vring_del_virtqueue(vq); - size = PAGE_ALIGN(vring_size(info->num, KVM_VIRTIO_CCW_RING_ALIGN)); - free_pages_exact(info->queue, size); - kfree(info->info_block); + ccw_device_dma_free(vcdev->cdev, info->info_block, + sizeof(*info->info_block)); kfree(info); } @@ -473,7 +492,7 @@ static void virtio_ccw_del_vqs(struct virtio_device *vdev) struct ccw1 *ccw; struct virtio_ccw_device *vcdev = to_vc_device(vdev); - ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); + ccw = ccw_device_dma_zalloc(vcdev->cdev, sizeof(*ccw)); if (!ccw) return; @@ -482,7 +501,7 @@ static void virtio_ccw_del_vqs(struct virtio_device *vdev) list_for_each_entry_safe(vq, n, &vdev->vqs, list) virtio_ccw_del_vq(vq, ccw); - kfree(ccw); + ccw_device_dma_free(vcdev->cdev, ccw, sizeof(*ccw)); } static struct virtqueue *virtio_ccw_setup_vq(struct virtio_device *vdev, @@ -494,8 +513,9 @@ static struct virtqueue *virtio_ccw_setup_vq(struct virtio_device *vdev, int err; struct virtqueue *vq = NULL; struct virtio_ccw_vq_info *info; - unsigned long size = 0; /* silence the compiler */ + u64 queue; unsigned long flags; + bool may_reduce; /* Allocate queue. */ info = kzalloc(sizeof(struct virtio_ccw_vq_info), GFP_KERNEL); @@ -504,8 +524,8 @@ static struct virtqueue *virtio_ccw_setup_vq(struct virtio_device *vdev, err = -ENOMEM; goto out_err; } - info->info_block = kzalloc(sizeof(*info->info_block), - GFP_DMA | GFP_KERNEL); + info->info_block = ccw_device_dma_zalloc(vcdev->cdev, + sizeof(*info->info_block)); if (!info->info_block) { dev_warn(&vcdev->cdev->dev, "no info block\n"); err = -ENOMEM; @@ -516,37 +536,34 @@ static struct virtqueue *virtio_ccw_setup_vq(struct virtio_device *vdev, err = info->num; goto out_err; } - size = PAGE_ALIGN(vring_size(info->num, KVM_VIRTIO_CCW_RING_ALIGN)); - info->queue = alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO); - if (info->queue == NULL) { - dev_warn(&vcdev->cdev->dev, "no queue\n"); - err = -ENOMEM; - goto out_err; - } + may_reduce = vcdev->revision > 0; + vq = vring_create_virtqueue(i, info->num, KVM_VIRTIO_CCW_RING_ALIGN, + vdev, true, may_reduce, ctx, + virtio_ccw_kvm_notify, callback, name); - vq = vring_new_virtqueue(i, info->num, KVM_VIRTIO_CCW_RING_ALIGN, vdev, - true, ctx, info->queue, virtio_ccw_kvm_notify, - callback, name); if (!vq) { /* For now, we fail if we can't get the requested size. */ dev_warn(&vcdev->cdev->dev, "no vq\n"); err = -ENOMEM; goto out_err; } + /* it may have been reduced */ + info->num = virtqueue_get_vring_size(vq); /* Register it with the host. */ + queue = virtqueue_get_desc_addr(vq); if (vcdev->revision == 0) { - info->info_block->l.queue = (__u64)info->queue; + info->info_block->l.queue = queue; info->info_block->l.align = KVM_VIRTIO_CCW_RING_ALIGN; info->info_block->l.index = i; info->info_block->l.num = info->num; ccw->count = sizeof(info->info_block->l); } else { - info->info_block->s.desc = (__u64)info->queue; + info->info_block->s.desc = queue; info->info_block->s.index = i; info->info_block->s.num = info->num; - info->info_block->s.avail = (__u64)virtqueue_get_avail(vq); - info->info_block->s.used = (__u64)virtqueue_get_used(vq); + info->info_block->s.avail = (__u64)virtqueue_get_avail_addr(vq); + info->info_block->s.used = (__u64)virtqueue_get_used_addr(vq); ccw->count = sizeof(info->info_block->s); } ccw->cmd_code = CCW_CMD_SET_VQ; @@ -572,9 +589,8 @@ out_err: if (vq) vring_del_virtqueue(vq); if (info) { - if (info->queue) - free_pages_exact(info->queue, size); - kfree(info->info_block); + ccw_device_dma_free(vcdev->cdev, info->info_block, + sizeof(*info->info_block)); } kfree(info); return ERR_PTR(err); @@ -588,7 +604,8 @@ static int virtio_ccw_register_adapter_ind(struct virtio_ccw_device *vcdev, struct virtio_thinint_area *thinint_area = NULL; struct airq_info *info; - thinint_area = kzalloc(sizeof(*thinint_area), GFP_DMA | GFP_KERNEL); + thinint_area = ccw_device_dma_zalloc(vcdev->cdev, + sizeof(*thinint_area)); if (!thinint_area) { ret = -ENOMEM; goto out; @@ -603,7 +620,7 @@ static int virtio_ccw_register_adapter_ind(struct virtio_ccw_device *vcdev, } info = vcdev->airq_info; thinint_area->summary_indicator = - (unsigned long) &info->summary_indicator; + (unsigned long) get_summary_indicator(info); thinint_area->isc = VIRTIO_AIRQ_ISC; ccw->cmd_code = CCW_CMD_SET_IND_ADAPTER; ccw->flags = CCW_FLAG_SLI; @@ -624,7 +641,7 @@ static int virtio_ccw_register_adapter_ind(struct virtio_ccw_device *vcdev, virtio_ccw_drop_indicators(vcdev); } out: - kfree(thinint_area); + ccw_device_dma_free(vcdev->cdev, thinint_area, sizeof(*thinint_area)); return ret; } @@ -640,7 +657,7 @@ static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs, int ret, i, queue_idx = 0; struct ccw1 *ccw; - ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); + ccw = ccw_device_dma_zalloc(vcdev->cdev, sizeof(*ccw)); if (!ccw) return -ENOMEM; @@ -664,10 +681,11 @@ static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs, * We need a data area under 2G to communicate. Our payload is * the address of the indicators. */ - indicatorp = kmalloc(sizeof(&vcdev->indicators), GFP_DMA | GFP_KERNEL); + indicatorp = ccw_device_dma_zalloc(vcdev->cdev, + sizeof(indicators(vcdev))); if (!indicatorp) goto out; - *indicatorp = (unsigned long) &vcdev->indicators; + *indicatorp = (unsigned long) indicators(vcdev); if (vcdev->is_thinint) { ret = virtio_ccw_register_adapter_ind(vcdev, vqs, nvqs, ccw); if (ret) @@ -676,32 +694,36 @@ static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs, } if (!vcdev->is_thinint) { /* Register queue indicators with host. */ - vcdev->indicators = 0; + *indicators(vcdev) = 0; ccw->cmd_code = CCW_CMD_SET_IND; ccw->flags = 0; - ccw->count = sizeof(&vcdev->indicators); + ccw->count = sizeof(indicators(vcdev)); ccw->cda = (__u32)(unsigned long) indicatorp; ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_IND); if (ret) goto out; } /* Register indicators2 with host for config changes */ - *indicatorp = (unsigned long) &vcdev->indicators2; - vcdev->indicators2 = 0; + *indicatorp = (unsigned long) indicators2(vcdev); + *indicators2(vcdev) = 0; ccw->cmd_code = CCW_CMD_SET_CONF_IND; ccw->flags = 0; - ccw->count = sizeof(&vcdev->indicators2); + ccw->count = sizeof(indicators2(vcdev)); ccw->cda = (__u32)(unsigned long) indicatorp; ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_CONF_IND); if (ret) goto out; - kfree(indicatorp); - kfree(ccw); + if (indicatorp) + ccw_device_dma_free(vcdev->cdev, indicatorp, + sizeof(indicators(vcdev))); + ccw_device_dma_free(vcdev->cdev, ccw, sizeof(*ccw)); return 0; out: - kfree(indicatorp); - kfree(ccw); + if (indicatorp) + ccw_device_dma_free(vcdev->cdev, indicatorp, + sizeof(indicators(vcdev))); + ccw_device_dma_free(vcdev->cdev, ccw, sizeof(*ccw)); virtio_ccw_del_vqs(vdev); return ret; } @@ -711,12 +733,12 @@ static void virtio_ccw_reset(struct virtio_device *vdev) struct virtio_ccw_device *vcdev = to_vc_device(vdev); struct ccw1 *ccw; - ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); + ccw = ccw_device_dma_zalloc(vcdev->cdev, sizeof(*ccw)); if (!ccw) return; /* Zero status bits. */ - *vcdev->status = 0; + vcdev->dma_area->status = 0; /* Send a reset ccw on device. */ ccw->cmd_code = CCW_CMD_VDEV_RESET; @@ -724,7 +746,7 @@ static void virtio_ccw_reset(struct virtio_device *vdev) ccw->count = 0; ccw->cda = 0; ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_RESET); - kfree(ccw); + ccw_device_dma_free(vcdev->cdev, ccw, sizeof(*ccw)); } static u64 virtio_ccw_get_features(struct virtio_device *vdev) @@ -735,11 +757,11 @@ static u64 virtio_ccw_get_features(struct virtio_device *vdev) u64 rc; struct ccw1 *ccw; - ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); + ccw = ccw_device_dma_zalloc(vcdev->cdev, sizeof(*ccw)); if (!ccw) return 0; - features = kzalloc(sizeof(*features), GFP_DMA | GFP_KERNEL); + features = ccw_device_dma_zalloc(vcdev->cdev, sizeof(*features)); if (!features) { rc = 0; goto out_free; @@ -772,20 +794,16 @@ static u64 virtio_ccw_get_features(struct virtio_device *vdev) rc |= (u64)le32_to_cpu(features->features) << 32; out_free: - kfree(features); - kfree(ccw); + ccw_device_dma_free(vcdev->cdev, features, sizeof(*features)); + ccw_device_dma_free(vcdev->cdev, ccw, sizeof(*ccw)); return rc; } static void ccw_transport_features(struct virtio_device *vdev) { /* - * Packed ring isn't enabled on virtio_ccw for now, - * because virtio_ccw uses some legacy accessors, - * e.g. virtqueue_get_avail() and virtqueue_get_used() - * which aren't available in packed ring currently. + * Currently nothing to do here. */ - __virtio_clear_bit(vdev, VIRTIO_F_RING_PACKED); } static int virtio_ccw_finalize_features(struct virtio_device *vdev) @@ -802,11 +820,11 @@ static int virtio_ccw_finalize_features(struct virtio_device *vdev) return -EINVAL; } - ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); + ccw = ccw_device_dma_zalloc(vcdev->cdev, sizeof(*ccw)); if (!ccw) return -ENOMEM; - features = kzalloc(sizeof(*features), GFP_DMA | GFP_KERNEL); + features = ccw_device_dma_zalloc(vcdev->cdev, sizeof(*features)); if (!features) { ret = -ENOMEM; goto out_free; @@ -841,8 +859,8 @@ static int virtio_ccw_finalize_features(struct virtio_device *vdev) ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_FEAT); out_free: - kfree(features); - kfree(ccw); + ccw_device_dma_free(vcdev->cdev, features, sizeof(*features)); + ccw_device_dma_free(vcdev->cdev, ccw, sizeof(*ccw)); return ret; } @@ -856,11 +874,12 @@ static void virtio_ccw_get_config(struct virtio_device *vdev, void *config_area; unsigned long flags; - ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); + ccw = ccw_device_dma_zalloc(vcdev->cdev, sizeof(*ccw)); if (!ccw) return; - config_area = kzalloc(VIRTIO_CCW_CONFIG_SIZE, GFP_DMA | GFP_KERNEL); + config_area = ccw_device_dma_zalloc(vcdev->cdev, + VIRTIO_CCW_CONFIG_SIZE); if (!config_area) goto out_free; @@ -882,8 +901,8 @@ static void virtio_ccw_get_config(struct virtio_device *vdev, memcpy(buf, config_area + offset, len); out_free: - kfree(config_area); - kfree(ccw); + ccw_device_dma_free(vcdev->cdev, config_area, VIRTIO_CCW_CONFIG_SIZE); + ccw_device_dma_free(vcdev->cdev, ccw, sizeof(*ccw)); } static void virtio_ccw_set_config(struct virtio_device *vdev, @@ -895,11 +914,12 @@ static void virtio_ccw_set_config(struct virtio_device *vdev, void *config_area; unsigned long flags; - ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); + ccw = ccw_device_dma_zalloc(vcdev->cdev, sizeof(*ccw)); if (!ccw) return; - config_area = kzalloc(VIRTIO_CCW_CONFIG_SIZE, GFP_DMA | GFP_KERNEL); + config_area = ccw_device_dma_zalloc(vcdev->cdev, + VIRTIO_CCW_CONFIG_SIZE); if (!config_area) goto out_free; @@ -918,61 +938,61 @@ static void virtio_ccw_set_config(struct virtio_device *vdev, ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_CONFIG); out_free: - kfree(config_area); - kfree(ccw); + ccw_device_dma_free(vcdev->cdev, config_area, VIRTIO_CCW_CONFIG_SIZE); + ccw_device_dma_free(vcdev->cdev, ccw, sizeof(*ccw)); } static u8 virtio_ccw_get_status(struct virtio_device *vdev) { struct virtio_ccw_device *vcdev = to_vc_device(vdev); - u8 old_status = *vcdev->status; + u8 old_status = vcdev->dma_area->status; struct ccw1 *ccw; if (vcdev->revision < 1) - return *vcdev->status; + return vcdev->dma_area->status; - ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); + ccw = ccw_device_dma_zalloc(vcdev->cdev, sizeof(*ccw)); if (!ccw) return old_status; ccw->cmd_code = CCW_CMD_READ_STATUS; ccw->flags = 0; - ccw->count = sizeof(*vcdev->status); - ccw->cda = (__u32)(unsigned long)vcdev->status; + ccw->count = sizeof(vcdev->dma_area->status); + ccw->cda = (__u32)(unsigned long)&vcdev->dma_area->status; ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_READ_STATUS); /* * If the channel program failed (should only happen if the device * was hotunplugged, and then we clean up via the machine check - * handler anyway), vcdev->status was not overwritten and we just + * handler anyway), vcdev->dma_area->status was not overwritten and we just * return the old status, which is fine. */ - kfree(ccw); + ccw_device_dma_free(vcdev->cdev, ccw, sizeof(*ccw)); - return *vcdev->status; + return vcdev->dma_area->status; } static void virtio_ccw_set_status(struct virtio_device *vdev, u8 status) { struct virtio_ccw_device *vcdev = to_vc_device(vdev); - u8 old_status = *vcdev->status; + u8 old_status = vcdev->dma_area->status; struct ccw1 *ccw; int ret; - ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); + ccw = ccw_device_dma_zalloc(vcdev->cdev, sizeof(*ccw)); if (!ccw) return; /* Write the status to the host. */ - *vcdev->status = status; + vcdev->dma_area->status = status; ccw->cmd_code = CCW_CMD_WRITE_STATUS; ccw->flags = 0; ccw->count = sizeof(status); - ccw->cda = (__u32)(unsigned long)vcdev->status; + ccw->cda = (__u32)(unsigned long)&vcdev->dma_area->status; ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_STATUS); /* Write failed? We assume status is unchanged. */ if (ret) - *vcdev->status = old_status; - kfree(ccw); + vcdev->dma_area->status = old_status; + ccw_device_dma_free(vcdev->cdev, ccw, sizeof(*ccw)); } static const char *virtio_ccw_bus_name(struct virtio_device *vdev) @@ -1005,8 +1025,8 @@ static void virtio_ccw_release_dev(struct device *_d) struct virtio_device *dev = dev_to_virtio(_d); struct virtio_ccw_device *vcdev = to_vc_device(dev); - kfree(vcdev->status); - kfree(vcdev->config_block); + ccw_device_dma_free(vcdev->cdev, vcdev->dma_area, + sizeof(*vcdev->dma_area)); kfree(vcdev); } @@ -1104,17 +1124,17 @@ static void virtio_ccw_int_handler(struct ccw_device *cdev, vcdev->err = -EIO; } virtio_ccw_check_activity(vcdev, activity); - for_each_set_bit(i, &vcdev->indicators, - sizeof(vcdev->indicators) * BITS_PER_BYTE) { + for_each_set_bit(i, indicators(vcdev), + sizeof(*indicators(vcdev)) * BITS_PER_BYTE) { /* The bit clear must happen before the vring kick. */ - clear_bit(i, &vcdev->indicators); + clear_bit(i, indicators(vcdev)); barrier(); vq = virtio_ccw_vq_by_ind(vcdev, i); vring_interrupt(0, vq); } - if (test_bit(0, &vcdev->indicators2)) { + if (test_bit(0, indicators2(vcdev))) { virtio_config_changed(&vcdev->vdev); - clear_bit(0, &vcdev->indicators2); + clear_bit(0, indicators2(vcdev)); } } @@ -1214,12 +1234,12 @@ static int virtio_ccw_set_transport_rev(struct virtio_ccw_device *vcdev) struct ccw1 *ccw; int ret; - ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL); + ccw = ccw_device_dma_zalloc(vcdev->cdev, sizeof(*ccw)); if (!ccw) return -ENOMEM; - rev = kzalloc(sizeof(*rev), GFP_DMA | GFP_KERNEL); + rev = ccw_device_dma_zalloc(vcdev->cdev, sizeof(*rev)); if (!rev) { - kfree(ccw); + ccw_device_dma_free(vcdev->cdev, ccw, sizeof(*ccw)); return -ENOMEM; } @@ -1249,8 +1269,8 @@ static int virtio_ccw_set_transport_rev(struct virtio_ccw_device *vcdev) } } while (ret == -EOPNOTSUPP); - kfree(ccw); - kfree(rev); + ccw_device_dma_free(vcdev->cdev, ccw, sizeof(*ccw)); + ccw_device_dma_free(vcdev->cdev, rev, sizeof(*rev)); return ret; } @@ -1266,24 +1286,19 @@ static int virtio_ccw_online(struct ccw_device *cdev) ret = -ENOMEM; goto out_free; } - vcdev->config_block = kzalloc(sizeof(*vcdev->config_block), - GFP_DMA | GFP_KERNEL); - if (!vcdev->config_block) { - ret = -ENOMEM; - goto out_free; - } - vcdev->status = kzalloc(sizeof(*vcdev->status), GFP_DMA | GFP_KERNEL); - if (!vcdev->status) { + vcdev->vdev.dev.parent = &cdev->dev; + vcdev->cdev = cdev; + vcdev->dma_area = ccw_device_dma_zalloc(vcdev->cdev, + sizeof(*vcdev->dma_area)); + if (!vcdev->dma_area) { ret = -ENOMEM; goto out_free; } vcdev->is_thinint = virtio_ccw_use_airq; /* at least try */ - vcdev->vdev.dev.parent = &cdev->dev; vcdev->vdev.dev.release = virtio_ccw_release_dev; vcdev->vdev.config = &virtio_ccw_config_ops; - vcdev->cdev = cdev; init_waitqueue_head(&vcdev->wait_q); INIT_LIST_HEAD(&vcdev->virtqueues); spin_lock_init(&vcdev->lock); @@ -1314,8 +1329,8 @@ out_put: return ret; out_free: if (vcdev) { - kfree(vcdev->status); - kfree(vcdev->config_block); + ccw_device_dma_free(vcdev->cdev, vcdev->dma_area, + sizeof(*vcdev->dma_area)); } kfree(vcdev); return ret; @@ -1485,8 +1500,17 @@ static void __init no_auto_parse(void) static int __init virtio_ccw_init(void) { + int rc; + /* parse no_auto string before we do anything further */ no_auto_parse(); - return ccw_driver_register(&virtio_ccw_driver); + + summary_indicators = cio_dma_zalloc(MAX_AIRQ_AREAS); + if (!summary_indicators) + return -ENOMEM; + rc = ccw_driver_register(&virtio_ccw_driver); + if (rc) + cio_dma_free(summary_indicators, MAX_AIRQ_AREAS); + return rc; } device_initcall(virtio_ccw_init); |